Merge branch 'merge' of git://git.secretlab.ca/git/linux-2.6 into merge

43 files changed, 2390 insertions, 929 deletions

diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd
index bf9c16b64c34..cf11736acb76 100644
--- a/Documentation/ABI/testing/debugfs-pktcdvd
+++ b/Documentation/ABI/testing/debugfs-pktcdvd
@@ -1,4 +1,4 @@
-What:           /debug/pktcdvd/pktcdvd[0-7]
+What:           /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
 Date:           Oct. 2006
 KernelVersion:  2.6.20
 Contact:        Thomas Maier <balagi@justmail.de>
@@ -10,10 +10,10 @@ debugfs interface
 The pktcdvd module (packet writing driver) creates
 these files in debugfs:
 
-/debug/pktcdvd/pktcdvd[0-7]/
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
     info            (0444) Lots of driver statistics and infos.
 
 Example:
 -------
 
-cat /debug/pktcdvd/pktcdvd0/info
+cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt
index b2a4d6d244d9..01f24e94bdb6 100644
--- a/Documentation/DMA-mapping.txt
+++ b/Documentation/DMA-mapping.txt
@@ -136,7 +136,7 @@ exactly why.
 The standard 32-bit addressing PCI device would do something like
 this:
 
-        if (pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
                 printk(KERN_WARNING
                        "mydev: No suitable DMA available.\n");
                 goto ignore_this_device;
@@ -155,9 +155,9 @@ all 64-bits when accessing streaming DMA:
 
         int using_dac;
 
-        if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
+        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
                 using_dac = 1;
-        } else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
                 using_dac = 0;
         } else {
                 printk(KERN_WARNING
@@ -170,14 +170,14 @@ the case would look like this:
 
         int using_dac, consistent_using_dac;
 
-        if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
+        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
                 using_dac = 1;
                 consistent_using_dac = 1;
-                pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
-        } else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
                 using_dac = 0;
                 consistent_using_dac = 0;
-                pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK);
+                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
         } else {
                 printk(KERN_WARNING
                        "mydev: No suitable DMA available.\n");
@@ -192,7 +192,7 @@ check the return value from pci_set_consistent_dma_mask().
 Finally, if your device can only drive the low 24-bits of
 address during PCI bus mastering you might do something like:
 
-        if (pci_set_dma_mask(pdev, DMA_24BIT_MASK)) {
+        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
                 printk(KERN_WARNING
                        "mydev: 24-bit DMA addressing not available.\n");
                 goto ignore_this_device;
@@ -213,7 +213,7 @@ most specific mask.
 
 Here is pseudo-code showing how this might be done:
 
-        #define PLAYBACK_ADDRESS_BITS   DMA_32BIT_MASK
+        #define PLAYBACK_ADDRESS_BITS   DMA_BIT_MASK(32)
         #define RECORD_ADDRESS_BITS     0x00ffffff
 
         struct my_sound_card *card;
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index a3a83d38f96f..8918a32c6b3a 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -31,7 +31,7 @@ PS_METHOD	= $(prefer-db2x)
 
 ###
 # The targets that may be used.
-PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs
+PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs
 
 BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
 xmldocs: $(BOOKS)
@@ -213,11 +213,12 @@ silent_gen_xml = :
 dochelp:
         @echo  ' Linux kernel internal documentation in different formats:'
         @echo  '  htmldocs        - HTML'
-        @echo  '  installmandocs  - install man pages generated by mandocs'
-        @echo  '  mandocs         - man pages'
         @echo  '  pdfdocs         - PDF'
         @echo  '  psdocs          - Postscript'
         @echo  '  xmldocs         - XML DocBook'
+        @echo  '  mandocs         - man pages'
+        @echo  '  installmandocs  - install man pages generated by mandocs'
+        @echo  '  cleandocs       - clean all generated DocBook files'
 
 ###
 # Temporary files left by various tools
@@ -235,6 +236,10 @@ clean-files := $(DOCBOOKS) \
 
 clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
 
+cleandocs:
+        $(Q)rm -f $(call objectify, $(clean-files))
+        $(Q)rm -rf $(call objectify, $(clean-dirs))
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable se we can use it in if_changed and friends.
 
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 58c194572c76..d6ac5d61820e 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -259,7 +259,7 @@ X!Earch/x86/kernel/mca_32.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c
-!Iblock/blktrace.c
+!Ikernel/trace/blktrace.c
 !Iblock/genhd.c
 !Eblock/genhd.c
   </chapter>
diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl
index 46b08fef3744..7a2e0e98986a 100644
--- a/Documentation/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl
@@ -1137,8 +1137,8 @@
           if (err < 0)
                   return err;
           /* check PCI availability (28bit DMA) */
-          if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
-              pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
+          if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
+              pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
                   printk(KERN_ERR "error to set 28bit mask DMA\n");
                   pci_disable_device(pci);
                   return -ENXIO;
@@ -1252,8 +1252,8 @@
   err = pci_enable_device(pci);
   if (err < 0)
           return err;
-  if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
-      pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
+  if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
+      pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
           printk(KERN_ERR "error to set 28bit mask DMA\n");
           pci_disable_device(pci);
           return -ENXIO;
diff --git a/Documentation/blockdev/00-INDEX b/Documentation/blockdev/00-INDEX
index 86f054c47013..c08df56dd91b 100644
--- a/Documentation/blockdev/00-INDEX
+++ b/Documentation/blockdev/00-INDEX
@@ -8,6 +8,8 @@ cpqarray.txt
         - info on using Compaq's SMART2 Intelligent Disk Array Controllers.
 floppy.txt
         - notes and driver options for the floppy disk driver.
+mflash.txt
+        - info on mGine m(g)flash driver for linux.
 nbd.txt
         - info on a TCP implementation of a network block device.
 paride.txt
diff --git a/Documentation/blockdev/mflash.txt b/Documentation/blockdev/mflash.txt
new file mode 100644
index 000000000000..1f610ecf698a
--- /dev/null
+++ b/Documentation/blockdev/mflash.txt
@@ -0,0 +1,84 @@
+This document describes m[g]flash support in linux.
+
+Contents
+  1. Overview
+  2. Reserved area configuration
+  3. Example of mflash platform driver registration
+
+1. Overview
+
+Mflash and gflash are embedded flash drive. The only difference is mflash is
+MCP(Multi Chip Package) device. These two device operate exactly same way.
+So the rest mflash repersents mflash and gflash altogether.
+
+Internally, mflash has nand flash and other hardware logics and supports
+2 different operation (ATA, IO) modes. ATA mode doesn't need any new
+driver and currently works well under standard IDE subsystem. Actually it's
+one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
+IDE interface.
+
+Followings are brief descriptions about IO mode.
+A. IO mode based on ATA protocol and uses some custom command. (read confirm,
+write confirm)
+B. IO mode uses SRAM bus interface.
+C. IO mode supports 4kB boot area, so host can boot from mflash.
+
+2. Reserved area configuration
+If host boot from mflash, usually needs raw area for boot loader image. All of
+the mflash's block device operation will be taken this value as start offset.
+Note that boot loader's size of reserved area and kernel configuration value
+must be same.
+
+3. Example of mflash platform driver registration
+Working mflash is very straight forward. Adding platform device stuff to board
+configuration file is all. Here is some pseudo example.
+
+static struct mg_drv_data mflash_drv_data = {
+        /* If you want to polling driver set to 1 */
+        .use_polling = 0,
+        /* device attribution */
+        .dev_attr = MG_BOOT_DEV
+};
+
+static struct resource mg_mflash_rsc[] = {
+        /* Base address of mflash */
+        [0] = {
+                .start = 0x08000000,
+                .end = 0x08000000 + SZ_64K - 1,
+                .flags = IORESOURCE_MEM
+        },
+        /* mflash interrupt pin */
+        [1] = {
+                .start = IRQ_GPIO(84),
+                .end = IRQ_GPIO(84),
+                .flags = IORESOURCE_IRQ
+        },
+        /* mflash reset pin */
+        [2] = {
+                .start = 43,
+                .end = 43,
+                .name = MG_RST_PIN,
+                .flags = IORESOURCE_IO
+        },
+        /* mflash reset-out pin
+         * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
+         * should assign this */
+        [3] = {
+                .start = 51,
+                .end = 51,
+                .name = MG_RSTOUT_PIN,
+                .flags = IORESOURCE_IO
+        }
+};
+
+static struct platform_device mflash_dev = {
+        .name = MG_DEV_NAME,
+        .id = -1,
+        .dev = {
+                .platform_data = &mflash_drv_data,
+        },
+        .num_resources = ARRAY_SIZE(mg_mflash_rsc),
+        .resource = mg_mflash_rsc
+};
+
+platform_device_register(&mflash_dev);
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index bb775fbe43d7..8b930946c52a 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -30,3 +30,21 @@ The above steps create a new group g1 and move the current shell
 process (bash) into it. CPU time consumed by this bash and its children
 can be obtained from g1/cpuacct.usage and the same is accumulated in
 /cgroups/cpuacct.usage also.
+
+cpuacct.stat file lists a few statistics which further divide the
+CPU time obtained by the cgroup into user and system times. Currently
+the following statistics are supported:
+
+user: Time spent by tasks of the cgroup in user mode.
+system: Time spent by tasks of the cgroup in kernel mode.
+
+user and system are in USER_HZ unit.
+
+cpuacct controller uses percpu_counter interface to collect user and
+system times. This has two side effects:
+
+- It is theoretically possible to see wrong values for user and system times.
+  This is because percpu_counter_read() on 32bit systems isn't safe
+  against concurrent writes.
+- It is possible to see slightly outdated values for user and system times
+  due to the batch processing nature of percpu_counter.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index a98a7fe7aabb..1a608877b14e 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -6,15 +6,14 @@ used here with the memory controller that is used in hardware.
 
 Salient features
 
-a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
+a. Enable control of Anonymous, Page Cache (mapped and unmapped) and
+   Swap Cache memory pages.
 b. The infrastructure allows easy addition of other types of memory to control
 c. Provides *zero overhead* for non memory controller users
 d. Provides a double LRU: global memory pressure causes reclaim from the
    global LRU; a cgroup on hitting a limit, reclaims from the per
    cgroup LRU
 
-NOTE: Swap Cache (unmapped) is not accounted now.
-
 Benefits and Purpose of the memory controller
 
 The memory controller isolates the memory behaviour of a group of tasks
@@ -290,34 +289,44 @@ will be charged as a new owner of it.
   moved to the parent. If you want to avoid that, force_empty will be useful.
 
 5.2 stat file
-  memory.stat file includes following statistics (now)
-        cache                   - # of pages from page-cache and shmem.
-        rss                     - # of pages from anonymous memory.
-        pgpgin                  - # of event of charging
-        pgpgout                 - # of event of uncharging
-        active_anon             - # of pages on active lru of anon, shmem.
-        inactive_anon           - # of pages on active lru of anon, shmem
-        active_file             - # of pages on active lru of file-cache
-        inactive_file           - # of pages on inactive lru of file cache
-        unevictable             - # of pages cannot be reclaimed.(mlocked etc)
-
-        Below is depend on CONFIG_DEBUG_VM.
-        inactive_ratio          - VM internal parameter. (see mm/page_alloc.c)
-        recent_rotated_anon     - VM internal parameter. (see mm/vmscan.c)
-        recent_rotated_file     - VM internal parameter. (see mm/vmscan.c)
-        recent_scanned_anon     - VM internal parameter. (see mm/vmscan.c)
-        recent_scanned_file     - VM internal parameter. (see mm/vmscan.c)
-
-  Memo:
+
+memory.stat file includes following statistics
+
+cache           - # of bytes of page cache memory.
+rss             - # of bytes of anonymous and swap cache memory.
+pgpgin          - # of pages paged in (equivalent to # of charging events).
+pgpgout         - # of pages paged out (equivalent to # of uncharging events).
+active_anon     - # of bytes of anonymous and  swap cache memory on active
+                  lru list.
+inactive_anon   - # of bytes of anonymous memory and swap cache memory on
+                  inactive lru list.
+active_file     - # of bytes of file-backed memory on active lru list.
+inactive_file   - # of bytes of file-backed memory on inactive lru list.
+unevictable     - # of bytes of memory that cannot be reclaimed (mlocked etc).
+
+The following additional stats are dependent on CONFIG_DEBUG_VM.
+
+inactive_ratio          - VM internal parameter. (see mm/page_alloc.c)
+recent_rotated_anon     - VM internal parameter. (see mm/vmscan.c)
+recent_rotated_file     - VM internal parameter. (see mm/vmscan.c)
+recent_scanned_anon     - VM internal parameter. (see mm/vmscan.c)
+recent_scanned_file     - VM internal parameter. (see mm/vmscan.c)
+
+Memo:
         recent_rotated means recent frequency of lru rotation.
         recent_scanned means recent # of scans to lru.
         showing for better debug please see the code for meanings.
 
+Note:
+        Only anonymous and swap cache memory is listed as part of 'rss' stat.
+        This should not be confused with the true 'resident set size' or the
+        amount of physical memory used by the cgroup. Per-cgroup rss
+        accounting is not done yet.
 
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroup's swapiness can't be changed.
+  Following cgroups' swapiness can't be changed.
   - root cgroup (uses /proc/sys/vm/swappiness).
   - a cgroup which uses hierarchy and it has child cgroup.
   - a cgroup which uses hierarchy and not the root of hierarchy.
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index f196ac1d7d25..95b24d766eab 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -47,13 +47,18 @@ to work with it.
 
 2. Basic accounting routines
 
- a. void res_counter_init(struct res_counter *rc)
+ a. void res_counter_init(struct res_counter *rc,
+                                struct res_counter *rc_parent)
 
         Initializes the resource counter. As usual, should be the first
         routine called for a new counter.
 
- b. int res_counter_charge[_locked]
-                        (struct res_counter *rc, unsigned long val)
+        The struct res_counter *parent can be used to define a hierarchical
+        child -> parent relationship directly in the res_counter structure,
+        NULL can be used to define no relationship.
+
+ c. int res_counter_charge(struct res_counter *rc, unsigned long val,
+                                struct res_counter **limit_fail_at)
 
         When a resource is about to be allocated it has to be accounted
         with the appropriate resource counter (controller should determine
@@ -67,15 +72,25 @@ to work with it.
           * if the charging is performed first, then it should be uncharged
             on error path (if the one is called).
 
- c. void res_counter_uncharge[_locked]
+        If the charging fails and a hierarchical dependency exists, the
+        limit_fail_at parameter is set to the particular res_counter element
+        where the charging failed.
+
+ d. int res_counter_charge_locked
+                        (struct res_counter *rc, unsigned long val)
+
+        The same as res_counter_charge(), but it must not acquire/release the
+        res_counter->lock internally (it must be called with res_counter->lock
+        held).
+
+ e. void res_counter_uncharge[_locked]
                         (struct res_counter *rc, unsigned long val)
 
         When a resource is released (freed) it should be de-accounted
         from the resource counter it was accounted to.  This is called
         "uncharging".
 
-    The _locked routines imply that the res_counter->lock is taken.
-
+        The _locked routines imply that the res_counter->lock is taken.
 
  2.1 Other accounting routines
 
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 327de1624759..53d64d382343 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -3,7 +3,7 @@
 
              Maintained by Alan Cox <device@lanana.org>
 
-                      Last revised: 29 November 2006
+                      Last revised: 6th April 2009
 
 This list is the Linux Device List, the official registry of allocated
 device numbers and /dev directory nodes for the Linux operating
@@ -2797,6 +2797,10 @@ Your cooperation is appreciated.
                  206 = /dev/ttySC1              SC26xx serial port 1
                  207 = /dev/ttySC2              SC26xx serial port 2
                  208 = /dev/ttySC3              SC26xx serial port 3
+                 209 = /dev/ttyMAX0             MAX3100 serial port 0
+                 210 = /dev/ttyMAX1             MAX3100 serial port 1
+                 211 = /dev/ttyMAX2             MAX3100 serial port 2
+                 212 = /dev/ttyMAX3             MAX3100 serial port 3
 
 205 char        Low-density serial ports (alternate device)
                   0 = /dev/culu0                Callout device for ttyLU0
diff --git a/Documentation/fb/uvesafb.txt b/Documentation/fb/uvesafb.txt
index 7ac3c4078ff9..eefdd91d298a 100644
--- a/Documentation/fb/uvesafb.txt
+++ b/Documentation/fb/uvesafb.txt
@@ -59,7 +59,8 @@ Accepted options:
 ypan    Enable display panning using the VESA protected mode
         interface.  The visible screen is just a window of the
         video memory, console scrolling is done by changing the
-        start of the window.  Available on x86 only.
+        start of the window.  This option is available on x86
+        only and is the default option on that architecture.
 
 ywrap   Same as ypan, but assumes your gfx board can wrap-around
         the video memory (i.e. starts reading from top if it
@@ -67,7 +68,7 @@ ywrap   Same as ypan, but assumes your gfx board can wrap-around
         Available on x86 only.
 
 redraw  Scroll by redrawing the affected part of the screen, this
-        is the safe (and slow) default.
+        is the default on non-x86.
 
 (If you're using uvesafb as a module, the above three options are
  used a parameter of the scroll option, e.g. scroll=ypan.)
@@ -182,7 +183,7 @@ from the Video BIOS if you set pixclock to 0 in fb_var_screeninfo.
 
 --
  Michal Januszewski <spock@gentoo.org>
- Last updated: 2007-06-16
+ Last updated: 2009-03-30
 
  Documentation of the uvesafb options is loosely based on vesafb.txt.
 
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 39246fc11257..de491a3e2313 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -354,7 +354,8 @@ Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
 
 ---------------------------
 
-What:   i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client()
+What:   i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client(),
+        i2c_adapter->client_register(), i2c_adapter->client_unregister
 When:   2.6.30
 Check:  i2c_attach_client i2c_detach_client
 Why:    Deprecated by the new (standard) device driver binding model. Use
@@ -427,3 +428,12 @@ Why:	In 2.6.27, the semantics of /sys/bus/pci/slots was redefined to
         After a reasonable transition period, we will remove the legacy
         fakephp interface.
 Who:    Alex Chiang <achiang@hp.com>
+
+---------------------------
+
+What:   i2c-voodoo3 driver
+When:   October 2009
+Why:    Superseded by tdfxfb. I2C/DDC support used to live in a separate
+        driver but this caused driver conflicts.
+Who:    Jean Delvare <khali@linux-fr.org>
+        Krzysztof Helt <krzysztof.h1@wp.pl>
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 52cd611277a3..8dd6db76171d 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -68,6 +68,8 @@ ncpfs.txt
         - info on Novell Netware(tm) filesystem using NCP protocol.
 nfsroot.txt
         - short guide on setting up a diskless box with NFS root filesystem.
+nilfs2.txt
+        - info and mount options for the NILFS2 filesystem.
 ntfs.txt
         - info and mount options for the NTFS filesystem (Windows NT).
 ocfs2.txt
diff --git a/Documentation/filesystems/knfsd-stats.txt b/Documentation/filesystems/knfsd-stats.txt
new file mode 100644
index 000000000000..64ced5149d37
--- /dev/null
+++ b/Documentation/filesystems/knfsd-stats.txt
@@ -0,0 +1,159 @@
+
+Kernel NFS Server Statistics
+============================
+
+This document describes the format and semantics of the statistics
+which the kernel NFS server makes available to userspace.  These
+statistics are available in several text form pseudo files, each of
+which is described separately below.
+
+In most cases you don't need to know these formats, as the nfsstat(8)
+program from the nfs-utils distribution provides a helpful command-line
+interface for extracting and printing them.
+
+All the files described here are formatted as a sequence of text lines,
+separated by newline '\n' characters.  Lines beginning with a hash
+'#' character are comments intended for humans and should be ignored
+by parsing routines.  All other lines contain a sequence of fields
+separated by whitespace.
+
+/proc/fs/nfsd/pool_stats
+------------------------
+
+This file is available in kernels from 2.6.30 onwards, if the
+/proc/fs/nfsd filesystem is mounted (it almost always should be).
+
+The first line is a comment which describes the fields present in
+all the other lines.  The other lines present the following data as
+a sequence of unsigned decimal numeric fields.  One line is shown
+for each NFS thread pool.
+
+All counters are 64 bits wide and wrap naturally.  There is no way
+to zero these counters, instead applications should do their own
+rate conversion.
+
+pool
+        The id number of the NFS thread pool to which this line applies.
+        This number does not change.
+
+        Thread pool ids are a contiguous set of small integers starting
+        at zero.  The maximum value depends on the thread pool mode, but
+        currently cannot be larger than the number of CPUs in the system.
+        Note that in the default case there will be a single thread pool
+        which contains all the nfsd threads and all the CPUs in the system,
+        and thus this file will have a single line with a pool id of "0".
+
+packets-arrived
+        Counts how many NFS packets have arrived.  More precisely, this
+        is the number of times that the network stack has notified the
+        sunrpc server layer that new data may be available on a transport
+        (e.g. an NFS or UDP socket or an NFS/RDMA endpoint).
+
+        Depending on the NFS workload patterns and various network stack
+        effects (such as Large Receive Offload) which can combine packets
+        on the wire, this may be either more or less than the number
+        of NFS calls received (which statistic is available elsewhere).
+        However this is a more accurate and less workload-dependent measure
+        of how much CPU load is being placed on the sunrpc server layer
+        due to NFS network traffic.
+
+sockets-enqueued
+        Counts how many times an NFS transport is enqueued to wait for
+        an nfsd thread to service it, i.e. no nfsd thread was considered
+        available.
+
+        The circumstance this statistic tracks indicates that there was NFS
+        network-facing work to be done but it couldn't be done immediately,
+        thus introducing a small delay in servicing NFS calls.  The ideal
+        rate of change for this counter is zero; significantly non-zero
+        values may indicate a performance limitation.
+
+        This can happen either because there are too few nfsd threads in the
+        thread pool for the NFS workload (the workload is thread-limited),
+        or because the NFS workload needs more CPU time than is available in
+        the thread pool (the workload is CPU-limited).  In the former case,
+        configuring more nfsd threads will probably improve the performance
+        of the NFS workload.  In the latter case, the sunrpc server layer is
+        already choosing not to wake idle nfsd threads because there are too
+        many nfsd threads which want to run but cannot, so configuring more
+        nfsd threads will make no difference whatsoever.  The overloads-avoided
+        statistic (see below) can be used to distinguish these cases.
+
+threads-woken
+        Counts how many times an idle nfsd thread is woken to try to
+        receive some data from an NFS transport.
+
+        This statistic tracks the circumstance where incoming
+        network-facing NFS work is being handled quickly, which is a good
+        thing.  The ideal rate of change for this counter will be close
+        to but less than the rate of change of the packets-arrived counter.
+
+overloads-avoided
+        Counts how many times the sunrpc server layer chose not to wake an
+        nfsd thread, despite the presence of idle nfsd threads, because
+        too many nfsd threads had been recently woken but could not get
+        enough CPU time to actually run.
+
+        This statistic counts a circumstance where the sunrpc layer
+        heuristically avoids overloading the CPU scheduler with too many
+        runnable nfsd threads.  The ideal rate of change for this counter
+        is zero.  Significant non-zero values indicate that the workload
+        is CPU limited.  Usually this is associated with heavy CPU usage
+        on all the CPUs in the nfsd thread pool.
+
+        If a sustained large overloads-avoided rate is detected on a pool,
+        the top(1) utility should be used to check for the following
+        pattern of CPU usage on all the CPUs associated with the given
+        nfsd thread pool.
+
+         - %us ~= 0 (as you're *NOT* running applications on your NFS server)
+
+         - %wa ~= 0
+
+         - %id ~= 0
+
+         - %sy + %hi + %si ~= 100
+
+        If this pattern is seen, configuring more nfsd threads will *not*
+        improve the performance of the workload.  If this patten is not
+        seen, then something more subtle is wrong.
+
+threads-timedout
+        Counts how many times an nfsd thread triggered an idle timeout,
+        i.e. was not woken to handle any incoming network packets for
+        some time.
+
+        This statistic counts a circumstance where there are more nfsd
+        threads configured than can be used by the NFS workload.  This is
+        a clue that the number of nfsd threads can be reduced without
+        affecting performance.  Unfortunately, it's only a clue and not
+        a strong indication, for a couple of reasons:
+
+         - Currently the rate at which the counter is incremented is quite
+           slow; the idle timeout is 60 minutes.  Unless the NFS workload
+           remains constant for hours at a time, this counter is unlikely
+           to be providing information that is still useful.
+
+         - It is usually a wise policy to provide some slack,
+           i.e. configure a few more nfsds than are currently needed,
+           to allow for future spikes in load.
+
+
+Note that incoming packets on NFS transports will be dealt with in
+one of three ways.  An nfsd thread can be woken (threads-woken counts
+this case), or the transport can be enqueued for later attention
+(sockets-enqueued counts this case), or the packet can be temporarily
+deferred because the transport is currently being used by an nfsd
+thread.  This last case is not very interesting and is not explicitly
+counted, but can be inferred from the other counters thus:
+
+packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken )
+
+
+More
+----
+Descriptions of the other statistics file should go here.
+
+
+Greg Banks <gnb@sgi.com>
+26 Mar 2009
diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt
new file mode 100644
index 000000000000..05d81cbcb2e1
--- /dev/null
+++ b/Documentation/filesystems/nfs41-server.txt
@@ -0,0 +1,161 @@
+NFSv4.1 Server Implementation
+
+Server support for minorversion 1 can be controlled using the
+/proc/fs/nfsd/versions control file.  The string output returned
+by reading this file will contain either "+4.1" or "-4.1"
+correspondingly.
+
+Currently, server support for minorversion 1 is disabled by default.
+It can be enabled at run time by writing the string "+4.1" to
+the /proc/fs/nfsd/versions control file.  Note that to write this
+control file, the nfsd service must be taken down.  Use your user-mode
+nfs-utils to set this up; see rpc.nfsd(8)
+
+The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
+on the latest NFSv4.1 Internet Draft:
+http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
+
+From the many new features in NFSv4.1 the current implementation
+focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
+"exactly once" semantics and better control and throttling of the
+resources allocated for each client.
+
+Other NFSv4.1 features, Parallel NFS operations in particular,
+are still under development out of tree.
+See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
+for more information.
+
+The table below, taken from the NFSv4.1 document, lists
+the operations that are mandatory to implement (REQ), optional
+(OPT), and NFSv4.0 operations that are required not to implement (MNI)
+in minor version 1.  The first column indicates the operations that
+are not supported yet by the linux server implementation.
+
+The OPTIONAL features identified and their abbreviations are as follows:
+        pNFS    Parallel NFS
+        FDELG   File Delegations
+        DDELG   Directory Delegations
+
+The following abbreviations indicate the linux server implementation status.
+        I       Implemented NFSv4.1 operations.
+        NS      Not Supported.
+        NS*     unimplemented optional feature.
+        P       pNFS features implemented out of tree.
+        PNS     pNFS features that are not supported yet (out of tree).
+
+Operations
+
+   +----------------------+------------+--------------+----------------+
+   | Operation            | REQ, REC,  | Feature      | Definition     |
+   |                      | OPT, or    | (REQ, REC,   |                |
+   |                      | MNI        | or OPT)      |                |
+   +----------------------+------------+--------------+----------------+
+   | ACCESS               | REQ        |              | Section 18.1   |
+NS | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
+NS | BIND_CONN_TO_SESSION | REQ        |              | Section 18.34  |
+   | CLOSE                | REQ        |              | Section 18.2   |
+   | COMMIT               | REQ        |              | Section 18.3   |
+   | CREATE               | REQ        |              | Section 18.4   |
+I  | CREATE_SESSION       | REQ        |              | Section 18.36  |
+NS*| DELEGPURGE           | OPT        | FDELG (REQ)  | Section 18.5   |
+   | DELEGRETURN          | OPT        | FDELG,       | Section 18.6   |
+   |                      |            | DDELG, pNFS  |                |
+   |                      |            | (REQ)        |                |
+NS | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
+I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
+I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
+NS | FREE_STATEID         | REQ        |              | Section 18.38  |
+   | GETATTR              | REQ        |              | Section 18.7   |
+P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
+P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
+   | GETFH                | REQ        |              | Section 18.8   |
+NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
+P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
+P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
+P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
+   | LINK                 | OPT        |              | Section 18.9   |
+   | LOCK                 | REQ        |              | Section 18.10  |
+   | LOCKT                | REQ        |              | Section 18.11  |
+   | LOCKU                | REQ        |              | Section 18.12  |
+   | LOOKUP               | REQ        |              | Section 18.13  |
+   | LOOKUPP              | REQ        |              | Section 18.14  |
+   | NVERIFY              | REQ        |              | Section 18.15  |
+   | OPEN                 | REQ        |              | Section 18.16  |
+NS*| OPENATTR             | OPT        |              | Section 18.17  |
+   | OPEN_CONFIRM         | MNI        |              | N/A            |
+   | OPEN_DOWNGRADE       | REQ        |              | Section 18.18  |
+   | PUTFH                | REQ        |              | Section 18.19  |
+   | PUTPUBFH             | REQ        |              | Section 18.20  |
+   | PUTROOTFH            | REQ        |              | Section 18.21  |
+   | READ                 | REQ        |              | Section 18.22  |
+   | READDIR              | REQ        |              | Section 18.23  |
+   | READLINK             | OPT        |              | Section 18.24  |
+NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
+   | REMOVE               | REQ        |              | Section 18.25  |
+   | RENAME               | REQ        |              | Section 18.26  |
+   | RENEW                | MNI        |              | N/A            |
+   | RESTOREFH            | REQ        |              | Section 18.27  |
+   | SAVEFH               | REQ        |              | Section 18.28  |
+   | SECINFO              | REQ        |              | Section 18.29  |
+NS | SECINFO_NO_NAME      | REC        | pNFS files   | Section 18.45, |
+   |                      |            | layout (REQ) | Section 13.12  |
+I  | SEQUENCE             | REQ        |              | Section 18.46  |
+   | SETATTR              | REQ        |              | Section 18.30  |
+   | SETCLIENTID          | MNI        |              | N/A            |
+   | SETCLIENTID_CONFIRM  | MNI        |              | N/A            |
+NS | SET_SSV              | REQ        |              | Section 18.47  |
+NS | TEST_STATEID         | REQ        |              | Section 18.48  |
+   | VERIFY               | REQ        |              | Section 18.31  |
+NS*| WANT_DELEGATION      | OPT        | FDELG (OPT)  | Section 18.49  |
+   | WRITE                | REQ        |              | Section 18.32  |
+
+Callback Operations
+
+   +-------------------------+-----------+-------------+---------------+
+   | Operation               | REQ, REC, | Feature     | Definition    |
+   |                         | OPT, or   | (REQ, REC,  |               |
+   |                         | MNI       | or OPT)     |               |
+   +-------------------------+-----------+-------------+---------------+
+   | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
+P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
+NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
+P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
+NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
+NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
+   | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_RECALL_ANY           | OPT       | FDELG,      | Section 20.6  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS | CB_RECALL_SLOT          | REQ       |             | Section 20.8  |
+NS*| CB_RECALLABLE_OBJ_AVAIL | OPT       | DDELG, pNFS | Section 20.7  |
+   |                         |           | (REQ)       |               |
+I  | CB_SEQUENCE             | OPT       | FDELG,      | Section 20.9  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+   +-------------------------+-----------+-------------+---------------+
+
+Implementation notes:
+
+EXCHANGE_ID:
+* only SP4_NONE state protection supported
+* implementation ids are ignored
+
+CREATE_SESSION:
+* backchannel attributes are ignored
+* backchannel security parameters are ignored
+
+SEQUENCE:
+* no support for dynamic slot table renegotiation (optional)
+
+nfsv4.1 COMPOUND rules:
+The following cases aren't supported yet:
+* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION,
+  DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
+* DESTROY_SESSION MUST be the final operation in the COMPOUND request.
+
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
new file mode 100644
index 000000000000..55c4300abfcb
--- /dev/null
+++ b/Documentation/filesystems/nilfs2.txt
@@ -0,0 +1,200 @@
+NILFS2
+------
+
+NILFS2 is a log-structured file system (LFS) supporting continuous
+snapshotting.  In addition to versioning capability of the entire file
+system, users can even restore files mistakenly overwritten or
+destroyed just a few seconds ago.  Since NILFS2 can keep consistency
+like conventional LFS, it achieves quick recovery after system
+crashes.
+
+NILFS2 creates a number of checkpoints every few seconds or per
+synchronous write basis (unless there is no change).  Users can select
+significant versions among continuously created checkpoints, and can
+change them into snapshots which will be preserved until they are
+changed back to checkpoints.
+
+There is no limit on the number of snapshots until the volume gets
+full.  Each snapshot is mountable as a read-only file system
+concurrently with its writable mount, and this feature is convenient
+for online backup.
+
+The userland tools are included in nilfs-utils package, which is
+available from the following download page.  At least "mkfs.nilfs2",
+"mount.nilfs2", "umount.nilfs2", and "nilfs_cleanerd" (so called
+cleaner or garbage collector) are required.  Details on the tools are
+described in the man pages included in the package.
+
+Project web page:    http://www.nilfs.org/en/
+Download page:       http://www.nilfs.org/en/download.html
+Git tree web page:   http://www.nilfs.org/git/
+NILFS mailing lists: http://www.nilfs.org/mailman/listinfo/users
+
+Caveats
+=======
+
+Features which NILFS2 does not support yet:
+
+        - atime
+        - extended attributes
+        - POSIX ACLs
+        - quotas
+        - writable snapshots
+        - remote backup (CDP)
+        - data integrity
+        - defragmentation
+
+Mount options
+=============
+
+NILFS2 supports the following mount options:
+(*) == default
+
+barrier=on(*)           This enables/disables barriers. barrier=off disables
+                        it, barrier=on enables it.
+errors=continue(*)      Keep going on a filesystem error.
+errors=remount-ro       Remount the filesystem read-only on an error.
+errors=panic            Panic and halt the machine if an error occurs.
+cp=n                    Specify the checkpoint-number of the snapshot to be
+                        mounted.  Checkpoints and snapshots are listed by lscp
+                        user command.  Only the checkpoints marked as snapshot
+                        are mountable with this option.  Snapshot is read-only,
+                        so a read-only mount option must be specified together.
+order=relaxed(*)        Apply relaxed order semantics that allows modified data
+                        blocks to be written to disk without making a
+                        checkpoint if no metadata update is going.  This mode
+                        is equivalent to the ordered data mode of the ext3
+                        filesystem except for the updates on data blocks still
+                        conserve atomicity.  This will improve synchronous
+                        write performance for overwriting.
+order=strict            Apply strict in-order semantics that preserves sequence
+                        of all file operations including overwriting of data
+                        blocks.  That means, it is guaranteed that no
+                        overtaking of events occurs in the recovered file
+                        system after a crash.
+
+NILFS2 usage
+============
+
+To use nilfs2 as a local file system, simply:
+
+ # mkfs -t nilfs2 /dev/block_device
+ # mount -t nilfs2 /dev/block_device /dir
+
+This will also invoke the cleaner through the mount helper program
+(mount.nilfs2).
+
+Checkpoints and snapshots are managed by the following commands.
+Their manpages are included in the nilfs-utils package above.
+
+  lscp     list checkpoints or snapshots.
+  mkcp     make a checkpoint or a snapshot.
+  chcp     change an existing checkpoint to a snapshot or vice versa.
+  rmcp     invalidate specified checkpoint(s).
+
+To mount a snapshot,
+
+ # mount -t nilfs2 -r -o cp=<cno> /dev/block_device /snap_dir
+
+where <cno> is the checkpoint number of the snapshot.
+
+To unmount the NILFS2 mount point or snapshot, simply:
+
+ # umount /dir
+
+Then, the cleaner daemon is automatically shut down by the umount
+helper program (umount.nilfs2).
+
+Disk format
+===========
+
+A nilfs2 volume is equally divided into a number of segments except
+for the super block (SB) and segment #0.  A segment is the container
+of logs.  Each log is composed of summary information blocks, payload
+blocks, and an optional super root block (SR):
+
+   ______________________________________________________
+  | |SB| | Segment | Segment | Segment | ... | Segment | |
+  |_|__|_|____0____|____1____|____2____|_____|____N____|_|
+  0 +1K +4K       +8M       +16M      +24M  +(8MB x N)
+       .             .            (Typical offsets for 4KB-block)
+    .                  .
+  .______________________.
+  | log | log |... | log |
+  |__1__|__2__|____|__m__|
+        .       .
+      .               .
+    .                       .
+  .______________________________.
+  | Summary | Payload blocks  |SR|
+  |_blocks__|_________________|__|
+
+The payload blocks are organized per file, and each file consists of
+data blocks and B-tree node blocks:
+
+    |<---       File-A        --->|<---       File-B        --->|
+   _______________________________________________________________
+    | Data blocks | B-tree blocks | Data blocks | B-tree blocks | ...
+   _|_____________|_______________|_____________|_______________|_
+
+
+Since only the modified blocks are written in the log, it may have
+files without data blocks or B-tree node blocks.
+
+The organization of the blocks is recorded in the summary information
+blocks, which contains a header structure (nilfs_segment_summary), per
+file structures (nilfs_finfo), and per block structures (nilfs_binfo):
+
+  _________________________________________________________________________
+ | Summary | finfo | binfo | ... | binfo | finfo | binfo | ... | binfo |...
+ |_blocks__|___A___|_(A,1)_|_____|(A,Na)_|___B___|_(B,1)_|_____|(B,Nb)_|___
+
+
+The logs include regular files, directory files, symbolic link files
+and several meta data files.  The mata data files are the files used
+to maintain file system meta data.  The current version of NILFS2 uses
+the following meta data files:
+
+ 1) Inode file (ifile)             -- Stores on-disk inodes
+ 2) Checkpoint file (cpfile)       -- Stores checkpoints
+ 3) Segment usage file (sufile)    -- Stores allocation state of segments
+ 4) Data address translation file  -- Maps virtual block numbers to usual
+    (DAT)                             block numbers.  This file serves to
+                                      make on-disk blocks relocatable.
+
+The following figure shows a typical organization of the logs:
+
+  _________________________________________________________________________
+ | Summary | regular file | file  | ... | ifile | cpfile | sufile | DAT |SR|
+ |_blocks__|_or_directory_|_______|_____|_______|________|________|_____|__|
+
+
+To stride over segment boundaries, this sequence of files may be split
+into multiple logs.  The sequence of logs that should be treated as
+logically one log, is delimited with flags marked in the segment
+summary.  The recovery code of nilfs2 looks this boundary information
+to ensure atomicity of updates.
+
+The super root block is inserted for every checkpoints.  It includes
+three special inodes, inodes for the DAT, cpfile, and sufile.  Inodes
+of regular files, directories, symlinks and other special files, are
+included in the ifile.  The inode of ifile itself is included in the
+corresponding checkpoint entry in the cpfile.  Thus, the hierarchy
+among NILFS2 files can be depicted as follows:
+
+  Super block (SB)
+       |
+       v
+  Super root block (the latest cno=xx)
+       |-- DAT
+       |-- sufile
+       `-- cpfile
+              |-- ifile (cno=c1)
+              |-- ifile (cno=c2) ---- file (ino=i1)
+              :        :          |-- file (ino=i2)
+              `-- ifile (cno=xx)  |-- file (ino=i3)
+                                  :        :
+                                  `-- file (ino=yy)
+                                    ( regular file, directory, or symlink )
+
+For detail on the format of each file, please see include/linux/nilfs2_fs.h.
diff --git a/Documentation/hwmon/g760a b/Documentation/hwmon/g760a
new file mode 100644
index 000000000000..e032eeb75629
--- /dev/null
+++ b/Documentation/hwmon/g760a
@@ -0,0 +1,36 @@
+Kernel driver g760a
+===================
+
+Supported chips:
+  * Global Mixed-mode Technology Inc. G760A
+    Prefix: 'g760a'
+    Datasheet: Publicly available at the GMT website
+      http://www.gmt.com.tw/datasheet/g760a.pdf
+
+Author: Herbert Valerio Riedel <hvr@gnu.org>
+
+Description
+-----------
+
+The GMT G760A Fan Speed PWM Controller is connected directly to a fan
+and performs closed-loop control of the fan speed.
+
+The fan speed is programmed by setting the period via 'pwm1' of two
+consecutive speed pulses. The period is defined in terms of clock
+cycle counts of an assumed 32kHz clock source.
+
+Setting a period of 0 stops the fan; setting the period to 255 sets
+fan to maximum speed.
+
+The measured fan rotation speed returned via 'fan1_input' is derived
+from the measured speed pulse period by assuming again a 32kHz clock
+source and a 2 pulse-per-revolution fan.
+
+The 'alarms' file provides access to the two alarm bits provided by
+the G760A chip's status register: Bit 0 is set when the actual fan
+speed differs more than 20% with respect to the programmed fan speed;
+bit 1 is set when fan speed is below 1920 RPM.
+
+The g760a driver will not update its values more frequently than every
+other second; reading them more often will do no harm, but will return
+'old' values.
diff --git a/Documentation/infiniband/ipoib.txt b/Documentation/infiniband/ipoib.txt
index 864ff3283780..6d40f00b358c 100644
--- a/Documentation/infiniband/ipoib.txt
+++ b/Documentation/infiniband/ipoib.txt
@@ -24,6 +24,49 @@ Partitions and P_Keys
   The P_Key for any interface is given by the "pkey" file, and the
   main interface for a subinterface is in "parent."
 
+Datagram vs Connected modes
+
+  The IPoIB driver supports two modes of operation: datagram and
+  connected.  The mode is set and read through an interface's
+  /sys/class/net/<intf name>/mode file.
+
+  In datagram mode, the IB UD (Unreliable Datagram) transport is used
+  and so the interface MTU has is equal to the IB L2 MTU minus the
+  IPoIB encapsulation header (4 bytes).  For example, in a typical IB
+  fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.
+
+  In connected mode, the IB RC (Reliable Connected) transport is used.
+  Connected mode is to takes advantage of the connected nature of the
+  IB transport and allows an MTU up to the maximal IP packet size of
+  64K, which reduces the number of IP packets needed for handling
+  large UDP datagrams, TCP segments, etc and increases the performance
+  for large messages.
+
+  In connected mode, the interface's UD QP is still used for multicast
+  and communication with peers that don't support connected mode. In
+  this case, RX emulation of ICMP PMTU packets is used to cause the
+  networking stack to use the smaller UD MTU for these neighbours.
+
+Stateless offloads
+
+  If the IB HW supports IPoIB stateless offloads, IPoIB advertises
+  TCP/IP checksum and/or Large Send (LSO) offloading capability to the
+  network stack.
+
+  Large Receive (LRO) offloading is also implemented and may be turned
+  on/off using ethtool calls.  Currently LRO is supported only for
+  checksum offload capable devices.
+
+  Stateless offloads are supported only in datagram mode.  
+
+Interrupt moderation
+
+  If the underlying IB device supports CQ event moderation, one can
+  use ethtool to set interrupt mitigation parameters and thus reduce
+  the overhead incurred by handling interrupts.  The main code path of
+  IPoIB doesn't use events for TX completion signaling so only RX
+  moderation is supported.
+
 Debugging Information
 
   By compiling the IPoIB driver with CONFIG_INFINIBAND_IPOIB_DEBUG set
@@ -55,3 +98,5 @@ References
     http://ietf.org/rfc/rfc4391.txt 
   IP over InfiniBand (IPoIB) Architecture (RFC 4392)
     http://ietf.org/rfc/rfc4392.txt 
+  IP over InfiniBand: Connected Mode (RFC 4755)
+    http://ietf.org/rfc/rfc4755.txt
diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt
new file mode 100644
index 000000000000..435102a26d96
--- /dev/null
+++ b/Documentation/input/rotary-encoder.txt
@@ -0,0 +1,101 @@
+rotary-encoder - a generic driver for GPIO connected devices
+Daniel Mack <daniel@caiaq.de>, Feb 2009
+
+0. Function
+-----------
+
+Rotary encoders are devices which are connected to the CPU or other
+peripherals with two wires. The outputs are phase-shifted by 90 degrees
+and by triggering on falling and rising edges, the turn direction can
+be determined.
+
+The phase diagram of these two outputs look like this:
+
+                  _____       _____       _____
+                 |     |     |     |     |     |
+  Channel A  ____|     |_____|     |_____|     |____
+
+                 :  :  :  :  :  :  :  :  :  :  :  :
+            __       _____       _____       _____
+              |     |     |     |     |     |     |
+  Channel B   |_____|     |_____|     |_____|     |__
+
+                 :  :  :  :  :  :  :  :  :  :  :  :
+  Event          a  b  c  d  a  b  c  d  a  b  c  d
+
+                |<-------->|
+                  one step
+
+
+For more information, please see
+        http://en.wikipedia.org/wiki/Rotary_encoder
+
+
+1. Events / state machine
+-------------------------
+
+a) Rising edge on channel A, channel B in low state
+        This state is used to recognize a clockwise turn
+
+b) Rising edge on channel B, channel A in high state
+        When entering this state, the encoder is put into 'armed' state,
+        meaning that there it has seen half the way of a one-step transition.
+
+c) Falling edge on channel A, channel B in high state
+        This state is used to recognize a counter-clockwise turn
+
+d) Falling edge on channel B, channel A in low state
+        Parking position. If the encoder enters this state, a full transition
+        should have happend, unless it flipped back on half the way. The
+        'armed' state tells us about that.
+
+2. Platform requirements
+------------------------
+
+As there is no hardware dependent call in this driver, the platform it is
+used with must support gpiolib. Another requirement is that IRQs must be
+able to fire on both edges.
+
+
+3. Board integration
+--------------------
+
+To use this driver in your system, register a platform_device with the
+name 'rotary-encoder' and associate the IRQs and some specific platform
+data with it.
+
+struct rotary_encoder_platform_data is declared in
+include/linux/rotary-encoder.h and needs to be filled with the number of
+steps the encoder has and can carry information about externally inverted
+signals (because of used invertig buffer or other reasons).
+
+Because GPIO to IRQ mapping is platform specific, this information must
+be given in seperately to the driver. See the example below.
+
+---------<snip>---------
+
+/* board support file example */
+
+#include <linux/input.h>
+#include <linux/rotary_encoder.h>
+
+#define GPIO_ROTARY_A 1
+#define GPIO_ROTARY_B 2
+
+static struct rotary_encoder_platform_data my_rotary_encoder_info = {
+        .steps          = 24,
+        .axis           = ABS_X,
+        .gpio_a         = GPIO_ROTARY_A,
+        .gpio_b         = GPIO_ROTARY_B,
+        .inverted_a     = 0,
+        .inverted_b     = 0,
+};
+
+static struct platform_device rotary_encoder_device = {
+        .name           = "rotary-encoder",
+        .id             = 0,
+        .dev            = {
+                .platform_data = &my_rotary_encoder_info,
+        }
+};
+
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index 55b2852904a4..02c0e9341dd8 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -61,24 +61,28 @@ GigaSet 307x Device Driver
      ---------------------
 2.1. Modules
      -------
-     To get the device working, you have to load the proper kernel module. You
-     can do this using
-         modprobe modulename
-     where modulename is ser_gigaset (M101), usb_gigaset (M105), or
-     bas_gigaset (direct USB connection to the base).
+     For the devices to work, the proper kernel modules have to be loaded.
+     This normally happens automatically when the system detects the USB
+     device (base, M105) or when the line discipline is attached (M101). It
+     can also be triggered manually using the modprobe(8) command, for example
+     for troubleshooting or to pass module parameters.
 
      The module ser_gigaset provides a serial line discipline N_GIGASET_M101
-     which drives the device through the regular serial line driver. To use it,
-     run the Gigaset M101 daemon "gigasetm101d" (also available from
-     http://sourceforge.net/projects/gigaset307x/) with the device file of the
-     RS232 port to the M101 as an argument, for example:
-         gigasetm101d /dev/ttyS1
-     This will open the device file, set its line discipline to N_GIGASET_M101,
-     and then sleep in the background, keeping the device open so that the
-     line discipline remains active. To deactivate it, kill the daemon, for
-     example with
-         killall gigasetm101d
-     before disconnecting the device.
+     which drives the device through the regular serial line driver. It must
+     be attached to the serial line to which the M101 is connected with the
+     ldattach(8) command (requires util-linux-ng release 2.14 or later), for
+     example:
+         ldattach GIGASET_M101 /dev/ttyS1
+     This will open the device file, attach the line discipline to it, and
+     then sleep in the background, keeping the device open so that the line
+     discipline remains active. To deactivate it, kill the daemon, for example
+     with
+         killall ldattach
+     before disconnecting the device. To have this happen automatically at
+     system startup/shutdown on an LSB compatible system, create and activate
+     an appropriate LSB startup script /etc/init.d/gigaset. (The init name
+     'gigaset' is officially assigned to this project by LANANA.)
+     Alternatively, just add the 'ldattach' command line to /etc/rc.local.
 
 2.2. Device nodes for user space programs
      ------------------------------------
@@ -194,10 +198,11 @@ GigaSet 307x Device Driver
      operation (for wireless access to the base), but are needed for access
      to the M105's own configuration mode (registration to the base, baudrate
      and line format settings, device status queries) via the gigacontr
-     utility. Their use is disabled in the driver by default for safety
-     reasons but can be enabled by setting the kernel configuration option
-     "Support for undocumented USB requests" (GIGASET_UNDOCREQ) to "Y" and
-     recompiling.
+     utility. Their use is controlled by the kernel configuration option
+     "Support for undocumented USB requests" (CONFIG_GIGASET_UNDOCREQ). If you
+     encounter error code -ENOTTY when trying to use some features of the
+     M105, try setting that option to "y" via 'make {x,menu}config' and
+     recompiling the driver.
 
 
 3.   Troubleshooting
@@ -228,6 +233,13 @@ GigaSet 307x Device Driver
      Solution:
         Select Unimodem mode for all DECT data adapters. (see section 2.4.)
 
+     Problem:
+        You want to configure your USB DECT data adapter (M105) but gigacontr
+        reports an error: "/dev/ttyGU0: Inappropriate ioctl for device".
+     Solution:
+        Recompile the usb_gigaset driver with the kernel configuration option
+        CONFIG_GIGASET_UNDOCREQ set to 'y'. (see section 2.6.)
+
 3.2. Telling the driver to provide more information
      ----------------------------------------------
      Building the driver with the "Gigaset debugging" kernel configuration
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 51104f9194a5..d4b05672f9f7 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -40,10 +40,16 @@ This document describes the Linux kernel Makefiles.
            --- 6.7 Custom kbuild commands
            --- 6.8 Preprocessing linker scripts
 
-        === 7 Kbuild Variables
-        === 8 Makefile language
-        === 9 Credits
-        === 10 TODO
+        === 7 Kbuild syntax for exported headers
+                --- 7.1 header-y
+                --- 7.2 objhdr-y
+                --- 7.3 destination-y
+                --- 7.4 unifdef-y (deprecated)
+
+        === 8 Kbuild Variables
+        === 9 Makefile language
+        === 10 Credits
+        === 11 TODO
 
 === 1 Overview
 
@@ -1143,8 +1149,69 @@ When kbuild executes, the following steps are followed (roughly):
         The kbuild infrastructure for *lds file are used in several
         architecture-specific files.
 
+=== 7 Kbuild syntax for exported headers
+
+The kernel include a set of headers that is exported to userspace.
+Many headers can be exported as-is but other headers requires  a
+minimal pre-processing before they are ready for user-space.
+The pre-processing does:
+- drop kernel specific annotations
+- drop include of compiler.h
+- drop all sections that is kernel internat (guarded by ifdef __KERNEL__)
+
+Each relevant directory contain a file name "Kbuild" which specify the
+headers to be exported.
+See subsequent chapter for the syntax of the Kbuild file.
+
+        --- 7.1 header-y
+
+        header-y specify header files to be exported.
+
+                Example:
+                        #include/linux/Kbuild
+                        header-y += usb/
+                        header-y += aio_abi.h
+
+        The convention is to list one file per line and
+        preferably in alphabetic order.
+
+        header-y also specify which subdirectories to visit.
+        A subdirectory is identified by a trailing '/' which
+        can be seen in the example above for the usb subdirectory.
+
+        Subdirectories are visited before their parent directories.
+
+        --- 7.2 objhdr-y
+
+        objhdr-y specifies generated files to be exported.
+        Generated files are special as they need to be looked
+        up in another directory when doing 'make O=...' builds.
+
+                Example:
+                        #include/linux/Kbuild
+                        objhdr-y += version.h
+
+        --- 7.3 destination-y
+
+        When an architecture have a set of exported headers that needs to be
+        exported to a different directory destination-y is used.
+        destination-y specify the destination directory for all exported
+        headers in the file where it is present.
+
+                Example:
+                        #arch/xtensa/platforms/s6105/include/platform/Kbuild
+                        destination-y := include/linux
+
+        In the example above all exported headers in the Kbuild file
+        will be located in the directory "include/linux" when exported.
+
+
+        --- 7.4 unifdef-y (deprecated)
+
+        unifdef-y is deprecated. A direct replacement is header-y.
+
 
-=== 7 Kbuild Variables
+=== 8 Kbuild Variables
 
 The top Makefile exports the following variables:
 
@@ -1206,7 +1273,7 @@ The top Makefile exports the following variables:
         INSTALL_MOD_STRIP will used as the option(s) to the strip command.
 
 
-=== 8 Makefile language
+=== 9 Makefile language
 
 The kernel Makefiles are designed to be run with GNU Make.  The Makefiles
 use only the documented features of GNU Make, but they do use many
@@ -1225,14 +1292,14 @@ time the left-hand side is used.
 There are some cases where "=" is appropriate.  Usually, though, ":="
 is the right choice.
 
-=== 9 Credits
+=== 10 Credits
 
 Original version made by Michael Elizabeth Chastain, <mailto:mec@shout.net>
 Updates by Kai Germaschewski <kai@tp1.ruhr-uni-bochum.de>
 Updates by Sam Ravnborg <sam@ravnborg.org>
 Language QA by Jan Engelhardt <jengelh@gmx.de>
 
-=== 10 TODO
+=== 11 TODO
 
 - Describe how kbuild supports shipped files with _shipped.
 - Generating offset header files.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 2895ce29dea5..6172e4360f60 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -153,60 +153,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         1,0: use 1st APIC table
                         default: 0
 
-        acpi_sleep=     [HW,ACPI] Sleep options
-                        Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-                                  old_ordering, s4_nonvs }
-                        See Documentation/power/video.txt for information on
-                        s3_bios and s3_mode.
-                        s3_beep is for debugging; it makes the PC's speaker beep
-                        as soon as the kernel's real-mode entry point is called.
-                        s4_nohwsig prevents ACPI hardware signature from being
-                        used during resume from hibernation.
-                        old_ordering causes the ACPI 1.0 ordering of the _PTS
-                        control method, with respect to putting devices into
-                        low power states, to be enforced (the ACPI 2.0 ordering
-                        of _PTS is used by default).
-                        s4_nonvs prevents the kernel from saving/restoring the
-                        ACPI NVS memory during hibernation.
-
-        acpi_sci=       [HW,ACPI] ACPI System Control Interrupt trigger mode
-                        Format: { level | edge | high | low }
-
-        acpi_irq_balance [HW,ACPI]
-                        ACPI will balance active IRQs
-                        default in APIC mode
-
-        acpi_irq_nobalance [HW,ACPI]
-                        ACPI will not move active IRQs (default)
-                        default in PIC mode
-
-        acpi_irq_pci=   [HW,ACPI] If irq_balance, clear listed IRQs for
-                        use by PCI
-                        Format: <irq>,<irq>...
-
-        acpi_irq_isa=   [HW,ACPI] If irq_balance, mark listed IRQs used by ISA
-                        Format: <irq>,<irq>...
-
-        acpi_no_auto_ssdt       [HW,ACPI] Disable automatic loading of SSDT
-
-        acpi_os_name=   [HW,ACPI] Tell ACPI BIOS the name of the OS
-                        Format: To spoof as Windows 98: ="Microsoft Windows"
-
-        acpi_osi=       [HW,ACPI] Modify list of supported OS interface strings
-                        acpi_osi="string1"      # add string1 -- only one string
-                        acpi_osi="!string2"     # remove built-in string2
-                        acpi_osi=               # disable all strings
-
-        acpi_serialize  [HW,ACPI] force serialization of AML methods
-
-        acpi_skip_timer_override [HW,ACPI]
-                        Recognize and ignore IRQ0/pin2 Interrupt Override.
-                        For broken nForce2 BIOS resulting in XT-PIC timer.
-        acpi_use_timer_override [HW,ACPI]
-                        Use timer override. For some broken Nvidia NF5 boards
-                        that require a timer override, but don't have
-                        HPET
-
         acpi_backlight= [HW,ACPI]
                         acpi_backlight=vendor
                         acpi_backlight=video
@@ -214,11 +160,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         (e.g. thinkpad_acpi, sony_acpi, etc.) instead
                         of the ACPI video.ko driver.
 
-        acpi_display_output=    [HW,ACPI]
-                        acpi_display_output=vendor
-                        acpi_display_output=video
-                        See above.
-
         acpi.debug_layer=       [HW,ACPI,ACPI_DEBUG]
         acpi.debug_level=       [HW,ACPI,ACPI_DEBUG]
                         Format: <int>
@@ -247,6 +188,41 @@ and is between 256 and 4096 characters. It is defined in the file
                         unusable.  The "log_buf_len" parameter may be useful
                         if you need to capture more output.
 
+        acpi_display_output=    [HW,ACPI]
+                        acpi_display_output=vendor
+                        acpi_display_output=video
+                        See above.
+
+        acpi_irq_balance [HW,ACPI]
+                        ACPI will balance active IRQs
+                        default in APIC mode
+
+        acpi_irq_nobalance [HW,ACPI]
+                        ACPI will not move active IRQs (default)
+                        default in PIC mode
+
+        acpi_irq_isa=   [HW,ACPI] If irq_balance, mark listed IRQs used by ISA
+                        Format: <irq>,<irq>...
+
+        acpi_irq_pci=   [HW,ACPI] If irq_balance, clear listed IRQs for
+                        use by PCI
+                        Format: <irq>,<irq>...
+
+        acpi_no_auto_ssdt       [HW,ACPI] Disable automatic loading of SSDT
+
+        acpi_os_name=   [HW,ACPI] Tell ACPI BIOS the name of the OS
+                        Format: To spoof as Windows 98: ="Microsoft Windows"
+
+        acpi_osi=       [HW,ACPI] Modify list of supported OS interface strings
+                        acpi_osi="string1"      # add string1 -- only one string
+                        acpi_osi="!string2"     # remove built-in string2
+                        acpi_osi=               # disable all strings
+
+        acpi_pm_good    [X86-32,X86-64]
+                        Override the pmtimer bug detection: force the kernel
+                        to assume that this machine's pmtimer latches its value
+                        and always returns good values.
+
         acpi.power_nocheck=     [HW,ACPI]
                         Format: 1/0 enable/disable the check of power state.
                         On some bogus BIOS the _PSC object/_STA object of
@@ -255,11 +231,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         power state again in power transition.
                         1 : disable the power state check
 
-        acpi_pm_good    [X86-32,X86-64]
-                        Override the pmtimer bug detection: force the kernel
-                        to assume that this machine's pmtimer latches its value
-                        and always returns good values.
-
         acpi_enforce_resources= [ACPI]
                         { strict | lax | no }
                         Check for resource conflicts between native drivers
@@ -276,22 +247,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         no: ACPI OperationRegions are not marked as reserved,
                         no further checks are performed.
 
-        agp=            [AGP]
-                        { off | try_unsupported }
-                        off: disable AGP support
-                        try_unsupported: try to drive unsupported chipsets
-                                (may crash computer or cause data corruption)
-
-        enable_timer_pin_1 [i386,x86-64]
-                        Enable PIN 1 of APIC timer
-                        Can be useful to work around chipset bugs
-                        (in particular on some ATI chipsets).
-                        The kernel tries to set a reasonable default.
-
-        disable_timer_pin_1 [i386,x86-64]
-                        Disable PIN 1 of APIC timer
-                        Can be useful to work around chipset bugs.
-
         ad1848=         [HW,OSS]
                         Format: <io>,<irq>,<dma>,<dma2>,<type>
 
@@ -305,6 +260,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         Format: <io>,<irq>,<dma>,<mss_io>,<mpu_io>,<mpu_irq>
                         See also header of sound/oss/aedsp16.c.
 
+        agp=            [AGP]
+                        { off | try_unsupported }
+                        off: disable AGP support
+                        try_unsupported: try to drive unsupported chipsets
+                                (may crash computer or cause data corruption)
+
         aha152x=        [HW,SCSI]
                         See Documentation/scsi/aha152x.txt.
 
@@ -432,12 +393,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         possible to determine what the correct size should be.
                         This option provides an override for these situations.
 
-        security=       [SECURITY] Choose a security module to enable at boot.
-                        If this boot parameter is not specified, only the first
-                        security module asking for security registration will be
-                        loaded. An invalid security module name will be treated
-                        as if no module has been chosen.
-
         capability.disable=
                         [SECURITY] Disable capabilities.  This would normally
                         be used only if an alternative security model is to be
@@ -509,24 +464,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         Range: 0 - 8192
                         Default: 64
 
-        dma_debug=off   If the kernel is compiled with DMA_API_DEBUG support
-                        this option disables the debugging code at boot.
-
-        dma_debug_entries=<number>
-                        This option allows to tune the number of preallocated
-                        entries for DMA-API debugging code. One entry is
-                        required per DMA-API allocation. Use this if the
-                        DMA-API debugging code disables itself because the
-                        architectural default is too low.
-
-        hpet=           [X86-32,HPET] option to control HPET usage
-                        Format: { enable (default) | disable | force |
-                                verbose }
-                        disable: disable HPET and use PIT instead
-                        force: allow force enabled of undocumented chips (ICH4,
-                        VIA, nVidia)
-                        verbose: show contents of HPET registers during setup
-
         com20020=       [HW,NET] ARCnet - COM20020 chipset
                         Format:
                         <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
@@ -570,23 +507,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         console=brl,ttyS0
                 For now, only VisioBraille is supported.
 
-        earlycon=       [KNL] Output early console device and options.
-                uart[8250],io,<addr>[,options]
-                uart[8250],mmio,<addr>[,options]
-                        Start an early, polled-mode console on the 8250/16550
-                        UART at the specified I/O port or MMIO address.
-                        The options are the same as for ttyS, above.
-
-        no_console_suspend
-                        [HW] Never suspend the console
-                        Disable suspending of consoles during suspend and
-                        hibernate operations.  Once disabled, debugging
-                        messages can reach various consoles while the rest
-                        of the system is being put to sleep (ie, while
-                        debugging driver suspend/resume hooks).  This may
-                        not work reliably with all consoles, but is known
-                        to work with serial and VGA consoles.
-
         coredump_filter=
                         [KNL] Change the default value for
                         /proc/<pid>/coredump_filter.
@@ -643,30 +563,13 @@ and is between 256 and 4096 characters. It is defined in the file
                         Format: <area>[,<node>]
                         See also Documentation/networking/decnet.txt.
 
-        vt.default_blu= [VT]
-                        Format: <blue0>,<blue1>,<blue2>,...,<blue15>
-                        Change the default blue palette of the console.
-                        This is a 16-member array composed of values
-                        ranging from 0-255.
-
-        vt.default_grn= [VT]
-                        Format: <green0>,<green1>,<green2>,...,<green15>
-                        Change the default green palette of the console.
-                        This is a 16-member array composed of values
-                        ranging from 0-255.
-
-        vt.default_red= [VT]
-                        Format: <red0>,<red1>,<red2>,...,<red15>
-                        Change the default red palette of the console.
-                        This is a 16-member array composed of values
-                        ranging from 0-255.
-
-        vt.default_utf8=
-                        [VT]
-                        Format=<0|1>
-                        Set system-wide default UTF-8 mode for all tty's.
-                        Default is 1, i.e. UTF-8 mode is enabled for all
-                        newly opened terminals.
+        default_hugepagesz=
+                        [same as hugepagesz=] The size of the default
+                        HugeTLB page size. This is the size represented by
+                        the legacy /proc/ hugepages APIs, used for SHM, and
+                        default size when mounting hugetlbfs filesystems.
+                        Defaults to the default architecture's huge page size
+                        if not specified.
 
         dhash_entries=  [KNL]
                         Set number of hash buckets for dentry cache.
@@ -679,27 +582,9 @@ and is between 256 and 4096 characters. It is defined in the file
                         Documentation/serial/digiepca.txt.
 
         disable_mtrr_cleanup [X86]
-        enable_mtrr_cleanup [X86]
                         The kernel tries to adjust MTRR layout from continuous
                         to discrete, to make X server driver able to add WB
-                        entry later. This parameter enables/disables that.
-
-        mtrr_chunk_size=nn[KMG] [X86]
-                        used for mtrr cleanup. It is largest continous chunk
-                        that could hold holes aka. UC entries.
-
-        mtrr_gran_size=nn[KMG] [X86]
-                        Used for mtrr cleanup. It is granularity of mtrr block.
-                        Default is 1.
-                        Large value could prevent small alignment from
-                        using up MTRRs.
-
-        mtrr_spare_reg_nr=n [X86]
-                        Format: <integer>
-                        Range: 0,7 : spare reg number
-                        Default : 1
-                        Used for mtrr cleanup. It is spare mtrr entries number.
-                        Set to 2 or more if your graphical card needs more.
+                        entry later. This parameter disables that.
 
         disable_mtrr_trim [X86, Intel and AMD only]
                         By default the kernel will trim any uncacheable
@@ -707,12 +592,38 @@ and is between 256 and 4096 characters. It is defined in the file
                         MTRR settings.  This parameter disables that behavior,
                         possibly causing your machine to run very slowly.
 
+        disable_timer_pin_1 [i386,x86-64]
+                        Disable PIN 1 of APIC timer
+                        Can be useful to work around chipset bugs.
+
         dmasound=       [HW,OSS] Sound subsystem buffers
 
+        dma_debug=off   If the kernel is compiled with DMA_API_DEBUG support,
+                        this option disables the debugging code at boot.
+
+        dma_debug_entries=<number>
+                        This option allows to tune the number of preallocated
+                        entries for DMA-API debugging code. One entry is
+                        required per DMA-API allocation. Use this if the
+                        DMA-API debugging code disables itself because the
+                        architectural default is too low.
+
         dscc4.setup=    [NET]
 
         dtc3181e=       [HW,SCSI]
 
+        dynamic_printk  Enables pr_debug()/dev_dbg() calls if
+                        CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled.
+                        These can also be switched on/off via
+                        <debugfs>/dynamic_printk/modules
+
+        earlycon=       [KNL] Output early console device and options.
+                uart[8250],io,<addr>[,options]
+                uart[8250],mmio,<addr>[,options]
+                        Start an early, polled-mode console on the 8250/16550
+                        UART at the specified I/O port or MMIO address.
+                        The options are the same as for ttyS, above.
+
         earlyprintk=    [X86-32,X86-64,SH,BLACKFIN]
                         earlyprintk=vga
                         earlyprintk=serial[,ttySn[,baudrate]]
@@ -754,6 +665,17 @@ and is between 256 and 4096 characters. It is defined in the file
                         pass this option to capture kernel.
                         See Documentation/kdump/kdump.txt for details.
 
+        enable_mtrr_cleanup [X86]
+                        The kernel tries to adjust MTRR layout from continuous
+                        to discrete, to make X server driver able to add WB
+                        entry later. This parameter enables that.
+
+        enable_timer_pin_1 [i386,x86-64]
+                        Enable PIN 1 of APIC timer
+                        Can be useful to work around chipset bugs
+                        (in particular on some ATI chipsets).
+                        The kernel tries to set a reasonable default.
+
         enforcing       [SELINUX] Set initial enforcing status.
                         Format: {"0" | "1"}
                         See security/selinux/Kconfig help text.
@@ -841,6 +763,16 @@ and is between 256 and 4096 characters. It is defined in the file
         hisax=          [HW,ISDN]
                         See Documentation/isdn/README.HiSax.
 
+        hlt             [BUGS=ARM,SH]
+
+        hpet=           [X86-32,HPET] option to control HPET usage
+                        Format: { enable (default) | disable | force |
+                                verbose }
+                        disable: disable HPET and use PIT instead
+                        force: allow force enabled of undocumented chips (ICH4,
+                                VIA, nVidia)
+                        verbose: show contents of HPET registers during setup
+
         hugepages=      [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
         hugepagesz=     [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
                         On x86-64 and powerpc, this option can be specified
@@ -850,15 +782,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         (when the CPU supports the "pdpe1gb" cpuinfo flag)
                         Note that 1GB pages can only be allocated at boot time
                         using hugepages= and not freed afterwards.
-        default_hugepagesz=
-                        [same as hugepagesz=] The size of the default
-                        HugeTLB page size. This is the size represented by
-                        the legacy /proc/ hugepages APIs, used for SHM, and
-                        default size when mounting hugetlbfs filesystems.
-                        Defaults to the default architecture's huge page size
-                        if not specified.
-
-        hlt             [BUGS=ARM,SH]
 
         hvc_iucv=       [S390] Number of z/VM IUCV hypervisor console (HVC)
                                terminal devices. Valid values: 0..8
@@ -919,6 +842,9 @@ and is between 256 and 4096 characters. It is defined in the file
         idebus=         [HW] (E)IDE subsystem - VLB/PCI bus speed
                         See Documentation/ide/ide.txt.
 
+        ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
+                        Claim all unknown PCI IDE storage controllers.
+
         idle=           [X86]
                         Format: idle=poll, idle=mwait, idle=halt, idle=nomwait
                         Poll forces a polling idle loop that can slightly
@@ -934,9 +860,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         In such case C2/C3 won't be used again.
                         idle=nomwait: Disable mwait for CPU C-states
 
-        ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
-                        Claim all unknown PCI IDE storage controllers.
-
         ignore_loglevel [KNL]
                         Ignore loglevel setting - this will print /all/
                         kernel messages to the console. Useful for debugging.
@@ -970,25 +893,6 @@ and is between 256 and 4096 characters. It is defined in the file
         inport.irq=     [HW] Inport (ATI XL and Microsoft) busmouse driver
                         Format: <irq>
 
-        inttest=        [IA64]
-
-        iomem=          Disable strict checking of access to MMIO memory
-                strict  regions from userspace.
-                relaxed
-
-        iommu=          [x86]
-                off
-                force
-                noforce
-                biomerge
-                panic
-                nopanic
-                merge
-                nomerge
-                forcesac
-                soft
-
-
         intel_iommu=    [DMAR] Intel IOMMU driver (DMAR) option
                 on
                         Enable intel iommu driver.
@@ -1012,6 +916,28 @@ and is between 256 and 4096 characters. It is defined in the file
                         result in a hardware IOTLB flush operation as opposed
                         to batching them for performance.
 
+        inttest=        [IA64]
+
+        iomem=          Disable strict checking of access to MMIO memory
+                strict  regions from userspace.
+                relaxed
+
+        iommu=          [x86]
+                off
+                force
+                noforce
+                biomerge
+                panic
+                nopanic
+                merge
+                nomerge
+                forcesac
+                soft
+
+        io7=            [HW] IO7 for Marvel based alpha systems
+                        See comment before marvel_specify_io7 in
+                        arch/alpha/kernel/core_marvel.c.
+
         io_delay=       [X86-32,X86-64] I/O delay method
                 0x80
                         Standard port 0x80 based delay
@@ -1022,10 +948,6 @@ and is between 256 and 4096 characters. It is defined in the file
                 none
                         No delay
 
-        io7=            [HW] IO7 for Marvel based alpha systems
-                        See comment before marvel_specify_io7 in
-                        arch/alpha/kernel/core_marvel.c.
-
         ip=             [IP_PNP]
                         See Documentation/filesystems/nfsroot.txt.
 
@@ -1036,12 +958,6 @@ and is between 256 and 4096 characters. It is defined in the file
         ips=            [HW,SCSI] Adaptec / IBM ServeRAID controller
                         See header of drivers/scsi/ips.c.
 
-        ports=          [IP_VS_FTP] IPVS ftp helper module
-                        Default is 21.
-                        Up to 8 (IP_VS_APP_MAX_PORTS) ports
-                        may be specified.
-                        Format: <port>,<port>....
-
         irqfixup        [HW]
                         When an interrupt is not handled search all handlers
                         for it. Intended to get systems with badly broken
@@ -1082,6 +998,8 @@ and is between 256 and 4096 characters. It is defined in the file
         js=             [HW,JOY] Analog joystick
                         See Documentation/input/joystick.txt.
 
+        keepinitrd      [HW,ARM]
+
         kernelcore=nn[KMG]      [KNL,X86-32,IA-64,PPC,X86-64] This parameter
                         specifies the amount of memory usable by the kernel
                         for non-movable allocations.  The requested amount is
@@ -1107,21 +1025,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         higher than default (KMEMTRACE_N_SUBBUFS in code) if
                         you experience buffer overruns.
 
-        movablecore=nn[KMG]     [KNL,X86-32,IA-64,PPC,X86-64] This parameter
-                        is similar to kernelcore except it specifies the
-                        amount of memory used for migratable allocations.
-                        If both kernelcore and movablecore is specified,
-                        then kernelcore will be at *least* the specified
-                        value but may be more. If movablecore on its own
-                        is specified, the administrator must be careful
-                        that the amount of memory usable for all allocations
-                        is not too small.
-
-        keepinitrd      [HW,ARM]
-
-        kstack=N        [X86-32,X86-64] Print N words from the kernel stack
-                        in oops dumps.
-
         kgdboc=         [HW] kgdb over consoles.
                         Requires a tty driver that supports console polling.
                         (only serial suported for now)
@@ -1131,6 +1034,9 @@ and is between 256 and 4096 characters. It is defined in the file
                         Configure the RouterBoard 532 series on-chip
                         Ethernet adapter MAC address.
 
+        kstack=N        [X86-32,X86-64] Print N words from the kernel stack
+                        in oops dumps.
+
         l2cr=           [PPC]
 
         l3cr=           [PPC]
@@ -1276,9 +1182,8 @@ and is between 256 and 4096 characters. It is defined in the file
                         (machvec) in a generic kernel.
                         Example: machvec=hpzx1_swiotlb
 
-        max_loop=       [LOOP] Maximum number of loopback devices that can
-                        be mounted
-                        Format: <1-256>
+        max_addr=nn[KMG]        [KNL,BOOT,ia64] All physical memory greater
+                        than or equal to this physical address is ignored.
 
         maxcpus=        [SMP] Maximum number of processors that an SMP kernel
                         should make use of.  maxcpus=n : n >= 0 limits the
@@ -1286,8 +1191,9 @@ and is between 256 and 4096 characters. It is defined in the file
                         it is equivalent to "nosmp", which also disables
                         the IO APIC.
 
-        max_addr=nn[KMG]        [KNL,BOOT,ia64] All physical memory greater than
-                        or equal to this physical address is ignored.
+        max_loop=       [LOOP] Maximum number of loopback devices that can
+                        be mounted
+                        Format: <1-256>
 
         max_luns=       [SCSI] Maximum number of LUNs to probe.
                         Should be between 1 and 2^32-1.
@@ -1414,6 +1320,16 @@ and is between 256 and 4096 characters. It is defined in the file
         mousedev.yres=  [MOUSE] Vertical screen resolution, used for devices
                         reporting absolute coordinates, such as tablets
 
+        movablecore=nn[KMG]     [KNL,X86-32,IA-64,PPC,X86-64] This parameter
+                        is similar to kernelcore except it specifies the
+                        amount of memory used for migratable allocations.
+                        If both kernelcore and movablecore is specified,
+                        then kernelcore will be at *least* the specified
+                        value but may be more. If movablecore on its own
+                        is specified, the administrator must be careful
+                        that the amount of memory usable for all allocations
+                        is not too small.
+
         mpu401=         [HW,OSS]
                         Format: <io>,<irq>
 
@@ -1435,6 +1351,23 @@ and is between 256 and 4096 characters. It is defined in the file
                         [HW] Make the MicroTouch USB driver use raw coordinates
                         ('y', default) or cooked coordinates ('n')
 
+        mtrr_chunk_size=nn[KMG] [X86]
+                        used for mtrr cleanup. It is largest continous chunk
+                        that could hold holes aka. UC entries.
+
+        mtrr_gran_size=nn[KMG] [X86]
+                        Used for mtrr cleanup. It is granularity of mtrr block.
+                        Default is 1.
+                        Large value could prevent small alignment from
+                        using up MTRRs.
+
+        mtrr_spare_reg_nr=n [X86]
+                        Format: <integer>
+                        Range: 0,7 : spare reg number
+                        Default : 1
+                        Used for mtrr cleanup. It is spare mtrr entries number.
+                        Set to 2 or more if your graphical card needs more.
+
         n2=             [NET] SDL Inc. RISCom/N2 synchronous serial card
 
         NCR_D700=       [HW,SCSI]
@@ -1495,11 +1428,13 @@ and is between 256 and 4096 characters. It is defined in the file
                         0 - turn nmi_watchdog off
                         1 - use the IO-APIC timer for the NMI watchdog
                         2 - use the local APIC for the NMI watchdog using
-                        a performance counter. Note: This will use one performance
-                        counter and the local APIC's performance vector.
-                        When panic is specified panic when an NMI watchdog timeout occurs.
-                        This is useful when you use a panic=... timeout and need the box
-                        quickly up again.
+                        a performance counter. Note: This will use one
+                        performance counter and the local APIC's performance
+                        vector.
+                        When panic is specified, panic when an NMI watchdog
+                        timeout occurs.
+                        This is useful when you use a panic=... timeout and
+                        need the box quickly up again.
                         Instead of 1 and 2 it is possible to use the following
                         symbolic names: lapic and ioapic
                         Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
@@ -1508,6 +1443,16 @@ and is between 256 and 4096 characters. It is defined in the file
                         emulation library even if a 387 maths coprocessor
                         is present.
 
+        no_console_suspend
+                        [HW] Never suspend the console
+                        Disable suspending of consoles during suspend and
+                        hibernate operations.  Once disabled, debugging
+                        messages can reach various consoles while the rest
+                        of the system is being put to sleep (ie, while
+                        debugging driver suspend/resume hooks).  This may
+                        not work reliably with all consoles, but is known
+                        to work with serial and VGA consoles.
+
         noaliencache    [MM, NUMA, SLAB] Disables the allocation of alien
                         caches in the slab allocator.  Saves per-node memory,
                         but will impact performance.
@@ -1522,6 +1467,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         nocache         [ARM]
 
+        noclflush       [BUGS=X86] Don't use the CLFLUSH instruction
+
         nodelayacct     [KNL] Disable per-task delay accounting
 
         nodisconnect    [HW,SCSI,M68K] Disables SCSI disconnects.
@@ -1550,8 +1497,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         register save and restore. The kernel will only save
                         legacy floating-point registers on task switch.
 
-        noclflush       [BUGS=X86] Don't use the CLFLUSH instruction
-
         nohlt           [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
                         wfi(ARM) instruction doesn't work correctly and not to
                         use it. This is also useful when using JTAG debugger.
@@ -1596,12 +1541,6 @@ and is between 256 and 4096 characters. It is defined in the file
 
         nolapic_timer   [X86-32,APIC] Do not use the local APIC timer.
 
-        nox2apic        [X86-64,APIC] Do not enable x2APIC mode.
-
-        x2apic_phys     [X86-64,APIC] Use x2apic physical mode instead of
-                        default x2apic cluster mode on platforms
-                        supporting x2apic.
-
         noltlbs         [PPC] Do not use large page/tlb entries for kernel
                         lowmem mapping on PPC40x.
 
@@ -1612,6 +1551,9 @@ and is between 256 and 4096 characters. It is defined in the file
         nomfgpt         [X86-32] Disable Multi-Function General Purpose
                         Timer usage (for AMD Geode machines).
 
+        norandmaps      Don't use address space randomization.  Equivalent to
+                        echo 0 > /proc/sys/kernel/randomize_va_space
+
         noreplace-paravirt      [X86-32,PV_OPS] Don't patch paravirt_ops
 
         noreplace-smp   [X86-32,SMP] Don't replace SMP instructions
@@ -1650,13 +1592,13 @@ and is between 256 and 4096 characters. It is defined in the file
                         purges which is reported from either PAL_VM_SUMMARY or
                         SAL PALO.
 
+        nr_uarts=       [SERIAL] maximum number of UARTs to be registered.
+
         numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
                         one of ['zone', 'node', 'default'] can be specified
                         This can be set from sysctl after boot.
                         See Documentation/sysctl/vm.txt for details.
 
-        nr_uarts=       [SERIAL] maximum number of UARTs to be registered.
-
         ohci1394_dma=early      [HW] enable debugging via the ohci1394 driver.
                         See Documentation/debugging-via-ohci1394.txt for more
                         info.
@@ -1905,6 +1847,14 @@ and is between 256 and 4096 characters. It is defined in the file
         printk.time=    Show timing data prefixed to each printk message line
                         Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 
+        processor.max_cstate=   [HW,ACPI]
+                        Limit processor to maximum C-state
+                        max_cstate=9 overrides any DMI blacklist limit.
+
+        processor.nocst [HW,ACPI]
+                        Ignore the _CST method to determine C-states,
+                        instead using the legacy FADT method
+
         profile=        [KNL] Enable kernel profiling via /proc/profile
                         Format: [schedule,]<number>
                         Param: "schedule" - profile schedule points.
@@ -1914,14 +1864,6 @@ and is between 256 and 4096 characters. It is defined in the file
                                 Requires CONFIG_SCHEDSTATS
                         Param: "kvm" - profile VM exits.
 
-        processor.max_cstate=   [HW,ACPI]
-                        Limit processor to maximum C-state
-                        max_cstate=9 overrides any DMI blacklist limit.
-
-        processor.nocst [HW,ACPI]
-                        Ignore the _CST method to determine C-states,
-                        instead using the legacy FADT method
-
         prompt_ramdisk= [RAM] List of RAM disks to prompt for floppy disk
                         before loading.
                         See Documentation/blockdev/ramdisk.txt.
@@ -2075,7 +2017,13 @@ and is between 256 and 4096 characters. It is defined in the file
                         allowing boot to proceed.  none ignores them, expecting
                         user space to do the scan.
 
-        selinux         [SELINUX] Disable or enable SELinux at boot time.
+        security=       [SECURITY] Choose a security module to enable at boot.
+                        If this boot parameter is not specified, only the first
+                        security module asking for security registration will be
+                        loaded. An invalid security module name will be treated
+                        as if no module has been chosen.
+
+        selinux=        [SELINUX] Disable or enable SELinux at boot time.
                         Format: { "0" | "1" }
                         See security/selinux/Kconfig help text.
                         0 -- disable.
@@ -2499,9 +2447,6 @@ and is between 256 and 4096 characters. It is defined in the file
                                         medium is write-protected).
                         Example: quirks=0419:aaf5:rl,0421:0433:rc
 
-        add_efi_memmap  [EFI; x86-32,X86-64] Include EFI memory map in
-                        kernel's map of available physical RAM.
-
         vdso=           [X86-32,SH,x86-64]
                         vdso=2: enable compat VDSO (default with COMPAT_VDSO)
                         vdso=1: enable VDSO (default)
@@ -2540,6 +2485,31 @@ and is between 256 and 4096 characters. It is defined in the file
         vmpoff=         [KNL,S390] Perform z/VM CP command after power off.
                         Format: <command>
 
+        vt.default_blu= [VT]
+                        Format: <blue0>,<blue1>,<blue2>,...,<blue15>
+                        Change the default blue palette of the console.
+                        This is a 16-member array composed of values
+                        ranging from 0-255.
+
+        vt.default_grn= [VT]
+                        Format: <green0>,<green1>,<green2>,...,<green15>
+                        Change the default green palette of the console.
+                        This is a 16-member array composed of values
+                        ranging from 0-255.
+
+        vt.default_red= [VT]
+                        Format: <red0>,<red1>,<red2>,...,<red15>
+                        Change the default red palette of the console.
+                        This is a 16-member array composed of values
+                        ranging from 0-255.
+
+        vt.default_utf8=
+                        [VT]
+                        Format=<0|1>
+                        Set system-wide default UTF-8 mode for all tty's.
+                        Default is 1, i.e. UTF-8 mode is enabled for all
+                        newly opened terminals.
+
         waveartist=     [HW,OSS]
                         Format: <io>,<irq>,<dma>,<dma2>
 
@@ -2552,6 +2522,10 @@ and is between 256 and 4096 characters. It is defined in the file
         wdt=            [WDT] Watchdog
                         See Documentation/watchdog/wdt.txt.
 
+        x2apic_phys     [X86-64,APIC] Use x2apic physical mode instead of
+                        default x2apic cluster mode on platforms
+                        supporting x2apic.
+
         xd=             [HW,XT] Original XT pre-IDE (RLL encoded) disks.
         xd_geo=         See header of drivers/block/xd.c.
 
@@ -2559,9 +2533,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         Format:
                         <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
 
-        norandmaps      Don't use address space randomization.  Equivalent to
-                        echo 0 > /proc/sys/kernel/randomize_va_space
-
 ______________________________________________________________________
 
 TODO:
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 48b3de90eb1e..1e7a769a10f9 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -212,7 +212,9 @@ hit, Kprobes calls kp->pre_handler.  After the probed instruction
 is single-stepped, Kprobe calls kp->post_handler.  If a fault
 occurs during execution of kp->pre_handler or kp->post_handler,
 or during single-stepping of the probed instruction, Kprobes calls
-kp->fault_handler.  Any or all handlers can be NULL.
+kp->fault_handler.  Any or all handlers can be NULL. If kp->flags
+is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
+so, it's handlers aren't hit until calling enable_kprobe(kp).
 
 NOTE:
 1. With the introduction of the "symbol_name" field to struct kprobe,
@@ -363,6 +365,26 @@ probes) in the specified array, they clear the addr field of those
 incorrect probes. However, other probes in the array are
 unregistered correctly.
 
+4.7 disable_*probe
+
+#include <linux/kprobes.h>
+int disable_kprobe(struct kprobe *kp);
+int disable_kretprobe(struct kretprobe *rp);
+int disable_jprobe(struct jprobe *jp);
+
+Temporarily disables the specified *probe. You can enable it again by using
+enable_*probe(). You must specify the probe which has been registered.
+
+4.8 enable_*probe
+
+#include <linux/kprobes.h>
+int enable_kprobe(struct kprobe *kp);
+int enable_kretprobe(struct kretprobe *rp);
+int enable_jprobe(struct jprobe *jp);
+
+Enables *probe which has been disabled by disable_*probe(). You must specify
+the probe which has been registered.
+
 5. Kprobes Features and Limitations
 
 Kprobes allows multiple probes at the same address.  Currently,
@@ -500,10 +522,14 @@ the probe. If the probed function belongs to a module, the module name
 is also specified. Following columns show probe status. If the probe is on
 a virtual address that is no longer valid (module init sections, module
 virtual addresses that correspond to modules that've been unloaded),
-such probes are marked with [GONE].
+such probes are marked with [GONE]. If the probe is temporarily disabled,
+such probes are marked with [DISABLED].
 
-/debug/kprobes/enabled: Turn kprobes ON/OFF
+/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
 
-Provides a knob to globally turn registered kprobes ON or OFF. By default,
-all kprobes are enabled. By echoing "0" to this file, all registered probes
-will be disarmed, till such time a "1" is echoed to this file.
+Provides a knob to globally and forcibly turn registered kprobes ON or OFF.
+By default, all kprobes are enabled. By echoing "0" to this file, all
+registered probes will be disarmed, till such time a "1" is echoed to this
+file. Note that this knob just disarms and arms all kprobes and doesn't
+change each probe's disabling state. This means that disabled kprobes (marked
+[DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 0ab0230cbcb0..d16b7a1c3793 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -43,12 +43,11 @@ Table of Contents
     2) Representing devices without a current OF specification
       a) PHY nodes
       b) Interrupt controllers
-      c) CFI or JEDEC memory-mapped NOR flash
-      d) 4xx/Axon EMAC ethernet nodes
-      e) Xilinx IP cores
-      f) USB EHCI controllers
-      g) MDIO on GPIOs
-      h) SPI busses
+      c) 4xx/Axon EMAC ethernet nodes
+      d) Xilinx IP cores
+      e) USB EHCI controllers
+      f) MDIO on GPIOs
+      g) SPI busses
 
   VII - Marvell Discovery mv64[345]6x System Controller chips
     1) The /system-controller node
@@ -999,7 +998,7 @@ compatibility.
       translation of SOC addresses for memory mapped SOC registers.
     - bus-frequency: Contains the bus frequency for the SOC node.
       Typically, the value of this field is filled in by the boot
-      loader. 
+      loader.
 
 
   Recommended properties:
@@ -1287,71 +1286,7 @@ platforms are moved over to use the flattened-device-tree model.
                 device_type = "open-pic";
         };
 
-   c) CFI or JEDEC memory-mapped NOR flash
-
-    Flash chips (Memory Technology Devices) are often used for solid state
-    file systems on embedded devices.
-
-     - compatible : should contain the specific model of flash chip(s)
-       used, if known, followed by either "cfi-flash" or "jedec-flash"
-     - reg : Address range of the flash chip
-     - bank-width : Width (in bytes) of the flash bank.  Equal to the
-       device width times the number of interleaved chips.
-     - device-width : (optional) Width of a single flash chip.  If
-       omitted, assumed to be equal to 'bank-width'.
-     - #address-cells, #size-cells : Must be present if the flash has
-       sub-nodes representing partitions (see below).  In this case
-       both #address-cells and #size-cells must be equal to 1.
-
-    For JEDEC compatible devices, the following additional properties
-    are defined:
-
-     - vendor-id : Contains the flash chip's vendor id (1 byte).
-     - device-id : Contains the flash chip's device id (1 byte).
-
-    In addition to the information on the flash bank itself, the
-    device tree may optionally contain additional information
-    describing partitions of the flash address space.  This can be
-    used on platforms which have strong conventions about which
-    portions of the flash are used for what purposes, but which don't
-    use an on-flash partition table such as RedBoot.
-
-    Each partition is represented as a sub-node of the flash device.
-    Each node's name represents the name of the corresponding
-    partition of the flash device.
-
-    Flash partitions
-     - reg : The partition's offset and size within the flash bank.
-     - label : (optional) The label / name for this flash partition.
-       If omitted, the label is taken from the node name (excluding
-       the unit address).
-     - read-only : (optional) This parameter, if present, is a hint to
-       Linux that this flash partition should only be mounted
-       read-only.  This is usually used for flash partitions
-       containing early-boot firmware images or data which should not
-       be clobbered.
-
-    Example:
-
-        flash@ff000000 {
-                compatible = "amd,am29lv128ml", "cfi-flash";
-                reg = <ff000000 01000000>;
-                bank-width = <4>;
-                device-width = <1>;
-                #address-cells = <1>;
-                #size-cells = <1>;
-                fs@0 {
-                        label = "fs";
-                        reg = <0 f80000>;
-                };
-                firmware@f80000 {
-                        label ="firmware";
-                        reg = <f80000 80000>;
-                        read-only;
-                };
-        };
-
-    d) 4xx/Axon EMAC ethernet nodes
+    c) 4xx/Axon EMAC ethernet nodes
 
     The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
     the Axon bridge.  To operate this needs to interact with a ths
@@ -1499,7 +1434,7 @@ platforms are moved over to use the flattened-device-tree model.
                            available.
                            For Axon: 0x0000012a
 
-   e) Xilinx IP cores
+   d) Xilinx IP cores
 
    The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
    in Xilinx Spartan and Virtex FPGAs.  The devices cover the whole range
@@ -1761,7 +1696,7 @@ platforms are moved over to use the flattened-device-tree model.
       listed above, nodes for these devices should include a phy-handle
       property, and may include other common network device properties
       like local-mac-address.
-      
+
       iv) Xilinx Uartlite
 
       Xilinx uartlite devices are simple fixed speed serial ports.
@@ -1793,7 +1728,7 @@ platforms are moved over to use the flattened-device-tree model.
        - reg-offset : A value of 3 is required
        - reg-shift : A value of 2 is required
 
-    f) USB EHCI controllers
+    e) USB EHCI controllers
 
     Required properties:
       - compatible : should be "usb-ehci".
@@ -1819,7 +1754,7 @@ platforms are moved over to use the flattened-device-tree model.
                    big-endian;
            };
 
-   g) MDIO on GPIOs
+   f) MDIO on GPIOs
 
    Currently defined compatibles:
    - virtual,gpio-mdio
@@ -1839,7 +1774,7 @@ platforms are moved over to use the flattened-device-tree model.
                          &qe_pio_c 6>;
         };
 
-    h) SPI (Serial Peripheral Interface) busses
+    g) SPI (Serial Peripheral Interface) busses
 
     SPI busses can be described with a node for the SPI master device
     and a set of child nodes for each SPI slave on the bus.  For this
diff --git a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
index 84a04d5eb8e6..a48b2cadc7f0 100644
--- a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
@@ -5,9 +5,21 @@ Required properties:
 - reg : should specify localbus chip select and size used for the chip.
 - fsl,upm-addr-offset : UPM pattern offset for the address latch.
 - fsl,upm-cmd-offset : UPM pattern offset for the command latch.
-- gpios : may specify optional GPIO connected to the Ready-Not-Busy pin.
 
-Example:
+Optional properties:
+- fsl,upm-wait-flags : add chip-dependent short delays after running the
+        UPM pattern (0x1), after writing a data byte (0x2) or after
+        writing out a buffer (0x4).
+- fsl,upm-addr-line-cs-offsets : address offsets for multi-chip support.
+        The corresponding address lines are used to select the chip.
+- gpios : may specify optional GPIOs connected to the Ready-Not-Busy pins
+        (R/B#). For multi-chip devices, "n" GPIO definitions are required
+        according to the number of chips.
+- chip-delay : chip dependent delay for transfering data from array to
+        read registers (tR). Required if property "gpios" is not used
+        (R/B# pins not connected).
+
+Examples:
 
 upm@1,0 {
         compatible = "fsl,upm-nand";
@@ -26,3 +38,26 @@ upm@1,0 {
                 };
         };
 };
+
+upm@3,0 {
+        #address-cells = <0>;
+        #size-cells = <0>;
+        compatible = "tqc,tqm8548-upm-nand", "fsl,upm-nand";
+        reg = <3 0x0 0x800>;
+        fsl,upm-addr-offset = <0x10>;
+        fsl,upm-cmd-offset = <0x08>;
+        /* Multi-chip NAND device */
+        fsl,upm-addr-line-cs-offsets = <0x0 0x200>;
+        fsl,upm-wait-flags = <0x5>;
+        chip-delay = <25>; // in micro-seconds
+
+        nand@0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+
+                partition@0 {
+                            label = "fs";
+                            reg = <0x00000000 0x10000000>;
+                };
+        };
+};
diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt
index ff51f4c0fa9d..4fe14deedc0a 100644
--- a/Documentation/powerpc/dts-bindings/gpio/led.txt
+++ b/Documentation/powerpc/dts-bindings/gpio/led.txt
@@ -1,15 +1,43 @@
-LED connected to GPIO
+LEDs connected to GPIO lines
 
 Required properties:
-- compatible : should be "gpio-led".
-- label : (optional) the label for this LED. If omitted, the label is
+- compatible : should be "gpio-leds".
+
+Each LED is represented as a sub-node of the gpio-leds device.  Each
+node's name represents the name of the corresponding LED.
+
+LED sub-node properties:
+- gpios :  Should specify the LED's GPIO, see "Specifying GPIO information
+  for devices" in Documentation/powerpc/booting-without-of.txt.  Active
+  low LEDs should be indicated using flags in the GPIO specifier.
+- label :  (optional) The label for this LED.  If omitted, the label is
   taken from the node name (excluding the unit address).
-- gpios : should specify LED GPIO.
+- linux,default-trigger :  (optional) This parameter, if present, is a
+  string defining the trigger assigned to the LED.  Current triggers are:
+    "backlight" - LED will act as a back-light, controlled by the framebuffer
+                  system
+    "default-on" - LED will turn on
+    "heartbeat" - LED "double" flashes at a load average based rate
+    "ide-disk" - LED indicates disk activity
+    "timer" - LED flashes at a fixed, configurable rate
 
-Example:
+Examples:
 
-led@0 {
-        compatible = "gpio-led";
-        label = "hdd";
-        gpios = <&mcu_pio 0 1>;
+leds {
+        compatible = "gpio-leds";
+        hdd {
+                label = "IDE Activity";
+                gpios = <&mcu_pio 0 1>; /* Active low */
+                linux,default-trigger = "ide-disk";
+        };
 };
+
+run-control {
+        compatible = "gpio-leds";
+        red {
+                gpios = <&mpc8572 6 0>;
+        };
+        green {
+                gpios = <&mpc8572 7 0>;
+        };
+}
diff --git a/Documentation/powerpc/dts-bindings/mtd-physmap.txt b/Documentation/powerpc/dts-bindings/mtd-physmap.txt
new file mode 100644
index 000000000000..667c9bde8699
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/mtd-physmap.txt
@@ -0,0 +1,80 @@
+CFI or JEDEC memory-mapped NOR flash
+
+Flash chips (Memory Technology Devices) are often used for solid state
+file systems on embedded devices.
+
+ - compatible : should contain the specific model of flash chip(s)
+   used, if known, followed by either "cfi-flash" or "jedec-flash"
+ - reg : Address range(s) of the flash chip(s)
+   It's possible to (optionally) define multiple "reg" tuples so that
+   non-identical NOR chips can be described in one flash node.
+ - bank-width : Width (in bytes) of the flash bank.  Equal to the
+   device width times the number of interleaved chips.
+ - device-width : (optional) Width of a single flash chip.  If
+   omitted, assumed to be equal to 'bank-width'.
+ - #address-cells, #size-cells : Must be present if the flash has
+   sub-nodes representing partitions (see below).  In this case
+   both #address-cells and #size-cells must be equal to 1.
+
+For JEDEC compatible devices, the following additional properties
+are defined:
+
+ - vendor-id : Contains the flash chip's vendor id (1 byte).
+ - device-id : Contains the flash chip's device id (1 byte).
+
+In addition to the information on the flash bank itself, the
+device tree may optionally contain additional information
+describing partitions of the flash address space.  This can be
+used on platforms which have strong conventions about which
+portions of the flash are used for what purposes, but which don't
+use an on-flash partition table such as RedBoot.
+
+Each partition is represented as a sub-node of the flash device.
+Each node's name represents the name of the corresponding
+partition of the flash device.
+
+Flash partitions
+ - reg : The partition's offset and size within the flash bank.
+ - label : (optional) The label / name for this flash partition.
+   If omitted, the label is taken from the node name (excluding
+   the unit address).
+ - read-only : (optional) This parameter, if present, is a hint to
+   Linux that this flash partition should only be mounted
+   read-only.  This is usually used for flash partitions
+   containing early-boot firmware images or data which should not
+   be clobbered.
+
+Example:
+
+        flash@ff000000 {
+                compatible = "amd,am29lv128ml", "cfi-flash";
+                reg = <ff000000 01000000>;
+                bank-width = <4>;
+                device-width = <1>;
+                #address-cells = <1>;
+                #size-cells = <1>;
+                fs@0 {
+                        label = "fs";
+                        reg = <0 f80000>;
+                };
+                firmware@f80000 {
+                        label ="firmware";
+                        reg = <f80000 80000>;
+                        read-only;
+                };
+        };
+
+Here an example with multiple "reg" tuples:
+
+        flash@f0000000,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "intel,PC48F4400P0VB", "cfi-flash";
+                reg = <0 0x00000000 0x02000000
+                       0 0x02000000 0x02000000>;
+                bank-width = <2>;
+                partition@0 {
+                        label = "test-part1";
+                        reg = <0 0x04000000>;
+                };
+        };
diff --git a/Documentation/scsi/aacraid.txt b/Documentation/scsi/aacraid.txt
index ddace3afc83b..30f643f611b2 100644
--- a/Documentation/scsi/aacraid.txt
+++ b/Documentation/scsi/aacraid.txt
@@ -60,17 +60,9 @@ Supported Cards/Chipsets
         9005:0285:9005:02d5     Adaptec ASR-2405 (Voodoo40 Lite)
         9005:0285:9005:02d6     Adaptec ASR-2445 (Voodoo44 Lite)
         9005:0285:9005:02d7     Adaptec ASR-2805 (Voodoo80 Lite)
-        9005:0285:9005:02d8     Adaptec 5405G (Voodoo40 PM)
-        9005:0285:9005:02d9     Adaptec 5445G (Voodoo44 PM)
-        9005:0285:9005:02da     Adaptec 5805G (Voodoo80 PM)
-        9005:0285:9005:02db     Adaptec 5085G (Voodoo08 PM)
-        9005:0285:9005:02dc     Adaptec 51245G (Voodoo124 PM)
-        9005:0285:9005:02dd     Adaptec 51645G (Voodoo164 PM)
-        9005:0285:9005:02de     Adaptec 52445G (Voodoo244 PM)
-        9005:0285:9005:02df     Adaptec ASR-2045G (Voodoo04 Lite PM)
-        9005:0285:9005:02e0     Adaptec ASR-2405G (Voodoo40 Lite PM)
-        9005:0285:9005:02e1     Adaptec ASR-2445G (Voodoo44 Lite PM)
-        9005:0285:9005:02e2     Adaptec ASR-2805G (Voodoo80 Lite PM)
+        9005:0285:9005:02d8     Adaptec 5405Z (Voodoo40 BLBU)
+        9005:0285:9005:02d9     Adaptec 5445Z (Voodoo44 BLBU)
+        9005:0285:9005:02da     Adaptec 5805Z (Voodoo80 BLBU)
         1011:0046:9005:0364     Adaptec 5400S (Mustang)
         1011:0046:9005:0365     Adaptec 5400S (Mustang)
         9005:0287:9005:0800     Adaptec Themisto (Jupiter)
@@ -140,6 +132,7 @@ Deanna Bonds                            (non-DASD support, PAE fibs and 64 bit,
                                          where fibs that go to the hardware are consistently called hw_fibs and
                                          not just fibs like the name of the driver tracking structure)
 Mark Salyzyn <Mark_Salyzyn@adaptec.com> Fixed panic issues and added some new product ids for upcoming hbas. Performance tuning, card failover and bug mitigations.
+Achim Leubner <Achim_Leubner@adaptec.com>
 
 Original Driver
 -------------------------
diff --git a/Documentation/sound/alsa/soc/jack.txt b/Documentation/sound/alsa/soc/jack.txt
new file mode 100644
index 000000000000..fcf82a417293
--- /dev/null
+++ b/Documentation/sound/alsa/soc/jack.txt
@@ -0,0 +1,71 @@
+ASoC jack detection
+===================
+
+ALSA has a standard API for representing physical jacks to user space,
+the kernel side of which can be seen in include/sound/jack.h.  ASoC
+provides a version of this API adding two additional features:
+
+ - It allows more than one jack detection method to work together on one
+   user visible jack.  In embedded systems it is common for multiple
+   to be present on a single jack but handled by separate bits of
+   hardware.
+
+ - Integration with DAPM, allowing DAPM endpoints to be updated
+   automatically based on the detected jack status (eg, turning off the
+   headphone outputs if no headphones are present).
+
+This is done by splitting the jacks up into three things working
+together: the jack itself represented by a struct snd_soc_jack, sets of
+snd_soc_jack_pins representing DAPM endpoints to update and blocks of
+code providing jack reporting mechanisms.
+
+For example, a system may have a stereo headset jack with two reporting
+mechanisms, one for the headphone and one for the microphone.  Some
+systems won't be able to use their speaker output while a headphone is
+connected and so will want to make sure to update both speaker and
+headphone when the headphone jack status changes.
+
+The jack - struct snd_soc_jack
+==============================
+
+This represents a physical jack on the system and is what is visible to
+user space.  The jack itself is completely passive, it is set up by the
+machine driver and updated by jack detection methods.
+
+Jacks are created by the machine driver calling snd_soc_jack_new().
+
+snd_soc_jack_pin
+================
+
+These represent a DAPM pin to update depending on some of the status
+bits supported by the jack.  Each snd_soc_jack has zero or more of these
+which are updated automatically.  They are created by the machine driver
+and associated with the jack using snd_soc_jack_add_pins().  The status
+of the endpoint may configured to be the opposite of the jack status if
+required (eg, enabling a built in microphone if a microphone is not
+connected via a jack).
+
+Jack detection methods
+======================
+
+Actual jack detection is done by code which is able to monitor some
+input to the system and update a jack by calling snd_soc_jack_report(),
+specifying a subset of bits to update.  The jack detection code should
+be set up by the machine driver, taking configuration for the jack to
+update and the set of things to report when the jack is connected.
+
+Often this is done based on the status of a GPIO - a handler for this is
+provided by the snd_soc_jack_add_gpio() function.  Other methods are
+also available, for example integrated into CODECs.  One example of
+CODEC integrated jack detection can be see in the WM8350 driver.
+
+Each jack may have multiple reporting mechanisms, though it will need at
+least one to be useful.
+
+Machine drivers
+===============
+
+These are all hooked together by the machine driver depending on the
+system hardware.  The machine driver will set up the snd_soc_jack and
+the list of pins to update then set up one or more jack detection
+mechanisms to update that jack based on their current status.
diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt
index 42f43fa59f24..34c76a55bc04 100644
--- a/Documentation/sparse.txt
+++ b/Documentation/sparse.txt
@@ -42,6 +42,14 @@ sure that bitwise types don't get mixed up (little-endian vs big-endian
 vs cpu-endian vs whatever), and there the constant "0" really _is_
 special.
 
+__bitwise__ - to be used for relatively compact stuff (gfp_t, etc.) that
+is mostly warning-free and is supposed to stay that way.  Warnings will
+be generated without __CHECK_ENDIAN__.
+
+__bitwise - noisy stuff; in particular, __le*/__be* are that.  We really
+don't want to drown in noise unless we'd explicitly asked for it.
+
+
 Getting sparse
 ~~~~~~~~~~~~~~
 
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index a34d55b65441..df38ef046f8d 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -95,7 +95,7 @@ of struct cmsghdr structures with appended data.
 
 There is only one file in this directory.
 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
-socket's buffer. It will not take effect unless PF_UNIX flag is spicified.
+socket's buffer. It will not take effect unless PF_UNIX flag is specified.
 
 
 3. /proc/sys/net/ipv4 - IPV4 settings
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 3197fc83bc51..97c4b3284329 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -39,6 +39,8 @@ Currently, these files are in /proc/sys/vm:
 - nr_hugepages
 - nr_overcommit_hugepages
 - nr_pdflush_threads
+- nr_pdflush_threads_min
+- nr_pdflush_threads_max
 - nr_trim_pages         (only if CONFIG_MMU=n)
 - numa_zonelist_order
 - oom_dump_tasks
@@ -463,6 +465,32 @@ The default value is 0.
 
 ==============================================================
 
+nr_pdflush_threads_min
+
+This value controls the minimum number of pdflush threads.
+
+At boot time, the kernel will create and maintain 'nr_pdflush_threads_min'
+threads for the kernel's lifetime.
+
+The default value is 2.  The minimum value you can specify is 1, and
+the maximum value is the current setting of 'nr_pdflush_threads_max'.
+
+See 'nr_pdflush_threads_max' below for more information.
+
+==============================================================
+
+nr_pdflush_threads_max
+
+This value controls the maximum number of pdflush threads that can be
+created.  The pdflush algorithm will create a new pdflush thread (up to
+this maximum) if no pdflush threads have been available for >= 1 second.
+
+The default value is 8.  The minimum value you can specify is the
+current value of 'nr_pdflush_threads_min' and the
+maximum is 1000.
+
+==============================================================
+
 overcommit_memory:
 
 This value contains a flag that enables memory overcommitment.
diff --git a/Documentation/tomoyo.txt b/Documentation/tomoyo.txt
new file mode 100644
index 000000000000..b3a232cae7f8
--- /dev/null
+++ b/Documentation/tomoyo.txt
@@ -0,0 +1,55 @@
+--- What is TOMOYO? ---
+
+TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel.
+
+LiveCD-based tutorials are available at
+http://tomoyo.sourceforge.jp/en/1.6.x/1st-step/ubuntu8.04-live/
+http://tomoyo.sourceforge.jp/en/1.6.x/1st-step/centos5-live/ .
+Though these tutorials use non-LSM version of TOMOYO, they are useful for you
+to know what TOMOYO is.
+
+--- How to enable TOMOYO? ---
+
+Build the kernel with CONFIG_SECURITY_TOMOYO=y and pass "security=tomoyo" on
+kernel's command line.
+
+Please see http://tomoyo.sourceforge.jp/en/2.2.x/ for details.
+
+--- Where is documentation? ---
+
+User <-> Kernel interface documentation is available at
+http://tomoyo.sourceforge.jp/en/2.2.x/policy-reference.html .
+
+Materials we prepared for seminars and symposiums are available at
+http://sourceforge.jp/projects/tomoyo/docs/?category_id=532&language_id=1 .
+Below lists are chosen from three aspects.
+
+What is TOMOYO?
+  TOMOYO Linux Overview
+    http://sourceforge.jp/projects/tomoyo/docs/lca2009-takeda.pdf
+  TOMOYO Linux: pragmatic and manageable security for Linux
+    http://sourceforge.jp/projects/tomoyo/docs/freedomhectaipei-tomoyo.pdf
+  TOMOYO Linux: A Practical Method to Understand and Protect Your Own Linux Box
+    http://sourceforge.jp/projects/tomoyo/docs/PacSec2007-en-no-demo.pdf
+
+What can TOMOYO do?
+  Deep inside TOMOYO Linux
+    http://sourceforge.jp/projects/tomoyo/docs/lca2009-kumaneko.pdf
+  The role of "pathname based access control" in security.
+    http://sourceforge.jp/projects/tomoyo/docs/lfj2008-bof.pdf
+
+History of TOMOYO?
+  Realities of Mainlining
+    http://sourceforge.jp/projects/tomoyo/docs/lfj2008.pdf
+
+--- What is future plan? ---
+
+We believe that inode based security and name based security are complementary
+and both should be used together. But unfortunately, so far, we cannot enable
+multiple LSM modules at the same time. We feel sorry that you have to give up
+SELinux/SMACK/AppArmor etc. when you want to use TOMOYO.
+
+We hope that LSM becomes stackable in future. Meanwhile, you can use non-LSM
+version of TOMOYO, available at http://tomoyo.sourceforge.jp/en/1.6.x/ .
+LSM version of TOMOYO is a subset of non-LSM version of TOMOYO. We are planning
+to port non-LSM version's functionalities to LSM versions.
diff --git a/Documentation/ftrace.txt b/Documentation/trace/ftrace.txt
index fd9a3e693813..fd9a3e693813 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
diff --git a/Documentation/vm/kmemtrace.txt b/Documentation/trace/kmemtrace.txt
index a956d9b7f943..a956d9b7f943 100644
--- a/Documentation/vm/kmemtrace.txt
+++ b/Documentation/trace/kmemtrace.txt
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/trace/mmiotrace.txt
index 5731c67abc55..5731c67abc55 100644
--- a/Documentation/tracers/mmiotrace.txt
+++ b/Documentation/trace/mmiotrace.txt
diff --git a/Documentation/tracepoints.txt b/Documentation/trace/tracepoints.txt
index c0e1ceed75a4..c0e1ceed75a4 100644
--- a/Documentation/tracepoints.txt
+++ b/Documentation/trace/tracepoints.txt
diff --git a/Documentation/video4linux/pxa_camera.txt b/Documentation/video4linux/pxa_camera.txt
new file mode 100644
index 000000000000..b1137f9a53eb
--- /dev/null
+++ b/Documentation/video4linux/pxa_camera.txt
@@ -0,0 +1,125 @@
+                              PXA-Camera Host Driver
+                              ======================
+
+Constraints
+-----------
+  a) Image size for YUV422P format
+     All YUV422P images are enforced to have width x height % 16 = 0.
+     This is due to DMA constraints, which transfers only planes of 8 byte
+     multiples.
+
+
+Global video workflow
+---------------------
+  a) QCI stopped
+     Initialy, the QCI interface is stopped.
+     When a buffer is queued (pxa_videobuf_ops->buf_queue), the QCI starts.
+
+  b) QCI started
+     More buffers can be queued while the QCI is started without halting the
+     capture.  The new buffers are "appended" at the tail of the DMA chain, and
+     smoothly captured one frame after the other.
+
+     Once a buffer is filled in the QCI interface, it is marked as "DONE" and
+     removed from the active buffers list. It can be then requeud or dequeued by
+     userland application.
+
+     Once the last buffer is filled in, the QCI interface stops.
+
+
+DMA usage
+---------
+  a) DMA flow
+     - first buffer queued for capture
+       Once a first buffer is queued for capture, the QCI is started, but data
+       transfer is not started. On "End Of Frame" interrupt, the irq handler
+       starts the DMA chain.
+     - capture of one videobuffer
+       The DMA chain starts transfering data into videobuffer RAM pages.
+       When all pages are transfered, the DMA irq is raised on "ENDINTR" status
+     - finishing one videobuffer
+       The DMA irq handler marks the videobuffer as "done", and removes it from
+       the active running queue
+       Meanwhile, the next videobuffer (if there is one), is transfered by DMA
+     - finishing the last videobuffer
+       On the DMA irq of the last videobuffer, the QCI is stopped.
+
+  b) DMA prepared buffer will have this structure
+
+     +------------+-----+---------------+-----------------+
+     | desc-sg[0] | ... | desc-sg[last] | finisher/linker |
+     +------------+-----+---------------+-----------------+
+
+     This structure is pointed by dma->sg_cpu.
+     The descriptors are used as follows :
+      - desc-sg[i]: i-th descriptor, transfering the i-th sg
+        element to the video buffer scatter gather
+      - finisher: has ddadr=DADDR_STOP, dcmd=ENDIRQEN
+      - linker: has ddadr= desc-sg[0] of next video buffer, dcmd=0
+
+     For the next schema, let's assume d0=desc-sg[0] .. dN=desc-sg[N],
+     "f" stands for finisher and "l" for linker.
+     A typical running chain is :
+
+         Videobuffer 1         Videobuffer 2
+     +---------+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+---+
+                      |    |
+                      +----+
+
+     After the chaining is finished, the chain looks like :
+
+         Videobuffer 1         Videobuffer 2         Videobuffer 3
+     +---------+----+---+  +----+----+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+-|-+  ^----+----+----+---+
+                      |    |                |    |
+                      +----+                +----+
+                                           new_link
+
+  c) DMA hot chaining timeslice issue
+
+     As DMA chaining is done while DMA _is_ running, the linking may be done
+     while the DMA jumps from one Videobuffer to another. On the schema, that
+     would be a problem if the following sequence is encountered :
+
+      - DMA chain is Videobuffer1 + Videobuffer2
+      - pxa_videobuf_queue() is called to queue Videobuffer3
+      - DMA controller finishes Videobuffer2, and DMA stops
+      =>
+         Videobuffer 1         Videobuffer 2
+     +---------+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+-^-+
+                      |    |                |
+                      +----+                +-- DMA DDADR loads DDADR_STOP
+
+      - pxa_dma_add_tail_buf() is called, the Videobuffer2 "finisher" is
+        replaced by a "linker" to Videobuffer3 (creation of new_link)
+      - pxa_videobuf_queue() finishes
+      - the DMA irq handler is called, which terminates Videobuffer2
+      - Videobuffer3 capture is not scheduled on DMA chain (as it stopped !!!)
+
+         Videobuffer 1         Videobuffer 2         Videobuffer 3
+     +---------+----+---+  +----+----+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+-|-+  ^----+----+----+---+
+                      |    |                |    |
+                      +----+                +----+
+                                           new_link
+                                          DMA DDADR still is DDADR_STOP
+
+      - pxa_camera_check_link_miss() is called
+        This checks if the DMA is finished and a buffer is still on the
+        pcdev->capture list. If that's the case, the capture will be restarted,
+        and Videobuffer3 is scheduled on DMA chain.
+      - the DMA irq handler finishes
+
+     Note: if DMA stops just after pxa_camera_check_link_miss() reads DDADR()
+     value, we have the guarantee that the DMA irq handler will be called back
+     when the DMA will finish the buffer, and pxa_camera_check_link_miss() will
+     be called again, to reschedule Videobuffer3.
+
+--
+Author: Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index a31177390e55..854808b67fae 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -90,7 +90,7 @@ up before calling v4l2_device_register then it will be untouched. If dev is
 NULL, then you *must* setup v4l2_dev->name before calling v4l2_device_register.
 
 The first 'dev' argument is normally the struct device pointer of a pci_dev,
-usb_device or platform_device. It is rare for dev to be NULL, but it happens
+usb_interface or platform_device. It is rare for dev to be NULL, but it happens
 with ISA devices or when one device creates multiple PCI devices, thus making
 it impossible to associate v4l2_dev with a particular parent.
 
@@ -351,17 +351,6 @@ And this to go from an i2c_client to a v4l2_subdev struct:
 
         struct v4l2_subdev *sd = i2c_get_clientdata(client);
 
-Finally you need to make a command function to make driver->command()
-call the right subdev_ops functions:
-
-static int subdev_command(struct i2c_client *client, unsigned cmd, void *arg)
-{
-        return v4l2_subdev_command(i2c_get_clientdata(client), cmd, arg);
-}
-
-If driver->command is never used then you can leave this out. Eventually the
-driver->command usage should be removed from v4l.
-
 Make sure to call v4l2_device_unregister_subdev(sd) when the remove() callback
 is called. This will unregister the sub-device from the bridge driver. It is
 safe to call this even if the sub-device was never registered.
@@ -375,14 +364,12 @@ from the remove() callback ensures that this is always done correctly.
 
 The bridge driver also has some helper functions it can use:
 
-struct v4l2_subdev *sd = v4l2_i2c_new_subdev(adapter, "module_foo", "chipid", 0x36);
+struct v4l2_subdev *sd = v4l2_i2c_new_subdev(v4l2_dev, adapter,
+               "module_foo", "chipid", 0x36);
 
 This loads the given module (can be NULL if no module needs to be loaded) and
 calls i2c_new_device() with the given i2c_adapter and chip/address arguments.
-If all goes well, then it registers the subdev with the v4l2_device. It gets
-the v4l2_device by calling i2c_get_adapdata(adapter), so you should make sure
-to call i2c_set_adapdata(adapter, v4l2_device) when you setup the i2c_adapter
-in your driver.
+If all goes well, then it registers the subdev with the v4l2_device.
 
 You can also use v4l2_i2c_new_probed_subdev() which is very similar to
 v4l2_i2c_new_subdev(), except that it has an array of possible I2C addresses
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index 2131b00b63f6..2f77ced35df7 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
         - this file.
+active_mm.txt
+        - An explanation from Linus about tsk->active_mm vs tsk->mm.
 balance
         - various information on memory balancing.
 hugetlbpage.txt
diff --git a/Documentation/vm/active_mm.txt b/Documentation/vm/active_mm.txt
new file mode 100644
index 000000000000..4ee1f643d897
--- /dev/null
+++ b/Documentation/vm/active_mm.txt
@@ -0,0 +1,83 @@
+List:       linux-kernel
+Subject:    Re: active_mm
+From:       Linus Torvalds <torvalds () transmeta ! com>
+Date:       1999-07-30 21:36:24
+
+Cc'd to linux-kernel, because I don't write explanations all that often,
+and when I do I feel better about more people reading them.
+
+On Fri, 30 Jul 1999, David Mosberger wrote:
+>
+> Is there a brief description someplace on how "mm" vs. "active_mm" in
+> the task_struct are supposed to be used?  (My apologies if this was
+> discussed on the mailing lists---I just returned from vacation and
+> wasn't able to follow linux-kernel for a while).
+
+Basically, the new setup is:
+
+ - we have "real address spaces" and "anonymous address spaces". The
+   difference is that an anonymous address space doesn't care about the
+   user-level page tables at all, so when we do a context switch into an
+   anonymous address space we just leave the previous address space
+   active.
+
+   The obvious use for a "anonymous address space" is any thread that
+   doesn't need any user mappings - all kernel threads basically fall into
+   this category, but even "real" threads can temporarily say that for
+   some amount of time they are not going to be interested in user space,
+   and that the scheduler might as well try to avoid wasting time on
+   switching the VM state around. Currently only the old-style bdflush
+   sync does that.
+
+ - "tsk->mm" points to the "real address space". For an anonymous process,
+   tsk->mm will be NULL, for the logical reason that an anonymous process
+   really doesn't _have_ a real address space at all.
+
+ - however, we obviously need to keep track of which address space we
+   "stole" for such an anonymous user. For that, we have "tsk->active_mm",
+   which shows what the currently active address space is.
+
+   The rule is that for a process with a real address space (ie tsk->mm is
+   non-NULL) the active_mm obviously always has to be the same as the real
+   one.
+
+   For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
+   "borrowed" mm while the anonymous process is running. When the
+   anonymous process gets scheduled away, the borrowed address space is
+   returned and cleared.
+
+To support all that, the "struct mm_struct" now has two counters: a
+"mm_users" counter that is how many "real address space users" there are,
+and a "mm_count" counter that is the number of "lazy" users (ie anonymous
+users) plus one if there are any real users.
+
+Usually there is at least one real user, but it could be that the real
+user exited on another CPU while a lazy user was still active, so you do
+actually get cases where you have a address space that is _only_ used by
+lazy users. That is often a short-lived state, because once that thread
+gets scheduled away in favour of a real thread, the "zombie" mm gets
+released because "mm_users" becomes zero.
+
+Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
+more. "init_mm" should be considered just a "lazy context when no other
+context is available", and in fact it is mainly used just at bootup when
+no real VM has yet been created. So code that used to check
+
+        if (current->mm == &init_mm)
+
+should generally just do
+
+        if (!current->mm)
+
+instead (which makes more sense anyway - the test is basically one of "do
+we have a user context", and is generally done by the page fault handler
+and things like that).
+
+Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
+because it slightly changes the interfaces to accomodate the alpha (who
+would have thought it, but the alpha actually ends up having one of the
+ugliest context switch codes - unlike the other architectures where the MM
+and register state is separate, the alpha PALcode joins the two, and you
+need to switch both together).
+
+(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt
index 0706a7282a8c..2d70d0d95108 100644
--- a/Documentation/vm/unevictable-lru.txt
+++ b/Documentation/vm/unevictable-lru.txt
@@ -1,588 +1,691 @@
-
-This document describes the Linux memory management "Unevictable LRU"
-infrastructure and the use of this infrastructure to manage several types
-of "unevictable" pages.  The document attempts to provide the overall
-rationale behind this mechanism and the rationale for some of the design
-decisions that drove the implementation.  The latter design rationale is
-discussed in the context of an implementation description.  Admittedly, one
-can obtain the implementation details--the "what does it do?"--by reading the
-code.  One hopes that the descriptions below add value by provide the answer
-to "why does it do that?".
-
-Unevictable LRU Infrastructure:
-
-The Unevictable LRU adds an additional LRU list to track unevictable pages
-and to hide these pages from vmscan.  This mechanism is based on a patch by
-Larry Woodman of Red Hat to address several scalability problems with page
+                        ==============================
+                        UNEVICTABLE LRU INFRASTRUCTURE
+                        ==============================
+
+========
+CONTENTS
+========
+
+ (*) The Unevictable LRU
+
+     - The unevictable page list.
+     - Memory control group interaction.
+     - Marking address spaces unevictable.
+     - Detecting Unevictable Pages.
+     - vmscan's handling of unevictable pages.
+
+ (*) mlock()'d pages.
+
+     - History.
+     - Basic management.
+     - mlock()/mlockall() system call handling.
+     - Filtering special vmas.
+     - munlock()/munlockall() system call handling.
+     - Migrating mlocked pages.
+     - mmap(MAP_LOCKED) system call handling.
+     - munmap()/exit()/exec() system call handling.
+     - try_to_unmap().
+     - try_to_munlock() reverse map scan.
+     - Page reclaim in shrink_*_list().
+
+
+============
+INTRODUCTION
+============
+
+This document describes the Linux memory manager's "Unevictable LRU"
+infrastructure and the use of this to manage several types of "unevictable"
+pages.
+
+The document attempts to provide the overall rationale behind this mechanism
+and the rationale for some of the design decisions that drove the
+implementation.  The latter design rationale is discussed in the context of an
+implementation description.  Admittedly, one can obtain the implementation
+details - the "what does it do?" - by reading the code.  One hopes that the
+descriptions below add value by provide the answer to "why does it do that?".
+
+
+===================
+THE UNEVICTABLE LRU
+===================
+
+The Unevictable LRU facility adds an additional LRU list to track unevictable
+pages and to hide these pages from vmscan.  This mechanism is based on a patch
+by Larry Woodman of Red Hat to address several scalability problems with page
 reclaim in Linux.  The problems have been observed at customer sites on large
-memory x86_64 systems.  For example, a non-numal x86_64 platform with 128GB
-of main memory will have over 32 million 4k pages in a single zone.  When a
-large fraction of these pages are not evictable for any reason [see below],
-vmscan will spend a lot of time scanning the LRU lists looking for the small
-fraction of pages that are evictable.  This can result in a situation where
-all cpus are spending 100% of their time in vmscan for hours or days on end,
-with the system completely unresponsive.
-
-The Unevictable LRU infrastructure addresses the following classes of
-unevictable pages:
-
-+ page owned by ramfs
-+ page mapped into SHM_LOCKed shared memory regions
-+ page mapped into VM_LOCKED [mlock()ed] vmas
-
-The infrastructure might be able to handle other conditions that make pages
+memory x86_64 systems.
+
+To illustrate this with an example, a non-NUMA x86_64 platform with 128GB of
+main memory will have over 32 million 4k pages in a single zone.  When a large
+fraction of these pages are not evictable for any reason [see below], vmscan
+will spend a lot of time scanning the LRU lists looking for the small fraction
+of pages that are evictable.  This can result in a situation where all CPUs are
+spending 100% of their time in vmscan for hours or days on end, with the system
+completely unresponsive.
+
+The unevictable list addresses the following classes of unevictable pages:
+
+ (*) Those owned by ramfs.
+
+ (*) Those mapped into SHM_LOCK'd shared memory regions.
+
+ (*) Those mapped into VM_LOCKED [mlock()ed] VMAs.
+
+The infrastructure may also be able to handle other conditions that make pages
 unevictable, either by definition or by circumstance, in the future.
 
 
-The Unevictable LRU List
+THE UNEVICTABLE PAGE LIST
+-------------------------
 
 The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
 called the "unevictable" list and an associated page flag, PG_unevictable, to
-indicate that the page is being managed on the unevictable list.  The
-PG_unevictable flag is analogous to, and mutually exclusive with, the PG_active
-flag in that it indicates on which LRU list a page resides when PG_lru is set.
-The unevictable LRU list is source configurable based on the UNEVICTABLE_LRU
-Kconfig option.
+indicate that the page is being managed on the unevictable list.
+
+The PG_unevictable flag is analogous to, and mutually exclusive with, the
+PG_active flag in that it indicates on which LRU list a page resides when
+PG_lru is set.  The unevictable list is compile-time configurable based on the
+UNEVICTABLE_LRU Kconfig option.
 
 The Unevictable LRU infrastructure maintains unevictable pages on an additional
 LRU list for a few reasons:
 
-1) We get to "treat unevictable pages just like we treat other pages in the
-   system, which means we get to use the same code to manipulate them, the
-   same code to isolate them (for migrate, etc.), the same code to keep track
-   of the statistics, etc..." [Rik van Riel]
+ (1) We get to "treat unevictable pages just like we treat other pages in the
+     system - which means we get to use the same code to manipulate them, the
+     same code to isolate them (for migrate, etc.), the same code to keep track
+     of the statistics, etc..." [Rik van Riel]
+
+ (2) We want to be able to migrate unevictable pages between nodes for memory
+     defragmentation, workload management and memory hotplug.  The linux kernel
+     can only migrate pages that it can successfully isolate from the LRU
+     lists.  If we were to maintain pages elsewhere than on an LRU-like list,
+     where they can be found by isolate_lru_page(), we would prevent their
+     migration, unless we reworked migration code to find the unevictable pages
+     itself.
 
-2) We want to be able to migrate unevictable pages between nodes--for memory
-   defragmentation, workload management and memory hotplug.  The linux kernel
-   can only migrate pages that it can successfully isolate from the lru lists.
-   If we were to maintain pages elsewise than on an lru-like list, where they
-   can be found by isolate_lru_page(), we would prevent their migration, unless
-   we reworked migration code to find the unevictable pages.
 
+The unevictable list does not differentiate between file-backed and anonymous,
+swap-backed pages.  This differentiation is only important while the pages are,
+in fact, evictable.
 
-The unevictable LRU list does not differentiate between file backed and swap
-backed [anon] pages.  This differentiation is only important while the pages
-are, in fact, evictable.
+The unevictable list benefits from the "arrayification" of the per-zone LRU
+lists and statistics originally proposed and posted by Christoph Lameter.
 
-The unevictable LRU list benefits from the "arrayification" of the per-zone
-LRU lists and statistics originally proposed and posted by Christoph Lameter.
+The unevictable list does not use the LRU pagevec mechanism. Rather,
+unevictable pages are placed directly on the page's zone's unevictable list
+under the zone lru_lock.  This allows us to prevent the stranding of pages on
+the unevictable list when one task has the page isolated from the LRU and other
+tasks are changing the "evictability" state of the page.
 
-The unevictable list does not use the lru pagevec mechanism. Rather,
-unevictable pages are placed directly on the page's zone's unevictable
-list under the zone lru_lock.  The reason for this is to prevent stranding
-of pages on the unevictable list when one task has the page isolated from the
-lru and other tasks are changing the "evictability" state of the page.
 
+MEMORY CONTROL GROUP INTERACTION
+--------------------------------
 
-Unevictable LRU and Memory Controller Interaction
+The unevictable LRU facility interacts with the memory control group [aka
+memory controller; see Documentation/cgroups/memory.txt] by extending the
+lru_list enum.
+
+The memory controller data structure automatically gets a per-zone unevictable
+list as a result of the "arrayification" of the per-zone LRU lists (one per
+lru_list enum element).  The memory controller tracks the movement of pages to
+and from the unevictable list.
 
-The memory controller data structure automatically gets a per zone unevictable
-lru list as a result of the "arrayification" of the per-zone LRU lists.  The
-memory controller tracks the movement of pages to and from the unevictable list.
 When a memory control group comes under memory pressure, the controller will
 not attempt to reclaim pages on the unevictable list.  This has a couple of
-effects.  Because the pages are "hidden" from reclaim on the unevictable list,
-the reclaim process can be more efficient, dealing only with pages that have
-a chance of being reclaimed.  On the other hand, if too many of the pages
-charged to the control group are unevictable, the evictable portion of the
-working set of the tasks in the control group may not fit into the available
-memory.  This can cause the control group to thrash or to oom-kill tasks.
-
-
-Unevictable LRU:  Detecting Unevictable Pages
-
-The function page_evictable(page, vma) in vmscan.c determines whether a
-page is evictable or not.  For ramfs pages and pages in SHM_LOCKed regions,
-page_evictable() tests a new address space flag, AS_UNEVICTABLE, in the page's
-address space using a wrapper function.  Wrapper functions are used to set,
-clear and test the flag to reduce the requirement for #ifdef's throughout the
-source code.  AS_UNEVICTABLE is set on ramfs inode/mapping when it is created.
-This flag remains for the life of the inode.
-
-For shared memory regions, AS_UNEVICTABLE is set when an application
-successfully SHM_LOCKs the region and is removed when the region is
-SHM_UNLOCKed.  Note that shmctl(SHM_LOCK, ...) does not populate the page
-tables for the region as does, for example, mlock().   So, we make no special
-effort to push any pages in the SHM_LOCKed region to the unevictable list.
-Vmscan will do this when/if it encounters the pages during reclaim.  On
-SHM_UNLOCK, shmctl() scans the pages in the region and "rescues" them from the
-unevictable list if no other condition keeps them unevictable.  If a SHM_LOCKed
-region is destroyed, the pages are also "rescued" from the unevictable list in
-the process of freeing them.
-
-page_evictable() detects mlock()ed pages by testing an additional page flag,
-PG_mlocked via the PageMlocked() wrapper.  If the page is NOT mlocked, and a
-non-NULL vma is supplied, page_evictable() will check whether the vma is
+effects:
+
+ (1) Because the pages are "hidden" from reclaim on the unevictable list, the
+     reclaim process can be more efficient, dealing only with pages that have a
+     chance of being reclaimed.
+
+ (2) On the other hand, if too many of the pages charged to the control group
+     are unevictable, the evictable portion of the working set of the tasks in
+     the control group may not fit into the available memory.  This can cause
+     the control group to thrash or to OOM-kill tasks.
+
+
+MARKING ADDRESS SPACES UNEVICTABLE
+----------------------------------
+
+For facilities such as ramfs none of the pages attached to the address space
+may be evicted.  To prevent eviction of any such pages, the AS_UNEVICTABLE
+address space flag is provided, and this can be manipulated by a filesystem
+using a number of wrapper functions:
+
+ (*) void mapping_set_unevictable(struct address_space *mapping);
+
+        Mark the address space as being completely unevictable.
+
+ (*) void mapping_clear_unevictable(struct address_space *mapping);
+
+        Mark the address space as being evictable.
+
+ (*) int mapping_unevictable(struct address_space *mapping);
+
+        Query the address space, and return true if it is completely
+        unevictable.
+
+These are currently used in two places in the kernel:
+
+ (1) By ramfs to mark the address spaces of its inodes when they are created,
+     and this mark remains for the life of the inode.
+
+ (2) By SYSV SHM to mark SHM_LOCK'd address spaces until SHM_UNLOCK is called.
+
+     Note that SHM_LOCK is not required to page in the locked pages if they're
+     swapped out; the application must touch the pages manually if it wants to
+     ensure they're in memory.
+
+
+DETECTING UNEVICTABLE PAGES
+---------------------------
+
+The function page_evictable() in vmscan.c determines whether a page is
+evictable or not using the query function outlined above [see section "Marking
+address spaces unevictable"] to check the AS_UNEVICTABLE flag.
+
+For address spaces that are so marked after being populated (as SHM regions
+might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate
+the page tables for the region as does, for example, mlock(), nor need it make
+any special effort to push any pages in the SHM_LOCK'd area to the unevictable
+list.  Instead, vmscan will do this if and when it encounters the pages during
+a reclamation scan.
+
+On an unlock action (such as SHM_UNLOCK), the unlocker (eg: shmctl()) must scan
+the pages in the region and "rescue" them from the unevictable list if no other
+condition is keeping them unevictable.  If an unevictable region is destroyed,
+the pages are also "rescued" from the unevictable list in the process of
+freeing them.
+
+page_evictable() also checks for mlocked pages by testing an additional page
+flag, PG_mlocked (as wrapped by PageMlocked()).  If the page is NOT mlocked,
+and a non-NULL VMA is supplied, page_evictable() will check whether the VMA is
 VM_LOCKED via is_mlocked_vma().  is_mlocked_vma() will SetPageMlocked() and
 update the appropriate statistics if the vma is VM_LOCKED.  This method allows
 efficient "culling" of pages in the fault path that are being faulted in to
-VM_LOCKED vmas.
+VM_LOCKED VMAs.
 
 
-Unevictable Pages and Vmscan [shrink_*_list()]
+VMSCAN'S HANDLING OF UNEVICTABLE PAGES
+--------------------------------------
 
 If unevictable pages are culled in the fault path, or moved to the unevictable
-list at mlock() or mmap() time, vmscan will never encounter the pages until
-they have become evictable again, for example, via munlock() and have been
-"rescued" from the unevictable list.  However, there may be situations where we
-decide, for the sake of expediency, to leave a unevictable page on one of the
-regular active/inactive LRU lists for vmscan to deal with.  Vmscan checks for
-such pages in all of the shrink_{active|inactive|page}_list() functions and
-will "cull" such pages that it encounters--that is, it diverts those pages to
-the unevictable list for the zone being scanned.
-
-There may be situations where a page is mapped into a VM_LOCKED vma, but the
-page is not marked as PageMlocked.  Such pages will make it all the way to
+list at mlock() or mmap() time, vmscan will not encounter the pages until they
+have become evictable again (via munlock() for example) and have been "rescued"
+from the unevictable list.  However, there may be situations where we decide,
+for the sake of expediency, to leave a unevictable page on one of the regular
+active/inactive LRU lists for vmscan to deal with.  vmscan checks for such
+pages in all of the shrink_{active|inactive|page}_list() functions and will
+"cull" such pages that it encounters: that is, it diverts those pages to the
+unevictable list for the zone being scanned.
+
+There may be situations where a page is mapped into a VM_LOCKED VMA, but the
+page is not marked as PG_mlocked.  Such pages will make it all the way to
 shrink_page_list() where they will be detected when vmscan walks the reverse
-map in try_to_unmap().  If try_to_unmap() returns SWAP_MLOCK, shrink_page_list()
-will cull the page at that point.
+map in try_to_unmap().  If try_to_unmap() returns SWAP_MLOCK,
+shrink_page_list() will cull the page at that point.
 
-To "cull" an unevictable page, vmscan simply puts the page back on the lru
-list using putback_lru_page()--the inverse operation to isolate_lru_page()--
-after dropping the page lock.  Because the condition which makes the page
-unevictable may change once the page is unlocked, putback_lru_page() will
-recheck the unevictable state of a page that it places on the unevictable lru
-list.  If the page has become unevictable, putback_lru_page() removes it from
-the list and retries, including the page_unevictable() test.  Because such a
-race is a rare event and movement of pages onto the unevictable list should be
-rare, these extra evictabilty checks should not occur in the majority of calls
-to putback_lru_page().
+To "cull" an unevictable page, vmscan simply puts the page back on the LRU list
+using putback_lru_page() - the inverse operation to isolate_lru_page() - after
+dropping the page lock.  Because the condition which makes the page unevictable
+may change once the page is unlocked, putback_lru_page() will recheck the
+unevictable state of a page that it places on the unevictable list.  If the
+page has become unevictable, putback_lru_page() removes it from the list and
+retries, including the page_unevictable() test.  Because such a race is a rare
+event and movement of pages onto the unevictable list should be rare, these
+extra evictabilty checks should not occur in the majority of calls to
+putback_lru_page().
 
 
-Mlocked Page:  Prior Work
+=============
+MLOCKED PAGES
+=============
 
-The "Unevictable Mlocked Pages" infrastructure is based on work originally
+The unevictable page list is also useful for mlock(), in addition to ramfs and
+SYSV SHM.  Note that mlock() is only available in CONFIG_MMU=y situations; in
+NOMMU situations, all mappings are effectively mlocked.
+
+
+HISTORY
+-------
+
+The "Unevictable mlocked Pages" infrastructure is based on work originally
 posted by Nick Piggin in an RFC patch entitled "mm: mlocked pages off LRU".
-Nick posted his patch as an alternative to a patch posted by Christoph
-Lameter to achieve the same objective--hiding mlocked pages from vmscan.
-In Nick's patch, he used one of the struct page lru list link fields as a count
-of VM_LOCKED vmas that map the page.  This use of the link field for a count
-prevented the management of the pages on an LRU list.  Thus, mlocked pages were
-not migratable as isolate_lru_page() could not find them and the lru list link
-field was not available to the migration subsystem.  Nick resolved this by
-putting mlocked pages back on the lru list before attempting to isolate them,
-thus abandoning the count of VM_LOCKED vmas.  When Nick's patch was integrated
-with the Unevictable LRU work, the count was replaced by walking the reverse
-map to determine whether any VM_LOCKED vmas mapped the page.  More on this
-below.
-
-
-Mlocked Pages:  Basic Management
-
-Mlocked pages--pages mapped into a VM_LOCKED vma--represent one class of
-unevictable pages.  When such a page has been "noticed" by the memory
-management subsystem, the page is marked with the PG_mlocked [PageMlocked()]
-flag.  A PageMlocked() page will be placed on the unevictable LRU list when
-it is added to the LRU.   Pages can be "noticed" by memory management in
-several places:
-
-1) in the mlock()/mlockall() system call handlers.
-2) in the mmap() system call handler when mmap()ing a region with the
-   MAP_LOCKED flag, or mmap()ing a region in a task that has called
-   mlockall() with the MCL_FUTURE flag.  Both of these conditions result
-   in the VM_LOCKED flag being set for the vma.
-3) in the fault path, if mlocked pages are "culled" in the fault path,
-   and when a VM_LOCKED stack segment is expanded.
-4) as mentioned above, in vmscan:shrink_page_list() when attempting to
-   reclaim a page in a VM_LOCKED vma via try_to_unmap().
-
-Mlocked pages become unlocked and rescued from the unevictable list when:
-
-1) mapped in a range unlocked via the munlock()/munlockall() system calls.
-2) munmapped() out of the last VM_LOCKED vma that maps the page, including
-   unmapping at task exit.
-3) when the page is truncated from the last VM_LOCKED vma of an mmap()ed file.
-4) before a page is COWed in a VM_LOCKED vma.
-
-
-Mlocked Pages:  mlock()/mlockall() System Call Handling
+Nick posted his patch as an alternative to a patch posted by Christoph Lameter
+to achieve the same objective: hiding mlocked pages from vmscan.
+
+In Nick's patch, he used one of the struct page LRU list link fields as a count
+of VM_LOCKED VMAs that map the page.  This use of the link field for a count
+prevented the management of the pages on an LRU list, and thus mlocked pages
+were not migratable as isolate_lru_page() could not find them, and the LRU list
+link field was not available to the migration subsystem.
+
+Nick resolved this by putting mlocked pages back on the lru list before
+attempting to isolate them, thus abandoning the count of VM_LOCKED VMAs.  When
+Nick's patch was integrated with the Unevictable LRU work, the count was
+replaced by walking the reverse map to determine whether any VM_LOCKED VMAs
+mapped the page.  More on this below.
+
+
+BASIC MANAGEMENT
+----------------
+
+mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable
+pages.  When such a page has been "noticed" by the memory management subsystem,
+the page is marked with the PG_mlocked flag.  This can be manipulated using the
+PageMlocked() functions.
+
+A PG_mlocked page will be placed on the unevictable list when it is added to
+the LRU.  Such pages can be "noticed" by memory management in several places:
+
+ (1) in the mlock()/mlockall() system call handlers;
+
+ (2) in the mmap() system call handler when mmapping a region with the
+     MAP_LOCKED flag;
+
+ (3) mmapping a region in a task that has called mlockall() with the MCL_FUTURE
+     flag
+
+ (4) in the fault path, if mlocked pages are "culled" in the fault path,
+     and when a VM_LOCKED stack segment is expanded; or
+
+ (5) as mentioned above, in vmscan:shrink_page_list() when attempting to
+     reclaim a page in a VM_LOCKED VMA via try_to_unmap()
+
+all of which result in the VM_LOCKED flag being set for the VMA if it doesn't
+already have it set.
+
+mlocked pages become unlocked and rescued from the unevictable list when:
+
+ (1) mapped in a range unlocked via the munlock()/munlockall() system calls;
+
+ (2) munmap()'d out of the last VM_LOCKED VMA that maps the page, including
+     unmapping at task exit;
+
+ (3) when the page is truncated from the last VM_LOCKED VMA of an mmapped file;
+     or
+
+ (4) before a page is COW'd in a VM_LOCKED VMA.
+
+
+mlock()/mlockall() SYSTEM CALL HANDLING
+---------------------------------------
 
 Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
-for each vma in the range specified by the call.  In the case of mlockall(),
+for each VMA in the range specified by the call.  In the case of mlockall(),
 this is the entire active address space of the task.  Note that mlock_fixup()
-is used for both mlock()ing and munlock()ing a range of memory.  A call to
-mlock() an already VM_LOCKED vma, or to munlock() a vma that is not VM_LOCKED
-is treated as a no-op--mlock_fixup() simply returns.
-
-If the vma passes some filtering described in "Mlocked Pages:  Filtering Vmas"
-below, mlock_fixup() will attempt to merge the vma with its neighbors or split
-off a subset of the vma if the range does not cover the entire vma.  Once the
-vma has been merged or split or neither, mlock_fixup() will call
-__mlock_vma_pages_range() to fault in the pages via get_user_pages() and
-to mark the pages as mlocked via mlock_vma_page().
-
-Note that the vma being mlocked might be mapped with PROT_NONE.  In this case,
-get_user_pages() will be unable to fault in the pages.  That's OK.  If pages
-do end up getting faulted into this VM_LOCKED vma, we'll handle them in the
+is used for both mlocking and munlocking a range of memory.  A call to mlock()
+an already VM_LOCKED VMA, or to munlock() a VMA that is not VM_LOCKED is
+treated as a no-op, and mlock_fixup() simply returns.
+
+If the VMA passes some filtering as described in "Filtering Special Vmas"
+below, mlock_fixup() will attempt to merge the VMA with its neighbors or split
+off a subset of the VMA if the range does not cover the entire VMA.  Once the
+VMA has been merged or split or neither, mlock_fixup() will call
+__mlock_vma_pages_range() to fault in the pages via get_user_pages() and to
+mark the pages as mlocked via mlock_vma_page().
+
+Note that the VMA being mlocked might be mapped with PROT_NONE.  In this case,
+get_user_pages() will be unable to fault in the pages.  That's okay.  If pages
+do end up getting faulted into this VM_LOCKED VMA, we'll handle them in the
 fault path or in vmscan.
 
 Also note that a page returned by get_user_pages() could be truncated or
-migrated out from under us, while we're trying to mlock it.  To detect
-this, __mlock_vma_pages_range() tests the page_mapping after acquiring
-the page lock.  If the page is still associated with its mapping, we'll
-go ahead and call mlock_vma_page().  If the mapping is gone, we just
-unlock the page and move on.  Worse case, this results in page mapped
-in a VM_LOCKED vma remaining on a normal LRU list without being
-PageMlocked().  Again, vmscan will detect and cull such pages.
-
-mlock_vma_page(), called with the page locked [N.B., not "mlocked"], will
-TestSetPageMlocked() for each page returned by get_user_pages().  We use
-TestSetPageMlocked() because the page might already be mlocked by another
-task/vma and we don't want to do extra work.  We especially do not want to
-count an mlocked page more than once in the statistics.  If the page was
-already mlocked, mlock_vma_page() is done.
+migrated out from under us, while we're trying to mlock it.  To detect this,
+__mlock_vma_pages_range() checks page_mapping() after acquiring the page lock.
+If the page is still associated with its mapping, we'll go ahead and call
+mlock_vma_page().  If the mapping is gone, we just unlock the page and move on.
+In the worst case, this will result in a page mapped in a VM_LOCKED VMA
+remaining on a normal LRU list without being PageMlocked().  Again, vmscan will
+detect and cull such pages.
+
+mlock_vma_page() will call TestSetPageMlocked() for each page returned by
+get_user_pages().  We use TestSetPageMlocked() because the page might already
+be mlocked by another task/VMA and we don't want to do extra work.  We
+especially do not want to count an mlocked page more than once in the
+statistics.  If the page was already mlocked, mlock_vma_page() need do nothing
+more.
 
 If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the
 page from the LRU, as it is likely on the appropriate active or inactive list
-at that time.  If the isolate_lru_page() succeeds, mlock_vma_page() will
-putback the page--putback_lru_page()--which will notice that the page is now
-mlocked and divert the page to the zone's unevictable LRU list.  If
+at that time.  If the isolate_lru_page() succeeds, mlock_vma_page() will put
+back the page - by calling putback_lru_page() - which will notice that the page
+is now mlocked and divert the page to the zone's unevictable list.  If
 mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
-it later if/when it attempts to reclaim the page.
+it later if and when it attempts to reclaim the page.
 
 
-Mlocked Pages:  Filtering Special Vmas
+FILTERING SPECIAL VMAS
+----------------------
 
-mlock_fixup() filters several classes of "special" vmas:
+mlock_fixup() filters several classes of "special" VMAs:
 
-1) vmas with VM_IO|VM_PFNMAP set are skipped entirely.  The pages behind
+1) VMAs with VM_IO or VM_PFNMAP set are skipped entirely.  The pages behind
    these mappings are inherently pinned, so we don't need to mark them as
-   mlocked.  In any case, most of the pages have no struct page in which to
-   so mark the page.  Because of this, get_user_pages() will fail for these
-   vmas, so there is no sense in attempting to visit them.
-
-2) vmas mapping hugetlbfs page are already effectively pinned into memory.
-   We don't need nor want to mlock() these pages.  However, to preserve the
-   prior behavior of mlock()--before the unevictable/mlock changes--
-   mlock_fixup() will call make_pages_present() in the hugetlbfs vma range
-   to allocate the huge pages and populate the ptes.
-
-3) vmas with VM_DONTEXPAND|VM_RESERVED are generally user space mappings of
-   kernel pages, such as the vdso page, relay channel pages, etc.  These pages
+   mlocked.  In any case, most of the pages have no struct page in which to so
+   mark the page.  Because of this, get_user_pages() will fail for these VMAs,
+   so there is no sense in attempting to visit them.
+
+2) VMAs mapping hugetlbfs page are already effectively pinned into memory.  We
+   neither need nor want to mlock() these pages.  However, to preserve the
+   prior behavior of mlock() - before the unevictable/mlock changes -
+   mlock_fixup() will call make_pages_present() in the hugetlbfs VMA range to
+   allocate the huge pages and populate the ptes.
+
+3) VMAs with VM_DONTEXPAND or VM_RESERVED are generally userspace mappings of
+   kernel pages, such as the VDSO page, relay channel pages, etc.  These pages
    are inherently unevictable and are not managed on the LRU lists.
-   mlock_fixup() treats these vmas the same as hugetlbfs vmas.  It calls
+   mlock_fixup() treats these VMAs the same as hugetlbfs VMAs.  It calls
    make_pages_present() to populate the ptes.
 
-Note that for all of these special vmas, mlock_fixup() does not set the
+Note that for all of these special VMAs, mlock_fixup() does not set the
 VM_LOCKED flag.  Therefore, we won't have to deal with them later during
-munlock() or munmap()--for example, at task exit.  Neither does mlock_fixup()
-account these vmas against the task's "locked_vm".
-
-Mlocked Pages:  Downgrading the Mmap Semaphore.
-
-mlock_fixup() must be called with the mmap semaphore held for write, because
-it may have to merge or split vmas.  However, mlocking a large region of
-memory can take a long time--especially if vmscan must reclaim pages to
-satisfy the regions requirements.  Faulting in a large region with the mmap
-semaphore held for write can hold off other faults on the address space, in
-the case of a multi-threaded task.  It can also hold off scans of the task's
-address space via /proc.  While testing under heavy load, it was observed that
-the ps(1) command could be held off for many minutes while a large segment was
-mlock()ed down.
-
-To address this issue, and to make the system more responsive during mlock()ing
-of large segments, mlock_fixup() downgrades the mmap semaphore to read mode
-during the call to __mlock_vma_pages_range().  This works fine.  However, the
-callers of mlock_fixup() expect the semaphore to be returned in write mode.
-So, mlock_fixup() "upgrades" the semphore to write mode.  Linux does not
-support an atomic upgrade_sem() call, so mlock_fixup() must drop the semaphore
-and reacquire it in write mode.  In a multi-threaded task, it is possible for
-the task memory map to change while the semaphore is dropped.  Therefore,
-mlock_fixup() looks up the vma at the range start address after reacquiring
-the semaphore in write mode and verifies that it still covers the original
-range.  If not, mlock_fixup() returns an error [-EAGAIN].  All callers of
-mlock_fixup() have been changed to deal with this new error condition.
-
-Note:  when munlocking a region, all of the pages should already be resident--
-unless we have racing threads mlocking() and munlocking() regions.  So,
-unlocking should not have to wait for page allocations nor faults  of any kind.
-Therefore mlock_fixup() does not downgrade the semaphore for munlock().
-
-
-Mlocked Pages:  munlock()/munlockall() System Call Handling
-
-The munlock() and munlockall() system calls are handled by the same functions--
-do_mlock[all]()--as the mlock() and mlockall() system calls with the unlock
-vs lock operation indicated by an argument.  So, these system calls are also
-handled by mlock_fixup().  Again, if called for an already munlock()ed vma,
-mlock_fixup() simply returns.  Because of the vma filtering discussed above,
-VM_LOCKED will not be set in any "special" vmas.  So, these vmas will be
+munlock(), munmap() or task exit.  Neither does mlock_fixup() account these
+VMAs against the task's "locked_vm".
+
+
+munlock()/munlockall() SYSTEM CALL HANDLING
+-------------------------------------------
+
+The munlock() and munlockall() system calls are handled by the same functions -
+do_mlock[all]() - as the mlock() and mlockall() system calls with the unlock vs
+lock operation indicated by an argument.  So, these system calls are also
+handled by mlock_fixup().  Again, if called for an already munlocked VMA,
+mlock_fixup() simply returns.  Because of the VMA filtering discussed above,
+VM_LOCKED will not be set in any "special" VMAs.  So, these VMAs will be
 ignored for munlock.
 
-If the vma is VM_LOCKED, mlock_fixup() again attempts to merge or split off
-the specified range.  The range is then munlocked via the function
-__mlock_vma_pages_range()--the same function used to mlock a vma range--
+If the VMA is VM_LOCKED, mlock_fixup() again attempts to merge or split off the
+specified range.  The range is then munlocked via the function
+__mlock_vma_pages_range() - the same function used to mlock a VMA range -
 passing a flag to indicate that munlock() is being performed.
 
-Because the vma access protections could have been changed to PROT_NONE after
+Because the VMA access protections could have been changed to PROT_NONE after
 faulting in and mlocking pages, get_user_pages() was unreliable for visiting
-these pages for munlocking.  Because we don't want to leave pages mlocked(),
+these pages for munlocking.  Because we don't want to leave pages mlocked,
 get_user_pages() was enhanced to accept a flag to ignore the permissions when
-fetching the pages--all of which should be resident as a result of previous
-mlock()ing.
+fetching the pages - all of which should be resident as a result of previous
+mlocking.
 
 For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling
 munlock_vma_page().  munlock_vma_page() unconditionally clears the PG_mlocked
-flag using TestClearPageMlocked().  As with mlock_vma_page(), munlock_vma_page()
-use the Test*PageMlocked() function to handle the case where the page might
-have already been unlocked by another task.  If the page was mlocked,
-munlock_vma_page() updates that zone statistics for the number of mlocked
-pages.  Note, however, that at this point we haven't checked whether the page
-is mapped by other VM_LOCKED vmas.
-
-We can't call try_to_munlock(), the function that walks the reverse map to check
-for other VM_LOCKED vmas, without first isolating the page from the LRU.
+flag using TestClearPageMlocked().  As with mlock_vma_page(),
+munlock_vma_page() use the Test*PageMlocked() function to handle the case where
+the page might have already been unlocked by another task.  If the page was
+mlocked, munlock_vma_page() updates that zone statistics for the number of
+mlocked pages.  Note, however, that at this point we haven't checked whether
+the page is mapped by other VM_LOCKED VMAs.
+
+We can't call try_to_munlock(), the function that walks the reverse map to
+check for other VM_LOCKED VMAs, without first isolating the page from the LRU.
 try_to_munlock() is a variant of try_to_unmap() and thus requires that the page
-not be on an lru list.  [More on these below.]  However, the call to
-isolate_lru_page() could fail, in which case we couldn't try_to_munlock().
-So, we go ahead and clear PG_mlocked up front, as this might be the only chance
-we have.  If we can successfully isolate the page, we go ahead and
+not be on an LRU list [more on these below].  However, the call to
+isolate_lru_page() could fail, in which case we couldn't try_to_munlock().  So,
+we go ahead and clear PG_mlocked up front, as this might be the only chance we
+have.  If we can successfully isolate the page, we go ahead and
 try_to_munlock(), which will restore the PG_mlocked flag and update the zone
-page statistics if it finds another vma holding the page mlocked.  If we fail
+page statistics if it finds another VMA holding the page mlocked.  If we fail
 to isolate the page, we'll have left a potentially mlocked page on the LRU.
-This is fine, because we'll catch it later when/if vmscan tries to reclaim the
-page.  This should be relatively rare.
-
-Mlocked Pages:  Migrating Them...
-
-A page that is being migrated has been isolated from the lru lists and is
-held locked across unmapping of the page, updating the page's mapping
-[address_space] entry and copying the contents and state, until the
-page table entry has been replaced with an entry that refers to the new
-page.  Linux supports migration of mlocked pages and other unevictable
-pages.  This involves simply moving the PageMlocked and PageUnevictable states
-from the old page to the new page.
-
-Note that page migration can race with mlocking or munlocking of the same
-page.  This has been discussed from the mlock/munlock perspective in the
-respective sections above.  Both processes [migration, m[un]locking], hold
-the page locked.  This provides the first level of synchronization.  Page
-migration zeros out the page_mapping of the old page before unlocking it,
-so m[un]lock can skip these pages by testing the page mapping under page
-lock.
-
-When completing page migration, we place the new and old pages back onto the
-lru after dropping the page lock.  The "unneeded" page--old page on success,
-new page on failure--will be freed when the reference count held by the
-migration process is released.  To ensure that we don't strand pages on the
-unevictable list because of a race between munlock and migration, page
-migration uses the putback_lru_page() function to add migrated pages back to
-the lru.
-
-
-Mlocked Pages:  mmap(MAP_LOCKED) System Call Handling
+This is fine, because we'll catch it later if and if vmscan tries to reclaim
+the page.  This should be relatively rare.
+
+
+MIGRATING MLOCKED PAGES
+-----------------------
+
+A page that is being migrated has been isolated from the LRU lists and is held
+locked across unmapping of the page, updating the page's address space entry
+and copying the contents and state, until the page table entry has been
+replaced with an entry that refers to the new page.  Linux supports migration
+of mlocked pages and other unevictable pages.  This involves simply moving the
+PG_mlocked and PG_unevictable states from the old page to the new page.
+
+Note that page migration can race with mlocking or munlocking of the same page.
+This has been discussed from the mlock/munlock perspective in the respective
+sections above.  Both processes (migration and m[un]locking) hold the page
+locked.  This provides the first level of synchronization.  Page migration
+zeros out the page_mapping of the old page before unlocking it, so m[un]lock
+can skip these pages by testing the page mapping under page lock.
+
+To complete page migration, we place the new and old pages back onto the LRU
+after dropping the page lock.  The "unneeded" page - old page on success, new
+page on failure - will be freed when the reference count held by the migration
+process is released.  To ensure that we don't strand pages on the unevictable
+list because of a race between munlock and migration, page migration uses the
+putback_lru_page() function to add migrated pages back to the LRU.
+
+
+mmap(MAP_LOCKED) SYSTEM CALL HANDLING
+-------------------------------------
 
 In addition the the mlock()/mlockall() system calls, an application can request
-that a region of memory be mlocked using the MAP_LOCKED flag with the mmap()
+that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap()
 call.  Furthermore, any mmap() call or brk() call that expands the heap by a
 task that has previously called mlockall() with the MCL_FUTURE flag will result
-in the newly mapped memory being mlocked.  Before the unevictable/mlock changes,
-the kernel simply called make_pages_present() to allocate pages and populate
-the page table.
+in the newly mapped memory being mlocked.  Before the unevictable/mlock
+changes, the kernel simply called make_pages_present() to allocate pages and
+populate the page table.
 
 To mlock a range of memory under the unevictable/mlock infrastructure, the
 mmap() handler and task address space expansion functions call
 mlock_vma_pages_range() specifying the vma and the address range to mlock.
-mlock_vma_pages_range() filters vmas like mlock_fixup(), as described above in
-"Mlocked Pages:  Filtering Vmas".  It will clear the VM_LOCKED flag, which will
-have already been set by the caller, in filtered vmas.  Thus these vma's need
-not be visited for munlock when the region is unmapped.
+mlock_vma_pages_range() filters VMAs like mlock_fixup(), as described above in
+"Filtering Special VMAs".  It will clear the VM_LOCKED flag, which will have
+already been set by the caller, in filtered VMAs.  Thus these VMA's need not be
+visited for munlock when the region is unmapped.
 
-For "normal" vmas, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
+For "normal" VMAs, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
 fault/allocate the pages and mlock them.  Again, like mlock_fixup(),
 mlock_vma_pages_range() downgrades the mmap semaphore to read mode before
-attempting to fault/allocate and mlock the pages; and "upgrades" the semaphore
+attempting to fault/allocate and mlock the pages and "upgrades" the semaphore
 back to write mode before returning.
 
-The callers of mlock_vma_pages_range() will have already added the memory
-range to be mlocked to the task's "locked_vm".  To account for filtered vmas,
+The callers of mlock_vma_pages_range() will have already added the memory range
+to be mlocked to the task's "locked_vm".  To account for filtered VMAs,
 mlock_vma_pages_range() returns the number of pages NOT mlocked.  All of the
-callers then subtract a non-negative return value from the task's locked_vm.
-A negative return value represent an error--for example, from get_user_pages()
-attempting to fault in a vma with PROT_NONE access.  In this case, we leave
-the memory range accounted as locked_vm, as the protections could be changed
-later and pages allocated into that region.
+callers then subtract a non-negative return value from the task's locked_vm.  A
+negative return value represent an error - for example, from get_user_pages()
+attempting to fault in a VMA with PROT_NONE access.  In this case, we leave the
+memory range accounted as locked_vm, as the protections could be changed later
+and pages allocated into that region.
 
 
-Mlocked Pages:  munmap()/exit()/exec() System Call Handling
+munmap()/exit()/exec() SYSTEM CALL HANDLING
+-------------------------------------------
 
 When unmapping an mlocked region of memory, whether by an explicit call to
 munmap() or via an internal unmap from exit() or exec() processing, we must
-munlock the pages if we're removing the last VM_LOCKED vma that maps the pages.
+munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages.
 Before the unevictable/mlock changes, mlocking did not mark the pages in any
 way, so unmapping them required no processing.
 
 To munlock a range of memory under the unevictable/mlock infrastructure, the
-munmap() hander and task address space tear down function call
+munmap() handler and task address space call tear down function
 munlock_vma_pages_all().  The name reflects the observation that one always
-specifies the entire vma range when munlock()ing during unmap of a region.
-Because of the vma filtering when mlocking() regions, only "normal" vmas that
+specifies the entire VMA range when munlock()ing during unmap of a region.
+Because of the VMA filtering when mlocking() regions, only "normal" VMAs that
 actually contain mlocked pages will be passed to munlock_vma_pages_all().
 
-munlock_vma_pages_all() clears the VM_LOCKED vma flag and, like mlock_fixup()
+munlock_vma_pages_all() clears the VM_LOCKED VMA flag and, like mlock_fixup()
 for the munlock case, calls __munlock_vma_pages_range() to walk the page table
-for the vma's memory range and munlock_vma_page() each resident page mapped by
-the vma.  This effectively munlocks the page, only if this is the last
-VM_LOCKED vma that maps the page.
-
+for the VMA's memory range and munlock_vma_page() each resident page mapped by
+the VMA.  This effectively munlocks the page, only if this is the last
+VM_LOCKED VMA that maps the page.
 
-Mlocked Page:  try_to_unmap()
 
-[Note:  the code changes represented by this section are really quite small
-compared to the text to describe what happening and why, and to discuss the
-implications.]
+try_to_unmap()
+--------------
 
-Pages can, of course, be mapped into multiple vmas.  Some of these vmas may
+Pages can, of course, be mapped into multiple VMAs.  Some of these VMAs may
 have VM_LOCKED flag set.  It is possible for a page mapped into one or more
-VM_LOCKED vmas not to have the PG_mlocked flag set and therefore reside on one
-of the active or inactive LRU lists.  This could happen if, for example, a
-task in the process of munlock()ing the page could not isolate the page from
-the LRU.  As a result, vmscan/shrink_page_list() might encounter such a page
-as described in "Unevictable Pages and Vmscan [shrink_*_list()]".  To
-handle this situation, try_to_unmap() has been enhanced to check for VM_LOCKED
-vmas while it is walking a page's reverse map.
+VM_LOCKED VMAs not to have the PG_mlocked flag set and therefore reside on one
+of the active or inactive LRU lists.  This could happen if, for example, a task
+in the process of munlocking the page could not isolate the page from the LRU.
+As a result, vmscan/shrink_page_list() might encounter such a page as described
+in section "vmscan's handling of unevictable pages".  To handle this situation,
+try_to_unmap() checks for VM_LOCKED VMAs while it is walking a page's reverse
+map.
 
 try_to_unmap() is always called, by either vmscan for reclaim or for page
-migration, with the argument page locked and isolated from the LRU.  BUG_ON()
-assertions enforce this requirement.  Separate functions handle anonymous and
-mapped file pages, as these types of pages have different reverse map
-mechanisms.
-
-        try_to_unmap_anon()
-
-To unmap anonymous pages, each vma in the list anchored in the anon_vma must be
-visited--at least until a VM_LOCKED vma is encountered.  If the page is being
-unmapped for migration, VM_LOCKED vmas do not stop the process because mlocked
-pages are migratable.  However, for reclaim, if the page is mapped into a
-VM_LOCKED vma, the scan stops.  try_to_unmap() attempts to acquire the mmap
-semphore of the mm_struct to which the vma belongs in read mode.  If this is
-successful, try_to_unmap() will mlock the page via mlock_vma_page()--we
-wouldn't have gotten to try_to_unmap() if the page were already mlocked--and
-will return SWAP_MLOCK, indicating that the page is unevictable.  If the
-mmap semaphore cannot be acquired, we are not sure whether the page is really
-unevictable or not.  In this case, try_to_unmap() will return SWAP_AGAIN.
-
-        try_to_unmap_file() -- linear mappings
-
-Unmapping of a mapped file page works the same, except that the scan visits
-all vmas that maps the page's index/page offset in the page's mapping's
-reverse map priority search tree.  It must also visit each vma in the page's
-mapping's non-linear list, if the list is non-empty.  As for anonymous pages,
-on encountering a VM_LOCKED vma for a mapped file page, try_to_unmap() will
-attempt to acquire the associated mm_struct's mmap semaphore to mlock the page,
-returning SWAP_MLOCK if this is successful, and SWAP_AGAIN, if not.
-
-        try_to_unmap_file() -- non-linear mappings
-
-If a page's mapping contains a non-empty non-linear mapping vma list, then
-try_to_un{map|lock}() must also visit each vma in that list to determine
-whether the page is mapped in a VM_LOCKED vma.  Again, the scan must visit
-all vmas in the non-linear list to ensure that the pages is not/should not be
-mlocked.  If a VM_LOCKED vma is found in the list, the scan could terminate.
-However, there is no easy way to determine whether the page is actually mapped
-in a given vma--either for unmapping or testing whether the VM_LOCKED vma
-actually pins the page.
-
-So, try_to_unmap_file() handles non-linear mappings by scanning a certain
-number of pages--a "cluster"--in each non-linear vma associated with the page's
-mapping, for each file mapped page that vmscan tries to unmap.  If this happens
-to unmap the page we're trying to unmap, try_to_unmap() will notice this on
-return--(page_mapcount(page) == 0)--and return SWAP_SUCCESS.  Otherwise, it
-will return SWAP_AGAIN, causing vmscan to recirculate this page.  We take
-advantage of the cluster scan in try_to_unmap_cluster() as follows:
-
-For each non-linear vma, try_to_unmap_cluster() attempts to acquire the mmap
-semaphore of the associated mm_struct for read without blocking.  If this
-attempt is successful and the vma is VM_LOCKED, try_to_unmap_cluster() will
-retain the mmap semaphore for the scan; otherwise it drops it here.  Then,
-for each page in the cluster, if we're holding the mmap semaphore for a locked
-vma, try_to_unmap_cluster() calls mlock_vma_page() to mlock the page.  This
-call is a no-op if the page is already locked, but will mlock any pages in
-the non-linear mapping that happen to be unlocked.  If one of the pages so
-mlocked is the page passed in to try_to_unmap(), try_to_unmap_cluster() will
-return SWAP_MLOCK, rather than the default SWAP_AGAIN.  This will allow vmscan
-to cull the page, rather than recirculating it on the inactive list.  Again,
-if try_to_unmap_cluster() cannot acquire the vma's mmap sem, it returns
-SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED vma, but
-couldn't be mlocked.
-
-
-Mlocked pages:  try_to_munlock() Reverse Map Scan
-
-TODO/FIXME:  a better name might be page_mlocked()--analogous to the
-page_referenced() reverse map walker.
-
-When munlock_vma_page()--see "Mlocked Pages:  munlock()/munlockall()
-System Call Handling" above--tries to munlock a page, it needs to
-determine whether or not the page is mapped by any VM_LOCKED vma, without
-actually attempting to unmap all ptes from the page.  For this purpose, the
-unevictable/mlock infrastructure introduced a variant of try_to_unmap() called
-try_to_munlock().
+migration, with the argument page locked and isolated from the LRU.  Separate
+functions handle anonymous and mapped file pages, as these types of pages have
+different reverse map mechanisms.
+
+ (*) try_to_unmap_anon()
+
+     To unmap anonymous pages, each VMA in the list anchored in the anon_vma
+     must be visited - at least until a VM_LOCKED VMA is encountered.  If the
+     page is being unmapped for migration, VM_LOCKED VMAs do not stop the
+     process because mlocked pages are migratable.  However, for reclaim, if
+     the page is mapped into a VM_LOCKED VMA, the scan stops.
+
+     try_to_unmap_anon() attempts to acquire in read mode the mmap semphore of
+     the mm_struct to which the VMA belongs.  If this is successful, it will
+     mlock the page via mlock_vma_page() - we wouldn't have gotten to
+     try_to_unmap_anon() if the page were already mlocked - and will return
+     SWAP_MLOCK, indicating that the page is unevictable.
+
+     If the mmap semaphore cannot be acquired, we are not sure whether the page
+     is really unevictable or not.  In this case, try_to_unmap_anon() will
+     return SWAP_AGAIN.
+
+ (*) try_to_unmap_file() - linear mappings
+
+     Unmapping of a mapped file page works the same as for anonymous mappings,
+     except that the scan visits all VMAs that map the page's index/page offset
+     in the page's mapping's reverse map priority search tree.  It also visits
+     each VMA in the page's mapping's non-linear list, if the list is
+     non-empty.
+
+     As for anonymous pages, on encountering a VM_LOCKED VMA for a mapped file
+     page, try_to_unmap_file() will attempt to acquire the associated
+     mm_struct's mmap semaphore to mlock the page, returning SWAP_MLOCK if this
+     is successful, and SWAP_AGAIN, if not.
+
+ (*) try_to_unmap_file() - non-linear mappings
+
+     If a page's mapping contains a non-empty non-linear mapping VMA list, then
+     try_to_un{map|lock}() must also visit each VMA in that list to determine
+     whether the page is mapped in a VM_LOCKED VMA.  Again, the scan must visit
+     all VMAs in the non-linear list to ensure that the pages is not/should not
+     be mlocked.
+
+     If a VM_LOCKED VMA is found in the list, the scan could terminate.
+     However, there is no easy way to determine whether the page is actually
+     mapped in a given VMA - either for unmapping or testing whether the
+     VM_LOCKED VMA actually pins the page.
+
+     try_to_unmap_file() handles non-linear mappings by scanning a certain
+     number of pages - a "cluster" - in each non-linear VMA associated with the
+     page's mapping, for each file mapped page that vmscan tries to unmap.  If
+     this happens to unmap the page we're trying to unmap, try_to_unmap() will
+     notice this on return (page_mapcount(page) will be 0) and return
+     SWAP_SUCCESS.  Otherwise, it will return SWAP_AGAIN, causing vmscan to
+     recirculate this page.  We take advantage of the cluster scan in
+     try_to_unmap_cluster() as follows:
+
+        For each non-linear VMA, try_to_unmap_cluster() attempts to acquire the
+        mmap semaphore of the associated mm_struct for read without blocking.
+
+        If this attempt is successful and the VMA is VM_LOCKED,
+        try_to_unmap_cluster() will retain the mmap semaphore for the scan;
+        otherwise it drops it here.
+
+        Then, for each page in the cluster, if we're holding the mmap semaphore
+        for a locked VMA, try_to_unmap_cluster() calls mlock_vma_page() to
+        mlock the page.  This call is a no-op if the page is already locked,
+        but will mlock any pages in the non-linear mapping that happen to be
+        unlocked.
+
+        If one of the pages so mlocked is the page passed in to try_to_unmap(),
+        try_to_unmap_cluster() will return SWAP_MLOCK, rather than the default
+        SWAP_AGAIN.  This will allow vmscan to cull the page, rather than
+        recirculating it on the inactive list.
+
+        Again, if try_to_unmap_cluster() cannot acquire the VMA's mmap sem, it
+        returns SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED
+        VMA, but couldn't be mlocked.
+
+
+try_to_munlock() REVERSE MAP SCAN
+---------------------------------
+
+ [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
+     page_referenced() reverse map walker.
+
+When munlock_vma_page() [see section "munlock()/munlockall() System Call
+Handling" above] tries to munlock a page, it needs to determine whether or not
+the page is mapped by any VM_LOCKED VMA without actually attempting to unmap
+all PTEs from the page.  For this purpose, the unevictable/mlock infrastructure
+introduced a variant of try_to_unmap() called try_to_munlock().
 
 try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
 mapped file pages with an additional argument specifing unlock versus unmap
 processing.  Again, these functions walk the respective reverse maps looking
-for VM_LOCKED vmas.  When such a vma is found for anonymous pages and file
+for VM_LOCKED VMAs.  When such a VMA is found for anonymous pages and file
 pages mapped in linear VMAs, as in the try_to_unmap() case, the functions
 attempt to acquire the associated mmap semphore, mlock the page via
 mlock_vma_page() and return SWAP_MLOCK.  This effectively undoes the
 pre-clearing of the page's PG_mlocked done by munlock_vma_page.
 
-If try_to_unmap() is unable to acquire a VM_LOCKED vma's associated mmap
-semaphore, it will return SWAP_AGAIN.  This will allow shrink_page_list()
-to recycle the page on the inactive list and hope that it has better luck
-with the page next time.
-
-For file pages mapped into non-linear vmas, the try_to_munlock() logic works
-slightly differently.  On encountering a VM_LOCKED non-linear vma that might
-map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking
-the page.  munlock_vma_page() will just leave the page unlocked and let
-vmscan deal with it--the usual fallback position.
-
-Note that try_to_munlock()'s reverse map walk must visit every vma in a pages'
-reverse map to determine that a page is NOT mapped into any VM_LOCKED vma.
-However, the scan can terminate when it encounters a VM_LOCKED vma and can
-successfully acquire the vma's mmap semphore for read and mlock the page.
-Although try_to_munlock() can be called many [very many!] times when
-munlock()ing a large region or tearing down a large address space that has been
-mlocked via mlockall(), overall this is a fairly rare event.
-
-Mlocked Page:  Page Reclaim in shrink_*_list()
-
-shrink_active_list() culls any obviously unevictable pages--i.e.,
-!page_evictable(page, NULL)--diverting these to the unevictable lru
-list.  However, shrink_active_list() only sees unevictable pages that
-made it onto the active/inactive lru lists.  Note that these pages do not
-have PageUnevictable set--otherwise, they would be on the unevictable list and
-shrink_active_list would never see them.
+If try_to_unmap() is unable to acquire a VM_LOCKED VMA's associated mmap
+semaphore, it will return SWAP_AGAIN.  This will allow shrink_page_list() to
+recycle the page on the inactive list and hope that it has better luck with the
+page next time.
+
+For file pages mapped into non-linear VMAs, the try_to_munlock() logic works
+slightly differently.  On encountering a VM_LOCKED non-linear VMA that might
+map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking the
+page.  munlock_vma_page() will just leave the page unlocked and let vmscan deal
+with it - the usual fallback position.
+
+Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's
+reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA.
+However, the scan can terminate when it encounters a VM_LOCKED VMA and can
+successfully acquire the VMA's mmap semphore for read and mlock the page.
+Although try_to_munlock() might be called a great many times when munlocking a
+large region or tearing down a large address space that has been mlocked via
+mlockall(), overall this is a fairly rare event.
+
+
+PAGE RECLAIM IN shrink_*_list()
+-------------------------------
+
+shrink_active_list() culls any obviously unevictable pages - i.e.
+!page_evictable(page, NULL) - diverting these to the unevictable list.
+However, shrink_active_list() only sees unevictable pages that made it onto the
+active/inactive lru lists.  Note that these pages do not have PageUnevictable
+set - otherwise they would be on the unevictable list and shrink_active_list
+would never see them.
 
 Some examples of these unevictable pages on the LRU lists are:
 
-1) ramfs pages that have been placed on the lru lists when first allocated.
+ (1) ramfs pages that have been placed on the LRU lists when first allocated.
+
+ (2) SHM_LOCK'd shared memory pages.  shmctl(SHM_LOCK) does not attempt to
+     allocate or fault in the pages in the shared memory region.  This happens
+     when an application accesses the page the first time after SHM_LOCK'ing
+     the segment.
 
-2) SHM_LOCKed shared memory pages.  shmctl(SHM_LOCK) does not attempt to
-   allocate or fault in the pages in the shared memory region.  This happens
-   when an application accesses the page the first time after SHM_LOCKing
-   the segment.
+ (3) mlocked pages that could not be isolated from the LRU and moved to the
+     unevictable list in mlock_vma_page().
 
-3) Mlocked pages that could not be isolated from the lru and moved to the
-   unevictable list in mlock_vma_page().
+ (4) Pages mapped into multiple VM_LOCKED VMAs, but try_to_munlock() couldn't
+     acquire the VMA's mmap semaphore to test the flags and set PageMlocked.
+     munlock_vma_page() was forced to let the page back on to the normal LRU
+     list for vmscan to handle.
 
-3) Pages mapped into multiple VM_LOCKED vmas, but try_to_munlock() couldn't
-   acquire the vma's mmap semaphore to test the flags and set PageMlocked.
-   munlock_vma_page() was forced to let the page back on to the normal
-   LRU list for vmscan to handle.
+shrink_inactive_list() also diverts any unevictable pages that it finds on the
+inactive lists to the appropriate zone's unevictable list.
 
-shrink_inactive_list() also culls any unevictable pages that it finds on
-the inactive lists, again diverting them to the appropriate zone's unevictable
-lru list.  shrink_inactive_list() should only see SHM_LOCKed pages that became
-SHM_LOCKed after shrink_active_list() had moved them to the inactive list, or
-pages mapped into VM_LOCKED vmas that munlock_vma_page() couldn't isolate from
-the lru to recheck via try_to_munlock().  shrink_inactive_list() won't notice
-the latter, but will pass on to shrink_page_list().
+shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd
+after shrink_active_list() had moved them to the inactive list, or pages mapped
+into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to
+recheck via try_to_munlock().  shrink_inactive_list() won't notice the latter,
+but will pass on to shrink_page_list().
 
 shrink_page_list() again culls obviously unevictable pages that it could
 encounter for similar reason to shrink_inactive_list().  Pages mapped into
-VM_LOCKED vmas but without PG_mlocked set will make it all the way to
+VM_LOCKED VMAs but without PG_mlocked set will make it all the way to
 try_to_unmap().  shrink_page_list() will divert them to the unevictable list
 when try_to_unmap() returns SWAP_MLOCK, as discussed above.