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: (97 commits)
  jbd2: Unify log messages in jbd2 code
  jbd/jbd2: validate sb->s_first in journal_get_superblock()
  ext4: let ext4_ext_rm_leaf work with EXT_DEBUG defined
  ext4: fix a syntax error in ext4_ext_insert_extent when debugging enabled
  ext4: fix a typo in struct ext4_allocation_context
  ext4: Don't normalize an falloc request if it can fit in 1 extent.
  ext4: remove comments about extent mount option in ext4_new_inode()
  ext4: let ext4_discard_partial_buffers handle unaligned range correctly
  ext4: return ENOMEM if find_or_create_pages fails
  ext4: move vars to local scope in ext4_discard_partial_page_buffers_no_lock()
  ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten
  ext4: optimize locking for end_io extent conversion
  ext4: remove unnecessary call to waitqueue_active()
  ext4: Use correct locking for ext4_end_io_nolock()
  ext4: fix race in xattr block allocation path
  ext4: trace punch_hole correctly in ext4_ext_map_blocks
  ext4: clean up AGGRESSIVE_TEST code
  ext4: move variables to their scope
  ext4: fix quota accounting during migration
  ext4: migrate cleanup
  ...

Documentation/filesystems/ext4.txt

@@ -160,7 +160,9 @@ noload			if the filesystem was not unmounted cleanly,
                      	lead to any number of problems.
 
 data=journal		All data are committed into the journal prior to being
-			written into the main file system.
+			written into the main file system.  Enabling
+			this mode will disable delayed allocation and
+			O_DIRECT support.
 
 data=ordered	(*)	All data are forced directly out to the main file
 			system prior to its metadata being committed to the
@@ -201,30 +203,19 @@ inode_readahead_blks=n	This tuning parameter controls the maximum
 			table readahead algorithm will pre-read into
 			the buffer cache.  The default value is 32 blocks.
 
-orlov		(*)	This enables the new Orlov block allocator. It is
-			enabled by default.
-
-oldalloc		This disables the Orlov block allocator and enables
-			the old block allocator.  Orlov should have better
-			performance - we'd like to get some feedback if it's
-			the contrary for you.
-
-user_xattr		Enables Extended User Attributes.  Additionally, you
-			need to have extended attribute support enabled in the
-			kernel configuration (CONFIG_EXT4_FS_XATTR).  See the
-			attr(5) manual page and http://acl.bestbits.at/ to
-			learn more about extended attributes.
-
-nouser_xattr		Disables Extended User Attributes.
-
-acl			Enables POSIX Access Control Lists support.
-			Additionally, you need to have ACL support enabled in
-			the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
-			See the acl(5) manual page and http://acl.bestbits.at/
-			for more information.
+nouser_xattr		Disables Extended User Attributes. If you have extended
+			attribute support enabled in the kernel configuration
+			(CONFIG_EXT4_FS_XATTR), extended attribute support
+			is enabled by default on mount. See the attr(5) manual
+			page and http://acl.bestbits.at/ for more information
+			about extended attributes.
 
 noacl			This option disables POSIX Access Control List
-			support.
+			support. If ACL support is enabled in the kernel
+			configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
+			enabled by default on mount. See the acl(5) manual
+			page and http://acl.bestbits.at/ for more information
+			about acl.
 
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
@@ -419,8 +410,8 @@ written to the journal first, and then to its final location.
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Currently ext4 does not have delayed
-allocation support if this data journalling mode is selected.
+outperforms all others modes.  Enabling this mode will disable delayed
+allocation and O_DIRECT support.
 
 /proc entries
 =============

fs/ext4/balloc.c

@@ -28,7 +28,8 @@
  */
 
 /*
- * Calculate the block group number and offset, given a block number
+ * Calculate the block group number and offset into the block/cluster
+ * allocation bitmap, given a block number
  */
 void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 		ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
@@ -37,7 +38,8 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 	ext4_grpblk_t offset;
 
 	blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
-	offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
+	offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >>
+		EXT4_SB(sb)->s_cluster_bits;
 	if (offsetp)
 		*offsetp = offset;
 	if (blockgrpp)
@@ -55,130 +57,169 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
 	return 0;
 }
 
-static int ext4_group_used_meta_blocks(struct super_block *sb,
-				       ext4_group_t block_group,
-				       struct ext4_group_desc *gdp)
+/* Return the number of clusters used for file system metadata; this
+ * represents the overhead needed by the file system.
+ */
+unsigned ext4_num_overhead_clusters(struct super_block *sb,
+				    ext4_group_t block_group,
+				    struct ext4_group_desc *gdp)
 {
-	ext4_fsblk_t tmp;
+	unsigned num_clusters;
+	int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
+	ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
+	ext4_fsblk_t itbl_blk;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	/* block bitmap, inode bitmap, and inode table blocks */
-	int used_blocks = sbi->s_itb_per_group + 2;
 
-	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
-		if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
-					block_group))
-			used_blocks--;
-
-		if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
-					block_group))
-			used_blocks--;
-
-		tmp = ext4_inode_table(sb, gdp);
-		for (; tmp < ext4_inode_table(sb, gdp) +
-				sbi->s_itb_per_group; tmp++) {
-			if (!ext4_block_in_group(sb, tmp, block_group))
-				used_blocks -= 1;
+	/* This is the number of clusters used by the superblock,
+	 * block group descriptors, and reserved block group
+	 * descriptor blocks */
+	num_clusters = ext4_num_base_meta_clusters(sb, block_group);
+
+	/*
+	 * For the allocation bitmaps and inode table, we first need
+	 * to check to see if the block is in the block group.  If it
+	 * is, then check to see if the cluster is already accounted
+	 * for in the clusters used for the base metadata cluster, or
+	 * if we can increment the base metadata cluster to include
+	 * that block.  Otherwise, we will have to track the cluster
+	 * used for the allocation bitmap or inode table explicitly.
+	 * Normally all of these blocks are contiguous, so the special
+	 * case handling shouldn't be necessary except for *very*
+	 * unusual file system layouts.
+	 */
+	if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
+		block_cluster = EXT4_B2C(sbi, (start -
+					       ext4_block_bitmap(sb, gdp)));
+		if (block_cluster < num_clusters)
+			block_cluster = -1;
+		else if (block_cluster == num_clusters) {
+			num_clusters++;
+			block_cluster = -1;
 		}
 	}
-	return used_blocks;
-}
 
-/* Initializes an uninitialized block bitmap if given, and returns the
- * number of blocks free in the group. */
-unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
-		 ext4_group_t block_group, struct ext4_group_desc *gdp)
-{
-	int bit, bit_max;
-	ext4_group_t ngroups = ext4_get_groups_count(sb);
-	unsigned free_blocks, group_blocks;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	if (bh) {
-		J_ASSERT_BH(bh, buffer_locked(bh));
-
-		/* If checksum is bad mark all blocks used to prevent allocation
-		 * essentially implementing a per-group read-only flag. */
-		if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
-			ext4_error(sb, "Checksum bad for group %u",
-					block_group);
-			ext4_free_blks_set(sb, gdp, 0);
-			ext4_free_inodes_set(sb, gdp, 0);
-			ext4_itable_unused_set(sb, gdp, 0);
-			memset(bh->b_data, 0xff, sb->s_blocksize);
-			return 0;
+	if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
+		inode_cluster = EXT4_B2C(sbi,
+					 start - ext4_inode_bitmap(sb, gdp));
+		if (inode_cluster < num_clusters)
+			inode_cluster = -1;
+		else if (inode_cluster == num_clusters) {
+			num_clusters++;
+			inode_cluster = -1;
 		}
-		memset(bh->b_data, 0, sb->s_blocksize);
 	}
 
-	/* Check for superblock and gdt backups in this group */
-	bit_max = ext4_bg_has_super(sb, block_group);
-
-	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
-	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
-			  sbi->s_desc_per_block) {
-		if (bit_max) {
-			bit_max += ext4_bg_num_gdb(sb, block_group);
-			bit_max +=
-				le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+	itbl_blk = ext4_inode_table(sb, gdp);
+	for (i = 0; i < sbi->s_itb_per_group; i++) {
+		if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
+			c = EXT4_B2C(sbi, start - itbl_blk + i);
+			if ((c < num_clusters) || (c == inode_cluster) ||
+			    (c == block_cluster) || (c == itbl_cluster))
+				continue;
+			if (c == num_clusters) {
+				num_clusters++;
+				continue;
+			}
+			num_clusters++;
+			itbl_cluster = c;
 		}
-	} else { /* For META_BG_BLOCK_GROUPS */
-		bit_max += ext4_bg_num_gdb(sb, block_group);
 	}
 
-	if (block_group == ngroups - 1) {
+	if (block_cluster != -1)
+		num_clusters++;
+	if (inode_cluster != -1)
+		num_clusters++;
+
+	return num_clusters;
+}
+
+static unsigned int num_clusters_in_group(struct super_block *sb,
+					  ext4_group_t block_group)
+{
+	unsigned int blocks;
+
+	if (block_group == ext4_get_groups_count(sb) - 1) {
 		/*
-		 * Even though mke2fs always initialize first and last group
-		 * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
-		 * to make sure we calculate the right free blocks
+		 * Even though mke2fs always initializes the first and
+		 * last group, just in case some other tool was used,
+		 * we need to make sure we calculate the right free
+		 * blocks.
 		 */
-		group_blocks = ext4_blocks_count(sbi->s_es) -
-			ext4_group_first_block_no(sb, ngroups - 1);
-	} else {
-		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
-	}
+		blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) -
+			ext4_group_first_block_no(sb, block_group);
+	} else
+		blocks = EXT4_BLOCKS_PER_GROUP(sb);
+	return EXT4_NUM_B2C(EXT4_SB(sb), blocks);
+}
 
-	free_blocks = group_blocks - bit_max;
+/* Initializes an uninitialized block bitmap */
+void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
+			    ext4_group_t block_group,
+			    struct ext4_group_desc *gdp)
+{
+	unsigned int bit, bit_max;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t start, tmp;
+	int flex_bg = 0;
+
+	J_ASSERT_BH(bh, buffer_locked(bh));
+
+	/* If checksum is bad mark all blocks used to prevent allocation
+	 * essentially implementing a per-group read-only flag. */
+	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+		ext4_error(sb, "Checksum bad for group %u", block_group);
+		ext4_free_group_clusters_set(sb, gdp, 0);
+		ext4_free_inodes_set(sb, gdp, 0);
+		ext4_itable_unused_set(sb, gdp, 0);
+		memset(bh->b_data, 0xff, sb->s_blocksize);
+		return;
+	}
+	memset(bh->b_data, 0, sb->s_blocksize);
 
-	if (bh) {
-		ext4_fsblk_t start, tmp;
-		int flex_bg = 0;
+	bit_max = ext4_num_base_meta_clusters(sb, block_group);
+	for (bit = 0; bit < bit_max; bit++)
+		ext4_set_bit(bit, bh->b_data);
 
-		for (bit = 0; bit < bit_max; bit++)
-			ext4_set_bit(bit, bh->b_data);
+	start = ext4_group_first_block_no(sb, block_group);
 
-		start = ext4_group_first_block_no(sb, block_group);
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+		flex_bg = 1;
 
-		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
-					      EXT4_FEATURE_INCOMPAT_FLEX_BG))
-			flex_bg = 1;
+	/* Set bits for block and inode bitmaps, and inode table */
+	tmp = ext4_block_bitmap(sb, gdp);
+	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
-		/* Set bits for block and inode bitmaps, and inode table */
-		tmp = ext4_block_bitmap(sb, gdp);
-		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
-			ext4_set_bit(tmp - start, bh->b_data);
+	tmp = ext4_inode_bitmap(sb, gdp);
+	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
-		tmp = ext4_inode_bitmap(sb, gdp);
+	tmp = ext4_inode_table(sb, gdp);
+	for (; tmp < ext4_inode_table(sb, gdp) +
+		     sbi->s_itb_per_group; tmp++) {
 		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
-			ext4_set_bit(tmp - start, bh->b_data);
-
-		tmp = ext4_inode_table(sb, gdp);
-		for (; tmp < ext4_inode_table(sb, gdp) +
-				sbi->s_itb_per_group; tmp++) {
-			if (!flex_bg ||
-				ext4_block_in_group(sb, tmp, block_group))
-				ext4_set_bit(tmp - start, bh->b_data);
-		}
-		/*
-		 * Also if the number of blocks within the group is
-		 * less than the blocksize * 8 ( which is the size
-		 * of bitmap ), set rest of the block bitmap to 1
-		 */
-		ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
-				     bh->b_data);
+			ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 	}
-	return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
+
+	/*
+	 * Also if the number of blocks within the group is less than
+	 * the blocksize * 8 ( which is the size of bitmap ), set rest
+	 * of the block bitmap to 1
+	 */
+	ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
+			     sb->s_blocksize * 8, bh->b_data);
 }
 
+/* Return the number of free blocks in a block group.  It is used when
+ * the block bitmap is uninitialized, so we can't just count the bits
+ * in the bitmap. */
+unsigned ext4_free_clusters_after_init(struct super_block *sb,
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
+{
+	return num_clusters_in_group(sb, block_group) - 
+		ext4_num_overhead_clusters(sb, block_group, gdp);
+}
 
 /*
  * The free blocks are managed by bitmaps.  A file system contains several
@@ -362,53 +403,54 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 }
 
 /**
- * ext4_has_free_blocks()
+ * ext4_has_free_clusters()
  * @sbi:	in-core super block structure.
- * @nblocks:	number of needed blocks
+ * @nclusters:	number of needed blocks
+ * @flags:	flags from ext4_mb_new_blocks()
  *
- * Check if filesystem has nblocks free & available for allocation.
+ * Check if filesystem has nclusters free & available for allocation.
  * On success return 1, return 0 on failure.
  */
-static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
-				s64 nblocks, unsigned int flags)
+static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
+				  s64 nclusters, unsigned int flags)
 {
-	s64 free_blocks, dirty_blocks, root_blocks;
-	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
-	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
-
-	free_blocks  = percpu_counter_read_positive(fbc);
-	dirty_blocks = percpu_counter_read_positive(dbc);
-	root_blocks = ext4_r_blocks_count(sbi->s_es);
-
-	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
-						EXT4_FREEBLOCKS_WATERMARK) {
-		free_blocks  = percpu_counter_sum_positive(fbc);
-		dirty_blocks = percpu_counter_sum_positive(dbc);
+	s64 free_clusters, dirty_clusters, root_clusters;
+	struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
+	struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
+
+	free_clusters  = percpu_counter_read_positive(fcc);
+	dirty_clusters = percpu_counter_read_positive(dcc);
+	root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
+
+	if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
+					EXT4_FREECLUSTERS_WATERMARK) {
+		free_clusters  = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
+		dirty_clusters = percpu_counter_sum_positive(dcc);
 	}
-	/* Check whether we have space after
-	 * accounting for current dirty blocks & root reserved blocks.
+	/* Check whether we have space after accounting for current
+	 * dirty clusters & root reserved clusters.
 	 */
-	if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+	if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters))
 		return 1;
 
-	/* Hm, nope.  Are (enough) root reserved blocks available? */
+	/* Hm, nope.  Are (enough) root reserved clusters available? */
 	if (sbi->s_resuid == current_fsuid() ||
 	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
 	    capable(CAP_SYS_RESOURCE) ||
 		(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
 
-		if (free_blocks >= (nblocks + dirty_blocks))
+		if (free_clusters >= (nclusters + dirty_clusters))
 			return 1;
 	}
 
 	return 0;
 }
 
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-			   s64 nblocks, unsigned int flags)
+int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+			     s64 nclusters, unsigned int flags)
 {
-	if (ext4_has_free_blocks(sbi, nblocks, flags)) {
-		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
+	if (ext4_has_free_clusters(sbi, nclusters, flags)) {
+		percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
 		return 0;
 	} else
 		return -ENOSPC;
@@ -428,7 +470,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
+	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
 	    (*retries)++ > 3 ||
 	    !EXT4_SB(sb)->s_journal)
 		return 0;
@@ -444,7 +486,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
  * @handle:             handle to this transaction
  * @inode:              file inode
  * @goal:               given target block(filesystem wide)
- * @count:		pointer to total number of blocks needed
+ * @count:		pointer to total number of clusters needed
  * @errp:               error code
  *
  * Return 1st allocated block number on success, *count stores total account
@@ -476,18 +518,19 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 		EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-		dquot_alloc_block_nofail(inode, ar.len);
+		dquot_alloc_block_nofail(inode,
+				EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
 	}
 	return ret;
 }
 
 /**
- * ext4_count_free_blocks() -- count filesystem free blocks
+ * ext4_count_free_clusters() -- count filesystem free clusters
  * @sb:		superblock
  *
- * Adds up the number of free blocks from each block group.
+ * Adds up the number of free clusters from each block group.
  */
-ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
+ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t desc_count;
 	struct ext4_group_desc *gdp;
@@ -508,7 +551,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += ext4_free_blks_count(sb, gdp);
+		desc_count += ext4_free_group_clusters(sb, gdp);
 		brelse(bitmap_bh);
 		bitmap_bh = ext4_read_block_bitmap(sb, i);
 		if (bitmap_bh == NULL)
@@ -516,12 +559,13 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 
 		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
 		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
-			i, ext4_free_blks_count(sb, gdp), x);
+			i, ext4_free_group_clusters(sb, gdp), x);
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);
-	printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
-		", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+	printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
+	       ", computed = %llu, %llu\n",
+	       EXT4_B2C(sbi, ext4_free_blocks_count(es)),
 	       desc_count, bitmap_count);
 	return bitmap_count;
 #else
@@ -530,7 +574,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += ext4_free_blks_count(sb, gdp);
+		desc_count += ext4_free_group_clusters(sb, gdp);
 	}
 
 	return desc_count;
@@ -620,6 +664,31 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 
 }
 
+/*
+ * This function returns the number of file system metadata clusters at
+ * the beginning of a block group, including the reserved gdt blocks.
+ */
+unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+				     ext4_group_t block_group)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	unsigned num;
+
+	/* Check for superblock and gdt backups in this group */
+	num = ext4_bg_has_super(sb, block_group);
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
+			  sbi->s_desc_per_block) {
+		if (num) {
+			num += ext4_bg_num_gdb(sb, block_group);
+			num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+		}
+	} else { /* For META_BG_BLOCK_GROUPS */
+		num += ext4_bg_num_gdb(sb, block_group);
+	}
+	return EXT4_NUM_B2C(sbi, num);
+}
 /**
  *	ext4_inode_to_goal_block - return a hint for block allocation
  *	@inode: inode for block allocation

fs/ext4/ext4.h

@@ -144,9 +144,17 @@ struct ext4_allocation_request {
 #define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
 #define EXT4_MAP_UNINIT		(1 << BH_Uninit)
+/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
+ * ext4_map_blocks wants to know whether or not the underlying cluster has
+ * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
+ * the requested mapping was from previously mapped (or delayed allocated)
+ * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
+ * should never appear on buffer_head's state flags.
+ */
+#define EXT4_MAP_FROM_CLUSTER	(1 << BH_AllocFromCluster)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
 				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
-				 EXT4_MAP_UNINIT)
+				 EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
@@ -239,8 +247,11 @@ struct ext4_io_submit {
 # define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
 #endif
 #define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
+					 EXT4_SB(s)->s_cluster_bits)
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
+# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
 #else
 # define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
 #endif
@@ -258,6 +269,14 @@ struct ext4_io_submit {
 #endif
 #define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
 
+/* Translate a block number to a cluster number */
+#define EXT4_B2C(sbi, blk)	((blk) >> (sbi)->s_cluster_bits)
+/* Translate a cluster number to a block number */
+#define EXT4_C2B(sbi, cluster)	((cluster) << (sbi)->s_cluster_bits)
+/* Translate # of blks to # of clusters */
+#define EXT4_NUM_B2C(sbi, blks)	(((blks) + (sbi)->s_cluster_ratio - 1) >> \
+				 (sbi)->s_cluster_bits)
+
 /*
  * Structure of a blocks group descriptor
  */
@@ -289,7 +308,7 @@ struct ext4_group_desc
 
 struct flex_groups {
 	atomic_t free_inodes;
-	atomic_t free_blocks;
+	atomic_t free_clusters;
 	atomic_t used_dirs;
 };
 
@@ -306,6 +325,7 @@ struct flex_groups {
 #define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
 #ifdef __KERNEL__
 # define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
 # define EXT4_DESC_PER_BLOCK(s)		(EXT4_SB(s)->s_desc_per_block)
 # define EXT4_INODES_PER_GROUP(s)	(EXT4_SB(s)->s_inodes_per_group)
 # define EXT4_DESC_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_desc_per_block_bits)
@@ -358,8 +378,7 @@ struct flex_groups {
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
-			   EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
-			   EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
 
@@ -520,6 +539,8 @@ struct ext4_new_group_data {
 #define EXT4_GET_BLOCKS_PUNCH_OUT_EXT		0x0020
 	/* Don't normalize allocation size (used for fallocate) */
 #define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
+	/* Request will not result in inode size update (user for fallocate) */
+#define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
 
 /*
  * Flags used by ext4_free_blocks
@@ -528,6 +549,13 @@ struct ext4_new_group_data {
 #define EXT4_FREE_BLOCKS_FORGET		0x0002
 #define EXT4_FREE_BLOCKS_VALIDATED	0x0004
 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
+#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
+#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
+
+/*
+ * Flags used by ext4_discard_partial_page_buffers
+ */
+#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED	0x0001
 
 /*
  * ioctl commands
@@ -538,9 +566,6 @@ struct ext4_new_group_data {
 #define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
 #define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
 #define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
-#endif
 #define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
 #define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
 #define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
@@ -563,9 +588,6 @@ struct ext4_new_group_data {
 #define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
 #define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
 #define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
-#endif
 #define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
 #define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
 #endif
@@ -837,6 +859,7 @@ struct ext4_inode_info {
 	ext4_group_t	i_last_alloc_group;
 
 	/* allocation reservation info for delalloc */
+	/* In case of bigalloc, these refer to clusters rather than blocks */
 	unsigned int i_reserved_data_blocks;
 	unsigned int i_reserved_meta_blocks;
 	unsigned int i_allocated_meta_blocks;
@@ -886,7 +909,6 @@ struct ext4_inode_info {
 /*
  * Mount flags
  */
-#define EXT4_MOUNT_OLDALLOC		0x00002  /* Don't use the new Orlov allocator */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
 #define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
@@ -918,6 +940,9 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
 #define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
 
+#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
+						      specified delalloc */
+
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
 #define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
@@ -968,9 +993,9 @@ struct ext4_super_block {
 /*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
 	__le32	s_first_data_block;	/* First Data Block */
 	__le32	s_log_block_size;	/* Block size */
-	__le32	s_obso_log_frag_size;	/* Obsoleted fragment size */
+	__le32	s_log_cluster_size;	/* Allocation cluster size */
 /*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
-	__le32	s_obso_frags_per_group;	/* Obsoleted fragments per group */
+	__le32	s_clusters_per_group;	/* # Clusters per group */
 	__le32	s_inodes_per_group;	/* # Inodes per group */
 	__le32	s_mtime;		/* Mount time */
 /*30*/	__le32	s_wtime;		/* Write time */
@@ -1066,7 +1091,10 @@ struct ext4_super_block {
 	__u8	s_last_error_func[32];	/* function where the error happened */
 #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
 	__u8	s_mount_opts[64];
-	__le32	s_reserved[112];        /* Padding to the end of the block */
+	__le32	s_usr_quota_inum;	/* inode for tracking user quota */
+	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
+	__le32	s_overhead_clusters;	/* overhead blocks/clusters in fs */
+	__le32  s_reserved[109];        /* Padding to the end of the block */
 };
 
 #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1086,6 +1114,7 @@ struct ext4_sb_info {
 	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
 	unsigned long s_inodes_per_block;/* Number of inodes per block */
 	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_clusters_per_group; /* Number of clusters in a group */
 	unsigned long s_inodes_per_group;/* Number of inodes in a group */
 	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
 	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
@@ -1094,6 +1123,8 @@ struct ext4_sb_info {
 	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
 	unsigned long s_overhead_last;  /* Last calculated overhead */
 	unsigned long s_blocks_last;    /* Last seen block count */
+	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
+	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
 	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
@@ -1117,10 +1148,10 @@ struct ext4_sb_info {
 	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_freeclusters_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
-	struct percpu_counter s_dirtyblocks_counter;
+	struct percpu_counter s_dirtyclusters_counter;
 	struct blockgroup_lock *s_blockgroup_lock;
 	struct proc_dir_entry *s_proc;
 	struct kobject s_kobj;
@@ -1136,10 +1167,6 @@ struct ext4_sb_info {
 	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) */
-	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
-#endif
 #ifdef CONFIG_QUOTA
 	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
 	int s_jquota_fmt;			/* Format of quota to use */
@@ -1248,6 +1275,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
 
+static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+					      struct ext4_io_end *io_end)
+{
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
+}
+
 /*
  * Inode dynamic state flags
  */
@@ -1360,6 +1396,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
 #define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
+#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
@@ -1402,7 +1439,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
 					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
 					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
-					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
+					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
+					 EXT4_FEATURE_RO_COMPAT_BIGALLOC)
 
 /*
  * Default values for user and/or group using reserved blocks
@@ -1735,9 +1773,9 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 					 unsigned int flags,
 					 unsigned long *count,
 					 int *errp);
-extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-				  s64 nblocks, unsigned int flags);
-extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+				    s64 nclusters, unsigned int flags);
+extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
 extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
@@ -1745,12 +1783,18 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
 				      ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc)			\
-		ext4_init_block_bitmap(sb, NULL, group, desc)
+extern void ext4_init_block_bitmap(struct super_block *sb,
+				   struct buffer_head *bh,
+				   ext4_group_t group,
+				   struct ext4_group_desc *desc);
+extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
+					      ext4_group_t block_group,
+					      struct ext4_group_desc *gdp);
+extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+					    ext4_group_t block_group);
+extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
+					   ext4_group_t block_group,
+					   struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
 /* dir.c */
@@ -1776,7 +1820,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct
 
 /* ialloc.c */
 extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
-				    const struct qstr *qstr, __u32 goal);
+				    const struct qstr *qstr, __u32 goal,
+				    uid_t *owner);
 extern void ext4_free_inode(handle_t *, struct inode *);
 extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -1839,6 +1884,12 @@ extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
 extern int ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length);
+extern int ext4_discard_partial_page_buffers(handle_t *handle,
+		struct address_space *mapping, loff_t from,
+		loff_t length, int flags);
+extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+		struct inode *inode, struct page *page, loff_t from,
+		loff_t length, int flags);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1927,8 +1978,8 @@ 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_group_clusters(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,
@@ -1941,8 +1992,9 @@ 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_group_clusters_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,
@@ -2051,13 +2103,13 @@ do {								\
 } while (0)
 
 #ifdef CONFIG_SMP
-/* Each CPU can accumulate percpu_counter_batch blocks in their local
- * counters. So we need to make sure we have free blocks more
+/* Each CPU can accumulate percpu_counter_batch clusters in their local
+ * counters. So we need to make sure we have free clusters more
  * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
  */
-#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
+#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
 #else
-#define EXT4_FREEBLOCKS_WATERMARK 0
+#define EXT4_FREECLUSTERS_WATERMARK 0
 #endif
 
 static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
@@ -2243,10 +2295,19 @@ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
 enum ext4_state_bits {
 	BH_Uninit	/* blocks are allocated but uninitialized on disk */
 	  = BH_JBDPrivateStart,
+	BH_AllocFromCluster,	/* allocated blocks were part of already
+				 * allocated cluster. Note that this flag will
+				 * never, ever appear in a buffer_head's state
+				 * flag. See EXT4_MAP_FROM_CLUSTER to see where
+				 * this is used. */
+	BH_Da_Mapped,	/* Delayed allocated block that now has a mapping. This
+			 * flag is set when ext4_map_blocks is called on a
+			 * delayed allocated block to get its real mapping. */
 };
 
 BUFFER_FNS(Uninit, uninit)
 TAS_BUFFER_FNS(Uninit, uninit)
+BUFFER_FNS(Da_Mapped, da_mapped)
 
 /*
  * Add new method to test wether block and inode bitmaps are properly
@@ -2282,4 +2343,6 @@ extern void ext4_resize_end(struct super_block *sb);
 
 #endif	/* __KERNEL__ */
 
+#include "ext4_extents.h"
+
 #endif	/* _EXT4_H */

fs/ext4/ext4_extents.h

@@ -290,5 +290,7 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
 							struct ext4_ext_path *);
 extern void ext4_ext_drop_refs(struct ext4_ext_path *);
 extern int ext4_ext_check_inode(struct inode *inode);
+extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+				      int search_hint_reverse);
 #endif /* _EXT4_EXTENTS */
 

fs/ext4/ext4_jbd2.c

@@ -109,9 +109,11 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_dirty_metadata(handle, bh);
-		if (err)
-			ext4_journal_abort_handle(where, line, __func__,
-						  bh, handle, err);
+		if (err) {
+			/* Errors can only happen if there is a bug */
+			handle->h_err = err;
+			__ext4_journal_stop(where, line, handle);
+		}
 	} else {
 		if (inode)
 			mark_buffer_dirty_inode(bh, inode);

fs/ext4/extents.c

@@ -42,7 +42,6 @@
 #include <asm/uaccess.h>
 #include <linux/fiemap.h>
 #include "ext4_jbd2.h"
-#include "ext4_extents.h"
 
 #include <trace/events/ext4.h>
 
@@ -96,13 +95,17 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
  *  - ENOMEM
  *  - EIO
  */
-static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
-				struct ext4_ext_path *path)
+#define ext4_ext_dirty(handle, inode, path) \
+		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path)
 {
 	int err;
 	if (path->p_bh) {
 		/* path points to block */
-		err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
+		err = __ext4_handle_dirty_metadata(where, line, handle,
+						   inode, path->p_bh);
 	} else {
 		/* path points to leaf/index in inode body */
 		err = ext4_mark_inode_dirty(handle, inode);
@@ -114,11 +117,9 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 			      struct ext4_ext_path *path,
 			      ext4_lblk_t block)
 {
-	int depth;
-
 	if (path) {
+		int depth = path->p_depth;
 		struct ext4_extent *ex;
-		depth = path->p_depth;
 
 		/*
 		 * Try to predict block placement assuming that we are
@@ -180,12 +181,10 @@ static inline int ext4_ext_space_block(struct inode *inode, int check)
 
 	size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
 			/ sizeof(struct ext4_extent);
-	if (!check) {
 #ifdef AGGRESSIVE_TEST
-		if (size > 6)
-			size = 6;
+	if (!check && size > 6)
+		size = 6;
 #endif
-	}
 	return size;
 }
 
@@ -195,12 +194,10 @@ static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
 
 	size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
 			/ sizeof(struct ext4_extent_idx);
-	if (!check) {
 #ifdef AGGRESSIVE_TEST
-		if (size > 5)
-			size = 5;
+	if (!check && size > 5)
+		size = 5;
 #endif
-	}
 	return size;
 }
 
@@ -211,12 +208,10 @@ static inline int ext4_ext_space_root(struct inode *inode, int check)
 	size = sizeof(EXT4_I(inode)->i_data);
 	size -= sizeof(struct ext4_extent_header);
 	size /= sizeof(struct ext4_extent);
-	if (!check) {
 #ifdef AGGRESSIVE_TEST
-		if (size > 3)
-			size = 3;
+	if (!check && size > 3)
+		size = 3;
 #endif
-	}
 	return size;
 }
 
@@ -227,12 +222,10 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
 	size = sizeof(EXT4_I(inode)->i_data);
 	size -= sizeof(struct ext4_extent_header);
 	size /= sizeof(struct ext4_extent_idx);
-	if (!check) {
 #ifdef AGGRESSIVE_TEST
-		if (size > 4)
-			size = 4;
+	if (!check && size > 4)
+		size = 4;
 #endif
-	}
 	return size;
 }
 
@@ -244,7 +237,7 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
 int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	int idxs, num = 0;
+	int idxs;
 
 	idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
 		/ sizeof(struct ext4_extent_idx));
@@ -259,6 +252,8 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
 	 */
 	if (ei->i_da_metadata_calc_len &&
 	    ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+		int num = 0;
+
 		if ((ei->i_da_metadata_calc_len % idxs) == 0)
 			num++;
 		if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
@@ -321,8 +316,6 @@ static int ext4_valid_extent_entries(struct inode *inode,
 				struct ext4_extent_header *eh,
 				int depth)
 {
-	struct ext4_extent *ext;
-	struct ext4_extent_idx *ext_idx;
 	unsigned short entries;
 	if (eh->eh_entries == 0)
 		return 1;
@@ -331,7 +324,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
 
 	if (depth == 0) {
 		/* leaf entries */
-		ext = EXT_FIRST_EXTENT(eh);
+		struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
 		while (entries) {
 			if (!ext4_valid_extent(inode, ext))
 				return 0;
@@ -339,7 +332,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
 			entries--;
 		}
 	} else {
-		ext_idx = EXT_FIRST_INDEX(eh);
+		struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
 		while (entries) {
 			if (!ext4_valid_extent_idx(inode, ext_idx))
 				return 0;
@@ -751,31 +744,30 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
 		return -EIO;
 	}
 
-	len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
 	if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
 		/* insert after */
-		if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
-			len = (len - 1) * sizeof(struct ext4_extent_idx);
-			len = len < 0 ? 0 : len;
-			ext_debug("insert new index %d after: %llu. "
-					"move %d from 0x%p to 0x%p\n",
-					logical, ptr, len,
-					(curp->p_idx + 1), (curp->p_idx + 2));
-			memmove(curp->p_idx + 2, curp->p_idx + 1, len);
-		}
+		ext_debug("insert new index %d after: %llu\n", logical, ptr);
 		ix = curp->p_idx + 1;
 	} else {
 		/* insert before */
-		len = len * sizeof(struct ext4_extent_idx);
-		len = len < 0 ? 0 : len;
-		ext_debug("insert new index %d before: %llu. "
-				"move %d from 0x%p to 0x%p\n",
-				logical, ptr, len,
-				curp->p_idx, (curp->p_idx + 1));
-		memmove(curp->p_idx + 1, curp->p_idx, len);
+		ext_debug("insert new index %d before: %llu\n", logical, ptr);
 		ix = curp->p_idx;
 	}
 
+	len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
+	BUG_ON(len < 0);
+	if (len > 0) {
+		ext_debug("insert new index %d: "
+				"move %d indices from 0x%p to 0x%p\n",
+				logical, len, ix, ix + 1);
+		memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
+	}
+
+	if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
+		EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
+		return -EIO;
+	}
+
 	ix->ei_block = cpu_to_le32(logical);
 	ext4_idx_store_pblock(ix, ptr);
 	le16_add_cpu(&curp->p_hdr->eh_entries, 1);
@@ -1042,16 +1034,14 @@ cleanup:
  */
 static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 				 unsigned int flags,
-				 struct ext4_ext_path *path,
 				 struct ext4_extent *newext)
 {
-	struct ext4_ext_path *curp = path;
 	struct ext4_extent_header *neh;
 	struct buffer_head *bh;
 	ext4_fsblk_t newblock;
 	int err = 0;
 
-	newblock = ext4_ext_new_meta_block(handle, inode, path,
+	newblock = ext4_ext_new_meta_block(handle, inode, NULL,
 		newext, &err, flags);
 	if (newblock == 0)
 		return err;
@@ -1071,7 +1061,8 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	}
 
 	/* move top-level index/leaf into new block */
-	memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+	memmove(bh->b_data, EXT4_I(inode)->i_data,
+		sizeof(EXT4_I(inode)->i_data));
 
 	/* set size of new block */
 	neh = ext_block_hdr(bh);
@@ -1089,32 +1080,23 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	if (err)
 		goto out;
 
-	/* create index in new top-level index: num,max,pointer */
-	err = ext4_ext_get_access(handle, inode, curp);
-	if (err)
-		goto out;
-
-	curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
-	curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
-	curp->p_hdr->eh_entries = cpu_to_le16(1);
-	curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
-
-	if (path[0].p_hdr->eh_depth)
-		curp->p_idx->ei_block =
-			EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
-	else
-		curp->p_idx->ei_block =
-			EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
-	ext4_idx_store_pblock(curp->p_idx, newblock);
-
+	/* Update top-level index: num,max,pointer */
 	neh = ext_inode_hdr(inode);
+	neh->eh_entries = cpu_to_le16(1);
+	ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock);
+	if (neh->eh_depth == 0) {
+		/* Root extent block becomes index block */
+		neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
+		EXT_FIRST_INDEX(neh)->ei_block =
+			EXT_FIRST_EXTENT(neh)->ee_block;
+	}
 	ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
 		  le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
 		  le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
 		  ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
 
-	neh->eh_depth = cpu_to_le16(path->p_depth + 1);
-	err = ext4_ext_dirty(handle, inode, curp);
+	neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+	ext4_mark_inode_dirty(handle, inode);
 out:
 	brelse(bh);
 
@@ -1162,8 +1144,7 @@ repeat:
 			err = PTR_ERR(path);
 	} else {
 		/* tree is full, time to grow in depth */
-		err = ext4_ext_grow_indepth(handle, inode, flags,
-					    path, newext);
+		err = ext4_ext_grow_indepth(handle, inode, flags, newext);
 		if (err)
 			goto out;
 
@@ -1235,9 +1216,9 @@ static int ext4_ext_search_left(struct inode *inode,
 			if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
 				EXT4_ERROR_INODE(inode,
 				  "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
-				  ix != NULL ? ix->ei_block : 0,
+				  ix != NULL ? le32_to_cpu(ix->ei_block) : 0,
 				  EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
-				    EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+		le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0,
 				  depth);
 				return -EIO;
 			}
@@ -1260,13 +1241,14 @@ static int ext4_ext_search_left(struct inode *inode,
 /*
  * search the closest allocated block to the right for *logical
  * and returns it at @logical + it's physical address at @phys
- * if *logical is the smallest allocated block, the function
+ * if *logical is the largest allocated block, the function
  * returns 0 at @phys
  * return value contains 0 (success) or error code
  */
 static int ext4_ext_search_right(struct inode *inode,
 				 struct ext4_ext_path *path,
-				 ext4_lblk_t *logical, ext4_fsblk_t *phys)
+				 ext4_lblk_t *logical, ext4_fsblk_t *phys,
+				 struct ext4_extent **ret_ex)
 {
 	struct buffer_head *bh = NULL;
 	struct ext4_extent_header *eh;
@@ -1308,9 +1290,7 @@ static int ext4_ext_search_right(struct inode *inode,
 				return -EIO;
 			}
 		}
-		*logical = le32_to_cpu(ex->ee_block);
-		*phys = ext4_ext_pblock(ex);
-		return 0;
+		goto found_extent;
 	}
 
 	if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
@@ -1323,9 +1303,7 @@ static int ext4_ext_search_right(struct inode *inode,
 	if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
 		/* next allocated block in this leaf */
 		ex++;
-		*logical = le32_to_cpu(ex->ee_block);
-		*phys = ext4_ext_pblock(ex);
-		return 0;
+		goto found_extent;
 	}
 
 	/* go up and search for index to the right */
@@ -1368,9 +1346,12 @@ got_index:
 		return -EIO;
 	}
 	ex = EXT_FIRST_EXTENT(eh);
+found_extent:
 	*logical = le32_to_cpu(ex->ee_block);
 	*phys = ext4_ext_pblock(ex);
-	put_bh(bh);
+	*ret_ex = ex;
+	if (bh)
+		put_bh(bh);
 	return 0;
 }
 
@@ -1395,7 +1376,8 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
 	while (depth >= 0) {
 		if (depth == path->p_depth) {
 			/* leaf */
-			if (path[depth].p_ext !=
+			if (path[depth].p_ext &&
+				path[depth].p_ext !=
 					EXT_LAST_EXTENT(path[depth].p_hdr))
 			  return le32_to_cpu(path[depth].p_ext[1].ee_block);
 		} else {
@@ -1623,7 +1605,8 @@ static int ext4_ext_try_to_merge(struct inode *inode,
  * such that there will be no overlap, and then returns 1.
  * If there is no overlap found, it returns 0.
  */
-static unsigned int ext4_ext_check_overlap(struct inode *inode,
+static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
+					   struct inode *inode,
 					   struct ext4_extent *newext,
 					   struct ext4_ext_path *path)
 {
@@ -1637,6 +1620,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
 	if (!path[depth].p_ext)
 		goto out;
 	b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+	b2 &= ~(sbi->s_cluster_ratio - 1);
 
 	/*
 	 * get the next allocated block if the extent in the path
@@ -1646,6 +1630,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
 		b2 = ext4_ext_next_allocated_block(path);
 		if (b2 == EXT_MAX_BLOCKS)
 			goto out;
+		b2 &= ~(sbi->s_cluster_ratio - 1);
 	}
 
 	/* check for wrap through zero on extent logical start block*/
@@ -1697,7 +1682,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	/* try to insert block into found extent and return */
 	if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
 		&& ext4_can_extents_be_merged(inode, ex, newext)) {
-		ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+		ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n",
 			  ext4_ext_is_uninitialized(newext),
 			  ext4_ext_get_actual_len(newext),
 			  le32_to_cpu(ex->ee_block),
@@ -1735,7 +1720,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
 		next = ext4_ext_next_leaf_block(path);
 	if (next != EXT_MAX_BLOCKS) {
-		ext_debug("next leaf block - %d\n", next);
+		ext_debug("next leaf block - %u\n", next);
 		BUG_ON(npath != NULL);
 		npath = ext4_ext_find_extent(inode, next, NULL);
 		if (IS_ERR(npath))
@@ -1773,46 +1758,51 @@ has_space:
 
 	if (!nearex) {
 		/* there is no extent in this leaf, create first one */
-		ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
+		ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
 				le32_to_cpu(newext->ee_block),
 				ext4_ext_pblock(newext),
 				ext4_ext_is_uninitialized(newext),
 				ext4_ext_get_actual_len(newext));
-		path[depth].p_ext = EXT_FIRST_EXTENT(eh);
-	} else if (le32_to_cpu(newext->ee_block)
+		nearex = EXT_FIRST_EXTENT(eh);
+	} else {
+		if (le32_to_cpu(newext->ee_block)
 			   > le32_to_cpu(nearex->ee_block)) {
-/*		BUG_ON(newext->ee_block == nearex->ee_block); */
-		if (nearex != EXT_LAST_EXTENT(eh)) {
-			len = EXT_MAX_EXTENT(eh) - nearex;
-			len = (len - 1) * sizeof(struct ext4_extent);
-			len = len < 0 ? 0 : len;
-			ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
-					"move %d from 0x%p to 0x%p\n",
+			/* Insert after */
+			ext_debug("insert %u:%llu:[%d]%d before: "
+					"nearest %p\n",
 					le32_to_cpu(newext->ee_block),
 					ext4_ext_pblock(newext),
 					ext4_ext_is_uninitialized(newext),
 					ext4_ext_get_actual_len(newext),
-					nearex, len, nearex + 1, nearex + 2);
-			memmove(nearex + 2, nearex + 1, len);
+					nearex);
+			nearex++;
+		} else {
+			/* Insert before */
+			BUG_ON(newext->ee_block == nearex->ee_block);
+			ext_debug("insert %u:%llu:[%d]%d after: "
+					"nearest %p\n",
+					le32_to_cpu(newext->ee_block),
+					ext4_ext_pblock(newext),
+					ext4_ext_is_uninitialized(newext),
+					ext4_ext_get_actual_len(newext),
+					nearex);
+		}
+		len = EXT_LAST_EXTENT(eh) - nearex + 1;
+		if (len > 0) {
+			ext_debug("insert %u:%llu:[%d]%d: "
+					"move %d extents from 0x%p to 0x%p\n",
+					le32_to_cpu(newext->ee_block),
+					ext4_ext_pblock(newext),
+					ext4_ext_is_uninitialized(newext),
+					ext4_ext_get_actual_len(newext),
+					len, nearex, nearex + 1);
+			memmove(nearex + 1, nearex,
+				len * sizeof(struct ext4_extent));
 		}
-		path[depth].p_ext = nearex + 1;
-	} else {
-		BUG_ON(newext->ee_block == nearex->ee_block);
-		len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
-		len = len < 0 ? 0 : len;
-		ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
-				"move %d from 0x%p to 0x%p\n",
-				le32_to_cpu(newext->ee_block),
-				ext4_ext_pblock(newext),
-				ext4_ext_is_uninitialized(newext),
-				ext4_ext_get_actual_len(newext),
-				nearex, len, nearex, nearex + 1);
-		memmove(nearex + 1, nearex, len);
-		path[depth].p_ext = nearex;
 	}
 
 	le16_add_cpu(&eh->eh_entries, 1);
-	nearex = path[depth].p_ext;
+	path[depth].p_ext = nearex;
 	nearex->ee_block = newext->ee_block;
 	ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
 	nearex->ee_len = newext->ee_len;
@@ -1962,6 +1952,7 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
 	struct ext4_ext_cache *cex;
 	BUG_ON(len == 0);
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+	trace_ext4_ext_put_in_cache(inode, block, len, start);
 	cex = &EXT4_I(inode)->i_cached_extent;
 	cex->ec_block = block;
 	cex->ec_len = len;
@@ -2063,6 +2054,7 @@ errout:
 		sbi->extent_cache_misses++;
 	else
 		sbi->extent_cache_hits++;
+	trace_ext4_ext_in_cache(inode, block, ret);
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 	return ret;
 }
@@ -2130,6 +2122,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 	if (err)
 		return err;
 	ext_debug("index is empty, remove it, free block %llu\n", leaf);
+	trace_ext4_ext_rm_idx(inode, leaf);
+
 	ext4_free_blocks(handle, inode, NULL, leaf, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 	return err;
@@ -2158,7 +2152,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
 			 *  need to account for leaf block credit
 			 *
 			 *  bitmaps and block group descriptor blocks
-			 *  and other metadat blocks still need to be
+			 *  and other metadata blocks still need to be
 			 *  accounted.
 			 */
 			/* 1 bitmap, 1 block group descriptor */
@@ -2195,14 +2189,40 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 }
 
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
-				struct ext4_extent *ex,
-				ext4_lblk_t from, ext4_lblk_t to)
+			      struct ext4_extent *ex,
+			      ext4_fsblk_t *partial_cluster,
+			      ext4_lblk_t from, ext4_lblk_t to)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
+	ext4_fsblk_t pblk;
 	int flags = EXT4_FREE_BLOCKS_FORGET;
 
 	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
 		flags |= EXT4_FREE_BLOCKS_METADATA;
+	/*
+	 * For bigalloc file systems, we never free a partial cluster
+	 * at the beginning of the extent.  Instead, we make a note
+	 * that we tried freeing the cluster, and check to see if we
+	 * need to free it on a subsequent call to ext4_remove_blocks,
+	 * or at the end of the ext4_truncate() operation.
+	 */
+	flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
+
+	trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster);
+	/*
+	 * If we have a partial cluster, and it's different from the
+	 * cluster of the last block, we need to explicitly free the
+	 * partial cluster here.
+	 */
+	pblk = ext4_ext_pblock(ex) + ee_len - 1;
+	if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+		ext4_free_blocks(handle, inode, NULL,
+				 EXT4_C2B(sbi, *partial_cluster),
+				 sbi->s_cluster_ratio, flags);
+		*partial_cluster = 0;
+	}
+
 #ifdef EXTENTS_STATS
 	{
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2222,12 +2242,24 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 	    && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		/* tail removal */
 		ext4_lblk_t num;
-		ext4_fsblk_t start;
 
 		num = le32_to_cpu(ex->ee_block) + ee_len - from;
-		start = ext4_ext_pblock(ex) + ee_len - num;
-		ext_debug("free last %u blocks starting %llu\n", num, start);
-		ext4_free_blocks(handle, inode, NULL, start, num, flags);
+		pblk = ext4_ext_pblock(ex) + ee_len - num;
+		ext_debug("free last %u blocks starting %llu\n", num, pblk);
+		ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
+		/*
+		 * If the block range to be freed didn't start at the
+		 * beginning of a cluster, and we removed the entire
+		 * extent, save the partial cluster here, since we
+		 * might need to delete if we determine that the
+		 * truncate operation has removed all of the blocks in
+		 * the cluster.
+		 */
+		if (pblk & (sbi->s_cluster_ratio - 1) &&
+		    (ee_len == num))
+			*partial_cluster = EXT4_B2C(sbi, pblk);
+		else
+			*partial_cluster = 0;
 	} else if (from == le32_to_cpu(ex->ee_block)
 		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		/* head removal */
@@ -2238,7 +2270,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		start = ext4_ext_pblock(ex);
 
 		ext_debug("free first %u blocks starting %llu\n", num, start);
-		ext4_free_blocks(handle, inode, 0, start, num, flags);
+		ext4_free_blocks(handle, inode, NULL, start, num, flags);
 
 	} else {
 		printk(KERN_INFO "strange request: removal(2) "
@@ -2262,19 +2294,19 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
  */
 static int
 ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
-		struct ext4_ext_path *path, ext4_lblk_t start,
-		ext4_lblk_t end)
+		 struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+		 ext4_lblk_t start, ext4_lblk_t end)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int err = 0, correct_index = 0;
 	int depth = ext_depth(inode), credits;
 	struct ext4_extent_header *eh;
-	ext4_lblk_t a, b, block;
+	ext4_lblk_t a, b;
 	unsigned num;
 	ext4_lblk_t ex_ee_block;
 	unsigned short ex_ee_len;
 	unsigned uninitialized = 0;
 	struct ext4_extent *ex;
-	struct ext4_map_blocks map;
 
 	/* the header must be checked already in ext4_ext_remove_space() */
 	ext_debug("truncate since %u in leaf\n", start);
@@ -2291,6 +2323,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
+
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
 			ex_ee_block + ex_ee_len > start) {
 
@@ -2315,86 +2349,18 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			ex_ee_block = le32_to_cpu(ex->ee_block);
 			ex_ee_len = ext4_ext_get_actual_len(ex);
 			continue;
-		} else if (a != ex_ee_block &&
-			b != ex_ee_block + ex_ee_len - 1) {
-			/*
-			 * If this is a truncate, then this condition should
-			 * never happen because at least one of the end points
-			 * needs to be on the edge of the extent.
-			 */
-			if (end == EXT_MAX_BLOCKS - 1) {
-				ext_debug("  bad truncate %u:%u\n",
-						start, end);
-				block = 0;
-				num = 0;
-				err = -EIO;
-				goto out;
-			}
-			/*
-			 * else this is a hole punch, so the extent needs to
-			 * be split since neither edge of the hole is on the
-			 * extent edge
-			 */
-			else{
-				map.m_pblk = ext4_ext_pblock(ex);
-				map.m_lblk = ex_ee_block;
-				map.m_len = b - ex_ee_block;
-
-				err = ext4_split_extent(handle,
-					inode, path, &map, 0,
-					EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
-					EXT4_GET_BLOCKS_PRE_IO);
-
-				if (err < 0)
-					goto out;
-
-				ex_ee_len = ext4_ext_get_actual_len(ex);
-
-				b = ex_ee_block+ex_ee_len - 1 < end ?
-					ex_ee_block+ex_ee_len - 1 : end;
-
-				/* Then remove tail of this extent */
-				block = ex_ee_block;
-				num = a - block;
-			}
+		} else if (b != ex_ee_block + ex_ee_len - 1) {
+			EXT4_ERROR_INODE(inode,"  bad truncate %u:%u\n",
+					 start, end);
+			err = -EIO;
+			goto out;
 		} else if (a != ex_ee_block) {
 			/* remove tail of the extent */
-			block = ex_ee_block;
-			num = a - block;
-		} else if (b != ex_ee_block + ex_ee_len - 1) {
-			/* remove head of the extent */
-			block = b;
-			num =  ex_ee_block + ex_ee_len - b;
-
-			/*
-			 * If this is a truncate, this condition
-			 * should never happen
-			 */
-			if (end == EXT_MAX_BLOCKS - 1) {
-				ext_debug("  bad truncate %u:%u\n",
-					start, end);
-				err = -EIO;
-				goto out;
-			}
+			num = a - ex_ee_block;
 		} else {
 			/* remove whole extent: excellent! */
-			block = ex_ee_block;
 			num = 0;
-			if (a != ex_ee_block) {
-				ext_debug("  bad truncate %u:%u\n",
-					start, end);
-				err = -EIO;
-				goto out;
-			}
-
-			if (b != ex_ee_block + ex_ee_len - 1) {
-				ext_debug("  bad truncate %u:%u\n",
-					start, end);
-				err = -EIO;
-				goto out;
-			}
 		}
-
 		/*
 		 * 3 for leaf, sb, and inode plus 2 (bmap and group
 		 * descriptor) for each block group; assume two block
@@ -2416,23 +2382,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		if (err)
 			goto out;
 
-		err = ext4_remove_blocks(handle, inode, ex, a, b);
+		err = ext4_remove_blocks(handle, inode, ex, partial_cluster,
+					 a, b);
 		if (err)
 			goto out;
 
-		if (num == 0) {
+		if (num == 0)
 			/* this extent is removed; mark slot entirely unused */
 			ext4_ext_store_pblock(ex, 0);
-		} else if (block != ex_ee_block) {
-			/*
-			 * If this was a head removal, then we need to update
-			 * the physical block since it is now at a different
-			 * location
-			 */
-			ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
-		}
 
-		ex->ee_block = cpu_to_le32(block);
 		ex->ee_len = cpu_to_le16(num);
 		/*
 		 * Do not mark uninitialized if all the blocks in the
@@ -2440,11 +2398,6 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		 */
 		if (uninitialized && num)
 			ext4_ext_mark_uninitialized(ex);
-
-		err = ext4_ext_dirty(handle, inode, path + depth);
-		if (err)
-			goto out;
-
 		/*
 		 * If the extent was completely released,
 		 * we need to remove it from the leaf
@@ -2464,9 +2417,14 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 					sizeof(struct ext4_extent));
 			}
 			le16_add_cpu(&eh->eh_entries, -1);
-		}
+		} else
+			*partial_cluster = 0;
 
-		ext_debug("new extent: %u:%u:%llu\n", block, num,
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		if (err)
+			goto out;
+
+		ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num,
 				ext4_ext_pblock(ex));
 		ex--;
 		ex_ee_block = le32_to_cpu(ex->ee_block);
@@ -2476,6 +2434,25 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	if (correct_index && eh->eh_entries)
 		err = ext4_ext_correct_indexes(handle, inode, path);
 
+	/*
+	 * If there is still a entry in the leaf node, check to see if
+	 * it references the partial cluster.  This is the only place
+	 * where it could; if it doesn't, we can free the cluster.
+	 */
+	if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
+	     *partial_cluster)) {
+		int flags = EXT4_FREE_BLOCKS_FORGET;
+
+		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+			flags |= EXT4_FREE_BLOCKS_METADATA;
+
+		ext4_free_blocks(handle, inode, NULL,
+				 EXT4_C2B(sbi, *partial_cluster),
+				 sbi->s_cluster_ratio, flags);
+		*partial_cluster = 0;
+	}
+
 	/* if this leaf is free, then we should
 	 * remove it from index block above */
 	if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
@@ -2511,6 +2488,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
 	struct ext4_ext_path *path;
+	ext4_fsblk_t partial_cluster = 0;
 	handle_t *handle;
 	int i, err;
 
@@ -2524,6 +2502,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 again:
 	ext4_ext_invalidate_cache(inode);
 
+	trace_ext4_ext_remove_space(inode, start, depth);
+
 	/*
 	 * We start scanning from right side, freeing all the blocks
 	 * after i_size and walking into the tree depth-wise.
@@ -2546,7 +2526,8 @@ again:
 		if (i == depth) {
 			/* this is leaf block */
 			err = ext4_ext_rm_leaf(handle, inode, path,
-					start, EXT_MAX_BLOCKS - 1);
+					       &partial_cluster, start,
+					       EXT_MAX_BLOCKS - 1);
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
 			path[i].p_bh = NULL;
@@ -2618,6 +2599,24 @@ again:
 		}
 	}
 
+	trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
+			path->p_hdr->eh_entries);
+
+	/* If we still have something in the partial cluster and we have removed
+	 * even the first extent, then we should free the blocks in the partial
+	 * cluster as well. */
+	if (partial_cluster && path->p_hdr->eh_entries == 0) {
+		int flags = EXT4_FREE_BLOCKS_FORGET;
+
+		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+			flags |= EXT4_FREE_BLOCKS_METADATA;
+
+		ext4_free_blocks(handle, inode, NULL,
+				 EXT4_C2B(EXT4_SB(sb), partial_cluster),
+				 EXT4_SB(sb)->s_cluster_ratio, flags);
+		partial_cluster = 0;
+	}
+
 	/* TODO: flexible tree reduction should be here */
 	if (path->p_hdr->eh_entries == 0) {
 		/*
@@ -2909,17 +2908,29 @@ out:
  *   a> There is no split required: Entire extent should be initialized
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * Pre-conditions:
+ *  - The extent pointed to by 'path' is uninitialized.
+ *  - The extent pointed to by 'path' contains a superset
+ *    of the logical span [map->m_lblk, map->m_lblk + map->m_len).
+ *
+ * Post-conditions on success:
+ *  - the returned value is the number of blocks beyond map->l_lblk
+ *    that are allocated and initialized.
+ *    It is guaranteed to be >= map->m_len.
  */
 static int ext4_ext_convert_to_initialized(handle_t *handle,
 					   struct inode *inode,
 					   struct ext4_map_blocks *map,
 					   struct ext4_ext_path *path)
 {
+	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
 	struct ext4_extent zero_ex;
 	struct ext4_extent *ex;
 	ext4_lblk_t ee_block, eof_block;
-	unsigned int allocated, ee_len, depth;
+	unsigned int ee_len, depth;
+	int allocated;
 	int err = 0;
 	int split_flag = 0;
 
@@ -2933,11 +2944,93 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		eof_block = map->m_lblk + map->m_len;
 
 	depth = ext_depth(inode);
+	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
 	allocated = ee_len - (map->m_lblk - ee_block);
 
+	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
+
+	/* Pre-conditions */
+	BUG_ON(!ext4_ext_is_uninitialized(ex));
+	BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
+	BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
+
+	/*
+	 * Attempt to transfer newly initialized blocks from the currently
+	 * uninitialized extent to its left neighbor. This is much cheaper
+	 * than an insertion followed by a merge as those involve costly
+	 * memmove() calls. This is the common case in steady state for
+	 * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
+	 * writes.
+	 *
+	 * Limitations of the current logic:
+	 *  - L1: we only deal with writes at the start of the extent.
+	 *    The approach could be extended to writes at the end
+	 *    of the extent but this scenario was deemed less common.
+	 *  - L2: we do not deal with writes covering the whole extent.
+	 *    This would require removing the extent if the transfer
+	 *    is possible.
+	 *  - L3: we only attempt to merge with an extent stored in the
+	 *    same extent tree node.
+	 */
+	if ((map->m_lblk == ee_block) &&	/*L1*/
+		(map->m_len < ee_len) &&	/*L2*/
+		(ex > EXT_FIRST_EXTENT(eh))) {	/*L3*/
+		struct ext4_extent *prev_ex;
+		ext4_lblk_t prev_lblk;
+		ext4_fsblk_t prev_pblk, ee_pblk;
+		unsigned int prev_len, write_len;
+
+		prev_ex = ex - 1;
+		prev_lblk = le32_to_cpu(prev_ex->ee_block);
+		prev_len = ext4_ext_get_actual_len(prev_ex);
+		prev_pblk = ext4_ext_pblock(prev_ex);
+		ee_pblk = ext4_ext_pblock(ex);
+		write_len = map->m_len;
+
+		/*
+		 * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+		 * upon those conditions:
+		 * - C1: prev_ex is initialized,
+		 * - C2: prev_ex is logically abutting ex,
+		 * - C3: prev_ex is physically abutting ex,
+		 * - C4: prev_ex can receive the additional blocks without
+		 *   overflowing the (initialized) length limit.
+		 */
+		if ((!ext4_ext_is_uninitialized(prev_ex)) &&		/*C1*/
+			((prev_lblk + prev_len) == ee_block) &&		/*C2*/
+			((prev_pblk + prev_len) == ee_pblk) &&		/*C3*/
+			(prev_len < (EXT_INIT_MAX_LEN - write_len))) {	/*C4*/
+			err = ext4_ext_get_access(handle, inode, path + depth);
+			if (err)
+				goto out;
+
+			trace_ext4_ext_convert_to_initialized_fastpath(inode,
+				map, ex, prev_ex);
+
+			/* Shift the start of ex by 'write_len' blocks */
+			ex->ee_block = cpu_to_le32(ee_block + write_len);
+			ext4_ext_store_pblock(ex, ee_pblk + write_len);
+			ex->ee_len = cpu_to_le16(ee_len - write_len);
+			ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+
+			/* Extend prev_ex by 'write_len' blocks */
+			prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+
+			/* Mark the block containing both extents as dirty */
+			ext4_ext_dirty(handle, inode, path + depth);
+
+			/* Update path to point to the right extent */
+			path[depth].p_ext = prev_ex;
+
+			/* Result: number of initialized blocks past m_lblk */
+			allocated = write_len;
+			goto out;
+		}
+	}
+
 	WARN_ON(map->m_lblk < ee_block);
 	/*
 	 * It is safe to convert extent to initialized via explicit
@@ -3165,6 +3258,192 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
 	return ext4_mark_inode_dirty(handle, inode);
 }
 
+/**
+ * ext4_find_delalloc_range: find delayed allocated block in the given range.
+ *
+ * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
+ * whether there are any buffers marked for delayed allocation. It returns '1'
+ * on the first delalloc'ed buffer head found. If no buffer head in the given
+ * range is marked for delalloc, it returns 0.
+ * lblk_start should always be <= lblk_end.
+ * search_hint_reverse is to indicate that searching in reverse from lblk_end to
+ * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
+ * block sooner). This is useful when blocks are truncated sequentially from
+ * lblk_start towards lblk_end.
+ */
+static int ext4_find_delalloc_range(struct inode *inode,
+				    ext4_lblk_t lblk_start,
+				    ext4_lblk_t lblk_end,
+				    int search_hint_reverse)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct buffer_head *head, *bh = NULL;
+	struct page *page;
+	ext4_lblk_t i, pg_lblk;
+	pgoff_t index;
+
+	/* reverse search wont work if fs block size is less than page size */
+	if (inode->i_blkbits < PAGE_CACHE_SHIFT)
+		search_hint_reverse = 0;
+
+	if (search_hint_reverse)
+		i = lblk_end;
+	else
+		i = lblk_start;
+
+	index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	while ((i >= lblk_start) && (i <= lblk_end)) {
+		page = find_get_page(mapping, index);
+		if (!page)
+			goto nextpage;
+
+		if (!page_has_buffers(page))
+			goto nextpage;
+
+		head = page_buffers(page);
+		if (!head)
+			goto nextpage;
+
+		bh = head;
+		pg_lblk = index << (PAGE_CACHE_SHIFT -
+						inode->i_blkbits);
+		do {
+			if (unlikely(pg_lblk < lblk_start)) {
+				/*
+				 * This is possible when fs block size is less
+				 * than page size and our cluster starts/ends in
+				 * middle of the page. So we need to skip the
+				 * initial few blocks till we reach the 'lblk'
+				 */
+				pg_lblk++;
+				continue;
+			}
+
+			/* Check if the buffer is delayed allocated and that it
+			 * is not yet mapped. (when da-buffers are mapped during
+			 * their writeout, their da_mapped bit is set.)
+			 */
+			if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
+				page_cache_release(page);
+				trace_ext4_find_delalloc_range(inode,
+						lblk_start, lblk_end,
+						search_hint_reverse,
+						1, i);
+				return 1;
+			}
+			if (search_hint_reverse)
+				i--;
+			else
+				i++;
+		} while ((i >= lblk_start) && (i <= lblk_end) &&
+				((bh = bh->b_this_page) != head));
+nextpage:
+		if (page)
+			page_cache_release(page);
+		/*
+		 * Move to next page. 'i' will be the first lblk in the next
+		 * page.
+		 */
+		if (search_hint_reverse)
+			index--;
+		else
+			index++;
+		i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	}
+
+	trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+					search_hint_reverse, 0, 0);
+	return 0;
+}
+
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+			       int search_hint_reverse)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	ext4_lblk_t lblk_start, lblk_end;
+	lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+	lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
+
+	return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+					search_hint_reverse);
+}
+
+/**
+ * Determines how many complete clusters (out of those specified by the 'map')
+ * are under delalloc and were reserved quota for.
+ * This function is called when we are writing out the blocks that were
+ * originally written with their allocation delayed, but then the space was
+ * allocated using fallocate() before the delayed allocation could be resolved.
+ * The cases to look for are:
+ * ('=' indicated delayed allocated blocks
+ *  '-' indicates non-delayed allocated blocks)
+ * (a) partial clusters towards beginning and/or end outside of allocated range
+ *     are not delalloc'ed.
+ *	Ex:
+ *	|----c---=|====c====|====c====|===-c----|
+ *	         |++++++ allocated ++++++|
+ *	==> 4 complete clusters in above example
+ *
+ * (b) partial cluster (outside of allocated range) towards either end is
+ *     marked for delayed allocation. In this case, we will exclude that
+ *     cluster.
+ *	Ex:
+ *	|----====c========|========c========|
+ *	     |++++++ allocated ++++++|
+ *	==> 1 complete clusters in above example
+ *
+ *	Ex:
+ *	|================c================|
+ *            |++++++ allocated ++++++|
+ *	==> 0 complete clusters in above example
+ *
+ * The ext4_da_update_reserve_space will be called only if we
+ * determine here that there were some "entire" clusters that span
+ * this 'allocated' range.
+ * In the non-bigalloc case, this function will just end up returning num_blks
+ * without ever calling ext4_find_delalloc_range.
+ */
+static unsigned int
+get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
+			   unsigned int num_blks)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	ext4_lblk_t alloc_cluster_start, alloc_cluster_end;
+	ext4_lblk_t lblk_from, lblk_to, c_offset;
+	unsigned int allocated_clusters = 0;
+
+	alloc_cluster_start = EXT4_B2C(sbi, lblk_start);
+	alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1);
+
+	/* max possible clusters for this allocation */
+	allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1;
+
+	trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
+
+	/* Check towards left side */
+	c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+	if (c_offset) {
+		lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+		lblk_to = lblk_from + c_offset - 1;
+
+		if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+			allocated_clusters--;
+	}
+
+	/* Now check towards right. */
+	c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+	if (allocated_clusters && c_offset) {
+		lblk_from = lblk_start + num_blks;
+		lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
+
+		if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+			allocated_clusters--;
+	}
+
+	return allocated_clusters;
+}
+
 static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map,
@@ -3181,6 +3460,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
 
+	trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
+						    newblock);
+
 	/* get_block() before submit the IO, split the extent */
 	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
 		ret = ext4_split_unwritten_extents(handle, inode, map,
@@ -3190,10 +3472,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		 * that this IO needs to conversion to written when IO is
 		 * completed
 		 */
-		if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
-			io->flag = EXT4_IO_END_UNWRITTEN;
-			atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
-		} else
+		if (io)
+			ext4_set_io_unwritten_flag(inode, io);
+		else
 			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		if (ext4_should_dioread_nolock(inode))
 			map->m_flags |= EXT4_MAP_UNINIT;
@@ -3234,14 +3515,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 
 	/* buffered write, writepage time, convert*/
 	ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
-	if (ret >= 0) {
+	if (ret >= 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
-		err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
-					 map->m_len);
-		if (err < 0)
-			goto out2;
-	}
-
 out:
 	if (ret <= 0) {
 		err = ret;
@@ -3270,11 +3545,24 @@ out:
 	 * But fallocate would have already updated quota and block
 	 * count for this offset. So cancel these reservation
 	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
-		ext4_da_update_reserve_space(inode, allocated, 0);
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+		unsigned int reserved_clusters;
+		reserved_clusters = get_reserved_cluster_alloc(inode,
+				map->m_lblk, map->m_len);
+		if (reserved_clusters)
+			ext4_da_update_reserve_space(inode,
+						     reserved_clusters,
+						     0);
+	}
 
 map_out:
 	map->m_flags |= EXT4_MAP_MAPPED;
+	if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {
+		err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+					 map->m_len);
+		if (err < 0)
+			goto out2;
+	}
 out1:
 	if (allocated > map->m_len)
 		allocated = map->m_len;
@@ -3289,6 +3577,111 @@ out2:
 	return err ? err : allocated;
 }
 
+/*
+ * get_implied_cluster_alloc - check to see if the requested
+ * allocation (in the map structure) overlaps with a cluster already
+ * allocated in an extent.
+ *	@sb	The filesystem superblock structure
+ *	@map	The requested lblk->pblk mapping
+ *	@ex	The extent structure which might contain an implied
+ *			cluster allocation
+ *
+ * This function is called by ext4_ext_map_blocks() after we failed to
+ * find blocks that were already in the inode's extent tree.  Hence,
+ * we know that the beginning of the requested region cannot overlap
+ * the extent from the inode's extent tree.  There are three cases we
+ * want to catch.  The first is this case:
+ *
+ *		 |--- cluster # N--|
+ *    |--- extent ---|	|---- requested region ---|
+ *			|==========|
+ *
+ * The second case that we need to test for is this one:
+ *
+ *   |--------- cluster # N ----------------|
+ *	   |--- requested region --|   |------- extent ----|
+ *	   |=======================|
+ *
+ * The third case is when the requested region lies between two extents
+ * within the same cluster:
+ *          |------------- cluster # N-------------|
+ * |----- ex -----|                  |---- ex_right ----|
+ *                  |------ requested region ------|
+ *                  |================|
+ *
+ * In each of the above cases, we need to set the map->m_pblk and
+ * map->m_len so it corresponds to the return the extent labelled as
+ * "|====|" from cluster #N, since it is already in use for data in
+ * cluster EXT4_B2C(sbi, map->m_lblk).	We will then return 1 to
+ * signal to ext4_ext_map_blocks() that map->m_pblk should be treated
+ * as a new "allocated" block region.  Otherwise, we will return 0 and
+ * ext4_ext_map_blocks() will then allocate one or more new clusters
+ * by calling ext4_mb_new_blocks().
+ */
+static int get_implied_cluster_alloc(struct super_block *sb,
+				     struct ext4_map_blocks *map,
+				     struct ext4_extent *ex,
+				     struct ext4_ext_path *path)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+	ext4_lblk_t ex_cluster_start, ex_cluster_end;
+	ext4_lblk_t rr_cluster_start, rr_cluster_end;
+	ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
+	ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
+	unsigned short ee_len = ext4_ext_get_actual_len(ex);
+
+	/* The extent passed in that we are trying to match */
+	ex_cluster_start = EXT4_B2C(sbi, ee_block);
+	ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1);
+
+	/* The requested region passed into ext4_map_blocks() */
+	rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
+	rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
+
+	if ((rr_cluster_start == ex_cluster_end) ||
+	    (rr_cluster_start == ex_cluster_start)) {
+		if (rr_cluster_start == ex_cluster_end)
+			ee_start += ee_len - 1;
+		map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
+			c_offset;
+		map->m_len = min(map->m_len,
+				 (unsigned) sbi->s_cluster_ratio - c_offset);
+		/*
+		 * Check for and handle this case:
+		 *
+		 *   |--------- cluster # N-------------|
+		 *		       |------- extent ----|
+		 *	   |--- requested region ---|
+		 *	   |===========|
+		 */
+
+		if (map->m_lblk < ee_block)
+			map->m_len = min(map->m_len, ee_block - map->m_lblk);
+
+		/*
+		 * Check for the case where there is already another allocated
+		 * block to the right of 'ex' but before the end of the cluster.
+		 *
+		 *          |------------- cluster # N-------------|
+		 * |----- ex -----|                  |---- ex_right ----|
+		 *                  |------ requested region ------|
+		 *                  |================|
+		 */
+		if (map->m_lblk > ee_block) {
+			ext4_lblk_t next = ext4_ext_next_allocated_block(path);
+			map->m_len = min(map->m_len, next - map->m_lblk);
+		}
+
+		trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1);
+		return 1;
+	}
+
+	trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0);
+	return 0;
+}
+
+
 /*
  * Block allocation/map/preallocation routine for extents based files
  *
@@ -3311,15 +3704,17 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map, int flags)
 {
 	struct ext4_ext_path *path = NULL;
-	struct ext4_extent newex, *ex;
+	struct ext4_extent newex, *ex, *ex2;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_fsblk_t newblock = 0;
-	int err = 0, depth, ret;
-	unsigned int allocated = 0;
+	int free_on_err = 0, err = 0, depth, ret;
+	unsigned int allocated = 0, offset = 0;
+	unsigned int allocated_clusters = 0;
 	unsigned int punched_out = 0;
 	unsigned int result = 0;
 	struct ext4_allocation_request ar;
 	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
-	struct ext4_map_blocks punch_map;
+	ext4_lblk_t cluster_offset;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
 		  map->m_lblk, map->m_len, inode->i_ino);
@@ -3329,6 +3724,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
 		ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
 		if (!newex.ee_start_lo && !newex.ee_start_hi) {
+			if ((sbi->s_cluster_ratio > 1) &&
+			    ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+				map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
 			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 				/*
 				 * block isn't allocated yet and
@@ -3339,6 +3738,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			/* we should allocate requested block */
 		} else {
 			/* block is already allocated */
+			if (sbi->s_cluster_ratio > 1)
+				map->m_flags |= EXT4_MAP_FROM_CLUSTER;
 			newblock = map->m_lblk
 				   - le32_to_cpu(newex.ee_block)
 				   + ext4_ext_pblock(&newex);
@@ -3384,8 +3785,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 * we split out initialized portions during a write.
 		 */
 		ee_len = ext4_ext_get_actual_len(ex);
+
+		trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len);
+
 		/* if found extent covers block, simply return it */
 		if (in_range(map->m_lblk, ee_block, ee_len)) {
+			struct ext4_map_blocks punch_map;
+			ext4_fsblk_t partial_cluster = 0;
+
 			newblock = map->m_lblk - ee_block + ee_start;
 			/* number of remaining blocks in the extent */
 			allocated = ee_len - (map->m_lblk - ee_block);
@@ -3469,7 +3876,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			ext4_ext_invalidate_cache(inode);
 
 			err = ext4_ext_rm_leaf(handle, inode, path,
-				map->m_lblk, map->m_lblk + punched_out);
+					       &partial_cluster, map->m_lblk,
+					       map->m_lblk + punched_out);
 
 			if (!err && path->p_hdr->eh_entries == 0) {
 				/*
@@ -3492,6 +3900,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		}
 	}
 
+	if ((sbi->s_cluster_ratio > 1) &&
+	    ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
 	/*
 	 * requested block isn't allocated yet;
 	 * we couldn't try to create block if create flag is zero
@@ -3504,9 +3916,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
 		goto out2;
 	}
+
 	/*
 	 * Okay, we need to do block allocation.
 	 */
+	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+	newex.ee_block = cpu_to_le32(map->m_lblk);
+	cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+
+	/*
+	 * If we are doing bigalloc, check to see if the extent returned
+	 * by ext4_ext_find_extent() implies a cluster we can use.
+	 */
+	if (cluster_offset && ex &&
+	    get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
+		ar.len = allocated = map->m_len;
+		newblock = map->m_pblk;
+		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+		goto got_allocated_blocks;
+	}
 
 	/* find neighbour allocated blocks */
 	ar.lleft = map->m_lblk;
@@ -3514,10 +3942,21 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	if (err)
 		goto out2;
 	ar.lright = map->m_lblk;
-	err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+	ex2 = NULL;
+	err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
 	if (err)
 		goto out2;
 
+	/* Check if the extent after searching to the right implies a
+	 * cluster we can use. */
+	if ((sbi->s_cluster_ratio > 1) && ex2 &&
+	    get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+		ar.len = allocated = map->m_len;
+		newblock = map->m_pblk;
+		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+		goto got_allocated_blocks;
+	}
+
 	/*
 	 * See if request is beyond maximum number of blocks we can have in
 	 * a single extent. For an initialized extent this limit is
@@ -3532,9 +3971,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		map->m_len = EXT_UNINIT_MAX_LEN;
 
 	/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
-	newex.ee_block = cpu_to_le32(map->m_lblk);
 	newex.ee_len = cpu_to_le16(map->m_len);
-	err = ext4_ext_check_overlap(inode, &newex, path);
+	err = ext4_ext_check_overlap(sbi, inode, &newex, path);
 	if (err)
 		allocated = ext4_ext_get_actual_len(&newex);
 	else
@@ -3544,7 +3982,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	ar.inode = inode;
 	ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
 	ar.logical = map->m_lblk;
-	ar.len = allocated;
+	/*
+	 * We calculate the offset from the beginning of the cluster
+	 * for the logical block number, since when we allocate a
+	 * physical cluster, the physical block should start at the
+	 * same offset from the beginning of the cluster.  This is
+	 * needed so that future calls to get_implied_cluster_alloc()
+	 * work correctly.
+	 */
+	offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+	ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
+	ar.goal -= offset;
+	ar.logical -= offset;
 	if (S_ISREG(inode->i_mode))
 		ar.flags = EXT4_MB_HINT_DATA;
 	else
@@ -3557,9 +4006,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		goto out2;
 	ext_debug("allocate new block: goal %llu, found %llu/%u\n",
 		  ar.goal, newblock, allocated);
+	free_on_err = 1;
+	allocated_clusters = ar.len;
+	ar.len = EXT4_C2B(sbi, ar.len) - offset;
+	if (ar.len > allocated)
+		ar.len = allocated;
 
+got_allocated_blocks:
 	/* try to insert new extent into found leaf and return */
-	ext4_ext_store_pblock(&newex, newblock);
+	ext4_ext_store_pblock(&newex, newblock + offset);
 	newex.ee_len = cpu_to_le16(ar.len);
 	/* Mark uninitialized */
 	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
@@ -3572,10 +4027,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 * that we need to perform conversion when IO is done.
 		 */
 		if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-			if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
-				io->flag = EXT4_IO_END_UNWRITTEN;
-				atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
-			} else
+			if (io)
+				ext4_set_io_unwritten_flag(inode, io);
+			else
 				ext4_set_inode_state(inode,
 						     EXT4_STATE_DIO_UNWRITTEN);
 		}
@@ -3583,11 +4037,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			map->m_flags |= EXT4_MAP_UNINIT;
 	}
 
-	err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
+	err = 0;
+	if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0)
+		err = check_eofblocks_fl(handle, inode, map->m_lblk,
+					 path, ar.len);
 	if (!err)
 		err = ext4_ext_insert_extent(handle, inode, path,
 					     &newex, flags);
-	if (err) {
+	if (err && free_on_err) {
 		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
 			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
 		/* free data blocks we just allocated */
@@ -3610,8 +4067,82 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * Update reserved blocks/metadata blocks after successful
 	 * block allocation which had been deferred till now.
 	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
-		ext4_da_update_reserve_space(inode, allocated, 1);
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+		unsigned int reserved_clusters;
+		/*
+		 * Check how many clusters we had reserved this allocated range
+		 */
+		reserved_clusters = get_reserved_cluster_alloc(inode,
+						map->m_lblk, allocated);
+		if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+			if (reserved_clusters) {
+				/*
+				 * We have clusters reserved for this range.
+				 * But since we are not doing actual allocation
+				 * and are simply using blocks from previously
+				 * allocated cluster, we should release the
+				 * reservation and not claim quota.
+				 */
+				ext4_da_update_reserve_space(inode,
+						reserved_clusters, 0);
+			}
+		} else {
+			BUG_ON(allocated_clusters < reserved_clusters);
+			/* We will claim quota for all newly allocated blocks.*/
+			ext4_da_update_reserve_space(inode, allocated_clusters,
+							1);
+			if (reserved_clusters < allocated_clusters) {
+				struct ext4_inode_info *ei = EXT4_I(inode);
+				int reservation = allocated_clusters -
+						  reserved_clusters;
+				/*
+				 * It seems we claimed few clusters outside of
+				 * the range of this allocation. We should give
+				 * it back to the reservation pool. This can
+				 * happen in the following case:
+				 *
+				 * * Suppose s_cluster_ratio is 4 (i.e., each
+				 *   cluster has 4 blocks. Thus, the clusters
+				 *   are [0-3],[4-7],[8-11]...
+				 * * First comes delayed allocation write for
+				 *   logical blocks 10 & 11. Since there were no
+				 *   previous delayed allocated blocks in the
+				 *   range [8-11], we would reserve 1 cluster
+				 *   for this write.
+				 * * Next comes write for logical blocks 3 to 8.
+				 *   In this case, we will reserve 2 clusters
+				 *   (for [0-3] and [4-7]; and not for [8-11] as
+				 *   that range has a delayed allocated blocks.
+				 *   Thus total reserved clusters now becomes 3.
+				 * * Now, during the delayed allocation writeout
+				 *   time, we will first write blocks [3-8] and
+				 *   allocate 3 clusters for writing these
+				 *   blocks. Also, we would claim all these
+				 *   three clusters above.
+				 * * Now when we come here to writeout the
+				 *   blocks [10-11], we would expect to claim
+				 *   the reservation of 1 cluster we had made
+				 *   (and we would claim it since there are no
+				 *   more delayed allocated blocks in the range
+				 *   [8-11]. But our reserved cluster count had
+				 *   already gone to 0.
+				 *
+				 *   Thus, at the step 4 above when we determine
+				 *   that there are still some unwritten delayed
+				 *   allocated blocks outside of our current
+				 *   block range, we should increment the
+				 *   reserved clusters count so that when the
+				 *   remaining blocks finally gets written, we
+				 *   could claim them.
+				 */
+				dquot_reserve_block(inode,
+						EXT4_C2B(sbi, reservation));
+				spin_lock(&ei->i_block_reservation_lock);
+				ei->i_reserved_data_blocks += reservation;
+				spin_unlock(&ei->i_block_reservation_lock);
+			}
+		}
+	}
 
 	/*
 	 * Cache the extent and update transaction to commit on fdatasync only
@@ -3634,12 +4165,12 @@ out2:
 		ext4_ext_drop_refs(path);
 		kfree(path);
 	}
-	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
-		newblock, map->m_len, err ? err : allocated);
-
 	result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
 			punched_out : allocated;
 
+	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+		newblock, map->m_len, err ? err : result);
+
 	return err ? err : result;
 }
 
@@ -3649,6 +4180,7 @@ void ext4_ext_truncate(struct inode *inode)
 	struct super_block *sb = inode->i_sb;
 	ext4_lblk_t last_block;
 	handle_t *handle;
+	loff_t page_len;
 	int err = 0;
 
 	/*
@@ -3665,8 +4197,16 @@ void ext4_ext_truncate(struct inode *inode)
 	if (IS_ERR(handle))
 		return;
 
-	if (inode->i_size & (sb->s_blocksize - 1))
-		ext4_block_truncate_page(handle, mapping, inode->i_size);
+	if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+		page_len = PAGE_CACHE_SIZE -
+			(inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+		err = ext4_discard_partial_page_buffers(handle,
+			mapping, inode->i_size, page_len, 0);
+
+		if (err)
+			goto out_stop;
+	}
 
 	if (ext4_orphan_add(handle, inode))
 		goto out_stop;
@@ -3760,6 +4300,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	int ret = 0;
 	int ret2 = 0;
 	int retries = 0;
+	int flags;
 	struct ext4_map_blocks map;
 	unsigned int credits, blkbits = inode->i_blkbits;
 
@@ -3796,6 +4337,16 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
 		return ret;
 	}
+	flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+	if (mode & FALLOC_FL_KEEP_SIZE)
+		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+	/*
+	 * Don't normalize the request if it can fit in one extent so
+	 * that it doesn't get unnecessarily split into multiple
+	 * extents.
+	 */
+	if (len <= EXT_UNINIT_MAX_LEN << blkbits)
+		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 retry:
 	while (ret >= 0 && ret < max_blocks) {
 		map.m_lblk = map.m_lblk + ret;
@@ -3805,9 +4356,7 @@ retry:
 			ret = PTR_ERR(handle);
 			break;
 		}
-		ret = ext4_map_blocks(handle, inode, &map,
-				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
-				      EXT4_GET_BLOCKS_NO_NORMALIZE);
+		ret = ext4_map_blocks(handle, inode, &map, flags);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);
@@ -4102,7 +4651,6 @@ found_delayed_extent:
 		return EXT_BREAK;
 	return EXT_CONTINUE;
 }
-
 /* fiemap flags we can handle specified here */
 #define EXT4_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
@@ -4162,17 +4710,28 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 	struct address_space *mapping = inode->i_mapping;
 	struct ext4_map_blocks map;
 	handle_t *handle;
-	loff_t first_block_offset, last_block_offset, block_len;
-	loff_t first_page, last_page, first_page_offset, last_page_offset;
+	loff_t first_page, last_page, page_len;
+	loff_t first_page_offset, last_page_offset;
 	int ret, credits, blocks_released, err = 0;
 
+	/* No need to punch hole beyond i_size */
+	if (offset >= inode->i_size)
+		return 0;
+
+	/*
+	 * If the hole extends beyond i_size, set the hole
+	 * to end after the page that contains i_size
+	 */
+	if (offset + length > inode->i_size) {
+		length = inode->i_size +
+		   PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+		   offset;
+	}
+
 	first_block = (offset + sb->s_blocksize - 1) >>
 		EXT4_BLOCK_SIZE_BITS(sb);
 	last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
 
-	first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
-	last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
-
 	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
 
@@ -4185,11 +4744,10 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 	 */
 	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 		err = filemap_write_and_wait_range(mapping,
-			first_page_offset == 0 ? 0 : first_page_offset-1,
-			last_page_offset);
+			offset, offset + length - 1);
 
-			if (err)
-				return err;
+		if (err)
+			return err;
 	}
 
 	/* Now release the pages */
@@ -4211,24 +4769,64 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 		goto out;
 
 	/*
-	 * Now we need to zero out the un block aligned data.
-	 * If the file is smaller than a block, just
-	 * zero out the middle
+	 * Now we need to zero out the non-page-aligned data in the
+	 * pages at the start and tail of the hole, and unmap the buffer
+	 * heads for the block aligned regions of the page that were
+	 * completely zeroed.
 	 */
-	if (first_block > last_block)
-		ext4_block_zero_page_range(handle, mapping, offset, length);
-	else {
-		/* zero out the head of the hole before the first block */
-		block_len  = first_block_offset - offset;
-		if (block_len > 0)
-			ext4_block_zero_page_range(handle, mapping,
-						   offset, block_len);
-
-		/* zero out the tail of the hole after the last block */
-		block_len = offset + length - last_block_offset;
-		if (block_len > 0) {
-			ext4_block_zero_page_range(handle, mapping,
-					last_block_offset, block_len);
+	if (first_page > last_page) {
+		/*
+		 * If the file space being truncated is contained within a page
+		 * just zero out and unmap the middle of that page
+		 */
+		err = ext4_discard_partial_page_buffers(handle,
+			mapping, offset, length, 0);
+
+		if (err)
+			goto out;
+	} else {
+		/*
+		 * zero out and unmap the partial page that contains
+		 * the start of the hole
+		 */
+		page_len  = first_page_offset - offset;
+		if (page_len > 0) {
+			err = ext4_discard_partial_page_buffers(handle, mapping,
+						   offset, page_len, 0);
+			if (err)
+				goto out;
+		}
+
+		/*
+		 * zero out and unmap the partial page that contains
+		 * the end of the hole
+		 */
+		page_len = offset + length - last_page_offset;
+		if (page_len > 0) {
+			err = ext4_discard_partial_page_buffers(handle, mapping,
+					last_page_offset, page_len, 0);
+			if (err)
+				goto out;
+		}
+	}
+
+
+	/*
+	 * If i_size is contained in the last page, we need to
+	 * unmap and zero the partial page after i_size
+	 */
+	if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+	   inode->i_size % PAGE_CACHE_SIZE != 0) {
+
+		page_len = PAGE_CACHE_SIZE -
+			(inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+		if (page_len > 0) {
+			err = ext4_discard_partial_page_buffers(handle,
+			  mapping, inode->i_size, page_len, 0);
+
+			if (err)
+				goto out;
 		}
 	}
 

fs/ext4/file.c

@@ -181,8 +181,8 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		path.dentry = mnt->mnt_root;
 		cp = d_path(&path, buf, sizeof(buf));
 		if (!IS_ERR(cp)) {
-			memcpy(sbi->s_es->s_last_mounted, cp,
-			       sizeof(sbi->s_es->s_last_mounted));
+			strlcpy(sbi->s_es->s_last_mounted, cp,
+				sizeof(sbi->s_es->s_last_mounted));
 			ext4_mark_super_dirty(sb);
 		}
 	}

fs/ext4/fsync.c

@@ -75,7 +75,7 @@ static void dump_completed_IO(struct inode * inode)
  * to written.
  * The function return the number of pending IOs on success.
  */
-extern int ext4_flush_completed_IO(struct inode *inode)
+int ext4_flush_completed_IO(struct inode *inode)
 {
 	ext4_io_end_t *io;
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -83,14 +83,12 @@ extern int ext4_flush_completed_IO(struct inode *inode)
 	int ret = 0;
 	int ret2 = 0;
 
-	if (list_empty(&ei->i_completed_io_list))
-		return ret;
-
 	dump_completed_IO(inode);
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
 	while (!list_empty(&ei->i_completed_io_list)){
 		io = list_entry(ei->i_completed_io_list.next,
 				ext4_io_end_t, list);
+		list_del_init(&io->list);
 		/*
 		 * Calling ext4_end_io_nolock() to convert completed
 		 * IO to written.
@@ -107,11 +105,9 @@ extern int ext4_flush_completed_IO(struct inode *inode)
 		 */
 		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 		ret = ext4_end_io_nolock(io);
-		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
 		if (ret < 0)
 			ret2 = ret;
-		else
-			list_del_init(&io->list);
+		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
 	}
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 	return (ret2 < 0) ? ret2 : 0;

fs/ext4/ialloc.c

@@ -78,7 +78,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
 		ext4_error(sb, "Checksum bad for group %u", block_group);
-		ext4_free_blks_set(sb, gdp, 0);
+		ext4_free_group_clusters_set(sb, gdp, 0);
 		ext4_free_inodes_set(sb, gdp, 0);
 		ext4_itable_unused_set(sb, gdp, 0);
 		memset(bh->b_data, 0xff, sb->s_blocksize);
@@ -293,121 +293,9 @@ error_return:
 	ext4_std_error(sb, fatal);
 }
 
-/*
- * 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
- * free space and a low directory-to-inode ratio; if that fails, then of
- * the groups with above-average free space, that group with the fewest
- * directories already is chosen.
- *
- * For other inodes, search forward from the parent directory\'s block
- * group to find a free inode.
- */
-static int find_group_dir(struct super_block *sb, struct inode *parent,
-				ext4_group_t *best_group)
-{
-	ext4_group_t ngroups = ext4_get_groups_count(sb);
-	unsigned int freei, avefreei;
-	struct ext4_group_desc *desc, *best_desc = NULL;
-	ext4_group_t group;
-	int ret = -1;
-
-	freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
-	avefreei = freei / ngroups;
-
-	for (group = 0; group < ngroups; group++) {
-		desc = ext4_get_group_desc(sb, group, NULL);
-		if (!desc || !ext4_free_inodes_count(sb, desc))
-			continue;
-		if (ext4_free_inodes_count(sb, desc) < avefreei)
-			continue;
-		if (!best_desc ||
-		    (ext4_free_blks_count(sb, desc) >
-		     ext4_free_blks_count(sb, best_desc))) {
-			*best_group = group;
-			best_desc = desc;
-			ret = 0;
-		}
-	}
-	return ret;
-}
-
-#define free_block_ratio 10
-
-static int find_group_flex(struct super_block *sb, struct inode *parent,
-			   ext4_group_t *best_group)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_group_desc *desc;
-	struct flex_groups *flex_group = sbi->s_flex_groups;
-	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
-	ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
-	ext4_group_t ngroups = ext4_get_groups_count(sb);
-	int flex_size = ext4_flex_bg_size(sbi);
-	ext4_group_t best_flex = parent_fbg_group;
-	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
-	int flexbg_free_blocks;
-	int flex_freeb_ratio;
-	ext4_group_t n_fbg_groups;
-	ext4_group_t i;
-
-	n_fbg_groups = (ngroups + flex_size - 1) >>
-		sbi->s_log_groups_per_flex;
-
-find_close_to_parent:
-	flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
-	flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
-	if (atomic_read(&flex_group[best_flex].free_inodes) &&
-	    flex_freeb_ratio > free_block_ratio)
-		goto found_flexbg;
-
-	if (best_flex && best_flex == parent_fbg_group) {
-		best_flex--;
-		goto find_close_to_parent;
-	}
-
-	for (i = 0; i < n_fbg_groups; i++) {
-		if (i == parent_fbg_group || i == parent_fbg_group - 1)
-			continue;
-
-		flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
-		flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
-
-		if (flex_freeb_ratio > free_block_ratio &&
-		    (atomic_read(&flex_group[i].free_inodes))) {
-			best_flex = i;
-			goto found_flexbg;
-		}
-
-		if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
-		    ((atomic_read(&flex_group[i].free_blocks) >
-		      atomic_read(&flex_group[best_flex].free_blocks)) &&
-		     atomic_read(&flex_group[i].free_inodes)))
-			best_flex = i;
-	}
-
-	if (!atomic_read(&flex_group[best_flex].free_inodes) ||
-	    !atomic_read(&flex_group[best_flex].free_blocks))
-		return -1;
-
-found_flexbg:
-	for (i = best_flex * flex_size; i < ngroups &&
-		     i < (best_flex + 1) * flex_size; i++) {
-		desc = ext4_get_group_desc(sb, i, NULL);
-		if (ext4_free_inodes_count(sb, desc)) {
-			*best_group = i;
-			goto out;
-		}
-	}
-
-	return -1;
-out:
-	return 0;
-}
-
 struct orlov_stats {
 	__u32 free_inodes;
-	__u32 free_blocks;
+	__u32 free_clusters;
 	__u32 used_dirs;
 };
 
@@ -424,7 +312,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 
 	if (flex_size > 1) {
 		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
+		stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
 		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
 		return;
 	}
@@ -432,11 +320,11 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 	desc = ext4_get_group_desc(sb, g, NULL);
 	if (desc) {
 		stats->free_inodes = ext4_free_inodes_count(sb, desc);
-		stats->free_blocks = ext4_free_blks_count(sb, desc);
+		stats->free_clusters = ext4_free_group_clusters(sb, desc);
 		stats->used_dirs = ext4_used_dirs_count(sb, desc);
 	} else {
 		stats->free_inodes = 0;
-		stats->free_blocks = 0;
+		stats->free_clusters = 0;
 		stats->used_dirs = 0;
 	}
 }
@@ -471,10 +359,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei;
-	ext4_fsblk_t freeb, avefreeb;
+	ext4_fsblk_t freeb, avefreec;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
-	ext4_grpblk_t min_blocks;
+	ext4_grpblk_t min_clusters;
 	ext4_group_t i, grp, g, ngroups;
 	struct ext4_group_desc *desc;
 	struct orlov_stats stats;
@@ -490,9 +378,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 
 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
 	avefreei = freei / ngroups;
-	freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
-	avefreeb = freeb;
-	do_div(avefreeb, ngroups);
+	freeb = EXT4_C2B(sbi,
+		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+	avefreec = freeb;
+	do_div(avefreec, ngroups);
 	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
 
 	if (S_ISDIR(mode) &&
@@ -518,7 +407,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 				continue;
 			if (stats.free_inodes < avefreei)
 				continue;
-			if (stats.free_blocks < avefreeb)
+			if (stats.free_clusters < avefreec)
 				continue;
 			grp = g;
 			ret = 0;
@@ -556,7 +445,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	min_inodes = avefreei - inodes_per_group*flex_size / 4;
 	if (min_inodes < 1)
 		min_inodes = 1;
-	min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4;
+	min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
 
 	/*
 	 * Start looking in the flex group where we last allocated an
@@ -575,7 +464,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 			continue;
 		if (stats.free_inodes < min_inodes)
 			continue;
-		if (stats.free_blocks < min_blocks)
+		if (stats.free_clusters < min_clusters)
 			continue;
 		goto found_flex_bg;
 	}
@@ -659,7 +548,7 @@ 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 && ext4_free_inodes_count(sb, desc) &&
-			ext4_free_blks_count(sb, desc))
+	    ext4_free_group_clusters(sb, desc))
 		return 0;
 
 	/*
@@ -683,7 +572,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 			*group -= ngroups;
 		desc = ext4_get_group_desc(sb, *group, NULL);
 		if (desc && ext4_free_inodes_count(sb, desc) &&
-				ext4_free_blks_count(sb, desc))
+		    ext4_free_group_clusters(sb, desc))
 			return 0;
 	}
 
@@ -802,7 +691,7 @@ err_ret:
  * group to find a free inode.
  */
 struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
-			     const struct qstr *qstr, __u32 goal)
+			     const struct qstr *qstr, __u32 goal, uid_t *owner)
 {
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
@@ -816,8 +705,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
 	int ret2, err = 0;
 	struct inode *ret;
 	ext4_group_t i;
-	int free = 0;
-	static int once = 1;
 	ext4_group_t flex_group;
 
 	/* Cannot create files in a deleted directory */
@@ -843,26 +730,9 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
 		goto got_group;
 	}
 
-	if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
-		ret2 = find_group_flex(sb, dir, &group);
-		if (ret2 == -1) {
-			ret2 = find_group_other(sb, dir, &group, mode);
-			if (ret2 == 0 && once) {
-				once = 0;
-				printk(KERN_NOTICE "ext4: find_group_flex "
-				       "failed, fallback succeeded dir %lu\n",
-				       dir->i_ino);
-			}
-		}
-		goto got_group;
-	}
-
-	if (S_ISDIR(mode)) {
-		if (test_opt(sb, OLDALLOC))
-			ret2 = find_group_dir(sb, dir, &group);
-		else
-			ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
-	} else
+	if (S_ISDIR(mode))
+		ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
+	else
 		ret2 = find_group_other(sb, dir, &group, mode);
 
 got_group:
@@ -950,26 +820,21 @@ got:
 			goto fail;
 		}
 
-		free = 0;
-		ext4_lock_group(sb, group);
+		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+		err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
+		brelse(block_bitmap_bh);
+
 		/* recheck and clear flag under lock if we still need to */
+		ext4_lock_group(sb, group);
 		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-			free = ext4_free_blocks_after_init(sb, group, gdp);
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
-			ext4_free_blks_set(sb, gdp, free);
+			ext4_free_group_clusters_set(sb, gdp,
+				ext4_free_clusters_after_init(sb, group, gdp));
 			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
 								gdp);
 		}
 		ext4_unlock_group(sb, group);
 
-		/* Don't need to dirty bitmap block if we didn't change it */
-		if (free) {
-			BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
-			err = ext4_handle_dirty_metadata(handle,
-							NULL, block_bitmap_bh);
-		}
-
-		brelse(block_bitmap_bh);
 		if (err)
 			goto fail;
 	}
@@ -987,8 +852,11 @@ got:
 		flex_group = ext4_flex_group(sbi, group);
 		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
 	}
-
-	if (test_opt(sb, GRPID)) {
+	if (owner) {
+		inode->i_mode = mode;
+		inode->i_uid = owner[0];
+		inode->i_gid = owner[1];
+	} else if (test_opt(sb, GRPID)) {
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = dir->i_gid;
@@ -1005,11 +873,7 @@ got:
 	ei->i_dir_start_lookup = 0;
 	ei->i_disksize = 0;
 
-	/*
-	 * Don't inherit extent flag from directory, amongst others. We set
-	 * extent flag on newly created directory and file only if -o extent
-	 * mount option is specified
-	 */
+	/* Don't inherit extent flag from directory, amongst others. */
 	ei->i_flags =
 		ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
 	ei->i_file_acl = 0;
@@ -1235,7 +1099,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
  * inode allocation from the current group, so we take alloc_sem lock, to
  * block ext4_claim_inode until we are finished.
  */
-extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 				 int barrier)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);

fs/ext4/indirect.c

@@ -699,6 +699,13 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	/*
 	 * Okay, we need to do block allocation.
 	*/
+	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+		EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
+				 "non-extent mapped inodes with bigalloc");
+		return -ENOSPC;
+	}
+
 	goal = ext4_find_goal(inode, map->m_lblk, partial);
 
 	/* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1343,7 +1350,9 @@ void ext4_ind_truncate(struct inode *inode)
 	__le32 nr = 0;
 	int n = 0;
 	ext4_lblk_t last_block, max_block;
+	loff_t page_len;
 	unsigned blocksize = inode->i_sb->s_blocksize;
+	int err;
 
 	handle = start_transaction(inode);
 	if (IS_ERR(handle))
@@ -1354,9 +1363,16 @@ void ext4_ind_truncate(struct inode *inode)
 	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
 					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
 
-	if (inode->i_size & (blocksize - 1))
-		if (ext4_block_truncate_page(handle, mapping, inode->i_size))
+	if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+		page_len = PAGE_CACHE_SIZE -
+			(inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+		err = ext4_discard_partial_page_buffers(handle,
+			mapping, inode->i_size, page_len, 0);
+
+		if (err)
 			goto out_stop;
+	}
 
 	if (last_block != max_block) {
 		n = ext4_block_to_path(inode, last_block, offsets, NULL);

fs/ext4/inode.c

@@ -42,7 +42,6 @@
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "ext4_extents.h"
 #include "truncate.h"
 
 #include <trace/events/ext4.h>
@@ -268,7 +267,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	spin_lock(&ei->i_block_reservation_lock);
-	trace_ext4_da_update_reserve_space(inode, used);
+	trace_ext4_da_update_reserve_space(inode, used, quota_claim);
 	if (unlikely(used > ei->i_reserved_data_blocks)) {
 		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
 			 "with only %d reserved data blocks\n",
@@ -281,7 +280,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	/* Update per-inode reservations */
 	ei->i_reserved_data_blocks -= used;
 	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
-	percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+	percpu_counter_sub(&sbi->s_dirtyclusters_counter,
 			   used + ei->i_allocated_meta_blocks);
 	ei->i_allocated_meta_blocks = 0;
 
@@ -291,7 +290,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 		 * only when we have written all of the delayed
 		 * allocation blocks.
 		 */
-		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+		percpu_counter_sub(&sbi->s_dirtyclusters_counter,
 				   ei->i_reserved_meta_blocks);
 		ei->i_reserved_meta_blocks = 0;
 		ei->i_da_metadata_calc_len = 0;
@@ -300,14 +299,14 @@ void ext4_da_update_reserve_space(struct inode *inode,
 
 	/* Update quota subsystem for data blocks */
 	if (quota_claim)
-		dquot_claim_block(inode, used);
+		dquot_claim_block(inode, EXT4_C2B(sbi, used));
 	else {
 		/*
 		 * We did fallocate with an offset that is already delayed
 		 * allocated. So on delayed allocated writeback we should
 		 * not re-claim the quota for fallocated blocks.
 		 */
-		dquot_release_reservation_block(inode, used);
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
 	}
 
 	/*
@@ -398,6 +397,49 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
 	return num;
 }
 
+/*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+static void set_buffers_da_mapped(struct inode *inode,
+				   struct ext4_map_blocks *map)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct pagevec pvec;
+	int i, nr_pages;
+	pgoff_t index, end;
+
+	index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	end = (map->m_lblk + map->m_len - 1) >>
+		(PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	pagevec_init(&pvec, 0);
+	while (index <= end) {
+		nr_pages = pagevec_lookup(&pvec, mapping, index,
+					  min(end - index + 1,
+					      (pgoff_t)PAGEVEC_SIZE));
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			struct buffer_head *bh, *head;
+
+			if (unlikely(page->mapping != mapping) ||
+			    !PageDirty(page))
+				break;
+
+			if (page_has_buffers(page)) {
+				bh = head = page_buffers(page);
+				do {
+					set_buffer_da_mapped(bh);
+					bh = bh->b_this_page;
+				} while (bh != head);
+			}
+			index++;
+		}
+		pagevec_release(&pvec);
+	}
+}
+
 /*
  * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -416,7 +458,7 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
  * the buffer head is mapped.
  *
  * It returns 0 if plain look up failed (blocks have not been allocated), in
- * that casem, buffer head is unmapped
+ * that case, buffer head is unmapped
  *
  * It returns the error in case of allocation failure.
  */
@@ -435,9 +477,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	down_read((&EXT4_I(inode)->i_data_sem));
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-		retval = ext4_ext_map_blocks(handle, inode, map, 0);
+		retval = ext4_ext_map_blocks(handle, inode, map, flags &
+					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	} else {
-		retval = ext4_ind_map_blocks(handle, inode, map, 0);
+		retval = ext4_ind_map_blocks(handle, inode, map, flags &
+					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	}
 	up_read((&EXT4_I(inode)->i_data_sem));
 
@@ -455,7 +499,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * Returns if the blocks have already allocated
 	 *
 	 * Note that if blocks have been preallocated
-	 * ext4_ext_get_block() returns th create = 0
+	 * ext4_ext_get_block() returns the create = 0
 	 * with buffer head unmapped.
 	 */
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
@@ -517,9 +561,17 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
 			ext4_da_update_reserve_space(inode, retval, 1);
 	}
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
 		ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
+		/* If we have successfully mapped the delayed allocated blocks,
+		 * set the BH_Da_Mapped bit on them. Its important to do this
+		 * under the protection of i_data_sem.
+		 */
+		if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+			set_buffers_da_mapped(inode, map);
+	}
+
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		int ret = check_block_validity(inode, map);
@@ -909,7 +961,11 @@ static int ext4_ordered_write_end(struct file *file,
 			ext4_orphan_add(handle, inode);
 		if (ret2 < 0)
 			ret = ret2;
+	} else {
+		unlock_page(page);
+		page_cache_release(page);
 	}
+
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -1037,14 +1093,14 @@ static int ext4_journalled_write_end(struct file *file,
 }
 
 /*
- * Reserve a single block located at lblock
+ * Reserve a single cluster located at lblock
  */
 static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 {
 	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	unsigned long md_needed;
+	unsigned int md_needed;
 	int ret;
 
 	/*
@@ -1054,7 +1110,8 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 */
 repeat:
 	spin_lock(&ei->i_block_reservation_lock);
-	md_needed = ext4_calc_metadata_amount(inode, lblock);
+	md_needed = EXT4_NUM_B2C(sbi,
+				 ext4_calc_metadata_amount(inode, lblock));
 	trace_ext4_da_reserve_space(inode, md_needed);
 	spin_unlock(&ei->i_block_reservation_lock);
 
@@ -1063,15 +1120,15 @@ repeat:
 	 * us from metadata over-estimation, though we may go over by
 	 * a small amount in the end.  Here we just reserve for data.
 	 */
-	ret = dquot_reserve_block(inode, 1);
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
 	if (ret)
 		return ret;
 	/*
 	 * We do still charge estimated metadata to the sb though;
 	 * we cannot afford to run out of free blocks.
 	 */
-	if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
-		dquot_release_reservation_block(inode, 1);
+	if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
 			goto repeat;
@@ -1118,19 +1175,21 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 		 * We can release all of the reserved metadata blocks
 		 * only when we have written all of the delayed
 		 * allocation blocks.
+		 * Note that in case of bigalloc, i_reserved_meta_blocks,
+		 * i_reserved_data_blocks, etc. refer to number of clusters.
 		 */
-		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+		percpu_counter_sub(&sbi->s_dirtyclusters_counter,
 				   ei->i_reserved_meta_blocks);
 		ei->i_reserved_meta_blocks = 0;
 		ei->i_da_metadata_calc_len = 0;
 	}
 
 	/* update fs dirty data blocks counter */
-	percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
+	percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
 
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	dquot_release_reservation_block(inode, to_free);
+	dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
 }
 
 static void ext4_da_page_release_reservation(struct page *page,
@@ -1139,6 +1198,9 @@ static void ext4_da_page_release_reservation(struct page *page,
 	int to_release = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
+	struct inode *inode = page->mapping->host;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int num_clusters;
 
 	head = page_buffers(page);
 	bh = head;
@@ -1148,10 +1210,24 @@ static void ext4_da_page_release_reservation(struct page *page,
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
 			to_release++;
 			clear_buffer_delay(bh);
+			clear_buffer_da_mapped(bh);
 		}
 		curr_off = next_off;
 	} while ((bh = bh->b_this_page) != head);
-	ext4_da_release_space(page->mapping->host, to_release);
+
+	/* If we have released all the blocks belonging to a cluster, then we
+	 * need to release the reserved space for that cluster. */
+	num_clusters = EXT4_NUM_B2C(sbi, to_release);
+	while (num_clusters > 0) {
+		ext4_fsblk_t lblk;
+		lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+			((num_clusters - 1) << sbi->s_cluster_bits);
+		if (sbi->s_cluster_ratio == 1 ||
+		    !ext4_find_delalloc_cluster(inode, lblk, 1))
+			ext4_da_release_space(inode, 1);
+
+		num_clusters--;
+	}
 }
 
 /*
@@ -1253,6 +1329,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 						clear_buffer_delay(bh);
 						bh->b_blocknr = pblock;
 					}
+					if (buffer_da_mapped(bh))
+						clear_buffer_da_mapped(bh);
 					if (buffer_unwritten(bh) ||
 					    buffer_mapped(bh))
 						BUG_ON(bh->b_blocknr != pblock);
@@ -1346,12 +1424,15 @@ static void ext4_print_free_blocks(struct inode *inode)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	printk(KERN_CRIT "Total free blocks count %lld\n",
-	       ext4_count_free_blocks(inode->i_sb));
+	       EXT4_C2B(EXT4_SB(inode->i_sb),
+			ext4_count_free_clusters(inode->i_sb)));
 	printk(KERN_CRIT "Free/Dirty block details\n");
 	printk(KERN_CRIT "free_blocks=%lld\n",
-	       (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+		percpu_counter_sum(&sbi->s_freeclusters_counter)));
 	printk(KERN_CRIT "dirty_blocks=%lld\n",
-	       (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+		percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
 	printk(KERN_CRIT "Block reservation details\n");
 	printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
 	       EXT4_I(inode)->i_reserved_data_blocks);
@@ -1430,8 +1511,7 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
 		if (err == -EAGAIN)
 			goto submit_io;
 
-		if (err == -ENOSPC &&
-		    ext4_count_free_blocks(sb)) {
+		if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
 			mpd->retval = err;
 			goto submit_io;
 		}
@@ -1471,13 +1551,15 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
 
 		for (i = 0; i < map.m_len; i++)
 			unmap_underlying_metadata(bdev, map.m_pblk + i);
-	}
 
-	if (ext4_should_order_data(mpd->inode)) {
-		err = ext4_jbd2_file_inode(handle, mpd->inode);
-		if (err)
-			/* This only happens if the journal is aborted */
-			return;
+		if (ext4_should_order_data(mpd->inode)) {
+			err = ext4_jbd2_file_inode(handle, mpd->inode);
+			if (err) {
+				/* Only if the journal is aborted */
+				mpd->retval = err;
+				goto submit_io;
+			}
+		}
 	}
 
 	/*
@@ -1583,6 +1665,66 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 	return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
 }
 
+/*
+ * This function is grabs code from the very beginning of
+ * ext4_map_blocks, but assumes that the caller is from delayed write
+ * time. This function looks up the requested blocks and sets the
+ * buffer delay bit under the protection of i_data_sem.
+ */
+static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+			      struct ext4_map_blocks *map,
+			      struct buffer_head *bh)
+{
+	int retval;
+	sector_t invalid_block = ~((sector_t) 0xffff);
+
+	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+		invalid_block = ~0;
+
+	map->m_flags = 0;
+	ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
+		  "logical block %lu\n", inode->i_ino, map->m_len,
+		  (unsigned long) map->m_lblk);
+	/*
+	 * Try to see if we can get the block without requesting a new
+	 * file system block.
+	 */
+	down_read((&EXT4_I(inode)->i_data_sem));
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+	else
+		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+
+	if (retval == 0) {
+		/*
+		 * XXX: __block_prepare_write() unmaps passed block,
+		 * is it OK?
+		 */
+		/* If the block was allocated from previously allocated cluster,
+		 * then we dont need to reserve it again. */
+		if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+			retval = ext4_da_reserve_space(inode, iblock);
+			if (retval)
+				/* not enough space to reserve */
+				goto out_unlock;
+		}
+
+		/* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
+		 * and it should not appear on the bh->b_state.
+		 */
+		map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+
+		map_bh(bh, inode->i_sb, invalid_block);
+		set_buffer_new(bh);
+		set_buffer_delay(bh);
+	}
+
+out_unlock:
+	up_read((&EXT4_I(inode)->i_data_sem));
+
+	return retval;
+}
+
 /*
  * This is a special get_blocks_t callback which is used by
  * ext4_da_write_begin().  It will either return mapped block or
@@ -1600,10 +1742,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 {
 	struct ext4_map_blocks map;
 	int ret = 0;
-	sector_t invalid_block = ~((sector_t) 0xffff);
-
-	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
-		invalid_block = ~0;
 
 	BUG_ON(create == 0);
 	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
@@ -1616,25 +1754,9 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_map_blocks(NULL, inode, &map, 0);
-	if (ret < 0)
+	ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+	if (ret <= 0)
 		return ret;
-	if (ret == 0) {
-		if (buffer_delay(bh))
-			return 0; /* Not sure this could or should happen */
-		/*
-		 * XXX: __block_write_begin() unmaps passed block, is it OK?
-		 */
-		ret = ext4_da_reserve_space(inode, iblock);
-		if (ret)
-			/* not enough space to reserve */
-			return ret;
-
-		map_bh(bh, inode->i_sb, invalid_block);
-		set_buffer_new(bh);
-		set_buffer_delay(bh);
-		return 0;
-	}
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
 	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
@@ -2050,6 +2172,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 	pgoff_t done_index = 0;
 	pgoff_t end;
+	struct blk_plug plug;
 
 	trace_ext4_da_writepages(inode, wbc);
 
@@ -2128,6 +2251,7 @@ retry:
 	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 
+	blk_start_plug(&plug);
 	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
@@ -2178,11 +2302,12 @@ retry:
 			ret = 0;
 		} else if (ret == MPAGE_DA_EXTENT_TAIL) {
 			/*
-			 * got one extent now try with
-			 * rest of the pages
+			 * Got one extent now try with rest of the pages.
+			 * If mpd.retval is set -EIO, journal is aborted.
+			 * So we don't need to write any more.
 			 */
 			pages_written += mpd.pages_written;
-			ret = 0;
+			ret = mpd.retval;
 			io_done = 1;
 		} else if (wbc->nr_to_write)
 			/*
@@ -2192,6 +2317,7 @@ retry:
 			 */
 			break;
 	}
+	blk_finish_plug(&plug);
 	if (!io_done && !cycled) {
 		cycled = 1;
 		index = 0;
@@ -2230,10 +2356,11 @@ static int ext4_nonda_switch(struct super_block *sb)
 	 * Delalloc need an accurate free block accounting. So switch
 	 * to non delalloc when we are near to error range.
 	 */
-	free_blocks  = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
-	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+	free_blocks  = EXT4_C2B(sbi,
+		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
 	if (2 * free_blocks < 3 * dirty_blocks ||
-		free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+		free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
 		/*
 		 * free block count is less than 150% of dirty blocks
 		 * or free blocks is less than watermark
@@ -2259,6 +2386,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	struct inode *inode = mapping->host;
 	handle_t *handle;
+	loff_t page_len;
 
 	index = pos >> PAGE_CACHE_SHIFT;
 
@@ -2305,6 +2433,13 @@ retry:
 		 */
 		if (pos + len > inode->i_size)
 			ext4_truncate_failed_write(inode);
+	} else {
+		page_len = pos & (PAGE_CACHE_SIZE - 1);
+		if (page_len > 0) {
+			ret = ext4_discard_partial_page_buffers_no_lock(handle,
+				inode, page, pos - page_len, page_len,
+				EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+		}
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2347,6 +2482,7 @@ static int ext4_da_write_end(struct file *file,
 	loff_t new_i_size;
 	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
+	loff_t page_len;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
 		if (ext4_should_order_data(inode)) {
@@ -2395,6 +2531,16 @@ static int ext4_da_write_end(struct file *file,
 	}
 	ret2 = generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
+
+	page_len = PAGE_CACHE_SIZE -
+			((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
+
+	if (page_len > 0) {
+		ret = ext4_discard_partial_page_buffers_no_lock(handle,
+			inode, page, pos + copied - 1, page_len,
+			EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+	}
+
 	copied = ret2;
 	if (ret2 < 0)
 		ret = ret2;
@@ -2689,10 +2835,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
 	 * but being more careful is always safe for the future change.
 	 */
 	inode = io_end->inode;
-	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		io_end->flag |= EXT4_IO_END_UNWRITTEN;
-		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
-	}
+	ext4_set_io_unwritten_flag(inode, io_end);
 
 	/* Add the io_end to per-inode completed io list*/
 	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
@@ -2858,6 +3001,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
+	/*
+	 * If we are doing data journalling we don't support O_DIRECT
+	 */
+	if (ext4_should_journal_data(inode))
+		return 0;
+
 	trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
@@ -2927,6 +3076,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.bmap			= ext4_bmap,
 	.invalidatepage		= ext4_invalidatepage,
 	.releasepage		= ext4_releasepage,
+	.direct_IO		= ext4_direct_IO,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 };
@@ -2963,6 +3113,227 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
 }
 
+
+/*
+ * ext4_discard_partial_page_buffers()
+ * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
+ * This function finds and locks the page containing the offset
+ * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
+ * Calling functions that already have the page locked should call
+ * ext4_discard_partial_page_buffers_no_lock directly.
+ */
+int ext4_discard_partial_page_buffers(handle_t *handle,
+		struct address_space *mapping, loff_t from,
+		loff_t length, int flags)
+{
+	struct inode *inode = mapping->host;
+	struct page *page;
+	int err = 0;
+
+	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+				   mapping_gfp_mask(mapping) & ~__GFP_FS);
+	if (!page)
+		return -ENOMEM;
+
+	err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
+		from, length, flags);
+
+	unlock_page(page);
+	page_cache_release(page);
+	return err;
+}
+
+/*
+ * ext4_discard_partial_page_buffers_no_lock()
+ * Zeros a page range of length 'length' starting from offset 'from'.
+ * Buffer heads that correspond to the block aligned regions of the
+ * zeroed range will be unmapped.  Unblock aligned regions
+ * will have the corresponding buffer head mapped if needed so that
+ * that region of the page can be updated with the partial zero out.
+ *
+ * This function assumes that the page has already been  locked.  The
+ * The range to be discarded must be contained with in the given page.
+ * If the specified range exceeds the end of the page it will be shortened
+ * to the end of the page that corresponds to 'from'.  This function is
+ * appropriate for updating a page and it buffer heads to be unmapped and
+ * zeroed for blocks that have been either released, or are going to be
+ * released.
+ *
+ * handle: The journal handle
+ * inode:  The files inode
+ * page:   A locked page that contains the offset "from"
+ * from:   The starting byte offset (from the begining of the file)
+ *         to begin discarding
+ * len:    The length of bytes to discard
+ * flags:  Optional flags that may be used:
+ *
+ *         EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
+ *         Only zero the regions of the page whose buffer heads
+ *         have already been unmapped.  This flag is appropriate
+ *         for updateing the contents of a page whose blocks may
+ *         have already been released, and we only want to zero
+ *         out the regions that correspond to those released blocks.
+ *
+ * Returns zero on sucess or negative on failure.
+ */
+int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+		struct inode *inode, struct page *page, loff_t from,
+		loff_t length, int flags)
+{
+	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned int offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned int blocksize, max, pos;
+	ext4_lblk_t iblock;
+	struct buffer_head *bh;
+	int err = 0;
+
+	blocksize = inode->i_sb->s_blocksize;
+	max = PAGE_CACHE_SIZE - offset;
+
+	if (index != page->index)
+		return -EINVAL;
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the page
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+	if (!page_has_buffers(page)) {
+		/*
+		 * If the range to be discarded covers a partial block
+		 * we need to get the page buffers.  This is because
+		 * partial blocks cannot be released and the page needs
+		 * to be updated with the contents of the block before
+		 * we write the zeros on top of it.
+		 */
+		if ((from & (blocksize - 1)) ||
+		    ((from + length) & (blocksize - 1))) {
+			create_empty_buffers(page, blocksize, 0);
+		} else {
+			/*
+			 * If there are no partial blocks,
+			 * there is nothing to update,
+			 * so we can return now
+			 */
+			return 0;
+		}
+	}
+
+	/* Find the buffer that contains "offset" */
+	bh = page_buffers(page);
+	pos = blocksize;
+	while (offset >= pos) {
+		bh = bh->b_this_page;
+		iblock++;
+		pos += blocksize;
+	}
+
+	pos = offset;
+	while (pos < offset + length) {
+		unsigned int end_of_block, range_to_discard;
+
+		err = 0;
+
+		/* The length of space left to zero and unmap */
+		range_to_discard = offset + length - pos;
+
+		/* The length of space until the end of the block */
+		end_of_block = blocksize - (pos & (blocksize-1));
+
+		/*
+		 * Do not unmap or zero past end of block
+		 * for this buffer head
+		 */
+		if (range_to_discard > end_of_block)
+			range_to_discard = end_of_block;
+
+
+		/*
+		 * Skip this buffer head if we are only zeroing unampped
+		 * regions of the page
+		 */
+		if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
+			buffer_mapped(bh))
+				goto next;
+
+		/* If the range is block aligned, unmap */
+		if (range_to_discard == blocksize) {
+			clear_buffer_dirty(bh);
+			bh->b_bdev = NULL;
+			clear_buffer_mapped(bh);
+			clear_buffer_req(bh);
+			clear_buffer_new(bh);
+			clear_buffer_delay(bh);
+			clear_buffer_unwritten(bh);
+			clear_buffer_uptodate(bh);
+			zero_user(page, pos, range_to_discard);
+			BUFFER_TRACE(bh, "Buffer discarded");
+			goto next;
+		}
+
+		/*
+		 * If this block is not completely contained in the range
+		 * to be discarded, then it is not going to be released. Because
+		 * we need to keep this block, we need to make sure this part
+		 * of the page is uptodate before we modify it by writeing
+		 * partial zeros on it.
+		 */
+		if (!buffer_mapped(bh)) {
+			/*
+			 * Buffer head must be mapped before we can read
+			 * from the block
+			 */
+			BUFFER_TRACE(bh, "unmapped");
+			ext4_get_block(inode, iblock, bh, 0);
+			/* unmapped? It's a hole - nothing to do */
+			if (!buffer_mapped(bh)) {
+				BUFFER_TRACE(bh, "still unmapped");
+				goto next;
+			}
+		}
+
+		/* Ok, it's mapped. Make sure it's up-to-date */
+		if (PageUptodate(page))
+			set_buffer_uptodate(bh);
+
+		if (!buffer_uptodate(bh)) {
+			err = -EIO;
+			ll_rw_block(READ, 1, &bh);
+			wait_on_buffer(bh);
+			/* Uhhuh. Read error. Complain and punt.*/
+			if (!buffer_uptodate(bh))
+				goto next;
+		}
+
+		if (ext4_should_journal_data(inode)) {
+			BUFFER_TRACE(bh, "get write access");
+			err = ext4_journal_get_write_access(handle, bh);
+			if (err)
+				goto next;
+		}
+
+		zero_user(page, pos, range_to_discard);
+
+		err = 0;
+		if (ext4_should_journal_data(inode)) {
+			err = ext4_handle_dirty_metadata(handle, inode, bh);
+		} else
+			mark_buffer_dirty(bh);
+
+		BUFFER_TRACE(bh, "Partial buffer zeroed");
+next:
+		bh = bh->b_this_page;
+		iblock++;
+		pos += range_to_discard;
+	}
+
+	return err;
+}
+
 /*
  * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
@@ -3005,7 +3376,7 @@ int ext4_block_zero_page_range(handle_t *handle,
 	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
 				   mapping_gfp_mask(mapping) & ~__GFP_FS);
 	if (!page)
-		return -EINVAL;
+		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
 	max = blocksize - (offset & (blocksize - 1));
@@ -3074,11 +3445,8 @@ int ext4_block_zero_page_range(handle_t *handle,
 	err = 0;
 	if (ext4_should_journal_data(inode)) {
 		err = ext4_handle_dirty_metadata(handle, inode, bh);
-	} else {
-		if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
-			err = ext4_jbd2_file_inode(handle, inode);
+	} else
 		mark_buffer_dirty(bh);
-	}
 
 unlock:
 	unlock_page(page);
@@ -3119,6 +3487,11 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 		return -ENOTSUPP;
 	}
 
+	if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+		/* TODO: Add support for bigalloc file systems */
+		return -ENOTSUPP;
+	}
+
 	return ext4_ext_punch_hole(file, offset, length);
 }
 
@@ -4420,6 +4793,7 @@ retry_alloc:
 			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
 			unlock_page(page);
 			ret = VM_FAULT_SIGBUS;
+			ext4_journal_stop(handle);
 			goto out;
 		}
 		ext4_set_inode_state(inode, EXT4_STATE_JDATA);

fs/ext4/ioctl.c

@@ -21,6 +21,7 @@
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
 
@@ -173,33 +174,8 @@ setversion_out:
 		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
-#ifdef CONFIG_JBD2_DEBUG
-	case EXT4_IOC_WAIT_FOR_READONLY:
-		/*
-		 * This is racy - by the time we're woken up and running,
-		 * the superblock could be released.  And the module could
-		 * have been unloaded.  So sue me.
-		 *
-		 * Returns 1 if it slept, else zero.
-		 */
-		{
-			struct super_block *sb = inode->i_sb;
-			DECLARE_WAITQUEUE(wait, current);
-			int ret = 0;
-
-			set_current_state(TASK_INTERRUPTIBLE);
-			add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
-			if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
-				schedule();
-				ret = 1;
-			}
-			remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
-			return ret;
-		}
-#endif
 	case EXT4_IOC_GROUP_EXTEND: {
 		ext4_fsblk_t n_blocks_count;
-		struct super_block *sb = inode->i_sb;
 		int err, err2=0;
 
 		err = ext4_resize_begin(sb);
@@ -209,6 +185,13 @@ setversion_out:
 		if (get_user(n_blocks_count, (__u32 __user *)arg))
 			return -EFAULT;
 
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online resizing not supported with bigalloc");
+			return -EOPNOTSUPP;
+		}
+
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			return err;
@@ -250,6 +233,13 @@ setversion_out:
 			goto mext_out;
 		}
 
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with bigalloc");
+			return -EOPNOTSUPP;
+		}
+
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			goto mext_out;
@@ -270,7 +260,6 @@ mext_out:
 
 	case EXT4_IOC_GROUP_ADD: {
 		struct ext4_new_group_data input;
-		struct super_block *sb = inode->i_sb;
 		int err, err2=0;
 
 		err = ext4_resize_begin(sb);
@@ -281,6 +270,13 @@ mext_out:
 				sizeof(input)))
 			return -EFAULT;
 
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online resizing not supported with bigalloc");
+			return -EOPNOTSUPP;
+		}
+
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			return err;
@@ -337,7 +333,6 @@ mext_out:
 
 	case FITRIM:
 	{
-		struct super_block *sb = inode->i_sb;
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		int ret = 0;
@@ -348,7 +343,14 @@ mext_out:
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
 
-		if (copy_from_user(&range, (struct fstrim_range *)arg,
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+			ext4_msg(sb, KERN_ERR,
+				 "FITRIM not supported with bigalloc");
+			return -EOPNOTSUPP;
+		}
+
+		if (copy_from_user(&range, (struct fstrim_range __user *)arg,
 		    sizeof(range)))
 			return -EFAULT;
 
@@ -358,7 +360,7 @@ mext_out:
 		if (ret < 0)
 			return ret;
 
-		if (copy_to_user((struct fstrim_range *)arg, &range,
+		if (copy_to_user((struct fstrim_range __user *)arg, &range,
 		    sizeof(range)))
 			return -EFAULT;
 
@@ -396,11 +398,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC32_SETVERSION_OLD:
 		cmd = EXT4_IOC_SETVERSION_OLD;
 		break;
-#ifdef CONFIG_JBD2_DEBUG
-	case EXT4_IOC32_WAIT_FOR_READONLY:
-		cmd = EXT4_IOC_WAIT_FOR_READONLY;
-		break;
-#endif
 	case EXT4_IOC32_GETRSVSZ:
 		cmd = EXT4_IOC_GETRSVSZ;
 		break;

fs/ext4/mballoc.c

@@ -70,8 +70,8 @@
  *
  * pa_lstart -> the logical start block for this prealloc space
  * pa_pstart -> the physical start block for this prealloc space
- * pa_len    -> length for this prealloc space
- * pa_free   ->  free space available in this prealloc space
+ * pa_len    -> length for this prealloc space (in clusters)
+ * pa_free   ->  free space available in this prealloc space (in clusters)
  *
  * The inode preallocation space is used looking at the _logical_ start
  * block. If only the logical file block falls within the range of prealloc
@@ -126,7 +126,8 @@
  * list. In case of inode preallocation we follow a list of heuristics
  * based on file size. This can be found in ext4_mb_normalize_request. If
  * we are doing a group prealloc we try to normalize the request to
- * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is
+ * sbi->s_mb_group_prealloc.  The default value of s_mb_group_prealloc is
+ * dependent on the cluster size; for non-bigalloc file systems, it is
  * 512 blocks. This can be tuned via
  * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in
  * terms of number of blocks. If we have mounted the file system with -O
@@ -459,7 +460,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 			ext4_fsblk_t blocknr;
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
-			blocknr += first + i;
+			blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
@@ -580,7 +581,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 				continue;
 			}
 
-			/* both bits in buddy2 must be 0 */
+			/* both bits in buddy2 must be 1 */
 			MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2));
 			MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2));
 
@@ -653,7 +654,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
 	ext4_grpblk_t chunk;
 	unsigned short border;
 
-	BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
+	BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
 
 	border = 2 << sb->s_blocksize_bits;
 
@@ -705,7 +706,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 				void *buddy, void *bitmap, ext4_group_t group)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
-	ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+	ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
 	ext4_grpblk_t i = 0;
 	ext4_grpblk_t first;
 	ext4_grpblk_t len;
@@ -734,7 +735,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 
 	if (free != grp->bb_free) {
 		ext4_grp_locked_error(sb, group, 0, 0,
-				      "%u blocks in bitmap, %u in gd",
+				      "%u clusters in bitmap, %u in gd",
 				      free, grp->bb_free);
 		/*
 		 * If we intent to continue, we consider group descritor
@@ -1339,7 +1340,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 			ext4_fsblk_t blocknr;
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
-			blocknr += block;
+			blocknr += EXT4_C2B(EXT4_SB(sb), block);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
@@ -1390,7 +1391,6 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
 {
 	int next = block;
 	int max;
-	int ord;
 	void *buddy;
 
 	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1432,9 +1432,8 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
 		if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
 			break;
 
-		ord = mb_find_order_for_block(e4b, next);
+		order = mb_find_order_for_block(e4b, next);
 
-		order = ord;
 		block = next >> order;
 		ex->fe_len += 1 << order;
 	}
@@ -1624,8 +1623,8 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
 	struct ext4_free_extent *gex = &ac->ac_g_ex;
 
 	BUG_ON(ex->fe_len <= 0);
-	BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
-	BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+	BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
 	BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
 
 	ac->ac_found++;
@@ -1823,15 +1822,15 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 
 	while (free && ac->ac_status == AC_STATUS_CONTINUE) {
 		i = mb_find_next_zero_bit(bitmap,
-						EXT4_BLOCKS_PER_GROUP(sb), i);
-		if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
+						EXT4_CLUSTERS_PER_GROUP(sb), i);
+		if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) {
 			/*
 			 * IF we have corrupt bitmap, we won't find any
 			 * free blocks even though group info says we
 			 * we have free blocks
 			 */
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
-					"%d free blocks as per "
+					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
 			break;
@@ -1841,7 +1840,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		BUG_ON(ex.fe_len <= 0);
 		if (free < ex.fe_len) {
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
-					"%d free blocks as per "
+					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
 			/*
@@ -1887,7 +1886,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
 	do_div(a, sbi->s_stripe);
 	i = (a * sbi->s_stripe) - first_group_block;
 
-	while (i < EXT4_BLOCKS_PER_GROUP(sb)) {
+	while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
 		if (!mb_test_bit(i, bitmap)) {
 			max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
 			if (max >= sbi->s_stripe) {
@@ -2252,10 +2251,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 	 */
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		meta_group_info[i]->bb_free =
-			ext4_free_blocks_after_init(sb, group, desc);
+			ext4_free_clusters_after_init(sb, group, desc);
 	} else {
 		meta_group_info[i]->bb_free =
-			ext4_free_blks_count(sb, desc);
+			ext4_free_group_clusters(sb, desc);
 	}
 
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
@@ -2473,7 +2472,20 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	sbi->s_mb_stats = MB_DEFAULT_STATS;
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
-	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
+	/*
+	 * The default group preallocation is 512, which for 4k block
+	 * sizes translates to 2 megabytes.  However for bigalloc file
+	 * systems, this is probably too big (i.e, if the cluster size
+	 * is 1 megabyte, then group preallocation size becomes half a
+	 * gigabyte!).  As a default, we will keep a two megabyte
+	 * group pralloc size for cluster sizes up to 64k, and after
+	 * that, we will force a minimum group preallocation size of
+	 * 32 clusters.  This translates to 8 megs when the cluster
+	 * size is 256k, and 32 megs when the cluster size is 1 meg,
+	 * which seems reasonable as a default.
+	 */
+	sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >>
+				       sbi->s_cluster_bits, 32);
 	/*
 	 * If there is a s_stripe > 1, then we set the s_mb_group_prealloc
 	 * to the lowest multiple of s_stripe which is bigger than
@@ -2490,7 +2502,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
 	if (sbi->s_locality_groups == NULL) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_free_groupinfo_slab;
 	}
 	for_each_possible_cpu(i) {
 		struct ext4_locality_group *lg;
@@ -2503,9 +2515,8 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 
 	/* init file for buddy data */
 	ret = ext4_mb_init_backend(sb);
-	if (ret != 0) {
-		goto out;
-	}
+	if (ret != 0)
+		goto out_free_locality_groups;
 
 	if (sbi->s_proc)
 		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
@@ -2513,11 +2524,19 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 
 	if (sbi->s_journal)
 		sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
+	return 0;
+
+out_free_locality_groups:
+	free_percpu(sbi->s_locality_groups);
+	sbi->s_locality_groups = NULL;
+out_free_groupinfo_slab:
+	ext4_groupinfo_destroy_slabs();
 out:
-	if (ret) {
-		kfree(sbi->s_mb_offsets);
-		kfree(sbi->s_mb_maxs);
-	}
+	kfree(sbi->s_mb_offsets);
+	sbi->s_mb_offsets = NULL;
+	kfree(sbi->s_mb_maxs);
+	sbi->s_mb_maxs = NULL;
 	return ret;
 }
 
@@ -2602,11 +2621,13 @@ int ext4_mb_release(struct super_block *sb)
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-		ext4_group_t block_group, ext4_grpblk_t block, int count)
+		ext4_group_t block_group, ext4_grpblk_t cluster, int count)
 {
 	ext4_fsblk_t discard_block;
 
-	discard_block = block + ext4_group_first_block_no(sb, block_group);
+	discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) +
+			 ext4_group_first_block_no(sb, block_group));
+	count = EXT4_C2B(EXT4_SB(sb), count);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
 	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
@@ -2633,7 +2654,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 
 		if (test_opt(sb, DISCARD))
 			ext4_issue_discard(sb, entry->group,
-					   entry->start_blk, entry->count);
+					   entry->start_cluster, entry->count);
 
 		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
@@ -2646,7 +2667,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 		ext4_lock_group(sb, entry->group);
 		/* Take it out of per group rb tree */
 		rb_erase(&entry->node, &(db->bb_free_root));
-		mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+		mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count);
 
 		/*
 		 * Clear the trimmed flag for the group so that the next
@@ -2752,7 +2773,7 @@ void ext4_exit_mballoc(void)
  */
 static noinline_for_stack int
 ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
-				handle_t *handle, unsigned int reserv_blks)
+				handle_t *handle, unsigned int reserv_clstrs)
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct ext4_group_desc *gdp;
@@ -2783,7 +2804,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		goto out_err;
 
 	ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
-			ext4_free_blks_count(sb, gdp));
+			ext4_free_group_clusters(sb, gdp));
 
 	err = ext4_journal_get_write_access(handle, gdp_bh);
 	if (err)
@@ -2791,7 +2812,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 
 	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 
-	len = ac->ac_b_ex.fe_len;
+	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
 	if (!ext4_data_block_valid(sbi, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata\n", block, block+len);
@@ -2823,28 +2844,29 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		      ac->ac_b_ex.fe_len);
 	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
-		ext4_free_blks_set(sb, gdp,
-					ext4_free_blocks_after_init(sb,
-					ac->ac_b_ex.fe_group, gdp));
+		ext4_free_group_clusters_set(sb, gdp,
+					     ext4_free_clusters_after_init(sb,
+						ac->ac_b_ex.fe_group, gdp));
 	}
-	len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
-	ext4_free_blks_set(sb, gdp, len);
+	len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
+	ext4_free_group_clusters_set(sb, gdp, len);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
 
 	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
-	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
+	percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len);
 	/*
 	 * Now reduce the dirty block count also. Should not go negative
 	 */
 	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
 		/* release all the reserved blocks if non delalloc */
-		percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+		percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+				   reserv_clstrs);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
 		atomic_sub(ac->ac_b_ex.fe_len,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+			   &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -2886,6 +2908,7 @@ static noinline_for_stack void
 ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 				struct ext4_allocation_request *ar)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	int bsbits, max;
 	ext4_lblk_t end;
 	loff_t size, orig_size, start_off;
@@ -2916,7 +2939,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 
 	/* first, let's learn actual file size
 	 * given current request is allocated */
-	size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+	size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
 	size = size << bsbits;
 	if (size < i_size_read(ac->ac_inode))
 		size = i_size_read(ac->ac_inode);
@@ -2988,7 +3011,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 			continue;
 		}
 
-		pa_end = pa->pa_lstart + pa->pa_len;
+		pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+						  pa->pa_len);
 
 		/* PA must not overlap original request */
 		BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
@@ -3018,9 +3042,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	rcu_read_lock();
 	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
 		ext4_lblk_t pa_end;
+
 		spin_lock(&pa->pa_lock);
 		if (pa->pa_deleted == 0) {
-			pa_end = pa->pa_lstart + pa->pa_len;
+			pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+							  pa->pa_len);
 			BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
 		}
 		spin_unlock(&pa->pa_lock);
@@ -3036,14 +3062,14 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
 	/* XXX: is it better to align blocks WRT to logical
 	 * placement or satisfy big request as is */
 	ac->ac_g_ex.fe_logical = start;
-	ac->ac_g_ex.fe_len = size;
+	ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
 
 	/* define goal start in order to merge */
 	if (ar->pright && (ar->lright == (start + size))) {
@@ -3112,14 +3138,16 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 				struct ext4_prealloc_space *pa)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	ext4_fsblk_t start;
 	ext4_fsblk_t end;
 	int len;
 
 	/* found preallocated blocks, use them */
 	start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart);
-	end = min(pa->pa_pstart + pa->pa_len, start + ac->ac_o_ex.fe_len);
-	len = end - start;
+	end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len),
+		  start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len));
+	len = EXT4_NUM_B2C(sbi, end - start);
 	ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group,
 					&ac->ac_b_ex.fe_start);
 	ac->ac_b_ex.fe_len = len;
@@ -3127,7 +3155,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 	ac->ac_pa = pa;
 
 	BUG_ON(start < pa->pa_pstart);
-	BUG_ON(start + len > pa->pa_pstart + pa->pa_len);
+	BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
 	BUG_ON(pa->pa_free < len);
 	pa->pa_free -= len;
 
@@ -3193,6 +3221,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
 static noinline_for_stack int
 ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	int order, i;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 	struct ext4_locality_group *lg;
@@ -3210,12 +3239,14 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		/* all fields in this condition don't change,
 		 * so we can skip locking for them */
 		if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
-			ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
+		    ac->ac_o_ex.fe_logical >= (pa->pa_lstart +
+					       EXT4_C2B(sbi, pa->pa_len)))
 			continue;
 
 		/* non-extent files can't have physical blocks past 2^32 */
 		if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
-			pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+		    (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) >
+		     EXT4_MAX_BLOCK_FILE_PHYS))
 			continue;
 
 		/* found preallocated blocks, use them */
@@ -3291,7 +3322,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 
 	while (n) {
 		entry = rb_entry(n, struct ext4_free_data, node);
-		ext4_set_bits(bitmap, entry->start_blk, entry->count);
+		ext4_set_bits(bitmap, entry->start_cluster, entry->count);
 		n = rb_next(n);
 	}
 	return;
@@ -3312,7 +3343,6 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 	ext4_group_t groupnr;
 	ext4_grpblk_t start;
 	int preallocated = 0;
-	int count = 0;
 	int len;
 
 	/* all form of preallocation discards first load group,
@@ -3335,7 +3365,6 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 		BUG_ON(groupnr != group);
 		ext4_set_bits(bitmap, start, len);
 		preallocated += len;
-		count++;
 	}
 	mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
 }
@@ -3412,6 +3441,7 @@ static noinline_for_stack int
 ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 {
 	struct super_block *sb = ac->ac_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_prealloc_space *pa;
 	struct ext4_group_info *grp;
 	struct ext4_inode_info *ei;
@@ -3443,16 +3473,18 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
 
 		/* also, we should cover whole original request */
-		wins = ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len;
+		wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
 
 		/* the smallest one defines real window */
 		win = min(winl, wins);
 
-		offs = ac->ac_o_ex.fe_logical % ac->ac_b_ex.fe_len;
+		offs = ac->ac_o_ex.fe_logical %
+			EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
 		if (offs && offs < win)
 			win = offs;
 
-		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - win;
+		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
+			EXT4_B2C(sbi, win);
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
 	}
@@ -3477,7 +3509,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	trace_ext4_mb_new_inode_pa(ac, pa);
 
 	ext4_mb_use_inode_pa(ac, pa);
-	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
+	atomic_add(pa->pa_free, &sbi->s_mb_preallocated);
 
 	ei = EXT4_I(ac->ac_inode);
 	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
@@ -3592,7 +3624,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
-	grp_blk_start = pa->pa_pstart - bit;
+	grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit);
 	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
 	end = bit + pa->pa_len;
 
@@ -3607,7 +3639,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		free += next - bit;
 
 		trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
-		trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit,
+		trace_ext4_mb_release_inode_pa(pa, (grp_blk_start +
+						    EXT4_C2B(sbi, bit)),
 					       next - bit);
 		mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
 		bit = next + 1;
@@ -3690,7 +3723,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 	}
 
 	if (needed == 0)
-		needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
+		needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1;
 
 	INIT_LIST_HEAD(&list);
 repeat:
@@ -3958,7 +3991,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
 		return;
 
-	size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+	size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
 		>> bsbits;
 
@@ -3969,6 +4002,11 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 		return;
 	}
 
+	if (sbi->s_mb_group_prealloc <= 0) {
+		ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+		return;
+	}
+
 	/* don't use group allocation for large files */
 	size = max(size, isize);
 	if (size > sbi->s_mb_stream_request) {
@@ -4007,8 +4045,8 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	len = ar->len;
 
 	/* just a dirty hack to filter too big requests  */
-	if (len >= EXT4_BLOCKS_PER_GROUP(sb) - 10)
-		len = EXT4_BLOCKS_PER_GROUP(sb) - 10;
+	if (len >= EXT4_CLUSTERS_PER_GROUP(sb) - 10)
+		len = EXT4_CLUSTERS_PER_GROUP(sb) - 10;
 
 	/* start searching from the goal */
 	goal = ar->goal;
@@ -4019,18 +4057,15 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 
 	/* set up allocation goals */
 	memset(ac, 0, sizeof(struct ext4_allocation_context));
-	ac->ac_b_ex.fe_logical = ar->logical;
+	ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
 	ac->ac_status = AC_STATUS_CONTINUE;
 	ac->ac_sb = sb;
 	ac->ac_inode = ar->inode;
-	ac->ac_o_ex.fe_logical = ar->logical;
+	ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical;
 	ac->ac_o_ex.fe_group = group;
 	ac->ac_o_ex.fe_start = block;
 	ac->ac_o_ex.fe_len = len;
-	ac->ac_g_ex.fe_logical = ar->logical;
-	ac->ac_g_ex.fe_group = group;
-	ac->ac_g_ex.fe_start = block;
-	ac->ac_g_ex.fe_len = len;
+	ac->ac_g_ex = ac->ac_o_ex;
 	ac->ac_flags = ar->flags;
 
 	/* we have to define context: we'll we work with a file or
@@ -4182,13 +4217,14 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
  */
 static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
 	if (pa) {
 		if (pa->pa_type == MB_GROUP_PA) {
 			/* see comment in ext4_mb_use_group_pa() */
 			spin_lock(&pa->pa_lock);
-			pa->pa_pstart += ac->ac_b_ex.fe_len;
-			pa->pa_lstart += ac->ac_b_ex.fe_len;
+			pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+			pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
 			pa->pa_free -= ac->ac_b_ex.fe_len;
 			pa->pa_len -= ac->ac_b_ex.fe_len;
 			spin_unlock(&pa->pa_lock);
@@ -4249,13 +4285,17 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	struct super_block *sb;
 	ext4_fsblk_t block = 0;
 	unsigned int inquota = 0;
-	unsigned int reserv_blks = 0;
+	unsigned int reserv_clstrs = 0;
 
 	sb = ar->inode->i_sb;
 	sbi = EXT4_SB(sb);
 
 	trace_ext4_request_blocks(ar);
 
+	/* Allow to use superuser reservation for quota file */
+	if (IS_NOQUOTA(ar->inode))
+		ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
+
 	/*
 	 * For delayed allocation, we could skip the ENOSPC and
 	 * EDQUOT check, as blocks and quotas have been already
@@ -4269,7 +4309,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 		 * and verify allocation doesn't exceed the quota limits.
 		 */
 		while (ar->len &&
-			ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+			ext4_claim_free_clusters(sbi, ar->len, ar->flags)) {
 
 			/* let others to free the space */
 			yield();
@@ -4279,12 +4319,14 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 			*errp = -ENOSPC;
 			return 0;
 		}
-		reserv_blks = ar->len;
+		reserv_clstrs = ar->len;
 		if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
-			dquot_alloc_block_nofail(ar->inode, ar->len);
+			dquot_alloc_block_nofail(ar->inode,
+						 EXT4_C2B(sbi, ar->len));
 		} else {
 			while (ar->len &&
-				dquot_alloc_block(ar->inode, ar->len)) {
+				dquot_alloc_block(ar->inode,
+						  EXT4_C2B(sbi, ar->len))) {
 
 				ar->flags |= EXT4_MB_HINT_NOPREALLOC;
 				ar->len--;
@@ -4328,7 +4370,7 @@ repeat:
 			ext4_mb_new_preallocation(ac);
 	}
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
-		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
+		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
 		if (*errp == -EAGAIN) {
 			/*
 			 * drop the reference that we took
@@ -4364,13 +4406,13 @@ out:
 	if (ac)
 		kmem_cache_free(ext4_ac_cachep, ac);
 	if (inquota && ar->len < inquota)
-		dquot_free_block(ar->inode, inquota - ar->len);
+		dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
 	if (!ar->len) {
 		if (!ext4_test_inode_state(ar->inode,
 					   EXT4_STATE_DELALLOC_RESERVED))
 			/* release all the reserved blocks if non delalloc */
-			percpu_counter_sub(&sbi->s_dirtyblocks_counter,
-						reserv_blks);
+			percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+						reserv_clstrs);
 	}
 
 	trace_ext4_allocate_blocks(ar, (unsigned long long)block);
@@ -4388,7 +4430,7 @@ static int can_merge(struct ext4_free_data *entry1,
 {
 	if ((entry1->t_tid == entry2->t_tid) &&
 	    (entry1->group == entry2->group) &&
-	    ((entry1->start_blk + entry1->count) == entry2->start_blk))
+	    ((entry1->start_cluster + entry1->count) == entry2->start_cluster))
 		return 1;
 	return 0;
 }
@@ -4398,7 +4440,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		      struct ext4_free_data *new_entry)
 {
 	ext4_group_t group = e4b->bd_group;
-	ext4_grpblk_t block;
+	ext4_grpblk_t cluster;
 	struct ext4_free_data *entry;
 	struct ext4_group_info *db = e4b->bd_info;
 	struct super_block *sb = e4b->bd_sb;
@@ -4411,7 +4453,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	BUG_ON(e4b->bd_buddy_page == NULL);
 
 	new_node = &new_entry->node;
-	block = new_entry->start_blk;
+	cluster = new_entry->start_cluster;
 
 	if (!*n) {
 		/* first free block exent. We need to
@@ -4425,13 +4467,14 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	while (*n) {
 		parent = *n;
 		entry = rb_entry(parent, struct ext4_free_data, node);
-		if (block < entry->start_blk)
+		if (cluster < entry->start_cluster)
 			n = &(*n)->rb_left;
-		else if (block >= (entry->start_blk + entry->count))
+		else if (cluster >= (entry->start_cluster + entry->count))
 			n = &(*n)->rb_right;
 		else {
 			ext4_grp_locked_error(sb, group, 0,
-				ext4_group_first_block_no(sb, group) + block,
+				ext4_group_first_block_no(sb, group) +
+				EXT4_C2B(sbi, cluster),
 				"Block already on to-be-freed list");
 			return 0;
 		}
@@ -4445,7 +4488,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, node);
 		if (can_merge(entry, new_entry)) {
-			new_entry->start_blk = entry->start_blk;
+			new_entry->start_cluster = entry->start_cluster;
 			new_entry->count += entry->count;
 			rb_erase(node, &(db->bb_free_root));
 			spin_lock(&sbi->s_md_lock);
@@ -4496,6 +4539,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	ext4_group_t block_group;
 	struct ext4_sb_info *sbi;
 	struct ext4_buddy e4b;
+	unsigned int count_clusters;
 	int err = 0;
 	int ret;
 
@@ -4544,6 +4588,38 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	if (!ext4_should_writeback_data(inode))
 		flags |= EXT4_FREE_BLOCKS_METADATA;
 
+	/*
+	 * If the extent to be freed does not begin on a cluster
+	 * boundary, we need to deal with partial clusters at the
+	 * beginning and end of the extent.  Normally we will free
+	 * blocks at the beginning or the end unless we are explicitly
+	 * requested to avoid doing so.
+	 */
+	overflow = block & (sbi->s_cluster_ratio - 1);
+	if (overflow) {
+		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+			overflow = sbi->s_cluster_ratio - overflow;
+			block += overflow;
+			if (count > overflow)
+				count -= overflow;
+			else
+				return;
+		} else {
+			block -= overflow;
+			count += overflow;
+		}
+	}
+	overflow = count & (sbi->s_cluster_ratio - 1);
+	if (overflow) {
+		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+			if (count > overflow)
+				count -= overflow;
+			else
+				return;
+		} else
+			count += sbi->s_cluster_ratio - overflow;
+	}
+
 do_more:
 	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -4552,10 +4628,12 @@ do_more:
 	 * 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);
+	if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+		overflow = EXT4_C2B(sbi, bit) + count -
+			EXT4_BLOCKS_PER_GROUP(sb);
 		count -= overflow;
 	}
+	count_clusters = EXT4_B2C(sbi, count);
 	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
 	if (!bitmap_bh) {
 		err = -EIO;
@@ -4570,9 +4648,9 @@ do_more:
 	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
 	    in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
 	    in_range(block, ext4_inode_table(sb, gdp),
-		      EXT4_SB(sb)->s_itb_per_group) ||
+		     EXT4_SB(sb)->s_itb_per_group) ||
 	    in_range(block + count - 1, ext4_inode_table(sb, gdp),
-		      EXT4_SB(sb)->s_itb_per_group)) {
+		     EXT4_SB(sb)->s_itb_per_group)) {
 
 		ext4_error(sb, "Freeing blocks in system zone - "
 			   "Block = %llu, count = %lu", block, count);
@@ -4597,11 +4675,11 @@ do_more:
 #ifdef AGGRESSIVE_CHECK
 	{
 		int i;
-		for (i = 0; i < count; i++)
+		for (i = 0; i < count_clusters; i++)
 			BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
 	}
 #endif
-	trace_ext4_mballoc_free(sb, inode, block_group, bit, count);
+	trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
 
 	err = ext4_mb_load_buddy(sb, block_group, &e4b);
 	if (err)
@@ -4618,13 +4696,13 @@ do_more:
 			err = -ENOMEM;
 			goto error_return;
 		}
-		new_entry->start_blk = bit;
+		new_entry->start_cluster = bit;
 		new_entry->group  = block_group;
-		new_entry->count = count;
+		new_entry->count = count_clusters;
 		new_entry->t_tid = handle->h_transaction->t_tid;
 
 		ext4_lock_group(sb, block_group);
-		mb_clear_bits(bitmap_bh->b_data, bit, count);
+		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
 		ext4_mb_free_metadata(handle, &e4b, new_entry);
 	} else {
 		/* need to update group_info->bb_free and bitmap
@@ -4632,25 +4710,29 @@ do_more:
 		 * them with group lock_held
 		 */
 		ext4_lock_group(sb, block_group);
-		mb_clear_bits(bitmap_bh->b_data, bit, count);
-		mb_free_blocks(inode, &e4b, bit, count);
+		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
+		mb_free_blocks(inode, &e4b, bit, count_clusters);
 	}
 
-	ret = ext4_free_blks_count(sb, gdp) + count;
-	ext4_free_blks_set(sb, gdp, ret);
+	ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
+	ext4_free_group_clusters_set(sb, gdp, ret);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
 	ext4_unlock_group(sb, block_group);
-	percpu_counter_add(&sbi->s_freeblocks_counter, count);
+	percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(count_clusters,
+			   &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
 
 	freed += count;
 
+	if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+		dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+
 	/* We dirtied the bitmap block */
 	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -4669,8 +4751,6 @@ do_more:
 	}
 	ext4_mark_super_dirty(sb);
 error_return:
-	if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
-		dquot_free_block(inode, freed);
 	brelse(bitmap_bh);
 	ext4_std_error(sb, err);
 	return;
@@ -4778,16 +4858,17 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	ext4_lock_group(sb, block_group);
 	mb_clear_bits(bitmap_bh->b_data, bit, count);
 	mb_free_blocks(NULL, &e4b, bit, count);
-	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
-	ext4_free_blks_set(sb, desc, blk_free_count);
+	blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc);
+	ext4_free_group_clusters_set(sb, desc, blk_free_count);
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
 	ext4_unlock_group(sb, block_group);
-	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+	percpu_counter_add(&sbi->s_freeclusters_counter,
+			   EXT4_B2C(sbi, blocks_freed));
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(blocks_freed,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(EXT4_B2C(sbi, blocks_freed),
+			   &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
@@ -4948,7 +5029,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	struct ext4_group_info *grp;
 	ext4_group_t first_group, last_group;
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
-	ext4_grpblk_t cnt = 0, first_block, last_block;
+	ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
 	uint64_t start, len, minlen, trimmed = 0;
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
@@ -4958,7 +5039,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	len = range->len >> sb->s_blocksize_bits;
 	minlen = range->minlen >> sb->s_blocksize_bits;
 
-	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+	if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)))
 		return -EINVAL;
 	if (start + len <= first_data_blk)
 		goto out;
@@ -4969,11 +5050,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 	/* Determine first and last group to examine based on start and len */
 	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
-				     &first_group, &first_block);
+				     &first_group, &first_cluster);
 	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
-				     &last_group, &last_block);
+				     &last_group, &last_cluster);
 	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
-	last_block = EXT4_BLOCKS_PER_GROUP(sb);
+	last_cluster = EXT4_CLUSTERS_PER_GROUP(sb);
 
 	if (first_group > last_group)
 		return -EINVAL;
@@ -4993,20 +5074,20 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		 * change it for the last group in which case start +
 		 * len < EXT4_BLOCKS_PER_GROUP(sb).
 		 */
-		if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
-			last_block = first_block + len;
-		len -= last_block - first_block;
+		if (first_cluster + len < EXT4_CLUSTERS_PER_GROUP(sb))
+			last_cluster = first_cluster + len;
+		len -= last_cluster - first_cluster;
 
 		if (grp->bb_free >= minlen) {
-			cnt = ext4_trim_all_free(sb, group, first_block,
-						last_block, minlen);
+			cnt = ext4_trim_all_free(sb, group, first_cluster,
+						last_cluster, minlen);
 			if (cnt < 0) {
 				ret = cnt;
 				break;
 			}
 		}
 		trimmed += cnt;
-		first_block = 0;
+		first_cluster = 0;
 	}
 	range->len = trimmed * sb->s_blocksize;
 

fs/ext4/mballoc.h

@@ -106,7 +106,7 @@ struct ext4_free_data {
 	ext4_group_t group;
 
 	/* free block extent */
-	ext4_grpblk_t start_blk;
+	ext4_grpblk_t start_cluster;
 	ext4_grpblk_t count;
 
 	/* transaction which freed this extent */
@@ -139,9 +139,9 @@ enum {
 
 struct ext4_free_extent {
 	ext4_lblk_t fe_logical;
-	ext4_grpblk_t fe_start;
+	ext4_grpblk_t fe_start;	/* In cluster units */
 	ext4_group_t fe_group;
-	ext4_grpblk_t fe_len;
+	ext4_grpblk_t fe_len;	/* In cluster units */
 };
 
 /*
@@ -175,7 +175,7 @@ struct ext4_allocation_context {
 	/* the best found extent */
 	struct ext4_free_extent ac_b_ex;
 
-	/* copy of the bext found extent taken before preallocation efforts */
+	/* copy of the best found extent taken before preallocation efforts */
 	struct ext4_free_extent ac_f_ex;
 
 	/* number of iterations done. we have to track to limit searching */
@@ -216,6 +216,7 @@ struct ext4_buddy {
 static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 					struct ext4_free_extent *fex)
 {
-	return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
+	return ext4_group_first_block_no(sb, fex->fe_group) +
+		(fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
 }
 #endif

fs/ext4/migrate.c

@@ -15,19 +15,18 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include "ext4_jbd2.h"
-#include "ext4_extents.h"
 
 /*
  * The contiguous blocks details which can be
  * represented by a single extent
  */
-struct list_blocks_struct {
-	ext4_lblk_t first_block, last_block;
+struct migrate_struct {
+	ext4_lblk_t first_block, last_block, curr_block;
 	ext4_fsblk_t first_pblock, last_pblock;
 };
 
 static int finish_range(handle_t *handle, struct inode *inode,
-				struct list_blocks_struct *lb)
+				struct migrate_struct *lb)
 
 {
 	int retval = 0, needed;
@@ -87,8 +86,7 @@ err_out:
 }
 
 static int update_extent_range(handle_t *handle, struct inode *inode,
-				ext4_fsblk_t pblock, ext4_lblk_t blk_num,
-				struct list_blocks_struct *lb)
+			       ext4_fsblk_t pblock, struct migrate_struct *lb)
 {
 	int retval;
 	/*
@@ -96,9 +94,10 @@ static int update_extent_range(handle_t *handle, struct inode *inode,
 	 */
 	if (lb->first_pblock &&
 		(lb->last_pblock+1 == pblock) &&
-		(lb->last_block+1 == blk_num)) {
+		(lb->last_block+1 == lb->curr_block)) {
 		lb->last_pblock = pblock;
-		lb->last_block = blk_num;
+		lb->last_block = lb->curr_block;
+		lb->curr_block++;
 		return 0;
 	}
 	/*
@@ -106,64 +105,49 @@ static int update_extent_range(handle_t *handle, struct inode *inode,
 	 */
 	retval = finish_range(handle, inode, lb);
 	lb->first_pblock = lb->last_pblock = pblock;
-	lb->first_block = lb->last_block = blk_num;
-
+	lb->first_block = lb->last_block = lb->curr_block;
+	lb->curr_block++;
 	return retval;
 }
 
 static int update_ind_extent_range(handle_t *handle, struct inode *inode,
-				   ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
-				   struct list_blocks_struct *lb)
+				   ext4_fsblk_t pblock,
+				   struct migrate_struct *lb)
 {
 	struct buffer_head *bh;
 	__le32 *i_data;
 	int i, retval = 0;
-	ext4_lblk_t blk_count = *blk_nump;
 	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
 
-	if (!pblock) {
-		/* Only update the file block number */
-		*blk_nump += max_entries;
-		return 0;
-	}
-
 	bh = sb_bread(inode->i_sb, pblock);
 	if (!bh)
 		return -EIO;
 
 	i_data = (__le32 *)bh->b_data;
-	for (i = 0; i < max_entries; i++, blk_count++) {
+	for (i = 0; i < max_entries; i++) {
 		if (i_data[i]) {
 			retval = update_extent_range(handle, inode,
-						le32_to_cpu(i_data[i]),
-						blk_count, lb);
+						le32_to_cpu(i_data[i]), lb);
 			if (retval)
 				break;
+		} else {
+			lb->curr_block++;
 		}
 	}
-
-	/* Update the file block number */
-	*blk_nump = blk_count;
 	put_bh(bh);
 	return retval;
 
 }
 
 static int update_dind_extent_range(handle_t *handle, struct inode *inode,
-				    ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
-				    struct list_blocks_struct *lb)
+				    ext4_fsblk_t pblock,
+				    struct migrate_struct *lb)
 {
 	struct buffer_head *bh;
 	__le32 *i_data;
 	int i, retval = 0;
-	ext4_lblk_t blk_count = *blk_nump;
 	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
 
-	if (!pblock) {
-		/* Only update the file block number */
-		*blk_nump += max_entries * max_entries;
-		return 0;
-	}
 	bh = sb_bread(inode->i_sb, pblock);
 	if (!bh)
 		return -EIO;
@@ -172,38 +156,28 @@ static int update_dind_extent_range(handle_t *handle, struct inode *inode,
 	for (i = 0; i < max_entries; i++) {
 		if (i_data[i]) {
 			retval = update_ind_extent_range(handle, inode,
-						le32_to_cpu(i_data[i]),
-						&blk_count, lb);
+						le32_to_cpu(i_data[i]), lb);
 			if (retval)
 				break;
 		} else {
 			/* Only update the file block number */
-			blk_count += max_entries;
+			lb->curr_block += max_entries;
 		}
 	}
-
-	/* Update the file block number */
-	*blk_nump = blk_count;
 	put_bh(bh);
 	return retval;
 
 }
 
 static int update_tind_extent_range(handle_t *handle, struct inode *inode,
-				     ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
-				     struct list_blocks_struct *lb)
+				    ext4_fsblk_t pblock,
+				    struct migrate_struct *lb)
 {
 	struct buffer_head *bh;
 	__le32 *i_data;
 	int i, retval = 0;
-	ext4_lblk_t blk_count = *blk_nump;
 	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
 
-	if (!pblock) {
-		/* Only update the file block number */
-		*blk_nump += max_entries * max_entries * max_entries;
-		return 0;
-	}
 	bh = sb_bread(inode->i_sb, pblock);
 	if (!bh)
 		return -EIO;
@@ -212,16 +186,14 @@ static int update_tind_extent_range(handle_t *handle, struct inode *inode,
 	for (i = 0; i < max_entries; i++) {
 		if (i_data[i]) {
 			retval = update_dind_extent_range(handle, inode,
-						le32_to_cpu(i_data[i]),
-						&blk_count, lb);
+						le32_to_cpu(i_data[i]), lb);
 			if (retval)
 				break;
-		} else
+		} else {
 			/* Only update the file block number */
-			blk_count += max_entries * max_entries;
+			lb->curr_block += max_entries * max_entries;
+		}
 	}
-	/* Update the file block number */
-	*blk_nump = blk_count;
 	put_bh(bh);
 	return retval;
 
@@ -462,12 +434,12 @@ int ext4_ext_migrate(struct inode *inode)
 	handle_t *handle;
 	int retval = 0, i;
 	__le32 *i_data;
-	ext4_lblk_t blk_count = 0;
 	struct ext4_inode_info *ei;
 	struct inode *tmp_inode = NULL;
-	struct list_blocks_struct lb;
+	struct migrate_struct lb;
 	unsigned long max_entries;
 	__u32 goal;
+	uid_t owner[2];
 
 	/*
 	 * If the filesystem does not support extents, or the inode
@@ -495,10 +467,12 @@ int ext4_ext_migrate(struct inode *inode)
 	}
 	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
 		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
+	owner[0] = inode->i_uid;
+	owner[1] = inode->i_gid;
 	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
-				   S_IFREG, NULL, goal);
+				   S_IFREG, NULL, goal, owner);
 	if (IS_ERR(tmp_inode)) {
-		retval = -ENOMEM;
+		retval = PTR_ERR(inode);
 		ext4_journal_stop(handle);
 		return retval;
 	}
@@ -551,35 +525,32 @@ int ext4_ext_migrate(struct inode *inode)
 
 	/* 32 bit block address 4 bytes */
 	max_entries = inode->i_sb->s_blocksize >> 2;
-	for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
+	for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
 		if (i_data[i]) {
 			retval = update_extent_range(handle, tmp_inode,
-						le32_to_cpu(i_data[i]),
-						blk_count, &lb);
+						le32_to_cpu(i_data[i]), &lb);
 			if (retval)
 				goto err_out;
-		}
+		} else
+			lb.curr_block++;
 	}
 	if (i_data[EXT4_IND_BLOCK]) {
 		retval = update_ind_extent_range(handle, tmp_inode,
-					le32_to_cpu(i_data[EXT4_IND_BLOCK]),
-					&blk_count, &lb);
+				le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb);
 			if (retval)
 				goto err_out;
 	} else
-		blk_count +=  max_entries;
+		lb.curr_block += max_entries;
 	if (i_data[EXT4_DIND_BLOCK]) {
 		retval = update_dind_extent_range(handle, tmp_inode,
-					le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
-					&blk_count, &lb);
+				le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb);
 			if (retval)
 				goto err_out;
 	} else
-		blk_count += max_entries * max_entries;
+		lb.curr_block += max_entries * max_entries;
 	if (i_data[EXT4_TIND_BLOCK]) {
 		retval = update_tind_extent_range(handle, tmp_inode,
-					le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
-					&blk_count, &lb);
+				le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb);
 			if (retval)
 				goto err_out;
 	}

fs/ext4/mmp.c

@@ -109,7 +109,7 @@ static int kmmpd(void *data)
 	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
 	bdevname(bh->b_bdev, mmp->mmp_bdevname);
 
-	memcpy(mmp->mmp_nodename, init_utsname()->sysname,
+	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
 	       sizeof(mmp->mmp_nodename));
 
 	while (!kthread_should_stop()) {
@@ -125,8 +125,9 @@ static int kmmpd(void *data)
 		 * Don't spew too many error messages. Print one every
 		 * (s_mmp_update_interval * 60) seconds.
 		 */
-		if (retval && (failed_writes % 60) == 0) {
-			ext4_error(sb, "Error writing to MMP block");
+		if (retval) {
+			if ((failed_writes % 60) == 0)
+				ext4_error(sb, "Error writing to MMP block");
 			failed_writes++;
 		}
 
@@ -295,7 +296,8 @@ skip:
 	/*
 	 * write a new random sequence number.
 	 */
-	mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
+	seq = mmp_new_seq();
+	mmp->mmp_seq = cpu_to_le32(seq);
 
 	retval = write_mmp_block(bh);
 	if (retval)

fs/ext4/move_extent.c

@@ -17,7 +17,6 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include "ext4_jbd2.h"
-#include "ext4_extents.h"
 #include "ext4.h"
 
 /**

fs/ext4/namei.c

@@ -1586,7 +1586,7 @@ 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_handle_dirty_metadata(handle, inode, bh2);
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1612,7 +1612,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
 		if (err) {
 			ext4_std_error(inode->i_sb, err);
 			goto cleanup;
@@ -1707,9 +1707,8 @@ static void ext4_inc_count(handle_t *handle, struct inode *inode)
  */
 static void ext4_dec_count(handle_t *handle, struct inode *inode)
 {
-	drop_nlink(inode);
-	if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0)
-		inc_nlink(inode);
+	if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+		drop_nlink(inode);
 }
 
 
@@ -1756,7 +1755,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
@@ -1792,7 +1791,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
@@ -1832,7 +1831,7 @@ retry:
 		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
-			       &dentry->d_name, 0);
+			       &dentry->d_name, 0, NULL);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
@@ -1863,7 +1862,7 @@ retry:
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
 	if (err)
 		goto out_clear_inode;
 	err = ext4_mark_inode_dirty(handle, inode);
@@ -2279,7 +2278,7 @@ retry:
 		ext4_handle_sync(handle);
 
 	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
-			       &dentry->d_name, 0);
+			       &dentry->d_name, 0, NULL);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
@@ -2530,7 +2529,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;

fs/ext4/page-io.c

@@ -70,7 +70,6 @@ static void put_io_page(struct ext4_io_page *io_page)
 void ext4_free_io_end(ext4_io_end_t *io)
 {
 	int i;
-	wait_queue_head_t *wq;
 
 	BUG_ON(!io);
 	if (io->page)
@@ -78,56 +77,43 @@ void ext4_free_io_end(ext4_io_end_t *io)
 	for (i = 0; i < io->num_io_pages; i++)
 		put_io_page(io->pages[i]);
 	io->num_io_pages = 0;
-	wq = ext4_ioend_wq(io->inode);
-	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
-	    waitqueue_active(wq))
-		wake_up_all(wq);
+	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
+		wake_up_all(ext4_ioend_wq(io->inode));
 	kmem_cache_free(io_end_cachep, io);
 }
 
 /*
  * check a range of space and convert unwritten extents to written.
+ *
+ * Called with inode->i_mutex; we depend on this when we manipulate
+ * io->flag, since we could otherwise race with ext4_flush_completed_IO()
  */
 int ext4_end_io_nolock(ext4_io_end_t *io)
 {
 	struct inode *inode = io->inode;
 	loff_t offset = io->offset;
 	ssize_t size = io->size;
-	wait_queue_head_t *wq;
 	int ret = 0;
 
 	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
 		   "list->prev 0x%p\n",
 		   io, inode->i_ino, io->list.next, io->list.prev);
 
-	if (list_empty(&io->list))
-		return ret;
-
-	if (!(io->flag & EXT4_IO_END_UNWRITTEN))
-		return ret;
-
 	ret = ext4_convert_unwritten_extents(inode, offset, size);
 	if (ret < 0) {
-		printk(KERN_EMERG "%s: failed to convert unwritten "
-			"extents to written extents, error is %d "
-			"io is still on inode %lu aio dio list\n",
-		       __func__, ret, inode->i_ino);
-		return ret;
+		ext4_msg(inode->i_sb, KERN_EMERG,
+			 "failed to convert unwritten extents to written "
+			 "extents -- potential data loss!  "
+			 "(inode %lu, offset %llu, size %zd, error %d)",
+			 inode->i_ino, offset, size, ret);
 	}
 
 	if (io->iocb)
 		aio_complete(io->iocb, io->result, 0);
-	/* clear the DIO AIO unwritten flag */
-	if (io->flag & EXT4_IO_END_UNWRITTEN) {
-		io->flag &= ~EXT4_IO_END_UNWRITTEN;
-		/* Wake up anyone waiting on unwritten extent conversion */
-		wq = ext4_ioend_wq(io->inode);
-		if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
-		    waitqueue_active(wq)) {
-			wake_up_all(wq);
-		}
-	}
 
+	/* Wake up anyone waiting on unwritten extent conversion */
+	if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
+		wake_up_all(ext4_ioend_wq(io->inode));
 	return ret;
 }
 
@@ -140,9 +126,15 @@ static void ext4_end_io_work(struct work_struct *work)
 	struct inode		*inode = io->inode;
 	struct ext4_inode_info	*ei = EXT4_I(inode);
 	unsigned long		flags;
-	int			ret;
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	if (list_empty(&io->list)) {
+		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+		goto free;
+	}
 
 	if (!mutex_trylock(&inode->i_mutex)) {
+		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 		/*
 		 * Requeue the work instead of waiting so that the work
 		 * items queued after this can be processed.
@@ -159,17 +151,11 @@ static void ext4_end_io_work(struct work_struct *work)
 		io->flag |= EXT4_IO_END_QUEUED;
 		return;
 	}
-	ret = ext4_end_io_nolock(io);
-	if (ret < 0) {
-		mutex_unlock(&inode->i_mutex);
-		return;
-	}
-
-	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	if (!list_empty(&io->list))
-		list_del_init(&io->list);
+	list_del_init(&io->list);
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+	(void) ext4_end_io_nolock(io);
 	mutex_unlock(&inode->i_mutex);
+free:
 	ext4_free_io_end(io);
 }
 
@@ -350,10 +336,8 @@ submit_and_retry:
 	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
 	    (io_end->pages[io_end->num_io_pages-1] != io_page))
 		goto submit_and_retry;
-	if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		io_end->flag |= EXT4_IO_END_UNWRITTEN;
-		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
-	}
+	if (buffer_uninit(bh))
+		ext4_set_io_unwritten_flag(inode, io_end);
 	io->io_end->size += bh->b_size;
 	io->io_next_block++;
 	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));

fs/ext4/resize.c

@@ -875,7 +875,7 @@ 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 */
-	ext4_free_blks_set(sb, gdp, input->free_blocks_count);
+	ext4_free_group_clusters_set(sb, gdp, input->free_blocks_count);
 	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);
@@ -937,8 +937,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 		input->reserved_blocks);
 
 	/* Update the free space counts */
-	percpu_counter_add(&sbi->s_freeblocks_counter,
-			   input->free_blocks_count);
+	percpu_counter_add(&sbi->s_freeclusters_counter,
+			   EXT4_B2C(sbi, input->free_blocks_count));
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb));
 
@@ -946,8 +946,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, input->group);
-		atomic_add(input->free_blocks_count,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(EXT4_B2C(sbi, input->free_blocks_count),
+			   &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}

fs/ext4/super.c

@@ -45,6 +45,7 @@
 #include <linux/freezer.h>
 
 #include "ext4.h"
+#include "ext4_extents.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
@@ -163,8 +164,8 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb,
 		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
 }
 
-__u32 ext4_free_blks_count(struct super_block *sb,
-			      struct ext4_group_desc *bg)
+__u32 ext4_free_group_clusters(struct super_block *sb,
+			       struct ext4_group_desc *bg)
 {
 	return le16_to_cpu(bg->bg_free_blocks_count_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
@@ -219,8 +220,8 @@ void ext4_inode_table_set(struct super_block *sb,
 		bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
 }
 
-void ext4_free_blks_set(struct super_block *sb,
-			  struct ext4_group_desc *bg, __u32 count)
+void ext4_free_group_clusters_set(struct super_block *sb,
+				  struct ext4_group_desc *bg, __u32 count)
 {
 	bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
 	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
@@ -414,6 +415,22 @@ static void save_error_info(struct super_block *sb, const char *func,
 	ext4_commit_super(sb, 1);
 }
 
+/*
+ * The del_gendisk() function uninitializes the disk-specific data
+ * structures, including the bdi structure, without telling anyone
+ * else.  Once this happens, any attempt to call mark_buffer_dirty()
+ * (for example, by ext4_commit_super), will cause a kernel OOPS.
+ * This is a kludge to prevent these oops until we can put in a proper
+ * hook in del_gendisk() to inform the VFS and file system layers.
+ */
+static int block_device_ejected(struct super_block *sb)
+{
+	struct inode *bd_inode = sb->s_bdev->bd_inode;
+	struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+
+	return bdi->dev == NULL;
+}
+
 
 /* Deal with the reporting of failure conditions on a filesystem such as
  * inconsistencies detected or read IO failures.
@@ -821,10 +838,10 @@ static void ext4_put_super(struct super_block *sb)
 		brelse(sbi->s_group_desc[i]);
 	ext4_kvfree(sbi->s_group_desc);
 	ext4_kvfree(sbi->s_flex_groups);
-	percpu_counter_destroy(&sbi->s_freeblocks_counter);
+	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
-	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
@@ -1057,8 +1074,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nouid32");
 	if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
 		seq_puts(seq, ",debug");
-	if (test_opt(sb, OLDALLOC))
-		seq_puts(seq, ",oldalloc");
 #ifdef CONFIG_EXT4_FS_XATTR
 	if (test_opt(sb, XATTR_USER))
 		seq_puts(seq, ",user_xattr");
@@ -1567,10 +1582,12 @@ static int parse_options(char *options, struct super_block *sb,
 			set_opt(sb, DEBUG);
 			break;
 		case Opt_oldalloc:
-			set_opt(sb, OLDALLOC);
+			ext4_msg(sb, KERN_WARNING,
+				 "Ignoring deprecated oldalloc option");
 			break;
 		case Opt_orlov:
-			clear_opt(sb, OLDALLOC);
+			ext4_msg(sb, KERN_WARNING,
+				 "Ignoring deprecated orlov option");
 			break;
 #ifdef CONFIG_EXT4_FS_XATTR
 		case Opt_user_xattr:
@@ -1801,6 +1818,7 @@ set_qf_format:
 			break;
 		case Opt_nodelalloc:
 			clear_opt(sb, DELALLOC);
+			clear_opt2(sb, EXPLICIT_DELALLOC);
 			break;
 		case Opt_mblk_io_submit:
 			set_opt(sb, MBLK_IO_SUBMIT);
@@ -1817,6 +1835,7 @@ set_qf_format:
 			break;
 		case Opt_delalloc:
 			set_opt(sb, DELALLOC);
+			set_opt2(sb, EXPLICIT_DELALLOC);
 			break;
 		case Opt_block_validity:
 			set_opt(sb, BLOCK_VALIDITY);
@@ -1935,7 +1954,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		res = MS_RDONLY;
 	}
 	if (read_only)
-		return res;
+		goto done;
 	if (!(sbi->s_mount_state & EXT4_VALID_FS))
 		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
 			 "running e2fsck is recommended");
@@ -1966,6 +1985,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 
 	ext4_commit_super(sb, 1);
+done:
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
 				"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
@@ -2015,8 +2035,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		flex_group = ext4_flex_group(sbi, i);
 		atomic_add(ext4_free_inodes_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
-		atomic_add(ext4_free_blks_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(ext4_free_group_clusters(sb, gdp),
+			   &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(ext4_used_dirs_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].used_dirs);
 	}
@@ -2134,7 +2154,8 @@ static int ext4_check_descriptors(struct super_block *sb,
 	if (NULL != first_not_zeroed)
 		*first_not_zeroed = grp;
 
-	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+	ext4_free_blocks_count_set(sbi->s_es,
+				   EXT4_C2B(sbi, ext4_count_free_clusters(sb)));
 	sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
 	return 1;
 }
@@ -2454,7 +2475,8 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
 					      char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
-			(s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+		(s64) EXT4_C2B(sbi,
+			percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
 }
 
 static ssize_t session_write_kbytes_show(struct ext4_attr *a,
@@ -2682,6 +2704,13 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 			return 0;
 		}
 	}
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) &&
+	    !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Can't support bigalloc feature without "
+			 "extents feature\n");
+		return 0;
+	}
 	return 1;
 }
 
@@ -3087,10 +3116,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	char *cp;
 	const char *descr;
 	int ret = -ENOMEM;
-	int blocksize;
+	int blocksize, clustersize;
 	unsigned int db_count;
 	unsigned int i;
-	int needs_recovery, has_huge_files;
+	int needs_recovery, has_huge_files, has_bigalloc;
 	__u64 blocks_count;
 	int err;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@@ -3224,6 +3253,33 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			   &journal_ioprio, NULL, 0))
 		goto failed_mount;
 
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
+			    "with data=journal disables delayed "
+			    "allocation and O_DIRECT support!\n");
+		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and delalloc");
+			goto failed_mount;
+		}
+		if (test_opt(sb, DIOREAD_NOLOCK)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and delalloc");
+			goto failed_mount;
+		}
+		if (test_opt(sb, DELALLOC))
+			clear_opt(sb, DELALLOC);
+	}
+
+	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+	if (test_opt(sb, DIOREAD_NOLOCK)) {
+		if (blocksize < PAGE_SIZE) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "dioread_nolock if block size != PAGE_SIZE");
+			goto failed_mount;
+		}
+	}
+
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
 
@@ -3265,8 +3321,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
 		goto failed_mount;
 
-	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
 	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
 	    blocksize > EXT4_MAX_BLOCK_SIZE) {
 		ext4_msg(sb, KERN_ERR,
@@ -3369,12 +3423,53 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sb->s_dirt = 1;
 	}
 
-	if (sbi->s_blocks_per_group > blocksize * 8) {
-		ext4_msg(sb, KERN_ERR,
-		       "#blocks per group too big: %lu",
-		       sbi->s_blocks_per_group);
-		goto failed_mount;
+	/* Handle clustersize */
+	clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
+	has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+	if (has_bigalloc) {
+		if (clustersize < blocksize) {
+			ext4_msg(sb, KERN_ERR,
+				 "cluster size (%d) smaller than "
+				 "block size (%d)", clustersize, blocksize);
+			goto failed_mount;
+		}
+		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
+			le32_to_cpu(es->s_log_block_size);
+		sbi->s_clusters_per_group =
+			le32_to_cpu(es->s_clusters_per_group);
+		if (sbi->s_clusters_per_group > blocksize * 8) {
+			ext4_msg(sb, KERN_ERR,
+				 "#clusters per group too big: %lu",
+				 sbi->s_clusters_per_group);
+			goto failed_mount;
+		}
+		if (sbi->s_blocks_per_group !=
+		    (sbi->s_clusters_per_group * (clustersize / blocksize))) {
+			ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
+				 "clusters per group (%lu) inconsistent",
+				 sbi->s_blocks_per_group,
+				 sbi->s_clusters_per_group);
+			goto failed_mount;
+		}
+	} else {
+		if (clustersize != blocksize) {
+			ext4_warning(sb, "fragment/cluster size (%d) != "
+				     "block size (%d)", clustersize,
+				     blocksize);
+			clustersize = blocksize;
+		}
+		if (sbi->s_blocks_per_group > blocksize * 8) {
+			ext4_msg(sb, KERN_ERR,
+				 "#blocks per group too big: %lu",
+				 sbi->s_blocks_per_group);
+			goto failed_mount;
+		}
+		sbi->s_clusters_per_group = sbi->s_blocks_per_group;
+		sbi->s_cluster_bits = 0;
 	}
+	sbi->s_cluster_ratio = clustersize / blocksize;
+
 	if (sbi->s_inodes_per_group > blocksize * 8) {
 		ext4_msg(sb, KERN_ERR,
 		       "#inodes per group too big: %lu",
@@ -3446,10 +3541,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-#ifdef CONFIG_PROC_FS
 	if (ext4_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-#endif
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -3483,8 +3576,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_err_report.function = print_daily_error_info;
 	sbi->s_err_report.data = (unsigned long) sb;
 
-	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-			ext4_count_free_blocks(sb));
+	err = percpu_counter_init(&sbi->s_freeclusters_counter,
+			ext4_count_free_clusters(sb));
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_freeinodes_counter,
 				ext4_count_free_inodes(sb));
@@ -3494,7 +3587,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				ext4_count_dirs(sb));
 	}
 	if (!err) {
-		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
 	}
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
@@ -3609,13 +3702,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * The journal may have updated the bg summary counts, so we
 	 * need to update the global counters.
 	 */
-	percpu_counter_set(&sbi->s_freeblocks_counter,
-			   ext4_count_free_blocks(sb));
+	percpu_counter_set(&sbi->s_freeclusters_counter,
+			   ext4_count_free_clusters(sb));
 	percpu_counter_set(&sbi->s_freeinodes_counter,
 			   ext4_count_free_inodes(sb));
 	percpu_counter_set(&sbi->s_dirs_counter,
 			   ext4_count_dirs(sb));
-	percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+	percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
 
 no_journal:
 	/*
@@ -3679,25 +3772,6 @@ no_journal:
 			 "available");
 	}
 
-	if (test_opt(sb, DELALLOC) &&
-	    (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
-		ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
-			 "requested data journaling mode");
-		clear_opt(sb, DELALLOC);
-	}
-	if (test_opt(sb, DIOREAD_NOLOCK)) {
-		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-			ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
-				"option - requested data journaling mode");
-			clear_opt(sb, DIOREAD_NOLOCK);
-		}
-		if (sb->s_blocksize < PAGE_SIZE) {
-			ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
-				"option - block size is too small");
-			clear_opt(sb, DIOREAD_NOLOCK);
-		}
-	}
-
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
@@ -3710,22 +3784,19 @@ no_journal:
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
 			 err);
-		goto failed_mount4;
+		goto failed_mount5;
 	}
 
 	err = ext4_register_li_request(sb, first_not_zeroed);
 	if (err)
-		goto failed_mount4;
+		goto failed_mount6;
 
 	sbi->s_kobj.kset = ext4_kset;
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
 				   "%s", sb->s_id);
-	if (err) {
-		ext4_mb_release(sb);
-		ext4_ext_release(sb);
-		goto failed_mount4;
-	};
+	if (err)
+		goto failed_mount7;
 
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
@@ -3759,13 +3830,19 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
+failed_mount7:
+	ext4_unregister_li_request(sb);
+failed_mount6:
+	ext4_ext_release(sb);
+failed_mount5:
+	ext4_mb_release(sb);
+	ext4_release_system_zone(sb);
 failed_mount4:
 	iput(root);
 	sb->s_root = NULL;
 	ext4_msg(sb, KERN_ERR, "mount failed");
 	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
 failed_mount_wq:
-	ext4_release_system_zone(sb);
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -3774,10 +3851,10 @@ failed_mount3:
 	del_timer(&sbi->s_err_report);
 	if (sbi->s_flex_groups)
 		ext4_kvfree(sbi->s_flex_groups);
-	percpu_counter_destroy(&sbi->s_freeblocks_counter);
+	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
-	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
@@ -4064,7 +4141,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
 	int error = 0;
 
-	if (!sbh)
+	if (!sbh || block_device_ejected(sb))
 		return error;
 	if (buffer_write_io_error(sbh)) {
 		/*
@@ -4100,8 +4177,9 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	else
 		es->s_kbytes_written =
 			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
-	ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
-					   &EXT4_SB(sb)->s_freeblocks_counter));
+	ext4_free_blocks_count_set(es,
+			EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
+				&EXT4_SB(sb)->s_freeclusters_counter)));
 	es->s_free_inodes_count =
 		cpu_to_le32(percpu_counter_sum_positive(
 				&EXT4_SB(sb)->s_freeinodes_counter));
@@ -4506,16 +4584,34 @@ restore_opts:
 	return err;
 }
 
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc.  This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time.  We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock.  If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	struct ext4_group_desc *gdp;
 	u64 fsid;
 	s64 bfree;
 
 	if (test_opt(sb, MINIX_DF)) {
 		sbi->s_overhead_last = 0;
+	} else if (es->s_overhead_clusters) {
+		sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
 	} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
 		ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 		ext4_fsblk_t overhead = 0;
@@ -4530,24 +4626,16 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 		 * All of the blocks before first_data_block are
 		 * overhead
 		 */
-		overhead = le32_to_cpu(es->s_first_data_block);
+		overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
 
 		/*
-		 * Add the overhead attributed to the superblock and
-		 * block group descriptors.  If the sparse superblocks
-		 * feature is turned on, then not all groups have this.
+		 * Add the overhead found in each block group
 		 */
 		for (i = 0; i < ngroups; i++) {
-			overhead += ext4_bg_has_super(sb, i) +
-				ext4_bg_num_gdb(sb, i);
+			gdp = ext4_get_group_desc(sb, i, NULL);
+			overhead += ext4_num_overhead_clusters(sb, i, gdp);
 			cond_resched();
 		}
-
-		/*
-		 * Every block group has an inode bitmap, a block
-		 * bitmap, and an inode table.
-		 */
-		overhead += ngroups * (2 + sbi->s_itb_per_group);
 		sbi->s_overhead_last = overhead;
 		smp_wmb();
 		sbi->s_blocks_last = ext4_blocks_count(es);
@@ -4555,11 +4643,12 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_type = EXT4_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
-	bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
-		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+	buf->f_blocks = (ext4_blocks_count(es) -
+			 EXT4_C2B(sbi, sbi->s_overhead_last));
+	bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
+		percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
 	/* prevent underflow in case that few free space is available */
-	buf->f_bfree = max_t(s64, bfree, 0);
+	buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
 	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
 	if (buf->f_bfree < ext4_r_blocks_count(es))
 		buf->f_bavail = 0;
@@ -4980,13 +5069,11 @@ static int __init ext4_init_fs(void)
 		return err;
 	err = ext4_init_system_zone();
 	if (err)
-		goto out7;
+		goto out6;
 	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
 	if (!ext4_kset)
-		goto out6;
-	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
-	if (!ext4_proc_root)
 		goto out5;
+	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
 
 	err = ext4_init_feat_adverts();
 	if (err)
@@ -5022,12 +5109,12 @@ out2:
 out3:
 	ext4_exit_feat_adverts();
 out4:
-	remove_proc_entry("fs/ext4", NULL);
-out5:
+	if (ext4_proc_root)
+		remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
-out6:
+out5:
 	ext4_exit_system_zone();
-out7:
+out6:
 	ext4_exit_pageio();
 	return err;
 }

fs/ext4/xattr.c

@@ -820,8 +820,14 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;
 
@@ -985,11 +991,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
 	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 
-	error = ext4_get_inode_loc(inode, &is.iloc);
-	if (error)
-		goto cleanup;
-
-	error = ext4_journal_get_write_access(handle, is.iloc.bh);
+	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
 	if (error)
 		goto cleanup;
 

fs/jbd/journal.c

@@ -1135,6 +1135,14 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
+		goto out;
+	}
+
 	return 0;
 
 out:

fs/jbd2/commit.c

@@ -352,7 +352,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
 	trace_jbd2_start_commit(journal, commit_transaction);
-	jbd_debug(1, "JBD: starting commit of transaction %d\n",
+	jbd_debug(1, "JBD2: starting commit of transaction %d\n",
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
@@ -427,7 +427,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	__jbd2_journal_clean_checkpoint_list(journal);
 	spin_unlock(&journal->j_list_lock);
 
-	jbd_debug (3, "JBD: commit phase 1\n");
+	jbd_debug(3, "JBD2: commit phase 1\n");
 
 	/*
 	 * Switch to a new revoke table.
@@ -447,7 +447,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	wake_up(&journal->j_wait_transaction_locked);
 	write_unlock(&journal->j_state_lock);
 
-	jbd_debug (3, "JBD: commit phase 2\n");
+	jbd_debug(3, "JBD2: commit phase 2\n");
 
 	/*
 	 * Now start flushing things to disk, in the order they appear
@@ -462,7 +462,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 					  WRITE_SYNC);
 	blk_finish_plug(&plug);
 
-	jbd_debug(3, "JBD: commit phase 2\n");
+	jbd_debug(3, "JBD2: commit phase 2\n");
 
 	/*
 	 * Way to go: we have now written out all of the data for a
@@ -522,7 +522,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			J_ASSERT (bufs == 0);
 
-			jbd_debug(4, "JBD: get descriptor\n");
+			jbd_debug(4, "JBD2: get descriptor\n");
 
 			descriptor = jbd2_journal_get_descriptor_buffer(journal);
 			if (!descriptor) {
@@ -531,7 +531,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			}
 
 			bh = jh2bh(descriptor);
-			jbd_debug(4, "JBD: got buffer %llu (%p)\n",
+			jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
 				(unsigned long long)bh->b_blocknr, bh->b_data);
 			header = (journal_header_t *)&bh->b_data[0];
 			header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
@@ -625,7 +625,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		    commit_transaction->t_buffers == NULL ||
 		    space_left < tag_bytes + 16) {
 
-			jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
+			jbd_debug(4, "JBD2: Submit %d IOs\n", bufs);
 
 			/* Write an end-of-descriptor marker before
                            submitting the IOs.  "tag" still points to
@@ -707,7 +707,7 @@ start_journal_io:
 	   so we incur less scheduling load.
 	*/
 
-	jbd_debug(3, "JBD: commit phase 3\n");
+	jbd_debug(3, "JBD2: commit phase 3\n");
 
 	/*
 	 * akpm: these are BJ_IO, and j_list_lock is not needed.
@@ -771,7 +771,7 @@ wait_for_iobuf:
 
 	J_ASSERT (commit_transaction->t_shadow_list == NULL);
 
-	jbd_debug(3, "JBD: commit phase 4\n");
+	jbd_debug(3, "JBD2: commit phase 4\n");
 
 	/* Here we wait for the revoke record and descriptor record buffers */
  wait_for_ctlbuf:
@@ -801,7 +801,7 @@ wait_for_iobuf:
 	if (err)
 		jbd2_journal_abort(journal, err);
 
-	jbd_debug(3, "JBD: commit phase 5\n");
+	jbd_debug(3, "JBD2: commit phase 5\n");
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH);
 	commit_transaction->t_state = T_COMMIT_JFLUSH;
@@ -830,7 +830,7 @@ wait_for_iobuf:
            transaction can be removed from any checkpoint list it was on
            before. */
 
-	jbd_debug(3, "JBD: commit phase 6\n");
+	jbd_debug(3, "JBD2: commit phase 6\n");
 
 	J_ASSERT(list_empty(&commit_transaction->t_inode_list));
 	J_ASSERT(commit_transaction->t_buffers == NULL);
@@ -964,7 +964,7 @@ restart_loop:
 
 	/* Done with this transaction! */
 
-	jbd_debug(3, "JBD: commit phase 7\n");
+	jbd_debug(3, "JBD2: commit phase 7\n");
 
 	J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH);
 
@@ -1039,7 +1039,7 @@ restart_loop:
 		journal->j_commit_callback(journal, commit_transaction);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
-	jbd_debug(1, "JBD: commit %d complete, head %d\n",
+	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 	if (to_free)
 		kfree(commit_transaction);

fs/jbd2/journal.c

@@ -491,7 +491,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 		 */
 
 		journal->j_commit_request = target;
-		jbd_debug(1, "JBD: requesting commit %d/%d\n",
+		jbd_debug(1, "JBD2: requesting commit %d/%d\n",
 			  journal->j_commit_request,
 			  journal->j_commit_sequence);
 		wake_up(&journal->j_wait_commit);
@@ -500,7 +500,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 		/* This should never happen, but if it does, preserve
 		   the evidence before kjournald goes into a loop and
 		   increments j_commit_sequence beyond all recognition. */
-		WARN_ONCE(1, "jbd: bad log_start_commit: %u %u %u %u\n",
+		WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n",
 			  journal->j_commit_request,
 			  journal->j_commit_sequence,
 			  target, journal->j_running_transaction ? 
@@ -645,7 +645,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	}
 #endif
 	while (tid_gt(tid, journal->j_commit_sequence)) {
-		jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
+		jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
 				  tid, journal->j_commit_sequence);
 		wake_up(&journal->j_wait_commit);
 		read_unlock(&journal->j_state_lock);
@@ -1093,7 +1093,7 @@ static int journal_reset(journal_t *journal)
 	first = be32_to_cpu(sb->s_first);
 	last = be32_to_cpu(sb->s_maxlen);
 	if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
-		printk(KERN_ERR "JBD: Journal too short (blocks %llu-%llu).\n",
+		printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n",
 		       first, last);
 		journal_fail_superblock(journal);
 		return -EINVAL;
@@ -1139,7 +1139,7 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 	 */
 	if (sb->s_start == 0 && journal->j_tail_sequence ==
 				journal->j_transaction_sequence) {
-		jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
+		jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
 			"(start %ld, seq %d, errno %d)\n",
 			journal->j_tail, journal->j_tail_sequence,
 			journal->j_errno);
@@ -1163,7 +1163,7 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 	}
 
 	read_lock(&journal->j_state_lock);
-	jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
+	jbd_debug(1, "JBD2: updating superblock (start %ld, seq %d, errno %d)\n",
 		  journal->j_tail, journal->j_tail_sequence, journal->j_errno);
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
@@ -1216,8 +1216,8 @@ static int journal_get_superblock(journal_t *journal)
 		ll_rw_block(READ, 1, &bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			printk (KERN_ERR
-				"JBD: IO error reading journal superblock\n");
+			printk(KERN_ERR
+				"JBD2: IO error reading journal superblock\n");
 			goto out;
 		}
 	}
@@ -1228,7 +1228,7 @@ static int journal_get_superblock(journal_t *journal)
 
 	if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
 	    sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
-		printk(KERN_WARNING "JBD: no valid journal superblock found\n");
+		printk(KERN_WARNING "JBD2: no valid journal superblock found\n");
 		goto out;
 	}
 
@@ -1240,14 +1240,22 @@ static int journal_get_superblock(journal_t *journal)
 		journal->j_format_version = 2;
 		break;
 	default:
-		printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
+		printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n");
 		goto out;
 	}
 
 	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
 		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
 	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
-		printk (KERN_WARNING "JBD: journal file too short\n");
+		printk(KERN_WARNING "JBD2: journal file too short\n");
+		goto out;
+	}
+
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD2: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
 		goto out;
 	}
 
@@ -1310,8 +1318,8 @@ int jbd2_journal_load(journal_t *journal)
 		     ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
 		    (sb->s_feature_incompat &
 		     ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
-			printk (KERN_WARNING
-				"JBD: Unrecognised features on journal\n");
+			printk(KERN_WARNING
+				"JBD2: Unrecognised features on journal\n");
 			return -EINVAL;
 		}
 	}
@@ -1346,7 +1354,7 @@ int jbd2_journal_load(journal_t *journal)
 	return 0;
 
 recovery_error:
-	printk (KERN_WARNING "JBD: recovery failed\n");
+	printk(KERN_WARNING "JBD2: recovery failed\n");
 	return -EIO;
 }
 
@@ -1577,7 +1585,7 @@ static int journal_convert_superblock_v1(journal_t *journal,
 	struct buffer_head *bh;
 
 	printk(KERN_WARNING
-		"JBD: Converting superblock from version 1 to 2.\n");
+		"JBD2: Converting superblock from version 1 to 2.\n");
 
 	/* Pre-initialise new fields to zero */
 	offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
@@ -1694,7 +1702,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (!journal->j_tail)
 		goto no_recovery;
 
-	printk (KERN_WARNING "JBD: %s recovery information on journal\n",
+	printk(KERN_WARNING "JBD2: %s recovery information on journal\n",
 		write ? "Clearing" : "Ignoring");
 
 	err = jbd2_journal_skip_recovery(journal);
@@ -2020,7 +2028,7 @@ static int journal_init_jbd2_journal_head_cache(void)
 	retval = 0;
 	if (!jbd2_journal_head_cache) {
 		retval = -ENOMEM;
-		printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
+		printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
 	}
 	return retval;
 }
@@ -2383,7 +2391,7 @@ static void __exit journal_exit(void)
 #ifdef CONFIG_JBD2_DEBUG
 	int n = atomic_read(&nr_journal_heads);
 	if (n)
-		printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
+		printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
 #endif
 	jbd2_remove_debugfs_entry();
 	jbd2_remove_jbd_stats_proc_entry();

fs/jbd2/recovery.c

@@ -89,7 +89,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
 		err = jbd2_journal_bmap(journal, next, &blocknr);
 
 		if (err) {
-			printk (KERN_ERR "JBD: bad block at offset %u\n",
+			printk(KERN_ERR "JBD2: bad block at offset %u\n",
 				next);
 			goto failed;
 		}
@@ -138,14 +138,14 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 	*bhp = NULL;
 
 	if (offset >= journal->j_maxlen) {
-		printk(KERN_ERR "JBD: corrupted journal superblock\n");
+		printk(KERN_ERR "JBD2: corrupted journal superblock\n");
 		return -EIO;
 	}
 
 	err = jbd2_journal_bmap(journal, offset, &blocknr);
 
 	if (err) {
-		printk (KERN_ERR "JBD: bad block at offset %u\n",
+		printk(KERN_ERR "JBD2: bad block at offset %u\n",
 			offset);
 		return err;
 	}
@@ -163,7 +163,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 	}
 
 	if (!buffer_uptodate(bh)) {
-		printk (KERN_ERR "JBD: Failed to read block at offset %u\n",
+		printk(KERN_ERR "JBD2: Failed to read block at offset %u\n",
 			offset);
 		brelse(bh);
 		return -EIO;
@@ -251,10 +251,10 @@ int jbd2_journal_recover(journal_t *journal)
 	if (!err)
 		err = do_one_pass(journal, &info, PASS_REPLAY);
 
-	jbd_debug(1, "JBD: recovery, exit status %d, "
+	jbd_debug(1, "JBD2: recovery, exit status %d, "
 		  "recovered transactions %u to %u\n",
 		  err, info.start_transaction, info.end_transaction);
-	jbd_debug(1, "JBD: Replayed %d and revoked %d/%d blocks\n",
+	jbd_debug(1, "JBD2: Replayed %d and revoked %d/%d blocks\n",
 		  info.nr_replays, info.nr_revoke_hits, info.nr_revokes);
 
 	/* Restart the log at the next transaction ID, thus invalidating
@@ -293,14 +293,14 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 	err = do_one_pass(journal, &info, PASS_SCAN);
 
 	if (err) {
-		printk(KERN_ERR "JBD: error %d scanning journal\n", err);
+		printk(KERN_ERR "JBD2: error %d scanning journal\n", err);
 		++journal->j_transaction_sequence;
 	} else {
 #ifdef CONFIG_JBD2_DEBUG
 		int dropped = info.end_transaction - 
 			be32_to_cpu(journal->j_superblock->s_sequence);
 		jbd_debug(1,
-			  "JBD: ignoring %d transaction%s from the journal.\n",
+			  "JBD2: ignoring %d transaction%s from the journal.\n",
 			  dropped, (dropped == 1) ? "" : "s");
 #endif
 		journal->j_transaction_sequence = ++info.end_transaction;
@@ -338,7 +338,7 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh,
 		wrap(journal, *next_log_block);
 		err = jread(&obh, journal, io_block);
 		if (err) {
-			printk(KERN_ERR "JBD: IO error %d recovering block "
+			printk(KERN_ERR "JBD2: IO error %d recovering block "
 				"%lu in log\n", err, io_block);
 			return 1;
 		} else {
@@ -411,7 +411,7 @@ static int do_one_pass(journal_t *journal,
 		 * either the next descriptor block or the final commit
 		 * record. */
 
-		jbd_debug(3, "JBD: checking block %ld\n", next_log_block);
+		jbd_debug(3, "JBD2: checking block %ld\n", next_log_block);
 		err = jread(&bh, journal, next_log_block);
 		if (err)
 			goto failed;
@@ -491,8 +491,8 @@ static int do_one_pass(journal_t *journal,
 					/* Recover what we can, but
 					 * report failure at the end. */
 					success = err;
-					printk (KERN_ERR
-						"JBD: IO error %d recovering "
+					printk(KERN_ERR
+						"JBD2: IO error %d recovering "
 						"block %ld in log\n",
 						err, io_block);
 				} else {
@@ -520,7 +520,7 @@ static int do_one_pass(journal_t *journal,
 							journal->j_blocksize);
 					if (nbh == NULL) {
 						printk(KERN_ERR
-						       "JBD: Out of memory "
+						       "JBD2: Out of memory "
 						       "during recovery.\n");
 						err = -ENOMEM;
 						brelse(bh);
@@ -689,7 +689,7 @@ static int do_one_pass(journal_t *journal,
 		/* It's really bad news if different passes end up at
 		 * different places (but possible due to IO errors). */
 		if (info->end_transaction != next_commit_ID) {
-			printk (KERN_ERR "JBD: recovery pass %d ended at "
+			printk(KERN_ERR "JBD2: recovery pass %d ended at "
 				"transaction %u, expected %u\n",
 				pass, next_commit_ID, info->end_transaction);
 			if (!success)

fs/jbd2/transaction.c

@@ -27,6 +27,7 @@
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
 #include <linux/backing-dev.h>
+#include <linux/bug.h>
 #include <linux/module.h>
 
 static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
@@ -115,7 +116,7 @@ static inline void update_t_max_wait(transaction_t *transaction,
  */
 
 static int start_this_handle(journal_t *journal, handle_t *handle,
-			     int gfp_mask)
+			     gfp_t gfp_mask)
 {
 	transaction_t	*transaction, *new_transaction = NULL;
 	tid_t		tid;
@@ -124,7 +125,7 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 	unsigned long ts = jiffies;
 
 	if (nblocks > journal->j_max_transaction_buffers) {
-		printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
+		printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n",
 		       current->comm, nblocks,
 		       journal->j_max_transaction_buffers);
 		return -ENOSPC;
@@ -320,7 +321,7 @@ static handle_t *new_handle(int nblocks)
  * Return a pointer to a newly allocated handle, or an ERR_PTR() value
  * on failure.
  */
-handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int gfp_mask)
+handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask)
 {
 	handle_t *handle = journal_current_handle();
 	int err;
@@ -443,7 +444,7 @@ out:
  * transaction capabable of guaranteeing the requested number of
  * credits.
  */
-int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
+int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
@@ -563,7 +564,7 @@ static void warn_dirty_buffer(struct buffer_head *bh)
 	char b[BDEVNAME_SIZE];
 
 	printk(KERN_WARNING
-	       "JBD: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+	       "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
 	       "There's a risk of filesystem corruption in case of system "
 	       "crash.\n",
 	       bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
@@ -1049,6 +1050,10 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh,
  * mark dirty metadata which needs to be journaled as part of the current
  * transaction.
  *
+ * The buffer must have previously had jbd2_journal_get_write_access()
+ * called so that it has a valid journal_head attached to the buffer
+ * head.
+ *
  * The buffer is placed on the transaction's metadata list and is marked
  * as belonging to the transaction.
  *
@@ -1065,11 +1070,16 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
 	struct journal_head *jh = bh2jh(bh);
+	int ret = 0;
 
 	jbd_debug(5, "journal_head %p\n", jh);
 	JBUFFER_TRACE(jh, "entry");
 	if (is_handle_aborted(handle))
 		goto out;
+	if (!buffer_jbd(bh)) {
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	jbd_lock_bh_state(bh);
 
@@ -1093,8 +1103,20 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	 */
 	if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) {
 		JBUFFER_TRACE(jh, "fastpath");
-		J_ASSERT_JH(jh, jh->b_transaction ==
-					journal->j_running_transaction);
+		if (unlikely(jh->b_transaction !=
+			     journal->j_running_transaction)) {
+			printk(KERN_EMERG "JBD: %s: "
+			       "jh->b_transaction (%llu, %p, %u) != "
+			       "journal->j_running_transaction (%p, %u)",
+			       journal->j_devname,
+			       (unsigned long long) bh->b_blocknr,
+			       jh->b_transaction,
+			       jh->b_transaction ? jh->b_transaction->t_tid : 0,
+			       journal->j_running_transaction,
+			       journal->j_running_transaction ?
+			       journal->j_running_transaction->t_tid : 0);
+			ret = -EINVAL;
+		}
 		goto out_unlock_bh;
 	}
 
@@ -1108,9 +1130,32 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	 */
 	if (jh->b_transaction != transaction) {
 		JBUFFER_TRACE(jh, "already on other transaction");
-		J_ASSERT_JH(jh, jh->b_transaction ==
-					journal->j_committing_transaction);
-		J_ASSERT_JH(jh, jh->b_next_transaction == transaction);
+		if (unlikely(jh->b_transaction !=
+			     journal->j_committing_transaction)) {
+			printk(KERN_EMERG "JBD: %s: "
+			       "jh->b_transaction (%llu, %p, %u) != "
+			       "journal->j_committing_transaction (%p, %u)",
+			       journal->j_devname,
+			       (unsigned long long) bh->b_blocknr,
+			       jh->b_transaction,
+			       jh->b_transaction ? jh->b_transaction->t_tid : 0,
+			       journal->j_committing_transaction,
+			       journal->j_committing_transaction ?
+			       journal->j_committing_transaction->t_tid : 0);
+			ret = -EINVAL;
+		}
+		if (unlikely(jh->b_next_transaction != transaction)) {
+			printk(KERN_EMERG "JBD: %s: "
+			       "jh->b_next_transaction (%llu, %p, %u) != "
+			       "transaction (%p, %u)",
+			       journal->j_devname,
+			       (unsigned long long) bh->b_blocknr,
+			       jh->b_next_transaction,
+			       jh->b_next_transaction ?
+			       jh->b_next_transaction->t_tid : 0,
+			       transaction, transaction->t_tid);
+			ret = -EINVAL;
+		}
 		/* And this case is illegal: we can't reuse another
 		 * transaction's data buffer, ever. */
 		goto out_unlock_bh;
@@ -1127,7 +1172,8 @@ out_unlock_bh:
 	jbd_unlock_bh_state(bh);
 out:
 	JBUFFER_TRACE(jh, "exit");
-	return 0;
+	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
+	return ret;
 }
 
 /*

include/linux/ext2_fs.h

@@ -197,8 +197,8 @@ struct ext2_group_desc
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
-			   EXT2_SYNC_FL | EXT2_IMMUTABLE_FL | EXT2_APPEND_FL |\
-			   EXT2_NODUMP_FL | EXT2_NOATIME_FL | EXT2_COMPRBLK_FL|\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
 			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
 			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
 

include/linux/ext3_fs.h

@@ -180,8 +180,8 @@ struct ext3_group_desc
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\
-			   EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\
-			   EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\
+			   EXT3_SYNC_FL | EXT3_NODUMP_FL |\
+			   EXT3_NOATIME_FL | EXT3_COMPRBLK_FL |\
 			   EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\
 			   EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL)
 

include/linux/fs.h

@@ -770,12 +770,13 @@ struct inode {
 	unsigned long		i_ino;
 	unsigned int		i_nlink;
 	dev_t			i_rdev;
-	loff_t			i_size;
 	struct timespec		i_atime;
 	struct timespec		i_mtime;
 	struct timespec		i_ctime;
-	unsigned int		i_blkbits;
+	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
+	unsigned short          i_bytes;
 	blkcnt_t		i_blocks;
+	loff_t			i_size;
 
 #ifdef __NEED_I_SIZE_ORDERED
 	seqcount_t		i_size_seqcount;
@@ -783,7 +784,6 @@ struct inode {
 
 	/* Misc */
 	unsigned long		i_state;
-	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	struct mutex		i_mutex;
 
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
@@ -797,9 +797,10 @@ struct inode {
 		struct rcu_head		i_rcu;
 	};
 	atomic_t		i_count;
+	unsigned int		i_blkbits;
 	u64			i_version;
-	unsigned short          i_bytes;
 	atomic_t		i_dio_count;
+	atomic_t		i_writecount;
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
 	struct address_space	i_data;
@@ -823,7 +824,6 @@ struct inode {
 #ifdef CONFIG_IMA
 	atomic_t		i_readcount; /* struct files open RO */
 #endif
-	atomic_t		i_writecount;
 	void			*i_private; /* fs or device private pointer */
 };
 

include/linux/jbd.h

@@ -244,6 +244,7 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)	BUG_ON(!(assert))
 
@@ -270,69 +271,6 @@ typedef struct journal_superblock_s
 #define J_EXPECT_JH(jh, expr, why...)	__journal_expect(expr, ## why)
 #endif
 
-enum jbd_state_bits {
-	BH_JBD			/* Has an attached ext3 journal_head */
-	  = BH_PrivateStart,
-	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
-	BH_Freed,		/* Has been freed (truncated) */
-	BH_Revoked,		/* Has been revoked from the log */
-	BH_RevokeValid,		/* Revoked flag is valid */
-	BH_JBDDirty,		/* Is dirty but journaled */
-	BH_State,		/* Pins most journal_head state */
-	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
-	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-
-static inline struct buffer_head *jh2bh(struct journal_head *jh)
-{
-	return jh->b_bh;
-}
-
-static inline struct journal_head *bh2jh(struct buffer_head *bh)
-{
-	return bh->b_private;
-}
-
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_State, &bh->b_state);
-}
-
-static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_JournalHead, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_JournalHead, &bh->b_state);
-}
-
 struct jbd_revoke_table_s;
 
 /**

include/linux/jbd2.h

@@ -275,6 +275,7 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)	BUG_ON(!(assert))
 
@@ -302,70 +303,6 @@ typedef struct journal_superblock_s
 #define J_EXPECT_JH(jh, expr, why...)	__journal_expect(expr, ## why)
 #endif
 
-enum jbd_state_bits {
-	BH_JBD			/* Has an attached ext3 journal_head */
-	  = BH_PrivateStart,
-	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
-	BH_Freed,		/* Has been freed (truncated) */
-	BH_Revoked,		/* Has been revoked from the log */
-	BH_RevokeValid,		/* Revoked flag is valid */
-	BH_JBDDirty,		/* Is dirty but journaled */
-	BH_State,		/* Pins most journal_head state */
-	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
-	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
-	BH_JBDPrivateStart,	/* First bit available for private use by FS */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-
-static inline struct buffer_head *jh2bh(struct journal_head *jh)
-{
-	return jh->b_bh;
-}
-
-static inline struct journal_head *bh2jh(struct buffer_head *bh)
-{
-	return bh->b_private;
-}
-
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_State, &bh->b_state);
-}
-
-static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_JournalHead, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_JournalHead, &bh->b_state);
-}
-
 /* Flags in jbd_inode->i_flags */
 #define __JI_COMMIT_RUNNING 0
 /* Commit of the inode data in progress. We use this flag to protect us from
@@ -1106,9 +1043,9 @@ static inline handle_t *journal_current_handle(void)
  */
 
 extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
-extern handle_t *jbd2__journal_start(journal_t *, int nblocks, int gfp_mask);
+extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask);
 extern int	 jbd2_journal_restart(handle_t *, int nblocks);
-extern int	 jbd2__journal_restart(handle_t *, int nblocks, int gfp_mask);
+extern int	 jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask);
 extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);

include/linux/jbd_common.h

@@ -0,0 +1,68 @@
+#ifndef _LINUX_JBD_STATE_H
+#define _LINUX_JBD_STATE_H
+
+enum jbd_state_bits {
+	BH_JBD			/* Has an attached ext3 journal_head */
+	  = BH_PrivateStart,
+	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
+	BH_Freed,		/* Has been freed (truncated) */
+	BH_Revoked,		/* Has been revoked from the log */
+	BH_RevokeValid,		/* Revoked flag is valid */
+	BH_JBDDirty,		/* Is dirty but journaled */
+	BH_State,		/* Pins most journal_head state */
+	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
+	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
+	BH_JBDPrivateStart,	/* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+
+static inline struct buffer_head *jh2bh(struct journal_head *jh)
+{
+	return jh->b_bh;
+}
+
+static inline struct journal_head *bh2jh(struct buffer_head *bh)
+{
+	return bh->b_private;
+}
+
+static inline void jbd_lock_bh_state(struct buffer_head *bh)
+{
+	bit_spin_lock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_trylock_bh_state(struct buffer_head *bh)
+{
+	return bit_spin_trylock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
+{
+	return bit_spin_is_locked(BH_State, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_state(struct buffer_head *bh)
+{
+	bit_spin_unlock(BH_State, &bh->b_state);
+}
+
+static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
+{
+	bit_spin_lock(BH_JournalHead, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
+{
+	bit_spin_unlock(BH_JournalHead, &bh->b_state);
+}
+
+#endif

include/trace/events/ext4.h

@@ -9,9 +9,12 @@
 
 struct ext4_allocation_context;
 struct ext4_allocation_request;
+struct ext4_extent;
 struct ext4_prealloc_space;
 struct ext4_inode_info;
 struct mpage_da_data;
+struct ext4_map_blocks;
+struct ext4_extent;
 
 #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
 
@@ -1032,9 +1035,9 @@ TRACE_EVENT(ext4_forget,
 );
 
 TRACE_EVENT(ext4_da_update_reserve_space,
-	TP_PROTO(struct inode *inode, int used_blocks),
+	TP_PROTO(struct inode *inode, int used_blocks, int quota_claim),
 
-	TP_ARGS(inode, used_blocks),
+	TP_ARGS(inode, used_blocks, quota_claim),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
@@ -1045,6 +1048,7 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 		__field(	int,	reserved_data_blocks	)
 		__field(	int,	reserved_meta_blocks	)
 		__field(	int,	allocated_meta_blocks	)
+		__field(	int,	quota_claim		)
 	),
 
 	TP_fast_assign(
@@ -1053,19 +1057,24 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 		__entry->mode	= inode->i_mode;
 		__entry->i_blocks = inode->i_blocks;
 		__entry->used_blocks = used_blocks;
-		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
-		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
-		__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
+		__entry->reserved_data_blocks =
+				EXT4_I(inode)->i_reserved_data_blocks;
+		__entry->reserved_meta_blocks =
+				EXT4_I(inode)->i_reserved_meta_blocks;
+		__entry->allocated_meta_blocks =
+				EXT4_I(inode)->i_allocated_meta_blocks;
+		__entry->quota_claim = quota_claim;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d "
 		  "reserved_data_blocks %d reserved_meta_blocks %d "
-		  "allocated_meta_blocks %d",
+		  "allocated_meta_blocks %d quota_claim %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->mode, __entry->i_blocks,
 		  __entry->used_blocks, __entry->reserved_data_blocks,
-		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
+		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks,
+		  __entry->quota_claim)
 );
 
 TRACE_EVENT(ext4_da_reserve_space,
@@ -1386,6 +1395,87 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit,
 	TP_ARGS(inode)
 );
 
+/* 'ux' is the uninitialized extent. */
+TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+		 struct ext4_extent *ux),
+
+	TP_ARGS(inode, map, ux),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	m_lblk	)
+		__field(	unsigned,	m_len	)
+		__field(	ext4_lblk_t,	u_lblk	)
+		__field(	unsigned,	u_len	)
+		__field(	ext4_fsblk_t,	u_pblk	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->m_lblk		= map->m_lblk;
+		__entry->m_len		= map->m_len;
+		__entry->u_lblk		= le32_to_cpu(ux->ee_block);
+		__entry->u_len		= ext4_ext_get_actual_len(ux);
+		__entry->u_pblk		= ext4_ext_pblock(ux);
+	),
+
+	TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u u_lblk %u u_len %u "
+		  "u_pblk %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->m_lblk, __entry->m_len,
+		  __entry->u_lblk, __entry->u_len, __entry->u_pblk)
+);
+
+/*
+ * 'ux' is the uninitialized extent.
+ * 'ix' is the initialized extent to which blocks are transferred.
+ */
+TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath,
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+		 struct ext4_extent *ux, struct ext4_extent *ix),
+
+	TP_ARGS(inode, map, ux, ix),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	m_lblk	)
+		__field(	unsigned,	m_len	)
+		__field(	ext4_lblk_t,	u_lblk	)
+		__field(	unsigned,	u_len	)
+		__field(	ext4_fsblk_t,	u_pblk	)
+		__field(	ext4_lblk_t,	i_lblk	)
+		__field(	unsigned,	i_len	)
+		__field(	ext4_fsblk_t,	i_pblk	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->m_lblk		= map->m_lblk;
+		__entry->m_len		= map->m_len;
+		__entry->u_lblk		= le32_to_cpu(ux->ee_block);
+		__entry->u_len		= ext4_ext_get_actual_len(ux);
+		__entry->u_pblk		= ext4_ext_pblock(ux);
+		__entry->i_lblk		= le32_to_cpu(ix->ee_block);
+		__entry->i_len		= ext4_ext_get_actual_len(ix);
+		__entry->i_pblk		= ext4_ext_pblock(ix);
+	),
+
+	TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u "
+		  "u_lblk %u u_len %u u_pblk %llu "
+		  "i_lblk %u i_len %u i_pblk %llu ",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->m_lblk, __entry->m_len,
+		  __entry->u_lblk, __entry->u_len, __entry->u_pblk,
+		  __entry->i_lblk, __entry->i_len, __entry->i_pblk)
+);
+
 DECLARE_EVENT_CLASS(ext4__map_blocks_enter,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
 		 unsigned int len, unsigned int flags),
@@ -1589,6 +1679,382 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free,
 	TP_ARGS(sb, group, start, len)
 );
 
+TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+		 unsigned int allocated, ext4_fsblk_t newblock),
+
+	TP_ARGS(inode, map, allocated, newblock),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino		)
+		__field(	dev_t,		dev		)
+		__field(	ext4_lblk_t,	lblk		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	unsigned int,	len		)
+		__field(	int,		flags		)
+		__field(	unsigned int,	allocated	)
+		__field(	ext4_fsblk_t,	newblk		)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->lblk		= map->m_lblk;
+		__entry->pblk		= map->m_pblk;
+		__entry->len		= map->m_len;
+		__entry->flags		= map->m_flags;
+		__entry->allocated	= allocated;
+		__entry->newblk		= newblock;
+	),
+
+	TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d"
+		  "allocated %d newblock %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->lblk, (unsigned long long) __entry->pblk,
+		  __entry->len, __entry->flags,
+		  (unsigned int) __entry->allocated,
+		  (unsigned long long) __entry->newblk)
+);
+
+TRACE_EVENT(ext4_get_implied_cluster_alloc_exit,
+	TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret),
+
+	TP_ARGS(sb, map, ret),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	lblk	)
+		__field(	ext4_fsblk_t,	pblk	)
+		__field(	unsigned int,	len	)
+		__field(	unsigned int,	flags	)
+		__field(	int,		ret	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->lblk	= map->m_lblk;
+		__entry->pblk	= map->m_pblk;
+		__entry->len	= map->m_len;
+		__entry->flags	= map->m_flags;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->lblk, (unsigned long long) __entry->pblk,
+		  __entry->len, __entry->flags, __entry->ret)
+);
+
+TRACE_EVENT(ext4_ext_put_in_cache,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len,
+		 ext4_fsblk_t start),
+
+	TP_ARGS(inode, lblk, len, start),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	lblk	)
+		__field(	unsigned int,	len	)
+		__field(	ext4_fsblk_t,	start	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->lblk	= lblk;
+		__entry->len	= len;
+		__entry->start	= start;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u len %u start %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->lblk,
+		  __entry->len,
+		  (unsigned long long) __entry->start)
+);
+
+TRACE_EVENT(ext4_ext_in_cache,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk, int ret),
+
+	TP_ARGS(inode, lblk, ret),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	lblk	)
+		__field(	int,		ret	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->lblk	= lblk;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u ret %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->lblk,
+		  __entry->ret)
+
+);
+
+TRACE_EVENT(ext4_find_delalloc_range,
+	TP_PROTO(struct inode *inode, ext4_lblk_t from, ext4_lblk_t to,
+		int reverse, int found, ext4_lblk_t found_blk),
+
+	TP_ARGS(inode, from, to, reverse, found, found_blk),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino		)
+		__field(	dev_t,		dev		)
+		__field(	ext4_lblk_t,	from		)
+		__field(	ext4_lblk_t,	to		)
+		__field(	int,		reverse		)
+		__field(	int,		found		)
+		__field(	ext4_lblk_t,	found_blk	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->from		= from;
+		__entry->to		= to;
+		__entry->reverse	= reverse;
+		__entry->found		= found;
+		__entry->found_blk	= found_blk;
+	),
+
+	TP_printk("dev %d,%d ino %lu from %u to %u reverse %d found %d "
+		  "(blk = %u)",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->from, (unsigned) __entry->to,
+		  __entry->reverse, __entry->found,
+		  (unsigned) __entry->found_blk)
+);
+
+TRACE_EVENT(ext4_get_reserved_cluster_alloc,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len),
+
+	TP_ARGS(inode, lblk, len),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	lblk	)
+		__field(	unsigned int,	len	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->lblk	= lblk;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u len %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->lblk,
+		  __entry->len)
+);
+
+TRACE_EVENT(ext4_ext_show_extent,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
+		 unsigned short len),
+
+	TP_ARGS(inode, lblk, pblk, len),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	lblk	)
+		__field(	ext4_fsblk_t,	pblk	)
+		__field(	unsigned short,	len	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->lblk	= lblk;
+		__entry->pblk	= pblk;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->lblk,
+		  (unsigned long long) __entry->pblk,
+		  (unsigned short) __entry->len)
+);
+
+TRACE_EVENT(ext4_remove_blocks,
+	    TP_PROTO(struct inode *inode, struct ext4_extent *ex,
+		ext4_lblk_t from, ext4_fsblk_t to,
+		ext4_fsblk_t partial_cluster),
+
+	TP_ARGS(inode, ex, from, to, partial_cluster),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	ee_lblk	)
+		__field(	ext4_fsblk_t,	ee_pblk	)
+		__field(	unsigned short,	ee_len	)
+		__field(	ext4_lblk_t,	from	)
+		__field(	ext4_lblk_t,	to	)
+		__field(	ext4_fsblk_t,	partial	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ee_lblk	= cpu_to_le32(ex->ee_block);
+		__entry->ee_pblk	= ext4_ext_pblock(ex);
+		__entry->ee_len		= ext4_ext_get_actual_len(ex);
+		__entry->from		= from;
+		__entry->to		= to;
+		__entry->partial	= partial_cluster;
+	),
+
+	TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]"
+		  "from %u to %u partial_cluster %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->ee_lblk,
+		  (unsigned long long) __entry->ee_pblk,
+		  (unsigned short) __entry->ee_len,
+		  (unsigned) __entry->from,
+		  (unsigned) __entry->to,
+		  (unsigned) __entry->partial)
+);
+
+TRACE_EVENT(ext4_ext_rm_leaf,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start,
+		 struct ext4_extent *ex, ext4_fsblk_t partial_cluster),
+
+	TP_ARGS(inode, start, ex, partial_cluster),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	start	)
+		__field(	ext4_lblk_t,	ee_lblk	)
+		__field(	ext4_fsblk_t,	ee_pblk	)
+		__field(	short,		ee_len	)
+		__field(	ext4_fsblk_t,	partial	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->start		= start;
+		__entry->ee_lblk	= le32_to_cpu(ex->ee_block);
+		__entry->ee_pblk	= ext4_ext_pblock(ex);
+		__entry->ee_len		= ext4_ext_get_actual_len(ex);
+		__entry->partial	= partial_cluster;
+	),
+
+	TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]"
+		  "partial_cluster %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->start,
+		  (unsigned) __entry->ee_lblk,
+		  (unsigned long long) __entry->ee_pblk,
+		  (unsigned short) __entry->ee_len,
+		  (unsigned) __entry->partial)
+);
+
+TRACE_EVENT(ext4_ext_rm_idx,
+	TP_PROTO(struct inode *inode, ext4_fsblk_t pblk),
+
+	TP_ARGS(inode, pblk),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_fsblk_t,	pblk	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->pblk	= pblk;
+	),
+
+	TP_printk("dev %d,%d ino %lu index_pblk %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned long long) __entry->pblk)
+);
+
+TRACE_EVENT(ext4_ext_remove_space,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth),
+
+	TP_ARGS(inode, start, depth),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino	)
+		__field(	dev_t,		dev	)
+		__field(	ext4_lblk_t,	start	)
+		__field(	int,		depth	)
+	),
+
+	TP_fast_assign(
+		__entry->ino	= inode->i_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->start	= start;
+		__entry->depth	= depth;
+	),
+
+	TP_printk("dev %d,%d ino %lu since %u depth %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->start,
+		  __entry->depth)
+);
+
+TRACE_EVENT(ext4_ext_remove_space_done,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth,
+		ext4_lblk_t partial, unsigned short eh_entries),
+
+	TP_ARGS(inode, start, depth, partial, eh_entries),
+
+	TP_STRUCT__entry(
+		__field(	ino_t,		ino		)
+		__field(	dev_t,		dev		)
+		__field(	ext4_lblk_t,	start		)
+		__field(	int,		depth		)
+		__field(	ext4_lblk_t,	partial		)
+		__field(	unsigned short,	eh_entries	)
+	),
+
+	TP_fast_assign(
+		__entry->ino		= inode->i_ino;
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->start		= start;
+		__entry->depth		= depth;
+		__entry->partial	= partial;
+		__entry->eh_entries	= eh_entries;
+	),
+
+	TP_printk("dev %d,%d ino %lu since %u depth %d partial %u "
+		  "remaining_entries %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  (unsigned) __entry->start,
+		  __entry->depth,
+		  (unsigned) __entry->partial,
+		  (unsigned short) __entry->eh_entries)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */