Merge branch 'master' into for-2.6.33

11 files changed, 502 insertions, 206 deletions

diff --git a/Documentation/fb/framebuffer.txt b/Documentation/fb/framebuffer.txt
index b3e3a0356839..fe79e3c8847d 100644
--- a/Documentation/fb/framebuffer.txt
+++ b/Documentation/fb/framebuffer.txt
@@ -312,10 +312,8 @@ and to the following documentation:
 8. Mailing list
 ---------------
 
-There are several frame buffer device related mailing lists at SourceForge:
-  - linux-fbdev-announce@lists.sourceforge.net, for announcements,
-  - linux-fbdev-user@lists.sourceforge.net, for generic user support,
-  - linux-fbdev-devel@lists.sourceforge.net, for project developers.
+There is a frame buffer device related mailing list at kernel.org:
+linux-fbdev@vger.kernel.org.
 
 Point your web browser to http://sourceforge.net/projects/linux-fbdev/ for
 subscription information and archive browsing.
diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt
index 9e94b9491d89..a91e2e2095b0 100644
--- a/Documentation/filesystems/caching/fscache.txt
+++ b/Documentation/filesystems/caching/fscache.txt
@@ -235,6 +235,7 @@ proc files.
                 neg=N   Number of negative lookups made
                 pos=N   Number of positive lookups made
                 crt=N   Number of objects created by lookup
+                tmo=N   Number of lookups timed out and requeued
         Updates n=N     Number of update cookie requests seen
                 nul=N   Number of upd reqs given a NULL parent
                 run=N   Number of upd reqs granted CPU time
@@ -250,8 +251,10 @@ proc files.
                 ok=N    Number of successful alloc reqs
                 wt=N    Number of alloc reqs that waited on lookup completion
                 nbf=N   Number of alloc reqs rejected -ENOBUFS
+                int=N   Number of alloc reqs aborted -ERESTARTSYS
                 ops=N   Number of alloc reqs submitted
                 owt=N   Number of alloc reqs waited for CPU time
+                abt=N   Number of alloc reqs aborted due to object death
         Retrvls n=N     Number of retrieval (read) requests seen
                 ok=N    Number of successful retr reqs
                 wt=N    Number of retr reqs that waited on lookup completion
@@ -261,6 +264,7 @@ proc files.
                 oom=N   Number of retr reqs failed -ENOMEM
                 ops=N   Number of retr reqs submitted
                 owt=N   Number of retr reqs waited for CPU time
+                abt=N   Number of retr reqs aborted due to object death
         Stores  n=N     Number of storage (write) requests seen
                 ok=N    Number of successful store reqs
                 agn=N   Number of store reqs on a page already pending storage
@@ -268,12 +272,37 @@ proc files.
                 oom=N   Number of store reqs failed -ENOMEM
                 ops=N   Number of store reqs submitted
                 run=N   Number of store reqs granted CPU time
+                pgs=N   Number of pages given store req processing time
+                rxd=N   Number of store reqs deleted from tracking tree
+                olm=N   Number of store reqs over store limit
+        VmScan  nos=N   Number of release reqs against pages with no pending store
+                gon=N   Number of release reqs against pages stored by time lock granted
+                bsy=N   Number of release reqs ignored due to in-progress store
+                can=N   Number of page stores cancelled due to release req
         Ops     pend=N  Number of times async ops added to pending queues
                 run=N   Number of times async ops given CPU time
                 enq=N   Number of times async ops queued for processing
+                can=N   Number of async ops cancelled
+                rej=N   Number of async ops rejected due to object lookup/create failure
                 dfr=N   Number of async ops queued for deferred release
                 rel=N   Number of async ops released
                 gc=N    Number of deferred-release async ops garbage collected
+        CacheOp alo=N   Number of in-progress alloc_object() cache ops
+                luo=N   Number of in-progress lookup_object() cache ops
+                luc=N   Number of in-progress lookup_complete() cache ops
+                gro=N   Number of in-progress grab_object() cache ops
+                upo=N   Number of in-progress update_object() cache ops
+                dro=N   Number of in-progress drop_object() cache ops
+                pto=N   Number of in-progress put_object() cache ops
+                syn=N   Number of in-progress sync_cache() cache ops
+                atc=N   Number of in-progress attr_changed() cache ops
+                rap=N   Number of in-progress read_or_alloc_page() cache ops
+                ras=N   Number of in-progress read_or_alloc_pages() cache ops
+                alp=N   Number of in-progress allocate_page() cache ops
+                als=N   Number of in-progress allocate_pages() cache ops
+                wrp=N   Number of in-progress write_page() cache ops
+                ucp=N   Number of in-progress uncache_page() cache ops
+                dsp=N   Number of in-progress dissociate_pages() cache ops
 
 
  (*) /proc/fs/fscache/histogram
@@ -299,6 +328,87 @@ proc files.
      jiffy range covered, and the SECS field the equivalent number of seconds.
 
 
+===========
+OBJECT LIST
+===========
+
+If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a
+list of all the objects currently allocated and allow them to be viewed
+through:
+
+        /proc/fs/fscache/objects
+
+This will look something like:
+
+        [root@andromeda ~]# head /proc/fs/fscache/objects
+        OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA       OBJECT_KEY, AUX_DATA
+        ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
+           17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
+           1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
+
+where the first set of columns before the '|' describe the object:
+
+        COLUMN  DESCRIPTION
+        ======= ===============================================================
+        OBJECT  Object debugging ID (appears as OBJ%x in some debug messages)
+        PARENT  Debugging ID of parent object
+        STAT    Object state
+        CHLDN   Number of child objects of this object
+        OPS     Number of outstanding operations on this object
+        OOP     Number of outstanding child object management operations
+        IPR
+        EX      Number of outstanding exclusive operations
+        READS   Number of outstanding read operations
+        EM      Object's event mask
+        EV      Events raised on this object
+        F       Object flags
+        S       Object slow-work work item flags
+
+and the second set of columns describe the object's cookie, if present:
+
+        COLUMN          DESCRIPTION
+        =============== =======================================================
+        NETFS_COOKIE_DEF Name of netfs cookie definition
+        TY              Cookie type (IX - index, DT - data, hex - special)
+        FL              Cookie flags
+        NETFS_DATA      Netfs private data stored in the cookie
+        OBJECT_KEY      Object key      } 1 column, with separating comma
+        AUX_DATA        Object aux data } presence may be configured
+
+The data shown may be filtered by attaching the a key to an appropriate keyring
+before viewing the file.  Something like:
+
+                keyctl add user fscache:objlist <restrictions> @s
+
+where <restrictions> are a selection of the following letters:
+
+        K       Show hexdump of object key (don't show if not given)
+        A       Show hexdump of object aux data (don't show if not given)
+
+and the following paired letters:
+
+        C       Show objects that have a cookie
+        c       Show objects that don't have a cookie
+        B       Show objects that are busy
+        b       Show objects that aren't busy
+        W       Show objects that have pending writes
+        w       Show objects that don't have pending writes
+        R       Show objects that have outstanding reads
+        r       Show objects that don't have outstanding reads
+        S       Show objects that have slow work queued
+        s       Show objects that don't have slow work queued
+
+If neither side of a letter pair is given, then both are implied.  For example:
+
+        keyctl add user fscache:objlist KB @s
+
+shows objects that are busy, and lists their object keys, but does not dump
+their auxiliary data.  It also implies "CcWwRrSs", but as 'B' is given, 'b' is
+not implied.
+
+By default all objects and all fields will be shown.
+
+
 =========
 DEBUGGING
 =========
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 2666b1ed5e9e..1902c57b72ef 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -641,7 +641,7 @@ data file must be retired (see the relinquish cookie function below).
 
 Furthermore, note that this does not cancel the asynchronous read or write
 operation started by the read/alloc and write functions, so the page
-invalidation and release functions must use:
+invalidation functions must use:
 
         bool fscache_check_page_write(struct fscache_cookie *cookie,
                                       struct page *page);
@@ -654,6 +654,25 @@ to see if a page is being written to the cache, and:
 to wait for it to finish if it is.
 
 
+When releasepage() is being implemented, a special FS-Cache function exists to
+manage the heuristics of coping with vmscan trying to eject pages, which may
+conflict with the cache trying to write pages to the cache (which may itself
+need to allocate memory):
+
+        bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+                                        struct page *page,
+                                        gfp_t gfp);
+
+This takes the netfs cookie, and the page and gfp arguments as supplied to
+releasepage().  It will return false if the page cannot be released yet for
+some reason and if it returns true, the page has been uncached and can now be
+released.
+
+To make a page available for release, this function may wait for an outstanding
+storage request to complete, or it may attempt to cancel the storage request -
+in which case the page will not be stored in the cache this time.
+
+
 ==========================
 INDEX AND DATA FILE UPDATE
 ==========================
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index bf4f4b7e11b3..6d94e0696f8c 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -134,9 +134,15 @@ ro                   	Mount filesystem read only. Note that ext4 will
                         mount options "ro,noload" can be used to prevent
                         writes to the filesystem.
 
+journal_checksum        Enable checksumming of the journal transactions.
+                        This will allow the recovery code in e2fsck and the
+                        kernel to detect corruption in the kernel.  It is a
+                        compatible change and will be ignored by older kernels.
+
 journal_async_commit    Commit block can be written to disk without waiting
                         for descriptor blocks. If enabled older kernels cannot
-                        mount the device.
+                        mount the device. This will enable 'journal_checksum'
+                        internally.
 
 journal=update          Update the ext4 file system's journal to the current
                         format.
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index c2a0871280a0..c58b9f5ba002 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -20,15 +20,16 @@ Lots of code taken from ext3 and other projects.
 Authors in alphabetical order:
 Joel Becker   <joel.becker@oracle.com>
 Zach Brown    <zach.brown@oracle.com>
-Mark Fasheh   <mark.fasheh@oracle.com>
+Mark Fasheh   <mfasheh@suse.com>
 Kurt Hackel   <kurt.hackel@oracle.com>
+Tao Ma        <tao.ma@oracle.com>
 Sunil Mushran <sunil.mushran@oracle.com>
 Manish Singh  <manish.singh@oracle.com>
+Tiger Yang    <tiger.yang@oracle.com>
 
 Caveats
 =======
 Features which OCFS2 does not support yet:
-        - quotas
         - Directory change notification (F_NOTIFY)
         - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
 
@@ -70,7 +71,6 @@ commit=nrsec	(*)	Ocfs2 can be told to sync all its data and metadata
                         performance.
 localalloc=8(*)         Allows custom localalloc size in MB. If the value is too
                         large, the fs will silently revert it to the default.
-                        Localalloc is not enabled for local mounts.
 localflocks             This disables cluster aware flock.
 inode64                 Indicates that Ocfs2 is allowed to create inodes at
                         any location in the filesystem, including those which
diff --git a/Documentation/i2c/busses/i2c-piix4 b/Documentation/i2c/busses/i2c-piix4
index c5b37c570554..ac540c71c7eb 100644
--- a/Documentation/i2c/busses/i2c-piix4
+++ b/Documentation/i2c/busses/i2c-piix4
@@ -8,7 +8,7 @@ Supported adapters:
     Datasheet: Only available via NDA from ServerWorks
   * ATI IXP200, IXP300, IXP400, SB600, SB700 and SB800 southbridges
     Datasheet: Not publicly available
-  * AMD SB900
+  * AMD Hudson-2
     Datasheet: Not publicly available
   * Standard Microsystems (SMSC) SLC90E66 (Victory66) southbridge
     Datasheet: Publicly available at the SMSC website http://www.smsc.com
diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt
index ebc50f808ea4..9dbf4470c7e1 100644
--- a/Documentation/slow-work.txt
+++ b/Documentation/slow-work.txt
@@ -41,6 +41,13 @@ expand files, provided the time taken to do so isn't too long.
 Operations of both types may sleep during execution, thus tying up the thread
 loaned to it.
 
+A further class of work item is available, based on the slow work item class:
+
+ (*) Delayed slow work items.
+
+These are slow work items that have a timer to defer queueing of the item for
+a while.
+
 
 THREAD-TO-CLASS ALLOCATION
 --------------------------
@@ -64,9 +71,11 @@ USING SLOW WORK ITEMS
 Firstly, a module or subsystem wanting to make use of slow work items must
 register its interest:
 
-         int ret = slow_work_register_user();
+         int ret = slow_work_register_user(struct module *module);
 
-This will return 0 if successful, or a -ve error upon failure.
+This will return 0 if successful, or a -ve error upon failure.  The module
+pointer should be the module interested in using this facility (almost
+certainly THIS_MODULE).
 
 
 Slow work items may then be set up by:
@@ -93,6 +102,10 @@ Slow work items may then be set up by:
 
      or:
 
+        delayed_slow_work_init(&myitem, &myitem_ops);
+
+     or:
+
         vslow_work_init(&myitem, &myitem_ops);
 
      depending on its class.
@@ -102,15 +115,92 @@ A suitably set up work item can then be enqueued for processing:
         int ret = slow_work_enqueue(&myitem);
 
 This will return a -ve error if the thread pool is unable to gain a reference
-on the item, 0 otherwise.
+on the item, 0 otherwise, or (for delayed work):
+
+        int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay);
 
 
 The items are reference counted, so there ought to be no need for a flush
-operation.  When all a module's slow work items have been processed, and the
+operation.  But as the reference counting is optional, means to cancel
+existing work items are also included:
+
+        cancel_slow_work(&myitem);
+        cancel_delayed_slow_work(&myitem);
+
+can be used to cancel pending work.  The above cancel function waits for
+existing work to have been executed (or prevent execution of them, depending
+on timing).
+
+
+When all a module's slow work items have been processed, and the
 module has no further interest in the facility, it should unregister its
 interest:
 
-        slow_work_unregister_user();
+        slow_work_unregister_user(struct module *module);
+
+The module pointer is used to wait for all outstanding work items for that
+module before completing the unregistration.  This prevents the put_ref() code
+from being taken away before it completes.  module should almost certainly be
+THIS_MODULE.
+
+
+================
+HELPER FUNCTIONS
+================
+
+The slow-work facility provides a function by which it can be determined
+whether or not an item is queued for later execution:
+
+        bool queued = slow_work_is_queued(struct slow_work *work);
+
+If it returns false, then the item is not on the queue (it may be executing
+with a requeue pending).  This can be used to work out whether an item on which
+another depends is on the queue, thus allowing a dependent item to be queued
+after it.
+
+If the above shows an item on which another depends not to be queued, then the
+owner of the dependent item might need to wait.  However, to avoid locking up
+the threads unnecessarily be sleeping in them, it can make sense under some
+circumstances to return the work item to the queue, thus deferring it until
+some other items have had a chance to make use of the yielded thread.
+
+To yield a thread and defer an item, the work function should simply enqueue
+the work item again and return.  However, this doesn't work if there's nothing
+actually on the queue, as the thread just vacated will jump straight back into
+the item's work function, thus busy waiting on a CPU.
+
+Instead, the item should use the thread to wait for the dependency to go away,
+but rather than using schedule() or schedule_timeout() to sleep, it should use
+the following function:
+
+        bool requeue = slow_work_sleep_till_thread_needed(
+                        struct slow_work *work,
+                        signed long *_timeout);
+
+This will add a second wait and then sleep, such that it will be woken up if
+either something appears on the queue that could usefully make use of the
+thread - and behind which this item can be queued, or if the event the caller
+set up to wait for happens.  True will be returned if something else appeared
+on the queue and this work function should perhaps return, of false if
+something else woke it up.  The timeout is as for schedule_timeout().
+
+For example:
+
+        wq = bit_waitqueue(&my_flags, MY_BIT);
+        init_wait(&wait);
+        requeue = false;
+        do {
+                prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+                if (!test_bit(MY_BIT, &my_flags))
+                        break;
+                requeue = slow_work_sleep_till_thread_needed(&my_work,
+                                                             &timeout);
+        } while (timeout > 0 && !requeue);
+        finish_wait(wq, &wait);
+        if (!test_bit(MY_BIT, &my_flags)
+                goto do_my_thing;
+        if (requeue)
+                return; // to slow_work
 
 
 ===============
@@ -118,7 +208,8 @@ ITEM OPERATIONS
 ===============
 
 Each work item requires a table of operations of type struct slow_work_ops.
-All members are required:
+Only ->execute() is required; the getting and putting of a reference and the
+describing of an item are all optional.
 
  (*) Get a reference on an item:
 
@@ -148,6 +239,16 @@ All members are required:
      This should perform the work required of the item.  It may sleep, it may
      perform disk I/O and it may wait for locks.
 
+ (*) View an item through /proc:
+
+        void (*desc)(struct slow_work *work, struct seq_file *m);
+
+     If supplied, this should print to 'm' a small string describing the work
+     the item is to do.  This should be no more than about 40 characters, and
+     shouldn't include a newline character.
+
+     See the 'Viewing executing and queued items' section below.
+
 
 ==================
 POOL CONFIGURATION
@@ -172,3 +273,50 @@ The slow-work thread pool has a number of configurables:
      is bounded to between 1 and one fewer than the number of active threads.
      This ensures there is always at least one thread that can process very
      slow work items, and always at least one thread that won't.
+
+
+==================================
+VIEWING EXECUTING AND QUEUED ITEMS
+==================================
+
+If CONFIG_SLOW_WORK_DEBUG is enabled, a debugfs file is made available:
+
+        /sys/kernel/debug/slow_work/runqueue
+
+through which the list of work items being executed and the queues of items to
+be executed may be viewed.  The owner of a work item is given the chance to
+add some information of its own.
+
+The contents look something like the following:
+
+    THR PID   ITEM ADDR        FL MARK  DESC
+    === ===== ================ == ===== ==========
+      0  3005 ffff880023f52348  a 952ms FSC: OBJ17d3: LOOK
+      1  3006 ffff880024e33668  2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2
+      2  3165 ffff8800296dd180  a 424ms FSC: OBJ17e4: LOOK
+      3  4089 ffff8800262c8d78  a 212ms FSC: OBJ17ea: CRTN
+      4  4090 ffff88002792bed8  2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2
+      5  4092 ffff88002a0ef308  2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2
+      6  4094 ffff88002abaf4b8  2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2
+      7  4095 ffff88002bb188e0  a 388ms FSC: OBJ17e9: CRTN
+    vsq     - ffff880023d99668  1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2
+    vsq     - ffff8800295d1740  1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2
+    vsq     - ffff880025ba3308  1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2
+    vsq     - ffff880024ec83e0  1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2
+    vsq     - ffff880026618e00  1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2
+    vsq     - ffff880025a2a4b8  1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2
+    vsq     - ffff880023cbe6d8  9 212ms FSC: OBJ17eb: LOOK
+    vsq     - ffff880024d37590  9 212ms FSC: OBJ17ec: LOOK
+    vsq     - ffff880027746cb0  9 212ms FSC: OBJ17ed: LOOK
+    vsq     - ffff880024d37ae8  9 212ms FSC: OBJ17ee: LOOK
+    vsq     - ffff880024d37cb0  9 212ms FSC: OBJ17ef: LOOK
+    vsq     - ffff880025036550  9 212ms FSC: OBJ17f0: LOOK
+    vsq     - ffff8800250368e0  9 212ms FSC: OBJ17f1: LOOK
+    vsq     - ffff880025036aa8  9 212ms FSC: OBJ17f2: LOOK
+
+In the 'THR' column, executing items show the thread they're occupying and
+queued threads indicate which queue they're on.  'PID' shows the process ID of
+a slow-work thread that's executing something.  'FL' shows the work item flags.
+'MARK' indicates how long since an item was queued or began executing.  Lastly,
+the 'DESC' column permits the owner of an item to give some information.
+
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 1c8eb4518ce0..fd9a2f67edf2 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -522,7 +522,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     pcm_devs       - Number of PCM devices assigned to each card
                      (default = 1, up to 4)
     pcm_substreams - Number of PCM substreams assigned to each PCM
-                     (default = 8, up to 16)
+                     (default = 8, up to 128)
     hrtimer        - Use hrtimer (=1, default) or system timer (=0)
     fake_buffer    - Fake buffer allocations (default = 1)
 
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index 70d68ce8640a..a87dc277a5ca 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -1,5 +1,5 @@
 Generic Thermal Sysfs driver How To
-=========================
+===================================
 
 Written by Sujith Thomas <sujith.thomas@intel.com>, Zhang Rui <rui.zhang@intel.com>
 
@@ -10,20 +10,20 @@ Copyright (c)  2008 Intel Corporation
 
 0. Introduction
 
-The generic thermal sysfs provides a set of interfaces for thermal zone devices (sensors)
-and thermal cooling devices (fan, processor...) to register with the thermal management
-solution and to be a part of it.
+The generic thermal sysfs provides a set of interfaces for thermal zone
+devices (sensors) and thermal cooling devices (fan, processor...) to register
+with the thermal management solution and to be a part of it.
 
-This how-to focuses on enabling new thermal zone and cooling devices to participate
-in thermal management.
-This solution is platform independent and any type of thermal zone devices and
-cooling devices should be able to make use of the infrastructure.
+This how-to focuses on enabling new thermal zone and cooling devices to
+participate in thermal management.
+This solution is platform independent and any type of thermal zone devices
+and cooling devices should be able to make use of the infrastructure.
 
-The main task of the thermal sysfs driver is to expose thermal zone attributes as well
-as cooling device attributes to the user space.
-An intelligent thermal management application can make decisions based on inputs
-from thermal zone attributes (the current temperature and trip point temperature)
-and throttle appropriate devices.
+The main task of the thermal sysfs driver is to expose thermal zone attributes
+as well as cooling device attributes to the user space.
+An intelligent thermal management application can make decisions based on
+inputs from thermal zone attributes (the current temperature and trip point
+temperature) and throttle appropriate devices.
 
 [0-*]   denotes any positive number starting from 0
 [1-*]   denotes any positive number starting from 1
@@ -31,77 +31,77 @@ and throttle appropriate devices.
 1. thermal sysfs driver interface functions
 
 1.1 thermal zone device interface
-1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *name, int trips,
-                                void *devdata, struct thermal_zone_device_ops *ops)
-
-        This interface function adds a new thermal zone device (sensor) to
-        /sys/class/thermal folder as thermal_zone[0-*].
-        It tries to bind all the thermal cooling devices registered at the same time.
-
-        name: the thermal zone name.
-        trips: the total number of trip points this thermal zone supports.
-        devdata: device private data
-        ops: thermal zone device call-backs.
-                .bind: bind the thermal zone device with a thermal cooling device.
-                .unbind: unbind the thermal zone device with a thermal cooling device.
-                .get_temp: get the current temperature of the thermal zone.
-                .get_mode: get the current mode (user/kernel) of the thermal zone.
-                           "kernel" means thermal management is done in kernel.
-                           "user" will prevent kernel thermal driver actions upon trip points
-                           so that user applications can take charge of thermal management.
-                .set_mode: set the mode (user/kernel) of the thermal zone.
-                .get_trip_type: get the type of certain trip point.
-                .get_trip_temp: get the temperature above which the certain trip point
-                                will be fired.
+1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *name,
+                int trips, void *devdata, struct thermal_zone_device_ops *ops)
+
+    This interface function adds a new thermal zone device (sensor) to
+    /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
+    thermal cooling devices registered at the same time.
+
+    name: the thermal zone name.
+    trips: the total number of trip points this thermal zone supports.
+    devdata: device private data
+    ops: thermal zone device call-backs.
+        .bind: bind the thermal zone device with a thermal cooling device.
+        .unbind: unbind the thermal zone device with a thermal cooling device.
+        .get_temp: get the current temperature of the thermal zone.
+        .get_mode: get the current mode (user/kernel) of the thermal zone.
+            - "kernel" means thermal management is done in kernel.
+            - "user" will prevent kernel thermal driver actions upon trip points
+              so that user applications can take charge of thermal management.
+        .set_mode: set the mode (user/kernel) of the thermal zone.
+        .get_trip_type: get the type of certain trip point.
+        .get_trip_temp: get the temperature above which the certain trip point
+                        will be fired.
 
 1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
-        This interface function removes the thermal zone device.
-        It deletes the corresponding entry form /sys/class/thermal folder and unbind all
-        the thermal cooling devices it uses.
+    This interface function removes the thermal zone device.
+    It deletes the corresponding entry form /sys/class/thermal folder and
+    unbind all the thermal cooling devices it uses.
 
 1.2 thermal cooling device interface
 1.2.1 struct thermal_cooling_device *thermal_cooling_device_register(char *name,
-                                        void *devdata, struct thermal_cooling_device_ops *)
-
-        This interface function adds a new thermal cooling device (fan/processor/...) to
-        /sys/class/thermal/ folder as cooling_device[0-*].
-        It tries to bind itself to all the thermal zone devices register at the same time.
-        name: the cooling device name.
-        devdata: device private data.
-        ops: thermal cooling devices call-backs.
-                .get_max_state: get the Maximum throttle state of the cooling device.
-                .get_cur_state: get the Current throttle state of the cooling device.
-                .set_cur_state: set the Current throttle state of the cooling device.
+                void *devdata, struct thermal_cooling_device_ops *)
+
+    This interface function adds a new thermal cooling device (fan/processor/...)
+    to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+    to all the thermal zone devices register at the same time.
+    name: the cooling device name.
+    devdata: device private data.
+    ops: thermal cooling devices call-backs.
+        .get_max_state: get the Maximum throttle state of the cooling device.
+        .get_cur_state: get the Current throttle state of the cooling device.
+        .set_cur_state: set the Current throttle state of the cooling device.
 
 1.2.2 void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 
-        This interface function remove the thermal cooling device.
-        It deletes the corresponding entry form /sys/class/thermal folder and unbind
-        itself from all the thermal zone devices using it.
+    This interface function remove the thermal cooling device.
+    It deletes the corresponding entry form /sys/class/thermal folder and
+    unbind itself from all the thermal zone devices using it.
 
 1.3 interface for binding a thermal zone device with a thermal cooling device
 1.3.1 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
-                        int trip, struct thermal_cooling_device *cdev);
+                int trip, struct thermal_cooling_device *cdev);
 
-        This interface function bind a thermal cooling device to the certain trip point
-        of a thermal zone device.
-        This function is usually called in the thermal zone device .bind callback.
-        tz: the thermal zone device
-        cdev: thermal cooling device
-        trip: indicates which trip point the cooling devices is associated with
-                 in this thermal zone.
+    This interface function bind a thermal cooling device to the certain trip
+    point of a thermal zone device.
+    This function is usually called in the thermal zone device .bind callback.
+    tz: the thermal zone device
+    cdev: thermal cooling device
+    trip: indicates which trip point the cooling devices is associated with
+          in this thermal zone.
 
 1.3.2 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
-                                int trip, struct thermal_cooling_device *cdev);
+                int trip, struct thermal_cooling_device *cdev);
 
-        This interface function unbind a thermal cooling device from the certain trip point
-        of a thermal zone device.
-        This function is usually called in the thermal zone device .unbind callback.
-        tz: the thermal zone device
-        cdev: thermal cooling device
-        trip: indicates which trip point the cooling devices is associated with
-                in this thermal zone.
+    This interface function unbind a thermal cooling device from the certain
+    trip point of a thermal zone device. This function is usually called in
+    the thermal zone device .unbind callback.
+    tz: the thermal zone device
+    cdev: thermal cooling device
+    trip: indicates which trip point the cooling devices is associated with
+          in this thermal zone.
 
 2. sysfs attributes structure
 
@@ -114,153 +114,166 @@ if hwmon is compiled in or built as a module.
 
 Thermal zone device sys I/F, created once it's registered:
 /sys/class/thermal/thermal_zone[0-*]:
-        |-----type:                     Type of the thermal zone
-        |-----temp:                     Current temperature
-        |-----mode:                     Working mode of the thermal zone
-        |-----trip_point_[0-*]_temp:    Trip point temperature
-        |-----trip_point_[0-*]_type:    Trip point type
+    |---type:                   Type of the thermal zone
+    |---temp:                   Current temperature
+    |---mode:                   Working mode of the thermal zone
+    |---trip_point_[0-*]_temp:  Trip point temperature
+    |---trip_point_[0-*]_type:  Trip point type
 
 Thermal cooling device sys I/F, created once it's registered:
 /sys/class/thermal/cooling_device[0-*]:
-        |-----type :                    Type of the cooling device(processor/fan/...)
-        |-----max_state:                Maximum cooling state of the cooling device
-        |-----cur_state:                Current cooling state of the cooling device
+    |---type:                   Type of the cooling device(processor/fan/...)
+    |---max_state:              Maximum cooling state of the cooling device
+    |---cur_state:              Current cooling state of the cooling device
 
 
-These two dynamic attributes are created/removed in pairs.
-They represent the relationship between a thermal zone and its associated cooling device.
-They are created/removed for each
-thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device successful execution.
+Then next two dynamic attributes are created/removed in pairs. They represent
+the relationship between a thermal zone and its associated cooling device.
+They are created/removed for each successful execution of
+thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device.
 
-/sys/class/thermal/thermal_zone[0-*]
-        |-----cdev[0-*]:                The [0-*]th cooling device in the current thermal zone
-        |-----cdev[0-*]_trip_point:     Trip point that cdev[0-*] is associated with
+/sys/class/thermal/thermal_zone[0-*]:
+    |---cdev[0-*]:              [0-*]th cooling device in current thermal zone
+    |---cdev[0-*]_trip_point:   Trip point that cdev[0-*] is associated with
 
 Besides the thermal zone device sysfs I/F and cooling device sysfs I/F,
-the generic thermal driver also creates a hwmon sysfs I/F for each _type_ of
-thermal zone device. E.g. the generic thermal driver registers one hwmon class device
-and build the associated hwmon sysfs I/F for all the registered ACPI thermal zones.
+the generic thermal driver also creates a hwmon sysfs I/F for each _type_
+of thermal zone device. E.g. the generic thermal driver registers one hwmon
+class device and build the associated hwmon sysfs I/F for all the registered
+ACPI thermal zones.
+
 /sys/class/hwmon/hwmon[0-*]:
-        |-----name:                     The type of the thermal zone devices.
-        |-----temp[1-*]_input:          The current temperature of thermal zone [1-*].
-        |-----temp[1-*]_critical:       The critical trip point of thermal zone [1-*].
+    |---name:                   The type of the thermal zone devices
+    |---temp[1-*]_input:        The current temperature of thermal zone [1-*]
+    |---temp[1-*]_critical:     The critical trip point of thermal zone [1-*]
+
 Please read Documentation/hwmon/sysfs-interface for additional information.
 
 ***************************
 * Thermal zone attributes *
 ***************************
 
-type                            Strings which represent the thermal zone type.
-                                This is given by thermal zone driver as part of registration.
-                                Eg: "acpitz" indicates it's an ACPI thermal device.
-                                In order to keep it consistent with hwmon sys attribute,
-                                this should be a short, lowercase string,
-                                not containing spaces nor dashes.
-                                RO
-                                Required
-
-temp                            Current temperature as reported by thermal zone (sensor)
-                                Unit: millidegree Celsius
-                                RO
-                                Required
-
-mode                            One of the predefined values in [kernel, user]
-                                This file gives information about the algorithm
-                                that is currently managing the thermal zone.
-                                It can be either default kernel based algorithm
-                                or user space application.
-                                RW
-                                Optional
-                                kernel  = Thermal management in kernel thermal zone driver.
-                                user    = Preventing kernel thermal zone driver actions upon
-                                          trip points so that user application can take full
-                                          charge of the thermal management.
-
-trip_point_[0-*]_temp           The temperature above which trip point will be fired
-                                Unit: millidegree Celsius
-                                RO
-                                Optional
-
-trip_point_[0-*]_type           Strings which indicate the type of the trip point
-                                E.g. it can be one of critical, hot, passive,
-                                    active[0-*] for ACPI thermal zone.
-                                RO
-                                Optional
-
-cdev[0-*]                       Sysfs link to the thermal cooling device node where the sys I/F
-                                for cooling device throttling control represents.
-                                RO
-                                Optional
-
-cdev[0-*]_trip_point            The trip point with which cdev[0-*] is associated in this thermal zone
-                                -1 means the cooling device is not associated with any trip point.
-                                RO
-                                Optional
-
-******************************
-* Cooling device  attributes *
-******************************
-
-type                            String which represents the type of device
-                                eg: For generic ACPI: this should be "Fan",
-                                "Processor" or "LCD"
-                                eg. For memory controller device on intel_menlow platform:
-                                this should be "Memory controller"
-                                RO
-                                Required
-
-max_state                       The maximum permissible cooling state of this cooling device.
-                                RO
-                                Required
-
-cur_state                       The current cooling state of this cooling device.
-                                the value can any integer numbers between 0 and max_state,
-                                cur_state == 0 means no cooling
-                                cur_state == max_state means the maximum cooling.
-                                RW
-                                Required
+type
+        Strings which represent the thermal zone type.
+        This is given by thermal zone driver as part of registration.
+        E.g: "acpitz" indicates it's an ACPI thermal device.
+        In order to keep it consistent with hwmon sys attribute; this should
+        be a short, lowercase string, not containing spaces nor dashes.
+        RO, Required
+
+temp
+        Current temperature as reported by thermal zone (sensor).
+        Unit: millidegree Celsius
+        RO, Required
+
+mode
+        One of the predefined values in [kernel, user].
+        This file gives information about the algorithm that is currently
+        managing the thermal zone. It can be either default kernel based
+        algorithm or user space application.
+        kernel  = Thermal management in kernel thermal zone driver.
+        user    = Preventing kernel thermal zone driver actions upon
+                  trip points so that user application can take full
+                  charge of the thermal management.
+        RW, Optional
+
+trip_point_[0-*]_temp
+        The temperature above which trip point will be fired.
+        Unit: millidegree Celsius
+        RO, Optional
+
+trip_point_[0-*]_type
+        Strings which indicate the type of the trip point.
+        E.g. it can be one of critical, hot, passive, active[0-*] for ACPI
+        thermal zone.
+        RO, Optional
+
+cdev[0-*]
+        Sysfs link to the thermal cooling device node where the sys I/F
+        for cooling device throttling control represents.
+        RO, Optional
+
+cdev[0-*]_trip_point
+        The trip point with which cdev[0-*] is associated in this thermal
+        zone; -1 means the cooling device is not associated with any trip
+        point.
+        RO, Optional
+
+passive
+        Attribute is only present for zones in which the passive cooling
+        policy is not supported by native thermal driver. Default is zero
+        and can be set to a temperature (in millidegrees) to enable a
+        passive trip point for the zone. Activation is done by polling with
+        an interval of 1 second.
+        Unit: millidegrees Celsius
+        RW, Optional
+
+*****************************
+* Cooling device attributes *
+*****************************
+
+type
+        String which represents the type of device, e.g:
+        - for generic ACPI: should be "Fan", "Processor" or "LCD"
+        - for memory controller device on intel_menlow platform:
+          should be "Memory controller".
+        RO, Required
+
+max_state
+        The maximum permissible cooling state of this cooling device.
+        RO, Required
+
+cur_state
+        The current cooling state of this cooling device.
+        The value can any integer numbers between 0 and max_state:
+        - cur_state == 0 means no cooling
+        - cur_state == max_state means the maximum cooling.
+        RW, Required
 
 3. A simple implementation
 
-ACPI thermal zone may support multiple trip points like critical/hot/passive/active.
-If an ACPI thermal zone supports critical, passive, active[0] and active[1] at the same time,
-it may register itself as a thermal_zone_device (thermal_zone1) with 4 trip points in all.
-It has one processor and one fan, which are both registered as thermal_cooling_device.
-If the processor is listed in _PSL method, and the fan is listed in _AL0 method,
-the sys I/F structure will be built like this:
+ACPI thermal zone may support multiple trip points like critical, hot,
+passive, active. If an ACPI thermal zone supports critical, passive,
+active[0] and active[1] at the same time, it may register itself as a
+thermal_zone_device (thermal_zone1) with 4 trip points in all.
+It has one processor and one fan, which are both registered as
+thermal_cooling_device.
+
+If the processor is listed in _PSL method, and the fan is listed in _AL0
+method, the sys I/F structure will be built like this:
 
 /sys/class/thermal:
 
 |thermal_zone1:
-        |-----type:                     acpitz
-        |-----temp:                     37000
-        |-----mode:                     kernel
-        |-----trip_point_0_temp:        100000
-        |-----trip_point_0_type:        critical
-        |-----trip_point_1_temp:        80000
-        |-----trip_point_1_type:        passive
-        |-----trip_point_2_temp:        70000
-        |-----trip_point_2_type:        active0
-        |-----trip_point_3_temp:        60000
-        |-----trip_point_3_type:        active1
-        |-----cdev0:                    --->/sys/class/thermal/cooling_device0
-        |-----cdev0_trip_point:         1       /* cdev0 can be used for passive */
-        |-----cdev1:                    --->/sys/class/thermal/cooling_device3
-        |-----cdev1_trip_point:         2       /* cdev1 can be used for active[0]*/
+    |---type:                   acpitz
+    |---temp:                   37000
+    |---mode:                   kernel
+    |---trip_point_0_temp:      100000
+    |---trip_point_0_type:      critical
+    |---trip_point_1_temp:      80000
+    |---trip_point_1_type:      passive
+    |---trip_point_2_temp:      70000
+    |---trip_point_2_type:      active0
+    |---trip_point_3_temp:      60000
+    |---trip_point_3_type:      active1
+    |---cdev0:                  --->/sys/class/thermal/cooling_device0
+    |---cdev0_trip_point:       1       /* cdev0 can be used for passive */
+    |---cdev1:                  --->/sys/class/thermal/cooling_device3
+    |---cdev1_trip_point:       2       /* cdev1 can be used for active[0]*/
 
 |cooling_device0:
-        |-----type:                     Processor
-        |-----max_state:                8
-        |-----cur_state:                0
+    |---type:                   Processor
+    |---max_state:              8
+    |---cur_state:              0
 
 |cooling_device3:
-        |-----type:                     Fan
-        |-----max_state:                2
-        |-----cur_state:                0
+    |---type:                   Fan
+    |---max_state:              2
+    |---cur_state:              0
 
 /sys/class/hwmon:
 
 |hwmon0:
-        |-----name:                     acpitz
-        |-----temp1_input:              37000
-        |-----temp1_crit:               100000
+    |---name:                   acpitz
+    |---temp1_input:            37000
+    |---temp1_crit:             100000
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 957b22fde2df..8179692fbb90 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1231,6 +1231,7 @@ something like this simple program:
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <string.h>
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -1265,6 +1266,7 @@ const char *find_debugfs(void)
                return NULL;
        }
 
+       strcat(debugfs, "/tracing/");
        debugfs_found = 1;
 
        return debugfs;
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index 3ec4f2a22585..4793c6aac733 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -218,7 +218,7 @@ static void fatal(const char *x, ...)
         exit(EXIT_FAILURE);
 }
 
-int checked_open(const char *pathname, int flags)
+static int checked_open(const char *pathname, int flags)
 {
         int fd = open(pathname, flags);