Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
"Major changes for 3.14 include support for the newly added ZERO_RANGE
and COLLAPSE_RANGE fallocate operations, and scalability improvements
in the jbd2 layer and in xattr handling when the extended attributes
spill over into an external block.

Other than that, the usual clean ups and minor bug fixes"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (42 commits)
ext4: fix premature freeing of partial clusters split across leaf blocks
ext4: remove unneeded test of ret variable
ext4: fix comment typo
ext4: make ext4_block_zero_page_range static
ext4: atomically set inode->i_flags in ext4_set_inode_flags()
ext4: optimize Hurd tests when reading/writing inodes
ext4: kill i_version support for Hurd-castrated file systems
ext4: each filesystem creates and uses its own mb_cache
fs/mbcache.c: doucple the locking of local from global data
fs/mbcache.c: change block and index hash chain to hlist_bl_node
ext4: Introduce FALLOC_FL_ZERO_RANGE flag for fallocate
ext4: refactor ext4_fallocate code
ext4: Update inode i_size after the preallocation
ext4: fix partial cluster handling for bigalloc file systems
ext4: delete path dealloc code in ext4_ext_handle_uninitialized_extents
ext4: only call sync_filesystm() when remounting read-only
fs: push sync_filesystem() down to the file system's remount_fs()
jbd2: improve error messages for inconsistent journal heads
jbd2: minimize region locked by j_list_lock in jbd2_journal_forget()
jbd2: minimize region locked by j_list_lock in journal_get_create_access()
...

fs/adfs/super.c

···
 
 static int adfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NODIRATIME;
 	return parse_options(sb, data);
 }

fs/affs/super.c

···
 
 	pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data);
 
+	sync_filesystem(sb);
 	*flags |= MS_NODIRATIME;
 
 	memcpy(volume, sbi->s_volume, 32);

fs/befs/linuxvfs.c

···
 static int
 befs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	if (!(*flags & MS_RDONLY))
 		return -EINVAL;
 	return 0;

fs/btrfs/super.c

···
 	unsigned int old_metadata_ratio = fs_info->metadata_ratio;
 	int ret;
 
+	sync_filesystem(sb);
 	btrfs_remount_prepare(fs_info);
 
 	ret = btrfs_parse_options(root, data);

fs/cifs/cifsfs.c

···
 
 static int cifs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NODIRATIME;
 	return 0;
 }

fs/coda/inode.c

···
 
 static int coda_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NOATIME;
 	return 0;
 }

fs/cramfs/inode.c

···
 
 static int cramfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/debugfs/inode.c

···
 	int err;
 	struct debugfs_fs_info *fsi = sb->s_fs_info;
 
+	sync_filesystem(sb);
 	err = debugfs_parse_options(data, &fsi->mount_opts);
 	if (err)
 		goto fail;

fs/devpts/inode.c

···
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
 	struct pts_mount_opts *opts = &fsi->mount_opts;
 
+	sync_filesystem(sb);
 	err = parse_mount_options(data, PARSE_REMOUNT, opts);
 
 	/*

fs/efs/super.c

···
 
 static int efs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/ext2/super.c

···
 	unsigned long old_sb_flags;
 	int err;
 
+	sync_filesystem(sb);
 	spin_lock(&sbi->s_lock);
 
 	/* Store the old options */

fs/ext3/super.c

···
 	int i;
 #endif
 
+	sync_filesystem(sb);
+
 	/* Store the original options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;

fs/ext4/ext4.h

···
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
 #include <crypto/hash.h>
+#include <linux/falloc.h>
 #ifdef __KERNEL__
 #include <linux/compat.h>
 #endif
···
 #define EXT4_GET_BLOCKS_NO_LOCK			0x0100
 	/* Do not put hole in extent cache */
 #define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
+	/* Convert written extents to unwritten */
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0400
 
 /*
  * The bit position of these flags must not overlap with any of the
···
 #define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
 						      size of blocksize * 8
 						      blocks */
+#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
+						      file systems */
 
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
···
 	struct list_head s_es_lru;
 	unsigned long s_es_last_sorted;
 	struct percpu_counter s_extent_cache_cnt;
+	struct mb_cache *s_mb_cache;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 
 	/* Ratelimit ext4 messages. */
···
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 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_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
···
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
 extern int ext4_ext_precache(struct inode *inode);
+extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,
···
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
+extern int mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
+			    struct ext4_extent **extent);
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);

fs/ext4/ext4_jbd2.c

···
 		if (WARN_ON_ONCE(err)) {
 			ext4_journal_abort_handle(where, line, __func__, bh,
 						  handle, err);
+			if (inode == NULL) {
+				pr_err("EXT4: jbd2_journal_dirty_metadata "
+				       "failed: handle type %u started at "
+				       "line %u, credits %u/%u, errcode %d",
+				       handle->h_type,
+				       handle->h_line_no,
+				       handle->h_requested_credits,
+				       handle->h_buffer_credits, err);
+				return err;
+			}
 			ext4_error_inode(inode, where, line,
 					 bh->b_blocknr,
 					 "journal_dirty_metadata failed: "

fs/ext4/extents.c

···
 #include <linux/quotaops.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/falloc.h>
 #include <asm/uaccess.h>
 #include <linux/fiemap.h>
 #include "ext4_jbd2.h"
···
 	 * the extent that was written properly split out and conversion to
 	 * initialized is trivial.
 	 */
-	if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
+	if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
 		return 0;
 
 	ext1_ee_len = ext4_ext_get_actual_len(ex1);
···
 	 * this can result in the top bit of ee_len being set.
 	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
+		return 0;
+	if (ext4_ext_is_uninitialized(ex1) &&
+	    (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
+	     atomic_read(&EXT4_I(inode)->i_unwritten) ||
+	     (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
 		return 0;
 #ifdef AGGRESSIVE_TEST
 	if (ext1_ee_len >= 4)
···
 {
 	struct ext4_extent_header *eh;
 	unsigned int depth, len;
-	int merge_done = 0;
+	int merge_done = 0, uninit;
 
 	depth = ext_depth(inode);
 	BUG_ON(path[depth].p_hdr == NULL);
···
 		if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
 			break;
 		/* merge with next extent! */
+		uninit = ext4_ext_is_uninitialized(ex);
 		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 				+ ext4_ext_get_actual_len(ex + 1));
+		if (uninit)
+			ext4_ext_mark_uninitialized(ex);
 
 		if (ex + 1 < EXT_LAST_EXTENT(eh)) {
 			len = (EXT_LAST_EXTENT(eh) - ex - 1)
···
 	struct ext4_ext_path *npath = NULL;
 	int depth, len, err;
 	ext4_lblk_t next;
-	int mb_flags = 0;
+	int mb_flags = 0, uninit;
 
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
 		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
···
 						  path + depth);
 			if (err)
 				return err;
-
+			uninit = ext4_ext_is_uninitialized(ex);
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
+			if (uninit)
+				ext4_ext_mark_uninitialized(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;
···
 			if (err)
 				return err;
 
+			uninit = ext4_ext_is_uninitialized(ex);
 			ex->ee_block = newext->ee_block;
 			ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
+			if (uninit)
+				ext4_ext_mark_uninitialized(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;
···
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	/*
+	 * If we're starting with an extent other than the last one in the
+	 * node, we need to see if it shares a cluster with the extent to
+	 * the right (towards the end of the file). If its leftmost cluster
+	 * is this extent's rightmost cluster and it is not cluster aligned,
+	 * we'll mark it as a partial that is not to be deallocated.
+	 */
+
+	if (ex != EXT_LAST_EXTENT(eh)) {
+		ext4_fsblk_t current_pblk, right_pblk;
+		long long current_cluster, right_cluster;
+
+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+		right_pblk = ext4_ext_pblock(ex + 1);
+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+		if (current_cluster == right_cluster &&
+			EXT4_PBLK_COFF(sbi, right_pblk))
+			*partial_cluster = -right_cluster;
+	}
+
 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
···
 		err = ext4_ext_correct_indexes(handle, inode, path);
 
 	/*
-	 * Free the partial cluster only if the current extent does not
-	 * reference it. Otherwise we might free used cluster.
+	 * If there's a partial cluster and at least one extent remains in
+	 * the leaf, free the partial cluster if it isn't shared with the
+	 * current extent.  If there's a partial cluster and no extents
+	 * remain in the leaf, it can't be freed here.  It can only be
+	 * freed when it's possible to determine if it's not shared with
+	 * any other extent - when the next leaf is processed or when space
+	 * removal is complete.
 	 */
-	if (*partial_cluster > 0 &&
+	if (*partial_cluster > 0 && eh->eh_entries &&
 	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
 	     *partial_cluster)) {
 		int flags = get_default_free_blocks_flags(inode);
···
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
+ * This works the same way in the case of initialized -> unwritten conversion.
+ *
  * One of more index blocks maybe needed if the extent tree grow after
  * the uninitialized extent split. To prevent ENOSPC occur at the IO
  * complete, we need to split the uninitialized extent before DIO submit
···
  *
  * Returns the size of uninitialized extent to be written on success.
  */
-static int ext4_split_unwritten_extents(handle_t *handle,
+static int ext4_split_convert_extents(handle_t *handle,
 					struct inode *inode,
 					struct ext4_map_blocks *map,
 					struct ext4_ext_path *path,
···
 	unsigned int ee_len;
 	int split_flag = 0, depth;
 
-	ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
-		"block %llu, max_blocks %u\n", inode->i_ino,
-		(unsigned long long)map->m_lblk, map->m_len);
+	ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
+		  __func__, inode->i_ino,
+		  (unsigned long long)map->m_lblk, map->m_len);
 
 	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
 		inode->i_sb->s_blocksize_bits;
···
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
 
-	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
-	split_flag |= EXT4_EXT_MARK_UNINIT2;
-	if (flags & EXT4_GET_BLOCKS_CONVERT)
-		split_flag |= EXT4_EXT_DATA_VALID2;
+	/* Convert to unwritten */
+	if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
+		split_flag |= EXT4_EXT_DATA_VALID1;
+	/* Convert to initialized */
+	} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+		split_flag |= ee_block + ee_len <= eof_block ?
+			      EXT4_EXT_MAY_ZEROOUT : 0;
+		split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+	}
 	flags |= EXT4_GET_BLOCKS_PRE_IO;
 	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
+
+static int ext4_convert_initialized_extents(handle_t *handle,
+					    struct inode *inode,
+					    struct ext4_map_blocks *map,
+					    struct ext4_ext_path *path)
+{
+	struct ext4_extent *ex;
+	ext4_lblk_t ee_block;
+	unsigned int ee_len;
+	int depth;
+	int err = 0;
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+
+	ext_debug("%s: inode %lu, logical"
+		"block %llu, max_blocks %u\n", __func__, inode->i_ino,
+		  (unsigned long long)ee_block, ee_len);
+
+	if (ee_block != map->m_lblk || ee_len > map->m_len) {
+		err = ext4_split_convert_extents(handle, inode, map, path,
+				EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+		if (err < 0)
+			goto out;
+		ext4_ext_drop_refs(path);
+		path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			goto out;
+		}
+		depth = ext_depth(inode);
+		ex = path[depth].p_ext;
+	}
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+	/* first mark the extent as uninitialized */
+	ext4_ext_mark_uninitialized(ex);
+
+	/* note: ext4_ext_correct_indexes() isn't needed here because
+	 * borders are not changed
+	 */
+	ext4_ext_try_to_merge(handle, inode, path, ex);
+
+	/* Mark modified extent as dirty */
+	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+out:
+	ext4_ext_show_leaf(inode, path);
+	return err;
+}
+
 
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 						struct inode *inode,
···
 			     inode->i_ino, (unsigned long long)ee_block, ee_len,
 			     (unsigned long long)map->m_lblk, map->m_len);
 #endif
-		err = ext4_split_unwritten_extents(handle, inode, map, path,
-						   EXT4_GET_BLOCKS_CONVERT);
+		err = ext4_split_convert_extents(handle, inode, map, path,
+						 EXT4_GET_BLOCKS_CONVERT);
 		if (err < 0)
 			goto out;
 		ext4_ext_drop_refs(path);
···
 }
 
 static int
+ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
+			struct ext4_map_blocks *map,
+			struct ext4_ext_path *path, int flags,
+			unsigned int allocated, ext4_fsblk_t newblock)
+{
+	int ret = 0;
+	int err = 0;
+
+	/*
+	 * Make sure that the extent is no bigger than we support with
+	 * uninitialized extent
+	 */
+	if (map->m_len > EXT_UNINIT_MAX_LEN)
+		map->m_len = EXT_UNINIT_MAX_LEN / 2;
+
+	ret = ext4_convert_initialized_extents(handle, inode, map,
+						path);
+	if (ret >= 0) {
+		ext4_update_inode_fsync_trans(handle, inode, 1);
+		err = check_eofblocks_fl(handle, inode, map->m_lblk,
+					 path, map->m_len);
+	} else
+		err = ret;
+	map->m_flags |= EXT4_MAP_UNWRITTEN;
+	if (allocated > map->m_len)
+		allocated = map->m_len;
+	map->m_len = allocated;
+
+	return err ? err : allocated;
+}
+
+static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map,
 			struct ext4_ext_path *path, int flags,
···
 
 	/* get_block() before submit the IO, split the extent */
 	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-		ret = ext4_split_unwritten_extents(handle, inode, map,
-						   path, flags);
+		ret = ext4_split_convert_extents(handle, inode, map,
+					 path, flags | EXT4_GET_BLOCKS_CONVERT);
 		if (ret <= 0)
 			goto out;
 		/*
···
 	map->m_pblk = newblock;
 	map->m_len = allocated;
 out2:
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
 	return err ? err : allocated;
 }
 
···
 	struct ext4_extent newex, *ex, *ex2;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_fsblk_t newblock = 0;
-	int free_on_err = 0, err = 0, depth;
+	int free_on_err = 0, err = 0, depth, ret;
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
···
 		ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
 		unsigned short ee_len;
 
+
 		/*
 		 * Uninitialized extents are treated as holes, except that
 		 * we split out initialized portions during a write.
···
 			ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
 				  ee_block, ee_len, newblock);
 
-			if (!ext4_ext_is_uninitialized(ex))
+			/*
+			 * If the extent is initialized check whether the
+			 * caller wants to convert it to unwritten.
+			 */
+			if ((!ext4_ext_is_uninitialized(ex)) &&
+			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
+				allocated = ext4_ext_convert_initialized_extent(
+						handle, inode, map, path, flags,
+						allocated, newblock);
+				goto out2;
+			} else if (!ext4_ext_is_uninitialized(ex))
 				goto out;
 
-			allocated = ext4_ext_handle_uninitialized_extents(
+			ret = ext4_ext_handle_uninitialized_extents(
 				handle, inode, map, path, flags,
 				allocated, newblock);
-			goto out3;
+			if (ret < 0)
+				err = ret;
+			else
+				allocated = ret;
+			goto out2;
 		}
 	}
 
···
 		kfree(path);
 	}
 
-out3:
 	trace_ext4_ext_map_blocks_exit(inode, flags, map,
 				       err ? err : allocated);
 	ext4_es_lru_add(inode);
···
 	ext4_std_error(inode->i_sb, err);
 }
 
-static void ext4_falloc_update_inode(struct inode *inode,
-				int mode, loff_t new_size, int update_ctime)
+static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
+				  ext4_lblk_t len, int flags, int mode)
 {
-	struct timespec now;
+	struct inode *inode = file_inode(file);
+	handle_t *handle;
+	int ret = 0;
+	int ret2 = 0;
+	int retries = 0;
+	struct ext4_map_blocks map;
+	unsigned int credits;
 
-	if (update_ctime) {
-		now = current_fs_time(inode->i_sb);
-		if (!timespec_equal(&inode->i_ctime, &now))
-			inode->i_ctime = now;
-	}
+	map.m_lblk = offset;
 	/*
-	 * Update only when preallocation was requested beyond
-	 * the file size.
+	 * Don't normalize the request if it can fit in one extent so
+	 * that it doesn't get unnecessarily split into multiple
+	 * extents.
 	 */
-	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+	if (len <= EXT_UNINIT_MAX_LEN)
+		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
+	/*
+	 * credits to insert 1 extent into extent tree
+	 */
+	credits = ext4_chunk_trans_blocks(inode, len);
+
+retry:
+	while (ret >= 0 && ret < len) {
+		map.m_lblk = map.m_lblk + ret;
+		map.m_len = len = len - ret;
+		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+					    credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			break;
+		}
+		ret = ext4_map_blocks(handle, inode, &map, flags);
+		if (ret <= 0) {
+			ext4_debug("inode #%lu: block %u: len %u: "
+				   "ext4_ext_map_blocks returned %d",
+				   inode->i_ino, map.m_lblk,
+				   map.m_len, ret);
+			ext4_mark_inode_dirty(handle, inode);
+			ret2 = ext4_journal_stop(handle);
+			break;
+		}
+		ret2 = ext4_journal_stop(handle);
+		if (ret2)
+			break;
+	}
+	if (ret == -ENOSPC &&
+			ext4_should_retry_alloc(inode->i_sb, &retries)) {
+		ret = 0;
+		goto retry;
+	}
+
+	return ret > 0 ? ret2 : ret;
+}
+
+static long ext4_zero_range(struct file *file, loff_t offset,
+			    loff_t len, int mode)
+{
+	struct inode *inode = file_inode(file);
+	handle_t *handle = NULL;
+	unsigned int max_blocks;
+	loff_t new_size = 0;
+	int ret = 0;
+	int flags;
+	int partial;
+	loff_t start, end;
+	ext4_lblk_t lblk;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned int blkbits = inode->i_blkbits;
+
+	trace_ext4_zero_range(inode, offset, len, mode);
+
+	/*
+	 * Write out all dirty pages to avoid race conditions
+	 * Then release them.
+	 */
+	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		ret = filemap_write_and_wait_range(mapping, offset,
+						   offset + len - 1);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Round up offset. This is not fallocate, we neet to zero out
+	 * blocks, so convert interior block aligned part of the range to
+	 * unwritten and possibly manually zero out unaligned parts of the
+	 * range.
+	 */
+	start = round_up(offset, 1 << blkbits);
+	end = round_down((offset + len), 1 << blkbits);
+
+	if (start < offset || end > offset + len)
+		return -EINVAL;
+	partial = (offset + len) & ((1 << blkbits) - 1);
+
+	lblk = start >> blkbits;
+	max_blocks = (end >> blkbits);
+	if (max_blocks < lblk)
+		max_blocks = 0;
+	else
+		max_blocks -= lblk;
+
+	flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+		EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
+	if (mode & FALLOC_FL_KEEP_SIZE)
+		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+	mutex_lock(&inode->i_mutex);
+
+	/*
+	 * Indirect files do not support unwritten extnets
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		ret = -EOPNOTSUPP;
+		goto out_mutex;
+	}
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+	     offset + len > i_size_read(inode)) {
+		new_size = offset + len;
+		ret = inode_newsize_ok(inode, new_size);
+		if (ret)
+			goto out_mutex;
+		/*
+		 * If we have a partial block after EOF we have to allocate
+		 * the entire block.
+		 */
+		if (partial)
+			max_blocks += 1;
+	}
+
+	if (max_blocks > 0) {
+
+		/* Now release the pages and zero block aligned part of pages*/
+		truncate_pagecache_range(inode, start, end - 1);
+
+		/* Wait all existing dio workers, newcomers will block on i_mutex */
+		ext4_inode_block_unlocked_dio(inode);
+		inode_dio_wait(inode);
+
+		/*
+		 * Remove entire range from the extent status tree.
+		 */
+		ret = ext4_es_remove_extent(inode, lblk, max_blocks);
+		if (ret)
+			goto out_dio;
+
+		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
+					     mode);
+		if (ret)
+			goto out_dio;
+	}
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		ext4_std_error(inode->i_sb, ret);
+		goto out_dio;
+	}
+
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+
+	if (new_size) {
 		if (new_size > i_size_read(inode))
 			i_size_write(inode, new_size);
 		if (new_size > EXT4_I(inode)->i_disksize)
 			ext4_update_i_disksize(inode, new_size);
 	} else {
 		/*
-		 * Mark that we allocate beyond EOF so the subsequent truncate
-		 * can proceed even if the new size is the same as i_size.
-		 */
-		if (new_size > i_size_read(inode))
+		* Mark that we allocate beyond EOF so the subsequent truncate
+		* can proceed even if the new size is the same as i_size.
+		*/
+		if ((offset + len) > i_size_read(inode))
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
 
+	ext4_mark_inode_dirty(handle, inode);
+
+	/* Zero out partial block at the edges of the range */
+	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+
+	if (file->f_flags & O_SYNC)
+		ext4_handle_sync(handle);
+
+	ext4_journal_stop(handle);
+out_dio:
+	ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
 }
 
 /*
···
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
-	loff_t new_size;
+	loff_t new_size = 0;
 	unsigned int max_blocks;
 	int ret = 0;
-	int ret2 = 0;
-	int retries = 0;
 	int flags;
-	struct ext4_map_blocks map;
-	unsigned int credits, blkbits = inode->i_blkbits;
+	ext4_lblk_t lblk;
+	struct timespec tv;
+	unsigned int blkbits = inode->i_blkbits;
 
 	/* Return error if mode is not supported */
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
 		return ext4_punch_hole(inode, offset, len);
+
+	if (mode & FALLOC_FL_COLLAPSE_RANGE)
+		return ext4_collapse_range(inode, offset, len);
 
 	ret = ext4_convert_inline_data(inode);
 	if (ret)
···
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EOPNOTSUPP;
 
+	if (mode & FALLOC_FL_ZERO_RANGE)
+		return ext4_zero_range(file, offset, len, mode);
+
 	trace_ext4_fallocate_enter(inode, offset, len, mode);
-	map.m_lblk = offset >> blkbits;
+	lblk = offset >> blkbits;
 	/*
 	 * We can't just convert len to max_blocks because
 	 * If blocksize = 4096 offset = 3072 and len = 2048
 	 */
 	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
-		- map.m_lblk;
-	/*
-	 * credits to insert 1 extent into extent tree
-	 */
-	credits = ext4_chunk_trans_blocks(inode, max_blocks);
-	mutex_lock(&inode->i_mutex);
-	ret = inode_newsize_ok(inode, (len + offset));
-	if (ret) {
-		mutex_unlock(&inode->i_mutex);
-		trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
-		return ret;
-	}
+		- lblk;
+
 	flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
-	/*
-	 * Don't normalize the request if it can fit in one extent so
-	 * that it doesn't get unnecessarily split into multiple
-	 * extents.
-	 */
-	if (len <= EXT_UNINIT_MAX_LEN << blkbits)
-		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-retry:
-	while (ret >= 0 && ret < max_blocks) {
-		map.m_lblk = map.m_lblk + ret;
-		map.m_len = max_blocks = max_blocks - ret;
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
-					    credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			break;
-		}
-		ret = ext4_map_blocks(handle, inode, &map, flags);
-		if (ret <= 0) {
-#ifdef EXT4FS_DEBUG
-			ext4_warning(inode->i_sb,
-				     "inode #%lu: block %u: len %u: "
-				     "ext4_ext_map_blocks returned %d",
-				     inode->i_ino, map.m_lblk,
-				     map.m_len, ret);
-#endif
-			ext4_mark_inode_dirty(handle, inode);
-			ret2 = ext4_journal_stop(handle);
-			break;
-		}
-		if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
-						blkbits) >> blkbits))
-			new_size = offset + len;
-		else
-			new_size = ((loff_t) map.m_lblk + ret) << blkbits;
+	mutex_lock(&inode->i_mutex);
 
-		ext4_falloc_update_inode(inode, mode, new_size,
-					 (map.m_flags & EXT4_MAP_NEW));
-		ext4_mark_inode_dirty(handle, inode);
-		if ((file->f_flags & O_SYNC) && ret >= max_blocks)
-			ext4_handle_sync(handle);
-		ret2 = ext4_journal_stop(handle);
-		if (ret2)
-			break;
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+	     offset + len > i_size_read(inode)) {
+		new_size = offset + len;
+		ret = inode_newsize_ok(inode, new_size);
+		if (ret)
+			goto out;
 	}
-	if (ret == -ENOSPC &&
-			ext4_should_retry_alloc(inode->i_sb, &retries)) {
-		ret = 0;
-		goto retry;
+
+	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+	if (ret)
+		goto out;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle))
+		goto out;
+
+	tv = inode->i_ctime = ext4_current_time(inode);
+
+	if (new_size) {
+		if (new_size > i_size_read(inode)) {
+			i_size_write(inode, new_size);
+			inode->i_mtime = tv;
+		}
+		if (new_size > EXT4_I(inode)->i_disksize)
+			ext4_update_i_disksize(inode, new_size);
+	} else {
+		/*
+		* Mark that we allocate beyond EOF so the subsequent truncate
+		* can proceed even if the new size is the same as i_size.
+		*/
+		if ((offset + len) > i_size_read(inode))
+			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
+	ext4_mark_inode_dirty(handle, inode);
+	if (file->f_flags & O_SYNC)
+		ext4_handle_sync(handle);
+
+	ext4_journal_stop(handle);
+out:
 	mutex_unlock(&inode->i_mutex);
-	trace_ext4_fallocate_exit(inode, offset, max_blocks,
-				ret > 0 ? ret2 : ret);
-	return ret > 0 ? ret2 : ret;
+	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+	return ret;
 }
 
 /*
···
 	}
 	ext4_es_lru_add(inode);
 	return error;
+}
+
+/*
+ * ext4_access_path:
+ * Function to access the path buffer for marking it dirty.
+ * It also checks if there are sufficient credits left in the journal handle
+ * to update path.
+ */
+static int
+ext4_access_path(handle_t *handle, struct inode *inode,
+		struct ext4_ext_path *path)
+{
+	int credits, err;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+
+	/*
+	 * Check if need to extend journal credits
+	 * 3 for leaf, sb, and inode plus 2 (bmap and group
+	 * descriptor) for each block group; assume two block
+	 * groups
+	 */
+	if (handle->h_buffer_credits < 7) {
+		credits = ext4_writepage_trans_blocks(inode);
+		err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+		/* EAGAIN is success */
+		if (err && err != -EAGAIN)
+			return err;
+	}
+
+	err = ext4_ext_get_access(handle, inode, path);
+	return err;
+}
+
+/*
+ * ext4_ext_shift_path_extents:
+ * Shift the extents of a path structure lying between path[depth].p_ext
+ * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift
+ * from starting block for each extent.
+ */
+static int
+ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
+			    struct inode *inode, handle_t *handle,
+			    ext4_lblk_t *start)
+{
+	int depth, err = 0;
+	struct ext4_extent *ex_start, *ex_last;
+	bool update = 0;
+	depth = path->p_depth;
+
+	while (depth >= 0) {
+		if (depth == path->p_depth) {
+			ex_start = path[depth].p_ext;
+			if (!ex_start)
+				return -EIO;
+
+			ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+			if (!ex_last)
+				return -EIO;
+
+			err = ext4_access_path(handle, inode, path + depth);
+			if (err)
+				goto out;
+
+			if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
+				update = 1;
+
+			*start = ex_last->ee_block +
+				ext4_ext_get_actual_len(ex_last);
+
+			while (ex_start <= ex_last) {
+				ex_start->ee_block -= shift;
+				if (ex_start >
+					EXT_FIRST_EXTENT(path[depth].p_hdr)) {
+					if (ext4_ext_try_to_merge_right(inode,
+						path, ex_start - 1))
+						ex_last--;
+				}
+				ex_start++;
+			}
+			err = ext4_ext_dirty(handle, inode, path + depth);
+			if (err)
+				goto out;
+
+			if (--depth < 0 || !update)
+				break;
+		}
+
+		/* Update index too */
+		err = ext4_access_path(handle, inode, path + depth);
+		if (err)
+			goto out;
+
+		path[depth].p_idx->ei_block -= shift;
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		if (err)
+			goto out;
+
+		/* we are done if current index is not a starting index */
+		if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
+			break;
+
+		depth--;
+	}
+
+out:
+	return err;
+}
+
+/*
+ * ext4_ext_shift_extents:
+ * All the extents which lies in the range from start to the last allocated
+ * block for the file are shifted downwards by shift blocks.
+ * On success, 0 is returned, error otherwise.
+ */
+static int
+ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
+		       ext4_lblk_t start, ext4_lblk_t shift)
+{
+	struct ext4_ext_path *path;
+	int ret = 0, depth;
+	struct ext4_extent *extent;
+	ext4_lblk_t stop_block, current_block;
+	ext4_lblk_t ex_start, ex_end;
+
+	/* Let path point to the last extent */
+	path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	depth = path->p_depth;
+	extent = path[depth].p_ext;
+	if (!extent) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		return ret;
+	}
+
+	stop_block = extent->ee_block + ext4_ext_get_actual_len(extent);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	/* Nothing to shift, if hole is at the end of file */
+	if (start >= stop_block)
+		return ret;
+
+	/*
+	 * Don't start shifting extents until we make sure the hole is big
+	 * enough to accomodate the shift.
+	 */
+	path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+	depth = path->p_depth;
+	extent =  path[depth].p_ext;
+	ex_start = extent->ee_block;
+	ex_end = extent->ee_block + ext4_ext_get_actual_len(extent);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	if ((start == ex_start && shift > ex_start) ||
+	    (shift > start - ex_end))
+		return -EINVAL;
+
+	/* Its safe to start updating extents */
+	while (start < stop_block) {
+		path = ext4_ext_find_extent(inode, start, NULL, 0);
+		if (IS_ERR(path))
+			return PTR_ERR(path);
+		depth = path->p_depth;
+		extent = path[depth].p_ext;
+		current_block = extent->ee_block;
+		if (start > current_block) {
+			/* Hole, move to the next extent */
+			ret = mext_next_extent(inode, path, &extent);
+			if (ret != 0) {
+				ext4_ext_drop_refs(path);
+				kfree(path);
+				if (ret == 1)
+					ret = 0;
+				break;
+			}
+		}
+		ret = ext4_ext_shift_path_extents(path, shift, inode,
+				handle, &start);
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/*
+ * ext4_collapse_range:
+ * This implements the fallocate's collapse range functionality for ext4
+ * Returns: 0 and non-zero on error.
+ */
+int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct super_block *sb = inode->i_sb;
+	ext4_lblk_t punch_start, punch_stop;
+	handle_t *handle;
+	unsigned int credits;
+	loff_t new_size;
+	int ret;
+
+	BUG_ON(offset + len > i_size_read(inode));
+
+	/* Collapse range works only on fs block size aligned offsets. */
+	if (offset & (EXT4_BLOCK_SIZE(sb) - 1) ||
+	    len & (EXT4_BLOCK_SIZE(sb) - 1))
+		return -EINVAL;
+
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	trace_ext4_collapse_range(inode, offset, len);
+
+	punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+	punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+	/* Write out all dirty pages */
+	ret = filemap_write_and_wait_range(inode->i_mapping, offset, -1);
+	if (ret)
+		return ret;
+
+	/* Take mutex lock */
+	mutex_lock(&inode->i_mutex);
+
+	/* It's not possible punch hole on append only file */
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+		ret = -EPERM;
+		goto out_mutex;
+	}
+
+	if (IS_SWAPFILE(inode)) {
+		ret = -ETXTBSY;
+		goto out_mutex;
+	}
+
+	/* Currently just for extent based files */
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		ret = -EOPNOTSUPP;
+		goto out_mutex;
+	}
+
+	truncate_pagecache_range(inode, offset, -1);
+
+	/* Wait for existing dio to complete */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
+	credits = ext4_writepage_trans_blocks(inode);
+	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out_dio;
+	}
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_discard_preallocations(inode);
+
+	ret = ext4_es_remove_extent(inode, punch_start,
+				    EXT_MAX_BLOCKS - punch_start - 1);
+	if (ret) {
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto out_stop;
+	}
+
+	ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
+	if (ret) {
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto out_stop;
+	}
+
+	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
+				     punch_stop - punch_start);
+	if (ret) {
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto out_stop;
+	}
+
+	new_size = i_size_read(inode) - len;
+	truncate_setsize(inode, new_size);
+	EXT4_I(inode)->i_disksize = new_size;
+
+	ext4_discard_preallocations(inode);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+
+out_stop:
+	ext4_journal_stop(handle);
+out_dio:
+	ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
 }

fs/ext4/extents_status.c

···
 	while (node) {
 		struct extent_status *es;
 		es = rb_entry(node, struct extent_status, rb_node);
-		printk(KERN_DEBUG " [%u/%u) %llu %llx",
+		printk(KERN_DEBUG " [%u/%u) %llu %x",
 		       es->es_lblk, es->es_len,
 		       ext4_es_pblock(es), ext4_es_status(es));
 		node = rb_next(node);
···
 				pr_warn("ES insert assertion failed for "
 					"inode: %lu we can find an extent "
 					"at block [%d/%d/%llu/%c], but we "
-					"want to add an delayed/hole extent "
-					"[%d/%d/%llu/%llx]\n",
+					"want to add a delayed/hole extent "
+					"[%d/%d/%llu/%x]\n",
 					inode->i_ino, ee_block, ee_len,
 					ee_start, ee_status ? 'u' : 'w',
 					es->es_lblk, es->es_len,
···
 		if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
 			pr_warn("ES insert assertion failed for inode: %lu "
 				"can't find an extent at block %d but we want "
-				"to add an written/unwritten extent "
-				"[%d/%d/%llu/%llx]\n", inode->i_ino,
+				"to add a written/unwritten extent "
+				"[%d/%d/%llu/%x]\n", inode->i_ino,
 				es->es_lblk, es->es_lblk, es->es_len,
 				ext4_es_pblock(es), ext4_es_status(es));
 		}
···
 			 */
 			pr_warn("ES insert assertion failed for inode: %lu "
 				"We can find blocks but we want to add a "
-				"delayed/hole extent [%d/%d/%llu/%llx]\n",
+				"delayed/hole extent [%d/%d/%llu/%x]\n",
 				inode->i_ino, es->es_lblk, es->es_len,
 				ext4_es_pblock(es), ext4_es_status(es));
 			return;
···
 		if (ext4_es_is_written(es)) {
 			pr_warn("ES insert assertion failed for inode: %lu "
 				"We can't find the block but we want to add "
-				"an written extent [%d/%d/%llu/%llx]\n",
+				"a written extent [%d/%d/%llu/%x]\n",
 				inode->i_ino, es->es_lblk, es->es_len,
 				ext4_es_pblock(es), ext4_es_status(es));
 			return;
···
 
 	newes.es_lblk = lblk;
 	newes.es_len = len;
-	ext4_es_store_pblock(&newes, pblk);
-	ext4_es_store_status(&newes, status);
+	ext4_es_store_pblock_status(&newes, pblk, status);
 	trace_ext4_es_insert_extent(inode, &newes);
 
 	ext4_es_insert_extent_check(inode, &newes);
···
 
 	newes.es_lblk = lblk;
 	newes.es_len = len;
-	ext4_es_store_pblock(&newes, pblk);
-	ext4_es_store_status(&newes, status);
+	ext4_es_store_pblock_status(&newes, pblk, status);
 	trace_ext4_es_cache_extent(inode, &newes);
 
 	if (!len)
···
 
 			newes.es_lblk = end + 1;
 			newes.es_len = len2;
+			block = 0x7FDEADBEEF;
 			if (ext4_es_is_written(&orig_es) ||
-			    ext4_es_is_unwritten(&orig_es)) {
+			    ext4_es_is_unwritten(&orig_es))
 				block = ext4_es_pblock(&orig_es) +
 					orig_es.es_len - len2;
-				ext4_es_store_pblock(&newes, block);
-			}
-			ext4_es_store_status(&newes, ext4_es_status(&orig_es));
+			ext4_es_store_pblock_status(&newes, block,
+						    ext4_es_status(&orig_es));
 			err = __es_insert_extent(inode, &newes);
 			if (err) {
 				es->es_lblk = orig_es.es_lblk;

fs/ext4/extents_status.h

···
 		       (es->es_pblk & ~ES_MASK));
 }
 
+static inline void ext4_es_store_pblock_status(struct extent_status *es,
+					       ext4_fsblk_t pb,
+					       unsigned int status)
+{
+	es->es_pblk = (((ext4_fsblk_t)
+			(status & EXTENT_STATUS_FLAGS) << ES_SHIFT) |
+		       (pb & ~ES_MASK));
+}
+
 extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_lru_add(struct inode *inode);

fs/ext4/inode.c

···
 {
 	struct extent_status es;
 	int retval;
+	int ret = 0;
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
···
 	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
 		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
 		  (unsigned long) map->m_lblk);
+
+	/*
+	 * ext4_map_blocks returns an int, and m_len is an unsigned int
+	 */
+	if (unlikely(map->m_len > INT_MAX))
+		map->m_len = INT_MAX;
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
···
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	}
 	if (retval > 0) {
-		int ret;
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
···
 
 found:
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-		int ret = check_block_validity(inode, map);
+		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
 	}
···
 	 * with buffer head unmapped.
 	 */
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
-		return retval;
+		/*
+		 * If we need to convert extent to unwritten
+		 * we continue and do the actual work in
+		 * ext4_ext_map_blocks()
+		 */
+		if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
+			return retval;
 
 	/*
 	 * Here we clear m_flags because after allocating an new extent,
···
 		ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
 	if (retval > 0) {
-		int ret;
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
···
 has_zeroout:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-		int ret = check_block_validity(inode, map);
+		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
 	}
···
 }
 
 /*
- * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
- * up to the end of the block which corresponds to `from'.
- * This required during truncate. We need to physically zero the tail end
- * of that block so it doesn't yield old data if the file is later grown.
- */
-int ext4_block_truncate_page(handle_t *handle,
-		struct address_space *mapping, loff_t from)
-{
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned length;
-	unsigned blocksize;
-	struct inode *inode = mapping->host;
-
-	blocksize = inode->i_sb->s_blocksize;
-	length = blocksize - (offset & (blocksize - 1));
-
-	return ext4_block_zero_page_range(handle, mapping, from, length);
-}
-
-/*
  * ext4_block_zero_page_range() zeros out a mapping of length 'length'
  * starting from file offset 'from'.  The range to be zero'd must
  * be contained with in one block.  If the specified range exceeds
  * the end of the block it will be shortened to end of the block
  * that cooresponds to 'from'
  */
-int ext4_block_zero_page_range(handle_t *handle,
+static int ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
···
 	return err;
 }
 
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+int ext4_block_truncate_page(handle_t *handle,
+		struct address_space *mapping, loff_t from)
+{
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned length;
+	unsigned blocksize;
+	struct inode *inode = mapping->host;
+
+	blocksize = inode->i_sb->s_blocksize;
+	length = blocksize - (offset & (blocksize - 1));
+
+	return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
 int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t length)
 {
···
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	trace_ext4_punch_hole(inode, offset, length);
+	trace_ext4_punch_hole(inode, offset, length, 0);
 
 	/*
 	 * Write out all dirty pages to avoid race conditions
···
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+
+	/* Now release the pages again to reduce race window */
+	if (last_block_offset > first_block_offset)
+		truncate_pagecache_range(inode, first_block_offset,
+					 last_block_offset);
+
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 out_stop:
···
 
 	/*
 	 * There is a possibility that we're either freeing the inode
-	 * or it completely new indode. In those cases we might not
+	 * or it's a completely new inode. In those cases we might not
 	 * have i_mutex locked because it's not necessary.
 	 */
 	if (!(inode->i_state & (I_NEW|I_FREEING)))
···
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	set_mask_bits(&inode->i_flags,
-		      S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
+	inode_set_flags(inode, new_fl,
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
···
 	EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
 	EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
 
-	inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
-		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-			inode->i_version |=
-			(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+		inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+		if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+			if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+				inode->i_version |=
+		    (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+		}
 	}
 
 	ret = 0;
···
 		goto out_brelse;
 	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
 	raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
-	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
-	    cpu_to_le32(EXT4_OS_HURD))
+	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
 		raw_inode->i_file_acl_high =
 			cpu_to_le16(ei->i_file_acl >> 32);
 	raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
···
 			raw_inode->i_block[block] = ei->i_data[block];
 	}
 
-	raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
-	if (ei->i_extra_isize) {
-		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-			raw_inode->i_version_hi =
-			cpu_to_le32(inode->i_version >> 32);
-		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+		raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+		if (ei->i_extra_isize) {
+			if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+				raw_inode->i_version_hi =
+					cpu_to_le32(inode->i_version >> 32);
+			raw_inode->i_extra_isize =
+				cpu_to_le16(ei->i_extra_isize);
+		}
 	}
 
 	ext4_inode_csum_set(inode, raw_inode, ei);
···
 			return -EIO;
 		}
 
-		if (wbc->sync_mode != WB_SYNC_ALL)
+		/*
+		 * No need to force transaction in WB_SYNC_NONE mode. Also
+		 * ext4_sync_fs() will force the commit after everything is
+		 * written.
+		 */
+		if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 			return 0;
 
 		err = ext4_force_commit(inode->i_sb);
···
 		err = __ext4_get_inode_loc(inode, &iloc, 0);
 		if (err)
 			return err;
-		if (wbc->sync_mode == WB_SYNC_ALL)
+		/*
+		 * sync(2) will flush the whole buffer cache. No need to do
+		 * it here separately for each inode.
+		 */
+		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
 			sync_dirty_buffer(iloc.bh);
 		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,

fs/ext4/ioctl.c

···
 	struct ext4_inode_info *ei_bl;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
-		err = -EINVAL;
-		goto swap_boot_out;
-	}
+	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
+		return -EINVAL;
 
-	if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
-		err = -EPERM;
-		goto swap_boot_out;
-	}
+	if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
+		return -EPERM;
 
 	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
-	if (IS_ERR(inode_bl)) {
-		err = PTR_ERR(inode_bl);
-		goto swap_boot_out;
-	}
+	if (IS_ERR(inode_bl))
+		return PTR_ERR(inode_bl);
 	ei_bl = EXT4_I(inode_bl);
 
 	filemap_flush(inode->i_mapping);
···
 			ext4_mark_inode_dirty(handle, inode);
 		}
 	}
-
 	ext4_journal_stop(handle);
-
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 journal_err_out:
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
-
 	unlock_two_nondirectories(inode, inode_bl);
-
 	iput(inode_bl);
-
-swap_boot_out:
 	return err;
 }
 

fs/ext4/mballoc.c

···
 	ext4_lock_group(ac->ac_sb, group);
 	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
+	ex.fe_logical = 0xDEADFA11; /* debug value */
 
 	if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
 		ext4_fsblk_t start;
···
 			 */
 			break;
 		}
-
+		ex.fe_logical = 0xDEADC0DE; /* debug value */
 		ext4_mb_measure_extent(ac, &ex, e4b);
 
 		i += ex.fe_len;
···
 			max = mb_find_extent(e4b, i, sbi->s_stripe, &ex);
 			if (max >= sbi->s_stripe) {
 				ac->ac_found++;
+				ex.fe_logical = 0xDEADF00D; /* debug value */
 				ac->ac_b_ex = ex;
 				ext4_mb_use_best_found(ac, e4b);
 				break;
···
 			(unsigned long)ac->ac_b_ex.fe_len,
 			(unsigned long)ac->ac_b_ex.fe_logical,
 			(int)ac->ac_criteria);
-	ext4_msg(ac->ac_sb, KERN_ERR, "%lu scanned, %d found",
-		 ac->ac_ex_scanned, ac->ac_found);
+	ext4_msg(ac->ac_sb, KERN_ERR, "%d found", ac->ac_found);
 	ext4_msg(ac->ac_sb, KERN_ERR, "groups: ");
 	ngroups = ext4_get_groups_count(sb);
 	for (i = 0; i < ngroups; i++) {

fs/ext4/mballoc.h

···
 		}							\
 	} while (0)
 #else
-#define mb_debug(n, fmt, a...)
+#define mb_debug(n, fmt, a...)		no_printk(fmt, ## a)
 #endif
 
 #define EXT4_MB_HISTORY_ALLOC		1	/* allocation */
···
 	/* copy of the best found extent taken before preallocation efforts */
 	struct ext4_free_extent ac_f_ex;
 
-	/* number of iterations done. we have to track to limit searching */
-	unsigned long ac_ex_scanned;
 	__u16 ac_groups_scanned;
 	__u16 ac_found;
 	__u16 ac_tail;

fs/ext4/move_extent.c

···
  * ext4_ext_path structure refers to the last extent, or a negative error
  * value on failure.
  */
-static int
+int
 mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 		      struct ext4_extent **extent)
 {
···
 			}
 			if (!buffer_mapped(bh)) {
 				zero_user(page, block_start, blocksize);
-				if (!err)
-					set_buffer_uptodate(bh);
+				set_buffer_uptodate(bh);
 				continue;
 			}
 		}

fs/ext4/super.c

···
 static struct ext4_lazy_init *ext4_li_info;
 static struct mutex ext4_li_mtx;
 static struct ext4_features *ext4_feat;
+static int ext4_mballoc_ready;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
···
 		invalidate_bdev(sbi->journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
+	if (sbi->s_mb_cache) {
+		ext4_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 	sb->s_fs_info = NULL;
···
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
 					     sizeof(struct ext4_inode_info),
···
 		       "feature flags set on rev 0 fs, "
 		       "running e2fsck is recommended");
 
+	if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
+		set_opt2(sb, HURD_COMPAT);
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+					      EXT4_FEATURE_INCOMPAT_64BIT)) {
+			ext4_msg(sb, KERN_ERR,
+				 "The Hurd can't support 64-bit file systems");
+			goto failed_mount;
+		}
+	}
+
 	if (IS_EXT2_SB(sb)) {
 		if (ext2_feature_set_ok(sb))
 			ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
···
 	percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
 
 no_journal:
+	if (ext4_mballoc_ready) {
+		sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
+		if (!sbi->s_mb_cache) {
+			ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+			goto failed_mount_wq;
+		}
+	}
+
 	/*
 	 * Get the # of file system overhead blocks from the
 	 * superblock if present.
···
 		}
 
 		if (*flags & MS_RDONLY) {
+			err = sync_filesystem(sb);
+			if (err < 0)
+				goto restore_opts;
 			err = dquot_suspend(sb, -1);
 			if (err < 0)
 				goto restore_opts;
···
 
 	err = ext4_init_mballoc();
 	if (err)
-		goto out3;
-
-	err = ext4_init_xattr();
-	if (err)
 		goto out2;
+	else
+		ext4_mballoc_ready = 1;
 	err = init_inodecache();
 	if (err)
 		goto out1;
···
 	unregister_as_ext3();
 	destroy_inodecache();
 out1:
-	ext4_exit_xattr();
-out2:
+	ext4_mballoc_ready = 0;
 	ext4_exit_mballoc();
-out3:
+out2:
 	ext4_exit_feat_adverts();
 out4:
 	if (ext4_proc_root)
···
 	unregister_as_ext3();
 	unregister_filesystem(&ext4_fs_type);
 	destroy_inodecache();
-	ext4_exit_xattr();
 	ext4_exit_mballoc();
 	ext4_exit_feat_adverts();
 	remove_proc_entry("fs/ext4", NULL);

fs/ext4/xattr.c

···
 # define ea_bdebug(bh, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
-static void ext4_xattr_cache_insert(struct buffer_head *);
+static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
 static struct buffer_head *ext4_xattr_cache_find(struct inode *,
 						 struct ext4_xattr_header *,
 						 struct mb_cache_entry **);
···
 			      struct ext4_xattr_entry *);
 static int ext4_xattr_list(struct dentry *dentry, char *buffer,
 			   size_t buffer_size);
-
-static struct mb_cache *ext4_xattr_cache;
 
 static const struct xattr_handler *ext4_xattr_handler_map[] = {
 	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
···
 #endif
 	NULL
 };
+
+#define EXT4_GET_MB_CACHE(inode)	(((struct ext4_sb_info *) \
+				inode->i_sb->s_fs_info)->s_mb_cache)
 
 static __le32 ext4_xattr_block_csum(struct inode *inode,
 				    sector_t block_nr,
···
 	struct ext4_xattr_entry *entry;
 	size_t size;
 	int error;
+	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
···
 		error = -EIO;
 		goto cleanup;
 	}
-	ext4_xattr_cache_insert(bh);
+	ext4_xattr_cache_insert(ext4_mb_cache, bh);
 	entry = BFIRST(bh);
 	error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
 	if (error == -EIO)
···
 	struct inode *inode = dentry->d_inode;
 	struct buffer_head *bh = NULL;
 	int error;
+	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
···
 		error = -EIO;
 		goto cleanup;
 	}
-	ext4_xattr_cache_insert(bh);
+	ext4_xattr_cache_insert(ext4_mb_cache, bh);
 	error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
 
 cleanup:
···
 {
 	struct mb_cache_entry *ce = NULL;
 	int error = 0;
+	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
-	ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
+	ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
 	error = ext4_journal_get_write_access(handle, bh);
 	if (error)
 		goto out;
···
 				    size_t *min_offs, void *base, int *total)
 {
 	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-		*total += EXT4_XATTR_LEN(last->e_name_len);
 		if (!last->e_value_block && last->e_value_size) {
 			size_t offs = le16_to_cpu(last->e_value_offs);
 			if (offs < *min_offs)
 				*min_offs = offs;
 		}
+		if (total)
+			*total += EXT4_XATTR_LEN(last->e_name_len);
 	}
 	return (*min_offs - ((void *)last - base) - sizeof(__u32));
 }
···
 	struct ext4_xattr_search *s = &bs->s;
 	struct mb_cache_entry *ce = NULL;
 	int error = 0;
+	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 #define header(x) ((struct ext4_xattr_header *)(x))
 
 	if (i->value && i->value_len > sb->s_blocksize)
 		return -ENOSPC;
 	if (s->base) {
-		ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev,
+		ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
 					bs->bh->b_blocknr);
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
···
 				if (!IS_LAST_ENTRY(s->first))
 					ext4_xattr_rehash(header(s->base),
 							  s->here);
-				ext4_xattr_cache_insert(bs->bh);
+				ext4_xattr_cache_insert(ext4_mb_cache,
+					bs->bh);
 			}
 			unlock_buffer(bs->bh);
 			if (error == -EIO)
···
 			memcpy(new_bh->b_data, s->base, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext4_xattr_cache_insert(new_bh);
+			ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
 			error = ext4_handle_dirty_xattr_block(handle,
 							      inode, new_bh);
 			if (error)
···
 	struct ext4_xattr_block_find *bs = NULL;
 	char *buffer = NULL, *b_entry_name = NULL;
 	size_t min_offs, free;
-	int total_ino, total_blk;
+	int total_ino;
 	void *base, *start, *end;
 	int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
···
 		first = BFIRST(bh);
 		end = bh->b_data + bh->b_size;
 		min_offs = end - base;
-		free = ext4_xattr_free_space(first, &min_offs, base,
-					     &total_blk);
+		free = ext4_xattr_free_space(first, &min_offs, base, NULL);
 		if (free < new_extra_isize) {
 			if (!tried_min_extra_isize && s_min_extra_isize) {
 				tried_min_extra_isize++;
···
  * Returns 0, or a negative error number on failure.
  */
 static void
-ext4_xattr_cache_insert(struct buffer_head *bh)
+ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
 {
 	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
 	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext4_xattr_cache, GFP_NOFS);
+	ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
 	if (!ce) {
 		ea_bdebug(bh, "out of memory");
 		return;
···
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
+	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext4_xattr_cache, inode->i_sb->s_bdev,
+	ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
 				       hash);
 	while (ce) {
 		struct buffer_head *bh;
···
 
 #undef BLOCK_HASH_SHIFT
 
-int __init
-ext4_init_xattr(void)
+#define	HASH_BUCKET_BITS	10
+
+struct mb_cache *
+ext4_xattr_create_cache(char *name)
 {
-	ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
-	if (!ext4_xattr_cache)
-		return -ENOMEM;
-	return 0;
+	return mb_cache_create(name, HASH_BUCKET_BITS);
 }
 
-void
-ext4_exit_xattr(void)
+void ext4_xattr_destroy_cache(struct mb_cache *cache)
 {
-	if (ext4_xattr_cache)
-		mb_cache_destroy(ext4_xattr_cache);
-	ext4_xattr_cache = NULL;
+	if (cache)
+		mb_cache_destroy(cache);
 }
+

fs/ext4/xattr.h

···
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
 
-extern int __init ext4_init_xattr(void);
-extern void ext4_exit_xattr(void);
-
 extern const struct xattr_handler *ext4_xattr_handlers[];
 
 extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
···
 extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 				       struct ext4_xattr_info *i,
 				       struct ext4_xattr_ibody_find *is);
+
+extern struct mb_cache *ext4_xattr_create_cache(char *name);
+extern void ext4_xattr_destroy_cache(struct mb_cache *);
 
 #ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,

fs/f2fs/super.c

···
 	struct f2fs_mount_info org_mount_opt;
 	int err, active_logs;
 
+	sync_filesystem(sb);
+
 	/*
 	 * Save the old mount options in case we
 	 * need to restore them.

fs/fat/inode.c

···
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
 
+	sync_filesystem(sb);
+
 	/* make sure we update state on remount. */
 	new_rdonly = *flags & MS_RDONLY;
 	if (new_rdonly != (sb->s_flags & MS_RDONLY)) {

fs/freevxfs/vxfs_super.c

···
 
 static int vxfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/fuse/inode.c

···
 
 static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	if (*flags & MS_MANDLOCK)
 		return -EINVAL;
 

fs/gfs2/super.c

···
 	struct gfs2_tune *gt = &sdp->sd_tune;
 	int error;
 
+	sync_filesystem(sb);
+
 	spin_lock(&gt->gt_spin);
 	args.ar_commit = gt->gt_logd_secs;
 	args.ar_quota_quantum = gt->gt_quota_quantum;

fs/hfs/super.c

···
 
 static int hfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NODIRATIME;
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;

fs/hfsplus/super.c

···
 
 static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 	if (!(*flags & MS_RDONLY)) {

fs/hpfs/super.c

···
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
 	char *new_opts = kstrdup(data, GFP_KERNEL);
 	
+	sync_filesystem(s);
+
 	*flags |= MS_NOATIME;
 	
 	hpfs_lock(s);

fs/inode.c

···
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 EXPORT_SYMBOL(inode_dio_done);
+
+/*
+ * inode_set_flags - atomically set some inode flags
+ *
+ * Note: the caller should be holding i_mutex, or else be sure that
+ * they have exclusive access to the inode structure (i.e., while the
+ * inode is being instantiated).  The reason for the cmpxchg() loop
+ * --- which wouldn't be necessary if all code paths which modify
+ * i_flags actually followed this rule, is that there is at least one
+ * code path which doesn't today --- for example,
+ * __generic_file_aio_write() calls file_remove_suid() without holding
+ * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ *
+ * In the long run, i_mutex is overkill, and we should probably look
+ * at using the i_lock spinlock to protect i_flags, and then make sure
+ * it is so documented in include/linux/fs.h and that all code follows
+ * the locking convention!!
+ */
+void inode_set_flags(struct inode *inode, unsigned int flags,
+		     unsigned int mask)
+{
+	unsigned int old_flags, new_flags;
+
+	WARN_ON_ONCE(flags & ~mask);
+	do {
+		old_flags = ACCESS_ONCE(inode->i_flags);
+		new_flags = (old_flags & ~mask) | flags;
+	} while (unlikely(cmpxchg(&inode->i_flags, old_flags,
+				  new_flags) != old_flags));
+}
+EXPORT_SYMBOL(inode_set_flags);

fs/isofs/inode.c

···
 
 static int isofs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	if (!(*flags & MS_RDONLY))
 		return -EROFS;
 	return 0;

fs/jbd2/commit.c

···
 	blk_start_plug(&plug);
 	jbd2_journal_write_revoke_records(journal, commit_transaction,
 					  &log_bufs, WRITE_SYNC);
-	blk_finish_plug(&plug);
 
 	jbd_debug(3, "JBD2: commit phase 2b\n");
 
···
 	err = 0;
 	bufs = 0;
 	descriptor = NULL;
-	blk_start_plug(&plug);
 	while (commit_transaction->t_buffers) {
 
 		/* Find the next buffer to be journaled... */
···
 		goto restart_loop;
 	}
 
+	/* Add the transaction to the checkpoint list
+	 * __journal_remove_checkpoint() can not destroy transaction
+	 * under us because it is not marked as T_FINISHED yet */
+	if (journal->j_checkpoint_transactions == NULL) {
+		journal->j_checkpoint_transactions = commit_transaction;
+		commit_transaction->t_cpnext = commit_transaction;
+		commit_transaction->t_cpprev = commit_transaction;
+	} else {
+		commit_transaction->t_cpnext =
+			journal->j_checkpoint_transactions;
+		commit_transaction->t_cpprev =
+			commit_transaction->t_cpnext->t_cpprev;
+		commit_transaction->t_cpnext->t_cpprev =
+			commit_transaction;
+		commit_transaction->t_cpprev->t_cpnext =
+				commit_transaction;
+	}
+	spin_unlock(&journal->j_list_lock);
+
 	/* Done with this transaction! */
 
 	jbd_debug(3, "JBD2: commit phase 7\n");
···
 		atomic_read(&commit_transaction->t_handle_count);
 	trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
 			     commit_transaction->t_tid, &stats.run);
-
-	/*
-	 * Calculate overall stats
-	 */
-	spin_lock(&journal->j_history_lock);
-	journal->j_stats.ts_tid++;
-	if (commit_transaction->t_requested)
-		journal->j_stats.ts_requested++;
-	journal->j_stats.run.rs_wait += stats.run.rs_wait;
-	journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
-	journal->j_stats.run.rs_running += stats.run.rs_running;
-	journal->j_stats.run.rs_locked += stats.run.rs_locked;
-	journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
-	journal->j_stats.run.rs_logging += stats.run.rs_logging;
-	journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
-	journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
-	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
-	spin_unlock(&journal->j_history_lock);
+	stats.ts_requested = (commit_transaction->t_requested) ? 1 : 0;
 
 	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
···
 
 	write_unlock(&journal->j_state_lock);
 
-	if (journal->j_checkpoint_transactions == NULL) {
-		journal->j_checkpoint_transactions = commit_transaction;
-		commit_transaction->t_cpnext = commit_transaction;
-		commit_transaction->t_cpprev = commit_transaction;
-	} else {
-		commit_transaction->t_cpnext =
-			journal->j_checkpoint_transactions;
-		commit_transaction->t_cpprev =
-			commit_transaction->t_cpnext->t_cpprev;
-		commit_transaction->t_cpnext->t_cpprev =
-			commit_transaction;
-		commit_transaction->t_cpprev->t_cpnext =
-				commit_transaction;
-	}
-	spin_unlock(&journal->j_list_lock);
-	/* Drop all spin_locks because commit_callback may be block.
-	 * __journal_remove_checkpoint() can not destroy transaction
-	 * under us because it is not marked as T_FINISHED yet */
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
···
 	write_lock(&journal->j_state_lock);
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
-	/* Recheck checkpoint lists after j_list_lock was dropped */
+	/* Check if the transaction can be dropped now that we are finished */
 	if (commit_transaction->t_checkpoint_list == NULL &&
 	    commit_transaction->t_checkpoint_io_list == NULL) {
 		__jbd2_journal_drop_transaction(journal, commit_transaction);
···
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+
+	/*
+	 * Calculate overall stats
+	 */
+	spin_lock(&journal->j_history_lock);
+	journal->j_stats.ts_tid++;
+	journal->j_stats.ts_requested += stats.ts_requested;
+	journal->j_stats.run.rs_wait += stats.run.rs_wait;
+	journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
+	journal->j_stats.run.rs_running += stats.run.rs_running;
+	journal->j_stats.run.rs_locked += stats.run.rs_locked;
+	journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+	journal->j_stats.run.rs_logging += stats.run.rs_logging;
+	journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+	journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
+	spin_unlock(&journal->j_history_lock);
 }

fs/jbd2/journal.c

···
 #endif
 
 /* Checksumming functions */
-int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
+static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
 	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
 		return 1;
···
 	return cpu_to_be32(csum);
 }
 
-int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
+static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
 	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
 		return 1;
···
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
 }
 
-void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
+static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
 	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
 		return;
···
 	journal->j_flags |= JBD2_UNMOUNT;
 
 	while (journal->j_task) {
-		wake_up(&journal->j_wait_commit);
 		write_unlock(&journal->j_state_lock);
+		wake_up(&journal->j_wait_commit);
 		wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
 		write_lock(&journal->j_state_lock);
 	}
···
 	while (tid_gt(tid, journal->j_commit_sequence)) {
 		jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
 				  tid, journal->j_commit_sequence);
-		wake_up(&journal->j_wait_commit);
 		read_unlock(&journal->j_state_lock);
+		wake_up(&journal->j_wait_commit);
 		wait_event(journal->j_wait_done_commit,
 				!tid_gt(tid, journal->j_commit_sequence));
 		read_lock(&journal->j_state_lock);

fs/jbd2/transaction.c

···
 	 * reused here.
 	 */
 	jbd_lock_bh_state(bh);
-	spin_lock(&journal->j_list_lock);
 	J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
 		jh->b_transaction == NULL ||
 		(jh->b_transaction == journal->j_committing_transaction &&
···
 		jh->b_modified = 0;
 
 		JBUFFER_TRACE(jh, "file as BJ_Reserved");
+		spin_lock(&journal->j_list_lock);
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
 	} else if (jh->b_transaction == journal->j_committing_transaction) {
 		/* first access by this transaction */
 		jh->b_modified = 0;
 
 		JBUFFER_TRACE(jh, "set next transaction");
+		spin_lock(&journal->j_list_lock);
 		jh->b_next_transaction = transaction;
 	}
 	spin_unlock(&journal->j_list_lock);
···
 			     journal->j_running_transaction)) {
 			printk(KERN_ERR "JBD2: %s: "
 			       "jh->b_transaction (%llu, %p, %u) != "
-			       "journal->j_running_transaction (%p, %u)",
+			       "journal->j_running_transaction (%p, %u)\n",
 			       journal->j_devname,
 			       (unsigned long long) bh->b_blocknr,
 			       jh->b_transaction,
···
 	 */
 	if (jh->b_transaction != transaction) {
 		JBUFFER_TRACE(jh, "already on other transaction");
-		if (unlikely(jh->b_transaction !=
-			     journal->j_committing_transaction)) {
-			printk(KERN_ERR "JBD2: %s: "
-			       "jh->b_transaction (%llu, %p, %u) != "
-			       "journal->j_committing_transaction (%p, %u)",
+		if (unlikely(((jh->b_transaction !=
+			       journal->j_committing_transaction)) ||
+			     (jh->b_next_transaction != transaction))) {
+			printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: "
+			       "bad jh for block %llu: "
+			       "transaction (%p, %u), "
+			       "jh->b_transaction (%p, %u), "
+			       "jh->b_next_transaction (%p, %u), jlist %u\n",
 			       journal->j_devname,
 			       (unsigned long long) bh->b_blocknr,
+			       transaction, transaction->t_tid,
 			       jh->b_transaction,
-			       jh->b_transaction ? jh->b_transaction->t_tid : 0,
-			       journal->j_committing_transaction,
-			       journal->j_committing_transaction ?
-			       journal->j_committing_transaction->t_tid : 0);
-			ret = -EINVAL;
-		}
-		if (unlikely(jh->b_next_transaction != transaction)) {
-			printk(KERN_ERR "JBD2: %s: "
-			       "jh->b_next_transaction (%llu, %p, %u) != "
-			       "transaction (%p, %u)",
-			       journal->j_devname,
-			       (unsigned long long) bh->b_blocknr,
+			       jh->b_transaction ?
+			       jh->b_transaction->t_tid : 0,
 			       jh->b_next_transaction,
 			       jh->b_next_transaction ?
 			       jh->b_next_transaction->t_tid : 0,
-			       transaction, transaction->t_tid);
+			       jh->b_jlist);
+			WARN_ON(1);
 			ret = -EINVAL;
 		}
 		/* And this case is illegal: we can't reuse another
···
 	BUFFER_TRACE(bh, "entry");
 
 	jbd_lock_bh_state(bh);
-	spin_lock(&journal->j_list_lock);
 
 	if (!buffer_jbd(bh))
 		goto not_jbd;
···
 		 * we know to remove the checkpoint after we commit.
 		 */
 
+		spin_lock(&journal->j_list_lock);
 		if (jh->b_cp_transaction) {
 			__jbd2_journal_temp_unlink_buffer(jh);
 			__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
···
 				goto drop;
 			}
 		}
+		spin_unlock(&journal->j_list_lock);
 	} else if (jh->b_transaction) {
 		J_ASSERT_JH(jh, (jh->b_transaction ==
 				 journal->j_committing_transaction));
···
 
 		if (jh->b_next_transaction) {
 			J_ASSERT(jh->b_next_transaction == transaction);
+			spin_lock(&journal->j_list_lock);
 			jh->b_next_transaction = NULL;
+			spin_unlock(&journal->j_list_lock);
 
 			/*
 			 * only drop a reference if this transaction modified
···
 	}
 
 not_jbd:
-	spin_unlock(&journal->j_list_lock);
 	jbd_unlock_bh_state(bh);
 	__brelse(bh);
 drop:
···
 	if (buffer_locked(bh) || buffer_dirty(bh))
 		goto out;
 
-	if (jh->b_next_transaction != NULL)
+	if (jh->b_next_transaction != NULL || jh->b_transaction != NULL)
 		goto out;
 
 	spin_lock(&journal->j_list_lock);
-	if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
+	if (jh->b_cp_transaction != NULL) {
 		/* written-back checkpointed metadata buffer */
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		__jbd2_journal_remove_checkpoint(jh);

fs/jffs2/super.c

···
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
 	int err;
 
+	sync_filesystem(sb);
 	err = jffs2_parse_options(c, data);
 	if (err)
 		return -EINVAL;

fs/jfs/super.c

···
 	int flag = JFS_SBI(sb)->flag;
 	int ret;
 
+	sync_filesystem(sb);
 	if (!parse_options(data, sb, &newLVSize, &flag)) {
 		return -EINVAL;
 	}

fs/mbcache.c

···
  * back on the lru list.
  */
 
+/*
+ * Lock descriptions and usage:
+ *
+ * Each hash chain of both the block and index hash tables now contains
+ * a built-in lock used to serialize accesses to the hash chain.
+ *
+ * Accesses to global data structures mb_cache_list and mb_cache_lru_list
+ * are serialized via the global spinlock mb_cache_spinlock.
+ *
+ * Each mb_cache_entry contains a spinlock, e_entry_lock, to serialize
+ * accesses to its local data, such as e_used and e_queued.
+ *
+ * Lock ordering:
+ *
+ * Each block hash chain's lock has the highest lock order, followed by an
+ * index hash chain's lock, mb_cache_bg_lock (used to implement mb_cache_entry's
+ * lock), and mb_cach_spinlock, with the lowest order.  While holding
+ * either a block or index hash chain lock, a thread can acquire an
+ * mc_cache_bg_lock, which in turn can also acquire mb_cache_spinlock.
+ *
+ * Synchronization:
+ *
+ * Since both mb_cache_entry_get and mb_cache_entry_find scan the block and
+ * index hash chian, it needs to lock the corresponding hash chain.  For each
+ * mb_cache_entry within the chain, it needs to lock the mb_cache_entry to
+ * prevent either any simultaneous release or free on the entry and also
+ * to serialize accesses to either the e_used or e_queued member of the entry.
+ *
+ * To avoid having a dangling reference to an already freed
+ * mb_cache_entry, an mb_cache_entry is only freed when it is not on a
+ * block hash chain and also no longer being referenced, both e_used,
+ * and e_queued are 0's.  When an mb_cache_entry is explicitly freed it is
+ * first removed from a block hash chain.
+ */
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 
···
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/init.h>
+#include <linux/list_bl.h>
 #include <linux/mbcache.h>
-
+#include <linux/init.h>
+#include <linux/blockgroup_lock.h>
 
 #ifdef MB_CACHE_DEBUG
 # define mb_debug(f...) do { \
···
 
 #define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
 
+#define MB_CACHE_ENTRY_LOCK_BITS	__builtin_log2(NR_BG_LOCKS)
+#define	MB_CACHE_ENTRY_LOCK_INDEX(ce)			\
+	(hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
+
 static DECLARE_WAIT_QUEUE_HEAD(mb_cache_queue);
-		
+static struct blockgroup_lock *mb_cache_bg_lock;
+static struct kmem_cache *mb_cache_kmem_cache;
+
 MODULE_AUTHOR("Andreas Gruenbacher <[e-mail]>");
 MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
 MODULE_LICENSE("GPL");
···
 static LIST_HEAD(mb_cache_lru_list);
 static DEFINE_SPINLOCK(mb_cache_spinlock);
 
+static inline void
+__spin_lock_mb_cache_entry(struct mb_cache_entry *ce)
+{
+	spin_lock(bgl_lock_ptr(mb_cache_bg_lock,
+		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
+}
+
+static inline void
+__spin_unlock_mb_cache_entry(struct mb_cache_entry *ce)
+{
+	spin_unlock(bgl_lock_ptr(mb_cache_bg_lock,
+		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
+}
+
 static inline int
-__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
+__mb_cache_entry_is_block_hashed(struct mb_cache_entry *ce)
 {
-	return !list_empty(&ce->e_block_list);
+	return !hlist_bl_unhashed(&ce->e_block_list);
 }
 
 
-static void
-__mb_cache_entry_unhash(struct mb_cache_entry *ce)
+static inline void
+__mb_cache_entry_unhash_block(struct mb_cache_entry *ce)
 {
-	if (__mb_cache_entry_is_hashed(ce)) {
-		list_del_init(&ce->e_block_list);
-		list_del(&ce->e_index.o_list);
-	}
+	if (__mb_cache_entry_is_block_hashed(ce))
+		hlist_bl_del_init(&ce->e_block_list);
 }
 
+static inline int
+__mb_cache_entry_is_index_hashed(struct mb_cache_entry *ce)
+{
+	return !hlist_bl_unhashed(&ce->e_index.o_list);
+}
+
+static inline void
+__mb_cache_entry_unhash_index(struct mb_cache_entry *ce)
+{
+	if (__mb_cache_entry_is_index_hashed(ce))
+		hlist_bl_del_init(&ce->e_index.o_list);
+}
+
+/*
+ * __mb_cache_entry_unhash_unlock()
+ *
+ * This function is called to unhash both the block and index hash
+ * chain.
+ * It assumes both the block and index hash chain is locked upon entry.
+ * It also unlock both hash chains both exit
+ */
+static inline void
+__mb_cache_entry_unhash_unlock(struct mb_cache_entry *ce)
+{
+	__mb_cache_entry_unhash_index(ce);
+	hlist_bl_unlock(ce->e_index_hash_p);
+	__mb_cache_entry_unhash_block(ce);
+	hlist_bl_unlock(ce->e_block_hash_p);
+}
 
 static void
 __mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
 {
 	struct mb_cache *cache = ce->e_cache;
 
-	mb_assert(!(ce->e_used || ce->e_queued));
+	mb_assert(!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt)));
 	kmem_cache_free(cache->c_entry_cache, ce);
 	atomic_dec(&cache->c_entry_count);
 }
 
-
 static void
-__mb_cache_entry_release_unlock(struct mb_cache_entry *ce)
-	__releases(mb_cache_spinlock)
+__mb_cache_entry_release(struct mb_cache_entry *ce)
 {
+	/* First lock the entry to serialize access to its local data. */
+	__spin_lock_mb_cache_entry(ce);
 	/* Wake up all processes queuing for this cache entry. */
 	if (ce->e_queued)
 		wake_up_all(&mb_cache_queue);
 	if (ce->e_used >= MB_CACHE_WRITER)
 		ce->e_used -= MB_CACHE_WRITER;
+	/*
+	 * Make sure that all cache entries on lru_list have
+	 * both e_used and e_qued of 0s.
+	 */
 	ce->e_used--;
-	if (!(ce->e_used || ce->e_queued)) {
-		if (!__mb_cache_entry_is_hashed(ce))
+	if (!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))) {
+		if (!__mb_cache_entry_is_block_hashed(ce)) {
+			__spin_unlock_mb_cache_entry(ce);
 			goto forget;
-		mb_assert(list_empty(&ce->e_lru_list));
-		list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
+		}
+		/*
+		 * Need access to lru list, first drop entry lock,
+		 * then reacquire the lock in the proper order.
+		 */
+		spin_lock(&mb_cache_spinlock);
+		if (list_empty(&ce->e_lru_list))
+			list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
+		spin_unlock(&mb_cache_spinlock);
 	}
-	spin_unlock(&mb_cache_spinlock);
+	__spin_unlock_mb_cache_entry(ce);
 	return;
 forget:
-	spin_unlock(&mb_cache_spinlock);
+	mb_assert(list_empty(&ce->e_lru_list));
 	__mb_cache_entry_forget(ce, GFP_KERNEL);
 }
-
 
 /*
  * mb_cache_shrink_scan()  memory pressure callback
···
 
 	mb_debug("trying to free %d entries", nr_to_scan);
 	spin_lock(&mb_cache_spinlock);
-	while (nr_to_scan-- && !list_empty(&mb_cache_lru_list)) {
+	while ((nr_to_scan-- > 0) && !list_empty(&mb_cache_lru_list)) {
 		struct mb_cache_entry *ce =
 			list_entry(mb_cache_lru_list.next,
-				   struct mb_cache_entry, e_lru_list);
-		list_move_tail(&ce->e_lru_list, &free_list);
-		__mb_cache_entry_unhash(ce);
-		freed++;
+				struct mb_cache_entry, e_lru_list);
+		list_del_init(&ce->e_lru_list);
+		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))
+			continue;
+		spin_unlock(&mb_cache_spinlock);
+		/* Prevent any find or get operation on the entry */
+		hlist_bl_lock(ce->e_block_hash_p);
+		hlist_bl_lock(ce->e_index_hash_p);
+		/* Ignore if it is touched by a find/get */
+		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt) ||
+			!list_empty(&ce->e_lru_list)) {
+			hlist_bl_unlock(ce->e_index_hash_p);
+			hlist_bl_unlock(ce->e_block_hash_p);
+			spin_lock(&mb_cache_spinlock);
+			continue;
+		}
+		__mb_cache_entry_unhash_unlock(ce);
+		list_add_tail(&ce->e_lru_list, &free_list);
+		spin_lock(&mb_cache_spinlock);
 	}
 	spin_unlock(&mb_cache_spinlock);
+
 	list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
 		__mb_cache_entry_forget(entry, gfp_mask);
+		freed++;
 	}
 	return freed;
 }
···
 	int n, bucket_count = 1 << bucket_bits;
 	struct mb_cache *cache = NULL;
 
+	if (!mb_cache_bg_lock) {
+		mb_cache_bg_lock = kmalloc(sizeof(struct blockgroup_lock),
+			GFP_KERNEL);
+		if (!mb_cache_bg_lock)
+			return NULL;
+		bgl_lock_init(mb_cache_bg_lock);
+	}
+
 	cache = kmalloc(sizeof(struct mb_cache), GFP_KERNEL);
 	if (!cache)
 		return NULL;
 	cache->c_name = name;
 	atomic_set(&cache->c_entry_count, 0);
 	cache->c_bucket_bits = bucket_bits;
-	cache->c_block_hash = kmalloc(bucket_count * sizeof(struct list_head),
-	                              GFP_KERNEL);
+	cache->c_block_hash = kmalloc(bucket_count *
+		sizeof(struct hlist_bl_head), GFP_KERNEL);
 	if (!cache->c_block_hash)
 		goto fail;
 	for (n=0; n<bucket_count; n++)
-		INIT_LIST_HEAD(&cache->c_block_hash[n]);
-	cache->c_index_hash = kmalloc(bucket_count * sizeof(struct list_head),
-				      GFP_KERNEL);
+		INIT_HLIST_BL_HEAD(&cache->c_block_hash[n]);
+	cache->c_index_hash = kmalloc(bucket_count *
+		sizeof(struct hlist_bl_head), GFP_KERNEL);
 	if (!cache->c_index_hash)
 		goto fail;
 	for (n=0; n<bucket_count; n++)
-		INIT_LIST_HEAD(&cache->c_index_hash[n]);
-	cache->c_entry_cache = kmem_cache_create(name,
-		sizeof(struct mb_cache_entry), 0,
-		SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-	if (!cache->c_entry_cache)
-		goto fail2;
+		INIT_HLIST_BL_HEAD(&cache->c_index_hash[n]);
+	if (!mb_cache_kmem_cache) {
+		mb_cache_kmem_cache = kmem_cache_create(name,
+			sizeof(struct mb_cache_entry), 0,
+			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+		if (!mb_cache_kmem_cache)
+			goto fail2;
+	}
+	cache->c_entry_cache = mb_cache_kmem_cache;
 
 	/*
 	 * Set an upper limit on the number of cache entries so that the hash
···
 mb_cache_shrink(struct block_device *bdev)
 {
 	LIST_HEAD(free_list);
-	struct list_head *l, *ltmp;
+	struct list_head *l;
+	struct mb_cache_entry *ce, *tmp;
 
+	l = &mb_cache_lru_list;
 	spin_lock(&mb_cache_spinlock);
-	list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
-		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_lru_list);
+	while (!list_is_last(l, &mb_cache_lru_list)) {
+		l = l->next;
+		ce = list_entry(l, struct mb_cache_entry, e_lru_list);
 		if (ce->e_bdev == bdev) {
-			list_move_tail(&ce->e_lru_list, &free_list);
-			__mb_cache_entry_unhash(ce);
+			list_del_init(&ce->e_lru_list);
+			if (ce->e_used || ce->e_queued ||
+				atomic_read(&ce->e_refcnt))
+				continue;
+			spin_unlock(&mb_cache_spinlock);
+			/*
+			 * Prevent any find or get operation on the entry.
+			 */
+			hlist_bl_lock(ce->e_block_hash_p);
+			hlist_bl_lock(ce->e_index_hash_p);
+			/* Ignore if it is touched by a find/get */
+			if (ce->e_used || ce->e_queued ||
+				atomic_read(&ce->e_refcnt) ||
+				!list_empty(&ce->e_lru_list)) {
+				hlist_bl_unlock(ce->e_index_hash_p);
+				hlist_bl_unlock(ce->e_block_hash_p);
+				l = &mb_cache_lru_list;
+				spin_lock(&mb_cache_spinlock);
+				continue;
+			}
+			__mb_cache_entry_unhash_unlock(ce);
+			mb_assert(!(ce->e_used || ce->e_queued ||
+				atomic_read(&ce->e_refcnt)));
+			list_add_tail(&ce->e_lru_list, &free_list);
+			l = &mb_cache_lru_list;
+			spin_lock(&mb_cache_spinlock);
 		}
 	}
 	spin_unlock(&mb_cache_spinlock);
-	list_for_each_safe(l, ltmp, &free_list) {
-		__mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
-						   e_lru_list), GFP_KERNEL);
+
+	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
+		__mb_cache_entry_forget(ce, GFP_KERNEL);
 	}
 }
 
···
 mb_cache_destroy(struct mb_cache *cache)
 {
 	LIST_HEAD(free_list);
-	struct list_head *l, *ltmp;
+	struct mb_cache_entry *ce, *tmp;
 
 	spin_lock(&mb_cache_spinlock);
-	list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
-		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_lru_list);
-		if (ce->e_cache == cache) {
+	list_for_each_entry_safe(ce, tmp, &mb_cache_lru_list, e_lru_list) {
+		if (ce->e_cache == cache)
 			list_move_tail(&ce->e_lru_list, &free_list);
-			__mb_cache_entry_unhash(ce);
-		}
 	}
 	list_del(&cache->c_cache_list);
 	spin_unlock(&mb_cache_spinlock);
 
-	list_for_each_safe(l, ltmp, &free_list) {
-		__mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
-						   e_lru_list), GFP_KERNEL);
+	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
+		list_del_init(&ce->e_lru_list);
+		/*
+		 * Prevent any find or get operation on the entry.
+		 */
+		hlist_bl_lock(ce->e_block_hash_p);
+		hlist_bl_lock(ce->e_index_hash_p);
+		mb_assert(!(ce->e_used || ce->e_queued ||
+			atomic_read(&ce->e_refcnt)));
+		__mb_cache_entry_unhash_unlock(ce);
+		__mb_cache_entry_forget(ce, GFP_KERNEL);
 	}
 
 	if (atomic_read(&cache->c_entry_count) > 0) {
···
 			  atomic_read(&cache->c_entry_count));
 	}
 
-	kmem_cache_destroy(cache->c_entry_cache);
-
+	if (list_empty(&mb_cache_list)) {
+		kmem_cache_destroy(mb_cache_kmem_cache);
+		mb_cache_kmem_cache = NULL;
+	}
 	kfree(cache->c_index_hash);
 	kfree(cache->c_block_hash);
 	kfree(cache);
···
 struct mb_cache_entry *
 mb_cache_entry_alloc(struct mb_cache *cache, gfp_t gfp_flags)
 {
-	struct mb_cache_entry *ce = NULL;
+	struct mb_cache_entry *ce;
 
 	if (atomic_read(&cache->c_entry_count) >= cache->c_max_entries) {
+		struct list_head *l;
+
+		l = &mb_cache_lru_list;
 		spin_lock(&mb_cache_spinlock);
-		if (!list_empty(&mb_cache_lru_list)) {
-			ce = list_entry(mb_cache_lru_list.next,
-					struct mb_cache_entry, e_lru_list);
-			list_del_init(&ce->e_lru_list);
-			__mb_cache_entry_unhash(ce);
+		while (!list_is_last(l, &mb_cache_lru_list)) {
+			l = l->next;
+			ce = list_entry(l, struct mb_cache_entry, e_lru_list);
+			if (ce->e_cache == cache) {
+				list_del_init(&ce->e_lru_list);
+				if (ce->e_used || ce->e_queued ||
+					atomic_read(&ce->e_refcnt))
+					continue;
+				spin_unlock(&mb_cache_spinlock);
+				/*
+				 * Prevent any find or get operation on the
+				 * entry.
+				 */
+				hlist_bl_lock(ce->e_block_hash_p);
+				hlist_bl_lock(ce->e_index_hash_p);
+				/* Ignore if it is touched by a find/get */
+				if (ce->e_used || ce->e_queued ||
+					atomic_read(&ce->e_refcnt) ||
+					!list_empty(&ce->e_lru_list)) {
+					hlist_bl_unlock(ce->e_index_hash_p);
+					hlist_bl_unlock(ce->e_block_hash_p);
+					l = &mb_cache_lru_list;
+					spin_lock(&mb_cache_spinlock);
+					continue;
+				}
+				mb_assert(list_empty(&ce->e_lru_list));
+				mb_assert(!(ce->e_used || ce->e_queued ||
+					atomic_read(&ce->e_refcnt)));
+				__mb_cache_entry_unhash_unlock(ce);
+				goto found;
+			}
 		}
 		spin_unlock(&mb_cache_spinlock);
 	}
-	if (!ce) {
-		ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
-		if (!ce)
-			return NULL;
-		atomic_inc(&cache->c_entry_count);
-		INIT_LIST_HEAD(&ce->e_lru_list);
-		INIT_LIST_HEAD(&ce->e_block_list);
-		ce->e_cache = cache;
-		ce->e_queued = 0;
-	}
+
+	ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
+	if (!ce)
+		return NULL;
+	atomic_inc(&cache->c_entry_count);
+	INIT_LIST_HEAD(&ce->e_lru_list);
+	INIT_HLIST_BL_NODE(&ce->e_block_list);
+	INIT_HLIST_BL_NODE(&ce->e_index.o_list);
+	ce->e_cache = cache;
+	ce->e_queued = 0;
+	atomic_set(&ce->e_refcnt, 0);
+found:
+	ce->e_block_hash_p = &cache->c_block_hash[0];
+	ce->e_index_hash_p = &cache->c_index_hash[0];
 	ce->e_used = 1 + MB_CACHE_WRITER;
 	return ce;
 }
···
 {
 	struct mb_cache *cache = ce->e_cache;
 	unsigned int bucket;
-	struct list_head *l;
-	int error = -EBUSY;
+	struct hlist_bl_node *l;
+	struct hlist_bl_head *block_hash_p;
+	struct hlist_bl_head *index_hash_p;
+	struct mb_cache_entry *lce;
 
+	mb_assert(ce);
 	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
 			   cache->c_bucket_bits);
-	spin_lock(&mb_cache_spinlock);
-	list_for_each_prev(l, &cache->c_block_hash[bucket]) {
-		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_block_list);
-		if (ce->e_bdev == bdev && ce->e_block == block)
-			goto out;
+	block_hash_p = &cache->c_block_hash[bucket];
+	hlist_bl_lock(block_hash_p);
+	hlist_bl_for_each_entry(lce, l, block_hash_p, e_block_list) {
+		if (lce->e_bdev == bdev && lce->e_block == block) {
+			hlist_bl_unlock(block_hash_p);
+			return -EBUSY;
+		}
 	}
-	__mb_cache_entry_unhash(ce);
+	mb_assert(!__mb_cache_entry_is_block_hashed(ce));
+	__mb_cache_entry_unhash_block(ce);
+	__mb_cache_entry_unhash_index(ce);
 	ce->e_bdev = bdev;
 	ce->e_block = block;
-	list_add(&ce->e_block_list, &cache->c_block_hash[bucket]);
+	ce->e_block_hash_p = block_hash_p;
 	ce->e_index.o_key = key;
+	hlist_bl_add_head(&ce->e_block_list, block_hash_p);
+	hlist_bl_unlock(block_hash_p);
 	bucket = hash_long(key, cache->c_bucket_bits);
-	list_add(&ce->e_index.o_list, &cache->c_index_hash[bucket]);
-	error = 0;
-out:
-	spin_unlock(&mb_cache_spinlock);
-	return error;
+	index_hash_p = &cache->c_index_hash[bucket];
+	hlist_bl_lock(index_hash_p);
+	ce->e_index_hash_p = index_hash_p;
+	hlist_bl_add_head(&ce->e_index.o_list, index_hash_p);
+	hlist_bl_unlock(index_hash_p);
+	return 0;
 }
 
 
···
 void
 mb_cache_entry_release(struct mb_cache_entry *ce)
 {
-	spin_lock(&mb_cache_spinlock);
-	__mb_cache_entry_release_unlock(ce);
+	__mb_cache_entry_release(ce);
 }
 
 
 /*
  * mb_cache_entry_free()
  *
- * This is equivalent to the sequence mb_cache_entry_takeout() --
- * mb_cache_entry_release().
  */
 void
 mb_cache_entry_free(struct mb_cache_entry *ce)
 {
-	spin_lock(&mb_cache_spinlock);
+	mb_assert(ce);
 	mb_assert(list_empty(&ce->e_lru_list));
-	__mb_cache_entry_unhash(ce);
-	__mb_cache_entry_release_unlock(ce);
+	hlist_bl_lock(ce->e_index_hash_p);
+	__mb_cache_entry_unhash_index(ce);
+	hlist_bl_unlock(ce->e_index_hash_p);
+	hlist_bl_lock(ce->e_block_hash_p);
+	__mb_cache_entry_unhash_block(ce);
+	hlist_bl_unlock(ce->e_block_hash_p);
+	__mb_cache_entry_release(ce);
 }
 
 
···
 		   sector_t block)
 {
 	unsigned int bucket;
-	struct list_head *l;
+	struct hlist_bl_node *l;
 	struct mb_cache_entry *ce;
+	struct hlist_bl_head *block_hash_p;
 
 	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
 			   cache->c_bucket_bits);
-	spin_lock(&mb_cache_spinlock);
-	list_for_each(l, &cache->c_block_hash[bucket]) {
-		ce = list_entry(l, struct mb_cache_entry, e_block_list);
+	block_hash_p = &cache->c_block_hash[bucket];
+	/* First serialize access to the block corresponding hash chain. */
+	hlist_bl_lock(block_hash_p);
+	hlist_bl_for_each_entry(ce, l, block_hash_p, e_block_list) {
+		mb_assert(ce->e_block_hash_p == block_hash_p);
 		if (ce->e_bdev == bdev && ce->e_block == block) {
-			DEFINE_WAIT(wait);
-
-			if (!list_empty(&ce->e_lru_list))
-				list_del_init(&ce->e_lru_list);
-
-			while (ce->e_used > 0) {
-				ce->e_queued++;
-				prepare_to_wait(&mb_cache_queue, &wait,
-						TASK_UNINTERRUPTIBLE);
-				spin_unlock(&mb_cache_spinlock);
-				schedule();
-				spin_lock(&mb_cache_spinlock);
-				ce->e_queued--;
+			/*
+			 * Prevent a free from removing the entry.
+			 */
+			atomic_inc(&ce->e_refcnt);
+			hlist_bl_unlock(block_hash_p);
+			__spin_lock_mb_cache_entry(ce);
+			atomic_dec(&ce->e_refcnt);
+			if (ce->e_used > 0) {
+				DEFINE_WAIT(wait);
+				while (ce->e_used > 0) {
+					ce->e_queued++;
+					prepare_to_wait(&mb_cache_queue, &wait,
+							TASK_UNINTERRUPTIBLE);
+					__spin_unlock_mb_cache_entry(ce);
+					schedule();
+					__spin_lock_mb_cache_entry(ce);
+					ce->e_queued--;
+				}
+				finish_wait(&mb_cache_queue, &wait);
 			}
-			finish_wait(&mb_cache_queue, &wait);
 			ce->e_used += 1 + MB_CACHE_WRITER;
+			__spin_unlock_mb_cache_entry(ce);
 
-			if (!__mb_cache_entry_is_hashed(ce)) {
-				__mb_cache_entry_release_unlock(ce);
+			if (!list_empty(&ce->e_lru_list)) {
+				spin_lock(&mb_cache_spinlock);
+				list_del_init(&ce->e_lru_list);
+				spin_unlock(&mb_cache_spinlock);
+			}
+			if (!__mb_cache_entry_is_block_hashed(ce)) {
+				__mb_cache_entry_release(ce);
 				return NULL;
 			}
-			goto cleanup;
+			return ce;
 		}
 	}
-	ce = NULL;
-
-cleanup:
-	spin_unlock(&mb_cache_spinlock);
-	return ce;
+	hlist_bl_unlock(block_hash_p);
+	return NULL;
 }
 
 #if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
 
 static struct mb_cache_entry *
-__mb_cache_entry_find(struct list_head *l, struct list_head *head,
+__mb_cache_entry_find(struct hlist_bl_node *l, struct hlist_bl_head *head,
 		      struct block_device *bdev, unsigned int key)
 {
-	while (l != head) {
+
+	/* The index hash chain is alredy acquire by caller. */
+	while (l != NULL) {
 		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_index.o_list);
+			hlist_bl_entry(l, struct mb_cache_entry,
+				e_index.o_list);
+		mb_assert(ce->e_index_hash_p == head);
 		if (ce->e_bdev == bdev && ce->e_index.o_key == key) {
-			DEFINE_WAIT(wait);
-
-			if (!list_empty(&ce->e_lru_list))
-				list_del_init(&ce->e_lru_list);
-
+			/*
+			 * Prevent a free from removing the entry.
+			 */
+			atomic_inc(&ce->e_refcnt);
+			hlist_bl_unlock(head);
+			__spin_lock_mb_cache_entry(ce);
+			atomic_dec(&ce->e_refcnt);
+			ce->e_used++;
 			/* Incrementing before holding the lock gives readers
 			   priority over writers. */
-			ce->e_used++;
-			while (ce->e_used >= MB_CACHE_WRITER) {
-				ce->e_queued++;
-				prepare_to_wait(&mb_cache_queue, &wait,
-						TASK_UNINTERRUPTIBLE);
-				spin_unlock(&mb_cache_spinlock);
-				schedule();
-				spin_lock(&mb_cache_spinlock);
-				ce->e_queued--;
-			}
-			finish_wait(&mb_cache_queue, &wait);
+			if (ce->e_used >= MB_CACHE_WRITER) {
+				DEFINE_WAIT(wait);
 
-			if (!__mb_cache_entry_is_hashed(ce)) {
-				__mb_cache_entry_release_unlock(ce);
+				while (ce->e_used >= MB_CACHE_WRITER) {
+					ce->e_queued++;
+					prepare_to_wait(&mb_cache_queue, &wait,
+							TASK_UNINTERRUPTIBLE);
+					__spin_unlock_mb_cache_entry(ce);
+					schedule();
+					__spin_lock_mb_cache_entry(ce);
+					ce->e_queued--;
+				}
+				finish_wait(&mb_cache_queue, &wait);
+			}
+			__spin_unlock_mb_cache_entry(ce);
+			if (!list_empty(&ce->e_lru_list)) {
 				spin_lock(&mb_cache_spinlock);
+				list_del_init(&ce->e_lru_list);
+				spin_unlock(&mb_cache_spinlock);
+			}
+			if (!__mb_cache_entry_is_block_hashed(ce)) {
+				__mb_cache_entry_release(ce);
 				return ERR_PTR(-EAGAIN);
 			}
 			return ce;
 		}
 		l = l->next;
 	}
+	hlist_bl_unlock(head);
 	return NULL;
 }
 
···
 			  unsigned int key)
 {
 	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct list_head *l;
-	struct mb_cache_entry *ce;
+	struct hlist_bl_node *l;
+	struct mb_cache_entry *ce = NULL;
+	struct hlist_bl_head *index_hash_p;
 
-	spin_lock(&mb_cache_spinlock);
-	l = cache->c_index_hash[bucket].next;
-	ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
-	spin_unlock(&mb_cache_spinlock);
+	index_hash_p = &cache->c_index_hash[bucket];
+	hlist_bl_lock(index_hash_p);
+	if (!hlist_bl_empty(index_hash_p)) {
+		l = hlist_bl_first(index_hash_p);
+		ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
+	} else
+		hlist_bl_unlock(index_hash_p);
 	return ce;
 }
 
···
 {
 	struct mb_cache *cache = prev->e_cache;
 	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct list_head *l;
+	struct hlist_bl_node *l;
 	struct mb_cache_entry *ce;
+	struct hlist_bl_head *index_hash_p;
 
-	spin_lock(&mb_cache_spinlock);
+	index_hash_p = &cache->c_index_hash[bucket];
+	mb_assert(prev->e_index_hash_p == index_hash_p);
+	hlist_bl_lock(index_hash_p);
+	mb_assert(!hlist_bl_empty(index_hash_p));
 	l = prev->e_index.o_list.next;
-	ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
-	__mb_cache_entry_release_unlock(prev);
+	ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
+	__mb_cache_entry_release(prev);
 	return ce;
 }
 

fs/minix/inode.c

···
 	struct minix_sb_info * sbi = minix_sb(sb);
 	struct minix_super_block * ms;
 
+	sync_filesystem(sb);
 	ms = sbi->s_ms;
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;

fs/ncpfs/inode.c

···
 
 static int ncp_remount(struct super_block *sb, int *flags, char* data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NODIRATIME;
 	return 0;
 }

fs/nfs/super.c

···
 	struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
 	u32 nfsvers = nfss->nfs_client->rpc_ops->version;
 
+	sync_filesystem(sb);
+
 	/*
 	 * Userspace mount programs that send binary options generally send
 	 * them populated with default values. We have no way to know which

fs/nilfs2/super.c

···
 	unsigned long old_mount_opt;
 	int err;
 
+	sync_filesystem(sb);
 	old_sb_flags = sb->s_flags;
 	old_mount_opt = nilfs->ns_mount_opt;
 

fs/ntfs/super.c

···
 
 	ntfs_debug("Entering with remount options string: %s", opt);
 
+	sync_filesystem(sb);
+
 #ifndef NTFS_RW
 	/* For read-only compiled driver, enforce read-only flag. */
 	*flags |= MS_RDONLY;

fs/ocfs2/super.c

···
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 	u32 tmp;
 
+	sync_filesystem(sb);
+
 	if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
 	    !ocfs2_check_set_options(sb, &parsed_options)) {
 		ret = -EINVAL;

fs/openpromfs/inode.c

···
 
 static int openprom_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_NOATIME;
 	return 0;
 }

fs/proc/root.c

···
 int proc_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct pid_namespace *pid = sb->s_fs_info;
+
+	sync_filesystem(sb);
 	return !proc_parse_options(data, pid);
 }
 

fs/pstore/inode.c

···
 
 static int pstore_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	parse_options(data);
 
 	return 0;

fs/qnx4/inode.c

···
 {
 	struct qnx4_sb_info *qs;
 
+	sync_filesystem(sb);
 	qs = qnx4_sb(sb);
 	qs->Version = QNX4_VERSION;
 	*flags |= MS_RDONLY;

fs/qnx6/inode.c

···
 
 static int qnx6_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/reiserfs/super.c

···
 	int i;
 #endif
 
+	sync_filesystem(s);
 	reiserfs_write_lock(s);
 
 #ifdef CONFIG_QUOTA

fs/romfs/super.c

···
  */
 static int romfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/squashfs/super.c

···
 
 static int squashfs_remount(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	*flags |= MS_RDONLY;
 	return 0;
 }

fs/super.c

···
 		}
 	}
 
-	sync_filesystem(sb);
-
 	if (sb->s_op->remount_fs) {
 		retval = sb->s_op->remount_fs(sb, &flags, data);
 		if (retval) {

fs/sysv/inode.c

···
 {
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
 
+	sync_filesystem(sb);
 	if (sbi->s_forced_ro)
 		*flags |= MS_RDONLY;
 	return 0;

fs/ubifs/super.c

···
 	int err;
 	struct ubifs_info *c = sb->s_fs_info;
 
+	sync_filesystem(sb);
 	dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags);
 
 	err = ubifs_parse_options(c, data, 1);

fs/udf/super.c

···
 	int error = 0;
 	struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb);
 
+	sync_filesystem(sb);
 	if (lvidiu) {
 		int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev);
 		if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))

fs/ufs/super.c

···
 	unsigned new_mount_opt, ufstype;
 	unsigned flags;
 
+	sync_filesystem(sb);
 	lock_ufs(sb);
 	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;

fs/xfs/xfs_super.c

···
 	char			*p;
 	int			error;
 
+	sync_filesystem(sb);
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
 

include/linux/fs.h

···
 void inode_dio_wait(struct inode *inode);
 void inode_dio_done(struct inode *inode);
 
+extern void inode_set_flags(struct inode *inode, unsigned int flags,
+			    unsigned int mask);
+
 extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))

include/linux/mbcache.h

···
 
   (C) 2001 by Andreas Gruenbacher, <[e-mail]>
 */
-
 struct mb_cache_entry {
 	struct list_head		e_lru_list;
 	struct mb_cache			*e_cache;
 	unsigned short			e_used;
 	unsigned short			e_queued;
+	atomic_t			e_refcnt;
 	struct block_device		*e_bdev;
 	sector_t			e_block;
-	struct list_head		e_block_list;
+	struct hlist_bl_node		e_block_list;
 	struct {
-		struct list_head	o_list;
+		struct hlist_bl_node	o_list;
 		unsigned int		o_key;
 	} e_index;
+	struct hlist_bl_head		*e_block_hash_p;
+	struct hlist_bl_head		*e_index_hash_p;
 };
 
 struct mb_cache {
···
 	int				c_max_entries;
 	int				c_bucket_bits;
 	struct kmem_cache		*c_entry_cache;
-	struct list_head		*c_block_hash;
-	struct list_head		*c_index_hash;
+	struct hlist_bl_head		*c_block_hash;
+	struct hlist_bl_head		*c_index_hash;
 };
 
 /* Functions on caches */

include/trace/events/ext4.h

···
 struct ext4_map_blocks;
 struct extent_status;
 
+/* shim until we merge in the xfs_collapse_range branch */
+#ifndef FALLOC_FL_COLLAPSE_RANGE
+#define FALLOC_FL_COLLAPSE_RANGE	0x08
+#endif
+
+#ifndef FALLOC_FL_ZERO_RANGE
+#define FALLOC_FL_ZERO_RANGE           0x10
+#endif
+
 #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
 
 #define show_mballoc_flags(flags) __print_flags(flags, "|",	\
···
 	{ EXTENT_STATUS_UNWRITTEN,	"U" },			\
 	{ EXTENT_STATUS_DELAYED,	"D" },			\
 	{ EXTENT_STATUS_HOLE,		"H" })
+
+#define show_falloc_mode(mode) __print_flags(mode, "|",		\
+	{ FALLOC_FL_KEEP_SIZE,		"KEEP_SIZE"},		\
+	{ FALLOC_FL_PUNCH_HOLE,		"PUNCH_HOLE"},		\
+	{ FALLOC_FL_NO_HIDE_STALE,	"NO_HIDE_STALE"},	\
+	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
+	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
 
 TRACE_EVENT(ext4_free_inode,
···
 		  __entry->rw, __entry->ret)
 );
 
-TRACE_EVENT(ext4_fallocate_enter,
+DECLARE_EVENT_CLASS(ext4__fallocate_mode,
 	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
 
 	TP_ARGS(inode, offset, len, mode),
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	loff_t,	len			)
+		__field(	loff_t,	offset			)
+		__field(	loff_t, len			)
 		__field(	int,	mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->pos	= offset;
+		__entry->offset	= offset;
 		__entry->len	= len;
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d",
+	TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->pos,
-		  __entry->len, __entry->mode)
+		  (unsigned long) __entry->ino,
+		  __entry->offset, __entry->len,
+		  show_falloc_mode(__entry->mode))
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range,
+
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+	TP_ARGS(inode, offset, len, mode)
 );
 
 TRACE_EVENT(ext4_fallocate_exit,
···
 		  (unsigned long) __entry->ino,
 		  __entry->pos, __entry->blocks,
 		  __entry->ret)
-);
-
-TRACE_EVENT(ext4_punch_hole,
-	TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
-
-	TP_ARGS(inode, offset, len),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	offset			)
-		__field(	loff_t, len			)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->offset	= offset;
-		__entry->len	= len;
-	),
-
-	TP_printk("dev %d,%d ino %lu offset %lld len %lld",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino,
-		  __entry->offset, __entry->len)
 );
 
 TRACE_EVENT(ext4_unlink_enter,
···
 	TP_printk("dev %d,%d shrunk_nr %d cache_cnt %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->shrunk_nr, __entry->cache_cnt)
+);
+
+TRACE_EVENT(ext4_collapse_range,
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
+
+	TP_ARGS(inode, offset, len),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	offset)
+		__field(loff_t, len)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->offset	= offset;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu offset %lld len %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->offset, __entry->len)
 );
 
 #endif /* _TRACE_EXT4_H */