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

Pull ext4 updates from Ted Ts'o:
"The big new feature added this time is supporting online resizing
using the meta_bg feature. This allows us to resize file systems
which are greater than 16TB. In addition, the speed of online
resizing has been improved in general.

We also fix a number of races, some of which could lead to deadlocks,
in ext4's Asynchronous I/O and online defrag support, thanks to good
work by Dmitry Monakhov.

There are also a large number of more minor bug fixes and cleanups
from a number of other ext4 contributors, quite of few of which have
submitted fixes for the first time."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (69 commits)
ext4: fix ext4_flush_completed_IO wait semantics
ext4: fix mtime update in nodelalloc mode
ext4: fix ext_remove_space for punch_hole case
ext4: punch_hole should wait for DIO writers
ext4: serialize truncate with owerwrite DIO workers
ext4: endless truncate due to nonlocked dio readers
ext4: serialize unlocked dio reads with truncate
ext4: serialize dio nonlocked reads with defrag workers
ext4: completed_io locking cleanup
ext4: fix unwritten counter leakage
ext4: give i_aiodio_unwritten a more appropriate name
ext4: ext4_inode_info diet
ext4: convert to use leXX_add_cpu()
ext4: ext4_bread usage audit
fs: reserve fallocate flag codepoint
ext4: remove redundant offset check in mext_check_arguments()
ext4: don't clear orphan list on ro mount with errors
jbd2: fix assertion failure in commit code due to lacking transaction credits
ext4: release donor reference when EXT4_IOC_MOVE_EXT ioctl fails
ext4: enable FITRIM ioctl on bigalloc file system
...

Documentation/ABI/testing/sysfs-fs-ext4

···
 Description:
 		The maximum number of megabytes the writeback code will
 		try to write out before move on to another inode.
+
+What:		/sys/fs/ext4/<disk>/extent_max_zeroout_kb
+Date:		August 2012
+Contact:	"Theodore Ts'o" <[e-mail]>
+Description:
+		The maximum number of kilobytes which will be zeroed
+		out in preference to creating a new uninitialized
+		extent when manipulating an inode's extent tree.  Note
+		that using a larger value will increase the
+		variability of time necessary to complete a random
+		write operation (since a 4k random write might turn
+		into a much larger write due to the zeroout
+		operation).

Documentation/filesystems/ext4.txt

···
 			Because of the restrictions this options comprises
 			it is off by default (e.g. dioread_lock).
 
+max_dir_size_kb=n	This limits the size of directories so that any
+			attempt to expand them beyond the specified
+			limit in kilobytes will cause an ENOSPC error.
+			This is useful in memory constrained
+			environments, where a very large directory can
+			cause severe performance problems or even
+			provoke the Out Of Memory killer.  (For example,
+			if there is only 512mb memory available, a 176mb
+			directory may seriously cramp the system's style.)
+
 i_version		Enable 64-bit inode version support. This option is
 			off by default.
 

fs/buffer.c

···
 	loff_t size;
 	int ret;
 
-	/*
-	 * Update file times before taking page lock. We may end up failing the
-	 * fault so this update may be superfluous but who really cares...
-	 */
-	file_update_time(vma->vm_file);
-
 	lock_page(page);
 	size = i_size_read(inode);
 	if ((page->mapping != inode->i_mapping) ||
···
 	struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
 
 	sb_start_pagefault(sb);
+
+	/*
+	 * Update file times before taking page lock. We may end up failing the
+	 * fault so this update may be superfluous but who really cares...
+	 */
+	file_update_time(vma->vm_file);
+
 	ret = __block_page_mkwrite(vma, vmf, get_block);
 	sb_end_pagefault(sb);
 	return block_page_mkwrite_return(ret);

fs/ext4/ext4.h

···
 #define EXT4_IO_END_ERROR	0x0002
 #define EXT4_IO_END_QUEUED	0x0004
 #define EXT4_IO_END_DIRECT	0x0008
-#define EXT4_IO_END_IN_FSYNC	0x0010
 
 struct ext4_io_page {
 	struct page	*p_page;
···
 	struct list_head i_completed_io_list;
 	spinlock_t i_completed_io_lock;
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
-	/* current io_end structure for async DIO write*/
-	ext4_io_end_t *cur_aio_dio;
-	atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
+	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
···
 	spinlock_t s_md_lock;
 	unsigned short *s_mb_offsets;
 	unsigned int *s_mb_maxs;
+	unsigned int s_group_info_size;
 
 	/* tunables */
 	unsigned long s_stripe;
···
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
 	unsigned int s_max_writeback_mb_bump;
+	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
···
 	unsigned long s_sectors_written_start;
 	u64 s_kbytes_written;
 
+	/* the size of zero-out chunk */
+	unsigned int s_extent_max_zeroout_kb;
+
 	unsigned int s_log_groups_per_flex;
 	struct flex_groups *s_flex_groups;
+	ext4_group_t s_flex_groups_allocated;
 
 	/* workqueue for dio unwritten */
 	struct workqueue_struct *dio_unwritten_wq;
···
 {
 	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
 		io_end->flag |= EXT4_IO_END_UNWRITTEN;
-		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+		atomic_inc(&EXT4_I(inode)->i_unwritten);
 	}
+}
+
+static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode)
+{
+	return inode->i_private;
+}
+
+static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io)
+{
+	inode->i_private = io;
 }
 
 /*
···
 	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
 	EXT4_STATE_NEWENTRY,		/* File just added to dir */
 	EXT4_STATE_DELALLOC_RESERVED,	/* blks already reserved for delalloc */
+	EXT4_STATE_DIOREAD_LOCK,	/* Disable support for dio read
+					   nolocking */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
···
 
 /* fsync.c */
 extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
-extern int ext4_flush_completed_IO(struct inode *);
+extern int ext4_flush_unwritten_io(struct inode *);
 
 /* hash.c */
 extern int ext4fs_dirhash(const char *name, int len, struct
···
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     struct buffer_head *bh, ext4_fsblk_t block,
 			     unsigned long count, int flags);
+extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
+				   ext4_group_t ngroups);
 extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
···
 extern void *ext4_kvmalloc(size_t size, gfp_t flags);
 extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern void ext4_kvfree(void *ptr);
+extern int ext4_alloc_flex_bg_array(struct super_block *sb,
+				    ext4_group_t ngroup);
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
···
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
+extern void ext4_unwritten_wait(struct inode *inode);
 
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
···
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
+extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
 extern void ext4_ioend_wait(struct inode *);
 extern void ext4_free_io_end(ext4_io_end_t *io);
 extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
-extern int ext4_end_io_nolock(ext4_io_end_t *io);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
···
 static inline void set_bitmap_uptodate(struct buffer_head *bh)
 {
 	set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+}
+
+/*
+ * Disable DIO read nolock optimization, so new dioreaders will be forced
+ * to grab i_mutex
+ */
+static inline void ext4_inode_block_unlocked_dio(struct inode *inode)
+{
+	ext4_set_inode_state(inode, EXT4_STATE_DIOREAD_LOCK);
+	smp_mb();
+}
+static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
+{
+	smp_mb();
+	ext4_clear_inode_state(inode, EXT4_STATE_DIOREAD_LOCK);
 }
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

fs/ext4/extents.c

···
 		  le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
 		  ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
 
-	neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1);
+	le16_add_cpu(&neh->eh_depth, 1);
 	ext4_mark_inode_dirty(handle, inode);
 out:
 	brelse(bh);
···
 }
 
 /*
+ * This function does a very simple check to see if we can collapse
+ * an extent tree with a single extent tree leaf block into the inode.
+ */
+static void ext4_ext_try_to_merge_up(handle_t *handle,
+				     struct inode *inode,
+				     struct ext4_ext_path *path)
+{
+	size_t s;
+	unsigned max_root = ext4_ext_space_root(inode, 0);
+	ext4_fsblk_t blk;
+
+	if ((path[0].p_depth != 1) ||
+	    (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) ||
+	    (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root))
+		return;
+
+	/*
+	 * We need to modify the block allocation bitmap and the block
+	 * group descriptor to release the extent tree block.  If we
+	 * can't get the journal credits, give up.
+	 */
+	if (ext4_journal_extend(handle, 2))
+		return;
+
+	/*
+	 * Copy the extent data up to the inode
+	 */
+	blk = ext4_idx_pblock(path[0].p_idx);
+	s = le16_to_cpu(path[1].p_hdr->eh_entries) *
+		sizeof(struct ext4_extent_idx);
+	s += sizeof(struct ext4_extent_header);
+
+	memcpy(path[0].p_hdr, path[1].p_hdr, s);
+	path[0].p_depth = 0;
+	path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) +
+		(path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr));
+	path[0].p_hdr->eh_max = cpu_to_le16(max_root);
+
+	brelse(path[1].p_bh);
+	ext4_free_blocks(handle, inode, NULL, blk, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+}
+
+/*
  * This function tries to merge the @ex extent to neighbours in the tree.
  * return 1 if merge left else 0.
  */
-static int ext4_ext_try_to_merge(struct inode *inode,
+static void ext4_ext_try_to_merge(handle_t *handle,
+				  struct inode *inode,
 				  struct ext4_ext_path *path,
 				  struct ext4_extent *ex) {
 	struct ext4_extent_header *eh;
 	unsigned int depth;
 	int merge_done = 0;
-	int ret = 0;
 
 	depth = ext_depth(inode);
 	BUG_ON(path[depth].p_hdr == NULL);
···
 		merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1);
 
 	if (!merge_done)
-		ret = ext4_ext_try_to_merge_right(inode, path, ex);
+		(void) ext4_ext_try_to_merge_right(inode, path, ex);
 
-	return ret;
+	ext4_ext_try_to_merge_up(handle, inode, path);
 }
 
 /*
···
 merge:
 	/* try to merge extents */
 	if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
-		ext4_ext_try_to_merge(inode, path, nearex);
+		ext4_ext_try_to_merge(handle, inode, path, nearex);
 
 
 	/* time to correct all indexes above */
···
 	if (err)
 		goto cleanup;
 
-	err = ext4_ext_dirty(handle, inode, path + depth);
+	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 
 cleanup:
 	if (npath) {
···
 }
 
 /*
- * ext4_ext_check_cache()
+ * ext4_ext_in_cache()
  * Checks to see if the given block is in the cache.
  * If it is, the cached extent is stored in the given
- * cache extent pointer.  If the cached extent is a hole,
- * this routine should be used instead of
- * ext4_ext_in_cache if the calling function needs to
- * know the size of the hole.
+ * cache extent pointer.
  *
  * @inode: The files inode
  * @block: The block to look for in the cache
···
  *
  * Return 0 if cache is invalid; 1 if the cache is valid
  */
-static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block,
-	struct ext4_ext_cache *ex){
+static int
+ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
+		  struct ext4_extent *ex)
+{
 	struct ext4_ext_cache *cex;
 	struct ext4_sb_info *sbi;
 	int ret = 0;
···
 		goto errout;
 
 	if (in_range(block, cex->ec_block, cex->ec_len)) {
-		memcpy(ex, cex, sizeof(struct ext4_ext_cache));
+		ex->ee_block = cpu_to_le32(cex->ec_block);
+		ext4_ext_store_pblock(ex, cex->ec_start);
+		ex->ee_len = cpu_to_le16(cex->ec_len);
 		ext_debug("%u cached by %u:%u:%llu\n",
 				block,
 				cex->ec_block, cex->ec_len, cex->ec_start);
···
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 	return ret;
 }
-
-/*
- * ext4_ext_in_cache()
- * Checks to see if the given block is in the cache.
- * If it is, the cached extent is stored in the given
- * extent pointer.
- *
- * @inode: The files inode
- * @block: The block to look for in the cache
- * @ex:    Pointer where the cached extent will be stored
- *         if it contains block
- *
- * Return 0 if cache is invalid; 1 if the cache is valid
- */
-static int
-ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
-			struct ext4_extent *ex)
-{
-	struct ext4_ext_cache cex;
-	int ret = 0;
-
-	if (ext4_ext_check_cache(inode, block, &cex)) {
-		ex->ee_block = cpu_to_le32(cex.ec_block);
-		ext4_ext_store_pblock(ex, cex.ec_start);
-		ex->ee_len = cpu_to_le16(cex.ec_len);
-		ret = 1;
-	}
-
-	return ret;
-}
-
 
 /*
  * ext4_ext_rm_idx:
···
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
 	ext4_fsblk_t pblk;
-	int flags = EXT4_FREE_BLOCKS_FORGET;
+	int flags = 0;
 
 	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		flags |= EXT4_FREE_BLOCKS_METADATA;
+		flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
+	else if (ext4_should_journal_data(inode))
+		flags |= EXT4_FREE_BLOCKS_FORGET;
+
 	/*
 	 * For bigalloc file systems, we never free a partial cluster
 	 * at the beginning of the extent.  Instead, we make a note
···
 	struct ext4_ext_path *path = NULL;
 	ext4_fsblk_t partial_cluster = 0;
 	handle_t *handle;
-	int i = 0, err;
+	int i = 0, err = 0;
 
 	ext_debug("truncate since %u to %u\n", start, end);
 
···
 			return PTR_ERR(path);
 		}
 		depth = ext_depth(inode);
+		/* Leaf not may not exist only if inode has no blocks at all */
 		ex = path[depth].p_ext;
 		if (!ex) {
-			ext4_ext_drop_refs(path);
-			kfree(path);
-			path = NULL;
-			goto cont;
+			if (depth) {
+				EXT4_ERROR_INODE(inode,
+						 "path[%d].p_hdr == NULL",
+						 depth);
+				err = -EIO;
+			}
+			goto out;
 		}
 
 		ee_block = le32_to_cpu(ex->ee_block);
···
 				goto out;
 		}
 	}
-cont:
-
 	/*
 	 * We start scanning from right side, freeing all the blocks
 	 * after i_size and walking into the tree depth-wise.
···
 			ext4_ext_mark_initialized(ex);
 
 		if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
-			ext4_ext_try_to_merge(inode, path, ex);
+			ext4_ext_try_to_merge(handle, inode, path, ex);
 
-		err = ext4_ext_dirty(handle, inode, path + depth);
+		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 		goto out;
 	}
 
···
 			goto fix_extent_len;
 		/* update the extent length and mark as initialized */
 		ex->ee_len = cpu_to_le16(ee_len);
-		ext4_ext_try_to_merge(inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + depth);
+		ext4_ext_try_to_merge(handle, inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 		goto out;
 	} else if (err)
 		goto fix_extent_len;
···
 	return err ? err : map->m_len;
 }
 
-#define EXT4_EXT_ZERO_LEN 7
 /*
  * This function is called by ext4_ext_map_blocks() if someone tries to write
  * to an uninitialized extent. It may result in splitting the uninitialized
···
 					   struct ext4_map_blocks *map,
 					   struct ext4_ext_path *path)
 {
+	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
 	struct ext4_extent zero_ex;
 	struct ext4_extent *ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth;
-	int allocated;
+	int allocated, max_zeroout = 0;
 	int err = 0;
 	int split_flag = 0;
 
···
 		"block %llu, max_blocks %u\n", inode->i_ino,
 		(unsigned long long)map->m_lblk, map->m_len);
 
+	sbi = EXT4_SB(inode->i_sb);
 	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
 		inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map->m_len)
···
 	 */
 	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
 
-	/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
-	if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
-	    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+	if (EXT4_EXT_MAY_ZEROOUT & split_flag)
+		max_zeroout = sbi->s_extent_max_zeroout_kb >>
+			inode->i_sb->s_blocksize_bits;
+
+	/* If extent is less than s_max_zeroout_kb, zeroout directly */
+	if (max_zeroout && (ee_len <= max_zeroout)) {
 		err = ext4_ext_zeroout(inode, ex);
 		if (err)
 			goto out;
···
 		if (err)
 			goto out;
 		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + depth);
+		ext4_ext_try_to_merge(handle, inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 		goto out;
 	}
 
···
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (allocated > map->m_len) {
-		if (allocated <= EXT4_EXT_ZERO_LEN &&
-		    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+	if (max_zeroout && (allocated > map->m_len)) {
+		if (allocated <= max_zeroout) {
 			/* case 3 */
 			zero_ex.ee_block =
 					 cpu_to_le32(map->m_lblk);
···
 				goto out;
 			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if ((map->m_lblk - ee_block + map->m_len <
-			   EXT4_EXT_ZERO_LEN) &&
-			   (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
 			/* case 2 */
 			if (map->m_lblk != ee_block) {
 				zero_ex.ee_block = ex->ee_block;
···
 	}
 
 	allocated = ext4_split_extent(handle, inode, path,
-				       &split_map, split_flag, 0);
+				      &split_map, split_flag, 0);
 	if (allocated < 0)
 		err = allocated;
 
···
  * to an uninitialized extent.
  *
  * Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple /initialized uninitialized extents (up to three)
+ * extent into multiple initialized/uninitialized extents (up to three)
  * There are three possibilities:
  *   a> There is no split required: Entire extent should be uninitialized
  *   b> Splits in two extents: Write is happening at either end of the extent
···
 	/* note: ext4_ext_correct_indexes() isn't needed here because
 	 * borders are not changed
 	 */
-	ext4_ext_try_to_merge(inode, path, ex);
+	ext4_ext_try_to_merge(handle, inode, path, ex);
 
 	/* Mark modified extent as dirty */
-	err = ext4_ext_dirty(handle, inode, path + depth);
+	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 out:
 	ext4_ext_show_leaf(inode, path);
 	return err;
···
 {
 	int ret = 0;
 	int err = 0;
-	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+	ext4_io_end_t *io = ext4_inode_aio(inode);
 
 	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
 		  "block %llu, max_blocks %u, flags %x, allocated %u\n",
···
 	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
 		ret = ext4_split_unwritten_extents(handle, inode, map,
 						   path, flags);
+		if (ret <= 0)
+			goto out;
 		/*
 		 * Flag the inode(non aio case) or end_io struct (aio case)
 		 * that this IO needs to conversion to written when IO is
···
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
-	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+	ext4_io_end_t *io = ext4_inode_aio(inode);
 	ext4_lblk_t cluster_offset;
+	int set_unwritten = 0;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
 		  map->m_lblk, map->m_len, inode->i_ino);
···
 		 * For non asycn direct IO case, flag the inode state
 		 * that we need to perform conversion when IO is done.
 		 */
-		if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-			if (io)
-				ext4_set_io_unwritten_flag(inode, io);
-			else
-				ext4_set_inode_state(inode,
-						     EXT4_STATE_DIO_UNWRITTEN);
-		}
+		if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+			set_unwritten = 1;
 		if (ext4_should_dioread_nolock(inode))
 			map->m_flags |= EXT4_MAP_UNINIT;
 	}
···
 	if (!err)
 		err = ext4_ext_insert_extent(handle, inode, path,
 					     &newex, flags);
+
+	if (!err && set_unwritten) {
+		if (io)
+			ext4_set_io_unwritten_flag(inode, io);
+		else
+			ext4_set_inode_state(inode,
+					     EXT4_STATE_DIO_UNWRITTEN);
+	}
+
 	if (err && free_on_err) {
 		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
 			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
···
 	 * finish any pending end_io work so we won't run the risk of
 	 * converting any truncated blocks to initialized later
 	 */
-	ext4_flush_completed_IO(inode);
+	ext4_flush_unwritten_io(inode);
 
 	/*
 	 * probably first extent we're gonna free will be last in block
···
 	loff_t first_page_offset, last_page_offset;
 	int credits, err = 0;
 
+	/*
+	 * Write out all dirty pages to avoid race conditions
+	 * Then release them.
+	 */
+	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		err = filemap_write_and_wait_range(mapping,
+			offset, offset + length - 1);
+
+		if (err)
+			return err;
+	}
+
+	mutex_lock(&inode->i_mutex);
+	/* It's not possible punch hole on append only file */
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+		err = -EPERM;
+		goto out_mutex;
+	}
+	if (IS_SWAPFILE(inode)) {
+		err = -ETXTBSY;
+		goto out_mutex;
+	}
+
 	/* No need to punch hole beyond i_size */
 	if (offset >= inode->i_size)
-		return 0;
+		goto out_mutex;
 
 	/*
 	 * If the hole extends beyond i_size, set the hole
···
 	first_page_offset = first_page << PAGE_CACHE_SHIFT;
 	last_page_offset = last_page << PAGE_CACHE_SHIFT;
 
-	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		err = filemap_write_and_wait_range(mapping,
-			offset, offset + length - 1);
-
-		if (err)
-			return err;
-	}
-
 	/* Now release the pages */
 	if (last_page_offset > first_page_offset) {
 		truncate_pagecache_range(inode, first_page_offset,
 					 last_page_offset - 1);
 	}
 
-	/* finish any pending end_io work */
-	ext4_flush_completed_IO(inode);
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	err = ext4_flush_unwritten_io(inode);
+	if (err)
+		goto out_dio;
+	inode_dio_wait(inode);
 
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, credits);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto out_dio;
+	}
 
-	err = ext4_orphan_add(handle, inode);
-	if (err)
-		goto out;
 
 	/*
 	 * Now we need to zero out the non-page-aligned data in the
···
 	up_write(&EXT4_I(inode)->i_data_sem);
 
 out:
-	ext4_orphan_del(handle, inode);
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);
+out_dio:
+	ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+	mutex_unlock(&inode->i_mutex);
 	return err;
 }
 int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,

fs/ext4/file.c

···
 	return 0;
 }
 
-static void ext4_aiodio_wait(struct inode *inode)
+void ext4_unwritten_wait(struct inode *inode)
 {
 	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
-	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
 }
 
 /*
···
 				 "performance will be poor.",
 				 inode->i_ino, current->comm);
 		mutex_lock(ext4_aio_mutex(inode));
-		ext4_aiodio_wait(inode);
+		ext4_unwritten_wait(inode);
 	}
 
 	BUG_ON(iocb->ki_pos != pos);

fs/ext4/fsync.c

···
 
 #include <trace/events/ext4.h>
 
-static void dump_completed_IO(struct inode * inode)
-{
-#ifdef	EXT4FS_DEBUG
-	struct list_head *cur, *before, *after;
-	ext4_io_end_t *io, *io0, *io1;
-	unsigned long flags;
-
-	if (list_empty(&EXT4_I(inode)->i_completed_io_list)){
-		ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
-		return;
-	}
-
-	ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino);
-	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
-	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){
-		cur = &io->list;
-		before = cur->prev;
-		io0 = container_of(before, ext4_io_end_t, list);
-		after = cur->next;
-		io1 = container_of(after, ext4_io_end_t, list);
-
-		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
-			    io, inode->i_ino, io0, io1);
-	}
-	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
-#endif
-}
-
-/*
- * This function is called from ext4_sync_file().
- *
- * When IO is completed, the work to convert unwritten extents to
- * written is queued on workqueue but may not get immediately
- * scheduled. When fsync is called, we need to ensure the
- * conversion is complete before fsync returns.
- * The inode keeps track of a list of pending/completed IO that
- * might needs to do the conversion. This function walks through
- * the list and convert the related unwritten extents for completed IO
- * to written.
- * The function return the number of pending IOs on success.
- */
-int ext4_flush_completed_IO(struct inode *inode)
-{
-	ext4_io_end_t *io;
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	unsigned long flags;
-	int ret = 0;
-	int ret2 = 0;
-
-	dump_completed_IO(inode);
-	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	while (!list_empty(&ei->i_completed_io_list)){
-		io = list_entry(ei->i_completed_io_list.next,
-				ext4_io_end_t, list);
-		list_del_init(&io->list);
-		io->flag |= EXT4_IO_END_IN_FSYNC;
-		/*
-		 * Calling ext4_end_io_nolock() to convert completed
-		 * IO to written.
-		 *
-		 * When ext4_sync_file() is called, run_queue() may already
-		 * about to flush the work corresponding to this io structure.
-		 * It will be upset if it founds the io structure related
-		 * to the work-to-be schedule is freed.
-		 *
-		 * Thus we need to keep the io structure still valid here after
-		 * conversion finished. The io structure has a flag to
-		 * avoid double converting from both fsync and background work
-		 * queue work.
-		 */
-		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-		ret = ext4_end_io_nolock(io);
-		if (ret < 0)
-			ret2 = ret;
-		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-		io->flag &= ~EXT4_IO_END_IN_FSYNC;
-	}
-	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-	return (ret2 < 0) ? ret2 : 0;
-}
-
 /*
  * If we're not journaling and this is a just-created file, we have to
  * sync our parent directory (if it was freshly created) since
···
 	struct inode *inode = file->f_mapping->host;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-	int ret;
+	int ret, err;
 	tid_t commit_tid;
 	bool needs_barrier = false;
 
···
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		goto out;
 
-	ret = ext4_flush_completed_IO(inode);
+	ret = ext4_flush_unwritten_io(inode);
 	if (ret < 0)
 		goto out;
 
···
 		needs_barrier = true;
 	jbd2_log_start_commit(journal, commit_tid);
 	ret = jbd2_log_wait_commit(journal, commit_tid);
-	if (needs_barrier)
-		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+	if (needs_barrier) {
+		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+		if (!ret)
+			ret = err;
+	}
  out:
 	mutex_unlock(&inode->i_mutex);
 	trace_ext4_sync_file_exit(inode, ret);

fs/ext4/ialloc.c

···
 		if (!gdp)
 			goto fail;
 
+		/*
+		 * Check free inodes count before loading bitmap.
+		 */
+		if (ext4_free_inodes_count(sb, gdp) == 0) {
+			if (++group == ngroups)
+				group = 0;
+			continue;
+		}
+
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		if (!inode_bitmap_bh)

fs/ext4/indirect.c

···
 
 retry:
 	if (rw == READ && ext4_should_dioread_nolock(inode)) {
-		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+		if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) {
 			mutex_lock(&inode->i_mutex);
-			ext4_flush_completed_IO(inode);
+			ext4_flush_unwritten_io(inode);
 			mutex_unlock(&inode->i_mutex);
+		}
+		/*
+		 * Nolock dioread optimization may be dynamically disabled
+		 * via ext4_inode_block_unlocked_dio(). Check inode's state
+		 * while holding extra i_dio_count ref.
+		 */
+		atomic_inc(&inode->i_dio_count);
+		smp_mb();
+		if (unlikely(ext4_test_inode_state(inode,
+						    EXT4_STATE_DIOREAD_LOCK))) {
+			inode_dio_done(inode);
+			goto locked;
 		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
+		inode_dio_done(inode);
 	} else {
+locked:
 		ret = blockdev_direct_IO(rw, iocb, inode, iov,
 				 offset, nr_segs, ext4_get_block);
 

fs/ext4/inode.c

···
 	err = ext4_map_blocks(handle, inode, &map,
 			      create ? EXT4_GET_BLOCKS_CREATE : 0);
 
+	/* ensure we send some value back into *errp */
+	*errp = 0;
+
 	if (err < 0)
 		*errp = err;
 	if (err <= 0)
 		return NULL;
-	*errp = 0;
 
 	bh = sb_getblk(inode->i_sb, map.m_pblk);
 	if (!bh) {
···
 	return ret;
 }
 
-static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
-static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
-
 /*
  * Note that we don't need to start a transaction unless we're journaling data
  * because we should have holes filled from ext4_page_mkwrite(). We even don't
···
 	free_blocks  = EXT4_C2B(sbi,
 		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
 	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
+	/*
+	 * Start pushing delalloc when 1/2 of free blocks are dirty.
+	 */
+	if (dirty_blocks && (free_blocks < 2 * dirty_blocks) &&
+	    !writeback_in_progress(sb->s_bdi) &&
+	    down_read_trylock(&sb->s_umount)) {
+		writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
+		up_read(&sb->s_umount);
+	}
+
 	if (2 * free_blocks < 3 * dirty_blocks ||
 		free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
 		/*
···
 		 */
 		return 1;
 	}
-	/*
-	 * Even if we don't switch but are nearing capacity,
-	 * start pushing delalloc when 1/2 of free blocks are dirty.
-	 */
-	if (free_blocks < 2 * dirty_blocks)
-		writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE);
-
 	return 0;
 }
 
···
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
         ext4_io_end_t *io_end = iocb->private;
-	struct workqueue_struct *wq;
-	unsigned long flags;
-	struct ext4_inode_info *ei;
 
 	/* if not async direct IO or dio with 0 bytes write, just return */
 	if (!io_end || !size)
···
 		io_end->iocb = iocb;
 		io_end->result = ret;
 	}
-	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
 
-	/* Add the io_end to per-inode completed aio dio list*/
-	ei = EXT4_I(io_end->inode);
-	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	list_add_tail(&io_end->list, &ei->i_completed_io_list);
-	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-
-	/* queue the work to convert unwritten extents to written */
-	queue_work(wq, &io_end->work);
+	ext4_add_complete_io(io_end);
 }
 
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
 {
 	ext4_io_end_t *io_end = bh->b_private;
-	struct workqueue_struct *wq;
 	struct inode *inode;
-	unsigned long flags;
 
 	if (!test_clear_buffer_uninit(bh) || !io_end)
 		goto out;
···
 	 */
 	inode = io_end->inode;
 	ext4_set_io_unwritten_flag(inode, io_end);
-
-	/* Add the io_end to per-inode completed io list*/
-	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
-	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
-	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
-
-	wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
-	/* queue the work to convert unwritten extents to written */
-	queue_work(wq, &io_end->work);
+	ext4_add_complete_io(io_end);
 out:
 	bh->b_private = NULL;
 	bh->b_end_io = NULL;
···
 		overwrite = *((int *)iocb->private);
 
 		if (overwrite) {
+			atomic_inc(&inode->i_dio_count);
 			down_read(&EXT4_I(inode)->i_data_sem);
 			mutex_unlock(&inode->i_mutex);
 		}
···
 		 * hook to the iocb.
  		 */
 		iocb->private = NULL;
-		EXT4_I(inode)->cur_aio_dio = NULL;
+		ext4_inode_aio_set(inode, NULL);
 		if (!is_sync_kiocb(iocb)) {
 			ext4_io_end_t *io_end =
 				ext4_init_io_end(inode, GFP_NOFS);
···
 			 * is a unwritten extents needs to be converted
 			 * when IO is completed.
 			 */
-			EXT4_I(inode)->cur_aio_dio = iocb->private;
+			ext4_inode_aio_set(inode, io_end);
 		}
 
 		if (overwrite)
···
 						 NULL,
 						 DIO_LOCKING);
 		if (iocb->private)
-			EXT4_I(inode)->cur_aio_dio = NULL;
+			ext4_inode_aio_set(inode, NULL);
 		/*
 		 * The io_end structure takes a reference to the inode,
 		 * that structure needs to be destroyed and the
···
 	retake_lock:
 		/* take i_mutex locking again if we do a ovewrite dio */
 		if (overwrite) {
+			inode_dio_done(inode);
 			up_read(&EXT4_I(inode)->i_data_sem);
 			mutex_lock(&inode->i_mutex);
 		}
···
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	int err = 0, rc, block;
+	int need_datasync = 0;
 	uid_t i_uid;
 	gid_t i_gid;
 
···
 		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);
-	ext4_isize_set(raw_inode, ei->i_disksize);
+	if (ei->i_disksize != ext4_isize(raw_inode)) {
+		ext4_isize_set(raw_inode, ei->i_disksize);
+		need_datasync = 1;
+	}
 	if (ei->i_disksize > 0x7fffffffULL) {
 		struct super_block *sb = inode->i_sb;
 		if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
···
 		err = rc;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 
-	ext4_update_inode_fsync_trans(handle, inode, 0);
+	ext4_update_inode_fsync_trans(handle, inode, need_datasync);
 out_brelse:
 	brelse(bh);
 	ext4_std_error(inode->i_sb, err);
···
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		inode_dio_wait(inode);
 
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
···
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(inode))
+		if (attr->ia_size != i_size_read(inode)) {
 			truncate_setsize(inode, attr->ia_size);
+			/* Inode size will be reduced, wait for dio in flight.
+			 * Temporarily disable dioread_nolock to prevent
+			 * livelock. */
+			if (orphan) {
+				ext4_inode_block_unlocked_dio(inode);
+				inode_dio_wait(inode);
+				ext4_inode_resume_unlocked_dio(inode);
+			}
+		}
 		ext4_truncate(inode);
 	}
 
···
 			return err;
 	}
 
+	/* Wait for all existing dio workers */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	jbd2_journal_lock_updates(journal);
 
 	/*
···
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
+	ext4_inode_resume_unlocked_dio(inode);
 
 	/* Finally we can mark the inode as dirty. */
 
···
 	int retries = 0;
 
 	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&

fs/ext4/ioctl.c

···
 			return -EOPNOTSUPP;
 		}
 
-		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
-			       EXT4_FEATURE_INCOMPAT_META_BG)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Online resizing not (yet) supported with meta_bg");
-			return -EOPNOTSUPP;
-		}
-
 		if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
 				   sizeof(__u64))) {
 			return -EFAULT;
-		}
-
-		if (n_blocks_count > MAX_32_NUM &&
-		    !EXT4_HAS_INCOMPAT_FEATURE(sb,
-					       EXT4_FEATURE_INCOMPAT_64BIT)) {
-			ext4_msg(sb, KERN_ERR,
-				 "File system only supports 32-bit block numbers");
-			return -EOPNOTSUPP;
 		}
 
 		err = ext4_resize_begin(sb);
···
 
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
-
-		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
-			ext4_msg(sb, KERN_ERR,
-				 "FITRIM not supported with bigalloc");
-			return -EOPNOTSUPP;
-		}
 
 		if (copy_from_user(&range, (struct fstrim_range __user *)arg,
 		    sizeof(range)))

fs/ext4/mballoc.c

···
 #include "ext4_jbd2.h"
 #include "mballoc.h"
 #include <linux/debugfs.h>
+#include <linux/log2.h>
 #include <linux/slab.h>
 #include <trace/events/ext4.h>
 
···
 	mb_check_buddy(e4b);
 }
 
-static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
+static int mb_find_extent(struct ext4_buddy *e4b, int block,
 				int needed, struct ext4_free_extent *ex)
 {
 	int next = block;
-	int max;
+	int max, order;
 	void *buddy;
 
 	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	BUG_ON(ex == NULL);
 
-	buddy = mb_find_buddy(e4b, order, &max);
+	buddy = mb_find_buddy(e4b, 0, &max);
 	BUG_ON(buddy == NULL);
 	BUG_ON(block >= max);
 	if (mb_test_bit(block, buddy)) {
···
 		return 0;
 	}
 
-	/* FIXME dorp order completely ? */
-	if (likely(order == 0)) {
-		/* find actual order */
-		order = mb_find_order_for_block(e4b, block);
-		block = block >> order;
-	}
+	/* find actual order */
+	order = mb_find_order_for_block(e4b, block);
+	block = block >> order;
 
 	ex->fe_len = 1 << order;
 	ex->fe_start = block << order;
···
 		/* recheck chunk's availability - we don't know
 		 * when it was found (within this lock-unlock
 		 * period or not) */
-		max = mb_find_extent(e4b, 0, bex->fe_start, gex->fe_len, &ex);
+		max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex);
 		if (max >= gex->fe_len) {
 			ext4_mb_use_best_found(ac, e4b);
 			return;
···
 		return err;
 
 	ext4_lock_group(ac->ac_sb, group);
-	max = mb_find_extent(e4b, 0, ex.fe_start, ex.fe_len, &ex);
+	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
 
 	if (max > 0) {
 		ac->ac_b_ex = ex;
···
 	int max;
 	int err;
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 	struct ext4_free_extent ex;
 
 	if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
+		return 0;
+	if (grp->bb_free == 0)
 		return 0;
 
 	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
···
 		return err;
 
 	ext4_lock_group(ac->ac_sb, group);
-	max = mb_find_extent(e4b, 0, ac->ac_g_ex.fe_start,
+	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
 
 	if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
···
 			break;
 		}
 
-		mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
+		mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex);
 		BUG_ON(ex.fe_len <= 0);
 		if (free < ex.fe_len) {
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
···
 
 	while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
 		if (!mb_test_bit(i, bitmap)) {
-			max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
+			max = mb_find_extent(e4b, i, sbi->s_stripe, &ex);
 			if (max >= sbi->s_stripe) {
 				ac->ac_found++;
 				ac->ac_b_ex = ex;
···
 
 	BUG_ON(cr < 0 || cr >= 4);
 
+	free = grp->bb_free;
+	if (free == 0)
+		return 0;
+	if (cr <= 2 && free < ac->ac_g_ex.fe_len)
+		return 0;
+
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
 		int ret = ext4_mb_init_group(ac->ac_sb, group);
···
 			return 0;
 	}
 
-	free = grp->bb_free;
 	fragments = grp->bb_fragments;
-	if (free == 0)
-		return 0;
 	if (fragments == 0)
 		return 0;
 
···
 	return cachep;
 }
 
+/*
+ * Allocate the top-level s_group_info array for the specified number
+ * of groups
+ */
+int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	unsigned size;
+	struct ext4_group_info ***new_groupinfo;
+
+	size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >>
+		EXT4_DESC_PER_BLOCK_BITS(sb);
+	if (size <= sbi->s_group_info_size)
+		return 0;
+
+	size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size);
+	new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL);
+	if (!new_groupinfo) {
+		ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
+		return -ENOMEM;
+	}
+	if (sbi->s_group_info) {
+		memcpy(new_groupinfo, sbi->s_group_info,
+		       sbi->s_group_info_size * sizeof(*sbi->s_group_info));
+		ext4_kvfree(sbi->s_group_info);
+	}
+	sbi->s_group_info = new_groupinfo;
+	sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
+	ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", 
+		   sbi->s_group_info_size);
+	return 0;
+}
+
 /* Create and initialize ext4_group_info data for the given group. */
 int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 			  struct ext4_group_desc *desc)
···
 		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
 	i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
 
-	meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
+	meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_KERNEL);
 	if (meta_group_info[i] == NULL) {
 		ext4_msg(sb, KERN_ERR, "can't allocate buddy mem");
 		goto exit_group_info;
 	}
-	memset(meta_group_info[i], 0, kmem_cache_size(cachep));
 	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT,
 		&(meta_group_info[i]->bb_state));
 
···
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_super_block *es = sbi->s_es;
-	int num_meta_group_infos;
-	int num_meta_group_infos_max;
-	int array_size;
+	int err;
 	struct ext4_group_desc *desc;
 	struct kmem_cache *cachep;
 
-	/* This is the number of blocks used by GDT */
-	num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
-				1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
+	err = ext4_mb_alloc_groupinfo(sb, ngroups);
+	if (err)
+		return err;
 
-	/*
-	 * This is the total number of blocks used by GDT including
-	 * the number of reserved blocks for GDT.
-	 * The s_group_info array is allocated with this value
-	 * to allow a clean online resize without a complex
-	 * manipulation of pointer.
-	 * The drawback is the unused memory when no resize
-	 * occurs but it's very low in terms of pages
-	 * (see comments below)
-	 * Need to handle this properly when META_BG resizing is allowed
-	 */
-	num_meta_group_infos_max = num_meta_group_infos +
-				le16_to_cpu(es->s_reserved_gdt_blocks);
-
-	/*
-	 * array_size is the size of s_group_info array. We round it
-	 * to the next power of two because this approximation is done
-	 * internally by kmalloc so we can have some more memory
-	 * for free here (e.g. may be used for META_BG resize).
-	 */
-	array_size = 1;
-	while (array_size < sizeof(*sbi->s_group_info) *
-	       num_meta_group_infos_max)
-		array_size = array_size << 1;
-	/* An 8TB filesystem with 64-bit pointers requires a 4096 byte
-	 * kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
-	 * So a two level scheme suffices for now. */
-	sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL);
-	if (sbi->s_group_info == NULL) {
-		ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
-		return -ENOMEM;
-	}
 	sbi->s_buddy_cache = new_inode(sb);
 	if (sbi->s_buddy_cache == NULL) {
 		ext4_msg(sb, KERN_ERR, "can't get new inode");
···
 	cachep = get_groupinfo_cache(sb->s_blocksize_bits);
 	while (i-- > 0)
 		kmem_cache_free(cachep, ext4_get_group_info(sb, i));
-	i = num_meta_group_infos;
+	i = sbi->s_group_info_size;
 	while (i-- > 0)
 		kfree(sbi->s_group_info[i]);
 	iput(sbi->s_buddy_cache);
···
 	ext4_get_group_no_and_offset(sb, goal, &group, &block);
 
 	/* set up allocation goals */
-	memset(ac, 0, sizeof(struct ext4_allocation_context));
 	ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
 	ac->ac_status = AC_STATUS_CONTINUE;
 	ac->ac_sb = sb;
···
 		}
 	}
 
-	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+	ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS);
 	if (!ac) {
 		ar->len = 0;
 		*errp = -ENOMEM;
···
 		 * with group lock held. generate_buddy look at
 		 * them with group lock_held
 		 */
+		if (test_opt(sb, DISCARD))
+			ext4_issue_discard(sb, block_group, bit, count);
 		ext4_lock_group(sb, block_group);
 		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
 		mb_free_blocks(inode, &e4b, bit, count_clusters);
···
 
 	start = range->start >> sb->s_blocksize_bits;
 	end = start + (range->len >> sb->s_blocksize_bits) - 1;
-	minlen = range->minlen >> sb->s_blocksize_bits;
+	minlen = EXT4_NUM_B2C(EXT4_SB(sb),
+			      range->minlen >> sb->s_blocksize_bits);
 
 	if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
 	    unlikely(start >= max_blks))
···
 		atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
 
 out:
-	range->len = trimmed * sb->s_blocksize;
+	range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits;
 	return ret;
 }

fs/ext4/mballoc.h

···
 #define MB_DEFAULT_MIN_TO_SCAN		10
 
 /*
- * How many groups mballoc will scan looking for the best chunk
- */
-#define MB_DEFAULT_MAX_GROUPS_TO_SCAN	5
-
-/*
  * with 'ext4_mb_stats' allocator will collect stats that will be
  * shown at umount. The collecting costs though!
  */

fs/ext4/move_extent.c

···
 }
 
 /**
- * mext_check_null_inode - NULL check for two inodes
- *
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
- */
-static int
-mext_check_null_inode(struct inode *inode1, struct inode *inode2,
-		      const char *function, unsigned int line)
-{
-	int ret = 0;
-
-	if (inode1 == NULL) {
-		__ext4_error(inode2->i_sb, function, line,
-			"Both inodes should not be NULL: "
-			"inode1 NULL inode2 %lu", inode2->i_ino);
-		ret = -EIO;
-	} else if (inode2 == NULL) {
-		__ext4_error(inode1->i_sb, function, line,
-			"Both inodes should not be NULL: "
-			"inode1 %lu inode2 NULL", inode1->i_ino);
-		ret = -EIO;
-	}
-	return ret;
-}
-
-/**
  * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
  *
- * @orig_inode:		original inode structure
- * @donor_inode:	donor inode structure
- * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
- * i_ino order.
+ * Acquire write lock of i_data_sem of the two inodes
  */
 static void
-double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+double_down_write_data_sem(struct inode *first, struct inode *second)
 {
-	struct inode *first = orig_inode, *second = donor_inode;
+	if (first < second) {
+		down_write(&EXT4_I(first)->i_data_sem);
+		down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+	} else {
+		down_write(&EXT4_I(second)->i_data_sem);
+		down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
 
-	/*
-	 * Use the inode number to provide the stable locking order instead
-	 * of its address, because the C language doesn't guarantee you can
-	 * compare pointers that don't come from the same array.
-	 */
-	if (donor_inode->i_ino < orig_inode->i_ino) {
-		first = donor_inode;
-		second = orig_inode;
 	}
-
-	down_write(&EXT4_I(first)->i_data_sem);
-	down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
 }
 
 /**
···
 	diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
 
 	ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
-	tmp_dext->ee_block =
-			cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
-	tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);
+	le32_add_cpu(&tmp_dext->ee_block, diff);
+	le16_add_cpu(&tmp_dext->ee_len, -diff);
 
 	if (max_count < ext4_ext_get_actual_len(tmp_dext))
 		tmp_dext->ee_len = cpu_to_le16(max_count);
···
 	copy_extent_status(&dext_old, tmp_oext);
 
 	return 0;
+}
+
+/**
+ * mext_check_coverage - Check that all extents in range has the same type
+ *
+ * @inode:		inode in question
+ * @from:		block offset of inode
+ * @count:		block count to be checked
+ * @uninit:		extents expected to be uninitialized
+ * @err:		pointer to save error value
+ *
+ * Return 1 if all extents in range has expected type, and zero otherwise.
+ */
+static int
+mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
+			  int uninit, int *err)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ext;
+	ext4_lblk_t last = from + count;
+	while (from < last) {
+		*err = get_ext_path(inode, from, &path);
+		if (*err)
+			return 0;
+		ext = path[ext_depth(inode)].p_ext;
+		if (!ext) {
+			ext4_ext_drop_refs(path);
+			return 0;
+		}
+		if (uninit != ext4_ext_is_uninitialized(ext)) {
+			ext4_ext_drop_refs(path);
+			return 0;
+		}
+		from += ext4_ext_get_actual_len(ext);
+		ext4_ext_drop_refs(path);
+	}
+	return 1;
 }
 
 /**
···
 	int depth;
 	int replaced_count = 0;
 	int dext_alen;
-
-	/* Protect extent trees against block allocations via delalloc */
-	double_down_write_data_sem(orig_inode, donor_inode);
 
 	/* Get the original extent for the block "orig_off" */
 	*err = get_ext_path(orig_inode, orig_off, &orig_path);
···
 	ext4_ext_invalidate_cache(orig_inode);
 	ext4_ext_invalidate_cache(donor_inode);
 
-	double_up_write_data_sem(orig_inode, donor_inode);
-
 	return replaced_count;
+}
+
+/**
+ * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2
+ *
+ * @inode1:	the inode structure
+ * @inode2:	the inode structure
+ * @index:	page index
+ * @page:	result page vector
+ *
+ * Grab two locked pages for inode's by inode order
+ */
+static int
+mext_page_double_lock(struct inode *inode1, struct inode *inode2,
+		      pgoff_t index, struct page *page[2])
+{
+	struct address_space *mapping[2];
+	unsigned fl = AOP_FLAG_NOFS;
+
+	BUG_ON(!inode1 || !inode2);
+	if (inode1 < inode2) {
+		mapping[0] = inode1->i_mapping;
+		mapping[1] = inode2->i_mapping;
+	} else {
+		mapping[0] = inode2->i_mapping;
+		mapping[1] = inode1->i_mapping;
+	}
+
+	page[0] = grab_cache_page_write_begin(mapping[0], index, fl);
+	if (!page[0])
+		return -ENOMEM;
+
+	page[1] = grab_cache_page_write_begin(mapping[1], index, fl);
+	if (!page[1]) {
+		unlock_page(page[0]);
+		page_cache_release(page[0]);
+		return -ENOMEM;
+	}
+
+	if (inode1 > inode2) {
+		struct page *tmp;
+		tmp = page[0];
+		page[0] = page[1];
+		page[1] = tmp;
+	}
+	return 0;
+}
+
+/* Force page buffers uptodate w/o dropping page's lock */
+static int
+mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
+{
+	struct inode *inode = page->mapping->host;
+	sector_t block;
+	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
+	unsigned int blocksize, block_start, block_end;
+	int i, err,  nr = 0, partial = 0;
+	BUG_ON(!PageLocked(page));
+	BUG_ON(PageWriteback(page));
+
+	if (PageUptodate(page))
+		return 0;
+
+	blocksize = 1 << inode->i_blkbits;
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+
+	head = page_buffers(page);
+	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	for (bh = head, block_start = 0; bh != head || !block_start;
+	     block++, block_start = block_end, bh = bh->b_this_page) {
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (!buffer_uptodate(bh))
+				partial = 1;
+			continue;
+		}
+		if (buffer_uptodate(bh))
+			continue;
+		if (!buffer_mapped(bh)) {
+			int err = 0;
+			err = ext4_get_block(inode, block, bh, 0);
+			if (err) {
+				SetPageError(page);
+				return err;
+			}
+			if (!buffer_mapped(bh)) {
+				zero_user(page, block_start, blocksize);
+				if (!err)
+					set_buffer_uptodate(bh);
+				continue;
+			}
+		}
+		BUG_ON(nr >= MAX_BUF_PER_PAGE);
+		arr[nr++] = bh;
+	}
+	/* No io required */
+	if (!nr)
+		goto out;
+
+	for (i = 0; i < nr; i++) {
+		bh = arr[i];
+		if (!bh_uptodate_or_lock(bh)) {
+			err = bh_submit_read(bh);
+			if (err)
+				return err;
+		}
+	}
+out:
+	if (!partial)
+		SetPageUptodate(page);
+	return 0;
 }
 
 /**
···
 		  int block_len_in_page, int uninit, int *err)
 {
 	struct inode *orig_inode = o_filp->f_dentry->d_inode;
-	struct address_space *mapping = orig_inode->i_mapping;
-	struct buffer_head *bh;
-	struct page *page = NULL;
-	const struct address_space_operations *a_ops = mapping->a_ops;
+	struct page *pagep[2] = {NULL, NULL};
 	handle_t *handle;
 	ext4_lblk_t orig_blk_offset;
 	long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int w_flags = 0;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	void *fsdata;
-	int i, jblocks;
-	int err2 = 0;
+	int err2, jblocks, retries = 0;
 	int replaced_count = 0;
+	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
 	 * inode and donor_inode may change each different metadata blocks.
 	 */
+again:
+	*err = 0;
 	jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
 	handle = ext4_journal_start(orig_inode, jblocks);
 	if (IS_ERR(handle)) {
···
 
 	orig_blk_offset = orig_page_offset * blocks_per_page +
 		data_offset_in_page;
-
-	/*
-	 * If orig extent is uninitialized one,
-	 * it's not necessary force the page into memory
-	 * and then force it to be written out again.
-	 * Just swap data blocks between orig and donor.
-	 */
-	if (uninit) {
-		replaced_count = mext_replace_branches(handle, orig_inode,
-						donor_inode, orig_blk_offset,
-						block_len_in_page, err);
-		goto out2;
-	}
 
 	offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
 
···
 
 	replaced_size = data_size;
 
-	*err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags,
-				 &page, &fsdata);
+	*err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
+				     pagep);
 	if (unlikely(*err < 0))
-		goto out;
+		goto stop_journal;
+	/*
+	 * If orig extent was uninitialized it can become initialized
+	 * at any time after i_data_sem was dropped, in order to
+	 * serialize with delalloc we have recheck extent while we
+	 * hold page's lock, if it is still the case data copy is not
+	 * necessary, just swap data blocks between orig and donor.
+	 */
+	if (uninit) {
+		double_down_write_data_sem(orig_inode, donor_inode);
+		/* If any of extents in range became initialized we have to
+		 * fallback to data copying */
+		uninit = mext_check_coverage(orig_inode, orig_blk_offset,
+					     block_len_in_page, 1, err);
+		if (*err)
+			goto drop_data_sem;
 
-	if (!PageUptodate(page)) {
-		mapping->a_ops->readpage(o_filp, page);
-		lock_page(page);
+		uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
+					      block_len_in_page, 1, err);
+		if (*err)
+			goto drop_data_sem;
+
+		if (!uninit) {
+			double_up_write_data_sem(orig_inode, donor_inode);
+			goto data_copy;
+		}
+		if ((page_has_private(pagep[0]) &&
+		     !try_to_release_page(pagep[0], 0)) ||
+		    (page_has_private(pagep[1]) &&
+		     !try_to_release_page(pagep[1], 0))) {
+			*err = -EBUSY;
+			goto drop_data_sem;
+		}
+		replaced_count = mext_replace_branches(handle, orig_inode,
+						donor_inode, orig_blk_offset,
+						block_len_in_page, err);
+	drop_data_sem:
+		double_up_write_data_sem(orig_inode, donor_inode);
+		goto unlock_pages;
+	}
+data_copy:
+	*err = mext_page_mkuptodate(pagep[0], from, from + replaced_size);
+	if (*err)
+		goto unlock_pages;
+
+	/* At this point all buffers in range are uptodate, old mapping layout
+	 * is no longer required, try to drop it now. */
+	if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) ||
+	    (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) {
+		*err = -EBUSY;
+		goto unlock_pages;
 	}
 
-	/*
-	 * try_to_release_page() doesn't call releasepage in writeback mode.
-	 * We should care about the order of writing to the same file
-	 * by multiple move extent processes.
-	 * It needs to call wait_on_page_writeback() to wait for the
-	 * writeback of the page.
-	 */
-	wait_on_page_writeback(page);
-
-	/* Release old bh and drop refs */
-	try_to_release_page(page, 0);
-
 	replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
-					orig_blk_offset, block_len_in_page,
-					&err2);
-	if (err2) {
+					       orig_blk_offset,
+					       block_len_in_page, err);
+	if (*err) {
 		if (replaced_count) {
 			block_len_in_page = replaced_count;
 			replaced_size =
 				block_len_in_page << orig_inode->i_blkbits;
 		} else
-			goto out;
+			goto unlock_pages;
 	}
+	/* Perform all necessary steps similar write_begin()/write_end()
+	 * but keeping in mind that i_size will not change */
+	*err = __block_write_begin(pagep[0], from, from + replaced_size,
+				   ext4_get_block);
+	if (!*err)
+		*err = block_commit_write(pagep[0], from, from + replaced_size);
 
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0);
+	if (unlikely(*err < 0))
+		goto repair_branches;
 
-	bh = page_buffers(page);
-	for (i = 0; i < data_offset_in_page; i++)
-		bh = bh->b_this_page;
+	/* Even in case of data=writeback it is reasonable to pin
+	 * inode to transaction, to prevent unexpected data loss */
+	*err = ext4_jbd2_file_inode(handle, orig_inode);
 
-	for (i = 0; i < block_len_in_page; i++) {
-		*err = ext4_get_block(orig_inode,
-				(sector_t)(orig_blk_offset + i), bh, 0);
-		if (*err < 0)
-			goto out;
-
-		if (bh->b_this_page != NULL)
-			bh = bh->b_this_page;
-	}
-
-	*err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size,
-			       page, fsdata);
-	page = NULL;
-
-out:
-	if (unlikely(page)) {
-		if (PageLocked(page))
-			unlock_page(page);
-		page_cache_release(page);
-		ext4_journal_stop(handle);
-	}
-out2:
+unlock_pages:
+	unlock_page(pagep[0]);
+	page_cache_release(pagep[0]);
+	unlock_page(pagep[1]);
+	page_cache_release(pagep[1]);
+stop_journal:
 	ext4_journal_stop(handle);
-
-	if (err2)
-		*err = err2;
-
+	/* Buffer was busy because probably is pinned to journal transaction,
+	 * force transaction commit may help to free it. */
+	if (*err == -EBUSY && ext4_should_retry_alloc(orig_inode->i_sb,
+						      &retries))
+		goto again;
 	return replaced_count;
+
+repair_branches:
+	/*
+	 * This should never ever happen!
+	 * Extents are swapped already, but we are not able to copy data.
+	 * Try to swap extents to it's original places
+	 */
+	double_down_write_data_sem(orig_inode, donor_inode);
+	replaced_count = mext_replace_branches(handle, donor_inode, orig_inode,
+					       orig_blk_offset,
+					       block_len_in_page, &err2);
+	double_up_write_data_sem(orig_inode, donor_inode);
+	if (replaced_count != block_len_in_page) {
+		EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset),
+				       "Unable to copy data block,"
+				       " data will be lost.");
+		*err = -EIO;
+	}
+	replaced_count = 0;
+	goto unlock_pages;
 }
 
 /**
···
 		return -EINVAL;
 	}
 
-	/* Files should be in the same ext4 FS */
-	if (orig_inode->i_sb != donor_inode->i_sb) {
-		ext4_debug("ext4 move extent: The argument files "
-			"should be in same FS [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
 	/* Ext4 move extent supports only extent based file */
 	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
 		ext4_debug("ext4 move extent: orig file is not extents "
···
 	}
 
 	if ((orig_start >= EXT_MAX_BLOCKS) ||
-	    (donor_start >= EXT_MAX_BLOCKS) ||
 	    (*len > EXT_MAX_BLOCKS) ||
 	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
 		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
···
  * @inode1:	the inode structure
  * @inode2:	the inode structure
  *
- * Lock two inodes' i_mutex by i_ino order.
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ * Lock two inodes' i_mutex
  */
-static int
+static void
 mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
 {
-	int ret = 0;
-
-	BUG_ON(inode1 == NULL && inode2 == NULL);
-
-	ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
-	if (ret < 0)
-		goto out;
-
-	if (inode1 == inode2) {
-		mutex_lock(&inode1->i_mutex);
-		goto out;
-	}
-
-	if (inode1->i_ino < inode2->i_ino) {
+	BUG_ON(inode1 == inode2);
+	if (inode1 < inode2) {
 		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
 		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
 	} else {
 		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
 		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
 	}
-
-out:
-	return ret;
 }
 
 /**
···
  * @inode1:     the inode that is released first
  * @inode2:     the inode that is released second
  *
- * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
  */
 
-static int
+static void
 mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
 {
-	int ret = 0;
-
-	BUG_ON(inode1 == NULL && inode2 == NULL);
-
-	ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
-	if (ret < 0)
-		goto out;
-
-	if (inode1)
-		mutex_unlock(&inode1->i_mutex);
-
-	if (inode2 && inode2 != inode1)
-		mutex_unlock(&inode2->i_mutex);
-
-out:
-	return ret;
+	mutex_unlock(&inode1->i_mutex);
+	mutex_unlock(&inode2->i_mutex);
 }
 
 /**
···
 	ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
 	ext4_lblk_t rest_blocks;
 	pgoff_t orig_page_offset = 0, seq_end_page;
-	int ret1, ret2, depth, last_extent = 0;
+	int ret, depth, last_extent = 0;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	int data_offset_in_page;
 	int block_len_in_page;
 	int uninit;
 
-	/* orig and donor should be different file */
-	if (orig_inode->i_ino == donor_inode->i_ino) {
+	if (orig_inode->i_sb != donor_inode->i_sb) {
+		ext4_debug("ext4 move extent: The argument files "
+			"should be in same FS [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* orig and donor should be different inodes */
+	if (orig_inode == donor_inode) {
 		ext4_debug("ext4 move extent: The argument files should not "
-			"be same file [ino:orig %lu, donor %lu]\n",
+			"be same inode [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
···
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
-
+	/* TODO: This is non obvious task to swap blocks for inodes with full
+	   jornaling enabled */
+	if (ext4_should_journal_data(orig_inode) ||
+	    ext4_should_journal_data(donor_inode)) {
+		return -EINVAL;
+	}
 	/* Protect orig and donor inodes against a truncate */
-	ret1 = mext_inode_double_lock(orig_inode, donor_inode);
-	if (ret1 < 0)
-		return ret1;
+	mext_inode_double_lock(orig_inode, donor_inode);
+
+	/* Wait for all existing dio workers */
+	ext4_inode_block_unlocked_dio(orig_inode);
+	ext4_inode_block_unlocked_dio(donor_inode);
+	inode_dio_wait(orig_inode);
+	inode_dio_wait(donor_inode);
 
 	/* Protect extent tree against block allocations via delalloc */
 	double_down_write_data_sem(orig_inode, donor_inode);
 	/* Check the filesystem environment whether move_extent can be done */
-	ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
+	ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
 				    donor_start, &len);
-	if (ret1)
+	if (ret)
 		goto out;
 
 	file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
···
 	if (file_end < block_end)
 		len -= block_end - file_end;
 
-	ret1 = get_ext_path(orig_inode, block_start, &orig_path);
-	if (ret1)
+	ret = get_ext_path(orig_inode, block_start, &orig_path);
+	if (ret)
 		goto out;
 
 	/* Get path structure to check the hole */
-	ret1 = get_ext_path(orig_inode, block_start, &holecheck_path);
-	if (ret1)
+	ret = get_ext_path(orig_inode, block_start, &holecheck_path);
+	if (ret)
 		goto out;
 
 	depth = ext_depth(orig_inode);
···
 		last_extent = mext_next_extent(orig_inode,
 					holecheck_path, &ext_cur);
 		if (last_extent < 0) {
-			ret1 = last_extent;
+			ret = last_extent;
 			goto out;
 		}
 		last_extent = mext_next_extent(orig_inode, orig_path,
 							&ext_dummy);
 		if (last_extent < 0) {
-			ret1 = last_extent;
+			ret = last_extent;
 			goto out;
 		}
 		seq_start = le32_to_cpu(ext_cur->ee_block);
···
 	if (le32_to_cpu(ext_cur->ee_block) > block_end) {
 		ext4_debug("ext4 move extent: The specified range of file "
 							"may be the hole\n");
-		ret1 = -EINVAL;
+		ret = -EINVAL;
 		goto out;
 	}
 
···
 		last_extent = mext_next_extent(orig_inode, holecheck_path,
 						&ext_cur);
 		if (last_extent < 0) {
-			ret1 = last_extent;
+			ret = last_extent;
 			break;
 		}
 		add_blocks = ext4_ext_get_actual_len(ext_cur);
···
 						orig_page_offset,
 						data_offset_in_page,
 						block_len_in_page, uninit,
-						&ret1);
+						&ret);
 
 			/* Count how many blocks we have exchanged */
 			*moved_len += block_len_in_page;
-			if (ret1 < 0)
+			if (ret < 0)
 				break;
 			if (*moved_len > len) {
 				EXT4_ERROR_INODE(orig_inode,
 					"We replaced blocks too much! "
 					"sum of replaced: %llu requested: %llu",
 					*moved_len, len);
-				ret1 = -EIO;
+				ret = -EIO;
 				break;
 			}
 
···
 		}
 
 		double_down_write_data_sem(orig_inode, donor_inode);
-		if (ret1 < 0)
+		if (ret < 0)
 			break;
 
 		/* Decrease buffer counter */
 		if (holecheck_path)
 			ext4_ext_drop_refs(holecheck_path);
-		ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path);
-		if (ret1)
+		ret = get_ext_path(orig_inode, seq_start, &holecheck_path);
+		if (ret)
 			break;
 		depth = holecheck_path->p_depth;
 
 		/* Decrease buffer counter */
 		if (orig_path)
 			ext4_ext_drop_refs(orig_path);
-		ret1 = get_ext_path(orig_inode, seq_start, &orig_path);
-		if (ret1)
+		ret = get_ext_path(orig_inode, seq_start, &orig_path);
+		if (ret)
 			break;
 
 		ext_cur = holecheck_path[depth].p_ext;
···
 		kfree(holecheck_path);
 	}
 	double_up_write_data_sem(orig_inode, donor_inode);
-	ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
+	ext4_inode_resume_unlocked_dio(orig_inode);
+	ext4_inode_resume_unlocked_dio(donor_inode);
+	mext_inode_double_unlock(orig_inode, donor_inode);
 
-	if (ret1)
-		return ret1;
-	else if (ret2)
-		return ret2;
-
-	return 0;
+	return ret;
 }

fs/ext4/namei.c

···
 {
 	struct buffer_head *bh;
 
+	if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb &&
+		     ((inode->i_size >> 10) >=
+		      EXT4_SB(inode->i_sb)->s_max_dir_size_kb))) {
+		*err = -ENOSPC;
+		return NULL;
+	}
+
 	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
 
 	bh = ext4_bread(handle, inode, *block, 1, err);
···
 			brelse(bh);
 			bh = NULL;
 		}
+	}
+	if (!bh && !(*err)) {
+		*err = -EIO;
+		ext4_error(inode->i_sb,
+			   "Directory hole detected on inode %lu\n",
+			   inode->i_ino);
 	}
 	return bh;
 }
···
 	u32 hash;
 
 	frame->bh = NULL;
-	if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
+	if (!(bh = ext4_bread(NULL, dir, 0, 0, err))) {
+		if (*err == 0)
+			*err = ERR_BAD_DX_DIR;
 		goto fail;
+	}
 	root = (struct dx_root *) bh->b_data;
 	if (root->info.hash_version != DX_HASH_TEA &&
 	    root->info.hash_version != DX_HASH_HALF_MD4 &&
···
 		frame->entries = entries;
 		frame->at = at;
 		if (!indirect--) return frame;
-		if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err)))
+		if (!(bh = ext4_bread(NULL, dir, dx_get_block(at), 0, err))) {
+			if (!(*err))
+				*err = ERR_BAD_DX_DIR;
 			goto fail2;
+		}
 		at = entries = ((struct dx_node *) bh->b_data)->entries;
 
 		if (!buffer_verified(bh) &&
···
 	 */
 	while (num_frames--) {
 		if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at),
-				      0, &err)))
+				      0, &err))) {
+			if (!err) {
+				ext4_error(dir->i_sb,
+					   "Directory hole detected on inode %lu\n",
+					   dir->i_ino);
+				return -EIO;
+			}
 			return err; /* Failure */
+		}
 
 		if (!buffer_verified(bh) &&
 		    !ext4_dx_csum_verify(dir,
···
 {
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de, *top;
-	int err, count = 0;
+	int err = 0, count = 0;
 
 	dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
 							(unsigned long)block));
-	if (!(bh = ext4_bread (NULL, dir, block, 0, &err)))
+	if (!(bh = ext4_bread(NULL, dir, block, 0, &err))) {
+		if (!err) {
+			err = -EIO;
+			ext4_error(dir->i_sb,
+				   "Directory hole detected on inode %lu\n",
+				   dir->i_ino);
+		}
 		return err;
+	}
 
 	if (!buffer_verified(bh) &&
 	    !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data))
···
 		return NULL;
 	do {
 		block = dx_get_block(frame->at);
-		if (!(bh = ext4_bread(NULL, dir, block, 0, err)))
+		if (!(bh = ext4_bread(NULL, dir, block, 0, err))) {
+			if (!(*err)) {
+				*err = -EIO;
+				ext4_error(dir->i_sb,
+					   "Directory hole detected on inode %lu\n",
+					   dir->i_ino);
+			}
 			goto errout;
+		}
 
 		if (!buffer_verified(bh) &&
 		    !ext4_dirent_csum_verify(dir,
···
 	}
 	blocks = dir->i_size >> sb->s_blocksize_bits;
 	for (block = 0; block < blocks; block++) {
-		bh = ext4_bread(handle, dir, block, 0, &retval);
-		if(!bh)
+		if (!(bh = ext4_bread(handle, dir, block, 0, &retval))) {
+			if (!retval) {
+				retval = -EIO;
+				ext4_error(inode->i_sb,
+					   "Directory hole detected on inode %lu\n",
+					   inode->i_ino);
+			}
 			return retval;
+		}
 		if (!buffer_verified(bh) &&
 		    !ext4_dirent_csum_verify(dir,
 				(struct ext4_dir_entry *)bh->b_data))
···
 	entries = frame->entries;
 	at = frame->at;
 
-	if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err)))
+	if (!(bh = ext4_bread(handle, dir, dx_get_block(frame->at), 0, &err))) {
+		if (!err) {
+			err = -EIO;
+			ext4_error(dir->i_sb,
+				   "Directory hole detected on inode %lu\n",
+				   dir->i_ino);
+		}
 		goto cleanup;
+	}
 
 	if (!buffer_verified(bh) &&
 	    !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data))
···
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT4_FS_XATTR
 		inode->i_op = &ext4_special_inode_operations;
-#endif
 		err = ext4_add_nondir(handle, dentry, inode);
 	}
 	ext4_journal_stop(handle);
···
 	inode->i_op = &ext4_dir_inode_operations;
 	inode->i_fop = &ext4_dir_operations;
 	inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
-	dir_block = ext4_bread(handle, inode, 0, 1, &err);
-	if (!dir_block)
+	if (!(dir_block = ext4_bread(handle, inode, 0, 1, &err))) {
+		if (!err) {
+			err = -EIO;
+			ext4_error(inode->i_sb,
+				   "Directory hole detected on inode %lu\n",
+				   inode->i_ino);
+		}
 		goto out_clear_inode;
+	}
 	BUFFER_TRACE(dir_block, "get_write_access");
 	err = ext4_journal_get_write_access(handle, dir_block);
 	if (err)
···
 					EXT4_ERROR_INODE(inode,
 						"error %d reading directory "
 						"lblock %u", err, lblock);
+				else
+					ext4_warning(inode->i_sb,
+						"bad directory (dir #%lu) - no data block",
+						inode->i_ino);
+
 				offset += sb->s_blocksize;
 				continue;
 			}
···
 	struct ext4_iloc iloc;
 	int err = 0, rc;
 
-	if (!ext4_handle_valid(handle))
+	if (!EXT4_SB(sb)->s_journal)
 		return 0;
 
 	mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
···
 	struct ext4_iloc iloc;
 	int err = 0;
 
-	/* ext4_handle_valid() assumes a valid handle_t pointer */
-	if (handle && !ext4_handle_valid(handle))
+	if (!EXT4_SB(inode->i_sb)->s_journal)
 		return 0;
 
 	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
···
 	 * transaction handle with which to update the orphan list on
 	 * disk, but we still need to remove the inode from the linked
 	 * list in memory. */
-	if (sbi->s_journal && !handle)
+	if (!handle)
 		goto out;
 
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
···
 				goto end_rename;
 		}
 		retval = -EIO;
-		dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
-		if (!dir_bh)
+		if (!(dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval))) {
+			if (!retval) {
+				retval = -EIO;
+				ext4_error(old_inode->i_sb,
+					   "Directory hole detected on inode %lu\n",
+					   old_inode->i_ino);
+			}
 			goto end_rename;
+		}
 		if (!buffer_verified(dir_bh) &&
 		    !ext4_dirent_csum_verify(old_inode,
 				(struct ext4_dir_entry *)dir_bh->b_data))

fs/ext4/page-io.c

···
 	int i;
 
 	BUG_ON(!io);
+	BUG_ON(!list_empty(&io->list));
+	BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
+
 	if (io->page)
 		put_page(io->page);
 	for (i = 0; i < io->num_io_pages; i++)
···
 	kmem_cache_free(io_end_cachep, io);
 }
 
-/*
- * check a range of space and convert unwritten extents to written.
- *
- * Called with inode->i_mutex; we depend on this when we manipulate
- * io->flag, since we could otherwise race with ext4_flush_completed_IO()
- */
-int ext4_end_io_nolock(ext4_io_end_t *io)
+/* check a range of space and convert unwritten extents to written. */
+static int ext4_end_io(ext4_io_end_t *io)
 {
 	struct inode *inode = io->inode;
 	loff_t offset = io->offset;
···
 			 "(inode %lu, offset %llu, size %zd, error %d)",
 			 inode->i_ino, offset, size, ret);
 	}
-
 	if (io->iocb)
 		aio_complete(io->iocb, io->result, 0);
 
 	if (io->flag & EXT4_IO_END_DIRECT)
 		inode_dio_done(inode);
 	/* Wake up anyone waiting on unwritten extent conversion */
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
+	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
 		wake_up_all(ext4_ioend_wq(io->inode));
+	return ret;
+}
+
+static void dump_completed_IO(struct inode *inode)
+{
+#ifdef	EXT4FS_DEBUG
+	struct list_head *cur, *before, *after;
+	ext4_io_end_t *io, *io0, *io1;
+	unsigned long flags;
+
+	if (list_empty(&EXT4_I(inode)->i_completed_io_list)) {
+		ext4_debug("inode %lu completed_io list is empty\n",
+			   inode->i_ino);
+		return;
+	}
+
+	ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino);
+	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) {
+		cur = &io->list;
+		before = cur->prev;
+		io0 = container_of(before, ext4_io_end_t, list);
+		after = cur->next;
+		io1 = container_of(after, ext4_io_end_t, list);
+
+		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+			    io, inode->i_ino, io0, io1);
+	}
+#endif
+}
+
+/* Add the io_end to per-inode completed end_io list. */
+void ext4_add_complete_io(ext4_io_end_t *io_end)
+{
+	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
+	struct workqueue_struct *wq;
+	unsigned long flags;
+
+	BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	if (list_empty(&ei->i_completed_io_list)) {
+		io_end->flag |= EXT4_IO_END_QUEUED;
+		queue_work(wq, &io_end->work);
+	}
+	list_add_tail(&io_end->list, &ei->i_completed_io_list);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+}
+
+static int ext4_do_flush_completed_IO(struct inode *inode,
+				      ext4_io_end_t *work_io)
+{
+	ext4_io_end_t *io;
+	struct list_head unwritten, complete, to_free;
+	unsigned long flags;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int err, ret = 0;
+
+	INIT_LIST_HEAD(&complete);
+	INIT_LIST_HEAD(&to_free);
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	dump_completed_IO(inode);
+	list_replace_init(&ei->i_completed_io_list, &unwritten);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+	while (!list_empty(&unwritten)) {
+		io = list_entry(unwritten.next, ext4_io_end_t, list);
+		BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
+		list_del_init(&io->list);
+
+		err = ext4_end_io(io);
+		if (unlikely(!ret && err))
+			ret = err;
+
+		list_add_tail(&io->list, &complete);
+	}
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	while (!list_empty(&complete)) {
+		io = list_entry(complete.next, ext4_io_end_t, list);
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* end_io context can not be destroyed now because it still
+		 * used by queued worker. Worker thread will destroy it later */
+		if (io->flag & EXT4_IO_END_QUEUED)
+			list_del_init(&io->list);
+		else
+			list_move(&io->list, &to_free);
+	}
+	/* If we are called from worker context, it is time to clear queued
+	 * flag, and destroy it's end_io if it was converted already */
+	if (work_io) {
+		work_io->flag &= ~EXT4_IO_END_QUEUED;
+		if (!(work_io->flag & EXT4_IO_END_UNWRITTEN))
+			list_add_tail(&work_io->list, &to_free);
+	}
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+	while (!list_empty(&to_free)) {
+		io = list_entry(to_free.next, ext4_io_end_t, list);
+		list_del_init(&io->list);
+		ext4_free_io_end(io);
+	}
 	return ret;
 }
 
···
  */
 static void ext4_end_io_work(struct work_struct *work)
 {
-	ext4_io_end_t		*io = container_of(work, ext4_io_end_t, work);
-	struct inode		*inode = io->inode;
-	struct ext4_inode_info	*ei = EXT4_I(inode);
-	unsigned long		flags;
+	ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
+	ext4_do_flush_completed_IO(io->inode, io);
+}
 
-	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	if (io->flag & EXT4_IO_END_IN_FSYNC)
-		goto requeue;
-	if (list_empty(&io->list)) {
-		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-		goto free;
-	}
-
-	if (!mutex_trylock(&inode->i_mutex)) {
-		bool was_queued;
-requeue:
-		was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
-		io->flag |= EXT4_IO_END_QUEUED;
-		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-		/*
-		 * Requeue the work instead of waiting so that the work
-		 * items queued after this can be processed.
-		 */
-		queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
-		/*
-		 * To prevent the ext4-dio-unwritten thread from keeping
-		 * requeueing end_io requests and occupying cpu for too long,
-		 * yield the cpu if it sees an end_io request that has already
-		 * been requeued.
-		 */
-		if (was_queued)
-			yield();
-		return;
-	}
-	list_del_init(&io->list);
-	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-	(void) ext4_end_io_nolock(io);
-	mutex_unlock(&inode->i_mutex);
-free:
-	ext4_free_io_end(io);
+int ext4_flush_unwritten_io(struct inode *inode)
+{
+	int ret;
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
+		     !(inode->i_state & I_FREEING));
+	ret = ext4_do_flush_completed_IO(inode, NULL);
+	ext4_unwritten_wait(inode);
+	return ret;
 }
 
 ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
···
 static void ext4_end_bio(struct bio *bio, int error)
 {
 	ext4_io_end_t *io_end = bio->bi_private;
-	struct workqueue_struct *wq;
 	struct inode *inode;
-	unsigned long flags;
 	int i;
 	sector_t bi_sector = bio->bi_sector;
 
···
 		return;
 	}
 
-	/* Add the io_end to per-inode completed io list*/
-	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
-	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
-	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
-
-	wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
-	/* queue the work to convert unwritten extents to written */
-	queue_work(wq, &io_end->work);
+	ext4_add_complete_io(io_end);
 }
 
 void ext4_io_submit(struct ext4_io_submit *io)

fs/ext4/resize.c

···
 	smp_mb__after_clear_bit();
 }
 
+static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
+					     ext4_group_t group) {
+	return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) <<
+	       EXT4_DESC_PER_BLOCK_BITS(sb);
+}
+
+static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb,
+					     ext4_group_t group) {
+	group = ext4_meta_bg_first_group(sb, group);
+	return ext4_group_first_block_no(sb, group);
+}
+
+static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb,
+						ext4_group_t group) {
+	ext4_grpblk_t overhead;
+	overhead = ext4_bg_num_gdb(sb, group);
+	if (ext4_bg_has_super(sb, group))
+		overhead += 1 +
+			  le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
+	return overhead;
+}
+
 #define outside(b, first, last)	((b) < (first) || (b) >= (last))
 #define inside(b, first, last)	((b) >= (first) && (b) < (last))
 
···
 	ext4_fsblk_t end = start + input->blocks_count;
 	ext4_group_t group = input->group;
 	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
-	unsigned overhead = ext4_bg_has_super(sb, group) ?
-		(1 + ext4_bg_num_gdb(sb, group) +
-		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+	unsigned overhead = ext4_group_overhead_blocks(sb, group);
 	ext4_fsblk_t metaend = start + overhead;
 	struct buffer_head *bh = NULL;
 	ext4_grpblk_t free_blocks_count, offset;
···
  * be a partial of a flex group.
  *
  * @sb: super block of fs to which the groups belongs
+ *
+ * Returns 0 on a successful allocation of the metadata blocks in the
+ * block group.
  */
-static void ext4_alloc_group_tables(struct super_block *sb,
+static int ext4_alloc_group_tables(struct super_block *sb,
 				struct ext4_new_flex_group_data *flex_gd,
 				int flexbg_size)
 {
 	struct ext4_new_group_data *group_data = flex_gd->groups;
-	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	ext4_fsblk_t start_blk;
 	ext4_fsblk_t last_blk;
 	ext4_group_t src_group;
···
 	       (last_group & ~(flexbg_size - 1))));
 next_group:
 	group = group_data[0].group;
+	if (src_group >= group_data[0].group + flex_gd->count)
+		return -ENOSPC;
 	start_blk = ext4_group_first_block_no(sb, src_group);
 	last_blk = start_blk + group_data[src_group - group].blocks_count;
 
-	overhead = ext4_bg_has_super(sb, src_group) ?
-		   (1 + ext4_bg_num_gdb(sb, src_group) +
-		    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+	overhead = ext4_group_overhead_blocks(sb, src_group);
 
 	start_blk += overhead;
 
-	BUG_ON(src_group >= group_data[0].group + flex_gd->count);
 	/* We collect contiguous blocks as much as possible. */
 	src_group++;
-	for (; src_group <= last_group; src_group++)
-		if (!ext4_bg_has_super(sb, src_group))
+	for (; src_group <= last_group; src_group++) {
+		overhead = ext4_group_overhead_blocks(sb, src_group);
+		if (overhead != 0)
 			last_blk += group_data[src_group - group].blocks_count;
 		else
 			break;
+	}
 
 	/* Allocate block bitmaps */
 	for (; bb_index < flex_gd->count; bb_index++) {
···
 			       group_data[i].free_blocks_count);
 		}
 	}
+	return 0;
 }
 
 static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
···
 	ext4_group_t group, count;
 	struct buffer_head *bh = NULL;
 	int reserved_gdb, i, j, err = 0, err2;
+	int meta_bg;
 
 	BUG_ON(!flex_gd->count || !group_data ||
 	       group_data[0].group != sbi->s_groups_count);
 
 	reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
+	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
 
 	/* This transaction may be extended/restarted along the way */
 	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
···
 	group = group_data[0].group;
 	for (i = 0; i < flex_gd->count; i++, group++) {
 		unsigned long gdblocks;
+		ext4_grpblk_t overhead;
 
 		gdblocks = ext4_bg_num_gdb(sb, group);
 		start = ext4_group_first_block_no(sb, group);
 
+		if (meta_bg == 0 && !ext4_bg_has_super(sb, group))
+			goto handle_itb;
+
+		if (meta_bg == 1) {
+			ext4_group_t first_group;
+			first_group = ext4_meta_bg_first_group(sb, group);
+			if (first_group != group + 1 &&
+			    first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1)
+				goto handle_itb;
+		}
+
+		block = start + ext4_bg_has_super(sb, group);
 		/* Copy all of the GDT blocks into the backup in this group */
-		for (j = 0, block = start + 1; j < gdblocks; j++, block++) {
+		for (j = 0; j < gdblocks; j++, block++) {
 			struct buffer_head *gdb;
 
 			ext4_debug("update backup group %#04llx\n", block);
···
 				goto out;
 		}
 
+handle_itb:
 		/* Initialize group tables of the grop @group */
 		if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED))
 			goto handle_bb;
···
 			err = PTR_ERR(bh);
 			goto out;
 		}
-		if (ext4_bg_has_super(sb, group)) {
+		overhead = ext4_group_overhead_blocks(sb, group);
+		if (overhead != 0) {
 			ext4_debug("mark backup superblock %#04llx (+0)\n",
 				   start);
-			ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb +
-						     1);
+			ext4_set_bits(bh->b_data, 0, overhead);
 		}
 		ext4_mark_bitmap_end(group_data[i].blocks_count,
 				     sb->s_blocksize * 8, bh->b_data);
···
 }
 
 /*
+ * add_new_gdb_meta_bg is the sister of add_new_gdb.
+ */
+static int add_new_gdb_meta_bg(struct super_block *sb,
+			       handle_t *handle, ext4_group_t group) {
+	ext4_fsblk_t gdblock;
+	struct buffer_head *gdb_bh;
+	struct buffer_head **o_group_desc, **n_group_desc;
+	unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
+	int err;
+
+	gdblock = ext4_meta_bg_first_block_no(sb, group) +
+		   ext4_bg_has_super(sb, group);
+	gdb_bh = sb_bread(sb, gdblock);
+	if (!gdb_bh)
+		return -EIO;
+	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
+				     sizeof(struct buffer_head *),
+				     GFP_NOFS);
+	if (!n_group_desc) {
+		err = -ENOMEM;
+		ext4_warning(sb, "not enough memory for %lu groups",
+			     gdb_num + 1);
+		return err;
+	}
+
+	o_group_desc = EXT4_SB(sb)->s_group_desc;
+	memcpy(n_group_desc, o_group_desc,
+	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+	n_group_desc[gdb_num] = gdb_bh;
+	EXT4_SB(sb)->s_group_desc = n_group_desc;
+	EXT4_SB(sb)->s_gdb_count++;
+	ext4_kvfree(o_group_desc);
+	err = ext4_journal_get_write_access(handle, gdb_bh);
+	if (unlikely(err))
+		brelse(gdb_bh);
+	return err;
+}
+
+/*
  * Called when we are adding a new group which has a backup copy of each of
  * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
  * We need to add these reserved backup GDT blocks to the resize inode, so
···
  * do not copy the full number of backups at this time.  The resize
  * which changed s_groups_count will backup again.
  */
-static void update_backups(struct super_block *sb,
-			   int blk_off, char *data, int size)
+static void update_backups(struct super_block *sb, int blk_off, char *data,
+			   int size, int meta_bg)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	const ext4_group_t last = sbi->s_groups_count;
+	ext4_group_t last;
 	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
 	unsigned three = 1;
 	unsigned five = 5;
 	unsigned seven = 7;
-	ext4_group_t group;
+	ext4_group_t group = 0;
 	int rest = sb->s_blocksize - size;
 	handle_t *handle;
 	int err = 0, err2;
···
 		goto exit_err;
 	}
 
-	ext4_superblock_csum_set(sb, (struct ext4_super_block *)data);
+	if (meta_bg == 0) {
+		group = ext4_list_backups(sb, &three, &five, &seven);
+		last = sbi->s_groups_count;
+	} else {
+		group = ext4_meta_bg_first_group(sb, group) + 1;
+		last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2);
+	}
 
-	while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
+	while (group < sbi->s_groups_count) {
 		struct buffer_head *bh;
+		ext4_fsblk_t backup_block;
 
 		/* Out of journal space, and can't get more - abort - so sad */
 		if (ext4_handle_valid(handle) &&
···
 		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
 			break;
 
-		bh = sb_getblk(sb, group * bpg + blk_off);
+		if (meta_bg == 0)
+			backup_block = group * bpg + blk_off;
+		else
+			backup_block = (ext4_group_first_block_no(sb, group) +
+					ext4_bg_has_super(sb, group));
+
+		bh = sb_getblk(sb, backup_block);
 		if (!bh) {
 			err = -EIO;
 			break;
 		}
-		ext4_debug("update metadata backup %#04lx\n",
-			  (unsigned long)bh->b_blocknr);
+		ext4_debug("update metadata backup %llu(+%llu)\n",
+			   backup_block, backup_block -
+			   ext4_group_first_block_no(sb, group));
 		if ((err = ext4_journal_get_write_access(handle, bh)))
 			break;
 		lock_buffer(bh);
···
 		if (unlikely(err))
 			ext4_std_error(sb, err);
 		brelse(bh);
+
+		if (meta_bg == 0)
+			group = ext4_list_backups(sb, &three, &five, &seven);
+		else if (group == last)
+			break;
+		else
+			group = last;
 	}
 	if ((err2 = ext4_journal_stop(handle)) && !err)
 		err = err2;
···
 	struct ext4_super_block *es = sbi->s_es;
 	struct buffer_head *gdb_bh;
 	int i, gdb_off, gdb_num, err = 0;
+	int meta_bg;
 
+	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
 	for (i = 0; i < count; i++, group++) {
 		int reserved_gdb = ext4_bg_has_super(sb, group) ?
 			le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
···
 
 			if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
 				err = reserve_backup_gdb(handle, resize_inode, group);
-		} else
+		} else if (meta_bg != 0) {
+			err = add_new_gdb_meta_bg(sb, handle, group);
+		} else {
 			err = add_new_gdb(handle, resize_inode, group);
+		}
 		if (err)
 			break;
 	}
···
 	struct buffer_head *bh = sb_getblk(sb, block);
 	if (!bh)
 		return NULL;
-
-	if (bitmap_uptodate(bh))
-		return bh;
-
-	lock_buffer(bh);
-	if (bh_submit_read(bh) < 0) {
-		unlock_buffer(bh);
-		brelse(bh);
-		return NULL;
+	if (!bh_uptodate_or_lock(bh)) {
+		if (bh_submit_read(bh) < 0) {
+			brelse(bh);
+			return NULL;
+		}
 	}
-	unlock_buffer(bh);
 
 	return bh;
 }
···
 		ext4_free_group_clusters_set(sb, gdp,
 					     EXT4_B2C(sbi, group_data->free_blocks_count));
 		ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
+		if (ext4_has_group_desc_csum(sb))
+			ext4_itable_unused_set(sb, gdp,
+					       EXT4_INODES_PER_GROUP(sb));
 		gdp->bg_flags = cpu_to_le16(*bg_flags);
 		ext4_group_desc_csum_set(sb, group, gdp);
 
···
 	}
 
 	reserved_blocks = ext4_r_blocks_count(es) * 100;
-	do_div(reserved_blocks, ext4_blocks_count(es));
+	reserved_blocks = div64_u64(reserved_blocks, ext4_blocks_count(es));
 	reserved_blocks *= blocks_count;
 	do_div(reserved_blocks, 100);
 
···
 	le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) *
 		     flex_gd->count);
 
+	ext4_debug("free blocks count %llu", ext4_free_blocks_count(es));
 	/*
 	 * We need to protect s_groups_count against other CPUs seeing
 	 * inconsistent state in the superblock.
···
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
 
+	ext4_debug("free blocks count %llu",
+		   percpu_counter_read(&sbi->s_freeclusters_counter));
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb,
 				      EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
 	    sbi->s_log_groups_per_flex) {
···
 		err = err2;
 
 	if (!err) {
-		int i;
+		int gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
+		int gdb_num_end = ((group + flex_gd->count - 1) /
+				   EXT4_DESC_PER_BLOCK(sb));
+		int meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb,
+				EXT4_FEATURE_INCOMPAT_META_BG);
+		sector_t old_gdb = 0;
+
 		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
-			       sizeof(struct ext4_super_block));
-		for (i = 0; i < flex_gd->count; i++, group++) {
+			       sizeof(struct ext4_super_block), 0);
+		for (; gdb_num <= gdb_num_end; gdb_num++) {
 			struct buffer_head *gdb_bh;
-			int gdb_num;
-			gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb);
+
 			gdb_bh = sbi->s_group_desc[gdb_num];
+			if (old_gdb == gdb_bh->b_blocknr)
+				continue;
 			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
-				       gdb_bh->b_size);
+				       gdb_bh->b_size, meta_bg);
+			old_gdb = gdb_bh->b_blocknr;
 		}
 	}
 exit:
···
 
 		group_data[i].group = group + i;
 		group_data[i].blocks_count = blocks_per_group;
-		overhead = ext4_bg_has_super(sb, group + i) ?
-			   (1 + ext4_bg_num_gdb(sb, group + i) +
-			    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+		overhead = ext4_group_overhead_blocks(sb, group + i);
 		group_data[i].free_blocks_count = blocks_per_group - overhead;
 		if (ext4_has_group_desc_csum(sb))
 			flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
···
 	if (err)
 		goto out;
 
+	err = ext4_alloc_flex_bg_array(sb, input->group + 1);
+	if (err)
+		return err;
+
+	err = ext4_mb_alloc_groupinfo(sb, input->group + 1);
+	if (err)
+		goto out;
+
 	flex_gd.count = 1;
 	flex_gd.groups = input;
 	flex_gd.bg_flags = &bg_flags;
···
 		err = err2;
 
 	if (!err) {
+		ext4_fsblk_t first_block;
+		first_block = ext4_group_first_block_no(sb, 0);
 		if (test_opt(sb, DEBUG))
 			printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
 			       "blocks\n", ext4_blocks_count(es));
-		update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
-			       sizeof(struct ext4_super_block));
+		update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr - first_block,
+			       (char *)es, sizeof(struct ext4_super_block), 0);
 	}
 	return err;
 }
···
 	return err;
 } /* ext4_group_extend */
 
+
+static int num_desc_blocks(struct super_block *sb, ext4_group_t groups)
+{
+	return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb);
+}
+
+/*
+ * Release the resize inode and drop the resize_inode feature if there
+ * are no more reserved gdt blocks, and then convert the file system
+ * to enable meta_bg
+ */
+static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
+{
+	handle_t *handle;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_fsblk_t nr;
+	int i, ret, err = 0;
+	int credits = 1;
+
+	ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg");
+	if (inode) {
+		if (es->s_reserved_gdt_blocks) {
+			ext4_error(sb, "Unexpected non-zero "
+				   "s_reserved_gdt_blocks");
+			return -EPERM;
+		}
+
+		/* Do a quick sanity check of the resize inode */
+		if (inode->i_blocks != 1 << (inode->i_blkbits - 9))
+			goto invalid_resize_inode;
+		for (i = 0; i < EXT4_N_BLOCKS; i++) {
+			if (i == EXT4_DIND_BLOCK) {
+				if (ei->i_data[i])
+					continue;
+				else
+					goto invalid_resize_inode;
+			}
+			if (ei->i_data[i])
+				goto invalid_resize_inode;
+		}
+		credits += 3;	/* block bitmap, bg descriptor, resize inode */
+	}
+
+	handle = ext4_journal_start_sb(sb, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+	if (err)
+		goto errout;
+
+	EXT4_CLEAR_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE);
+	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
+	sbi->s_es->s_first_meta_bg =
+		cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+
+	err = ext4_handle_dirty_super(handle, sb);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto errout;
+	}
+
+	if (inode) {
+		nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]);
+		ext4_free_blocks(handle, inode, NULL, nr, 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
+		ei->i_data[EXT4_DIND_BLOCK] = 0;
+		inode->i_blocks = 0;
+
+		err = ext4_mark_inode_dirty(handle, inode);
+		if (err)
+			ext4_std_error(sb, err);
+	}
+
+errout:
+	ret = ext4_journal_stop(handle);
+	if (!err)
+		err = ret;
+	return ret;
+
+invalid_resize_inode:
+	ext4_error(sb, "corrupted/inconsistent resize inode");
+	return -EINVAL;
+}
+
 /*
  * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count
  *
···
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
 	struct buffer_head *bh;
-	struct inode *resize_inode;
-	ext4_fsblk_t o_blocks_count;
-	ext4_group_t o_group;
-	ext4_group_t n_group;
-	ext4_grpblk_t offset, add;
+	struct inode *resize_inode = NULL;
+	ext4_grpblk_t add, offset;
 	unsigned long n_desc_blocks;
 	unsigned long o_desc_blocks;
-	unsigned long desc_blocks;
-	int err = 0, flexbg_size = 1;
+	ext4_group_t o_group;
+	ext4_group_t n_group;
+	ext4_fsblk_t o_blocks_count;
+	ext4_fsblk_t n_blocks_count_retry = 0;
+	unsigned long last_update_time = 0;
+	int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex;
+	int meta_bg;
 
+	/* See if the device is actually as big as what was requested */
+	bh = sb_bread(sb, n_blocks_count - 1);
+	if (!bh) {
+		ext4_warning(sb, "can't read last block, resize aborted");
+		return -ENOSPC;
+	}
+	brelse(bh);
+
+retry:
 	o_blocks_count = ext4_blocks_count(es);
 
-	if (test_opt(sb, DEBUG))
-		ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu "
-		       "to %llu blocks", o_blocks_count, n_blocks_count);
+	ext4_msg(sb, KERN_INFO, "resizing filesystem from %llu "
+		 "to %llu blocks", o_blocks_count, n_blocks_count);
 
 	if (n_blocks_count < o_blocks_count) {
 		/* On-line shrinking not supported */
···
 	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
 	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
 
-	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
-			EXT4_DESC_PER_BLOCK(sb);
-	o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
-			EXT4_DESC_PER_BLOCK(sb);
-	desc_blocks = n_desc_blocks - o_desc_blocks;
+	n_desc_blocks = num_desc_blocks(sb, n_group + 1);
+	o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count);
 
-	if (desc_blocks &&
-	    (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) ||
-	     le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) {
-		ext4_warning(sb, "No reserved GDT blocks, can't resize");
-		return -EPERM;
+	meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
+
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) {
+		if (meta_bg) {
+			ext4_error(sb, "resize_inode and meta_bg enabled "
+				   "simultaneously");
+			return -EINVAL;
+		}
+		if (n_desc_blocks > o_desc_blocks +
+		    le16_to_cpu(es->s_reserved_gdt_blocks)) {
+			n_blocks_count_retry = n_blocks_count;
+			n_desc_blocks = o_desc_blocks +
+				le16_to_cpu(es->s_reserved_gdt_blocks);
+			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
+			n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
+			n_group--; /* set to last group number */
+		}
+
+		if (!resize_inode)
+			resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
+		if (IS_ERR(resize_inode)) {
+			ext4_warning(sb, "Error opening resize inode");
+			return PTR_ERR(resize_inode);
+		}
 	}
 
-	resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
-	if (IS_ERR(resize_inode)) {
-		ext4_warning(sb, "Error opening resize inode");
-		return PTR_ERR(resize_inode);
+	if ((!resize_inode && !meta_bg) || n_blocks_count == o_blocks_count) {
+		err = ext4_convert_meta_bg(sb, resize_inode);
+		if (err)
+			goto out;
+		if (resize_inode) {
+			iput(resize_inode);
+			resize_inode = NULL;
+		}
+		if (n_blocks_count_retry) {
+			n_blocks_count = n_blocks_count_retry;
+			n_blocks_count_retry = 0;
+			goto retry;
+		}
 	}
-
-	/* See if the device is actually as big as what was requested */
-	bh = sb_bread(sb, n_blocks_count - 1);
-	if (!bh) {
-		ext4_warning(sb, "can't read last block, resize aborted");
-		return -ENOSPC;
-	}
-	brelse(bh);
 
 	/* extend the last group */
 	if (n_group == o_group)
···
 			goto out;
 	}
 
-	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
-	    es->s_log_groups_per_flex)
-		flexbg_size = 1 << es->s_log_groups_per_flex;
+	if (ext4_blocks_count(es) == n_blocks_count)
+		goto out;
 
-	o_blocks_count = ext4_blocks_count(es);
-	if (o_blocks_count == n_blocks_count)
+	err = ext4_alloc_flex_bg_array(sb, n_group + 1);
+	if (err)
+		return err;
+
+	err = ext4_mb_alloc_groupinfo(sb, n_group + 1);
+	if (err)
 		goto out;
 
 	flex_gd = alloc_flex_gd(flexbg_size);
···
 	 */
 	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
 					      flexbg_size)) {
-		ext4_alloc_group_tables(sb, flex_gd, flexbg_size);
+		if (jiffies - last_update_time > HZ * 10) {
+			if (last_update_time)
+				ext4_msg(sb, KERN_INFO,
+					 "resized to %llu blocks",
+					 ext4_blocks_count(es));
+			last_update_time = jiffies;
+		}
+		if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0)
+			break;
 		err = ext4_flex_group_add(sb, resize_inode, flex_gd);
 		if (unlikely(err))
 			break;
 	}
 
+	if (!err && n_blocks_count_retry) {
+		n_blocks_count = n_blocks_count_retry;
+		n_blocks_count_retry = 0;
+		free_flex_gd(flex_gd);
+		flex_gd = NULL;
+		goto retry;
+	}
+
 out:
 	if (flex_gd)
 		free_flex_gd(flex_gd);
-
-	iput(resize_inode);
-	if (test_opt(sb, DEBUG))
-		ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu "
-		       "upto %llu blocks", o_blocks_count, n_blocks_count);
+	if (resize_inode != NULL)
+		iput(resize_inode);
+	ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count);
 	return err;
 }

fs/ext4/super.c

···
 	 */
 	if (!es->s_error_count)
 		mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
-	es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
+	le32_add_cpu(&es->s_error_count, 1);
 }
 
 static void save_error_info(struct super_block *sb, const char *func,
···
 	flush_workqueue(sbi->dio_unwritten_wq);
 	destroy_workqueue(sbi->dio_unwritten_wq);
 
-	lock_super(sb);
 	if (sbi->s_journal) {
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
···
 	 * Now that we are completely done shutting down the
 	 * superblock, we need to actually destroy the kobject.
 	 */
-	unlock_super(sb);
 	kobject_put(&sbi->s_kobj);
 	wait_for_completion(&sbi->s_kobj_unregister);
 	if (sbi->s_chksum_driver)
···
 	ei->jinode = NULL;
 	INIT_LIST_HEAD(&ei->i_completed_io_list);
 	spin_lock_init(&ei->i_completed_io_lock);
-	ei->cur_aio_dio = NULL;
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
-	atomic_set(&ei->i_aiodio_unwritten, 0);
+	atomic_set(&ei->i_unwritten, 0);
 
 	return &ei->vfs_inode;
 }
···
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
+	Opt_max_dir_size_kb,
 };
 
 static const match_table_t tokens = {
···
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
···
 	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
 	{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
 	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
+	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_err, 0, 0}
 };
 
···
 			if (!args->from)
 				arg = EXT4_DEF_LI_WAIT_MULT;
 			sbi->s_li_wait_mult = arg;
+		} else if (token == Opt_max_dir_size_kb) {
+			sbi->s_max_dir_size_kb = arg;
 		} else if (token == Opt_stripe) {
 			sbi->s_stripe = arg;
 		} else if (m->flags & MOPT_DATAJ) {
···
 		 * Initialize args struct so we know whether arg was
 		 * found; some options take optional arguments.
 		 */
-		args[0].to = args[0].from = 0;
+		args[0].to = args[0].from = NULL;
 		token = match_token(p, tokens, args);
 		if (handle_mount_opt(sb, p, token, args, journal_devnum,
 				     journal_ioprio, is_remount) < 0)
···
 
 static const char *token2str(int token)
 {
-	static const struct match_token *t;
+	const struct match_token *t;
 
 	for (t = tokens; t->token != Opt_err; t++)
 		if (t->token == token && !strchr(t->pattern, '='))
···
 	if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
 		       (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
 		SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
+	if (nodefs || sbi->s_max_dir_size_kb)
+		SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
 
 	ext4_show_quota_options(seq, sb);
 	return 0;
···
 	return res;
 }
 
+int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct flex_groups *new_groups;
+	int size;
+
+	if (!sbi->s_log_groups_per_flex)
+		return 0;
+
+	size = ext4_flex_group(sbi, ngroup - 1) + 1;
+	if (size <= sbi->s_flex_groups_allocated)
+		return 0;
+
+	size = roundup_pow_of_two(size * sizeof(struct flex_groups));
+	new_groups = ext4_kvzalloc(size, GFP_KERNEL);
+	if (!new_groups) {
+		ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
+			 size / (int) sizeof(struct flex_groups));
+		return -ENOMEM;
+	}
+
+	if (sbi->s_flex_groups) {
+		memcpy(new_groups, sbi->s_flex_groups,
+		       (sbi->s_flex_groups_allocated *
+			sizeof(struct flex_groups)));
+		ext4_kvfree(sbi->s_flex_groups);
+	}
+	sbi->s_flex_groups = new_groups;
+	sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
+	return 0;
+}
+
 static int ext4_fill_flex_info(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = NULL;
-	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
 	unsigned int groups_per_flex = 0;
-	size_t size;
-	int i;
+	int i, err;
 
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
 	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
···
 	}
 	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
-	/* We allocate both existing and potentially added groups */
-	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
-			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
-			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
-	size = flex_group_count * sizeof(struct flex_groups);
-	sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL);
-	if (sbi->s_flex_groups == NULL) {
-		ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups",
-			 flex_group_count);
+	err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
+	if (err)
 		goto failed;
-	}
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
···
 	}
 
 	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
-		if (es->s_last_orphan)
+		/* don't clear list on RO mount w/ errors */
+		if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
 			jbd_debug(1, "Errors on filesystem, "
 				  "clearing orphan list.\n");
-		es->s_last_orphan = 0;
+			es->s_last_orphan = 0;
+		}
 		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
 		return;
 	}
···
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
 EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
 
 static struct attribute *ext4_attrs[] = {
···
 	ATTR_LIST(mb_stream_req),
 	ATTR_LIST(mb_group_prealloc),
 	ATTR_LIST(max_writeback_mb_bump),
+	ATTR_LIST(extent_max_zeroout_kb),
 	ATTR_LIST(trigger_fs_error),
 	NULL,
 };
···
 /* Features this copy of ext4 supports */
 EXT4_INFO_ATTR(lazy_itable_init);
 EXT4_INFO_ATTR(batched_discard);
+EXT4_INFO_ATTR(meta_bg_resize);
 
 static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(lazy_itable_init),
 	ATTR_LIST(batched_discard),
+	ATTR_LIST(meta_bg_resize),
 	NULL,
 };
 
···
 	 * enable delayed allocation by default
 	 * Use -o nodelalloc to turn it off
 	 */
-	if (!IS_EXT3_SB(sb) &&
+	if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) &&
 	    ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
 		set_opt(sb, DELALLOC);
 
···
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_max_writeback_mb_bump = 128;
+	sbi->s_extent_max_zeroout_kb = 32;
 
 	/*
 	 * set up enough so that it can read an inode
···
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	lock_super(sb);
 	/* Reset the needs_recovery flag before the fs is unlocked. */
 	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 	ext4_commit_super(sb, 1);
-	unlock_super(sb);
 	return 0;
 }
 
···
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 
 	/* Store the original options */
-	lock_super(sb);
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
 	old_opts.s_mount_opt2 = sbi->s_mount_opt2;
···
 	if (sbi->s_journal == NULL)
 		ext4_commit_super(sb, 1);
 
-	unlock_super(sb);
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
 	for (i = 0; i < MAXQUOTAS; i++)
···
 		else if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 					EXT4_FEATURE_RO_COMPAT_QUOTA)) {
 			err = ext4_enable_quotas(sb);
-			if (err) {
-				lock_super(sb);
+			if (err)
 				goto restore_opts;
-			}
 		}
 	}
 #endif
···
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
 #endif
-	unlock_super(sb);
 	kfree(orig_data);
 	return err;
 }
···
 	if (err)
 		goto out6;
 	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
-	if (!ext4_kset)
+	if (!ext4_kset) {
+		err = -ENOMEM;
 		goto out5;
+	}
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
 
 	err = ext4_init_feat_adverts();

fs/fs-writeback.c

···
 {
 	return test_bit(BDI_writeback_running, &bdi->state);
 }
+EXPORT_SYMBOL(writeback_in_progress);
 
 static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 {

fs/jbd2/commit.c

···
 		 * there's no point in keeping a checkpoint record for
 		 * it. */
 
-		/* A buffer which has been freed while still being
-		 * journaled by a previous transaction may end up still
-		 * being dirty here, but we want to avoid writing back
-		 * that buffer in the future after the "add to orphan"
-		 * operation been committed,  That's not only a performance
-		 * gain, it also stops aliasing problems if the buffer is
-		 * left behind for writeback and gets reallocated for another
-		 * use in a different page. */
-		if (buffer_freed(bh) && !jh->b_next_transaction) {
-			clear_buffer_freed(bh);
-			clear_buffer_jbddirty(bh);
+		/*
+		* A buffer which has been freed while still being journaled by
+		* a previous transaction.
+		*/
+		if (buffer_freed(bh)) {
+			/*
+			 * If the running transaction is the one containing
+			 * "add to orphan" operation (b_next_transaction !=
+			 * NULL), we have to wait for that transaction to
+			 * commit before we can really get rid of the buffer.
+			 * So just clear b_modified to not confuse transaction
+			 * credit accounting and refile the buffer to
+			 * BJ_Forget of the running transaction. If the just
+			 * committed transaction contains "add to orphan"
+			 * operation, we can completely invalidate the buffer
+			 * now. We are rather through in that since the
+			 * buffer may be still accessible when blocksize <
+			 * pagesize and it is attached to the last partial
+			 * page.
+			 */
+			jh->b_modified = 0;
+			if (!jh->b_next_transaction) {
+				clear_buffer_freed(bh);
+				clear_buffer_jbddirty(bh);
+				clear_buffer_mapped(bh);
+				clear_buffer_new(bh);
+				clear_buffer_req(bh);
+				bh->b_bdev = NULL;
+			}
 		}
 
 		if (buffer_jbddirty(bh)) {

fs/jbd2/journal.c

···
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	read_lock(&journal->j_state_lock);
+	/* Is it already empty? */
+	if (sb->s_start == 0) {
+		read_unlock(&journal->j_state_lock);
+		return;
+	}
 	jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
 		  journal->j_tail_sequence);
 

fs/jbd2/recovery.c

···
 	if (!err)
 		err = err2;
 	/* Make sure all replayed data is on permanent storage */
-	if (journal->j_flags & JBD2_BARRIER)
-		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+	if (journal->j_flags & JBD2_BARRIER) {
+		err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+		if (!err)
+			err = err2;
+	}
 	return err;
 }
 

fs/jbd2/transaction.c

···
  * We're outside-transaction here.  Either or both of j_running_transaction
  * and j_committing_transaction may be NULL.
  */
-static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
+static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
+				int partial_page)
 {
 	transaction_t *transaction;
 	struct journal_head *jh;
 	int may_free = 1;
-	int ret;
 
 	BUFFER_TRACE(bh, "entry");
 
+retry:
 	/*
 	 * It is safe to proceed here without the j_list_lock because the
 	 * buffers cannot be stolen by try_to_free_buffers as long as we are
···
 	 * clear the buffer dirty bit at latest at the moment when the
 	 * transaction marking the buffer as freed in the filesystem
 	 * structures is committed because from that moment on the
-	 * buffer can be reallocated and used by a different page.
+	 * block can be reallocated and used by a different page.
 	 * Since the block hasn't been freed yet but the inode has
 	 * already been added to orphan list, it is safe for us to add
 	 * the buffer to BJ_Forget list of the newest transaction.
+	 *
+	 * Also we have to clear buffer_mapped flag of a truncated buffer
+	 * because the buffer_head may be attached to the page straddling
+	 * i_size (can happen only when blocksize < pagesize) and thus the
+	 * buffer_head can be reused when the file is extended again. So we end
+	 * up keeping around invalidated buffers attached to transactions'
+	 * BJ_Forget list just to stop checkpointing code from cleaning up
+	 * the transaction this buffer was modified in.
 	 */
 	transaction = jh->b_transaction;
 	if (transaction == NULL) {
···
 			 * committed, the buffer won't be needed any
 			 * longer. */
 			JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
-			ret = __dispose_buffer(jh,
+			may_free = __dispose_buffer(jh,
 					journal->j_running_transaction);
-			jbd2_journal_put_journal_head(jh);
-			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
-			write_unlock(&journal->j_state_lock);
-			return ret;
+			goto zap_buffer;
 		} else {
 			/* There is no currently-running transaction. So the
 			 * orphan record which we wrote for this file must have
···
 			 * the committing transaction, if it exists. */
 			if (journal->j_committing_transaction) {
 				JBUFFER_TRACE(jh, "give to committing trans");
-				ret = __dispose_buffer(jh,
+				may_free = __dispose_buffer(jh,
 					journal->j_committing_transaction);
-				jbd2_journal_put_journal_head(jh);
-				spin_unlock(&journal->j_list_lock);
-				jbd_unlock_bh_state(bh);
-				write_unlock(&journal->j_state_lock);
-				return ret;
+				goto zap_buffer;
 			} else {
 				/* The orphan record's transaction has
 				 * committed.  We can cleanse this buffer */
···
 		JBUFFER_TRACE(jh, "on committing transaction");
 		/*
 		 * The buffer is committing, we simply cannot touch
-		 * it. So we just set j_next_transaction to the
-		 * running transaction (if there is one) and mark
-		 * buffer as freed so that commit code knows it should
-		 * clear dirty bits when it is done with the buffer.
+		 * it. If the page is straddling i_size we have to wait
+		 * for commit and try again.
+		 */
+		if (partial_page) {
+			tid_t tid = journal->j_committing_transaction->t_tid;
+
+			jbd2_journal_put_journal_head(jh);
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			write_unlock(&journal->j_state_lock);
+			jbd2_log_wait_commit(journal, tid);
+			goto retry;
+		}
+		/*
+		 * OK, buffer won't be reachable after truncate. We just set
+		 * j_next_transaction to the running transaction (if there is
+		 * one) and mark buffer as freed so that commit code knows it
+		 * should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
···
 	}
 
 zap_buffer:
+	/*
+	 * This is tricky. Although the buffer is truncated, it may be reused
+	 * if blocksize < pagesize and it is attached to the page straddling
+	 * EOF. Since the buffer might have been added to BJ_Forget list of the
+	 * running transaction, journal_get_write_access() won't clear
+	 * b_modified and credit accounting gets confused. So clear b_modified
+	 * here.
+	 */
+	jh->b_modified = 0;
 	jbd2_journal_put_journal_head(jh);
 zap_buffer_no_jh:
 	spin_unlock(&journal->j_list_lock);
···
 		if (offset <= curr_off) {
 			/* This block is wholly outside the truncation point */
 			lock_buffer(bh);
-			may_free &= journal_unmap_buffer(journal, bh);
+			may_free &= journal_unmap_buffer(journal, bh,
+							 offset > 0);
 			unlock_buffer(bh);
 		}
 		curr_off = next_off;

fs/nilfs2/file.c

···
 	if (unlikely(ret))
 		goto out;
 
+	file_update_time(vma->vm_file);
 	ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
 	if (ret) {
 		nilfs_transaction_abort(inode->i_sb);

include/linux/falloc.h

···
 
 #define FALLOC_FL_KEEP_SIZE	0x01 /* default is extend size */
 #define FALLOC_FL_PUNCH_HOLE	0x02 /* de-allocates range */
+#define FALLOC_FL_NO_HIDE_STALE	0x04 /* reserved codepoint */
 
 #ifdef __KERNEL__
 

include/trace/events/ext4.h

···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16, mode			)
 		__field(	uid_t,	uid			)
 		__field(	gid_t,	gid			)
 		__field(	__u64, blocks			)
+		__field(	__u16, mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->mode	= inode->i_mode;
 		__entry->uid	= i_uid_read(inode);
 		__entry->gid	= i_gid_read(inode);
 		__entry->blocks	= inode->i_blocks;
+		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu",
···
 		__field(	long,	pages_skipped		)
 		__field(	loff_t,	range_start		)
 		__field(	loff_t,	range_end		)
+		__field(       pgoff_t,	writeback_index		)
 		__field(	int,	sync_mode		)
 		__field(	char,	for_kupdate		)
 		__field(	char,	range_cyclic		)
-		__field(       pgoff_t,	writeback_index		)
 	),
 
 	TP_fast_assign(
···
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
 		__entry->sync_mode	= wbc->sync_mode;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->range_cyclic	= wbc->range_cyclic;
-		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
 	TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld "
-		  "range_start %lld range_end %lld sync_mode %d"
+		  "range_start %lld range_end %lld sync_mode %d "
 		  "for_kupdate %d range_cyclic %d writeback_index %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->nr_to_write,
···
 		__field(	int,	ret			)
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
-		__field(	int,	sync_mode		)
 		__field(       pgoff_t,	writeback_index		)
+		__field(	int,	sync_mode		)
 	),
 
 	TP_fast_assign(
···
 		__entry->ret		= ret;
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
-		__entry->sync_mode	= wbc->sync_mode;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
+		__entry->sync_mode	= wbc->sync_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld "
···
 	TP_ARGS(page),
 
 	TP_STRUCT__entry(
-		__field(	pgoff_t, index			)
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	pgoff_t, index			)
 
 	),
 
 	TP_fast_assign(
-		__entry->index	= page->index;
-		__entry->ino	= page->mapping->host->i_ino;
 		__entry->dev	= page->mapping->host->i_sb->s_dev;
+		__entry->ino	= page->mapping->host->i_ino;
+		__entry->index	= page->index;
 	),
 
 	TP_printk("dev %d,%d ino %lu page_index %lu",
···
 	TP_ARGS(page, offset),
 
 	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	pgoff_t, index			)
 		__field(	unsigned long, offset		)
-		__field(	ino_t,	ino			)
-		__field(	dev_t,	dev			)
 
 	),
 
 	TP_fast_assign(
+		__entry->dev	= page->mapping->host->i_sb->s_dev;
+		__entry->ino	= page->mapping->host->i_ino;
 		__entry->index	= page->index;
 		__entry->offset	= offset;
-		__entry->ino	= page->mapping->host->i_ino;
-		__entry->dev	= page->mapping->host->i_sb->s_dev;
 	),
 
 	TP_printk("dev %d,%d ino %lu page_index %lu offset %lu",
···
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 		__field(	__u64,	pa_pstart		)
-		__field(	__u32,	pa_len			)
 		__field(	__u64,	pa_lstart		)
+		__field(	__u32,	pa_len			)
 
 	),
 
···
 		__entry->dev		= ac->ac_sb->s_dev;
 		__entry->ino		= ac->ac_inode->i_ino;
 		__entry->pa_pstart	= pa->pa_pstart;
-		__entry->pa_len		= pa->pa_len;
 		__entry->pa_lstart	= pa->pa_lstart;
+		__entry->pa_len		= pa->pa_len;
 	),
 
 	TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu",
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	unsigned int, flags		)
 		__field(	unsigned int, len		)
 		__field(	__u32,  logical			)
 		__field(	__u32,	lleft			)
···
 		__field(	__u64,	goal			)
 		__field(	__u64,	pleft			)
 		__field(	__u64,	pright			)
+		__field(	unsigned int, flags		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= ar->inode->i_sb->s_dev;
 		__entry->ino	= ar->inode->i_ino;
-		__entry->flags	= ar->flags;
 		__entry->len	= ar->len;
 		__entry->logical = ar->logical;
 		__entry->goal	= ar->goal;
···
 		__entry->lright	= ar->lright;
 		__entry->pleft	= ar->pleft;
 		__entry->pright	= ar->pright;
+		__entry->flags	= ar->flags;
 	),
 
 	TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu "
···
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 		__field(	__u64,	block			)
-		__field(	unsigned int, flags		)
 		__field(	unsigned int, len		)
 		__field(	__u32,  logical			)
 		__field(	__u32,	lleft			)
···
 		__field(	__u64,	goal			)
 		__field(	__u64,	pleft			)
 		__field(	__u64,	pright			)
+		__field(	unsigned int, flags		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= ar->inode->i_sb->s_dev;
 		__entry->ino	= ar->inode->i_ino;
 		__entry->block	= block;
-		__entry->flags	= ar->flags;
 		__entry->len	= ar->len;
 		__entry->logical = ar->logical;
 		__entry->goal	= ar->goal;
···
 		__entry->lright	= ar->lright;
 		__entry->pleft	= ar->pleft;
 		__entry->pright	= ar->pright;
+		__entry->flags	= ar->flags;
 	),
 
 	TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u "
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,	mode			)
 		__field(	__u64,	block			)
 		__field(	unsigned long,	count		)
 		__field(	int,	flags			)
+		__field(	__u16,	mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
-		__entry->mode		= inode->i_mode;
 		__entry->block		= block;
 		__entry->count		= count;
 		__entry->flags		= flags;
+		__entry->mode		= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d",
···
 	TP_ARGS(inode, ret),
 
 	TP_STRUCT__entry(
-		__field(	int,	ret			)
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	int,	ret			)
 	),
 
 	TP_fast_assign(
-		__entry->ret		= ret;
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->ret		= ret;
 	),
 
 	TP_printk("dev %d,%d ino %lu ret %d",
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,	found			)
-		__field(	__u16,	groups			)
-		__field(	__u16,	buddy			)
-		__field(	__u16,	flags			)
-		__field(	__u16,	tail			)
-		__field(	__u8,	cr			)
 		__field(	__u32, 	orig_logical		)
 		__field(	  int,	orig_start		)
 		__field(	__u32, 	orig_group		)
···
 		__field(	  int,	result_start		)
 		__field(	__u32, 	result_group		)
 		__field(	  int,	result_len		)
+		__field(	__u16,	found			)
+		__field(	__u16,	groups			)
+		__field(	__u16,	buddy			)
+		__field(	__u16,	flags			)
+		__field(	__u16,	tail			)
+		__field(	__u8,	cr			)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= ac->ac_inode->i_sb->s_dev;
 		__entry->ino		= ac->ac_inode->i_ino;
-		__entry->found		= ac->ac_found;
-		__entry->flags		= ac->ac_flags;
-		__entry->groups		= ac->ac_groups_scanned;
-		__entry->buddy		= ac->ac_buddy;
-		__entry->tail		= ac->ac_tail;
-		__entry->cr		= ac->ac_criteria;
 		__entry->orig_logical	= ac->ac_o_ex.fe_logical;
 		__entry->orig_start	= ac->ac_o_ex.fe_start;
 		__entry->orig_group	= ac->ac_o_ex.fe_group;
···
 		__entry->result_start	= ac->ac_f_ex.fe_start;
 		__entry->result_group	= ac->ac_f_ex.fe_group;
 		__entry->result_len	= ac->ac_f_ex.fe_len;
+		__entry->found		= ac->ac_found;
+		__entry->flags		= ac->ac_flags;
+		__entry->groups		= ac->ac_groups_scanned;
+		__entry->buddy		= ac->ac_buddy;
+		__entry->tail		= ac->ac_tail;
+		__entry->cr		= ac->ac_criteria;
 	),
 
 	TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u "
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,	mode			)
-		__field(	int,	is_metadata		)
 		__field(	__u64,	block			)
+		__field(	int,	is_metadata		)
+		__field(	__u16,	mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->mode	= inode->i_mode;
-		__entry->is_metadata = is_metadata;
 		__entry->block	= block;
+		__entry->is_metadata = is_metadata;
+		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu",
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,	mode			)
 		__field(	__u64,	i_blocks		)
 		__field(	int,	used_blocks		)
 		__field(	int,	reserved_data_blocks	)
 		__field(	int,	reserved_meta_blocks	)
 		__field(	int,	allocated_meta_blocks	)
 		__field(	int,	quota_claim		)
+		__field(	__u16,	mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->mode	= inode->i_mode;
 		__entry->i_blocks = inode->i_blocks;
 		__entry->used_blocks = used_blocks;
 		__entry->reserved_data_blocks =
···
 		__entry->allocated_meta_blocks =
 				EXT4_I(inode)->i_allocated_meta_blocks;
 		__entry->quota_claim = quota_claim;
+		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d "
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,  mode			)
 		__field(	__u64,	i_blocks		)
 		__field(	int,	md_needed		)
 		__field(	int,	reserved_data_blocks	)
 		__field(	int,	reserved_meta_blocks	)
+		__field(	__u16,  mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->mode	= inode->i_mode;
 		__entry->i_blocks = inode->i_blocks;
 		__entry->md_needed = md_needed;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d "
···
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	__u16,  mode			)
 		__field(	__u64,	i_blocks		)
 		__field(	int,	freed_blocks		)
 		__field(	int,	reserved_data_blocks	)
 		__field(	int,	reserved_meta_blocks	)
 		__field(	int,	allocated_meta_blocks	)
+		__field(	__u16,  mode			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->mode	= inode->i_mode;
 		__entry->i_blocks = inode->i_blocks;
 		__entry->freed_blocks = freed_blocks;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
 		__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
+		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d "
···
 	TP_ARGS(inode, offset, len, rw),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned long,	len		)
 		__field(	int,	rw			)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->pos	= offset;
 		__entry->len	= len;
 		__entry->rw	= rw;
···
 	TP_ARGS(inode, offset, len, rw, ret),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned long,	len		)
 		__field(	int,	rw			)
···
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->pos	= offset;
 		__entry->len	= len;
 		__entry->rw	= rw;
···
 	TP_ARGS(inode, offset, len, mode),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	loff_t,	len			)
 		__field(	int,	mode			)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->pos	= offset;
 		__entry->len	= len;
 		__entry->mode	= mode;
···
 	TP_ARGS(inode, offset, max_blocks, ret),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned int,	blocks		)
 		__field(	int, 	ret			)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->pos	= offset;
 		__entry->blocks	= max_blocks;
 		__entry->ret	= ret;
···
 	TP_ARGS(parent, dentry),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	parent			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	size			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	ino_t,	parent			)
+		__field(	loff_t,	size			)
 	),
 
 	TP_fast_assign(
-		__entry->parent		= parent->i_ino;
-		__entry->ino		= dentry->d_inode->i_ino;
-		__entry->size		= dentry->d_inode->i_size;
 		__entry->dev		= dentry->d_inode->i_sb->s_dev;
+		__entry->ino		= dentry->d_inode->i_ino;
+		__entry->parent		= parent->i_ino;
+		__entry->size		= dentry->d_inode->i_size;
 	),
 
 	TP_printk("dev %d,%d ino %lu size %lld parent %lu",
···
 	TP_ARGS(dentry, ret),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino			)
 		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
 		__field(	int,	ret			)
 	),
 
 	TP_fast_assign(
-		__entry->ino		= dentry->d_inode->i_ino;
 		__entry->dev		= dentry->d_inode->i_sb->s_dev;
+		__entry->ino		= dentry->d_inode->i_ino;
 		__entry->ret		= ret;
 	),
 
···
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,  	ino		)
-		__field(	dev_t,  	dev		)
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
 		__field(	__u64,		blocks		)
 	),
 
 	TP_fast_assign(
-		__entry->ino    = inode->i_ino;
 		__entry->dev    = inode->i_sb->s_dev;
+		__entry->ino    = inode->i_ino;
 		__entry->blocks	= inode->i_blocks;
 	),
 
···
 	TP_ARGS(inode, map, ux),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	m_lblk	)
 		__field(	unsigned,	m_len	)
 		__field(	ext4_lblk_t,	u_lblk	)
···
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
 		__entry->m_lblk		= map->m_lblk;
 		__entry->m_len		= map->m_len;
 		__entry->u_lblk		= le32_to_cpu(ux->ee_block);
···
 	TP_ARGS(inode, map, ux, ix),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	m_lblk	)
 		__field(	unsigned,	m_len	)
 		__field(	ext4_lblk_t,	u_lblk	)
···
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
 		__entry->m_lblk		= map->m_lblk;
 		__entry->m_len		= map->m_len;
 		__entry->u_lblk		= le32_to_cpu(ux->ee_block);
···
 	TP_ARGS(inode, lblk, len, flags),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,  	ino		)
-		__field(	dev_t,  	dev		)
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
 		__field(	ext4_lblk_t,	lblk		)
 		__field(	unsigned int,	len		)
 		__field(	unsigned int,	flags		)
 	),
 
 	TP_fast_assign(
-		__entry->ino    = inode->i_ino;
 		__entry->dev    = inode->i_sb->s_dev;
+		__entry->ino    = inode->i_ino;
 		__entry->lblk	= lblk;
 		__entry->len	= len;
 		__entry->flags	= flags;
···
 	TP_ARGS(inode, lblk, pblk, len, ret),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino		)
 		__field(	dev_t,		dev		)
-		__field(	ext4_lblk_t,	lblk		)
+		__field(	ino_t,		ino		)
 		__field(	ext4_fsblk_t,	pblk		)
+		__field(	ext4_lblk_t,	lblk		)
 		__field(	unsigned int,	len		)
 		__field(	int,		ret		)
 	),
 
 	TP_fast_assign(
-		__entry->ino    = inode->i_ino;
 		__entry->dev    = inode->i_sb->s_dev;
-		__entry->lblk	= lblk;
+		__entry->ino    = inode->i_ino;
 		__entry->pblk	= pblk;
+		__entry->lblk	= lblk;
 		__entry->len	= len;
 		__entry->ret	= ret;
 	),
···
 	TP_ARGS(inode, lblk, pblk),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino		)
 		__field(	dev_t,		dev		)
-		__field(	ext4_lblk_t,	lblk		)
+		__field(	ino_t,		ino		)
 		__field(	ext4_fsblk_t,	pblk		)
+		__field(	ext4_lblk_t,	lblk		)
 	),
 
 	TP_fast_assign(
-		__entry->ino    = inode->i_ino;
 		__entry->dev    = inode->i_sb->s_dev;
-		__entry->lblk	= lblk;
+		__entry->ino    = inode->i_ino;
 		__entry->pblk	= pblk;
+		__entry->lblk	= lblk;
 	),
 
 	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu",
···
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,	ino		)
 		__field(	dev_t,	dev		)
+		__field(	ino_t,	ino		)
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
 	),
 
 	TP_printk("dev %d,%d ino %ld",
···
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
-		__field(	  int, 	nblocks			)
 		__field(unsigned long,	ip			)
+		__field(	int,	nblocks			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	 = sb->s_dev;
-		__entry->nblocks = nblocks;
 		__entry->ip	 = IP;
+		__entry->nblocks = nblocks;
 	),
 
 	TP_printk("dev %d,%d nblocks %d caller %pF",
···
 	TP_ARGS(inode, map, allocated, newblock),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino		)
 		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	int,		flags		)
 		__field(	ext4_lblk_t,	lblk		)
 		__field(	ext4_fsblk_t,	pblk		)
 		__field(	unsigned int,	len		)
-		__field(	int,		flags		)
 		__field(	unsigned int,	allocated	)
 		__field(	ext4_fsblk_t,	newblk		)
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->flags		= map->m_flags;
 		__entry->lblk		= map->m_lblk;
 		__entry->pblk		= map->m_pblk;
 		__entry->len		= map->m_len;
-		__entry->flags		= map->m_flags;
 		__entry->allocated	= allocated;
 		__entry->newblk		= newblock;
 	),
···
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev	)
+		__field(	unsigned int,	flags	)
 		__field(	ext4_lblk_t,	lblk	)
 		__field(	ext4_fsblk_t,	pblk	)
 		__field(	unsigned int,	len	)
-		__field(	unsigned int,	flags	)
 		__field(	int,		ret	)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= sb->s_dev;
+		__entry->flags	= map->m_flags;
 		__entry->lblk	= map->m_lblk;
 		__entry->pblk	= map->m_pblk;
 		__entry->len	= map->m_len;
-		__entry->flags	= map->m_flags;
 		__entry->ret	= ret;
 	),
 
···
 	TP_ARGS(inode, lblk, len, start),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	lblk	)
 		__field(	unsigned int,	len	)
 		__field(	ext4_fsblk_t,	start	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->lblk	= lblk;
 		__entry->len	= len;
 		__entry->start	= start;
···
 	TP_ARGS(inode, lblk, ret),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	lblk	)
 		__field(	int,		ret	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->lblk	= lblk;
 		__entry->ret	= ret;
 	),
···
 	TP_ARGS(inode, from, to, reverse, found, found_blk),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino		)
 		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
 		__field(	ext4_lblk_t,	from		)
 		__field(	ext4_lblk_t,	to		)
 		__field(	int,		reverse		)
···
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
 		__entry->from		= from;
 		__entry->to		= to;
 		__entry->reverse	= reverse;
···
 	TP_ARGS(inode, lblk, len),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	lblk	)
 		__field(	unsigned int,	len	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->lblk	= lblk;
 		__entry->len	= len;
 	),
···
 	TP_ARGS(inode, lblk, pblk, len),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
-		__field(	ext4_lblk_t,	lblk	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_fsblk_t,	pblk	)
+		__field(	ext4_lblk_t,	lblk	)
 		__field(	unsigned short,	len	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
-		__entry->lblk	= lblk;
+		__entry->ino	= inode->i_ino;
 		__entry->pblk	= pblk;
+		__entry->lblk	= lblk;
 		__entry->len	= len;
 	),
 
···
 	TP_ARGS(inode, ex, from, to, partial_cluster),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
-		__field(	ext4_lblk_t,	ee_lblk	)
-		__field(	ext4_fsblk_t,	ee_pblk	)
-		__field(	unsigned short,	ee_len	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	from	)
 		__field(	ext4_lblk_t,	to	)
 		__field(	ext4_fsblk_t,	partial	)
+		__field(	ext4_fsblk_t,	ee_pblk	)
+		__field(	ext4_lblk_t,	ee_lblk	)
+		__field(	unsigned short,	ee_len	)
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
-		__entry->ee_lblk	= cpu_to_le32(ex->ee_block);
-		__entry->ee_pblk	= ext4_ext_pblock(ex);
-		__entry->ee_len		= ext4_ext_get_actual_len(ex);
+		__entry->ino		= inode->i_ino;
 		__entry->from		= from;
 		__entry->to		= to;
 		__entry->partial	= partial_cluster;
+		__entry->ee_pblk	= ext4_ext_pblock(ex);
+		__entry->ee_lblk	= cpu_to_le32(ex->ee_block);
+		__entry->ee_len		= ext4_ext_get_actual_len(ex);
 	),
 
 	TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]"
···
 	TP_ARGS(inode, start, ex, partial_cluster),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
+		__field(	ext4_fsblk_t,	partial	)
 		__field(	ext4_lblk_t,	start	)
 		__field(	ext4_lblk_t,	ee_lblk	)
 		__field(	ext4_fsblk_t,	ee_pblk	)
 		__field(	short,		ee_len	)
-		__field(	ext4_fsblk_t,	partial	)
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->partial	= partial_cluster;
 		__entry->start		= start;
 		__entry->ee_lblk	= le32_to_cpu(ex->ee_block);
 		__entry->ee_pblk	= ext4_ext_pblock(ex);
 		__entry->ee_len		= ext4_ext_get_actual_len(ex);
-		__entry->partial	= partial_cluster;
 	),
 
 	TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]"
···
 	TP_ARGS(inode, pblk),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_fsblk_t,	pblk	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->pblk	= pblk;
 	),
 
···
 	TP_ARGS(inode, start, depth),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino	)
 		__field(	dev_t,		dev	)
+		__field(	ino_t,		ino	)
 		__field(	ext4_lblk_t,	start	)
 		__field(	int,		depth	)
 	),
 
 	TP_fast_assign(
-		__entry->ino	= inode->i_ino;
 		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
 		__entry->start	= start;
 		__entry->depth	= depth;
 	),
···
 	TP_ARGS(inode, start, depth, partial, eh_entries),
 
 	TP_STRUCT__entry(
-		__field(	ino_t,		ino		)
 		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
 		__field(	ext4_lblk_t,	start		)
 		__field(	int,		depth		)
 		__field(	ext4_lblk_t,	partial		)
···
 	),
 
 	TP_fast_assign(
-		__entry->ino		= inode->i_ino;
 		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
 		__entry->start		= start;
 		__entry->depth		= depth;
 		__entry->partial	= partial;