6 files changed, 180 insertions, 15 deletions

diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 8c624a18f67d..7b52ba7bf32a 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -38,6 +38,8 @@ dnotify_test.c
         - example program for dnotify
 ecryptfs.txt
         - docs on eCryptfs: stacked cryptographic filesystem for Linux.
+efivarfs.txt
+        - info for the efivarfs filesystem.
 exofs.txt
         - info, usage, mount options, design about EXOFS.
 ext2.txt
diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
new file mode 100644
index 000000000000..c477af086e65
--- /dev/null
+++ b/Documentation/filesystems/efivarfs.txt
@@ -0,0 +1,16 @@
+
+efivarfs - a (U)EFI variable filesystem
+
+The efivarfs filesystem was created to address the shortcomings of
+using entries in sysfs to maintain EFI variables. The old sysfs EFI
+variables code only supported variables of up to 1024 bytes. This
+limitation existed in version 0.99 of the EFI specification, but was
+removed before any full releases. Since variables can now be larger
+than a single page, sysfs isn't the best interface for this.
+
+Variables can be created, deleted and modified with the efivarfs
+filesystem.
+
+efivarfs is typically mounted like this,
+
+        mount -t efivarfs none /sys/firmware/efi/efivars
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 104322bf378c..34ea4f1fa6ea 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -200,12 +200,9 @@ inode_readahead_blks=n	This tuning parameter controls the maximum
                         table readahead algorithm will pre-read into
                         the buffer cache.  The default value is 32 blocks.
 
-nouser_xattr            Disables Extended User Attributes. If you have extended
-                        attribute support enabled in the kernel configuration
-                        (CONFIG_EXT4_FS_XATTR), extended attribute support
-                        is enabled by default on mount. See the attr(5) manual
-                        page and http://acl.bestbits.at/ for more information
-                        about extended attributes.
+nouser_xattr            Disables Extended User Attributes.  See the
+                        attr(5) manual page and http://acl.bestbits.at/
+                        for more information about extended attributes.
 
 noacl                   This option disables POSIX Access Control List
                         support. If ACL support is enabled in the kernel
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a1793d670cd0..fd8d0d594fc7 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -33,7 +33,7 @@ Table of Contents
   2     Modifying System Parameters
 
   3     Per-Process Parameters
-  3.1   /proc/<pid>/oom_score_adj - Adjust the oom-killer
+  3.1   /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
                                                                 score
   3.2   /proc/<pid>/oom_score - Display current oom-killer score
   3.3   /proc/<pid>/io - Display the IO accounting fields
@@ -41,6 +41,7 @@ Table of Contents
   3.5   /proc/<pid>/mountinfo - Information about mounts
   3.6   /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
   3.7   /proc/<pid>/task/<tid>/children - Information about task children
+  3.8   /proc/<pid>/fdinfo/<fd> - Information about opened file
 
   4     Configuring procfs
   4.1   Mount options
@@ -142,7 +143,7 @@ Table 1-1: Process specific entries in /proc
  pagemap        Page table
  stack          Report full stack trace, enable via CONFIG_STACKTRACE
  smaps          a extension based on maps, showing the memory consumption of
-                each mapping
+                each mapping and flags associated with it
 ..............................................................................
 
 For example, to get the status information of a process, all you have to do is
@@ -181,6 +182,7 @@ read the file /proc/PID/status:
   CapPrm: 0000000000000000
   CapEff: 0000000000000000
   CapBnd: ffffffffffffffff
+  Seccomp:        0
   voluntary_ctxt_switches:        0
   nonvoluntary_ctxt_switches:     1
 
@@ -237,6 +239,7 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7)
  CapPrm                      bitmap of permitted capabilities
  CapEff                      bitmap of effective capabilities
  CapBnd                      bitmap of capabilities bounding set
+ Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
  Cpus_allowed                mask of CPUs on which this process may run
  Cpus_allowed_list           Same as previous, but in "list format"
  Mems_allowed                mask of memory nodes allowed to this process
@@ -415,8 +418,9 @@ Swap:                  0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 Locked:              374 kB
+VmFlags: rd ex mr mw me de
 
-The first of these lines shows the same information as is displayed for the
+the first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 (size), the amount of the mapping that is currently resident in RAM (RSS), the
 process' proportional share of this mapping (PSS), the number of clean and
@@ -430,6 +434,41 @@ and a page is modified, the file page is replaced by a private anonymous copy.
 "Swap" shows how much would-be-anonymous memory is also used, but out on
 swap.
 
+"VmFlags" field deserves a separate description. This member represents the kernel
+flags associated with the particular virtual memory area in two letter encoded
+manner. The codes are the following:
+    rd  - readable
+    wr  - writeable
+    ex  - executable
+    sh  - shared
+    mr  - may read
+    mw  - may write
+    me  - may execute
+    ms  - may share
+    gd  - stack segment growns down
+    pf  - pure PFN range
+    dw  - disabled write to the mapped file
+    lo  - pages are locked in memory
+    io  - memory mapped I/O area
+    sr  - sequential read advise provided
+    rr  - random read advise provided
+    dc  - do not copy area on fork
+    de  - do not expand area on remapping
+    ac  - area is accountable
+    nr  - swap space is not reserved for the area
+    ht  - area uses huge tlb pages
+    nl  - non-linear mapping
+    ar  - architecture specific flag
+    dd  - do not include area into core dump
+    mm  - mixed map area
+    hg  - huge page advise flag
+    nh  - no-huge page advise flag
+    mg  - mergable advise flag
+
+Note that there is no guarantee that every flag and associated mnemonic will
+be present in all further kernel releases. Things get changed, the flags may
+be vanished or the reverse -- new added.
+
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
 
@@ -1320,10 +1359,10 @@ of the kernel.
 CHAPTER 3: PER-PROCESS PARAMETERS
 ------------------------------------------------------------------------------
 
-3.1 /proc/<pid>/oom_score_adj- Adjust the oom-killer score
+3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
 --------------------------------------------------------------------------------
 
-This file can be used to adjust the badness heuristic used to select which
+These file can be used to adjust the badness heuristic used to select which
 process gets killed in out of memory conditions.
 
 The badness heuristic assigns a value to each candidate task ranging from 0
@@ -1361,6 +1400,12 @@ same system, cpuset, mempolicy, or memory controller resources to use at least
 equivalent to discounting 50% of the task's allowed memory from being considered
 as scoring against the task.
 
+For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
+be used to tune the badness score.  Its acceptable values range from -16
+(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
+(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
+scaled linearly with /proc/<pid>/oom_score_adj.
+
 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
 requires CAP_SYS_RESOURCE.
@@ -1375,7 +1420,9 @@ minimal amount of work.
 -------------------------------------------------------------
 
 This file can be used to check the current score used by the oom-killer is for
-any given <pid>.
+any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
+process should be killed in an out-of-memory situation.
+
 
 3.3  /proc/<pid>/io - Display the IO accounting fields
 -------------------------------------------------------
@@ -1587,6 +1634,93 @@ pids, so one need to either stop or freeze processes being inspected
 if precise results are needed.
 
 
+3.7     /proc/<pid>/fdinfo/<fd> - Information about opened file
+---------------------------------------------------------------
+This file provides information associated with an opened file. The regular
+files have at least two fields -- 'pos' and 'flags'. The 'pos' represents
+the current offset of the opened file in decimal form [see lseek(2) for
+details] and 'flags' denotes the octal O_xxx mask the file has been
+created with [see open(2) for details].
+
+A typical output is
+
+        pos:    0
+        flags:  0100002
+
+The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
+pair provide additional information particular to the objects they represent.
+
+        Eventfd files
+        ~~~~~~~~~~~~~
+        pos:    0
+        flags:  04002
+        eventfd-count:  5a
+
+        where 'eventfd-count' is hex value of a counter.
+
+        Signalfd files
+        ~~~~~~~~~~~~~~
+        pos:    0
+        flags:  04002
+        sigmask:        0000000000000200
+
+        where 'sigmask' is hex value of the signal mask associated
+        with a file.
+
+        Epoll files
+        ~~~~~~~~~~~
+        pos:    0
+        flags:  02
+        tfd:        5 events:       1d data: ffffffffffffffff
+
+        where 'tfd' is a target file descriptor number in decimal form,
+        'events' is events mask being watched and the 'data' is data
+        associated with a target [see epoll(7) for more details].
+
+        Fsnotify files
+        ~~~~~~~~~~~~~~
+        For inotify files the format is the following
+
+        pos:    0
+        flags:  02000000
+        inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
+
+        where 'wd' is a watch descriptor in decimal form, ie a target file
+        descriptor number, 'ino' and 'sdev' are inode and device where the
+        target file resides and the 'mask' is the mask of events, all in hex
+        form [see inotify(7) for more details].
+
+        If the kernel was built with exportfs support, the path to the target
+        file is encoded as a file handle.  The file handle is provided by three
+        fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
+        format.
+
+        If the kernel is built without exportfs support the file handle won't be
+        printed out.
+
+        If there is no inotify mark attached yet the 'inotify' line will be omitted.
+
+        For fanotify files the format is
+
+        pos:    0
+        flags:  02
+        fanotify flags:10 event-flags:0
+        fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
+        fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
+
+        where fanotify 'flags' and 'event-flags' are values used in fanotify_init
+        call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
+        flags associated with mark which are tracked separately from events
+        mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
+        mask and 'ignored_mask' is the mask of events which are to be ignored.
+        All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
+        does provide information about flags and mask used in fanotify_mark
+        call [see fsnotify manpage for details].
+
+        While the first three lines are mandatory and always printed, the rest is
+        optional and may be omitted if no marks created yet.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index de1e6c4dccff..d230dd9c99b0 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -111,6 +111,15 @@ tz=UTC        -- Interpret timestamps as UTC rather than local time.
                  useful when mounting devices (like digital cameras)
                  that are set to UTC in order to avoid the pitfalls of
                  local time.
+time_offset=minutes
+              -- Set offset for conversion of timestamps from local time
+                 used by FAT to UTC. I.e. <minutes> minutes will be subtracted
+                 from each timestamp to convert it to UTC used internally by
+                 Linux. This is useful when time zone set in sys_tz is
+                 not the time zone used by the filesystem. Note that this
+                 option still does not provide correct time stamps in all
+                 cases in presence of DST - time stamps in a different DST
+                 setting will be off by one hour.
 
 showexec      -- If set, the execute permission bits of the file will be
                  allowed only if the extension part of the name is .EXE,
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 3fc0c31a6f5d..3e4b3dd1e046 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -43,7 +43,7 @@ When mounting an XFS filesystem, the following options are accepted.
         Issue command to let the block device reclaim space freed by the
         filesystem.  This is useful for SSD devices, thinly provisioned
         LUNs and virtual machine images, but may have a performance
-        impact.  This option is incompatible with the nodelaylog option.
+        impact.
 
   dmapi
         Enable the DMAPI (Data Management API) event callouts.
@@ -72,8 +72,15 @@ When mounting an XFS filesystem, the following options are accepted.
         Indicates that XFS is allowed to create inodes at any location
         in the filesystem, including those which will result in inode
         numbers occupying more than 32 bits of significance.  This is
-        provided for backwards compatibility, but causes problems for
-        backup applications that cannot handle large inode numbers.
+        the default allocation option. Applications which do not handle
+        inode numbers bigger than 32 bits, should use inode32 option.
+
+  inode32
+        Indicates that XFS is limited to create inodes at locations which
+        will not result in inode numbers with more than 32 bits of
+        significance. This is provided for backwards compatibility, since
+        64 bits inode numbers might cause problems for some applications
+        that cannot handle large inode numbers.
 
   largeio/nolargeio
         If "nolargeio" is specified, the optimal I/O reported in