Merge branch 'linus' into core/percpu

Conflicts:
	kernel/irq/handle.c

12 files changed, 179 insertions, 26 deletions

diff --git a/Documentation/Changes b/Documentation/Changes
index cb2b141b1c3..b95082be4d5 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -33,10 +33,12 @@ o  Gnu make               3.79.1                  # make --version
 o  binutils               2.12                    # ld -v
 o  util-linux             2.10o                   # fdformat --version
 o  module-init-tools      0.9.10                  # depmod -V
-o  e2fsprogs              1.29                    # tune2fs
+o  e2fsprogs              1.41.4                  # e2fsck -V
 o  jfsutils               1.1.3                   # fsck.jfs -V
 o  reiserfsprogs          3.6.3                   # reiserfsck -V 2>&1|grep reiserfsprogs
 o  xfsprogs               2.6.0                   # xfs_db -V
+o  squashfs-tools         4.0                     # mksquashfs -version
+o  btrfs-progs            0.18                    # btrfsck
 o  pcmciautils            004                     # pccardctl -V
 o  quota-tools            3.09                    # quota -V
 o  PPP                    2.4.0                   # pppd --version
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 1875e502f87..72968cd5eaf 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -483,17 +483,25 @@ values.  To do the latter, you can stick the following in your .emacs file:
     (* (max steps 1)
        c-basic-offset)))
 
+(add-hook 'c-mode-common-hook
+          (lambda ()
+            ;; Add kernel style
+            (c-add-style
+             "linux-tabs-only"
+             '("linux" (c-offsets-alist
+                        (arglist-cont-nonempty
+                         c-lineup-gcc-asm-reg
+                         c-lineup-arglist-tabs-only))))))
+
 (add-hook 'c-mode-hook
           (lambda ()
             (let ((filename (buffer-file-name)))
               ;; Enable kernel mode for the appropriate files
               (when (and filename
-                         (string-match "~/src/linux-trees" filename))
+                         (string-match (expand-file-name "~/src/linux-trees")
+                                       filename))
                 (setq indent-tabs-mode t)
-                (c-set-style "linux")
-                (c-set-offset 'arglist-cont-nonempty
-                              '(c-lineup-gcc-asm-reg
-                                c-lineup-arglist-tabs-only))))))
+                (c-set-style "linux-tabs-only")))))
 
 This will make emacs go better with the kernel coding style for C
 files below ~/src/linux-trees.
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 52441694fe0..2a3fcc55e98 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -5,7 +5,7 @@
 
 This document describes the DMA API.  For a more gentle introduction
 phrased in terms of the pci_ equivalents (and actual examples) see
-DMA-mapping.txt
+Documentation/PCI/PCI-DMA-mapping.txt.
 
 This API is split into two pieces.  Part I describes the API and the
 corresponding pci_ API.  Part II describes the extensions to the API
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index b787e4721c9..52e1b79ce0e 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -42,6 +42,12 @@ GPL version 2.
 
 <revhistory>
 	<revision>
+	<revnumber>0.7</revnumber>
+	<date>2008-12-23</date>
+	<authorinitials>hjk</authorinitials>
+	<revremark>Added generic platform drivers and offset attribute.</revremark>
+	</revision>
+	<revision>
 	<revnumber>0.6</revnumber>
 	<date>2008-12-05</date>
 	<authorinitials>hjk</authorinitials>
@@ -312,6 +318,16 @@ interested in translating it, please email me
 	pointed to by addr.
 	</para>
 </listitem>
+<listitem>
+	<para>
+	<filename>offset</filename>: The offset, in bytes, that has to be
+	added to the pointer returned by <function>mmap()</function> to get
+	to the actual device memory. This is important if the device's memory
+	is not page aligned. Remember that pointers returned by
+	<function>mmap()</function> are always page aligned, so it is good
+	style to always add this offset.
+	</para>
+</listitem>
 </itemizedlist>
 
 <para>
@@ -594,6 +610,78 @@ framework to set up sysfs files for this region. Simply leave it alone.
 	</para>
 </sect1>
 
+<sect1 id="using_uio_pdrv">
+<title>Using uio_pdrv for platform devices</title>
+	<para>
+	In many cases, UIO drivers for platform devices can be handled in a
+	generic way. In the same place where you define your
+	<varname>struct platform_device</varname>, you simply also implement
+	your interrupt handler and fill your
+	<varname>struct uio_info</varname>. A pointer to this
+	<varname>struct uio_info</varname> is then used as
+	<varname>platform_data</varname> for your platform device.
+	</para>
+	<para>
+	You also need to set up an array of <varname>struct resource</varname>
+	containing addresses and sizes of your memory mappings. This
+	information is passed to the driver using the
+	<varname>.resource</varname> and <varname>.num_resources</varname>
+	elements of <varname>struct platform_device</varname>.
+	</para>
+	<para>
+	You now have to set the <varname>.name</varname> element of
+	<varname>struct platform_device</varname> to
+	<varname>"uio_pdrv"</varname> to use the generic UIO platform device
+	driver. This driver will fill the <varname>mem[]</varname> array
+	according to the resources given, and register the device.
+	</para>
+	<para>
+	The advantage of this approach is that you only have to edit a file
+	you need to edit anyway. You do not have to create an extra driver.
+	</para>
+</sect1>
+
+<sect1 id="using_uio_pdrv_genirq">
+<title>Using uio_pdrv_genirq for platform devices</title>
+	<para>
+	Especially in embedded devices, you frequently find chips where the
+	irq pin is tied to its own dedicated interrupt line. In such cases,
+	where you can be really sure the interrupt is not shared, we can take
+	the concept of <varname>uio_pdrv</varname> one step further and use a
+	generic interrupt handler. That's what
+	<varname>uio_pdrv_genirq</varname> does.
+	</para>
+	<para>
+	The setup for this driver is the same as described above for
+	<varname>uio_pdrv</varname>, except that you do not implement an
+	interrupt handler. The <varname>.handler</varname> element of
+	<varname>struct uio_info</varname> must remain
+	<varname>NULL</varname>. The  <varname>.irq_flags</varname> element
+	must not contain <varname>IRQF_SHARED</varname>.
+	</para>
+	<para>
+	You will set the <varname>.name</varname> element of
+	<varname>struct platform_device</varname> to
+	<varname>"uio_pdrv_genirq"</varname> to use this driver.
+	</para>
+	<para>
+	The generic interrupt handler of <varname>uio_pdrv_genirq</varname>
+	will simply disable the interrupt line using
+	<function>disable_irq_nosync()</function>. After doing its work,
+	userspace can reenable the interrupt by writing 0x00000001 to the UIO
+	device file. The driver already implements an
+	<function>irq_control()</function> to make this possible, you must not
+	implement your own.
+	</para>
+	<para>
+	Using <varname>uio_pdrv_genirq</varname> not only saves a few lines of
+	interrupt handler code. You also do not need to know anything about
+	the chip's internal registers to create the kernel part of the driver.
+	All you need to know is the irq number of the pin the chip is
+	connected to.
+	</para>
+</sect1>
+
 </chapter>
 
 <chapter id="userspace_driver" xreflabel="Writing a driver in user space">
diff --git a/Documentation/IO-mapping.txt b/Documentation/IO-mapping.txt
index 86edb61bdee..78a440695e1 100644
--- a/Documentation/IO-mapping.txt
+++ b/Documentation/IO-mapping.txt
@@ -1,6 +1,6 @@
 [ NOTE: The virt_to_bus() and bus_to_virt() functions have been
-	superseded by the functionality provided by the PCI DMA
-	interface (see Documentation/DMA-mapping.txt).  They continue
+	superseded by the functionality provided by the PCI DMA interface
+	(see Documentation/PCI/PCI-DMA-mapping.txt).  They continue
 	to be documented below for historical purposes, but new code
 	must not use them. --davidm 00/12/12 ]
 
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 3c5434c83da..5d2480d33b4 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -186,8 +186,9 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to DMA-mapping.txt for a discussion on PCI high mem DMA
-aspects and mapping of scatter gather lists, and support for 64 bit PCI.
+Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+on PCI high mem DMA aspects and mapping of scatter gather lists, and support
+for 64 bit PCI.
 
 Special handling is required only for cases where i/o needs to happen on
 pages at physical memory addresses beyond what the device can support. In these
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 19533f93b7a..523a9c16c40 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,6 +1,6 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2008/12/15
-Base Kernel Version: based on 2.6.28-rc8-mm.
+Last Updated: 2009/1/19
+Base Kernel Version: based on 2.6.29-rc2.
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -340,3 +340,23 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
 
 	and do task move, mkdir, rmdir etc...under this.
+
+ 9.7 swapoff.
+	Besides management of swap is one of complicated parts of memcg,
+	call path of swap-in at swapoff is not same as usual swap-in path..
+	It's worth to be tested explicitly.
+
+	For example, test like following is good.
+	(Shell-A)
+	# mount -t cgroup none /cgroup -t memory
+	# mkdir /cgroup/test
+	# echo 40M > /cgroup/test/memory.limit_in_bytes
+	# echo 0 > /cgroup/test/tasks
+	Run malloc(100M) program under this. You'll see 60M of swaps.
+	(Shell-B)
+	# move all tasks in /cgroup/test to /cgroup
+	# /sbin/swapoff -a
+	# rmdir /test/cgroup
+	# kill malloc task.
+
+	Of course, tmpfs v.s. swapoff test should be tested, too.
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index 44bd766f2e5..85eaeaddd27 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -251,7 +251,7 @@ NFS/RDMA Setup
 
     Instruct the server to listen on the RDMA transport:
 
-    $ echo rdma 2050 > /proc/fs/nfsd/portlist
+    $ echo rdma 20049 > /proc/fs/nfsd/portlist
 
   - On the client system
 
@@ -263,7 +263,7 @@ NFS/RDMA Setup
     Regardless of how the client was built (module or built-in), use this
     command to mount the NFS/RDMA server:
 
-    $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt
+    $ mount -o rdma,port=20049 <IPoIB-server-name-or-address>:/<export> /mnt
 
     To verify that the mount is using RDMA, run "cat /proc/mounts" and check
     the "proto" field for the given mount.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index bbebc3a43ac..a87be42f821 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -2027,6 +2027,34 @@ increase the likelihood of this process being killed by the oom-killer.  Valid
 values are in the range -16 to +15, plus the special value -17, which disables
 oom-killing altogether for this process.
 
+The process to be killed in an out-of-memory situation is selected among all others
+based on its badness score. This value equals the original memory size of the process
+and is then updated according to its CPU time (utime + stime) and the
+run time (uptime - start time). The longer it runs the smaller is the score.
+Badness score is divided by the square root of the CPU time and then by
+the double square root of the run time.
+
+Swapped out tasks are killed first. Half of each child's memory size is added to
+the parent's score if they do not share the same memory. Thus forking servers
+are the prime candidates to be killed. Having only one 'hungry' child will make
+parent less preferable than the child.
+
+/proc/<pid>/oom_score shows process' current badness score.
+
+The following heuristics are then applied:
+ * if the task was reniced, its score doubles
+ * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
+ 	or CAP_SYS_RAWIO) have their score divided by 4
+ * if oom condition happened in one cpuset and checked task does not belong
+ 	to it, its score is divided by 8
+ * the resulting score is multiplied by two to the power of oom_adj, i.e.
+	points <<= oom_adj when it is positive and
+	points >>= -(oom_adj) otherwise
+
+The task with the highest badness score is then selected and its children
+are killed, process itself will be killed in an OOM situation when it does
+not have children or some of them disabled oom like described above.
+
 2.13 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------
 
diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt
index b3ffe870de3..14265837c4c 100644
--- a/Documentation/ja_JP/stable_kernel_rules.txt
+++ b/Documentation/ja_JP/stable_kernel_rules.txt
@@ -12,11 +12,11 @@ file at first.
 
 ==================================
 これは、
-linux-2.6.24/Documentation/stable_kernel_rules.txt
+linux-2.6.29/Documentation/stable_kernel_rules.txt
 の和訳です。
 
 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2007/12/30
+翻訳日： 2009/1/14
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： 武井伸光さん、<takei at webmasters dot gr dot jp>
          かねこさん (Seiji Kaneko) <skaneko at a2 dot mbn dot or dot jp>
@@ -38,12 +38,15 @@ linux-2.6.24/Documentation/stable_kernel_rules.txt
  - ビルドエラー(CONFIG_BROKENになっているものを除く), oops, ハング、デー
    タ破壊、現実のセキュリティ問題、その他 "ああ、これはダメだね"という
    ようなものを修正しなければならない。短く言えば、重大な問題。
+ - 新しい device ID とクオークも受け入れられる。
  - どのように競合状態が発生するかの説明も一緒に書かれていない限り、
    "理論的には競合状態になる"ようなものは不可。
  - いかなる些細な修正も含めることはできない。(スペルの修正、空白のクリー
    ンアップなど)
- - 対応するサブシステムメンテナが受け入れたものでなければならない。
  - Documentation/SubmittingPatches の規則に従ったものでなければならない。
+ - パッチ自体か同等の修正が Linus のツリーに既に存在しなければならない。
+　 Linus のツリーでのコミットID を -stable へのパッチ投稿の際に引用す
+   ること。
 
 -stable ツリーにパッチを送付する手続き-
 
@@ -52,8 +55,10 @@ linux-2.6.24/Documentation/stable_kernel_rules.txt
  - 送信者はパッチがキューに受け付けられた際には ACK を、却下された場合
    には NAK を受け取る。この反応は開発者たちのスケジュールによって、数
    日かかる場合がある。
- - もし受け取られたら、パッチは他の開発者たちのレビューのために
-   -stable キューに追加される。
+ - もし受け取られたら、パッチは他の開発者たちと関連するサブシステムの
+   メンテナーによるレビューのために -stable キューに追加される。
+ - パッチに stable@kernel.org のアドレスが付加されているときには、それ
+   が Linus のツリーに入る時に自動的に stable チームに email される。
  - セキュリティパッチはこのエイリアス (stable@kernel.org) に送られるべ
    きではなく、代わりに security@kernel.org のアドレスに送られる。
 
diff --git a/Documentation/lguest/Makefile b/Documentation/lguest/Makefile
index 725eef81cd4..1f4f9e888bd 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/lguest/Makefile
@@ -1,5 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include
+CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
 LDLIBS:=-lz
 
 all: lguest
diff --git a/Documentation/usb/dma.txt b/Documentation/usb/dma.txt
index e8b50b7de9d..cfdcd16e3ab 100644
--- a/Documentation/usb/dma.txt
+++ b/Documentation/usb/dma.txt
@@ -6,8 +6,9 @@ in the kernel usb programming guide (kerneldoc, from the source code).
 API OVERVIEW
 
 The big picture is that USB drivers can continue to ignore most DMA issues,
-though they still must provide DMA-ready buffers (see DMA-mapping.txt).
-That's how they've worked through the 2.4 (and earlier) kernels.
+though they still must provide DMA-ready buffers (see
+Documentation/PCI/PCI-DMA-mapping.txt).  That's how they've worked through
+the 2.4 (and earlier) kernels.
 
 OR:  they can now be DMA-aware.
 
@@ -62,8 +63,8 @@ and effects like cache-trashing can impose subtle penalties.
   force a consistent memory access ordering by using memory barriers.  It's
   not using a streaming DMA mapping, so it's good for small transfers on
   systems where the I/O would otherwise thrash an IOMMU mapping.  (See
-  Documentation/DMA-mapping.txt for definitions of "coherent" and "streaming"
-  DMA mappings.)
+  Documentation/PCI/PCI-DMA-mapping.txt for definitions of "coherent" and
+  "streaming" DMA mappings.)
 
   Asking for 1/Nth of a page (as well as asking for N pages) is reasonably
   space-efficient.
@@ -93,7 +94,7 @@ WORKING WITH EXISTING BUFFERS
 Existing buffers aren't usable for DMA without first being mapped into the
 DMA address space of the device.  However, most buffers passed to your
 driver can safely be used with such DMA mapping.  (See the first section
-of DMA-mapping.txt, titled "What memory is DMA-able?")
+of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?")
 
 - When you're using scatterlists, you can map everything at once.  On some
   systems, this kicks in an IOMMU and turns the scatterlists into single