24 files changed, 635 insertions, 536 deletions

diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index b462bb149543..52441694fe03 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -170,16 +170,15 @@ Returns: 0 if successful and a negative error if not.
 u64
 dma_get_required_mask(struct device *dev)
 
-After setting the mask with dma_set_mask(), this API returns the
-actual mask (within that already set) that the platform actually
-requires to operate efficiently.  Usually this means the returned mask
+This API returns the mask that the platform requires to
+operate efficiently.  Usually this means the returned mask
 is the minimum required to cover all of memory.  Examining the
 required mask gives drivers with variable descriptor sizes the
 opportunity to use smaller descriptors as necessary.
 
 Requesting the required mask does not alter the current mask.  If you
-wish to take advantage of it, you should issue another dma_set_mask()
-call to lower the mask again.
+wish to take advantage of it, you should issue a dma_set_mask()
+call to set the mask to the value returned.
 
 
 Part Id - Streaming DMA mappings
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index cc49400b4af8..7ea231172c85 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -392,6 +392,10 @@ int main(int argc, char *argv[])
                         goto err;
                 }
         }
+        if (!maskset && !tid && !containerset) {
+                usage();
+                goto err;
+        }
 
         do {
                 int i;
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index e33ee74eee77..d9e5d6f41b92 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -1,7 +1,8 @@
                                 CGROUPS
                                 -------
 
-Written by Paul Menage <menage@google.com> based on Documentation/cpusets.txt
+Written by Paul Menage <menage@google.com> based on
+Documentation/cgroups/cpusets.txt
 
 Original copyright statements from cpusets.txt:
 Portions Copyright (C) 2004 BULL SA.
@@ -68,7 +69,7 @@ On their own, the only use for cgroups is for simple job
 tracking. The intention is that other subsystems hook into the generic
 cgroup support to provide new attributes for cgroups, such as
 accounting/limiting the resources which processes in a cgroup can
-access. For example, cpusets (see Documentation/cpusets.txt) allows
+access. For example, cpusets (see Documentation/cgroups/cpusets.txt) allows
 you to associate a set of CPUs and a set of memory nodes with the
 tasks in each cgroup.
 
diff --git a/Documentation/controllers/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index bb775fbe43d7..bb775fbe43d7 100644
--- a/Documentation/controllers/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
diff --git a/Documentation/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 5c86c258c791..5c86c258c791 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
diff --git a/Documentation/controllers/devices.txt b/Documentation/cgroups/devices.txt
index 7cc6e6a60672..7cc6e6a60672 100644
--- a/Documentation/controllers/devices.txt
+++ b/Documentation/cgroups/devices.txt
diff --git a/Documentation/controllers/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 08d4d3ea0d79..19533f93b7a2 100644
--- a/Documentation/controllers/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -6,7 +6,7 @@ Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
 Please note that implementation details can be changed.
 
-(*) Topics on API should be in Documentation/controllers/memory.txt)
+(*) Topics on API should be in Documentation/cgroups/memory.txt)
 
 0. How to record usage ?
    2 objects are used.
diff --git a/Documentation/controllers/memory.txt b/Documentation/cgroups/memory.txt
index e1501964df1e..e1501964df1e 100644
--- a/Documentation/controllers/memory.txt
+++ b/Documentation/cgroups/memory.txt
diff --git a/Documentation/controllers/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index f196ac1d7d25..f196ac1d7d25 100644
--- a/Documentation/controllers/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 45932ec21cee..b41f3e58aefa 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -18,11 +18,11 @@ For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
-#define topology_thread_siblings(cpu)
-#define topology_core_siblings(cpu)
+#define topology_thread_cpumask(cpu)
+#define topology_core_cpumask(cpu)
 
 The type of **_id is int.
-The type of siblings is cpumask_t.
+The type of siblings is (const) struct cpumask *.
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index 44bd766f2e5d..85eaeaddd27c 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -251,7 +251,7 @@ NFS/RDMA Setup
 
     Instruct the server to listen on the RDMA transport:
 
-    $ echo rdma 2050 > /proc/fs/nfsd/portlist
+    $ echo rdma 20049 > /proc/fs/nfsd/portlist
 
   - On the client system
 
@@ -263,7 +263,7 @@ NFS/RDMA Setup
     Regardless of how the client was built (module or built-in), use this
     command to mount the NFS/RDMA server:
 
-    $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt
+    $ mount -o rdma,port=20049 <IPoIB-server-name-or-address>:/<export> /mnt
 
     To verify that the mount is using RDMA, run "cat /proc/mounts" and check
     the "proto" field for the given mount.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index d105eb45282a..bbebc3a43ac0 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1371,292 +1371,8 @@ auto_msgmni default value is 1.
 2.4 /proc/sys/vm - The virtual memory subsystem
 -----------------------------------------------
 
-The files  in  this directory can be used to tune the operation of the virtual
-memory (VM)  subsystem  of  the  Linux  kernel.
-
-vfs_cache_pressure
-------------------
-
-Controls the tendency of the kernel to reclaim the memory which is used for
-caching of directory and inode objects.
-
-At the default value of vfs_cache_pressure=100 the kernel will attempt to
-reclaim dentries and inodes at a "fair" rate with respect to pagecache and
-swapcache reclaim.  Decreasing vfs_cache_pressure causes the kernel to prefer
-to retain dentry and inode caches.  Increasing vfs_cache_pressure beyond 100
-causes the kernel to prefer to reclaim dentries and inodes.
-
-dirty_background_bytes
-----------------------
-
-Contains the amount of dirty memory at which the pdflush background writeback
-daemon will start writeback.
-
-If dirty_background_bytes is written, dirty_background_ratio becomes a function
-of its value (dirty_background_bytes / the amount of dirtyable system memory).
-
-dirty_background_ratio
-----------------------
-
-Contains, as a percentage of the dirtyable system memory (free pages + mapped
-pages + file cache, not including locked pages and HugePages), the number of
-pages at which the pdflush background writeback daemon will start writing out
-dirty data.
-
-If dirty_background_ratio is written, dirty_background_bytes becomes a function
-of its value (dirty_background_ratio * the amount of dirtyable system memory).
-
-dirty_bytes
------------
-
-Contains the amount of dirty memory at which a process generating disk writes
-will itself start writeback.
-
-If dirty_bytes is written, dirty_ratio becomes a function of its value
-(dirty_bytes / the amount of dirtyable system memory).
-
-dirty_ratio
------------
-
-Contains, as a percentage of the dirtyable system memory (free pages + mapped
-pages + file cache, not including locked pages and HugePages), the number of
-pages at which a process which is generating disk writes will itself start
-writing out dirty data.
-
-If dirty_ratio is written, dirty_bytes becomes a function of its value
-(dirty_ratio * the amount of dirtyable system memory).
-
-dirty_writeback_centisecs
--------------------------
-
-The pdflush writeback daemons will periodically wake up and write `old' data
-out to disk.  This tunable expresses the interval between those wakeups, in
-100'ths of a second.
-
-Setting this to zero disables periodic writeback altogether.
-
-dirty_expire_centisecs
-----------------------
-
-This tunable is used to define when dirty data is old enough to be eligible
-for writeout by the pdflush daemons.  It is expressed in 100'ths of a second. 
-Data which has been dirty in-memory for longer than this interval will be
-written out next time a pdflush daemon wakes up.
-
-highmem_is_dirtyable
---------------------
-
-Only present if CONFIG_HIGHMEM is set.
-
-This defaults to 0 (false), meaning that the ratios set above are calculated
-as a percentage of lowmem only.  This protects against excessive scanning
-in page reclaim, swapping and general VM distress.
-
-Setting this to 1 can be useful on 32 bit machines where you want to make
-random changes within an MMAPed file that is larger than your available
-lowmem without causing large quantities of random IO.  Is is safe if the
-behavior of all programs running on the machine is known and memory will
-not be otherwise stressed.
-
-legacy_va_layout
-----------------
-
-If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
-will use the legacy (2.4) layout for all processes.
-
-lowmem_reserve_ratio
----------------------
-
-For some specialised workloads on highmem machines it is dangerous for
-the kernel to allow process memory to be allocated from the "lowmem"
-zone.  This is because that memory could then be pinned via the mlock()
-system call, or by unavailability of swapspace.
-
-And on large highmem machines this lack of reclaimable lowmem memory
-can be fatal.
-
-So the Linux page allocator has a mechanism which prevents allocations
-which _could_ use highmem from using too much lowmem.  This means that
-a certain amount of lowmem is defended from the possibility of being
-captured into pinned user memory.
-
-(The same argument applies to the old 16 megabyte ISA DMA region.  This
-mechanism will also defend that region from allocations which could use
-highmem or lowmem).
-
-The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
-in defending these lower zones.
-
-If you have a machine which uses highmem or ISA DMA and your
-applications are using mlock(), or if you are running with no swap then
-you probably should change the lowmem_reserve_ratio setting.
-
-The lowmem_reserve_ratio is an array. You can see them by reading this file.
--
-% cat /proc/sys/vm/lowmem_reserve_ratio
-256     256     32
--
-Note: # of this elements is one fewer than number of zones. Because the highest
-      zone's value is not necessary for following calculation.
-
-But, these values are not used directly. The kernel calculates # of protection
-pages for each zones from them. These are shown as array of protection pages
-in /proc/zoneinfo like followings. (This is an example of x86-64 box).
-Each zone has an array of protection pages like this.
-
--
-Node 0, zone      DMA
-  pages free     1355
-        min      3
-        low      3
-        high     4
-        :
-        :
-    numa_other   0
-        protection: (0, 2004, 2004, 2004)
-        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-  pagesets
-    cpu: 0 pcp: 0
-        :
--
-These protections are added to score to judge whether this zone should be used
-for page allocation or should be reclaimed.
-
-In this example, if normal pages (index=2) are required to this DMA zone and
-pages_high is used for watermark, the kernel judges this zone should not be
-used because pages_free(1355) is smaller than watermark + protection[2]
-(4 + 2004 = 2008). If this protection value is 0, this zone would be used for
-normal page requirement. If requirement is DMA zone(index=0), protection[0]
-(=0) is used.
-
-zone[i]'s protection[j] is calculated by following expression.
-
-(i < j):
-  zone[i]->protection[j]
-  = (total sums of present_pages from zone[i+1] to zone[j] on the node)
-    / lowmem_reserve_ratio[i];
-(i = j):
-   (should not be protected. = 0;
-(i > j):
-   (not necessary, but looks 0)
-
-The default values of lowmem_reserve_ratio[i] are
-    256 (if zone[i] means DMA or DMA32 zone)
-    32  (others).
-As above expression, they are reciprocal number of ratio.
-256 means 1/256. # of protection pages becomes about "0.39%" of total present
-pages of higher zones on the node.
-
-If you would like to protect more pages, smaller values are effective.
-The minimum value is 1 (1/1 -> 100%).
-
-page-cluster
-------------
-
-page-cluster controls the number of pages which are written to swap in
-a single attempt.  The swap I/O size.
-
-It is a logarithmic value - setting it to zero means "1 page", setting
-it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
-
-The default value is three (eight pages at a time).  There may be some
-small benefits in tuning this to a different value if your workload is
-swap-intensive.
-
-overcommit_memory
------------------
-
-Controls overcommit of system memory, possibly allowing processes
-to allocate (but not use) more memory than is actually available.
-
-
-0       -       Heuristic overcommit handling. Obvious overcommits of
-                address space are refused. Used for a typical system. It
-                ensures a seriously wild allocation fails while allowing
-                overcommit to reduce swap usage.  root is allowed to
-                allocate slightly more memory in this mode. This is the
-                default.
-
-1       -       Always overcommit. Appropriate for some scientific
-                applications.
-
-2       -       Don't overcommit. The total address space commit
-                for the system is not permitted to exceed swap plus a
-                configurable percentage (default is 50) of physical RAM.
-                Depending on the percentage you use, in most situations
-                this means a process will not be killed while attempting
-                to use already-allocated memory but will receive errors
-                on memory allocation as appropriate.
-
-overcommit_ratio
-----------------
-
-Percentage of physical memory size to include in overcommit calculations
-(see above.)
-
-Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
-
-        swapspace = total size of all swap areas
-        physmem = size of physical memory in system
-
-nr_hugepages and hugetlb_shm_group
-----------------------------------
-
-nr_hugepages configures number of hugetlb page reserved for the system.
-
-hugetlb_shm_group contains group id that is allowed to create SysV shared
-memory segment using hugetlb page.
-
-hugepages_treat_as_movable
---------------------------
-
-This parameter is only useful when kernelcore= is specified at boot time to
-create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
-are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
-value written to hugepages_treat_as_movable allows huge pages to be allocated
-from ZONE_MOVABLE.
-
-Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
-pages pool can easily grow or shrink within. Assuming that applications are
-not running that mlock() a lot of memory, it is likely the huge pages pool
-can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
-into nr_hugepages and triggering page reclaim.
-
-laptop_mode
------------
-
-laptop_mode is a knob that controls "laptop mode". All the things that are
-controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
-
-block_dump
-----------
-
-block_dump enables block I/O debugging when set to a nonzero value. More
-information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
-
-swap_token_timeout
-------------------
-
-This file contains valid hold time of swap out protection token. The Linux
-VM has token based thrashing control mechanism and uses the token to prevent
-unnecessary page faults in thrashing situation. The unit of the value is
-second. The value would be useful to tune thrashing behavior.
-
-drop_caches
------------
-
-Writing to this will cause the kernel to drop clean caches, dentries and
-inodes from memory, causing that memory to become free.
-
-To free pagecache:
-        echo 1 > /proc/sys/vm/drop_caches
-To free dentries and inodes:
-        echo 2 > /proc/sys/vm/drop_caches
-To free pagecache, dentries and inodes:
-        echo 3 > /proc/sys/vm/drop_caches
-
-As this is a non-destructive operation and dirty objects are not freeable, the
-user should run `sync' first.
+Please see: Documentation/sysctls/vm.txt for a description of these
+entries.
 
 
 2.5 /proc/sys/dev - Device specific parameters
diff --git a/Documentation/hwmon/adt7475 b/Documentation/hwmon/adt7475
new file mode 100644
index 000000000000..a2b1abec850e
--- /dev/null
+++ b/Documentation/hwmon/adt7475
@@ -0,0 +1,87 @@
+This describes the interface for the ADT7475 driver:
+
+(there are 4 fans, numbered fan1 to fan4):
+
+fanX_input              Read the current speed of the fan (in RPMs)
+fanX_min                Read/write the minimum speed of the fan.  Dropping
+                        below this sets an alarm.
+
+(there are three PWMs, numbered pwm1 to pwm3):
+
+pwmX                    Read/write the current duty cycle of the PWM.  Writes
+                        only have effect when auto mode is turned off (see
+                        below).  Range is 0 - 255.
+
+pwmX_enable             Fan speed control method:
+
+                        0 - No control (fan at full speed)
+                        1 - Manual fan speed control (using pwm[1-*])
+                        2 - Automatic fan speed control
+
+pwmX_auto_channels_temp Select which channels affect this PWM
+
+                        1 - TEMP1 controls PWM
+                        2 - TEMP2 controls PWM
+                        4 - TEMP3 controls PWM
+                        6 - TEMP2 and TEMP3 control PWM
+                        7 - All three inputs control PWM
+
+pwmX_freq               Read/write the PWM frequency in Hz. The number
+                        should be one of the following:
+
+                        11 Hz
+                        14 Hz
+                        22 Hz
+                        29 Hz
+                        35 Hz
+                        44 Hz
+                        58 Hz
+                        88 Hz
+
+pwmX_auto_point1_pwm    Read/write the minimum PWM duty cycle in automatic mode
+
+pwmX_auto_point2_pwm    Read/write the maximum PWM duty cycle in automatic mode
+
+(there are three temperature settings numbered temp1 to temp3):
+
+tempX_input             Read the current temperature.  The value is in milli
+                        degrees of Celsius.
+
+tempX_max               Read/write the upper temperature limit - exceeding this
+                        will cause an alarm.
+
+tempX_min               Read/write the lower temperature limit - exceeding this
+                        will cause an alarm.
+
+tempX_offset            Read/write the temperature adjustment offset
+
+tempX_crit              Read/write the THERM limit for remote1.
+
+tempX_crit_hyst         Set the temperature value below crit where the
+                        fans will stay on - this helps drive the temperature
+                        low enough so it doesn't stay near the edge and
+                        cause THERM to keep tripping.
+
+tempX_auto_point1_temp  Read/write the minimum temperature where the fans will
+                        turn on in automatic mode.
+
+tempX_auto_point2_temp  Read/write the maximum temperature over which the fans
+                        will run in automatic mode.  tempX_auto_point1_temp
+                        and tempX_auto_point2_temp together define the
+                        range of automatic control.
+
+tempX_alarm             Read a 1 if the max/min alarm is set
+tempX_fault             Read a 1 if either temp1 or temp3 diode has a fault
+
+(There are two voltage settings, in1 and in2):
+
+inX_input               Read the current voltage on VCC.  Value is in
+                        millivolts.
+
+inX_min                 read/write the minimum voltage limit.
+                        Dropping below this causes an alarm.
+
+inX_max                 read/write the maximum voltage limit.
+                        Exceeding this causes an alarm.
+
+inX_alarm               Read a 1 if the max/min alarm is set.
diff --git a/Documentation/hwmon/lis3lv02d b/Documentation/hwmon/lis3lv02d
index 65dfb0c0fd67..0fcfc4a7ccdc 100644
--- a/Documentation/hwmon/lis3lv02d
+++ b/Documentation/hwmon/lis3lv02d
@@ -13,18 +13,21 @@ Author:
 Description
 -----------
 
-This driver provides support for the accelerometer found in various HP laptops
-sporting the feature officially called "HP Mobile Data Protection System 3D" or
-"HP 3D DriveGuard". It detect automatically laptops with this sensor. Known models
-(for now the HP 2133, nc6420, nc2510, nc8510, nc84x0, nw9440 and nx9420) will
-have their axis automatically oriented on standard way (eg: you can directly
-play neverball).  The accelerometer data is readable via
+This driver provides support for the accelerometer found in various HP
+laptops sporting the feature officially called "HP Mobile Data
+Protection System 3D" or "HP 3D DriveGuard". It detect automatically
+laptops with this sensor. Known models (for now the HP 2133, nc6420,
+nc2510, nc8510, nc84x0, nw9440 and nx9420) will have their axis
+automatically oriented on standard way (eg: you can directly play
+neverball).  The accelerometer data is readable via
 /sys/devices/platform/lis3lv02d.
 
 Sysfs attributes under /sys/devices/platform/lis3lv02d/:
 position - 3D position that the accelerometer reports. Format: "(x,y,z)"
-calibrate - read: values (x, y, z) that are used as the base for input class device operation.
-            write: forces the base to be recalibrated with the current position.
+calibrate - read: values (x, y, z) that are used as the base for input
+                  class device operation.
+            write: forces the base to be recalibrated with the current
+                  position.
 rate - reports the sampling rate of the accelerometer device in HZ
 
 This driver also provides an absolute input class device, allowing
@@ -39,11 +42,12 @@ the accelerometer are converted into a "standard" organisation of the axes
  * When the laptop is horizontal the position reported is about 0 for X and Y
 and a positive value for Z
  * If the left side is elevated, X increases (becomes positive)
- * If the front side (where the touchpad is) is elevated, Y decreases (becomes negative)
+ * If the front side (where the touchpad is) is elevated, Y decreases
+        (becomes negative)
  * If the laptop is put upside-down, Z becomes negative
 
-If your laptop model is not recognized (cf "dmesg"), you can send an email to the
-authors to add it to the database.  When reporting a new laptop, please include
-the output of "dmidecode" plus the value of /sys/devices/platform/lis3lv02d/position
-in these four cases.
+If your laptop model is not recognized (cf "dmesg"), you can send an
+email to the authors to add it to the database.  When reporting a new
+laptop, please include the output of "dmidecode" plus the value of
+/sys/devices/platform/lis3lv02d/position in these four cases.
 
diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
index 923f9ddee8f6..f3355b6812df 100644
--- a/Documentation/kbuild/kbuild.txt
+++ b/Documentation/kbuild/kbuild.txt
@@ -3,7 +3,7 @@ Environment variables
 KCPPFLAGS
 --------------------------------------------------
 Additional options to pass when preprocessing. The preprocessing options
-will be used in all cases where kbuild do preprocessing including
+will be used in all cases where kbuild does preprocessing including
 building C files and assembler files.
 
 KAFLAGS
@@ -16,7 +16,7 @@ Additional options to the C compiler.
 
 KBUILD_VERBOSE
 --------------------------------------------------
-Set the kbuild verbosity. Can be assinged same values as "V=...".
+Set the kbuild verbosity. Can be assigned same values as "V=...".
 See make help for the full list.
 Setting "V=..." takes precedence over KBUILD_VERBOSE.
 
@@ -35,14 +35,14 @@ KBUILD_OUTPUT
 --------------------------------------------------
 Specify the output directory when building the kernel.
 The output directory can also be specificed using "O=...".
-Setting "O=..." takes precedence over KBUILD_OUTPUT
+Setting "O=..." takes precedence over KBUILD_OUTPUT.
 
 ARCH
 --------------------------------------------------
 Set ARCH to the architecture to be built.
 In most cases the name of the architecture is the same as the
 directory name found in the arch/ directory.
-But some architectures suach as x86 and sparc has aliases.
+But some architectures such as x86 and sparc have aliases.
 x86: i386 for 32 bit, x86_64 for 64 bit
 sparc: sparc for 32 bit, sparc64 for 64 bit
 
@@ -63,7 +63,7 @@ CF is often used on the command-line like this:
 INSTALL_PATH
 --------------------------------------------------
 INSTALL_PATH specifies where to place the updated kernel and system map
-images. Default is /boot, but you can set it to other values
+images. Default is /boot, but you can set it to other values.
 
 
 MODLIB
@@ -90,7 +90,7 @@ INSTALL_MOD_STRIP will used as the options to the strip command.
 
 INSTALL_FW_PATH
 --------------------------------------------------
-INSTALL_FW_PATH specify where to install the firmware blobs.
+INSTALL_FW_PATH specifies where to install the firmware blobs.
 The default value is:
 
     $(INSTALL_MOD_PATH)/lib/firmware
@@ -99,7 +99,7 @@ The value can be overridden in which case the default value is ignored.
 
 INSTALL_HDR_PATH
 --------------------------------------------------
-INSTALL_HDR_PATH specify where to install user space headers when
+INSTALL_HDR_PATH specifies where to install user space headers when
 executing "make headers_*".
 The default value is:
 
@@ -112,22 +112,23 @@ The value can be overridden in which case the default value is ignored.
 
 KBUILD_MODPOST_WARN
 --------------------------------------------------
-KBUILD_MODPOST_WARN can be set to avoid error out in case of undefined
-symbols in the final module linking stage.
+KBUILD_MODPOST_WARN can be set to avoid errors in case of undefined
+symbols in the final module linking stage. It changes such errors
+into warnings.
 
-KBUILD_MODPOST_FINAL
+KBUILD_MODPOST_NOFINAL
 --------------------------------------------------
 KBUILD_MODPOST_NOFINAL can be set to skip the final link of modules.
-This is solely usefull to speed up test compiles.
+This is solely useful to speed up test compiles.
 
 KBUILD_EXTRA_SYMBOLS
 --------------------------------------------------
-For modules use symbols from another modules.
+For modules that use symbols from other modules.
 See more details in modules.txt.
 
 ALLSOURCE_ARCHS
 --------------------------------------------------
-For tags/TAGS/cscope targets, you can specify more than one archs
-to be included in the databases, separated by blankspace. e.g.
+For tags/TAGS/cscope targets, you can specify more than one arch
+to be included in the databases, separated by blank space. E.g.:
 
     $ make ALLSOURCE_ARCHS="x86 mips arm" tags
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8511d3532c27..d8362cf9909e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -577,9 +577,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         a memory unit (amount[KMG]). See also
                         Documentation/kdump/kdump.txt for a example.
 
-        cs4232=         [HW,OSS]
-                        Format: <io>,<irq>,<dma>,<dma2>,<mpuio>,<mpuirq>
-
         cs89x0_dma=     [HW,NET]
                         Format: <dma>
 
@@ -732,10 +729,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         Default value is 0.
                         Value can be changed at runtime via /selinux/enforce.
 
-        es1371=         [HW,OSS]
-                        Format: <spdif>,[<nomix>,[<amplifier>]]
-                        See also header of sound/oss/es1371.c.
-
         ether=          [HW,NET] Ethernet cards parameters
                         This option is obsoleted by the "netdev=" option, which
                         has equivalent usage. See its documentation for details.
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 898b4987bb80..41bc99fa1884 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -1,7 +1,7 @@
                      ThinkPad ACPI Extras Driver
 
-                            Version 0.21
-                           May 29th, 2008
+                            Version 0.22
+                        November 23rd,  2008
 
                Borislav Deianov <borislav@users.sf.net>
              Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -16,7 +16,8 @@ supported by the generic Linux ACPI drivers.
 This driver used to be named ibm-acpi until kernel 2.6.21 and release
 0.13-20070314.  It used to be in the drivers/acpi tree, but it was
 moved to the drivers/misc tree and renamed to thinkpad-acpi for kernel
-2.6.22, and release 0.14.
+2.6.22, and release 0.14.  It was moved to drivers/platform/x86 for
+kernel 2.6.29 and release 0.22.
 
 The driver is named "thinkpad-acpi".  In some places, like module
 names, "thinkpad_acpi" is used because of userspace issues.
@@ -1412,6 +1413,24 @@ Sysfs notes:
         rfkill controller switch "tpacpi_wwan_sw": refer to
         Documentation/rfkill.txt for details.
 
+EXPERIMENTAL: UWB
+-----------------
+
+This feature is marked EXPERIMENTAL because it has not been extensively
+tested and validated in various ThinkPad models yet.  The feature may not
+work as expected. USE WITH CAUTION! To use this feature, you need to supply
+the experimental=1 parameter when loading the module.
+
+sysfs rfkill class: switch "tpacpi_uwb_sw"
+
+This feature exports an rfkill controller for the UWB device, if one is
+present and enabled in the BIOS.
+
+Sysfs notes:
+
+        rfkill controller switch "tpacpi_uwb_sw": refer to
+        Documentation/rfkill.txt for details.
+
 Multiple Commands, Module Parameters
 ------------------------------------
 
diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README
index f54962aea84d..8ace35ebdcd5 100644
--- a/Documentation/mips/AU1xxx_IDE.README
+++ b/Documentation/mips/AU1xxx_IDE.README
@@ -52,14 +52,12 @@ Two files are introduced:
   b) 'drivers/ide/mips/au1xxx-ide.c'
      contains the functionality of the AU1XXX IDE driver
 
-Four configs variables are introduced:
+Following extra configs variables are introduced:
 
   CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA    - enable the PIO+DBDMA mode
   CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA  - enable the MWDMA mode
   CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON - set Burstable FIFO in DBDMA
                                            controller
-  CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ - maximum transfer size
-                                           per descriptor
 
 
 SUPPORTED IDE MODES
@@ -87,7 +85,6 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
 CONFIG_IDEDMA_PCI_AUTO=y
 CONFIG_BLK_DEV_IDE_AU1XXX=y
 CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y
-CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
 CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_IDEDMA_AUTO=y
 
@@ -105,7 +102,6 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
 CONFIG_IDEDMA_PCI_AUTO=y
 CONFIG_BLK_DEV_IDE_AU1XXX=y
 CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y
-CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
 CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_IDEDMA_AUTO=y
 
diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt
index 3c2f2b328638..8d022073e3ef 100644
--- a/Documentation/networking/netconsole.txt
+++ b/Documentation/networking/netconsole.txt
@@ -51,7 +51,8 @@ Built-in netconsole starts immediately after the TCP stack is
 initialized and attempts to bring up the supplied dev at the supplied
 address.
 
-The remote host can run either 'netcat -u -l -p <port>' or syslogd.
+The remote host can run either 'netcat -u -l -p <port>',
+'nc -l -u <port>' or syslogd.
 
 Dynamic reconfiguration:
 ========================
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 8398ca4ff4ed..6f33593e59e2 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -231,7 +231,7 @@ CPU bandwidth control purposes:
 
    This options needs CONFIG_CGROUPS to be defined, and lets the administrator
    create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
-   Documentation/cgroups.txt for more information about this filesystem.
+   Documentation/cgroups/cgroups.txt for more information about this filesystem.
 
 Only one of these options to group tasks can be chosen and not both.
 
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 4b7ac21ea9eb..0f5d26bea80f 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -275,7 +275,8 @@ STAC9200
   dell-m25      Dell Inspiron E1505n
   dell-m26      Dell Inspiron 1501
   dell-m27      Dell Inspiron E1705/9400
-  gateway       Gateway laptops with EAPD control
+  gateway-m4    Gateway laptops with EAPD control
+  gateway-m4-2  Gateway laptops with EAPD control
   panasonic     Panasonic CF-74
 
 STAC9205/9254
@@ -302,6 +303,7 @@ STAC9220/9221
   macbook-pro   Intel Mac Book Pro 2nd generation (eq. type 3)
   imac-intel    Intel iMac (eq. type 2)
   imac-intel-20 Intel iMac (newer version) (eq. type 3)
+  ecs202        ECS/PC chips
   dell-d81      Dell (unknown)
   dell-d82      Dell (unknown)
   dell-m81      Dell (unknown)
@@ -310,9 +312,13 @@ STAC9220/9221
 STAC9202/9250/9251
 ==================
   ref           Reference board, base config
+  m1            Some Gateway MX series laptops (NX560XL)
+  m1-2          Some Gateway MX series laptops (MX6453)
+  m2            Some Gateway MX series laptops (M255)
   m2-2          Some Gateway MX series laptops
+  m3            Some Gateway MX series laptops
+  m5            Some Gateway MX series laptops (MP6954)
   m6            Some Gateway NX series laptops
-  pa6           Gateway NX860 series
 
 STAC9227/9228/9229/927x
 =======================
@@ -329,6 +335,7 @@ STAC92HD71B*
   dell-m4-1     Dell desktops
   dell-m4-2     Dell desktops
   dell-m4-3     Dell desktops
+  hp-m4         HP dv laptops
 
 STAC92HD73*
 ===========
@@ -337,10 +344,12 @@ STAC92HD73*
   dell-m6-amic  Dell desktops/laptops with analog mics
   dell-m6-dmic  Dell desktops/laptops with digital mics
   dell-m6       Dell desktops/laptops with both type of mics
+  dell-eq       Dell desktops/laptops
 
 STAC92HD83*
 ===========
   ref           Reference board
+  mic-ref       Reference board with power managment for ports
 
 STAC9872
 ========
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index a3415070bcac..3197fc83bc51 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -1,12 +1,13 @@
-Documentation for /proc/sys/vm/*        kernel version 2.2.10
+Documentation for /proc/sys/vm/*        kernel version 2.6.29
         (c) 1998, 1999,  Rik van Riel <riel@nl.linux.org>
+        (c) 2008         Peter W. Morreale <pmorreale@novell.com>
 
 For general info and legal blurb, please look in README.
 
 ==============================================================
 
 This file contains the documentation for the sysctl files in
-/proc/sys/vm and is valid for Linux kernel version 2.2.
+/proc/sys/vm and is valid for Linux kernel version 2.6.29.
 
 The files in this directory can be used to tune the operation
 of the virtual memory (VM) subsystem of the Linux kernel and
@@ -16,180 +17,274 @@ Default values and initialization routines for most of these
 files can be found in mm/swap.c.
 
 Currently, these files are in /proc/sys/vm:
-- overcommit_memory
-- page-cluster
-- dirty_ratio
+
+- block_dump
+- dirty_background_bytes
 - dirty_background_ratio
+- dirty_bytes
 - dirty_expire_centisecs
+- dirty_ratio
 - dirty_writeback_centisecs
-- highmem_is_dirtyable   (only if CONFIG_HIGHMEM set)
+- drop_caches
+- hugepages_treat_as_movable
+- hugetlb_shm_group
+- laptop_mode
+- legacy_va_layout
+- lowmem_reserve_ratio
 - max_map_count
 - min_free_kbytes
-- laptop_mode
-- block_dump
-- drop-caches
-- zone_reclaim_mode
-- min_unmapped_ratio
 - min_slab_ratio
-- panic_on_oom
-- oom_dump_tasks
-- oom_kill_allocating_task
-- mmap_min_address
-- numa_zonelist_order
+- min_unmapped_ratio
+- mmap_min_addr
 - nr_hugepages
 - nr_overcommit_hugepages
-- nr_trim_pages         (only if CONFIG_MMU=n)
+- nr_pdflush_threads
+- nr_trim_pages         (only if CONFIG_MMU=n)
+- numa_zonelist_order
+- oom_dump_tasks
+- oom_kill_allocating_task
+- overcommit_memory
+- overcommit_ratio
+- page-cluster
+- panic_on_oom
+- percpu_pagelist_fraction
+- stat_interval
+- swappiness
+- vfs_cache_pressure
+- zone_reclaim_mode
+
 
 ==============================================================
 
-dirty_bytes, dirty_ratio, dirty_background_bytes,
-dirty_background_ratio, dirty_expire_centisecs,
-dirty_writeback_centisecs, highmem_is_dirtyable,
-vfs_cache_pressure, laptop_mode, block_dump, swap_token_timeout,
-drop-caches, hugepages_treat_as_movable:
+block_dump
 
-See Documentation/filesystems/proc.txt
+block_dump enables block I/O debugging when set to a nonzero value. More
+information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
 
 ==============================================================
 
-overcommit_memory:
+dirty_background_bytes
 
-This value contains a flag that enables memory overcommitment.
+Contains the amount of dirty memory at which the pdflush background writeback
+daemon will start writeback.
 
-When this flag is 0, the kernel attempts to estimate the amount
-of free memory left when userspace requests more memory.
+If dirty_background_bytes is written, dirty_background_ratio becomes a function
+of its value (dirty_background_bytes / the amount of dirtyable system memory).
 
-When this flag is 1, the kernel pretends there is always enough
-memory until it actually runs out.
+==============================================================
 
-When this flag is 2, the kernel uses a "never overcommit"
-policy that attempts to prevent any overcommit of memory.  
+dirty_background_ratio
 
-This feature can be very useful because there are a lot of
-programs that malloc() huge amounts of memory "just-in-case"
-and don't use much of it.
+Contains, as a percentage of total system memory, the number of pages at which
+the pdflush background writeback daemon will start writing out dirty data.
 
-The default value is 0.
+==============================================================
 
-See Documentation/vm/overcommit-accounting and
-security/commoncap.c::cap_vm_enough_memory() for more information.
+dirty_bytes
+
+Contains the amount of dirty memory at which a process generating disk writes
+will itself start writeback.
+
+If dirty_bytes is written, dirty_ratio becomes a function of its value
+(dirty_bytes / the amount of dirtyable system memory).
 
 ==============================================================
 
-overcommit_ratio:
+dirty_expire_centisecs
 
-When overcommit_memory is set to 2, the committed address
-space is not permitted to exceed swap plus this percentage
-of physical RAM.  See above.
+This tunable is used to define when dirty data is old enough to be eligible
+for writeout by the pdflush daemons.  It is expressed in 100'ths of a second.
+Data which has been dirty in-memory for longer than this interval will be
+written out next time a pdflush daemon wakes up.
+
+==============================================================
+
+dirty_ratio
+
+Contains, as a percentage of total system memory, the number of pages at which
+a process which is generating disk writes will itself start writing out dirty
+data.
 
 ==============================================================
 
-page-cluster:
+dirty_writeback_centisecs
 
-The Linux VM subsystem avoids excessive disk seeks by reading
-multiple pages on a page fault. The number of pages it reads
-is dependent on the amount of memory in your machine.
+The pdflush writeback daemons will periodically wake up and write `old' data
+out to disk.  This tunable expresses the interval between those wakeups, in
+100'ths of a second.
 
-The number of pages the kernel reads in at once is equal to
-2 ^ page-cluster. Values above 2 ^ 5 don't make much sense
-for swap because we only cluster swap data in 32-page groups.
+Setting this to zero disables periodic writeback altogether.
 
 ==============================================================
 
-max_map_count:
+drop_caches
 
-This file contains the maximum number of memory map areas a process
-may have. Memory map areas are used as a side-effect of calling
-malloc, directly by mmap and mprotect, and also when loading shared
-libraries.
+Writing to this will cause the kernel to drop clean caches, dentries and
+inodes from memory, causing that memory to become free.
 
-While most applications need less than a thousand maps, certain
-programs, particularly malloc debuggers, may consume lots of them,
-e.g., up to one or two maps per allocation.
+To free pagecache:
+        echo 1 > /proc/sys/vm/drop_caches
+To free dentries and inodes:
+        echo 2 > /proc/sys/vm/drop_caches
+To free pagecache, dentries and inodes:
+        echo 3 > /proc/sys/vm/drop_caches
 
-The default value is 65536.
+As this is a non-destructive operation and dirty objects are not freeable, the
+user should run `sync' first.
 
 ==============================================================
 
-min_free_kbytes:
+hugepages_treat_as_movable
 
-This is used to force the Linux VM to keep a minimum number 
-of kilobytes free.  The VM uses this number to compute a pages_min
-value for each lowmem zone in the system.  Each lowmem zone gets 
-a number of reserved free pages based proportionally on its size.
+This parameter is only useful when kernelcore= is specified at boot time to
+create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
+are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
+value written to hugepages_treat_as_movable allows huge pages to be allocated
+from ZONE_MOVABLE.
 
-Some minimal amount of memory is needed to satisfy PF_MEMALLOC
-allocations; if you set this to lower than 1024KB, your system will
-become subtly broken, and prone to deadlock under high loads.
-
-Setting this too high will OOM your machine instantly.
+Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
+pages pool can easily grow or shrink within. Assuming that applications are
+not running that mlock() a lot of memory, it is likely the huge pages pool
+can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
+into nr_hugepages and triggering page reclaim.
 
 ==============================================================
 
-percpu_pagelist_fraction
+hugetlb_shm_group
 
-This is the fraction of pages at most (high mark pcp->high) in each zone that
-are allocated for each per cpu page list.  The min value for this is 8.  It
-means that we don't allow more than 1/8th of pages in each zone to be
-allocated in any single per_cpu_pagelist.  This entry only changes the value
-of hot per cpu pagelists.  User can specify a number like 100 to allocate
-1/100th of each zone to each per cpu page list.
+hugetlb_shm_group contains group id that is allowed to create SysV
+shared memory segment using hugetlb page.
 
-The batch value of each per cpu pagelist is also updated as a result.  It is
-set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
+==============================================================
 
-The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+laptop_mode
 
-===============================================================
+laptop_mode is a knob that controls "laptop mode". All the things that are
+controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
 
-zone_reclaim_mode:
+==============================================================
 
-Zone_reclaim_mode allows someone to set more or less aggressive approaches to
-reclaim memory when a zone runs out of memory. If it is set to zero then no
-zone reclaim occurs. Allocations will be satisfied from other zones / nodes
-in the system.
+legacy_va_layout
 
-This is value ORed together of
+If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
+will use the legacy (2.4) layout for all processes.
 
-1       = Zone reclaim on
-2       = Zone reclaim writes dirty pages out
-4       = Zone reclaim swaps pages
+==============================================================
 
-zone_reclaim_mode is set during bootup to 1 if it is determined that pages
-from remote zones will cause a measurable performance reduction. The
-page allocator will then reclaim easily reusable pages (those page
-cache pages that are currently not used) before allocating off node pages.
+lowmem_reserve_ratio
+
+For some specialised workloads on highmem machines it is dangerous for
+the kernel to allow process memory to be allocated from the "lowmem"
+zone.  This is because that memory could then be pinned via the mlock()
+system call, or by unavailability of swapspace.
+
+And on large highmem machines this lack of reclaimable lowmem memory
+can be fatal.
+
+So the Linux page allocator has a mechanism which prevents allocations
+which _could_ use highmem from using too much lowmem.  This means that
+a certain amount of lowmem is defended from the possibility of being
+captured into pinned user memory.
+
+(The same argument applies to the old 16 megabyte ISA DMA region.  This
+mechanism will also defend that region from allocations which could use
+highmem or lowmem).
+
+The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
+in defending these lower zones.
+
+If you have a machine which uses highmem or ISA DMA and your
+applications are using mlock(), or if you are running with no swap then
+you probably should change the lowmem_reserve_ratio setting.
+
+The lowmem_reserve_ratio is an array. You can see them by reading this file.
+-
+% cat /proc/sys/vm/lowmem_reserve_ratio
+256     256     32
+-
+Note: # of this elements is one fewer than number of zones. Because the highest
+      zone's value is not necessary for following calculation.
+
+But, these values are not used directly. The kernel calculates # of protection
+pages for each zones from them. These are shown as array of protection pages
+in /proc/zoneinfo like followings. (This is an example of x86-64 box).
+Each zone has an array of protection pages like this.
+
+-
+Node 0, zone      DMA
+  pages free     1355
+        min      3
+        low      3
+        high     4
+        :
+        :
+    numa_other   0
+        protection: (0, 2004, 2004, 2004)
+        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  pagesets
+    cpu: 0 pcp: 0
+        :
+-
+These protections are added to score to judge whether this zone should be used
+for page allocation or should be reclaimed.
+
+In this example, if normal pages (index=2) are required to this DMA zone and
+pages_high is used for watermark, the kernel judges this zone should not be
+used because pages_free(1355) is smaller than watermark + protection[2]
+(4 + 2004 = 2008). If this protection value is 0, this zone would be used for
+normal page requirement. If requirement is DMA zone(index=0), protection[0]
+(=0) is used.
+
+zone[i]'s protection[j] is calculated by following expression.
+
+(i < j):
+  zone[i]->protection[j]
+  = (total sums of present_pages from zone[i+1] to zone[j] on the node)
+    / lowmem_reserve_ratio[i];
+(i = j):
+   (should not be protected. = 0;
+(i > j):
+   (not necessary, but looks 0)
+
+The default values of lowmem_reserve_ratio[i] are
+    256 (if zone[i] means DMA or DMA32 zone)
+    32  (others).
+As above expression, they are reciprocal number of ratio.
+256 means 1/256. # of protection pages becomes about "0.39%" of total present
+pages of higher zones on the node.
+
+If you would like to protect more pages, smaller values are effective.
+The minimum value is 1 (1/1 -> 100%).
 
-It may be beneficial to switch off zone reclaim if the system is
-used for a file server and all of memory should be used for caching files
-from disk. In that case the caching effect is more important than
-data locality.
+==============================================================
 
-Allowing zone reclaim to write out pages stops processes that are
-writing large amounts of data from dirtying pages on other nodes. Zone
-reclaim will write out dirty pages if a zone fills up and so effectively
-throttle the process. This may decrease the performance of a single process
-since it cannot use all of system memory to buffer the outgoing writes
-anymore but it preserve the memory on other nodes so that the performance
-of other processes running on other nodes will not be affected.
+max_map_count:
 
-Allowing regular swap effectively restricts allocations to the local
-node unless explicitly overridden by memory policies or cpuset
-configurations.
+This file contains the maximum number of memory map areas a process
+may have. Memory map areas are used as a side-effect of calling
+malloc, directly by mmap and mprotect, and also when loading shared
+libraries.
 
-=============================================================
+While most applications need less than a thousand maps, certain
+programs, particularly malloc debuggers, may consume lots of them,
+e.g., up to one or two maps per allocation.
 
-min_unmapped_ratio:
+The default value is 65536.
 
-This is available only on NUMA kernels.
+==============================================================
 
-A percentage of the total pages in each zone.  Zone reclaim will only
-occur if more than this percentage of pages are file backed and unmapped.
-This is to insure that a minimal amount of local pages is still available for
-file I/O even if the node is overallocated.
+min_free_kbytes:
 
-The default is 1 percent.
+This is used to force the Linux VM to keep a minimum number
+of kilobytes free.  The VM uses this number to compute a pages_min
+value for each lowmem zone in the system.  Each lowmem zone gets
+a number of reserved free pages based proportionally on its size.
+
+Some minimal amount of memory is needed to satisfy PF_MEMALLOC
+allocations; if you set this to lower than 1024KB, your system will
+become subtly broken, and prone to deadlock under high loads.
+
+Setting this too high will OOM your machine instantly.
 
 =============================================================
 
@@ -211,82 +306,73 @@ and may not be fast.
 
 =============================================================
 
-panic_on_oom
+min_unmapped_ratio:
 
-This enables or disables panic on out-of-memory feature.
+This is available only on NUMA kernels.
 
-If this is set to 0, the kernel will kill some rogue process,
-called oom_killer.  Usually, oom_killer can kill rogue processes and
-system will survive.
+A percentage of the total pages in each zone.  Zone reclaim will only
+occur if more than this percentage of pages are file backed and unmapped.
+This is to insure that a minimal amount of local pages is still available for
+file I/O even if the node is overallocated.
 
-If this is set to 1, the kernel panics when out-of-memory happens.
-However, if a process limits using nodes by mempolicy/cpusets,
-and those nodes become memory exhaustion status, one process
-may be killed by oom-killer. No panic occurs in this case.
-Because other nodes' memory may be free. This means system total status
-may be not fatal yet.
+The default is 1 percent.
 
-If this is set to 2, the kernel panics compulsorily even on the
-above-mentioned.
+==============================================================
 
-The default value is 0.
-1 and 2 are for failover of clustering. Please select either
-according to your policy of failover.
+mmap_min_addr
 
-=============================================================
+This file indicates the amount of address space  which a user process will
+be restricted from mmaping.  Since kernel null dereference bugs could
+accidentally operate based on the information in the first couple of pages
+of memory userspace processes should not be allowed to write to them.  By
+default this value is set to 0 and no protections will be enforced by the
+security module.  Setting this value to something like 64k will allow the
+vast majority of applications to work correctly and provide defense in depth
+against future potential kernel bugs.
 
-oom_dump_tasks
+==============================================================
 
-Enables a system-wide task dump (excluding kernel threads) to be
-produced when the kernel performs an OOM-killing and includes such
-information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
-name.  This is helpful to determine why the OOM killer was invoked
-and to identify the rogue task that caused it.
+nr_hugepages
 
-If this is set to zero, this information is suppressed.  On very
-large systems with thousands of tasks it may not be feasible to dump
-the memory state information for each one.  Such systems should not
-be forced to incur a performance penalty in OOM conditions when the
-information may not be desired.
+Change the minimum size of the hugepage pool.
 
-If this is set to non-zero, this information is shown whenever the
-OOM killer actually kills a memory-hogging task.
+See Documentation/vm/hugetlbpage.txt
 
-The default value is 0.
+==============================================================
 
-=============================================================
+nr_overcommit_hugepages
 
-oom_kill_allocating_task
+Change the maximum size of the hugepage pool. The maximum is
+nr_hugepages + nr_overcommit_hugepages.
 
-This enables or disables killing the OOM-triggering task in
-out-of-memory situations.
+See Documentation/vm/hugetlbpage.txt
 
-If this is set to zero, the OOM killer will scan through the entire
-tasklist and select a task based on heuristics to kill.  This normally
-selects a rogue memory-hogging task that frees up a large amount of
-memory when killed.
+==============================================================
 
-If this is set to non-zero, the OOM killer simply kills the task that
-triggered the out-of-memory condition.  This avoids the expensive
-tasklist scan.
+nr_pdflush_threads
 
-If panic_on_oom is selected, it takes precedence over whatever value
-is used in oom_kill_allocating_task.
+The current number of pdflush threads.  This value is read-only.
+The value changes according to the number of dirty pages in the system.
 
-The default value is 0.
+When neccessary, additional pdflush threads are created, one per second, up to
+nr_pdflush_threads_max.
 
 ==============================================================
 
-mmap_min_addr
+nr_trim_pages
 
-This file indicates the amount of address space  which a user process will
-be restricted from mmaping.  Since kernel null dereference bugs could
-accidentally operate based on the information in the first couple of pages
-of memory userspace processes should not be allowed to write to them.  By
-default this value is set to 0 and no protections will be enforced by the
-security module.  Setting this value to something like 64k will allow the
-vast majority of applications to work correctly and provide defense in depth
-against future potential kernel bugs.
+This is available only on NOMMU kernels.
+
+This value adjusts the excess page trimming behaviour of power-of-2 aligned
+NOMMU mmap allocations.
+
+A value of 0 disables trimming of allocations entirely, while a value of 1
+trims excess pages aggressively. Any value >= 1 acts as the watermark where
+trimming of allocations is initiated.
+
+The default value is 1.
+
+See Documentation/nommu-mmap.txt for more information.
 
 ==============================================================
 
@@ -335,34 +421,199 @@ this is causing problems for your system/application.
 
 ==============================================================
 
-nr_hugepages
+oom_dump_tasks
 
-Change the minimum size of the hugepage pool.
+Enables a system-wide task dump (excluding kernel threads) to be
+produced when the kernel performs an OOM-killing and includes such
+information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
+name.  This is helpful to determine why the OOM killer was invoked
+and to identify the rogue task that caused it.
 
-See Documentation/vm/hugetlbpage.txt
+If this is set to zero, this information is suppressed.  On very
+large systems with thousands of tasks it may not be feasible to dump
+the memory state information for each one.  Such systems should not
+be forced to incur a performance penalty in OOM conditions when the
+information may not be desired.
+
+If this is set to non-zero, this information is shown whenever the
+OOM killer actually kills a memory-hogging task.
+
+The default value is 0.
 
 ==============================================================
 
-nr_overcommit_hugepages
+oom_kill_allocating_task
 
-Change the maximum size of the hugepage pool. The maximum is
-nr_hugepages + nr_overcommit_hugepages.
+This enables or disables killing the OOM-triggering task in
+out-of-memory situations.
 
-See Documentation/vm/hugetlbpage.txt
+If this is set to zero, the OOM killer will scan through the entire
+tasklist and select a task based on heuristics to kill.  This normally
+selects a rogue memory-hogging task that frees up a large amount of
+memory when killed.
+
+If this is set to non-zero, the OOM killer simply kills the task that
+triggered the out-of-memory condition.  This avoids the expensive
+tasklist scan.
+
+If panic_on_oom is selected, it takes precedence over whatever value
+is used in oom_kill_allocating_task.
+
+The default value is 0.
 
 ==============================================================
 
-nr_trim_pages
+overcommit_memory:
 
-This is available only on NOMMU kernels.
+This value contains a flag that enables memory overcommitment.
 
-This value adjusts the excess page trimming behaviour of power-of-2 aligned
-NOMMU mmap allocations.
+When this flag is 0, the kernel attempts to estimate the amount
+of free memory left when userspace requests more memory.
 
-A value of 0 disables trimming of allocations entirely, while a value of 1
-trims excess pages aggressively. Any value >= 1 acts as the watermark where
-trimming of allocations is initiated.
+When this flag is 1, the kernel pretends there is always enough
+memory until it actually runs out.
 
-The default value is 1.
+When this flag is 2, the kernel uses a "never overcommit"
+policy that attempts to prevent any overcommit of memory.
 
-See Documentation/nommu-mmap.txt for more information.
+This feature can be very useful because there are a lot of
+programs that malloc() huge amounts of memory "just-in-case"
+and don't use much of it.
+
+The default value is 0.
+
+See Documentation/vm/overcommit-accounting and
+security/commoncap.c::cap_vm_enough_memory() for more information.
+
+==============================================================
+
+overcommit_ratio:
+
+When overcommit_memory is set to 2, the committed address
+space is not permitted to exceed swap plus this percentage
+of physical RAM.  See above.
+
+==============================================================
+
+page-cluster
+
+page-cluster controls the number of pages which are written to swap in
+a single attempt.  The swap I/O size.
+
+It is a logarithmic value - setting it to zero means "1 page", setting
+it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
+
+The default value is three (eight pages at a time).  There may be some
+small benefits in tuning this to a different value if your workload is
+swap-intensive.
+
+=============================================================
+
+panic_on_oom
+
+This enables or disables panic on out-of-memory feature.
+
+If this is set to 0, the kernel will kill some rogue process,
+called oom_killer.  Usually, oom_killer can kill rogue processes and
+system will survive.
+
+If this is set to 1, the kernel panics when out-of-memory happens.
+However, if a process limits using nodes by mempolicy/cpusets,
+and those nodes become memory exhaustion status, one process
+may be killed by oom-killer. No panic occurs in this case.
+Because other nodes' memory may be free. This means system total status
+may be not fatal yet.
+
+If this is set to 2, the kernel panics compulsorily even on the
+above-mentioned.
+
+The default value is 0.
+1 and 2 are for failover of clustering. Please select either
+according to your policy of failover.
+
+=============================================================
+
+percpu_pagelist_fraction
+
+This is the fraction of pages at most (high mark pcp->high) in each zone that
+are allocated for each per cpu page list.  The min value for this is 8.  It
+means that we don't allow more than 1/8th of pages in each zone to be
+allocated in any single per_cpu_pagelist.  This entry only changes the value
+of hot per cpu pagelists.  User can specify a number like 100 to allocate
+1/100th of each zone to each per cpu page list.
+
+The batch value of each per cpu pagelist is also updated as a result.  It is
+set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
+
+The initial value is zero.  Kernel does not use this value at boot time to set
+the high water marks for each per cpu page list.
+
+==============================================================
+
+stat_interval
+
+The time interval between which vm statistics are updated.  The default
+is 1 second.
+
+==============================================================
+
+swappiness
+
+This control is used to define how aggressive the kernel will swap
+memory pages.  Higher values will increase agressiveness, lower values
+descrease the amount of swap.
+
+The default value is 60.
+
+==============================================================
+
+vfs_cache_pressure
+------------------
+
+Controls the tendency of the kernel to reclaim the memory which is used for
+caching of directory and inode objects.
+
+At the default value of vfs_cache_pressure=100 the kernel will attempt to
+reclaim dentries and inodes at a "fair" rate with respect to pagecache and
+swapcache reclaim.  Decreasing vfs_cache_pressure causes the kernel to prefer
+to retain dentry and inode caches.  Increasing vfs_cache_pressure beyond 100
+causes the kernel to prefer to reclaim dentries and inodes.
+
+==============================================================
+
+zone_reclaim_mode:
+
+Zone_reclaim_mode allows someone to set more or less aggressive approaches to
+reclaim memory when a zone runs out of memory. If it is set to zero then no
+zone reclaim occurs. Allocations will be satisfied from other zones / nodes
+in the system.
+
+This is value ORed together of
+
+1       = Zone reclaim on
+2       = Zone reclaim writes dirty pages out
+4       = Zone reclaim swaps pages
+
+zone_reclaim_mode is set during bootup to 1 if it is determined that pages
+from remote zones will cause a measurable performance reduction. The
+page allocator will then reclaim easily reusable pages (those page
+cache pages that are currently not used) before allocating off node pages.
+
+It may be beneficial to switch off zone reclaim if the system is
+used for a file server and all of memory should be used for caching files
+from disk. In that case the caching effect is more important than
+data locality.
+
+Allowing zone reclaim to write out pages stops processes that are
+writing large amounts of data from dirtying pages on other nodes. Zone
+reclaim will write out dirty pages if a zone fills up and so effectively
+throttle the process. This may decrease the performance of a single process
+since it cannot use all of system memory to buffer the outgoing writes
+anymore but it preserve the memory on other nodes so that the performance
+of other processes running on other nodes will not be affected.
+
+Allowing regular swap effectively restricts allocations to the local
+node unless explicitly overridden by memory policies or cpuset
+configurations.
+
+============ End of Document =================================
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 10a0263ebb3f..9e592c718afb 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -1,6 +1,5 @@
 Linux Magic System Request Key Hacks
 Documentation for sysrq.c
-Last update: 2007-AUG-04
 
 *  What is the magic SysRq key?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -211,6 +210,24 @@ within a function called by handle_sysrq, you must be aware that you are in
 a lock (you are also in an interrupt handler, which means don't sleep!), so
 you must call __handle_sysrq_nolock instead.
 
+*  When I hit a SysRq key combination only the header appears on the console?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Sysrq output is subject to the same console loglevel control as all
+other console output.  This means that if the kernel was booted 'quiet'
+as is common on distro kernels the output may not appear on the actual
+console, even though it will appear in the dmesg buffer, and be accessible
+via the dmesg command and to the consumers of /proc/kmsg.  As a specific
+exception the header line from the sysrq command is passed to all console
+consumers as if the current loglevel was maximum.  If only the header
+is emitted it is almost certain that the kernel loglevel is too low.
+Should you require the output on the console channel then you will need
+to temporarily up the console loglevel using alt-sysrq-8 or:
+
+    echo 8 > /proc/sysrq-trigger
+
+Remember to return the loglevel to normal after triggering the sysrq
+command you are interested in.
+
 *  I have more questions, who can I ask?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 And I'll answer any questions about the registration system you got, also
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 7b4596ac4120..12299697b7cd 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -158,7 +158,7 @@ Offset	Proto	Name		Meaning
 0202/4  2.00+   header          Magic signature "HdrS"
 0206/2  2.00+   version         Boot protocol version supported
 0208/4  2.00+   realmode_swtch  Boot loader hook (see below)
-020C/2  2.00+   start_sys       The load-low segment (0x1000) (obsolete)
+020C/2  2.00+   start_sys_seg   The load-low segment (0x1000) (obsolete)
 020E/2  2.00+   kernel_version  Pointer to kernel version string
 0210/1  2.00+   type_of_loader  Boot loader identifier
 0211/1  2.00+   loadflags       Boot protocol option flags
@@ -170,10 +170,11 @@ Offset	Proto	Name		Meaning
 0224/2  2.01+   heap_end_ptr    Free memory after setup end
 0226/2  N/A     pad1            Unused
 0228/4  2.02+   cmd_line_ptr    32-bit pointer to the kernel command line
-022C/4  2.03+   initrd_addr_max Highest legal initrd address
+022C/4  2.03+   ramdisk_max     Highest legal initrd address
 0230/4  2.05+   kernel_alignment Physical addr alignment required for kernel
 0234/1  2.05+   relocatable_kernel Whether kernel is relocatable or not
-0235/3  N/A     pad2            Unused
+0235/1  N/A     pad2            Unused
+0236/2  N/A     pad3            Unused
 0238/4  2.06+   cmdline_size    Maximum size of the kernel command line
 023C/4  2.07+   hardware_subarch Hardware subarchitecture
 0240/8  2.07+   hardware_subarch_data Subarchitecture-specific data
@@ -299,14 +300,14 @@ Protocol:	2.00+
   e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version
   10.17.
 
-Field name:     readmode_swtch
+Field name:     realmode_swtch
 Type:           modify (optional)
 Offset/size:    0x208/4
 Protocol:       2.00+
 
   Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
 
-Field name:     start_sys
+Field name:     start_sys_seg
 Type:           read
 Offset/size:    0x20c/2
 Protocol:       2.00+
@@ -468,7 +469,7 @@ Protocol:	2.02+
   zero, the kernel will assume that your boot loader does not support
   the 2.02+ protocol.
 
-Field name:     initrd_addr_max
+Field name:     ramdisk_max
 Type:           read
 Offset/size:    0x22c/4
 Protocol:       2.03+