19 files changed, 333 insertions, 186 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
new file mode 100644
index 000000000000..aa11dbdd794b
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
@@ -0,0 +1,56 @@
+What:           /sys/class/backlight/<backlight>/<ambient light zone>_max
+What:           /sys/class/backlight/<backlight>/l1_daylight_max
+What:           /sys/class/backlight/<backlight>/l2_bright_max
+What:           /sys/class/backlight/<backlight>/l3_office_max
+What:           /sys/class/backlight/<backlight>/l4_indoor_max
+What:           /sys/class/backlight/<backlight>/l5_dark_max
+Date:           Mai 2011
+KernelVersion:  2.6.40
+Contact:        device-drivers-devel@blackfin.uclinux.org
+Description:
+                Control the maximum brightness for <ambient light zone>
+                on this <backlight>. Values are between 0 and 127. This file
+                will also show the brightness level stored for this
+                <ambient light zone>.
+
+What:           /sys/class/backlight/<backlight>/<ambient light zone>_dim
+What:           /sys/class/backlight/<backlight>/l2_bright_dim
+What:           /sys/class/backlight/<backlight>/l3_office_dim
+What:           /sys/class/backlight/<backlight>/l4_indoor_dim
+What:           /sys/class/backlight/<backlight>/l5_dark_dim
+Date:           Mai 2011
+KernelVersion:  2.6.40
+Contact:        device-drivers-devel@blackfin.uclinux.org
+Description:
+                Control the dim brightness for <ambient light zone>
+                on this <backlight>. Values are between 0 and 127, typically
+                set to 0. Full off when the backlight is disabled.
+                This file will also show the dim brightness level stored for
+                this <ambient light zone>.
+
+What:           /sys/class/backlight/<backlight>/ambient_light_level
+Date:           Mai 2011
+KernelVersion:  2.6.40
+Contact:        device-drivers-devel@blackfin.uclinux.org
+Description:
+                Get conversion value of the light sensor.
+                This value is updated every 80 ms (when the light sensor
+                is enabled). Returns integer between 0 (dark) and
+                8000 (max ambient brightness)
+
+What:           /sys/class/backlight/<backlight>/ambient_light_zone
+Date:           Mai 2011
+KernelVersion:  2.6.40
+Contact:        device-drivers-devel@blackfin.uclinux.org
+Description:
+                Get/Set current ambient light zone. Reading returns
+                integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark).
+                Writing a value between 1..5 forces the backlight controller
+                to enter the corresponding ambient light zone.
+                Writing 0 returns to normal/automatic ambient light level
+                operation. The ambient light sensing feature on these devices
+                is an extension to the API documented in
+                Documentation/ABI/stable/sysfs-class-backlight.
+                It can be enabled by writing the value stored in
+                /sys/class/backlight/<backlight>/max_brightness to
+                /sys/class/backlight/<backlight>/brightness.
\ No newline at end of file
diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt
index eda40fd39cad..d16a9849e60e 100644
--- a/Documentation/accounting/cgroupstats.txt
+++ b/Documentation/accounting/cgroupstats.txt
@@ -21,7 +21,7 @@ information will not be available.
 To extract cgroup statistics a utility very similar to getdelays.c
 has been developed, the sample output of the utility is shown below
 
-~/balbir/cgroupstats # ./getdelays  -C "/cgroup/a"
+~/balbir/cgroupstats # ./getdelays  -C "/sys/fs/cgroup/a"
 sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0
-~/balbir/cgroupstats # ./getdelays  -C "/cgroup"
+~/balbir/cgroupstats # ./getdelays  -C "/sys/fs/cgroup"
 sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 465351d4cf85..cd45c8ea7463 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -28,16 +28,19 @@ cgroups. Here is what you can do.
 - Enable group scheduling in CFQ
         CONFIG_CFQ_GROUP_IOSCHED=y
 
-- Compile and boot into kernel and mount IO controller (blkio).
+- Compile and boot into kernel and mount IO controller (blkio); see
+  cgroups.txt, Why are cgroups needed?.
 
-        mount -t cgroup -o blkio none /cgroup
+        mount -t tmpfs cgroup_root /sys/fs/cgroup
+        mkdir /sys/fs/cgroup/blkio
+        mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
 
 - Create two cgroups
-        mkdir -p /cgroup/test1/ /cgroup/test2
+        mkdir -p /sys/fs/cgroup/blkio/test1/ /sys/fs/cgroup/blkio/test2
 
 - Set weights of group test1 and test2
-        echo 1000 > /cgroup/test1/blkio.weight
-        echo 500 > /cgroup/test2/blkio.weight
+        echo 1000 > /sys/fs/cgroup/blkio/test1/blkio.weight
+        echo 500 > /sys/fs/cgroup/blkio/test2/blkio.weight
 
 - Create two same size files (say 512MB each) on same disk (file1, file2) and
   launch two dd threads in different cgroup to read those files.
@@ -46,12 +49,12 @@ cgroups. Here is what you can do.
         echo 3 > /proc/sys/vm/drop_caches
 
         dd if=/mnt/sdb/zerofile1 of=/dev/null &
-        echo $! > /cgroup/test1/tasks
-        cat /cgroup/test1/tasks
+        echo $! > /sys/fs/cgroup/blkio/test1/tasks
+        cat /sys/fs/cgroup/blkio/test1/tasks
 
         dd if=/mnt/sdb/zerofile2 of=/dev/null &
-        echo $! > /cgroup/test2/tasks
-        cat /cgroup/test2/tasks
+        echo $! > /sys/fs/cgroup/blkio/test2/tasks
+        cat /sys/fs/cgroup/blkio/test2/tasks
 
 - At macro level, first dd should finish first. To get more precise data, keep
   on looking at (with the help of script), at blkio.disk_time and
@@ -68,13 +71,13 @@ Throttling/Upper Limit policy
 - Enable throttling in block layer
         CONFIG_BLK_DEV_THROTTLING=y
 
-- Mount blkio controller
-        mount -t cgroup -o blkio none /cgroup/blkio
+- Mount blkio controller (see cgroups.txt, Why are cgroups needed?)
+        mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
 
 - Specify a bandwidth rate on particular device for root group. The format
   for policy is "<major>:<minor>  <byes_per_second>".
 
-        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+        echo "8:16  1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device
 
   Above will put a limit of 1MB/second on reads happening for root group
   on device having major/minor number 8:16.
@@ -108,7 +111,7 @@ Hierarchical Cgroups
   CFQ and throttling will practically treat all groups at same level.
 
                                 pivot
-                             /  |   \  \
+                             /  /   \  \
                         root  test1 test2  test3
 
   Down the line we can implement hierarchical accounting/control support
@@ -149,7 +152,7 @@ Proportional weight policy files
 
           Following is the format.
 
-          #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device
+          # echo dev_maj:dev_minor weight > blkio.weight_device
           Configure weight=300 on /dev/sdb (8:16) in this cgroup
           # echo 8:16 300 > blkio.weight_device
           # cat blkio.weight_device
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0ed99f08f1f3..cd67e90003c0 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -138,11 +138,11 @@ With the ability to classify tasks differently for different resources
 the admin can easily set up a script which receives exec notifications
 and depending on who is launching the browser he can
 
-       # echo browser_pid > /mnt/<restype>/<userclass>/tasks
+    # echo browser_pid > /sys/fs/cgroup/<restype>/<userclass>/tasks
 
 With only a single hierarchy, he now would potentially have to create
 a separate cgroup for every browser launched and associate it with
-approp network and other resource class.  This may lead to
+appropriate network and other resource class.  This may lead to
 proliferation of such cgroups.
 
 Also lets say that the administrator would like to give enhanced network
@@ -153,9 +153,9 @@ apps enhanced CPU power,
 With ability to write pids directly to resource classes, it's just a
 matter of :
 
-       # echo pid > /mnt/network/<new_class>/tasks
+       # echo pid > /sys/fs/cgroup/network/<new_class>/tasks
        (after some time)
-       # echo pid > /mnt/network/<orig_class>/tasks
+       # echo pid > /sys/fs/cgroup/network/<orig_class>/tasks
 
 Without this ability, he would have to split the cgroup into
 multiple separate ones and then associate the new cgroups with the
@@ -310,21 +310,24 @@ subsystem, this is the case for the cpuset.
 To start a new job that is to be contained within a cgroup, using
 the "cpuset" cgroup subsystem, the steps are something like:
 
- 1) mkdir /dev/cgroup
- 2) mount -t cgroup -ocpuset cpuset /dev/cgroup
- 3) Create the new cgroup by doing mkdir's and write's (or echo's) in
-    the /dev/cgroup virtual file system.
- 4) Start a task that will be the "founding father" of the new job.
- 5) Attach that task to the new cgroup by writing its pid to the
-    /dev/cgroup tasks file for that cgroup.
- 6) fork, exec or clone the job tasks from this founding father task.
+ 1) mount -t tmpfs cgroup_root /sys/fs/cgroup
+ 2) mkdir /sys/fs/cgroup/cpuset
+ 3) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
+ 4) Create the new cgroup by doing mkdir's and write's (or echo's) in
+    the /sys/fs/cgroup virtual file system.
+ 5) Start a task that will be the "founding father" of the new job.
+ 6) Attach that task to the new cgroup by writing its pid to the
+    /sys/fs/cgroup/cpuset/tasks file for that cgroup.
+ 7) fork, exec or clone the job tasks from this founding father task.
 
 For example, the following sequence of commands will setup a cgroup
 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
 and then start a subshell 'sh' in that cgroup:
 
-  mount -t cgroup cpuset -ocpuset /dev/cgroup
-  cd /dev/cgroup
+  mount -t tmpfs cgroup_root /sys/fs/cgroup
+  mkdir /sys/fs/cgroup/cpuset
+  mount -t cgroup cpuset -ocpuset /sys/fs/cgroup/cpuset
+  cd /sys/fs/cgroup/cpuset
   mkdir Charlie
   cd Charlie
   /bin/echo 2-3 > cpuset.cpus
@@ -345,7 +348,7 @@ Creating, modifying, using the cgroups can be done through the cgroup
 virtual filesystem.
 
 To mount a cgroup hierarchy with all available subsystems, type:
-# mount -t cgroup xxx /dev/cgroup
+# mount -t cgroup xxx /sys/fs/cgroup
 
 The "xxx" is not interpreted by the cgroup code, but will appear in
 /proc/mounts so may be any useful identifying string that you like.
@@ -354,23 +357,32 @@ Note: Some subsystems do not work without some user input first.  For instance,
 if cpusets are enabled the user will have to populate the cpus and mems files
 for each new cgroup created before that group can be used.
 
+As explained in section `1.2 Why are cgroups needed?' you should create
+different hierarchies of cgroups for each single resource or group of
+resources you want to control. Therefore, you should mount a tmpfs on
+/sys/fs/cgroup and create directories for each cgroup resource or resource
+group.
+
+# mount -t tmpfs cgroup_root /sys/fs/cgroup
+# mkdir /sys/fs/cgroup/rg1
+
 To mount a cgroup hierarchy with just the cpuset and memory
 subsystems, type:
-# mount -t cgroup -o cpuset,memory hier1 /dev/cgroup
+# mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1
 
 To change the set of subsystems bound to a mounted hierarchy, just
 remount with different options:
-# mount -o remount,cpuset,blkio hier1 /dev/cgroup
+# mount -o remount,cpuset,blkio hier1 /sys/fs/cgroup/rg1
 
 Now memory is removed from the hierarchy and blkio is added.
 
 Note this will add blkio to the hierarchy but won't remove memory or
 cpuset, because the new options are appended to the old ones:
-# mount -o remount,blkio /dev/cgroup
+# mount -o remount,blkio /sys/fs/cgroup/rg1
 
 To Specify a hierarchy's release_agent:
 # mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \
-  xxx /dev/cgroup
+  xxx /sys/fs/cgroup/rg1
 
 Note that specifying 'release_agent' more than once will return failure.
 
@@ -379,17 +391,17 @@ when the hierarchy consists of a single (root) cgroup. Supporting
 the ability to arbitrarily bind/unbind subsystems from an existing
 cgroup hierarchy is intended to be implemented in the future.
 
-Then under /dev/cgroup you can find a tree that corresponds to the
-tree of the cgroups in the system. For instance, /dev/cgroup
+Then under /sys/fs/cgroup/rg1 you can find a tree that corresponds to the
+tree of the cgroups in the system. For instance, /sys/fs/cgroup/rg1
 is the cgroup that holds the whole system.
 
 If you want to change the value of release_agent:
-# echo "/sbin/new_release_agent" > /dev/cgroup/release_agent
+# echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent
 
 It can also be changed via remount.
 
-If you want to create a new cgroup under /dev/cgroup:
-# cd /dev/cgroup
+If you want to create a new cgroup under /sys/fs/cgroup/rg1:
+# cd /sys/fs/cgroup/rg1
 # mkdir my_cgroup
 
 Now you want to do something with this cgroup.
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index 8b930946c52a..9ad85df4b983 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -10,26 +10,25 @@ directly present in its group.
 
 Accounting groups can be created by first mounting the cgroup filesystem.
 
-# mkdir /cgroups
-# mount -t cgroup -ocpuacct none /cgroups
-
-With the above step, the initial or the parent accounting group
-becomes visible at /cgroups. At bootup, this group includes all the
-tasks in the system. /cgroups/tasks lists the tasks in this cgroup.
-/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by
-this group which is essentially the CPU time obtained by all the tasks
+# mount -t cgroup -ocpuacct none /sys/fs/cgroup
+
+With the above step, the initial or the parent accounting group becomes
+visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
+the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
+/sys/fs/cgroup/cpuacct.usage gives the CPU time (in nanoseconds) obtained
+by this group which is essentially the CPU time obtained by all the tasks
 in the system.
 
-New accounting groups can be created under the parent group /cgroups.
+New accounting groups can be created under the parent group /sys/fs/cgroup.
 
-# cd /cgroups
+# cd /sys/fs/cgroup
 # mkdir g1
 # echo $$ > g1
 
 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.
+/sys/fs/cgroup/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
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 98a30829af7a..5b0d78e55ccc 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -661,21 +661,21 @@ than stress the kernel.
 
 To start a new job that is to be contained within a cpuset, the steps are:
 
- 1) mkdir /dev/cpuset
- 2) mount -t cgroup -ocpuset cpuset /dev/cpuset
+ 1) mkdir /sys/fs/cgroup/cpuset
+ 2) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
  3) Create the new cpuset by doing mkdir's and write's (or echo's) in
-    the /dev/cpuset virtual file system.
+    the /sys/fs/cgroup/cpuset virtual file system.
  4) Start a task that will be the "founding father" of the new job.
  5) Attach that task to the new cpuset by writing its pid to the
-    /dev/cpuset tasks file for that cpuset.
+    /sys/fs/cgroup/cpuset tasks file for that cpuset.
  6) fork, exec or clone the job tasks from this founding father task.
 
 For example, the following sequence of commands will setup a cpuset
 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
 and then start a subshell 'sh' in that cpuset:
 
-  mount -t cgroup -ocpuset cpuset /dev/cpuset
-  cd /dev/cpuset
+  mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
+  cd /sys/fs/cgroup/cpuset
   mkdir Charlie
   cd Charlie
   /bin/echo 2-3 > cpuset.cpus
@@ -710,14 +710,14 @@ Creating, modifying, using the cpusets can be done through the cpuset
 virtual filesystem.
 
 To mount it, type:
-# mount -t cgroup -o cpuset cpuset /dev/cpuset
+# mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset
 
-Then under /dev/cpuset you can find a tree that corresponds to the
-tree of the cpusets in the system. For instance, /dev/cpuset
+Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the
+tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset
 is the cpuset that holds the whole system.
 
-If you want to create a new cpuset under /dev/cpuset:
-# cd /dev/cpuset
+If you want to create a new cpuset under /sys/fs/cgroup/cpuset:
+# cd /sys/fs/cgroup/cpuset
 # mkdir my_cpuset
 
 Now you want to do something with this cpuset.
@@ -765,12 +765,12 @@ wrapper around the cgroup filesystem.
 
 The command
 
-mount -t cpuset X /dev/cpuset
+mount -t cpuset X /sys/fs/cgroup/cpuset
 
 is equivalent to
 
-mount -t cgroup -ocpuset,noprefix X /dev/cpuset
-echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
+mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset
+echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent
 
 2.2 Adding/removing cpus
 ------------------------
diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt
index 57ca4c89fe5c..16624a7f8222 100644
--- a/Documentation/cgroups/devices.txt
+++ b/Documentation/cgroups/devices.txt
@@ -22,16 +22,16 @@ removed from the child(ren).
 An entry is added using devices.allow, and removed using
 devices.deny.  For instance
 
-        echo 'c 1:3 mr' > /cgroups/1/devices.allow
+        echo 'c 1:3 mr' > /sys/fs/cgroup/1/devices.allow
 
 allows cgroup 1 to read and mknod the device usually known as
 /dev/null.  Doing
 
-        echo a > /cgroups/1/devices.deny
+        echo a > /sys/fs/cgroup/1/devices.deny
 
 will remove the default 'a *:* rwm' entry. Doing
 
-        echo a > /cgroups/1/devices.allow
+        echo a > /sys/fs/cgroup/1/devices.allow
 
 will add the 'a *:* rwm' entry to the whitelist.
 
diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt
index 41f37fea1276..c21d77742a07 100644
--- a/Documentation/cgroups/freezer-subsystem.txt
+++ b/Documentation/cgroups/freezer-subsystem.txt
@@ -59,28 +59,28 @@ is non-freezable.
 
 * Examples of usage :
 
-   # mkdir /containers
-   # mount -t cgroup -ofreezer freezer  /containers
-   # mkdir /containers/0
-   # echo $some_pid > /containers/0/tasks
+   # mkdir /sys/fs/cgroup/freezer
+   # mount -t cgroup -ofreezer freezer /sys/fs/cgroup/freezer
+   # mkdir /sys/fs/cgroup/freezer/0
+   # echo $some_pid > /sys/fs/cgroup/freezer/0/tasks
 
 to get status of the freezer subsystem :
 
-   # cat /containers/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    THAWED
 
 to freeze all tasks in the container :
 
-   # echo FROZEN > /containers/0/freezer.state
-   # cat /containers/0/freezer.state
+   # echo FROZEN > /sys/fs/cgroup/freezer/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    FREEZING
-   # cat /containers/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    FROZEN
 
 to unfreeze all tasks in the container :
 
-   # echo THAWED > /containers/0/freezer.state
-   # cat /containers/0/freezer.state
+   # echo THAWED > /sys/fs/cgroup/freezer/0/freezer.state
+   # cat /sys/fs/cgroup/freezer/0/freezer.state
    THAWED
 
 This is the basic mechanism which should do the right thing for user space task
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 7c163477fcd8..06eb6d957c83 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -1,8 +1,8 @@
 Memory Resource Controller
 
-NOTE: The Memory Resource Controller has been generically been referred
-      to as the memory controller in this document. Do not confuse memory
-      controller used here with the memory controller that is used in hardware.
+NOTE: The Memory Resource Controller has generically been referred to as the
+      memory controller in this document. Do not confuse memory controller
+      used here with the memory controller that is used in hardware.
 
 (For editors)
 In this document:
@@ -70,6 +70,7 @@ Brief summary of control files.
                                  (See sysctl's vm.swappiness)
  memory.move_charge_at_immigrate # set/show controls of moving charges
  memory.oom_control              # set/show oom controls.
+ memory.numa_stat                # show the number of memory usage per numa node
 
 1. History
 
@@ -181,7 +182,7 @@ behind this approach is that a cgroup that aggressively uses a shared
 page will eventually get charged for it (once it is uncharged from
 the cgroup that brought it in -- this will happen on memory pressure).
 
-Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
+Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.
 When you do swapoff and make swapped-out pages of shmem(tmpfs) to
 be backed into memory in force, charges for pages are accounted against the
 caller of swapoff rather than the users of shmem.
@@ -213,7 +214,7 @@ affecting global LRU, memory+swap limit is better than just limiting swap from
 OS point of view.
 
 * What happens when a cgroup hits memory.memsw.limit_in_bytes
-When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out
+When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out
 in this cgroup. Then, swap-out will not be done by cgroup routine and file
 caches are dropped. But as mentioned above, global LRU can do swapout memory
 from it for sanity of the system's memory management state. You can't forbid
@@ -263,16 +264,17 @@ b. Enable CONFIG_RESOURCE_COUNTERS
 c. Enable CONFIG_CGROUP_MEM_RES_CTLR
 d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
 
-1. Prepare the cgroups
-# mkdir -p /cgroups
-# mount -t cgroup none /cgroups -o memory
+1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
+# mount -t tmpfs none /sys/fs/cgroup
+# mkdir /sys/fs/cgroup/memory
+# mount -t cgroup none /sys/fs/cgroup/memory -o memory
 
 2. Make the new group and move bash into it
-# mkdir /cgroups/0
-# echo $$ > /cgroups/0/tasks
+# mkdir /sys/fs/cgroup/memory/0
+# echo $$ > /sys/fs/cgroup/memory/0/tasks
 
 Since now we're in the 0 cgroup, we can alter the memory limit:
-# echo 4M > /cgroups/0/memory.limit_in_bytes
+# echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
 
 NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
 mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
@@ -280,11 +282,11 @@ mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
 NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
 NOTE: We cannot set limits on the root cgroup any more.
 
-# cat /cgroups/0/memory.limit_in_bytes
+# cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
 4194304
 
 We can check the usage:
-# cat /cgroups/0/memory.usage_in_bytes
+# cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
 1216512
 
 A successful write to this file does not guarantee a successful set of
@@ -464,6 +466,24 @@ value for efficient access. (Of course, when necessary, it's synchronized.)
 If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP)
 value in memory.stat(see 5.2).
 
+5.6 numa_stat
+
+This is similar to numa_maps but operates on a per-memcg basis.  This is
+useful for providing visibility into the numa locality information within
+an memcg since the pages are allowed to be allocated from any physical
+node.  One of the usecases is evaluating application performance by
+combining this information with the application's cpu allocation.
+
+We export "total", "file", "anon" and "unevictable" pages per-node for
+each memcg.  The ouput format of memory.numa_stat is:
+
+total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
+file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
+anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+
+And we have total = file + anon + unevictable.
+
 6. Hierarchy support
 
 The memory controller supports a deep hierarchy and hierarchical accounting.
@@ -471,13 +491,13 @@ The hierarchy is created by creating the appropriate cgroups in the
 cgroup filesystem. Consider for example, the following cgroup filesystem
 hierarchy
 
-                root
+               root
              /  |   \
-           /    |    \
-          a     b       c
-                        | \
-                        |  \
-                        d   e
+            /   |    \
+           a    b     c
+                      | \
+                      |  \
+                      d   e
 
 In the diagram above, with hierarchical accounting enabled, all memory
 usage of e, is accounted to its ancestors up until the root (i.e, c and root),
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 1a9446b59153..72e238465b0b 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -481,23 +481,6 @@ Who:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 
 ----------------------------
 
-What:   namespace cgroup (ns_cgroup)
-When:   2.6.38
-Why:    The ns_cgroup leads to some problems:
-        * cgroup creation is out-of-control
-        * cgroup name can conflict when pids are looping
-        * it is not possible to have a single process handling
-        a lot of namespaces without falling in a exponential creation time
-        * we may want to create a namespace without creating a cgroup
-
-        The ns_cgroup is replaced by a compatibility flag 'clone_children',
-        where a newly created cgroup will copy the parent cgroup values.
-        The userspace has to manually create a cgroup and add a task to
-        the 'tasks' file.
-Who:    Daniel Lezcano <daniel.lezcano@free.fr>
-
-----------------------------
-
 What:   iwlwifi disable_hw_scan module parameters
 When:   2.6.40
 Why:    Hareware scan is the prefer method for iwlwifi devices for
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index f48178024067..db3b1aba32a3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -843,6 +843,7 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
+     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
index 090e6ee04536..51063e681ca4 100644
--- a/Documentation/kmemleak.txt
+++ b/Documentation/kmemleak.txt
@@ -11,7 +11,9 @@ with the difference that the orphan objects are not freed but only
 reported via /sys/kernel/debug/kmemleak. A similar method is used by the
 Valgrind tool (memcheck --leak-check) to detect the memory leaks in
 user-space applications.
-Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze and tile.
+
+Please check DEBUG_KMEMLEAK dependencies in lib/Kconfig.debug for supported
+architectures.
 
 Usage
 -----
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 2366b1c8cf19..f0eee83ff78a 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -555,7 +555,7 @@ also have
    sync_min
    sync_max
      The two values, given as numbers of sectors, indicate a range
-     withing the array where 'check'/'repair' will operate. Must be
+     within the array where 'check'/'repair' will operate. Must be
      a multiple of chunk_size. When it reaches "sync_max" it will
      pause, rather than complete.
      You can use 'select' or 'poll' on "sync_completed" to wait for
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 88880839ece4..64565aac6e40 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -520,59 +520,20 @@ Support for power domains is provided through the pwr_domain field of struct
 device.  This field is a pointer to an object of type struct dev_power_domain,
 defined in include/linux/pm.h, providing a set of power management callbacks
 analogous to the subsystem-level and device driver callbacks that are executed
-for the given device during all power transitions, in addition to the respective
-subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
-(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
-executed after the analogous subsystem-level callbacks, while the power domain
-"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
-etc.) are executed before the analogous subsystem-level callbacks.  Error codes
-returned by the "suspend" and "resume" power domain callbacks are ignored.
-
-Power domain ->runtime_idle() callback is executed before the subsystem-level
-->runtime_idle() callback and the result returned by it is not ignored.  Namely,
-if it returns error code, the subsystem-level ->runtime_idle() callback will not
-be called and the helper function rpm_idle() executing it will return error
-code.  This mechanism is intended to help platforms where saving device state
-is a time consuming operation and should only be carried out if all devices
-in the power domain are idle, before turning off the shared power resource(s).
-Namely, the power domain ->runtime_idle() callback may return error code until
-the pm_runtime_idle() helper (or its asychronous version) has been called for
-all devices in the power domain (it is recommended that the returned error code
-be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
-callback from being run prematurely.
-
-The support for device power domains is only relevant to platforms needing to
-use the same subsystem-level (e.g. platform bus type) and device driver power
-management callbacks in many different power domain configurations and wanting
-to avoid incorporating the support for power domains into the subsystem-level
-callbacks.  The other platforms need not implement it or take it into account
-in any way.
-
-
-System Devices
---------------
-System devices (sysdevs) follow a slightly different API, which can be found in
-
-        include/linux/sysdev.h
-        drivers/base/sys.c
-
-System devices will be suspended with interrupts disabled, and after all other
-devices have been suspended.  On resume, they will be resumed before any other
-devices, and also with interrupts disabled.  These things occur in special
-"sysdev_driver" phases, which affect only system devices.
-
-Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when
-the non-boot CPUs are all offline and IRQs are disabled on the remaining online
-CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a
-sleep state (or a system image is created).  During resume (or after the image
-has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs
-are enabled on the only online CPU, the non-boot CPUs are enabled, and the
-resume_noirq (or thaw_noirq or restore_noirq) phase begins.
-
-Code to actually enter and exit the system-wide low power state sometimes
-involves hardware details that are only known to the boot firmware, and
-may leave a CPU running software (from SRAM or flash memory) that monitors
-the system and manages its wakeup sequence.
+for the given device during all power transitions, instead of the respective
+subsystem-level callbacks.  Specifically, if a device's pm_domain pointer is
+not NULL, the ->suspend() callback from the object pointed to by it will be
+executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and
+anlogously for all of the remaining callbacks.  In other words, power management
+domain callbacks, if defined for the given device, always take precedence over
+the callbacks provided by the device's subsystem (e.g. bus type).
+
+The support for device power management domains is only relevant to platforms
+needing to use the same device driver power management callbacks in many
+different power domain configurations and wanting to avoid incorporating the
+support for power domains into subsystem-level callbacks, for example by
+modifying the platform bus type.  Other platforms need not implement it or take
+it into account in any way.
 
 
 Device Low Power (suspend) States
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 654097b130b4..22accb3eb40e 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -566,11 +566,6 @@ to do this is:
         pm_runtime_set_active(dev);
         pm_runtime_enable(dev);
 
-The PM core always increments the run-time usage counter before calling the
-->prepare() callback and decrements it after calling the ->complete() callback.
-Hence disabling run-time PM temporarily like this will not cause any run-time
-suspend callbacks to be lost.
-
 7. Generic subsystem callbacks
 
 Subsystems may wish to conserve code space by using the set of generic power
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 1b5a5ddbc3ef..5df176ed59b8 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -9,7 +9,121 @@ If variable is of Type,		use printk format specifier:
                 size_t                  %zu or %zx
                 ssize_t                 %zd or %zx
 
-Raw pointer value SHOULD be printed with %p.
+Raw pointer value SHOULD be printed with %p. The kernel supports
+the following extended format specifiers for pointer types:
+
+Symbols/Function Pointers:
+
+        %pF     versatile_init+0x0/0x110
+        %pf     versatile_init
+        %pS     versatile_init+0x0/0x110
+        %ps     versatile_init
+        %pB     prev_fn_of_versatile_init+0x88/0x88
+
+        For printing symbols and function pointers. The 'S' and 's' specifiers
+        result in the symbol name with ('S') or without ('s') offsets. Where
+        this is used on a kernel without KALLSYMS - the symbol address is
+        printed instead.
+
+        The 'B' specifier results in the symbol name with offsets and should be
+        used when printing stack backtraces. The specifier takes into
+        consideration the effect of compiler optimisations which may occur
+        when tail-call's are used and marked with the noreturn GCC attribute.
+
+        On ia64, ppc64 and parisc64 architectures function pointers are
+        actually function descriptors which must first be resolved. The 'F' and
+        'f' specifiers perform this resolution and then provide the same
+        functionality as the 'S' and 's' specifiers.
+
+Kernel Pointers:
+
+        %pK     0x01234567 or 0x0123456789abcdef
+
+        For printing kernel pointers which should be hidden from unprivileged
+        users. The behaviour of %pK depends on the kptr_restrict sysctl - see
+        Documentation/sysctl/kernel.txt for more details.
+
+Struct Resources:
+
+        %pr     [mem 0x60000000-0x6fffffff flags 0x2200] or
+                [mem 0x0000000060000000-0x000000006fffffff flags 0x2200]
+        %pR     [mem 0x60000000-0x6fffffff pref] or
+                [mem 0x0000000060000000-0x000000006fffffff pref]
+
+        For printing struct resources. The 'R' and 'r' specifiers result in a
+        printed resource with ('R') or without ('r') a decoded flags member.
+
+MAC/FDDI addresses:
+
+        %pM     00:01:02:03:04:05
+        %pMF    00-01-02-03-04-05
+        %pm     000102030405
+
+        For printing 6-byte MAC/FDDI addresses in hex notation. The 'M' and 'm'
+        specifiers result in a printed address with ('M') or without ('m') byte
+        separators. The default byte separator is the colon (':').
+
+        Where FDDI addresses are concerned the 'F' specifier can be used after
+        the 'M' specifier to use dash ('-') separators instead of the default
+        separator.
+
+IPv4 addresses:
+
+        %pI4    1.2.3.4
+        %pi4    001.002.003.004
+        %p[Ii][hnbl]
+
+        For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4'
+        specifiers result in a printed address with ('i4') or without ('I4')
+        leading zeros.
+
+        The additional 'h', 'n', 'b', and 'l' specifiers are used to specify
+        host, network, big or little endian order addresses respectively. Where
+        no specifier is provided the default network/big endian order is used.
+
+IPv6 addresses:
+
+        %pI6    0001:0002:0003:0004:0005:0006:0007:0008
+        %pi6    00010002000300040005000600070008
+        %pI6c   1:2:3:4:5:6:7:8
+
+        For printing IPv6 network-order 16-bit hex addresses. The 'I6' and 'i6'
+        specifiers result in a printed address with ('I6') or without ('i6')
+        colon-separators. Leading zeros are always used.
+
+        The additional 'c' specifier can be used with the 'I' specifier to
+        print a compressed IPv6 address as described by
+        http://tools.ietf.org/html/rfc5952
+
+UUID/GUID addresses:
+
+        %pUb    00010203-0405-0607-0809-0a0b0c0d0e0f
+        %pUB    00010203-0405-0607-0809-0A0B0C0D0E0F
+        %pUl    03020100-0504-0706-0809-0a0b0c0e0e0f
+        %pUL    03020100-0504-0706-0809-0A0B0C0E0E0F
+
+        For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L',
+        'b' and 'B' specifiers are used to specify a little endian order in
+        lower ('l') or upper case ('L') hex characters - and big endian order
+        in lower ('b') or upper case ('B') hex characters.
+
+        Where no additional specifiers are used the default little endian
+        order with lower case hex characters will be printed.
+
+struct va_format:
+
+        %pV
+
+        For printing struct va_format structures. These contain a format string
+        and va_list as follows:
+
+        struct va_format {
+                const char *fmt;
+                va_list *va;
+        };
+
+        Do not use this feature without some mechanism to verify the
+        correctness of the format string and va_list arguments.
 
 u64 SHOULD be printed with %llu/%llx, (unsigned long long):
 
@@ -32,4 +146,5 @@ Reminder: sizeof() result is of type size_t.
 Thank you for your cooperation and attention.
 
 
-By Randy Dunlap <rdunlap@xenotime.net>
+By Randy Dunlap <rdunlap@xenotime.net> and
+Andrew Murray <amurray@mpc-data.co.uk>
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 99961993257a..91ecff07cede 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -223,9 +223,10 @@ When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
-        # mkdir /dev/cpuctl
-        # mount -t cgroup -ocpu none /dev/cpuctl
-        # cd /dev/cpuctl
+        # mount -t tmpfs cgroup_root /sys/fs/cgroup
+        # mkdir /sys/fs/cgroup/cpu
+        # mount -t cgroup -ocpu none /sys/fs/cgroup/cpu
+        # cd /sys/fs/cgroup/cpu
 
         # mkdir multimedia      # create "multimedia" group of tasks
         # mkdir browser         # create "browser" group of tasks
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 605b0d40329d..71b54d549987 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -129,9 +129,8 @@ priority!
 Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
 CPU bandwidth to task groups.
 
-This uses the /cgroup virtual file system and
-"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group.
+This uses the cgroup virtual file system and "<cgroup>/cpu.rt_runtime_us"
+to control the CPU time reserved for each control group.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -150,7 +149,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 
 There is work in progress to make the scheduling period for each group
-("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
+("<cgroup>/cpu.rt_period_us") configurable as well.
 
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 12f9ba20ccb7..550068466605 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -129,12 +129,12 @@ Limit injection to pages owned by memgroup. Specified by inode number
 of the memcg.
 
 Example:
-        mkdir /cgroup/hwpoison
+        mkdir /sys/fs/cgroup/mem/hwpoison
 
         usemem -m 100 -s 1000 &
-        echo `jobs -p` > /cgroup/hwpoison/tasks
+        echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
 
-        memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ')
+        memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
         echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
 
         page-types -p `pidof init`   --hwpoison  # shall do nothing