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
  ...

21 files changed, 2210 insertions, 1103 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f8224adf496..f6dba4505f1 100644
--- a/fs/ext4/balloc.c
+++ b/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
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cec3145e532..5b0e26a1272 100644
--- a/fs/ext4/ext4.h
+++ b/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_ino