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: (57 commits)
  jbd2: Fix oops in jbd2_journal_init_inode() on corrupted fs
  ext4: Remove "extents" mount option
  block: Add Kconfig help which notes that ext4 needs CONFIG_LBD
  ext4: Make printk's consistently prefixed with "EXT4-fs: "
  ext4: Add sanity checks for the superblock before mounting the filesystem
  ext4: Add mount option to set kjournald's I/O priority
  jbd2: Submit writes to the journal using WRITE_SYNC
  jbd2: Add pid and journal device name to the "kjournald2 starting" message
  ext4: Add markers for better debuggability
  ext4: Remove code to create the journal inode
  ext4: provide function to release metadata pages under memory pressure
  ext3: provide function to release metadata pages under memory pressure
  add releasepage hooks to block devices which can be used by file systems
  ext4: Fix s_dirty_blocks_counter if block allocation failed with nodelalloc
  ext4: Init the complete page while building buddy cache
  ext4: Don't allow new groups to be added during block allocation
  ext4: mark the blocks/inode bitmap beyond end of group as used
  ext4: Use new buffer_head flag to check uninit group bitmaps initialization
  ext4: Fix the race between read_inode_bitmap() and ext4_new_inode()
  ext4: code cleanup
  ...

Documentation/filesystems/ext4.txt

@@ -58,13 +58,22 @@ Note: More extensive information for getting started with ext4 can be
 
 	# mount -t ext4 /dev/hda1 /wherever
 
-  - When comparing performance with other filesystems, remember that
+  - When comparing performance with other filesystems, it's always
-    ext3/4 by default offers higher data integrity guarantees than most.
+    important to try multiple workloads; very often a subtle change in a
-    So when comparing with a metadata-only journalling filesystem, such
+    workload parameter can completely change the ranking of which
-    as ext3, use `mount -o data=writeback'.  And you might as well use
+    filesystems do well compared to others.  When comparing versus ext3,
-    `mount -o nobh' too along with it.  Making the journal larger than
+    note that ext4 enables write barriers by default, while ext3 does
-    the mke2fs default often helps performance with metadata-intensive
+    not enable write barriers by default.  So it is useful to use
-    workloads.
+    explicitly specify whether barriers are enabled or not when via the
+    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+    for a fair comparison.  When tuning ext3 for best benchmark numbers,
+    it is often worthwhile to try changing the data journaling mode; '-o
+    data=writeback,nobh' can be faster for some workloads.  (Note
+    however that running mounted with data=writeback can potentially
+    leave stale data exposed in recently written files in case of an
+    unclean shutdown, which could be a security exposure in some
+    situations.)  Configuring the filesystem with a large journal can
+    also be helpful for metadata-intensive workloads.
 
 2. Features
 ===========
@@ -74,7 +83,7 @@ Note: More extensive information for getting started with ext4 can be
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
-* internal redunancy in tree
+* internal redundancy in tree
 * improved file allocation (multi-block alloc)
 * fix 32000 subdirectory limit
 * nsec timestamps for mtime, atime, ctime, create time
@@ -116,10 +125,11 @@ grouping of bitmaps and inode tables.  Some test results available here:
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
-extents		(*)	ext4 will use extents to address file data.  The
+ro                   	Mount filesystem read only. Note that ext4 will
-			file system will no longer be mountable by ext3.
+                     	replay the journal (and thus write to the
-
+                     	partition) even when mounted "read only". The
-noextents		ext4 will not use extents for newly created files
+                     	mount options "ro,noload" can be used to prevent
+		     	writes to the filesystem.
 
 journal_checksum	Enable checksumming of the journal transactions.
 			This will allow the recovery code in e2fsck and the
@@ -134,17 +144,17 @@ journal_async_commit	Commit block can be written to disk without waiting
 journal=update		Update the ext4 file system's journal to the current
 			format.
 
-journal=inum		When a journal already exists, this option is ignored.
-			Otherwise, it specifies the number of the inode which
-			will represent the ext4 file system's journal file.
-
 journal_dev=devnum	When the external journal device's major/minor numbers
 			have changed, this option allows the user to specify
 			the new journal location.  The journal device is
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.
+noload			Don't load the journal on mounting.  Note that
+                     	if the filesystem was not unmounted cleanly,
+                     	skipping the journal replay will lead to the
+                     	filesystem containing inconsistencies that can
+                     	lead to any number of problems.
 
 data=journal		All data are committed into the journal prior to being
 			written into the main file system.
@@ -219,9 +229,12 @@ minixdf			Make 'df' act like Minix.
 
 debug			Extra debugging information is sent to syslog.
 
-errors=remount-ro(*)	Remount the filesystem read-only on an error.
+errors=remount-ro	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
+                        (These mount options override the errors behavior
+                        specified in the superblock, which can be configured
+                        using tune2fs)
 
 data_err=ignore(*)	Just print an error message if an error occurs
 			in a file data buffer in ordered mode.
@@ -261,6 +274,42 @@ delalloc	(*)	Deferring block allocation until write-out time.
 nodelalloc		Disable delayed allocation. Blocks are allocation
 			when data is copied from user to page cache.
 
+max_batch_time=usec	Maximum amount of time ext4 should wait for
+			additional filesystem operations to be batch
+			together with a synchronous write operation.
+			Since a synchronous write operation is going to
+			force a commit and then a wait for the I/O
+			complete, it doesn't cost much, and can be a
+			huge throughput win, we wait for a small amount
+			of time to see if any other transactions can
+			piggyback on the synchronous write.   The
+			algorithm used is designed to automatically tune
+			for the speed of the disk, by measuring the
+			amount of time (on average) that it takes to
+			finish committing a transaction.  Call this time
+			the "commit time".  If the time that the
+			transactoin has been running is less than the
+			commit time, ext4 will try sleeping for the
+			commit time to see if other operations will join
+			the transaction.   The commit time is capped by
+			the max_batch_time, which defaults to 15000us
+			(15ms).   This optimization can be turned off
+			entirely by setting max_batch_time to 0.
+
+min_batch_time=usec	This parameter sets the commit time (as
+			described above) to be at least min_batch_time.
+			It defaults to zero microseconds.  Increasing
+			this parameter may improve the throughput of
+			multi-threaded, synchronous workloads on very
+			fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio	The I/O priority (from 0 to 7, where 0 is the
+			highest priorty) which should be used for I/O
+			operations submitted by kjournald2 during a
+			commit operation.  This defaults to 3, which is
+			a slightly higher priority than the default I/O
+			priority.
+
 Data Mode
 =========
 There are 3 different data modes:

block/Kconfig

@@ -36,6 +36,12 @@ config LBD
 	  This option also enables support for single files larger than
 	  2TB.
 
+	  The ext4 filesystem requires that this feature be enabled in
+	  order to support filesystems that have the huge_file feature
+	  enabled.    Otherwise, it will refuse to mount any filesystems
+	  that use the huge_file feature, which is enabled by default
+	  by mke2fs.ext4.   The GFS2 filesystem also requires this feature.
+
 	  If unsure, say N.
 
 config BLK_DEV_IO_TRACE

fs/block_dev.c

@@ -1234,6 +1234,20 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
+/*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+static int blkdev_releasepage(struct page *page, gfp_t wait)
+{
+	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+	if (super && super->s_op->bdev_try_to_free_page)
+		return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+	return try_to_free_buffers(page);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
@@ -1241,6 +1255,7 @@ static const struct address_space_operations def_blk_aops = {
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.writepages	= generic_writepages,
+	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 };
 

fs/ext3/hash.c

@@ -35,23 +35,71 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
-	while (len--) {
+	const unsigned char *ucp = (const unsigned char *) name;
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
 
-		if (hash & 0x80000000) hash -= 0x7fffffff;
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
 		hash1 = hash0;
 		hash0 = hash;
 	}
-	return (hash0 << 1);
+	return hash0 << 1;
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
 {
 	__u32	pad, val;
 	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +110,7 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	for (i=0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
-		val = msg[i] + (val << 8);
+		val = ((int) ucp[i]) + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +143,8 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +163,18 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
-	case DX_HASH_LEGACY:
+	case DX_HASH_LEGACY_UNSIGNED:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash_unsigned(name, len);
 		break;
+	case DX_HASH_LEGACY:
+		hash = dx_hack_hash_signed(name, len);
+		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			(*str2hashbuf)(p, len, in, 8);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +182,12 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			(*str2hashbuf)(p, len, in, 4);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;

fs/ext3/namei.c

@@ -364,6 +364,8 @@ dx_probe(struct qstr *entry, struct inode *dir,
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	if (entry)
 		ext3fs_dirhash(entry->name, entry->len, hinfo);
@@ -632,6 +634,9 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
 		hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT3_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
@@ -1152,9 +1157,9 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	u32 hash2;
 	struct dx_map_entry *map;
 	char *data1 = (*bh)->b_data, *data2;
-	unsigned split, move, size, i;
+	unsigned split, move, size;
 	struct ext3_dir_entry_2 *de = NULL, *de2;
-	int	err = 0;
+	int	err = 0, i;
 
 	bh2 = ext3_append (handle, dir, &newblock, &err);
 	if (!(bh2)) {
@@ -1394,6 +1399,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	ext3fs_dirhash(name, namelen, &hinfo);
 	frame = frames;

fs/ext3/super.c

@@ -683,6 +683,26 @@ static struct dentry *ext3_fh_to_parent(struct super_block *sb, struct fid *fid,
 				    ext3_nfs_get_inode);
 }
 
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device.  Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+				 gfp_t wait)
+{
+	journal_t *journal = EXT3_SB(sb)->s_journal;
+
+	WARN_ON(PageChecked(page));
+	if (!page_has_buffers(page))
+		return 0;
+	if (journal)
+		return journal_try_to_free_buffers(journal, page, 
+						   wait & ~__GFP_WAIT);
+	return try_to_free_buffers(page);
+}
+
 #ifdef CONFIG_QUOTA
 #define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
 #define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
@@ -749,6 +769,7 @@ static const struct super_operations ext3_sops = {
 	.quota_read	= ext3_quota_read,
 	.quota_write	= ext3_quota_write,
 #endif
+	.bdev_try_to_free_page = bdev_try_to_free_page,
 };
 
 static const struct export_operations ext3_export_ops = {
@@ -1750,6 +1771,18 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	for (i=0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
+	i = le32_to_cpu(es->s_flags);
+	if (i & EXT2_FLAGS_UNSIGNED_HASH)
+		sbi->s_hash_unsigned = 3;
+	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+		sbi->s_hash_unsigned = 3;
+#else
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		sb->s_dirt = 1;
+	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
 		printk (KERN_ERR

fs/ext4/balloc.c

@@ -20,6 +20,7 @@
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "group.h"
+#include "mballoc.h"
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines
@@ -100,10 +101,10 @@ 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, __func__,
-				  "Checksum bad for group %lu\n", block_group);
+				  "Checksum bad for group %u", block_group);
-			gdp->bg_free_blocks_count = 0;
+			ext4_free_blks_set(sb, gdp, 0);
-			gdp->bg_free_inodes_count = 0;
+			ext4_free_inodes_set(sb, gdp, 0);
-			gdp->bg_itable_unused = 0;
+			ext4_itable_unused_set(sb, gdp, 0);
 			memset(bh->b_data, 0xff, sb->s_blocksize);
 			return 0;
 		}
@@ -205,15 +206,15 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 					     ext4_group_t block_group,
 					     struct buffer_head **bh)
 {
-	unsigned long group_desc;
+	unsigned int group_desc;
-	unsigned long offset;
+	unsigned int offset;
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (block_group >= sbi->s_groups_count) {
 		ext4_error(sb, "ext4_get_group_desc",
 			   "block_group >= groups_count - "
-			   "block_group = %lu, groups_count = %lu",
+			   "block_group = %u, groups_count = %u",
 			   block_group, sbi->s_groups_count);
 
 		return NULL;
@@ -225,7 +226,7 @@ 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 = %lu, group_desc = %lu, desc = %lu",
+			   "block_group = %u, group_desc = %u, desc = %u",
 			   block_group, group_desc, offset);
 		return NULL;
 	}
@@ -315,29 +316,50 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	if (unlikely(!bh)) {
 		ext4_error(sb, __func__,
 			    "Cannot read block bitmap - "
-			    "block_group = %lu, block_bitmap = %llu",
+			    "block_group = %u, block_bitmap = %llu",
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (buffer_uptodate(bh) &&
+
-	    !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
+	if (bitmap_uptodate(bh))
 		return bh;
 
 	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		ext4_init_block_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		unlock_buffer(bh);
 		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		unlock_buffer(bh);
 		return bh;
 	}
 	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
 		ext4_error(sb, __func__,
 			    "Cannot read block bitmap - "
-			    "block_group = %lu, block_bitmap = %llu",
+			    "block_group = %u, block_bitmap = %llu",
 			    block_group, bitmap_blk);
 		return NULL;
 	}
@@ -350,62 +372,44 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 }
 
 /**
- * ext4_free_blocks_sb() -- Free given blocks and update quota
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
  * @handle:			handle to this transaction
  * @sb:				super block
- * @block:			start physcial block to free
+ * @block:			start physcial block to add to the block group
  * @count:			number of blocks to free
- * @pdquot_freed_blocks:	pointer to quota
  *
- * XXX This function is only used by the on-line resizing code, which
+ * This marks the blocks as free in the bitmap. We ask the
- * should probably be fixed up to call the mballoc variant.  There
+ * mballoc to reload the buddy after this by setting group
- * this needs to be cleaned up later; in fact, I'm not convinced this
+ * EXT4_GROUP_INFO_NEED_INIT_BIT flag
- * is 100% correct in the face of the mballoc code.  The online resizing
- * code needs to be fixed up to more tightly (and correctly) interlock
- * with the mballoc code.
  */
-void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
-			 ext4_fsblk_t block, unsigned long count,
+			 ext4_fsblk_t block, unsigned long count)
-			 unsigned long *pdquot_freed_blocks)
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct buffer_head *gd_bh;
 	ext4_group_t block_group;
 	ext4_grpblk_t bit;
-	unsigned long i;
+	unsigned int i;
-	unsigned long overflow;
 	struct ext4_group_desc *desc;
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
-	int err = 0, ret;
+	int err = 0, ret, blk_free_count;
-	ext4_grpblk_t group_freed;
+	ext4_grpblk_t blocks_freed;
+	struct ext4_group_info *grp;
 
-	*pdquot_freed_blocks = 0;
 	sbi = EXT4_SB(sb);
 	es = sbi->s_es;
-	if (block < le32_to_cpu(es->s_first_data_block) ||
+	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
-	    block + count < block ||
-	    block + count > ext4_blocks_count(es)) {
-		ext4_error(sb, "ext4_free_blocks",
-			   "Freeing blocks not in datazone - "
-			   "block = %llu, count = %lu", block, count);
-		goto error_return;
-	}
 
-	ext4_debug("freeing block(s) %llu-%llu\n", block, block + count - 1);
-
-do_more:
-	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	grp = ext4_get_group_info(sb, block_group);
 	/*
 	 * Check to see if we are freeing blocks across a group
 	 * boundary.
 	 */
 	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
-		overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
+		goto error_return;
-		count -= overflow;
 	}
-	brelse(bitmap_bh);
 	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
 	if (!bitmap_bh)
 		goto error_return;
@@ -418,18 +422,17 @@ do_more:
 	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
 	    in_range(block + count - 1, ext4_inode_table(sb, desc),
 		     sbi->s_itb_per_group)) {
-		ext4_error(sb, "ext4_free_blocks",
+		ext4_error(sb, __func__,
-			   "Freeing blocks in system zones - "
+			   "Adding blocks in system zones - "
 			   "Block = %llu, count = %lu",
 			   block, count);
 		goto error_return;
 	}
 
 	/*
-	 * We are about to start releasing blocks in the bitmap,
+	 * We are about to add blocks to the bitmap,
 	 * so we need undo access.
 	 */
-	/* @@@ check errors */
 	BUFFER_TRACE(bitmap_bh, "getting undo access");
 	err = ext4_journal_get_undo_access(handle, bitmap_bh);
 	if (err)
@@ -444,107 +447,55 @@ do_more:
 	err = ext4_journal_get_write_access(handle, gd_bh);
 	if (err)
 		goto error_return;
-
+	/*
-	jbd_lock_bh_state(bitmap_bh);
+	 * make sure we don't allow a parallel init on other groups in the
-
+	 * same buddy cache
-	for (i = 0, group_freed = 0; i < count; i++) {
+	 */
-		/*
+	down_write(&grp->alloc_sem);
-		 * An HJ special.  This is expensive...
+	for (i = 0, blocks_freed = 0; i < count; i++) {
-		 */
-#ifdef CONFIG_JBD2_DEBUG
-		jbd_unlock_bh_state(bitmap_bh);
-		{
-			struct buffer_head *debug_bh;
-			debug_bh = sb_find_get_block(sb, block + i);
-			if (debug_bh) {
-				BUFFER_TRACE(debug_bh, "Deleted!");
-				if (!bh2jh(bitmap_bh)->b_committed_data)
-					BUFFER_TRACE(debug_bh,
-						"No commited data in bitmap");
-				BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap");
-				__brelse(debug_bh);
-			}
-		}
-		jbd_lock_bh_state(bitmap_bh);
-#endif
-		if (need_resched()) {
-			jbd_unlock_bh_state(bitmap_bh);
-			cond_resched();
-			jbd_lock_bh_state(bitmap_bh);
-		}
-		/* @@@ This prevents newly-allocated data from being
-		 * freed and then reallocated within the same
-		 * transaction.
-		 *
-		 * Ideally we would want to allow that to happen, but to
-		 * do so requires making jbd2_journal_forget() capable of
-		 * revoking the queued write of a data block, which
-		 * implies blocking on the journal lock.  *forget()
-		 * cannot block due to truncate races.
-		 *
-		 * Eventually we can fix this by making jbd2_journal_forget()
-		 * return a status indicating whether or not it was able
-		 * to revoke the buffer.  On successful revoke, it is
-		 * safe not to set the allocation bit in the committed
-		 * bitmap, because we know that there is no outstanding
-		 * activity on the buffer any more and so it is safe to
-		 * reallocate it.
-		 */
-		BUFFER_TRACE(bitmap_bh, "set in b_committed_data");
-		J_ASSERT_BH(bitmap_bh,
-				bh2jh(bitmap_bh)->b_committed_data != NULL);
-		ext4_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
-				bh2jh(bitmap_bh)->b_committed_data);
-
-		/*
-		 * We clear the bit in the bitmap after setting the committed
-		 * data bit, because this is the reverse order to that which
-		 * the allocator uses.
-		 */
 		BUFFER_TRACE(bitmap_bh, "clear bit");
 		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 						bit + i, bitmap_bh->b_data)) {
-			jbd_unlock_bh_state(bitmap_bh);
 			ext4_error(sb, __func__,
 				   "bit already cleared for block %llu",
 				   (ext4_fsblk_t)(block + i));
-			jbd_lock_bh_state(bitmap_bh);
 			BUFFER_TRACE(bitmap_bh, "bit already cleared");
 		} else {
-			group_freed++;
+			blocks_freed++;
 		}
 	}
-	jbd_unlock_bh_state(bitmap_bh);
-
 	spin_lock(sb_bgl_lock(sbi, block_group));
-	le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
+	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
+	ext4_free_blks_set(sb, desc, blk_free_count);
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
 	spin_unlock(sb_bgl_lock(sbi, block_group));
-	percpu_counter_add(&sbi->s_freeblocks_counter, count);
+	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
 		spin_lock(sb_bgl_lock(sbi, flex_group));
-		sbi->s_flex_groups[flex_group].free_blocks += count;
+		sbi->s_flex_groups[flex_group].free_blocks += blocks_freed;
 		spin_unlock(sb_bgl_lock(sbi, flex_group));
 	}
+	/*
+	 * request to reload the buddy with the
+	 * new bitmap information
+	 */
+	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
+	ext4_mb_update_group_info(grp, blocks_freed);
+	up_write(&grp->alloc_sem);
 
 	/* We dirtied the bitmap block */
 	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
-	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 
 	/* And the group descriptor block */
 	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
-	ret = ext4_journal_dirty_metadata(handle, gd_bh);
+	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
-	if (!err) err = ret;
+	if (!err)
-	*pdquot_freed_blocks += group_freed;
+		err = ret;
-
-	if (overflow && !err) {
-		block += count;
-		count = overflow;
-		goto do_more;
-	}
 	sb->s_dirt = 1;
+
 error_return:
 	brelse(bitmap_bh);
 	ext4_std_error(sb, err);
@@ -614,7 +565,7 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 		if (dirty_blocks < 0) {
 			printk(KERN_CRIT "Dirty block accounting "
 					"went wrong %lld\n",
-					dirty_blocks);
+					(long long)dirty_blocks);
 		}
 	}
 	/* Check whether we have space after
@@ -666,101 +617,45 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 	return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
 }
 
-#define EXT4_META_BLOCK 0x1
-
-static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, ext4_fsblk_t goal,
-				unsigned long *count, int *errp, int flags)
-{
-	struct ext4_allocation_request ar;
-	ext4_fsblk_t ret;
-
-	memset(&ar, 0, sizeof(ar));
-	/* Fill with neighbour allocated blocks */
-
-	ar.inode = inode;
-	ar.goal = goal;
-	ar.len = *count;
-	ar.logical = iblock;
-
-	if (S_ISREG(inode->i_mode) && !(flags & EXT4_META_BLOCK))
-		/* enable in-core preallocation for data block allocation */
-		ar.flags = EXT4_MB_HINT_DATA;
-	else
-		/* disable in-core preallocation for non-regular files */
-		ar.flags = 0;
-
-	ret = ext4_mb_new_blocks(handle, &ar, errp);
-	*count = ar.len;
-	return ret;
-}
-
 /*
  * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks
  *
  * @handle:             handle to this transaction
  * @inode:              file inode
  * @goal:               given target block(filesystem wide)
- * @count:		total number of blocks need
+ * @count:		pointer to total number of blocks needed
  * @errp:               error code
  *
- * Return 1st allocated block numberon success, *count stores total account
+ * Return 1st allocated block number on success, *count stores total account
  * error stores in errp pointer
  */
 ext4_fsblk_t ext4_new_meta_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;
-	ret = do_blk_alloc(handle, inode, 0, goal,
+
-				count, errp, EXT4_META_BLOCK);
+	memset(&ar, 0, sizeof(ar));
+	/* Fill with neighbour allocated blocks */
+	ar.inode = inode;
+	ar.goal = goal;
+	ar.len = count ? *count : 1;
+
+	ret = ext4_mb_new_blocks(handle, &ar, errp);
+	if (count)
+		*count = ar.len;
+
 	/*
 	 * Account for the allocated meta blocks
 	 */
 	if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
 		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-		EXT4_I(inode)->i_allocated_meta_blocks += *count;
+		EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 	}
 	return ret;
 }
 
-/*
- * ext4_new_meta_block() -- allocate block for meta data (indexing) blocks
- *
- * @handle:             handle to this transaction
- * @inode:              file inode
- * @goal:               given target block(filesystem wide)
- * @errp:               error code
- *
- * Return allocated block number on success
- */
-ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
-		ext4_fsblk_t goal, int *errp)
-{
-	unsigned long count = 1;
-	return ext4_new_meta_blocks(handle, inode, goal, &count, errp);
-}
-
-/*
- * ext4_new_blocks() -- allocate data blocks
- *
- * @handle:             handle to this transaction
- * @inode:              file inode
- * @goal:               given target block(filesystem wide)
- * @count:		total number of blocks need
- * @errp:               error code
- *
- * Return 1st allocated block numberon success, *count stores total account
- * error stores in errp pointer
- */
-
-ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, ext4_fsblk_t goal,
-				unsigned long *count, int *errp)
-{
-	return do_blk_alloc(handle, inode, iblock, goal, count, errp, 0);
-}
-
 /**
  * ext4_count_free_blocks() -- count filesystem free blocks
  * @sb:		superblock
@@ -776,7 +671,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
-	unsigned long x;
+	unsigned int x;
 	struct buffer_head *bitmap_bh = NULL;
 
 	es = EXT4_SB(sb)->s_es;
@@ -796,7 +691,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 			continue;
 
 		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
-		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
+		printk(KERN_DEBUG "group %lu: stored = %d, counted = %u\n",
 			i, le16_to_cpu(gdp->bg_free_blocks_count), x);
 		bitmap_count += x;
 	}
@@ -812,7 +707,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+		desc_count += ext4_free_blks_count(sb, gdp);
 	}
 
 	return desc_count;

fs/ext4/bitmap.c

@@ -15,10 +15,9 @@
 
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
 {
-	unsigned int i;
+	unsigned int i, sum = 0;
-	unsigned long sum = 0;
 
 	if (!map)
 		return 0;

fs/ext4/dir.c

@@ -64,7 +64,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 int ext4_check_dir_entry(const char *function, struct inode *dir,
 			 struct ext4_dir_entry_2 *de,
 			 struct buffer_head *bh,
-			 unsigned long offset)
+			 unsigned int offset)
 {
 	const char *error_msg = NULL;
 	const int rlen = ext4_rec_len_from_disk(de->rec_len);
@@ -84,9 +84,9 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
 	if (error_msg != NULL)
 		ext4_error(dir->i_sb, function,
 			"bad entry in directory #%lu: %s - "
-			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+			"offset=%u, inode=%u, rec_len=%d, name_len=%d",
 			dir->i_ino, error_msg, offset,
-			(unsigned long) le32_to_cpu(de->inode),
+			le32_to_cpu(de->inode),
 			rlen, de->name_len);
 	return error_msg == NULL ? 1 : 0;
 }
@@ -95,7 +95,7 @@ static int ext4_readdir(struct file *filp,
 			 void *dirent, filldir_t filldir)
 {
 	int error = 0;
-	unsigned long offset;
+	unsigned int offset;
 	int i, stored;
 	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
@@ -405,7 +405,7 @@ static int call_filldir(struct file *filp, void *dirent,
 	sb = inode->i_sb;
 
 	if (!fname) {
-		printk(KERN_ERR "ext4: call_filldir: called with "
+		printk(KERN_ERR "EXT4-fs: call_filldir: called with "
 		       "null fname?!?\n");
 		return 0;
 	}

fs/ext4/ext4.h

@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/blkdev.h>
 #include <linux/magic.h>
+#include <linux/jbd2.h>
 #include "ext4_i.h"
 
 /*
@@ -94,9 +95,9 @@ struct ext4_allocation_request {
 	/* phys. block for ^^^ */
 	ext4_fsblk_t pright;
 	/* how many blocks we want to allocate */
-	unsigned long len;
+	unsigned int len;
 	/* flags. see above EXT4_MB_HINT_* */
-	unsigned long flags;
+	unsigned int flags;
 };
 
 /*
@@ -156,12 +157,12 @@ struct ext4_group_desc
 	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
 	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
 	__le32	bg_inode_table_lo;	/* Inodes table block */
-	__le16	bg_free_blocks_count;	/* Free blocks count */
+	__le16	bg_free_blocks_count_lo;/* Free blocks count */
-	__le16	bg_free_inodes_count;	/* Free inodes count */
+	__le16	bg_free_inodes_count_lo;/* Free inodes count */
-	__le16	bg_used_dirs_count;	/* Directories count */
+	__le16	bg_used_dirs_count_lo;	/* Directories count */
 	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
 	__u32	bg_reserved[2];		/* Likely block/inode bitmap checksum */
-	__le16  bg_itable_unused;	/* Unused inodes count */
+	__le16  bg_itable_unused_lo;	/* Unused inodes count */
 	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
 	__le32	bg_block_bitmap_hi;	/* Blocks bitmap block MSB */
 	__le32	bg_inode_bitmap_hi;	/* Inodes bitmap block MSB */
@@ -169,7 +170,7 @@ struct ext4_group_desc
 	__le16	bg_free_blocks_count_hi;/* Free blocks count MSB */
 	__le16	bg_free_inodes_count_hi;/* Free inodes count MSB */
 	__le16	bg_used_dirs_count_hi;	/* Directories count MSB */
-	__le16	bg_itable_unused_hi;	/* Unused inodes count MSB */
+	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
 	__u32	bg_reserved2[3];
 };
 
@@ -328,6 +329,7 @@ struct ext4_mount_options {
 	uid_t s_resuid;
 	gid_t s_resgid;
 	unsigned long s_commit_interval;
+	u32 s_min_batch_time, s_max_batch_time;
 #ifdef CONFIG_QUOTA
 	int s_jquota_fmt;
 	char *s_qf_names[MAXQUOTAS];
@@ -534,7 +536,6 @@ do {									       \
 #define EXT4_MOUNT_QUOTA		0x80000 /* Some quota option set */
 #define EXT4_MOUNT_USRQUOTA		0x100000 /* "old" user quota */
 #define EXT4_MOUNT_GRPQUOTA		0x200000 /* "old" group quota */
-#define EXT4_MOUNT_EXTENTS		0x400000 /* Extents support */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
@@ -726,11 +727,11 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
  */
 
 #define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
-	(EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask))
+	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
 #define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
-	(EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask))
+	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
 #define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
-	(EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask))
+	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
 #define EXT4_SET_COMPAT_FEATURE(sb,mask)			\
 	EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
 #define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)			\
@@ -805,6 +806,12 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define EXT4_DEFM_JMODE_ORDERED	0x0040
 #define EXT4_DEFM_JMODE_WBACK	0x0060
 
+/*
+ * Default journal batch times
+ */
+#define EXT4_DEF_MIN_BATCH_TIME	0
+#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */
+
 /*
  * Structure of a directory entry
  */
@@ -891,6 +898,9 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len)
 #define DX_HASH_LEGACY		0
 #define DX_HASH_HALF_MD4	1
 #define DX_HASH_TEA		2
+#define DX_HASH_LEGACY_UNSIGNED	3
+#define DX_HASH_HALF_MD4_UNSIGNED	4
+#define DX_HASH_TEA_UNSIGNED		5
 
 #ifdef __KERNEL__
 
@@ -955,7 +965,7 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 #define ERR_BAD_DX_DIR	-75000
 
 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);
 
 extern struct proc_dir_entry *ext4_proc_root;
 
@@ -987,6 +997,9 @@ do {									\
 # define ATTRIB_NORET	__attribute__((noreturn))
 # define NORET_AND	noreturn,
 
+/* bitmap.c */
+extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+
 /* balloc.c */
 extern unsigned int ext4_block_group(struct super_block *sb,
 			ext4_fsblk_t blocknr);
@@ -995,20 +1008,14 @@ extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
 extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
 extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
 			ext4_group_t group);
-extern ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t goal, int *errp);
 extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t goal, unsigned long *count, int *errp);
-extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
-					ext4_lblk_t iblock, ext4_fsblk_t goal,
-					unsigned long *count, int *errp);
 extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
-				ext4_fsblk_t block, unsigned long count,
+				ext4_fsblk_t block, unsigned long count);
-				unsigned long *pdquot_freed_blocks);
 extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
 extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
@@ -1019,7 +1026,7 @@ extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 /* dir.c */
 extern int ext4_check_dir_entry(const char *, struct inode *,
 				struct ext4_dir_entry_2 *,
-				struct buffer_head *, unsigned long);
+				struct buffer_head *, unsigned int);
 extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 				    __u32 minor_hash,
 				    struct ext4_dir_entry_2 *dirent);
@@ -1039,7 +1046,6 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
 extern unsigned long ext4_count_dirs(struct super_block *);
 extern void ext4_check_inodes_bitmap(struct super_block *);
-extern unsigned long ext4_count_free(struct buffer_head *, unsigned);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1054,12 +1060,13 @@ extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
 		unsigned long, unsigned long, int, unsigned long *);
-extern int ext4_mb_add_more_groupinfo(struct super_block *sb,
+extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
 		ext4_grpblk_t add);
-
+extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
-
+extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
+						ext4_group_t, int);
 /* inode.c */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 		struct buffer_head *bh, ext4_fsblk_t blocknr);
@@ -1069,10 +1076,6 @@ struct buffer_head *ext4_bread(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
 int ext4_get_block(struct inode *inode, sector_t iblock,
 				struct buffer_head *bh_result, int create);
-int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, unsigned long maxblocks,
-				struct buffer_head *bh_result,
-				int create, int extend_disksize);
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, int);
@@ -1123,6 +1126,9 @@ extern void ext4_abort(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
 extern void ext4_warning(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
+				const char *, const char *, ...)
+	__attribute__ ((format (printf, 4, 5)));
 extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
 					__u32 compat);
@@ -1136,12 +1142,28 @@ extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
 				      struct ext4_group_desc *bg);
 extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
 				     struct ext4_group_desc *bg);
+extern __u32 ext4_free_blks_count(struct super_block *sb,
+				struct ext4_group_desc *bg);
+extern __u32 ext4_free_inodes_count(struct super_block *sb,
+				 struct ext4_group_desc *bg);
+extern __u32 ext4_used_dirs_count(struct super_block *sb,
+				struct ext4_group_desc *bg);
+extern __u32 ext4_itable_unused_count(struct super_block *sb,
+				   struct ext4_group_desc *bg);
 extern void ext4_block_bitmap_set(struct super_block *sb,
 				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
 extern void ext4_inode_bitmap_set(struct super_block *sb,
 				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
 extern void ext4_inode_table_set(struct super_block *sb,
 				 struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_free_blks_set(struct super_block *sb,
+			       struct ext4_group_desc *bg, __u32 count);
+extern void ext4_free_inodes_set(struct super_block *sb,
+				struct ext4_group_desc *bg, __u32 count);
+extern void ext4_used_dirs_set(struct super_block *sb,
+				struct ext4_group_desc *bg, __u32 count);
+extern void ext4_itable_unused_set(struct super_block *sb,
+				   struct ext4_group_desc *bg, __u32 count);
 
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
@@ -1246,6 +1268,50 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 	return ;
 }
 
+struct ext4_group_info {
+	unsigned long   bb_state;
+	struct rb_root  bb_free_root;
+	unsigned short  bb_first_free;
+	unsigned short  bb_free;
+	unsigned short  bb_fragments;
+	struct          list_head bb_prealloc_list;
+#ifdef DOUBLE_CHECK
+	void            *bb_bitmap;
+#endif
+	struct rw_semaphore alloc_sem;
+	unsigned short  bb_counters[];
+};
+
+#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
+#define EXT4_GROUP_INFO_LOCKED_BIT	1
+
+#define EXT4_MB_GRP_NEED_INIT(grp)	\
+	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+
+static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline void ext4_unlock_group(struct super_block *sb,
+					ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline int ext4_is_group_locked(struct super_block *sb,
+					ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
+						&(grinfo->bb_state));
+}
+
 /*
  * Inodes and files operations
  */
@@ -1271,18 +1337,38 @@ extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 				       int chunk);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
-			ext4_lblk_t iblock,
+			       ext4_lblk_t iblock, unsigned int max_blocks,
-			unsigned long max_blocks, struct buffer_head *bh_result,
+			       struct buffer_head *bh_result,
-			int create, int extend_disksize);
+			       int create, int extend_disksize);
 extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
 extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
-			sector_t block, unsigned long max_blocks,
+			sector_t block, unsigned int max_blocks,
 			struct buffer_head *bh, int create,
 			int extend_disksize, int flag);
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+			__u64 start, __u64 len);
+
+/*
+ * Add new method to test wether block and inode bitmaps are properly
+ * initialized. With uninit_bg reading the block from disk is not enough
+ * to mark the bitmap uptodate. We need to also zero-out the bitmap
+ */
+#define BH_BITMAP_UPTODATE BH_JBDPrivateStart
+
+static inline int bitmap_uptodate(struct buffer_head *bh)
+{
+	return (buffer_uptodate(bh) &&
+			test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
+}
+static inline void set_bitmap_uptodate(struct buffer_head *bh)
+{
+	set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+}
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */

fs/ext4/ext4_extents.h

@@ -194,11 +194,6 @@ static inline unsigned short ext_depth(struct inode *inode)
 	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
 }
 
-static inline void ext4_ext_tree_changed(struct inode *inode)
-{
-	EXT4_I(inode)->i_ext_generation++;
-}
-
 static inline void
 ext4_ext_invalidate_cache(struct inode *inode)
 {

fs/ext4/ext4_i.h

@@ -31,7 +31,7 @@ typedef unsigned long long ext4_fsblk_t;
 typedef __u32 ext4_lblk_t;
 
 /* data type for block group number */
-typedef unsigned long ext4_group_t;
+typedef unsigned int ext4_group_t;
 
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
@@ -100,9 +100,6 @@ struct ext4_inode_info {
 	 */
 	loff_t	i_disksize;
 
-	/* on-disk additional length */
-	__u16 i_extra_isize;
-
 	/*
 	 * i_data_sem is for serialising ext4_truncate() against
 	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
@@ -117,7 +114,6 @@ struct ext4_inode_info {
 	struct inode vfs_inode;
 	struct jbd2_inode jinode;
 
-	unsigned long i_ext_generation;
 	struct ext4_ext_cache i_cached_extent;
 	/*
 	 * File creation time. Its function is same as that of
@@ -130,10 +126,14 @@ struct ext4_inode_info {
 	spinlock_t i_prealloc_lock;
 
 	/* allocation reservation info for delalloc */
-	unsigned long i_reserved_data_blocks;
+	unsigned int i_reserved_data_blocks;
-	unsigned long i_reserved_meta_blocks;
+	unsigned int i_reserved_meta_blocks;
-	unsigned long i_allocated_meta_blocks;
+	unsigned int i_allocated_meta_blocks;
 	unsigned short i_delalloc_reserved_flag;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
 	spinlock_t i_block_reservation_lock;
 };
 

fs/ext4/ext4_jbd2.c

@@ -7,53 +7,96 @@
 int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_undo_access(handle, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_undo_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_get_write_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_write_access(handle, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_write_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_forget(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_forget(handle, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_forget(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_revoke(const char *where, handle_t *handle,
 				ext4_fsblk_t blocknr, struct buffer_head *bh)
 {
-	int err = jbd2_journal_revoke(handle, blocknr, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_revoke(handle, blocknr, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_get_create_access(const char *where,
 				handle_t *handle, struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_create_access(handle, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_create_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
-int __ext4_journal_dirty_metadata(const char *where,
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
-				handle_t *handle, struct buffer_head *bh)
+				 struct inode *inode, struct buffer_head *bh)
 {
-	int err = jbd2_journal_dirty_metadata(handle, bh);
+	int err = 0;
-	if (err)
+
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	} else {
+		mark_buffer_dirty(bh);
+		if (inode && inode_needs_sync(inode)) {
+			sync_dirty_buffer(bh);
+			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				ext4_error(inode->i_sb, __func__,
+					   "IO error syncing inode, "
+					   "inode=%lu, block=%llu",
+					   inode->i_ino,
+					   (unsigned long long) bh->b_blocknr);
+				err = -EIO;
+			}
+		}
+	}
 	return err;
 }

fs/ext4/ext4_jbd2.h

@@ -32,8 +32,8 @@
  * 5 levels of tree + root which are stored in the inode. */
 
 #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
-	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)	\
+	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)   \
-		|| test_opt(sb, EXTENTS) ? 27U : 8U)
+	 ? 27U : 8U)
 
 /* Extended attribute operations touch at most two data buffers,
  * two bitmap buffers, and two group summaries, in addition to the inode
@@ -122,12 +122,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
  * been done yet.
  */
 
-static inline void ext4_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	jbd2_journal_release_buffer(handle, bh);
-}
-
 void ext4_journal_abort_handle(const char *caller, const char *err_fn,
 		struct buffer_head *bh, handle_t *handle, int err);
 
@@ -146,8 +140,8 @@ int __ext4_journal_revoke(const char *where, handle_t *handle,
 int __ext4_journal_get_create_access(const char *where,
 				handle_t *handle, struct buffer_head *bh);
 
-int __ext4_journal_dirty_metadata(const char *where,
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
-				handle_t *handle, struct buffer_head *bh);
+				 struct inode *inode, struct buffer_head *bh);
 
 #define ext4_journal_get_undo_access(handle, bh) \
 	__ext4_journal_get_undo_access(__func__, (handle), (bh))
@@ -157,14 +151,57 @@ int __ext4_journal_dirty_metadata(const char *where,
 	__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
 #define ext4_journal_get_create_access(handle, bh) \
 	__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_dirty_metadata(handle, bh) \
-	__ext4_journal_dirty_metadata(__func__, (handle), (bh))
 #define ext4_journal_forget(handle, bh) \
 	__ext4_journal_forget(__func__, (handle), (bh))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+	__ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
 
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
 int __ext4_journal_stop(const char *where, handle_t *handle);
 
+#define EXT4_NOJOURNAL_HANDLE	((handle_t *) 0x1)
+
+static inline int ext4_handle_valid(handle_t *handle)
+{
+	if (handle == EXT4_NOJOURNAL_HANDLE)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		handle->h_sync = 1;
+}
+
+static inline void ext4_handle_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	if (ext4_handle_valid(handle))
+		jbd2_journal_release_buffer(handle, bh);
+}
+
+static inline int ext4_handle_is_aborted(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		return is_handle_aborted(handle);
+	return 0;
+}
+
+static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+{
+	if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_journal_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	if (ext4_handle_valid(handle))
+		jbd2_journal_release_buffer(handle, bh);
+}
+
 static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
 {
 	return ext4_journal_start_sb(inode->i_sb, nblocks);
@@ -180,27 +217,37 @@ static inline handle_t *ext4_journal_current_handle(void)
 
 static inline int ext4_journal_extend(handle_t *handle, int nblocks)
 {
-	return jbd2_journal_extend(handle, nblocks);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_extend(handle, nblocks);
+	return 0;
 }
 
 static inline int ext4_journal_restart(handle_t *handle, int nblocks)
 {
-	return jbd2_journal_restart(handle, nblocks);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_restart(handle, nblocks);
+	return 0;
 }
 
 static inline int ext4_journal_blocks_per_page(struct inode *inode)
 {
-	return jbd2_journal_blocks_per_page(inode);
+	if (EXT4_JOURNAL(inode) != NULL)
+		return jbd2_journal_blocks_per_page(inode);
+	return 0;
 }
 
 static inline int ext4_journal_force_commit(journal_t *journal)
 {
-	return jbd2_journal_force_commit(journal);
+	if (journal)
+		return jbd2_journal_force_commit(journal);
+	return 0;
 }
 
 static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
 {
-	return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+	return 0;
 }
 
 /* super.c */
@@ -208,6 +255,8 @@ int ext4_force_commit(struct super_block *sb);
 
 static inline int ext4_should_journal_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 1;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -219,6 +268,8 @@ static inline int ext4_should_journal_data(struct inode *inode)
 
 static inline int ext4_should_order_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
 	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
@@ -230,6 +281,8 @@ static inline int ext4_should_order_data(struct inode *inode)
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
 	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)

fs/ext4/ext4_sb.h

@@ -57,6 +57,7 @@ struct ext4_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
@@ -73,6 +74,8 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	unsigned long s_commit_interval;
+	u32 s_max_batch_time;
+	u32 s_min_batch_time;
 	struct block_device *journal_bdev;
 #ifdef CONFIG_JBD2_DEBUG
 	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
@@ -101,7 +104,8 @@ struct ext4_sb_info {
 	spinlock_t s_reserve_lock;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
-	unsigned short *s_mb_offsets, *s_mb_maxs;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
 
 	/* tunables */
 	unsigned long s_stripe;

fs/ext4/extents.c

@@ -97,6 +97,8 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed)
 {
 	int err;
 
+	if (!ext4_handle_valid(handle))
+		return 0;
 	if (handle->h_buffer_credits > needed)
 		return 0;
 	err = ext4_journal_extend(handle, needed);
@@ -134,7 +136,7 @@ static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
 	int err;
 	if (path->p_bh) {
 		/* path points to block */
-		err = ext4_journal_dirty_metadata(handle, path->p_bh);
+		err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
 	} else {
 		/* path points to leaf/index in inode body */
 		err = ext4_mark_inode_dirty(handle, inode);
@@ -191,7 +193,7 @@ ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t goal, newblock;
 
 	goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
-	newblock = ext4_new_meta_block(handle, inode, goal, err);
+	newblock = ext4_new_meta_blocks(handle, inode, goal, NULL, err);
 	return newblock;
 }
 
@@ -780,7 +782,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 
-	err = ext4_journal_dirty_metadata(handle, bh);
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
 	if (err)
 		goto cleanup;
 	brelse(bh);
@@ -859,7 +861,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 
-		err = ext4_journal_dirty_metadata(handle, bh);
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (err)
 			goto cleanup;
 		brelse(bh);
@@ -955,7 +957,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 
-	err = ext4_journal_dirty_metadata(handle, bh);
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
 	if (err)
 		goto out;
 
@@ -1160,15 +1162,13 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
 	while (--depth >= 0) {
 		ix = path[depth].p_idx;
 		if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
-			break;
+			goto got_index;
 	}
 
-	if (depth < 0) {
+	/* we've gone up to the root and found no index to the right */
-		/* we've gone up to the root and
+	return 0;
-		 * found no index to the right */
-		return 0;
-	}
 
+got_index:
 	/* we've found index to the right, let's
 	 * follow it and find the closest allocated
 	 * block to the right */
@@ -1201,7 +1201,6 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
 	*phys = ext_pblock(ex);
 	put_bh(bh);
 	return 0;
-
 }
 
 /*
@@ -1622,7 +1621,6 @@ cleanup:
 		ext4_ext_drop_refs(npath);
 		kfree(npath);
 	}
-	ext4_ext_tree_changed(inode);
 	ext4_ext_invalidate_cache(inode);
 	return err;
 }
@@ -2233,7 +2231,6 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 		}
 	}
 out:
-	ext4_ext_tree_changed(inode);
 	ext4_ext_drop_refs(path);
 	kfree(path);
 	ext4_journal_stop(handle);
@@ -2250,7 +2247,7 @@ void ext4_ext_init(struct super_block *sb)
 	 * possible initialization would be here
 	 */
 
-	if (test_opt(sb, EXTENTS)) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 		printk(KERN_INFO "EXT4-fs: file extents enabled");
 #ifdef AGGRESSIVE_TEST
 		printk(", aggressive tests");
@@ -2275,7 +2272,7 @@ void ext4_ext_init(struct super_block *sb)
  */
 void ext4_ext_release(struct super_block *sb)
 {
-	if (!test_opt(sb, EXTENTS))
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
 		return;
 
 #ifdef EXTENTS_STATS
@@ -2380,7 +2377,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 						struct inode *inode,
 						struct ext4_ext_path *path,
 						ext4_lblk_t iblock,
-						unsigned long max_blocks)
+						unsigned int max_blocks)
 {
 	struct ext4_extent *ex, newex, orig_ex;
 	struct ext4_extent *ex1 = NULL;
@@ -2678,26 +2675,26 @@ fix_extent_len:
  */
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
-			unsigned long max_blocks, struct buffer_head *bh_result,
+			unsigned int max_blocks, struct buffer_head *bh_result,
 			int create, int extend_disksize)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent_header *eh;
 	struct ext4_extent newex, *ex;
-	ext4_fsblk_t goal, newblock;
+	ext4_fsblk_t newblock;
-	int err = 0, depth, ret;
+	int err = 0, depth, ret, cache_type;
-	unsigned long allocated = 0;
+	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
 	loff_t disksize;
 
 	__clear_bit(BH_New, &bh_result->b_state);
-	ext_debug("blocks %u/%lu requested for inode %u\n",
+	ext_debug("blocks %u/%u requested for inode %u\n",
 			iblock, max_blocks, inode->i_ino);
 
 	/* check in cache */
-	goal = ext4_ext_in_cache(inode, iblock, &newex);
+	cache_type = ext4_ext_in_cache(inode, iblock, &newex);
-	if (goal) {
+	if (cache_type) {
-		if (goal == EXT4_EXT_CACHE_GAP) {
+		if (cache_type == EXT4_EXT_CACHE_GAP) {
 			if (!create) {
 				/*
 				 * block isn't allocated yet and
@@ -2706,7 +2703,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 				goto out2;
 			}
 			/* we should allocate requested block */
-		} else if (goal == EXT4_EXT_CACHE_EXTENT) {
+		} else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
 			/* block is already allocated */
 			newblock = iblock
 				   - le32_to_cpu(newex.ee_block)
@@ -2854,7 +2851,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	if (!newblock)
 		goto out2;
 	ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
-			goal, newblock, allocated);
+		  ar.goal, newblock, allocated);
 
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
@@ -2950,7 +2947,7 @@ void ext4_ext_truncate(struct inode *inode)
 	 * transaction synchronous.
 	 */
 	if (IS_SYNC(inode))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 out_stop:
 	up_write(&EXT4_I(inode)->i_data_sem);
@@ -3004,7 +3001,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	handle_t *handle;
 	ext4_lblk_t block;
 	loff_t new_size;
-	unsigned long max_blocks;
+	unsigned int max_blocks;
 	int ret = 0;
 	int ret2 = 0;
 	int retries = 0;
@@ -3083,7 +3080,7 @@ retry:
 /*
  * Callback function called for each extent to gather FIEMAP information.
  */
-int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
 		       void *data)
 {
@@ -3152,7 +3149,8 @@ int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 /* fiemap flags we can handle specified here */
 #define EXT4_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
-int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+static int ext4_xattr_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo)
 {
 	__u64 physical = 0;
 	__u64 length;

fs/ext4/file.c

@@ -140,9 +140,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len);
-
 const struct file_operations ext4_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,

fs/ext4/hash.c

@@ -35,23 +35,43 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash(const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
-	while (len--) {
+	const unsigned char *ucp = (const unsigned char *) name;
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
 
-		if (hash & 0x80000000) hash -= 0x7fffffff;
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
 		hash1 = hash0;
 		hash0 = hash;
 	}
-	return (hash0 << 1);
+	return hash0 << 1;
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
 {
 	__u32	pad, val;
 	int	i;
+	const signed char *scp = (const signed char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +82,35 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	for (i = 0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
-		val = msg[i] + (val << 8);
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) ucp[i]) + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +143,8 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +163,18 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
-	case DX_HASH_LEGACY:
+	case DX_HASH_LEGACY_UNSIGNED:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash_unsigned(name, len);
 		break;
+	case DX_HASH_LEGACY:
+		hash = dx_hack_hash_signed(name, len);
+		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			(*str2hashbuf)(p, len, in, 8);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +182,12 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			(*str2hashbuf)(p, len, in, 4);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;

fs/ext4/ialloc.c

@@ -74,17 +74,17 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
 	/* 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, __func__, "Checksum bad for group %lu\n",
+		ext4_error(sb, __func__, "Checksum bad for group %u",
 			   block_group);
-		gdp->bg_free_blocks_count = 0;
+		ext4_free_blks_set(sb, gdp, 0);
-		gdp->bg_free_inodes_count = 0;
+		ext4_free_inodes_set(sb, gdp, 0);
-		gdp->bg_itable_unused = 0;
+		ext4_itable_unused_set(sb, gdp, 0);
 		memset(bh->b_data, 0xff, sb->s_blocksize);
 		return 0;
 	}
 
 	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
+	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
 			bh->b_data);
 
 	return EXT4_INODES_PER_GROUP(sb);
@@ -111,29 +111,49 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	if (unlikely(!bh)) {
 		ext4_error(sb, __func__,
 			    "Cannot read inode bitmap - "
-			    "block_group = %lu, inode_bitmap = %llu",
+			    "block_group = %u, inode_bitmap = %llu",
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (buffer_uptodate(bh) &&
+	if (bitmap_uptodate(bh))
-	    !(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
 		return bh;
 
 	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		unlock_buffer(bh);
 		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		unlock_buffer(bh);
 		return bh;
 	}
 	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
 		ext4_error(sb, __func__,
 			    "Cannot read inode bitmap - "
-			    "block_group = %lu, inode_bitmap = %llu",
+			    "block_group = %u, inode_bitmap = %llu",
 			    block_group, bitmap_blk);
 		return NULL;
 	}
@@ -168,7 +188,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	struct ext4_group_desc *gdp;
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
-	int fatal = 0, err;
+	int fatal = 0, err, count;
 	ext4_group_t flex_group;
 
 	if (atomic_read(&inode->i_count) > 1) {
@@ -190,6 +210,11 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 
 	ino = inode->i_ino;
 	ext4_debug("freeing inode %lu\n", ino);
+	trace_mark(ext4_free_inode,
+		   "dev %s ino %lu mode %d uid %lu gid %lu bocks %llu",
+		   sb->s_id, inode->i_ino, inode->i_mode,
+		   (unsigned long) inode->i_uid, (unsigned long) inode->i_gid,
+		   (unsigned long long) inode->i_blocks);
 
 	/*
 	 * Note: we must free any quota before locking the superblock,
@@ -236,9 +261,12 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 
 		if (gdp) {
 			spin_lock(sb_bgl_lock(sbi, block_group));
-			le16_add_cpu(&gdp->bg_free_inodes_count, 1);
+			count = ext4_free_inodes_count(sb, gdp) + 1;
-			if (is_directory)
+			ext4_free_inodes_set(sb, gdp, count);
-				le16_add_cpu(&gdp->bg_used_dirs_count, -1);
+			if (is_directory) {
+				count = ext4_used_dirs_count(sb, gdp) - 1;
+				ext4_used_dirs_set(sb, gdp, count);
+			}
 			gdp->bg_checksum = ext4_group_desc_csum(sbi,
 							block_group, gdp);
 			spin_unlock(sb_bgl_lock(sbi, block_group));
@@ -253,12 +281,12 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 				spin_unlock(sb_bgl_lock(sbi, flex_group));
 			}
 		}
-		BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
-		err = ext4_journal_dirty_metadata(handle, bh2);
+		err = ext4_handle_dirty_metadata(handle, NULL, bh2);
 		if (!fatal) fatal = err;
 	}
-	BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
+	BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
-	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 	if (!fatal)
 		fatal = err;
 	sb->s_dirt = 1;
@@ -291,13 +319,13 @@ static int find_group_dir(struct super_block *sb, struct inode *parent,
 
 	for (group = 0; group < ngroups; group++) {
 		desc = ext4_get_group_desc(sb, group, NULL);
-		if (!desc || !desc->bg_free_inodes_count)
+		if (!desc || !ext4_free_inodes_count(sb, desc))
 			continue;
-		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+		if (ext4_free_inodes_count(sb, desc) < avefreei)
 			continue;
 		if (!best_desc ||
-		    (le16_to_cpu(desc->bg_free_blocks_count) >
+		    (ext4_free_blks_count(sb, desc) >
-		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
+		     ext4_free_blks_count(sb, best_desc))) {
 			*best_group = group;
 			best_desc = desc;
 			ret = 0;
@@ -369,7 +397,7 @@ found_flexbg:
 	for (i = best_flex * flex_size; i < ngroups &&
 		     i < (best_flex + 1) * flex_size; i++) {
 		desc = ext4_get_group_desc(sb, i, &bh);
-		if (le16_to_cpu(desc->bg_free_inodes_count)) {
+		if (ext4_free_inodes_count(sb, desc)) {
 			*best_group = i;
 			goto out;
 		}
@@ -443,17 +471,17 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		for (i = 0; i < ngroups; i++) {
 			grp = (parent_group + i) % ngroups;
 			desc = ext4_get_group_desc(sb, grp, NULL);
-			if (!desc || !desc->bg_free_inodes_count)
+			if (!desc || !ext4_free_inodes_count(sb, desc))
 				continue;
-			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
+			if (ext4_used_dirs_count(sb, desc) >= best_ndir)
 				continue;
-			if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+			if (ext4_free_inodes_count(sb, desc) < avefreei)
 				continue;
-			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
+			if (ext4_free_blks_count(sb, desc) < avefreeb)
 				continue;
 			*group = grp;
 			ret = 0;
-			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+			best_ndir = ext4_used_dirs_count(sb, desc);
 		}
 		if (ret == 0)
 			return ret;
@@ -479,13 +507,13 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	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)
+		if (!desc || !ext4_free_inodes_count(sb, desc))
 			continue;
-		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
+		if (ext4_used_dirs_count(sb, desc) >= max_dirs)
 			continue;
-		if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
+		if (ext4_free_inodes_count(sb, desc) < min_inodes)
 			continue;
-		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
+		if (ext4_free_blks_count(sb, desc) < min_blocks)
 			continue;
 		return 0;
 	}
@@ -494,8 +522,8 @@ 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 &&
+		if (desc && ext4_free_inodes_count(sb, desc) &&
-			le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+			ext4_free_inodes_count(sb, desc) >= avefreei)
 			return 0;
 	}
 
@@ -524,8 +552,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 	 */
 	*group = parent_group;
 	desc = ext4_get_group_desc(sb, *group, NULL);
-	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+	if (desc && ext4_free_inodes_count(sb, desc) &&
-			le16_to_cpu(desc->bg_free_blocks_count))
+			ext4_free_blks_count(sb, desc))
 		return 0;
 
 	/*
@@ -548,8 +576,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		if (*group >= ngroups)
 			*group -= ngroups;
 		desc = ext4_get_group_desc(sb, *group, NULL);
-		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+		if (desc && ext4_free_inodes_count(sb, desc) &&
-				le16_to_cpu(desc->bg_free_blocks_count))
+				ext4_free_blks_count(sb, desc))
 			return 0;
 	}
 
@@ -562,13 +590,86 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		if (++*group >= ngroups)
 			*group = 0;
 		desc = ext4_get_group_desc(sb, *group, NULL);
-		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+		if (desc && ext4_free_inodes_count(sb, desc))
 			return 0;
 	}
 
 	return -1;
 }
 
+/*
+ * claim the inode from the inode bitmap. If the group
+ * is uninit we need to take the groups's sb_bgl_lock
+ * and clear the uninit flag. The inode bitmap update
+ * and group desc uninit flag clear should be done
+ * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * doesn't race with the ext4_claim_inode
+ */
+static int ext4_claim_inode(struct super_block *sb,
+			struct buffer_head *inode_bitmap_bh,
+			unsigned long ino, ext4_group_t group, int mode)
+{
+	int free = 0, retval = 0, count;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+	spin_lock(sb_bgl_lock(sbi, group));
+	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
+		/* not a free inode */
+		retval = 1;
+		goto err_ret;
+	}
+	ino++;
+	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
+			ino > EXT4_INODES_PER_GROUP(sb)) {
+		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_error(sb, __func__,
+			   "reserved inode or inode > inodes count - "
+			   "block_group = %u, inode=%lu", group,
+			   ino + group * EXT4_INODES_PER_GROUP(sb));
+		return 1;
+	}
+	/* If we didn't allocate from within the initialized part of the inode
+	 * table then we need to initialize up to this inode. */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			/* When marking the block group with
+			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
+			 * on the value of bg_itable_unused even though
+			 * mke2fs could have initialized the same for us.
+			 * Instead we calculated the value below
+			 */
+
+			free = 0;
+		} else {
+			free = EXT4_INODES_PER_GROUP(sb) -
+				ext4_itable_unused_count(sb, gdp);
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to  update the bg_itable_unused count
+		 *
+		 */
+		if (ino > free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - ino));
+	}
+	count = ext4_free_inodes_count(sb, gdp) - 1;
+	ext4_free_inodes_set(sb, gdp, count);
+	if (S_ISDIR(mode)) {
+		count = ext4_used_dirs_count(sb, gdp) + 1;
+		ext4_used_dirs_set(sb, gdp, count);
+	}
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+err_ret:
+	spin_unlock(sb_bgl_lock(sbi, group));
+	return retval;
+}
+
 /*
  * There are two policies for allocating an inode.  If the new inode is
  * a directory, then a forward search is made for a block group with both
@@ -582,8 +683,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 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 *inode_bitmap_bh = NULL;
-	struct buffer_head *bh2;
+	struct buffer_head *group_desc_bh;
 	ext4_group_t group = 0;
 	unsigned long ino = 0;
 	struct inode *inode;
@@ -602,6 +703,8 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 		return ERR_PTR(-EPERM);
 
 	sb = dir->i_sb;
+	trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
+		   dir->i_ino, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
@@ -631,40 +734,52 @@ got_group:
 	for (i = 0; i < sbi->s_groups_count; i++) {
 		err = -EIO;
 
-		gdp = ext4_get_group_desc(sb, group, &bh2);
+		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
 		if (!gdp)
 			goto fail;
 
-		brelse(bitmap_bh);
+		brelse(inode_bitmap_bh);
-		bitmap_bh = ext4_read_inode_bitmap(sb, group);
+		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
-		if (!bitmap_bh)
+		if (!inode_bitmap_bh)
 			goto fail;
 
 		ino = 0;
 
 repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
-				bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
+					      inode_bitmap_bh->b_data,
+					      EXT4_INODES_PER_GROUP(sb), ino);
+
 		if (ino < EXT4_INODES_PER_GROUP(sb)) {
 
-			BUFFER_TRACE(bitmap_bh, "get_write_access");
+			BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle, bitmap_bh);
+			err = ext4_journal_get_write_access(handle,
+							    inode_bitmap_bh);
 			if (err)
 				goto fail;
 
-			if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
+			BUFFER_TRACE(group_desc_bh, "get_write_access");
-						ino, bitmap_bh->b_data)) {
+			err = ext4_journal_get_write_access(handle,
+								group_desc_bh);
+			if (err)
+				goto fail;
+			if (!ext4_claim_inode(sb, inode_bitmap_bh,
+						ino, group, mode)) {
 				/* we won it */
-				BUFFER_TRACE(bitmap_bh,
+				BUFFER_TRACE(inode_bitmap_bh,
-					"call ext4_journal_dirty_metadata");
+					"call ext4_handle_dirty_metadata");
-				err = ext4_journal_dirty_metadata(handle,
+				err = ext4_handle_dirty_metadata(handle,
-								bitmap_bh);
+								 inode,
+							inode_bitmap_bh);
 				if (err)
 					goto fail;
+				/* zero bit is inode number 1*/
+				ino++;
 				goto got;
 			}
 			/* we lost it */
-			jbd2_journal_release_buffer(handle, bitmap_bh);
+			ext4_handle_release_buffer(handle, inode_bitmap_bh);
+			ext4_handle_release_buffer(handle, group_desc_bh);
 
 			if (++ino < EXT4_INODES_PER_GROUP(sb))
 				goto repeat_in_this_group;
@@ -684,30 +799,16 @@ repeat_in_this_group:
 	goto out;
 
 got:
-	ino++;
-	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
-	    ino > EXT4_INODES_PER_GROUP(sb)) {
-		ext4_error(sb, __func__,
-			   "reserved inode or inode > inodes count - "
-			   "block_group = %lu, inode=%lu", group,
-			   ino + group * EXT4_INODES_PER_GROUP(sb));
-		err = -EIO;
-		goto fail;
-	}
-
-	BUFFER_TRACE(bh2, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh2);
-	if (err) goto fail;
-
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-		struct buffer_head *block_bh = ext4_read_block_bitmap(sb, group);
+		struct buffer_head *block_bitmap_bh;
 
-		BUFFER_TRACE(block_bh, "get block bitmap access");
+		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
-		err = ext4_journal_get_write_access(handle, block_bh);
+		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
+		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
-			brelse(block_bh);
+			brelse(block_bitmap_bh);
 			goto fail;
 		}
 
@@ -715,9 +816,9 @@ got:
 		spin_lock(sb_bgl_lock(sbi, group));
 		/* recheck and clear flag under lock if we still need to */
 		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			free = ext4_free_blocks_after_init(sb, group, gdp);
-			gdp->bg_free_blocks_count = cpu_to_le16(free);
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+			ext4_free_blks_set(sb, gdp, free);
 			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
 								gdp);
 		}
@@ -725,55 +826,19 @@ got:
 
 		/* Don't need to dirty bitmap block if we didn't change it */
 		if (free) {
-			BUFFER_TRACE(block_bh, "dirty block bitmap");
+			BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
-			err = ext4_journal_dirty_metadata(handle, block_bh);
+			err = ext4_handle_dirty_metadata(handle,
+							NULL, block_bitmap_bh);
 		}
 
-		brelse(block_bh);
+		brelse(block_bitmap_bh);
 		if (err)
 			goto fail;
 	}
-
+	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
-	spin_lock(sb_bgl_lock(sbi, group));
+	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
-	/* If we didn't allocate from within the initialized part of the inode
+	if (err)
-	 * table then we need to initialize up to this inode. */
+		goto fail;
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
-
-			/* When marking the block group with
-			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
-			 * on the value of bg_itable_unused even though
-			 * mke2fs could have initialized the same for us.
-			 * Instead we calculated the value below
-			 */
-
-			free = 0;
-		} else {
-			free = EXT4_INODES_PER_GROUP(sb) -
-				le16_to_cpu(gdp->bg_itable_unused);
-		}
-
-		/*
-		 * Check the relative inode number against the last used
-		 * relative inode number in this group. if it is greater
-		 * we need to  update the bg_itable_unused count
-		 *
-		 */
-		if (ino > free)
-			gdp->bg_itable_unused =
-				cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
-	}
-
-	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
-	if (S_ISDIR(mode)) {
-		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
-	}
-	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
-	spin_unlock(sb_bgl_lock(sbi, group));
-	BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
-	err = ext4_journal_dirty_metadata(handle, bh2);
-	if (err) goto fail;
 
 	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
@@ -825,7 +890,7 @@ got:
 
 	ext4_set_inode_flags(inode);
 	if (IS_DIRSYNC(inode))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
 		err = -EINVAL;
 		goto fail_drop;
@@ -852,7 +917,7 @@ got:
 	if (err)
 		goto fail_free_drop;
 
-	if (test_opt(sb, EXTENTS)) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 		/* set extent flag only for directory, file and normal symlink*/
 		if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
 			EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
@@ -867,6 +932,8 @@ got:
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
+	trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d",
+		   sb->s_id, inode->i_ino, dir->i_ino, mode);
 	goto really_out;
 fail:
 	ext4_std_error(sb, err);
@@ -874,7 +941,7 @@ out:
 	iput(inode);
 	ret = ERR_PTR(err);
 really_out:
-	brelse(bitmap_bh);
+	brelse(inode_bitmap_bh);
 	return ret;
 
 fail_free_drop:
@@ -886,7 +953,7 @@ fail_drop:
 	inode->i_nlink = 0;
 	unlock_new_inode(inode);
 	iput(inode);
-	brelse(bitmap_bh);
+	brelse(inode_bitmap_bh);
 	return ERR_PTR(err);
 }
 
@@ -985,7 +1052,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+		desc_count += ext4_free_inodes_count(sb, gdp);
 		brelse(bitmap_bh);
 		bitmap_bh = ext4_read_inode_bitmap(sb, i);
 		if (!bitmap_bh)
@@ -993,7 +1060,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 
 		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
-			i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+			i, ext4_free_inodes_count(sb, gdp), x);
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);
@@ -1007,7 +1074,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+		desc_count += ext4_free_inodes_count(sb, gdp);
 		cond_resched();
 	}
 	return desc_count;
@@ -1024,8 +1091,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
 		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		count += le16_to_cpu(gdp->bg_used_dirs_count);
+		count += ext4_used_dirs_count(sb, gdp);
 	}
 	return count;
 }
-

fs/ext4/inode.c

@@ -72,12 +72,17 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
  * "bh" may be NULL: a metadata block may have been freed from memory
  * but there may still be a record of it in the journal, and that record
  * still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling so there's nothing to do.
  */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 			struct buffer_head *bh, ext4_fsblk_t blocknr)
 {
 	int err;
 
+	if (!ext4_handle_valid(handle))
+		return 0;
+
 	might_sleep();
 
 	BUFFER_TRACE(bh, "enter");
@@ -170,7 +175,9 @@ static handle_t *start_transaction(struct inode *inode)
  */
 static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
 {
-	if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+	if (!ext4_handle_valid(handle))
+		return 0;
+	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
 		return 0;
 	if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
 		return 0;
@@ -184,6 +191,7 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
  */
 static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
 {
+	BUG_ON(EXT4_JOURNAL(inode) == NULL);
 	jbd_debug(2, "restarting handle %p\n", handle);
 	return ext4_journal_restart(handle, blocks_for_truncate(inode));
 }
@@ -216,7 +224,7 @@ void ext4_delete_inode(struct inode *inode)
 	}
 
 	if (IS_SYNC(inode))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 	inode->i_size = 0;
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
@@ -233,7 +241,7 @@ void ext4_delete_inode(struct inode *inode)
 	 * enough credits left in the handle to remove the inode from
 	 * the orphan list and set the dtime field.
 	 */
-	if (handle->h_buffer_credits < 3) {
+	if (!ext4_handle_has_enough_credits(handle, 3)) {
 		err = ext4_journal_extend(handle, 3);
 		if (err > 0)
 			err = ext4_journal_restart(handle, 3);
@@ -506,10 +514,10 @@ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
  *	return the total number of blocks to be allocate, including the
  *	direct and indirect blocks.
  */
-static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
+static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
 		int blocks_to_boundary)
 {
-	unsigned long count = 0;
+	unsigned int count = 0;
 
 	/*
 	 * Simple case, [t,d]Indirect block(s) has not allocated yet
@@ -547,6 +555,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 				int indirect_blks, int blks,
 				ext4_fsblk_t new_blocks[4], int *err)
 {
+	struct ext4_allocation_request ar;
 	int target, i;
 	unsigned long count = 0, blk_allocated = 0;
 	int index = 0;
@@ -595,10 +604,17 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	if (!target)
 		goto allocated;
 	/* Now allocate data blocks */
-	count = target;
+	memset(&ar, 0, sizeof(ar));
-	/* allocating blocks for data blocks */
+	ar.inode = inode;
-	current_block = ext4_new_blocks(handle, inode, iblock,
+	ar.goal = goal;
-						goal, &count, err);
+	ar.len = target;
+	ar.logical = iblock;
+	if (S_ISREG(inode->i_mode))
+		/* enable in-core preallocation only for regular files */
+		ar.flags = EXT4_MB_HINT_DATA;
+
+	current_block = ext4_mb_new_blocks(handle, &ar, err);
+
 	if (*err && (target == blks)) {
 		/*
 		 * if the allocation failed and we didn't allocate
@@ -614,7 +630,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 		 */
 			new_blocks[index] = current_block;
 		}
-		blk_allocated += count;
+		blk_allocated += ar.len;
 	}
 allocated:
 	/* total number of blocks allocated for direct blocks */
@@ -709,8 +725,8 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 
-		BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-		err = ext4_journal_dirty_metadata(handle, bh);
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (err)
 			goto failed;
 	}
@@ -792,8 +808,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 		 * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
 		 */
 		jbd_debug(5, "splicing indirect only\n");
-		BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
-		err = ext4_journal_dirty_metadata(handle, where->bh);
+		err = ext4_handle_dirty_metadata(handle, inode, where->bh);
 		if (err)
 			goto err_out;
 	} else {
@@ -840,10 +856,10 @@ err_out:
  * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
  * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
  */
-int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
-		ext4_lblk_t iblock, unsigned long maxblocks,
+				  ext4_lblk_t iblock, unsigned int maxblocks,
-		struct buffer_head *bh_result,
+				  struct buffer_head *bh_result,
-		int create, int extend_disksize)
+				  int create, int extend_disksize)
 {
 	int err = -EIO;
 	ext4_lblk_t offsets[4];
@@ -1045,7 +1061,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
  * It returns the error in case of allocation failure.
  */
 int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
-			unsigned long max_blocks, struct buffer_head *bh,
+			unsigned int max_blocks, struct buffer_head *bh,
 			int create, int extend_disksize, int flag)
 {
 	int retval;
@@ -1221,8 +1237,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 				set_buffer_uptodate(bh);
 			}
 			unlock_buffer(bh);
-			BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-			err = ext4_journal_dirty_metadata(handle, bh);
+			err = ext4_handle_dirty_metadata(handle, inode, bh);
 			if (!fatal)
 				fatal = err;
 		} else {
@@ -1335,6 +1351,10 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
  	pgoff_t index;
 	unsigned from, to;
 
+	trace_mark(ext4_write_begin,
+		   "dev %s ino %lu pos %llu len %u flags %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, flags);
  	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
@@ -1387,7 +1407,7 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
 	set_buffer_uptodate(bh);
-	return ext4_journal_dirty_metadata(handle, bh);
+	return ext4_handle_dirty_metadata(handle, NULL, bh);
 }
 
 /*
@@ -1406,6 +1426,10 @@ static int ext4_ordered_write_end(struct file *file,
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 
+	trace_mark(ext4_ordered_write_end,
+		   "dev %s ino %lu pos %llu len %u copied %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, copied);
 	ret = ext4_jbd2_file_inode(handle, inode);
 
 	if (ret == 0) {
@@ -1444,6 +1468,10 @@ static int ext4_writeback_write_end(struct file *file,
 	int ret = 0, ret2;
 	loff_t new_i_size;
 
+	trace_mark(ext4_writeback_write_end,
+		   "dev %s ino %lu pos %llu len %u copied %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, copied);
 	new_i_size = pos + copied;
 	if (new_i_size > EXT4_I(inode)->i_disksize) {
 		ext4_update_i_disksize(inode, new_i_size);
@@ -1479,6 +1507,10 @@ static int ext4_journalled_write_end(struct file *file,
 	unsigned from, to;
 	loff_t new_i_size;
 
+	trace_mark(ext4_journalled_write_end,
+		   "dev %s ino %lu pos %llu len %u copied %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
@@ -1625,7 +1657,7 @@ struct mpage_da_data {
 	get_block_t *get_block;
 	struct writeback_control *wbc;
 	int io_done;
-	long pages_written;
+	int pages_written;
 	int retval;
 };
 
@@ -1645,35 +1677,39 @@ struct mpage_da_data {
  */
 static int mpage_da_submit_io(struct mpage_da_data *mpd)
 {
-	struct address_space *mapping = mpd->inode->i_mapping;
-	int ret = 0, err, nr_pages, i;
-	unsigned long index, end;
-	struct pagevec pvec;
 	long pages_skipped;
+	struct pagevec pvec;
+	unsigned long index, end;
+	int ret = 0, err, nr_pages, i;
+	struct inode *inode = mpd->inode;
+	struct address_space *mapping = inode->i_mapping;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-	pagevec_init(&pvec, 0);
+	/*
+	 * We need to start from the first_page to the next_page - 1
+	 * to make sure we also write the mapped dirty buffer_heads.
+	 * If we look at mpd->lbh.b_blocknr we would only be looking
+	 * at the currently mapped buffer_heads.
+	 */
 	index = mpd->first_page;
 	end = mpd->next_page - 1;
 
+	pagevec_init(&pvec, 0);
 	while (index <= end) {
-		/*
+		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
-		 * We can use PAGECACHE_TAG_DIRTY lookup here because
-		 * even though we have cleared the dirty flag on the page
-		 * We still keep the page in the radix tree with tag
-		 * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
-		 * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
-		 * which is called via the below writepage callback.
-		 */
-		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-					PAGECACHE_TAG_DIRTY,
-					min(end - index,
-					(pgoff_t)PAGEVEC_SIZE-1) + 1);
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
+			index = page->index;
+			if (index > end)
+				break;
+			index++;
+
+			BUG_ON(!PageLocked(page));
+			BUG_ON(PageWriteback(page));
+
 			pages_skipped = mpd->wbc->pages_skipped;
 			err = mapping->a_ops->writepage(page, mpd->wbc);
 			if (!err && (pages_skipped == mpd->wbc->pages_skipped))
@@ -1831,13 +1867,13 @@ static void ext4_print_free_blocks(struct inode *inode)
 			ext4_count_free_blocks(inode->i_sb));
 	printk(KERN_EMERG "Free/Dirty block details\n");
 	printk(KERN_EMERG "free_blocks=%lld\n",
-			percpu_counter_sum(&sbi->s_freeblocks_counter));
+			(long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
 	printk(KERN_EMERG "dirty_blocks=%lld\n",
-			percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+			(long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
 	printk(KERN_EMERG "Block reservation details\n");
-	printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+	printk(KERN_EMERG "i_reserved_data_blocks=%u\n",
 			EXT4_I(inode)->i_reserved_data_blocks);
-	printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+	printk(KERN_EMERG "i_reserved_meta_blocks=%u\n",
 			EXT4_I(inode)->i_reserved_meta_blocks);
 	return;
 }
@@ -2087,11 +2123,29 @@ static int __mpage_da_writepage(struct page *page,
 		bh = head;
 		do {
 			BUG_ON(buffer_locked(bh));
+			/*
+			 * We need to try to allocate
+			 * unmapped blocks in the same page.
+			 * Otherwise we won't make progress
+			 * with the page in ext4_da_writepage
+			 */
 			if (buffer_dirty(bh) &&
 				(!buffer_mapped(bh) || buffer_delay(bh))) {
 				mpage_add_bh_to_extent(mpd, logical, bh);
 				if (mpd->io_done)
 					return MPAGE_DA_EXTENT_TAIL;
+			} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+				/*
+				 * mapped dirty buffer. We need to update
+				 * the b_state because we look at
+				 * b_state in mpage_da_map_blocks. We don't
+				 * update b_size because if we find an
+				 * unmapped buffer_head later we need to
+				 * use the b_state flag of that buffer_head.
+				 */
+				if (mpd->lbh.b_size == 0)
+					mpd->lbh.b_state =
+						bh->b_state & BH_FLAGS;
 			}
 			logical++;
 		} while ((bh = bh->b_this_page) != head);
@@ -2269,10 +2323,13 @@ static int ext4_da_writepage(struct page *page,
 {
 	int ret = 0;
 	loff_t size;
-	unsigned long len;
+	unsigned int len;
 	struct buffer_head *page_bufs;
 	struct inode *inode = page->mapping->host;
 
+	trace_mark(ext4_da_writepage,
+		   "dev %s ino %lu page_index %lu",
+		   inode->i_sb->s_id, inode->i_ino, page->index);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2378,10 +2435,25 @@ static int ext4_da_writepages(struct address_space *mapping,
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
 	int no_nrwrite_index_update;
-	long pages_written = 0, pages_skipped;
+	int pages_written = 0;
+	long pages_skipped;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
+	trace_mark(ext4_da_writepages,
+		   "dev %s ino %lu nr_t_write %ld "
+		   "pages_skipped %ld range_start %llu "
+		   "range_end %llu nonblocking %d "
+		   "for_kupdate %d for_reclaim %d "
+		   "for_writepages %d range_cyclic %d",
+		   inode->i_sb->s_id, inode->i_ino,
+		   wbc->nr_to_write, wbc->pages_skipped,
+		   (unsigned long long) wbc->range_start,
+		   (unsigned long long) wbc->range_end,
+		   wbc->nonblocking, wbc->for_kupdate,
+		   wbc->for_reclaim, wbc->for_writepages,
+		   wbc->range_cyclic);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -2389,6 +2461,20 @@ static int ext4_da_writepages(struct address_space *mapping,
 	 */
 	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
+
+	/*
+	 * If the filesystem has aborted, it is read-only, so return
+	 * right away instead of dumping stack traces later on that
+	 * will obscure the real source of the problem.  We test
+	 * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+	 * the latter could be true if the filesystem is mounted
+	 * read-only, and in that case, ext4_da_writepages should
+	 * *never* be called, so if that ever happens, we would want
+	 * the stack trace.
+	 */
+	if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+		return -EROFS;
+
 	/*
 	 * Make sure nr_to_write is >= sbi->s_mb_stream_request
 	 * This make sure small files blocks are allocated in
@@ -2433,7 +2519,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 		handle = ext4_journal_start(inode, needed_blocks);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
-			printk(KERN_EMERG "%s: jbd2_start: "
+			printk(KERN_CRIT "%s: jbd2_start: "
 			       "%ld pages, ino %lu; err %d\n", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
 			dump_stack();
@@ -2486,6 +2572,14 @@ out_writepages:
 	if (!no_nrwrite_index_update)
 		wbc->no_nrwrite_index_update = 0;
 	wbc->nr_to_write -= nr_to_writebump;
+	trace_mark(ext4_da_writepage_result,
+		   "dev %s ino %lu ret %d pages_written %d "
+		   "pages_skipped %ld congestion %d "
+		   "more_io %d no_nrwrite_index_update %d",
+		   inode->i_sb->s_id, inode->i_ino, ret,
+		   pages_written, wbc->pages_skipped,
+		   wbc->encountered_congestion, wbc->more_io,
+		   wbc->no_nrwrite_index_update);
 	return ret;
 }
 
@@ -2537,6 +2631,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 					len, flags, pagep, fsdata);
 	}
 	*fsdata = (void *)0;
+
+	trace_mark(ext4_da_write_begin,
+		   "dev %s ino %lu pos %llu len %u flags %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, flags);
 retry:
 	/*
 	 * With delayed allocation, we don't log the i_disksize update
@@ -2626,6 +2725,10 @@ static int ext4_da_write_end(struct file *file,
 		}
 	}
 
+	trace_mark(ext4_da_write_end,
+		   "dev %s ino %lu pos %llu len %u copied %u",
+		   inode->i_sb->s_id, inode->i_ino,
+		   (unsigned long long) pos, len, copied);
 	start = pos & (PAGE_CACHE_SIZE - 1);
 	end = start + copied - 1;
 
@@ -2718,7 +2821,10 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 		filemap_write_and_wait(mapping);
 	}
 
-	if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+	BUG_ON(!EXT4_JOURNAL(inode) &&
+	       EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
+
+	if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
 		/*
 		 * This is a REALLY heavyweight approach, but the use of
 		 * bmap on dirty files is expected to be extremely rare:
@@ -2836,6 +2942,9 @@ static int ext4_normal_writepage(struct page *page,
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
+	trace_mark(ext4_normal_writepage,
+		   "dev %s ino %lu page_index %lu",
+		   inode->i_sb->s_id, inode->i_ino, page->index);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2921,6 +3030,9 @@ static int ext4_journalled_writepage(struct page *page,
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
+	trace_mark(ext4_journalled_writepage,
+		   "dev %s ino %lu page_index %lu",
+		   inode->i_sb->s_id, inode->i_ino, page->index);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2989,7 +3101,10 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset)
 	if (offset == 0)
 		ClearPageChecked(page);
 
-	jbd2_journal_invalidatepage(journal, page, offset);
+	if (journal)
+		jbd2_journal_invalidatepage(journal, page, offset);
+	else
+		block_invalidatepage(page, offset);
 }
 
 static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -2999,7 +3114,10 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 	WARN_ON(PageChecked(page));
 	if (!page_has_buffers(page))
 		return 0;
-	return jbd2_journal_try_to_free_buffers(journal, page, wait);
+	if (journal)
+		return jbd2_journal_try_to_free_buffers(journal, page, wait);
+	else
+		return try_to_free_buffers(page);
 }
 
 /*
@@ -3271,7 +3389,7 @@ int ext4_block_truncate_page(handle_t *handle,
 
 	err = 0;
 	if (ext4_should_journal_data(inode)) {
-		err = ext4_journal_dirty_metadata(handle, bh);
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
 	} else {
 		if (ext4_should_order_data(inode))
 			err = ext4_jbd2_file_inode(handle, inode);
@@ -3395,8 +3513,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	__le32 *p;
 	if (try_to_extend_transaction(handle, inode)) {
 		if (bh) {
-			BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-			ext4_journal_dirty_metadata(handle, bh);
+			ext4_handle_dirty_metadata(handle, inode, bh);
 		}
 		ext4_mark_inode_dirty(handle, inode);
 		ext4_journal_test_restart(handle, inode);
@@ -3496,7 +3614,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
 				  count, block_to_free_p, p);
 
 	if (this_bh) {
-		BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
 
 		/*
 		 * The buffer head should have an attached journal head at this
@@ -3505,7 +3623,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
 		 * the block was cleared. Check for this instead of OOPSing.
 		 */
 		if (bh2jh(this_bh))
-			ext4_journal_dirty_metadata(handle, this_bh);
+			ext4_handle_dirty_metadata(handle, inode, this_bh);
 		else
 			ext4_error(inode->i_sb, __func__,
 				   "circular indirect block detected, "
@@ -3535,7 +3653,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t nr;
 	__le32 *p;
 
-	if (is_handle_aborted(handle))
+	if (ext4_handle_is_aborted(handle))
 		return;
 
 	if (depth--) {
@@ -3605,7 +3723,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 			 * will merely complain about releasing a free block,
 			 * rather than leaking blocks.
 			 */
-			if (is_handle_aborted(handle))
+			if (ext4_handle_is_aborted(handle))
 				return;
 			if (try_to_extend_transaction(handle, inode)) {
 				ext4_mark_inode_dirty(handle, inode);
@@ -3624,9 +3742,10 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 								   parent_bh)){
 					*p = 0;
 					BUFFER_TRACE(parent_bh,
-					"call ext4_journal_dirty_metadata");
+					"call ext4_handle_dirty_metadata");
-					ext4_journal_dirty_metadata(handle,
+					ext4_handle_dirty_metadata(handle,
-								    parent_bh);
+								   inode,
+								   parent_bh);
 				}
 			}
 		}
@@ -3814,7 +3933,7 @@ do_indirects:
 	 * synchronous
 	 */
 	if (IS_SYNC(inode))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 out_stop:
 	/*
 	 * If this was a simple ftruncate(), and the file will remain alive
@@ -3844,7 +3963,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	ext4_fsblk_t		block;
 	int			inodes_per_block, inode_offset;
 
-	iloc->bh = 0;
+	iloc->bh = NULL;
 	if (!ext4_valid_inum(sb, inode->i_ino))
 		return -EIO;
 
@@ -3951,7 +4070,7 @@ make_io:
 			num = EXT4_INODES_PER_GROUP(sb);
 			if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
-				num -= le16_to_cpu(gdp->bg_itable_unused);
+				num -= ext4_itable_unused_count(sb, gdp);
 			table += num / inodes_per_block;
 			if (end > table)
 				end = table;
@@ -4313,8 +4432,8 @@ static int ext4_do_update_inode(handle_t *handle,
 			EXT4_SET_RO_COMPAT_FEATURE(sb,
 					EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
 			sb->s_dirt = 1;
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
-			err = ext4_journal_dirty_metadata(handle,
+			err = ext4_handle_dirty_metadata(handle, inode,
 					EXT4_SB(sb)->s_sbh);
 		}
 	}
@@ -4341,9 +4460,8 @@ static int ext4_do_update_inode(handle_t *handle,
 		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
 	}
 
-
+	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+	rc = ext4_handle_dirty_metadata(handle, inode, bh);
-	rc = ext4_journal_dirty_metadata(handle, bh);
 	if (!err)
 		err = rc;
 	ei->i_state &= ~EXT4_STATE_NEW;
@@ -4406,6 +4524,25 @@ int ext4_write_inode(struct inode *inode, int wait)
 	return ext4_force_commit(inode->i_sb);
 }
 
+int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
+{
+	int err = 0;
+
+	mark_buffer_dirty(bh);
+	if (inode && inode_needs_sync(inode)) {
+		sync_dirty_buffer(bh);
+		if (buffer_req(bh) && !buffer_uptodate(bh)) {
+			ext4_error(inode->i_sb, __func__,
+				   "IO error syncing inode, "
+				   "inode=%lu, block=%llu",
+				   inode->i_ino,
+				   (unsigned long long)bh->b_blocknr);
+			err = -EIO;
+		}
+	}
+	return err;
+}
+
 /*
  * ext4_setattr()
  *
@@ -4710,16 +4847,15 @@ int
 ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 			 struct ext4_iloc *iloc)
 {
-	int err = 0;
+	int err;
-	if (handle) {
+
-		err = ext4_get_inode_loc(inode, iloc);
+	err = ext4_get_inode_loc(inode, iloc);
-		if (!err) {
+	if (!err) {
-			BUFFER_TRACE(iloc->bh, "get_write_access");
+		BUFFER_TRACE(iloc->bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle, iloc->bh);
+		err = ext4_journal_get_write_access(handle, iloc->bh);
-			if (err) {
+		if (err) {
-				brelse(iloc->bh);
+			brelse(iloc->bh);
-				iloc->bh = NULL;
+			iloc->bh = NULL;
-			}
 		}
 	}
 	ext4_std_error(inode->i_sb, err);
@@ -4791,7 +4927,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 
 	might_sleep();
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
-	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+	if (ext4_handle_valid(handle) &&
+	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
 		/*
 		 * We need extra buffer credits since we may write into EA block
@@ -4843,6 +4980,11 @@ void ext4_dirty_inode(struct inode *inode)
 	handle_t *current_handle = ext4_journal_current_handle();
 	handle_t *handle;
 
+	if (!ext4_handle_valid(current_handle)) {
+		ext4_mark_inode_dirty(current_handle, inode);
+		return;
+	}
+
 	handle = ext4_journal_start(inode, 2);
 	if (IS_ERR(handle))
 		goto out;
@@ -4880,8 +5022,9 @@ static int ext4_pin_inode(handle_t *handle, struct inode *inode)
 			BUFFER_TRACE(iloc.bh, "get_write_access");
 			err = jbd2_journal_get_write_access(handle, iloc.bh);
 			if (!err)
-				err = ext4_journal_dirty_metadata(handle,
+				err = ext4_handle_dirty_metadata(handle,
-								  iloc.bh);
+								 inode,
+								 iloc.bh);
 			brelse(iloc.bh);
 		}
 	}
@@ -4907,6 +5050,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	 */
 
 	journal = EXT4_JOURNAL(inode);
+	if (!journal)
+		return 0;
 	if (is_journal_aborted(journal))
 		return -EROFS;
 
@@ -4936,7 +5081,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		return PTR_ERR(handle);
 
 	err = ext4_mark_inode_dirty(handle, inode);
-	handle->h_sync = 1;
+	ext4_handle_sync(handle);
 	ext4_journal_stop(handle);
 	ext4_std_error(inode->i_sb, err);
 

fs/ext4/ioctl.c

@@ -99,7 +99,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			goto flags_out;
 		}
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err)
 			goto flags_err;

fs/ext4/mballoc.h

@@ -20,6 +20,7 @@
 #include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/marker.h>
+#include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "group.h"
@@ -98,9 +99,6 @@
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
-static struct kmem_cache *ext4_pspace_cachep;
-static struct kmem_cache *ext4_ac_cachep;
-static struct kmem_cache *ext4_free_ext_cachep;
 
 struct ext4_free_data {
 	/* this links the free block information from group_info */
@@ -120,26 +118,6 @@ struct ext4_free_data {
 	tid_t	t_tid;
 };
 
-struct ext4_group_info {
-	unsigned long	bb_state;
-	struct rb_root  bb_free_root;
-	unsigned short	bb_first_free;
-	unsigned short	bb_free;
-	unsigned short	bb_fragments;
-	struct		list_head bb_prealloc_list;
-#ifdef DOUBLE_CHECK
-	void		*bb_bitmap;
-#endif
-	unsigned short	bb_counters[];
-};
-
-#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
-#define EXT4_GROUP_INFO_LOCKED_BIT	1
-
-#define EXT4_MB_GRP_NEED_INIT(grp)	\
-	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
-
-
 struct ext4_prealloc_space {
 	struct list_head	pa_inode_list;
 	struct list_head	pa_group_list;
@@ -217,6 +195,11 @@ struct ext4_allocation_context {
 	__u8 ac_op;		/* operation, for history only */
 	struct page *ac_bitmap_page;
 	struct page *ac_buddy_page;
+	/*
+	 * pointer to the held semaphore upon successful
+	 * block allocation
+	 */
+	struct rw_semaphore *alloc_semp;
 	struct ext4_prealloc_space *ac_pa;
 	struct ext4_locality_group *ac_lg;
 };
@@ -250,6 +233,7 @@ struct ext4_buddy {
 	struct super_block *bd_sb;
 	__u16 bd_blkbits;
 	ext4_group_t bd_group;
+	struct rw_semaphore *alloc_semp;
 };
 #define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
 #define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
@@ -259,51 +243,12 @@ static inline void ext4_mb_store_history(struct ext4_allocation_context *ac)
 {
 	return;
 }
-#else
-static void ext4_mb_store_history(struct ext4_allocation_context *ac);
 #endif
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
 struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
-
+static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
-					ext4_group_t group);
-static void ext4_mb_return_to_preallocation(struct inode *inode,
-					struct ext4_buddy *e4b, sector_t block,
-					int count);
-static void ext4_mb_put_pa(struct ext4_allocation_context *,
-			struct super_block *, struct ext4_prealloc_space *pa);
-static int ext4_mb_init_per_dev_proc(struct super_block *sb);
-static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
-
-
-static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline void ext4_unlock_group(struct super_block *sb,
-					ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline int ext4_is_group_locked(struct super_block *sb,
-					ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
-						&(grinfo->bb_state));
-}
-
-static ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 					struct ext4_free_extent *fex)
 {
 	ext4_fsblk_t block;

fs/ext4/migrate.c

@@ -59,7 +59,8 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	/*
 	 * Make sure the credit we accumalated is not really high
 	 */
-	if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
+	if (needed && ext4_handle_has_enough_credits(handle,
+						EXT4_RESERVE_TRANS_BLOCKS)) {
 		retval = ext4_journal_restart(handle, needed);
 		if (retval)
 			goto err_out;
@@ -229,7 +230,7 @@ static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
 {
 	int retval = 0, needed;
 
-	if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
 		return 0;
 	/*
 	 * We are freeing a blocks. During this we touch
@@ -458,13 +459,13 @@ int ext4_ext_migrate(struct inode *inode)
 	struct list_blocks_struct lb;
 	unsigned long max_entries;
 
-	if (!test_opt(inode->i_sb, EXTENTS))
+	/*
-		/*
+	 * If the filesystem does not support extents, or the inode
-		 * if mounted with noextents we don't allow the migrate
+	 * already is extent-based, error out.
-		 */
+	 */
-		return -EINVAL;
+	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
-
+				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
-	if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	    (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
 		return -EINVAL;
 
 	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)

fs/ext4/namei.c

@@ -368,6 +368,8 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	if (d_name)
 		ext4fs_dirhash(d_name->name, d_name->len, hinfo);
@@ -637,6 +639,9 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
 		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT4_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
@@ -802,7 +807,7 @@ static inline int ext4_match (int len, const char * const name,
 static inline int search_dirblock(struct buffer_head *bh,
 				  struct inode *dir,
 				  const struct qstr *d_name,
-				  unsigned long offset,
+				  unsigned int offset,
 				  struct ext4_dir_entry_2 ** res_dir)
 {
 	struct ext4_dir_entry_2 * de;
@@ -1039,11 +1044,11 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
 	bh = ext4_find_entry(dir, &dentry->d_name, &de);
 	inode = NULL;
 	if (bh) {
-		unsigned long ino = le32_to_cpu(de->inode);
+		__u32 ino = le32_to_cpu(de->inode);
 		brelse(bh);
 		if (!ext4_valid_inum(dir->i_sb, ino)) {
 			ext4_error(dir->i_sb, "ext4_lookup",
-				   "bad inode number: %lu", ino);
+				   "bad inode number: %u", ino);
 			return ERR_PTR(-EIO);
 		}
 		inode = ext4_iget(dir->i_sb, ino);
@@ -1056,7 +1061,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
 
 struct dentry *ext4_get_parent(struct dentry *child)
 {
-	unsigned long ino;
+	__u32 ino;
 	struct inode *inode;
 	static const struct qstr dotdot = {
 		.name = "..",
@@ -1074,7 +1079,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
 
 	if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
 		ext4_error(child->d_inode->i_sb, "ext4_get_parent",
-			   "bad inode number: %lu", ino);
+			   "bad inode number: %u", ino);
 		return ERR_PTR(-EIO);
 	}
 
@@ -1162,9 +1167,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	u32 hash2;
 	struct dx_map_entry *map;
 	char *data1 = (*bh)->b_data, *data2;
-	unsigned split, move, size, i;
+	unsigned split, move, size;
 	struct ext4_dir_entry_2 *de = NULL, *de2;
-	int	err = 0;
+	int	err = 0, i;
 
 	bh2 = ext4_append (handle, dir, &newblock, &err);
 	if (!(bh2)) {
@@ -1224,10 +1229,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		de = de2;
 	}
 	dx_insert_block(frame, hash2 + continued, newblock);
-	err = ext4_journal_dirty_metadata(handle, bh2);
+	err = ext4_handle_dirty_metadata(handle, dir, bh2);
 	if (err)
 		goto journal_error;
-	err = ext4_journal_dirty_metadata(handle, frame->bh);
+	err = ext4_handle_dirty_metadata(handle, dir, frame->bh);
 	if (err)
 		goto journal_error;
 	brelse(bh2);
@@ -1262,7 +1267,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	struct inode	*dir = dentry->d_parent->d_inode;
 	const char	*name = dentry->d_name.name;
 	int		namelen = dentry->d_name.len;
-	unsigned long	offset = 0;
+	unsigned int	offset = 0;
 	unsigned short	reclen;
 	int		nlen, rlen, err;
 	char		*top;
@@ -1331,8 +1336,8 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	ext4_update_dx_flag(dir);
 	dir->i_version++;
 	ext4_mark_inode_dirty(handle, dir);
-	BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	err = ext4_journal_dirty_metadata(handle, bh);
+	err = ext4_handle_dirty_metadata(handle, dir, bh);
 	if (err)
 		ext4_std_error(dir->i_sb, err);
 	brelse(bh);
@@ -1404,6 +1409,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	ext4fs_dirhash(name, namelen, &hinfo);
 	frame = frames;
@@ -1433,7 +1440,6 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 			  struct inode *inode)
 {
 	struct inode *dir = dentry->d_parent->d_inode;
-	unsigned long offset;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
@@ -1455,7 +1461,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		ext4_mark_inode_dirty(handle, dir);
 	}
 	blocks = dir->i_size >> sb->s_blocksize_bits;
-	for (block = 0, offset = 0; block < blocks; block++) {
+	for (block = 0; block < blocks; block++) {
 		bh = ext4_bread(handle, dir, block, 0, &retval);
 		if(!bh)
 			return retval;
@@ -1570,7 +1576,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			dxtrace(dx_show_index("node", frames[1].entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
-			err = ext4_journal_dirty_metadata(handle, bh2);
+			err = ext4_handle_dirty_metadata(handle, inode, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1596,7 +1602,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		ext4_journal_dirty_metadata(handle, frames[0].bh);
+		ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
 	}
 	de = do_split(handle, dir, &bh, frame, &hinfo, &err);
 	if (!de)
@@ -1642,8 +1648,8 @@ static int ext4_delete_entry(handle_t *handle,
 			else
 				de->inode = 0;
 			dir->i_version++;
-			BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-			ext4_journal_dirty_metadata(handle, bh);
+			ext4_handle_dirty_metadata(handle, dir, bh);
 			return 0;
 		}
 		i += ext4_rec_len_from_disk(de->rec_len);
@@ -1721,7 +1727,7 @@ retry:
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode (handle, dir, mode);
 	err = PTR_ERR(inode);
@@ -1755,7 +1761,7 @@ retry:
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode(handle, dir, mode);
 	err = PTR_ERR(inode);
@@ -1791,7 +1797,7 @@ retry:
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
 	err = PTR_ERR(inode);
@@ -1820,8 +1826,8 @@ retry:
 	strcpy(de->name, "..");
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
-	BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
+	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	ext4_journal_dirty_metadata(handle, dir_block);
+	ext4_handle_dirty_metadata(handle, dir, dir_block);
 	brelse(dir_block);
 	ext4_mark_inode_dirty(handle, inode);
 	err = ext4_add_entry(handle, dentry, inode);
@@ -1850,7 +1856,7 @@ out_stop:
  */
 static int empty_dir(struct inode *inode)
 {
-	unsigned long offset;
+	unsigned int offset;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de, *de1;
 	struct super_block *sb;
@@ -1895,7 +1901,7 @@ static int empty_dir(struct inode *inode)
 				if (err)
 					ext4_error(sb, __func__,
 						   "error %d reading directory"
-						   " #%lu offset %lu",
+						   " #%lu offset %u",
 						   err, inode->i_ino, offset);
 				offset += sb->s_blocksize;
 				continue;
@@ -1933,6 +1939,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	struct ext4_iloc iloc;
 	int err = 0, rc;
 
+	if (!ext4_handle_valid(handle))
+		return 0;
+
 	lock_super(sb);
 	if (!list_empty(&EXT4_I(inode)->i_orphan))
 		goto out_unlock;
@@ -1961,7 +1970,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	/* Insert this inode at the head of the on-disk orphan list... */
 	NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
 	EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
-	err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+	err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
 	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	if (!err)
 		err = rc;
@@ -1995,10 +2004,13 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	struct list_head *prev;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi;
-	unsigned long ino_next;
+	__u32 ino_next;
 	struct ext4_iloc iloc;
 	int err = 0;
 
+	if (!ext4_handle_valid(handle))
+		return 0;
+
 	lock_super(inode->i_sb);
 	if (list_empty(&ei->i_orphan)) {
 		unlock_super(inode->i_sb);
@@ -2017,7 +2029,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	 * transaction handle with which to update the orphan list on
 	 * disk, but we still need to remove the inode from the linked
 	 * list in memory. */
-	if (!handle)
+	if (sbi->s_journal && !handle)
 		goto out;
 
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
@@ -2025,19 +2037,19 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 		goto out_err;
 
 	if (prev == &sbi->s_orphan) {
-		jbd_debug(4, "superblock will point to %lu\n", ino_next);
+		jbd_debug(4, "superblock will point to %u\n", ino_next);
 		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 		if (err)
 			goto out_brelse;
 		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
-		err = ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+		err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
 	} else {
 		struct ext4_iloc iloc2;
 		struct inode *i_prev =
 			&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
 
-		jbd_debug(4, "orphan inode %lu will point to %lu\n",
+		jbd_debug(4, "orphan inode %lu will point to %u\n",
 			  i_prev->i_ino, ino_next);
 		err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
 		if (err)
@@ -2082,7 +2094,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 		goto end_rmdir;
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode = dentry->d_inode;
 
@@ -2136,7 +2148,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de);
@@ -2193,7 +2205,7 @@ retry:
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
 	err = PTR_ERR(inode);
@@ -2256,7 +2268,7 @@ retry:
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	inode->i_ctime = ext4_current_time(inode);
 	ext4_inc_count(handle, inode);
@@ -2305,7 +2317,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return PTR_ERR(handle);
 
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 	old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
 	/*
@@ -2359,8 +2371,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_dir->i_ctime = new_dir->i_mtime =
 					ext4_current_time(new_dir);
 		ext4_mark_inode_dirty(handle, new_dir);
-		BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
-		ext4_journal_dirty_metadata(handle, new_bh);
+		ext4_handle_dirty_metadata(handle, new_dir, new_bh);
 		brelse(new_bh);
 		new_bh = NULL;
 	}
@@ -2410,8 +2422,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		BUFFER_TRACE(dir_bh, "get_write_access");
 		ext4_journal_get_write_access(handle, dir_bh);
 		PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
-		BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata");
+		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		ext4_journal_dirty_metadata(handle, dir_bh);
+		ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
 		ext4_dec_count(handle, old_dir);
 		if (new_inode) {
 			/* checked empty_dir above, can't have another parent,

fs/ext4/resize.c

@@ -50,7 +50,7 @@ static int verify_group_input(struct super_block *sb,
 	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
 	if (group != sbi->s_groups_count)
 		ext4_warning(sb, __func__,
-			     "Cannot add at group %u (only %lu groups)",
+			     "Cannot add at group %u (only %u groups)",
 			     input->group, sbi->s_groups_count);
 	else if (offset != 0)
 			ext4_warning(sb, __func__, "Last group not full");
@@ -149,7 +149,7 @@ static int extend_or_restart_transaction(handle_t *handle, int thresh,
 {
 	int err;
 
-	if (handle->h_buffer_credits >= thresh)
+	if (ext4_handle_has_enough_credits(handle, thresh))
 		return 0;
 
 	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
@@ -232,7 +232,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
 		set_buffer_uptodate(gdb);
 		unlock_buffer(gdb);
-		ext4_journal_dirty_metadata(handle, gdb);
+		ext4_handle_dirty_metadata(handle, NULL, gdb);
 		ext4_set_bit(bit, bh->b_data);
 		brelse(gdb);
 	}
@@ -251,7 +251,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 			err = PTR_ERR(bh);
 			goto exit_bh;
 		}
-		ext4_journal_dirty_metadata(handle, gdb);
+		ext4_handle_dirty_metadata(handle, NULL, gdb);
 		ext4_set_bit(bit, bh->b_data);
 		brelse(gdb);
 	}
@@ -276,7 +276,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 			err = PTR_ERR(it);
 			goto exit_bh;
 		}
-		ext4_journal_dirty_metadata(handle, it);
+		ext4_handle_dirty_metadata(handle, NULL, it);
 		brelse(it);
 		ext4_set_bit(bit, bh->b_data);
 	}
@@ -284,11 +284,9 @@ static int setup_new_group_blocks(struct super_block *sb,
 	if ((err = extend_or_restart_transaction(handle, 2, bh)))
 		goto exit_bh;
 
-	mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
+	mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data);
-			bh->b_data);
+	ext4_handle_dirty_metadata(handle, NULL, bh);
-	ext4_journal_dirty_metadata(handle, bh);
 	brelse(bh);
-
 	/* Mark unused entries in inode bitmap used */
 	ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
 		   input->inode_bitmap, input->inode_bitmap - start);
@@ -297,9 +295,9 @@ static int setup_new_group_blocks(struct super_block *sb,
 		goto exit_journal;
 	}
 
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
+	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
 			bh->b_data);
-	ext4_journal_dirty_metadata(handle, bh);
+	ext4_handle_dirty_metadata(handle, NULL, bh);
 exit_bh:
 	brelse(bh);
 
@@ -486,12 +484,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	 * reserved inode, and will become GDT blocks (primary and backup).
 	 */
 	data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
-	ext4_journal_dirty_metadata(handle, dind);
+	ext4_handle_dirty_metadata(handle, NULL, dind);
 	brelse(dind);
 	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
 	ext4_mark_iloc_dirty(handle, inode, &iloc);
 	memset((*primary)->b_data, 0, sb->s_blocksize);
-	ext4_journal_dirty_metadata(handle, *primary);
+	ext4_handle_dirty_metadata(handle, NULL, *primary);
 
 	o_group_desc = EXT4_SB(sb)->s_group_desc;
 	memcpy(n_group_desc, o_group_desc,
@@ -502,7 +500,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	kfree(o_group_desc);
 
 	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
-	ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+	ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 
 	return 0;
 
@@ -618,7 +616,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 		       primary[i]->b_blocknr, gdbackups,
 		       blk + primary[i]->b_blocknr); */
 		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
-		err2 = ext4_journal_dirty_metadata(handle, primary[i]);
+		err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
 		if (!err)
 			err = err2;
 	}
@@ -676,7 +674,8 @@ static void update_backups(struct super_block *sb,
 		struct buffer_head *bh;
 
 		/* Out of journal space, and can't get more - abort - so sad */
-		if (handle->h_buffer_credits == 0 &&
+		if (ext4_handle_valid(handle) &&
+		    handle->h_buffer_credits == 0 &&
 		    ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
 		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
 			break;
@@ -696,7 +695,7 @@ static void update_backups(struct super_block *sb,
 			memset(bh->b_data + size, 0, rest);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
-		ext4_journal_dirty_metadata(handle, bh);
+		ext4_handle_dirty_metadata(handle, NULL, bh);
 		brelse(bh);
 	}
 	if ((err2 = ext4_journal_stop(handle)) && !err)
@@ -715,7 +714,7 @@ static void update_backups(struct super_block *sb,
 exit_err:
 	if (err) {
 		ext4_warning(sb, __func__,
-			     "can't update backup for group %lu (err %d), "
+			     "can't update backup for group %u (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);
@@ -747,6 +746,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	struct inode *inode = NULL;
 	handle_t *handle;
 	int gdb_off, gdb_num;
+	int num_grp_locked = 0;
 	int err, err2;
 
 	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
@@ -761,13 +761,13 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 
 	if (ext4_blocks_count(es) + input->blocks_count <
 	    ext4_blocks_count(es)) {
-		ext4_warning(sb, __func__, "blocks_count overflow\n");
+		ext4_warning(sb, __func__, "blocks_count overflow");
 		return -EINVAL;
 	}
 
 	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
 	    le32_to_cpu(es->s_inodes_count)) {
-		ext4_warning(sb, __func__, "inodes_count overflow\n");
+		ext4_warning(sb, __func__, "inodes_count overflow");
 		return -EINVAL;
 	}
 
@@ -787,6 +787,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 		}
 	}
 
+
 	if ((err = verify_group_input(sb, input)))
 		goto exit_put;
 
@@ -855,6 +856,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
          * using the new disk blocks.
          */
 
+	num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, input->group);
 	/* Update group descriptor block for new group */
 	gdp = (struct ext4_group_desc *)((char *)primary->b_data +
 					 gdb_off * EXT4_DESC_SIZE(sb));
@@ -862,17 +864,20 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
 	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
 	ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
-	gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
+	ext4_free_blks_set(sb, gdp, input->free_blocks_count);
-	gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
+	ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
+	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
 
 	/*
 	 * We can allocate memory for mb_alloc based on the new group
 	 * descriptor
 	 */
-	err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
+	err = ext4_mb_add_groupinfo(sb, input->group, gdp);
-	if (err)
+	if (err) {
+		ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
 		goto exit_journal;
+	}
 
 	/*
 	 * Make the new blocks and inodes valid next.  We do this before
@@ -914,8 +919,9 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 
 	/* Update the global fs size fields */
 	sbi->s_groups_count++;
+	ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
 
-	ext4_journal_dirty_metadata(handle, primary);
+	ext4_handle_dirty_metadata(handle, NULL, primary);
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
@@ -937,7 +943,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 			EXT4_INODES_PER_GROUP(sb);
 	}
 
-	ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+	ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 	sb->s_dirt = 1;
 
 exit_journal:
@@ -975,9 +981,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	struct buffer_head *bh;
 	handle_t *handle;
 	int err;
-	unsigned long freed_blocks;
 	ext4_group_t group;
-	struct ext4_group_info *grp;
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after
@@ -997,8 +1001,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 			" too large to resize to %llu blocks safely\n",
 			sb->s_id, n_blocks_count);
 		if (sizeof(sector_t) < 8)
-			ext4_warning(sb, __func__,
+			ext4_warning(sb, __func__, "CONFIG_LBD not enabled");
-			"CONFIG_LBD not enabled\n");
 		return -EINVAL;
 	}
 
@@ -1071,62 +1074,18 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 		goto exit_put;
 	}
 	ext4_blocks_count_set(es, o_blocks_count + add);
-	ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+	ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	sb->s_dirt = 1;
 	unlock_super(sb);
 	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);
+	/* We add the blocks to the bitmap and set the group need init bit */
+	ext4_add_groupblocks(handle, sb, o_blocks_count, add);
 	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	if ((err = ext4_journal_stop(handle)))
 		goto exit_put;
 
-	/*
-	 * Mark mballoc pages as not up to date so that they will be updated
-	 * next time they are loaded by ext4_mb_load_buddy.
-	 *
-	 * XXX Bad, Bad, BAD!!!  We should not be overloading the
-	 * Uptodate flag, particularly on thte bitmap bh, as way of
-	 * hinting to ext4_mb_load_buddy() that it needs to be
-	 * overloaded.  A user could take a LVM snapshot, then do an
-	 * on-line fsck, and clear the uptodate flag, and this would
-	 * not be a bug in userspace, but a bug in the kernel.  FIXME!!!
-	 */
-	{
-		struct ext4_sb_info *sbi = EXT4_SB(sb);
-		struct inode *inode = sbi->s_buddy_cache;
-		int blocks_per_page;
-		int block;
-		int pnum;
-		struct page *page;
-
-		/* Set buddy page as not up to date */
-		blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
-		block = group * 2;
-		pnum = block / blocks_per_page;
-		page = find_get_page(inode->i_mapping, pnum);
-		if (page != NULL) {
-			ClearPageUptodate(page);
-			page_cache_release(page);
-		}
-
-		/* Set bitmap page as not up to date */
-		block++;
-		pnum = block / blocks_per_page;
-		page = find_get_page(inode->i_mapping, pnum);
-		if (page != NULL) {
-			ClearPageUptodate(page);
-			page_cache_release(page);
-		}
-
-		/* Get the info on the last group */
-		grp = ext4_get_group_info(sb, group);
-
-		/* Update free blocks in group info */
-		ext4_mb_update_group_info(grp, add);
-	}
-
 	if (test_opt(sb, DEBUG))
 		printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
 		       ext4_blocks_count(es));

fs/ext4/xattr.c

@@ -457,7 +457,7 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
 		EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
 		sb->s_dirt = 1;
-		ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+		ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	}
 }
 
@@ -487,9 +487,9 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
-		error = ext4_journal_dirty_metadata(handle, bh);
+		error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 		DQUOT_FREE_BLOCK(inode, 1);
 		ea_bdebug(bh, "refcount now=%d; releasing",
 			  le32_to_cpu(BHDR(bh)->h_refcount));
@@ -724,8 +724,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			if (error == -EIO)
 				goto bad_block;
 			if (!error)
-				error = ext4_journal_dirty_metadata(handle,
+				error = ext4_handle_dirty_metadata(handle,
-								    bs->bh);
+								   inode,
+								   bs->bh);
 			if (error)
 				goto cleanup;
 			goto inserted;
@@ -794,8 +795,9 @@ inserted:
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					le32_to_cpu(BHDR(new_bh)->h_refcount));
 				unlock_buffer(new_bh);
-				error = ext4_journal_dirty_metadata(handle,
+				error = ext4_handle_dirty_metadata(handle,
-								    new_bh);
+								   inode,
+								   new_bh);
 				if (error)
 					goto cleanup_dquot;
 			}
@@ -810,8 +812,8 @@ inserted:
 			/* We need to allocate a new block */
 			ext4_fsblk_t goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
-			ext4_fsblk_t block = ext4_new_meta_block(handle, inode,
+			ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode,
-							goal, &error);
+						  goal, NULL, &error);
 			if (error)
 				goto cleanup;
 			ea_idebug(inode, "creating block %d", block);
@@ -833,7 +835,8 @@ getblk_failed:
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
 			ext4_xattr_cache_insert(new_bh);
-			error = ext4_journal_dirty_metadata(handle, new_bh);
+			error = ext4_handle_dirty_metadata(handle,
+							   inode, new_bh);
 			if (error)
 				goto cleanup;
 		}
@@ -1040,7 +1043,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		 */
 		is.iloc.bh = NULL;
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 	}
 
 cleanup:

fs/ioprio.c

@@ -27,7 +27,7 @@
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
 
-static int set_task_ioprio(struct task_struct *task, int ioprio)
+int set_task_ioprio(struct task_struct *task, int ioprio)
 {
 	int err;
 	struct io_context *ioc;
@@ -70,6 +70,7 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
 	task_unlock(task);
 	return err;
 }
+EXPORT_SYMBOL_GPL(set_task_ioprio);
 
 asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 {

fs/jbd2/checkpoint.c

@@ -249,16 +249,14 @@ restart:
 	return ret;
 }
 
-#define NR_BATCH	64
-
 static void
-__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
+__flush_batch(journal_t *journal, int *batch_count)
 {
 	int i;
 
-	ll_rw_block(SWRITE, *batch_count, bhs);
+	ll_rw_block(SWRITE, *batch_count, journal->j_chkpt_bhs);
 	for (i = 0; i < *batch_count; i++) {
-		struct buffer_head *bh = bhs[i];
+		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		clear_buffer_jwrite(bh);
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
@@ -277,8 +275,7 @@ __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,
+			    int *batch_count, transaction_t *transaction)
-			transaction_t *transaction)
 {
 	struct buffer_head *bh = jh2bh(jh);
 	int ret = 0;
@@ -325,14 +322,14 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		get_bh(bh);
 		J_ASSERT_BH(bh, !buffer_jwrite(bh));
 		set_buffer_jwrite(bh);
-		bhs[*batch_count] = bh;
+		journal->j_chkpt_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) {
+		if (*batch_count == JBD2_NR_BATCH) {
 			spin_unlock(&journal->j_list_lock);
-			__flush_batch(journal, bhs, batch_count);
+			__flush_batch(journal, batch_count);
 			ret = 1;
 		}
 	}
@@ -388,7 +385,6 @@ restart:
 	if (journal->j_checkpoint_transactions == transaction &&
 			transaction->t_tid == this_tid) {
 		int batch_count = 0;
-		struct buffer_head *bhs[NR_BATCH];
 		struct journal_head *jh;
 		int retry = 0, err;
 
@@ -402,7 +398,7 @@ restart:
 				retry = 1;
 				break;
 			}
-			retry = __process_buffer(journal, jh, bhs, &batch_count,
+			retry = __process_buffer(journal, jh, &batch_count,
 						 transaction);
 			if (retry < 0 && !result)
 				result = retry;
@@ -419,7 +415,7 @@ restart:
 				spin_unlock(&journal->j_list_lock);
 				retry = 1;
 			}
-			__flush_batch(journal, bhs, &batch_count);
+			__flush_batch(journal, &batch_count);
 		}
 
 		if (retry) {
@@ -686,6 +682,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	   safely remove this transaction from the log */
 
 	__jbd2_journal_drop_transaction(journal, transaction);
+	kfree(transaction);
 
 	/* Just in case anybody was waiting for more transactions to be
            checkpointed... */
@@ -760,5 +757,4 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 	J_ASSERT(journal->j_running_transaction != transaction);
 
 	jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
-	kfree(transaction);
 }

fs/jbd2/commit.c

@@ -25,6 +25,7 @@
 #include <linux/crc32.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
+#include <linux/bio.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -137,7 +138,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		set_buffer_ordered(bh);
 		barrier_done = 1;
 	}
-	ret = submit_bh(WRITE, bh);
+	ret = submit_bh(WRITE_SYNC, bh);
 	if (barrier_done)
 		clear_buffer_ordered(bh);
 
@@ -158,7 +159,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		lock_buffer(bh);
 		set_buffer_uptodate(bh);
 		clear_buffer_dirty(bh);
-		ret = submit_bh(WRITE, bh);
+		ret = submit_bh(WRITE_SYNC, bh);
 	}
 	*cbh = bh;
 	return ret;
@@ -168,12 +169,34 @@ static int journal_submit_commit_record(journal_t *journal,
  * 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)
+static int journal_wait_on_commit_record(journal_t *journal,
+					 struct buffer_head *bh)
 {
 	int ret = 0;
 
+retry:
 	clear_buffer_dirty(bh);
 	wait_on_buffer(bh);
+	if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
+		printk(KERN_WARNING
+		       "JBD2: wait_on_commit_record: sync failed on %s - "
+		       "disabling barriers\n", journal->j_devname);
+		spin_lock(&journal->j_state_lock);
+		journal->j_flags &= ~JBD2_BARRIER;
+		spin_unlock(&journal->j_state_lock);
+
+		lock_buffer(bh);
+		clear_buffer_dirty(bh);
+		set_buffer_uptodate(bh);
+		bh->b_end_io = journal_end_buffer_io_sync;
+
+		ret = submit_bh(WRITE_SYNC, bh);
+		if (ret) {
+			unlock_buffer(bh);
+			return ret;
+		}
+		goto retry;
+	}
 
 	if (unlikely(!buffer_uptodate(bh)))
 		ret = -EIO;
@@ -332,13 +355,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int flags;
 	int err;
 	unsigned long long blocknr;
+	ktime_t start_time;
+	u64 commit_time;
 	char *tagp = NULL;
 	journal_header_t *header;
 	journal_block_tag_t *tag = NULL;
 	int space_left = 0;
 	int first_tag = 0;
 	int tag_flag;
-	int i;
+	int i, to_free = 0;
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
@@ -458,6 +483,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	commit_transaction->t_state = T_FLUSH;
 	journal->j_committing_transaction = commit_transaction;
 	journal->j_running_transaction = NULL;
+	start_time = ktime_get();
 	commit_transaction->t_log_start = journal->j_head;
 	wake_up(&journal->j_wait_transaction_locked);
 	spin_unlock(&journal->j_state_lock);
@@ -803,7 +829,7 @@ wait_for_iobuf:
 			__jbd2_journal_abort_hard(journal);
 	}
 	if (!err && !is_journal_aborted(journal))
-		err = journal_wait_on_commit_record(cbh);
+		err = journal_wait_on_commit_record(journal, cbh);
 
 	if (err)
 		jbd2_journal_abort(journal, err);
@@ -981,14 +1007,23 @@ restart_loop:
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;
 	journal->j_committing_transaction = NULL;
-	spin_unlock(&journal->j_state_lock);
+	commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
 
-	if (journal->j_commit_callback)
+	/*
-		journal->j_commit_callback(journal, commit_transaction);
+	 * weight the commit time higher than the average time so we don't
+	 * react too strongly to vast changes in the commit time
+	 */
+	if (likely(journal->j_average_commit_time))
+		journal->j_average_commit_time = (commit_time +
+				journal->j_average_commit_time*3) / 4;
+	else
+		journal->j_average_commit_time = commit_time;
+	spin_unlock(&journal->j_state_lock);
 
 	if (commit_transaction->t_checkpoint_list == NULL &&
 	    commit_transaction->t_checkpoint_io_list == NULL) {
 		__jbd2_journal_drop_transaction(journal, commit_transaction);
+		to_free = 1;
 	} else {
 		if (journal->j_checkpoint_transactions == NULL) {
 			journal->j_checkpoint_transactions = commit_transaction;
@@ -1007,11 +1042,16 @@ restart_loop:
 	}
 	spin_unlock(&journal->j_list_lock);
 
+	if (journal->j_commit_callback)
+		journal->j_commit_callback(journal, commit_transaction);
+
 	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
-		   journal->j_devname, journal->j_commit_sequence,
+		   journal->j_devname, commit_transaction->t_tid,
 		   journal->j_tail_sequence);
 	jbd_debug(1, "JBD: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
+	if (to_free)
+		kfree(commit_transaction);
 
 	wake_up(&journal->j_wait_done_commit);
 }

fs/jbd2/journal.c

@@ -40,6 +40,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
+#include <asm/div64.h>
 
 EXPORT_SYMBOL(jbd2_journal_start);
 EXPORT_SYMBOL(jbd2_journal_restart);
@@ -66,7 +67,6 @@ EXPORT_SYMBOL(jbd2_journal_update_format);
 EXPORT_SYMBOL(jbd2_journal_check_used_features);
 EXPORT_SYMBOL(jbd2_journal_check_available_features);
 EXPORT_SYMBOL(jbd2_journal_set_features);
-EXPORT_SYMBOL(jbd2_journal_create);
 EXPORT_SYMBOL(jbd2_journal_load);
 EXPORT_SYMBOL(jbd2_journal_destroy);
 EXPORT_SYMBOL(jbd2_journal_abort);
@@ -132,8 +132,9 @@ static int kjournald2(void *arg)
 	journal->j_task = current;
 	wake_up(&journal->j_wait_done_commit);
 
-	printk(KERN_INFO "kjournald2 starting.  Commit interval %ld seconds\n",
+	printk(KERN_INFO "kjournald2 starting: pid %d, dev %s, "
-			journal->j_commit_interval / HZ);
+	       "commit interval %ld seconds\n", current->pid,
+	       journal->j_devname, journal->j_commit_interval / HZ);
 
 	/*
 	 * And now, wait forever for commit wakeup events.
@@ -650,6 +651,8 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
 		return NULL;
 
 	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+	if (!bh)
+		return NULL;
 	lock_buffer(bh);
 	memset(bh->b_data, 0, journal->j_blocksize);
 	set_buffer_uptodate(bh);
@@ -843,6 +846,8 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v)
 	    jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
 	seq_printf(seq, "  %ums logging transaction\n",
 	    jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
+	seq_printf(seq, "  %luus average transaction commit time\n",
+		   do_div(s->journal->j_average_commit_time, 1000));
 	seq_printf(seq, "  %lu handles per transaction\n",
 	    s->stats->u.run.rs_handle_count / s->stats->ts_tid);
 	seq_printf(seq, "  %lu blocks per transaction\n",
@@ -980,6 +985,8 @@ static journal_t * journal_init_common (void)
 	spin_lock_init(&journal->j_state_lock);
 
 	journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
+	journal->j_min_batch_time = 0;
+	journal->j_max_batch_time = 15000; /* 15ms */
 
 	/* The journal is marked for error until we succeed with recovery! */
 	journal->j_flags = JBD2_ABORT;
@@ -1035,15 +1042,14 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 
 	/* journal descriptor can store up to n blocks -bzzz */
 	journal->j_blocksize = blocksize;
+	jbd2_stats_proc_init(journal);
 	n = journal->j_blocksize / sizeof(journal_block_tag_t);
 	journal->j_wbufsize = n;
 	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
 			__func__);
-		kfree(journal);
+		goto out_err;
-		journal = NULL;
-		goto out;
 	}
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
@@ -1053,14 +1059,22 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 	p = journal->j_devname;
 	while ((p = strchr(p, '/')))
 		*p = '!';
-	jbd2_stats_proc_init(journal);
 
 	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
-	J_ASSERT(bh != NULL);
+	if (!bh) {
+		printk(KERN_ERR
+		       "%s: Cannot get buffer for journal superblock\n",
+		       __func__);
+		goto out_err;
+	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
-out:
+
 	return journal;
+out_err:
+	jbd2_stats_proc_exit(journal);
+	kfree(journal);
+	return NULL;
 }
 
 /**
@@ -1108,9 +1122,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
 			__func__);
-		jbd2_stats_proc_exit(journal);
+		goto out_err;
-		kfree(journal);
-		return NULL;
 	}
 
 	err = jbd2_journal_bmap(journal, 0, &blocknr);
@@ -1118,17 +1130,24 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	if (err) {
 		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
 		       __func__);
-		jbd2_stats_proc_exit(journal);
+		goto out_err;
-		kfree(journal);
-		return NULL;
 	}
 
 	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
-	J_ASSERT(bh != NULL);
+	if (!bh) {
+		printk(KERN_ERR
+		       "%s: Cannot get buffer for journal superblock\n",
+		       __func__);
+		goto out_err;
+	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
 
 	return journal;
+out_err:
+	jbd2_stats_proc_exit(journal);
+	kfree(journal);
+	return NULL;
 }
 
 /*
@@ -1176,77 +1195,6 @@ static int journal_reset(journal_t *journal)
 	return jbd2_journal_start_thread(journal);
 }
 
-/**
- * int jbd2_journal_create() - Initialise the new journal file
- * @journal: Journal to create. This structure must have been initialised
- *
- * Given a journal_t structure which tells us which disk blocks we can
- * use, create a new journal superblock and initialise all of the
- * journal fields from scratch.
- **/
-int jbd2_journal_create(journal_t *journal)
-{
-	unsigned long long blocknr;
-	struct buffer_head *bh;
-	journal_superblock_t *sb;
-	int i, err;
-
-	if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
-		printk (KERN_ERR "Journal length (%d blocks) too short.\n",
-			journal->j_maxlen);
-		journal_fail_superblock(journal);
-		return -EINVAL;
-	}
-
-	if (journal->j_inode == NULL) {
-		/*
-		 * We don't know what block to start at!
-		 */
-		printk(KERN_EMERG
-		       "%s: creation of journal on external device!\n",
-		       __func__);
-		BUG();
-	}
-
-	/* Zero out the entire journal on disk.  We cannot afford to
-	   have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
-	jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
-	for (i = 0; i < journal->j_maxlen; i++) {
-		err = jbd2_journal_bmap(journal, i, &blocknr);
-		if (err)
-			return err;
-		bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
-		lock_buffer(bh);
-		memset (bh->b_data, 0, journal->j_blocksize);
-		BUFFER_TRACE(bh, "marking dirty");
-		mark_buffer_dirty(bh);
-		BUFFER_TRACE(bh, "marking uptodate");
-		set_buffer_uptodate(bh);
-		unlock_buffer(bh);
-		__brelse(bh);
-	}
-
-	sync_blockdev(journal->j_dev);
-	jbd_debug(1, "JBD: journal cleared.\n");
-
-	/* OK, fill in the initial static fields in the new superblock */
-	sb = journal->j_superblock;
-
-	sb->s_header.h_magic	 = cpu_to_be32(JBD2_MAGIC_NUMBER);
-	sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
-
-	sb->s_blocksize	= cpu_to_be32(journal->j_blocksize);
-	sb->s_maxlen	= cpu_to_be32(journal->j_maxlen);
-	sb->s_first	= cpu_to_be32(1);
-
-	journal->j_transaction_sequence = 1;
-
-	journal->j_flags &= ~JBD2_ABORT;
-	journal->j_format_version = 2;
-
-	return journal_reset(journal);
-}
-
 /**
  * void jbd2_journal_update_superblock() - Update journal sb on disk.
  * @journal: The journal to update.
@@ -1491,7 +1439,9 @@ int jbd2_journal_destroy(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
+		mutex_lock(&journal->j_checkpoint_mutex);
 		jbd2_log_do_checkpoint(journal);
+		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
 	}
 

fs/jbd2/transaction.c

@@ -25,6 +25,7 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/hrtimer.h>
 
 static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
 
@@ -48,6 +49,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
 {
 	transaction->t_journal = journal;
 	transaction->t_state = T_RUNNING;
+	transaction->t_start_time = ktime_get();
 	transaction->t_tid = journal->j_transaction_sequence++;
 	transaction->t_expires = jiffies + journal->j_commit_interval;
 	spin_lock_init(&transaction->t_handle_lock);
@@ -1240,7 +1242,7 @@ int jbd2_journal_stop(handle_t *handle)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
-	int old_handle_count, err;
+	int err;
 	pid_t pid;
 
 	J_ASSERT(journal_current_handle() == handle);
@@ -1263,24 +1265,54 @@ int jbd2_journal_stop(handle_t *handle)
 	/*
 	 * Implement synchronous transaction batching.  If the handle
 	 * was synchronous, don't force a commit immediately.  Let's
-	 * yield and let another thread piggyback onto this transaction.
+	 * yield and let another thread piggyback onto this
-	 * Keep doing that while new threads continue to arrive.
+	 * transaction.  Keep doing that while new threads continue to
-	 * It doesn't cost much - we're about to run a commit and sleep
+	 * arrive.  It doesn't cost much - we're about to run a commit
-	 * on IO anyway.  Speeds up many-threaded, many-dir operations
+	 * and sleep on IO anyway.  Speeds up many-threaded, many-dir
-	 * by 30x or more...
+	 * operations by 30x or more...
 	 *
-	 * But don't do this if this process was the most recent one to
+	 * We try and optimize the sleep time against what the
-	 * perform a synchronous write.  We do this to detect the case where a
+	 * underlying disk can do, instead of having a static sleep
-	 * single process is doing a stream of sync writes.  No point in waiting
+	 * time.  This is useful for the case where our storage is so
-	 * for joiners in that case.
+	 * fast that it is more optimal to go ahead and force a flush
+	 * and wait for the transaction to be committed than it is to
+	 * wait for an arbitrary amount of time for new writers to
+	 * join the transaction.  We achieve this by measuring how
+	 * long it takes to commit a transaction, and compare it with
+	 * how long this transaction has been running, and if run time
+	 * < commit time then we sleep for the delta and commit.  This
+	 * greatly helps super fast disks that would see slowdowns as
+	 * more threads started doing fsyncs.
+	 *
+	 * But don't do this if this process was the most recent one
+	 * to perform a synchronous write.  We do this to detect the
+	 * case where a single process is doing a stream of sync
+	 * writes.  No point in waiting for joiners in that case.
 	 */
 	pid = current->pid;
 	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+		u64 commit_time, trans_time;
+
 		journal->j_last_sync_writer = pid;
-		do {
+
-			old_handle_count = transaction->t_handle_count;
+		spin_lock(&journal->j_state_lock);
-			schedule_timeout_uninterruptible(1);
+		commit_time = journal->j_average_commit_time;
-		} while (old_handle_count != transaction->t_handle_count);
+		spin_unlock(&journal->j_state_lock);
+
+		trans_time = ktime_to_ns(ktime_sub(ktime_get(),
+						   transaction->t_start_time));
+
+		commit_time = max_t(u64, commit_time,
+				    1000*journal->j_min_batch_time);
+		commit_time = min_t(u64, commit_time,
+				    1000*journal->j_max_batch_time);
+
+		if (trans_time < commit_time) {
+			ktime_t expires = ktime_add_ns(ktime_get(),
+						       commit_time);
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+		}
 	}
 
 	current->journal_info = NULL;

fs/super.c

@@ -810,6 +810,7 @@ int get_sb_bdev(struct file_system_type *fs_type,
 		}
 
 		s->s_flags |= MS_ACTIVE;
+		bdev->bd_super = s;
 	}
 
 	return simple_set_mnt(mnt, s);
@@ -829,6 +830,7 @@ void kill_block_super(struct super_block *sb)
 	struct block_device *bdev = sb->s_bdev;
 	fmode_t mode = sb->s_mode;
 
+	bdev->bd_super = 0;
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
 	close_bdev_exclusive(bdev, mode);

include/linux/ext3_fs.h

@@ -377,6 +377,13 @@ struct ext3_inode {
 #define	EXT3_ERROR_FS			0x0002	/* Errors detected */
 #define	EXT3_ORPHAN_FS			0x0004	/* Orphans being recovered */
 
+/*
+ * Misc. filesystem flags
+ */
+#define EXT2_FLAGS_SIGNED_HASH		0x0001  /* Signed dirhash in use */
+#define EXT2_FLAGS_UNSIGNED_HASH	0x0002  /* Unsigned dirhash in use */
+#define EXT2_FLAGS_TEST_FILESYS		0x0004	/* to test development code */
+
 /*
  * Mount flags
  */
@@ -513,7 +520,23 @@ struct ext3_super_block {
 	__u16	s_reserved_word_pad;
 	__le32	s_default_mount_opts;
 	__le32	s_first_meta_bg;	/* First metablock block group */
-	__u32	s_reserved[190];	/* Padding to the end of the block */
+	__le32	s_mkfs_time;		/* When the filesystem was created */
+	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
+	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
+	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
+	__le32	s_free_blocks_count_hi;	/* Free blocks count */
+	__le16	s_min_extra_isize;	/* All inodes have at least # bytes */
+	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
+	__le32	s_flags;		/* Miscellaneous flags */
+	__le16  s_raid_stride;		/* RAID stride */
+	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
+	__le64  s_mmp_block;            /* Block for multi-mount protection */
+	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
+	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
+	__u8	s_reserved_char_pad2;
+	__le16  s_reserved_pad;
+	__u32   s_reserved[162];        /* Padding to the end of the block */
 };
 
 #ifdef __KERNEL__
@@ -718,6 +741,9 @@ static inline __le16 ext3_rec_len_to_disk(unsigned len)
 #define DX_HASH_LEGACY		0
 #define DX_HASH_HALF_MD4	1
 #define DX_HASH_TEA		2
+#define DX_HASH_LEGACY_UNSIGNED	3
+#define DX_HASH_HALF_MD4_UNSIGNED	4
+#define DX_HASH_TEA_UNSIGNED		5
 
 #ifdef __KERNEL__
 

include/linux/ext3_fs_sb.h

@@ -57,6 +57,7 @@ struct ext3_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;

include/linux/fs.h

@@ -565,6 +565,7 @@ struct address_space {
 struct block_device {
 	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
 	struct inode *		bd_inode;	/* will die */
+	struct super_block *	bd_super;
 	int			bd_openers;
 	struct mutex		bd_mutex;	/* open/close mutex */
 	struct semaphore	bd_mount_sem;
@@ -1389,6 +1390,7 @@ struct super_operations {
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
+	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 };
 
 /*

include/linux/ioprio.h

@@ -86,4 +86,6 @@ static inline int task_nice_ioclass(struct task_struct *task)
  */
 extern int ioprio_best(unsigned short aprio, unsigned short bprio);
 
+extern int set_task_ioprio(struct task_struct *task, int ioprio);
+
 #endif

include/linux/jbd2.h

@@ -637,6 +637,11 @@ struct transaction_s
 	 */
 	unsigned long		t_expires;
 
+	/*
+	 * When this transaction started, in nanoseconds [no locking]
+	 */
+	ktime_t			t_start_time;
+
 	/*
 	 * How many handles used this transaction? [t_handle_lock]
 	 */
@@ -682,6 +687,8 @@ jbd2_time_diff(unsigned long start, unsigned long end)
 	return end + (MAX_JIFFY_OFFSET - start);
 }
 
+#define JBD2_NR_BATCH	64
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -825,6 +832,14 @@ struct journal_s
 	/* Semaphore for locking against concurrent checkpoints */
 	struct mutex		j_checkpoint_mutex;
 
+	/*
+	 * List of buffer heads used by the checkpoint routine.  This
+	 * was moved from jbd2_log_do_checkpoint() to reduce stack
+	 * usage.  Access to this array is controlled by the
+	 * j_checkpoint_mutex.  [j_checkpoint_mutex]
+	 */
+	struct buffer_head	*j_chkpt_bhs[JBD2_NR_BATCH];
+	
 	/*
 	 * Journal head: identifies the first unused block in the journal.
 	 * [j_state_lock]
@@ -939,8 +954,26 @@ struct journal_s
 	struct buffer_head	**j_wbuf;
 	int			j_wbufsize;
 
+	/*
+	 * this is the pid of hte last person to run a synchronous operation
+	 * through the journal
+	 */
 	pid_t			j_last_sync_writer;
 
+	/*
+	 * the average amount of time in nanoseconds it takes to commit a
+	 * transaction to disk. [j_state_lock]
+	 */
+	u64			j_average_commit_time;
+
+	/*
+	 * minimum and maximum times that we should wait for
+	 * additional filesystem operations to get batched into a
+	 * synchronous handle in microseconds
+	 */
+	u32			j_min_batch_time;
+	u32			j_max_batch_time;
+
 	/* This function is called when a transaction is closed */
 	void			(*j_commit_callback)(journal_t *,
 						     transaction_t *);
@@ -1102,7 +1135,6 @@ extern int	   jbd2_journal_set_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern void	   jbd2_journal_clear_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
-extern int	   jbd2_journal_create     (journal_t *);
 extern int	   jbd2_journal_load       (journal_t *journal);
 extern int	   jbd2_journal_destroy    (journal_t *);
 extern int	   jbd2_journal_recover    (journal_t *journal);
@@ -1177,8 +1209,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 
 void __jbd2_log_wait_for_space(journal_t *journal);
-extern void	__jbd2_journal_drop_transaction(journal_t *, transaction_t *);
+extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
-extern int	jbd2_cleanup_journal_tail(journal_t *);
+extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Debugging code only: */