1 files changed, 478 insertions, 339 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 14c3af26c67..fca382037dd 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -21,12 +21,34 @@
 #include "ext4_jbd2.h"
 #include "mballoc.h"
 
+#include <trace/events/ext4.h>
+
+static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+					    ext4_group_t block_group);
 /*
  * balloc.c contains the blocks allocation and deallocation routines
  */
 
 /*
- * Calculate the block group number and offset, given a block number
+ * Calculate block group number for a given block number
+ */
+ext4_group_t ext4_get_group_number(struct super_block *sb,
+				   ext4_fsblk_t block)
+{
+	ext4_group_t group;
+
+	if (test_opt2(sb, STD_GROUP_SIZE))
+		group = (block -
+			 le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
+			(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
+	else
+		ext4_get_group_no_and_offset(sb, block, &group, NULL);
+	return group;
+}
+
+/*
+ * 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)
@@ -35,7 +57,8 @@ 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)
@@ -43,140 +66,195 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 
 }
 
-static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
-			ext4_group_t block_group)
+/*
+ * Check whether the 'block' lives within the 'block_group'. Returns 1 if so
+ * and 0 otherwise.
+ */
+static inline int ext4_block_in_group(struct super_block *sb,
+				      ext4_fsblk_t block,
+				      ext4_group_t block_group)
 {
 	ext4_group_t actual_group;
-	ext4_get_group_no_and_offset(sb, block, &actual_group, NULL);
-	if (actual_group == block_group)
-		return 1;
-	return 0;
+
+	actual_group = ext4_get_group_number(sb, block);
+	return (actual_group == block_group) ? 1 : 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.
+ */
+static 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,
+					 ext4_block_bitmap(sb, gdp) - start);
+		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,
+					 ext4_inode_bitmap(sb, gdp) - start);
+		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, itbl_blk + i - start);
+			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);
+}
+
+/* Initializes an uninitialized block bitmap */
+static 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;
+	struct ext4_group_info *grp;
 
-	free_blocks = group_blocks - bit_max;
+	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(sb, block_group, gdp)) {
+		ext4_error(sb, "Checksum bad for group %u", block_group);
+		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
+		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+		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);
+	ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
+	ext4_group_desc_csum_set(sb, block_group, gdp);
 }
 
+/* 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
@@ -230,14 +308,19 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 	return desc;
 }
 
-static int ext4_valid_block_bitmap(struct super_block *sb,
-					struct ext4_group_desc *desc,
-					unsigned int block_group,
-					struct buffer_head *bh)
+/*
+ * Return the block number which was discovered to be invalid, or 0 if
+ * the block bitmap is valid.
+ */
+static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
+					    struct ext4_group_desc *desc,
+					    ext4_group_t block_group,
+					    struct buffer_head *bh)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t offset;
 	ext4_grpblk_t next_zero_bit;
-	ext4_fsblk_t bitmap_blk;
+	ext4_fsblk_t blk;
 	ext4_fsblk_t group_first_block;
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
@@ -247,41 +330,77 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
 		 * or it has to also read the block group where the bitmaps
 		 * are located to verify they are set.
 		 */
-		return 1;
+		return 0;
 	}
 	group_first_block = ext4_group_first_block_no(sb, block_group);
 
 	/* check whether block bitmap block number is set */
-	bitmap_blk = ext4_block_bitmap(sb, desc);
-	offset = bitmap_blk - group_first_block;
-	if (!ext4_test_bit(offset, bh->b_data))
+	blk = ext4_block_bitmap(sb, desc);
+	offset = blk - group_first_block;
+	if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
-		goto err_out;
+		return blk;
 
 	/* check whether the inode bitmap block number is set */
-	bitmap_blk = ext4_inode_bitmap(sb, desc);
-	offset = bitmap_blk - group_first_block;
-	if (!ext4_test_bit(offset, bh->b_data))
+	blk = ext4_inode_bitmap(sb, desc);
+	offset = blk - group_first_block;
+	if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
-		goto err_out;
+		return blk;
 
 	/* check whether the inode table block number is set */
-	bitmap_blk = ext4_inode_table(sb, desc);
-	offset = bitmap_blk - group_first_block;
+	blk = ext4_inode_table(sb, desc);
+	offset = blk - group_first_block;
 	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
-				offset + EXT4_SB(sb)->s_itb_per_group,
-				offset);
-	if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
-		/* good bitmap for inode tables */
-		return 1;
-
-err_out:
-	ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
-			block_group, bitmap_blk);
+			EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
+			EXT4_B2C(sbi, offset));
+	if (next_zero_bit <
+	    EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group))
+		/* bad bitmap for inode tables */
+		return blk;
 	return 0;
 }
+
+static void ext4_validate_block_bitmap(struct super_block *sb,
+				       struct ext4_group_desc *desc,
+				       ext4_group_t block_group,
+				       struct buffer_head *bh)
+{
+	ext4_fsblk_t	blk;
+	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (buffer_verified(bh))
+		return;
+
+	ext4_lock_group(sb, block_group);
+	blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
+	if (unlikely(blk != 0)) {
+		ext4_unlock_group(sb, block_group);
+		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
+			   block_group, blk);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		return;
+	}
+	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
+			desc, bh))) {
+		ext4_unlock_group(sb, block_group);
+		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		return;
+	}
+	set_buffer_verified(bh);
+	ext4_unlock_group(sb, block_group);
+}
+
 /**
- * ext4_read_block_bitmap()
+ * ext4_read_block_bitmap_nowait()
  * @sb:			super block
  * @block_group:	given block group
  *
@@ -291,10 +410,10 @@ err_out:
  * Return buffer_head on success or NULL in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 {
 	struct ext4_group_desc *desc;
-	struct buffer_head *bh = NULL;
+	struct buffer_head *bh;
 	ext4_fsblk_t bitmap_blk;
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -303,19 +422,19 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	bitmap_blk = ext4_block_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot read block bitmap - "
-			    "block_group = %u, block_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_error(sb, "Cannot get buffer for block bitmap - "
+			   "block_group = %u, block_bitmap = %llu",
+			   block_group, bitmap_blk);
 		return NULL;
 	}
 
 	if (bitmap_uptodate(bh))
-		return bh;
+		goto verify;
 
 	lock_buffer(bh);
 	if (bitmap_uptodate(bh)) {
 		unlock_buffer(bh);
-		return bh;
+		goto verify;
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -334,204 +453,127 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 		 */
 		set_bitmap_uptodate(bh);
 		unlock_buffer(bh);
-		return bh;
-	}
-	/*
-	 * submit the buffer_head for read. We can
-	 * safely mark the bitmap as uptodate now.
-	 * We do it here so the bitmap uptodate bit
-	 * get set with buffer lock held.
-	 */
-	set_bitmap_uptodate(bh);
-	if (bh_submit_read(bh) < 0) {
-		put_bh(bh);
-		ext4_error(sb, "Cannot read block bitmap - "
-			    "block_group = %u, block_bitmap = %llu",
-			    block_group, bitmap_blk);
-		return NULL;
+		goto verify;
 	}
-	ext4_valid_block_bitmap(sb, desc, block_group, bh);
 	/*
-	 * file system mounted not to panic on error,
-	 * continue with corrupt bitmap
+	 * submit the buffer_head for reading
 	 */
+	set_buffer_new(bh);
+	trace_ext4_read_block_bitmap_load(sb, block_group);
+	bh->b_end_io = ext4_end_bitmap_read;
+	get_bh(bh);
+	submit_bh(READ | REQ_META | REQ_PRIO, bh);
 	return bh;
+verify:
+	ext4_validate_block_bitmap(sb, desc, block_group, bh);
+	if (buffer_verified(bh))
+		return bh;
+	put_bh(bh);
+	return NULL;
 }
 
-/**
- * ext4_add_groupblocks() -- Add given blocks to an existing group
- * @handle:			handle to this transaction
- * @sb:				super block
- * @block:			start physcial block to add to the block group
- * @count:			number of blocks to free
- *
- * This marks the blocks as free in the bitmap. We ask the
- * mballoc to reload the buddy after this by setting group
- * EXT4_GROUP_INFO_NEED_INIT_BIT flag
- */
-void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
-			 ext4_fsblk_t block, unsigned long count)
+/* Returns 0 on success, 1 on error */
+int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
+			   struct buffer_head *bh)
 {
-	struct buffer_head *bitmap_bh = NULL;
-	struct buffer_head *gd_bh;
-	ext4_group_t block_group;
-	ext4_grpblk_t bit;
-	unsigned int i;
 	struct ext4_group_desc *desc;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int err = 0, ret, blk_free_count;
-	ext4_grpblk_t blocks_freed;
-	struct ext4_group_info *grp;
-
-	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
 
-	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
-	grp = ext4_get_group_info(sb, block_group);
-	/*
-	 * Check to see if we are freeing blocks across a group
-	 * boundary.
-	 */
-	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
-		goto error_return;
-	}
-	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
-	if (!bitmap_bh)
-		goto error_return;
-	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!buffer_new(bh))
+		return 0;
+	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
-		goto error_return;
-
-	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
-	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, desc),
-		     sbi->s_itb_per_group)) {
-		ext4_error(sb, "Adding blocks in system zones - "
-			   "Block = %llu, count = %lu",
-			   block, count);
-		goto error_return;
+		return 1;
+	wait_on_buffer(bh);
+	if (!buffer_uptodate(bh)) {
+		ext4_error(sb, "Cannot read block bitmap - "
+			   "block_group = %u, block_bitmap = %llu",
+			   block_group, (unsigned long long) bh->b_blocknr);
+		return 1;
 	}
+	clear_buffer_new(bh);
+	/* Panic or remount fs read-only if block bitmap is invalid */
+	ext4_validate_block_bitmap(sb, desc, block_group, bh);
+	/* ...but check for error just in case errors=continue. */
+	return !buffer_verified(bh);
+}
 
-	/*
-	 * We are about to add blocks to the bitmap,
-	 * so we need undo access.
-	 */
-	BUFFER_TRACE(bitmap_bh, "getting undo access");
-	err = ext4_journal_get_undo_access(handle, bitmap_bh);
-	if (err)
-		goto error_return;
-
-	/*
-	 * We are about to modify some metadata.  Call the journal APIs
-	 * to unshare ->b_data if a currently-committing transaction is
-	 * using it
-	 */
-	BUFFER_TRACE(gd_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, gd_bh);
-	if (err)
-		goto error_return;
-	/*
-	 * make sure we don't allow a parallel init on other groups in the
-	 * same buddy cache
-	 */
-	down_write(&grp->alloc_sem);
-	for (i = 0, blocks_freed = 0; i < count; i++) {
-		BUFFER_TRACE(bitmap_bh, "clear bit");
-		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
-						bit + i, bitmap_bh->b_data)) {
-			ext4_error(sb, "bit already cleared for block %llu",
-				   (ext4_fsblk_t)(block + i));
-			BUFFER_TRACE(bitmap_bh, "bit already cleared");
-		} else {
-			blocks_freed++;
-		}
-	}
-	ext4_lock_group(sb, block_group);
-	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
-	ext4_free_blks_set(sb, desc, blk_free_count);
-	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
-	ext4_unlock_group(sb, block_group);
-	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+struct buffer_head *
+ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+	struct buffer_head *bh;
 
-	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);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	if (!bh)
+		return NULL;
+	if (ext4_wait_block_bitmap(sb, block_group, bh)) {
+		put_bh(bh);
+		return NULL;
 	}
-	/*
-	 * request to reload the buddy with the
-	 * new bitmap information
-	 */
-	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
-	grp->bb_free += blocks_freed;
-	up_write(&grp->alloc_sem);
-
-	/* We dirtied the bitmap block */
-	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
-	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-
-	/* And the group descriptor block */
-	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
-	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
-	if (!err)
-		err = ret;
-
-error_return:
-	brelse(bitmap_bh);
-	ext4_std_error(sb, err);
-	return;
+	return bh;
 }
 
 /**
- * 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)
+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);
-		if (dirty_blocks < 0) {
-			printk(KERN_CRIT "Dirty block accounting "
-					"went wrong %lld\n",
-					(long long)dirty_blocks);
-		}
+	s64 free_clusters, dirty_clusters, rsv, resv_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);
+	resv_clusters = atomic64_read(&sbi->s_resv_clusters);
+
+	/*
+	 * r_blocks_count should always be multiple of the cluster ratio so
+	 * we are safe to do a plane bit shift only.
+	 */
+	rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) +
+	      resv_clusters;
+
+	if (free_clusters - (nclusters + rsv + dirty_clusters) <
+					EXT4_FREECLUSTERS_WATERMARK) {
+		free_clusters  = 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 >= (rsv + nclusters + dirty_clusters))
 		return 1;
 
-	/* Hm, nope.  Are (enough) root reserved blocks available? */
-	if (sbi->s_resuid == current_fsuid() ||
-	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
-	    capable(CAP_SYS_RESOURCE)) {
-		if (free_blocks >= (nblocks + dirty_blocks))
+	/* Hm, nope.  Are (enough) root reserved clusters available? */
+	if (uid_eq(sbi->s_resuid, current_fsuid()) ||
+	    (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) ||
+	    capable(CAP_SYS_RESOURCE) ||
+	    (flags & EXT4_MB_USE_ROOT_BLOCKS)) {
+
+		if (free_clusters >= (nclusters + dirty_clusters +
+				      resv_clusters))
+			return 1;
+	}
+	/* No free blocks. Let's see if we can dip into reserved pool */
+	if (flags & EXT4_MB_USE_RESERVED) {
+		if (free_clusters >= (nclusters + dirty_clusters))
 			return 1;
 	}
 
 	return 0;
 }
 
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-						s64 nblocks)
+int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+			     s64 nclusters, unsigned int flags)
 {
-	if (ext4_has_free_blocks(sbi, nblocks)) {
-		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;
@@ -544,14 +586,14 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
  *
  * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
  * it is profitable to retry the operation, this function will wait
- * for the current or commiting transaction to complete, and then
+ * for the current or committing transaction to complete, and then
  * return TRUE.
  *
  * if the total number of retries exceed three times, return FALSE.
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) ||
+	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
 	    (*retries)++ > 3 ||
 	    !EXT4_SB(sb)->s_journal)
 		return 0;
@@ -567,14 +609,15 @@ 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
  * error stores in errp pointer
  */
 ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
-		ext4_fsblk_t goal, unsigned long *count, int *errp)
+				  ext4_fsblk_t goal, unsigned int flags,
+				  unsigned long *count, int *errp)
 {
 	struct ext4_allocation_request ar;
 	ext4_fsblk_t ret;
@@ -584,6 +627,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	ar.inode = inode;
 	ar.goal = goal;
 	ar.len = count ? *count : 1;
+	ar.flags = flags;
 
 	ret = ext4_mb_new_blocks(handle, &ar, errp);
 	if (count)
@@ -592,27 +636,30 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	 * Account for the allocated meta blocks.  We will never
 	 * fail EDQUOT for metdata, but we do account for it.
 	 */
-	if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
+	if (!(*errp) &&
+	    ext4_test_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED)) {
 		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;
 	ext4_group_t i;
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_group_info *grp;
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
@@ -628,20 +675,26 @@ 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);
+		grp = NULL;
+		if (EXT4_SB(sb)->s_group_info)
+			grp = ext4_get_group_info(sb, i);
+		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			desc_count += ext4_free_group_clusters(sb, gdp);
 		brelse(bitmap_bh);
 		bitmap_bh = ext4_read_block_bitmap(sb, i);
 		if (bitmap_bh == NULL)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_CLUSTERS_PER_GROUP(sb) / 8);
 		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_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
 	       desc_count, bitmap_count);
 	return bitmap_count;
 #else
@@ -650,7 +703,11 @@ 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);
+		grp = NULL;
+		if (EXT4_SB(sb)->s_group_info)
+			grp = ext4_get_group_info(sb, i);
+		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			desc_count += ext4_free_group_clusters(sb, gdp);
 	}
 
 	return desc_count;
@@ -659,21 +716,15 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 
 static inline int test_root(ext4_group_t a, int b)
 {
-	int num = b;
-
-	while (a > num)
-		num *= b;
-	return num == a;
-}
-
-static int ext4_group_sparse(ext4_group_t group)
-{
-	if (group <= 1)
-		return 1;
-	if (!(group & 1))
-		return 0;
-	return (test_root(group, 7) || test_root(group, 5) ||
-		test_root(group, 3));
+	while (1) {
+		if (a < b)
+			return 0;
+		if (a == b)
+			return 1;
+		if ((a % b) != 0)
+			return 0;
+		a = a / b;
+	}
 }
 
 /**
@@ -686,11 +737,26 @@ static int ext4_group_sparse(ext4_group_t group)
  */
 int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
 {
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
-			!ext4_group_sparse(group))
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	if (group == 0)
+		return 1;
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) {
+		if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
+		    group == le32_to_cpu(es->s_backup_bgs[1]))
+			return 1;
+		return 0;
+	}
+	if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER))
+		return 1;
+	if (!(group & 1))
 		return 0;
-	return 1;
+	if (test_root(group, 3) || (test_root(group, 5)) ||
+	    test_root(group, 7))
+		return 1;
+
+	return 0;
 }
 
 static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
@@ -740,3 +806,76 @@ 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.
+ */
+static 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
+ *
+ *	Return the ideal location to start allocating blocks for a
+ *	newly created inode.
+ */
+ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_group_t block_group;
+	ext4_grpblk_t colour;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
+	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
+
+	block_group = ei->i_block_group;
+	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+		/*
+		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
+		 * block groups per flexgroup, reserve the first block
+		 * group for directories and special files.  Regular
+		 * files will start at the second block group.  This
+		 * tends to speed up directory access and improves
+		 * fsck times.
+		 */
+		block_group &= ~(flex_size-1);
+		if (S_ISREG(inode->i_mode))
+			block_group++;
+	}
+	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	/*
+	 * If we are doing delayed allocation, we don't need take
+	 * colour into account.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		return bg_start;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
+			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+	return bg_start + colour;
+}
+