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/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 @@ revalidate:
 				 * 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 @@ revalidate:
 				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 @@ revalidate:
 					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/ioctl.c

@@ -199,7 +199,7 @@ flags_err:
 		 * 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 @@ flags_err:
 			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 @@ flags_err:
 		return err;
 	}
 
+	case EXT4_IOC_MIGRATE:
+		return ext4_ext_migrate(inode, filp, cmd, arg);
+
 	default:
 		return -ENOTTY;
 	}

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 @@ inserted:
 			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 @@ restart:
 				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/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__ */