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: (50 commits)
  jbd2: sparse pointer use of zero as null
  jbd2: Use round-jiffies() function for the "5 second" ext4/jbd2 wakeup
  jbd2: Mark jbd2 slabs as SLAB_TEMPORARY
  jbd2: add lockdep support
  ext4: Use the ext4_ext_actual_len() helper function
  ext4: fix uniniatilized extent splitting error
  ext4: Check for return value from sb_set_blocksize
  ext4: Add stripe= option to /proc/mounts
  ext4: Enable the multiblock allocator by default
  ext4: Add multi block allocator for ext4
  ext4: Add new functions for searching extent tree
  ext4: Add ext4_find_next_bit()
  ext4: fix up EXT4FS_DEBUG builds
  ext4: Fix ext4_show_options to show the correct mount options.
  ext4: Add EXT4_IOC_MIGRATE ioctl
  ext4: Add inode version support in ext4
  vfs: Add 64 bit i_version support
  ext4: Add the journal checksum feature
  jbd2: jbd2 stats through procfs
  ext4: Take read lock during overwrite case.
  ...

Documentation/filesystems/ext4.txt

@@ -86,9 +86,21 @@ Alex is working on a new set of patches right now.
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
-extents			ext4 will use extents to address file data.  The
+extents		(*)	ext4 will use extents to address file data.  The
 			file system will no longer be mountable by ext3.
 
+noextents		ext4 will not use extents for newly created files
+
+journal_checksum	Enable checksumming of the journal transactions.
+			This will allow the recovery code in e2fsck and the
+			kernel to detect corruption in the kernel.  It is a
+			compatible change and will be ignored by older kernels.
+
+journal_async_commit	Commit block can be written to disk without waiting
+			for descriptor blocks. If enabled older kernels cannot
+			mount the device. This will enable 'journal_checksum'
+			internally.
+
 journal=update		Update the ext4 file system's journal to the current
 			format.
 
@@ -196,6 +208,12 @@ nobh			(a) cache disk block mapping information
 			"nobh" option tries to avoid associating buffer
 			heads (supported only for "writeback" mode).
 
+mballoc		(*)	Use the multiple block allocator for block allocation
+nomballoc		disabled multiple block allocator for block allocation.
+stripe=n		Number of filesystem blocks that mballoc will try
+			to use for allocation size and alignment. For RAID5/6
+			systems this should be the number of data
+			disks *  RAID chunk size in file system blocks.
 
 Data Mode
 ---------

Documentation/filesystems/proc.txt

@@ -857,6 +857,45 @@ 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 mutiblock 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.
 
 ------------------------------------------------------------------------------
 Summary

fs/Kconfig

@@ -236,6 +236,7 @@ config JBD_DEBUG
 
 config JBD2
 	tristate
+	select CRC32
 	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

fs/afs/dir.c

@@ -546,11 +546,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 	dentry->d_op = &afs_fs_dentry_operations;
 
 	d_add(dentry, inode);
-	_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%lu }",
+	_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
 	       fid.vnode,
 	       fid.unique,
 	       dentry->d_inode->i_ino,
-	       dentry->d_inode->i_version);
+	       (unsigned long long)dentry->d_inode->i_version);
 
 	return NULL;
 }
@@ -630,9 +630,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 		 * been deleted and replaced, and the original vnode ID has
 		 * been reused */
 		if (fid.unique != vnode->fid.unique) {
-			_debug("%s: file deleted (uq %u -> %u I:%lu)",
+			_debug("%s: file deleted (uq %u -> %u I:%llu)",
 			       dentry->d_name.name, fid.unique,
-			       vnode->fid.unique, dentry->d_inode->i_version);
+			       vnode->fid.unique,
+			       (unsigned long long)dentry->d_inode->i_version);
 			spin_lock(&vnode->lock);
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
 			spin_unlock(&vnode->lock);

fs/afs/inode.c

@@ -301,7 +301,8 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
 	inode = dentry->d_inode;
 
-	_enter("{ ino=%lu v=%lu }", inode->i_ino, inode->i_version);
+	_enter("{ ino=%lu v=%llu }", inode->i_ino,
+		(unsigned long long)inode->i_version);
 
 	generic_fillattr(inode, stat);
 	return 0;

fs/buffer.c

@@ -3213,6 +3213,50 @@ static int buffer_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+/**
+ * bh_uptodate_or_lock: Test whether the buffer is uptodate
+ * @bh: struct buffer_head
+ *
+ * Return true if the buffer is up-to-date and false,
+ * with the buffer locked, if not.
+ */
+int bh_uptodate_or_lock(struct buffer_head *bh)
+{
+	if (!buffer_uptodate(bh)) {
+		lock_buffer(bh);
+		if (!buffer_uptodate(bh))
+			return 0;
+		unlock_buffer(bh);
+	}
+	return 1;
+}
+EXPORT_SYMBOL(bh_uptodate_or_lock);
+
+/**
+ * bh_submit_read: Submit a locked buffer for reading
+ * @bh: struct buffer_head
+ *
+ * Returns zero on success and -EIO on error.
+ */
+int bh_submit_read(struct buffer_head *bh)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+
+	get_bh(bh);
+	bh->b_end_io = end_buffer_read_sync;
+	submit_bh(READ, bh);
+	wait_on_buffer(bh);
+	if (buffer_uptodate(bh))
+		return 0;
+	return -EIO;
+}
+EXPORT_SYMBOL(bh_submit_read);
+
 void __init buffer_init(void)
 {
 	int nrpages;

fs/ext2/super.c

@@ -680,11 +680,31 @@ static int ext2_check_descriptors (struct super_block * sb)
 static loff_t ext2_max_size(int bits)
 {
 	loff_t res = EXT2_NDIR_BLOCKS;
-	/* This constant is calculated to be the largest file size for a
-	 * dense, 4k-blocksize file such that the total number of
+	int meta_blocks;
+	loff_t upper_limit;
+
+	/* This is calculated to be the largest file size for a
+	 * dense, file such that the total number of
 	 * sectors in the file, including data and all indirect blocks,
-	 * does not exceed 2^32. */
-	const loff_t upper_limit = 0x1ff7fffd000LL;
+	 * does not exceed 2^32 -1
+	 * __u32 i_blocks representing the total number of
+	 * 512 bytes blocks of the file
+	 */
+	upper_limit = (1LL << 32) - 1;
+
+	/* total blocks in file system block size */
+	upper_limit >>= (bits - 9);
+
+
+	/* indirect blocks */
+	meta_blocks = 1;
+	/* double indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2));
+	/* tripple indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
+
+	upper_limit -= meta_blocks;
+	upper_limit <<= bits;
 
 	res += 1LL << (bits-2);
 	res += 1LL << (2*(bits-2));
@@ -692,6 +712,10 @@ static loff_t ext2_max_size(int bits)
 	res <<= bits;
 	if (res > upper_limit)
 		res = upper_limit;
+
+	if (res > MAX_LFS_FILESIZE)
+		res = MAX_LFS_FILESIZE;
+
 	return res;
 }
 

fs/ext3/super.c

@@ -1436,11 +1436,31 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 static loff_t ext3_max_size(int bits)
 {
 	loff_t res = EXT3_NDIR_BLOCKS;
-	/* This constant is calculated to be the largest file size for a
-	 * dense, 4k-blocksize file such that the total number of
+	int meta_blocks;
+	loff_t upper_limit;
+
+	/* This is calculated to be the largest file size for a
+	 * dense, file such that the total number of
 	 * sectors in the file, including data and all indirect blocks,
-	 * does not exceed 2^32. */
-	const loff_t upper_limit = 0x1ff7fffd000LL;
+	 * does not exceed 2^32 -1
+	 * __u32 i_blocks representing the total number of
+	 * 512 bytes blocks of the file
+	 */
+	upper_limit = (1LL << 32) - 1;
+
+	/* total blocks in file system block size */
+	upper_limit >>= (bits - 9);
+
+
+	/* indirect blocks */
+	meta_blocks = 1;
+	/* double indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2));
+	/* tripple indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
+
+	upper_limit -= meta_blocks;
+	upper_limit <<= bits;
 
 	res += 1LL << (bits-2);
 	res += 1LL << (2*(bits-2));
@@ -1448,6 +1468,10 @@ static loff_t ext3_max_size(int bits)
 	res <<= bits;
 	if (res > upper_limit)
 		res = upper_limit;
+
+	if (res > MAX_LFS_FILESIZE)
+		res = MAX_LFS_FILESIZE;
+
 	return res;
 }
 

fs/ext4/Makefile

@@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o
 
 ext4dev-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
+		   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

fs/ext4/balloc.c

@@ -29,7 +29,7 @@
  * Calculate the block group number and offset, given a block number
  */
 void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
-		unsigned long *blockgrpp, ext4_grpblk_t *offsetp)
+		ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
 {
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	ext4_grpblk_t offset;
@@ -46,7 +46,7 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 /* 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,
-				int block_group, struct ext4_group_desc *gdp)
+		 ext4_group_t block_group, struct ext4_group_desc *gdp)
 {
 	unsigned long start;
 	int bit, bit_max;
@@ -60,7 +60,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 * essentially implementing a per-group read-only flag. */
 		if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
 			ext4_error(sb, __FUNCTION__,
-				   "Checksum bad for group %u\n", block_group);
+				  "Checksum bad for group %lu\n", block_group);
 			gdp->bg_free_blocks_count = 0;
 			gdp->bg_free_inodes_count = 0;
 			gdp->bg_itable_unused = 0;
@@ -153,7 +153,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
  *			group descriptor
  */
 struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
-					     unsigned int block_group,
+					     ext4_group_t block_group,
 					     struct buffer_head ** bh)
 {
 	unsigned long group_desc;
@@ -164,7 +164,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 	if (block_group >= sbi->s_groups_count) {
 		ext4_error (sb, "ext4_get_group_desc",
 			    "block_group >= groups_count - "
-			    "block_group = %d, groups_count = %lu",
+			    "block_group = %lu, groups_count = %lu",
 			    block_group, sbi->s_groups_count);
 
 		return NULL;
@@ -176,7 +176,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 	if (!sbi->s_group_desc[group_desc]) {
 		ext4_error (sb, "ext4_get_group_desc",
 			    "Group descriptor not loaded - "
-			    "block_group = %d, group_desc = %lu, desc = %lu",
+			    "block_group = %lu, group_desc = %lu, desc = %lu",
 			     block_group, group_desc, offset);
 		return NULL;
 	}
@@ -189,18 +189,70 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 	return desc;
 }
 
+static int ext4_valid_block_bitmap(struct super_block *sb,
+					struct ext4_group_desc *desc,
+					unsigned int block_group,
+					struct buffer_head *bh)
+{
+	ext4_grpblk_t offset;
+	ext4_grpblk_t next_zero_bit;
+	ext4_fsblk_t bitmap_blk;
+	ext4_fsblk_t group_first_block;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		/* with FLEX_BG, the inode/block bitmaps and itable
+		 * blocks may not be in the group at all
+		 * so the bitmap validation will be skipped for those groups
+		 * or it has to also read the block group where the bitmaps
+		 * are located to verify they are set.
+		 */
+		return 1;
+	}
+	group_first_block = ext4_group_first_block_no(sb, block_group);
+
+	/* check whether block bitmap block number is set */
+	bitmap_blk = ext4_block_bitmap(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	if (!ext4_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode bitmap block number is set */
+	bitmap_blk = ext4_inode_bitmap(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	if (!ext4_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode table block number is set */
+	bitmap_blk = ext4_inode_table(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
+				offset + EXT4_SB(sb)->s_itb_per_group,
+				offset);
+	if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
+		/* good bitmap for inode tables */
+		return 1;
+
+err_out:
+	ext4_error(sb, __FUNCTION__,
+			"Invalid block bitmap - "
+			"block_group = %d, block = %llu",
+			block_group, bitmap_blk);
+	return 0;
+}
 /**
  * read_block_bitmap()
  * @sb:			super block
  * @block_group:	given block group
  *
- * Read the bitmap for a given block_group, reading into the specified
- * slot in the superblock's bitmap cache.
+ * Read the bitmap for a given block_group,and validate the
+ * bits for block/inode/inode tables are set in the bitmaps
  *
  * Return buffer_head on success or NULL in case of failure.
  */
 struct buffer_head *
-read_block_bitmap(struct super_block *sb, unsigned int block_group)
+read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 {
 	struct ext4_group_desc * desc;
 	struct buffer_head * bh = NULL;
@@ -210,25 +262,36 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 	if (!desc)
 		return NULL;
 	bitmap_blk = ext4_block_bitmap(sb, desc);
+	bh = sb_getblk(sb, bitmap_blk);
+	if (unlikely(!bh)) {
+		ext4_error(sb, __FUNCTION__,
+			    "Cannot read block bitmap - "
+			    "block_group = %d, block_bitmap = %llu",
+			    (int)block_group, (unsigned long long)bitmap_blk);
+		return NULL;
+	}
+	if (bh_uptodate_or_lock(bh))
+		return bh;
+
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-		bh = sb_getblk(sb, bitmap_blk);
-		if (!buffer_uptodate(bh)) {
-			lock_buffer(bh);
-			if (!buffer_uptodate(bh)) {
-				ext4_init_block_bitmap(sb, bh, block_group,
-						       desc);
-				set_buffer_uptodate(bh);
-			}
-			unlock_buffer(bh);
-		}
-	} else {
-		bh = sb_bread(sb, bitmap_blk);
+		ext4_init_block_bitmap(sb, bh, block_group, desc);
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
 	}
-	if (!bh)
-		ext4_error (sb, __FUNCTION__,
+	if (bh_submit_read(bh) < 0) {
+		put_bh(bh);
+		ext4_error(sb, __FUNCTION__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %llu",
-			    block_group, bitmap_blk);
+			    (int)block_group, (unsigned long long)bitmap_blk);
+		return NULL;
+	}
+	if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
+		put_bh(bh);
+		return NULL;
+	}
+
 	return bh;
 }
 /*
@@ -320,7 +383,7 @@ static void __rsv_window_dump(struct rb_root *root, int verbose,
  */
 static int
 goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
-			unsigned int group, struct super_block * sb)
+			ext4_group_t group, struct super_block *sb)
 {
 	ext4_fsblk_t group_first_block, group_last_block;
 
@@ -463,7 +526,7 @@ static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
  * when setting the reservation window size through ioctl before the file
  * is open for write (needs block allocation).
  *
- * Needs truncate_mutex protection prior to call this function.
+ * Needs down_write(i_data_sem) protection prior to call this function.
  */
 void ext4_init_block_alloc_info(struct inode *inode)
 {
@@ -514,6 +577,8 @@ void ext4_discard_reservation(struct inode *inode)
 	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;
 
@@ -540,7 +605,7 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct buffer_head *gd_bh;
-	unsigned long block_group;
+	ext4_group_t block_group;
 	ext4_grpblk_t bit;
 	unsigned long i;
 	unsigned long overflow;
@@ -587,11 +652,13 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
 	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
 	    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))
+		     sbi->s_itb_per_group)) {
 		ext4_error (sb, "ext4_free_blocks",
 			    "Freeing blocks in system zones - "
 			    "Block = %llu, count = %lu",
 			    block, count);
+		goto error_return;
+	}
 
 	/*
 	 * We are about to start releasing blocks in the bitmap,
@@ -720,19 +787,29 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
  * @inode:		inode
  * @block:		start physical block to free
  * @count:		number of blocks to count
+ * @metadata: 		Are these metadata blocks
  */
 void ext4_free_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t block, unsigned long count)
+			ext4_fsblk_t block, unsigned long count,
+			int metadata)
 {
 	struct super_block * sb;
 	unsigned long dquot_freed_blocks;
 
+	/* this isn't the right place to decide whether block is metadata
+	 * inode.c/extents.c knows better, but for safety ... */
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
+			ext4_should_journal_data(inode))
+		metadata = 1;
+
 	sb = inode->i_sb;
-	if (!sb) {
-		printk ("ext4_free_blocks: nonexistent device");
-		return;
-	}
-	ext4_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
+
+	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);
 	if (dquot_freed_blocks)
 		DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
 	return;
@@ -920,9 +997,10 @@ claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
  * 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, int group,
-			struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal,
-			unsigned long *count, struct ext4_reserve_window *my_rsv)
+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;
@@ -1156,7 +1234,7 @@ static int find_next_reservable_window(
  */
 static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
 		ext4_grpblk_t grp_goal, struct super_block *sb,
-		unsigned int group, struct buffer_head *bitmap_bh)
+		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;
@@ -1354,7 +1432,7 @@ static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv,
  */
 static ext4_grpblk_t
 ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
-			unsigned int group, struct buffer_head *bitmap_bh,
+			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)
@@ -1510,7 +1588,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 }
 
 /**
- * ext4_new_blocks() -- core block(s) allocation function
+ * ext4_new_blocks_old() -- core block(s) allocation function
  * @handle:		handle to this transaction
  * @inode:		file inode
  * @goal:		given target block(filesystem wide)
@@ -1523,17 +1601,17 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
  * any specific goal block.
  *
  */
-ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
+ext4_fsblk_t ext4_new_blocks_old(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;
-	unsigned long group_no;
-	int goal_group;
+	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 */
-	int bgi;			/* blockgroup iteration index */
+	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 */
@@ -1544,10 +1622,7 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 	struct ext4_reserve_window_node *my_rsv = NULL;
 	struct ext4_block_alloc_info *block_i;
 	unsigned short windowsz = 0;
-#ifdef EXT4FS_DEBUG
-	static int goal_hits, goal_attempts;
-#endif
-	unsigned long ngroups;
+	ext4_group_t ngroups;
 	unsigned long num = *count;
 
 	*errp = -ENOSPC;
@@ -1567,7 +1642,7 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 
 	sbi = EXT4_SB(sb);
 	es = EXT4_SB(sb)->s_es;
-	ext4_debug("goal=%lu.\n", goal);
+	ext4_debug("goal=%llu.\n", goal);
 	/*
 	 * Allocate a block from reservation only when
 	 * filesystem is mounted with reservation(default,-o reservation), and
@@ -1677,7 +1752,7 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 
 allocated:
 
-	ext4_debug("using block group %d(%d)\n",
+	ext4_debug("using block group %lu(%d)\n",
 			group_no, gdp->bg_free_blocks_count);
 
 	BUFFER_TRACE(gdp_bh, "get_write_access");
@@ -1692,11 +1767,13 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 	    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_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);
+		goto out;
+	}
 
 	performed_allocation = 1;
 
@@ -1743,9 +1820,6 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 	 * list of some description.  We don't know in advance whether
 	 * the caller wants to use it as metadata or data.
 	 */
-	ext4_debug("allocating block %lu. Goal hits %d of %d.\n",
-			ret_block, goal_hits, goal_attempts);
-
 	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);
@@ -1787,13 +1861,46 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 }
 
 ext4_fsblk_t ext4_new_block(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t goal, int *errp)
+		ext4_fsblk_t goal, int *errp)
 {
-	unsigned long count = 1;
+	struct ext4_allocation_request ar;
+	ext4_fsblk_t ret;
 
-	return ext4_new_blocks(handle, inode, goal, &count, errp);
+	if (!test_opt(inode->i_sb, MBALLOC)) {
+		unsigned long count = 1;
+		ret = ext4_new_blocks_old(handle, inode, goal, &count, errp);
+		return ret;
+	}
+
+	memset(&ar, 0, sizeof(ar));
+	ar.inode = inode;
+	ar.goal = goal;
+	ar.len = 1;
+	ret = ext4_mb_new_blocks(handle, &ar, errp);
+	return ret;
+}
+
+ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
+		ext4_fsblk_t goal, unsigned long *count, int *errp)
+{
+	struct ext4_allocation_request ar;
+	ext4_fsblk_t ret;
+
+	if (!test_opt(inode->i_sb, MBALLOC)) {
+		ret = ext4_new_blocks_old(handle, inode, goal, count, errp);
+		return ret;
+	}
+
+	memset(&ar, 0, sizeof(ar));
+	ar.inode = inode;
+	ar.goal = goal;
+	ar.len = *count;
+	ret = ext4_mb_new_blocks(handle, &ar, errp);
+	*count = ar.len;
+	return ret;
 }
 
+
 /**
  * ext4_count_free_blocks() -- count filesystem free blocks
  * @sb:		superblock
@@ -1804,8 +1911,8 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 {
 	ext4_fsblk_t desc_count;
 	struct ext4_group_desc *gdp;
-	int i;
-	unsigned long ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t i;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
@@ -1829,14 +1936,14 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 			continue;
 
 		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
-		printk("group %d: stored = %d, counted = %lu\n",
+		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			i, le16_to_cpu(gdp->bg_free_blocks_count), x);
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);
 	printk("ext4_count_free_blocks: stored = %llu"
 		", computed = %llu, %llu\n",
-	       EXT4_FREE_BLOCKS_COUNT(es),
+		ext4_free_blocks_count(es),
 		desc_count, bitmap_count);
 	return bitmap_count;
 #else
@@ -1853,7 +1960,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 #endif
 }
 
-static inline int test_root(int a, int b)
+static inline int test_root(ext4_group_t a, int b)
 {
 	int num = b;
 
@@ -1862,7 +1969,7 @@ static inline int test_root(int a, int b)
 	return num == a;
 }
 
-static int ext4_group_sparse(int group)
+static int ext4_group_sparse(ext4_group_t group)
 {
 	if (group <= 1)
 		return 1;
@@ -1880,7 +1987,7 @@ static int ext4_group_sparse(int group)
  *	Return the number of blocks used by the superblock (primary or backup)
  *	in this group.  Currently this will be only 0 or 1.
  */
-int ext4_bg_has_super(struct super_block *sb, int group)
+int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
 {
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
@@ -1889,18 +1996,20 @@ int ext4_bg_has_super(struct super_block *sb, int group)
 	return 1;
 }
 
-static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group)
+static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
+					ext4_group_t group)
 {
 	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
-	unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb);
-	unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
+	ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb);
+	ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
 
 	if (group == first || group == first + 1 || group == last)
 		return 1;
 	return 0;
 }
 
-static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
+static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
+					ext4_group_t group)
 {
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
@@ -1918,7 +2027,7 @@ static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
  *	(primary or backup) in this group.  In the future there may be a
  *	different number of descriptor blocks in each group.
  */
-unsigned long ext4_bg_num_gdb(struct super_block *sb, int group)
+unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 {
 	unsigned long first_meta_bg =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);

fs/ext4/dir.c

@@ -67,7 +67,7 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
 			  unsigned long offset)
 {
 	const char * error_msg = NULL;
-	const int rlen = le16_to_cpu(de->rec_len);
+	const int rlen = ext4_rec_len_from_disk(de->rec_len);
 
 	if (rlen < EXT4_DIR_REC_LEN(1))
 		error_msg = "rec_len is smaller than minimal";
@@ -124,7 +124,7 @@ static int ext4_readdir(struct file * filp,
 	offset = filp->f_pos & (sb->s_blocksize - 1);
 
 	while (!error && !stored && filp->f_pos < inode->i_size) {
-		unsigned long blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
+		ext4_lblk_t blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
 		struct buffer_head map_bh;
 		struct buffer_head *bh = NULL;
 
@@ -172,10 +172,10 @@ static int ext4_readdir(struct file * filp,
 				 * least that it is non-zero.  A
 				 * failure will be detected in the
 				 * dirent test below. */
-				if (le16_to_cpu(de->rec_len) <
-						EXT4_DIR_REC_LEN(1))
+				if (ext4_rec_len_from_disk(de->rec_len)
+						< EXT4_DIR_REC_LEN(1))
 					break;
-				i += le16_to_cpu(de->rec_len);
+				i += ext4_rec_len_from_disk(de->rec_len);
 			}
 			offset = i;
 			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
@@ -197,7 +197,7 @@ static int ext4_readdir(struct file * filp,
 				ret = stored;
 				goto out;
 			}
-			offset += le16_to_cpu(de->rec_len);
+			offset += ext4_rec_len_from_disk(de->rec_len);
 			if (le32_to_cpu(de->inode)) {
 				/* We might block in the next section
 				 * if the data destination is
@@ -219,7 +219,7 @@ static int ext4_readdir(struct file * filp,
 					goto revalidate;
 				stored ++;
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
 		}
 		offset = 0;
 		brelse (bh);

fs/ext4/file.c

@@ -37,9 +37,9 @@ static int ext4_release_file (struct inode * inode, struct file * filp)
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1))
 	{
-		mutex_lock(&EXT4_I(inode)->truncate_mutex);
+		down_write(&EXT4_I(inode)->i_data_sem);
 		ext4_discard_reservation(inode);
-		mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
 		ext4_htree_free_dir_info(filp->private_data);
@@ -56,8 +56,25 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t ret;
 	int err;
 
-	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+
+	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+		size_t length = iov_length(iov, nr_segs);
 
+		if (pos > sbi->s_bitmap_maxbytes)
+			return -EFBIG;
+
+		if (pos + length > sbi->s_bitmap_maxbytes) {
+			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
+					      sbi->s_bitmap_maxbytes - pos);
+		}
+	}
+
+	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
 	/*
 	 * Skip flushing if there was an error, or if nothing was written.
 	 */

fs/ext4/group.h

@@ -14,14 +14,16 @@ extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
 extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
 				       struct ext4_group_desc *gdp);
 struct buffer_head *read_block_bitmap(struct super_block *sb,
-				      unsigned int block_group);
+				      ext4_group_t block_group);
 extern unsigned ext4_init_block_bitmap(struct super_block *sb,
-				       struct buffer_head *bh, int group,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
 				       struct ext4_group_desc *desc);
 #define ext4_free_blocks_after_init(sb, group, desc)			\
 		ext4_init_block_bitmap(sb, NULL, group, desc)
 extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
-				       struct buffer_head *bh, int group,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
 				       struct ext4_group_desc *desc);
 extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
 #endif /* _LINUX_EXT4_GROUP_H */

fs/ext4/ialloc.c

@@ -64,8 +64,8 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 }
 
 /* Initializes an uninitialized inode bitmap */
-unsigned ext4_init_inode_bitmap(struct super_block *sb,
-				struct buffer_head *bh, int block_group,
+unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
+				ext4_group_t block_group,
 				struct ext4_group_desc *gdp)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -75,7 +75,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
-		ext4_error(sb, __FUNCTION__, "Checksum bad for group %u\n",
+		ext4_error(sb, __FUNCTION__, "Checksum bad for group %lu\n",
 			   block_group);
 		gdp->bg_free_blocks_count = 0;
 		gdp->bg_free_inodes_count = 0;
@@ -98,7 +98,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb,
  * Return buffer_head of bitmap on success or NULL.
  */
 static struct buffer_head *
-read_inode_bitmap(struct super_block * sb, unsigned long block_group)
+read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 {
 	struct ext4_group_desc *desc;
 	struct buffer_head *bh = NULL;
@@ -152,7 +152,7 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
 	unsigned long ino;
 	struct buffer_head *bitmap_bh = NULL;
 	struct buffer_head *bh2;
-	unsigned long block_group;
+	ext4_group_t block_group;
 	unsigned long bit;
 	struct ext4_group_desc * gdp;
 	struct ext4_super_block * es;
@@ -260,12 +260,14 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
  * For other inodes, search forward from the parent directory\'s block
  * group to find a free inode.
  */
-static int find_group_dir(struct super_block *sb, struct inode *parent)
+static int find_group_dir(struct super_block *sb, struct inode *parent,
+				ext4_group_t *best_group)
 {
-	int ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
 	unsigned int freei, avefreei;
 	struct ext4_group_desc *desc, *best_desc = NULL;
-	int group, best_group = -1;
+	ext4_group_t group;
+	int ret = -1;
 
 	freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
 	avefreei = freei / ngroups;
@@ -279,11 +281,12 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
 		if (!best_desc ||
 		    (le16_to_cpu(desc->bg_free_blocks_count) >
 		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
-			best_group = group;
+			*best_group = group;
 			best_desc = desc;
+			ret = 0;
 		}
 	}
-	return best_group;
+	return ret;
 }
 
 /*
@@ -314,12 +317,13 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
 #define INODE_COST 64
 #define BLOCK_COST 256
 
-static int find_group_orlov(struct super_block *sb, struct inode *parent)
+static int find_group_orlov(struct super_block *sb, struct inode *parent,
+				ext4_group_t *group)
 {
-	int parent_group = EXT4_I(parent)->i_block_group;
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	int ngroups = sbi->s_groups_count;
+	ext4_group_t ngroups = sbi->s_groups_count;
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei;
 	ext4_fsblk_t freeb, avefreeb;
@@ -327,7 +331,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 	unsigned int ndirs;
 	int max_debt, max_dirs, min_inodes;
 	ext4_grpblk_t min_blocks;
-	int group = -1, i;
+	ext4_group_t i;
 	struct ext4_group_desc *desc;
 
 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
@@ -340,13 +344,14 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 	if ((parent == sb->s_root->d_inode) ||
 	    (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
 		int best_ndir = inodes_per_group;
-		int best_group = -1;
+		ext4_group_t grp;
+		int ret = -1;
 
-		get_random_bytes(&group, sizeof(group));
-		parent_group = (unsigned)group % ngroups;
+		get_random_bytes(&grp, sizeof(grp));
+		parent_group = (unsigned)grp % ngroups;
 		for (i = 0; i < ngroups; i++) {
-			group = (parent_group + i) % ngroups;
-			desc = ext4_get_group_desc (sb, group, NULL);
+			grp = (parent_group + i) % ngroups;
+			desc = ext4_get_group_desc(sb, grp, NULL);
 			if (!desc || !desc->bg_free_inodes_count)
 				continue;
 			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
@@ -355,11 +360,12 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 				continue;
 			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
 				continue;
-			best_group = group;
+			*group = grp;
+			ret = 0;
 			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
 		}
-		if (best_group >= 0)
-			return best_group;
+		if (ret == 0)
+			return ret;
 		goto fallback;
 	}
 
@@ -380,8 +386,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 		max_debt = 1;
 
 	for (i = 0; i < ngroups; i++) {
-		group = (parent_group + i) % ngroups;
-		desc = ext4_get_group_desc (sb, group, NULL);
+		*group = (parent_group + i) % ngroups;
+		desc = ext4_get_group_desc(sb, *group, NULL);
 		if (!desc || !desc->bg_free_inodes_count)
 			continue;
 		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
@@ -390,17 +396,16 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 			continue;
 		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
 			continue;
-		return group;
+		return 0;
 	}
 
 fallback:
 	for (i = 0; i < ngroups; i++) {
-		group = (parent_group + i) % ngroups;
-		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)
-			return group;
+		*group = (parent_group + i) % ngroups;
+		desc = ext4_get_group_desc(sb, *group, NULL);
+		if (desc && desc->bg_free_inodes_count &&
+			le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+			return 0;
 	}
 
 	if (avefreei) {
@@ -415,21 +420,22 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 	return -1;
 }
 
-static int find_group_other(struct super_block *sb, struct inode *parent)
+static int find_group_other(struct super_block *sb, struct inode *parent,
+				ext4_group_t *group)
 {
-	int parent_group = EXT4_I(parent)->i_block_group;
-	int ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
 	struct ext4_group_desc *desc;
-	int group, i;
+	ext4_group_t i;
 
 	/*
 	 * Try to place the inode in its parent directory
 	 */
-	group = parent_group;
-	desc = ext4_get_group_desc (sb, group, NULL);
+	*group = parent_group;
+	desc = ext4_get_group_desc(sb, *group, NULL);
 	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
 			le16_to_cpu(desc->bg_free_blocks_count))
-		return group;
+		return 0;
 
 	/*
 	 * We're going to place this inode in a different blockgroup from its
@@ -440,33 +446,33 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
 	 *
 	 * So add our directory's i_ino into the starting point for the hash.
 	 */
-	group = (group + parent->i_ino) % ngroups;
+	*group = (*group + parent->i_ino) % ngroups;
 
 	/*
 	 * Use a quadratic hash to find a group with a free inode and some free
 	 * blocks.
 	 */
 	for (i = 1; i < ngroups; i <<= 1) {
-		group += i;
-		if (group >= ngroups)
-			group -= ngroups;
-		desc = ext4_get_group_desc (sb, group, NULL);
+		*group += i;
+		if (*group >= ngroups)
+			*group -= ngroups;
+		desc = ext4_get_group_desc(sb, *group, NULL);
 		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
 				le16_to_cpu(desc->bg_free_blocks_count))
-			return group;
+			return 0;
 	}
 
 	/*
 	 * That failed: try linear search for a free inode, even if that group
 	 * has no free blocks.
 	 */
-	group = parent_group;
+	*group = parent_group;
 	for (i = 0; i < ngroups; i++) {
-		if (++group >= ngroups)
-			group = 0;
-		desc = ext4_get_group_desc (sb, group, NULL);
+		if (++*group >= ngroups)
+			*group = 0;
+		desc = ext4_get_group_desc(sb, *group, NULL);
 		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
-			return group;
+			return 0;
 	}
 
 	return -1;
@@ -487,16 +493,17 @@ 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;
-	int group;
+	ext4_group_t group = 0;
 	unsigned long ino = 0;
 	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 err = 0;
+	int ret2, err = 0;
 	struct inode *ret;
-	int i, free = 0;
+	ext4_group_t i;
+	int free = 0;
 
 	/* Cannot create files in a deleted directory */
 	if (!dir || !dir->i_nlink)
@@ -512,14 +519,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	es = sbi->s_es;
 	if (S_ISDIR(mode)) {
 		if (test_opt (sb, OLDALLOC))
-			group = find_group_dir(sb, dir);
+			ret2 = find_group_dir(sb, dir, &group);
 		else
-			group = find_group_orlov(sb, dir);
+			ret2 = find_group_orlov(sb, dir, &group);
 	} else
-		group = find_group_other(sb, dir);
+		ret2 = find_group_other(sb, dir, &group);
 
 	err = -ENOSPC;
-	if (group == -1)
+	if (ret2 == -1)
 		goto out;
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
@@ -583,7 +590,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	    ino > EXT4_INODES_PER_GROUP(sb)) {
 		ext4_error(sb, __FUNCTION__,
 			   "reserved inode or inode > inodes count - "
-			   "block_group = %d, inode=%lu", group,
+			   "block_group = %lu, inode=%lu", group,
 			   ino + group * EXT4_INODES_PER_GROUP(sb));
 		err = -EIO;
 		goto fail;
@@ -702,7 +709,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	if (!S_ISDIR(mode))
 		ei->i_flags &= ~EXT4_DIRSYNC_FL;
 	ei->i_file_acl = 0;
-	ei->i_dir_acl = 0;
 	ei->i_dtime = 0;
 	ei->i_block_alloc_info = NULL;
 	ei->i_block_group = group;
@@ -741,13 +747,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	if (test_opt(sb, EXTENTS)) {
 		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
 		ext4_ext_tree_init(handle, inode);
-		if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
-			err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
-			if (err) goto fail;
-			EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
-			BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
-			err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
-		}
+		err = ext4_update_incompat_feature(handle, sb,
+						EXT4_FEATURE_INCOMPAT_EXTENTS);
+		if (err)
+			goto fail;
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
@@ -777,7 +780,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 {
 	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
-	unsigned long block_group;
+	ext4_group_t block_group;
 	int bit;
 	struct buffer_head *bitmap_bh = NULL;
 	struct inode *inode = NULL;
@@ -833,7 +836,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 {
 	unsigned long desc_count;
 	struct ext4_group_desc *gdp;
-	int i;
+	ext4_group_t i;
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	unsigned long bitmap_count, x;
@@ -854,7 +857,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 			continue;
 
 		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
-		printk("group %d: stored = %d, counted = %lu\n",
+		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			i, le16_to_cpu(gdp->bg_free_inodes_count), x);
 		bitmap_count += x;
 	}
@@ -879,7 +882,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 unsigned long ext4_count_dirs (struct super_block * sb)
 {
 	unsigned long count = 0;
-	int i;
+	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);

fs/ext4/ioctl.c

@@ -199,7 +199,7 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * need to allocate reservation structure for this inode
 		 * before set the window size
 		 */
-		mutex_lock(&ei->truncate_mutex);
+		down_write(&ei->i_data_sem);
 		if (!ei->i_block_alloc_info)
 			ext4_init_block_alloc_info(inode);
 
@@ -207,7 +207,7 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 			struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
 			rsv->rsv_goal_size = rsv_window_size;
 		}
-		mutex_unlock(&ei->truncate_mutex);
+		up_write(&ei->i_data_sem);
 		return 0;
 	}
 	case EXT4_IOC_GROUP_EXTEND: {
@@ -254,6 +254,9 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		return err;
 	}
 
+	case EXT4_IOC_MIGRATE:
+		return ext4_ext_migrate(inode, filp, cmd, arg);
+
 	default:
 		return -ENOTTY;
 	}

fs/ext4/migrate.c

+/*
+ * Copyright IBM Corporation, 2007
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs_extents.h>
+
+/*
+ * The contiguous blocks details which can be
+ * represented by a single extent
+ */
+struct list_blocks_struct {
+	ext4_lblk_t first_block, last_block;
+	ext4_fsblk_t first_pblock, last_pblock;
+};
+
+static int finish_range(handle_t *handle, struct inode *inode,
+				struct list_blocks_struct *lb)
+
+{
+	int retval = 0, needed;
+	struct ext4_extent newext;
+	struct ext4_ext_path *path;
+	if (lb->first_pblock == 0)
+		return 0;
+
+	/* Add the extent to temp inode*/
+	newext.ee_block = cpu_to_le32(lb->first_block);
+	newext.ee_len   = cpu_to_le16(lb->last_block - lb->first_block + 1);
+	ext4_ext_store_pblock(&newext, lb->first_pblock);
+	path = ext4_ext_find_extent(inode, lb->first_block, NULL);
+
+	if (IS_ERR(path)) {
+		retval = PTR_ERR(path);
+		goto err_out;
+	}
+
+	/*
+	 * Calculate the credit needed to inserting this extent
+	 * Since we are doing this in loop we may accumalate extra
+	 * credit. But below we try to not accumalate too much
+	 * of them by restarting the journal.
+	 */
+	needed = ext4_ext_calc_credits_for_insert(inode, path);
+
+	/*
+	 * Make sure the credit we accumalated is not really high
+	 */
+	if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
+		retval = ext4_journal_restart(handle, needed);
+		if (retval)
+			goto err_out;
+	}
+	if (needed) {
+		retval = ext4_journal_extend(handle, needed);
+		if (retval != 0) {
+			/*
+			 * IF not able to extend the journal restart the journal
+			 */
+			retval = ext4_journal_restart(handle, needed);
+			if (retval)
+				goto err_out;
+		}
+	}
+	retval = ext4_ext_insert_extent(handle, inode, path, &newext);
+err_out:
+	lb->first_pblock = 0;
+	return retval;
+}
+
+static int update_extent_range(handle_t *handle, struct inode *inode,
+				ext4_fsblk_t pblock, ext4_lblk_t blk_num,
+				struct list_blocks_struct *lb)
+{
+	int retval;
+	/*
+	 * See if we can add on to the existing range (if it exists)
+	 */
+	if (lb->first_pblock &&
+		(lb->last_pblock+1 == pblock) &&
+		(lb->last_block+1 == blk_num)) {
+		lb->last_pblock = pblock;
+		lb->last_block = blk_num;
+		return 0;
+	}
+	/*
+	 * Start a new range.
+	 */
+	retval = finish_range(handle, inode, lb);
+	lb->first_pblock = lb->last_pblock = pblock;
+	lb->first_block = lb->last_block = blk_num;
+
+	return retval;
+}
+
+static int update_ind_extent_range(handle_t *handle, struct inode *inode,
+				   ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				   struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries;
+		return 0;
+	}
+
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++, blk_count++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						blk_count, lb);
+			if (retval)
+				break;
+		}
+	}
+
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_dind_extent_range(handle_t *handle, struct inode *inode,
+				    ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				    struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries * max_entries;
+		return 0;
+	}
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_ind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						&blk_count, lb);
+			if (retval)
+				break;
+		} else {
+			/* Only update the file block number */
+			blk_count += max_entries;
+		}
+	}
+
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_tind_extent_range(handle_t *handle, struct inode *inode,
+				     ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				     struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries * max_entries * max_entries;
+		return 0;
+	}
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_dind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						&blk_count, lb);
+			if (retval)
+				break;
+		} else
+			/* Only update the file block number */
+			blk_count += max_entries * max_entries;
+	}
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int free_dind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
+	if (!bh)
+		return -EIO;
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i])
+			ext4_free_blocks(handle, inode,
+					le32_to_cpu(tmp_idata[i]), 1, 1);
+	}
+	put_bh(bh);
+	ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+	return 0;
+}
+
+static int free_tind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i, retval = 0;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
+	if (!bh)
+		return -EIO;
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i]) {
+			retval = free_dind_blocks(handle,
+					inode, tmp_idata[i]);
+			if (retval) {
+				put_bh(bh);
+				return retval;
+			}
+		}
+	}
+	put_bh(bh);
+	ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+	return 0;
+}
+
+static int free_ind_block(handle_t *handle, struct inode *inode)
+{
+	int retval;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (ei->i_data[EXT4_IND_BLOCK])
+		ext4_free_blocks(handle, inode,
+				le32_to_cpu(ei->i_data[EXT4_IND_BLOCK]), 1, 1);
+
+	if (ei->i_data[EXT4_DIND_BLOCK]) {
+		retval = free_dind_blocks(handle, inode,
+						ei->i_data[EXT4_DIND_BLOCK]);
+		if (retval)
+			return retval;
+	}
+
+	if (ei->i_data[EXT4_TIND_BLOCK]) {
+		retval = free_tind_blocks(handle, inode,
+						ei->i_data[EXT4_TIND_BLOCK]);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
+				struct inode *tmp_inode, int retval)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
+
+	retval = free_ind_block(handle, inode);
+	if (retval)
+		goto err_out;
+
+	/*
+	 * One credit accounted for writing the
+	 * i_data field of the original inode
+	 */
+	retval = ext4_journal_extend(handle, 1);
+	if (retval != 0) {
+		retval = ext4_journal_restart(handle, 1);
+		if (retval)
+			goto err_out;
+	}
+
+	/*
+	 * We have the extent map build with the tmp inode.
+	 * Now copy the i_data across
+	 */
+	ei->i_flags |= EXT4_EXTENTS_FL;
+	memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
+
+	/*
+	 * Update i_blocks with the new blocks that got
+	 * allocated while adding extents for extent index
+	 * blocks.
+	 *
+	 * While converting to extents we need not
+	 * update the orignal inode i_blocks for extent blocks
+	 * via quota APIs. The quota update happened via tmp_inode already.
+	 */
+	spin_lock(&inode->i_lock);
+	inode->i_blocks += tmp_inode->i_blocks;
+	spin_unlock(&inode->i_lock);
+
+	ext4_mark_inode_dirty(handle, inode);
+err_out:
+	return retval;
+}
+
+static int free_ext_idx(handle_t *handle, struct inode *inode,
+					struct ext4_extent_idx *ix)
+{
+	int i, retval = 0;
+	ext4_fsblk_t block;
+	struct buffer_head *bh;
+	struct ext4_extent_header *eh;
+
+	block = idx_pblock(ix);
+	bh = sb_bread(inode->i_sb, block);
+	if (!bh)
+		return -EIO;
+
+	eh = (struct ext4_extent_header *)bh->b_data;
+	if (eh->eh_depth != 0) {
+		ix = EXT_FIRST_INDEX(eh);
+		for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+			retval = free_ext_idx(handle, inode, ix);
+			if (retval)
+				break;
+		}
+	}
+	put_bh(bh);
+	ext4_free_blocks(handle, inode, block, 1, 1);
+	return retval;
+}
+
+/*
+ * Free the extent meta data blocks only
+ */
+static int free_ext_block(handle_t *handle, struct inode *inode)
+{
+	int i, retval = 0;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data;
+	struct ext4_extent_idx *ix;
+	if (eh->eh_depth == 0)
+		/*
+		 * No extra blocks allocated for extent meta data
+		 */
+		return 0;
+	ix = EXT_FIRST_INDEX(eh);
+	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+		retval = free_ext_idx(handle, inode, ix);
+		if (retval)
+			return retval;
+	}
+	return retval;
+
+}
+
+int ext4_ext_migrate(struct inode *inode, struct file *filp,
+				unsigned int cmd, unsigned long arg)
+{
+	handle_t *handle;
+	int retval = 0, i;
+	__le32 *i_data;
+	ext4_lblk_t blk_count = 0;
+	struct ext4_inode_info *ei;
+	struct inode *tmp_inode = NULL;
+	struct list_blocks_struct lb;
+	unsigned long max_entries;
+
+	if (!test_opt(inode->i_sb, EXTENTS))
+		/*
+		 * if mounted with noextents we don't allow the migrate
+		 */
+		return -EINVAL;
+
+	if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+		return -EINVAL;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	handle = ext4_journal_start(inode,
+					EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+					2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
+					+ 1);
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto err_out;
+	}
+	tmp_inode = ext4_new_inode(handle,
+				inode->i_sb->s_root->d_inode,
+				S_IFREG);
+	if (IS_ERR(tmp_inode)) {
+		retval = -ENOMEM;
+		ext4_journal_stop(handle);
+		tmp_inode = NULL;
+		goto err_out;
+	}
+	i_size_write(tmp_inode, i_size_read(inode));
+	/*
+	 * We don't want the inode to be reclaimed
+	 * if we got interrupted in between. We have
+	 * this tmp inode carrying reference to the
+	 * data blocks of the original file. We set
+	 * the i_nlink to zero at the last stage after
+	 * switching the original file to extent format
+	 */
+	tmp_inode->i_nlink = 1;
+
+	ext4_ext_tree_init(handle, tmp_inode);
+	ext4_orphan_add(handle, tmp_inode);
+	ext4_journal_stop(handle);
+
+	ei = EXT4_I(inode);
+	i_data = ei->i_data;
+	memset(&lb, 0, sizeof(lb));
+
+	/* 32 bit block address 4 bytes */
+	max_entries = inode->i_sb->s_blocksize >> 2;
+
+	/*
+	 * start with one credit accounted for
+	 * superblock modification.
+	 *
+	 * For the tmp_inode we already have commited the
+	 * trascation that created the inode. Later as and
+	 * when we add extents we extent the journal
+	 */
+	handle = ext4_journal_start(inode, 1);
+	for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, tmp_inode,
+						le32_to_cpu(i_data[i]),
+						blk_count, &lb);
+			if (retval)
+				goto err_out;
+		}
+	}
+	if (i_data[EXT4_IND_BLOCK]) {
+		retval = update_ind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_IND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	} else
+		blk_count +=  max_entries;
+	if (i_data[EXT4_DIND_BLOCK]) {
+		retval = update_dind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	} else
+		blk_count += max_entries * max_entries;
+	if (i_data[EXT4_TIND_BLOCK]) {
+		retval = update_tind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	}
+	/*
+	 * Build the last extent
+	 */
+	retval = finish_range(handle, tmp_inode, &lb);
+err_out:
+	/*
+	 * We are either freeing extent information or indirect
+	 * blocks. During this we touch superblock, group descriptor
+	 * and block bitmap. Later we mark the tmp_inode dirty
+	 * via ext4_ext_tree_init. So allocate a credit of 4
+	 * We may update quota (user and group).
+	 *
+	 * FIXME!! we may be touching bitmaps in different block groups.
+	 */
+	if (ext4_journal_extend(handle,
+			4 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb)) != 0)
+		ext4_journal_restart(handle,
+				4 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb));
+	if (retval)
+		/*
+		 * Failure case delete the extent information with the
+		 * tmp_inode
+		 */
+		free_ext_block(handle, tmp_inode);
+	else
+		retval = ext4_ext_swap_inode_data(handle, inode,
+							tmp_inode, retval);
+
+	/*
+	 * Mark the tmp_inode as of size zero
+	 */
+	i_size_write(tmp_inode, 0);
+
+	/*
+	 * set the  i_blocks count to zero
+	 * so that the ext4_delete_inode does the
+	 * right job
+	 *
+	 * We don't need to take the i_lock because
+	 * the inode is not visible to user space.
+	 */
+	tmp_inode->i_blocks = 0;
+
+	/* Reset the extent details */
+	ext4_ext_tree_init(handle, tmp_inode);
+
+	/*
+	 * Set the i_nlink to zero so that
+	 * generic_drop_inode really deletes the
+	 * inode
+	 */
+	tmp_inode->i_nlink = 0;
+
+	ext4_journal_stop(handle);
+
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+	if (tmp_inode)
+		iput(tmp_inode);
+
+	return retval;
+}

fs/ext4/namei.c

@@ -51,7 +51,7 @@
 
 static struct buffer_head *ext4_append(handle_t *handle,
 					struct inode *inode,
-					u32 *block, int *err)
+					ext4_lblk_t *block, int *err)
 {
 	struct buffer_head *bh;
 
@@ -144,8 +144,8 @@ struct dx_map_entry
 	u16 size;
 };
 
-static inline unsigned dx_get_block (struct dx_entry *entry);
-static void dx_set_block (struct dx_entry *entry, unsigned value);
+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);
@@ -166,7 +166,8 @@ 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,
 		struct dx_map_entry *offsets, int count);
 static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
-static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
+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,
@@ -181,12 +182,12 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
  * Mask them off for now.
  */
 
-static inline unsigned dx_get_block (struct dx_entry *entry)
+static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
 {
 	return le32_to_cpu(entry->block) & 0x00ffffff;
 }
 
-static inline void dx_set_block (struct dx_entry *entry, unsigned value)
+static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
 {
 	entry->block = cpu_to_le32(value);
 }
@@ -243,8 +244,8 @@ static void dx_show_index (char * label, struct dx_entry *entries)
 	int i, n = dx_get_count (entries);
 	printk("%s index ", label);
 	for (i = 0; i < n; i++) {
-		printk("%x->%u ", i? dx_get_hash(entries + i) :
-				0, dx_get_block(entries + i));
+		printk("%x->%lu ", i? dx_get_hash(entries + i) :
+				0, (unsigned long)dx_get_block(entries + i));
 	}
 	printk("\n");
 }
@@ -280,7 +281,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent
 			space += EXT4_DIR_REC_LEN(de->name_len);
 			names++;
 		}
-		de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
+		de = ext4_next_entry(de);
 	}
 	printk("(%i)\n", names);
 	return (struct stats) { names, space, 1 };
@@ -297,7 +298,8 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
 	printk("%i indexed blocks...\n", count);
 	for (i = 0; i < count; i++, entries++)
 	{
-		u32 block = dx_get_block(entries), hash = i? dx_get_hash(entries): 0;
+		ext4_lblk_t block = dx_get_block(entries);
+		ext4_lblk_t hash  = i ? dx_get_hash(entries): 0;
 		u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
 		struct stats stats;
 		printk("%s%3u:%03u hash %8x/%8x ",levels?"":"   ", i, block, hash, range);
@@ -551,7 +553,8 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
  */
 static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *p)
 {
-	return (struct ext4_dir_entry_2 *)((char*)p + le16_to_cpu(p->rec_len));
+	return (struct ext4_dir_entry_2 *)((char *)p +
+		ext4_rec_len_from_disk(p->rec_len));
 }
 
 /*
@@ -560,7 +563,7 @@ static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *
  * into the tree.  If there is an error it is returned in err.
  */
 static int htree_dirblock_to_tree(struct file *dir_file,
-				  struct inode *dir, int block,
+				  struct inode *dir, ext4_lblk_t block,
 				  struct dx_hash_info *hinfo,
 				  __u32 start_hash, __u32 start_minor_hash)
 {
@@ -568,7 +571,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 	struct ext4_dir_entry_2 *de, *top;
 	int err, count = 0;
 
-	dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));
+	dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
+							(unsigned long)block));
 	if (!(bh = ext4_bread (NULL, dir, block, 0, &err)))
 		return err;
 
@@ -620,9 +624,9 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	struct ext4_dir_entry_2 *de;
 	struct dx_frame frames[2], *frame;
 	struct inode *dir;
-	int block, err;
+	ext4_lblk_t block;
 	int count = 0;
-	int ret;
+	int ret, err;
 	__u32 hashval;
 
 	dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
@@ -720,7 +724,7 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
 			cond_resched();
 		}
 		/* XXX: do we need to check rec_len == 0 case? -Chris */
-		de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
+		de = ext4_next_entry(de);
 	}
 	return count;
 }
@@ -752,7 +756,7 @@ static void dx_sort_map (struct dx_map_entry *map, unsigned count)
 	} while(more);
 }
 
-static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block)
+static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
 {
 	struct dx_entry *entries = frame->entries;
 	struct dx_entry *old = frame->at, *new = old + 1;
@@ -820,7 +824,7 @@ static inline int search_dirblock(struct buffer_head * bh,
 			return 1;
 		}
 		/* prevent looping on a bad block */
-		de_len = le16_to_cpu(de->rec_len);
+		de_len = ext4_rec_len_from_disk(de->rec_len);
 		if (de_len <= 0)
 			return -1;
 		offset += de_len;
@@ -847,23 +851,20 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 	struct super_block * sb;
 	struct buffer_head * bh_use[NAMEI_RA_SIZE];
 	struct buffer_head * bh, *ret = NULL;
-	unsigned long start, block, b;
+	ext4_lblk_t start, block, b;
 	int ra_max = 0;		/* Number of bh's in the readahead
 				   buffer, bh_use[] */
 	int ra_ptr = 0;		/* Current index into readahead
 				   buffer */
 	int num = 0;
-	int nblocks, i, err;
+	ext4_lblk_t  nblocks;
+	int i, err;
 	struct inode *dir = dentry->d_parent->d_inode;
 	int namelen;
-	const u8 *name;
-	unsigned blocksize;
 
 	*res_dir = NULL;
 	sb = dir->i_sb;
-	blocksize = sb->s_blocksize;
 	namelen = dentry->d_name.len;
-	name = dentry->d_name.name;
 	if (namelen > EXT4_NAME_LEN)
 		return NULL;
 	if (is_dx(dir)) {
@@ -914,7 +915,8 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 		if (!buffer_uptodate(bh)) {
 			/* read error, skip block & hope for the best */
 			ext4_error(sb, __FUNCTION__, "reading directory #%lu "
-				   "offset %lu", dir->i_ino, block);
+				   "offset %lu", dir->i_ino,
+				   (unsigned long)block);
 			brelse(bh);
 			goto next;
 		}
@@ -961,7 +963,7 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 	struct dx_frame frames[2], *frame;
 	struct ext4_dir_entry_2 *de, *top;
 	struct buffer_head *bh;
-	unsigned long block;
+	ext4_lblk_t block;
 	int retval;
 	int namelen = dentry->d_name.len;
 	const u8 *name = dentry->d_name.name;
@@ -1128,7 +1130,7 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
 		rec_len = EXT4_DIR_REC_LEN(de->name_len);
 		memcpy (to, de, rec_len);
 		((struct ext4_dir_entry_2 *) to)->rec_len =
-				cpu_to_le16(rec_len);
+				ext4_rec_len_to_disk(rec_len);
 		de->inode = 0;
 		map++;
 		to += rec_len;
@@ -1147,13 +1149,12 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size)
 
 	prev = to = de;
 	while ((char*)de < base + size) {
-		next = (struct ext4_dir_entry_2 *) ((char *) de +
-						    le16_to_cpu(de->rec_len));
+		next = ext4_next_entry(de);
 		if (de->inode && de->name_len) {
 			rec_len = EXT4_DIR_REC_LEN(de->name_len);
 			if (de > to)
 				memmove(to, de, rec_len);
-			to->rec_len = cpu_to_le16(rec_len);
+			to->rec_len = ext4_rec_len_to_disk(rec_len);
 			prev = to;
 			to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len);
 		}
@@ -1174,7 +1175,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	unsigned blocksize = dir->i_sb->s_blocksize;
 	unsigned count, continued;
 	struct buffer_head *bh2;
-	u32 newblock;
+	ext4_lblk_t newblock;
 	u32 hash2;
 	struct dx_map_entry *map;
 	char *data1 = (*bh)->b_data, *data2;
@@ -1221,14 +1222,15 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	split = count - move;
 	hash2 = map[split].hash;
 	continued = hash2 == map[split - 1].hash;
-	dxtrace(printk("Split block %i at %x, %i/%i\n",
-		dx_get_block(frame->at), hash2, split, count-split));
+	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
+			(unsigned long)dx_get_block(frame->at),
+					hash2, split, count-split));
 
 	/* Fancy dance to stay within two buffers */
 	de2 = dx_move_dirents(data1, data2, map + split, count - split);
 	de = dx_pack_dirents(data1,blocksize);
-	de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
-	de2->rec_len = cpu_to_le16(data2 + blocksize - (char *) de2);
+	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));
 	dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
 
@@ -1297,7 +1299,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 				return -EEXIST;
 			}
 			nlen = EXT4_DIR_REC_LEN(de->name_len);
-			rlen = le16_to_cpu(de->rec_len);
+			rlen = ext4_rec_len_from_disk(de->rec_len);
 			if ((de->inode? rlen - nlen: rlen) >= reclen)
 				break;
 			de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
@@ -1316,11 +1318,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 
 	/* By now the buffer is marked for journaling */
 	nlen = EXT4_DIR_REC_LEN(de->name_len);
-	rlen = le16_to_cpu(de->rec_len);
+	rlen = ext4_rec_len_from_disk(de->rec_len);
 	if (de->inode) {
 		struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen);
-		de1->rec_len = cpu_to_le16(rlen - nlen);
-		de->rec_len = cpu_to_le16(nlen);
+		de1->rec_len = ext4_rec_len_to_disk(rlen - nlen);
+		de->rec_len = ext4_rec_len_to_disk(nlen);
 		de = de1;
 	}
 	de->file_type = EXT4_FT_UNKNOWN;
@@ -1374,7 +1376,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	int		retval;
 	unsigned	blocksize;
 	struct dx_hash_info hinfo;
-	u32		block;
+	ext4_lblk_t  block;
 	struct fake_dirent *fde;
 
 	blocksize =  dir->i_sb->s_blocksize;
@@ -1397,17 +1399,18 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	/* The 0th block becomes the root, move the dirents out */
 	fde = &root->dotdot;
-	de = (struct ext4_dir_entry_2 *)((char *)fde + le16_to_cpu(fde->rec_len));
+	de = (struct ext4_dir_entry_2 *)((char *)fde +
+		ext4_rec_len_from_disk(fde->rec_len));
 	len = ((char *) root) + blocksize - (char *) de;
 	memcpy (data1, de, len);
 	de = (struct ext4_dir_entry_2 *) data1;
 	top = data1 + len;
-	while ((char *)(de2=(void*)de+le16_to_cpu(de->rec_len)) < top)
+	while ((char *)(de2 = ext4_next_entry(de)) < top)
 		de = de2;
-	de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
+	de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
 	/* Initialize the root; the dot dirents already exist */
 	de = (struct ext4_dir_entry_2 *) (&root->dotdot);
-	de->rec_len = cpu_to_le16(blocksize - EXT4_DIR_REC_LEN(2));
+	de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2));
 	memset (&root->info, 0, sizeof(root->info));
 	root->info.info_length = sizeof(root->info);
 	root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
@@ -1454,7 +1457,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 	int	retval;
 	int	dx_fallback=0;
 	unsigned blocksize;
-	u32 block, blocks;
+	ext4_lblk_t block, blocks;
 
 	sb = dir->i_sb;
 	blocksize = sb->s_blocksize;
@@ -1487,7 +1490,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 		return retval;
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	de->inode = 0;
-	de->rec_len = cpu_to_le16(blocksize);
+	de->rec_len = ext4_rec_len_to_disk(blocksize);
 	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
 
@@ -1531,7 +1534,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 		       dx_get_count(entries), dx_get_limit(entries)));
 	/* Need to split index? */
 	if (dx_get_count(entries) == dx_get_limit(entries)) {
-		u32 newblock;
+		ext4_lblk_t newblock;
 		unsigned icount = dx_get_count(entries);
 		int levels = frame - frames;
 		struct dx_entry *entries2;
@@ -1550,7 +1553,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			goto cleanup;
 		node2 = (struct dx_node *)(bh2->b_data);
 		entries2 = node2->entries;
-		node2->fake.rec_len = cpu_to_le16(sb->s_blocksize);
+		node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize);
 		node2->fake.inode = 0;
 		BUFFER_TRACE(frame->bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, frame->bh);
@@ -1648,9 +1651,9 @@ static int ext4_delete_entry (handle_t *handle,
 			BUFFER_TRACE(bh, "get_write_access");
 			ext4_journal_get_write_access(handle, bh);
 			if (pde)
-				pde->rec_len =
-					cpu_to_le16(le16_to_cpu(pde->rec_len) +
-						    le16_to_cpu(de->rec_len));
+				pde->rec_len = ext4_rec_len_to_disk(
+					ext4_rec_len_from_disk(pde->rec_len) +
+					ext4_rec_len_from_disk(de->rec_len));
 			else
 				de->inode = 0;
 			dir->i_version++;
@@ -1658,10 +1661,9 @@ static int ext4_delete_entry (handle_t *handle,
 			ext4_journal_dirty_metadata(handle, bh);
 			return 0;
 		}
-		i += le16_to_cpu(de->rec_len);
+		i += ext4_rec_len_from_disk(de->rec_len);
 		pde = de;
-		de = (struct ext4_dir_entry_2 *)
-			((char *) de + le16_to_cpu(de->rec_len));
+		de = ext4_next_entry(de);
 	}
 	return -ENOENT;
 }
@@ -1824,13 +1826,13 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 	de = (struct ext4_dir_entry_2 *) dir_block->b_data;
 	de->inode = cpu_to_le32(inode->i_ino);
 	de->name_len = 1;
-	de->rec_len = cpu_to_le16(EXT4_DIR_REC_LEN(de->name_len));
+	de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len));
 	strcpy (de->name, ".");
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
-	de = (struct ext4_dir_entry_2 *)
-			((char *) de + le16_to_cpu(de->rec_len));
+	de = ext4_next_entry(de);
 	de->inode = cpu_to_le32(dir->i_ino);
-	de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize-EXT4_DIR_REC_LEN(1));
+	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, "..");
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
@@ -1882,8 +1884,7 @@ static int empty_dir (struct inode * inode)
 		return 1;
 	}
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
-	de1 = (struct ext4_dir_entry_2 *)
-			((char *) de + le16_to_cpu(de->rec_len));
+	de1 = ext4_next_entry(de);
 	if (le32_to_cpu(de->inode) != inode->i_ino ||
 			!le32_to_cpu(de1->inode) ||
 			strcmp (".", de->name) ||
@@ -1894,9 +1895,9 @@ static int empty_dir (struct inode * inode)
 		brelse (bh);
 		return 1;
 	}
-	offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len);
-	de = (struct ext4_dir_entry_2 *)
-			((char *) de1 + le16_to_cpu(de1->rec_len));
+	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 ) {
 		if (!bh ||
 			(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
@@ -1925,9 +1926,8 @@ static int empty_dir (struct inode * inode)
 			brelse (bh);
 			return 0;
 		}
-		offset += le16_to_cpu(de->rec_len);
-		de = (struct ext4_dir_entry_2 *)
-				((char *) de + le16_to_cpu(de->rec_len));
+		offset += ext4_rec_len_from_disk(de->rec_len);
+		de = ext4_next_entry(de);
 	}
 	brelse (bh);
 	return 1;
@@ -2282,8 +2282,7 @@ static int ext4_link (struct dentry * old_dentry,
 }
 
 #define PARENT_INO(buffer) \
-	((struct ext4_dir_entry_2 *) ((char *) buffer + \
-	le16_to_cpu(((struct ext4_dir_entry_2 *) buffer)->rec_len)))->inode
+	(ext4_next_entry((struct ext4_dir_entry_2 *)(buffer))->inode)
 
 /*
  * Anybody can rename anything with this: the permission checks are left to the

fs/ext4/resize.c

@@ -28,7 +28,7 @@ static int verify_group_input(struct super_block *sb,
 	struct ext4_super_block *es = sbi->s_es;
 	ext4_fsblk_t start = ext4_blocks_count(es);
 	ext4_fsblk_t end = start + input->blocks_count;
-	unsigned group = input->group;
+	ext4_group_t group = input->group;
 	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
 	unsigned overhead = ext4_bg_has_super(sb, group) ?
 		(1 + ext4_bg_num_gdb(sb, group) +
@@ -206,7 +206,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	}
 
 	if (ext4_bg_has_super(sb, input->group)) {
-		ext4_debug("mark backup superblock %#04lx (+0)\n", start);
+		ext4_debug("mark backup superblock %#04llx (+0)\n", start);
 		ext4_set_bit(0, bh->b_data);
 	}
 
@@ -215,7 +215,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	     i < gdblocks; i++, block++, bit++) {
 		struct buffer_head *gdb;
 
-		ext4_debug("update backup group %#04lx (+%d)\n", block, bit);
+		ext4_debug("update backup group %#04llx (+%d)\n", block, bit);
 
 		if ((err = extend_or_restart_transaction(handle, 1, bh)))
 			goto exit_bh;
@@ -243,7 +243,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	     i < reserved_gdb; i++, block++, bit++) {
 		struct buffer_head *gdb;
 
-		ext4_debug("clear reserved block %#04lx (+%d)\n", block, bit);
+		ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit);
 
 		if ((err = extend_or_restart_transaction(handle, 1, bh)))
 			goto exit_bh;
@@ -256,10 +256,10 @@ static int setup_new_group_blocks(struct super_block *sb,
 		ext4_set_bit(bit, bh->b_data);
 		brelse(gdb);
 	}
-	ext4_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
+	ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
 		   input->block_bitmap - start);
 	ext4_set_bit(input->block_bitmap - start, bh->b_data);
-	ext4_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
+	ext4_debug("mark inode bitmap %#04llx (+%llu)\n", input->inode_bitmap,
 		   input->inode_bitmap - start);
 	ext4_set_bit(input->inode_bitmap - start, bh->b_data);
 
@@ -268,7 +268,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	     i < sbi->s_itb_per_group; i++, bit++, block++) {
 		struct buffer_head *it;
 
-		ext4_debug("clear inode block %#04lx (+%d)\n", block, bit);
+		ext4_debug("clear inode block %#04llx (+%d)\n", block, bit);
 
 		if ((err = extend_or_restart_transaction(handle, 1, bh)))
 			goto exit_bh;
@@ -291,7 +291,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	brelse(bh);
 
 	/* Mark unused entries in inode bitmap used */
-	ext4_debug("clear inode bitmap %#04x (+%ld)\n",
+	ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
 		   input->inode_bitmap, input->inode_bitmap - start);
 	if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
 		err = PTR_ERR(bh);
@@ -357,7 +357,7 @@ static int verify_reserved_gdb(struct super_block *sb,
 			       struct buffer_head *primary)
 {
 	const ext4_fsblk_t blk = primary->b_blocknr;
-	const unsigned long end = EXT4_SB(sb)->s_groups_count;
+	const ext4_group_t end = EXT4_SB(sb)->s_groups_count;
 	unsigned three = 1;
 	unsigned five = 5;
 	unsigned seven = 7;
@@ -656,12 +656,12 @@ static void update_backups(struct super_block *sb,
 			   int blk_off, char *data, int size)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	const unsigned long last = sbi->s_groups_count;
+	const ext4_group_t last = sbi->s_groups_count;
 	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
 	unsigned three = 1;
 	unsigned five = 5;
 	unsigned seven = 7;
-	unsigned group;
+	ext4_group_t group;
 	int rest = sb->s_blocksize - size;
 	handle_t *handle;
 	int err = 0, err2;
@@ -716,7 +716,7 @@ static void update_backups(struct super_block *sb,
 exit_err:
 	if (err) {
 		ext4_warning(sb, __FUNCTION__,
-			     "can't update backup for group %d (err %d), "
+			     "can't update backup for group %lu (err %d), "
 			     "forcing fsck on next reboot", group, err);
 		sbi->s_mount_state &= ~EXT4_VALID_FS;
 		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
@@ -952,7 +952,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 		      ext4_fsblk_t n_blocks_count)
 {
 	ext4_fsblk_t o_blocks_count;
-	unsigned long o_groups_count;
+	ext4_group_t o_groups_count;
 	ext4_grpblk_t last;
 	ext4_grpblk_t add;
 	struct buffer_head * bh;
@@ -1054,7 +1054,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
 	sb->s_dirt = 1;
 	unlock_super(sb);
-	ext4_debug("freeing blocks %lu through %llu\n", o_blocks_count,
+	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
 	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,

fs/ext4/xattr.c

@@ -480,7 +480,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		ea_bdebug(bh, "refcount now=0; freeing");
 		if (ce)
 			mb_cache_entry_free(ce);
-		ext4_free_blocks(handle, inode, bh->b_blocknr, 1);
+		ext4_free_blocks(handle, inode, bh->b_blocknr, 1, 1);
 		get_bh(bh);
 		ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
 	} else {
@@ -821,7 +821,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			new_bh = sb_getblk(sb, block);
 			if (!new_bh) {
 getblk_failed:
-				ext4_free_blocks(handle, inode, block, 1);
+				ext4_free_blocks(handle, inode, block, 1, 1);
 				error = -EIO;
 				goto cleanup;
 			}

fs/inode.c

@@ -1276,6 +1276,11 @@ void file_update_time(struct file *file)
 		sync_it = 1;
 	}
 
+	if (IS_I_VERSION(inode)) {
+		inode_inc_iversion(inode);
+		sync_it = 1;
+	}
+
 	if (sync_it)
 		mark_inode_dirty_sync(inode);
 }

fs/jbd2/checkpoint.c

@@ -232,7 +232,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
 static int __process_buffer(journal_t *journal, struct journal_head *jh,
-			struct buffer_head **bhs, int *batch_count)
+			struct buffer_head **bhs, int *batch_count,
+			transaction_t *transaction)
 {
 	struct buffer_head *bh = jh2bh(jh);
 	int ret = 0;
@@ -250,6 +251,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		transaction_t *t = jh->b_transaction;
 		tid_t tid = t->t_tid;
 
+		transaction->t_chp_stats.cs_forced_to_close++;
 		spin_unlock(&journal->j_list_lock);
 		jbd_unlock_bh_state(bh);
 		jbd2_log_start_commit(journal, tid);
@@ -279,6 +281,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		bhs[*batch_count] = bh;
 		__buffer_relink_io(jh);
 		jbd_unlock_bh_state(bh);
+		transaction->t_chp_stats.cs_written++;
 		(*batch_count)++;
 		if (*batch_count == NR_BATCH) {
 			spin_unlock(&journal->j_list_lock);
@@ -322,6 +325,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 	if (!journal->j_checkpoint_transactions)
 		goto out;
 	transaction = journal->j_checkpoint_transactions;
+	if (transaction->t_chp_stats.cs_chp_time == 0)
+		transaction->t_chp_stats.cs_chp_time = jiffies;
 	this_tid = transaction->t_tid;
 restart:
 	/*
@@ -346,7 +351,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 				retry = 1;
 				break;
 			}
-			retry = __process_buffer(journal, jh, bhs,&batch_count);
+			retry = __process_buffer(journal, jh, bhs, &batch_count,
+						 transaction);
 			if (!retry && lock_need_resched(&journal->j_list_lock)){
 				spin_unlock(&journal->j_list_lock);
 				retry = 1;
@@ -602,15 +608,15 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 
 	/*
 	 * There is one special case to worry about: if we have just pulled the
-	 * buffer off a committing transaction's forget list, then even if the
-	 * checkpoint list is empty, the transaction obviously cannot be
-	 * dropped!
+	 * buffer off a running or committing transaction's checkpoing list,
+	 * then even if the checkpoint list is empty, the transaction obviously
+	 * cannot be dropped!
 	 *
-	 * The locking here around j_committing_transaction is a bit sleazy.
+	 * The locking here around t_state is a bit sleazy.
 	 * See the comment at the end of jbd2_journal_commit_transaction().
 	 */
-	if (transaction == journal->j_committing_transaction) {
-		JBUFFER_TRACE(jh, "belongs to committing transaction");
+	if (transaction->t_state != T_FINISHED) {
+		JBUFFER_TRACE(jh, "belongs to running/committing transaction");
 		goto out;
 	}
 

fs/jbd2/commit.c

@@ -20,6 +20,8 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/jiffies.h>
+#include <linux/crc32.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -92,19 +94,23 @@ static int inverted_lock(journal_t *journal, struct buffer_head *bh)
 	return 1;
 }
 
-/* Done it all: now write the commit record.  We should have
+/*
+ * Done it all: now submit the commit record.  We should have
  * cleaned up our previous buffers by now, so if we are in abort
  * mode we can now just skip the rest of the journal write
  * entirely.
  *
  * Returns 1 if the journal needs to be aborted or 0 on success
  */
-static int journal_write_commit_record(journal_t *journal,
-					transaction_t *commit_transaction)
+static int journal_submit_commit_record(journal_t *journal,
+					transaction_t *commit_transaction,
+					struct buffer_head **cbh,
+					__u32 crc32_sum)
 {
 	struct journal_head *descriptor;
+	struct commit_header *tmp;
 	struct buffer_head *bh;
-	int i, ret;
+	int ret;
 	int barrier_done = 0;
 
 	if (is_journal_aborted(journal))
@@ -116,21 +122,33 @@ static int journal_write_commit_record(journal_t *journal,
 
 	bh = jh2bh(descriptor);
 
-	/* AKPM: buglet - add `i' to tmp! */
-	for (i = 0; i < bh->b_size; i += 512) {
-		journal_header_t *tmp = (journal_header_t*)bh->b_data;
-		tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
-		tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
-		tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+	tmp = (struct commit_header *)bh->b_data;
+	tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+	tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
+	tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+
+	if (JBD2_HAS_COMPAT_FEATURE(journal,
+				    JBD2_FEATURE_COMPAT_CHECKSUM)) {
+		tmp->h_chksum_type 	= JBD2_CRC32_CHKSUM;
+		tmp->h_chksum_size 	= JBD2_CRC32_CHKSUM_SIZE;
+		tmp->h_chksum[0] 	= cpu_to_be32(crc32_sum);
 	}
 
-	JBUFFER_TRACE(descriptor, "write commit block");
+	JBUFFER_TRACE(descriptor, "submit commit block");
+	lock_buffer(bh);
+
 	set_buffer_dirty(bh);
-	if (journal->j_flags & JBD2_BARRIER) {
+	set_buffer_uptodate(bh);
+	bh->b_end_io = journal_end_buffer_io_sync;
+
+	if (journal->j_flags & JBD2_BARRIER &&
+		!JBD2_HAS_COMPAT_FEATURE(journal,
+					 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
 		set_buffer_ordered(bh);
 		barrier_done = 1;
 	}
-	ret = sync_dirty_buffer(bh);
+	ret = submit_bh(WRITE, bh);
+
 	/* is it possible for another commit to fail at roughly
 	 * the same time as this one?  If so, we don't want to
 	 * trust the barrier flag in the super, but instead want
@@ -151,14 +169,72 @@ static int journal_write_commit_record(journal_t *journal,
 		clear_buffer_ordered(bh);
 		set_buffer_uptodate(bh);
 		set_buffer_dirty(bh);
-		ret = sync_dirty_buffer(bh);
+		ret = submit_bh(WRITE, bh);
 	}
-	put_bh(bh);		/* One for getblk() */
-	jbd2_journal_put_journal_head(descriptor);
+	*cbh = bh;
+	return ret;
+}
+
+/*
+ * This function along with journal_submit_commit_record
+ * allows to write the commit record asynchronously.
+ */
+static int journal_wait_on_commit_record(struct buffer_head *bh)
+{
+	int ret = 0;
+
+	clear_buffer_dirty(bh);
+	wait_on_buffer(bh);
+
+	if (unlikely(!buffer_uptodate(bh)))
+		ret = -EIO;
+	put_bh(bh);            /* One for getblk() */
+	jbd2_journal_put_journal_head(bh2jh(bh));
 
-	return (ret == -EIO);
+	return ret;
 }
 
+/*
+ * Wait for all submitted IO to complete.
+ */
+static int journal_wait_on_locked_list(journal_t *journal,
+				       transaction_t *commit_transaction)
+{
+	int ret = 0;
+	struct journal_head *jh;
+
+	while (commit_transaction->t_locked_list) {
+		struct buffer_head *bh;
+
+		jh = commit_transaction->t_locked_list->b_tprev;
+		bh = jh2bh(jh);
+		get_bh(bh);
+		if (buffer_locked(bh)) {
+			spin_unlock(&journal->j_list_lock);
+			wait_on_buffer(bh);
+			if (unlikely(!buffer_uptodate(bh)))
+				ret = -EIO;
+			spin_lock(&journal->j_list_lock);
+		}
+		if (!inverted_lock(journal, bh)) {
+			put_bh(bh);
+			spin_lock(&journal->j_list_lock);
+			continue;
+		}
+		if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
+			__jbd2_journal_unfile_buffer(jh);
+			jbd_unlock_bh_state(bh);
+			jbd2_journal_remove_journal_head(bh);
+			put_bh(bh);
+		} else {
+			jbd_unlock_bh_state(bh);
+		}
+		put_bh(bh);
+		cond_resched_lock(&journal->j_list_lock);
+	}
+	return ret;
+  }
+
 static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
 {
 	int i;
@@ -274,7 +350,21 @@ static void journal_submit_data_buffers(journal_t *journal,
 	journal_do_submit_data(wbuf, bufs);
 }
 
-static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
+{
+	struct page *page = bh->b_page;
+	char *addr;
+	__u32 checksum;
+
+	addr = kmap_atomic(page, KM_USER0);
+	checksum = crc32_be(crc32_sum,
+		(void *)(addr + offset_in_page(bh->b_data)), bh->b_size);
+	kunmap_atomic(addr, KM_USER0);
+
+	return checksum;
+}
+
+static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
@@ -290,6 +380,7 @@ static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
  */
 void jbd2_journal_commit_transaction(journal_t *journal)
 {
+	struct transaction_stats_s stats;
 	transaction_t *commit_transaction;
 	struct journal_head *jh, *new_jh, *descriptor;
 	struct buffer_head **wbuf = journal->j_wbuf;
@@ -305,6 +396,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int tag_flag;
 	int i;
 	int tag_bytes = journal_tag_bytes(journal);
+	struct buffer_head *cbh = NULL; /* For transactional checksums */
+	__u32 crc32_sum = ~0;
 
 	/*
 	 * First job: lock down the current transaction and wait for
@@ -337,6 +430,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	spin_lock(&journal->j_state_lock);
 	commit_transaction->t_state = T_LOCKED;
 
+	stats.u.run.rs_wait = commit_transaction->t_max_wait;
+	stats.u.run.rs_locked = jiffies;
+	stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
+						stats.u.run.rs_locked);
+
 	spin_lock(&commit_transaction->t_handle_lock);
 	while (commit_transaction->t_updates) {
 		DEFINE_WAIT(wait);
@@ -407,6 +505,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	jbd2_journal_switch_revoke_table(journal);
 
+	stats.u.run.rs_flushing = jiffies;
+	stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
+					       stats.u.run.rs_flushing);
+
 	commit_transaction->t_state = T_FLUSH;
 	journal->j_committing_transaction = commit_transaction;
 	journal->j_running_transaction = NULL;
@@ -440,38 +542,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	journal_submit_data_buffers(journal, commit_transaction);
 
 	/*
-	 * Wait for all previously submitted IO to complete.
+	 * Wait for all previously submitted IO to complete if commit
+	 * record is to be written synchronously.
 	 */
 	spin_lock(&journal->j_list_lock);
-	while (commit_transaction->t_locked_list) {
-		struct buffer_head *bh;
+	if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
+		JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
+		err = journal_wait_on_locked_list(journal,
+						commit_transaction);
 
-		jh = commit_transaction->t_locked_list->b_tprev;
-		bh = jh2bh(jh);
-		get_bh(bh);
-		if (buffer_locked(bh)) {
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			if (unlikely(!buffer_uptodate(bh)))
-				err = -EIO;
-			spin_lock(&journal->j_list_lock);
-		}
-		if (!inverted_lock(journal, bh)) {
-			put_bh(bh);
-			spin_lock(&journal->j_list_lock);
-			continue;
-		}
-		if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
-			__jbd2_journal_unfile_buffer(jh);
-			jbd_unlock_bh_state(bh);
-			jbd2_journal_remove_journal_head(bh);
-			put_bh(bh);
-		} else {
-			jbd_unlock_bh_state(bh);
-		}
-		put_bh(bh);
-		cond_resched_lock(&journal->j_list_lock);
-	}
 	spin_unlock(&journal->j_list_lock);
 
 	if (err)
@@ -498,6 +577,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	commit_transaction->t_state = T_COMMIT;
 
+	stats.u.run.rs_logging = jiffies;
+	stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
+						 stats.u.run.rs_logging);
+	stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits;
+	stats.u.run.rs_blocks_logged = 0;
+
 	descriptor = NULL;
 	bufs = 0;
 	while (commit_transaction->t_buffers) {
@@ -639,6 +724,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 start_journal_io:
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
+				/*
+				 * Compute checksum.
+				 */
+				if (JBD2_HAS_COMPAT_FEATURE(journal,
+					JBD2_FEATURE_COMPAT_CHECKSUM)) {
+					crc32_sum =
+					    jbd2_checksum_data(crc32_sum, bh);
+				}
+
 				lock_buffer(bh);
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
@@ -646,6 +740,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 				submit_bh(WRITE, bh);
 			}
 			cond_resched();
+			stats.u.run.rs_blocks_logged += bufs;
 
 			/* Force a new descriptor to be generated next
                            time round the loop. */
@@ -654,6 +749,23 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		}
 	}
 
+	/* Done it all: now write the commit record asynchronously. */
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal,
+		JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+		err = journal_submit_commit_record(journal, commit_transaction,
+						 &cbh, crc32_sum);
+		if (err)
+			__jbd2_journal_abort_hard(journal);
+
+		spin_lock(&journal->j_list_lock);
+		err = journal_wait_on_locked_list(journal,
+						commit_transaction);
+		spin_unlock(&journal->j_list_lock);
+		if (err)
+			__jbd2_journal_abort_hard(journal);
+	}
+
 	/* Lo and behold: we have just managed to send a transaction to
            the log.  Before we can commit it, wait for the IO so far to
            complete.  Control buffers being written are on the
@@ -753,8 +865,14 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 	jbd_debug(3, "JBD: commit phase 6\n");
 
-	if (journal_write_commit_record(journal, commit_transaction))
-		err = -EIO;
+	if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
+		JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+		err = journal_submit_commit_record(journal, commit_transaction,
+						&cbh, crc32_sum);
+		if (err)
+			__jbd2_journal_abort_hard(journal);
+	}
+	err = journal_wait_on_commit_record(cbh);
 
 	if (err)
 		jbd2_journal_abort(journal, err);
@@ -816,6 +934,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		cp_transaction = jh->b_cp_transaction;
 		if (cp_transaction) {
 			JBUFFER_TRACE(jh, "remove from old cp transaction");
+			cp_transaction->t_chp_stats.cs_dropped++;
 			__jbd2_journal_remove_checkpoint(jh);
 		}
 
@@ -867,10 +986,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	}
 	spin_unlock(&journal->j_list_lock);
 	/*
-	 * This is a bit sleazy.  We borrow j_list_lock to protect
-	 * journal->j_committing_transaction in __jbd2_journal_remove_checkpoint.
-	 * Really, __jbd2_journal_remove_checkpoint should be using j_state_lock but
-	 * it's a bit hassle to hold that across __jbd2_journal_remove_checkpoint
+	 * This is a bit sleazy.  We use j_list_lock to protect transition
+	 * of a transaction into T_FINISHED state and calling
+	 * __jbd2_journal_drop_transaction(). Otherwise we could race with
+	 * other checkpointing code processing the transaction...
 	 */
 	spin_lock(&journal->j_state_lock);
 	spin_lock(&journal->j_list_lock);
@@ -890,6 +1009,36 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
 
+	commit_transaction->t_start = jiffies;
+	stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging,
+						commit_transaction->t_start);
+
+	/*
+	 * File the transaction for history
+	 */
+	stats.ts_type = JBD2_STATS_RUN;
+	stats.ts_tid = commit_transaction->t_tid;
+	stats.u.run.rs_handle_count = commit_transaction->t_handle_count;
+	spin_lock(&journal->j_history_lock);
+	memcpy(journal->j_history + journal->j_history_cur, &stats,
+			sizeof(stats));
+	if (++journal->j_history_cur == journal->j_history_max)
+		journal->j_history_cur = 0;
+
+	/*
+	 * Calculate overall stats
+	 */
+	journal->j_stats.ts_tid++;
+	journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait;
+	journal->j_stats.u.run.rs_running += stats.u.run.rs_running;
+	journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked;
+	journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing;
+	journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging;
+	journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count;
+	journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks;
+	journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged;
+	spin_unlock(&journal->j_history_lock);
+
 	commit_transaction->t_state = T_FINISHED;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;

fs/jbd2/revoke.c

@@ -171,13 +171,15 @@ int __init jbd2_journal_init_revoke_caches(void)
 {
 	jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
 					   sizeof(struct jbd2_revoke_record_s),
-					   0, SLAB_HWCACHE_ALIGN, NULL);
+					   0,
+					   SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
+					   NULL);
 	if (jbd2_revoke_record_cache == 0)
 		return -ENOMEM;
 
 	jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
 					   sizeof(struct jbd2_revoke_table_s),
-					   0, 0, NULL);
+					   0, SLAB_TEMPORARY, NULL);
 	if (jbd2_revoke_table_cache == 0) {
 		kmem_cache_destroy(jbd2_revoke_record_cache);
 		jbd2_revoke_record_cache = NULL;

fs/read_write.c

@@ -446,6 +446,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 	}
 	return seg;
 }
+EXPORT_SYMBOL(iov_shorten);
 
 ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)

include/asm-arm/bitops.h

@@ -310,6 +310,8 @@ static inline int constant_fls(int x)
 		_find_first_zero_bit_le(p,sz)
 #define ext2_find_next_zero_bit(p,sz,off)	\
 		_find_next_zero_bit_le(p,sz,off)
+#define ext2_find_next_bit(p, sz, off) \
+		_find_next_bit_le(p, sz, off)
 
 /*
  * Minix is defined to use little-endian byte ordering.

include/asm-generic/bitops/ext2-non-atomic.h

@@ -14,5 +14,7 @@
 	generic_find_first_zero_le_bit((unsigned long *)(addr), (size))
 #define ext2_find_next_zero_bit(addr, size, off) \
 	generic_find_next_zero_le_bit((unsigned long *)(addr), (size), (off))
+#define ext2_find_next_bit(addr, size, off) \
+	generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 
 #endif /* _ASM_GENERIC_BITOPS_EXT2_NON_ATOMIC_H_ */

include/asm-generic/bitops/le.h

@@ -20,6 +20,8 @@
 #define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr)
 
 #define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset)
+#define generic_find_next_le_bit(addr, size, offset) \
+			find_next_bit(addr, size, offset)
 
 #elif defined(__BIG_ENDIAN)
 
@@ -42,6 +44,8 @@
 
 extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
 		unsigned long size, unsigned long offset);
+extern unsigned long generic_find_next_le_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
 
 #else
 #error "Please fix <asm/byteorder.h>"

include/asm-m68k/bitops.h

@@ -410,6 +410,8 @@ static inline int ext2_find_next_zero_bit(const void *vaddr, unsigned size,
 	res = ext2_find_first_zero_bit (p, size - 32 * (p - addr));
 	return (p - addr) * 32 + res;
 }
+#define ext2_find_next_bit(addr, size, off) \
+	generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 
 #endif /* __KERNEL__ */