Merge branch 'master' into pm-sleep

* master: (848 commits)
  SELinux: Fix RCU deref check warning in sel_netport_insert()
  binary_sysctl(): fix memory leak
  mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
  ipmi_watchdog: restore settings when BMC reset
  oom: fix integer overflow of points in oom_badness
  memcg: keep root group unchanged if creation fails
  nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
  nilfs2: unbreak compat ioctl
  cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
  evm: prevent racing during tfm allocation
  evm: key must be set once during initialization
  mmc: vub300: fix type of firmware_rom_wait_states module parameter
  Revert "mmc: enable runtime PM by default"
  mmc: sdhci: remove "state" argument from sdhci_suspend_host
  x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
  IB/qib: Correct sense on freectxts increment and decrement
  RDMA/cma: Verify private data length
  cgroups: fix a css_set not found bug in cgroup_attach_proc
  oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
  Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
  ...

Conflicts:
	kernel/cgroup_freezer.c

23 files changed, 195 insertions, 124 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c7a6d3b5bc7..94acd8172b5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -805,9 +805,6 @@ extern void blk_unprep_request(struct request *);
  */
 extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
 					spinlock_t *lock, int node_id);
-extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
-							   request_fn_proc *,
-							   spinlock_t *, int node_id);
 extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
 extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 						      request_fn_proc *, spinlock_t *);
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 139c4db55f1..081147da056 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -71,7 +71,7 @@ struct timecounter {
 
 /**
  * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
- * @tc:		Pointer to cycle counter.
+ * @cc:		Pointer to cycle counter.
  * @cycles:	Cycles
  *
  * XXX - This could use some mult_lxl_ll() asm optimization. Same code
@@ -114,7 +114,7 @@ extern u64 timecounter_read(struct timecounter *tc);
  *                        time base as values returned by
  *                        timecounter_read()
  * @tc:		Pointer to time counter.
- * @cycle:	a value returned by tc->cc->read()
+ * @cycle_tstamp:	a value returned by tc->cc->read()
  *
  * Cycle counts that are converted correctly as long as they
  * fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
@@ -156,10 +156,12 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @mult:		cycle to nanosecond multiplier
  * @shift:		cycle to nanosecond divisor (power of two)
  * @max_idle_ns:	max idle time permitted by the clocksource (nsecs)
+ * @maxadj:		maximum adjustment value to mult (~11%)
  * @flags:		flags describing special properties
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
  * @resume:		resume function for the clocksource, if necessary
+ * @cycle_last:		most recent cycle counter value seen by ::read()
  */
 struct clocksource {
 	/*
@@ -172,7 +174,7 @@ struct clocksource {
 	u32 mult;
 	u32 shift;
 	u64 max_idle_ns;
-
+	u32 maxadj;
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
 	struct arch_clocksource_data archdata;
 #endif
@@ -186,6 +188,7 @@ struct clocksource {
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
 
+	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
 	struct list_head wd_list;
@@ -260,6 +263,9 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
 
 /**
  * clocksource_cyc2ns - converts clocksource cycles to nanoseconds
+ * @cycles:	cycles
+ * @mult:	cycle to nanosecond multiplier
+ * @shift:	cycle to nanosecond divisor (power of two)
  *
  * Converts cycles to nanoseconds, using the given mult and shift.
  *
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 154bf568301..66ed067fb72 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -552,5 +552,14 @@ extern ssize_t compat_rw_copy_check_uvector(int type,
 
 extern void __user *compat_alloc_user_space(unsigned long len);
 
+asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid,
+		const struct compat_iovec __user *lvec,
+		unsigned long liovcnt, const struct compat_iovec __user *rvec,
+		unsigned long riovcnt, unsigned long flags);
+asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
+		const struct compat_iovec __user *lvec,
+		unsigned long liovcnt, const struct compat_iovec __user *rvec,
+		unsigned long riovcnt, unsigned long flags);
+
 #endif /* CONFIG_COMPAT */
 #endif /* _LINUX_COMPAT_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 4df92619936..ed9f74f6c51 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -339,7 +339,8 @@ extern int d_validate(struct dentry *, struct dentry *);
  */
 extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
 
-extern char *__d_path(const struct path *path, struct path *root, char *, int);
+extern char *__d_path(const struct path *, const struct path *, char *, int);
+extern char *d_absolute_path(const struct path *, char *, int);
 extern char *d_path(const struct path *, char *, int);
 extern char *d_path_with_unreachable(const struct path *, char *, int);
 extern char *dentry_path_raw(struct dentry *, char *, int);
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index ef90cbd8e17..57c9a8ae4f2 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -31,6 +31,7 @@ extern void free_dmar_iommu(struct intel_iommu *iommu);
 extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
+extern int intel_iommu_enabled;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {
@@ -44,6 +45,7 @@ static inline void free_dmar_iommu(struct intel_iommu *iommu)
 {
 }
 #define dmar_disabled	(1)
+#define intel_iommu_enabled (0)
 #endif
 
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e3130220ce3..e0bc4ffb8e7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -393,8 +393,8 @@ struct inodes_stat_t {
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
 #include <linux/rculist_bl.h>
-#include <linux/shrinker.h>
 #include <linux/atomic.h>
+#include <linux/shrinker.h>
 
 #include <asm/byteorder.h>
 
@@ -1942,6 +1942,7 @@ extern int fd_statfs(int, struct kstatfs *);
 extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
+extern bool our_mnt(struct vfsmount *mnt);
 
 extern int current_umask(void);
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 96efa6794ea..c3da42dd22b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -172,6 +172,7 @@ enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
+	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 };
 
 enum {
@@ -179,6 +180,7 @@ enum {
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
 	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
+	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 };
 
 struct ftrace_event_call {
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 94b1e356c02..32574eef939 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -126,6 +126,8 @@ extern struct cred init_cred;
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#define INIT_TASK_COMM "swapper"
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -162,7 +164,7 @@ extern struct cred init_cred;
 	.group_leader	= &tsk,						\
 	RCU_INIT_POINTER(.real_cred, &init_cred),			\
 	RCU_INIT_POINTER(.cred, &init_cred),				\
-	.comm		= "swapper",					\
+	.comm		= INIT_TASK_COMM,				\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
 	.files		= &init_files,					\
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 25b808631cd..fd7ff3d91e6 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -185,7 +185,6 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define rounddown_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 0 :			\
 		(1UL << ilog2(n))) :		\
 	__rounddown_pow_of_two(n)		\
  )
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3dc3a8c2c48..4baadd18f4a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -10,6 +10,7 @@
 #include <linux/mmzone.h>
 #include <linux/rbtree.h>
 #include <linux/prio_tree.h>
+#include <linux/atomic.h>
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
 #include <linux/range.h>
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 415f2db414e..c8ef9bc54d5 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -218,6 +218,7 @@ struct mmc_card {
 #define MMC_QUIRK_INAND_CMD38	(1<<6)		/* iNAND devices have broken CMD38 */
 #define MMC_QUIRK_BLK_NO_CMD23	(1<<7)		/* Avoid CMD23 for regular multiblock */
 #define MMC_QUIRK_BROKEN_BYTE_MODE_512 (1<<8)	/* Avoid sending 512 bytes in */
+#define MMC_QUIRK_LONG_READ_TIME (1<<9)		/* Data read time > CSD says */
 						/* byte mode */
 	unsigned int    poweroff_notify_state;	/* eMMC4.5 notify feature */
 #define MMC_NO_POWER_NOTIFICATION	0
@@ -433,6 +434,11 @@ static inline int mmc_card_broken_byte_mode_512(const struct mmc_card *c)
 	return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512;
 }
 
+static inline int mmc_card_long_read_time(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_LONG_READ_TIME;
+}
+
 #define mmc_card_name(c)	((c)->cid.prod_name)
 #define mmc_card_id(c)		(dev_name(&(c)->dev))
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cbeb5867cff..a82ad4dd306 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2536,6 +2536,8 @@ extern void		net_disable_timestamp(void);
 extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
 extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
 extern void dev_seq_stop(struct seq_file *seq, void *v);
+extern int dev_seq_open_ops(struct inode *inode, struct file *file,
+			    const struct seq_operations *ops);
 #endif
 
 extern int netdev_class_create_file(struct class_attribute *class_attr);
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index e3d0b389024..7ef68724f0f 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -12,7 +12,7 @@ struct pci_ats {
 	unsigned int is_enabled:1;      /* Enable bit is set */
 };
 
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 
 extern int pci_enable_ats(struct pci_dev *dev, int ps);
 extern void pci_disable_ats(struct pci_dev *dev);
@@ -29,7 +29,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 	return dev->ats && dev->ats->is_enabled;
 }
 
-#else /* CONFIG_PCI_IOV */
+#else /* CONFIG_PCI_ATS */
 
 static inline int pci_enable_ats(struct pci_dev *dev, int ps)
 {
@@ -50,7 +50,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 	return 0;
 }
 
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_ATS */
 
 #ifdef CONFIG_PCI_PRI
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 337df0d5d5f..7cda65b5f79 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -338,7 +338,7 @@ struct pci_dev {
 	struct list_head msi_list;
 #endif
 	struct pci_vpd *vpd;
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 	union {
 		struct pci_sriov *sriov;	/* SR-IOV capability related */
 		struct pci_dev *physfn;	/* the PF this VF is associated with */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 172ba70306d..2aaee0ca9da 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -517,8 +517,12 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM	0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_F0	0x1600
+#define PCI_DEVICE_ID_AMD_15H_NB_F1	0x1601
+#define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602
 #define PCI_DEVICE_ID_AMD_15H_NB_F3	0x1603
 #define PCI_DEVICE_ID_AMD_15H_NB_F4	0x1604
+#define PCI_DEVICE_ID_AMD_15H_NB_F5	0x1605
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1e9ebe5e009..b1f89122bf6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -822,6 +822,7 @@ struct perf_event {
 	int				mmap_locked;
 	struct user_struct		*mmap_user;
 	struct ring_buffer		*rb;
+	struct list_head		rb_entry;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index c5336705921..7281d5acf2f 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -30,7 +30,7 @@
  */
 
 struct tc_stats {
-	__u64	bytes;			/* NUmber of enqueues bytes */
+	__u64	bytes;			/* Number of enqueued bytes */
 	__u32	packets;		/* Number of enqueued packets	*/
 	__u32	drops;			/* Packets dropped because of lack of resources */
 	__u32	overlimits;		/* Number of throttle events when this
@@ -297,7 +297,7 @@ struct tc_htb_glob {
 	__u32 debug;		/* debug flags */
 
 	/* stats */
-	__u32 direct_pkts; /* count of non shapped packets */
+	__u32 direct_pkts; /* count of non shaped packets */
 };
 enum {
 	TCA_HTB_UNSPEC,
@@ -503,7 +503,7 @@ enum {
 };
 #define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
 
-/* State transition probablities for 4 state model */
+/* State transition probabilities for 4 state model */
 struct tc_netem_gimodel {
 	__u32	p13;
 	__u32	p31;
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 5c4c8b18c8b..3f3ed83a9aa 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -54,118 +54,145 @@ typedef struct pm_message {
 /**
  * struct dev_pm_ops - device PM callbacks
  *
- * Several driver power state transitions are externally visible, affecting
+ * Several device power state transitions are externally visible, affecting
  * the state of pending I/O queues and (for drivers that touch hardware)
  * interrupts, wakeups, DMA, and other hardware state.  There may also be
- * internal transitions to various low power modes, which are transparent
+ * internal transitions to various low-power modes which are transparent
  * to the rest of the driver stack (such as a driver that's ON gating off
  * clocks which are not in active use).
  *
- * The externally visible transitions are handled with the help of the following
- * callbacks included in this structure:
- *
- * @prepare: Prepare the device for the upcoming transition, but do NOT change
- *	its hardware state.  Prevent new children of the device from being
- *	registered after @prepare() returns (the driver's subsystem and
- *	generally the rest of the kernel is supposed to prevent new calls to the
- *	probe method from being made too once @prepare() has succeeded).  If
- *	@prepare() detects a situation it cannot handle (e.g. registration of a
- *	child already in progress), it may return -EAGAIN, so that the PM core
- *	can execute it once again (e.g. after the new child has been registered)
- *	to recover from the race condition.  This method is executed for all
- *	kinds of suspend transitions and is followed by one of the suspend
- *	callbacks: @suspend(), @freeze(), or @poweroff().
- *	The PM core executes @prepare() for all devices before starting to
- *	execute suspend callbacks for any of them, so drivers may assume all of
- *	the other devices to be present and functional while @prepare() is being
- *	executed.  In particular, it is safe to make GFP_KERNEL memory
- *	allocations from within @prepare().  However, drivers may NOT assume
- *	anything about the availability of the user space at that time and it
- *	is not correct to request firmware from within @prepare() (it's too
- *	late to do that).  [To work around this limitation, drivers may
- *	register suspend and hibernation notifiers that are executed before the
- *	freezing of tasks.]
+ * The externally visible transitions are handled with the help of callbacks
+ * included in this structure in such a way that two levels of callbacks are
+ * involved.  First, the PM core executes callbacks provided by PM domains,
+ * device types, classes and bus types.  They are the subsystem-level callbacks
+ * supposed to execute callbacks provided by device drivers, although they may
+ * choose not to do that.  If the driver callbacks are executed, they have to
+ * collaborate with the subsystem-level callbacks to achieve the goals
+ * appropriate for the given system transition, given transition phase and the
+ * subsystem the device belongs to.
+ *
+ * @prepare: The principal role of this callback is to prevent new children of
+ *	the device from being registered after it has returned (the driver's
+ *	subsystem and generally the rest of the kernel is supposed to prevent
+ *	new calls to the probe method from being made too once @prepare() has
+ *	succeeded).  If @prepare() detects a situation it cannot handle (e.g.
+ *	registration of a child already in progress), it may return -EAGAIN, so
+ *	that the PM core can execute it once again (e.g. after a new child has
+ *	been registered) to recover from the race condition.
+ *	This method is executed for all kinds of suspend transitions and is
+ *	followed by one of the suspend callbacks: @suspend(), @freeze(), or
+ *	@poweroff().  The PM core executes subsystem-level @prepare() for all
+ *	devices before starting to invoke suspend callbacks for any of them, so
+ *	generally devices may be assumed to be functional or to respond to
+ *	runtime resume requests while @prepare() is being executed.  However,
+ *	device drivers may NOT assume anything about the availability of user
+ *	space at that time and it is NOT valid to request firmware from within
+ *	@prepare() (it's too late to do that).  It also is NOT valid to allocate
+ *	substantial amounts of memory from @prepare() in the GFP_KERNEL mode.
+ *	[To work around these limitations, drivers may register suspend and
+ *	hibernation notifiers to be executed before the freezing of tasks.]
  *
  * @complete: Undo the changes made by @prepare().  This method is executed for
  *	all kinds of resume transitions, following one of the resume callbacks:
  *	@resume(), @thaw(), @restore().  Also called if the state transition
- *	fails before the driver's suspend callback (@suspend(), @freeze(),
- *	@poweroff()) can be executed (e.g. if the suspend callback fails for one
+ *	fails before the driver's suspend callback: @suspend(), @freeze() or
+ *	@poweroff(), can be executed (e.g. if the suspend callback fails for one
  *	of the other devices that the PM core has unsuccessfully attempted to
  *	suspend earlier).
- *	The PM core executes @complete() after it has executed the appropriate
- *	resume callback for all devices.
+ *	The PM core executes subsystem-level @complete() after it has executed
+ *	the appropriate resume callbacks for all devices.
  *
  * @suspend: Executed before putting the system into a sleep state in which the
- *	contents of main memory are preserved.  Quiesce the device, put it into
- *	a low power state appropriate for the upcoming system state (such as
- *	PCI_D3hot), and enable wakeup events as appropriate.
+ *	contents of main memory are preserved.  The exact action to perform
+ *	depends on the device's subsystem (PM domain, device type, class or bus
+ *	type), but generally the device must be quiescent after subsystem-level
+ *	@suspend() has returned, so that it doesn't do any I/O or DMA.
+ *	Subsystem-level @suspend() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @resume: Executed after waking the system up from a sleep state in which the
- *	contents of main memory were preserved.  Put the device into the
- *	appropriate state, according to the information saved in memory by the
- *	preceding @suspend().  The driver starts working again, responding to
- *	hardware events and software requests.  The hardware may have gone
- *	through a power-off reset, or it may have maintained state from the
- *	previous suspend() which the driver may rely on while resuming.  On most
- *	platforms, there are no restrictions on availability of resources like
- *	clocks during @resume().
+ *	contents of main memory were preserved.  The exact action to perform
+ *	depends on the device's subsystem, but generally the driver is expected
+ *	to start working again, responding to hardware events and software
+ *	requests (the device itself may be left in a low-power state, waiting
+ *	for a runtime resume to occur).  The state of the device at the time its
+ *	driver's @resume() callback is run depends on the platform and subsystem
+ *	the device belongs to.  On most platforms, there are no restrictions on
+ *	availability of resources like clocks during @resume().
+ *	Subsystem-level @resume() is executed for all devices after invoking
+ *	subsystem-level @resume_noirq() for all of them.
  *
  * @freeze: Hibernation-specific, executed before creating a hibernation image.
- *	Quiesce operations so that a consistent image can be created, but do NOT
- *	otherwise put the device into a low power device state and do NOT emit
- *	system wakeup events.  Save in main memory the device settings to be
- *	used by @restore() during the subsequent resume from hibernation or by
- *	the subsequent @thaw(), if the creation of the image or the restoration
- *	of main memory contents from it fails.
+ *	Analogous to @suspend(), but it should not enable the device to signal
+ *	wakeup events or change its power state.  The majority of subsystems
+ *	(with the notable exception of the PCI bus type) expect the driver-level
+ *	@freeze() to save the device settings in memory to be used by @restore()
+ *	during the subsequent resume from hibernation.
+ *	Subsystem-level @freeze() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @thaw: Hibernation-specific, executed after creating a hibernation image OR
- *	if the creation of the image fails.  Also executed after a failing
+ *	if the creation of an image has failed.  Also executed after a failing
  *	attempt to restore the contents of main memory from such an image.
  *	Undo the changes made by the preceding @freeze(), so the device can be
  *	operated in the same way as immediately before the call to @freeze().
+ *	Subsystem-level @thaw() is executed for all devices after invoking
+ *	subsystem-level @thaw_noirq() for all of them.  It also may be executed
+ *	directly after @freeze() in case of a transition error.
  *
  * @poweroff: Hibernation-specific, executed after saving a hibernation image.
- *	Quiesce the device, put it into a low power state appropriate for the
- *	upcoming system state (such as PCI_D3hot), and enable wakeup events as
- *	appropriate.
+ *	Analogous to @suspend(), but it need not save the device's settings in
+ *	memory.
+ *	Subsystem-level @poweroff() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @restore: Hibernation-specific, executed after restoring the contents of main
- *	memory from a hibernation image.  Driver starts working again,
- *	responding to hardware events and software requests.  Drivers may NOT
- *	make ANY assumptions about the hardware state right prior to @restore().
- *	On most platforms, there are no restrictions on availability of
- *	resources like clocks during @restore().
- *
- * @suspend_noirq: Complete the operations of ->suspend() by carrying out any
- *	actions required for suspending the device that need interrupts to be
- *	disabled
- *
- * @resume_noirq: Prepare for the execution of ->resume() by carrying out any
- *	actions required for resuming the device that need interrupts to be
- *	disabled
- *
- * @freeze_noirq: Complete the operations of ->freeze() by carrying out any
- *	actions required for freezing the device that need interrupts to be
- *	disabled
- *
- * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any
- *	actions required for thawing the device that need interrupts to be
- *	disabled
- *
- * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any
- *	actions required for handling the device that need interrupts to be
- *	disabled
- *
- * @restore_noirq: Prepare for the execution of ->restore() by carrying out any
- *	actions required for restoring the operations of the device that need
- *	interrupts to be disabled
+ *	memory from a hibernation image, analogous to @resume().
+ *
+ * @suspend_noirq: Complete the actions started by @suspend().  Carry out any
+ *	additional operations required for suspending the device that might be
+ *	racing with its driver's interrupt handler, which is guaranteed not to
+ *	run while @suspend_noirq() is being executed.
+ *	It generally is expected that the device will be in a low-power state
+ *	(appropriate for the target system sleep state) after subsystem-level
+ *	@suspend_noirq() has returned successfully.  If the device can generate
+ *	system wakeup signals and is enabled to wake up the system, it should be
+ *	configured to do so at that time.  However, depending on the platform
+ *	and device's subsystem, @suspend() may be allowed to put the device into
+ *	the low-power state and configure it to generate wakeup signals, in
+ *	which case it generally is not necessary to define @suspend_noirq().
+ *
+ * @resume_noirq: Prepare for the execution of @resume() by carrying out any
+ *	operations required for resuming the device that might be racing with
+ *	its driver's interrupt handler, which is guaranteed not to run while
+ *	@resume_noirq() is being executed.
+ *
+ * @freeze_noirq: Complete the actions started by @freeze().  Carry out any
+ *	additional operations required for freezing the device that might be
+ *	racing with its driver's interrupt handler, which is guaranteed not to
+ *	run while @freeze_noirq() is being executed.
+ *	The power state of the device should not be changed by either @freeze()
+ *	or @freeze_noirq() and it should not be configured to signal system
+ *	wakeup by any of these callbacks.
+ *
+ * @thaw_noirq: Prepare for the execution of @thaw() by carrying out any
+ *	operations required for thawing the device that might be racing with its
+ *	driver's interrupt handler, which is guaranteed not to run while
+ *	@thaw_noirq() is being executed.
+ *
+ * @poweroff_noirq: Complete the actions started by @poweroff().  Analogous to
+ *	@suspend_noirq(), but it need not save the device's settings in memory.
+ *
+ * @restore_noirq: Prepare for the execution of @restore() by carrying out any
+ *	operations required for thawing the device that might be racing with its
+ *	driver's interrupt handler, which is guaranteed not to run while
+ *	@restore_noirq() is being executed.  Analogous to @resume_noirq().
  *
  * All of the above callbacks, except for @complete(), return error codes.
  * However, the error codes returned by the resume operations, @resume(),
- * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq() do
+ * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do
  * not cause the PM core to abort the resume transition during which they are
- * returned.  The error codes returned in that cases are only printed by the PM
+ * returned.  The error codes returned in those cases are only printed by the PM
  * core to the system logs for debugging purposes.  Still, it is recommended
  * that drivers only return error codes from their resume methods in case of an
  * unrecoverable failure (i.e. when the device being handled refuses to resume
@@ -174,31 +201,43 @@ typedef struct pm_message {
  * their children.
  *
  * It is allowed to unregister devices while the above callbacks are being
- * executed.  However, it is not allowed to unregister a device from within any
- * of its own callbacks.
+ * executed.  However, a callback routine must NOT try to unregister the device
+ * it was called for, although it may unregister children of that device (for
+ * example, if it detects that a child was unplugged while the system was
+ * asleep).
+ *
+ * Refer to Documentation/power/devices.txt for more information about the role
+ * of the above callbacks in the system suspend process.
  *
- * There also are the following callbacks related to run-time power management
- * of devices:
+ * There also are callbacks related to runtime power management of devices.
+ * Again, these callbacks are executed by the PM core only for subsystems
+ * (PM domains, device types, classes and bus types) and the subsystem-level
+ * callbacks are supposed to invoke the driver callbacks.  Moreover, the exact
+ * actions to be performed by a device driver's callbacks generally depend on
+ * the platform and subsystem the device belongs to.
  *
  * @runtime_suspend: Prepare the device for a condition in which it won't be
  *	able to communicate with the CPU(s) and RAM due to power management.
- *	This need not mean that the device should be put into a low power state.
+ *	This need not mean that the device should be put into a low-power state.
  *	For example, if the device is behind a link which is about to be turned
  *	off, the device may remain at full power.  If the device does go to low
- *	power and is capable of generating run-time wake-up events, remote
- *	wake-up (i.e., a hardware mechanism allowing the device to request a
- *	change of its power state via a wake-up event, such as PCI PME) should
- *	be enabled for it.
+ *	power and is capable of generating runtime wakeup events, remote wakeup
+ *	(i.e., a hardware mechanism allowing the device to request a change of
+ *	its power state via an interrupt) should be enabled for it.
  *
  * @runtime_resume: Put the device into the fully active state in response to a
- *	wake-up event generated by hardware or at the request of software.  If
- *	necessary, put the device into the full power state and restore its
+ *	wakeup event generated by hardware or at the request of software.  If
+ *	necessary, put the device into the full-power state and restore its
  *	registers, so that it is fully operational.
  *
- * @runtime_idle: Device appears to be inactive and it might be put into a low
- *	power state if all of the necessary conditions are satisfied.  Check
+ * @runtime_idle: Device appears to be inactive and it might be put into a
+ *	low-power state if all of the necessary conditions are satisfied.  Check
  *	these conditions and handle the device as appropriate, possibly queueing
  *	a suspend request for it.  The return value is ignored by the PM core.
+ *
+ * Refer to Documentation/power/runtime_pm.txt for more information about the
+ * role of the above callbacks in device runtime power management.
+ *
  */
 
 struct dev_pm_ops {
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index ea567321ae3..2ca8cde5459 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -35,10 +35,12 @@ struct pstore_info {
 	spinlock_t	buf_lock;	/* serialize access to 'buf' */
 	char		*buf;
 	size_t		bufsize;
+	struct mutex	read_mutex;	/* serialize open/read/close */
 	int		(*open)(struct pstore_info *psi);
 	int		(*close)(struct pstore_info *psi);
 	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
-			struct timespec *time, struct pstore_info *psi);
+			struct timespec *time, char **buf,
+			struct pstore_info *psi);
 	int		(*write)(enum pstore_type_id type, u64 *id,
 			unsigned int part, size_t size, struct pstore_info *psi);
 	int		(*erase)(enum pstore_type_id type, u64 id,
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index a83833a1f7a..07ceb97d53f 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -35,7 +35,7 @@ struct shrinker {
 
 	/* These are for internal use */
 	struct list_head list;
-	long nr;	/* objs pending delete */
+	atomic_long_t nr_in_batch; /* objs pending delete */
 };
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
 extern void register_shrinker(struct shrinker *);
diff --git a/include/linux/sigma.h b/include/linux/sigma.h
index e2accb3164d..d0de882c0d9 100644
--- a/include/linux/sigma.h
+++ b/include/linux/sigma.h
@@ -24,7 +24,7 @@ struct sigma_firmware {
 struct sigma_firmware_header {
 	unsigned char magic[7];
 	u8 version;
-	u32 crc;
+	__le32 crc;
 };
 
 enum {
@@ -40,19 +40,14 @@ enum {
 struct sigma_action {
 	u8 instr;
 	u8 len_hi;
-	u16 len;
-	u16 addr;
+	__le16 len;
+	__be16 addr;
 	unsigned char payload[];
 };
 
 static inline u32 sigma_action_len(struct sigma_action *sa)
 {
-	return (sa->len_hi << 16) | sa->len;
-}
-
-static inline size_t sigma_action_size(struct sigma_action *sa, u32 payload_len)
-{
-	return sizeof(*sa) + payload_len + (payload_len % 2);
+	return (sa->len_hi << 16) | le16_to_cpu(sa->len);
 }
 
 extern int process_sigma_firmware(struct i2c_client *client, const char *name);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index add4790b21f..e9e72bda1b7 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -85,6 +85,8 @@
  * @reset: reset the device
  *	vdev: the virtio device
  *	After this, status and feature negotiation must be done again
+ *	Device must not be reset from its vq/config callbacks, or in
+ *	parallel with being added/removed.
  * @find_vqs: find virtqueues and instantiate them.
  *	vdev: the virtio_device
  *	nvqs: the number of virtqueues to find
diff --git a/include/linux/virtio_mmio.h b/include/linux/virtio_mmio.h
index 27c7edefbc8..5c7b6f0daef 100644
--- a/include/linux/virtio_mmio.h
+++ b/include/linux/virtio_mmio.h
@@ -63,7 +63,7 @@
 #define VIRTIO_MMIO_GUEST_FEATURES	0x020
 
 /* Activated features set selector - Write Only */
-#define VIRTIO_MMIO_GUEST_FEATURES_SET	0x024
+#define VIRTIO_MMIO_GUEST_FEATURES_SEL	0x024
 
 /* Guest's memory page size in bytes - Write Only */
 #define VIRTIO_MMIO_GUEST_PAGE_SIZE	0x028