13 files changed, 318 insertions, 215 deletions

diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index 6208f55c44c3..57e0b80a5274 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -18,11 +18,11 @@ the 9p client is available in the form of a USENIX paper:
 
 Other applications are described in the following papers:
         * XCPU & Clustering
-                http://www.xcpu.org/xcpu-talk.pdf
+                http://xcpu.org/papers/xcpu-talk.pdf
         * KVMFS: control file system for KVM
-                http://www.xcpu.org/kvmfs.pdf
-        * CellFS: A New ProgrammingModel for the Cell BE
-                http://www.xcpu.org/cellfs-talk.pdf
+                http://xcpu.org/papers/kvmfs.pdf
+        * CellFS: A New Programming Model for the Cell BE
+                http://xcpu.org/papers/cellfs-talk.pdf
         * PROSE I/O: Using 9p to enable Application Partitions
                 http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf
 
@@ -48,6 +48,7 @@ OPTIONS
                                 (see rfdno and wfdno)
                         virtio  - connect to the next virtio channel available
                                 (from lguest or KVM with trans_virtio module)
+                        rdma    - connect to a specified RDMA channel
 
   uname=name    user name to attempt mount as on the remote server.  The
                 server may override or ignore this value.  Certain user
@@ -59,16 +60,22 @@ OPTIONS
   cache=mode    specifies a caching policy.  By default, no caches are used.
                         loose = no attempts are made at consistency,
                                 intended for exclusive, read-only mounts
+                        fscache = use FS-Cache for a persistent, read-only
+                                cache backend.
 
   debug=n       specifies debug level.  The debug level is a bitmask.
-                        0x01 = display verbose error messages
-                        0x02 = developer debug (DEBUG_CURRENT)
-                        0x04 = display 9p trace
-                        0x08 = display VFS trace
-                        0x10 = display Marshalling debug
-                        0x20 = display RPC debug
-                        0x40 = display transport debug
-                        0x80 = display allocation debug
+                        0x01  = display verbose error messages
+                        0x02  = developer debug (DEBUG_CURRENT)
+                        0x04  = display 9p trace
+                        0x08  = display VFS trace
+                        0x10  = display Marshalling debug
+                        0x20  = display RPC debug
+                        0x40  = display transport debug
+                        0x80  = display allocation debug
+                        0x100 = display protocol message debug
+                        0x200 = display Fid debug
+                        0x400 = display packet debug
+                        0x800 = display fscache tracing debug
 
   rfdno=n       the file descriptor for reading with trans=fd
 
@@ -100,6 +107,10 @@ OPTIONS
                         any   = v9fs does single attach and performs all
                                 operations as one user
 
+  cachetag      cache tag to use the specified persistent cache.
+                cache tags for existing cache sessions can be listed at
+                /sys/fs/9p/caches. (applies only to cache=fscache)
+
 RESOURCES
 =========
 
@@ -118,7 +129,7 @@ and export.
 A Linux version of the 9p server is now maintained under the npfs project
 on sourceforge (http://sourceforge.net/projects/npfs).  The currently
 maintained version is the single-threaded version of the server (named spfs)
-available from the same CVS repository.
+available from the same SVN repository.
 
 There are user and developer mailing lists available through the v9fs project
 on sourceforge (http://sourceforge.net/projects/v9fs).
@@ -126,7 +137,8 @@ on sourceforge (http://sourceforge.net/projects/v9fs).
 A stand-alone version of the module (which should build for any 2.6 kernel)
 is available via (http://github.com/ericvh/9p-sac/tree/master)
 
-News and other information is maintained on SWiK (http://swik.net/v9fs).
+News and other information is maintained on SWiK (http://swik.net/v9fs)
+and the Wiki (http://sf.net/apps/mediawiki/v9fs/index.php).
 
 Bug reports may be issued through the kernel.org bugzilla 
 (http://bugzilla.kernel.org)
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/ext3.txt b/Documentation/filesystems/ext3.txt
index 570f9bd9be2b..05d5cf1d743f 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -123,10 +123,18 @@ resuid=n		The user ID which may use the reserved blocks.
 
 sb=n                    Use alternate superblock at this location.
 
-quota
-noquota
-grpquota
-usrquota
+quota                   These options are ignored by the filesystem. They
+noquota                 are used only by quota tools to recognize volumes
+grpquota                where quota should be turned on. See documentation
+usrquota                in the quota-tools package for more details
+                        (http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type>      These options tell filesystem details about quota
+usrjquota=<file>        so that quota information can be properly updated
+grpjquota=<file>        during journal replay. They replace the above
+                        quota options. See documentation in the quota-tools
+                        package for more details
+                        (http://sourceforge.net/projects/linuxquota).
 
 bh              (*)     ext3 associates buffer heads to data pages to
 nobh                    (a) cache disk block mapping information
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 18b5ec8cea45..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.
@@ -282,9 +288,16 @@ stripe=n		Number of filesystem blocks that mballoc will try
                         to use for allocation size and alignment. For RAID5/6
                         systems this should be the number of data
                         disks *  RAID chunk size in file system blocks.
-delalloc        (*)     Deferring block allocation until write-out time.
-nodelalloc              Disable delayed allocation. Blocks are allocation
-                        when data is copied from user to page cache.
+
+delalloc        (*)     Defer block allocation until just before ext4
+                        writes out the block(s) in question.  This
+                        allows ext4 to better allocation decisions
+                        more efficiently.
+nodelalloc              Disable delayed allocation.  Blocks are allocated
+                        when the data is copied from userspace to the
+                        page cache, either via the write(2) system call
+                        or when an mmap'ed page which was previously
+                        unallocated is written for the first time.
 
 max_batch_time=usec     Maximum amount of time ext4 should wait for
                         additional filesystem operations to be batch
diff --git a/Documentation/filesystems/ncpfs.txt b/Documentation/filesystems/ncpfs.txt
index f12c30c93f2f..5af164f4b37b 100644
--- a/Documentation/filesystems/ncpfs.txt
+++ b/Documentation/filesystems/ncpfs.txt
@@ -7,6 +7,6 @@ ftp.gwdg.de/pub/linux/misc/ncpfs, but sunsite and its many mirrors
 will have it as well.
 
 Related products are linware and mars_nwe, which will give Linux partial
-NetWare server functionality.  Linware's home site is
-klokan.sh.cvut.cz/pub/linux/linware; mars_nwe can be found on
-ftp.gwdg.de/pub/linux/misc/ncpfs.
+NetWare server functionality.
+
+mars_nwe can be found on ftp.gwdg.de/pub/linux/misc/ncpfs.
diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt
index 05d81cbcb2e1..5920fe26e6ff 100644
--- a/Documentation/filesystems/nfs41-server.txt
+++ b/Documentation/filesystems/nfs41-server.txt
@@ -11,6 +11,11 @@ the /proc/fs/nfsd/versions control file.  Note that to write this
 control file, the nfsd service must be taken down.  Use your user-mode
 nfs-utils to set this up; see rpc.nfsd(8)
 
+(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
+"-4", respectively.  Therefore, code meant to work on both new and old
+kernels must turn 4.1 on or off *before* turning support for version 4
+on or off; rpc.nfsd does this correctly.)
+
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
 on the latest NFSv4.1 Internet Draft:
 http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
@@ -25,6 +30,49 @@ are still under development out of tree.
 See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
 for more information.
 
+The current implementation is intended for developers only: while it
+does support ordinary file operations on clients we have tested against
+(including the linux client), it is incomplete in ways which may limit
+features unexpectedly, cause known bugs in rare cases, or cause
+interoperability problems with future clients.  Known issues:
+
+        - gss support is questionable: currently mounts with kerberos
+          from a linux client are possible, but we aren't really
+          conformant with the spec (for example, we don't use kerberos
+          on the backchannel correctly).
+        - no trunking support: no clients currently take advantage of
+          trunking, but this is a mandatory failure, and its use is
+          recommended to clients in a number of places.  (E.g. to ensure
+          timely renewal in case an existing connection's retry timeouts
+          have gotten too long; see section 8.3 of the draft.)
+          Therefore, lack of this feature may cause future clients to
+          fail.
+        - Incomplete backchannel support: incomplete backchannel gss
+          support and no support for BACKCHANNEL_CTL mean that
+          callbacks (hence delegations and layouts) may not be
+          available and clients confused by the incomplete
+          implementation may fail.
+        - Server reboot recovery is unsupported; if the server reboots,
+          clients may fail.
+        - We do not support SSV, which provides security for shared
+          client-server state (thus preventing unauthorized tampering
+          with locks and opens, for example).  It is mandatory for
+          servers to support this, though no clients use it yet.
+        - Mandatory operations which we do not support, such as
+          DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and
+          TEST_STATEID, are not currently used by clients, but will be
+          (and the spec recommends their uses in common cases), and
+          clients should not be expected to know how to recover from the
+          case where they are not supported.  This will eventually cause
+          interoperability failures.
+
+In addition, some limitations are inherited from the current NFSv4
+implementation:
+
+        - Incomplete delegation enforcement: if a file is renamed or
+          unlinked, a client holding a delegation may continue to
+          indefinitely allow opens of the file under the old name.
+
 The table below, taken from the NFSv4.1 document, lists
 the operations that are mandatory to implement (REQ), optional
 (OPT), and NFSv4.0 operations that are required not to implement (MNI)
@@ -142,6 +190,12 @@ NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
 
 Implementation notes:
 
+DELEGPURGE:
+* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
+  CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
+  persist across client reboots).  Thus we need not implement this for
+  now.
+
 EXCHANGE_ID:
 * only SP4_NONE state protection supported
 * implementation ids are ignored
diff --git a/Documentation/filesystems/nfsroot.txt b/Documentation/filesystems/nfsroot.txt
index 68baddf3c3e0..3ba0b945aaf8 100644
--- a/Documentation/filesystems/nfsroot.txt
+++ b/Documentation/filesystems/nfsroot.txt
@@ -105,7 +105,7 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
                 the client address and this parameter is NOT empty only
                 replies from the specified server are accepted.
 
-                Only required for for NFS root. That is autoconfiguration
+                Only required for NFS root. That is autoconfiguration
                 will not be triggered if it is missing and NFS root is not
                 in operation.
 
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/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index ffead13f9443..2c48f945546b 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -176,6 +176,7 @@ read the file /proc/PID/status:
   CapBnd: ffffffffffffffff
   voluntary_ctxt_switches:        0
   nonvoluntary_ctxt_switches:     1
+  Stack usage:    12 kB
 
 This shows you nearly the same information you would get if you viewed it with
 the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
@@ -229,6 +230,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  Mems_allowed_list           Same as previous, but in "list format"
  voluntary_ctxt_switches     number of voluntary context switches
  nonvoluntary_ctxt_switches  number of non voluntary context switches
+ Stack usage:                stack usage high water mark (round up to page size)
 ..............................................................................
 
 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
@@ -307,7 +309,7 @@ address           perms offset  dev   inode      pathname
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -343,6 +345,7 @@ is not associated with a file:
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
+ [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 
@@ -375,6 +378,19 @@ of memory currently marked as referenced or accessed.
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
 
+The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
+bits on both physical and virtual pages associated with a process.
+To clear the bits for all the pages associated with the process
+    > echo 1 > /proc/PID/clear_refs
+
+To clear the bits for the anonymous pages associated with the process
+    > echo 2 > /proc/PID/clear_refs
+
+To clear the bits for the file mapped pages associated with the process
+    > echo 3 > /proc/PID/clear_refs
+Any other value written to /proc/PID/clear_refs will have no effect.
+
+
 1.2 Kernel data
 ---------------
 
@@ -1032,9 +1048,9 @@ Various pieces   of  information about  kernel activity  are  available in the
 since the system first booted.  For a quick look, simply cat the file:
 
   > cat /proc/stat
-  cpu  2255 34 2290 22625563 6290 127 456 0
-  cpu0 1132 34 1441 11311718 3675 127 438 0
-  cpu1 1123 0 849 11313845 2614 0 18 0
+  cpu  2255 34 2290 22625563 6290 127 456 0 0
+  cpu0 1132 34 1441 11311718 3675 127 438 0 0
+  cpu1 1123 0 849 11313845 2614 0 18 0 0
   intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
   ctxt 1990473
   btime 1062191376
@@ -1056,6 +1072,7 @@ second).  The meanings of the columns are as follows, from left to right:
 - irq: servicing interrupts
 - softirq: servicing softirqs
 - steal: involuntary wait
+- guest: running a guest
 
 The "intr" line gives counts of interrupts  serviced since boot time, for each
 of the  possible system interrupts.   The first  column  is the  total of  all
@@ -1096,7 +1113,6 @@ Table 1-12: Files in /proc/fs/ext4/<devname>
 ..............................................................................
  File            Content                                        
  mb_groups       details of multiblock allocator buddy cache of free blocks
- mb_history      multiblock allocation history
 ..............................................................................
 
 
@@ -1191,7 +1207,7 @@ The following heuristics are then applied:
  * if the task was reniced, its score doubles
  * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
         or CAP_SYS_RAWIO) have their score divided by 4
- * if oom condition happened in one cpuset and checked task does not belong
+ * if oom condition happened in one cpuset and checked process does not belong
         to it, its score is divided by 8
  * the resulting score is multiplied by two to the power of oom_adj, i.e.
         points <<= oom_adj when it is positive and
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 736540045dc7..23a181074f94 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -4,7 +4,7 @@ Shared Subtrees
 Contents:
         1) Overview
         2) Features
-        3) smount command
+        3) Setting mount states
         4) Use-case
         5) Detailed semantics
         6) Quiz
@@ -41,14 +41,14 @@ replicas continue to be exactly same.
 
         Here is an example:
 
-        Lets say /mnt has a mount that is shared.
+        Let's say /mnt has a mount that is shared.
         mount --make-shared /mnt
 
-        note: mount command does not yet support the --make-shared flag.
-        I have included a small C program which does the same by executing
-        'smount /mnt shared'
+        Note: mount(8) command now supports the --make-shared flag,
+        so the sample 'smount' program is no longer needed and has been
+        removed.
 
-        #mount --bind /mnt /tmp
+        # mount --bind /mnt /tmp
         The above command replicates the mount at /mnt to the mountpoint /tmp
         and the contents of both the mounts remain identical.
 
@@ -58,8 +58,8 @@ replicas continue to be exactly same.
         #ls /tmp
         a b c
 
-        Now lets say we mount a device at /tmp/a
-        #mount /dev/sd0  /tmp/a
+        Now let's say we mount a device at /tmp/a
+        # mount /dev/sd0  /tmp/a
 
         #ls /tmp/a
         t1 t2 t2
@@ -80,21 +80,20 @@ replicas continue to be exactly same.
 
         Here is an example:
 
-        Lets say /mnt has a mount which is shared.
-        #mount --make-shared /mnt
+        Let's say /mnt has a mount which is shared.
+        # mount --make-shared /mnt
 
-        Lets bind mount /mnt to /tmp
-        #mount --bind /mnt /tmp
+        Let's bind mount /mnt to /tmp
+        # mount --bind /mnt /tmp
 
         the new mount at /tmp becomes a shared mount and it is a replica of
         the mount at /mnt.
 
-        Now lets make the mount at /tmp; a slave of /mnt
-        #mount --make-slave /tmp
-        [or smount /tmp slave]
+        Now let's make the mount at /tmp; a slave of /mnt
+        # mount --make-slave /tmp
 
-        lets mount /dev/sd0 on /mnt/a
-        #mount /dev/sd0 /mnt/a
+        let's mount /dev/sd0 on /mnt/a
+        # mount /dev/sd0 /mnt/a
 
         #ls /mnt/a
         t1 t2 t3
@@ -104,9 +103,9 @@ replicas continue to be exactly same.
 
         Note the mount event has propagated to the mount at /tmp
 
-        However lets see what happens if we mount something on the mount at /tmp
+        However let's see what happens if we mount something on the mount at /tmp
 
-        #mount /dev/sd1 /tmp/b
+        # mount /dev/sd1 /tmp/b
 
         #ls /tmp/b
         s1 s2 s3
@@ -124,12 +123,11 @@ replicas continue to be exactly same.
 
 2d) A unbindable mount is a unbindable private mount
 
-        lets say we have a mount at /mnt and we make is unbindable
+        let's say we have a mount at /mnt and we make is unbindable
 
-        #mount --make-unbindable /mnt
-         [ smount /mnt  unbindable ]
+        # mount --make-unbindable /mnt
 
-         Lets try to bind mount this mount somewhere else.
+         Let's try to bind mount this mount somewhere else.
          # mount --bind /mnt /tmp
          mount: wrong fs type, bad option, bad superblock on /mnt,
                 or too many mounted file systems
@@ -137,149 +135,15 @@ replicas continue to be exactly same.
         Binding a unbindable mount is a invalid operation.
 
 
-3) smount command
+3) Setting mount states
 
-        Currently the mount command is not aware of shared subtree features.
-        Work is in progress to add the support in mount ( util-linux package ).
-        Till then use the following program.
+        The mount command (util-linux package) can be used to set mount
+        states:
 
-        ------------------------------------------------------------------------
-        //
-        //this code was developed my Miklos Szeredi <miklos@szeredi.hu>
-        //and modified by Ram Pai <linuxram@us.ibm.com>
-        // sample usage:
-        //              smount /tmp shared
-        //
-        #include <stdio.h>
-        #include <stdlib.h>
-        #include <unistd.h>
-        #include <string.h>
-        #include <sys/mount.h>
-        #include <sys/fsuid.h>
-
-        #ifndef MS_REC
-        #define MS_REC          0x4000  /* 16384: Recursive loopback */
-        #endif
-
-        #ifndef MS_SHARED
-        #define MS_SHARED               1<<20   /* Shared */
-        #endif
-
-        #ifndef MS_PRIVATE
-        #define MS_PRIVATE              1<<18   /* Private */
-        #endif
-
-        #ifndef MS_SLAVE
-        #define MS_SLAVE                1<<19   /* Slave */
-        #endif
-
-        #ifndef MS_UNBINDABLE
-        #define MS_UNBINDABLE           1<<17   /* Unbindable */
-        #endif
-
-        int main(int argc, char *argv[])
-        {
-                int type;
-                if(argc != 3) {
-                        fprintf(stderr, "usage: %s dir "
-                        "<rshared|rslave|rprivate|runbindable|shared|slave"
-                        "|private|unbindable>\n" , argv[0]);
-                        return 1;
-                }
-
-                fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]);
-
-                if (strcmp(argv[2],"rshared")==0)
-                        type=(MS_SHARED|MS_REC);
-                else if (strcmp(argv[2],"rslave")==0)
-                        type=(MS_SLAVE|MS_REC);
-                else if (strcmp(argv[2],"rprivate")==0)
-                        type=(MS_PRIVATE|MS_REC);
-                else if (strcmp(argv[2],"runbindable")==0)
-                        type=(MS_UNBINDABLE|MS_REC);
-                else if (strcmp(argv[2],"shared")==0)
-                        type=MS_SHARED;
-                else if (strcmp(argv[2],"slave")==0)
-                        type=MS_SLAVE;
-                else if (strcmp(argv[2],"private")==0)
-                        type=MS_PRIVATE;
-                else if (strcmp(argv[2],"unbindable")==0)
-                        type=MS_UNBINDABLE;
-                else {
-                        fprintf(stderr, "invalid operation: %s\n", argv[2]);
-                        return 1;
-                }
-                setfsuid(getuid());
-
-                if(mount("", argv[1], "dontcare", type, "") == -1) {
-                        perror("mount");
-                        return 1;
-                }
-                return 0;
-        }
-        -----------------------------------------------------------------------
-
-        Copy the above code snippet into smount.c
-        gcc -o smount smount.c
-
-
-        (i) To mark all the mounts under /mnt as shared execute the following
-        command:
-
-                smount /mnt rshared
-                the corresponding syntax planned for mount command is
-                mount --make-rshared /mnt
-
-            just to mark a mount /mnt as shared, execute the following
-            command:
-                smount /mnt shared
-                the corresponding syntax planned for mount command is
-                mount --make-shared /mnt
-
-        (ii) To mark all the shared mounts under /mnt as slave execute the
-        following
-
-             command:
-                smount /mnt rslave
-                the corresponding syntax planned for mount command is
-                mount --make-rslave /mnt
-
-            just to mark a mount /mnt as slave, execute the following
-            command:
-                smount /mnt slave
-                the corresponding syntax planned for mount command is
-                mount --make-slave /mnt
-
-        (iii) To mark all the mounts under /mnt as private execute the
-        following command:
-
-                smount /mnt rprivate
-                the corresponding syntax planned for mount command is
-                mount --make-rprivate /mnt
-
-            just to mark a mount /mnt as private, execute the following
-            command:
-                smount /mnt private
-                the corresponding syntax planned for mount command is
-                mount --make-private /mnt
-
-              NOTE: by default all the mounts are created as private. But if
-              you want to change some shared/slave/unbindable  mount as
-              private at a later point in time, this command can help.
-
-        (iv) To mark all the mounts under /mnt as unbindable execute the
-        following
-
-             command:
-                smount /mnt runbindable
-                the corresponding syntax planned for mount command is
-                mount --make-runbindable /mnt
-
-            just to mark a mount /mnt as unbindable, execute the following
-            command:
-                smount /mnt unbindable
-                the corresponding syntax planned for mount command is
-                mount --make-unbindable /mnt
+        mount --make-shared mountpoint
+        mount --make-slave mountpoint
+        mount --make-private mountpoint
+        mount --make-unbindable mountpoint
 
 
 4) Use cases
@@ -350,7 +214,7 @@ replicas continue to be exactly same.
                 mount --rbind / /view/v3
                 mount --rbind / /view/v4
 
-                and if /usr has a versioning filesystem mounted, than that
+                and if /usr has a versioning filesystem mounted, then that
                 mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and
                 /view/v4/usr too
 
@@ -390,7 +254,7 @@ replicas continue to be exactly same.
 
                 For example:
                         mount --make-shared /mnt
-                        mount --bin /mnt /tmp
+                        mount --bind /mnt /tmp
 
                 The mount at /mnt and that at /tmp are both shared and belong
                 to the same peer group. Anything mounted or unmounted under
@@ -558,7 +422,7 @@ replicas continue to be exactly same.
         then the subtree under the unbindable mount is pruned in the new
         location.
 
-        eg: lets say we have the following mount tree.
+        eg: let's say we have the following mount tree.
 
                 A
               /   \
@@ -566,7 +430,7 @@ replicas continue to be exactly same.
              / \ / \
              D E F G
 
-             Lets say all the mount except the mount C in the tree are
+             Let's say all the mount except the mount C in the tree are
              of a type other than unbindable.
 
              If this tree is rbound to say Z
@@ -683,13 +547,13 @@ replicas continue to be exactly same.
         'b' on mounts that receive propagation from mount 'B' and does not have
         sub-mounts within them are unmounted.
 
-        Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to
+        Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to
         each other.
 
-        lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
+        let's say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
         'B1', 'B2' and 'B3' respectively.
 
-        lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
+        let's say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
         mount 'B1', 'B2' and 'B3' respectively.
 
         if 'C1' is unmounted, all the mounts that are most-recently-mounted on
@@ -710,7 +574,7 @@ replicas continue to be exactly same.
         A cloned namespace contains all the mounts as that of the parent
         namespace.
 
-        Lets say 'A' and 'B' are the corresponding mounts in the parent and the
+        Let's say 'A' and 'B' are the corresponding mounts in the parent and the
         child namespace.
 
         If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to
@@ -759,11 +623,11 @@ replicas continue to be exactly same.
                 mount --make-slave /mnt
 
                 At this point we have the first mount at /tmp and
-                its root dentry is 1. Lets call this mount 'A'
+                its root dentry is 1. Let's call this mount 'A'
                 And then we have a second mount at /tmp1 with root
-                dentry 2. Lets call this mount 'B'
+                dentry 2. Let's call this mount 'B'
                 Next we have a third mount at /mnt with root dentry
-                mnt. Lets call this mount 'C'
+                mnt. Let's call this mount 'C'
 
                 'B' is the slave of 'A' and 'C' is a slave of 'B'
                 A -> B -> C
@@ -794,7 +658,7 @@ replicas continue to be exactly same.
 
         Q3 Why is unbindable mount needed?
 
-                Lets say we want to replicate the mount tree at multiple
+                Let's say we want to replicate the mount tree at multiple
                 locations within the same subtree.
 
                 if one rbind mounts a tree within the same subtree 'n' times
@@ -803,7 +667,7 @@ replicas continue to be exactly same.
                 mounts. Here is a example.
 
                 step 1:
-                   lets say the root tree has just two directories with
+                   let's say the root tree has just two directories with
                    one vfsmount.
                                     root
                                    /    \
@@ -875,7 +739,7 @@ replicas continue to be exactly same.
                 Unclonable mounts come in handy here.
 
                 step 1:
-                   lets say the root tree has just two directories with
+                   let's say the root tree has just two directories with
                    one vfsmount.
                                     root
                                    /    \
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index b58b84b50fa2..eed520fd0c8e 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -102,7 +102,7 @@ shortname=lower|win95|winnt|mixed
                  winnt: emulate the Windows NT rule for display/create.
                  mixed: emulate the Windows NT rule for display,
                         emulate the Windows 95 rule for create.
-                 Default setting is `lower'.
+                 Default setting is `mixed'.
 
 tz=UTC        -- Interpret timestamps as UTC rather than local time.
                  This option disables the conversion of timestamps
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f49eecf2e573..623f094c9d8d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -536,6 +536,7 @@ struct address_space_operations {
         /* migrate the contents of a page to the specified target */
         int (*migratepage) (struct page *, struct page *);
         int (*launder_page) (struct page *);
+        int (*error_remove_page) (struct mapping *mapping, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations {
         prevent redirtying the page, it is kept locked during the whole
         operation.
 
+  error_remove_page: normally set to generic_error_remove_page if truncation
+        is ok for this address space. Used for memory failure handling.
+        Setting this implies you deal with pages going away under you,
+        unless you have them locked or reference counts increased.
+
+
 The File Object
 ===============