Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (43 commits)
  ext4: Rename ext4dev to ext4
  ext4: Avoid double dirtying of super block in ext4_put_super()
  Update ext4 MAINTAINERS file
  Hook ext4 to the vfs fiemap interface.
  generic block based fiemap implementation
  ocfs2: fiemap support
  vfs: vfs-level fiemap interface
  ext4: fix xattr deadlock
  jbd2: Fix buffer head leak when writing the commit block
  ext4: Add debugging markers that can be used by systemtap
  jbd2: abort instead of waiting for nonexistent transaction
  ext4: fix initialization of UNINIT bitmap blocks
  ext4: Remove old legacy block allocator
  ext4: Use readahead when reading an inode from the inode table
  ext4: Improve the documentation for ext4's /proc tunables
  ext4: Combine proc file handling into a single set of functions
  ext4: move /proc setup and teardown out of mballoc.c
  ext4: Don't use 'struct dentry' for internal lookups
  ext4/jbd2: Avoid WARN() messages when failing to write to the superblock
  ext4: use percpu data structures for lg_prealloc_list
  ...

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.
 
@@ -252,6 +257,7 @@ 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:

Documentation/filesystems/fiemap.txt

+============
+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.

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.
-
-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.
-
-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.
+
+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.
+
+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
+..............................................................................
+
 
 ------------------------------------------------------------------------------
 Summary

MAINTAINERS

@@ -1659,9 +1659,10 @@ L:	linux-ext4@vger.kernel.org
 S:	Maintained
 
 EXT4 FILE SYSTEM
-P:	Stephen Tweedie, Andrew Morton
-M:	sct@redhat.com, akpm@linux-foundation.org, adilger@sun.com
+P:	Theodore Ts'o
+M:	tytso@mit.edu, adilger@sun.com
 L:	linux-ext4@vger.kernel.org
+W:	http://ext4.wiki.kernel.org
 S:	Maintained
 
 F71805F HARDWARE MONITORING DRIVER

fs/Kconfig

@@ -136,37 +136,51 @@ config EXT3_FS_SECURITY
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
 
-config EXT4DEV_FS
-	tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+config EXT4_FS
+	tristate "The Extended 4 (ext4) filesystem"
 	select JBD2
 	select CRC16
 	help
-	  Ext4dev is a predecessor filesystem of the next generation
-	  extended fs ext4, based on ext3 filesystem code. It will be
-	  renamed ext4 fs later, once ext4dev is mature and stabilized.
+	  This is the next generation of the ext3 filesystem.
 
 	  Unlike the change from ext2 filesystem to ext3 filesystem,
-	  the on-disk format of ext4dev is not the same as ext3 any more:
-	  it is based on extent maps and it supports 48-bit physical block
-	  numbers. These combined on-disk format changes will allow
-	  ext4dev/ext4 to handle more than 16 TB filesystem volumes --
-	  a hard limit that ext3 cannot overcome without changing the
-	  on-disk format.
-
-	  Other than extent maps and 48-bit block numbers, ext4dev also is
-	  likely to have other new features such as persistent preallocation,
-	  high resolution time stamps, and larger file support etc.  These
-	  features will be added to ext4dev gradually.
+	  the on-disk format of ext4 is not forwards compatible with
+	  ext3; it is based on extent maps and it supports 48-bit
+	  physical block numbers.  The ext4 filesystem also supports delayed
+	  allocation, persistent preallocation, high resolution time stamps,
+	  and a number of other features to improve performance and speed
+	  up fsck time.  For more information, please see the web pages at
+	  http://ext4.wiki.kernel.org.
+
+	  The ext4 filesystem will support mounting an ext3
+	  filesystem; while there will be some performance gains from
+	  the delayed allocation and inode table readahead, the best
+	  performance gains will require enabling ext4 features in the
+	  filesystem, or formating a new filesystem as an ext4
+	  filesystem initially.
 
 	  To compile this file system support as a module, choose M here. The
 	  module will be called ext4dev.
 
 	  If unsure, say N.
 
-config EXT4DEV_FS_XATTR
-	bool "Ext4dev extended attributes"
-	depends on EXT4DEV_FS
+config EXT4DEV_COMPAT
+	bool "Enable ext4dev compatibility"
+	depends on EXT4_FS
+	help
+	  Starting with 2.6.28, the name of the ext4 filesystem was
+	  renamed from ext4dev to ext4.  Unfortunately there are some
+	  lagecy userspace programs (such as klibc's fstype) have
+	  "ext4dev" hardcoded.  
+
+	  To enable backwards compatibility so that systems that are
+	  still expecting to mount ext4 filesystems using ext4dev,
+	  chose Y here.   This feature will go away by 2.6.31, so
+	  please arrange to get your userspace programs fixed!
+
+config EXT4_FS_XATTR
+	bool "Ext4 extended attributes"
+	depends on EXT4_FS
 	default y
 	help
 	  Extended attributes are name:value pairs associated with inodes by
@@ -175,11 +189,11 @@ config EXT4DEV_FS_XATTR
 
 	  If unsure, say N.
 
-	  You need this for POSIX ACL support on ext4dev/ext4.
+	  You need this for POSIX ACL support on ext4.
 
-config EXT4DEV_FS_POSIX_ACL
-	bool "Ext4dev POSIX Access Control Lists"
-	depends on EXT4DEV_FS_XATTR
+config EXT4_FS_POSIX_ACL
+	bool "Ext4 POSIX Access Control Lists"
+	depends on EXT4_FS_XATTR
 	select FS_POSIX_ACL
 	help
 	  POSIX Access Control Lists (ACLs) support permissions for users and
@@ -190,14 +204,14 @@ config EXT4DEV_FS_POSIX_ACL
 
 	  If you don't know what Access Control Lists are, say N
 
-config EXT4DEV_FS_SECURITY
-	bool "Ext4dev Security Labels"
-	depends on EXT4DEV_FS_XATTR
+config EXT4_FS_SECURITY
+	bool "Ext4 Security Labels"
+	depends on EXT4_FS_XATTR
 	help
 	  Security labels support alternative access control models
 	  implemented by security modules like SELinux.  This option
 	  enables an extended attribute handler for file security
-	  labels in the ext4dev/ext4 filesystem.
+	  labels in the ext4 filesystem.
 
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
@@ -240,22 +254,22 @@ config JBD2
 	help
 	  This is a generic journaling layer for block devices that support
 	  both 32-bit and 64-bit block numbers.  It is currently used by
-	  the ext4dev/ext4 filesystem, but it could also be used to add
+	  the ext4 filesystem, but it could also be used to add
 	  journal support to other file systems or block devices such
 	  as RAID or LVM.
 
-	  If you are using ext4dev/ext4, you need to say Y here. If you are not
-	  using ext4dev/ext4 then you will probably want to say N.
+	  If you are using ext4, you need to say Y here. If you are not
+	  using ext4 then you will probably want to say N.
 
 	  To compile this device as a module, choose M here. The module will be
-	  called jbd2.  If you are compiling ext4dev/ext4 into the kernel,
+	  called jbd2.  If you are compiling ext4 into the kernel,
 	  you cannot compile this code as a module.
 
 config JBD2_DEBUG
-	bool "JBD2 (ext4dev/ext4) debugging support"
+	bool "JBD2 (ext4) debugging support"
 	depends on JBD2 && DEBUG_FS
 	help
-	  If you are using the ext4dev/ext4 journaled file system (or
+	  If you are using the ext4 journaled file system (or
 	  potentially any other filesystem/device using JBD2), this option
 	  allows you to enable debugging output while the system is running,
 	  in order to help track down any problems you are having.
@@ -270,9 +284,9 @@ config JBD2_DEBUG
 config FS_MBCACHE
 # Meta block cache for Extended Attributes (ext2/ext3/ext4)
 	tristate
-	depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4DEV_FS_XATTR
-	default y if EXT2_FS=y || EXT3_FS=y || EXT4DEV_FS=y
-	default m if EXT2_FS=m || EXT3_FS=m || EXT4DEV_FS=m
+	depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR
+	default y if EXT2_FS=y || EXT3_FS=y || EXT4_FS=y
+	default m if EXT2_FS=m || EXT3_FS=m || EXT4_FS=m
 
 config REISERFS_FS
 	tristate "Reiserfs support"

fs/Makefile

@@ -69,7 +69,7 @@ obj-$(CONFIG_DLM)		+= dlm/
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
-obj-$(CONFIG_EXT4DEV_FS)	+= ext4/ # Before ext2 so root fs can be ext4dev
+obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4dev
 obj-$(CONFIG_JBD)		+= jbd/
 obj-$(CONFIG_JBD2)		+= jbd2/
 obj-$(CONFIG_EXT2_FS)		+= ext2/

fs/ext2/ext2.h

@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);
 extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len);
 int __ext2_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, void **fsdata);

fs/ext2/file.c

@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
 #endif
 	.setattr	= ext2_setattr,
 	.permission	= ext2_permission,
+	.fiemap		= ext2_fiemap,
 };

fs/ext2/inode.c

@@ -31,6 +31,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
+#include <linux/fiemap.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
 
 }
 
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 len)
+{
+	return generic_block_fiemap(inode, fieinfo, start, len,
+				    ext2_get_block);
+}
+
 static int ext2_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, ext2_get_block, wbc);

fs/ext3/file.c

@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.permission	= ext3_permission,
+	.fiemap		= ext3_fiemap,
 };
 

fs/ext3/inode.c

@@ -36,6 +36,7 @@
 #include <linux/mpage.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+#include <linux/fiemap.h>
 #include "xattr.h"
 #include "acl.h"
 
@@ -981,6 +982,13 @@ static int ext3_get_block(struct inode *inode, sector_t iblock,
 	return ret;
 }
 
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 len)
+{
+	return generic_block_fiemap(inode, fieinfo, start, len,
+				    ext3_get_block);
+}
+
 /*
  * `handle' can be NULL if create is zero
  */

fs/ext4/Makefile

@@ -2,12 +2,12 @@
 # Makefile for the linux ext4-filesystem routines.
 #
 
-obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o
+obj-$(CONFIG_EXT4_FS) += ext4.o
 
-ext4dev-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
 		   ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
 		   ext4_jbd2.o migrate.o mballoc.o
 
-ext4dev-$(CONFIG_EXT4DEV_FS_XATTR)	+= xattr.o xattr_user.o xattr_trusted.o
-ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL)	+= acl.o
-ext4dev-$(CONFIG_EXT4DEV_FS_SECURITY)	+= xattr_security.o
+ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
+ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
+ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o

fs/ext4/acl.h

@@ -51,18 +51,18 @@ static inline int ext4_acl_count(size_t size)
 	}
 }
 
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 
 /* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl
    if the ACL has not been cached */
 #define EXT4_ACL_NOT_CACHED ((void *)-1)
 
 /* acl.c */
-extern int ext4_permission (struct inode *, int);
-extern int ext4_acl_chmod (struct inode *);
-extern int ext4_init_acl (handle_t *, struct inode *, struct inode *);
+extern int ext4_permission(struct inode *, int);
+extern int ext4_acl_chmod(struct inode *);
+extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
 
-#else  /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+#else  /* CONFIG_EXT4_FS_POSIX_ACL */
 #include <linux/sched.h>
 #define ext4_permission NULL
 
@@ -77,5 +77,5 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 {
 	return 0;
 }
-#endif  /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+#endif  /* CONFIG_EXT4_FS_POSIX_ACL */
 

fs/ext4/balloc.c

@@ -83,6 +83,7 @@ static int ext4_group_used_meta_blocks(struct super_block *sb,
 	}
 	return used_blocks;
 }
+
 /* Initializes an uninitialized block bitmap if given, and returns the
  * number of blocks free in the group. */
 unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
@@ -132,7 +133,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		group_blocks = ext4_blocks_count(sbi->s_es) -
 			le32_to_cpu(sbi->s_es->s_first_data_block) -
-			(EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1));
+			(EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
 	} else {
 		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
 	}
@@ -200,20 +201,20 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
  * @bh:			pointer to the buffer head to store the block
  *			group descriptor
  */
-struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 					     ext4_group_t block_group,
-					     struct buffer_head ** bh)
+					     struct buffer_head **bh)
 {
 	unsigned long group_desc;
 	unsigned long offset;
-	struct ext4_group_desc * desc;
+	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (block_group >= sbi->s_groups_count) {
-		ext4_error (sb, "ext4_get_group_desc",
-			    "block_group >= groups_count - "
-			    "block_group = %lu, groups_count = %lu",
-			    block_group, sbi->s_groups_count);
+		ext4_error(sb, "ext4_get_group_desc",
+			   "block_group >= groups_count - "
+			   "block_group = %lu, groups_count = %lu",
+			   block_group, sbi->s_groups_count);
 
 		return NULL;
 	}
@@ -222,10 +223,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
 	if (!sbi->s_group_desc[group_desc]) {
-		ext4_error (sb, "ext4_get_group_desc",
-			    "Group descriptor not loaded - "
-			    "block_group = %lu, group_desc = %lu, desc = %lu",
-			     block_group, group_desc, offset);
+		ext4_error(sb, "ext4_get_group_desc",
+			   "Group descriptor not loaded - "
+			   "block_group = %lu, group_desc = %lu, desc = %lu",
+			   block_group, group_desc, offset);
 		return NULL;
 	}
 
@@ -302,8 +303,8 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
 struct buffer_head *
 ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 {
-	struct ext4_group_desc * desc;
-	struct buffer_head * bh = NULL;
+	struct ext4_group_desc *desc;
+	struct buffer_head *bh = NULL;
 	ext4_fsblk_t bitmap_blk;
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -318,9 +319,11 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (bh_uptodate_or_lock(bh))
+	if (buffer_uptodate(bh) &&
+	    !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
 		return bh;
 
+	lock_buffer(bh);
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		ext4_init_block_bitmap(sb, bh, block_group, desc);
@@ -345,301 +348,6 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 */
 	return bh;
 }
-/*
- * The reservation window structure operations
- * --------------------------------------------
- * Operations include:
- * dump, find, add, remove, is_empty, find_next_reservable_window, etc.
- *
- * We use a red-black tree to represent per-filesystem reservation
- * windows.
- *
- */
-
-/**
- * __rsv_window_dump() -- Dump the filesystem block allocation reservation map
- * @rb_root:		root of per-filesystem reservation rb tree
- * @verbose:		verbose mode
- * @fn:			function which wishes to dump the reservation map
- *
- * If verbose is turned on, it will print the whole block reservation
- * windows(start, end).	Otherwise, it will only print out the "bad" windows,
- * those windows that overlap with their immediate neighbors.
- */
-#if 1
-static void __rsv_window_dump(struct rb_root *root, int verbose,
-			      const char *fn)
-{
-	struct rb_node *n;
-	struct ext4_reserve_window_node *rsv, *prev;
-	int bad;
-
-restart:
-	n = rb_first(root);
-	bad = 0;
-	prev = NULL;
-
-	printk("Block Allocation Reservation Windows Map (%s):\n", fn);
-	while (n) {
-		rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-		if (verbose)
-			printk("reservation window 0x%p "
-			       "start:  %llu, end:  %llu\n",
-			       rsv, rsv->rsv_start, rsv->rsv_end);
-		if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
-			printk("Bad reservation %p (start >= end)\n",
-			       rsv);
-			bad = 1;
-		}
-		if (prev && prev->rsv_end >= rsv->rsv_start) {
-			printk("Bad reservation %p (prev->end >= start)\n",
-			       rsv);
-			bad = 1;
-		}
-		if (bad) {
-			if (!verbose) {
-				printk("Restarting reservation walk in verbose mode\n");
-				verbose = 1;
-				goto restart;
-			}
-		}
-		n = rb_next(n);
-		prev = rsv;
-	}
-	printk("Window map complete.\n");
-	BUG_ON(bad);
-}
-#define rsv_window_dump(root, verbose) \
-	__rsv_window_dump((root), (verbose), __func__)
-#else
-#define rsv_window_dump(root, verbose) do {} while (0)
-#endif
-
-/**
- * goal_in_my_reservation()
- * @rsv:		inode's reservation window
- * @grp_goal:		given goal block relative to the allocation block group
- * @group:		the current allocation block group
- * @sb:			filesystem super block
- *
- * Test if the given goal block (group relative) is within the file's
- * own block reservation window range.
- *
- * If the reservation window is outside the goal allocation group, return 0;
- * grp_goal (given goal block) could be -1, which means no specific
- * goal block. In this case, always return 1.
- * If the goal block is within the reservation window, return 1;
- * otherwise, return 0;
- */
-static int
-goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
-			ext4_group_t group, struct super_block *sb)
-{
-	ext4_fsblk_t group_first_block, group_last_block;
-
-	group_first_block = ext4_group_first_block_no(sb, group);
-	group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-	if ((rsv->_rsv_start > group_last_block) ||
-	    (rsv->_rsv_end < group_first_block))
-		return 0;
-	if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
-		|| (grp_goal + group_first_block > rsv->_rsv_end)))
-		return 0;
-	return 1;
-}
-
-/**
- * search_reserve_window()
- * @rb_root:		root of reservation tree
- * @goal:		target allocation block
- *
- * Find the reserved window which includes the goal, or the previous one
- * if the goal is not in any window.
- * Returns NULL if there are no windows or if all windows start after the goal.
- */
-static struct ext4_reserve_window_node *
-search_reserve_window(struct rb_root *root, ext4_fsblk_t goal)
-{
-	struct rb_node *n = root->rb_node;
-	struct ext4_reserve_window_node *rsv;
-
-	if (!n)
-		return NULL;
-
-	do {
-		rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-
-		if (goal < rsv->rsv_start)
-			n = n->rb_left;
-		else if (goal > rsv->rsv_end)
-			n = n->rb_right;
-		else
-			return rsv;
-	} while (n);
-	/*
-	 * We've fallen off the end of the tree: the goal wasn't inside
-	 * any particular node.  OK, the previous node must be to one
-	 * side of the interval containing the goal.  If it's the RHS,
-	 * we need to back up one.
-	 */
-	if (rsv->rsv_start > goal) {
-		n = rb_prev(&rsv->rsv_node);
-		rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-	}
-	return rsv;
-}
-
-/**
- * ext4_rsv_window_add() -- Insert a window to the block reservation rb tree.
- * @sb:			super block
- * @rsv:		reservation window to add
- *
- * Must be called with rsv_lock hold.
- */
-void ext4_rsv_window_add(struct super_block *sb,
-		    struct ext4_reserve_window_node *rsv)
-{
-	struct rb_root *root = &EXT4_SB(sb)->s_rsv_window_root;
-	struct rb_node *node = &rsv->rsv_node;
-	ext4_fsblk_t start = rsv->rsv_start;
-
-	struct rb_node ** p = &root->rb_node;
-	struct rb_node * parent = NULL;
-	struct ext4_reserve_window_node *this;
-
-	while (*p)
-	{
-		parent = *p;
-		this = rb_entry(parent, struct ext4_reserve_window_node, rsv_node);
-
-		if (start < this->rsv_start)
-			p = &(*p)->rb_left;
-		else if (start > this->rsv_end)
-			p = &(*p)->rb_right;
-		else {
-			rsv_window_dump(root, 1);
-			BUG();
-		}
-	}
-
-	rb_link_node(node, parent, p);
-	rb_insert_color(node, root);
-}
-
-/**
- * ext4_rsv_window_remove() -- unlink a window from the reservation rb tree
- * @sb:			super block
- * @rsv:		reservation window to remove
- *
- * Mark the block reservation window as not allocated, and unlink it
- * from the filesystem reservation window rb tree. Must be called with
- * rsv_lock hold.
- */
-static void rsv_window_remove(struct super_block *sb,
-			      struct ext4_reserve_window_node *rsv)
-{
-	rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-	rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-	rsv->rsv_alloc_hit = 0;
-	rb_erase(&rsv->rsv_node, &EXT4_SB(sb)->s_rsv_window_root);
-}
-
-/*
- * rsv_is_empty() -- Check if the reservation window is allocated.
- * @rsv:		given reservation window to check
- *
- * returns 1 if the end block is EXT4_RESERVE_WINDOW_NOT_ALLOCATED.
- */
-static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
-{
-	/* a valid reservation end block could not be 0 */
-	return rsv->_rsv_end == EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-}
-
-/**
- * ext4_init_block_alloc_info()
- * @inode:		file inode structure
- *
- * Allocate and initialize the	reservation window structure, and
- * link the window to the ext4 inode structure at last
- *
- * The reservation window structure is only dynamically allocated
- * and linked to ext4 inode the first time the open file
- * needs a new block. So, before every ext4_new_block(s) call, for
- * regular files, we should check whether the reservation window
- * structure exists or not. In the latter case, this function is called.
- * Fail to do so will result in block reservation being turned off for that
- * open file.
- *
- * This function is called from ext4_get_blocks_handle(), also called
- * when setting the reservation window size through ioctl before the file
- * is open for write (needs block allocation).
- *
- * Needs down_write(i_data_sem) protection prior to call this function.
- */
-void ext4_init_block_alloc_info(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
-	struct super_block *sb = inode->i_sb;
-
-	block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
-	if (block_i) {
-		struct ext4_reserve_window_node *rsv = &block_i->rsv_window_node;
-
-		rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-		rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-
-		/*
-		 * if filesystem is mounted with NORESERVATION, the goal
-		 * reservation window size is set to zero to indicate
-		 * block reservation is off
-		 */
-		if (!test_opt(sb, RESERVATION))
-			rsv->rsv_goal_size = 0;
-		else
-			rsv->rsv_goal_size = EXT4_DEFAULT_RESERVE_BLOCKS;
-		rsv->rsv_alloc_hit = 0;
-		block_i->last_alloc_logical_block = 0;
-		block_i->last_alloc_physical_block = 0;
-	}
-	ei->i_block_alloc_info = block_i;
-}
-
-/**
- * ext4_discard_reservation()
- * @inode:		inode
- *
- * Discard(free) block reservation window on last file close, or truncate
- * or at last iput().
- *
- * It is being called in three cases:
- *	ext4_release_file(): last writer close the file
- *	ext4_clear_inode(): last iput(), when nobody link to this file.
- *	ext4_truncate(): when the block indirect map is about to change.
- *
- */
-void ext4_discard_reservation(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
-	struct ext4_reserve_window_node *rsv;
-	spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock;
-
-	ext4_mb_discard_inode_preallocations(inode);
-
-	if (!block_i)
-		return;
-
-	rsv = &block_i->rsv_window_node;
-	if (!rsv_is_empty(&rsv->rsv_window)) {
-		spin_lock(rsv_lock);
-		if (!rsv_is_empty(&rsv->rsv_window))
-			rsv_window_remove(inode->i_sb, rsv);
-		spin_unlock(rsv_lock);
-	}
-}
 
 /**
  * ext4_free_blocks_sb() -- Free given blocks and update quota
@@ -648,6 +356,13 @@ void ext4_discard_reservation(struct inode *inode)
  * @block:			start physcial block to free
  * @count:			number of blocks to free
  * @pdquot_freed_blocks:	pointer to quota
+ *
+ * XXX This function is only used by the on-line resizing code, which
+ * should probably be fixed up to call the mballoc variant.  There
+ * this needs to be cleaned up later; in fact, I'm not convinced this
+ * is 100% correct in the face of the mballoc code.  The online resizing
+ * code needs to be fixed up to more tightly (and correctly) interlock
+ * with the mballoc code.
  */
 void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 			 ext4_fsblk_t block, unsigned long count,
@@ -659,8 +374,8 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 	ext4_grpblk_t bit;
 	unsigned long i;
 	unsigned long overflow;
-	struct ext4_group_desc * desc;
-	struct ext4_super_block * es;
+	struct ext4_group_desc *desc;
+	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
 	int err = 0, ret;
 	ext4_grpblk_t group_freed;
@@ -671,13 +386,13 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 	if (block < le32_to_cpu(es->s_first_data_block) ||
 	    block + count < block ||
 	    block + count > ext4_blocks_count(es)) {
-		ext4_error (sb, "ext4_free_blocks",
-			    "Freeing blocks not in datazone - "
-			    "block = %llu, count = %lu", block, count);
+		ext4_error(sb, "ext4_free_blocks",
+			   "Freeing blocks not in datazone - "
+			   "block = %llu, count = %lu", block, count);
 		goto error_return;
 	}
 
-	ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1);
+	ext4_debug("freeing block(s) %llu-%llu\n", block, block + count - 1);
 
 do_more:
 	overflow = 0;
@@ -694,7 +409,7 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
 	if (!bitmap_bh)
 		goto error_return;
-	desc = ext4_get_group_desc (sb, block_group, &gd_bh);
+	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
 	if (!desc)
 		goto error_return;
 
@@ -703,10 +418,10 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
 	    in_range(block + count - 1, ext4_inode_table(sb, desc),
 		     sbi->s_itb_per_group)) {
-		ext4_error (sb, "ext4_free_blocks",
-			    "Freeing blocks in system zones - "
-			    "Block = %llu, count = %lu",
-			    block, count);
+		ext4_error(sb, "ext4_free_blocks",
+			   "Freeing blocks in system zones - "
+			   "Block = %llu, count = %lu",
+			   block, count);
 		goto error_return;
 	}
 
@@ -848,7 +563,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count,
 			int metadata)
 {
-	struct super_block * sb;
+	struct super_block *sb;
 	unsigned long dquot_freed_blocks;
 
 	/* this isn't the right place to decide whether block is metadata
@@ -859,747 +574,51 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	sb = inode->i_sb;
 
-	if (!test_opt(sb, MBALLOC) || !EXT4_SB(sb)->s_group_info)
-		ext4_free_blocks_sb(handle, sb, block, count,
-						&dquot_freed_blocks);
-	else
-		ext4_mb_free_blocks(handle, inode, block, count,
-						metadata, &dquot_freed_blocks);
+	ext4_mb_free_blocks(handle, inode, block, count,
+			    metadata, &dquot_freed_blocks);
 	if (dquot_freed_blocks)
 		DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
 	return;
 }
 
-/**
- * ext4_test_allocatable()
- * @nr:			given allocation block group
- * @bh:			bufferhead contains the bitmap of the given block group
- *
- * For ext4 allocations, we must not reuse any blocks which are
- * allocated in the bitmap buffer's "last committed data" copy.  This
- * prevents deletes from freeing up the page for reuse until we have
- * committed the delete transaction.
- *
- * If we didn't do this, then deleting something and reallocating it as
- * data would allow the old block to be overwritten before the
- * transaction committed (because we force data to disk before commit).
- * This would lead to corruption if we crashed between overwriting the
- * data and committing the delete.
- *
- * @@@ We may want to make this allocation behaviour conditional on
- * data-writes at some point, and disable it for metadata allocations or
- * sync-data inodes.
- */
-static int ext4_test_allocatable(ext4_grpblk_t nr, struct buffer_head *bh)
-{
-	int ret;
-	struct journal_head *jh = bh2jh(bh);
-
-	if (ext4_test_bit(nr, bh->b_data))
-		return 0;
-
-	jbd_lock_bh_state(bh);
-	if (!jh->b_committed_data)
-		ret = 1;
-	else
-		ret = !ext4_test_bit(nr, jh->b_committed_data);
-	jbd_unlock_bh_state(bh);
-	return ret;
-}
-
-/**
- * bitmap_search_next_usable_block()
- * @start:		the starting block (group relative) of the search
- * @bh:			bufferhead contains the block group bitmap
- * @maxblocks:		the ending block (group relative) of the reservation
- *
- * The bitmap search --- search forward alternately through the actual
- * bitmap on disk and the last-committed copy in journal, until we find a
- * bit free in both bitmaps.
- */
-static ext4_grpblk_t
-bitmap_search_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
-					ext4_grpblk_t maxblocks)
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+						s64 nblocks)
 {
-	ext4_grpblk_t next;
-	struct journal_head *jh = bh2jh(bh);
-
-	while (start < maxblocks) {
-		next = ext4_find_next_zero_bit(bh->b_data, maxblocks, start);
-		if (next >= maxblocks)
-			return -1;
-		if (ext4_test_allocatable(next, bh))
-			return next;
-		jbd_lock_bh_state(bh);
-		if (jh->b_committed_data)
-			start = ext4_find_next_zero_bit(jh->b_committed_data,
-							maxblocks, next);
-		jbd_unlock_bh_state(bh);
-	}
-	return -1;
-}
+	s64 free_blocks, dirty_blocks;
+	s64 root_blocks = 0;
+	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
-/**
- * find_next_usable_block()
- * @start:		the starting block (group relative) to find next
- *			allocatable block in bitmap.
- * @bh:			bufferhead contains the block group bitmap
- * @maxblocks:		the ending block (group relative) for the search
- *
- * Find an allocatable block in a bitmap.  We honor both the bitmap and
- * its last-committed copy (if that exists), and perform the "most
- * appropriate allocation" algorithm of looking for a free block near
- * the initial goal; then for a free byte somewhere in the bitmap; then
- * for any free bit in the bitmap.
- */
-static ext4_grpblk_t
-find_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
-			ext4_grpblk_t maxblocks)
-{
-	ext4_grpblk_t here, next;
-	char *p, *r;
-
-	if (start > 0) {
-		/*
-		 * The goal was occupied; search forward for a free
-		 * block within the next XX blocks.
-		 *
-		 * end_goal is more or less random, but it has to be
-		 * less than EXT4_BLOCKS_PER_GROUP. Aligning up to the
-		 * next 64-bit boundary is simple..
-		 */
-		ext4_grpblk_t end_goal = (start + 63) & ~63;
-		if (end_goal > maxblocks)
-			end_goal = maxblocks;
-		here = ext4_find_next_zero_bit(bh->b_data, end_goal, start);
-		if (here < end_goal && ext4_test_allocatable(here, bh))
-			return here;
-		ext4_debug("Bit not found near goal\n");
-	}
-
-	here = start;
-	if (here < 0)
-		here = 0;
-
-	p = ((char *)bh->b_data) + (here >> 3);
-	r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
-	next = (r - ((char *)bh->b_data)) << 3;
-
-	if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh))
-		return next;
-
-	/*
-	 * The bitmap search --- search forward alternately through the actual
-	 * bitmap and the last-committed copy until we find a bit free in
-	 * both
-	 */
-	here = bitmap_search_next_usable_block(here, bh, maxblocks);
-	return here;
-}
-
-/**
- * claim_block()
- * @block:		the free block (group relative) to allocate
- * @bh:			the bufferhead containts the block group bitmap
- *
- * We think we can allocate this block in this bitmap.  Try to set the bit.
- * If that succeeds then check that nobody has allocated and then freed the
- * block since we saw that is was not marked in b_committed_data.  If it _was_
- * allocated and freed then clear the bit in the bitmap again and return
- * zero (failure).
- */
-static inline int
-claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
-{
-	struct journal_head *jh = bh2jh(bh);
-	int ret;
-
-	if (ext4_set_bit_atomic(lock, block, bh->b_data))
-		return 0;
-	jbd_lock_bh_state(bh);
-	if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) {
-		ext4_clear_bit_atomic(lock, block, bh->b_data);
-		ret = 0;
-	} else {
-		ret = 1;
-	}
-	jbd_unlock_bh_state(bh);
-	return ret;
-}
+	free_blocks  = percpu_counter_read_positive(fbc);
+	dirty_blocks = percpu_counter_read_positive(dbc);
 
-/**
- * ext4_try_to_allocate()
- * @sb:			superblock
- * @handle:		handle to this transaction
- * @group:		given allocation block group
- * @bitmap_bh:		bufferhead holds the block bitmap
- * @grp_goal:		given target block within the group
- * @count:		target number of blocks to allocate
- * @my_rsv:		reservation window
- *
- * Attempt to allocate blocks within a give range. Set the range of allocation
- * first, then find the first free bit(s) from the bitmap (within the range),
- * and at last, allocate the blocks by claiming the found free bit as allocated.
- *
- * To set the range of this allocation:
- *	if there is a reservation window, only try to allocate block(s) from the
- *	file's own reservation window;
- *	Otherwise, the allocation range starts from the give goal block, ends at
- *	the block group's last block.
- *
- * If we failed to allocate the desired block then we may end up crossing to a
- * new bitmap.  In that case we must release write access to the old one via
- * ext4_journal_release_buffer(), else we'll run out of credits.
- */
-static ext4_grpblk_t
-ext4_try_to_allocate(struct super_block *sb, handle_t *handle,
-			ext4_group_t group, struct buffer_head *bitmap_bh,
-			ext4_grpblk_t grp_goal, unsigned long *count,
-			struct ext4_reserve_window *my_rsv)
-{
-	ext4_fsblk_t group_first_block;
-	ext4_grpblk_t start, end;
-	unsigned long num = 0;
-
-	/* we do allocation within the reservation window if we have a window */
-	if (my_rsv) {
-		group_first_block = ext4_group_first_block_no(sb, group);
-		if (my_rsv->_rsv_start >= group_first_block)
-			start = my_rsv->_rsv_start - group_first_block;
-		else
-			/* reservation window cross group boundary */
-			start = 0;
-		end = my_rsv->_rsv_end - group_first_block + 1;
-		if (end > EXT4_BLOCKS_PER_GROUP(sb))
-			/* reservation window crosses group boundary */
-			end = EXT4_BLOCKS_PER_GROUP(sb);
-		if ((start <= grp_goal) && (grp_goal < end))
-			start = grp_goal;
-		else
-			grp_goal = -1;
-	} else {
-		if (grp_goal > 0)
-			start = grp_goal;
-		else
-			start = 0;
-		end = EXT4_BLOCKS_PER_GROUP(sb);
-	}
-
-	BUG_ON(start > EXT4_BLOCKS_PER_GROUP(sb));
-
-repeat:
-	if (grp_goal < 0 || !ext4_test_allocatable(grp_goal, bitmap_bh)) {
-		grp_goal = find_next_usable_block(start, bitmap_bh, end);
-		if (grp_goal < 0)
-			goto fail_access;
-		if (!my_rsv) {
-			int i;
-
-			for (i = 0; i < 7 && grp_goal > start &&
-					ext4_test_allocatable(grp_goal - 1,
-								bitmap_bh);
-					i++, grp_goal--)
-				;
-		}
-	}
-	start = grp_goal;
-
-	if (!claim_block(sb_bgl_lock(EXT4_SB(sb), group),
-		grp_goal, bitmap_bh)) {
-		/*
-		 * The block was allocated by another thread, or it was
-		 * allocated and then freed by another thread
-		 */
-		start++;
-		grp_goal++;
-		if (start >= end)
-			goto fail_access;
-		goto repeat;
-	}
-	num++;
-	grp_goal++;
-	while (num < *count && grp_goal < end
-		&& ext4_test_allocatable(grp_goal, bitmap_bh)
-		&& claim_block(sb_bgl_lock(EXT4_SB(sb), group),
-				grp_goal, bitmap_bh)) {
-		num++;
-		grp_goal++;
-	}
-	*count = num;
-	return grp_goal - num;
-fail_access:
-	*count = num;
-	return -1;
-}
-
-/**
- *	find_next_reservable_window():
- *		find a reservable space within the given range.
- *		It does not allocate the reservation window for now:
- *		alloc_new_reservation() will do the work later.
- *
- *	@search_head: the head of the searching list;
- *		This is not necessarily the list head of the whole filesystem
- *
- *		We have both head and start_block to assist the search
- *		for the reservable space. The list starts from head,
- *		but we will shift to the place where start_block is,
- *		then start from there, when looking for a reservable space.
- *
- *	@size: the target new reservation window size
- *
- *	@group_first_block: the first block we consider to start
- *			the real search from
- *
- *	@last_block:
- *		the maximum block number that our goal reservable space
- *		could start from. This is normally the last block in this
- *		group. The search will end when we found the start of next
- *		possible reservable space is out of this boundary.
- *		This could handle the cross boundary reservation window
- *		request.
- *
- *	basically we search from the given range, rather than the whole
- *	reservation double linked list, (start_block, last_block)
- *	to find a free region that is of my size and has not
- *	been reserved.
- *
- */
-static int find_next_reservable_window(
-				struct ext4_reserve_window_node *search_head,
-				struct ext4_reserve_window_node *my_rsv,
-				struct super_block * sb,
-				ext4_fsblk_t start_block,
-				ext4_fsblk_t last_block)
-{
-	struct rb_node *next;
-	struct ext4_reserve_window_node *rsv, *prev;
-	ext4_fsblk_t cur;
-	int size = my_rsv->rsv_goal_size;
-
-	/* TODO: make the start of the reservation window byte-aligned */
-	/* cur = *start_block & ~7;*/
-	cur = start_block;
-	rsv = search_head;
-	if (!rsv)
-		return -1;
-
-	while (1) {
-		if (cur <= rsv->rsv_end)
-			cur = rsv->rsv_end + 1;
-
-		/* TODO?
-		 * in the case we could not find a reservable space
-		 * that is what is expected, during the re-search, we could
-		 * remember what's the largest reservable space we could have
-		 * and return that one.
-		 *
-		 * For now it will fail if we could not find the reservable
-		 * space with expected-size (or more)...
-		 */
-		if (cur > last_block)
-			return -1;		/* fail */
-
-		prev = rsv;
-		next = rb_next(&rsv->rsv_node);
-		rsv = rb_entry(next,struct ext4_reserve_window_node,rsv_node);
+	if (!capable(CAP_SYS_RESOURCE) &&
+		sbi->s_resuid != current->fsuid &&
+		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
+		root_blocks = ext4_r_blocks_count(sbi->s_es);
 
-		/*
-		 * Reached the last reservation, we can just append to the
-		 * previous one.
-		 */
-		if (!next)
-			break;
-
-		if (cur + size <= rsv->rsv_start) {
-			/*
-			 * Found a reserveable space big enough.  We could
-			 * have a reservation across the group boundary here
-			 */
-			break;
+	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+						EXT4_FREEBLOCKS_WATERMARK) {
+		free_blocks  = percpu_counter_sum(fbc);
+		dirty_blocks = percpu_counter_sum(dbc);
+		if (dirty_blocks < 0) {
+			printk(KERN_CRIT "Dirty block accounting "
+					"went wrong %lld\n",
+					dirty_blocks);
 		}
 	}
-	/*
-	 * we come here either :
-	 * when we reach the end of the whole list,
-	 * and there is empty reservable space after last entry in the list.
-	 * append it to the end of the list.
-	 *
-	 * or we found one reservable space in the middle of the list,
-	 * return the reservation window that we could append to.
-	 * succeed.
+	/* Check whether we have space after
+	 * accounting for current dirty blocks
 	 */
+	if (free_blocks < ((root_blocks + nblocks) + dirty_blocks))
+		/* we don't have free space */
+		return -ENOSPC;
 
-	if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
-		rsv_window_remove(sb, my_rsv);
-
-	/*
-	 * Let's book the whole avaliable window for now.  We will check the
-	 * disk bitmap later and then, if there are free blocks then we adjust
-	 * the window size if it's larger than requested.
-	 * Otherwise, we will remove this node from the tree next time
-	 * call find_next_reservable_window.
-	 */
-	my_rsv->rsv_start = cur;
-	my_rsv->rsv_end = cur + size - 1;
-	my_rsv->rsv_alloc_hit = 0;
-
-	if (prev != my_rsv)
-		ext4_rsv_window_add(sb, my_rsv);
-
+	/* Add the blocks to nblocks */
+	percpu_counter_add(dbc, nblocks);
 	return 0;
 }
 
-/**
- *	alloc_new_reservation()--allocate a new reservation window
- *
- *		To make a new reservation, we search part of the filesystem
- *		reservation list (the list that inside the group). We try to
- *		allocate a new reservation window near the allocation goal,
- *		or the beginning of the group, if there is no goal.
- *
- *		We first find a reservable space after the goal, then from
- *		there, we check the bitmap for the first free block after
- *		it. If there is no free block until the end of group, then the
- *		whole group is full, we failed. Otherwise, check if the free
- *		block is inside the expected reservable space, if so, we
- *		succeed.
- *		If the first free block is outside the reservable space, then
- *		start from the first free block, we search for next available
- *		space, and go on.
- *
- *	on succeed, a new reservation will be found and inserted into the list
- *	It contains at least one free block, and it does not overlap with other
- *	reservation windows.
- *
- *	failed: we failed to find a reservation window in this group
- *
- *	@rsv: the reservation
- *
- *	@grp_goal: The goal (group-relative).  It is where the search for a
- *		free reservable space should start from.
- *		if we have a grp_goal(grp_goal >0 ), then start from there,
- *		no grp_goal(grp_goal = -1), we start from the first block
- *		of the group.
- *
- *	@sb: the super block
- *	@group: the group we are trying to allocate in
- *	@bitmap_bh: the block group block bitmap
- *
- */
-static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
-		ext4_grpblk_t grp_goal, struct super_block *sb,
-		ext4_group_t group, struct buffer_head *bitmap_bh)
-{
-	struct ext4_reserve_window_node *search_head;
-	ext4_fsblk_t group_first_block, group_end_block, start_block;
-	ext4_grpblk_t first_free_block;
-	struct rb_root *fs_rsv_root = &EXT4_SB(sb)->s_rsv_window_root;
-	unsigned long size;
-	int ret;
-	spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
-
-	group_first_block = ext4_group_first_block_no(sb, group);
-	group_end_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-	if (grp_goal < 0)
-		start_block = group_first_block;
-	else
-		start_block = grp_goal + group_first_block;
-
-	size = my_rsv->rsv_goal_size;
-
-	if (!rsv_is_empty(&my_rsv->rsv_window)) {
-		/*
-		 * if the old reservation is cross group boundary
-		 * and if the goal is inside the old reservation window,
-		 * we will come here when we just failed to allocate from
-		 * the first part of the window. We still have another part
-		 * that belongs to the next group. In this case, there is no
-		 * point to discard our window and try to allocate a new one
-		 * in this group(which will fail). we should
-		 * keep the reservation window, just simply move on.
-		 *
-		 * Maybe we could shift the start block of the reservation
-		 * window to the first block of next group.
-		 */
-
-		if ((my_rsv->rsv_start <= group_end_block) &&
-				(my_rsv->rsv_end > group_end_block) &&
-				(start_block >= my_rsv->rsv_start))
-			return -1;
-
-		if ((my_rsv->rsv_alloc_hit >
-		     (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
-			/*
-			 * if the previously allocation hit ratio is
-			 * greater than 1/2, then we double the size of
-			 * the reservation window the next time,
-			 * otherwise we keep the same size window
-			 */
-			size = size * 2;
-			if (size > EXT4_MAX_RESERVE_BLOCKS)
-				size = EXT4_MAX_RESERVE_BLOCKS;
-			my_rsv->rsv_goal_size= size;
-		}
-	}
-
-	spin_lock(rsv_lock);
-	/*
-	 * shift the search start to the window near the goal block
-	 */
-	search_head = search_reserve_window(fs_rsv_root, start_block);
-
-	/*
-	 * find_next_reservable_window() simply finds a reservable window
-	 * inside the given range(start_block, group_end_block).
-	 *
-	 * To make sure the reservation window has a free bit inside it, we
-	 * need to check the bitmap after we found a reservable window.
-	 */
-retry:
-	ret = find_next_reservable_window(search_head, my_rsv, sb,
-						start_block, group_end_block);
-
-	if (ret == -1) {
-		if (!rsv_is_empty(&my_rsv->rsv_window))
-			rsv_window_remove(sb, my_rsv);
-		spin_unlock(rsv_lock);
-		return -1;
-	}
-
-	/*
-	 * On success, find_next_reservable_window() returns the
-	 * reservation window where there is a reservable space after it.
-	 * Before we reserve this reservable space, we need
-	 * to make sure there is at least a free block inside this region.
-	 *
-	 * searching the first free bit on the block bitmap and copy of
-	 * last committed bitmap alternatively, until we found a allocatable
-	 * block. Search start from the start block of the reservable space
-	 * we just found.
-	 */
-	spin_unlock(rsv_lock);
-	first_free_block = bitmap_search_next_usable_block(
-			my_rsv->rsv_start - group_first_block,
-			bitmap_bh, group_end_block - group_first_block + 1);
-
-	if (first_free_block < 0) {
-		/*
-		 * no free block left on the bitmap, no point
-		 * to reserve the space. return failed.
-		 */
-		spin_lock(rsv_lock);
-		if (!rsv_is_empty(&my_rsv->rsv_window))
-			rsv_window_remove(sb, my_rsv);
-		spin_unlock(rsv_lock);
-		return -1;		/* failed */
-	}
-
-	start_block = first_free_block + group_first_block;
-	/*
-	 * check if the first free block is within the
-	 * free space we just reserved
-	 */
-	if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end)
-		return 0;		/* success */
-	/*
-	 * if the first free bit we found is out of the reservable space
-	 * continue search for next reservable space,
-	 * start from where the free block is,
-	 * we also shift the list head to where we stopped last time
-	 */
-	search_head = my_rsv;
-	spin_lock(rsv_lock);
-	goto retry;
-}
-
-/**
- * try_to_extend_reservation()
- * @my_rsv:		given reservation window
- * @sb:			super block
- * @size:		the delta to extend
- *
- * Attempt to expand the reservation window large enough to have
- * required number of free blocks
- *
- * Since ext4_try_to_allocate() will always allocate blocks within
- * the reservation window range, if the window size is too small,
- * multiple blocks allocation has to stop at the end of the reservation
- * window. To make this more efficient, given the total number of
- * blocks needed and the current size of the window, we try to
- * expand the reservation window size if necessary on a best-effort
- * basis before ext4_new_blocks() tries to allocate blocks,
- */
-static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv,
-			struct super_block *sb, int size)
-{
-	struct ext4_reserve_window_node *next_rsv;
-	struct rb_node *next;
-	spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
-
-	if (!spin_trylock(rsv_lock))
-		return;
-
-	next = rb_next(&my_rsv->rsv_node);
-
-	if (!next)
-		my_rsv->rsv_end += size;
-	else {
-		next_rsv = rb_entry(next, struct ext4_reserve_window_node, rsv_node);
-
-		if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
-			my_rsv->rsv_end += size;
-		else
-			my_rsv->rsv_end = next_rsv->rsv_start - 1;
-	}
-	spin_unlock(rsv_lock);
-}
-
-/**
- * ext4_try_to_allocate_with_rsv()
- * @sb:			superblock
- * @handle:		handle to this transaction
- * @group:		given allocation block group
- * @bitmap_bh:		bufferhead holds the block bitmap
- * @grp_goal:		given target block within the group
- * @count:		target number of blocks to allocate
- * @my_rsv:		reservation window
- * @errp:		pointer to store the error code
- *
- * This is the main function used to allocate a new block and its reservation
- * window.
- *
- * Each time when a new block allocation is need, first try to allocate from
- * its own reservation.  If it does not have a reservation window, instead of
- * looking for a free bit on bitmap first, then look up the reservation list to
- * see if it is inside somebody else's reservation window, we try to allocate a
- * reservation window for it starting from the goal first. Then do the block
- * allocation within the reservation window.
- *
- * This will avoid keeping on searching the reservation list again and
- * again when somebody is looking for a free block (without
- * reservation), and there are lots of free blocks, but they are all
- * being reserved.
- *
- * We use a red-black tree for the per-filesystem reservation list.
- *
- */
-static ext4_grpblk_t
-ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
-			ext4_group_t group, struct buffer_head *bitmap_bh,
-			ext4_grpblk_t grp_goal,
-			struct ext4_reserve_window_node * my_rsv,
-			unsigned long *count, int *errp)
-{
-	ext4_fsblk_t group_first_block, group_last_block;
-	ext4_grpblk_t ret = 0;
-	int fatal;
-	unsigned long num = *count;
-
-	*errp = 0;
-
-	/*
-	 * Make sure we use undo access for the bitmap, because it is critical
-	 * that we do the frozen_data COW on bitmap buffers in all cases even
-	 * if the buffer is in BJ_Forget state in the committing transaction.
-	 */
-	BUFFER_TRACE(bitmap_bh, "get undo access for new block");
-	fatal = ext4_journal_get_undo_access(handle, bitmap_bh);
-	if (fatal) {
-		*errp = fatal;
-		return -1;
-	}
-
-	/*
-	 * we don't deal with reservation when
-	 * filesystem is mounted without reservation
-	 * or the file is not a regular file
-	 * or last attempt to allocate a block with reservation turned on failed
-	 */
-	if (my_rsv == NULL ) {
-		ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
-						grp_goal, count, NULL);
-		goto out;
-	}
-	/*
-	 * grp_goal is a group relative block number (if there is a goal)
-	 * 0 <= grp_goal < EXT4_BLOCKS_PER_GROUP(sb)
-	 * first block is a filesystem wide block number
-	 * first block is the block number of the first block in this group
-	 */
-	group_first_block = ext4_group_first_block_no(sb, group);
-	group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-	/*
-	 * Basically we will allocate a new block from inode's reservation
-	 * window.
-	 *
-	 * We need to allocate a new reservation window, if:
-	 * a) inode does not have a reservation window; or
-	 * b) last attempt to allocate a block from existing reservation
-	 *    failed; or
-	 * c) we come here with a goal and with a reservation window
-	 *
-	 * We do not need to allocate a new reservation window if we come here
-	 * at the beginning with a goal and the goal is inside the window, or
-	 * we don't have a goal but already have a reservation window.
-	 * then we could go to allocate from the reservation window directly.
-	 */
-	while (1) {
-		if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
-			!goal_in_my_reservation(&my_rsv->rsv_window,
-						grp_goal, group, sb)) {
-			if (my_rsv->rsv_goal_size < *count)
-				my_rsv->rsv_goal_size = *count;
-			ret = alloc_new_reservation(my_rsv, grp_goal, sb,
-							group, bitmap_bh);
-			if (ret < 0)
-				break;			/* failed */
-
-			if (!goal_in_my_reservation(&my_rsv->rsv_window,
-							grp_goal, group, sb))
-				grp_goal = -1;
-		} else if (grp_goal >= 0) {
-			int curr = my_rsv->rsv_end -
-					(grp_goal + group_first_block) + 1;
-
-			if (curr < *count)
-				try_to_extend_reservation(my_rsv, sb,
-							*count - curr);
-		}
-
-		if ((my_rsv->rsv_start > group_last_block) ||
-				(my_rsv->rsv_end < group_first_block)) {
-			rsv_window_dump(&EXT4_SB(sb)->s_rsv_window_root, 1);
-			BUG();
-		}
-		ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
-					   grp_goal, &num, &my_rsv->rsv_window);
-		if (ret >= 0) {
-			my_rsv->rsv_alloc_hit += num;
-			*count = num;
-			break;				/* succeed */
-		}
-		num = *count;
-	}
-out:
-	if (ret >= 0) {
-		BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
-					"bitmap block");
-		fatal = ext4_journal_dirty_metadata(handle, bitmap_bh);
-		if (fatal) {
-			*errp = fatal;
-			return -1;
-		}
-		return ret;
-	}
-
-	BUFFER_TRACE(bitmap_bh, "journal_release_buffer");
-	ext4_journal_release_buffer(handle, bitmap_bh);
-	return ret;
-}
-
 /**
  * ext4_has_free_blocks()
  * @sbi:	in-core super block structure.
@@ -1610,29 +629,34 @@ ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
  * On success, return nblocks
  */
 ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-						ext4_fsblk_t nblocks)
+						s64 nblocks)
 {
-	ext4_fsblk_t free_blocks;
-	ext4_fsblk_t root_blocks = 0;
+	s64 free_blocks, dirty_blocks;
+	s64 root_blocks = 0;
+	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
-	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	free_blocks  = percpu_counter_read_positive(fbc);
+	dirty_blocks = percpu_counter_read_positive(dbc);
 
 	if (!capable(CAP_SYS_RESOURCE) &&
 		sbi->s_resuid != current->fsuid &&
 		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
 		root_blocks = ext4_r_blocks_count(sbi->s_es);
-#ifdef CONFIG_SMP
-	if (free_blocks - root_blocks < FBC_BATCH)
-		free_blocks =
-			percpu_counter_sum_and_set(&sbi->s_freeblocks_counter);
-#endif
-	if (free_blocks <= root_blocks)
+
+	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+						EXT4_FREEBLOCKS_WATERMARK) {
+		free_blocks  = percpu_counter_sum(fbc);
+		dirty_blocks = percpu_counter_sum(dbc);
+	}
+	if (free_blocks <= (root_blocks + dirty_blocks))
 		/* we don't have free space */
 		return 0;
-	if (free_blocks - root_blocks < nblocks)
-		return free_blocks - root_blocks;
+
+	if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
+		return free_blocks - (root_blocks + dirty_blocks);
 	return nblocks;
- }
+}
 
 
 /**
@@ -1657,303 +681,6 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 	return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
 }
 
-/**
- * ext4_old_new_blocks() -- core block bitmap based block allocation function
- *
- * @handle:		handle to this transaction
- * @inode:		file inode
- * @goal:		given target block(filesystem wide)
- * @count:		target number of blocks to allocate
- * @errp:		error code
- *
- * ext4_old_new_blocks uses a goal block to assist allocation and look up
- * the block bitmap directly to do block allocation.  It tries to
- * allocate block(s) from the block group contains the goal block first. If
- * that fails, it will try to allocate block(s) from other block groups
- * without any specific goal block.
- *
- * This function is called when -o nomballoc mount option is enabled
- *
- */
-ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t goal, unsigned long *count, int *errp)
-{
-	struct buffer_head *bitmap_bh = NULL;
-	struct buffer_head *gdp_bh;
-	ext4_group_t group_no;
-	ext4_group_t goal_group;
-	ext4_grpblk_t grp_target_blk;	/* blockgroup relative goal block */
-	ext4_grpblk_t grp_alloc_blk;	/* blockgroup-relative allocated block*/
-	ext4_fsblk_t ret_block;		/* filesyetem-wide allocated block */
-	ext4_group_t bgi;			/* blockgroup iteration index */
-	int fatal = 0, err;
-	int performed_allocation = 0;
-	ext4_grpblk_t free_blocks;	/* number of free blocks in a group */
-	struct super_block *sb;
-	struct ext4_group_desc *gdp;
-	struct ext4_super_block *es;
-	struct ext4_sb_info *sbi;
-	struct ext4_reserve_window_node *my_rsv = NULL;
-	struct ext4_block_alloc_info *block_i;
-	unsigned short windowsz = 0;
-	ext4_group_t ngroups;
-	unsigned long num = *count;
-
-	sb = inode->i_sb;
-	if (!sb) {
-		*errp = -ENODEV;
-		printk("ext4_new_block: nonexistent device");
-		return 0;
-	}
-
-	sbi = EXT4_SB(sb);
-	if (!EXT4_I(inode)->i_delalloc_reserved_flag) {
-		/*
-		 * With delalloc we already reserved the blocks
-		 */
-		*count = ext4_has_free_blocks(sbi, *count);
-	}
-	if (*count == 0) {
-		*errp = -ENOSPC;
-		return 0;	/*return with ENOSPC error */
-	}
-	num = *count;
-
-	/*
-	 * Check quota for allocation of this block.
-	 */
-	if (DQUOT_ALLOC_BLOCK(inode, num)) {
-		*errp = -EDQUOT;
-		return 0;
-	}
-
-	sbi = EXT4_SB(sb);
-	es = EXT4_SB(sb)->s_es;
-	ext4_debug("goal=%llu.\n", goal);
-	/*
-	 * Allocate a block from reservation only when
-	 * filesystem is mounted with reservation(default,-o reservation), and
-	 * it's a regular file, and
-	 * the desired window size is greater than 0 (One could use ioctl
-	 * command EXT4_IOC_SETRSVSZ to set the window size to 0 to turn off
-	 * reservation on that particular file)
-	 */
-	block_i = EXT4_I(inode)->i_block_alloc_info;
-	if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
-		my_rsv = &block_i->rsv_window_node;
-
-	/*
-	 * First, test whether the goal block is free.
-	 */
-	if (goal < le32_to_cpu(es->s_first_data_block) ||
-	    goal >= ext4_blocks_count(es))
-		goal = le32_to_cpu(es->s_first_data_block);
-	ext4_get_group_no_and_offset(sb, goal, &group_no, &grp_target_blk);
-	goal_group = group_no;
-retry_alloc:
-	gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
-	if (!gdp)
-		goto io_error;
-
-	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
-	/*
-	 * if there is not enough free blocks to make a new resevation
-	 * turn off reservation for this allocation
-	 */
-	if (my_rsv && (free_blocks < windowsz)
-		&& (rsv_is_empty(&my_rsv->rsv_window)))
-		my_rsv = NULL;
-
-	if (free_blocks > 0) {
-		bitmap_bh = ext4_read_block_bitmap(sb, group_no);
-		if (!bitmap_bh)
-			goto io_error;
-		grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
-					group_no, bitmap_bh, grp_target_blk,
-					my_rsv,	&num, &fatal);
-		if (fatal)
-			goto out;
-		if (grp_alloc_blk >= 0)
-			goto allocated;
-	}
-
-	ngroups = EXT4_SB(sb)->s_groups_count;
-	smp_rmb();
-
-	/*
-	 * Now search the rest of the groups.  We assume that
-	 * group_no and gdp correctly point to the last group visited.
-	 */
-	for (bgi = 0; bgi < ngroups; bgi++) {
-		group_no++;
-		if (group_no >= ngroups)
-			group_no = 0;
-		gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
-		if (!gdp)
-			goto io_error;
-		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
-		/*
-		 * skip this group if the number of
-		 * free blocks is less than half of the reservation
-		 * window size.
-		 */
-		if (free_blocks <= (windowsz/2))
-			continue;
-
-		brelse(bitmap_bh);
-		bitmap_bh = ext4_read_block_bitmap(sb, group_no);
-		if (!bitmap_bh)
-			goto io_error;
-		/*
-		 * try to allocate block(s) from this group, without a goal(-1).
-		 */
-		grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
-					group_no, bitmap_bh, -1, my_rsv,
-					&num, &fatal);
-		if (fatal)
-			goto out;
-		if (grp_alloc_blk >= 0)
-			goto allocated;
-	}
-	/*
-	 * We may end up a bogus ealier ENOSPC error due to
-	 * filesystem is "full" of reservations, but
-	 * there maybe indeed free blocks avaliable on disk
-	 * In this case, we just forget about the reservations
-	 * just do block allocation as without reservations.
-	 */
-	if (my_rsv) {
-		my_rsv = NULL;
-		windowsz = 0;
-		group_no = goal_group;
-		goto retry_alloc;
-	}
-	/* No space left on the device */
-	*errp = -ENOSPC;
-	goto out;
-
-allocated:
-
-	ext4_debug("using block group %lu(%d)\n",
-			group_no, gdp->bg_free_blocks_count);
-
-	BUFFER_TRACE(gdp_bh, "get_write_access");
-	fatal = ext4_journal_get_write_access(handle, gdp_bh);
-	if (fatal)
-		goto out;
-
-	ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no);
-
-	if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), ret_block, num) ||
-	    in_range(ret_block, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group) ||
-	    in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group)) {
-		ext4_error(sb, "ext4_new_block",
-			    "Allocating block in system zone - "
-			    "blocks from %llu, length %lu",
-			     ret_block, num);
-		/*
-		 * claim_block marked the blocks we allocated
-		 * as in use. So we may want to selectively
-		 * mark some of the blocks as free
-		 */
-		goto retry_alloc;
-	}
-
-	performed_allocation = 1;
-
-#ifdef CONFIG_JBD2_DEBUG
-	{
-		struct buffer_head *debug_bh;
-
-		/* Record bitmap buffer state in the newly allocated block */
-		debug_bh = sb_find_get_block(sb, ret_block);
-		if (debug_bh) {
-			BUFFER_TRACE(debug_bh, "state when allocated");
-			BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state");
-			brelse(debug_bh);
-		}
-	}
-	jbd_lock_bh_state(bitmap_bh);
-	spin_lock(sb_bgl_lock(sbi, group_no));
-	if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
-		int i;
-
-		for (i = 0; i < num; i++) {
-			if (ext4_test_bit(grp_alloc_blk+i,
-					bh2jh(bitmap_bh)->b_committed_data)) {
-				printk("%s: block was unexpectedly set in "
-					"b_committed_data\n", __func__);
-			}
-		}
-	}
-	ext4_debug("found bit %d\n", grp_alloc_blk);
-	spin_unlock(sb_bgl_lock(sbi, group_no));
-	jbd_unlock_bh_state(bitmap_bh);
-#endif
-
-	if (ret_block + num - 1 >= ext4_blocks_count(es)) {
-		ext4_error(sb, "ext4_new_block",
-			    "block(%llu) >= blocks count(%llu) - "
-			    "block_group = %lu, es == %p ", ret_block,
-			ext4_blocks_count(es), group_no, es);
-		goto out;
-	}
-
-	/*
-	 * It is up to the caller to add the new buffer to a journal
-	 * list of some description.  We don't know in advance whether
-	 * the caller wants to use it as metadata or data.
-	 */
-	spin_lock(sb_bgl_lock(sbi, group_no));
-	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
-		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
-	le16_add_cpu(&gdp->bg_free_blocks_count, -num);
-	gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
-	spin_unlock(sb_bgl_lock(sbi, group_no));
-	if (!EXT4_I(inode)->i_delalloc_reserved_flag)
-		percpu_counter_sub(&sbi->s_freeblocks_counter, num);
-
-	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t flex_group = ext4_flex_group(sbi, group_no);
-		spin_lock(sb_bgl_lock(sbi, flex_group));
-		sbi->s_flex_groups[flex_group].free_blocks -= num;
-		spin_unlock(sb_bgl_lock(sbi, flex_group));
-	}
-
-	BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
-	err = ext4_journal_dirty_metadata(handle, gdp_bh);
-	if (!fatal)
-		fatal = err;
-
-	sb->s_dirt = 1;
-	if (fatal)
-		goto out;
-
-	*errp = 0;
-	brelse(bitmap_bh);
-	DQUOT_FREE_BLOCK(inode, *count-num);
-	*count = num;
-	return ret_block;
-
-io_error:
-	*errp = -EIO;
-out:
-	if (fatal) {
-		*errp = fatal;
-		ext4_std_error(sb, fatal);
-	}
-	/*
-	 * Undo the block allocation
-	 */
-	if (!performed_allocation)
-		DQUOT_FREE_BLOCK(inode, *count);
-	brelse(bitmap_bh);
-	return 0;
-}
-
 #define EXT4_META_BLOCK 0x1
 
 static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
@@ -1963,10 +690,6 @@ static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
 	struct ext4_allocation_request ar;
 	ext4_fsblk_t ret;
 
-	if (!test_opt(inode->i_sb, MBALLOC)) {
-		return ext4_old_new_blocks(handle, inode, goal, count, errp);
-	}
-
 	memset(&ar, 0, sizeof(ar));
 	/* Fill with neighbour allocated blocks */
 
@@ -2008,7 +731,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	/*
 	 * Account for the allocated meta blocks
 	 */
-	if (!(*errp)) {
+	if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
 		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 		EXT4_I(inode)->i_allocated_meta_blocks += *count;
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
@@ -2093,10 +816,9 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);
-	printk("ext4_count_free_blocks: stored = %llu"
-		", computed = %llu, %llu\n",
-		ext4_free_blocks_count(es),
-		desc_count, bitmap_count);
+	printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
+		", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+	       desc_count, bitmap_count);
 	return bitmap_count;
 #else
 	desc_count = 0;
@@ -2183,8 +905,9 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 
 	if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
 			metagroup < first_meta_bg)
-		return ext4_bg_num_gdb_nometa(sb,group);
+		return ext4_bg_num_gdb_nometa(sb, group);
 
 	return ext4_bg_num_gdb_meta(sb,group);
 
 }
+

fs/ext4/bitmap.c

@@ -15,17 +15,17 @@
 
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned long ext4_count_free (struct buffer_head * map, unsigned int numchars)
+unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
 {
 	unsigned int i;
 	unsigned long sum = 0;
 
 	if (!map)
-		return (0);
+		return 0;
 	for (i = 0; i < numchars; i++)
 		sum += nibblemap[map->b_data[i] & 0xf] +
 			nibblemap[(map->b_data[i] >> 4) & 0xf];
-	return (sum);
+	return sum;
 }
 
 #endif  /*  EXT4FS_DEBUG  */

fs/ext4/dir.c

@@ -33,10 +33,10 @@ static unsigned char ext4_filetype_table[] = {
 };
 
 static int ext4_readdir(struct file *, void *, filldir_t);
-static int ext4_dx_readdir(struct file * filp,
-			   void * dirent, filldir_t filldir);
-static int ext4_release_dir (struct inode * inode,
-				struct file * filp);
+static int ext4_dx_readdir(struct file *filp,
+			   void *dirent, filldir_t filldir);
+static int ext4_release_dir(struct inode *inode,
+				struct file *filp);
 
 const struct file_operations ext4_dir_operations = {
 	.llseek		= generic_file_llseek,
@@ -61,12 +61,12 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 }
 
 
-int ext4_check_dir_entry (const char * function, struct inode * dir,
-			  struct ext4_dir_entry_2 * de,
-			  struct buffer_head * bh,
-			  unsigned long offset)
+int ext4_check_dir_entry(const char *function, struct inode *dir,
+			 struct ext4_dir_entry_2 *de,
+			 struct buffer_head *bh,
+			 unsigned long offset)
 {
-	const char * error_msg = NULL;
+	const char *error_msg = NULL;
 	const int rlen = ext4_rec_len_from_disk(de->rec_len);
 
 	if (rlen < EXT4_DIR_REC_LEN(1))
@@ -82,7 +82,7 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
 		error_msg = "inode out of bounds";
 
 	if (error_msg != NULL)
-		ext4_error (dir->i_sb, function,
+		ext4_error(dir->i_sb, function,
 			"bad entry in directory #%lu: %s - "
 			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
 			dir->i_ino, error_msg, offset,
@@ -91,8 +91,8 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
 	return error_msg == NULL ? 1 : 0;
 }
 
-static int ext4_readdir(struct file * filp,
-			 void * dirent, filldir_t filldir)
+static int ext4_readdir(struct file *filp,
+			 void *dirent, filldir_t filldir)
 {
 	int error = 0;
 	unsigned long offset;
@@ -102,6 +102,7 @@ static int ext4_readdir(struct file * filp,
 	int err;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	int ret = 0;
+	int dir_has_error = 0;
 
 	sb = inode->i_sb;
 
@@ -148,9 +149,13 @@ static int ext4_readdir(struct file * filp,
 		 * of recovering data when there's a bad sector
 		 */
 		if (!bh) {
-			ext4_error (sb, "ext4_readdir",
-				"directory #%lu contains a hole at offset %lu",
-				inode->i_ino, (unsigned long)filp->f_pos);
+			if (!dir_has_error) {
+				ext4_error(sb, __func__, "directory #%lu "
+					   "contains a hole at offset %Lu",
+					   inode->i_ino,
+					   (unsigned long long) filp->f_pos);
+				dir_has_error = 1;
+			}
 			/* corrupt size?  Maybe no more blocks to read */
 			if (filp->f_pos > inode->i_blocks << 9)
 				break;
@@ -187,14 +192,14 @@ static int ext4_readdir(struct file * filp,
 		while (!error && filp->f_pos < inode->i_size
 		       && offset < sb->s_blocksize) {
 			de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
-			if (!ext4_check_dir_entry ("ext4_readdir", inode, de,
-						   bh, offset)) {
+			if (!ext4_check_dir_entry("ext4_readdir", inode, de,
+						  bh, offset)) {
 				/*
 				 * On error, skip the f_pos to the next block
 				 */
 				filp->f_pos = (filp->f_pos |
 						(sb->s_blocksize - 1)) + 1;
-				brelse (bh);
+				brelse(bh);
 				ret = stored;
 				goto out;
 			}
@@ -218,12 +223,12 @@ static int ext4_readdir(struct file * filp,
 					break;
 				if (version != filp->f_version)
 					goto revalidate;
-				stored ++;
+				stored++;
 			}
 			filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
 		}
 		offset = 0;
-		brelse (bh);
+		brelse(bh);
 	}
 out:
 	return ret;
@@ -290,9 +295,9 @@ static void free_rb_tree_fname(struct rb_root *root)
 		parent = rb_parent(n);
 		fname = rb_entry(n, struct fname, rb_hash);
 		while (fname) {
-			struct fname * old = fname;
+			struct fname *old = fname;
 			fname = fname->next;
-			kfree (old);
+			kfree(old);
 		}
 		if (!parent)
 			root->rb_node = NULL;
@@ -331,7 +336,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 			     struct ext4_dir_entry_2 *dirent)
 {
 	struct rb_node **p, *parent = NULL;
-	struct fname * fname, *new_fn;
+	struct fname *fname, *new_fn;
 	struct dir_private_info *info;
 	int len;
 
@@ -388,19 +393,20 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
  * for all entres on the fname linked list.  (Normally there is only
  * one entry on the linked list, unless there are 62 bit hash collisions.)
  */
-static int call_filldir(struct file * filp, void * dirent,
+static int call_filldir(struct file *filp, void *dirent,
 			filldir_t filldir, struct fname *fname)
 {
 	struct dir_private_info *info = filp->private_data;
 	loff_t	curr_pos;
 	struct inode *inode = filp->f_path.dentry->d_inode;
-	struct super_block * sb;
+	struct super_block *sb;
 	int error;
 
 	sb = inode->i_sb;
 
 	if (!fname) {
-		printk("call_filldir: called with null fname?!?\n");
+		printk(KERN_ERR "ext4: call_filldir: called with "
+		       "null fname?!?\n");
 		return 0;
 	}
 	curr_pos = hash2pos(fname->hash, fname->minor_hash);
@@ -419,8 +425,8 @@ static int call_filldir(struct file * filp, void * dirent,
 	return 0;
 }
 
-static int ext4_dx_readdir(struct file * filp,
-			 void * dirent, filldir_t filldir)
+static int ext4_dx_readdir(struct file *filp,
+			 void *dirent, filldir_t filldir)
 {
 	struct dir_private_info *info = filp->private_data;
 	struct inode *inode = filp->f_path.dentry->d_inode;
@@ -511,7 +517,7 @@ static int ext4_dx_readdir(struct file * filp,
 	return 0;
 }
 
-static int ext4_release_dir (struct inode * inode, struct file * filp)
+static int ext4_release_dir(struct inode *inode, struct file *filp)
 {
 	if (filp->private_data)
 		ext4_htree_free_dir_info(filp->private_data);

fs/ext4/ext4.h

@@ -44,9 +44,9 @@
 #ifdef EXT4FS_DEBUG
 #define ext4_debug(f, a...)						\
 	do {								\
-		printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
+		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
 			__FILE__, __LINE__, __func__);			\
-		printk (KERN_DEBUG f, ## a);				\
+		printk(KERN_DEBUG f, ## a);				\
 	} while (0)
 #else
 #define ext4_debug(f, a...)	do {} while (0)
@@ -128,7 +128,7 @@ struct ext4_allocation_request {
 #else
 # define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
 #endif
-#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof (__u32))
+#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
 #else
@@ -245,7 +245,7 @@ struct flex_groups {
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE		0x000BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE		0x000B80FF /* User modifiable flags */
 
 /*
  * Inode dynamic state flags
@@ -291,8 +291,6 @@ struct ext4_new_group_data {
 #define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
 #define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
 #define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
-#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
-#define EXT4_IOC_GROUP_ADD		_IOW('f', 8,struct ext4_new_group_input)
 #define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
 #define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
 #ifdef CONFIG_JBD2_DEBUG
@@ -300,7 +298,10 @@ struct ext4_new_group_data {
 #endif
 #define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
 #define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
-#define EXT4_IOC_MIGRATE		_IO('f', 7)
+#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
+#define EXT4_IOC_GROUP_ADD		_IOW('f', 8, struct ext4_new_group_input)
+#define EXT4_IOC_MIGRATE		_IO('f', 9)
+ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
 
 /*
  * ioctl commands in 32 bit emulation
@@ -538,7 +539,6 @@ do {									       \
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
-#define EXT4_MOUNT_MBALLOC		0x4000000 /* Buddy allocation support */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
@@ -667,7 +667,7 @@ struct ext4_super_block {
 };
 
 #ifdef __KERNEL__
-static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb)
+static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
 }
@@ -725,11 +725,11 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
  */
 
 #define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
-	( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+	(EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask))
 #define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
-	( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+	(EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask))
 #define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
-	( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+	(EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask))
 #define EXT4_SET_COMPAT_FEATURE(sb,mask)			\
 	EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
 #define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)			\
@@ -789,6 +789,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define	EXT4_DEF_RESUID		0
 #define	EXT4_DEF_RESGID		0
 
+#define EXT4_DEF_INODE_READAHEAD_BLKS	32
+
 /*
  * Default mount options
  */
@@ -954,6 +956,24 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 			unsigned long *blockgrpp, ext4_grpblk_t *offsetp);
 
+extern struct proc_dir_entry *ext4_proc_root;
+
+#ifdef CONFIG_PROC_FS
+extern const struct file_operations ext4_ui_proc_fops;
+
+#define	EXT4_PROC_HANDLER(name, var)					\
+do {									\
+	proc = proc_create_data(name, mode, sbi->s_proc,		\
+				&ext4_ui_proc_fops, &sbi->s_##var);	\
+	if (proc == NULL) {						\
+		printk(KERN_ERR "EXT4-fs: can't create %s\n", name);	\
+		goto err_out;						\
+	}								\
+} while (0)
+#else
+#define EXT4_PROC_HANDLER(name, var)
+#endif
+
 /*
  * Function prototypes
  */
@@ -981,23 +1001,20 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 					ext4_lblk_t iblock, ext4_fsblk_t goal,
 					unsigned long *count, int *errp);
-extern ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-						ext4_fsblk_t nblocks);
-extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
+					 s64 nblocks);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
-				 ext4_fsblk_t block, unsigned long count,
+extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+				ext4_fsblk_t block, unsigned long count,
 				unsigned long *pdquot_freed_blocks);
-extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
-extern void ext4_check_blocks_bitmap (struct super_block *);
+extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
-extern void ext4_init_block_alloc_info(struct inode *);
-extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv);
 
 /* dir.c */
 extern int ext4_check_dir_entry(const char *, struct inode *,
@@ -1009,20 +1026,20 @@ extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 extern void ext4_htree_free_dir_info(struct dir_private_info *p);
 
 /* fsync.c */
-extern int ext4_sync_file (struct file *, struct dentry *, int);
+extern int ext4_sync_file(struct file *, struct dentry *, int);
 
 /* hash.c */
 extern int ext4fs_dirhash(const char *name, int len, struct
 			  dx_hash_info *hinfo);
 
 /* ialloc.c */
-extern struct inode * ext4_new_inode (handle_t *, struct inode *, int);
-extern void ext4_free_inode (handle_t *, struct inode *);
-extern struct inode * ext4_orphan_get (struct super_block *, unsigned long);
-extern unsigned long ext4_count_free_inodes (struct super_block *);
-extern unsigned long ext4_count_dirs (struct super_block *);
-extern void ext4_check_inodes_bitmap (struct super_block *);
-extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
+extern struct inode * ext4_new_inode(handle_t *, struct inode *, int);
+extern void ext4_free_inode(handle_t *, struct inode *);
+extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
+extern unsigned long ext4_count_free_inodes(struct super_block *);
+extern unsigned long ext4_count_dirs(struct super_block *);
+extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned long ext4_count_free(struct buffer_head *, unsigned);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1032,7 +1049,7 @@ extern int ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
 extern int ext4_mb_reserve_blocks(struct super_block *, int);
-extern void ext4_mb_discard_inode_preallocations(struct inode *);
+extern void ext4_discard_preallocations(struct inode *);
 extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
@@ -1050,24 +1067,25 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
 struct buffer_head *ext4_bread(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
+int ext4_get_block(struct inode *inode, sector_t iblock,
+				struct buffer_head *bh_result, int create);
 int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 				ext4_lblk_t iblock, unsigned long maxblocks,
 				struct buffer_head *bh_result,
 				int create, int extend_disksize);
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
-extern int  ext4_write_inode (struct inode *, int);
-extern int  ext4_setattr (struct dentry *, struct iattr *);
+extern int  ext4_write_inode(struct inode *, int);
+extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 				struct kstat *stat);
-extern void ext4_delete_inode (struct inode *);
-extern int  ext4_sync_inode (handle_t *, struct inode *);
-extern void ext4_discard_reservation (struct inode *);
+extern void ext4_delete_inode(struct inode *);
+extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
-extern void ext4_truncate (struct inode *);
+extern void ext4_truncate(struct inode *);
 extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
@@ -1080,11 +1098,10 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
-extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
+extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* migrate.c */
-extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int,
-		       unsigned long);
+extern int ext4_ext_migrate(struct inode *);
 /* namei.c */
 extern int ext4_orphan_add(handle_t *, struct inode *);
 extern int ext4_orphan_del(handle_t *, struct inode *);
@@ -1099,14 +1116,14 @@ extern int ext4_group_extend(struct super_block *sb,
 				ext4_fsblk_t n_blocks_count);
 
 /* super.c */
-extern void ext4_error (struct super_block *, const char *, const char *, ...)
+extern void ext4_error(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
-extern void __ext4_std_error (struct super_block *, const char *, int);
-extern void ext4_abort (struct super_block *, const char *, const char *, ...)
+extern void __ext4_std_error(struct super_block *, const char *, int);
+extern void ext4_abort(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning (struct super_block *, const char *, const char *, ...)
+extern void ext4_warning(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
-extern void ext4_update_dynamic_rev (struct super_block *sb);
+extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
 					__u32 compat);
 extern int ext4_update_rocompat_feature(handle_t *handle,
@@ -1179,7 +1196,7 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
 
 static inline
 struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
-							ext4_group_t group)
+					    ext4_group_t group)
 {
 	 struct ext4_group_info ***grp_info;
 	 long indexv, indexh;
@@ -1207,6 +1224,28 @@ do {								\
 		__ext4_std_error((sb), __func__, (errno));	\
 } while (0)
 
+#ifdef CONFIG_SMP
+/* Each CPU can accumulate FBC_BATCH blocks in their local
+ * counters. So we need to make sure we have free blocks more
+ * than FBC_BATCH  * nr_cpu_ids. Also add a window of 4 times.
+ */
+#define EXT4_FREEBLOCKS_WATERMARK (4 * (FBC_BATCH * nr_cpu_ids))
+#else
+#define EXT4_FREEBLOCKS_WATERMARK 0
+#endif
+
+static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+	/*
+	 * XXX: replace with spinlock if seen contended -bzzz
+	 */
+	down_write(&EXT4_I(inode)->i_data_sem);
+	if (newsize > EXT4_I(inode)->i_disksize)
+		EXT4_I(inode)->i_disksize = newsize;
+	up_write(&EXT4_I(inode)->i_data_sem);
+	return ;
+}
+
 /*
  * Inodes and files operations
  */

fs/ext4/ext4_extents.h

@@ -124,6 +124,19 @@ struct ext4_ext_path {
 #define EXT4_EXT_CACHE_GAP	1
 #define EXT4_EXT_CACHE_EXTENT	2
 
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+					struct ext4_ext_cache *,
+					struct ext4_extent *, void *);
+
+#define EXT_CONTINUE   0
+#define EXT_BREAK      1
+#define EXT_REPEAT     2
 
 #define EXT_MAX_BLOCK	0xffffffff
 
@@ -224,6 +237,8 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
 				 struct ext4_extent *);
 extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
+							ext_prepare_callback, void *);
 extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
 							struct ext4_ext_path *);
 extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,

fs/ext4/ext4_i.h

@@ -33,38 +33,6 @@ typedef __u32 ext4_lblk_t;
 /* data type for block group number */
 typedef unsigned long ext4_group_t;
 
-struct ext4_reserve_window {
-	ext4_fsblk_t	_rsv_start;	/* First byte reserved */
-	ext4_fsblk_t	_rsv_end;	/* Last byte reserved or 0 */
-};
-
-struct ext4_reserve_window_node {
-	struct rb_node		rsv_node;
-	__u32			rsv_goal_size;
-	__u32			rsv_alloc_hit;
-	struct ext4_reserve_window	rsv_window;
-};
-
-struct ext4_block_alloc_info {
-	/* information about reservation window */
-	struct ext4_reserve_window_node rsv_window_node;
-	/*
-	 * was i_next_alloc_block in ext4_inode_info
-	 * is the logical (file-relative) number of the
-	 * most-recently-allocated block in this file.
-	 * We use this for detecting linearly ascending allocation requests.
-	 */
-	ext4_lblk_t last_alloc_logical_block;
-	/*
-	 * Was i_next_alloc_goal in ext4_inode_info
-	 * is the *physical* companion to i_next_alloc_block.
-	 * it the physical block number of the block which was most-recentl
-	 * allocated to this file.  This give us the goal (target) for the next
-	 * allocation when we detect linearly ascending requests.
-	 */
-	ext4_fsblk_t last_alloc_physical_block;
-};
-
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
 
@@ -97,11 +65,8 @@ struct ext4_inode_info {
 	ext4_group_t	i_block_group;
 	__u32	i_state;		/* Dynamic state flags for ext4 */
 
-	/* block reservation info */
-	struct ext4_block_alloc_info *i_block_alloc_info;
-
 	ext4_lblk_t		i_dir_start_lookup;
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	/*
 	 * Extended attributes can be read independently of the main file
 	 * data. Taking i_mutex even when reading would cause contention
@@ -111,7 +76,7 @@ struct ext4_inode_info {
 	 */
 	struct rw_semaphore xattr_sem;
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	struct posix_acl	*i_acl;
 	struct posix_acl	*i_default_acl;
 #endif

fs/ext4/ext4_sb.h

@@ -40,8 +40,8 @@ struct ext4_sb_info {
 	unsigned long s_blocks_last;    /* Last seen block count */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
-	struct ext4_super_block * s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head ** s_group_desc;
+	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head **s_group_desc;
 	unsigned long  s_mount_opt;
 	ext4_fsblk_t s_sb_block;
 	uid_t s_resuid;
@@ -52,6 +52,7 @@ struct ext4_sb_info {
 	int s_desc_per_block_bits;
 	int s_inode_size;
 	int s_first_ino;
+	unsigned int s_inode_readahead_blks;
 	spinlock_t s_next_gen_lock;
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
@@ -59,16 +60,17 @@ struct ext4_sb_info {
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
+	struct percpu_counter s_dirtyblocks_counter;
 	struct blockgroup_lock s_blockgroup_lock;
+	struct proc_dir_entry *s_proc;
 
 	/* root of the per fs reservation window tree */
 	spinlock_t s_rsv_window_lock;
 	struct rb_root s_rsv_window_root;
-	struct ext4_reserve_window_node s_rsv_window_head;
 
 	/* Journaling */
-	struct inode * s_journal_inode;
-	struct journal_s * s_journal;
+	struct inode *s_journal_inode;
+	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	unsigned long s_commit_interval;
 	struct block_device *journal_bdev;
@@ -106,12 +108,12 @@ struct ext4_sb_info {
 
 	/* tunables */
 	unsigned long s_stripe;
-	unsigned long s_mb_stream_request;
-	unsigned long s_mb_max_to_scan;
-	unsigned long s_mb_min_to_scan;
-	unsigned long s_mb_stats;
-	unsigned long s_mb_order2_reqs;
-	unsigned long s_mb_group_prealloc;
+	unsigned int s_mb_stream_request;
+	unsigned int s_mb_max_to_scan;
+	unsigned int s_mb_min_to_scan;
+	unsigned int s_mb_stats;
+	unsigned int s_mb_order2_reqs;
+	unsigned int s_mb_group_prealloc;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
@@ -121,7 +123,6 @@ struct ext4_sb_info {
 	int s_mb_history_cur;
 	int s_mb_history_max;
 	int s_mb_history_num;
-	struct proc_dir_entry *s_mb_proc;
 	spinlock_t s_mb_history_lock;
 	int s_mb_history_filter;
 

fs/ext4/extents.c

@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/falloc.h>
 #include <asm/uaccess.h>
+#include <linux/fiemap.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 
@@ -383,8 +384,8 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
 	ext_debug("\n");
 }
 #else
-#define ext4_ext_show_path(inode,path)
-#define ext4_ext_show_leaf(inode,path)
+#define ext4_ext_show_path(inode, path)
+#define ext4_ext_show_leaf(inode, path)
 #endif
 
 void ext4_ext_drop_refs(struct ext4_ext_path *path)
@@ -440,9 +441,10 @@ ext4_ext_binsearch_idx(struct inode *inode,
 		for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
 		  if (k != 0 &&
 		      le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
-				printk("k=%d, ix=0x%p, first=0x%p\n", k,
-					ix, EXT_FIRST_INDEX(eh));
-				printk("%u <= %u\n",
+				printk(KERN_DEBUG "k=%d, ix=0x%p, "
+				       "first=0x%p\n", k,
+				       ix, EXT_FIRST_INDEX(eh));
+				printk(KERN_DEBUG "%u <= %u\n",
 				       le32_to_cpu(ix->ei_block),
 				       le32_to_cpu(ix[-1].ei_block));
 			}
@@ -1475,7 +1477,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 				struct ext4_ext_path *path,
 				struct ext4_extent *newext)
 {
-	struct ext4_extent_header * eh;
+	struct ext4_extent_header *eh;
 	struct ext4_extent *ex, *fex;
 	struct ext4_extent *nearex; /* nearest extent */
 	struct ext4_ext_path *npath = NULL;
@@ -1625,6 +1627,113 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	return err;
 }
 
+int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+			ext4_lblk_t num, ext_prepare_callback func,
+			void *cbdata)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_ext_cache cbex;
+	struct ext4_extent *ex;
+	ext4_lblk_t next, start = 0, end = 0;
+	ext4_lblk_t last = block + num;
+	int depth, exists, err = 0;
+
+	BUG_ON(func == NULL);
+	BUG_ON(inode == NULL);
+
+	while (block < last && block != EXT_MAX_BLOCK) {
+		num = last - block;
+		/* find extent for this block */
+		path = ext4_ext_find_extent(inode, block, path);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			path = NULL;
+			break;
+		}
+
+		depth = ext_depth(inode);
+		BUG_ON(path[depth].p_hdr == NULL);
+		ex = path[depth].p_ext;
+		next = ext4_ext_next_allocated_block(path);
+
+		exists = 0;
+		if (!ex) {
+			/* there is no extent yet, so try to allocate
+			 * all requested space */
+			start = block;
+			end = block + num;
+		} else if (le32_to_cpu(ex->ee_block) > block) {
+			/* need to allocate space before found extent */
+			start = block;
+			end = le32_to_cpu(ex->ee_block);
+			if (block + num < end)
+				end = block + num;
+		} else if (block >= le32_to_cpu(ex->ee_block)
+					+ ext4_ext_get_actual_len(ex)) {
+			/* need to allocate space after found extent */
+			start = block;
+			end = block + num;
+			if (end >= next)
+				end = next;
+		} else if (block >= le32_to_cpu(ex->ee_block)) {
+			/*
+			 * some part of requested space is covered
+			 * by found extent
+			 */
+			start = block;
+			end = le32_to_cpu(ex->ee_block)
+				+ ext4_ext_get_actual_len(ex);
+			if (block + num < end)
+				end = block + num;
+			exists = 1;
+		} else {
+			BUG();
+		}
+		BUG_ON(end <= start);
+
+		if (!exists) {
+			cbex.ec_block = start;
+			cbex.ec_len = end - start;
+			cbex.ec_start = 0;
+			cbex.ec_type = EXT4_EXT_CACHE_GAP;
+		} else {
+			cbex.ec_block = le32_to_cpu(ex->ee_block);
+			cbex.ec_len = ext4_ext_get_actual_len(ex);
+			cbex.ec_start = ext_pblock(ex);
+			cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+		}
+
+		BUG_ON(cbex.ec_len == 0);
+		err = func(inode, path, &cbex, ex, cbdata);
+		ext4_ext_drop_refs(path);
+
+		if (err < 0)
+			break;
+
+		if (err == EXT_REPEAT)
+			continue;
+		else if (err == EXT_BREAK) {
+			err = 0;
+			break;
+		}
+
+		if (ext_depth(inode) != depth) {
+			/* depth was changed. we have to realloc path */
+			kfree(path);
+			path = NULL;
+		}
+
+		block = cbex.ec_block + cbex.ec_len;
+	}
+
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+
+	return err;
+}
+
 static void
 ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
 			__u32 len, ext4_fsblk_t start, int type)
@@ -2142,7 +2251,7 @@ void ext4_ext_init(struct super_block *sb)
 	 */
 
 	if (test_opt(sb, EXTENTS)) {
-		printk("EXT4-fs: file extents enabled");
+		printk(KERN_INFO "EXT4-fs: file extents enabled");
 #ifdef AGGRESSIVE_TEST
 		printk(", aggressive tests");
 #endif
@@ -2696,11 +2805,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 		goto out2;
 	}
 	/*
-	 * Okay, we need to do block allocation.  Lazily initialize the block
-	 * allocation info here if necessary.
+	 * Okay, we need to do block allocation.
 	 */
-	if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
-		ext4_init_block_alloc_info(inode);
 
 	/* find neighbour allocated blocks */
 	ar.lleft = iblock;
@@ -2760,7 +2866,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 		/* free data blocks we just allocated */
 		/* not a good idea to call discard here directly,
 		 * but otherwise we'd need to call it every free() */
-		ext4_mb_discard_inode_preallocations(inode);
+		ext4_discard_preallocations(inode);
 		ext4_free_blocks(handle, inode, ext_pblock(&newex),
 					ext4_ext_get_actual_len(&newex), 0);
 		goto out2;
@@ -2824,7 +2930,7 @@ void ext4_ext_truncate(struct inode *inode)
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_ext_invalidate_cache(inode);
 
-	ext4_discard_reservation(inode);
+	ext4_discard_preallocations(inode);
 
 	/*
 	 * TODO: optimization is possible here.
@@ -2877,10 +2983,11 @@ static void ext4_falloc_update_inode(struct inode *inode,
 	 * Update only when preallocation was requested beyond
 	 * the file size.
 	 */
-	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-				new_size > i_size_read(inode)) {
-		i_size_write(inode, new_size);
-		EXT4_I(inode)->i_disksize = new_size;
+	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+		if (new_size > i_size_read(inode))
+			i_size_write(inode, new_size);
+		if (new_size > EXT4_I(inode)->i_disksize)
+			ext4_update_i_disksize(inode, new_size);
 	}
 
 }
@@ -2972,3 +3079,143 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	mutex_unlock(&inode->i_mutex);
 	return ret > 0 ? ret2 : ret;
 }
+
+/*
+ * Callback function called for each extent to gather FIEMAP information.
+ */
+int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
+		       void *data)
+{
+	struct fiemap_extent_info *fieinfo = data;
+	unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+	__u64	logical;
+	__u64	physical;
+	__u64	length;
+	__u32	flags = 0;
+	int	error;
+
+	logical =  (__u64)newex->ec_block << blksize_bits;
+
+	if (newex->ec_type == EXT4_EXT_CACHE_GAP) {
+		pgoff_t offset;
+		struct page *page;
+		struct buffer_head *bh = NULL;
+
+		offset = logical >> PAGE_SHIFT;
+		page = find_get_page(inode->i_mapping, offset);
+		if (!page || !page_has_buffers(page))
+			return EXT_CONTINUE;
+
+		bh = page_buffers(page);
+
+		if (!bh)
+			return EXT_CONTINUE;
+
+		if (buffer_delay(bh)) {
+			flags |= FIEMAP_EXTENT_DELALLOC;
+			page_cache_release(page);
+		} else {
+			page_cache_release(page);
+			return EXT_CONTINUE;
+		}
+	}
+
+	physical = (__u64)newex->ec_start << blksize_bits;
+	length =   (__u64)newex->ec_len << blksize_bits;
+
+	if (ex && ext4_ext_is_uninitialized(ex))
+		flags |= FIEMAP_EXTENT_UNWRITTEN;
+
+	/*
+	 * If this extent reaches EXT_MAX_BLOCK, it must be last.
+	 *
+	 * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
+	 * this also indicates no more allocated blocks.
+	 *
+	 * XXX this might miss a single-block extent at EXT_MAX_BLOCK
+	 */
+	if (logical + length - 1 == EXT_MAX_BLOCK ||
+	    ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+		flags |= FIEMAP_EXTENT_LAST;
+
+	error = fiemap_fill_next_extent(fieinfo, logical, physical,
+					length, flags);
+	if (error < 0)
+		return error;
+	if (error == 1)
+		return EXT_BREAK;
+
+	return EXT_CONTINUE;
+}
+
+/* fiemap flags we can handle specified here */
+#define EXT4_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+{
+	__u64 physical = 0;
+	__u64 length;
+	__u32 flags = FIEMAP_EXTENT_LAST;
+	int blockbits = inode->i_sb->s_blocksize_bits;
+	int error = 0;
+
+	/* in-inode? */
+	if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+		struct ext4_iloc iloc;
+		int offset;	/* offset of xattr in inode */
+
+		error = ext4_get_inode_loc(inode, &iloc);
+		if (error)
+			return error;
+		physical = iloc.bh->b_blocknr << blockbits;
+		offset = EXT4_GOOD_OLD_INODE_SIZE +
+				EXT4_I(inode)->i_extra_isize;
+		physical += offset;
+		length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
+	} else { /* external block */
+		physical = EXT4_I(inode)->i_file_acl << blockbits;
+		length = inode->i_sb->s_blocksize;
+	}
+
+	if (physical)
+		error = fiemap_fill_next_extent(fieinfo, 0, physical,
+						length, flags);
+	return (error < 0 ? error : 0);
+}
+
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		__u64 start, __u64 len)
+{
+	ext4_lblk_t start_blk;
+	ext4_lblk_t len_blks;
+	int error = 0;
+
+	/* fallback to generic here if not in extents fmt */
+	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+		return generic_block_fiemap(inode, fieinfo, start, len,
+			ext4_get_block);
+
+	if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
+		return -EBADR;
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+		error = ext4_xattr_fiemap(inode, fieinfo);
+	} else {
+		start_blk = start >> inode->i_sb->s_blocksize_bits;
+		len_blks = len >> inode->i_sb->s_blocksize_bits;
+
+		/*
+		 * Walk the extent tree gathering extent information.
+		 * ext4_ext_fiemap_cb will push extents back to user.
+		 */
+		down_write(&EXT4_I(inode)->i_data_sem);
+		error = ext4_ext_walk_space(inode, start_blk, len_blks,
+					  ext4_ext_fiemap_cb, fieinfo);
+		up_write(&EXT4_I(inode)->i_data_sem);
+	}
+
+	return error;
+}
+

fs/ext4/file.c

@@ -31,14 +31,14 @@
  * from ext4_file_open: open gets called at every open, but release
  * gets called only when /all/ the files are closed.
  */
-static int ext4_release_file (struct inode * inode, struct file * filp)
+static int ext4_release_file(struct inode *inode, struct file *filp)
 {
 	/* if we are the last writer on the inode, drop the block reservation */
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1))
 	{
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_reservation(inode);
+		ext4_discard_preallocations(inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
@@ -140,6 +140,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		__u64 start, __u64 len);
+
 const struct file_operations ext4_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -162,7 +165,7 @@ const struct inode_operations ext4_file_inode_operations = {
 	.truncate	= ext4_truncate,
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
@@ -170,5 +173,6 @@ const struct inode_operations ext4_file_inode_operations = {
 #endif
 	.permission	= ext4_permission,
 	.fallocate	= ext4_fallocate,
+	.fiemap		= ext4_fiemap,
 };
 

fs/ext4/fsync.c

@@ -28,6 +28,7 @@
 #include <linux/writeback.h>
 #include <linux/jbd2.h>
 #include <linux/blkdev.h>
+#include <linux/marker.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
@@ -43,7 +44,7 @@
  * inode to disk.
  */
 
-int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
+int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 {
 	struct inode *inode = dentry->d_inode;
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
@@ -51,6 +52,10 @@ int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
+	trace_mark(ext4_sync_file, "dev %s datasync %d ino %ld parent %ld",
+		   inode->i_sb->s_id, datasync, inode->i_ino,
+		   dentry->d_parent->d_inode->i_ino);
+
 	/*
 	 * data=writeback:
 	 *  The caller's filemap_fdatawrite()/wait will sync the data.

fs/ext4/hash.c

@@ -27,7 +27,7 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 		sum += DELTA;
 		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
 		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
-	} while(--n);
+	} while (--n);
 
 	buf[0] += b0;
 	buf[1] += b1;
@@ -35,7 +35,7 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash(const char *name, int len)
 {
 	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
 	while (len--) {
@@ -59,7 +59,7 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	val = pad;
 	if (len > num*4)
 		len = num * 4;
-	for (i=0; i < len; i++) {
+	for (i = 0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
 		val = msg[i] + (val << 8);
@@ -104,7 +104,7 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 
 	/* Check to see if the seed is all zero's */
 	if (hinfo->seed) {
-		for (i=0; i < 4; i++) {
+		for (i = 0; i < 4; i++) {
 			if (hinfo->seed[i])
 				break;
 		}

fs/ext4/ialloc.c

@@ -115,9 +115,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (bh_uptodate_or_lock(bh))
+	if (buffer_uptodate(bh) &&
+	    !(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
 		return bh;
 
+	lock_buffer(bh);
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -154,39 +156,40 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
  * though), and then we'd have two inodes sharing the
  * same inode number and space on the harddisk.
  */
-void ext4_free_inode (handle_t *handle, struct inode * inode)
+void ext4_free_inode(handle_t *handle, struct inode *inode)
 {
-	struct super_block * sb = inode->i_sb;
+	struct super_block *sb = inode->i_sb;
 	int is_directory;
 	unsigned long ino;
 	struct buffer_head *bitmap_bh = NULL;
 	struct buffer_head *bh2;
 	ext4_group_t block_group;
 	unsigned long bit;
-	struct ext4_group_desc * gdp;
-	struct ext4_super_block * es;
+	struct ext4_group_desc *gdp;
+	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
 	int fatal = 0, err;
 	ext4_group_t flex_group;
 
 	if (atomic_read(&inode->i_count) > 1) {
-		printk ("ext4_free_inode: inode has count=%d\n",
-					atomic_read(&inode->i_count));
+		printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
+		       atomic_read(&inode->i_count));
 		return;
 	}
 	if (inode->i_nlink) {
-		printk ("ext4_free_inode: inode has nlink=%d\n",
-			inode->i_nlink);
+		printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
+		       inode->i_nlink);
 		return;
 	}
 	if (!sb) {
-		printk("ext4_free_inode: inode on nonexistent device\n");
+		printk(KERN_ERR "ext4_free_inode: inode on "
+		       "nonexistent device\n");
 		return;
 	}
 	sbi = EXT4_SB(sb);
 
 	ino = inode->i_ino;
-	ext4_debug ("freeing inode %lu\n", ino);
+	ext4_debug("freeing inode %lu\n", ino);
 
 	/*
 	 * Note: we must free any quota before locking the superblock,
@@ -200,12 +203,12 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
 	is_directory = S_ISDIR(inode->i_mode);
 
 	/* Do this BEFORE marking the inode not in use or returning an error */
-	clear_inode (inode);
+	clear_inode(inode);
 
 	es = EXT4_SB(sb)->s_es;
 	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
-		ext4_error (sb, "ext4_free_inode",
-			    "reserved or nonexistent inode %lu", ino);
+		ext4_error(sb, "ext4_free_inode",
+			   "reserved or nonexistent inode %lu", ino);
 		goto error_return;
 	}
 	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
@@ -222,10 +225,10 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
 	/* Ok, now we can actually update the inode bitmaps.. */
 	if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 					bit, bitmap_bh->b_data))
-		ext4_error (sb, "ext4_free_inode",
-			      "bit already cleared for inode %lu", ino);
+		ext4_error(sb, "ext4_free_inode",
+			   "bit already cleared for inode %lu", ino);
 	else {
-		gdp = ext4_get_group_desc (sb, block_group, &bh2);
+		gdp = ext4_get_group_desc(sb, block_group, &bh2);
 
 		BUFFER_TRACE(bh2, "get_write_access");
 		fatal = ext4_journal_get_write_access(handle, bh2);
@@ -287,7 +290,7 @@ static int find_group_dir(struct super_block *sb, struct inode *parent,
 	avefreei = freei / ngroups;
 
 	for (group = 0; group < ngroups; group++) {
-		desc = ext4_get_group_desc (sb, group, NULL);
+		desc = ext4_get_group_desc(sb, group, NULL);
 		if (!desc || !desc->bg_free_inodes_count)
 			continue;
 		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
@@ -576,16 +579,16 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
  * For other inodes, search forward from the parent directory's block
  * group to find a free inode.
  */
-struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
+struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 {
 	struct super_block *sb;
 	struct buffer_head *bitmap_bh = NULL;
 	struct buffer_head *bh2;
 	ext4_group_t group = 0;
 	unsigned long ino = 0;
-	struct inode * inode;
-	struct ext4_group_desc * gdp = NULL;
-	struct ext4_super_block * es;
+	struct inode *inode;
+	struct ext4_group_desc *gdp = NULL;
+	struct ext4_super_block *es;
 	struct ext4_inode_info *ei;
 	struct ext4_sb_info *sbi;
 	int ret2, err = 0;
@@ -613,7 +616,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	}
 
 	if (S_ISDIR(mode)) {
-		if (test_opt (sb, OLDALLOC))
+		if (test_opt(sb, OLDALLOC))
 			ret2 = find_group_dir(sb, dir, &group);
 		else
 			ret2 = find_group_orlov(sb, dir, &group);
@@ -783,7 +786,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	}
 
 	inode->i_uid = current->fsuid;
-	if (test_opt (sb, GRPID))
+	if (test_opt(sb, GRPID))
 		inode->i_gid = dir->i_gid;
 	else if (dir->i_mode & S_ISGID) {
 		inode->i_gid = dir->i_gid;
@@ -816,7 +819,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 		ei->i_flags &= ~EXT4_DIRSYNC_FL;
 	ei->i_file_acl = 0;
 	ei->i_dtime = 0;
-	ei->i_block_alloc_info = NULL;
 	ei->i_block_group = group;
 
 	ext4_set_inode_flags(inode);
@@ -832,7 +834,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
 
 	ret = inode;
-	if(DQUOT_ALLOC_INODE(inode)) {
+	if (DQUOT_ALLOC_INODE(inode)) {
 		err = -EDQUOT;
 		goto fail_drop;
 	}
@@ -841,7 +843,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	if (err)
 		goto fail_free_drop;
 
-	err = ext4_init_security(handle,inode, dir);
+	err = ext4_init_security(handle, inode, dir);
 	if (err)
 		goto fail_free_drop;
 
@@ -959,7 +961,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	return ERR_PTR(err);
 }
 
-unsigned long ext4_count_free_inodes (struct super_block * sb)
+unsigned long ext4_count_free_inodes(struct super_block *sb)
 {
 	unsigned long desc_count;
 	struct ext4_group_desc *gdp;
@@ -974,7 +976,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 	bitmap_count = 0;
 	gdp = NULL;
 	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-		gdp = ext4_get_group_desc (sb, i, NULL);
+		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
 		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
@@ -989,13 +991,14 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);
-	printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
-		le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+	printk(KERN_DEBUG "ext4_count_free_inodes: "
+	       "stored = %u, computed = %lu, %lu\n",
+	       le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
 	return desc_count;
 #else
 	desc_count = 0;
 	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-		gdp = ext4_get_group_desc (sb, i, NULL);
+		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
 		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
@@ -1006,13 +1009,13 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 }
 
 /* Called at mount-time, super-block is locked */
-unsigned long ext4_count_dirs (struct super_block * sb)
+unsigned long ext4_count_dirs(struct super_block * sb)
 {
 	unsigned long count = 0;
 	ext4_group_t i;
 
 	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-		struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
 		count += le16_to_cpu(gdp->bg_used_dirs_count);

fs/ext4/inode.c

@@ -190,7 +190,7 @@ static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
 /*
  * Called at the last iput() if i_nlink is zero.
  */
-void ext4_delete_inode (struct inode * inode)
+void ext4_delete_inode(struct inode *inode)
 {
 	handle_t *handle;
 	int err;
@@ -330,11 +330,11 @@ static int ext4_block_to_path(struct inode *inode,
 	int final = 0;
 
 	if (i_block < 0) {
-		ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0");
+		ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
 	} else if (i_block < direct_blocks) {
 		offsets[n++] = i_block;
 		final = direct_blocks;
-	} else if ( (i_block -= direct_blocks) < indirect_blocks) {
+	} else if ((i_block -= direct_blocks) < indirect_blocks) {
 		offsets[n++] = EXT4_IND_BLOCK;
 		offsets[n++] = i_block;
 		final = ptrs;
@@ -400,14 +400,14 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 
 	*err = 0;
 	/* i_data is not going away, no lock needed */
-	add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets);
+	add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
 	if (!p->key)
 		goto no_block;
 	while (--depth) {
 		bh = sb_bread(sb, le32_to_cpu(p->key));
 		if (!bh)
 			goto failure;
-		add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
+		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
 		/* Reader: end */
 		if (!p->key)
 			goto no_block;
@@ -443,7 +443,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
+	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
 	__le32 *p;
 	ext4_fsblk_t bg_start;
 	ext4_fsblk_t last_block;
@@ -486,18 +486,9 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
 		Indirect *partial)
 {
-	struct ext4_block_alloc_info *block_i;
-
-	block_i =  EXT4_I(inode)->i_block_alloc_info;
-
 	/*
-	 * try the heuristic for sequential allocation,
-	 * failing that at least try to get decent locality.
+	 * XXX need to get goal block from mballoc's data structures
 	 */
-	if (block_i && (block == block_i->last_alloc_logical_block + 1)
-		&& (block_i->last_alloc_physical_block != 0)) {
-		return block_i->last_alloc_physical_block + 1;
-	}
 
 	return ext4_find_near(inode, partial);
 }
@@ -630,7 +621,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	*err = 0;
 	return ret;
 failed_out:
-	for (i = 0; i <index; i++)
+	for (i = 0; i < index; i++)
 		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
 	return ret;
 }
@@ -703,7 +694,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		branch[n].p = (__le32 *) bh->b_data + offsets[n];
 		branch[n].key = cpu_to_le32(new_blocks[n]);
 		*branch[n].p = branch[n].key;
-		if ( n == indirect_blks) {
+		if (n == indirect_blks) {
 			current_block = new_blocks[n];
 			/*
 			 * End of chain, update the last new metablock of
@@ -730,7 +721,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
 		ext4_journal_forget(handle, branch[i].bh);
 	}
-	for (i = 0; i <indirect_blks; i++)
+	for (i = 0; i < indirect_blks; i++)
 		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
 
 	ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
@@ -757,10 +748,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 {
 	int i;
 	int err = 0;
-	struct ext4_block_alloc_info *block_i;
 	ext4_fsblk_t current_block;
 
-	block_i = EXT4_I(inode)->i_block_alloc_info;
 	/*
 	 * If we're splicing into a [td]indirect block (as opposed to the
 	 * inode) then we need to get write access to the [td]indirect block
@@ -783,18 +772,7 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	if (num == 0 && blks > 1) {
 		current_block = le32_to_cpu(where->key) + 1;
 		for (i = 1; i < blks; i++)
-			*(where->p + i ) = cpu_to_le32(current_block++);
-	}
-
-	/*
-	 * update the most recently allocated logical & physical block
-	 * in i_block_alloc_info, to assist find the proper goal block for next
-	 * allocation
-	 */
-	if (block_i) {
-		block_i->last_alloc_logical_block = block + blks - 1;
-		block_i->last_alloc_physical_block =
-				le32_to_cpu(where[num].key) + blks - 1;
+			*(where->p + i) = cpu_to_le32(current_block++);
 	}
 
 	/* We are done with atomic stuff, now do the rest of housekeeping */
@@ -914,12 +892,8 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 		goto cleanup;
 
 	/*
-	 * Okay, we need to do block allocation.  Lazily initialize the block
-	 * allocation info here if necessary
+	 * Okay, we need to do block allocation.
 	*/
-	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
-		ext4_init_block_alloc_info(inode);
-
 	goal = ext4_find_goal(inode, iblock, partial);
 
 	/* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1030,19 +1004,20 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
 	mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
 
-	/* Account for allocated meta_blocks */
-	mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+	if (mdb_free) {
+		/* Account for allocated meta_blocks */
+		mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
 
-	/* update fs free blocks counter for truncate case */
-	percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+		/* update fs dirty blocks counter */
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
+		EXT4_I(inode)->i_allocated_meta_blocks = 0;
+		EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+	}
 
 	/* update per-inode reservations */
 	BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
 	EXT4_I(inode)->i_reserved_data_blocks -= used;
 
-	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-	EXT4_I(inode)->i_reserved_meta_blocks = mdb;
-	EXT4_I(inode)->i_allocated_meta_blocks = 0;
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 }
 
@@ -1160,8 +1135,8 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
-static int ext4_get_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create)
+int ext4_get_block(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	int ret = 0, started = 0;
@@ -1241,7 +1216,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 			BUFFER_TRACE(bh, "call get_create_access");
 			fatal = ext4_journal_get_create_access(handle, bh);
 			if (!fatal && !buffer_uptodate(bh)) {
-				memset(bh->b_data,0,inode->i_sb->s_blocksize);
+				memset(bh->b_data, 0, inode->i_sb->s_blocksize);
 				set_buffer_uptodate(bh);
 			}
 			unlock_buffer(bh);
@@ -1266,7 +1241,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 			       ext4_lblk_t block, int create, int *err)
 {
-	struct buffer_head * bh;
+	struct buffer_head *bh;
 
 	bh = ext4_getblk(handle, inode, block, create, err);
 	if (!bh)
@@ -1282,13 +1257,13 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 	return NULL;
 }
 
-static int walk_page_buffers(	handle_t *handle,
-				struct buffer_head *head,
-				unsigned from,
-				unsigned to,
-				int *partial,
-				int (*fn)(	handle_t *handle,
-						struct buffer_head *bh))
+static int walk_page_buffers(handle_t *handle,
+			     struct buffer_head *head,
+			     unsigned from,
+			     unsigned to,
+			     int *partial,
+			     int (*fn)(handle_t *handle,
+				       struct buffer_head *bh))
 {
 	struct buffer_head *bh;
 	unsigned block_start, block_end;
@@ -1296,9 +1271,9 @@ static int walk_page_buffers(	handle_t *handle,
 	int err, ret = 0;
 	struct buffer_head *next;
 
-	for (	bh = head, block_start = 0;
-		ret == 0 && (bh != head || !block_start);
-		block_start = block_end, bh = next)
+	for (bh = head, block_start = 0;
+	     ret == 0 && (bh != head || !block_start);
+	     block_start = block_end, bh = next)
 	{
 		next = bh->b_this_page;
 		block_end = block_start + blocksize;
@@ -1351,23 +1326,23 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
 {
- 	struct inode *inode = mapping->host;
+	struct inode *inode = mapping->host;
 	int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
 	handle_t *handle;
 	int retries = 0;
- 	struct page *page;
+	struct page *page;
  	pgoff_t index;
- 	unsigned from, to;
+	unsigned from, to;
 
  	index = pos >> PAGE_CACHE_SHIFT;
- 	from = pos & (PAGE_CACHE_SIZE - 1);
- 	to = from + len;
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
 
 retry:
-  	handle = ext4_journal_start(inode, needed_blocks);
-  	if (IS_ERR(handle)) {
-  		ret = PTR_ERR(handle);
-  		goto out;
+	handle = ext4_journal_start(inode, needed_blocks);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
 	}
 
 	page = __grab_cache_page(mapping, index);
@@ -1387,9 +1362,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 	if (ret) {
- 		unlock_page(page);
+		unlock_page(page);
 		ext4_journal_stop(handle);
- 		page_cache_release(page);
+		page_cache_release(page);
+		/*
+		 * block_write_begin may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + len > inode->i_size)
+			vmtruncate(inode, inode->i_size);
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -1426,16 +1408,18 @@ static int ext4_ordered_write_end(struct file *file,
 	ret = ext4_jbd2_file_inode(handle, inode);
 
 	if (ret == 0) {
-		/*
-		 * generic_write_end() will run mark_inode_dirty() if i_size
-		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
-		 * into that.
-		 */
 		loff_t new_i_size;
 
 		new_i_size = pos + copied;
-		if (new_i_size > EXT4_I(inode)->i_disksize)
-			EXT4_I(inode)->i_disksize = new_i_size;
+		if (new_i_size > EXT4_I(inode)->i_disksize) {
+			ext4_update_i_disksize(inode, new_i_size);
+			/* We need to mark inode dirty even if
+			 * new_i_size is less that inode->i_size
+			 * bu greater than i_disksize.(hint delalloc)
+			 */
+			ext4_mark_inode_dirty(handle, inode);
+		}
+
 		ret2 = generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 		copied = ret2;
@@ -1460,8 +1444,14 @@ static int ext4_writeback_write_end(struct file *file,
 	loff_t new_i_size;
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize)
-		EXT4_I(inode)->i_disksize = new_i_size;
+	if (new_i_size > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, new_i_size);
+		/* We need to mark inode dirty even if
+		 * new_i_size is less that inode->i_size
+		 * bu greater than i_disksize.(hint delalloc)
+		 */
+		ext4_mark_inode_dirty(handle, inode);
+	}
 
 	ret2 = generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
@@ -1486,6 +1476,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int ret = 0, ret2;
 	int partial = 0;
 	unsigned from, to;
+	loff_t new_i_size;
 
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
@@ -1500,11 +1491,12 @@ static int ext4_journalled_write_end(struct file *file,
 				to, &partial, write_end_fn);
 	if (!partial)
 		SetPageUptodate(page);
-	if (pos+copied > inode->i_size)
+	new_i_size = pos + copied;
+	if (new_i_size > inode->i_size)
 		i_size_write(inode, pos+copied);
 	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
-	if (inode->i_size > EXT4_I(inode)->i_disksize) {
-		EXT4_I(inode)->i_disksize = inode->i_size;
+	if (new_i_size > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, new_i_size);
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
@@ -1521,6 +1513,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 {
+	int retries = 0;
        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
        unsigned long md_needed, mdblocks, total = 0;
 
@@ -1529,6 +1522,7 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 	 * in order to allocate nrblocks
 	 * worse case is one extent per block
 	 */
+repeat:
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 	total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
 	mdblocks = ext4_calc_metadata_amount(inode, total);
@@ -1537,13 +1531,14 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 	md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
 	total = md_needed + nrblocks;
 
-	if (ext4_has_free_blocks(sbi, total) < total) {
+	if (ext4_claim_free_blocks(sbi, total)) {
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+			yield();
+			goto repeat;
+		}
 		return -ENOSPC;
 	}
-	/* reduce fs free blocks counter */
-	percpu_counter_sub(&sbi->s_freeblocks_counter, total);
-
 	EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
 	EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
 
@@ -1585,8 +1580,8 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 
 	release = to_free + mdb_free;
 
-	/* update fs free blocks counter for truncate case */
-	percpu_counter_add(&sbi->s_freeblocks_counter, release);
+	/* update fs dirty blocks counter for truncate case */
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
 
 	/* update per-inode reservations */
 	BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
@@ -1630,6 +1625,7 @@ struct mpage_da_data {
 	struct writeback_control *wbc;
 	int io_done;
 	long pages_written;
+	int retval;
 };
 
 /*
@@ -1783,6 +1779,57 @@ static inline void __unmap_underlying_blocks(struct inode *inode,
 		unmap_underlying_metadata(bdev, bh->b_blocknr + i);
 }
 
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
+					sector_t logical, long blk_cnt)
+{
+	int nr_pages, i;
+	pgoff_t index, end;
+	struct pagevec pvec;
+	struct inode *inode = mpd->inode;
+	struct address_space *mapping = inode->i_mapping;
+
+	index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	end   = (logical + blk_cnt - 1) >>
+				(PAGE_CACHE_SHIFT - inode->i_blkbits);
+	while (index <= end) {
+		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			index = page->index;
+			if (index > end)
+				break;
+			index++;
+
+			BUG_ON(!PageLocked(page));
+			BUG_ON(PageWriteback(page));
+			block_invalidatepage(page, 0);
+			ClearPageUptodate(page);
+			unlock_page(page);
+		}
+	}
+	return;
+}
+
+static void ext4_print_free_blocks(struct inode *inode)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	printk(KERN_EMERG "Total free blocks count %lld\n",
+			ext4_count_free_blocks(inode->i_sb));
+	printk(KERN_EMERG "Free/Dirty block details\n");
+	printk(KERN_EMERG "free_blocks=%lld\n",
+			percpu_counter_sum(&sbi->s_freeblocks_counter));
+	printk(KERN_EMERG "dirty_blocks=%lld\n",
+			percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+	printk(KERN_EMERG "Block reservation details\n");
+	printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+			EXT4_I(inode)->i_reserved_data_blocks);
+	printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+			EXT4_I(inode)->i_reserved_meta_blocks);
+	return;
+}
+
 /*
  * mpage_da_map_blocks - go through given space
  *
@@ -1792,32 +1839,69 @@ static inline void __unmap_underlying_blocks(struct inode *inode,
  * The function skips space we know is already mapped to disk blocks.
  *
  */
-static void mpage_da_map_blocks(struct mpage_da_data *mpd)
+static int  mpage_da_map_blocks(struct mpage_da_data *mpd)
 {
 	int err = 0;
-	struct buffer_head *lbh = &mpd->lbh;
-	sector_t next = lbh->b_blocknr;
 	struct buffer_head new;
+	struct buffer_head *lbh = &mpd->lbh;
+	sector_t next;
 
 	/*
 	 * We consider only non-mapped and non-allocated blocks
 	 */
 	if (buffer_mapped(lbh) && !buffer_delay(lbh))
-		return;
-
+		return 0;
 	new.b_state = lbh->b_state;
 	new.b_blocknr = 0;
 	new.b_size = lbh->b_size;
-
+	next = lbh->b_blocknr;
 	/*
 	 * If we didn't accumulate anything
 	 * to write simply return
 	 */
 	if (!new.b_size)
-		return;
+		return 0;
 	err = mpd->get_block(mpd->inode, next, &new, 1);
-	if (err)
-		return;
+	if (err) {
+
+		/* If get block returns with error
+		 * we simply return. Later writepage
+		 * will redirty the page and writepages
+		 * will find the dirty page again
+		 */
+		if (err == -EAGAIN)
+			return 0;
+
+		if (err == -ENOSPC &&
+				ext4_count_free_blocks(mpd->inode->i_sb)) {
+			mpd->retval = err;
+			return 0;
+		}
+
+		/*
+		 * get block failure will cause us
+		 * to loop in writepages. Because
+		 * a_ops->writepage won't be able to
+		 * make progress. The page will be redirtied
+		 * by writepage and writepages will again
+		 * try to write the same.
+		 */
+		printk(KERN_EMERG "%s block allocation failed for inode %lu "
+				  "at logical offset %llu with max blocks "
+				  "%zd with error %d\n",
+				  __func__, mpd->inode->i_ino,
+				  (unsigned long long)next,
+				  lbh->b_size >> mpd->inode->i_blkbits, err);
+		printk(KERN_EMERG "This should not happen.!! "
+					"Data will be lost\n");
+		if (err == -ENOSPC) {
+			ext4_print_free_blocks(mpd->inode);
+		}
+		/* invlaidate all the pages */
+		ext4_da_block_invalidatepages(mpd, next,
+				lbh->b_size >> mpd->inode->i_blkbits);
+		return err;
+	}
 	BUG_ON(new.b_size == 0);
 
 	if (buffer_new(&new))
@@ -1830,7 +1914,7 @@ static void mpage_da_map_blocks(struct mpage_da_data *mpd)
 	if (buffer_delay(lbh) || buffer_unwritten(lbh))
 		mpage_put_bnr_to_bhs(mpd, next, &new);
 
-	return;
+	return 0;
 }
 
 #define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
@@ -1899,8 +1983,8 @@ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
 	 * We couldn't merge the block to our extent, so we
 	 * need to flush current  extent and start new one
 	 */
-	mpage_da_map_blocks(mpd);
-	mpage_da_submit_io(mpd);
+	if (mpage_da_map_blocks(mpd) == 0)
+		mpage_da_submit_io(mpd);
 	mpd->io_done = 1;
 	return;
 }
@@ -1942,8 +2026,8 @@ static int __mpage_da_writepage(struct page *page,
 		 * and start IO on them using writepage()
 		 */
 		if (mpd->next_page != mpd->first_page) {
-			mpage_da_map_blocks(mpd);
-			mpage_da_submit_io(mpd);
+			if (mpage_da_map_blocks(mpd) == 0)
+				mpage_da_submit_io(mpd);
 			/*
 			 * skip rest of the page in the page_vec
 			 */
@@ -2018,39 +2102,36 @@ static int __mpage_da_writepage(struct page *page,
  */
 static int mpage_da_writepages(struct address_space *mapping,
 			       struct writeback_control *wbc,
-			       get_block_t get_block)
+			       struct mpage_da_data *mpd)
 {
-	struct mpage_da_data mpd;
 	long to_write;
 	int ret;
 
-	if (!get_block)
+	if (!mpd->get_block)
 		return generic_writepages(mapping, wbc);
 
-	mpd.wbc = wbc;
-	mpd.inode = mapping->host;
-	mpd.lbh.b_size = 0;
-	mpd.lbh.b_state = 0;
-	mpd.lbh.b_blocknr = 0;
-	mpd.first_page = 0;
-	mpd.next_page = 0;
-	mpd.get_block = get_block;
-	mpd.io_done = 0;
-	mpd.pages_written = 0;
+	mpd->lbh.b_size = 0;
+	mpd->lbh.b_state = 0;
+	mpd->lbh.b_blocknr = 0;
+	mpd->first_page = 0;
+	mpd->next_page = 0;
+	mpd->io_done = 0;
+	mpd->pages_written = 0;
+	mpd->retval = 0;
 
 	to_write = wbc->nr_to_write;
 
-	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd);
+	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
 
 	/*
 	 * Handle last extent of pages
 	 */
-	if (!mpd.io_done && mpd.next_page != mpd.first_page) {
-		mpage_da_map_blocks(&mpd);
-		mpage_da_submit_io(&mpd);
+	if (!mpd->io_done && mpd->next_page != mpd->first_page) {
+		if (mpage_da_map_blocks(mpd) == 0)
+			mpage_da_submit_io(mpd);
 	}
 
-	wbc->nr_to_write = to_write - mpd.pages_written;
+	wbc->nr_to_write = to_write - mpd->pages_written;
 	return ret;
 }
 
@@ -2103,18 +2184,24 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
 	handle_t *handle = NULL;
 
 	handle = ext4_journal_current_handle();
-	if (!handle) {
-		ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
-				   bh_result, 0, 0, 0);
-		BUG_ON(!ret);
-	} else {
-		ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
-				   bh_result, create, 0, EXT4_DELALLOC_RSVED);
-	}
-
+	BUG_ON(!handle);
+	ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+			bh_result, create, 0, EXT4_DELALLOC_RSVED);
 	if (ret > 0) {
+
 		bh_result->b_size = (ret << inode->i_blkbits);
 
+		if (ext4_should_order_data(inode)) {
+			int retval;
+			retval = ext4_jbd2_file_inode(handle, inode);
+			if (retval)
+				/*
+				 * Failed to add inode for ordered
+				 * mode. Don't update file size
+				 */
+				return retval;
+		}
+
 		/*
 		 * Update on-disk size along with block allocation
 		 * we don't use 'extend_disksize' as size may change
@@ -2124,18 +2211,9 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
 		if (disksize > i_size_read(inode))
 			disksize = i_size_read(inode);
 		if (disksize > EXT4_I(inode)->i_disksize) {
-			/*
-			 * XXX: replace with spinlock if seen contended -bzzz
-			 */
-			down_write(&EXT4_I(inode)->i_data_sem);
-			if (disksize > EXT4_I(inode)->i_disksize)
-				EXT4_I(inode)->i_disksize = disksize;
-			up_write(&EXT4_I(inode)->i_data_sem);
-
-			if (EXT4_I(inode)->i_disksize == disksize) {
-				ret = ext4_mark_inode_dirty(handle, inode);
-				return ret;
-			}
+			ext4_update_i_disksize(inode, disksize);
+			ret = ext4_mark_inode_dirty(handle, inode);
+			return ret;
 		}
 		ret = 0;
 	}
@@ -2284,6 +2362,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 {
 	handle_t *handle = NULL;
 	loff_t range_start = 0;
+	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	long to_write, pages_skipped = 0;
@@ -2317,6 +2396,9 @@ static int ext4_da_writepages(struct address_space *mapping,
 	range_start =  wbc->range_start;
 	pages_skipped = wbc->pages_skipped;
 
+	mpd.wbc = wbc;
+	mpd.inode = mapping->host;
+
 restart_loop:
 	to_write = wbc->nr_to_write;
 	while (!ret && to_write > 0) {
@@ -2340,23 +2422,17 @@ static int ext4_da_writepages(struct address_space *mapping,
 			dump_stack();
 			goto out_writepages;
 		}
-		if (ext4_should_order_data(inode)) {
-			/*
-			 * With ordered mode we need to add
-			 * the inode to the journal handl
-			 * when we do block allocation.
-			 */
-			ret = ext4_jbd2_file_inode(handle, inode);
-			if (ret) {
-				ext4_journal_stop(handle);
-				goto out_writepages;
-			}
-		}
-
 		to_write -= wbc->nr_to_write;
-		ret = mpage_da_writepages(mapping, wbc,
-					  ext4_da_get_block_write);
+
+		mpd.get_block = ext4_da_get_block_write;
+		ret = mpage_da_writepages(mapping, wbc, &mpd);
+
 		ext4_journal_stop(handle);
+
+		if (mpd.retval == -ENOSPC)
+			jbd2_journal_force_commit_nested(sbi->s_journal);
+
+		/* reset the retry count */
 		if (ret == MPAGE_DA_EXTENT_TAIL) {
 			/*
 			 * got one extent now try with
@@ -2391,6 +2467,33 @@ static int ext4_da_writepages(struct address_space *mapping,
 	return ret;
 }
 
+#define FALL_BACK_TO_NONDELALLOC 1
+static int ext4_nonda_switch(struct super_block *sb)
+{
+	s64 free_blocks, dirty_blocks;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	/*
+	 * switch to non delalloc mode if we are running low
+	 * on free block. The free block accounting via percpu
+	 * counters can get slightly wrong with FBC_BATCH getting
+	 * accumulated on each CPU without updating global counters
+	 * Delalloc need an accurate free block accounting. So switch
+	 * to non delalloc when we are near to error range.
+	 */
+	free_blocks  = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+	if (2 * free_blocks < 3 * dirty_blocks ||
+		free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+		/*
+		 * free block count is less that 150% of dirty blocks
+		 * or free blocks is less that watermark
+		 */
+		return 1;
+	}
+	return 0;
+}
+
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
@@ -2406,6 +2509,12 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
+	if (ext4_nonda_switch(inode->i_sb)) {
+		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
+		return ext4_write_begin(file, mapping, pos,
+					len, flags, pagep, fsdata);
+	}
+	*fsdata = (void *)0;
 retry:
 	/*
 	 * With delayed allocation, we don't log the i_disksize update
@@ -2433,6 +2542,13 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 		unlock_page(page);
 		ext4_journal_stop(handle);
 		page_cache_release(page);
+		/*
+		 * block_write_begin may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + len > inode->i_size)
+			vmtruncate(inode, inode->i_size);
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2456,7 +2572,7 @@ static int ext4_da_should_update_i_disksize(struct page *page,
 	bh = page_buffers(page);
 	idx = offset >> inode->i_blkbits;
 
-	for (i=0; i < idx; i++)
+	for (i = 0; i < idx; i++)
 		bh = bh->b_this_page;
 
 	if (!buffer_mapped(bh) || (buffer_delay(bh)))
@@ -2474,9 +2590,22 @@ static int ext4_da_write_end(struct file *file,
 	handle_t *handle = ext4_journal_current_handle();
 	loff_t new_i_size;
 	unsigned long start, end;
+	int write_mode = (int)(unsigned long)fsdata;
+
+	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+		if (ext4_should_order_data(inode)) {
+			return ext4_ordered_write_end(file, mapping, pos,
+					len, copied, page, fsdata);
+		} else if (ext4_should_writeback_data(inode)) {
+			return ext4_writeback_write_end(file, mapping, pos,
+					len, copied, page, fsdata);
+		} else {
+			BUG();
+		}
+	}
 
 	start = pos & (PAGE_CACHE_SIZE - 1);
-	end = start + copied -1;
+	end = start + copied - 1;
 
 	/*
 	 * generic_write_end() will run mark_inode_dirty() if i_size
@@ -2500,6 +2629,11 @@ static int ext4_da_write_end(struct file *file,
 				EXT4_I(inode)->i_disksize = new_i_size;
 			}
 			up_write(&EXT4_I(inode)->i_data_sem);
+			/* We need to mark inode dirty even if
+			 * new_i_size is less that inode->i_size
+			 * bu greater than i_disksize.(hint delalloc)
+			 */
+			ext4_mark_inode_dirty(handle, inode);
 		}
 	}
 	ret2 = generic_write_end(file, mapping, pos, len, copied,
@@ -2591,7 +2725,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 			return 0;
 	}
 
-	return generic_block_bmap(mapping,block,ext4_get_block);
+	return generic_block_bmap(mapping, block, ext4_get_block);
 }
 
 static int bget_one(handle_t *handle, struct buffer_head *bh)
@@ -3197,7 +3331,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
 	if (!partial->key && *partial->p)
 		/* Writer: end */
 		goto no_top;
-	for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--)
+	for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
 		;
 	/*
 	 * OK, we've found the last block that must survive. The rest of our
@@ -3216,7 +3350,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
 	}
 	/* Writer: end */
 
-	while(partial > p) {
+	while (partial > p) {
 		brelse(partial->bh);
 		partial--;
 	}
@@ -3408,9 +3542,9 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 			/* This zaps the entire block.  Bottom up. */
 			BUFFER_TRACE(bh, "free child branches");
 			ext4_free_branches(handle, inode, bh,
-					   (__le32*)bh->b_data,
-					   (__le32*)bh->b_data + addr_per_block,
-					   depth);
+					(__le32 *) bh->b_data,
+					(__le32 *) bh->b_data + addr_per_block,
+					depth);
 
 			/*
 			 * We've probably journalled the indirect block several
@@ -3578,7 +3712,7 @@ void ext4_truncate(struct inode *inode)
 	 */
 	down_write(&ei->i_data_sem);
 
-	ext4_discard_reservation(inode);
+	ext4_discard_preallocations(inode);
 
 	/*
 	 * The orphan list entry will now protect us from any crash which
@@ -3673,41 +3807,6 @@ void ext4_truncate(struct inode *inode)
 	ext4_journal_stop(handle);
 }
 
-static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
-		unsigned long ino, struct ext4_iloc *iloc)
-{
-	ext4_group_t block_group;
-	unsigned long offset;
-	ext4_fsblk_t block;
-	struct ext4_group_desc *gdp;
-
-	if (!ext4_valid_inum(sb, ino)) {
-		/*
-		 * This error is already checked for in namei.c unless we are
-		 * looking at an NFS filehandle, in which case no error
-		 * report is needed
-		 */
-		return 0;
-	}
-
-	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
-	gdp = ext4_get_group_desc(sb, block_group, NULL);
-	if (!gdp)
-		return 0;
-
-	/*
-	 * Figure out the offset within the block group inode table
-	 */
-	offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)) *
-		EXT4_INODE_SIZE(sb);
-	block = ext4_inode_table(sb, gdp) +
-		(offset >> EXT4_BLOCK_SIZE_BITS(sb));
-
-	iloc->block_group = block_group;
-	iloc->offset = offset & (EXT4_BLOCK_SIZE(sb) - 1);
-	return block;
-}
-
 /*
  * ext4_get_inode_loc returns with an extra refcount against the inode's
  * underlying buffer_head on success. If 'in_mem' is true, we have all
@@ -3717,19 +3816,35 @@ static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
 static int __ext4_get_inode_loc(struct inode *inode,
 				struct ext4_iloc *iloc, int in_mem)
 {
-	ext4_fsblk_t block;
-	struct buffer_head *bh;
+	struct ext4_group_desc	*gdp;
+	struct buffer_head	*bh;
+	struct super_block	*sb = inode->i_sb;
+	ext4_fsblk_t		block;
+	int			inodes_per_block, inode_offset;
+
+	iloc->bh = 0;
+	if (!ext4_valid_inum(sb, inode->i_ino))
+		return -EIO;
 
-	block = ext4_get_inode_block(inode->i_sb, inode->i_ino, iloc);
-	if (!block)
+	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
+	if (!gdp)
 		return -EIO;
 
-	bh = sb_getblk(inode->i_sb, block);
+	/*
+	 * Figure out the offset within the block group inode table
+	 */
+	inodes_per_block = (EXT4_BLOCK_SIZE(sb) / EXT4_INODE_SIZE(sb));
+	inode_offset = ((inode->i_ino - 1) %
+			EXT4_INODES_PER_GROUP(sb));
+	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
+	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
+
+	bh = sb_getblk(sb, block);
 	if (!bh) {
-		ext4_error (inode->i_sb, "ext4_get_inode_loc",
-				"unable to read inode block - "
-				"inode=%lu, block=%llu",
-				 inode->i_ino, block);
+		ext4_error(sb, "ext4_get_inode_loc", "unable to read "
+			   "inode block - inode=%lu, block=%llu",
+			   inode->i_ino, block);
 		return -EIO;
 	}
 	if (!buffer_uptodate(bh)) {
@@ -3757,28 +3872,12 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		 */
 		if (in_mem) {
 			struct buffer_head *bitmap_bh;
-			struct ext4_group_desc *desc;
-			int inodes_per_buffer;
-			int inode_offset, i;
-			ext4_group_t block_group;
-			int start;
-
-			block_group = (inode->i_ino - 1) /
-					EXT4_INODES_PER_GROUP(inode->i_sb);
-			inodes_per_buffer = bh->b_size /
-				EXT4_INODE_SIZE(inode->i_sb);
-			inode_offset = ((inode->i_ino - 1) %
-					EXT4_INODES_PER_GROUP(inode->i_sb));
-			start = inode_offset & ~(inodes_per_buffer - 1);
+			int i, start;
 
-			/* Is the inode bitmap in cache? */
-			desc = ext4_get_group_desc(inode->i_sb,
-						block_group, NULL);
-			if (!desc)
-				goto make_io;
+			start = inode_offset & ~(inodes_per_block - 1);
 
-			bitmap_bh = sb_getblk(inode->i_sb,
-				ext4_inode_bitmap(inode->i_sb, desc));
+			/* Is the inode bitmap in cache? */
+			bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
 			if (!bitmap_bh)
 				goto make_io;
 
@@ -3791,14 +3890,14 @@ static int __ext4_get_inode_loc(struct inode *inode,
 				brelse(bitmap_bh);
 				goto make_io;
 			}
-			for (i = start; i < start + inodes_per_buffer; i++) {
+			for (i = start; i < start + inodes_per_block; i++) {
 				if (i == inode_offset)
 					continue;
 				if (ext4_test_bit(i, bitmap_bh->b_data))
 					break;
 			}
 			brelse(bitmap_bh);
-			if (i == start + inodes_per_buffer) {
+			if (i == start + inodes_per_block) {
 				/* all other inodes are free, so skip I/O */
 				memset(bh->b_data, 0, bh->b_size);
 				set_buffer_uptodate(bh);
@@ -3808,6 +3907,36 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		}
 
 make_io:
+		/*
+		 * If we need to do any I/O, try to pre-readahead extra
+		 * blocks from the inode table.
+		 */
+		if (EXT4_SB(sb)->s_inode_readahead_blks) {
+			ext4_fsblk_t b, end, table;
+			unsigned num;
+
+			table = ext4_inode_table(sb, gdp);
+			/* Make sure s_inode_readahead_blks is a power of 2 */
+			while (EXT4_SB(sb)->s_inode_readahead_blks &
+			       (EXT4_SB(sb)->s_inode_readahead_blks-1))
+				EXT4_SB(sb)->s_inode_readahead_blks = 
+				   (EXT4_SB(sb)->s_inode_readahead_blks &
+				    (EXT4_SB(sb)->s_inode_readahead_blks-1));
+			b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
+			if (table > b)
+				b = table;
+			end = b + EXT4_SB(sb)->s_inode_readahead_blks;
+			num = EXT4_INODES_PER_GROUP(sb);
+			if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+				num -= le16_to_cpu(gdp->bg_itable_unused);
+			table += num / inodes_per_block;
+			if (end > table)
+				end = table;
+			while (b <= end)
+				sb_breadahead(sb, b++);
+		}
+
 		/*
 		 * There are other valid inodes in the buffer, this inode
 		 * has in-inode xattrs, or we don't have this inode in memory.
@@ -3818,10 +3947,9 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		submit_bh(READ_META, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			ext4_error(inode->i_sb, "ext4_get_inode_loc",
-					"unable to read inode block - "
-					"inode=%lu, block=%llu",
-					inode->i_ino, block);
+			ext4_error(sb, __func__,
+				   "unable to read inode block - inode=%lu, "
+				   "block=%llu", inode->i_ino, block);
 			brelse(bh);
 			return -EIO;
 		}
@@ -3913,11 +4041,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		return inode;
 
 	ei = EXT4_I(inode);
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	ei->i_acl = EXT4_ACL_NOT_CACHED;
 	ei->i_default_acl = EXT4_ACL_NOT_CACHED;
 #endif
-	ei->i_block_alloc_info = NULL;
 
 	ret = __ext4_get_inode_loc(inode, &iloc, 0);
 	if (ret < 0)
@@ -3927,7 +4054,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
 	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
 	inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
-	if(!(test_opt (inode->i_sb, NO_UID32))) {
+	if (!(test_opt(inode->i_sb, NO_UID32))) {
 		inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
 		inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
@@ -3945,7 +4072,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		if (inode->i_mode == 0 ||
 		    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
 			/* this inode is deleted */
-			brelse (bh);
+			brelse(bh);
 			ret = -ESTALE;
 			goto bad_inode;
 		}
@@ -3978,7 +4105,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
 		if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
 		    EXT4_INODE_SIZE(inode->i_sb)) {
-			brelse (bh);
+			brelse(bh);
 			ret = -EIO;
 			goto bad_inode;
 		}
@@ -4031,7 +4158,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 			init_special_inode(inode, inode->i_mode,
 			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
 	}
-	brelse (iloc.bh);
+	brelse(iloc.bh);
 	ext4_set_inode_flags(inode);
 	unlock_new_inode(inode);
 	return inode;
@@ -4113,14 +4240,14 @@ static int ext4_do_update_inode(handle_t *handle,
 
 	ext4_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
-	if(!(test_opt(inode->i_sb, NO_UID32))) {
+	if (!(test_opt(inode->i_sb, NO_UID32))) {
 		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
 		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
 /*
  * Fix up interoperability with old kernels. Otherwise, old inodes get
  * re-used with the upper 16 bits of the uid/gid intact
  */
-		if(!ei->i_dtime) {
+		if (!ei->i_dtime) {
 			raw_inode->i_uid_high =
 				cpu_to_le16(high_16_bits(inode->i_uid));
 			raw_inode->i_gid_high =
@@ -4208,7 +4335,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	ei->i_state &= ~EXT4_STATE_NEW;
 
 out_brelse:
-	brelse (bh);
+	brelse(bh);
 	ext4_std_error(inode->i_sb, err);
 	return err;
 }
@@ -4811,6 +4938,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 	loff_t size;
 	unsigned long len;
 	int ret = -EINVAL;
+	void *fsdata;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
@@ -4849,11 +4977,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 	 * on the same page though
 	 */
 	ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
-			len, AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+			len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
 	if (ret < 0)
 		goto out_unlock;
 	ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
-			len, len, page, NULL);
+			len, len, page, fsdata);
 	if (ret < 0)
 		goto out_unlock;
 	ret = 0;

fs/ext4/ioctl.c

@@ -23,9 +23,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
-	unsigned short rsv_window_size;
 
-	ext4_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+	ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
 
 	switch (cmd) {
 	case EXT4_IOC_GETFLAGS:
@@ -34,7 +33,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return put_user(flags, (int __user *) arg);
 	case EXT4_IOC_SETFLAGS: {
 		handle_t *handle = NULL;
-		int err;
+		int err, migrate = 0;
 		struct ext4_iloc iloc;
 		unsigned int oldflags;
 		unsigned int jflag;
@@ -82,6 +81,17 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			if (!capable(CAP_SYS_RESOURCE))
 				goto flags_out;
 		}
+		if (oldflags & EXT4_EXTENTS_FL) {
+			/* We don't support clearning extent flags */
+			if (!(flags & EXT4_EXTENTS_FL)) {
+				err = -EOPNOTSUPP;
+				goto flags_out;
+			}
+		} else if (flags & EXT4_EXTENTS_FL) {
+			/* migrate the file */
+			migrate = 1;
+			flags &= ~EXT4_EXTENTS_FL;
+		}
 
 		handle = ext4_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
@@ -109,6 +119,10 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
 			err = ext4_change_inode_journal_flag(inode, jflag);
+		if (err)
+			goto flags_out;
+		if (migrate)
+			err = ext4_ext_migrate(inode);
 flags_out:
 		mutex_unlock(&inode->i_mutex);
 		mnt_drop_write(filp->f_path.mnt);
@@ -175,49 +189,6 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return ret;
 		}
 #endif
-	case EXT4_IOC_GETRSVSZ:
-		if (test_opt(inode->i_sb, RESERVATION)
-			&& S_ISREG(inode->i_mode)
-			&& ei->i_block_alloc_info) {
-			rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
-			return put_user(rsv_window_size, (int __user *)arg);
-		}
-		return -ENOTTY;
-	case EXT4_IOC_SETRSVSZ: {
-		int err;
-
-		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
-			return -ENOTTY;
-
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
-
-		if (get_user(rsv_window_size, (int __user *)arg))
-			return -EFAULT;
-
-		err = mnt_want_write(filp->f_path.mnt);
-		if (err)
-			return err;
-
-		if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS)
-			rsv_window_size = EXT4_MAX_RESERVE_BLOCKS;
-
-		/*
-		 * need to allocate reservation structure for this inode
-		 * before set the window size
-		 */
-		down_write(&ei->i_data_sem);
-		if (!ei->i_block_alloc_info)
-			ext4_init_block_alloc_info(inode);
-
-		if (ei->i_block_alloc_info){
-			struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
-			rsv->rsv_goal_size = rsv_window_size;
-		}
-		up_write(&ei->i_data_sem);
-		mnt_drop_write(filp->f_path.mnt);
-		return 0;
-	}
 	case EXT4_IOC_GROUP_EXTEND: {
 		ext4_fsblk_t n_blocks_count;
 		struct super_block *sb = inode->i_sb;
@@ -267,7 +238,26 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 
 	case EXT4_IOC_MIGRATE:
-		return ext4_ext_migrate(inode, filp, cmd, arg);
+	{
+		int err;
+		if (!is_owner_or_cap(inode))
+			return -EACCES;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+		/*
+		 * inode_mutex prevent write and truncate on the file.
+		 * Read still goes through. We take i_data_sem in
+		 * ext4_ext_swap_inode_data before we switch the
+		 * inode format to prevent read.
+		 */
+		mutex_lock(&(inode->i_mutex));
+		err = ext4_ext_migrate(inode);
+		mutex_unlock(&(inode->i_mutex));
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	}
 
 	default:
 		return -ENOTTY;

fs/ext4/mballoc.c

@@ -477,9 +477,10 @@ static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap)
 		b2 = (unsigned char *) bitmap;
 		for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
 			if (b1[i] != b2[i]) {
-				printk("corruption in group %lu at byte %u(%u):"
-				       " %x in copy != %x on disk/prealloc\n",
-					e4b->bd_group, i, i * 8, b1[i], b2[i]);
+				printk(KERN_ERR "corruption in group %lu "
+				       "at byte %u(%u): %x in copy != %x "
+				       "on disk/prealloc\n",
+				       e4b->bd_group, i, i * 8, b1[i], b2[i]);
 				BUG();
 			}
 		}
@@ -533,9 +534,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	void *buddy;
 	void *buddy2;
 
-	if (!test_opt(sb, MBALLOC))
-		return 0;
-
 	{
 		static int mb_check_counter;
 		if (mb_check_counter++ % 100 != 0)
@@ -784,9 +782,11 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 		if (bh[i] == NULL)
 			goto out;
 
-		if (bh_uptodate_or_lock(bh[i]))
+		if (buffer_uptodate(bh[i]) &&
+		    !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
 			continue;
 
+		lock_buffer(bh[i]);
 		spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
 		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			ext4_init_block_bitmap(sb, bh[i],
@@ -2169,9 +2169,10 @@ static void ext4_mb_history_release(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	remove_proc_entry("mb_groups", sbi->s_mb_proc);
-	remove_proc_entry("mb_history", sbi->s_mb_proc);
-
+	if (sbi->s_proc != NULL) {
+		remove_proc_entry("mb_groups", sbi->s_proc);
+		remove_proc_entry("mb_history", sbi->s_proc);
+	}
 	kfree(sbi->s_mb_history);
 }
 
@@ -2180,10 +2181,10 @@ static void ext4_mb_history_init(struct super_block *sb)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int i;
 
-	if (sbi->s_mb_proc != NULL) {
-		proc_create_data("mb_history", S_IRUGO, sbi->s_mb_proc,
+	if (sbi->s_proc != NULL) {
+		proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
 				 &ext4_mb_seq_history_fops, sb);
-		proc_create_data("mb_groups", S_IRUGO, sbi->s_mb_proc,
+		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
 				 &ext4_mb_seq_groups_fops, sb);
 	}
 
@@ -2485,19 +2486,14 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	unsigned max;
 	int ret;
 
-	if (!test_opt(sb, MBALLOC))
-		return 0;
-
 	i = (sb->s_blocksize_bits + 2) * sizeof(unsigned short);
 
 	sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
 	if (sbi->s_mb_offsets == NULL) {
-		clear_opt(sbi->s_mount_opt, MBALLOC);
 		return -ENOMEM;
 	}
 	sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
 	if (sbi->s_mb_maxs == NULL) {
-		clear_opt(sbi->s_mount_opt, MBALLOC);
 		kfree(sbi->s_mb_maxs);
 		return -ENOMEM;
 	}
@@ -2520,7 +2516,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	/* init file for buddy data */
 	ret = ext4_mb_init_backend(sb);
 	if (ret != 0) {
-		clear_opt(sbi->s_mount_opt, MBALLOC);
 		kfree(sbi->s_mb_offsets);
 		kfree(sbi->s_mb_maxs);
 		return ret;
@@ -2540,17 +2535,15 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT;
 	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
 
-	i = sizeof(struct ext4_locality_group) * nr_cpu_ids;
-	sbi->s_locality_groups = kmalloc(i, GFP_KERNEL);
+	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
 	if (sbi->s_locality_groups == NULL) {
-		clear_opt(sbi->s_mount_opt, MBALLOC);
 		kfree(sbi->s_mb_offsets);
 		kfree(sbi->s_mb_maxs);
 		return -ENOMEM;
 	}
-	for (i = 0; i < nr_cpu_ids; i++) {
+	for_each_possible_cpu(i) {
 		struct ext4_locality_group *lg;
-		lg = &sbi->s_locality_groups[i];
+		lg = per_cpu_ptr(sbi->s_locality_groups, i);
 		mutex_init(&lg->lg_mutex);
 		for (j = 0; j < PREALLOC_TB_SIZE; j++)
 			INIT_LIST_HEAD(&lg->lg_prealloc_list[j]);
@@ -2560,7 +2553,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	ext4_mb_init_per_dev_proc(sb);
 	ext4_mb_history_init(sb);
 
-	printk("EXT4-fs: mballoc enabled\n");
+	printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
 	return 0;
 }
 
@@ -2589,9 +2582,6 @@ int ext4_mb_release(struct super_block *sb)
 	struct ext4_group_info *grinfo;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!test_opt(sb, MBALLOC))
-		return 0;
-
 	/* release freed, non-committed blocks */
 	spin_lock(&sbi->s_md_lock);
 	list_splice_init(&sbi->s_closed_transaction,
@@ -2647,8 +2637,7 @@ int ext4_mb_release(struct super_block *sb)
 				atomic_read(&sbi->s_mb_discarded));
 	}
 
-	kfree(sbi->s_locality_groups);
-
+	free_percpu(sbi->s_locality_groups);
 	ext4_mb_history_release(sb);
 	ext4_mb_destroy_per_dev_proc(sb);
 
@@ -2721,118 +2710,46 @@ ext4_mb_free_committed_blocks(struct super_block *sb)
 #define EXT4_MB_STREAM_REQ		"stream_req"
 #define EXT4_MB_GROUP_PREALLOC		"group_prealloc"
 
-
-
-#define MB_PROC_FOPS(name)					\
-static int ext4_mb_##name##_proc_show(struct seq_file *m, void *v)	\
-{								\
-	struct ext4_sb_info *sbi = m->private;			\
-								\
-	seq_printf(m, "%ld\n", sbi->s_mb_##name);		\
-	return 0;						\
-}								\
-								\
-static int ext4_mb_##name##_proc_open(struct inode *inode, struct file *file)\
-{								\
-	return single_open(file, ext4_mb_##name##_proc_show, PDE(inode)->data);\
-}								\
-								\
-static ssize_t ext4_mb_##name##_proc_write(struct file *file,	\
-		const char __user *buf, size_t cnt, loff_t *ppos)	\
-{								\
-	struct ext4_sb_info *sbi = PDE(file->f_path.dentry->d_inode)->data;\
-	char str[32];						\
-	long value;						\
-	if (cnt >= sizeof(str))					\
-		return -EINVAL;					\
-	if (copy_from_user(str, buf, cnt))			\
-		return -EFAULT;					\
-	value = simple_strtol(str, NULL, 0);			\
-	if (value <= 0)						\
-		return -ERANGE;					\
-	sbi->s_mb_##name = value;				\
-	return cnt;						\
-}								\
-								\
-static const struct file_operations ext4_mb_##name##_proc_fops = {	\
-	.owner		= THIS_MODULE,				\
-	.open		= ext4_mb_##name##_proc_open,		\
-	.read		= seq_read,				\
-	.llseek		= seq_lseek,				\
-	.release	= single_release,			\
-	.write		= ext4_mb_##name##_proc_write,		\
-};
-
-MB_PROC_FOPS(stats);
-MB_PROC_FOPS(max_to_scan);
-MB_PROC_FOPS(min_to_scan);
-MB_PROC_FOPS(order2_reqs);
-MB_PROC_FOPS(stream_request);
-MB_PROC_FOPS(group_prealloc);
-
-#define	MB_PROC_HANDLER(name, var)					\
-do {									\
-	proc = proc_create_data(name, mode, sbi->s_mb_proc,		\
-				&ext4_mb_##var##_proc_fops, sbi);	\
-	if (proc == NULL) {						\
-		printk(KERN_ERR "EXT4-fs: can't to create %s\n", name);	\
-		goto err_out;						\
-	}								\
-} while (0)
-
 static int ext4_mb_init_per_dev_proc(struct super_block *sb)
 {
 	mode_t mode = S_IFREG | S_IRUGO | S_IWUSR;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct proc_dir_entry *proc;
-	char devname[64];
 
-	if (proc_root_ext4 == NULL) {
-		sbi->s_mb_proc = NULL;
+	if (sbi->s_proc == NULL)
 		return -EINVAL;
-	}
-	bdevname(sb->s_bdev, devname);
-	sbi->s_mb_proc = proc_mkdir(devname, proc_root_ext4);
-
-	MB_PROC_HANDLER(EXT4_MB_STATS_NAME, stats);
-	MB_PROC_HANDLER(EXT4_MB_MAX_TO_SCAN_NAME, max_to_scan);
-	MB_PROC_HANDLER(EXT4_MB_MIN_TO_SCAN_NAME, min_to_scan);
-	MB_PROC_HANDLER(EXT4_MB_ORDER2_REQ, order2_reqs);
-	MB_PROC_HANDLER(EXT4_MB_STREAM_REQ, stream_request);
-	MB_PROC_HANDLER(EXT4_MB_GROUP_PREALLOC, group_prealloc);
 
+	EXT4_PROC_HANDLER(EXT4_MB_STATS_NAME, mb_stats);
+	EXT4_PROC_HANDLER(EXT4_MB_MAX_TO_SCAN_NAME, mb_max_to_scan);
+	EXT4_PROC_HANDLER(EXT4_MB_MIN_TO_SCAN_NAME, mb_min_to_scan);
+	EXT4_PROC_HANDLER(EXT4_MB_ORDER2_REQ, mb_order2_reqs);
+	EXT4_PROC_HANDLER(EXT4_MB_STREAM_REQ, mb_stream_request);
+	EXT4_PROC_HANDLER(EXT4_MB_GROUP_PREALLOC, mb_group_prealloc);
 	return 0;
 
 err_out:
-	printk(KERN_ERR "EXT4-fs: Unable to create %s\n", devname);
-	remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_mb_proc);
-	remove_proc_entry(devname, proc_root_ext4);
-	sbi->s_mb_proc = NULL;
-
+	remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
 	return -ENOMEM;
 }
 
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	char devname[64];
 
-	if (sbi->s_mb_proc == NULL)
+	if (sbi->s_proc == NULL)
 		return -EINVAL;
 
-	bdevname(sb->s_bdev, devname);
-	remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_mb_proc);
-	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_mb_proc);
-	remove_proc_entry(devname, proc_root_ext4);
+	remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
+	remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
 
 	return 0;
 }
@@ -2854,11 +2771,6 @@ int __init init_ext4_mballoc(void)
 		kmem_cache_destroy(ext4_pspace_cachep);
 		return -ENOMEM;
 	}
-#ifdef CONFIG_PROC_FS
-	proc_root_ext4 = proc_mkdir("fs/ext4", NULL);
-	if (proc_root_ext4 == NULL)
-		printk(KERN_ERR "EXT4-fs: Unable to create fs/ext4\n");
-#endif
 	return 0;
 }
 
@@ -2867,9 +2779,6 @@ void exit_ext4_mballoc(void)
 	/* XXX: synchronize_rcu(); */
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
-#ifdef CONFIG_PROC_FS
-	remove_proc_entry("fs/ext4", NULL);
-#endif
 }
 
 
@@ -2879,7 +2788,7 @@ void exit_ext4_mballoc(void)
  */
 static noinline_for_stack int
 ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
-				handle_t *handle)
+				handle_t *handle, unsigned long reserv_blks)
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct ext4_super_block *es;
@@ -2968,15 +2877,16 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
 	spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-
+	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
 	/*
-	 * free blocks account has already be reduced/reserved
-	 * at write_begin() time for delayed allocation
-	 * do not double accounting
+	 * Now reduce the dirty block count also. Should not go negative
 	 */
 	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
-		percpu_counter_sub(&sbi->s_freeblocks_counter,
-					ac->ac_b_ex.fe_len);
+		/* release all the reserved blocks if non delalloc */
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+	else
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+						ac->ac_b_ex.fe_len);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -3884,7 +3794,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_mb_discard_inode_preallocations(struct inode *inode)
+void ext4_discard_preallocations(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -3896,7 +3806,7 @@ void ext4_mb_discard_inode_preallocations(struct inode *inode)
 	struct ext4_buddy e4b;
 	int err;
 
-	if (!test_opt(sb, MBALLOC) || !S_ISREG(inode->i_mode)) {
+	if (!S_ISREG(inode->i_mode)) {
 		/*BUG_ON(!list_empty(&ei->i_prealloc_list));*/
 		return;
 	}
@@ -4094,8 +4004,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	 * per cpu locality group is to reduce the contention between block
 	 * request from multiple CPUs.
 	 */
-	ac->ac_lg = &sbi->s_locality_groups[get_cpu()];
-	put_cpu();
+	ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
 
 	/* we're going to use group allocation */
 	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
@@ -4369,33 +4278,32 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
 ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 				 struct ext4_allocation_request *ar, int *errp)
 {
+	int freed;
 	struct ext4_allocation_context *ac = NULL;
 	struct ext4_sb_info *sbi;
 	struct super_block *sb;
 	ext4_fsblk_t block = 0;
-	int freed;
-	int inquota;
+	unsigned long inquota;
+	unsigned long reserv_blks = 0;
 
 	sb = ar->inode->i_sb;
 	sbi = EXT4_SB(sb);
 
-	if (!test_opt(sb, MBALLOC)) {
-		block = ext4_old_new_blocks(handle, ar->inode, ar->goal,
-					    &(ar->len), errp);
-		return block;
-	}
 	if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) {
 		/*
 		 * With delalloc we already reserved the blocks
 		 */
-		ar->len = ext4_has_free_blocks(sbi, ar->len);
-	}
-
-	if (ar->len == 0) {
-		*errp = -ENOSPC;
-		return 0;
+		while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+			/* let others to free the space */
+			yield();
+			ar->len = ar->len >> 1;
+		}
+		if (!ar->len) {
+			*errp = -ENOSPC;
+			return 0;
+		}
+		reserv_blks = ar->len;
 	}
-
 	while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
 		ar->flags |= EXT4_MB_HINT_NOPREALLOC;
 		ar->len--;
@@ -4441,7 +4349,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
-		*errp = ext4_mb_mark_diskspace_used(ac, handle);
+		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
 		if (*errp ==  -EAGAIN) {
 			ac->ac_b_ex.fe_group = 0;
 			ac->ac_b_ex.fe_start = 0;

fs/ext4/mballoc.h

@@ -257,7 +257,6 @@ static void ext4_mb_store_history(struct ext4_allocation_context *ac);
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
-static struct proc_dir_entry *proc_root_ext4;
 struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
 
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,

fs/ext4/migrate.c

@@ -447,8 +447,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 
 }
 
-int ext4_ext_migrate(struct inode *inode, struct file *filp,
-				unsigned int cmd, unsigned long arg)
+int ext4_ext_migrate(struct inode *inode)
 {
 	handle_t *handle;
 	int retval = 0, i;
@@ -515,12 +514,6 @@ int ext4_ext_migrate(struct inode *inode, struct file *filp,
 	 * trascation that created the inode. Later as and
 	 * when we add extents we extent the journal
 	 */
-	/*
-	 * inode_mutex prevent write and truncate on the file. Read still goes
-	 * through. We take i_data_sem in ext4_ext_swap_inode_data before we
-	 * switch the inode format to prevent read.
-	 */
-	mutex_lock(&(inode->i_mutex));
 	/*
 	 * Even though we take i_mutex we can still cause block allocation
 	 * via mmap write to holes. If we have allocated new blocks we fail
@@ -623,7 +616,6 @@ int ext4_ext_migrate(struct inode *inode, struct file *filp,
 	tmp_inode->i_nlink = 0;
 
 	ext4_journal_stop(handle);
-	mutex_unlock(&(inode->i_mutex));
 
 	if (tmp_inode)
 		iput(tmp_inode);

fs/ext4/namei.c

@@ -151,34 +151,36 @@ struct dx_map_entry
 
 static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
 static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
-static inline unsigned dx_get_hash (struct dx_entry *entry);
-static void dx_set_hash (struct dx_entry *entry, unsigned value);
-static unsigned dx_get_count (struct dx_entry *entries);
-static unsigned dx_get_limit (struct dx_entry *entries);
-static void dx_set_count (struct dx_entry *entries, unsigned value);
-static void dx_set_limit (struct dx_entry *entries, unsigned value);
-static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
-static unsigned dx_node_limit (struct inode *dir);
-static struct dx_frame *dx_probe(struct dentry *dentry,
+static inline unsigned dx_get_hash(struct dx_entry *entry);
+static void dx_set_hash(struct dx_entry *entry, unsigned value);
+static unsigned dx_get_count(struct dx_entry *entries);
+static unsigned dx_get_limit(struct dx_entry *entries);
+static void dx_set_count(struct dx_entry *entries, unsigned value);
+static void dx_set_limit(struct dx_entry *entries, unsigned value);
+static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
+static unsigned dx_node_limit(struct inode *dir);
+static struct dx_frame *dx_probe(const struct qstr *d_name,
 				 struct inode *dir,
 				 struct dx_hash_info *hinfo,
 				 struct dx_frame *frame,
 				 int *err);
-static void dx_release (struct dx_frame *frames);
-static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
-			struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static void dx_release(struct dx_frame *frames);
+static int dx_make_map(struct ext4_dir_entry_2 *de, int size,
+		       struct dx_hash_info *hinfo, struct dx_map_entry map[]);
 static void dx_sort_map(struct dx_map_entry *map, unsigned count);
-static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to,
+static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
 		struct dx_map_entry *offsets, int count);
-static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size);
 static void dx_insert_block(struct dx_frame *frame,
 					u32 hash, ext4_lblk_t block);
 static int ext4_htree_next_block(struct inode *dir, __u32 hash,
 				 struct dx_frame *frame,
 				 struct dx_frame *frames,
 				 __u32 *start_hash);
-static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
-		       struct ext4_dir_entry_2 **res_dir, int *err);
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
+		const struct qstr *d_name,
+		struct ext4_dir_entry_2 **res_dir,
+		int *err);
 static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode);
 
@@ -207,44 +209,44 @@ static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
 	entry->block = cpu_to_le32(value);
 }
 
-static inline unsigned dx_get_hash (struct dx_entry *entry)
+static inline unsigned dx_get_hash(struct dx_entry *entry)
 {
 	return le32_to_cpu(entry->hash);
 }
 
-static inline void dx_set_hash (struct dx_entry *entry, unsigned value)
+static inline void dx_set_hash(struct dx_entry *entry, unsigned value)
 {
 	entry->hash = cpu_to_le32(value);
 }
 
-static inline unsigned dx_get_count (struct dx_entry *entries)
+static inline unsigned dx_get_count(struct dx_entry *entries)
 {
 	return le16_to_cpu(((struct dx_countlimit *) entries)->count);
 }
 
-static inline unsigned dx_get_limit (struct dx_entry *entries)
+static inline unsigned dx_get_limit(struct dx_entry *entries)
 {
 	return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
 }
 
-static inline void dx_set_count (struct dx_entry *entries, unsigned value)
+static inline void dx_set_count(struct dx_entry *entries, unsigned value)
 {
 	((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
 }
 
-static inline void dx_set_limit (struct dx_entry *entries, unsigned value)
+static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
 {
 	((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
 }
 
-static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
+static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
 		EXT4_DIR_REC_LEN(2) - infosize;
 	return entry_space / sizeof(struct dx_entry);
 }
 
-static inline unsigned dx_node_limit (struct inode *dir)
+static inline unsigned dx_node_limit(struct inode *dir)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
 	return entry_space / sizeof(struct dx_entry);
@@ -254,12 +256,12 @@ static inline unsigned dx_node_limit (struct inode *dir)
  * Debug
  */
 #ifdef DX_DEBUG
-static void dx_show_index (char * label, struct dx_entry *entries)
+static void dx_show_index(char * label, struct dx_entry *entries)
 {
 	int i, n = dx_get_count (entries);
-	printk("%s index ", label);
+	printk(KERN_DEBUG "%s index ", label);
 	for (i = 0; i < n; i++) {
-		printk("%x->%lu ", i? dx_get_hash(entries + i) :
+		printk("%x->%lu ", i ? dx_get_hash(entries + i) :
 				0, (unsigned long)dx_get_block(entries + i));
 	}
 	printk("\n");
@@ -306,7 +308,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
 			     struct dx_entry *entries, int levels)
 {
 	unsigned blocksize = dir->i_sb->s_blocksize;
-	unsigned count = dx_get_count (entries), names = 0, space = 0, i;
+	unsigned count = dx_get_count(entries), names = 0, space = 0, i;
 	unsigned bcount = 0;
 	struct buffer_head *bh;
 	int err;
@@ -325,11 +327,12 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
 		names += stats.names;
 		space += stats.space;
 		bcount += stats.bcount;
-		brelse (bh);
+		brelse(bh);
 	}
 	if (bcount)
-		printk("%snames %u, fullness %u (%u%%)\n", levels?"":"   ",
-			names, space/bcount,(space/bcount)*100/blocksize);
+		printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n", 
+		       levels ? "" : "   ", names, space/bcount,
+		       (space/bcount)*100/blocksize);
 	return (struct stats) { names, space, bcount};
 }
 #endif /* DX_DEBUG */
@@ -344,7 +347,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
  * back to userspace.
  */
 static struct dx_frame *
-dx_probe(struct dentry *dentry, struct inode *dir,
+dx_probe(const struct qstr *d_name, struct inode *dir,
 	 struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
 {
 	unsigned count, indirect;
@@ -355,8 +358,6 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	u32 hash;
 
 	frame->bh = NULL;
-	if (dentry)
-		dir = dentry->d_parent->d_inode;
 	if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
 		goto fail;
 	root = (struct dx_root *) bh->b_data;
@@ -372,8 +373,8 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	}
 	hinfo->hash_version = root->info.hash_version;
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
-	if (dentry)
-		ext4fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);
+	if (d_name)
+		ext4fs_dirhash(d_name->name, d_name->len, hinfo);
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
@@ -406,7 +407,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 		goto fail;
 	}
 
-	dxtrace (printk("Look up %x", hash));
+	dxtrace(printk("Look up %x", hash));
 	while (1)
 	{
 		count = dx_get_count(entries);
@@ -555,7 +556,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
 				      0, &err)))
 			return err; /* Failure */
 		p++;
-		brelse (p->bh);
+		brelse(p->bh);
 		p->bh = bh;
 		p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
 	}
@@ -593,7 +594,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 			/* On error, skip the f_pos to the next block. */
 			dir_file->f_pos = (dir_file->f_pos |
 					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse (bh);
+			brelse(bh);
 			return count;
 		}
 		ext4fs_dirhash(de->name, de->name_len, hinfo);
@@ -635,8 +636,8 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	int ret, err;
 	__u32 hashval;
 
-	dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
-		       start_minor_hash));
+	dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n", 
+		       start_hash, start_minor_hash));
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
 		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
@@ -648,7 +649,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	}
 	hinfo.hash = start_hash;
 	hinfo.minor_hash = 0;
-	frame = dx_probe(NULL, dir_file->f_path.dentry->d_inode, &hinfo, frames, &err);
+	frame = dx_probe(NULL, dir, &hinfo, frames, &err);
 	if (!frame)
 		return err;
 
@@ -694,8 +695,8 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 			break;
 	}
 	dx_release(frames);
-	dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n",
-		       count, *next_hash));
+	dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, "
+		       "next hash: %x\n", count, *next_hash));
 	return count;
 errout:
 	dx_release(frames);
@@ -802,17 +803,17 @@ static inline int ext4_match (int len, const char * const name,
 /*
  * Returns 0 if not found, -1 on failure, and 1 on success
  */
-static inline int search_dirblock(struct buffer_head * bh,
+static inline int search_dirblock(struct buffer_head *bh,
 				  struct inode *dir,
-				  struct dentry *dentry,
+				  const struct qstr *d_name,
 				  unsigned long offset,
 				  struct ext4_dir_entry_2 ** res_dir)
 {
 	struct ext4_dir_entry_2 * de;
 	char * dlimit;
 	int de_len;
-	const char *name = dentry->d_name.name;
-	int namelen = dentry->d_name.len;
+	const char *name = d_name->name;
+	int namelen = d_name->len;
 
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	dlimit = bh->b_data + dir->i_sb->s_blocksize;
@@ -851,12 +852,13 @@ static inline int search_dirblock(struct buffer_head * bh,
  * The returned buffer_head has ->b_count elevated.  The caller is expected
  * to brelse() it when appropriate.
  */
-static struct buffer_head * ext4_find_entry (struct dentry *dentry,
+static struct buffer_head * ext4_find_entry (struct inode *dir,
+					const struct qstr *d_name,
 					struct ext4_dir_entry_2 ** res_dir)
 {
-	struct super_block * sb;
-	struct buffer_head * bh_use[NAMEI_RA_SIZE];
-	struct buffer_head * bh, *ret = NULL;
+	struct super_block *sb;
+	struct buffer_head *bh_use[NAMEI_RA_SIZE];
+	struct buffer_head *bh, *ret = NULL;
 	ext4_lblk_t start, block, b;
 	int ra_max = 0;		/* Number of bh's in the readahead
 				   buffer, bh_use[] */
@@ -865,16 +867,15 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 	int num = 0;
 	ext4_lblk_t  nblocks;
 	int i, err;
-	struct inode *dir = dentry->d_parent->d_inode;
 	int namelen;
 
 	*res_dir = NULL;
 	sb = dir->i_sb;
-	namelen = dentry->d_name.len;
+	namelen = d_name->len;
 	if (namelen > EXT4_NAME_LEN)
 		return NULL;
 	if (is_dx(dir)) {
-		bh = ext4_dx_find_entry(dentry, res_dir, &err);
+		bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
 		/*
 		 * On success, or if the error was file not found,
 		 * return.  Otherwise, fall back to doing a search the
@@ -882,7 +883,8 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 		 */
 		if (bh || (err != ERR_BAD_DX_DIR))
 			return bh;
-		dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
+		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+			       "falling back\n"));
 	}
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	start = EXT4_I(dir)->i_dir_start_lookup;
@@ -926,7 +928,7 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 			brelse(bh);
 			goto next;
 		}
-		i = search_dirblock(bh, dir, dentry,
+		i = search_dirblock(bh, dir, d_name,
 			    block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
 		if (i == 1) {
 			EXT4_I(dir)->i_dir_start_lookup = block;
@@ -956,11 +958,11 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 cleanup_and_exit:
 	/* Clean up the read-ahead blocks */
 	for (; ra_ptr < ra_max; ra_ptr++)
-		brelse (bh_use[ra_ptr]);
+		brelse(bh_use[ra_ptr]);
 	return ret;
 }
 
-static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
 		       struct ext4_dir_entry_2 **res_dir, int *err)
 {
 	struct super_block * sb;
@@ -971,14 +973,13 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 	struct buffer_head *bh;
 	ext4_lblk_t block;
 	int retval;
-	int namelen = dentry->d_name.len;
-	const u8 *name = dentry->d_name.name;
-	struct inode *dir = dentry->d_parent->d_inode;
+	int namelen = d_name->len;
+	const u8 *name = d_name->name;
 
 	sb = dir->i_sb;
 	/* NFS may look up ".." - look at dx_root directory block */
 	if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){
-		if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err)))
+		if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
 			return NULL;
 	} else {
 		frame = frames;
@@ -1010,7 +1011,7 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 				return bh;
 			}
 		}
-		brelse (bh);
+		brelse(bh);
 		/* Check to see if we should continue to search */
 		retval = ext4_htree_next_block(dir, hash, frame,
 					       frames, NULL);
@@ -1025,25 +1026,25 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 
 	*err = -ENOENT;
 errout:
-	dxtrace(printk("%s not found\n", name));
+	dxtrace(printk(KERN_DEBUG "%s not found\n", name));
 	dx_release (frames);
 	return NULL;
 }
 
-static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
-	struct inode * inode;
-	struct ext4_dir_entry_2 * de;
-	struct buffer_head * bh;
+	struct inode *inode;
+	struct ext4_dir_entry_2 *de;
+	struct buffer_head *bh;
 
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	bh = ext4_find_entry(dentry, &de);
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
 	inode = NULL;
 	if (bh) {
 		unsigned long ino = le32_to_cpu(de->inode);
-		brelse (bh);
+		brelse(bh);
 		if (!ext4_valid_inum(dir->i_sb, ino)) {
 			ext4_error(dir->i_sb, "ext4_lookup",
 				   "bad inode number: %lu", ino);
@@ -1062,15 +1063,14 @@ struct dentry *ext4_get_parent(struct dentry *child)
 	unsigned long ino;
 	struct dentry *parent;
 	struct inode *inode;
-	struct dentry dotdot;
+	static const struct qstr dotdot = {
+		.name = "..",
+		.len = 2,
+	};
 	struct ext4_dir_entry_2 * de;
 	struct buffer_head *bh;
 
-	dotdot.d_name.name = "..";
-	dotdot.d_name.len = 2;
-	dotdot.d_parent = child; /* confusing, isn't it! */
-
-	bh = ext4_find_entry(&dotdot, &de);
+	bh = ext4_find_entry(child->d_inode, &dotdot, &de);
 	inode = NULL;
 	if (!bh)
 		return ERR_PTR(-ENOENT);
@@ -1201,10 +1201,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 
 	/* create map in the end of data2 block */
 	map = (struct dx_map_entry *) (data2 + blocksize);
-	count = dx_make_map ((struct ext4_dir_entry_2 *) data1,
+	count = dx_make_map((struct ext4_dir_entry_2 *) data1,
 			     blocksize, hinfo, map);
 	map -= count;
-	dx_sort_map (map, count);
+	dx_sort_map(map, count);
 	/* Split the existing block in the middle, size-wise */
 	size = 0;
 	move = 0;
@@ -1225,7 +1225,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 
 	/* Fancy dance to stay within two buffers */
 	de2 = dx_move_dirents(data1, data2, map + split, count - split);
-	de = dx_pack_dirents(data1,blocksize);
+	de = dx_pack_dirents(data1, blocksize);
 	de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
 	de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2);
 	dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
@@ -1237,15 +1237,15 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		swap(*bh, bh2);
 		de = de2;
 	}
-	dx_insert_block (frame, hash2 + continued, newblock);
-	err = ext4_journal_dirty_metadata (handle, bh2);
+	dx_insert_block(frame, hash2 + continued, newblock);
+	err = ext4_journal_dirty_metadata(handle, bh2);
 	if (err)
 		goto journal_error;
-	err = ext4_journal_dirty_metadata (handle, frame->bh);
+	err = ext4_journal_dirty_metadata(handle, frame->bh);
 	if (err)
 		goto journal_error;
-	brelse (bh2);
-	dxtrace(dx_show_index ("frame", frame->entries));
+	brelse(bh2);
+	dxtrace(dx_show_index("frame", frame->entries));
 	return de;
 
 journal_error:
@@ -1271,7 +1271,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
  */
 static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode, struct ext4_dir_entry_2 *de,
-			     struct buffer_head * bh)
+			     struct buffer_head *bh)
 {
 	struct inode	*dir = dentry->d_parent->d_inode;
 	const char	*name = dentry->d_name.name;
@@ -1288,11 +1288,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 		while ((char *) de <= top) {
 			if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
 						  bh, offset)) {
-				brelse (bh);
+				brelse(bh);
 				return -EIO;
 			}
-			if (ext4_match (namelen, name, de)) {
-				brelse (bh);
+			if (ext4_match(namelen, name, de)) {
+				brelse(bh);
 				return -EEXIST;
 			}
 			nlen = EXT4_DIR_REC_LEN(de->name_len);
@@ -1329,7 +1329,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	} else
 		de->inode = 0;
 	de->name_len = namelen;
-	memcpy (de->name, name, namelen);
+	memcpy(de->name, name, namelen);
 	/*
 	 * XXX shouldn't update any times until successful
 	 * completion of syscall, but too many callers depend
@@ -1377,7 +1377,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	struct fake_dirent *fde;
 
 	blocksize =  dir->i_sb->s_blocksize;
-	dxtrace(printk("Creating index\n"));
+	dxtrace(printk(KERN_DEBUG "Creating index\n"));
 	retval = ext4_journal_get_write_access(handle, bh);
 	if (retval) {
 		ext4_std_error(dir->i_sb, retval);
@@ -1386,7 +1386,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	}
 	root = (struct dx_root *) bh->b_data;
 
-	bh2 = ext4_append (handle, dir, &block, &retval);
+	bh2 = ext4_append(handle, dir, &block, &retval);
 	if (!(bh2)) {
 		brelse(bh);
 		return retval;
@@ -1412,9 +1412,9 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	root->info.info_length = sizeof(root->info);
 	root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
 	entries = root->entries;
-	dx_set_block (entries, 1);
-	dx_set_count (entries, 1);
-	dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info)));
+	dx_set_block(entries, 1);
+	dx_set_count(entries, 1);
+	dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
@@ -1443,14 +1443,14 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
  * may not sleep between calling this and putting something into
  * the entry, as someone else might have used it while you slept.
  */
-static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
-	struct inode *inode)
+static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
+			  struct inode *inode)
 {
 	struct inode *dir = dentry->d_parent->d_inode;
 	unsigned long offset;
-	struct buffer_head * bh;
+	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
-	struct super_block * sb;
+	struct super_block *sb;
 	int	retval;
 	int	dx_fallback=0;
 	unsigned blocksize;
@@ -1500,13 +1500,13 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	struct dx_frame frames[2], *frame;
 	struct dx_entry *entries, *at;
 	struct dx_hash_info hinfo;
-	struct buffer_head * bh;
+	struct buffer_head *bh;
 	struct inode *dir = dentry->d_parent->d_inode;
-	struct super_block * sb = dir->i_sb;
+	struct super_block *sb = dir->i_sb;
 	struct ext4_dir_entry_2 *de;
 	int err;
 
-	frame = dx_probe(dentry, NULL, &hinfo, frames, &err);
+	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
 	if (!frame)
 		return err;
 	entries = frame->entries;
@@ -1527,7 +1527,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	}
 
 	/* Block full, should compress but for now just split */
-	dxtrace(printk("using %u of %u node entries\n",
+	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
 		       dx_get_count(entries), dx_get_limit(entries)));
 	/* Need to split index? */
 	if (dx_get_count(entries) == dx_get_limit(entries)) {
@@ -1559,7 +1559,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 		if (levels) {
 			unsigned icount1 = icount/2, icount2 = icount - icount1;
 			unsigned hash2 = dx_get_hash(entries + icount1);
-			dxtrace(printk("Split index %i/%i\n", icount1, icount2));
+			dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
+				       icount1, icount2));
 
 			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
 			err = ext4_journal_get_write_access(handle,
@@ -1567,11 +1568,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 
-			memcpy ((char *) entries2, (char *) (entries + icount1),
-				icount2 * sizeof(struct dx_entry));
-			dx_set_count (entries, icount1);
-			dx_set_count (entries2, icount2);
-			dx_set_limit (entries2, dx_node_limit(dir));
+			memcpy((char *) entries2, (char *) (entries + icount1),
+			       icount2 * sizeof(struct dx_entry));
+			dx_set_count(entries, icount1);
+			dx_set_count(entries2, icount2);
+			dx_set_limit(entries2, dx_node_limit(dir));
 
 			/* Which index block gets the new entry? */
 			if (at - entries >= icount1) {
@@ -1579,16 +1580,17 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 				frame->entries = entries = entries2;
 				swap(frame->bh, bh2);
 			}
-			dx_insert_block (frames + 0, hash2, newblock);
-			dxtrace(dx_show_index ("node", frames[1].entries));
-			dxtrace(dx_show_index ("node",
+			dx_insert_block(frames + 0, hash2, newblock);
+			dxtrace(dx_show_index("node", frames[1].entries));
+			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
 			err = ext4_journal_dirty_metadata(handle, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
 		} else {
-			dxtrace(printk("Creating second level index...\n"));
+			dxtrace(printk(KERN_DEBUG
+				       "Creating second level index...\n"));
 			memcpy((char *) entries2, (char *) entries,
 			       icount * sizeof(struct dx_entry));
 			dx_set_limit(entries2, dx_node_limit(dir));
@@ -1630,12 +1632,12 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
  * ext4_delete_entry deletes a directory entry by merging it with the
  * previous entry
  */
-static int ext4_delete_entry (handle_t *handle,
-			      struct inode * dir,
-			      struct ext4_dir_entry_2 * de_del,
-			      struct buffer_head * bh)
+static int ext4_delete_entry(handle_t *handle,
+			     struct inode *dir,
+			     struct ext4_dir_entry_2 *de_del,
+			     struct buffer_head *bh)
 {
-	struct ext4_dir_entry_2 * de, * pde;
+	struct ext4_dir_entry_2 *de, *pde;
 	int i;
 
 	i = 0;
@@ -1716,11 +1718,11 @@ static int ext4_add_nondir(handle_t *handle,
  * If the create succeeds, we fill in the inode information
  * with d_instantiate().
  */
-static int ext4_create (struct inode * dir, struct dentry * dentry, int mode,
-		struct nameidata *nd)
+static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
+		       struct nameidata *nd)
 {
 	handle_t *handle;
-	struct inode * inode;
+	struct inode *inode;
 	int err, retries = 0;
 
 retry:
@@ -1747,8 +1749,8 @@ static int ext4_create (struct inode * dir, struct dentry * dentry, int mode,
 	return err;
 }
 
-static int ext4_mknod (struct inode * dir, struct dentry *dentry,
-			int mode, dev_t rdev)
+static int ext4_mknod(struct inode *dir, struct dentry *dentry,
+		      int mode, dev_t rdev)
 {
 	handle_t *handle;
 	struct inode *inode;
@@ -1767,11 +1769,11 @@ static int ext4_mknod (struct inode * dir, struct dentry *dentry,
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext4_new_inode (handle, dir, mode);
+	inode = ext4_new_inode(handle, dir, mode);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 		inode->i_op = &ext4_special_inode_operations;
 #endif
 		err = ext4_add_nondir(handle, dentry, inode);
@@ -1782,12 +1784,12 @@ static int ext4_mknod (struct inode * dir, struct dentry *dentry,
 	return err;
 }
 
-static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
 	handle_t *handle;
-	struct inode * inode;
-	struct buffer_head * dir_block;
-	struct ext4_dir_entry_2 * de;
+	struct inode *inode;
+	struct buffer_head *dir_block;
+	struct ext4_dir_entry_2 *de;
 	int err, retries = 0;
 
 	if (EXT4_DIR_LINK_MAX(dir))
@@ -1803,7 +1805,7 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext4_new_inode (handle, dir, S_IFDIR | mode);
+	inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
@@ -1811,7 +1813,7 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 	inode->i_op = &ext4_dir_inode_operations;
 	inode->i_fop = &ext4_dir_operations;
 	inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
-	dir_block = ext4_bread (handle, inode, 0, 1, &err);
+	dir_block = ext4_bread(handle, inode, 0, 1, &err);
 	if (!dir_block)
 		goto out_clear_inode;
 	BUFFER_TRACE(dir_block, "get_write_access");
@@ -1820,26 +1822,26 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 	de->inode = cpu_to_le32(inode->i_ino);
 	de->name_len = 1;
 	de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len));
-	strcpy (de->name, ".");
+	strcpy(de->name, ".");
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	de = ext4_next_entry(de);
 	de->inode = cpu_to_le32(dir->i_ino);
 	de->rec_len = ext4_rec_len_to_disk(inode->i_sb->s_blocksize -
 						EXT4_DIR_REC_LEN(1));
 	de->name_len = 2;
-	strcpy (de->name, "..");
+	strcpy(de->name, "..");
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
 	ext4_journal_dirty_metadata(handle, dir_block);
-	brelse (dir_block);
+	brelse(dir_block);
 	ext4_mark_inode_dirty(handle, inode);
-	err = ext4_add_entry (handle, dentry, inode);
+	err = ext4_add_entry(handle, dentry, inode);
 	if (err) {
 out_clear_inode:
 		clear_nlink(inode);
 		ext4_mark_inode_dirty(handle, inode);
-		iput (inode);
+		iput(inode);
 		goto out_stop;
 	}
 	ext4_inc_count(handle, dir);
@@ -1856,17 +1858,17 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 /*
  * routine to check that the specified directory is empty (for rmdir)
  */
-static int empty_dir (struct inode * inode)
+static int empty_dir(struct inode *inode)
 {
 	unsigned long offset;
-	struct buffer_head * bh;
-	struct ext4_dir_entry_2 * de, * de1;
-	struct super_block * sb;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de, *de1;
+	struct super_block *sb;
 	int err = 0;
 
 	sb = inode->i_sb;
 	if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
-	    !(bh = ext4_bread (NULL, inode, 0, 0, &err))) {
+	    !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
 		if (err)
 			ext4_error(inode->i_sb, __func__,
 				   "error %d reading directory #%lu offset 0",
@@ -1881,23 +1883,23 @@ static int empty_dir (struct inode * inode)
 	de1 = ext4_next_entry(de);
 	if (le32_to_cpu(de->inode) != inode->i_ino ||
 			!le32_to_cpu(de1->inode) ||
-			strcmp (".", de->name) ||
-			strcmp ("..", de1->name)) {
-		ext4_warning (inode->i_sb, "empty_dir",
-			      "bad directory (dir #%lu) - no `.' or `..'",
-			      inode->i_ino);
-		brelse (bh);
+			strcmp(".", de->name) ||
+			strcmp("..", de1->name)) {
+		ext4_warning(inode->i_sb, "empty_dir",
+			     "bad directory (dir #%lu) - no `.' or `..'",
+			     inode->i_ino);
+		brelse(bh);
 		return 1;
 	}
 	offset = ext4_rec_len_from_disk(de->rec_len) +
 		 ext4_rec_len_from_disk(de1->rec_len);
 	de = ext4_next_entry(de1);
-	while (offset < inode->i_size ) {
+	while (offset < inode->i_size) {
 		if (!bh ||
 			(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
 			err = 0;
-			brelse (bh);
-			bh = ext4_bread (NULL, inode,
+			brelse(bh);
+			bh = ext4_bread(NULL, inode,
 				offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
 			if (!bh) {
 				if (err)
@@ -1917,13 +1919,13 @@ static int empty_dir (struct inode * inode)
 			continue;
 		}
 		if (le32_to_cpu(de->inode)) {
-			brelse (bh);
+			brelse(bh);
 			return 0;
 		}
 		offset += ext4_rec_len_from_disk(de->rec_len);
 		de = ext4_next_entry(de);
 	}
-	brelse (bh);
+	brelse(bh);
 	return 1;
 }
 
@@ -1954,8 +1956,8 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	 * ->i_nlink. For, say it, character device. Not a regular file,
 	 * not a directory, not a symlink and ->i_nlink > 0.
 	 */
-	J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
 
 	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
@@ -2069,12 +2071,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	goto out_err;
 }
 
-static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
+static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int retval;
-	struct inode * inode;
-	struct buffer_head * bh;
-	struct ext4_dir_entry_2 * de;
+	struct inode *inode;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
 	handle_t *handle;
 
 	/* Initialize quotas before so that eventual writes go in
@@ -2085,7 +2087,7 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
 		return PTR_ERR(handle);
 
 	retval = -ENOENT;
-	bh = ext4_find_entry (dentry, &de);
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
 	if (!bh)
 		goto end_rmdir;
 
@@ -2099,16 +2101,16 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
 		goto end_rmdir;
 
 	retval = -ENOTEMPTY;
-	if (!empty_dir (inode))
+	if (!empty_dir(inode))
 		goto end_rmdir;
 
 	retval = ext4_delete_entry(handle, dir, de, bh);
 	if (retval)
 		goto end_rmdir;
 	if (!EXT4_DIR_LINK_EMPTY(inode))
-		ext4_warning (inode->i_sb, "ext4_rmdir",
-			      "empty directory has too many links (%d)",
-			      inode->i_nlink);
+		ext4_warning(inode->i_sb, "ext4_rmdir",
+			     "empty directory has too many links (%d)",
+			     inode->i_nlink);
 	inode->i_version++;
 	clear_nlink(inode);
 	/* There's no need to set i_disksize: the fact that i_nlink is
@@ -2124,16 +2126,16 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
 
 end_rmdir:
 	ext4_journal_stop(handle);
-	brelse (bh);
+	brelse(bh);
 	return retval;
 }
 
-static int ext4_unlink(struct inode * dir, struct dentry *dentry)
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int retval;
-	struct inode * inode;
-	struct buffer_head * bh;
-	struct ext4_dir_entry_2 * de;
+	struct inode *inode;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
 	handle_t *handle;
 
 	/* Initialize quotas before so that eventual writes go
@@ -2147,7 +2149,7 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
 		handle->h_sync = 1;
 
 	retval = -ENOENT;
-	bh = ext4_find_entry (dentry, &de);
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
 	if (!bh)
 		goto end_unlink;
 
@@ -2158,9 +2160,9 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
 		goto end_unlink;
 
 	if (!inode->i_nlink) {
-		ext4_warning (inode->i_sb, "ext4_unlink",
-			      "Deleting nonexistent file (%lu), %d",
-			      inode->i_ino, inode->i_nlink);
+		ext4_warning(inode->i_sb, "ext4_unlink",
+			     "Deleting nonexistent file (%lu), %d",
+			     inode->i_ino, inode->i_nlink);
 		inode->i_nlink = 1;
 	}
 	retval = ext4_delete_entry(handle, dir, de, bh);
@@ -2178,15 +2180,15 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
 
 end_unlink:
 	ext4_journal_stop(handle);
-	brelse (bh);
+	brelse(bh);
 	return retval;
 }
 
-static int ext4_symlink (struct inode * dir,
-		struct dentry *dentry, const char * symname)
+static int ext4_symlink(struct inode *dir,
+			struct dentry *dentry, const char *symname)
 {
 	handle_t *handle;
-	struct inode * inode;
+	struct inode *inode;
 	int l, err, retries = 0;
 
 	l = strlen(symname)+1;
@@ -2203,12 +2205,12 @@ static int ext4_symlink (struct inode * dir,
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext4_new_inode (handle, dir, S_IFLNK|S_IRWXUGO);
+	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
 
-	if (l > sizeof (EXT4_I(inode)->i_data)) {
+	if (l > sizeof(EXT4_I(inode)->i_data)) {
 		inode->i_op = &ext4_symlink_inode_operations;
 		ext4_set_aops(inode);
 		/*
@@ -2221,14 +2223,14 @@ static int ext4_symlink (struct inode * dir,
 		if (err) {
 			clear_nlink(inode);
 			ext4_mark_inode_dirty(handle, inode);
-			iput (inode);
+			iput(inode);
 			goto out_stop;
 		}
 	} else {
 		/* clear the extent format for fast symlink */
 		EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
 		inode->i_op = &ext4_fast_symlink_inode_operations;
-		memcpy((char*)&EXT4_I(inode)->i_data,symname,l);
+		memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
 		inode->i_size = l-1;
 	}
 	EXT4_I(inode)->i_disksize = inode->i_size;
@@ -2240,8 +2242,8 @@ static int ext4_symlink (struct inode * dir,
 	return err;
 }
 
-static int ext4_link (struct dentry * old_dentry,
-		struct inode * dir, struct dentry *dentry)
+static int ext4_link(struct dentry *old_dentry,
+		     struct inode *dir, struct dentry *dentry)
 {
 	handle_t *handle;
 	struct inode *inode = old_dentry->d_inode;
@@ -2284,13 +2286,13 @@ static int ext4_link (struct dentry * old_dentry,
  * Anybody can rename anything with this: the permission checks are left to the
  * higher-level routines.
  */
-static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
-			   struct inode * new_dir,struct dentry *new_dentry)
+static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
+		       struct inode *new_dir, struct dentry *new_dentry)
 {
 	handle_t *handle;
-	struct inode * old_inode, * new_inode;
-	struct buffer_head * old_bh, * new_bh, * dir_bh;
-	struct ext4_dir_entry_2 * old_de, * new_de;
+	struct inode *old_inode, *new_inode;
+	struct buffer_head *old_bh, *new_bh, *dir_bh;
+	struct ext4_dir_entry_2 *old_de, *new_de;
 	int retval;
 
 	old_bh = new_bh = dir_bh = NULL;
@@ -2308,7 +2310,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
 		handle->h_sync = 1;
 
-	old_bh = ext4_find_entry (old_dentry, &old_de);
+	old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -2321,32 +2323,32 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
 		goto end_rename;
 
 	new_inode = new_dentry->d_inode;
-	new_bh = ext4_find_entry (new_dentry, &new_de);
+	new_bh = ext4_find_entry(new_dir, &new_dentry->d_name, &new_de);
 	if (new_bh) {
 		if (!new_inode) {
-			brelse (new_bh);
+			brelse(new_bh);
 			new_bh = NULL;
 		}
 	}
 	if (S_ISDIR(old_inode->i_mode)) {
 		if (new_inode) {
 			retval = -ENOTEMPTY;
-			if (!empty_dir (new_inode))
+			if (!empty_dir(new_inode))
 				goto end_rename;
 		}
 		retval = -EIO;
-		dir_bh = ext4_bread (handle, old_inode, 0, 0, &retval);
+		dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
 		if (!dir_bh)
 			goto end_rename;
 		if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
 			goto end_rename;
 		retval = -EMLINK;
-		if (!new_inode && new_dir!=old_dir &&
+		if (!new_inode && new_dir != old_dir &&
 				new_dir->i_nlink >= EXT4_LINK_MAX)
 			goto end_rename;
 	}
 	if (!new_bh) {
-		retval = ext4_add_entry (handle, new_dentry, old_inode);
+		retval = ext4_add_entry(handle, new_dentry, old_inode);
 		if (retval)
 			goto end_rename;
 	} else {
@@ -2388,7 +2390,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
 		struct buffer_head *old_bh2;
 		struct ext4_dir_entry_2 *old_de2;
 
-		old_bh2 = ext4_find_entry(old_dentry, &old_de2);
+		old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de2);
 		if (old_bh2) {
 			retval = ext4_delete_entry(handle, old_dir,
 						   old_de2, old_bh2);
@@ -2433,9 +2435,9 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
 	retval = 0;
 
 end_rename:
-	brelse (dir_bh);
-	brelse (old_bh);
-	brelse (new_bh);
+	brelse(dir_bh);
+	brelse(old_bh);
+	brelse(new_bh);
 	ext4_journal_stop(handle);
 	return retval;
 }
@@ -2454,7 +2456,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.mknod		= ext4_mknod,
 	.rename		= ext4_rename,
 	.setattr	= ext4_setattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
@@ -2465,7 +2467,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 
 const struct inode_operations ext4_special_inode_operations = {
 	.setattr	= ext4_setattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,

fs/ext4/resize.c

@@ -416,8 +416,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
 		       gdb_num);
 
-        /*
-         * If we are not using the primary superblock/GDT copy don't resize,
+	/*
+	 * If we are not using the primary superblock/GDT copy don't resize,
          * because the user tools have no way of handling this.  Probably a
          * bad time to do it anyways.
          */
@@ -870,11 +870,10 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	 * We can allocate memory for mb_alloc based on the new group
 	 * descriptor
 	 */
-	if (test_opt(sb, MBALLOC)) {
-		err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
-		if (err)
-			goto exit_journal;
-	}
+	err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
+	if (err)
+		goto exit_journal;
+
 	/*
 	 * Make the new blocks and inodes valid next.  We do this before
 	 * increasing the group count so that once the group is enabled,
@@ -929,6 +928,15 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb));
 
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		ext4_group_t flex_group;
+		flex_group = ext4_flex_group(sbi, input->group);
+		sbi->s_flex_groups[flex_group].free_blocks +=
+			input->free_blocks_count;
+		sbi->s_flex_groups[flex_group].free_inodes +=
+			EXT4_INODES_PER_GROUP(sb);
+	}
+
 	ext4_journal_dirty_metadata(handle, sbi->s_sbh);
 	sb->s_dirt = 1;
 
@@ -964,7 +972,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	ext4_group_t o_groups_count;
 	ext4_grpblk_t last;
 	ext4_grpblk_t add;
-	struct buffer_head * bh;
+	struct buffer_head *bh;
 	handle_t *handle;
 	int err;
 	unsigned long freed_blocks;
@@ -1077,8 +1085,15 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	/*
 	 * Mark mballoc pages as not up to date so that they will be updated
 	 * next time they are loaded by ext4_mb_load_buddy.
+	 *
+	 * XXX Bad, Bad, BAD!!!  We should not be overloading the
+	 * Uptodate flag, particularly on thte bitmap bh, as way of
+	 * hinting to ext4_mb_load_buddy() that it needs to be
+	 * overloaded.  A user could take a LVM snapshot, then do an
+	 * on-line fsck, and clear the uptodate flag, and this would
+	 * not be a bug in userspace, but a bug in the kernel.  FIXME!!!
 	 */
-	if (test_opt(sb, MBALLOC)) {
+	{
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		struct inode *inode = sbi->s_buddy_cache;
 		int blocks_per_page;

fs/ext4/super.c

@@ -34,6 +34,8 @@
 #include <linux/namei.h>
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/marker.h>
 #include <linux/log2.h>
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
@@ -45,6 +47,8 @@
 #include "namei.h"
 #include "group.h"
 
+struct proc_dir_entry *ext4_proc_root;
+
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
 static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
@@ -508,10 +512,12 @@ static void ext4_put_super(struct super_block *sb)
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
-		BUFFER_TRACE(sbi->s_sbh, "marking dirty");
-		mark_buffer_dirty(sbi->s_sbh);
 		ext4_commit_super(sb, es, 1);
 	}
+	if (sbi->s_proc) {
+		remove_proc_entry("inode_readahead_blks", sbi->s_proc);
+		remove_proc_entry(sb->s_id, ext4_proc_root);
+	}
 
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(sbi->s_group_desc[i]);
@@ -520,6 +526,7 @@ static void ext4_put_super(struct super_block *sb)
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
@@ -562,11 +569,10 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
 	if (!ei)
 		return NULL;
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	ei->i_acl = EXT4_ACL_NOT_CACHED;
 	ei->i_default_acl = EXT4_ACL_NOT_CACHED;
 #endif
-	ei->i_block_alloc_info = NULL;
 	ei->vfs_inode.i_version = 1;
 	ei->vfs_inode.i_data.writeback_index = 0;
 	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
@@ -599,7 +605,7 @@ static void init_once(void *foo)
 	struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
 
 	INIT_LIST_HEAD(&ei->i_orphan);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	init_rwsem(&ei->xattr_sem);
 #endif
 	init_rwsem(&ei->i_data_sem);
@@ -625,8 +631,7 @@ static void destroy_inodecache(void)
 
 static void ext4_clear_inode(struct inode *inode)
 {
-	struct ext4_block_alloc_info *rsv = EXT4_I(inode)->i_block_alloc_info;
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	if (EXT4_I(inode)->i_acl &&
 			EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) {
 		posix_acl_release(EXT4_I(inode)->i_acl);
@@ -638,10 +643,7 @@ static void ext4_clear_inode(struct inode *inode)
 		EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED;
 	}
 #endif
-	ext4_discard_reservation(inode);
-	EXT4_I(inode)->i_block_alloc_info = NULL;
-	if (unlikely(rsv))
-		kfree(rsv);
+	ext4_discard_preallocations(inode);
 	jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
 				       &EXT4_I(inode)->jinode);
 }
@@ -654,7 +656,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
 
 	if (sbi->s_jquota_fmt)
 		seq_printf(seq, ",jqfmt=%s",
-		(sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
+		(sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
 
 	if (sbi->s_qf_names[USRQUOTA])
 		seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
@@ -718,7 +720,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",debug");
 	if (test_opt(sb, OLDALLOC))
 		seq_puts(seq, ",oldalloc");
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	if (test_opt(sb, XATTR_USER) &&
 		!(def_mount_opts & EXT4_DEFM_XATTR_USER))
 		seq_puts(seq, ",user_xattr");
@@ -727,7 +729,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nouser_xattr");
 	}
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
 		seq_puts(seq, ",acl");
 	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
@@ -752,8 +754,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nobh");
 	if (!test_opt(sb, EXTENTS))
 		seq_puts(seq, ",noextents");
-	if (!test_opt(sb, MBALLOC))
-		seq_puts(seq, ",nomballoc");
 	if (test_opt(sb, I_VERSION))
 		seq_puts(seq, ",i_version");
 	if (!test_opt(sb, DELALLOC))
@@ -773,6 +773,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
 		seq_puts(seq, ",data=writeback");
 
+	if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
+		seq_printf(seq, ",inode_readahead_blks=%u",
+			   sbi->s_inode_readahead_blks);
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -822,7 +826,7 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
 }
 
 #ifdef CONFIG_QUOTA
-#define QTYPE2NAME(t) ((t) == USRQUOTA?"user":"group")
+#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
 #define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
 
 static int ext4_dquot_initialize(struct inode *inode, int type);
@@ -907,6 +911,7 @@ enum {
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
 	Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
 	Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+	Opt_inode_readahead_blks
 };
 
 static match_table_t tokens = {
@@ -967,6 +972,7 @@ static match_table_t tokens = {
 	{Opt_resize, "resize"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_nodelalloc, "nodelalloc"},
+	{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
 	{Opt_err, NULL},
 };
 
@@ -981,7 +987,7 @@ static ext4_fsblk_t get_sb_block(void **data)
 	/*todo: use simple_strtoll with >32bit ext4 */
 	sb_block = simple_strtoul(options, &options, 0);
 	if (*options && *options != ',') {
-		printk("EXT4-fs: Invalid sb specification: %s\n",
+		printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
 		       (char *) *data);
 		return 1;
 	}
@@ -1072,7 +1078,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_orlov:
 			clear_opt(sbi->s_mount_opt, OLDALLOC);
 			break;
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 		case Opt_user_xattr:
 			set_opt(sbi->s_mount_opt, XATTR_USER);
 			break;
@@ -1082,10 +1088,11 @@ static int parse_options(char *options, struct super_block *sb,
 #else
 		case Opt_user_xattr:
 		case Opt_nouser_xattr:
-			printk("EXT4 (no)user_xattr options not supported\n");
+			printk(KERN_ERR "EXT4 (no)user_xattr options "
+			       "not supported\n");
 			break;
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 		case Opt_acl:
 			set_opt(sbi->s_mount_opt, POSIX_ACL);
 			break;
@@ -1095,7 +1102,8 @@ static int parse_options(char *options, struct super_block *sb,
 #else
 		case Opt_acl:
 		case Opt_noacl:
-			printk("EXT4 (no)acl options not supported\n");
+			printk(KERN_ERR "EXT4 (no)acl options "
+			       "not supported\n");
 			break;
 #endif
 		case Opt_reservation:
@@ -1189,8 +1197,8 @@ static int parse_options(char *options, struct super_block *sb,
 			     sb_any_quota_suspended(sb)) &&
 			    !sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR
-					"EXT4-fs: Cannot change journaled "
-					"quota options when quota turned on.\n");
+				       "EXT4-fs: Cannot change journaled "
+				       "quota options when quota turned on.\n");
 				return 0;
 			}
 			qname = match_strdup(&args[0]);
@@ -1357,12 +1365,6 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_nodelalloc:
 			clear_opt(sbi->s_mount_opt, DELALLOC);
 			break;
-		case Opt_mballoc:
-			set_opt(sbi->s_mount_opt, MBALLOC);
-			break;
-		case Opt_nomballoc:
-			clear_opt(sbi->s_mount_opt, MBALLOC);
-			break;
 		case Opt_stripe:
 			if (match_int(&args[0], &option))
 				return 0;
@@ -1373,6 +1375,13 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_delalloc:
 			set_opt(sbi->s_mount_opt, DELALLOC);
 			break;
+		case Opt_inode_readahead_blks:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0 || option > (1 << 30))
+				return 0;
+			sbi->s_inode_readahead_blks = option;
+			break;
 		default:
 			printk(KERN_ERR
 			       "EXT4-fs: Unrecognized mount option \"%s\" "
@@ -1473,15 +1482,9 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			EXT4_INODES_PER_GROUP(sb),
 			sbi->s_mount_opt);
 
-	printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id);
-	if (EXT4_SB(sb)->s_journal->j_inode == NULL) {
-		char b[BDEVNAME_SIZE];
-
-		printk("external journal on %s\n",
-			bdevname(EXT4_SB(sb)->s_journal->j_dev, b));
-	} else {
-		printk("internal journal\n");
-	}
+	printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
+	       sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+	       "external", EXT4_SB(sb)->s_journal->j_devname);
 	return res;
 }
 
@@ -1504,8 +1507,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
 	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
-	flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
-		groups_per_flex;
+	/* We allocate both existing and potentially added groups */
+	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
+			    ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
+			      EXT4_DESC_PER_BLOCK_BITS(sb))) /
+			   groups_per_flex;
 	sbi->s_flex_groups = kzalloc(flex_group_count *
 				     sizeof(struct flex_groups), GFP_KERNEL);
 	if (sbi->s_flex_groups == NULL) {
@@ -1584,7 +1590,7 @@ static int ext4_check_descriptors(struct super_block *sb)
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		flexbg_flag = 1;
 
-	ext4_debug ("Checking group descriptors");
+	ext4_debug("Checking group descriptors");
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
 		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
@@ -1623,8 +1629,10 @@ static int ext4_check_descriptors(struct super_block *sb)
 			       "Checksum for group %lu failed (%u!=%u)\n",
 			       i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
 			       gdp)), le16_to_cpu(gdp->bg_checksum));
-			if (!(sb->s_flags & MS_RDONLY))
+			if (!(sb->s_flags & MS_RDONLY)) {
+				spin_unlock(sb_bgl_lock(sbi, i));
 				return 0;
+			}
 		}
 		spin_unlock(sb_bgl_lock(sbi, i));
 		if (!flexbg_flag)
@@ -1714,9 +1722,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		DQUOT_INIT(inode);
 		if (inode->i_nlink) {
 			printk(KERN_DEBUG
-				"%s: truncating inode %lu to %Ld bytes\n",
+				"%s: truncating inode %lu to %lld bytes\n",
 				__func__, inode->i_ino, inode->i_size);
-			jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
+			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
 			ext4_truncate(inode);
 			nr_truncates++;
@@ -1914,6 +1922,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned long journal_devnum = 0;
 	unsigned long def_mount_opts;
 	struct inode *root;
+	char *cp;
 	int ret = -EINVAL;
 	int blocksize;
 	int db_count;
@@ -1930,10 +1939,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_mount_opt = 0;
 	sbi->s_resuid = EXT4_DEF_RESUID;
 	sbi->s_resgid = EXT4_DEF_RESGID;
+	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sb_block = sb_block;
 
 	unlock_kernel();
 
+	/* Cleanup superblock name */
+	for (cp = sb->s_id; (cp = strchr(cp, '/'));)
+		*cp = '!';
+
 	blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
 	if (!blocksize) {
 		printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
@@ -1973,11 +1987,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		set_opt(sbi->s_mount_opt, GRPID);
 	if (def_mount_opts & EXT4_DEFM_UID16)
 		set_opt(sbi->s_mount_opt, NO_UID32);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	if (def_mount_opts & EXT4_DEFM_XATTR_USER)
 		set_opt(sbi->s_mount_opt, XATTR_USER);
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	if (def_mount_opts & EXT4_DEFM_ACL)
 		set_opt(sbi->s_mount_opt, POSIX_ACL);
 #endif
@@ -2012,11 +2026,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		ext4_warning(sb, __func__,
 			"extents feature not enabled on this filesystem, "
 			"use tune2fs.\n");
-	/*
-	 * turn on mballoc code by default in ext4 filesystem
-	 * Use -o nomballoc to turn it off
-	 */
-	set_opt(sbi->s_mount_opt, MBALLOC);
 
 	/*
 	 * enable delayed allocation by default
@@ -2040,16 +2049,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		       "EXT4-fs warning: feature flags set on rev 0 fs, "
 		       "running e2fsck is recommended\n");
 
-	/*
-	 * Since ext4 is still considered development code, we require
-	 * that the TEST_FILESYS flag in s->flags be set.
-	 */
-	if (!(le32_to_cpu(es->s_flags) & EXT2_FLAGS_TEST_FILESYS)) {
-		printk(KERN_WARNING "EXT4-fs: %s: not marked "
-		       "OK to use with test code.\n", sb->s_id);
-		goto failed_mount;
-	}
-
 	/*
 	 * Check feature flags regardless of the revision level, since we
 	 * previously didn't change the revision level when setting the flags,
@@ -2219,6 +2218,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (ext4_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
+
+	if (sbi->s_proc)
+		proc_create_data("inode_readahead_blks", 0644, sbi->s_proc,
+				 &ext4_ui_proc_fops,
+				 &sbi->s_inode_readahead_blks);
+
 	bgl_lock_init(&sbi->s_blockgroup_lock);
 
 	for (i = 0; i < db_count; i++) {
@@ -2257,24 +2264,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		err = percpu_counter_init(&sbi->s_dirs_counter,
 				ext4_count_dirs(sb));
 	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+	}
 	if (err) {
 		printk(KERN_ERR "EXT4-fs: insufficient memory\n");
 		goto failed_mount3;
 	}
 
-	/* per fileystem reservation list head & lock */
-	spin_lock_init(&sbi->s_rsv_window_lock);
-	sbi->s_rsv_window_root = RB_ROOT;
-	/* Add a single, static dummy reservation to the start of the
-	 * reservation window list --- it gives us a placeholder for
-	 * append-at-start-of-list which makes the allocation logic
-	 * _much_ simpler. */
-	sbi->s_rsv_window_head.rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-	sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
-	sbi->s_rsv_window_head.rsv_goal_size = 0;
-	ext4_rsv_window_add(sb, &sbi->s_rsv_window_head);
-
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 
 	/*
@@ -2471,7 +2468,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
 
 	ext4_ext_init(sb);
-	ext4_mb_init(sb, needs_recovery);
+	err = ext4_mb_init(sb, needs_recovery);
+	if (err) {
+		printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
+		       err);
+		goto failed_mount4;
+	}
 
 	lock_kernel();
 	return 0;
@@ -2489,11 +2491,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	kfree(sbi->s_group_desc);
 failed_mount:
+	if (sbi->s_proc) {
+		remove_proc_entry("inode_readahead_blks", sbi->s_proc);
+		remove_proc_entry(sb->s_id, ext4_proc_root);
+	}
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
@@ -2552,7 +2559,7 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 		return NULL;
 	}
 
-	jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
+	jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
 		  journal_inode, journal_inode->i_size);
 	if (!S_ISREG(journal_inode->i_mode)) {
 		printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
@@ -2715,6 +2722,11 @@ static int ext4_load_journal(struct super_block *sb,
 			return -EINVAL;
 	}
 
+	if (journal->j_flags & JBD2_BARRIER)
+		printk(KERN_INFO "EXT4-fs: barriers enabled\n");
+	else
+		printk(KERN_INFO "EXT4-fs: barriers disabled\n");
+
 	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
 		err = jbd2_journal_update_format(journal);
 		if (err)  {
@@ -2799,13 +2811,34 @@ static void ext4_commit_super(struct super_block *sb,
 
 	if (!sbh)
 		return;
+	if (buffer_write_io_error(sbh)) {
+		/*
+		 * Oh, dear.  A previous attempt to write the
+		 * superblock failed.  This could happen because the
+		 * USB device was yanked out.  Or it could happen to
+		 * be a transient write error and maybe the block will
+		 * be remapped.  Nothing we can do but to retry the
+		 * write and hope for the best.
+		 */
+		printk(KERN_ERR "ext4: previous I/O error to "
+		       "superblock detected for %s.\n", sb->s_id);
+		clear_buffer_write_io_error(sbh);
+		set_buffer_uptodate(sbh);
+	}
 	es->s_wtime = cpu_to_le32(get_seconds());
 	ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb));
 	es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
 	BUFFER_TRACE(sbh, "marking dirty");
 	mark_buffer_dirty(sbh);
-	if (sync)
+	if (sync) {
 		sync_dirty_buffer(sbh);
+		if (buffer_write_io_error(sbh)) {
+			printk(KERN_ERR "ext4: I/O error while writing "
+			       "superblock for %s.\n", sb->s_id);
+			clear_buffer_write_io_error(sbh);
+			set_buffer_uptodate(sbh);
+		}
+	}
 }
 
 
@@ -2907,6 +2940,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 {
 	tid_t target;
 
+	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
 	sb->s_dirt = 0;
 	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
 		if (wait)
@@ -3162,7 +3196,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_type = EXT4_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
-	buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+	buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
 	ext4_free_blocks_count_set(es, buf->f_bfree);
 	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
 	if (buf->f_bfree < ext4_r_blocks_count(es))
@@ -3432,7 +3467,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	handle_t *handle = journal_current_handle();
 
 	if (!handle) {
-		printk(KERN_WARNING "EXT4-fs: Quota write (off=%Lu, len=%Lu)"
+		printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
 			" cancelled because transaction is not started.\n",
 			(unsigned long long)off, (unsigned long long)len);
 		return -EIO;
@@ -3493,18 +3528,82 @@ static int ext4_get_sb(struct file_system_type *fs_type,
 	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
 }
 
+#ifdef CONFIG_PROC_FS
+static int ext4_ui_proc_show(struct seq_file *m, void *v)
+{
+	unsigned int *p = m->private;
+
+	seq_printf(m, "%u\n", *p);
+	return 0;
+}
+
+static int ext4_ui_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ext4_ui_proc_show, PDE(inode)->data);
+}
+
+static ssize_t ext4_ui_proc_write(struct file *file, const char __user *buf,
+			       size_t cnt, loff_t *ppos)
+{
+	unsigned int *p = PDE(file->f_path.dentry->d_inode)->data;
+	char str[32];
+	unsigned long value;
+
+	if (cnt >= sizeof(str))
+		return -EINVAL;
+	if (copy_from_user(str, buf, cnt))
+		return -EFAULT;
+	value = simple_strtol(str, NULL, 0);
+	if (value < 0)
+		return -ERANGE;
+	*p = value;
+	return cnt;
+}
+
+const struct file_operations ext4_ui_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ext4_ui_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= ext4_ui_proc_write,
+};
+#endif
+
+static struct file_system_type ext4_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext4",
+	.get_sb		= ext4_get_sb,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+
+#ifdef CONFIG_EXT4DEV_COMPAT
+static int ext4dev_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	printk(KERN_WARNING "EXT4-fs: Update your userspace programs "
+	       "to mount using ext4\n");
+	printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility "
+	       "will go away by 2.6.31\n");
+	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+}
+
 static struct file_system_type ext4dev_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "ext4dev",
-	.get_sb		= ext4_get_sb,
+	.get_sb		= ext4dev_get_sb,
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS("ext4dev");
+#endif
 
 static int __init init_ext4_fs(void)
 {
 	int err;
 
+	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
 	err = init_ext4_mballoc();
 	if (err)
 		return err;
@@ -3515,9 +3614,16 @@ static int __init init_ext4_fs(void)
 	err = init_inodecache();
 	if (err)
 		goto out1;
-	err = register_filesystem(&ext4dev_fs_type);
+	err = register_filesystem(&ext4_fs_type);
 	if (err)
 		goto out;
+#ifdef CONFIG_EXT4DEV_COMPAT
+	err = register_filesystem(&ext4dev_fs_type);
+	if (err) {
+		unregister_filesystem(&ext4_fs_type);
+		goto out;
+	}
+#endif
 	return 0;
 out:
 	destroy_inodecache();
@@ -3530,10 +3636,14 @@ static int __init init_ext4_fs(void)
 
 static void __exit exit_ext4_fs(void)
 {
+	unregister_filesystem(&ext4_fs_type);
+#ifdef CONFIG_EXT4DEV_COMPAT
 	unregister_filesystem(&ext4dev_fs_type);
+#endif
 	destroy_inodecache();
 	exit_ext4_xattr();
 	exit_ext4_mballoc();
+	remove_proc_entry("fs/ext4", NULL);
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");

fs/ext4/symlink.c

@@ -23,10 +23,10 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static void * ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
-	nd_set_link(nd, (char*)ei->i_data);
+	nd_set_link(nd, (char *) ei->i_data);
 	return NULL;
 }
 
@@ -34,7 +34,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
@@ -45,7 +45,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext4_follow_link,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,

fs/ext4/xattr.c

@@ -99,12 +99,12 @@ static struct mb_cache *ext4_xattr_cache;
 
 static struct xattr_handler *ext4_xattr_handler_map[] = {
 	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &ext4_xattr_acl_access_handler,
 	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
 #endif
 	[EXT4_XATTR_INDEX_TRUSTED]	     = &ext4_xattr_trusted_handler,
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
 	[EXT4_XATTR_INDEX_SECURITY]	     = &ext4_xattr_security_handler,
 #endif
 };
@@ -112,11 +112,11 @@ static struct xattr_handler *ext4_xattr_handler_map[] = {
 struct xattr_handler *ext4_xattr_handlers[] = {
 	&ext4_xattr_user_handler,
 	&ext4_xattr_trusted_handler,
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 	&ext4_xattr_acl_access_handler,
 	&ext4_xattr_acl_default_handler,
 #endif
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
 	&ext4_xattr_security_handler,
 #endif
 	NULL
@@ -959,6 +959,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	struct ext4_xattr_block_find bs = {
 		.s = { .not_found = -ENODATA, },
 	};
+	unsigned long no_expand;
 	int error;
 
 	if (!name)
@@ -966,6 +967,9 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	if (strlen(name) > 255)
 		return -ERANGE;
 	down_write(&EXT4_I(inode)->xattr_sem);
+	no_expand = EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND;
+	EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+
 	error = ext4_get_inode_loc(inode, &is.iloc);
 	if (error)
 		goto cleanup;
@@ -1042,6 +1046,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 cleanup:
 	brelse(is.iloc.bh);
 	brelse(bs.bh);
+	if (no_expand == 0)
+		EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
 	up_write(&EXT4_I(inode)->xattr_sem);
 	return error;
 }

fs/ext4/xattr.h

@@ -51,8 +51,8 @@ struct ext4_xattr_entry {
 	(((name_len) + EXT4_XATTR_ROUND + \
 	sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
 #define EXT4_XATTR_NEXT(entry) \
-	( (struct ext4_xattr_entry *)( \
-	  (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)) )
+	((struct ext4_xattr_entry *)( \
+	 (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)))
 #define EXT4_XATTR_SIZE(size) \
 	(((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
 
@@ -63,7 +63,7 @@ struct ext4_xattr_entry {
 		EXT4_I(inode)->i_extra_isize))
 #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
 
-# ifdef CONFIG_EXT4DEV_FS_XATTR
+# ifdef CONFIG_EXT4_FS_XATTR
 
 extern struct xattr_handler ext4_xattr_user_handler;
 extern struct xattr_handler ext4_xattr_trusted_handler;
@@ -88,7 +88,7 @@ extern void exit_ext4_xattr(void);
 
 extern struct xattr_handler *ext4_xattr_handlers[];
 
-# else  /* CONFIG_EXT4DEV_FS_XATTR */
+# else  /* CONFIG_EXT4_FS_XATTR */
 
 static inline int
 ext4_xattr_get(struct inode *inode, int name_index, const char *name,
@@ -141,9 +141,9 @@ ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 
 #define ext4_xattr_handlers	NULL
 
-# endif  /* CONFIG_EXT4DEV_FS_XATTR */
+# endif  /* CONFIG_EXT4_FS_XATTR */
 
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,
 				struct inode *dir);
 #else

fs/ioctl.c

@@ -13,9 +13,14 @@
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
 
 #include <asm/ioctls.h>
 
+/* So that the fiemap access checks can't overflow on 32 bit machines. */
+#define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))
+
 /**
  * vfs_ioctl - call filesystem specific ioctl methods
  * @filp:	open file to invoke ioctl method on
@@ -71,6 +76,272 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
 	return put_user(res, p);
 }
 
+/**
+ * fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo:	Fiemap context passed into ->fiemap
+ * @logical:	Extent logical start offset, in bytes
+ * @phys:	Extent physical start offset, in bytes
+ * @len:	Extent length, in bytes
+ * @flags:	FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
+			    u64 phys, u64 len, u32 flags)
+{
+	struct fiemap_extent extent;
+	struct fiemap_extent *dest = fieinfo->fi_extents_start;
+
+	/* only count the extents */
+	if (fieinfo->fi_extents_max == 0) {
+		fieinfo->fi_extents_mapped++;
+		return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+	}
+
+	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+		return 1;
+
+	if (flags & SET_UNKNOWN_FLAGS)
+		flags |= FIEMAP_EXTENT_UNKNOWN;
+	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+		flags |= FIEMAP_EXTENT_ENCODED;
+	if (flags & SET_NOT_ALIGNED_FLAGS)
+		flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+	memset(&extent, 0, sizeof(extent));
+	extent.fe_logical = logical;
+	extent.fe_physical = phys;
+	extent.fe_length = len;
+	extent.fe_flags = flags;
+
+	dest += fieinfo->fi_extents_mapped;
+	if (copy_to_user(dest, &extent, sizeof(extent)))
+		return -EFAULT;
+
+	fieinfo->fi_extents_mapped++;
+	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+		return 1;
+	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+EXPORT_SYMBOL(fiemap_fill_next_extent);
+
+/**
+ * fiemap_check_flags - check validity of requested flags for fiemap
+ * @fieinfo:	Fiemap context passed into ->fiemap
+ * @fs_flags:	Set of fiemap flags that the file system understands
+ *
+ * Called from file system ->fiemap callback. This will compute the
+ * intersection of valid fiemap flags and those that the fs supports. That
+ * value is then compared against the user supplied flags. In case of bad user
+ * flags, the invalid values will be written into the fieinfo structure, and
+ * -EBADR is returned, which tells ioctl_fiemap() to return those values to
+ * userspace. For this reason, a return code of -EBADR should be preserved.
+ *
+ * Returns 0 on success, -EBADR on bad flags.
+ */
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
+{
+	u32 incompat_flags;
+
+	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
+	if (incompat_flags) {
+		fieinfo->fi_flags = incompat_flags;
+		return -EBADR;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(fiemap_check_flags);
+
+static int fiemap_check_ranges(struct super_block *sb,
+			       u64 start, u64 len, u64 *new_len)
+{
+	*new_len = len;
+
+	if (len == 0)
+		return -EINVAL;
+
+	if (start > sb->s_maxbytes)
+		return -EFBIG;
+
+	/*
+	 * Shrink request scope to what the fs can actually handle.
+	 */
+	if ((len > sb->s_maxbytes) ||
+	    (sb->s_maxbytes - len) < start)
+		*new_len = sb->s_maxbytes - start;
+
+	return 0;
+}
+
+static int ioctl_fiemap(struct file *filp, unsigned long arg)
+{
+	struct fiemap fiemap;
+	struct fiemap_extent_info fieinfo = { 0, };
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	u64 len;
+	int error;
+
+	if (!inode->i_op->fiemap)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
+			   sizeof(struct fiemap)))
+		return -EFAULT;
+
+	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
+		return -EINVAL;
+
+	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
+				    &len);
+	if (error)
+		return error;
+
+	fieinfo.fi_flags = fiemap.fm_flags;
+	fieinfo.fi_extents_max = fiemap.fm_extent_count;
+	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+
+	if (fiemap.fm_extent_count != 0 &&
+	    !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
+		       fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
+		return -EFAULT;
+
+	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
+		filemap_write_and_wait(inode->i_mapping);
+
+	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
+	fiemap.fm_flags = fieinfo.fi_flags;
+	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
+	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
+		error = -EFAULT;
+
+	return error;
+}
+
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes.  Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+			 struct fiemap_extent_info *fieinfo, u64 start,
+			 u64 len, get_block_t *get_block)
+{
+	struct buffer_head tmp;
+	unsigned int start_blk;
+	long long length = 0, map_len = 0;
+	u64 logical = 0, phys = 0, size = 0;
+	u32 flags = FIEMAP_EXTENT_MERGED;
+	int ret = 0;
+
+	if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+		return ret;
+
+	start_blk = logical_to_blk(inode, start);
+
+	/* guard against change */
+	mutex_lock(&inode->i_mutex);
+
+	length = (long long)min_t(u64, len, i_size_read(inode));
+	map_len = length;
+
+	do {
+		/*
+		 * we set b_size to the total size we want so it will map as
+		 * many contiguous blocks as possible at once
+		 */
+		memset(&tmp, 0, sizeof(struct buffer_head));
+		tmp.b_size = map_len;
+
+		ret = get_block(inode, start_blk, &tmp, 0);
+		if (ret)
+			break;
+
+		/* HOLE */
+		if (!buffer_mapped(&tmp)) {
+			/*
+			 * first hole after going past the EOF, this is our
+			 * last extent
+			 */
+			if (length <= 0) {
+				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+				ret = fiemap_fill_next_extent(fieinfo, logical,
+							      phys, size,
+							      flags);
+				break;
+			}
+
+			length -= blk_to_logical(inode, 1);
+
+			/* if we have holes up to/past EOF then we're done */
+			if (length <= 0)
+				break;
+
+			start_blk++;
+		} else {
+			if (length <= 0 && size) {
+				ret = fiemap_fill_next_extent(fieinfo, logical,
+							      phys, size,
+							      flags);
+				if (ret)
+					break;
+			}
+
+			logical = blk_to_logical(inode, start_blk);
+			phys = blk_to_logical(inode, tmp.b_blocknr);
+			size = tmp.b_size;
+			flags = FIEMAP_EXTENT_MERGED;
+
+			length -= tmp.b_size;
+			start_blk += logical_to_blk(inode, size);
+
+			/*
+			 * if we are past the EOF we need to loop again to see
+			 * if there is a hole so we can mark this extent as the
+			 * last one, and if not keep mapping things until we
+			 * find a hole, or we run out of slots in the extent
+			 * array
+			 */
+			if (length <= 0)
+				continue;
+
+			ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+						      size, flags);
+			if (ret)
+				break;
+		}
+		cond_resched();
+	} while (1);
+
+	mutex_unlock(&inode->i_mutex);
+
+	/* if ret is 1 then we just hit the end of the extent array */
+	if (ret == 1)
+		ret = 0;
+
+	return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
 static int file_ioctl(struct file *filp, unsigned int cmd,
 		unsigned long arg)
 {
@@ -80,6 +351,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
 	switch (cmd) {
 	case FIBMAP:
 		return ioctl_fibmap(filp, p);
+	case FS_IOC_FIEMAP:
+		return ioctl_fiemap(filp, arg);
 	case FIGETBSZ:
 		return put_user(inode->i_sb->s_blocksize, p);
 	case FIONREAD:

fs/jbd2/checkpoint.c

@@ -20,6 +20,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 
@@ -126,14 +127,29 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 
 		/*
 		 * Test again, another process may have checkpointed while we
-		 * were waiting for the checkpoint lock
+		 * were waiting for the checkpoint lock. If there are no
+		 * outstanding transactions there is nothing to checkpoint and
+		 * we can't make progress. Abort the journal in this case.
 		 */
 		spin_lock(&journal->j_state_lock);
+		spin_lock(&journal->j_list_lock);
 		nblocks = jbd_space_needed(journal);
 		if (__jbd2_log_space_left(journal) < nblocks) {
+			int chkpt = journal->j_checkpoint_transactions != NULL;
+
+			spin_unlock(&journal->j_list_lock);
 			spin_unlock(&journal->j_state_lock);
-			jbd2_log_do_checkpoint(journal);
+			if (chkpt) {
+				jbd2_log_do_checkpoint(journal);
+			} else {
+				printk(KERN_ERR "%s: no transactions\n",
+				       __func__);
+				jbd2_journal_abort(journal, 0);
+			}
+
 			spin_lock(&journal->j_state_lock);
+		} else {
+			spin_unlock(&journal->j_list_lock);
 		}
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
@@ -313,6 +329,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 	 * journal straight away.
 	 */
 	result = jbd2_cleanup_journal_tail(journal);
+	trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d",
+		   journal->j_devname, result);
 	jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
 	if (result <= 0)
 		return result;

fs/jbd2/commit.c

@@ -16,6 +16,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -126,8 +127,7 @@ static int journal_submit_commit_record(journal_t *journal,
 
 	JBUFFER_TRACE(descriptor, "submit commit block");
 	lock_buffer(bh);
-	get_bh(bh);
-	set_buffer_dirty(bh);
+	clear_buffer_dirty(bh);
 	set_buffer_uptodate(bh);
 	bh->b_end_io = journal_end_buffer_io_sync;
 
@@ -147,12 +147,9 @@ static int journal_submit_commit_record(journal_t *journal,
 	 * to remember if we sent a barrier request
 	 */
 	if (ret == -EOPNOTSUPP && barrier_done) {
-		char b[BDEVNAME_SIZE];
-
 		printk(KERN_WARNING
-			"JBD: barrier-based sync failed on %s - "
-			"disabling barriers\n",
-			bdevname(journal->j_dev, b));
+		       "JBD: barrier-based sync failed on %s - "
+		       "disabling barriers\n", journal->j_devname);
 		spin_lock(&journal->j_state_lock);
 		journal->j_flags &= ~JBD2_BARRIER;
 		spin_unlock(&journal->j_state_lock);
@@ -160,7 +157,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		/* And try again, without the barrier */
 		lock_buffer(bh);
 		set_buffer_uptodate(bh);
-		set_buffer_dirty(bh);
+		clear_buffer_dirty(bh);
 		ret = submit_bh(WRITE, bh);
 	}
 	*cbh = bh;
@@ -371,6 +368,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	commit_transaction = journal->j_running_transaction;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
+	trace_mark(jbd2_start_commit, "dev %s transaction %d",
+		   journal->j_devname, commit_transaction->t_tid);
 	jbd_debug(1, "JBD: starting commit of transaction %d\n",
 			commit_transaction->t_tid);
 
@@ -681,11 +680,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	err = journal_finish_inode_data_buffers(journal, commit_transaction);
 	if (err) {
-		char b[BDEVNAME_SIZE];
-
 		printk(KERN_WARNING
 			"JBD2: Detected IO errors while flushing file data "
-			"on %s\n", bdevname(journal->j_fs_dev, b));
+		       "on %s\n", journal->j_devname);
 		err = 0;
 	}
 
@@ -990,6 +987,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	}
 	spin_unlock(&journal->j_list_lock);
 
+	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
+		   journal->j_devname, commit_transaction->t_tid,
+		   journal->j_tail_sequence);
 	jbd_debug(1, "JBD: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 

fs/jbd2/journal.c

@@ -597,13 +597,9 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
 		if (ret)
 			*retp = ret;
 		else {
-			char b[BDEVNAME_SIZE];
-
 			printk(KERN_ALERT "%s: journal block not found "
 					"at offset %lu on %s\n",
-				__func__,
-				blocknr,
-				bdevname(journal->j_dev, b));
+			       __func__, blocknr, journal->j_devname);
 			err = -EIO;
 			__journal_abort_soft(journal, err);
 		}
@@ -901,10 +897,7 @@ static struct proc_dir_entry *proc_jbd2_stats;
 
 static void jbd2_stats_proc_init(journal_t *journal)
 {
-	char name[BDEVNAME_SIZE];
-
-	bdevname(journal->j_dev, name);
-	journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats);
+	journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
 	if (journal->j_proc_entry) {
 		proc_create_data("history", S_IRUGO, journal->j_proc_entry,
 				 &jbd2_seq_history_fops, journal);
@@ -915,12 +908,9 @@ static void jbd2_stats_proc_init(journal_t *journal)
 
 static void jbd2_stats_proc_exit(journal_t *journal)
 {
-	char name[BDEVNAME_SIZE];
-
-	bdevname(journal->j_dev, name);
 	remove_proc_entry("info", journal->j_proc_entry);
 	remove_proc_entry("history", journal->j_proc_entry);
-	remove_proc_entry(name, proc_jbd2_stats);
+	remove_proc_entry(journal->j_devname, proc_jbd2_stats);
 }
 
 static void journal_init_stats(journal_t *journal)
@@ -1018,6 +1008,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 {
 	journal_t *journal = journal_init_common();
 	struct buffer_head *bh;
+	char *p;
 	int n;
 
 	if (!journal)
@@ -1039,6 +1030,10 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
 	journal->j_maxlen = len;
+	bdevname(journal->j_dev, journal->j_devname);
+	p = journal->j_devname;
+	while ((p = strchr(p, '/')))
+		*p = '!';
 	jbd2_stats_proc_init(journal);
 
 	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
@@ -1061,6 +1056,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 {
 	struct buffer_head *bh;
 	journal_t *journal = journal_init_common();
+	char *p;
 	int err;
 	int n;
 	unsigned long long blocknr;
@@ -1070,6 +1066,12 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 
 	journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
 	journal->j_inode = inode;
+	bdevname(journal->j_dev, journal->j_devname);
+	p = journal->j_devname;
+	while ((p = strchr(p, '/')))
+		*p = '!';
+	p = journal->j_devname + strlen(journal->j_devname);
+	sprintf(p, ":%lu", journal->j_inode->i_ino);
 	jbd_debug(1,
 		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
 		  journal, inode->i_sb->s_id, inode->i_ino,
@@ -1253,6 +1255,22 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 		goto out;
 	}
 
+	if (buffer_write_io_error(bh)) {
+		/*
+		 * Oh, dear.  A previous attempt to write the journal
+		 * superblock failed.  This could happen because the
+		 * USB device was yanked out.  Or it could happen to
+		 * be a transient write error and maybe the block will
+		 * be remapped.  Nothing we can do but to retry the
+		 * write and hope for the best.
+		 */
+		printk(KERN_ERR "JBD2: previous I/O error detected "
+		       "for journal superblock update for %s.\n",
+		       journal->j_devname);
+		clear_buffer_write_io_error(bh);
+		set_buffer_uptodate(bh);
+	}
+
 	spin_lock(&journal->j_state_lock);
 	jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
 		  journal->j_tail, journal->j_tail_sequence, journal->j_errno);
@@ -1264,9 +1282,16 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 
 	BUFFER_TRACE(bh, "marking dirty");
 	mark_buffer_dirty(bh);
-	if (wait)
+	if (wait) {
 		sync_dirty_buffer(bh);
-	else
+		if (buffer_write_io_error(bh)) {
+			printk(KERN_ERR "JBD2: I/O error detected "
+			       "when updating journal superblock for %s.\n",
+			       journal->j_devname);
+			clear_buffer_write_io_error(bh);
+			set_buffer_uptodate(bh);
+		}
+	} else
 		ll_rw_block(SWRITE, 1, &bh);
 
 out:
@@ -1760,23 +1785,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	return err;
 }
 
-/*
- * journal_dev_name: format a character string to describe on what
- * device this journal is present.
- */
-
-static const char *journal_dev_name(journal_t *journal, char *buffer)
-{
-	struct block_device *bdev;
-
-	if (journal->j_inode)
-		bdev = journal->j_inode->i_sb->s_bdev;
-	else
-		bdev = journal->j_dev;
-
-	return bdevname(bdev, buffer);
-}
-
 /*
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
@@ -1793,13 +1801,12 @@ static const char *journal_dev_name(journal_t *journal, char *buffer)
 void __jbd2_journal_abort_hard(journal_t *journal)
 {
 	transaction_t *transaction;
-	char b[BDEVNAME_SIZE];
 
 	if (journal->j_flags & JBD2_ABORT)
 		return;
 
 	printk(KERN_ERR "Aborting journal on device %s.\n",
-		journal_dev_name(journal, b));
+	       journal->j_devname);
 
 	spin_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_ABORT;

fs/ocfs2/alloc.c

@@ -989,15 +989,6 @@ static int ocfs2_grow_tree(struct inode *inode, handle_t *handle,
 	return ret;
 }
 
-/*
- * This is only valid for leaf nodes, which are the only ones that can
- * have empty extents anyway.
- */
-static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
-{
-	return !rec->e_leaf_clusters;
-}
-
 /*
  * This function will discard the rightmost extent record.
  */

fs/ocfs2/alloc.h

@@ -146,4 +146,13 @@ static inline unsigned int ocfs2_rec_clusters(struct ocfs2_extent_list *el,
 		return le16_to_cpu(rec->e_leaf_clusters);
 }
 
+/*
+ * This is only valid for leaf nodes, which are the only ones that can
+ * have empty extents anyway.
+ */
+static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
+{
+	return !rec->e_leaf_clusters;
+}
+
 #endif /* OCFS2_ALLOC_H */

fs/ocfs2/extent_map.c

@@ -25,6 +25,7 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/fiemap.h>
 
 #define MLOG_MASK_PREFIX ML_EXTENT_MAP
 #include <cluster/masklog.h>
@@ -32,6 +33,7 @@
 #include "ocfs2.h"
 
 #include "alloc.h"
+#include "dlmglue.h"
 #include "extent_map.h"
 #include "inode.h"
 #include "super.h"
@@ -282,6 +284,51 @@ void ocfs2_extent_map_insert_rec(struct inode *inode,
 		kfree(new_emi);
 }
 
+static int ocfs2_last_eb_is_empty(struct inode *inode,
+				  struct ocfs2_dinode *di)
+{
+	int ret, next_free;
+	u64 last_eb_blk = le64_to_cpu(di->i_last_eb_blk);
+	struct buffer_head *eb_bh = NULL;
+	struct ocfs2_extent_block *eb;
+	struct ocfs2_extent_list *el;
+
+	ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), last_eb_blk,
+			       &eb_bh, OCFS2_BH_CACHED, inode);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+	el = &eb->h_list;
+
+	if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
+		ret = -EROFS;
+		OCFS2_RO_ON_INVALID_EXTENT_BLOCK(inode->i_sb, eb);
+		goto out;
+	}
+
+	if (el->l_tree_depth) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %lu has non zero tree depth in "
+			    "leaf block %llu\n", inode->i_ino,
+			    (unsigned long long)eb_bh->b_blocknr);
+		ret = -EROFS;
+		goto out;
+	}
+
+	next_free = le16_to_cpu(el->l_next_free_rec);
+
+	if (next_free == 0 ||
+	    (next_free == 1 && ocfs2_is_empty_extent(&el->l_recs[0])))
+		ret = 1;
+
+out:
+	brelse(eb_bh);
+	return ret;
+}
+
 /*
  * Return the 1st index within el which contains an extent start
  * larger than v_cluster.
@@ -373,42 +420,28 @@ static int ocfs2_figure_hole_clusters(struct inode *inode,
 	return ret;
 }
 
-int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
-		       u32 *p_cluster, u32 *num_clusters,
-		       unsigned int *extent_flags)
+static int ocfs2_get_clusters_nocache(struct inode *inode,
+				      struct buffer_head *di_bh,
+				      u32 v_cluster, unsigned int *hole_len,
+				      struct ocfs2_extent_rec *ret_rec,
+				      unsigned int *is_last)
 {
-	int ret, i;
-	unsigned int flags = 0;
-	struct buffer_head *di_bh = NULL;
-	struct buffer_head *eb_bh = NULL;
+	int i, ret, tree_height, len;
 	struct ocfs2_dinode *di;
-	struct ocfs2_extent_block *eb;
+	struct ocfs2_extent_block *uninitialized_var(eb);
 	struct ocfs2_extent_list *el;
 	struct ocfs2_extent_rec *rec;
-	u32 coff;
-
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-		ret = -ERANGE;
-		mlog_errno(ret);
-		goto out;
-	}
-
-	ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
-				      num_clusters, extent_flags);
-	if (ret == 0)
-		goto out;
+	struct buffer_head *eb_bh = NULL;
 
-	ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
-			       &di_bh, OCFS2_BH_CACHED, inode);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
+	memset(ret_rec, 0, sizeof(*ret_rec));
+	if (is_last)
+		*is_last = 0;
 
 	di = (struct ocfs2_dinode *) di_bh->b_data;
 	el = &di->id2.i_list;
+	tree_height = le16_to_cpu(el->l_tree_depth);
 
-	if (el->l_tree_depth) {
+	if (tree_height > 0) {
 		ret = ocfs2_find_leaf(inode, el, v_cluster, &eb_bh);
 		if (ret) {
 			mlog_errno(ret);
@@ -431,46 +464,143 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
 	i = ocfs2_search_extent_list(el, v_cluster);
 	if (i == -1) {
 		/*
-		 * A hole was found. Return some canned values that
-		 * callers can key on. If asked for, num_clusters will
-		 * be populated with the size of the hole.
+		 * Holes can be larger than the maximum size of an
+		 * extent, so we return their lengths in a seperate
+		 * field.
 		 */
-		*p_cluster = 0;
-		if (num_clusters) {
+		if (hole_len) {
 			ret = ocfs2_figure_hole_clusters(inode, el, eb_bh,
-							 v_cluster,
-							 num_clusters);
+							 v_cluster, &len);
 			if (ret) {
 				mlog_errno(ret);
 				goto out;
 			}
+
+			*hole_len = len;
 		}
-	} else {
-		rec = &el->l_recs[i];
+		goto out_hole;
+	}
 
-		BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
+	rec = &el->l_recs[i];
 
-		if (!rec->e_blkno) {
-			ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-				    "record (%u, %u, 0)", inode->i_ino,
-				    le32_to_cpu(rec->e_cpos),
-				    ocfs2_rec_clusters(el, rec));
-			ret = -EROFS;
-			goto out;
+	BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
+
+	if (!rec->e_blkno) {
+		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+			    "record (%u, %u, 0)", inode->i_ino,
+			    le32_to_cpu(rec->e_cpos),
+			    ocfs2_rec_clusters(el, rec));
+		ret = -EROFS;
+		goto out;
+	}
+
+	*ret_rec = *rec;
+
+	/*
+	 * Checking for last extent is potentially expensive - we
+	 * might have to look at the next leaf over to see if it's
+	 * empty.
+	 *
+	 * The first two checks are to see whether the caller even
+	 * cares for this information, and if the extent is at least
+	 * the last in it's list.
+	 *
+	 * If those hold true, then the extent is last if any of the
+	 * additional conditions hold true:
+	 *  - Extent list is in-inode
+	 *  - Extent list is right-most
+	 *  - Extent list is 2nd to rightmost, with empty right-most
+	 */
+	if (is_last) {
+		if (i == (le16_to_cpu(el->l_next_free_rec) - 1)) {
+			if (tree_height == 0)
+				*is_last = 1;
+			else if (eb->h_blkno == di->i_last_eb_blk)
+				*is_last = 1;
+			else if (eb->h_next_leaf_blk == di->i_last_eb_blk) {
+				ret = ocfs2_last_eb_is_empty(inode, di);
+				if (ret < 0) {
+					mlog_errno(ret);
+					goto out;
+				}
+				if (ret == 1)
+					*is_last = 1;
+			}
 		}
+	}
+
+out_hole:
+	ret = 0;
+out:
+	brelse(eb_bh);
+	return ret;
+}
+
+static void ocfs2_relative_extent_offsets(struct super_block *sb,
+					  u32 v_cluster,
+					  struct ocfs2_extent_rec *rec,
+					  u32 *p_cluster, u32 *num_clusters)
+
+{
+	u32 coff = v_cluster - le32_to_cpu(rec->e_cpos);
+
+	*p_cluster = ocfs2_blocks_to_clusters(sb, le64_to_cpu(rec->e_blkno));
+	*p_cluster = *p_cluster + coff;
+
+	if (num_clusters)
+		*num_clusters = le16_to_cpu(rec->e_leaf_clusters) - coff;
+}
+
+int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
+		       u32 *p_cluster, u32 *num_clusters,
+		       unsigned int *extent_flags)
+{
+	int ret;
+	unsigned int uninitialized_var(hole_len), flags = 0;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_extent_rec rec;
 
-		coff = v_cluster - le32_to_cpu(rec->e_cpos);
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = -ERANGE;
+		mlog_errno(ret);
+		goto out;
+	}
 
-		*p_cluster = ocfs2_blocks_to_clusters(inode->i_sb,
-						    le64_to_cpu(rec->e_blkno));
-		*p_cluster = *p_cluster + coff;
+	ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
+				      num_clusters, extent_flags);
+	if (ret == 0)
+		goto out;
 
-		if (num_clusters)
-			*num_clusters = ocfs2_rec_clusters(el, rec) - coff;
+	ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
+			       &di_bh, OCFS2_BH_CACHED, inode);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
 
-		flags = rec->e_flags;
+	ret = ocfs2_get_clusters_nocache(inode, di_bh, v_cluster, &hole_len,
+					 &rec, NULL);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
 
-		ocfs2_extent_map_insert_rec(inode, rec);
+	if (rec.e_blkno == 0ULL) {
+		/*
+		 * A hole was found. Return some canned values that
+		 * callers can key on. If asked for, num_clusters will
+		 * be populated with the size of the hole.
+		 */
+		*p_cluster = 0;
+		if (num_clusters) {
+			*num_clusters = hole_len;
+		}
+	} else {
+		ocfs2_relative_extent_offsets(inode->i_sb, v_cluster, &rec,
+					      p_cluster, num_clusters);
+		flags = rec.e_flags;
+
+		ocfs2_extent_map_insert_rec(inode, &rec);
 	}
 
 	if (extent_flags)
@@ -478,7 +608,6 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
 
 out:
 	brelse(di_bh);
-	brelse(eb_bh);
 	return ret;
 }
 
@@ -521,3 +650,114 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
 out:
 	return ret;
 }
+
+static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
+			       struct fiemap_extent_info *fieinfo,
+			       u64 map_start)
+{
+	int ret;
+	unsigned int id_count;
+	struct ocfs2_dinode *di;
+	u64 phys;
+	u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	id_count = le16_to_cpu(di->id2.i_data.id_count);
+
+	if (map_start < id_count) {
+		phys = oi->ip_blkno << inode->i_sb->s_blocksize_bits;
+		phys += offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+
+		ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
+					      flags);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+#define OCFS2_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC)
+
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		 u64 map_start, u64 map_len)
+{
+	int ret, is_last;
+	u32 mapping_end, cpos;
+	unsigned int hole_size;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	u64 len_bytes, phys_bytes, virt_bytes;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_extent_rec rec;
+
+	ret = fiemap_check_flags(fieinfo, OCFS2_FIEMAP_FLAGS);
+	if (ret)
+		return ret;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	/*
+	 * Handle inline-data separately.
+	 */
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = ocfs2_fiemap_inline(inode, di_bh, fieinfo, map_start);
+		goto out_unlock;
+	}
+
+	cpos = map_start >> osb->s_clustersize_bits;
+	mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
+					       map_start + map_len);
+	mapping_end -= cpos;
+	is_last = 0;
+	while (cpos < mapping_end && !is_last) {
+		u32 fe_flags;
+
+		ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos,
+						 &hole_size, &rec, &is_last);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		if (rec.e_blkno == 0ULL) {
+			cpos += hole_size;
+			continue;
+		}
+
+		fe_flags = 0;
+		if (rec.e_flags & OCFS2_EXT_UNWRITTEN)
+			fe_flags |= FIEMAP_EXTENT_UNWRITTEN;
+		if (is_last)
+			fe_flags |= FIEMAP_EXTENT_LAST;
+		len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
+		phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
+		virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
+
+		ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
+					      len_bytes, fe_flags);
+		if (ret)
+			break;
+
+		cpos = le32_to_cpu(rec.e_cpos)+ le16_to_cpu(rec.e_leaf_clusters);
+	}
+
+	if (ret > 0)
+		ret = 0;
+
+out_unlock:
+	brelse(di_bh);
+
+	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	ocfs2_inode_unlock(inode, 0);
+out:
+
+	return ret;
+}

fs/ocfs2/extent_map.h

@@ -50,4 +50,7 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, u32 *p_cluster,
 int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
 				u64 *ret_count, unsigned int *extent_flags);
 
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		 u64 map_start, u64 map_len);
+
 #endif  /* _EXTENT_MAP_H */

fs/ocfs2/file.c

@@ -2228,6 +2228,7 @@ const struct inode_operations ocfs2_file_iops = {
 	.getattr	= ocfs2_getattr,
 	.permission	= ocfs2_permission,
 	.fallocate	= ocfs2_fallocate,
+	.fiemap		= ocfs2_fiemap,
 };
 
 const struct inode_operations ocfs2_special_file_iops = {

include/linux/ext3_fs.h

@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
 extern void ext3_set_inode_flags(struct inode *);
 extern void ext3_get_inode_flags(struct ext3_inode_info *);
 extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len);
 
 /* ioctl.c */
 extern int ext3_ioctl (struct inode *, struct file *, unsigned int,

include/linux/fiemap.h

+/*
+ * FS_IOC_FIEMAP ioctl infrastructure.
+ *
+ * Some portions copyright (C) 2007 Cluster File Systems, Inc
+ *
+ * Authors: Mark Fasheh <mfasheh@suse.com>
+ *          Kalpak Shah <kalpak.shah@sun.com>
+ *          Andreas Dilger <adilger@sun.com>
+ */
+
+#ifndef _LINUX_FIEMAP_H
+#define _LINUX_FIEMAP_H
+
+struct fiemap_extent {
+	__u64 fe_logical;  /* logical offset in bytes for the start of
+			    * the extent from the beginning of the file */
+	__u64 fe_physical; /* physical offset in bytes for the start
+			    * of the extent from the beginning of the disk */
+	__u64 fe_length;   /* length in bytes for this extent */
+	__u64 fe_reserved64[2];
+	__u32 fe_flags;    /* FIEMAP_EXTENT_* flags for this extent */
+	__u32 fe_reserved[3];
+};
+
+struct fiemap {
+	__u64 fm_start;		/* logical offset (inclusive) at
+				 * which to start mapping (in) */
+	__u64 fm_length;	/* logical length of mapping which
+				 * userspace wants (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) */
+};
+
+#define FIEMAP_MAX_OFFSET	(~0ULL)
+
+#define FIEMAP_FLAG_SYNC	0x00000001 /* sync file data before map */
+#define FIEMAP_FLAG_XATTR	0x00000002 /* map extended attribute tree */
+
+#define FIEMAP_FLAGS_COMPAT	(FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
+
+#define FIEMAP_EXTENT_LAST		0x00000001 /* Last extent in file. */
+#define FIEMAP_EXTENT_UNKNOWN		0x00000002 /* Data location unknown. */
+#define FIEMAP_EXTENT_DELALLOC		0x00000004 /* Location still pending.
+						    * Sets EXTENT_UNKNOWN. */
+#define FIEMAP_EXTENT_ENCODED		0x00000008 /* Data can not be read
+						    * while fs is unmounted */
+#define FIEMAP_EXTENT_DATA_ENCRYPTED	0x00000080 /* Data is encrypted by fs.
+						    * Sets EXTENT_NO_BYPASS. */
+#define FIEMAP_EXTENT_NOT_ALIGNED	0x00000100 /* Extent offsets may not be
+						    * block aligned. */
+#define FIEMAP_EXTENT_DATA_INLINE	0x00000200 /* Data mixed with metadata.
+						    * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_DATA_TAIL		0x00000400 /* Multiple files in block.
+						    * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_UNWRITTEN		0x00000800 /* Space allocated, but
+						    * no data (i.e. zero). */
+#define FIEMAP_EXTENT_MERGED		0x00001000 /* File does not natively
+						    * support extents. Result
+						    * merged for efficiency. */
+
+#endif /* _LINUX_FIEMAP_H */

include/linux/fs.h

@@ -234,6 +234,7 @@ extern int dir_notify_enable;
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
 #define	FS_IOC_GETVERSION		_IOR('v', 1, long)
 #define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
 #define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
 #define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
 #define FS_IOC32_GETVERSION		_IOR('v', 1, int)
@@ -294,6 +295,7 @@ extern int dir_notify_enable;
 #include <linux/mutex.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
+#include <linux/fiemap.h>
 
 #include <asm/atomic.h>
 #include <asm/byteorder.h>
@@ -1181,6 +1183,20 @@ extern void dentry_unhash(struct dentry *dentry);
  */
 extern int file_permission(struct file *, int);
 
+/*
+ * VFS FS_IOC_FIEMAP helper definitions.
+ */
+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 */
+};
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+			    u64 phys, u64 len, u32 flags);
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
 /*
  * File types
  *
@@ -1290,6 +1306,8 @@ struct inode_operations {
 	void (*truncate_range)(struct inode *, loff_t, loff_t);
 	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
+	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+		      u64 len);
 };
 
 struct seq_file;
@@ -1987,6 +2005,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
 
 extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		    unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo, u64 start,
+				u64 len, get_block_t *get_block);
 
 extern void get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);

include/linux/jbd2.h

@@ -850,7 +850,8 @@ struct journal_s
 	 */
 	struct block_device	*j_dev;
 	int			j_blocksize;
-	unsigned long long		j_blk_offset;
+	unsigned long long	j_blk_offset;
+	char			j_devname[BDEVNAME_SIZE+24];
 
 	/*
 	 * Device which holds the client fs.  For internal journal this will be

include/linux/percpu_counter.h

@@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
-s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
+s64 __percpu_counter_sum(struct percpu_counter *fbc);
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -44,19 +44,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
-	s64 ret = __percpu_counter_sum(fbc, 0);
+	s64 ret = __percpu_counter_sum(fbc);
 	return ret < 0 ? 0 : ret;
 }
 
-static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
-{
-	return __percpu_counter_sum(fbc, 1);
-}
-
-
 static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 {
-	return __percpu_counter_sum(fbc, 0);
+	return __percpu_counter_sum(fbc);
 }
 
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)

lib/percpu_counter.c

@@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add);
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
  */
-s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
 {
 	s64 ret;
 	int cpu;
@@ -62,11 +62,9 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
 	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
-		if (set)
-			*pcount = 0;
+		*pcount = 0;
 	}
-	if (set)
-		fbc->count = ret;
+	fbc->count = ret;
 
 	spin_unlock(&fbc->lock);
 	return ret;