1 files changed, 528 insertions, 429 deletions

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f3624ead4f6..5b87fc36aab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -50,7 +50,7 @@
  * need to use it within a single byte (to ensure we get endianness right).
  * We can use memset for the rest of the bitmap as there are no other users.
  */
-void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 {
 	int i;
 
@@ -65,33 +65,54 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 }
 
 /* Initializes an uninitialized inode bitmap */
-unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
-				ext4_group_t block_group,
-				struct ext4_group_desc *gdp)
+static unsigned ext4_init_inode_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
 {
+	struct ext4_group_info *grp;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
-	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
-		ext4_error(sb, __func__, "Checksum bad for group %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);
+	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 0;
 	}
 
 	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
 			bh->b_data);
+	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
+				   EXT4_INODES_PER_GROUP(sb) / 8);
+	ext4_group_desc_csum_set(sb, block_group, gdp);
 
 	return EXT4_INODES_PER_GROUP(sb);
 }
 
+void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
+{
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+		set_bitmap_uptodate(bh);
+	}
+	unlock_buffer(bh);
+	put_bh(bh);
+}
+
 /*
  * Read the inode allocation bitmap for a given block_group, reading
  * into the specified slot in the superblock's bitmap cache.
@@ -104,37 +125,42 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct ext4_group_desc *desc;
 	struct buffer_head *bh = NULL;
 	ext4_fsblk_t bitmap_blk;
+	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
 		return NULL;
+
 	bitmap_blk = ext4_inode_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, __func__,
-			    "Cannot read inode bitmap - "
+		ext4_error(sb, "Cannot read inode bitmap - "
 			    "block_group = %u, inode_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_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
+		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
+
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -142,23 +168,45 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		 */
 		set_bitmap_uptodate(bh);
 		unlock_buffer(bh);
-		return bh;
+		goto verify;
 	}
 	/*
-	 * 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.
+	 * submit the buffer_head for reading
 	 */
-	set_bitmap_uptodate(bh);
-	if (bh_submit_read(bh) < 0) {
+	trace_ext4_load_inode_bitmap(sb, block_group);
+	bh->b_end_io = ext4_end_bitmap_read;
+	get_bh(bh);
+	submit_bh(READ | REQ_META | REQ_PRIO, bh);
+	wait_on_buffer(bh);
+	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
-		ext4_error(sb, __func__,
-			    "Cannot read inode bitmap - "
-			    "block_group = %u, inode_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_error(sb, "Cannot read inode bitmap - "
+			   "block_group = %u, inode_bitmap = %llu",
+			   block_group, bitmap_blk);
 		return NULL;
 	}
+
+verify:
+	ext4_lock_group(sb, block_group);
+	if (!buffer_verified(bh) &&
+	    !ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
+					   EXT4_INODES_PER_GROUP(sb) / 8)) {
+		ext4_unlock_group(sb, block_group);
+		put_bh(bh);
+		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
+			   "inode_bitmap = %llu", block_group, bitmap_blk);
+		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, desc);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
+		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+		return NULL;
+	}
+	ext4_unlock_group(sb, block_group);
+	set_buffer_verified(bh);
 	return bh;
 }
 
@@ -191,20 +239,22 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
 	int fatal = 0, err, count, cleared;
+	struct ext4_group_info *grp;
 
-	if (atomic_read(&inode->i_count) > 1) {
-		printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
-		       atomic_read(&inode->i_count));
+	if (!sb) {
+		printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
+		       "nonexistent device\n", __func__, __LINE__);
 		return;
 	}
-	if (inode->i_nlink) {
-		printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
-		       inode->i_nlink);
+	if (atomic_read(&inode->i_count) > 1) {
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
+			 __func__, __LINE__, inode->i_ino,
+			 atomic_read(&inode->i_count));
 		return;
 	}
-	if (!sb) {
-		printk(KERN_ERR "ext4_free_inode: inode on "
-		       "nonexistent device\n");
+	if (inode->i_nlink) {
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n",
+			 __func__, __LINE__, inode->i_ino, inode->i_nlink);
 		return;
 	}
 	sbi = EXT4_SB(sb);
@@ -217,26 +267,27 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	 * Note: we must free any quota before locking the superblock,
 	 * as writing the quota to disk may need the lock as well.
 	 */
-	vfs_dq_init(inode);
+	dquot_initialize(inode);
 	ext4_xattr_delete_inode(handle, inode);
-	vfs_dq_free_inode(inode);
-	vfs_dq_drop(inode);
+	dquot_free_inode(inode);
+	dquot_drop(inode);
 
 	is_directory = S_ISDIR(inode->i_mode);
 
 	/* Do this BEFORE marking the inode not in use or returning an error */
-	clear_inode(inode);
+	ext4_clear_inode(inode);
 
 	es = EXT4_SB(sb)->s_es;
 	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
-		ext4_error(sb, "ext4_free_inode",
-			   "reserved or nonexistent inode %lu", ino);
+		ext4_error(sb, "reserved or nonexistent inode %lu", ino);
 		goto error_return;
 	}
 	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
-	if (!bitmap_bh)
+	/* Don't bother if the inode bitmap is corrupt. */
+	grp = ext4_get_group_info(sb, block_group);
+	if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || !bitmap_bh)
 		goto error_return;
 
 	BUFFER_TRACE(bitmap_bh, "get_write_access");
@@ -244,177 +295,66 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	if (fatal)
 		goto error_return;
 
-	/* Ok, now we can actually update the inode bitmaps.. */
-	cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
-					bit, bitmap_bh->b_data);
-	if (!cleared)
-		ext4_error(sb, "ext4_free_inode",
-			   "bit already cleared for inode %lu", ino);
-	else {
-		gdp = ext4_get_group_desc(sb, block_group, &bh2);
-
+	fatal = -ESRCH;
+	gdp = ext4_get_group_desc(sb, block_group, &bh2);
+	if (gdp) {
 		BUFFER_TRACE(bh2, "get_write_access");
 		fatal = ext4_journal_get_write_access(handle, bh2);
-		if (fatal) goto error_return;
-
-		if (gdp) {
-			ext4_lock_group(sb, block_group);
-			count = ext4_free_inodes_count(sb, gdp) + 1;
-			ext4_free_inodes_set(sb, gdp, count);
-			if (is_directory) {
-				count = ext4_used_dirs_count(sb, gdp) - 1;
-				ext4_used_dirs_set(sb, gdp, count);
-				if (sbi->s_log_groups_per_flex) {
-					ext4_group_t f;
-
-					f = ext4_flex_group(sbi, block_group);
-					atomic_dec(&sbi->s_flex_groups[f].free_inodes);
-				}
-
-			}
-			gdp->bg_checksum = ext4_group_desc_csum(sbi,
-							block_group, gdp);
-			ext4_unlock_group(sb, block_group);
-			percpu_counter_inc(&sbi->s_freeinodes_counter);
-			if (is_directory)
-				percpu_counter_dec(&sbi->s_dirs_counter);
-
-			if (sbi->s_log_groups_per_flex) {
-				ext4_group_t f;
-
-				f = ext4_flex_group(sbi, block_group);
-				atomic_inc(&sbi->s_flex_groups[f].free_inodes);
-			}
-		}
-		BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
-		err = ext4_handle_dirty_metadata(handle, NULL, bh2);
-		if (!fatal) fatal = err;
 	}
-	BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-	if (!fatal)
-		fatal = err;
-	sb->s_dirt = 1;
-error_return:
-	brelse(bitmap_bh);
-	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;
-		}
+	ext4_lock_group(sb, block_group);
+	cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data);
+	if (fatal || !cleared) {
+		ext4_unlock_group(sb, block_group);
+		goto out;
 	}
-	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;
+	count = ext4_free_inodes_count(sb, gdp) + 1;
+	ext4_free_inodes_set(sb, gdp, count);
+	if (is_directory) {
+		count = ext4_used_dirs_count(sb, gdp) - 1;
+		ext4_used_dirs_set(sb, gdp, count);
+		percpu_counter_dec(&sbi->s_dirs_counter);
 	}
+	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
+				   EXT4_INODES_PER_GROUP(sb) / 8);
+	ext4_group_desc_csum_set(sb, block_group, gdp);
+	ext4_unlock_group(sb, block_group);
 
-	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;
-		}
+	percpu_counter_inc(&sbi->s_freeinodes_counter);
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t f = ext4_flex_group(sbi, block_group);
 
-		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;
+		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		if (is_directory)
+			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
 	}
-
-	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;
+	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
+out:
+	if (cleared) {
+		BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+		if (!fatal)
+			fatal = err;
+	} else {
+		ext4_error(sb, "bit already cleared for inode %lu", ino);
+		if (gdp && !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 -1;
-out:
-	return 0;
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, fatal);
 }
 
 struct orlov_stats {
+	__u64 free_clusters;
 	__u32 free_inodes;
-	__u32 free_blocks;
 	__u32 used_dirs;
 };
 
@@ -423,15 +363,15 @@ struct orlov_stats {
  * for a particular block group or flex_bg.  If flex_size is 1, then g
  * is a block group number; otherwise it is flex_bg number.
  */
-void get_orlov_stats(struct super_block *sb, ext4_group_t g,
-		       int flex_size, struct orlov_stats *stats)
+static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
+			    int flex_size, struct orlov_stats *stats)
 {
 	struct ext4_group_desc *desc;
 	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
 
 	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 = atomic64_read(&flex_group[g].free_clusters);
 		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
 		return;
 	}
@@ -439,11 +379,11 @@ 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;
 	}
 }
@@ -470,18 +410,18 @@ void get_orlov_stats(struct super_block *sb, ext4_group_t g,
  */
 
 static int find_group_orlov(struct super_block *sb, struct inode *parent,
-			    ext4_group_t *group, int mode,
+			    ext4_group_t *group, umode_t mode,
 			    const struct qstr *qstr)
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	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;
+	unsigned int freei, avefreei, grp_free;
+	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;
@@ -497,14 +437,15 @@ 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) &&
 	    ((parent == sb->s_root->d_inode) ||
-	     (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL))) {
+	     (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
 		int best_ndir = inodes_per_group;
 		int ret = -1;
 
@@ -514,7 +455,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
 			grp = hinfo.hash;
 		} else
-			get_random_bytes(&grp, sizeof(grp));
+			grp = prandom_u32();
 		parent_group = (unsigned)grp % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			g = (parent_group + i) % ngroups;
@@ -525,7 +466,7 @@ 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;
@@ -563,7 +504,7 @@ 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
@@ -582,7 +523,7 @@ 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;
 	}
@@ -595,10 +536,12 @@ fallback_retry:
 	for (i = 0; i < ngroups; i++) {
 		grp = (parent_group + i) % ngroups;
 		desc = ext4_get_group_desc(sb, grp, NULL);
-		if (desc && ext4_free_inodes_count(sb, desc) &&
-		    ext4_free_inodes_count(sb, desc) >= avefreei) {
-			*group = grp;
-			return 0;
+		if (desc) {
+			grp_free = ext4_free_inodes_count(sb, desc);
+			if (grp_free && grp_free >= avefreei) {
+				*group = grp;
+				return 0;
+			}
 		}
 	}
 
@@ -615,7 +558,7 @@ fallback_retry:
 }
 
 static int find_group_other(struct super_block *sb, struct inode *parent,
-			    ext4_group_t *group, int mode)
+			    ext4_group_t *group, umode_t mode)
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
@@ -657,7 +600,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		*group = parent_group + flex_size;
 		if (*group > ngroups)
 			*group = 0;
-		return find_group_orlov(sb, parent, group, mode, 0);
+		return find_group_orlov(sb, parent, group, mode, NULL);
 	}
 
 	/*
@@ -666,7 +609,7 @@ 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;
 
 	/*
@@ -690,7 +633,7 @@ 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;
 	}
 
@@ -711,81 +654,48 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 }
 
 /*
- * claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's ext4_group_lock
- * and clear the uninit flag. The inode bitmap update
- * and group desc uninit flag clear should be done
- * after holding ext4_group_lock so that ext4_read_inode_bitmap
- * doesn't race with the ext4_claim_inode
+ * In no journal mode, if an inode has recently been deleted, we want
+ * to avoid reusing it until we're reasonably sure the inode table
+ * block has been written back to disk.  (Yes, these values are
+ * somewhat arbitrary...)
  */
-static int ext4_claim_inode(struct super_block *sb,
-			struct buffer_head *inode_bitmap_bh,
-			unsigned long ino, ext4_group_t group, int mode)
-{
-	int free = 0, retval = 0, count;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
-
-	ext4_lock_group(sb, group);
-	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
-		/* not a free inode */
-		retval = 1;
-		goto err_ret;
-	}
-	ino++;
-	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
-			ino > EXT4_INODES_PER_GROUP(sb)) {
-		ext4_unlock_group(sb, group);
-		ext4_error(sb, __func__,
-			   "reserved inode or inode > inodes count - "
-			   "block_group = %u, inode=%lu", group,
-			   ino + group * EXT4_INODES_PER_GROUP(sb));
-		return 1;
-	}
-	/* If we didn't allocate from within the initialized part of the inode
-	 * table then we need to initialize up to this inode. */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+#define RECENTCY_MIN	5
+#define RECENTCY_DIRTY	30
 
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
-			/* When marking the block group with
-			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
-			 * on the value of bg_itable_unused even though
-			 * mke2fs could have initialized the same for us.
-			 * Instead we calculated the value below
-			 */
-
-			free = 0;
-		} else {
-			free = EXT4_INODES_PER_GROUP(sb) -
-				ext4_itable_unused_count(sb, gdp);
-		}
+static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
+{
+	struct ext4_group_desc	*gdp;
+	struct ext4_inode	*raw_inode;
+	struct buffer_head	*bh;
+	unsigned long		dtime, now;
+	int	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	int	offset, ret = 0, recentcy = RECENTCY_MIN;
+
+	gdp = ext4_get_group_desc(sb, group, NULL);
+	if (unlikely(!gdp))
+		return 0;
 
+	bh = sb_getblk(sb, ext4_inode_table(sb, gdp) +
+		       (ino / inodes_per_block));
+	if (unlikely(!bh) || !buffer_uptodate(bh))
 		/*
-		 * Check the relative inode number against the last used
-		 * relative inode number in this group. if it is greater
-		 * we need to  update the bg_itable_unused count
-		 *
+		 * If the block is not in the buffer cache, then it
+		 * must have been written out.
 		 */
-		if (ino > free)
-			ext4_itable_unused_set(sb, gdp,
-					(EXT4_INODES_PER_GROUP(sb) - ino));
-	}
-	count = ext4_free_inodes_count(sb, gdp) - 1;
-	ext4_free_inodes_set(sb, gdp, count);
-	if (S_ISDIR(mode)) {
-		count = ext4_used_dirs_count(sb, gdp) + 1;
-		ext4_used_dirs_set(sb, gdp, count);
-		if (sbi->s_log_groups_per_flex) {
-			ext4_group_t f = ext4_flex_group(sbi, group);
+		goto out;
 
-			atomic_inc(&sbi->s_flex_groups[f].free_inodes);
-		}
-	}
-	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
-err_ret:
-	ext4_unlock_group(sb, group);
-	return retval;
+	offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb);
+	raw_inode = (struct ext4_inode *) (bh->b_data + offset);
+	dtime = le32_to_cpu(raw_inode->i_dtime);
+	now = get_seconds();
+	if (buffer_dirty(bh))
+		recentcy += RECENTCY_DIRTY;
+
+	if (dtime && (dtime < now) && (now < dtime + recentcy))
+		ret = 1;
+out:
+	brelse(bh);
+	return ret;
 }
 
 /*
@@ -798,8 +708,10 @@ err_ret:
  * For other inodes, search forward from the parent directory's block
  * 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)
+struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
+			       umode_t mode, const struct qstr *qstr,
+			       __u32 goal, uid_t *owner, int handle_type,
+			       unsigned int line_no, int nblocks)
 {
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
@@ -813,9 +725,8 @@ 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;
+	struct ext4_group_info *grp;
 
 	/* Cannot create files in a deleted directory */
 	if (!dir || !dir->i_nlink)
@@ -830,6 +741,23 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
 	ei = EXT4_I(inode);
 	sbi = EXT4_SB(sb);
 
+	/*
+	 * Initalize owners and quota early so that we don't have to account
+	 * for quota initialization worst case in standard inode creating
+	 * transaction
+	 */
+	if (owner) {
+		inode->i_mode = mode;
+		i_uid_write(inode, owner[0]);
+		i_gid_write(inode, owner[1]);
+	} else if (test_opt(sb, GRPID)) {
+		inode->i_mode = mode;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = dir->i_gid;
+	} else
+		inode_init_owner(inode, dir, mode);
+	dquot_initialize(inode);
+
 	if (!goal)
 		goal = sbi->s_inode_goal;
 
@@ -840,26 +768,9 @@ 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:
@@ -868,65 +779,87 @@ got_group:
 	if (ret2 == -1)
 		goto out;
 
+	/*
+	 * Normally we will only go through one pass of this loop,
+	 * unless we get unlucky and it turns out the group we selected
+	 * had its last inode grabbed by someone else.
+	 */
 	for (i = 0; i < ngroups; i++, ino = 0) {
 		err = -EIO;
 
 		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
 		if (!gdp)
-			goto fail;
+			goto out;
+
+		/*
+		 * Check free inodes count before loading bitmap.
+		 */
+		if (ext4_free_inodes_count(sb, gdp) == 0) {
+			if (++group == ngroups)
+				group = 0;
+			continue;
+		}
+
+		grp = ext4_get_group_info(sb, group);
+		/* Skip groups with already-known suspicious inode tables */
+		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			if (++group == ngroups)
+				group = 0;
+			continue;
+		}
 
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
-		if (!inode_bitmap_bh)
-			goto fail;
+		/* Skip groups with suspicious inode tables */
+		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || !inode_bitmap_bh) {
+			if (++group == ngroups)
+				group = 0;
+			continue;
+		}
 
 repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
 					      inode_bitmap_bh->b_data,
 					      EXT4_INODES_PER_GROUP(sb), ino);
-
-		if (ino < EXT4_INODES_PER_GROUP(sb)) {
-
-			BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle,
-							    inode_bitmap_bh);
-			if (err)
-				goto fail;
-
-			BUFFER_TRACE(group_desc_bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle,
-								group_desc_bh);
-			if (err)
-				goto fail;
-			if (!ext4_claim_inode(sb, inode_bitmap_bh,
-						ino, group, mode)) {
-				/* we won it */
-				BUFFER_TRACE(inode_bitmap_bh,
-					"call ext4_handle_dirty_metadata");
-				err = ext4_handle_dirty_metadata(handle,
-								 inode,
-							inode_bitmap_bh);
-				if (err)
-					goto fail;
-				/* zero bit is inode number 1*/
-				ino++;
-				goto got;
+		if (ino >= EXT4_INODES_PER_GROUP(sb))
+			goto next_group;
+		if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
+			ext4_error(sb, "reserved inode found cleared - "
+				   "inode=%lu", ino + 1);
+			continue;
+		}
+		if ((EXT4_SB(sb)->s_journal == NULL) &&
+		    recently_deleted(sb, group, ino)) {
+			ino++;
+			goto next_inode;
+		}
+		if (!handle) {
+			BUG_ON(nblocks <= 0);
+			handle = __ext4_journal_start_sb(dir->i_sb, line_no,
+							 handle_type, nblocks,
+							 0);
+			if (IS_ERR(handle)) {
+				err = PTR_ERR(handle);
+				ext4_std_error(sb, err);
+				goto out;
 			}
-			/* we lost it */
-			ext4_handle_release_buffer(handle, inode_bitmap_bh);
-			ext4_handle_release_buffer(handle, group_desc_bh);
-
-			if (++ino < EXT4_INODES_PER_GROUP(sb))
-				goto repeat_in_this_group;
 		}
-
-		/*
-		 * This case is possible in concurrent environment.  It is very
-		 * rare.  We cannot repeat the find_group_xxx() call because
-		 * that will simply return the same blockgroup, because the
-		 * group descriptor metadata has not yet been updated.
-		 * So we just go onto the next blockgroup.
-		 */
+		BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+		if (err) {
+			ext4_std_error(sb, err);
+			goto out;
+		}
+		ext4_lock_group(sb, group);
+		ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
+		ext4_unlock_group(sb, group);
+		ino++;		/* the inode bitmap is zero-based */
+		if (!ret2)
+			goto got; /* we grabbed the inode! */
+next_inode:
+		if (ino < EXT4_INODES_PER_GROUP(sb))
+			goto repeat_in_this_group;
+next_group:
 		if (++group == ngroups)
 			group = 0;
 	}
@@ -934,8 +867,22 @@ repeat_in_this_group:
 	goto out;
 
 got:
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
+	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		struct buffer_head *block_bitmap_bh;
 
@@ -944,58 +891,90 @@ got:
 		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
 			brelse(block_bitmap_bh);
-			goto fail;
+			ext4_std_error(sb, err);
+			goto out;
 		}
 
-		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);
+
 		/* 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);
-			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
-								gdp);
+			ext4_free_group_clusters_set(sb, gdp,
+				ext4_free_clusters_after_init(sb, group, gdp));
+			ext4_block_bitmap_csum_set(sb, group, gdp,
+						   block_bitmap_bh);
+			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
+		brelse(block_bitmap_bh);
 
-		/* 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);
+		if (err) {
+			ext4_std_error(sb, err);
+			goto out;
 		}
+	}
 
-		brelse(block_bitmap_bh);
-		if (err)
-			goto fail;
+	/* Update the relevant bg descriptor fields */
+	if (ext4_has_group_desc_csum(sb)) {
+		int free;
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+		ext4_lock_group(sb, group); /* while we modify the bg desc */
+		free = EXT4_INODES_PER_GROUP(sb) -
+			ext4_itable_unused_count(sb, gdp);
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			free = 0;
+		}
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to update the bg_itable_unused count
+		 */
+		if (ino > free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - ino));
+		up_read(&grp->alloc_sem);
+	} else {
+		ext4_lock_group(sb, group);
 	}
+
+	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+	if (S_ISDIR(mode)) {
+		ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1);
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t f = ext4_flex_group(sbi, group);
+
+			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+		}
+	}
+	if (ext4_has_group_desc_csum(sb)) {
+		ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
+					   EXT4_INODES_PER_GROUP(sb) / 8);
+		ext4_group_desc_csum_set(sb, group, gdp);
+	}
+	ext4_unlock_group(sb, group);
+
 	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
-	if (err)
-		goto fail;
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
 
 	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
-	sb->s_dirt = 1;
 
 	if (sbi->s_log_groups_per_flex) {
 		flex_group = ext4_flex_group(sbi, group);
 		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
 	}
 
-	inode->i_uid = current_fsuid();
-	if (test_opt(sb, GRPID))
-		inode->i_gid = dir->i_gid;
-	else if (dir->i_mode & S_ISGID) {
-		inode->i_gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
-	} else
-		inode->i_gid = current_fsgid();
-	inode->i_mode = mode;
-
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
@@ -1006,11 +985,7 @@ 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;
@@ -1022,39 +997,66 @@ got:
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		ext4_error(sb, "failed to insert inode %lu: doubly allocated?",
+			   inode->i_ino);
+		goto out;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
 	spin_unlock(&sbi->s_next_gen_lock);
 
-	ei->i_state = EXT4_STATE_NEW;
+	/* Precompute checksum seed for inode metadata */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+		__u32 csum;
+		__le32 inum = cpu_to_le32(inode->i_ino);
+		__le32 gen = cpu_to_le32(inode->i_generation);
+		csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
+				   sizeof(inum));
+		ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen,
+					      sizeof(gen));
+	}
+
+	ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
+	ext4_set_inode_state(inode, EXT4_STATE_NEW);
 
 	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
 
+	ei->i_inline_off = 0;
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA))
+		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+
 	ret = inode;
-	if (vfs_dq_alloc_inode(inode)) {
-		err = -EDQUOT;
+	err = dquot_alloc_inode(inode);
+	if (err)
 		goto fail_drop;
-	}
 
 	err = ext4_init_acl(handle, inode, dir);
 	if (err)
 		goto fail_free_drop;
 
-	err = ext4_init_security(handle, inode, dir);
+	err = ext4_init_security(handle, inode, dir, qstr);
 	if (err)
 		goto fail_free_drop;
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 		/* set extent flag only for directory, file and normal symlink*/
 		if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
-			EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+			ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
 			ext4_ext_tree_init(handle, inode);
 		}
 	}
 
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
 		ext4_std_error(sb, err);
@@ -1063,24 +1065,17 @@ got:
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
 	trace_ext4_allocate_inode(inode, dir, mode);
-	goto really_out;
-fail:
-	ext4_std_error(sb, err);
-out:
-	iput(inode);
-	ret = ERR_PTR(err);
-really_out:
 	brelse(inode_bitmap_bh);
 	return ret;
 
 fail_free_drop:
-	vfs_dq_free_inode(inode);
-
+	dquot_free_inode(inode);
 fail_drop:
-	vfs_dq_drop(inode);
-	inode->i_flags |= S_NOQUOTA;
-	inode->i_nlink = 0;
+	clear_nlink(inode);
 	unlock_new_inode(inode);
+out:
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
 	iput(inode);
 	brelse(inode_bitmap_bh);
 	return ERR_PTR(err);
@@ -1098,8 +1093,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 
 	/* Error cases - e2fsck has already cleaned up for us */
 	if (ino > max_ino) {
-		ext4_warning(sb, __func__,
-			     "bad orphan ino %lu!  e2fsck was run?", ino);
+		ext4_warning(sb, "bad orphan ino %lu!  e2fsck was run?", ino);
 		goto error;
 	}
 
@@ -1107,8 +1101,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
 	if (!bitmap_bh) {
-		ext4_warning(sb, __func__,
-			     "inode bitmap error for orphan %lu", ino);
+		ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
 		goto error;
 	}
 
@@ -1140,19 +1133,18 @@ iget_failed:
 	err = PTR_ERR(inode);
 	inode = NULL;
 bad_orphan:
-	ext4_warning(sb, __func__,
-		     "bad orphan inode %lu!  e2fsck was run?", ino);
-	printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+	ext4_warning(sb, "bad orphan inode %lu!  e2fsck was run?", ino);
+	printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
 	       bit, (unsigned long long)bitmap_bh->b_blocknr,
 	       ext4_test_bit(bit, bitmap_bh->b_data));
-	printk(KERN_NOTICE "inode=%p\n", inode);
+	printk(KERN_WARNING "inode=%p\n", inode);
 	if (inode) {
-		printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+		printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
 		       is_bad_inode(inode));
-		printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+		printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
 		       NEXT_ORPHAN(inode));
-		printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
-		printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
+		printk(KERN_WARNING "max_ino=%lu\n", max_ino);
+		printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
 		/* Avoid freeing blocks if we got a bad deleted inode */
 		if (inode->i_nlink == 0)
 			inode->i_blocks = 0;
@@ -1187,7 +1179,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		if (!bitmap_bh)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_INODES_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
 		bitmap_count += x;
@@ -1224,3 +1217,109 @@ unsigned long ext4_count_dirs(struct super_block * sb)
 	}
 	return count;
 }
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_new_inode() until we are finished.
+ */
+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);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	struct buffer_head *group_desc_bh;
+	handle_t *handle;
+	ext4_fsblk_t blk;
+	int num, ret = 0, used_blks = 0;
+
+	/* This should not happen, but just to be sure check this */
+	if (sb->s_flags & MS_RDONLY) {
+		ret = 1;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp)
+		goto out;
+
+	/*
+	 * We do not need to lock this, because we are the only one
+	 * handling this flag.
+	 */
+	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+		goto out;
+
+	handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	down_write(&grp->alloc_sem);
+	/*
+	 * If inode bitmap was already initialized there may be some
+	 * used inodes so we need to skip blocks with used inodes in
+	 * inode table.
+	 */
+	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+			    ext4_itable_unused_count(sb, gdp)),
+			    sbi->s_inodes_per_block);
+
+	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+		ext4_error(sb, "Something is wrong with group %u: "
+			   "used itable blocks: %d; "
+			   "itable unused count: %u",
+			   group, used_blks,
+			   ext4_itable_unused_count(sb, gdp));
+		ret = 1;
+		goto err_out;
+	}
+
+	blk = ext4_inode_table(sb, gdp) + used_blks;
+	num = sbi->s_itb_per_group - used_blks;
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	ret = ext4_journal_get_write_access(handle,
+					    group_desc_bh);
+	if (ret)
+		goto err_out;
+
+	/*
+	 * Skip zeroout if the inode table is full. But we set the ZEROED
+	 * flag anyway, because obviously, when it is full it does not need
+	 * further zeroing.
+	 */
+	if (unlikely(num == 0))
+		goto skip_zeroout;
+
+	ext4_debug("going to zero out inode table in group %d\n",
+		   group);
+	ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS);
+	if (ret < 0)
+		goto err_out;
+	if (barrier)
+		blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);
+
+skip_zeroout:
+	ext4_lock_group(sb, group);
+	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	ext4_group_desc_csum_set(sb, group, gdp);
+	ext4_unlock_group(sb, group);
+
+	BUFFER_TRACE(group_desc_bh,
+		     "call ext4_handle_dirty_metadata");
+	ret = ext4_handle_dirty_metadata(handle, NULL,
+					 group_desc_bh);
+
+err_out:
+	up_write(&grp->alloc_sem);
+	ext4_journal_stop(handle);
+out:
+	return ret;
+}