Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	include/asm-x86/statfs.h

5 files changed, 303 insertions, 51 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 680fb566b928..8362860e21a7 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -144,8 +144,8 @@ prototypes:
         void (*kill_sb) (struct super_block *);
 locking rules:
                 may block       BKL
-get_sb          yes             yes
-kill_sb         yes             yes
+get_sb          yes             no
+kill_sb         yes             no
 
 ->get_sb() returns error or 0 with locked superblock attached to the vfsmount
 (exclusive on ->s_umount).
@@ -409,12 +409,12 @@ ioctl:			yes	(see below)
 unlocked_ioctl:         no      (see below)
 compat_ioctl:           no
 mmap:                   no
-open:                   maybe   (see below)
+open:                   no
 flush:                  no
 release:                no
 fsync:                  no      (see below)
 aio_fsync:              no
-fasync:                 yes     (see below)
+fasync:                 no
 lock:                   yes
 readv:                  no
 writev:                 no
@@ -431,13 +431,6 @@ For many filesystems, it is probably safe to acquire the inode
 semaphore.  Note some filesystems (i.e. remote ones) provide no
 protection for i_size so you will need to use the BKL.
 
-->open() locking is in-transit: big lock partially moved into the methods.
-The only exception is ->open() in the instances of file_operations that never
-end up in ->i_fop/->proc_fops, i.e. ones that belong to character devices
-(chrdev_open() takes lock before replacing ->f_op and calling the secondary
-method. As soon as we fix the handling of module reference counters all
-instances of ->open() will be called without the BKL.
-
 Note: ext2_release() was *the* source of contention on fs-intensive
 loads and dropping BKL on ->release() helps to get rid of that (we still
 grab BKL for cases when we close a file that had been opened r/w, but that
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 0d5394920a31..eb154ef36c2a 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -32,9 +32,9 @@ Mailing list: linux-ext4@vger.kernel.org
     you will need to merge your changes with the version from e2fsprogs
     1.41.x.
 
-  - Create a new filesystem using the ext4dev filesystem type:
+  - Create a new filesystem using the ext4 filesystem type:
 
-        # mke2fs -t ext4dev /dev/hda1
+        # mke2fs -t ext4 /dev/hda1
 
     Or configure an existing ext3 filesystem to support extents and set
     the test_fs flag to indicate that it's ok for an in-development
@@ -47,13 +47,13 @@ Mailing list: linux-ext4@vger.kernel.org
 
         # tune2fs -I 256 /dev/hda1
 
-    (Note: we currently do not have tools to convert an ext4dev
+    (Note: we currently do not have tools to convert an ext4
     filesystem back to ext3; so please do not do try this on production
     filesystems.)
 
   - Mounting:
 
-        # mount -t ext4dev /dev/hda1 /wherever
+        # mount -t ext4 /dev/hda1 /wherever
 
   - When comparing performance with other filesystems, remember that
     ext3/4 by default offers higher data integrity guarantees than most.
@@ -177,6 +177,11 @@ barrier=<0|1(*)>	This enables/disables the use of write barriers in
                         your disks are battery-backed in one way or another,
                         disabling barriers may safely improve performance.
 
+inode_readahead=n       This tuning parameter controls the maximum
+                        number of inode table blocks that ext4's inode
+                        table readahead algorithm will pre-read into
+                        the buffer cache.  The default value is 32 blocks.
+
 orlov           (*)     This enables the new Orlov block allocator. It is
                         enabled by default.
 
@@ -218,6 +223,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue         Keep going on a filesystem error.
 errors=panic            Panic and halt the machine if an error occurs.
 
+data_err=ignore(*)      Just print an error message if an error occurs
+                        in a file data buffer in ordered mode.
+data_err=abort          Abort the journal if an error occurs in a file
+                        data buffer in ordered mode.
+
 grpid                   Give objects the same group ID as their creator.
 bsdgroups
 
@@ -252,6 +262,7 @@ stripe=n		Number of filesystem blocks that mballoc will try
 delalloc        (*)     Deferring block allocation until write-out time.
 nodelalloc              Disable delayed allocation. Blocks are allocation
                         when data is copied from user to page cache.
+
 Data Mode
 =========
 There are 3 different data modes:
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
new file mode 100644
index 000000000000..1e3defcfe50b
--- /dev/null
+++ b/Documentation/filesystems/fiemap.txt
@@ -0,0 +1,228 @@
+============
+Fiemap Ioctl
+============
+
+The fiemap ioctl is an efficient method for userspace to get file
+extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
+returns a list of extents.
+
+
+Request Basics
+--------------
+
+A fiemap request is encoded within struct fiemap:
+
+struct fiemap {
+        __u64   fm_start;        /* logical offset (inclusive) at
+                                  * which to start mapping (in) */
+        __u64   fm_length;       /* logical length of mapping which
+                                  * userspace cares about (in) */
+        __u32   fm_flags;        /* FIEMAP_FLAG_* flags for request (in/out) */
+        __u32   fm_mapped_extents; /* number of extents that were
+                                    * mapped (out) */
+        __u32   fm_extent_count; /* size of fm_extents array (in) */
+        __u32   fm_reserved;
+        struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+
+
+fm_start, and fm_length specify the logical range within the file
+which the process would like mappings for. Extents returned mirror
+those on disk - that is, the logical offset of the 1st returned extent
+may start before fm_start, and the range covered by the last returned
+extent may end after fm_length. All offsets and lengths are in bytes.
+
+Certain flags to modify the way in which mappings are looked up can be
+set in fm_flags. If the kernel doesn't understand some particular
+flags, it will return EBADR and the contents of fm_flags will contain
+the set of flags which caused the error. If the kernel is compatible
+with all flags passed, the contents of fm_flags will be unmodified.
+It is up to userspace to determine whether rejection of a particular
+flag is fatal to it's operation. This scheme is intended to allow the
+fiemap interface to grow in the future but without losing
+compatibility with old software.
+
+fm_extent_count specifies the number of elements in the fm_extents[] array
+that can be used to return extents.  If fm_extent_count is zero, then the
+fm_extents[] array is ignored (no extents will be returned), and the
+fm_mapped_extents count will hold the number of extents needed in
+fm_extents[] to hold the file's current mapping.  Note that there is
+nothing to prevent the file from changing between calls to FIEMAP.
+
+The following flags can be set in fm_flags:
+
+* FIEMAP_FLAG_SYNC
+If this flag is set, the kernel will sync the file before mapping extents.
+
+* FIEMAP_FLAG_XATTR
+If this flag is set, the extents returned will describe the inodes
+extended attribute lookup tree, instead of it's data tree.
+
+
+Extent Mapping
+--------------
+
+Extent information is returned within the embedded fm_extents array
+which userspace must allocate along with the fiemap structure. The
+number of elements in the fiemap_extents[] array should be passed via
+fm_extent_count. The number of extents mapped by kernel will be
+returned via fm_mapped_extents. If the number of fiemap_extents
+allocated is less than would be required to map the requested range,
+the maximum number of extents that can be mapped in the fm_extent[]
+array will be returned and fm_mapped_extents will be equal to
+fm_extent_count. In that case, the last extent in the array will not
+complete the requested range and will not have the FIEMAP_EXTENT_LAST
+flag set (see the next section on extent flags).
+
+Each extent is described by a single fiemap_extent structure as
+returned in fm_extents.
+
+struct fiemap_extent {
+        __u64   fe_logical;  /* logical offset in bytes for the start of
+                              * the extent */
+        __u64   fe_physical; /* physical offset in bytes for the start
+                              * of the extent */
+        __u64   fe_length;   /* length in bytes for the extent */
+        __u64   fe_reserved64[2];
+        __u32   fe_flags;    /* FIEMAP_EXTENT_* flags for this extent */
+        __u32   fe_reserved[3];
+};
+
+All offsets and lengths are in bytes and mirror those on disk.  It is valid
+for an extents logical offset to start before the request or it's logical
+length to extend past the request.  Unless FIEMAP_EXTENT_NOT_ALIGNED is
+returned, fe_logical, fe_physical, and fe_length will be aligned to the
+block size of the file system.  With the exception of extents flagged as
+FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
+
+The fe_flags field contains flags which describe the extent returned.
+A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
+the file so that the process making fiemap calls can determine when no
+more extents are available, without having to call the ioctl again.
+
+Some flags are intentionally vague and will always be set in the
+presence of other more specific flags. This way a program looking for
+a general property does not have to know all existing and future flags
+which imply that property.
+
+For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
+are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
+for inline or tail-packed data can key on the specific flag. Software
+which simply cares not to try operating on non-aligned extents
+however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
+worry about all present and future flags which might imply unaligned
+data. Note that the opposite is not true - it would be valid for
+FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
+
+* FIEMAP_EXTENT_LAST
+This is the last extent in the file. A mapping attempt past this
+extent will return nothing.
+
+* FIEMAP_EXTENT_UNKNOWN
+The location of this extent is currently unknown. This may indicate
+the data is stored on an inaccessible volume or that no storage has
+been allocated for the file yet.
+
+* FIEMAP_EXTENT_DELALLOC
+  - This will also set FIEMAP_EXTENT_UNKNOWN.
+Delayed allocation - while there is data for this extent, it's
+physical location has not been allocated yet.
+
+* FIEMAP_EXTENT_ENCODED
+This extent does not consist of plain filesystem blocks but is
+encoded (e.g. encrypted or compressed).  Reading the data in this
+extent via I/O to the block device will have undefined results.
+
+Note that it is *always* undefined to try to update the data
+in-place by writing to the indicated location without the
+assistance of the filesystem, or to access the data using the
+information returned by the FIEMAP interface while the filesystem
+is mounted.  In other words, user applications may only read the
+extent data via I/O to the block device while the filesystem is
+unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is
+clear; user applications must not try reading or writing to the
+filesystem via the block device under any other circumstances.
+
+* FIEMAP_EXTENT_DATA_ENCRYPTED
+  - This will also set FIEMAP_EXTENT_ENCODED
+The data in this extent has been encrypted by the file system.
+
+* FIEMAP_EXTENT_NOT_ALIGNED
+Extent offsets and length are not guaranteed to be block aligned.
+
+* FIEMAP_EXTENT_DATA_INLINE
+  This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is located within a meta data block.
+
+* FIEMAP_EXTENT_DATA_TAIL
+  This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is packed into a block with data from other files.
+
+* FIEMAP_EXTENT_UNWRITTEN
+Unwritten extent - the extent is allocated but it's data has not been
+initialized.  This indicates the extent's data will be all zero if read
+through the filesystem but the contents are undefined if read directly from
+the device.
+
+* FIEMAP_EXTENT_MERGED
+This will be set when a file does not support extents, i.e., it uses a block
+based addressing scheme.  Since returning an extent for each block back to
+userspace would be highly inefficient, the kernel will try to merge most
+adjacent blocks into 'extents'.
+
+
+VFS -> File System Implementation
+---------------------------------
+
+File systems wishing to support fiemap must implement a ->fiemap callback on
+their inode_operations structure. The fs ->fiemap call is responsible for
+defining it's set of supported fiemap flags, and calling a helper function on
+each discovered extent:
+
+struct inode_operations {
+       ...
+
+       int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+                     u64 len);
+
+->fiemap is passed struct fiemap_extent_info which describes the
+fiemap request:
+
+struct fiemap_extent_info {
+        unsigned int fi_flags;          /* Flags as passed from user */
+        unsigned int fi_extents_mapped; /* Number of mapped extents */
+        unsigned int fi_extents_max;    /* Size of fiemap_extent array */
+        struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
+};
+
+It is intended that the file system should not need to access any of this
+structure directly.
+
+
+Flag checking should be done at the beginning of the ->fiemap callback via the
+fiemap_check_flags() helper:
+
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
+fiemap_check_flags finds invalid user flags, it will place the bad values in
+fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
+fiemap_check_flags(), it should immediately exit, returning that error back to
+ioctl_fiemap().
+
+
+For each extent in the request range, the file system should call
+the helper function, fiemap_fill_next_extent():
+
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+                            u64 phys, u64 len, u32 flags, u32 dev);
+
+fiemap_fill_next_extent() will use the passed values to populate the
+next free extent in the fm_extents array. 'General' extent flags will
+automatically be set from specific flags on behalf of the calling file
+system so that the userspace API is not broken.
+
+fiemap_fill_next_extent() returns 0 on success, and 1 when the
+user-supplied fm_extents array is full. If an error is encountered
+while copying the extent to user memory, -EFAULT will be returned.
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index e79ee2db183a..ac2a261c5f7d 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -40,7 +40,7 @@ Web site
 ========
 
 There is plenty of additional information on the linux-ntfs web site
-at http://linux-ntfs.sourceforge.net/
+at http://www.linux-ntfs.org/
 
 The web site has a lot of additional information, such as a comprehensive
 FAQ, documentation on the NTFS on-disk format, information on the Linux-NTFS
@@ -272,7 +272,7 @@ And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 =
 For Win2k and later dynamic disks, you can for example use the ldminfo utility
 which is part of the Linux LDM tools (the latest version at the time of
 writing is linux-ldm-0.0.8.tar.bz2).  You can download it from:
-        http://linux-ntfs.sourceforge.net/downloads.html
+        http://www.linux-ntfs.org/
 Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go
 into it (cd linux-ldm-0.0.8) and change to the test directory (cd test).  You
 will find the precompiled (i386) ldminfo utility there.  NOTE: You will not be
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 64557821ee59..d831d24d2a6c 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -923,45 +923,44 @@ CPUs.
 The   "procs_blocked" line gives  the  number of  processes currently blocked,
 waiting for I/O to complete.
 
+
 1.9 Ext4 file system parameters
 ------------------------------
-Ext4 file system have one directory per partition under /proc/fs/ext4/
-# ls /proc/fs/ext4/hdc/
-group_prealloc  max_to_scan  mb_groups  mb_history  min_to_scan  order2_req
-stats  stream_req
-
-mb_groups:
-This file gives the details of multiblock allocator buddy cache of free blocks
-
-mb_history:
-Multiblock allocation history.
-
-stats:
-This file indicate whether the multiblock allocator should start collecting
-statistics. The statistics are shown during unmount
 
-group_prealloc:
-The multiblock allocator normalize the block allocation request to
-group_prealloc filesystem blocks if we don't have strip value set.
-The stripe value can be specified at mount time or during mke2fs.
+Information about mounted ext4 file systems can be found in
+/proc/fs/ext4.  Each mounted filesystem will have a directory in
+/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
+/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
+in Table 1-10, below.
 
-max_to_scan:
-How long multiblock allocator can look for a best extent (in found extents)
-
-min_to_scan:
-How long multiblock allocator  must look for a best extent
-
-order2_req:
-Multiblock allocator use  2^N search using buddies only for requests greater
-than or equal to order2_req. The request size is specfied in file system
-blocks. A value of 2 indicate only if the requests are greater than or equal
-to 4 blocks.
+Table 1-10: Files in /proc/fs/ext4/<devname>
+..............................................................................
+ File            Content                                        
+ mb_groups       details of multiblock allocator buddy cache of free blocks
+ mb_history      multiblock allocation history
+ stats           controls whether the multiblock allocator should start
+                 collecting statistics, which are shown during the unmount
+ group_prealloc  the multiblock allocator will round up allocation
+                 requests to a multiple of this tuning parameter if the
+                 stripe size is not set in the ext4 superblock
+ max_to_scan     The maximum number of extents the multiblock allocator
+                 will search to find the best extent
+ min_to_scan     The minimum number of extents the multiblock allocator
+                 will search to find the best extent
+ order2_req      Tuning parameter which controls the minimum size for 
+                 requests (as a power of 2) where the buddy cache is
+                 used
+ stream_req      Files which have fewer blocks than this tunable
+                 parameter will have their blocks allocated out of a
+                 block group specific preallocation pool, so that small
+                 files are packed closely together.  Each large file
+                 will have its blocks allocated out of its own unique
+                 preallocation pool.
+inode_readahead  Tuning parameter which controls the maximum number of
+                 inode table blocks that ext4's inode table readahead
+                 algorithm will pre-read into the buffer cache
+..............................................................................
 
-stream_req:
-Files smaller than stream_req are served by the stream allocator, whose
-purpose is to pack requests as close each to other as possible to
-produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16
-filesystem block size will use group based preallocation.
 
 ------------------------------------------------------------------------------
 Summary
@@ -1339,6 +1338,25 @@ Enables/Disables the protection of the per-process proc entries "maps" and
 "smaps".  When enabled, the contents of these files are visible only to
 readers that are allowed to ptrace() the given process.
 
+msgmni
+------
+
+Maximum number of message queue ids on the system.
+This value scales to the amount of lowmem. It is automatically recomputed
+upon memory add/remove or ipc namespace creation/removal.
+When a value is written into this file, msgmni's value becomes fixed, i.e. it
+is not recomputed anymore when one of the above events occurs.
+Use auto_msgmni to change this behavior.
+
+auto_msgmni
+-----------
+
+Enables/Disables automatic recomputing of msgmni upon memory add/remove or
+upon ipc namespace creation/removal (see the msgmni description above).
+Echoing "1" into this file enables msgmni automatic recomputing.
+Echoing "0" turns it off.
+auto_msgmni default value is 1.
+
 
 2.4 /proc/sys/vm - The virtual memory subsystem
 -----------------------------------------------
@@ -2394,6 +2412,8 @@ The following 4 memory types are supported:
   - (bit 1) anonymous shared memory
   - (bit 2) file-backed private memory
   - (bit 3) file-backed shared memory
+  - (bit 4) ELF header pages in file-backed private memory areas (it is
+            effective only if the bit 2 is cleared)
 
   Note that MMIO pages such as frame buffer are never dumped and vDSO pages
   are always dumped regardless of the bitmask status.