11 files changed, 120 insertions, 68 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4471a416c274..61b31acb9176 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -128,7 +128,7 @@ alloc_inode:
 destroy_inode:
 dirty_inode:                            (must not sleep)
 write_inode:
-drop_inode:                             !!!inode_lock!!!
+drop_inode:                             !!!inode->i_lock!!!
 evict_inode:
 put_super:              write
 write_super:            read
@@ -166,13 +166,11 @@ prototypes:
         void (*kill_sb) (struct super_block *);
 locking rules:
                 may block
-get_sb          yes
 mount           yes
 kill_sb         yes
 
-->get_sb() returns error or 0 with locked superblock attached to the vfsmount
-(exclusive on ->s_umount).
-->mount() returns ERR_PTR or the root dentry.
+->mount() returns ERR_PTR or the root dentry; its superblock should be locked
+on return.
 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 unlocks and drops the reference.
 
diff --git a/Documentation/filesystems/adfs.txt b/Documentation/filesystems/adfs.txt
index 9e8811f92b84..5949766353f7 100644
--- a/Documentation/filesystems/adfs.txt
+++ b/Documentation/filesystems/adfs.txt
@@ -9,6 +9,9 @@ Mount options for ADFS
                 will be nnn.  Default 0700.
   othmask=nnn   The permission mask for ADFS 'other' permissions
                 will be nnn.  Default 0077.
+  ftsuffix=n    When ftsuffix=0, no file type suffix will be applied.
+                When ftsuffix=1, a hexadecimal suffix corresponding to
+                the RISC OS file type will be added.  Default 0.
 
 Mapping of ADFS permissions to Linux permissions
 ------------------------------------------------
@@ -55,3 +58,18 @@ Mapping of ADFS permissions to Linux permissions
 
   You can therefore tailor the permission translation to whatever you
   desire the permissions should be under Linux.
+
+RISC OS file type suffix
+------------------------
+
+  RISC OS file types are stored in bits 19..8 of the file load address.
+
+  To enable non-RISC OS systems to be used to store files without losing
+  file type information, a file naming convention was devised (initially
+  for use with NFS) such that a hexadecimal suffix of the form ,xyz
+  denoted the file type: e.g. BasicFile,ffb is a BASIC (0xffb) file.  This
+  naming convention is now also used by RISC OS emulators such as RPCEmu.
+
+  Mounting an ADFS disc with option ftsuffix=1 will cause appropriate file
+  type suffixes to be appended to file names read from a directory.  If the
+  ftsuffix option is zero or omitted, no file type suffixes will be added.
diff --git a/Documentation/filesystems/exofs.txt b/Documentation/filesystems/exofs.txt
index abd2a9b5b787..23583a136975 100644
--- a/Documentation/filesystems/exofs.txt
+++ b/Documentation/filesystems/exofs.txt
@@ -104,7 +104,15 @@ Where:
     exofs specific options: Options are separated by commas (,)
                 pid=<integer> - The partition number to mount/create as
                                 container of the filesystem.
-                                This option is mandatory.
+                                This option is mandatory. integer can be
+                                Hex by pre-pending an 0x to the number.
+                osdname=<id>  - Mount by a device's osdname.
+                                osdname is usually a 36 character uuid of the
+                                form "d2683732-c906-4ee1-9dbd-c10c27bb40df".
+                                It is one of the device's uuid specified in the
+                                mkfs.exofs format command.
+                                If this option is specified then the /dev/osdX
+                                above can be empty and is ignored.
                 to=<integer>  - Timeout in ticks for a single command.
                                 default is (60 * HZ) [for debugging only]
 
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
index bc0b9cfe095b..983e14abe7e9 100644
--- a/Documentation/filesystems/nfs/pnfs.txt
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -46,3 +46,10 @@ data server cache
 file driver devices refer to data servers, which are kept in a module
 level cache.  Its reference is held over the lifetime of the deviceid
 pointing to it.
+
+lseg
+----
+lseg maintains an extra reference corresponding to the NFS_LSEG_VALID
+bit which holds it in the pnfs_layout_hdr's list.  When the final lseg
+is removed from the pnfs_layout_hdr's list, the NFS_LAYOUT_DESTROYED
+bit is set, preventing any new lsegs from being added.
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index dfbcd1b00b0a..6e29954851a2 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -298,11 +298,14 @@ be used instead.  It gets called whenever the inode is evicted, whether it has
 remaining links or not.  Caller does *not* evict the pagecache or inode-associated
 metadata buffers; getting rid of those is responsibility of method, as it had
 been for ->delete_inode().
-        ->drop_inode() returns int now; it's called on final iput() with inode_lock
-held and it returns true if filesystems wants the inode to be dropped.  As before,
-generic_drop_inode() is still the default and it's been updated appropriately.
-generic_delete_inode() is also alive and it consists simply of return 1.  Note that
-all actual eviction work is done by caller after ->drop_inode() returns.
+
+        ->drop_inode() returns int now; it's called on final iput() with
+inode->i_lock held and it returns true if filesystems wants the inode to be
+dropped.  As before, generic_drop_inode() is still the default and it's been
+updated appropriately.  generic_delete_inode() is also alive and it consists
+simply of return 1.  Note that all actual eviction work is done by caller after
+->drop_inode() returns.
+
         clear_inode() is gone; use end_writeback() instead.  As before, it must
 be called exactly once on each call of ->evict_inode() (as it used to be for
 each call of ->delete_inode()).  Unlike before, if you are using inode-associated
@@ -394,3 +397,13 @@ file) you must return -EOPNOTSUPP if FALLOC_FL_PUNCH_HOLE is set in mode.
 Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set,
 so the i_size should not change when hole punching, even when puching the end of
 a file off.
+
+--
+[mandatory]
+
+--
+[mandatory]
+        ->get_sb() is gone.  Switch to use of ->mount().  Typically it's just
+a matter of switching from calling get_sb_... to mount_... and changing the
+function type.  If you were doing it manually, just switch from setting ->mnt_root
+to some pointer to returning that pointer.  On errors return ERR_PTR(...).
diff --git a/Documentation/filesystems/romfs.txt b/Documentation/filesystems/romfs.txt
index 2d2a7b2a16b9..e2b07cc9120a 100644
--- a/Documentation/filesystems/romfs.txt
+++ b/Documentation/filesystems/romfs.txt
@@ -17,8 +17,7 @@ comparison, an actual rescue disk used up 3202 blocks with ext2, while
 with romfs, it needed 3079 blocks.
 
 To create such a file system, you'll need a user program named
-genromfs.  It is available via anonymous ftp on sunsite.unc.edu and
-its mirrors, in the /pub/Linux/system/recovery/ directory.
+genromfs. It is available on http://romfs.sourceforge.net/
 
 As the name suggests, romfs could be also used (space-efficiently) on
 various read-only media, like (E)EPROM disks if someone will have the
diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt
index 66699afd66ca..2d78f1911844 100644
--- a/Documentation/filesystems/squashfs.txt
+++ b/Documentation/filesystems/squashfs.txt
@@ -59,12 +59,15 @@ obtained from this site also.
 3. SQUASHFS FILESYSTEM DESIGN
 -----------------------------
 
-A squashfs filesystem consists of a maximum of eight parts, packed together on a byte
-alignment:
+A squashfs filesystem consists of a maximum of nine parts, packed together on a
+byte alignment:
 
          ---------------
         |  superblock   |
         |---------------|
+        |  compression  |
+        |    options    |
+        |---------------|
         |  datablocks   |
         |  & fragments  |
         |---------------|
@@ -91,7 +94,14 @@ the source directory, and checked for duplicates.  Once all file data has been
 written the completed inode, directory, fragment, export and uid/gid lookup
 tables are written.
 
-3.1 Inodes
+3.1 Compression options
+-----------------------
+
+Compressors can optionally support compression specific options (e.g.
+dictionary size).  If non-default compression options have been used, then
+these are stored here.
+
+3.2 Inodes
 ----------
 
 Metadata (inodes and directories) are compressed in 8Kbyte blocks.  Each
@@ -114,7 +124,7 @@ directory inode are defined: inodes optimised for frequently occurring
 regular files and directories, and extended types where extra
 information has to be stored.
 
-3.2 Directories
+3.3 Directories
 ---------------
 
 Like inodes, directories are packed into compressed metadata blocks, stored
@@ -144,7 +154,7 @@ decompressed to do a lookup irrespective of the length of the directory.
 This scheme has the advantage that it doesn't require extra memory overhead
 and doesn't require much extra storage on disk.
 
-3.3 File data
+3.4 File data
 -------------
 
 Regular files consist of a sequence of contiguous compressed blocks, and/or a
@@ -163,7 +173,7 @@ Larger files use multiple slots, with 1.75 TiB files using all 8 slots.
 The index cache is designed to be memory efficient, and by default uses
 16 KiB.
 
-3.4 Fragment lookup table
+3.5 Fragment lookup table
 -------------------------
 
 Regular files can contain a fragment index which is mapped to a fragment
@@ -173,7 +183,7 @@ A second index table is used to locate these.  This second index table for
 speed of access (and because it is small) is read at mount time and cached
 in memory.
 
-3.5 Uid/gid lookup table
+3.6 Uid/gid lookup table
 ------------------------
 
 For space efficiency regular files store uid and gid indexes, which are
@@ -182,7 +192,7 @@ stored compressed into metadata blocks.  A second index table is used to
 locate these.  This second index table for speed of access (and because it
 is small) is read at mount time and cached in memory.
 
-3.6 Export table
+3.7 Export table
 ----------------
 
 To enable Squashfs filesystems to be exportable (via NFS etc.) filesystems
@@ -196,7 +206,7 @@ This table is stored compressed into metadata blocks.  A second index table is
 used to locate these.  This second index table for speed of access (and because
 it is small) is read at mount time and cached in memory.
 
-3.7 Xattr table
+3.8 Xattr table
 ---------------
 
 The xattr table contains extended attributes for each inode.  The xattrs
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 5d1335faec2d..f806e50aaa63 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -39,10 +39,12 @@ userspace. Top-level directories in sysfs represent the common
 ancestors of object hierarchies; i.e. the subsystems the objects
 belong to. 
 
-Sysfs internally stores the kobject that owns the directory in the
-->d_fsdata pointer of the directory's dentry. This allows sysfs to do
-reference counting directly on the kobject when the file is opened and
-closed. 
+Sysfs internally stores a pointer to the kobject that implements a
+directory in the sysfs_dirent object associated with the directory. In
+the past this kobject pointer has been used by sysfs to do reference
+counting directly on the kobject whenever the file is opened or closed.
+With the current sysfs implementation the kobject reference count is
+only modified directly by the function sysfs_schedule_callback().
 
 
 Attributes
@@ -208,9 +210,9 @@ Other notes:
   is 4096. 
 
 - show() methods should return the number of bytes printed into the
-  buffer. This is the return value of snprintf().
+  buffer. This is the return value of scnprintf().
 
-- show() should always use snprintf(). 
+- show() should always use scnprintf().
 
 - store() should return the number of bytes used from the buffer. If the
   entire buffer has been used, just return the count argument.
@@ -229,7 +231,7 @@ A very simple (and naive) implementation of a device attribute is:
 static ssize_t show_name(struct device *dev, struct device_attribute *attr,
                          char *buf)
 {
-        return snprintf(buf, PAGE_SIZE, "%s\n", dev->name);
+        return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name);
 }
 
 static ssize_t store_name(struct device *dev, struct device_attribute *attr,
diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt
index 12fedb7834c6..d7b13b01e980 100644
--- a/Documentation/filesystems/ubifs.txt
+++ b/Documentation/filesystems/ubifs.txt
@@ -82,12 +82,12 @@ Mount options
 bulk_read               read more in one go to take advantage of flash
                         media that read faster sequentially
 no_bulk_read (*)        do not bulk-read
-no_chk_data_crc         skip checking of CRCs on data nodes in order to
+no_chk_data_crc (*)     skip checking of CRCs on data nodes in order to
                         improve read performance. Use this option only
                         if the flash media is highly reliable. The effect
                         of this option is that corruption of the contents
                         of a file can go unnoticed.
-chk_data_crc (*)        do not skip checking CRCs on data nodes
+chk_data_crc            do not skip checking CRCs on data nodes
 compr=none              override default compressor and set it to "none"
 compr=lzo               override default compressor and set it to "lzo"
 compr=zlib              override default compressor and set it to "zlib"
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 94cf97b901d7..80815ed654cb 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -95,10 +95,11 @@ functions:
    extern int unregister_filesystem(struct file_system_type *);
 
 The passed struct file_system_type describes your filesystem. When a
-request is made to mount a device onto a directory in your filespace,
-the VFS will call the appropriate get_sb() method for the specific
-filesystem. The dentry for the mount point will then be updated to
-point to the root inode for the new filesystem.
+request is made to mount a filesystem onto a directory in your namespace,
+the VFS will call the appropriate mount() method for the specific
+filesystem.  New vfsmount refering to the tree returned by ->mount()
+will be attached to the mountpoint, so that when pathname resolution
+reaches the mountpoint it will jump into the root of that vfsmount.
 
 You can see all filesystems that are registered to the kernel in the
 file /proc/filesystems.
@@ -107,14 +108,14 @@ file /proc/filesystems.
 struct file_system_type
 -----------------------
 
-This describes the filesystem. As of kernel 2.6.22, the following
+This describes the filesystem. As of kernel 2.6.39, the following
 members are defined:
 
 struct file_system_type {
         const char *name;
         int fs_flags;
-        int (*get_sb) (struct file_system_type *, int,
-                       const char *, void *, struct vfsmount *);
+        struct dentry (*mount) (struct file_system_type *, int,
+                       const char *, void *);
         void (*kill_sb) (struct super_block *);
         struct module *owner;
         struct file_system_type * next;
@@ -128,11 +129,11 @@ struct file_system_type {
 
   fs_flags: various flags (i.e. FS_REQUIRES_DEV, FS_NO_DCACHE, etc.)
 
-  get_sb: the method to call when a new instance of this
+  mount: the method to call when a new instance of this
         filesystem should be mounted
 
   kill_sb: the method to call when an instance of this filesystem
-        should be unmounted
+        should be shut down
 
   owner: for internal VFS use: you should initialize this to THIS_MODULE in
         most cases.
@@ -141,7 +142,7 @@ struct file_system_type {
 
   s_lock_key, s_umount_key: lockdep-specific
 
-The get_sb() method has the following arguments:
+The mount() method has the following arguments:
 
   struct file_system_type *fs_type: describes the filesystem, partly initialized
         by the specific filesystem code
@@ -153,32 +154,39 @@ The get_sb() method has the following arguments:
   void *data: arbitrary mount options, usually comes as an ASCII
         string (see "Mount Options" section)
 
-  struct vfsmount *mnt: a vfs-internal representation of a mount point
+The mount() method must return the root dentry of the tree requested by
+caller.  An active reference to its superblock must be grabbed and the
+superblock must be locked.  On failure it should return ERR_PTR(error).
 
-The get_sb() method must determine if the block device specified
-in the dev_name and fs_type contains a filesystem of the type the method
-supports. If it succeeds in opening the named block device, it initializes a
-struct super_block descriptor for the filesystem contained by the block device.
-On failure it returns an error.
+The arguments match those of mount(2) and their interpretation
+depends on filesystem type.  E.g. for block filesystems, dev_name is
+interpreted as block device name, that device is opened and if it
+contains a suitable filesystem image the method creates and initializes
+struct super_block accordingly, returning its root dentry to caller.
+
+->mount() may choose to return a subtree of existing filesystem - it
+doesn't have to create a new one.  The main result from the caller's
+point of view is a reference to dentry at the root of (sub)tree to
+be attached; creation of new superblock is a common side effect.
 
 The most interesting member of the superblock structure that the
-get_sb() method fills in is the "s_op" field. This is a pointer to
+mount() method fills in is the "s_op" field. This is a pointer to
 a "struct super_operations" which describes the next level of the
 filesystem implementation.
 
-Usually, a filesystem uses one of the generic get_sb() implementations
-and provides a fill_super() method instead. The generic methods are:
+Usually, a filesystem uses one of the generic mount() implementations
+and provides a fill_super() callback instead. The generic variants are:
 
-  get_sb_bdev: mount a filesystem residing on a block device
+  mount_bdev: mount a filesystem residing on a block device
 
-  get_sb_nodev: mount a filesystem that is not backed by a device
+  mount_nodev: mount a filesystem that is not backed by a device
 
-  get_sb_single: mount a filesystem which shares the instance between
+  mount_single: mount a filesystem which shares the instance between
         all mounts
 
-A fill_super() method implementation has the following arguments:
+A fill_super() callback implementation has the following arguments:
 
-  struct super_block *sb: the superblock structure. The method fill_super()
+  struct super_block *sb: the superblock structure. The callback
         must initialize this properly.
 
   void *data: arbitrary mount options, usually comes as an ASCII
@@ -246,7 +254,7 @@ or bottom half).
         should be synchronous or not, not all filesystems check this flag.
 
   drop_inode: called when the last access to the inode is dropped,
-        with the inode_lock spinlock held.
+        with the inode->i_lock spinlock held.
 
         This method should be either NULL (normal UNIX filesystem
         semantics) or "generic_delete_inode" (for filesystems that do not
@@ -865,7 +873,7 @@ struct dentry_operations {
         void (*d_iput)(struct dentry *, struct inode *);
         char *(*d_dname)(struct dentry *, char *, int);
         struct vfsmount *(*d_automount)(struct path *);
-        int (*d_manage)(struct dentry *, bool, bool);
+        int (*d_manage)(struct dentry *, bool);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -961,10 +969,6 @@ struct dentry_operations {
         mounted on it and not to check the automount flag.  Any other error
         code will abort pathwalk completely.
 
-        If the 'mounting_here' parameter is true, then namespace_sem is being
-        held by the caller and the function should not initiate any mounts or
-        unmounts that it will then wait for.
-
         If the 'rcu_walk' parameter is true, then the caller is doing a
         pathwalk in RCU-walk mode.  Sleeping is not permitted in this mode,
         and the caller can be asked to leave it and call again by returing
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.txt b/Documentation/filesystems/xfs-delayed-logging-design.txt
index 7445bf335dae..5282e3e51413 100644
--- a/Documentation/filesystems/xfs-delayed-logging-design.txt
+++ b/Documentation/filesystems/xfs-delayed-logging-design.txt
@@ -791,10 +791,3 @@ mount option. Fundamentally, there is no reason why the log manager would not
 be able to swap methods automatically and transparently depending on load
 characteristics, but this should not be necessary if delayed logging works as
 designed.
-
-Roadmap:
-
-2.6.39 Switch default mount option to use delayed logging
-        => should be roughly 12 months after initial merge
-        => enough time to shake out remaining problems before next round of
-           enterprise distro kernel rebases