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

Pull ext4 updates from Ted Ts'o:
 "A large number of cleanups and bug fixes, with some (minor) journal
  optimizations"

[ This got sent to me before -rc1, but was stuck in my spam folder.   - Linus ]

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (67 commits)
  ext4: check s_chksum_driver when looking for bg csum presence
  ext4: move error report out of atomic context in ext4_init_block_bitmap()
  ext4: Replace open coded mdata csum feature to helper function
  ext4: delete useless comments about ext4_move_extents
  ext4: fix reservation overflow in ext4_da_write_begin
  ext4: add ext4_iget_normal() which is to be used for dir tree lookups
  ext4: don't orphan or truncate the boot loader inode
  ext4: grab missed write_count for EXT4_IOC_SWAP_BOOT
  ext4: optimize block allocation on grow indepth
  ext4: get rid of code duplication
  ext4: fix over-defensive complaint after journal abort
  ext4: fix return value of ext4_do_update_inode
  ext4: fix mmap data corruption when blocksize < pagesize
  vfs: fix data corruption when blocksize < pagesize for mmaped data
  ext4: fold ext4_nojournal_sops into ext4_sops
  ext4: support freezing ext2 (nojournal) file systems
  ext4: fold ext4_sync_fs_nojournal() into ext4_sync_fs()
  ext4: don't check quota format when there are no quota files
  jbd2: simplify calling convention around __jbd2_journal_clean_checkpoint_list
  jbd2: avoid pointless scanning of checkpoint lists
  ...

fs/buffer.c

@@ -993,7 +993,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
  */
 static int
 grow_dev_page(struct block_device *bdev, sector_t block,
-		pgoff_t index, int size, int sizebits)
+	      pgoff_t index, int size, int sizebits, gfp_t gfp)
 {
 	struct inode *inode = bdev->bd_inode;
 	struct page *page;
@@ -1002,8 +1002,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	int ret = 0;		/* Will call free_more_memory() */
 	gfp_t gfp_mask;
 
-	gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
-	gfp_mask |= __GFP_MOVABLE;
+	gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
+
 	/*
 	 * XXX: __getblk_slow() can not really deal with failure and
 	 * will endlessly loop on improvised global reclaim.  Prefer
@@ -1060,7 +1060,7 @@ failed:
  * that page was dirty, the buffers are set dirty also.
  */
 static int
-grow_buffers(struct block_device *bdev, sector_t block, int size)
+grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
 {
 	pgoff_t index;
 	int sizebits;
@@ -1087,11 +1087,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
 	}
 
 	/* Create a page with the proper size buffers.. */
-	return grow_dev_page(bdev, block, index, size, sizebits);
+	return grow_dev_page(bdev, block, index, size, sizebits, gfp);
 }
 
-static struct buffer_head *
-__getblk_slow(struct block_device *bdev, sector_t block, int size)
+struct buffer_head *
+__getblk_slow(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
 {
 	/* Size must be multiple of hard sectorsize */
 	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
@@ -1113,13 +1114,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
 		if (bh)
 			return bh;
 
-		ret = grow_buffers(bdev, block, size);
+		ret = grow_buffers(bdev, block, size, gfp);
 		if (ret < 0)
 			return NULL;
 		if (ret == 0)
 			free_more_memory();
 	}
 }
+EXPORT_SYMBOL(__getblk_slow);
 
 /*
  * The relationship between dirty buffers and dirty pages:
@@ -1373,24 +1375,25 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__find_get_block);
 
 /*
- * __getblk will locate (and, if necessary, create) the buffer_head
+ * __getblk_gfp() will locate (and, if necessary, create) the buffer_head
  * which corresponds to the passed block_device, block and size. The
  * returned buffer has its reference count incremented.
  *
- * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
- * attempt is failing.  FIXME, perhaps?
+ * __getblk_gfp() will lock up the machine if grow_dev_page's
+ * try_to_free_buffers() attempt is failing.  FIXME, perhaps?
  */
 struct buffer_head *
-__getblk(struct block_device *bdev, sector_t block, unsigned size)
+__getblk_gfp(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
 {
 	struct buffer_head *bh = __find_get_block(bdev, block, size);
 
 	might_sleep();
 	if (bh == NULL)
-		bh = __getblk_slow(bdev, block, size);
+		bh = __getblk_slow(bdev, block, size, gfp);
 	return bh;
 }
-EXPORT_SYMBOL(__getblk);
+EXPORT_SYMBOL(__getblk_gfp);
 
 /*
  * Do async read-ahead on a buffer..
@@ -1406,24 +1409,28 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__breadahead);
 
 /**
- *  __bread() - reads a specified block and returns the bh
+ *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
  *  @block: number of block
  *  @size: size (in bytes) to read
- * 
+ *  @gfp: page allocation flag
+ *
  *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache can be allocated from non-movable area
+ *  not to prevent page migration if you set gfp to zero.
  *  It returns NULL if the block was unreadable.
  */
 struct buffer_head *
-__bread(struct block_device *bdev, sector_t block, unsigned size)
+__bread_gfp(struct block_device *bdev, sector_t block,
+		   unsigned size, gfp_t gfp)
 {
-	struct buffer_head *bh = __getblk(bdev, block, size);
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
 
 	if (likely(bh) && !buffer_uptodate(bh))
 		bh = __bread_slow(bh);
 	return bh;
 }
-EXPORT_SYMBOL(__bread);
+EXPORT_SYMBOL(__bread_gfp);
 
 /*
  * invalidate_bh_lrus() is called rarely - but not only at unmount.
@@ -2082,6 +2089,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
 	int i_size_changed = 0;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2101,6 +2109,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
 	 * makes the holding time of page lock longer. Second, it forces lock

fs/ext4/balloc.c

@@ -176,7 +176,7 @@ static unsigned int num_clusters_in_group(struct super_block *sb,
 }
 
 /* Initializes an uninitialized block bitmap */
-static void ext4_init_block_bitmap(struct super_block *sb,
+static int ext4_init_block_bitmap(struct super_block *sb,
 				   struct buffer_head *bh,
 				   ext4_group_t block_group,
 				   struct ext4_group_desc *gdp)
@@ -192,7 +192,6 @@ static void ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -205,7 +204,7 @@ static void ext4_init_block_bitmap(struct super_block *sb,
 					   count);
 		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
-		return;
+		return -EIO;
 	}
 	memset(bh->b_data, 0, sb->s_blocksize);
 
@@ -243,6 +242,7 @@ static void ext4_init_block_bitmap(struct super_block *sb,
 			     sb->s_blocksize * 8, bh->b_data);
 	ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
+	return 0;
 }
 
 /* Return the number of free blocks in a block group.  It is used when
@@ -438,11 +438,15 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-		ext4_init_block_bitmap(sb, bh, block_group, desc);
+		int err;
+
+		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
+		if (err)
+			ext4_error(sb, "Checksum bad for grp %u", block_group);
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
@@ -636,8 +640,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	 * Account for the allocated meta blocks.  We will never
 	 * fail EDQUOT for metdata, but we do account for it.
 	 */
-	if (!(*errp) &&
-	    ext4_test_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED)) {
+	if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
 		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 		dquot_alloc_block_nofail(inode,

fs/ext4/bitmap.c

@@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	__u32 provided, calculated;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
@@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
@@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo);
@@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);

fs/ext4/dir.c

@@ -151,13 +151,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					&file->f_ra, file,
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
-			bh = ext4_bread(NULL, inode, map.m_lblk, 0, &err);
+			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
+			if (IS_ERR(bh))
+				return PTR_ERR(bh);
 		}
 
-		/*
-		 * We ignore I/O errors on directories so users have a chance
-		 * of recovering data when there's a bad sector
-		 */
 		if (!bh) {
 			if (!dir_has_error) {
 				EXT4_ERROR_FILE(file, 0,

fs/ext4/ext4.h

@@ -572,15 +572,15 @@ enum {
 
 /*
  * The bit position of these flags must not overlap with any of the
- * EXT4_GET_BLOCKS_*.  They are used by ext4_ext_find_extent(),
+ * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
  * read_extent_tree_block(), ext4_split_extent_at(),
  * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
  * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
  * caching the extents when reading from the extent tree while a
  * truncate or punch hole operation is in progress.
  */
-#define EXT4_EX_NOCACHE				0x0400
-#define EXT4_EX_FORCE_CACHE			0x0800
+#define EXT4_EX_NOCACHE				0x40000000
+#define EXT4_EX_FORCE_CACHE			0x20000000
 
 /*
  * Flags used by ext4_free_blocks
@@ -890,6 +890,7 @@ struct ext4_inode_info {
 	struct ext4_es_tree i_es_tree;
 	rwlock_t i_es_lock;
 	struct list_head i_es_lru;
+	unsigned int i_es_all_nr;	/* protected by i_es_lock */
 	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
 	unsigned long i_touch_when;	/* jiffies of last accessing */
 
@@ -1174,6 +1175,9 @@ struct ext4_super_block {
 #define EXT4_MF_MNTDIR_SAMPLED	0x0001
 #define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
 
+/* Number of quota types we support */
+#define EXT4_MAXQUOTAS 2
+
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1237,7 +1241,7 @@ struct ext4_sb_info {
 	u32 s_min_batch_time;
 	struct block_device *journal_bdev;
 #ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	char *s_qf_names[EXT4_MAXQUOTAS];	/* Names of quota files with journalled quota */
 	int s_jquota_fmt;			/* Format of quota to use */
 #endif
 	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
@@ -1330,8 +1334,7 @@ struct ext4_sb_info {
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
 	struct list_head s_es_lru;
-	unsigned long s_es_last_sorted;
-	struct percpu_counter s_extent_cache_cnt;
+	struct ext4_es_stats s_es_stats;
 	struct mb_cache *s_mb_cache;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 
@@ -1399,7 +1402,6 @@ enum {
 	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
 	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 */
 	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
@@ -2086,10 +2088,8 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 
 /* inode.c */
-struct buffer_head *ext4_getblk(handle_t *, struct inode *,
-						ext4_lblk_t, int, int *);
-struct buffer_head *ext4_bread(handle_t *, struct inode *,
-						ext4_lblk_t, int, int *);
+struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
+struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
 int ext4_get_block_write(struct inode *inode, sector_t iblock,
 			 struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
@@ -2109,6 +2109,7 @@ int do_journal_get_write_access(handle_t *handle,
 #define CONVERT_INLINE_DATA	 2
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
+extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -2332,10 +2333,18 @@ extern int ext4_register_li_request(struct super_block *sb,
 static inline int ext4_has_group_desc_csum(struct super_block *sb)
 {
 	return EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
-					  EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
+					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM) ||
+	       (EXT4_SB(sb)->s_chksum_driver != NULL);
 }
 
+static inline int ext4_has_metadata_csum(struct super_block *sb)
+{
+	WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+		     !EXT4_SB(sb)->s_chksum_driver);
+
+	return (EXT4_SB(sb)->s_chksum_driver != NULL);
+}
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
 	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
@@ -2731,21 +2740,26 @@ extern int ext4_can_extents_be_merged(struct inode *inode,
 				      struct ext4_extent *ex1,
 				      struct ext4_extent *ex2);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *,
-				  struct ext4_ext_path *,
+				  struct ext4_ext_path **,
 				  struct ext4_extent *, int);
-extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
-						  struct ext4_ext_path *,
-						  int flags);
+extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
+					      struct ext4_ext_path **,
+					      int flags);
 extern void ext4_ext_drop_refs(struct ext4_ext_path *);
 extern int ext4_ext_check_inode(struct inode *inode);
 extern int ext4_find_delalloc_range(struct inode *inode,
 				    ext4_lblk_t lblk_start,
 				    ext4_lblk_t lblk_end);
 extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
+extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
 extern int ext4_ext_precache(struct inode *inode);
 extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
+extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
+				struct inode *inode2, ext4_lblk_t lblk1,
+			     ext4_lblk_t lblk2,  ext4_lblk_t count,
+			     int mark_unwritten,int *err);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,
@@ -2755,8 +2769,6 @@ extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
-extern int mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
-			    struct ext4_extent **extent);
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);

fs/ext4/ext4_extents.h

@@ -123,6 +123,7 @@ find_ext4_extent_tail(struct ext4_extent_header *eh)
 struct ext4_ext_path {
 	ext4_fsblk_t			p_block;
 	__u16				p_depth;
+	__u16				p_maxdepth;
 	struct ext4_extent		*p_ext;
 	struct ext4_extent_idx		*p_idx;
 	struct ext4_extent_header	*p_hdr;

fs/ext4/ext4_jbd2.c

@@ -256,8 +256,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 	set_buffer_prio(bh);
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_dirty_metadata(handle, bh);
-		/* Errors can only happen if there is a bug */
-		if (WARN_ON_ONCE(err)) {
+		/* Errors can only happen due to aborted journal or a nasty bug */
+		if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
 			ext4_journal_abort_handle(where, line, __func__, bh,
 						  handle, err);
 			if (inode == NULL) {

fs/ext4/ext4_jbd2.h

@@ -102,9 +102,9 @@
 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0
 #endif
-#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
 static inline int ext4_jbd2_credits_xattr(struct inode *inode)
 {

fs/ext4/extents.c

@@ -73,8 +73,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode,
 {
 	struct ext4_extent_tail *et;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	et = find_ext4_extent_tail(eh);
@@ -88,8 +87,7 @@ static void ext4_extent_block_csum_set(struct inode *inode,
 {
 	struct ext4_extent_tail *et;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	et = find_ext4_extent_tail(eh);
@@ -98,14 +96,14 @@ static void ext4_extent_block_csum_set(struct inode *inode,
 
 static int ext4_split_extent(handle_t *handle,
 				struct inode *inode,
-				struct ext4_ext_path *path,
+				struct ext4_ext_path **ppath,
 				struct ext4_map_blocks *map,
 				int split_flag,
 				int flags);
 
 static int ext4_split_extent_at(handle_t *handle,
 			     struct inode *inode,
-			     struct ext4_ext_path *path,
+			     struct ext4_ext_path **ppath,
 			     ext4_lblk_t split,
 			     int split_flag,
 			     int flags);
@@ -291,6 +289,20 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
 	return size;
 }
 
+static inline int
+ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
+			   struct ext4_ext_path **ppath, ext4_lblk_t lblk,
+			   int nofail)
+{
+	struct ext4_ext_path *path = *ppath;
+	int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
+
+	return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ?
+			EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0,
+			EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO |
+			(nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
+}
+
 /*
  * Calculate the number of metadata blocks needed
  * to allocate @blocks
@@ -695,9 +707,11 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
 
 void ext4_ext_drop_refs(struct ext4_ext_path *path)
 {
-	int depth = path->p_depth;
-	int i;
+	int depth, i;
 
+	if (!path)
+		return;
+	depth = path->p_depth;
 	for (i = 0; i <= depth; i++, path++)
 		if (path->p_bh) {
 			brelse(path->p_bh);
@@ -841,24 +855,32 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
 }
 
 struct ext4_ext_path *
-ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
-		     struct ext4_ext_path *path, int flags)
+ext4_find_extent(struct inode *inode, ext4_lblk_t block,
+		 struct ext4_ext_path **orig_path, int flags)
 {
 	struct ext4_extent_header *eh;
 	struct buffer_head *bh;
-	short int depth, i, ppos = 0, alloc = 0;
+	struct ext4_ext_path *path = orig_path ? *orig_path : NULL;
+	short int depth, i, ppos = 0;
 	int ret;
 
 	eh = ext_inode_hdr(inode);
 	depth = ext_depth(inode);
 
-	/* account possible depth increase */
+	if (path) {
+		ext4_ext_drop_refs(path);
+		if (depth > path[0].p_maxdepth) {
+			kfree(path);
+			*orig_path = path = NULL;
+		}
+	}
 	if (!path) {
+		/* account possible depth increase */
 		path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 2),
 				GFP_NOFS);
-		if (!path)
+		if (unlikely(!path))
 			return ERR_PTR(-ENOMEM);
-		alloc = 1;
+		path[0].p_maxdepth = depth + 1;
 	}
 	path[0].p_hdr = eh;
 	path[0].p_bh = NULL;
@@ -876,7 +898,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 
 		bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
 					    flags);
-		if (IS_ERR(bh)) {
+		if (unlikely(IS_ERR(bh))) {
 			ret = PTR_ERR(bh);
 			goto err;
 		}
@@ -910,8 +932,9 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 
 err:
 	ext4_ext_drop_refs(path);
-	if (alloc)
-		kfree(path);
+	kfree(path);
+	if (orig_path)
+		*orig_path = NULL;
 	return ERR_PTR(ret);
 }
 
@@ -1238,16 +1261,24 @@ cleanup:
  *   just created block
  */
 static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
-				 unsigned int flags,
-				 struct ext4_extent *newext)
+				 unsigned int flags)
 {
 	struct ext4_extent_header *neh;
 	struct buffer_head *bh;
-	ext4_fsblk_t newblock;
+	ext4_fsblk_t newblock, goal = 0;
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 	int err = 0;
 
-	newblock = ext4_ext_new_meta_block(handle, inode, NULL,
-		newext, &err, flags);
+	/* Try to prepend new index to old one */
+	if (ext_depth(inode))
+		goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode)));
+	if (goal > le32_to_cpu(es->s_first_data_block)) {
+		flags |= EXT4_MB_HINT_TRY_GOAL;
+		goal--;
+	} else
+		goal = ext4_inode_to_goal_block(inode);
+	newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
+					NULL, &err);
 	if (newblock == 0)
 		return err;
 
@@ -1314,9 +1345,10 @@ out:
 static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
 				    unsigned int mb_flags,
 				    unsigned int gb_flags,
-				    struct ext4_ext_path *path,
+				    struct ext4_ext_path **ppath,
 				    struct ext4_extent *newext)
 {
+	struct ext4_ext_path *path = *ppath;
 	struct ext4_ext_path *curp;
 	int depth, i, err = 0;
 
@@ -1340,23 +1372,21 @@ repeat:
 			goto out;
 
 		/* refill path */
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode,
+		path = ext4_find_extent(inode,
 				    (ext4_lblk_t)le32_to_cpu(newext->ee_block),
-				    path, gb_flags);
+				    ppath, gb_flags);
 		if (IS_ERR(path))
 			err = PTR_ERR(path);
 	} else {
 		/* tree is full, time to grow in depth */
-		err = ext4_ext_grow_indepth(handle, inode, mb_flags, newext);
+		err = ext4_ext_grow_indepth(handle, inode, mb_flags);
 		if (err)
 			goto out;
 
 		/* refill path */
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode,
+		path = ext4_find_extent(inode,
 				   (ext4_lblk_t)le32_to_cpu(newext->ee_block),
-				    path, gb_flags);
+				    ppath, gb_flags);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out;
@@ -1559,7 +1589,7 @@ found_extent:
  * allocated block. Thus, index entries have to be consistent
  * with leaves.
  */
-static ext4_lblk_t
+ext4_lblk_t
 ext4_ext_next_allocated_block(struct ext4_ext_path *path)
 {
 	int depth;
@@ -1802,6 +1832,7 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
 		sizeof(struct ext4_extent_idx);
 	s += sizeof(struct ext4_extent_header);
 
+	path[1].p_maxdepth = path[0].p_maxdepth;
 	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) +
@@ -1896,9 +1927,10 @@ out:
  * creating new leaf in the no-space case.
  */
 int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
-				struct ext4_ext_path *path,
+				struct ext4_ext_path **ppath,
 				struct ext4_extent *newext, int gb_flags)
 {
+	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent_header *eh;
 	struct ext4_extent *ex, *fex;
 	struct ext4_extent *nearex; /* nearest extent */
@@ -1907,6 +1939,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	ext4_lblk_t next;
 	int mb_flags = 0, unwritten;
 
+	if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		mb_flags |= EXT4_MB_DELALLOC_RESERVED;
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
 		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
 		return -EIO;
@@ -1925,7 +1959,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 		/*
 		 * Try to see whether we should rather test the extent on
 		 * right from ex, or from the left of ex. This is because
-		 * ext4_ext_find_extent() can return either extent on the
+		 * ext4_find_extent() can return either extent on the
 		 * left, or on the right from the searched position. This
 		 * will make merging more effective.
 		 */
@@ -2008,7 +2042,7 @@ prepend:
 	if (next != EXT_MAX_BLOCKS) {
 		ext_debug("next leaf block - %u\n", next);
 		BUG_ON(npath != NULL);
-		npath = ext4_ext_find_extent(inode, next, NULL, 0);
+		npath = ext4_find_extent(inode, next, NULL, 0);
 		if (IS_ERR(npath))
 			return PTR_ERR(npath);
 		BUG_ON(npath->p_depth != path->p_depth);
@@ -2028,9 +2062,9 @@ prepend:
 	 * We're gonna add a new leaf in the tree.
 	 */
 	if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
-		mb_flags = EXT4_MB_USE_RESERVED;
+		mb_flags |= EXT4_MB_USE_RESERVED;
 	err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
-				       path, newext);
+				       ppath, newext);
 	if (err)
 		goto cleanup;
 	depth = ext_depth(inode);
@@ -2108,10 +2142,8 @@ merge:
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 
 cleanup:
-	if (npath) {
-		ext4_ext_drop_refs(npath);
-		kfree(npath);
-	}
+	ext4_ext_drop_refs(npath);
+	kfree(npath);
 	return err;
 }
 
@@ -2133,13 +2165,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 		/* find extent for this block */
 		down_read(&EXT4_I(inode)->i_data_sem);
 
-		if (path && ext_depth(inode) != depth) {
-			/* depth was changed. we have to realloc path */
-			kfree(path);
-			path = NULL;
-		}
-
-		path = ext4_ext_find_extent(inode, block, path, 0);
+		path = ext4_find_extent(inode, block, &path, 0);
 		if (IS_ERR(path)) {
 			up_read(&EXT4_I(inode)->i_data_sem);
 			err = PTR_ERR(path);
@@ -2156,7 +2182,6 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 		}
 		ex = path[depth].p_ext;
 		next = ext4_ext_next_allocated_block(path);
-		ext4_ext_drop_refs(path);
 
 		flags = 0;
 		exists = 0;
@@ -2266,11 +2291,8 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 		block = es.es_lblk + es.es_len;
 	}
 
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
-
+	ext4_ext_drop_refs(path);
+	kfree(path);
 	return err;
 }
 
@@ -2826,7 +2848,7 @@ again:
 		ext4_lblk_t ee_block;
 
 		/* find extent for this block */
-		path = ext4_ext_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
+		path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
 		if (IS_ERR(path)) {
 			ext4_journal_stop(handle);
 			return PTR_ERR(path);
@@ -2854,24 +2876,14 @@ again:
 		 */
 		if (end >= ee_block &&
 		    end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
-			int split_flag = 0;
-
-			if (ext4_ext_is_unwritten(ex))
-				split_flag = EXT4_EXT_MARK_UNWRIT1 |
-					     EXT4_EXT_MARK_UNWRIT2;
-
 			/*
 			 * Split the extent in two so that 'end' is the last
 			 * block in the first new extent. Also we should not
 			 * fail removing space due to ENOSPC so try to use
 			 * reserved block if that happens.
 			 */
-			err = ext4_split_extent_at(handle, inode, path,
-					end + 1, split_flag,
-					EXT4_EX_NOCACHE |
-					EXT4_GET_BLOCKS_PRE_IO |
-					EXT4_GET_BLOCKS_METADATA_NOFAIL);
-
+			err = ext4_force_split_extent_at(handle, inode, &path,
+							 end + 1, 1);
 			if (err < 0)
 				goto out;
 		}
@@ -2893,7 +2905,7 @@ again:
 			ext4_journal_stop(handle);
 			return -ENOMEM;
 		}
-		path[0].p_depth = depth;
+		path[0].p_maxdepth = path[0].p_depth = depth;
 		path[0].p_hdr = ext_inode_hdr(inode);
 		i = 0;
 
@@ -3013,10 +3025,9 @@ again:
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
-	if (err == -EAGAIN) {
-		path = NULL;
+	path = NULL;
+	if (err == -EAGAIN)
 		goto again;
-	}
 	ext4_journal_stop(handle);
 
 	return err;
@@ -3130,11 +3141,12 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
  */
 static int ext4_split_extent_at(handle_t *handle,
 			     struct inode *inode,
-			     struct ext4_ext_path *path,
+			     struct ext4_ext_path **ppath,
 			     ext4_lblk_t split,
 			     int split_flag,
 			     int flags)
 {
+	struct ext4_ext_path *path = *ppath;
 	ext4_fsblk_t newblock;
 	ext4_lblk_t ee_block;
 	struct ext4_extent *ex, newex, orig_ex, zero_ex;
@@ -3205,7 +3217,7 @@ static int ext4_split_extent_at(handle_t *handle,
 	if (split_flag & EXT4_EXT_MARK_UNWRIT2)
 		ext4_ext_mark_unwritten(ex2);
 
-	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+	err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
 	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
 		if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
 			if (split_flag & EXT4_EXT_DATA_VALID1) {
@@ -3271,11 +3283,12 @@ fix_extent_len:
  */
 static int ext4_split_extent(handle_t *handle,
 			      struct inode *inode,
-			      struct ext4_ext_path *path,
+			      struct ext4_ext_path **ppath,
 			      struct ext4_map_blocks *map,
 			      int split_flag,
 			      int flags)
 {
+	struct ext4_ext_path *path = *ppath;
 	ext4_lblk_t ee_block;
 	struct ext4_extent *ex;
 	unsigned int ee_len, depth;
@@ -3298,7 +3311,7 @@ static int ext4_split_extent(handle_t *handle,
 				       EXT4_EXT_MARK_UNWRIT2;
 		if (split_flag & EXT4_EXT_DATA_VALID2)
 			split_flag1 |= EXT4_EXT_DATA_VALID1;
-		err = ext4_split_extent_at(handle, inode, path,
+		err = ext4_split_extent_at(handle, inode, ppath,
 				map->m_lblk + map->m_len, split_flag1, flags1);
 		if (err)
 			goto out;
@@ -3309,8 +3322,7 @@ static int ext4_split_extent(handle_t *handle,
 	 * Update path is required because previous ext4_split_extent_at() may
 	 * result in split of original leaf or extent zeroout.
 	 */
-	ext4_ext_drop_refs(path);
-	path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+	path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	depth = ext_depth(inode);
@@ -3330,7 +3342,7 @@ static int ext4_split_extent(handle_t *handle,
 			split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
 						     EXT4_EXT_MARK_UNWRIT2);
 		}
-		err = ext4_split_extent_at(handle, inode, path,
+		err = ext4_split_extent_at(handle, inode, ppath,
 				map->m_lblk, split_flag1, flags);
 		if (err)
 			goto out;
@@ -3364,9 +3376,10 @@ out:
 static int ext4_ext_convert_to_initialized(handle_t *handle,
 					   struct inode *inode,
 					   struct ext4_map_blocks *map,
-					   struct ext4_ext_path *path,
+					   struct ext4_ext_path **ppath,
 					   int flags)
 {
+	struct ext4_ext_path *path = *ppath;
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
@@ -3590,7 +3603,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		}
 	}
 
-	allocated = ext4_split_extent(handle, inode, path,
+	allocated = ext4_split_extent(handle, inode, ppath,
 				      &split_map, split_flag, flags);
 	if (allocated < 0)
 		err = allocated;
@@ -3629,9 +3642,10 @@ out:
 static int ext4_split_convert_extents(handle_t *handle,
 					struct inode *inode,
 					struct ext4_map_blocks *map,
-					struct ext4_ext_path *path,
+					struct ext4_ext_path **ppath,
 					int flags)
 {
+	struct ext4_ext_path *path = *ppath;
 	ext4_lblk_t eof_block;
 	ext4_lblk_t ee_block;
 	struct ext4_extent *ex;
@@ -3665,74 +3679,15 @@ static int ext4_split_convert_extents(handle_t *handle,
 		split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
 	}
 	flags |= EXT4_GET_BLOCKS_PRE_IO;
-	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
-}
-
-static int ext4_convert_initialized_extents(handle_t *handle,
-					    struct inode *inode,
-					    struct ext4_map_blocks *map,
-					    struct ext4_ext_path *path)
-{
-	struct ext4_extent *ex;
-	ext4_lblk_t ee_block;
-	unsigned int ee_len;
-	int depth;
-	int err = 0;
-
-	depth = ext_depth(inode);
-	ex = path[depth].p_ext;
-	ee_block = le32_to_cpu(ex->ee_block);
-	ee_len = ext4_ext_get_actual_len(ex);
-
-	ext_debug("%s: inode %lu, logical"
-		"block %llu, max_blocks %u\n", __func__, inode->i_ino,
-		  (unsigned long long)ee_block, ee_len);
-
-	if (ee_block != map->m_lblk || ee_len > map->m_len) {
-		err = ext4_split_convert_extents(handle, inode, map, path,
-				EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
-		if (err < 0)
-			goto out;
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
-		if (IS_ERR(path)) {
-			err = PTR_ERR(path);
-			goto out;
-		}
-		depth = ext_depth(inode);
-		ex = path[depth].p_ext;
-		if (!ex) {
-			EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
-					 (unsigned long) map->m_lblk);
-			err = -EIO;
-			goto out;
-		}
-	}
-
-	err = ext4_ext_get_access(handle, inode, path + depth);
-	if (err)
-		goto out;
-	/* first mark the extent as unwritten */
-	ext4_ext_mark_unwritten(ex);
-
-	/* note: ext4_ext_correct_indexes() isn't needed here because
-	 * borders are not changed
-	 */
-	ext4_ext_try_to_merge(handle, inode, path, ex);
-
-	/* Mark modified extent as dirty */
-	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-out:
-	ext4_ext_show_leaf(inode, path);
-	return err;
+	return ext4_split_extent(handle, inode, ppath, map, split_flag, flags);
 }
 
-
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 						struct inode *inode,
 						struct ext4_map_blocks *map,
-						struct ext4_ext_path *path)
+						struct ext4_ext_path **ppath)
 {
+	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
 	ext4_lblk_t ee_block;
 	unsigned int ee_len;
@@ -3761,16 +3716,13 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 			     inode->i_ino, (unsigned long long)ee_block, ee_len,
 			     (unsigned long long)map->m_lblk, map->m_len);
 #endif
-		err = ext4_split_convert_extents(handle, inode, map, path,
+		err = ext4_split_convert_extents(handle, inode, map, ppath,
 						 EXT4_GET_BLOCKS_CONVERT);
 		if (err < 0)
-			goto out;
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
-		if (IS_ERR(path)) {
-			err = PTR_ERR(path);
-			goto out;
-		}
+			return err;
+		path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+		if (IS_ERR(path))
+			return PTR_ERR(path);
 		depth = ext_depth(inode);
 		ex = path[depth].p_ext;
 	}
@@ -3963,12 +3915,16 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 }
 
 static int
-ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
-			struct ext4_map_blocks *map,
-			struct ext4_ext_path *path, int flags,
-			unsigned int allocated, ext4_fsblk_t newblock)
+convert_initialized_extent(handle_t *handle, struct inode *inode,
+			   struct ext4_map_blocks *map,
+			   struct ext4_ext_path **ppath, int flags,
+			   unsigned int allocated, ext4_fsblk_t newblock)
 {
-	int ret = 0;
+	struct ext4_ext_path *path = *ppath;
+	struct ext4_extent *ex;
+	ext4_lblk_t ee_block;
+	unsigned int ee_len;
+	int depth;
 	int err = 0;
 
 	/*
@@ -3978,28 +3934,67 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
 	if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
 		map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
 
-	ret = ext4_convert_initialized_extents(handle, inode, map,
-						path);
-	if (ret >= 0) {
-		ext4_update_inode_fsync_trans(handle, inode, 1);
-		err = check_eofblocks_fl(handle, inode, map->m_lblk,
-					 path, map->m_len);
-	} else
-		err = ret;
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+
+	ext_debug("%s: inode %lu, logical"
+		"block %llu, max_blocks %u\n", __func__, inode->i_ino,
+		  (unsigned long long)ee_block, ee_len);
+
+	if (ee_block != map->m_lblk || ee_len > map->m_len) {
+		err = ext4_split_convert_extents(handle, inode, map, ppath,
+				EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+		if (err < 0)
+			return err;
+		path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+		if (IS_ERR(path))
+			return PTR_ERR(path);
+		depth = ext_depth(inode);
+		ex = path[depth].p_ext;
+		if (!ex) {
+			EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+					 (unsigned long) map->m_lblk);
+			return -EIO;
+		}
+	}
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		return err;
+	/* first mark the extent as unwritten */
+	ext4_ext_mark_unwritten(ex);
+
+	/* note: ext4_ext_correct_indexes() isn't needed here because
+	 * borders are not changed
+	 */
+	ext4_ext_try_to_merge(handle, inode, path, ex);
+
+	/* Mark modified extent as dirty */
+	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+	if (err)
+		return err;
+	ext4_ext_show_leaf(inode, path);
+
+	ext4_update_inode_fsync_trans(handle, inode, 1);
+	err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len);
+	if (err)
+		return err;
 	map->m_flags |= EXT4_MAP_UNWRITTEN;
 	if (allocated > map->m_len)
 		allocated = map->m_len;
 	map->m_len = allocated;
-
-	return err ? err : allocated;
+	return allocated;
 }
 
 static int
 ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map,
-			struct ext4_ext_path *path, int flags,
+			struct ext4_ext_path **ppath, int flags,
 			unsigned int allocated, ext4_fsblk_t newblock)
 {
+	struct ext4_ext_path *path = *ppath;
 	int ret = 0;
 	int err = 0;
 	ext4_io_end_t *io = ext4_inode_aio(inode);
@@ -4021,8 +4016,8 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 
 	/* get_block() before submit the IO, split the extent */
 	if (flags & EXT4_GET_BLOCKS_PRE_IO) {
-		ret = ext4_split_convert_extents(handle, inode, map,
-					 path, flags | EXT4_GET_BLOCKS_CONVERT);
+		ret = ext4_split_convert_extents(handle, inode, map, ppath,
+					 flags | EXT4_GET_BLOCKS_CONVERT);
 		if (ret <= 0)
 			goto out;
 		/*
@@ -4040,7 +4035,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	/* IO end_io complete, convert the filled extent to written */
 	if (flags & EXT4_GET_BLOCKS_CONVERT) {
 		ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
-							path);
+							   ppath);
 		if (ret >= 0) {
 			ext4_update_inode_fsync_trans(handle, inode, 1);
 			err = check_eofblocks_fl(handle, inode, map->m_lblk,
@@ -4078,7 +4073,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	}
 
 	/* buffered write, writepage time, convert*/
-	ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags);
+	ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags);
 	if (ret >= 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 out:
@@ -4279,7 +4274,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 
 	/* find extent for this block */
-	path = ext4_ext_find_extent(inode, map->m_lblk, NULL, 0);
+	path = ext4_find_extent(inode, map->m_lblk, NULL, 0);
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
 		path = NULL;
@@ -4291,7 +4286,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	/*
 	 * consistent leaf must not be empty;
 	 * this situation is possible, though, _during_ tree modification;
-	 * this is why assert can't be put in ext4_ext_find_extent()
+	 * this is why assert can't be put in ext4_find_extent()
 	 */
 	if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
 		EXT4_ERROR_INODE(inode, "bad extent address "
@@ -4331,15 +4326,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			 */
 			if ((!ext4_ext_is_unwritten(ex)) &&
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
-				allocated = ext4_ext_convert_initialized_extent(
-						handle, inode, map, path, flags,
-						allocated, newblock);
+				allocated = convert_initialized_extent(
+						handle, inode, map, &path,
+						flags, allocated, newblock);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
 
 			ret = ext4_ext_handle_unwritten_extents(
-				handle, inode, map, path, flags,
+				handle, inode, map, &path, flags,
 				allocated, newblock);
 			if (ret < 0)
 				err = ret;
@@ -4376,7 +4371,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 	/*
 	 * If we are doing bigalloc, check to see if the extent returned
-	 * by ext4_ext_find_extent() implies a cluster we can use.
+	 * by ext4_find_extent() implies a cluster we can use.
 	 */
 	if (cluster_offset && ex &&
 	    get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
@@ -4451,6 +4446,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		ar.flags = 0;
 	if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
 		ar.flags |= EXT4_MB_HINT_NOPREALLOC;
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ar.flags |= EXT4_MB_DELALLOC_RESERVED;
 	newblock = ext4_mb_new_blocks(handle, &ar, &err);
 	if (!newblock)
 		goto out2;
@@ -4486,7 +4483,7 @@ got_allocated_blocks:
 		err = check_eofblocks_fl(handle, inode, map->m_lblk,
 					 path, ar.len);
 	if (!err)
-		err = ext4_ext_insert_extent(handle, inode, path,
+		err = ext4_ext_insert_extent(handle, inode, &path,
 					     &newex, flags);
 
 	if (!err && set_unwritten) {
@@ -4619,10 +4616,8 @@ out:
 	map->m_pblk = newblock;
 	map->m_len = allocated;
 out2:
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
+	ext4_ext_drop_refs(path);
+	kfree(path);
 
 	trace_ext4_ext_map_blocks_exit(inode, flags, map,
 				       err ? err : allocated);
@@ -4799,7 +4794,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		max_blocks -= lblk;
 
 	flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
-		EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
+		EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+		EXT4_EX_NOCACHE;
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
@@ -4837,15 +4833,21 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		ext4_inode_block_unlocked_dio(inode);
 		inode_dio_wait(inode);
 
+		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+					     flags, mode);
+		if (ret)
+			goto out_dio;
 		/*
 		 * Remove entire range from the extent status tree.
+		 *
+		 * ext4_es_remove_extent(inode, lblk, max_blocks) is
+		 * NOT sufficient.  I'm not sure why this is the case,
+		 * but let's be conservative and remove the extent
+		 * status tree for the entire inode.  There should be
+		 * no outstanding delalloc extents thanks to the
+		 * filemap_write_and_wait_range() call above.
 		 */
-		ret = ext4_es_remove_extent(inode, lblk, max_blocks);
-		if (ret)
-			goto out_dio;
-
-		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
-					     flags, mode);
+		ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 		if (ret)
 			goto out_dio;
 	}
@@ -5304,36 +5306,31 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	struct ext4_ext_path *path;
 	int ret = 0, depth;
 	struct ext4_extent *extent;
-	ext4_lblk_t stop_block, current_block;
+	ext4_lblk_t stop_block;
 	ext4_lblk_t ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
 	depth = path->p_depth;
 	extent = path[depth].p_ext;
-	if (!extent) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-		return ret;
-	}
+	if (!extent)
+		goto out;
 
 	stop_block = le32_to_cpu(extent->ee_block) +
 			ext4_ext_get_actual_len(extent);
-	ext4_ext_drop_refs(path);
-	kfree(path);
 
 	/* Nothing to shift, if hole is at the end of file */
 	if (start >= stop_block)
-		return ret;
+		goto out;
 
 	/*
 	 * Don't start shifting extents until we make sure the hole is big
 	 * enough to accomodate the shift.
 	 */
-	path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+	path = ext4_find_extent(inode, start - 1, &path, 0);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	depth = path->p_depth;
@@ -5346,8 +5343,6 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 		ex_start = 0;
 		ex_end = 0;
 	}
-	ext4_ext_drop_refs(path);
-	kfree(path);
 
 	if ((start == ex_start && shift > ex_start) ||
 	    (shift > start - ex_end))
@@ -5355,7 +5350,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 
 	/* Its safe to start updating extents */
 	while (start < stop_block) {
-		path = ext4_ext_find_extent(inode, start, NULL, 0);
+		path = ext4_find_extent(inode, start, &path, 0);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5365,27 +5360,23 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					 (unsigned long) start);
 			return -EIO;
 		}
-
-		current_block = le32_to_cpu(extent->ee_block);
-		if (start > current_block) {
+		if (start > le32_to_cpu(extent->ee_block)) {
 			/* Hole, move to the next extent */
-			ret = mext_next_extent(inode, path, &extent);
-			if (ret != 0) {
-				ext4_ext_drop_refs(path);
-				kfree(path);
-				if (ret == 1)
-					ret = 0;
-				break;
+			if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) {
+				path[depth].p_ext++;
+			} else {
+				start = ext4_ext_next_allocated_block(path);
+				continue;
 			}
 		}
 		ret = ext4_ext_shift_path_extents(path, shift, inode,
 				handle, &start);
-		ext4_ext_drop_refs(path);
-		kfree(path);
 		if (ret)
 			break;
 	}
-
+out:
+	ext4_ext_drop_refs(path);
+	kfree(path);
 	return ret;
 }
 
@@ -5508,3 +5499,199 @@ out_mutex:
 	mutex_unlock(&inode->i_mutex);
 	return ret;
 }
+
+/**
+ * ext4_swap_extents - Swap extents between two inodes
+ *
+ * @inode1:	First inode
+ * @inode2:	Second inode
+ * @lblk1:	Start block for first inode
+ * @lblk2:	Start block for second inode
+ * @count:	Number of blocks to swap
+ * @mark_unwritten: Mark second inode's extents as unwritten after swap
+ * @erp:	Pointer to save error value
+ *
+ * This helper routine does exactly what is promise "swap extents". All other
+ * stuff such as page-cache locking consistency, bh mapping consistency or
+ * extent's data copying must be performed by caller.
+ * Locking:
+ * 		i_mutex is held for both inodes
+ * 		i_data_sem is locked for write for both inodes
+ * Assumptions:
+ *		All pages from requested range are locked for both inodes
+ */
+int
+ext4_swap_extents(handle_t *handle, struct inode *inode1,
+		     struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2,
+		  ext4_lblk_t count, int unwritten, int *erp)
+{
+	struct ext4_ext_path *path1 = NULL;
+	struct ext4_ext_path *path2 = NULL;
+	int replaced_count = 0;
+
+	BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem));
+	BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem));
+	BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+	BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+
+	*erp = ext4_es_remove_extent(inode1, lblk1, count);
+	if (unlikely(*erp))
+		return 0;
+	*erp = ext4_es_remove_extent(inode2, lblk2, count);
+	if (unlikely(*erp))
+		return 0;
+
+	while (count) {
+		struct ext4_extent *ex1, *ex2, tmp_ex;
+		ext4_lblk_t e1_blk, e2_blk;
+		int e1_len, e2_len, len;
+		int split = 0;
+
+		path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE);
+		if (unlikely(IS_ERR(path1))) {
+			*erp = PTR_ERR(path1);
+			path1 = NULL;
+		finish:
+			count = 0;
+			goto repeat;
+		}
+		path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE);
+		if (unlikely(IS_ERR(path2))) {
+			*erp = PTR_ERR(path2);
+			path2 = NULL;
+			goto finish;
+		}
+		ex1 = path1[path1->p_depth].p_ext;
+		ex2 = path2[path2->p_depth].p_ext;
+		/* Do we have somthing to swap ? */
+		if (unlikely(!ex2 || !ex1))
+			goto finish;
+
+		e1_blk = le32_to_cpu(ex1->ee_block);
+		e2_blk = le32_to_cpu(ex2->ee_block);
+		e1_len = ext4_ext_get_actual_len(ex1);
+		e2_len = ext4_ext_get_actual_len(ex2);
+
+		/* Hole handling */
+		if (!in_range(lblk1, e1_blk, e1_len) ||
+		    !in_range(lblk2, e2_blk, e2_len)) {
+			ext4_lblk_t next1, next2;
+
+			/* if hole after extent, then go to next extent */
+			next1 = ext4_ext_next_allocated_block(path1);
+			next2 = ext4_ext_next_allocated_block(path2);
+			/* If hole before extent, then shift to that extent */
+			if (e1_blk > lblk1)
+				next1 = e1_blk;
+			if (e2_blk > lblk2)
+				next2 = e1_blk;
+			/* Do we have something to swap */
+			if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS)
+				goto finish;
+			/* Move to the rightest boundary */
+			len = next1 - lblk1;
+			if (len < next2 - lblk2)
+				len = next2 - lblk2;
+			if (len > count)
+				len = count;
+			lblk1 += len;
+			lblk2 += len;
+			count -= len;
+			goto repeat;
+		}
+
+		/* Prepare left boundary */
+		if (e1_blk < lblk1) {
+			split = 1;
+			*erp = ext4_force_split_extent_at(handle, inode1,
+						&path1, lblk1, 0);
+			if (unlikely(*erp))
+				goto finish;
+		}
+		if (e2_blk < lblk2) {
+			split = 1;
+			*erp = ext4_force_split_extent_at(handle, inode2,
+						&path2,  lblk2, 0);
+			if (unlikely(*erp))
+				goto finish;
+		}
+		/* ext4_split_extent_at() may result in leaf extent split,
+		 * path must to be revalidated. */
+		if (split)
+			goto repeat;
+
+		/* Prepare right boundary */
+		len = count;
+		if (len > e1_blk + e1_len - lblk1)
+			len = e1_blk + e1_len - lblk1;
+		if (len > e2_blk + e2_len - lblk2)
+			len = e2_blk + e2_len - lblk2;
+
+		if (len != e1_len) {
+			split = 1;
+			*erp = ext4_force_split_extent_at(handle, inode1,
+						&path1, lblk1 + len, 0);
+			if (unlikely(*erp))
+				goto finish;
+		}
+		if (len != e2_len) {
+			split = 1;
+			*erp = ext4_force_split_extent_at(handle, inode2,
+						&path2, lblk2 + len, 0);
+			if (*erp)
+				goto finish;
+		}
+		/* ext4_split_extent_at() may result in leaf extent split,
+		 * path must to be revalidated. */
+		if (split)
+			goto repeat;
+
+		BUG_ON(e2_len != e1_len);
+		*erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth);
+		if (unlikely(*erp))
+			goto finish;
+		*erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth);
+		if (unlikely(*erp))
+			goto finish;
+
+		/* Both extents are fully inside boundaries. Swap it now */
+		tmp_ex = *ex1;
+		ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2));
+		ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex));
+		ex1->ee_len = cpu_to_le16(e2_len);
+		ex2->ee_len = cpu_to_le16(e1_len);
+		if (unwritten)
+			ext4_ext_mark_unwritten(ex2);
+		if (ext4_ext_is_unwritten(&tmp_ex))
+			ext4_ext_mark_unwritten(ex1);
+
+		ext4_ext_try_to_merge(handle, inode2, path2, ex2);
+		ext4_ext_try_to_merge(handle, inode1, path1, ex1);
+		*erp = ext4_ext_dirty(handle, inode2, path2 +
+				      path2->p_depth);
+		if (unlikely(*erp))
+			goto finish;
+		*erp = ext4_ext_dirty(handle, inode1, path1 +
+				      path1->p_depth);
+		/*
+		 * Looks scarry ah..? second inode already points to new blocks,
+		 * and it was successfully dirtied. But luckily error may happen
+		 * only due to journal error, so full transaction will be
+		 * aborted anyway.
+		 */
+		if (unlikely(*erp))
+			goto finish;
+		lblk1 += len;
+		lblk2 += len;
+		replaced_count += len;
+		count -= len;
+
+	repeat:
+		ext4_ext_drop_refs(path1);
+		kfree(path1);
+		ext4_ext_drop_refs(path2);
+		kfree(path2);
+		path1 = path2 = NULL;
+	}
+	return replaced_count;
+}

fs/ext4/extents_status.c

@@ -11,6 +11,8 @@
  */
 #include <linux/rbtree.h>
 #include <linux/list_sort.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include "ext4.h"
 #include "extents_status.h"
 
@@ -313,19 +315,27 @@ ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
 	 */
 	if (!ext4_es_is_delayed(es)) {
 		EXT4_I(inode)->i_es_lru_nr++;
-		percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+		percpu_counter_inc(&EXT4_SB(inode->i_sb)->
+					s_es_stats.es_stats_lru_cnt);
 	}
 
+	EXT4_I(inode)->i_es_all_nr++;
+	percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+
 	return es;
 }
 
 static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 {
+	EXT4_I(inode)->i_es_all_nr--;
+	percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+
 	/* Decrease the lru counter when this es is not delayed */
 	if (!ext4_es_is_delayed(es)) {
 		BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
 		EXT4_I(inode)->i_es_lru_nr--;
-		percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+		percpu_counter_dec(&EXT4_SB(inode->i_sb)->
+					s_es_stats.es_stats_lru_cnt);
 	}
 
 	kmem_cache_free(ext4_es_cachep, es);
@@ -426,7 +436,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
 	unsigned short ee_len;
 	int depth, ee_status, es_status;
 
-	path = ext4_ext_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE);
+	path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return;
 
@@ -499,10 +509,8 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
 		}
 	}
 out:
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
+	ext4_ext_drop_refs(path);
+	kfree(path);
 }
 
 static void ext4_es_insert_extent_ind_check(struct inode *inode,
@@ -731,6 +739,7 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 			  struct extent_status *es)
 {
 	struct ext4_es_tree *tree;
+	struct ext4_es_stats *stats;
 	struct extent_status *es1 = NULL;
 	struct rb_node *node;
 	int found = 0;
@@ -767,11 +776,15 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 	}
 
 out:
+	stats = &EXT4_SB(inode->i_sb)->s_es_stats;
 	if (found) {
 		BUG_ON(!es1);
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
+		stats->es_stats_cache_hits++;
+	} else {
+		stats->es_stats_cache_misses++;
 	}
 
 	read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -933,11 +946,16 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 			    struct ext4_inode_info *locked_ei)
 {
 	struct ext4_inode_info *ei;
+	struct ext4_es_stats *es_stats;
 	struct list_head *cur, *tmp;
 	LIST_HEAD(skipped);
+	ktime_t start_time;
+	u64 scan_time;
 	int nr_shrunk = 0;
 	int retried = 0, skip_precached = 1, nr_skipped = 0;
 
+	es_stats = &sbi->s_es_stats;
+	start_time = ktime_get();
 	spin_lock(&sbi->s_es_lru_lock);
 
 retry:
@@ -948,7 +966,8 @@ retry:
 		 * If we have already reclaimed all extents from extent
 		 * status tree, just stop the loop immediately.
 		 */
-		if (percpu_counter_read_positive(&sbi->s_extent_cache_cnt) == 0)
+		if (percpu_counter_read_positive(
+				&es_stats->es_stats_lru_cnt) == 0)
 			break;
 
 		ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
@@ -958,7 +977,7 @@ retry:
 		 * time.  Normally we try hard to avoid shrinking
 		 * precached inodes, but we will as a last resort.
 		 */
-		if ((sbi->s_es_last_sorted < ei->i_touch_when) ||
+		if ((es_stats->es_stats_last_sorted < ei->i_touch_when) ||
 		    (skip_precached && ext4_test_inode_state(&ei->vfs_inode,
 						EXT4_STATE_EXT_PRECACHED))) {
 			nr_skipped++;
@@ -992,7 +1011,7 @@ retry:
 	if ((nr_shrunk == 0) && nr_skipped && !retried) {
 		retried++;
 		list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
-		sbi->s_es_last_sorted = jiffies;
+		es_stats->es_stats_last_sorted = jiffies;
 		ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info,
 				      i_es_lru);
 		/*
@@ -1010,6 +1029,22 @@ retry:
 	if (locked_ei && nr_shrunk == 0)
 		nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan);
 
+	scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+	if (likely(es_stats->es_stats_scan_time))
+		es_stats->es_stats_scan_time = (scan_time +
+				es_stats->es_stats_scan_time*3) / 4;
+	else
+		es_stats->es_stats_scan_time = scan_time;
+	if (scan_time > es_stats->es_stats_max_scan_time)
+		es_stats->es_stats_max_scan_time = scan_time;
+	if (likely(es_stats->es_stats_shrunk))
+		es_stats->es_stats_shrunk = (nr_shrunk +
+				es_stats->es_stats_shrunk*3) / 4;
+	else
+		es_stats->es_stats_shrunk = nr_shrunk;
+
+	trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, skip_precached,
+			     nr_skipped, retried);
 	return nr_shrunk;
 }
 
@@ -1020,8 +1055,8 @@ static unsigned long ext4_es_count(struct shrinker *shrink,
 	struct ext4_sb_info *sbi;
 
 	sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker);
-	nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
-	trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr);
+	nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+	trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr);
 	return nr;
 }
 
@@ -1033,31 +1068,160 @@ static unsigned long ext4_es_scan(struct shrinker *shrink,
 	int nr_to_scan = sc->nr_to_scan;
 	int ret, nr_shrunk;
 
-	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
-	trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
+	ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+	trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
 
 	if (!nr_to_scan)
 		return ret;
 
 	nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
 
-	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
+	trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
 	return nr_shrunk;
 }
 
-void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
+static void *ext4_es_seq_shrinker_info_start(struct seq_file *seq, loff_t *pos)
 {
+	return *pos ? NULL : SEQ_START_TOKEN;
+}
+
+static void *
+ext4_es_seq_shrinker_info_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return NULL;
+}
+
+static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v)
+{
+	struct ext4_sb_info *sbi = seq->private;
+	struct ext4_es_stats *es_stats = &sbi->s_es_stats;
+	struct ext4_inode_info *ei, *max = NULL;
+	unsigned int inode_cnt = 0;
+
+	if (v != SEQ_START_TOKEN)
+		return 0;
+
+	/* here we just find an inode that has the max nr. of objects */
+	spin_lock(&sbi->s_es_lru_lock);
+	list_for_each_entry(ei, &sbi->s_es_lru, i_es_lru) {
+		inode_cnt++;
+		if (max && max->i_es_all_nr < ei->i_es_all_nr)
+			max = ei;
+		else if (!max)
+			max = ei;
+	}
+	spin_unlock(&sbi->s_es_lru_lock);
+
+	seq_printf(seq, "stats:\n  %lld objects\n  %lld reclaimable objects\n",
+		   percpu_counter_sum_positive(&es_stats->es_stats_all_cnt),
+		   percpu_counter_sum_positive(&es_stats->es_stats_lru_cnt));
+	seq_printf(seq, "  %lu/%lu cache hits/misses\n",
+		   es_stats->es_stats_cache_hits,
+		   es_stats->es_stats_cache_misses);
+	if (es_stats->es_stats_last_sorted != 0)
+		seq_printf(seq, "  %u ms last sorted interval\n",
+			   jiffies_to_msecs(jiffies -
+					    es_stats->es_stats_last_sorted));
+	if (inode_cnt)
+		seq_printf(seq, "  %d inodes on lru list\n", inode_cnt);
+
+	seq_printf(seq, "average:\n  %llu us scan time\n",
+	    div_u64(es_stats->es_stats_scan_time, 1000));
+	seq_printf(seq, "  %lu shrunk objects\n", es_stats->es_stats_shrunk);
+	if (inode_cnt)
+		seq_printf(seq,
+		    "maximum:\n  %lu inode (%u objects, %u reclaimable)\n"
+		    "  %llu us max scan time\n",
+		    max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_lru_nr,
+		    div_u64(es_stats->es_stats_max_scan_time, 1000));
+
+	return 0;
+}
+
+static void ext4_es_seq_shrinker_info_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations ext4_es_seq_shrinker_info_ops = {
+	.start = ext4_es_seq_shrinker_info_start,
+	.next  = ext4_es_seq_shrinker_info_next,
+	.stop  = ext4_es_seq_shrinker_info_stop,
+	.show  = ext4_es_seq_shrinker_info_show,
+};
+
+static int
+ext4_es_seq_shrinker_info_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &ext4_es_seq_shrinker_info_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = PDE_DATA(inode);
+	}
+
+	return ret;
+}
+
+static int
+ext4_es_seq_shrinker_info_release(struct inode *inode, struct file *file)
+{
+	return seq_release(inode, file);
+}
+
+static const struct file_operations ext4_es_seq_shrinker_info_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ext4_es_seq_shrinker_info_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= ext4_es_seq_shrinker_info_release,
+};
+
+int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
+{
+	int err;
+
 	INIT_LIST_HEAD(&sbi->s_es_lru);
 	spin_lock_init(&sbi->s_es_lru_lock);
-	sbi->s_es_last_sorted = 0;
+	sbi->s_es_stats.es_stats_last_sorted = 0;
+	sbi->s_es_stats.es_stats_shrunk = 0;
+	sbi->s_es_stats.es_stats_cache_hits = 0;
+	sbi->s_es_stats.es_stats_cache_misses = 0;
+	sbi->s_es_stats.es_stats_scan_time = 0;
+	sbi->s_es_stats.es_stats_max_scan_time = 0;
+	err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL);
+	if (err)
+		return err;
+	err = percpu_counter_init(&sbi->s_es_stats.es_stats_lru_cnt, 0, GFP_KERNEL);
+	if (err)
+		goto err1;
+
 	sbi->s_es_shrinker.scan_objects = ext4_es_scan;
 	sbi->s_es_shrinker.count_objects = ext4_es_count;
 	sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
-	register_shrinker(&sbi->s_es_shrinker);
+	err = register_shrinker(&sbi->s_es_shrinker);
+	if (err)
+		goto err2;
+
+	if (sbi->s_proc)
+		proc_create_data("es_shrinker_info", S_IRUGO, sbi->s_proc,
+				 &ext4_es_seq_shrinker_info_fops, sbi);
+
+	return 0;
+
+err2:
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
+err1:
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
+	return err;
 }
 
 void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
 {
+	if (sbi->s_proc)
+		remove_proc_entry("es_shrinker_info", sbi->s_proc);
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
 	unregister_shrinker(&sbi->s_es_shrinker);
 }
 

fs/ext4/extents_status.h

@@ -64,6 +64,17 @@ struct ext4_es_tree {
 	struct extent_status *cache_es;	/* recently accessed extent */
 };
 
+struct ext4_es_stats {
+	unsigned long es_stats_last_sorted;
+	unsigned long es_stats_shrunk;
+	unsigned long es_stats_cache_hits;
+	unsigned long es_stats_cache_misses;
+	u64 es_stats_scan_time;
+	u64 es_stats_max_scan_time;
+	struct percpu_counter es_stats_all_cnt;
+	struct percpu_counter es_stats_lru_cnt;
+};
+
 extern int __init ext4_init_es(void);
 extern void ext4_exit_es(void);
 extern void ext4_es_init_tree(struct ext4_es_tree *tree);
@@ -138,7 +149,7 @@ static inline void ext4_es_store_pblock_status(struct extent_status *es,
 		       (pb & ~ES_MASK));
 }
 
-extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi);
+extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_lru_add(struct inode *inode);
 extern void ext4_es_lru_del(struct inode *inode);

fs/ext4/ialloc.c

@@ -1011,8 +1011,7 @@ got:
 	spin_unlock(&sbi->s_next_gen_lock);
 
 	/* Precompute checksum seed for inode metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+	if (ext4_has_metadata_csum(sb)) {
 		__u32 csum;
 		__le32 inum = cpu_to_le32(inode->i_ino);
 		__le32 gen = cpu_to_le32(inode->i_generation);

fs/ext4/indirect.c

@@ -318,34 +318,24 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
  *	ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
  *	as described above and return 0.
  */
-static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
-			     ext4_lblk_t iblock, int indirect_blks,
-			     int *blks, ext4_fsblk_t goal,
-			     ext4_lblk_t *offsets, Indirect *branch)
+static int ext4_alloc_branch(handle_t *handle,
+			     struct ext4_allocation_request *ar,
+			     int indirect_blks, ext4_lblk_t *offsets,
+			     Indirect *branch)
 {
-	struct ext4_allocation_request	ar;
 	struct buffer_head *		bh;
 	ext4_fsblk_t			b, new_blocks[4];
 	__le32				*p;
 	int				i, j, err, len = 1;
 
-	/*
-	 * Set up for the direct block allocation
-	 */
-	memset(&ar, 0, sizeof(ar));
-	ar.inode = inode;
-	ar.len = *blks;
-	ar.logical = iblock;
-	if (S_ISREG(inode->i_mode))
-		ar.flags = EXT4_MB_HINT_DATA;
-
 	for (i = 0; i <= indirect_blks; i++) {
 		if (i == indirect_blks) {
-			ar.goal = goal;
-			new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err);
+			new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err);
 		} else
-			goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode,
-							goal, 0, NULL, &err);
+			ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle,
+					ar->inode, ar->goal,
+					ar->flags & EXT4_MB_DELALLOC_RESERVED,
+					NULL, &err);
 		if (err) {
 			i--;
 			goto failed;
@@ -354,7 +344,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		if (i == 0)
 			continue;
 
-		bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]);
+		bh = branch[i].bh = sb_getblk(ar->inode->i_sb, new_blocks[i-1]);
 		if (unlikely(!bh)) {
 			err = -ENOMEM;
 			goto failed;
@@ -372,7 +362,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		b = new_blocks[i];
 
 		if (i == indirect_blks)
-			len = ar.len;
+			len = ar->len;
 		for (j = 0; j < len; j++)
 			*p++ = cpu_to_le32(b++);
 
@@ -381,11 +371,10 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		unlock_buffer(bh);
 
 		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		err = ext4_handle_dirty_metadata(handle, ar->inode, bh);
 		if (err)
 			goto failed;
 	}
-	*blks = ar.len;
 	return 0;
 failed:
 	for (; i >= 0; i--) {
@@ -396,10 +385,10 @@ failed:
 		 * existing before ext4_alloc_branch() was called.
 		 */
 		if (i > 0 && i != indirect_blks && branch[i].bh)
-			ext4_forget(handle, 1, inode, branch[i].bh,
+			ext4_forget(handle, 1, ar->inode, branch[i].bh,
 				    branch[i].bh->b_blocknr);
-		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
-				 (i == indirect_blks) ? ar.len : 1, 0);
+		ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i],
+				 (i == indirect_blks) ? ar->len : 1, 0);
 	}
 	return err;
 }
@@ -419,9 +408,9 @@ failed:
  * inode (->i_blocks, etc.). In case of success we end up with the full
  * chain to new block and return 0.
  */
-static int ext4_splice_branch(handle_t *handle, struct inode *inode,
-			      ext4_lblk_t block, Indirect *where, int num,
-			      int blks)
+static int ext4_splice_branch(handle_t *handle,
+			      struct ext4_allocation_request *ar,
+			      Indirect *where, int num)
 {
 	int i;
 	int err = 0;
@@ -446,9 +435,9 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	 * Update the host buffer_head or inode to point to more just allocated
 	 * direct blocks blocks
 	 */
-	if (num == 0 && blks > 1) {
+	if (num == 0 && ar->len > 1) {
 		current_block = le32_to_cpu(where->key) + 1;
-		for (i = 1; i < blks; i++)
+		for (i = 1; i < ar->len; i++)
 			*(where->p + i) = cpu_to_le32(current_block++);
 	}
 
@@ -465,14 +454,14 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 		 */
 		jbd_debug(5, "splicing indirect only\n");
 		BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
-		err = ext4_handle_dirty_metadata(handle, inode, where->bh);
+		err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh);
 		if (err)
 			goto err_out;
 	} else {
 		/*
 		 * OK, we spliced it into the inode itself on a direct block.
 		 */
-		ext4_mark_inode_dirty(handle, inode);
+		ext4_mark_inode_dirty(handle, ar->inode);
 		jbd_debug(5, "splicing direct\n");
 	}
 	return err;
@@ -484,11 +473,11 @@ err_out:
 		 * need to revoke the block, which is why we don't
 		 * need to set EXT4_FREE_BLOCKS_METADATA.
 		 */
-		ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+		ext4_free_blocks(handle, ar->inode, where[i].bh, 0, 1,
 				 EXT4_FREE_BLOCKS_FORGET);
 	}
-	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
-			 blks, 0);
+	ext4_free_blocks(handle, ar->inode, NULL, le32_to_cpu(where[num].key),
+			 ar->len, 0);
 
 	return err;
 }
@@ -525,11 +514,11 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map,
 			int flags)
 {
+	struct ext4_allocation_request ar;
 	int err = -EIO;
 	ext4_lblk_t offsets[4];
 	Indirect chain[4];
 	Indirect *partial;
-	ext4_fsblk_t goal;
 	int indirect_blks;
 	int blocks_to_boundary = 0;
 	int depth;
@@ -579,7 +568,16 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		return -ENOSPC;
 	}
 
-	goal = ext4_find_goal(inode, map->m_lblk, partial);
+	/* Set up for the direct block allocation */
+	memset(&ar, 0, sizeof(ar));
+	ar.inode = inode;
+	ar.logical = map->m_lblk;
+	if (S_ISREG(inode->i_mode))
+		ar.flags = EXT4_MB_HINT_DATA;
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ar.flags |= EXT4_MB_DELALLOC_RESERVED;
+
+	ar.goal = ext4_find_goal(inode, map->m_lblk, partial);
 
 	/* the number of blocks need to allocate for [d,t]indirect blocks */
 	indirect_blks = (chain + depth) - partial - 1;
@@ -588,13 +586,13 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	 * Next look up the indirect map to count the totoal number of
 	 * direct blocks to allocate for this branch.
 	 */
-	count = ext4_blks_to_allocate(partial, indirect_blks,
-				      map->m_len, blocks_to_boundary);
+	ar.len = ext4_blks_to_allocate(partial, indirect_blks,
+				       map->m_len, blocks_to_boundary);
+
 	/*
 	 * Block out ext4_truncate while we alter the tree
 	 */
-	err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
-				&count, goal,
+	err = ext4_alloc_branch(handle, &ar, indirect_blks,
 				offsets + (partial - chain), partial);
 
 	/*
@@ -605,14 +603,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	 * may need to return -EAGAIN upwards in the worst case.  --sct
 	 */
 	if (!err)
-		err = ext4_splice_branch(handle, inode, map->m_lblk,
-					 partial, indirect_blks, count);
+		err = ext4_splice_branch(handle, &ar, partial, indirect_blks);
 	if (err)
 		goto cleanup;
 
 	map->m_flags |= EXT4_MAP_NEW;
 
 	ext4_update_inode_fsync_trans(handle, inode, 1);
+	count = ar.len;
 got_it:
 	map->m_flags |= EXT4_MAP_MAPPED;
 	map->m_pblk = le32_to_cpu(chain[depth-1].key);

fs/ext4/inline.c

@@ -594,6 +594,7 @@ retry:
 	if (ret) {
 		unlock_page(page);
 		page_cache_release(page);
+		page = NULL;
 		ext4_orphan_add(handle, inode);
 		up_write(&EXT4_I(inode)->xattr_sem);
 		sem_held = 0;
@@ -613,7 +614,8 @@ retry:
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 
-	block_commit_write(page, from, to);
+	if (page)
+		block_commit_write(page, from, to);
 out:
 	if (page) {
 		unlock_page(page);
@@ -1126,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
 		inline_size - EXT4_INLINE_DOTDOT_SIZE);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	inode->i_size = inode->i_sb->s_blocksize;

fs/ext4/inode.c

@@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
 
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_LINUX) ||
-	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	    !ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	provided = le16_to_cpu(raw->i_checksum_lo);
@@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
 
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_LINUX) ||
-	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	    !ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	csum = ext4_inode_csum(inode, raw, ei);
@@ -224,16 +222,15 @@ void ext4_evict_inode(struct inode *inode)
 		goto no_delete;
 	}
 
-	if (!is_bad_inode(inode))
-		dquot_initialize(inode);
+	if (is_bad_inode(inode))
+		goto no_delete;
+	dquot_initialize(inode);
 
 	if (ext4_should_order_data(inode))
 		ext4_begin_ordered_truncate(inode, 0);
 	truncate_inode_pages_final(&inode->i_data);
 
 	WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
-	if (is_bad_inode(inode))
-		goto no_delete;
 
 	/*
 	 * Protect us against freezing - iput() caller didn't have to have any
@@ -590,19 +587,11 @@ found:
 	/*
 	 * New blocks allocate and/or writing to unwritten extent
 	 * will possibly result in updating i_data, so we take
-	 * the write lock of i_data_sem, and call get_blocks()
+	 * the write lock of i_data_sem, and call get_block()
 	 * with create == 1 flag.
 	 */
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	/*
-	 * if the caller is from delayed allocation writeout path
-	 * we have already reserved fs blocks for allocation
-	 * let the underlying get_block() function know to
-	 * avoid double accounting
-	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
-		ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 	/*
 	 * We need to check for EXT4 here because migrate
 	 * could have changed the inode type in between
@@ -631,8 +620,6 @@ found:
 			(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
 			ext4_da_update_reserve_space(inode, retval, 1);
 	}
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
-		ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
 	if (retval > 0) {
 		unsigned int status;
@@ -734,11 +721,11 @@ int ext4_get_block(struct inode *inode, sector_t iblock,
  * `handle' can be NULL if create is zero
  */
 struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
-				ext4_lblk_t block, int create, int *errp)
+				ext4_lblk_t block, int create)
 {
 	struct ext4_map_blocks map;
 	struct buffer_head *bh;
-	int fatal = 0, err;
+	int err;
 
 	J_ASSERT(handle != NULL || create == 0);
 
@@ -747,21 +734,14 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	err = ext4_map_blocks(handle, inode, &map,
 			      create ? EXT4_GET_BLOCKS_CREATE : 0);
 
-	/* ensure we send some value back into *errp */
-	*errp = 0;
-
-	if (create && err == 0)
-		err = -ENOSPC;	/* should never happen */
+	if (err == 0)
+		return create ? ERR_PTR(-ENOSPC) : NULL;
 	if (err < 0)
-		*errp = err;
-	if (err <= 0)
-		return NULL;
+		return ERR_PTR(err);
 
 	bh = sb_getblk(inode->i_sb, map.m_pblk);
-	if (unlikely(!bh)) {
-		*errp = -ENOMEM;
-		return NULL;
-	}
+	if (unlikely(!bh))
+		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
 		J_ASSERT(create != 0);
 		J_ASSERT(handle != NULL);
@@ -775,44 +755,44 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 		 */
 		lock_buffer(bh);
 		BUFFER_TRACE(bh, "call get_create_access");
-		fatal = ext4_journal_get_create_access(handle, bh);
-		if (!fatal && !buffer_uptodate(bh)) {
+		err = ext4_journal_get_create_access(handle, bh);
+		if (unlikely(err)) {
+			unlock_buffer(bh);
+			goto errout;
+		}
+		if (!buffer_uptodate(bh)) {
 			memset(bh->b_data, 0, inode->i_sb->s_blocksize);
 			set_buffer_uptodate(bh);
 		}
 		unlock_buffer(bh);
 		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 		err = ext4_handle_dirty_metadata(handle, inode, bh);
-		if (!fatal)
-			fatal = err;
-	} else {
+		if (unlikely(err))
+			goto errout;
+	} else
 		BUFFER_TRACE(bh, "not a new buffer");
-	}
-	if (fatal) {
-		*errp = fatal;
-		brelse(bh);
-		bh = NULL;
-	}
 	return bh;
+errout:
+	brelse(bh);
+	return ERR_PTR(err);
 }
 
 struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
-			       ext4_lblk_t block, int create, int *err)
+			       ext4_lblk_t block, int create)
 {
 	struct buffer_head *bh;
 
-	bh = ext4_getblk(handle, inode, block, create, err);
-	if (!bh)
+	bh = ext4_getblk(handle, inode, block, create);
+	if (IS_ERR(bh))
 		return bh;
-	if (buffer_uptodate(bh))
+	if (!bh || buffer_uptodate(bh))
 		return bh;
 	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
 	put_bh(bh);
-	*err = -EIO;
-	return NULL;
+	return ERR_PTR(-EIO);
 }
 
 int ext4_walk_page_buffers(handle_t *handle,
@@ -1536,7 +1516,7 @@ out_unlock:
 }
 
 /*
- * This is a special get_blocks_t callback which is used by
+ * This is a special get_block_t callback which is used by
  * ext4_da_write_begin().  It will either return mapped block or
  * reserve space for a single block.
  *
@@ -2011,12 +1991,10 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	 * in data loss.  So use reserved blocks to allocate metadata if
 	 * possible.
 	 *
-	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if the blocks
-	 * in question are delalloc blocks.  This affects functions in many
-	 * different parts of the allocation call path.  This flag exists
-	 * primarily because we don't want to change *many* call functions, so
-	 * ext4_map_blocks() will set the EXT4_STATE_DELALLOC_RESERVED flag
-	 * once the inode's allocation semaphore is taken.
+	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if
+	 * the blocks in question are delalloc blocks.  This indicates
+	 * that the blocks and quotas has already been checked when
+	 * the data was copied into the page cache.
 	 */
 	get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
 			   EXT4_GET_BLOCKS_METADATA_NOFAIL;
@@ -2515,6 +2493,20 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
+/* We always reserve for an inode update; the superblock could be there too */
+static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
+{
+	if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				EXT4_FEATURE_RO_COMPAT_LARGE_FILE)))
+		return 1;
+
+	if (pos + len <= 0x7fffffffULL)
+		return 1;
+
+	/* We might need to update the superblock to set LARGE_FILE */
+	return 2;
+}
+
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
@@ -2565,7 +2557,8 @@ retry_grab:
 	 * of file which has an already mapped buffer.
 	 */
 retry_journal:
-	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
+	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+				ext4_da_write_credits(inode, pos, len));
 	if (IS_ERR(handle)) {
 		page_cache_release(page);
 		return PTR_ERR(handle);
@@ -2658,10 +2651,7 @@ static int ext4_da_write_end(struct file *file,
 	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
 		if (ext4_has_inline_data(inode) ||
 		    ext4_da_should_update_i_disksize(page, end)) {
-			down_write(&EXT4_I(inode)->i_data_sem);
-			if (new_i_size > EXT4_I(inode)->i_disksize)
-				EXT4_I(inode)->i_disksize = new_i_size;
-			up_write(&EXT4_I(inode)->i_data_sem);
+			ext4_update_i_disksize(inode, new_i_size);
 			/* We need to mark inode dirty even if
 			 * new_i_size is less that inode->i_size
 			 * bu greater than i_disksize.(hint delalloc)
@@ -3936,8 +3926,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ei->i_extra_isize = 0;
 
 	/* Precompute checksum seed for inode metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+	if (ext4_has_metadata_csum(sb)) {
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 		__u32 csum;
 		__le32 inum = cpu_to_le32(inode->i_ino);
@@ -4127,6 +4116,13 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
+struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino)
+{
+	if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+		return ERR_PTR(-EIO);
+	return ext4_iget(sb, ino);
+}
+
 static int ext4_inode_blocks_set(handle_t *handle,
 				struct ext4_inode *raw_inode,
 				struct ext4_inode_info *ei)
@@ -4226,7 +4222,8 @@ static int ext4_do_update_inode(handle_t *handle,
 	EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
 	EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
 
-	if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
+	err = ext4_inode_blocks_set(handle, raw_inode, ei);
+	if (err) {
 		spin_unlock(&ei->i_raw_lock);
 		goto out_brelse;
 	}
@@ -4536,8 +4533,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_orphan_del(NULL, inode);
 				goto err_out;
 			}
-		} else
+		} else {
+			loff_t oldsize = inode->i_size;
+
 			i_size_write(inode, attr->ia_size);
+			pagecache_isize_extended(inode, oldsize, inode->i_size);
+		}
 
 		/*
 		 * Blocks are going to be removed from the inode. Wait

fs/ext4/ioctl.c

@@ -331,8 +331,7 @@ flags_out:
 		if (!inode_owner_or_capable(inode))
 			return -EPERM;
 
-		if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+		if (ext4_has_metadata_csum(inode->i_sb)) {
 			ext4_warning(sb, "Setting inode version is not "
 				     "supported with metadata_csum enabled.");
 			return -ENOTTY;
@@ -532,9 +531,17 @@ group_add_out:
 	}
 
 	case EXT4_IOC_SWAP_BOOT:
+	{
+		int err;
 		if (!(filp->f_mode & FMODE_WRITE))
 			return -EBADF;
-		return swap_inode_boot_loader(sb, inode);
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+		err = swap_inode_boot_loader(sb, inode);
+		mnt_drop_write_file(filp);
+		return err;
+	}
 
 	case EXT4_IOC_RESIZE_FS: {
 		ext4_fsblk_t n_blocks_count;

fs/ext4/mballoc.c

@@ -3155,9 +3155,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 			 "start %lu, size %lu, fe_logical %lu",
 			 (unsigned long) start, (unsigned long) size,
 			 (unsigned long) ac->ac_o_ex.fe_logical);
+		BUG();
 	}
-	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
-			start > ac->ac_o_ex.fe_logical);
 	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
@@ -4410,14 +4409,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	if (IS_NOQUOTA(ar->inode))
 		ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
 
-	/*
-	 * For delayed allocation, we could skip the ENOSPC and
-	 * EDQUOT check, as blocks and quotas have been already
-	 * reserved when data being copied into pagecache.
-	 */
-	if (ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED))
-		ar->flags |= EXT4_MB_DELALLOC_RESERVED;
-	else {
+	if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) {
 		/* Without delayed allocation we need to verify
 		 * there is enough free blocks to do block allocation
 		 * and verify allocation doesn't exceed the quota limits.
@@ -4528,8 +4520,7 @@ out:
 	if (inquota && ar->len < inquota)
 		dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
 	if (!ar->len) {
-		if (!ext4_test_inode_state(ar->inode,
-					   EXT4_STATE_DELALLOC_RESERVED))
+		if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0)
 			/* release all the reserved blocks if non delalloc */
 			percpu_counter_sub(&sbi->s_dirtyclusters_counter,
 						reserv_clstrs);

fs/ext4/migrate.c

@@ -41,8 +41,7 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	ext4_ext_store_pblock(&newext, lb->first_pblock);
 	/* Locking only for convinience since we are operating on temp inode */
 	down_write(&EXT4_I(inode)->i_data_sem);
-	path = ext4_ext_find_extent(inode, lb->first_block, NULL, 0);
-
+	path = ext4_find_extent(inode, lb->first_block, NULL, 0);
 	if (IS_ERR(path)) {
 		retval = PTR_ERR(path);
 		path = NULL;
@@ -81,13 +80,11 @@ static int finish_range(handle_t *handle, struct inode *inode,
 				goto err_out;
 		}
 	}
-	retval = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
+	retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0);
 err_out:
 	up_write((&EXT4_I(inode)->i_data_sem));
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
+	ext4_ext_drop_refs(path);
+	kfree(path);
 	lb->first_pblock = 0;
 	return retval;
 }

fs/ext4/mmp.c

@@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 
 static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
@@ -29,8 +28,7 @@ static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 
 static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);

fs/ext4/move_extent.c

@@ -27,120 +27,26 @@
  * @lblock:	logical block number to find an extent path
  * @path:	pointer to an extent path pointer (for output)
  *
- * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
+ * ext4_find_extent wrapper. Return 0 on success, or a negative error value
  * on failure.
  */
 static inline int
 get_ext_path(struct inode *inode, ext4_lblk_t lblock,
-		struct ext4_ext_path **orig_path)
+		struct ext4_ext_path **ppath)
 {
-	int ret = 0;
 	struct ext4_ext_path *path;
 
-	path = ext4_ext_find_extent(inode, lblock, *orig_path, EXT4_EX_NOCACHE);
+	path = ext4_find_extent(inode, lblock, ppath, EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
-		ret = PTR_ERR(path);
-	else if (path[ext_depth(inode)].p_ext == NULL)
-		ret = -ENODATA;
-	else
-		*orig_path = path;
-
-	return ret;
-}
-
-/**
- * copy_extent_status - Copy the extent's initialization status
- *
- * @src:	an extent for getting initialize status
- * @dest:	an extent to be set the status
- */
-static void
-copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
-{
-	if (ext4_ext_is_unwritten(src))
-		ext4_ext_mark_unwritten(dest);
-	else
-		dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
-}
-
-/**
- * mext_next_extent - Search for the next extent and set it to "extent"
- *
- * @inode:	inode which is searched
- * @path:	this will obtain data for the next extent
- * @extent:	pointer to the next extent we have just gotten
- *
- * Search the next extent in the array of ext4_ext_path structure (@path)
- * and set it to ext4_extent structure (@extent). In addition, the member of
- * @path (->p_ext) also points the next extent. Return 0 on success, 1 if
- * ext4_ext_path structure refers to the last extent, or a negative error
- * value on failure.
- */
-int
-mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
-		      struct ext4_extent **extent)
-{
-	struct ext4_extent_header *eh;
-	int ppos, leaf_ppos = path->p_depth;
-
-	ppos = leaf_ppos;
-	if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
-		/* leaf block */
-		*extent = ++path[ppos].p_ext;
-		path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
-		return 0;
-	}
-
-	while (--ppos >= 0) {
-		if (EXT_LAST_INDEX(path[ppos].p_hdr) >
-		    path[ppos].p_idx) {
-			int cur_ppos = ppos;
-
-			/* index block */
-			path[ppos].p_idx++;
-			path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
-			if (path[ppos+1].p_bh)
-				brelse(path[ppos+1].p_bh);
-			path[ppos+1].p_bh =
-				sb_bread(inode->i_sb, path[ppos].p_block);
-			if (!path[ppos+1].p_bh)
-				return -EIO;
-			path[ppos+1].p_hdr =
-				ext_block_hdr(path[ppos+1].p_bh);
-
-			/* Halfway index block */
-			while (++cur_ppos < leaf_ppos) {
-				path[cur_ppos].p_idx =
-					EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
-				path[cur_ppos].p_block =
-					ext4_idx_pblock(path[cur_ppos].p_idx);
-				if (path[cur_ppos+1].p_bh)
-					brelse(path[cur_ppos+1].p_bh);
-				path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
-					path[cur_ppos].p_block);
-				if (!path[cur_ppos+1].p_bh)
-					return -EIO;
-				path[cur_ppos+1].p_hdr =
-					ext_block_hdr(path[cur_ppos+1].p_bh);
-			}
-
-			path[leaf_ppos].p_ext = *extent = NULL;
-
-			eh = path[leaf_ppos].p_hdr;
-			if (le16_to_cpu(eh->eh_entries) == 0)
-				/* empty leaf is found */
-				return -ENODATA;
-
-			/* leaf block */
-			path[leaf_ppos].p_ext = *extent =
-				EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
-			path[leaf_ppos].p_block =
-					ext4_ext_pblock(path[leaf_ppos].p_ext);
-			return 0;
-		}
+		return PTR_ERR(path);
+	if (path[ext_depth(inode)].p_ext == NULL) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		*ppath = NULL;
+		return -ENODATA;
 	}
-	/* We found the last extent */
-	return 1;
+	*ppath = path;
+	return 0;
 }
 
 /**
@@ -177,417 +83,6 @@ ext4_double_up_write_data_sem(struct inode *orig_inode,
 	up_write(&EXT4_I(donor_inode)->i_data_sem);
 }
 
-/**
- * mext_insert_across_blocks - Insert extents across leaf block
- *
- * @handle:		journal handle
- * @orig_inode:		original inode
- * @o_start:		first original extent to be changed
- * @o_end:		last original extent to be changed
- * @start_ext:		first new extent to be inserted
- * @new_ext:		middle of new extent to be inserted
- * @end_ext:		last new extent to be inserted
- *
- * Allocate a new leaf block and insert extents into it. Return 0 on success,
- * or a negative error value on failure.
- */
-static int
-mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
-		struct ext4_extent *o_start, struct ext4_extent *o_end,
-		struct ext4_extent *start_ext, struct ext4_extent *new_ext,
-		struct ext4_extent *end_ext)
-{
-	struct ext4_ext_path *orig_path = NULL;
-	ext4_lblk_t eblock = 0;
-	int new_flag = 0;
-	int end_flag = 0;
-	int err = 0;
-
-	if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) {
-		if (o_start == o_end) {
-
-			/*       start_ext   new_ext    end_ext
-			 * donor |---------|-----------|--------|
-			 * orig  |------------------------------|
-			 */
-			end_flag = 1;
-		} else {
-
-			/*       start_ext   new_ext   end_ext
-			 * donor |---------|----------|---------|
-			 * orig  |---------------|--------------|
-			 */
-			o_end->ee_block = end_ext->ee_block;
-			o_end->ee_len = end_ext->ee_len;
-			ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
-		}
-
-		o_start->ee_len = start_ext->ee_len;
-		eblock = le32_to_cpu(start_ext->ee_block);
-		new_flag = 1;
-
-	} else if (start_ext->ee_len && new_ext->ee_len &&
-		   !end_ext->ee_len && o_start == o_end) {
-
-		/*	 start_ext	new_ext
-		 * donor |--------------|---------------|
-		 * orig  |------------------------------|
-		 */
-		o_start->ee_len = start_ext->ee_len;
-		eblock = le32_to_cpu(start_ext->ee_block);
-		new_flag = 1;
-
-	} else if (!start_ext->ee_len && new_ext->ee_len &&
-		   end_ext->ee_len && o_start == o_end) {
-
-		/*	  new_ext	end_ext
-		 * donor |--------------|---------------|
-		 * orig  |------------------------------|
-		 */
-		o_end->ee_block = end_ext->ee_block;
-		o_end->ee_len = end_ext->ee_len;
-		ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
-
-		/*
-		 * Set 0 to the extent block if new_ext was
-		 * the first block.
-		 */
-		if (new_ext->ee_block)
-			eblock = le32_to_cpu(new_ext->ee_block);
-
-		new_flag = 1;
-	} else {
-		ext4_debug("ext4 move extent: Unexpected insert case\n");
-		return -EIO;
-	}
-
-	if (new_flag) {
-		err = get_ext_path(orig_inode, eblock, &orig_path);
-		if (err)
-			goto out;
-
-		if (ext4_ext_insert_extent(handle, orig_inode,
-					orig_path, new_ext, 0))
-			goto out;
-	}
-
-	if (end_flag) {
-		err = get_ext_path(orig_inode,
-				le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
-		if (err)
-			goto out;
-
-		if (ext4_ext_insert_extent(handle, orig_inode,
-					   orig_path, end_ext, 0))
-			goto out;
-	}
-out:
-	if (orig_path) {
-		ext4_ext_drop_refs(orig_path);
-		kfree(orig_path);
-	}
-
-	return err;
-
-}
-
-/**
- * mext_insert_inside_block - Insert new extent to the extent block
- *
- * @o_start:		first original extent to be moved
- * @o_end:		last original extent to be moved
- * @start_ext:		first new extent to be inserted
- * @new_ext:		middle of new extent to be inserted
- * @end_ext:		last new extent to be inserted
- * @eh:			extent header of target leaf block
- * @range_to_move:	used to decide how to insert extent
- *
- * Insert extents into the leaf block. The extent (@o_start) is overwritten
- * by inserted extents.
- */
-static void
-mext_insert_inside_block(struct ext4_extent *o_start,
-			      struct ext4_extent *o_end,
-			      struct ext4_extent *start_ext,
-			      struct ext4_extent *new_ext,
-			      struct ext4_extent *end_ext,
-			      struct ext4_extent_header *eh,
-			      int range_to_move)
-{
-	int i = 0;
-	unsigned long len;
-
-	/* Move the existing extents */
-	if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) {
-		len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) -
-			(unsigned long)(o_end + 1);
-		memmove(o_end + 1 + range_to_move, o_end + 1, len);
-	}
-
-	/* Insert start entry */
-	if (start_ext->ee_len)
-		o_start[i++].ee_len = start_ext->ee_len;
-
-	/* Insert new entry */
-	if (new_ext->ee_len) {
-		o_start[i] = *new_ext;
-		ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
-	}
-
-	/* Insert end entry */
-	if (end_ext->ee_len)
-		o_start[i] = *end_ext;
-
-	/* Increment the total entries counter on the extent block */
-	le16_add_cpu(&eh->eh_entries, range_to_move);
-}
-
-/**
- * mext_insert_extents - Insert new extent
- *
- * @handle:	journal handle
- * @orig_inode:	original inode
- * @orig_path:	path indicates first extent to be changed
- * @o_start:	first original extent to be changed
- * @o_end:	last original extent to be changed
- * @start_ext:	first new extent to be inserted
- * @new_ext:	middle of new extent to be inserted
- * @end_ext:	last new extent to be inserted
- *
- * Call the function to insert extents. If we cannot add more extents into
- * the leaf block, we call mext_insert_across_blocks() to create a
- * new leaf block. Otherwise call mext_insert_inside_block(). Return 0
- * on success, or a negative error value on failure.
- */
-static int
-mext_insert_extents(handle_t *handle, struct inode *orig_inode,
-			 struct ext4_ext_path *orig_path,
-			 struct ext4_extent *o_start,
-			 struct ext4_extent *o_end,
-			 struct ext4_extent *start_ext,
-			 struct ext4_extent *new_ext,
-			 struct ext4_extent *end_ext)
-{
-	struct  ext4_extent_header *eh;
-	unsigned long need_slots, slots_range;
-	int	range_to_move, depth, ret;
-
-	/*
-	 * The extents need to be inserted
-	 * start_extent + new_extent + end_extent.
-	 */
-	need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) +
-		(new_ext->ee_len ? 1 : 0);
-
-	/* The number of slots between start and end */
-	slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1)
-		/ sizeof(struct ext4_extent);
-
-	/* Range to move the end of extent */
-	range_to_move = need_slots - slots_range;
-	depth = orig_path->p_depth;
-	orig_path += depth;
-	eh = orig_path->p_hdr;
-
-	if (depth) {
-		/* Register to journal */
-		BUFFER_TRACE(orig_path->p_bh, "get_write_access");
-		ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
-		if (ret)
-			return ret;
-	}
-
-	/* Expansion */
-	if (range_to_move > 0 &&
-		(range_to_move > le16_to_cpu(eh->eh_max)
-			- le16_to_cpu(eh->eh_entries))) {
-
-		ret = mext_insert_across_blocks(handle, orig_inode, o_start,
-					o_end, start_ext, new_ext, end_ext);
-		if (ret < 0)
-			return ret;
-	} else
-		mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
-						end_ext, eh, range_to_move);
-
-	return ext4_ext_dirty(handle, orig_inode, orig_path);
-}
-
-/**
- * mext_leaf_block - Move one leaf extent block into the inode.
- *
- * @handle:		journal handle
- * @orig_inode:		original inode
- * @orig_path:		path indicates first extent to be changed
- * @dext:		donor extent
- * @from:		start offset on the target file
- *
- * In order to insert extents into the leaf block, we must divide the extent
- * in the leaf block into three extents. The one is located to be inserted
- * extents, and the others are located around it.
- *
- * Therefore, this function creates structures to save extents of the leaf
- * block, and inserts extents by calling mext_insert_extents() with
- * created extents. Return 0 on success, or a negative error value on failure.
- */
-static int
-mext_leaf_block(handle_t *handle, struct inode *orig_inode,
-		     struct ext4_ext_path *orig_path, struct ext4_extent *dext,
-		     ext4_lblk_t *from)
-{
-	struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
-	struct ext4_extent new_ext, start_ext, end_ext;
-	ext4_lblk_t new_ext_end;
-	int oext_alen, new_ext_alen, end_ext_alen;
-	int depth = ext_depth(orig_inode);
-	int ret;
-
-	start_ext.ee_block = end_ext.ee_block = 0;
-	o_start = o_end = oext = orig_path[depth].p_ext;
-	oext_alen = ext4_ext_get_actual_len(oext);
-	start_ext.ee_len = end_ext.ee_len = 0;
-
-	new_ext.ee_block = cpu_to_le32(*from);
-	ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
-	new_ext.ee_len = dext->ee_len;
-	new_ext_alen = ext4_ext_get_actual_len(&new_ext);
-	new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
-
-	/*
-	 * Case: original extent is first
-	 * oext      |--------|
-	 * new_ext      |--|
-	 * start_ext |--|
-	 */
-	if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) &&
-		le32_to_cpu(new_ext.ee_block) <
-		le32_to_cpu(oext->ee_block) + oext_alen) {
-		start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
-					       le32_to_cpu(oext->ee_block));
-		start_ext.ee_block = oext->ee_block;
-		copy_extent_status(oext, &start_ext);
-	} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
-		prev_ext = oext - 1;
-		/*
-		 * We can merge new_ext into previous extent,
-		 * if these are contiguous and same extent type.
-		 */
-		if (ext4_can_extents_be_merged(orig_inode, prev_ext,
-					       &new_ext)) {
-			o_start = prev_ext;
-			start_ext.ee_len = cpu_to_le16(
-				ext4_ext_get_actual_len(prev_ext) +
-				new_ext_alen);
-			start_ext.ee_block = oext->ee_block;
-			copy_extent_status(prev_ext, &start_ext);
-			new_ext.ee_len = 0;
-		}
-	}
-
-	/*
-	 * Case: new_ext_end must be less than oext
-	 * oext      |-----------|
-	 * new_ext       |-------|
-	 */
-	if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
-		EXT4_ERROR_INODE(orig_inode,
-			"new_ext_end(%u) should be less than or equal to "
-			"oext->ee_block(%u) + oext_alen(%d) - 1",
-			new_ext_end, le32_to_cpu(oext->ee_block),
-			oext_alen);
-		ret = -EIO;
-		goto out;
-	}
-
-	/*
-	 * Case: new_ext is smaller than original extent
-	 * oext    |---------------|
-	 * new_ext |-----------|
-	 * end_ext             |---|
-	 */
-	if (le32_to_cpu(oext->ee_block) <= new_ext_end &&
-		new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) {
-		end_ext.ee_len =
-			cpu_to_le16(le32_to_cpu(oext->ee_block) +
-			oext_alen - 1 - new_ext_end);
-		copy_extent_status(oext, &end_ext);
-		end_ext_alen = ext4_ext_get_actual_len(&end_ext);
-		ext4_ext_store_pblock(&end_ext,
-			(ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
-		end_ext.ee_block =
-			cpu_to_le32(le32_to_cpu(o_end->ee_block) +
-			oext_alen - end_ext_alen);
-	}
-
-	ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
-				o_end, &start_ext, &new_ext, &end_ext);
-out:
-	return ret;
-}
-
-/**
- * mext_calc_swap_extents - Calculate extents for extent swapping.
- *
- * @tmp_dext:		the extent that will belong to the original inode
- * @tmp_oext:		the extent that will belong to the donor inode
- * @orig_off:		block offset of original inode
- * @donor_off:		block offset of donor inode
- * @max_count:		the maximum length of extents
- *
- * Return 0 on success, or a negative error value on failure.
- */
-static int
-mext_calc_swap_extents(struct ext4_extent *tmp_dext,
-			      struct ext4_extent *tmp_oext,
-			      ext4_lblk_t orig_off, ext4_lblk_t donor_off,
-			      ext4_lblk_t max_count)
-{
-	ext4_lblk_t diff, orig_diff;
-	struct ext4_extent dext_old, oext_old;
-
-	BUG_ON(orig_off != donor_off);
-
-	/* original and donor extents have to cover the same block offset */
-	if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
-	    le32_to_cpu(tmp_oext->ee_block) +
-			ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
-		return -ENODATA;
-
-	if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
-	    le32_to_cpu(tmp_dext->ee_block) +
-			ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
-		return -ENODATA;
-
-	dext_old = *tmp_dext;
-	oext_old = *tmp_oext;
-
-	/* When tmp_dext is too large, pick up the target range. */
-	diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
-
-	ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + 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);
-
-	orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
-	ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
-
-	/* Adjust extent length if donor extent is larger than orig */
-	if (ext4_ext_get_actual_len(tmp_dext) >
-	    ext4_ext_get_actual_len(tmp_oext) - orig_diff)
-		tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) -
-						orig_diff);
-
-	tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext));
-
-	copy_extent_status(&oext_old, tmp_dext);
-	copy_extent_status(&dext_old, tmp_oext);
-
-	return 0;
-}
-
 /**
  * mext_check_coverage - Check that all extents in range has the same type
  *
@@ -619,171 +114,25 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
 	}
 	ret = 1;
 out:
-	if (path) {
-		ext4_ext_drop_refs(path);
-		kfree(path);
-	}
+	ext4_ext_drop_refs(path);
+	kfree(path);
 	return ret;
 }
 
-/**
- * mext_replace_branches - Replace original extents with new extents
- *
- * @handle:		journal handle
- * @orig_inode:		original inode
- * @donor_inode:	donor inode
- * @from:		block offset of orig_inode
- * @count:		block count to be replaced
- * @err:		pointer to save return value
- *
- * Replace original inode extents and donor inode extents page by page.
- * We implement this replacement in the following three steps:
- * 1. Save the block information of original and donor inodes into
- *    dummy extents.
- * 2. Change the block information of original inode to point at the
- *    donor inode blocks.
- * 3. Change the block information of donor inode to point at the saved
- *    original inode blocks in the dummy extents.
- *
- * Return replaced block count.
- */
-static int
-mext_replace_branches(handle_t *handle, struct inode *orig_inode,
-			   struct inode *donor_inode, ext4_lblk_t from,
-			   ext4_lblk_t count, int *err)
-{
-	struct ext4_ext_path *orig_path = NULL;
-	struct ext4_ext_path *donor_path = NULL;
-	struct ext4_extent *oext, *dext;
-	struct ext4_extent tmp_dext, tmp_oext;
-	ext4_lblk_t orig_off = from, donor_off = from;
-	int depth;
-	int replaced_count = 0;
-	int dext_alen;
-
-	*err = ext4_es_remove_extent(orig_inode, from, count);
-	if (*err)
-		goto out;
-
-	*err = ext4_es_remove_extent(donor_inode, from, count);
-	if (*err)
-		goto out;
-
-	/* Get the original extent for the block "orig_off" */
-	*err = get_ext_path(orig_inode, orig_off, &orig_path);
-	if (*err)
-		goto out;
-
-	/* Get the donor extent for the head */
-	*err = get_ext_path(donor_inode, donor_off, &donor_path);
-	if (*err)
-		goto out;
-	depth = ext_depth(orig_inode);
-	oext = orig_path[depth].p_ext;
-	tmp_oext = *oext;
-
-	depth = ext_depth(donor_inode);
-	dext = donor_path[depth].p_ext;
-	if (unlikely(!dext))
-		goto missing_donor_extent;
-	tmp_dext = *dext;
-
-	*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
-				      donor_off, count);
-	if (*err)
-		goto out;
-
-	/* Loop for the donor extents */
-	while (1) {
-		/* The extent for donor must be found. */
-		if (unlikely(!dext)) {
-		missing_donor_extent:
-			EXT4_ERROR_INODE(donor_inode,
-				   "The extent for donor must be found");
-			*err = -EIO;
-			goto out;
-		} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
-			EXT4_ERROR_INODE(donor_inode,
-				"Donor offset(%u) and the first block of donor "
-				"extent(%u) should be equal",
-				donor_off,
-				le32_to_cpu(tmp_dext.ee_block));
-			*err = -EIO;
-			goto out;
-		}
-
-		/* Set donor extent to orig extent */
-		*err = mext_leaf_block(handle, orig_inode,
-					   orig_path, &tmp_dext, &orig_off);
-		if (*err)
-			goto out;
-
-		/* Set orig extent to donor extent */
-		*err = mext_leaf_block(handle, donor_inode,
-					   donor_path, &tmp_oext, &donor_off);
-		if (*err)
-			goto out;
-
-		dext_alen = ext4_ext_get_actual_len(&tmp_dext);
-		replaced_count += dext_alen;
-		donor_off += dext_alen;
-		orig_off += dext_alen;
-
-		BUG_ON(replaced_count > count);
-		/* Already moved the expected blocks */
-		if (replaced_count >= count)
-			break;
-
-		if (orig_path)
-			ext4_ext_drop_refs(orig_path);
-		*err = get_ext_path(orig_inode, orig_off, &orig_path);
-		if (*err)
-			goto out;
-		depth = ext_depth(orig_inode);
-		oext = orig_path[depth].p_ext;
-		tmp_oext = *oext;
-
-		if (donor_path)
-			ext4_ext_drop_refs(donor_path);
-		*err = get_ext_path(donor_inode, donor_off, &donor_path);
-		if (*err)
-			goto out;
-		depth = ext_depth(donor_inode);
-		dext = donor_path[depth].p_ext;
-		tmp_dext = *dext;
-
-		*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
-					   donor_off, count - replaced_count);
-		if (*err)
-			goto out;
-	}
-
-out:
-	if (orig_path) {
-		ext4_ext_drop_refs(orig_path);
-		kfree(orig_path);
-	}
-	if (donor_path) {
-		ext4_ext_drop_refs(donor_path);
-		kfree(donor_path);
-	}
-
-	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
+ * @index1:	page index
+ * @index2:	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])
+		      pgoff_t index1, pgoff_t index2, struct page *page[2])
 {
 	struct address_space *mapping[2];
 	unsigned fl = AOP_FLAG_NOFS;
@@ -793,15 +142,18 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 		mapping[0] = inode1->i_mapping;
 		mapping[1] = inode2->i_mapping;
 	} else {
+		pgoff_t tmp = index1;
+		index1 = index2;
+		index2 = tmp;
 		mapping[0] = inode2->i_mapping;
 		mapping[1] = inode1->i_mapping;
 	}
 
-	page[0] = grab_cache_page_write_begin(mapping[0], index, fl);
+	page[0] = grab_cache_page_write_begin(mapping[0], index1, fl);
 	if (!page[0])
 		return -ENOMEM;
 
-	page[1] = grab_cache_page_write_begin(mapping[1], index, fl);
+	page[1] = grab_cache_page_write_begin(mapping[1], index2, fl);
 	if (!page[1]) {
 		unlock_page(page[0]);
 		page_cache_release(page[0]);
@@ -893,25 +245,27 @@ out:
  * @o_filp:			file structure of original file
  * @donor_inode:		donor inode
  * @orig_page_offset:		page index on original file
+ * @donor_page_offset:		page index on donor file
  * @data_offset_in_page:	block index where data swapping starts
  * @block_len_in_page:		the number of blocks to be swapped
  * @unwritten:			orig extent is unwritten or not
  * @err:			pointer to save return value
  *
  * Save the data in original inode blocks and replace original inode extents
- * with donor inode extents by calling mext_replace_branches().
+ * with donor inode extents by calling ext4_swap_extents().
  * Finally, write out the saved data in new original inode blocks. Return
  * replaced block count.
  */
 static int
 move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
-		  pgoff_t orig_page_offset, int data_offset_in_page,
-		  int block_len_in_page, int unwritten, int *err)
+		     pgoff_t orig_page_offset, pgoff_t donor_page_offset,
+		     int data_offset_in_page,
+		     int block_len_in_page, int unwritten, int *err)
 {
 	struct inode *orig_inode = file_inode(o_filp);
 	struct page *pagep[2] = {NULL, NULL};
 	handle_t *handle;
-	ext4_lblk_t orig_blk_offset;
+	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int w_flags = 0;
 	unsigned int tmp_data_size, data_size, replaced_size;
@@ -939,6 +293,9 @@ again:
 	orig_blk_offset = orig_page_offset * blocks_per_page +
 		data_offset_in_page;
 
+	donor_blk_offset = donor_page_offset * blocks_per_page +
+		data_offset_in_page;
+
 	/* Calculate data_size */
 	if ((orig_blk_offset + block_len_in_page - 1) ==
 	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
@@ -959,7 +316,7 @@ again:
 	replaced_size = data_size;
 
 	*err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
-				     pagep);
+				     donor_page_offset, pagep);
 	if (unlikely(*err < 0))
 		goto stop_journal;
 	/*
@@ -978,7 +335,7 @@ again:
 		if (*err)
 			goto drop_data_sem;
 
-		unwritten &= mext_check_coverage(donor_inode, orig_blk_offset,
+		unwritten &= mext_check_coverage(donor_inode, donor_blk_offset,
 						 block_len_in_page, 1, err);
 		if (*err)
 			goto drop_data_sem;
@@ -994,9 +351,10 @@ again:
 			*err = -EBUSY;
 			goto drop_data_sem;
 		}
-		replaced_count = mext_replace_branches(handle, orig_inode,
-						donor_inode, orig_blk_offset,
-						block_len_in_page, err);
+		replaced_count = ext4_swap_extents(handle, orig_inode,
+						   donor_inode, orig_blk_offset,
+						   donor_blk_offset,
+						   block_len_in_page, 1, err);
 	drop_data_sem:
 		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		goto unlock_pages;
@@ -1014,9 +372,9 @@ data_copy:
 		goto unlock_pages;
 	}
 	ext4_double_down_write_data_sem(orig_inode, donor_inode);
-	replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
-					       orig_blk_offset,
-					       block_len_in_page, err);
+	replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode,
+					       orig_blk_offset, donor_blk_offset,
+					   block_len_in_page, 1, err);
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	if (*err) {
 		if (replaced_count) {
@@ -1061,9 +419,9 @@ repair_branches:
 	 * Try to swap extents to it's original places
 	 */
 	ext4_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);
+	replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode,
+					       orig_blk_offset, donor_blk_offset,
+					   block_len_in_page, 0, &err2);
 	ext4_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),
@@ -1093,10 +451,14 @@ mext_check_arguments(struct inode *orig_inode,
 		     struct inode *donor_inode, __u64 orig_start,
 		     __u64 donor_start, __u64 *len)
 {
-	ext4_lblk_t orig_blocks, donor_blocks;
+	__u64 orig_eof, donor_eof;
 	unsigned int blkbits = orig_inode->i_blkbits;
 	unsigned int blocksize = 1 << blkbits;
 
+	orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits;
+	donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits;
+
+
 	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
 		ext4_debug("ext4 move extent: suid or sgid is set"
 			   " to donor file [ino:orig %lu, donor %lu]\n",
@@ -1112,7 +474,7 @@ mext_check_arguments(struct inode *orig_inode,
 		ext4_debug("ext4 move extent: The argument files should "
 			"not be swapfile [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
+		return -EBUSY;
 	}
 
 	/* Ext4 move extent supports only extent based file */
@@ -1132,67 +494,28 @@ mext_check_arguments(struct inode *orig_inode,
 	}
 
 	/* Start offset should be same */
-	if (orig_start != donor_start) {
+	if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
+	    (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
 		ext4_debug("ext4 move extent: orig and donor's start "
-			"offset are not same [ino:orig %lu, donor %lu]\n",
+			"offset are not alligned [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
 
 	if ((orig_start >= EXT_MAX_BLOCKS) ||
+	    (donor_start >= EXT_MAX_BLOCKS) ||
 	    (*len > EXT_MAX_BLOCKS) ||
+	    (donor_start + *len >= EXT_MAX_BLOCKS) ||
 	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
 		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
 			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
-
-	if (orig_inode->i_size > donor_inode->i_size) {
-		donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits;
-		/* TODO: eliminate this artificial restriction */
-		if (orig_start >= donor_blocks) {
-			ext4_debug("ext4 move extent: orig start offset "
-			"[%llu] should be less than donor file blocks "
-			"[%u] [ino:orig %lu, donor %lu]\n",
-			orig_start, donor_blocks,
-			orig_inode->i_ino, donor_inode->i_ino);
-			return -EINVAL;
-		}
-
-		/* TODO: eliminate this artificial restriction */
-		if (orig_start + *len > donor_blocks) {
-			ext4_debug("ext4 move extent: End offset [%llu] should "
-				"be less than donor file blocks [%u]."
-				"So adjust length from %llu to %llu "
-				"[ino:orig %lu, donor %lu]\n",
-				orig_start + *len, donor_blocks,
-				*len, donor_blocks - orig_start,
-				orig_inode->i_ino, donor_inode->i_ino);
-			*len = donor_blocks - orig_start;
-		}
-	} else {
-		orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits;
-		if (orig_start >= orig_blocks) {
-			ext4_debug("ext4 move extent: start offset [%llu] "
-				"should be less than original file blocks "
-				"[%u] [ino:orig %lu, donor %lu]\n",
-				 orig_start, orig_blocks,
-				orig_inode->i_ino, donor_inode->i_ino);
-			return -EINVAL;
-		}
-
-		if (orig_start + *len > orig_blocks) {
-			ext4_debug("ext4 move extent: Adjust length "
-				"from %llu to %llu. Because it should be "
-				"less than original file blocks "
-				"[ino:orig %lu, donor %lu]\n",
-				*len, orig_blocks - orig_start,
-				orig_inode->i_ino, donor_inode->i_ino);
-			*len = orig_blocks - orig_start;
-		}
-	}
-
+	if (orig_eof < orig_start + *len - 1)
+		*len = orig_eof - orig_start;
+	if (donor_eof < donor_start + *len - 1)
+		*len = donor_eof - donor_start;
 	if (!*len) {
 		ext4_debug("ext4 move extent: len should not be 0 "
 			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
@@ -1208,60 +531,26 @@ mext_check_arguments(struct inode *orig_inode,
  *
  * @o_filp:		file structure of the original file
  * @d_filp:		file structure of the donor file
- * @orig_start:		start offset in block for orig
- * @donor_start:	start offset in block for donor
+ * @orig_blk:		start offset in block for orig
+ * @donor_blk:		start offset in block for donor
  * @len:		the number of blocks to be moved
  * @moved_len:		moved block length
  *
  * This function returns 0 and moved block length is set in moved_len
  * if succeed, otherwise returns error value.
  *
- * Note: ext4_move_extents() proceeds the following order.
- * 1:ext4_move_extents() calculates the last block number of moving extent
- *   function by the start block number (orig_start) and the number of blocks
- *   to be moved (len) specified as arguments.
- *   If the {orig, donor}_start points a hole, the extent's start offset
- *   pointed by ext_cur (current extent), holecheck_path, orig_path are set
- *   after hole behind.
- * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent
- *   or the ext_cur exceeds the block_end which is last logical block number.
- * 3:To get the length of continues area, call mext_next_extent()
- *   specified with the ext_cur (initial value is holecheck_path) re-cursive,
- *   until find un-continuous extent, the start logical block number exceeds
- *   the block_end or the extent points to the last extent.
- * 4:Exchange the original inode data with donor inode data
- *   from orig_page_offset to seq_end_page.
- *   The start indexes of data are specified as arguments.
- *   That of the original inode is orig_page_offset,
- *   and the donor inode is also orig_page_offset
- *   (To easily handle blocksize != pagesize case, the offset for the
- *   donor inode is block unit).
- * 5:Update holecheck_path and orig_path to points a next proceeding extent,
- *   then returns to step 2.
- * 6:Release holecheck_path, orig_path and set the len to moved_len
- *   which shows the number of moved blocks.
- *   The moved_len is useful for the command to calculate the file offset
- *   for starting next move extent ioctl.
- * 7:Return 0 on success, or a negative error value on failure.
  */
 int
-ext4_move_extents(struct file *o_filp, struct file *d_filp,
-		 __u64 orig_start, __u64 donor_start, __u64 len,
-		 __u64 *moved_len)
+ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
+		  __u64 donor_blk, __u64 len, __u64 *moved_len)
 {
 	struct inode *orig_inode = file_inode(o_filp);
 	struct inode *donor_inode = file_inode(d_filp);
-	struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL;
-	struct ext4_extent *ext_prev, *ext_cur, *ext_dummy;
-	ext4_lblk_t block_start = orig_start;
-	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 ret, depth, last_extent = 0;
+	struct ext4_ext_path *path = NULL;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
-	int data_offset_in_page;
-	int block_len_in_page;
-	int unwritten;
+	ext4_lblk_t o_end, o_start = orig_blk;
+	ext4_lblk_t d_start = donor_blk;
+	int ret;
 
 	if (orig_inode->i_sb != donor_inode->i_sb) {
 		ext4_debug("ext4 move extent: The argument files "
@@ -1303,121 +592,58 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 	/* Protect extent tree against block allocations via delalloc */
 	ext4_double_down_write_data_sem(orig_inode, donor_inode);
 	/* Check the filesystem environment whether move_extent can be done */
-	ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
-				    donor_start, &len);
+	ret = mext_check_arguments(orig_inode, donor_inode, orig_blk,
+				    donor_blk, &len);
 	if (ret)
 		goto out;
+	o_end = o_start + len;
 
-	file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
-	block_end = block_start + len - 1;
-	if (file_end < block_end)
-		len -= block_end - file_end;
+	while (o_start < o_end) {
+		struct ext4_extent *ex;
+		ext4_lblk_t cur_blk, next_blk;
+		pgoff_t orig_page_index, donor_page_index;
+		int offset_in_page;
+		int unwritten, cur_len;
 
-	ret = get_ext_path(orig_inode, block_start, &orig_path);
-	if (ret)
-		goto out;
-
-	/* Get path structure to check the hole */
-	ret = get_ext_path(orig_inode, block_start, &holecheck_path);
-	if (ret)
-		goto out;
-
-	depth = ext_depth(orig_inode);
-	ext_cur = holecheck_path[depth].p_ext;
-
-	/*
-	 * Get proper starting location of block replacement if block_start was
-	 * within the hole.
-	 */
-	if (le32_to_cpu(ext_cur->ee_block) +
-		ext4_ext_get_actual_len(ext_cur) - 1 < block_start) {
-		/*
-		 * The hole exists between extents or the tail of
-		 * original file.
-		 */
-		last_extent = mext_next_extent(orig_inode,
-					holecheck_path, &ext_cur);
-		if (last_extent < 0) {
-			ret = last_extent;
-			goto out;
-		}
-		last_extent = mext_next_extent(orig_inode, orig_path,
-							&ext_dummy);
-		if (last_extent < 0) {
-			ret = last_extent;
+		ret = get_ext_path(orig_inode, o_start, &path);
+		if (ret)
 			goto out;
-		}
-		seq_start = le32_to_cpu(ext_cur->ee_block);
-	} else if (le32_to_cpu(ext_cur->ee_block) > block_start)
-		/* The hole exists at the beginning of original file. */
-		seq_start = le32_to_cpu(ext_cur->ee_block);
-	else
-		seq_start = block_start;
-
-	/* No blocks within the specified range. */
-	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");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* Adjust start blocks */
-	add_blocks = min(le32_to_cpu(ext_cur->ee_block) +
-			 ext4_ext_get_actual_len(ext_cur), block_end + 1) -
-		     max(le32_to_cpu(ext_cur->ee_block), block_start);
-
-	while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) {
-		seq_blocks += add_blocks;
-
-		/* Adjust tail blocks */
-		if (seq_start + seq_blocks - 1 > block_end)
-			seq_blocks = block_end - seq_start + 1;
-
-		ext_prev = ext_cur;
-		last_extent = mext_next_extent(orig_inode, holecheck_path,
-						&ext_cur);
-		if (last_extent < 0) {
-			ret = last_extent;
-			break;
-		}
-		add_blocks = ext4_ext_get_actual_len(ext_cur);
-
-		/*
-		 * Extend the length of contiguous block (seq_blocks)
-		 * if extents are contiguous.
-		 */
-		if (ext4_can_extents_be_merged(orig_inode,
-					       ext_prev, ext_cur) &&
-		    block_end >= le32_to_cpu(ext_cur->ee_block) &&
-		    !last_extent)
+		ex = path[path->p_depth].p_ext;
+		next_blk = ext4_ext_next_allocated_block(path);
+		cur_blk = le32_to_cpu(ex->ee_block);
+		cur_len = ext4_ext_get_actual_len(ex);
+		/* Check hole before the start pos */
+		if (cur_blk + cur_len - 1 < o_start) {
+			if (next_blk == EXT_MAX_BLOCKS) {
+				o_start = o_end;
+				ret = -ENODATA;
+				goto out;
+			}
+			d_start += next_blk - o_start;
+			o_start = next_blk;
 			continue;
-
-		/* Is original extent is unwritten */
-		unwritten = ext4_ext_is_unwritten(ext_prev);
-
-		data_offset_in_page = seq_start % blocks_per_page;
-
-		/*
-		 * Calculate data blocks count that should be swapped
-		 * at the first page.
-		 */
-		if (data_offset_in_page + seq_blocks > blocks_per_page) {
-			/* Swapped blocks are across pages */
-			block_len_in_page =
-					blocks_per_page - data_offset_in_page;
-		} else {
-			/* Swapped blocks are in a page */
-			block_len_in_page = seq_blocks;
+		/* Check hole after the start pos */
+		} else if (cur_blk > o_start) {
+			/* Skip hole */
+			d_start += cur_blk - o_start;
+			o_start = cur_blk;
+			/* Extent inside requested range ?*/
+			if (cur_blk >= o_end)
+				goto out;
+		} else { /* in_range(o_start, o_blk, o_len) */
+			cur_len += cur_blk - o_start;
 		}
-
-		orig_page_offset = seq_start >>
-				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
-		seq_end_page = (seq_start + seq_blocks - 1) >>
-				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
-		seq_start = le32_to_cpu(ext_cur->ee_block);
-		rest_blocks = seq_blocks;
-
+		unwritten = ext4_ext_is_unwritten(ex);
+		if (o_end - o_start < cur_len)
+			cur_len = o_end - o_start;
+
+		orig_page_index = o_start >> (PAGE_CACHE_SHIFT -
+					       orig_inode->i_blkbits);
+		donor_page_index = d_start >> (PAGE_CACHE_SHIFT -
+					       donor_inode->i_blkbits);
+		offset_in_page = o_start % blocks_per_page;
+		if (cur_len > blocks_per_page- offset_in_page)
+			cur_len = blocks_per_page - offset_in_page;
 		/*
 		 * Up semaphore to avoid following problems:
 		 * a. transaction deadlock among ext4_journal_start,
@@ -1426,77 +652,29 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		 *    in move_extent_per_page
 		 */
 		ext4_double_up_write_data_sem(orig_inode, donor_inode);
-
-		while (orig_page_offset <= seq_end_page) {
-
-			/* Swap original branches with new branches */
-			block_len_in_page = move_extent_per_page(
-						o_filp, donor_inode,
-						orig_page_offset,
-						data_offset_in_page,
-						block_len_in_page,
-						unwritten, &ret);
-
-			/* Count how many blocks we have exchanged */
-			*moved_len += block_len_in_page;
-			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);
-				ret = -EIO;
-				break;
-			}
-
-			orig_page_offset++;
-			data_offset_in_page = 0;
-			rest_blocks -= block_len_in_page;
-			if (rest_blocks > blocks_per_page)
-				block_len_in_page = blocks_per_page;
-			else
-				block_len_in_page = rest_blocks;
-		}
-
+		/* Swap original branches with new branches */
+		move_extent_per_page(o_filp, donor_inode,
+				     orig_page_index, donor_page_index,
+				     offset_in_page, cur_len,
+				     unwritten, &ret);
 		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		if (ret < 0)
 			break;
-
-		/* Decrease buffer counter */
-		if (holecheck_path)
-			ext4_ext_drop_refs(holecheck_path);
-		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);
-		ret = get_ext_path(orig_inode, seq_start, &orig_path);
-		if (ret)
-			break;
-
-		ext_cur = holecheck_path[depth].p_ext;
-		add_blocks = ext4_ext_get_actual_len(ext_cur);
-		seq_blocks = 0;
-
+		o_start += cur_len;
+		d_start += cur_len;
 	}
+	*moved_len = o_start - orig_blk;
+	if (*moved_len > len)
+		*moved_len = len;
+
 out:
 	if (*moved_len) {
 		ext4_discard_preallocations(orig_inode);
 		ext4_discard_preallocations(donor_inode);
 	}
 
-	if (orig_path) {
-		ext4_ext_drop_refs(orig_path);
-		kfree(orig_path);
-	}
-	if (holecheck_path) {
-		ext4_ext_drop_refs(holecheck_path);
-		kfree(holecheck_path);
-	}
+	ext4_ext_drop_refs(path);
+	kfree(path);
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);

fs/ext4/namei.c

@@ -53,7 +53,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
 					ext4_lblk_t *block)
 {
 	struct buffer_head *bh;
-	int err = 0;
+	int err;
 
 	if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb &&
 		     ((inode->i_size >> 10) >=
@@ -62,9 +62,9 @@ static struct buffer_head *ext4_append(handle_t *handle,
 
 	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
 
-	bh = ext4_bread(handle, inode, *block, 1, &err);
-	if (!bh)
-		return ERR_PTR(err);
+	bh = ext4_bread(handle, inode, *block, 1);
+	if (IS_ERR(bh))
+		return bh;
 	inode->i_size += inode->i_sb->s_blocksize;
 	EXT4_I(inode)->i_disksize = inode->i_size;
 	BUFFER_TRACE(bh, "get_write_access");
@@ -94,20 +94,20 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 {
 	struct buffer_head *bh;
 	struct ext4_dir_entry *dirent;
-	int err = 0, is_dx_block = 0;
+	int is_dx_block = 0;
 
-	bh = ext4_bread(NULL, inode, block, 0, &err);
-	if (!bh) {
-		if (err == 0) {
-			ext4_error_inode(inode, __func__, line, block,
-					       "Directory hole found");
-			return ERR_PTR(-EIO);
-		}
+	bh = ext4_bread(NULL, inode, block, 0);
+	if (IS_ERR(bh)) {
 		__ext4_warning(inode->i_sb, __func__, line,
-			       "error reading directory block "
-			       "(ino %lu, block %lu)", inode->i_ino,
+			       "error %ld reading directory block "
+			       "(ino %lu, block %lu)", PTR_ERR(bh), inode->i_ino,
 			       (unsigned long) block);
-		return ERR_PTR(err);
+
+		return bh;
+	}
+	if (!bh) {
+		ext4_error_inode(inode, __func__, line, block, "Directory hole found");
+		return ERR_PTR(-EIO);
 	}
 	dirent = (struct ext4_dir_entry *) bh->b_data;
 	/* Determine whether or not we have an index block */
@@ -124,8 +124,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 		       "directory leaf block found instead of index block");
 		return ERR_PTR(-EIO);
 	}
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) ||
+	if (!ext4_has_metadata_csum(inode->i_sb) ||
 	    buffer_verified(bh))
 		return bh;
 
@@ -253,8 +252,7 @@ static unsigned dx_node_limit(struct inode *dir);
 static struct dx_frame *dx_probe(const struct qstr *d_name,
 				 struct inode *dir,
 				 struct dx_hash_info *hinfo,
-				 struct dx_frame *frame,
-				 int *err);
+				 struct dx_frame *frame);
 static void dx_release(struct dx_frame *frames);
 static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
 		       struct dx_hash_info *hinfo, struct dx_map_entry map[]);
@@ -270,8 +268,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
 				 __u32 *start_hash);
 static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 		const struct qstr *d_name,
-		struct ext4_dir_entry_2 **res_dir,
-		int *err);
+		struct ext4_dir_entry_2 **res_dir);
 static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode);
 
@@ -340,8 +337,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent)
 {
 	struct ext4_dir_entry_tail *t;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	t = get_dirent_tail(inode, dirent);
@@ -362,8 +358,7 @@ static void ext4_dirent_csum_set(struct inode *inode,
 {
 	struct ext4_dir_entry_tail *t;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	t = get_dirent_tail(inode, dirent);
@@ -438,8 +433,7 @@ static int ext4_dx_csum_verify(struct inode *inode,
 	struct dx_tail *t;
 	int count_offset, limit, count;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -468,8 +462,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent)
 	struct dx_tail *t;
 	int count_offset, limit, count;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -557,8 +550,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
 		EXT4_DIR_REC_LEN(2) - infosize;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		entry_space -= sizeof(struct dx_tail);
 	return entry_space / sizeof(struct dx_entry);
 }
@@ -567,8 +559,7 @@ static inline unsigned dx_node_limit(struct inode *dir)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		entry_space -= sizeof(struct dx_tail);
 	return entry_space / sizeof(struct dx_entry);
 }
@@ -641,7 +632,9 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
 		u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
 		struct stats stats;
 		printk("%s%3u:%03u hash %8x/%8x ",levels?"":"   ", i, block, hash, range);
-		if (!(bh = ext4_bread (NULL,dir, block, 0,&err))) continue;
+		bh = ext4_bread(NULL,dir, block, 0);
+		if (!bh || IS_ERR(bh))
+			continue;
 		stats = levels?
 		   dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
 		   dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0);
@@ -669,29 +662,25 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
  */
 static struct dx_frame *
 dx_probe(const struct qstr *d_name, struct inode *dir,
-	 struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
+	 struct dx_hash_info *hinfo, struct dx_frame *frame_in)
 {
 	unsigned count, indirect;
 	struct dx_entry *at, *entries, *p, *q, *m;
 	struct dx_root *root;
-	struct buffer_head *bh;
 	struct dx_frame *frame = frame_in;
+	struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
 	u32 hash;
 
-	frame->bh = NULL;
-	bh = ext4_read_dirblock(dir, 0, INDEX);
-	if (IS_ERR(bh)) {
-		*err = PTR_ERR(bh);
-		goto fail;
-	}
-	root = (struct dx_root *) bh->b_data;
+	frame->bh = ext4_read_dirblock(dir, 0, INDEX);
+	if (IS_ERR(frame->bh))
+		return (struct dx_frame *) frame->bh;
+
+	root = (struct dx_root *) frame->bh->b_data;
 	if (root->info.hash_version != DX_HASH_TEA &&
 	    root->info.hash_version != DX_HASH_HALF_MD4 &&
 	    root->info.hash_version != DX_HASH_LEGACY) {
 		ext4_warning(dir->i_sb, "Unrecognised inode hash code %d",
 			     root->info.hash_version);
-		brelse(bh);
-		*err = ERR_BAD_DX_DIR;
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
@@ -705,16 +694,12 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 	if (root->info.unused_flags & 1) {
 		ext4_warning(dir->i_sb, "Unimplemented inode hash flags: %#06x",
 			     root->info.unused_flags);
-		brelse(bh);
-		*err = ERR_BAD_DX_DIR;
 		goto fail;
 	}
 
 	if ((indirect = root->info.indirect_levels) > 1) {
 		ext4_warning(dir->i_sb, "Unimplemented inode hash depth: %#06x",
 			     root->info.indirect_levels);
-		brelse(bh);
-		*err = ERR_BAD_DX_DIR;
 		goto fail;
 	}
 
@@ -724,27 +709,21 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 	if (dx_get_limit(entries) != dx_root_limit(dir,
 						   root->info.info_length)) {
 		ext4_warning(dir->i_sb, "dx entry: limit != root limit");
-		brelse(bh);
-		*err = ERR_BAD_DX_DIR;
 		goto fail;
 	}
 
 	dxtrace(printk("Look up %x", hash));
-	while (1)
-	{
+	while (1) {
 		count = dx_get_count(entries);
 		if (!count || count > dx_get_limit(entries)) {
 			ext4_warning(dir->i_sb,
 				     "dx entry: no count or count > limit");
-			brelse(bh);
-			*err = ERR_BAD_DX_DIR;
-			goto fail2;
+			goto fail;
 		}
 
 		p = entries + 1;
 		q = entries + count - 1;
-		while (p <= q)
-		{
+		while (p <= q) {
 			m = p + (q - p)/2;
 			dxtrace(printk("."));
 			if (dx_get_hash(m) > hash)
@@ -753,8 +732,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 				p = m + 1;
 		}
 
-		if (0) // linear search cross check
-		{
+		if (0) { // linear search cross check
 			unsigned n = count - 1;
 			at = entries;
 			while (n--)
@@ -771,38 +749,35 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 
 		at = p - 1;
 		dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at)));
-		frame->bh = bh;
 		frame->entries = entries;
 		frame->at = at;
-		if (!indirect--) return frame;
-		bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
-		if (IS_ERR(bh)) {
-			*err = PTR_ERR(bh);
-			goto fail2;
+		if (!indirect--)
+			return frame;
+		frame++;
+		frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
+		if (IS_ERR(frame->bh)) {
+			ret_err = (struct dx_frame *) frame->bh;
+			frame->bh = NULL;
+			goto fail;
 		}
-		entries = ((struct dx_node *) bh->b_data)->entries;
+		entries = ((struct dx_node *) frame->bh->b_data)->entries;
 
 		if (dx_get_limit(entries) != dx_node_limit (dir)) {
 			ext4_warning(dir->i_sb,
 				     "dx entry: limit != node limit");
-			brelse(bh);
-			*err = ERR_BAD_DX_DIR;
-			goto fail2;
+			goto fail;
 		}
-		frame++;
-		frame->bh = NULL;
 	}
-fail2:
+fail:
 	while (frame >= frame_in) {
 		brelse(frame->bh);
 		frame--;
 	}
-fail:
-	if (*err == ERR_BAD_DX_DIR)
+	if (ret_err == ERR_PTR(ERR_BAD_DX_DIR))
 		ext4_warning(dir->i_sb,
 			     "Corrupt dir inode %lu, running e2fsck is "
 			     "recommended.", dir->i_ino);
-	return NULL;
+	return ret_err;
 }
 
 static void dx_release (struct dx_frame *frames)
@@ -988,9 +963,9 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	}
 	hinfo.hash = start_hash;
 	hinfo.minor_hash = 0;
-	frame = dx_probe(NULL, dir, &hinfo, frames, &err);
-	if (!frame)
-		return err;
+	frame = dx_probe(NULL, dir, &hinfo, frames);
+	if (IS_ERR(frame))
+		return PTR_ERR(frame);
 
 	/* Add '.' and '..' from the htree header */
 	if (!start_hash && !start_minor_hash) {
@@ -1227,8 +1202,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 				   buffer */
 	int num = 0;
 	ext4_lblk_t  nblocks;
-	int i, err = 0;
-	int namelen;
+	int i, namelen;
 
 	*res_dir = NULL;
 	sb = dir->i_sb;
@@ -1258,17 +1232,13 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 		goto restart;
 	}
 	if (is_dx(dir)) {
-		bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
+		bh = ext4_dx_find_entry(dir, d_name, res_dir);
 		/*
 		 * On success, or if the error was file not found,
 		 * return.  Otherwise, fall back to doing a search the
 		 * old fashioned way.
 		 */
-		if (err == -ENOENT)
-			return NULL;
-		if (err && err != ERR_BAD_DX_DIR)
-			return ERR_PTR(err);
-		if (bh)
+		if (!IS_ERR(bh) || PTR_ERR(bh) != ERR_BAD_DX_DIR)
 			return bh;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
@@ -1298,10 +1268,10 @@ restart:
 					break;
 				}
 				num++;
-				bh = ext4_getblk(NULL, dir, b++, 0, &err);
-				if (unlikely(err)) {
+				bh = ext4_getblk(NULL, dir, b++, 0);
+				if (unlikely(IS_ERR(bh))) {
 					if (ra_max == 0)
-						return ERR_PTR(err);
+						return bh;
 					break;
 				}
 				bh_use[ra_max] = bh;
@@ -1366,7 +1336,7 @@ cleanup_and_exit:
 }
 
 static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
-		       struct ext4_dir_entry_2 **res_dir, int *err)
+		       struct ext4_dir_entry_2 **res_dir)
 {
 	struct super_block * sb = dir->i_sb;
 	struct dx_hash_info	hinfo;
@@ -1375,25 +1345,23 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
 	ext4_lblk_t block;
 	int retval;
 
-	if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
-		return NULL;
+	frame = dx_probe(d_name, dir, &hinfo, frames);
+	if (IS_ERR(frame))
+		return (struct buffer_head *) frame;
 	do {
 		block = dx_get_block(frame->at);
 		bh = ext4_read_dirblock(dir, block, DIRENT);
-		if (IS_ERR(bh)) {
-			*err = PTR_ERR(bh);
+		if (IS_ERR(bh))
 			goto errout;
-		}
+
 		retval = search_dirblock(bh, dir, d_name,
 					 block << EXT4_BLOCK_SIZE_BITS(sb),
 					 res_dir);
-		if (retval == 1) { 	/* Success! */
-			dx_release(frames);
-			return bh;
-		}
+		if (retval == 1)
+			goto success;
 		brelse(bh);
 		if (retval == -1) {
-			*err = ERR_BAD_DX_DIR;
+			bh = ERR_PTR(ERR_BAD_DX_DIR);
 			goto errout;
 		}
 
@@ -1402,18 +1370,19 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
 					       frames, NULL);
 		if (retval < 0) {
 			ext4_warning(sb,
-			     "error reading index page in directory #%lu",
-			     dir->i_ino);
-			*err = retval;
+			     "error %d reading index page in directory #%lu",
+			     retval, dir->i_ino);
+			bh = ERR_PTR(retval);
 			goto errout;
 		}
 	} while (retval == 1);
 
-	*err = -ENOENT;
+	bh = NULL;
 errout:
 	dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
-	dx_release (frames);
-	return NULL;
+success:
+	dx_release(frames);
+	return bh;
 }
 
 static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
@@ -1441,7 +1410,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 					 dentry);
 			return ERR_PTR(-EIO);
 		}
-		inode = ext4_iget(dir->i_sb, ino);
+		inode = ext4_iget_normal(dir->i_sb, ino);
 		if (inode == ERR_PTR(-ESTALE)) {
 			EXT4_ERROR_INODE(dir,
 					 "deleted inode referenced: %u",
@@ -1474,7 +1443,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
 		return ERR_PTR(-EIO);
 	}
 
-	return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
+	return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino));
 }
 
 /*
@@ -1533,7 +1502,7 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize)
  */
 static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 			struct buffer_head **bh,struct dx_frame *frame,
-			struct dx_hash_info *hinfo, int *error)
+			struct dx_hash_info *hinfo)
 {
 	unsigned blocksize = dir->i_sb->s_blocksize;
 	unsigned count, continued;
@@ -1548,16 +1517,14 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	int	csum_size = 0;
 	int	err = 0, i;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	bh2 = ext4_append(handle, dir, &newblock);
 	if (IS_ERR(bh2)) {
 		brelse(*bh);
 		*bh = NULL;
-		*error = PTR_ERR(bh2);
-		return NULL;
+		return (struct ext4_dir_entry_2 *) bh2;
 	}
 
 	BUFFER_TRACE(*bh, "get_write_access");
@@ -1617,8 +1584,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
 
 	/* Which block gets the new entry? */
-	if (hinfo->hash >= hash2)
-	{
+	if (hinfo->hash >= hash2) {
 		swap(*bh, bh2);
 		de = de2;
 	}
@@ -1638,8 +1604,7 @@ journal_error:
 	brelse(bh2);
 	*bh = NULL;
 	ext4_std_error(dir->i_sb, err);
-	*error = err;
-	return NULL;
+	return ERR_PTR(err);
 }
 
 int ext4_find_dest_de(struct inode *dir, struct inode *inode,
@@ -1718,8 +1683,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	int		csum_size = 0;
 	int		err;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	if (!de) {
@@ -1786,8 +1750,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	struct fake_dirent *fde;
 	int		csum_size = 0;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	blocksize =  dir->i_sb->s_blocksize;
@@ -1862,8 +1825,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	ext4_handle_dirty_dx_node(handle, dir, frame->bh);
 	ext4_handle_dirty_dirent_node(handle, dir, bh);
 
-	de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
-	if (!de) {
+	de = do_split(handle,dir, &bh, frame, &hinfo);
+	if (IS_ERR(de)) {
 		/*
 		 * Even if the block split failed, we have to properly write
 		 * out all the changes we did so far. Otherwise we can end up
@@ -1871,7 +1834,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 		 */
 		ext4_mark_inode_dirty(handle, dir);
 		dx_release(frames);
-		return retval;
+		return PTR_ERR(de);
 	}
 	dx_release(frames);
 
@@ -1904,8 +1867,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	ext4_lblk_t block, blocks;
 	int	csum_size = 0;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	sb = dir->i_sb;
@@ -1982,9 +1944,9 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	struct ext4_dir_entry_2 *de;
 	int err;
 
-	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
-	if (!frame)
-		return err;
+	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames);
+	if (IS_ERR(frame))
+		return PTR_ERR(frame);
 	entries = frame->entries;
 	at = frame->at;
 	bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT);
@@ -2095,9 +2057,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			goto cleanup;
 		}
 	}
-	de = do_split(handle, dir, &bh, frame, &hinfo, &err);
-	if (!de)
+	de = do_split(handle, dir, &bh, frame, &hinfo);
+	if (IS_ERR(de)) {
+		err = PTR_ERR(de);
 		goto cleanup;
+	}
 	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
 	goto cleanup;
 
@@ -2167,8 +2131,7 @@ static int ext4_delete_entry(handle_t *handle,
 			return err;
 	}
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	BUFFER_TRACE(bh, "get_write_access");
@@ -2387,8 +2350,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 	int csum_size = 0;
 	int err;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -2403,10 +2365,6 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 	dir_block = ext4_append(handle, inode, &block);
 	if (IS_ERR(dir_block))
 		return PTR_ERR(dir_block);
-	BUFFER_TRACE(dir_block, "get_write_access");
-	err = ext4_journal_get_write_access(handle, dir_block);
-	if (err)
-		goto out;
 	de = (struct ext4_dir_entry_2 *)dir_block->b_data;
 	ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0);
 	set_nlink(inode, 2);
@@ -2573,7 +2531,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	int err = 0, rc;
 	bool dirty = false;
 
-	if (!sbi->s_journal)
+	if (!sbi->s_journal || is_bad_inode(inode))
 		return 0;
 
 	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&

fs/ext4/resize.c

@@ -1212,8 +1212,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb,
 {
 	struct buffer_head *bh;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 0;
 
 	bh = ext4_get_bitmap(sb, group_data->inode_bitmap);

fs/ext4/super.c

@@ -70,7 +70,6 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
 static void ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
-static int ext4_sync_fs_nojournal(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int ext4_unfreeze(struct super_block *sb);
@@ -141,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
 static int ext4_superblock_csum_verify(struct super_block *sb,
 				       struct ext4_super_block *es)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	return es->s_checksum == ext4_superblock_csum(sb, es);
@@ -152,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb)
 {
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	es->s_checksum = ext4_superblock_csum(sb, es);
@@ -820,10 +817,9 @@ static void ext4_put_super(struct super_block *sb)
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
 #endif
 
@@ -885,6 +881,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
 	INIT_LIST_HEAD(&ei->i_es_lru);
+	ei->i_es_all_nr = 0;
 	ei->i_es_lru_nr = 0;
 	ei->i_touch_when = 0;
 	ei->i_reserved_data_blocks = 0;
@@ -1002,7 +999,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb,
 	 * Currently we don't know the generation for parent directory, so
 	 * a generation of 0 means "accept any"
 	 */
-	inode = ext4_iget(sb, ino);
+	inode = ext4_iget_normal(sb, ino);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 	if (generation && inode->i_generation != generation) {
@@ -1124,25 +1121,6 @@ static const struct super_operations ext4_sops = {
 	.bdev_try_to_free_page = bdev_try_to_free_page,
 };
 
-static const struct super_operations ext4_nojournal_sops = {
-	.alloc_inode	= ext4_alloc_inode,
-	.destroy_inode	= ext4_destroy_inode,
-	.write_inode	= ext4_write_inode,
-	.dirty_inode	= ext4_dirty_inode,
-	.drop_inode	= ext4_drop_inode,
-	.evict_inode	= ext4_evict_inode,
-	.sync_fs	= ext4_sync_fs_nojournal,
-	.put_super	= ext4_put_super,
-	.statfs		= ext4_statfs,
-	.remount_fs	= ext4_remount,
-	.show_options	= ext4_show_options,
-#ifdef CONFIG_QUOTA
-	.quota_read	= ext4_quota_read,
-	.quota_write	= ext4_quota_write,
-#endif
-	.bdev_try_to_free_page = bdev_try_to_free_page,
-};
-
 static const struct export_operations ext4_export_ops = {
 	.fh_to_dentry = ext4_fh_to_dentry,
 	.fh_to_parent = ext4_fh_to_parent,
@@ -1712,13 +1690,6 @@ static int parse_options(char *options, struct super_block *sb,
 					"not specified");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext4_msg(sb, KERN_ERR, "journaled quota format "
-					"specified with no journaling "
-					"enabled");
-			return 0;
-		}
 	}
 #endif
 	if (test_opt(sb, DIOREAD_NOLOCK)) {
@@ -2016,8 +1987,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	__u16 crc = 0;
 	__le32 le_group = cpu_to_le32(block_group);
 
-	if ((sbi->s_es->s_feature_ro_compat &
-	     cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) {
+	if (ext4_has_metadata_csum(sbi->s_sb)) {
 		/* Use new metadata_csum algorithm */
 		__le16 save_csum;
 		__u32 csum32;
@@ -2035,6 +2005,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	}
 
 	/* old crc16 code */
+	if (!(sbi->s_es->s_feature_ro_compat &
+	      cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)))
+		return 0;
+
 	offset = offsetof(struct ext4_group_desc, bg_checksum);
 
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
@@ -2191,7 +2165,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
 		/* don't clear list on RO mount w/ errors */
 		if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
-			jbd_debug(1, "Errors on filesystem, "
+			ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
 				  "clearing orphan list.\n");
 			es->s_last_orphan = 0;
 		}
@@ -2207,7 +2181,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	/* Needed for iput() to work correctly and not trash data */
 	sb->s_flags |= MS_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
 		if (EXT4_SB(sb)->s_qf_names[i]) {
 			int ret = ext4_quota_on_mount(sb, i);
 			if (ret < 0)
@@ -2263,7 +2237,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		       PLURAL(nr_truncates));
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
 		if (sb_dqopt(sb)->files[i])
 			dquot_quota_off(sb, i);
 	}
@@ -2548,6 +2522,16 @@ static ssize_t sbi_ui_store(struct ext4_attr *a,
 	return count;
 }
 
+static ssize_t es_ui_show(struct ext4_attr *a,
+			   struct ext4_sb_info *sbi, char *buf)
+{
+
+	unsigned int *ui = (unsigned int *) (((char *) sbi->s_es) +
+			   a->u.offset);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
 static ssize_t reserved_clusters_show(struct ext4_attr *a,
 				  struct ext4_sb_info *sbi, char *buf)
 {
@@ -2601,14 +2585,29 @@ static struct ext4_attr ext4_attr_##_name = {			\
 		.offset = offsetof(struct ext4_sb_info, _elname),\
 	},							\
 }
+
+#define EXT4_ATTR_OFFSET_ES(_name,_mode,_show,_store,_elname)		\
+static struct ext4_attr ext4_attr_##_name = {				\
+	.attr = {.name = __stringify(_name), .mode = _mode },		\
+	.show	= _show,						\
+	.store	= _store,						\
+	.u = {								\
+		.offset = offsetof(struct ext4_super_block, _elname),	\
+	},								\
+}
+
 #define EXT4_ATTR(name, mode, show, store) \
 static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 
 #define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
 #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
 #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
+
+#define EXT4_RO_ATTR_ES_UI(name, elname)	\
+	EXT4_ATTR_OFFSET_ES(name, 0444, es_ui_show, NULL, elname)
 #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
 	EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
+
 #define ATTR_LIST(name) &ext4_attr_##name.attr
 #define EXT4_DEPRECATED_ATTR(_name, _val)	\
 static struct ext4_attr ext4_attr_##_name = {			\
@@ -2641,6 +2640,9 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.int
 EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
+EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
+EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
+EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
 
 static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(delayed_allocation_blocks),
@@ -2664,6 +2666,9 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(warning_ratelimit_burst),
 	ATTR_LIST(msg_ratelimit_interval_ms),
 	ATTR_LIST(msg_ratelimit_burst),
+	ATTR_LIST(errors_count),
+	ATTR_LIST(first_error_time),
+	ATTR_LIST(last_error_time),
 	NULL,
 };
 
@@ -2723,9 +2728,25 @@ static void ext4_feat_release(struct kobject *kobj)
 	complete(&ext4_feat->f_kobj_unregister);
 }
 
+static ssize_t ext4_feat_show(struct kobject *kobj,
+			      struct attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "supported\n");
+}
+
+/*
+ * We can not use ext4_attr_show/store because it relies on the kobject
+ * being embedded in the ext4_sb_info structure which is definitely not
+ * true in this case.
+ */
+static const struct sysfs_ops ext4_feat_ops = {
+	.show	= ext4_feat_show,
+	.store	= NULL,
+};
+
 static struct kobj_type ext4_feat_ktype = {
 	.default_attrs	= ext4_feat_attrs,
-	.sysfs_ops	= &ext4_attr_ops,
+	.sysfs_ops	= &ext4_feat_ops,
 	.release	= ext4_feat_release,
 };
 
@@ -3179,8 +3200,7 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 	int compat, incompat;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+	if (ext4_has_metadata_csum(sb)) {
 		/* journal checksum v3 */
 		compat = 0;
 		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
@@ -3190,6 +3210,10 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		incompat = 0;
 	}
 
+	jbd2_journal_clear_features(sbi->s_journal,
+			JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+			JBD2_FEATURE_INCOMPAT_CSUM_V3 |
+			JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
 		ret = jbd2_journal_set_features(sbi->s_journal,
 				compat, 0,
@@ -3202,11 +3226,8 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		jbd2_journal_clear_features(sbi->s_journal, 0, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
 	} else {
-		jbd2_journal_clear_features(sbi->s_journal,
-				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
-				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
-				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
-				JBD2_FEATURE_INCOMPAT_CSUM_V2);
+		jbd2_journal_clear_features(sbi->s_journal, 0, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
 	}
 
 	return ret;
@@ -3436,7 +3457,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		logical_sb_block = sb_block;
 	}
 
-	if (!(bh = sb_bread(sb, logical_sb_block))) {
+	if (!(bh = sb_bread_unmovable(sb, logical_sb_block))) {
 		ext4_msg(sb, KERN_ERR, "unable to read superblock");
 		goto out_fail;
 	}
@@ -3487,8 +3508,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(sb))
 		sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
 					       sizeof(es->s_uuid));
 
@@ -3519,8 +3539,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		set_opt(sb, ERRORS_CONT);
 	else
 		set_opt(sb, ERRORS_RO);
-	if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
-		set_opt(sb, BLOCK_VALIDITY);
+	/* block_validity enabled by default; disable with noblock_validity */
+	set_opt(sb, BLOCK_VALIDITY);
 	if (def_mount_opts & EXT4_DEFM_DISCARD)
 		set_opt(sb, DISCARD);
 
@@ -3646,7 +3666,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		brelse(bh);
 		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
 		offset = do_div(logical_sb_block, blocksize);
-		bh = sb_bread(sb, logical_sb_block);
+		bh = sb_bread_unmovable(sb, logical_sb_block);
 		if (!bh) {
 			ext4_msg(sb, KERN_ERR,
 			       "Can't read superblock on 2nd try");
@@ -3868,7 +3888,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sbi->s_group_desc[i] = sb_bread(sb, block);
+		sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
 		if (!sbi->s_group_desc[i]) {
 			ext4_msg(sb, KERN_ERR,
 			       "can't read group descriptor %d", i);
@@ -3890,13 +3910,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_err_report.data = (unsigned long) sb;
 
 	/* Register extent status tree shrinker */
-	ext4_es_register_shrinker(sbi);
-
-	err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0, GFP_KERNEL);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "insufficient memory");
+	if (ext4_es_register_shrinker(sbi))
 		goto failed_mount3;
-	}
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_extent_max_zeroout_kb = 32;
@@ -3904,11 +3919,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/*
 	 * set up enough so that it can read an inode
 	 */
-	if (!test_opt(sb, NOLOAD) &&
-	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
-		sb->s_op = &ext4_sops;
-	else
-		sb->s_op = &ext4_nojournal_sops;
+	sb->s_op = &ext4_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
@@ -4229,10 +4240,9 @@ failed_mount_wq:
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
-failed_mount3:
 	ext4_es_unregister_shrinker(sbi);
+failed_mount3:
 	del_timer_sync(&sbi->s_err_report);
-	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
@@ -4247,7 +4257,7 @@ failed_mount:
 		remove_proc_entry(sb->s_id, ext4_proc_root);
 	}
 #ifdef CONFIG_QUOTA
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
 #endif
 	ext4_blkdev_remove(sbi);
@@ -4375,6 +4385,15 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 		goto out_bdev;
 	}
 
+	if ((le32_to_cpu(es->s_feature_ro_compat) &
+	     EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+	    es->s_checksum != ext4_superblock_csum(sb, es)) {
+		ext4_msg(sb, KERN_ERR, "external journal has "
+				       "corrupt superblock");
+		brelse(bh);
+		goto out_bdev;
+	}
+
 	if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
 		ext4_msg(sb, KERN_ERR, "journal UUID does not match");
 		brelse(bh);
@@ -4677,15 +4696,19 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	 * being sent at the end of the function. But we can skip it if
 	 * transaction_commit will do it for us.
 	 */
-	target = jbd2_get_latest_transaction(sbi->s_journal);
-	if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
-	    !jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
+	if (sbi->s_journal) {
+		target = jbd2_get_latest_transaction(sbi->s_journal);
+		if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
+		    !jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
+			needs_barrier = true;
+
+		if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
+			if (wait)
+				ret = jbd2_log_wait_commit(sbi->s_journal,
+							   target);
+		}
+	} else if (wait && test_opt(sb, BARRIER))
 		needs_barrier = true;
-
-	if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
-		if (wait)
-			ret = jbd2_log_wait_commit(sbi->s_journal, target);
-	}
 	if (needs_barrier) {
 		int err;
 		err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
@@ -4696,19 +4719,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	return ret;
 }
 
-static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
-{
-	int ret = 0;
-
-	trace_ext4_sync_fs(sb, wait);
-	flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
-	dquot_writeback_dquots(sb, -1);
-	if (wait && test_opt(sb, BARRIER))
-		ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
-
-	return ret;
-}
-
 /*
  * LVM calls this function before a (read-only) snapshot is created.  This
  * gives us a chance to flush the journal completely and mark the fs clean.
@@ -4727,23 +4737,26 @@ static int ext4_freeze(struct super_block *sb)
 
 	journal = EXT4_SB(sb)->s_journal;
 
-	/* Now we set up the journal barrier. */
-	jbd2_journal_lock_updates(journal);
+	if (journal) {
+		/* Now we set up the journal barrier. */
+		jbd2_journal_lock_updates(journal);
 
-	/*
-	 * Don't clear the needs_recovery flag if we failed to flush
-	 * the journal.
-	 */
-	error = jbd2_journal_flush(journal);
-	if (error < 0)
-		goto out;
+		/*
+		 * Don't clear the needs_recovery flag if we failed to
+		 * flush the journal.
+		 */
+		error = jbd2_journal_flush(journal);
+		if (error < 0)
+			goto out;
+	}
 
 	/* Journal blocked and flushed, clear needs_recovery flag. */
 	EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 	error = ext4_commit_super(sb, 1);
 out:
-	/* we rely on upper layer to stop further updates */
-	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+	if (journal)
+		/* we rely on upper layer to stop further updates */
+		jbd2_journal_unlock_updates(journal);
 	return error;
 }
 
@@ -4774,7 +4787,7 @@ struct ext4_mount_options {
 	u32 s_min_batch_time, s_max_batch_time;
 #ifdef CONFIG_QUOTA
 	int s_jquota_fmt;
-	char *s_qf_names[MAXQUOTAS];
+	char *s_qf_names[EXT4_MAXQUOTAS];
 #endif
 };
 
@@ -4804,7 +4817,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	old_opts.s_max_batch_time = sbi->s_max_batch_time;
 #ifdef CONFIG_QUOTA
 	old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		if (sbi->s_qf_names[i]) {
 			old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
 							 GFP_KERNEL);
@@ -4965,7 +4978,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(old_opts.s_qf_names[i]);
 	if (enable_quota) {
 		if (sb_any_quota_suspended(sb))
@@ -4994,7 +5007,7 @@ restore_opts:
 	sbi->s_max_batch_time = old_opts.s_max_batch_time;
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
 		kfree(sbi->s_qf_names[i]);
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
@@ -5197,7 +5210,7 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 {
 	int err;
 	struct inode *qf_inode;
-	unsigned long qf_inums[MAXQUOTAS] = {
+	unsigned long qf_inums[EXT4_MAXQUOTAS] = {
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
 	};
@@ -5225,13 +5238,13 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 static int ext4_enable_quotas(struct super_block *sb)
 {
 	int type, err = 0;
-	unsigned long qf_inums[MAXQUOTAS] = {
+	unsigned long qf_inums[EXT4_MAXQUOTAS] = {
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
 	};
 
 	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < EXT4_MAXQUOTAS; type++) {
 		if (qf_inums[type]) {
 			err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
 						DQUOT_USAGE_ENABLED);
@@ -5309,7 +5322,6 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 {
 	struct inode *inode = sb_dqopt(sb)->files[type];
 	ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
-	int err = 0;
 	int offset = off & (sb->s_blocksize - 1);
 	int tocopy;
 	size_t toread;
@@ -5324,9 +5336,9 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 	while (toread > 0) {
 		tocopy = sb->s_blocksize - offset < toread ?
 				sb->s_blocksize - offset : toread;
-		bh = ext4_bread(NULL, inode, blk, 0, &err);
-		if (err)
-			return err;
+		bh = ext4_bread(NULL, inode, blk, 0);
+		if (IS_ERR(bh))
+			return PTR_ERR(bh);
 		if (!bh)	/* A hole? */
 			memset(data, 0, tocopy);
 		else
@@ -5347,8 +5359,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 {
 	struct inode *inode = sb_dqopt(sb)->files[type];
 	ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
-	int err = 0;
-	int offset = off & (sb->s_blocksize - 1);
+	int err, offset = off & (sb->s_blocksize - 1);
 	struct buffer_head *bh;
 	handle_t *handle = journal_current_handle();
 
@@ -5369,14 +5380,16 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 		return -EIO;
 	}
 
-	bh = ext4_bread(handle, inode, blk, 1, &err);
+	bh = ext4_bread(handle, inode, blk, 1);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (!bh)
 		goto out;
 	BUFFER_TRACE(bh, "get write access");
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err) {
 		brelse(bh);
-		goto out;
+		return err;
 	}
 	lock_buffer(bh);
 	memcpy(bh->b_data+offset, data, len);
@@ -5385,8 +5398,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	err = ext4_handle_dirty_metadata(handle, NULL, bh);
 	brelse(bh);
 out:
-	if (err)
-		return err;
 	if (inode->i_size < off + len) {
 		i_size_write(inode, off + len);
 		EXT4_I(inode)->i_disksize = inode->i_size;

fs/ext4/xattr.c

@@ -142,8 +142,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode,
 					sector_t block_nr,
 					struct ext4_xattr_header *hdr)
 {
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+	if (ext4_has_metadata_csum(inode->i_sb) &&
 	    (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
 		return 0;
 	return 1;
@@ -153,8 +152,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode,
 				      sector_t block_nr,
 				      struct ext4_xattr_header *hdr)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
@@ -190,14 +188,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
 }
 
 static int
-ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
+		       void *value_start)
 {
-	while (!IS_LAST_ENTRY(entry)) {
-		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+	struct ext4_xattr_entry *e = entry;
+
+	while (!IS_LAST_ENTRY(e)) {
+		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EIO;
-		entry = next;
+		e = next;
 	}
+
+	while (!IS_LAST_ENTRY(entry)) {
+		if (entry->e_value_size != 0 &&
+		    (value_start + le16_to_cpu(entry->e_value_offs) <
+		     (void *)e + sizeof(__u32) ||
+		     value_start + le16_to_cpu(entry->e_value_offs) +
+		    le32_to_cpu(entry->e_value_size) > end))
+			return -EIO;
+		entry = EXT4_XATTR_NEXT(entry);
+	}
+
 	return 0;
 }
 
@@ -214,7 +226,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 		return -EIO;
 	if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
 		return -EIO;
-	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
+				       bh->b_data);
 	if (!error)
 		set_buffer_verified(bh);
 	return error;
@@ -331,7 +344,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(entry, end);
+	error = ext4_xattr_check_names(entry, end, entry);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -463,7 +476,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	raw_inode = ext4_raw_inode(&iloc);
 	header = IHDR(inode, raw_inode);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(IFIRST(header), end);
+	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -899,14 +912,8 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
-			/*
-			 * take i_data_sem because we will test
-			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
-			 */
-			down_read(&EXT4_I(inode)->i_data_sem);
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
-			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;
 
@@ -986,7 +993,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	is->s.here = is->s.first;
 	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
-		error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+		error = ext4_xattr_check_names(IFIRST(header), is->s.end,
+					       IFIRST(header));
 		if (error)
 			return error;
 		/* Find the named attribute. */

fs/jbd/journal.c

@@ -886,7 +886,7 @@ journal_t * journal_init_inode (struct inode *inode)
 		goto out_err;
 	}
 
-	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+	bh = getblk_unmovable(journal->j_dev, blocknr, journal->j_blocksize);
 	if (!bh) {
 		printk(KERN_ERR
 		       "%s: Cannot get buffer for journal superblock\n",

fs/jbd2/checkpoint.c

@@ -96,15 +96,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 
 	if (jh->b_transaction == NULL && !buffer_locked(bh) &&
 	    !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
-		/*
-		 * Get our reference so that bh cannot be freed before
-		 * we unlock it
-		 */
-		get_bh(bh);
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		ret = __jbd2_journal_remove_checkpoint(jh) + 1;
-		BUFFER_TRACE(bh, "release");
-		__brelse(bh);
 	}
 	return ret;
 }
@@ -122,8 +115,6 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 
 	nblocks = jbd2_space_needed(journal);
 	while (jbd2_log_space_left(journal) < nblocks) {
-		if (journal->j_flags & JBD2_ABORT)
-			return;
 		write_unlock(&journal->j_state_lock);
 		mutex_lock(&journal->j_checkpoint_mutex);
 
@@ -139,6 +130,10 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 		 * trace for forensic evidence.
 		 */
 		write_lock(&journal->j_state_lock);
+		if (journal->j_flags & JBD2_ABORT) {
+			mutex_unlock(&journal->j_checkpoint_mutex);
+			return;
+		}
 		spin_lock(&journal->j_list_lock);
 		nblocks = jbd2_space_needed(journal);
 		space_left = jbd2_log_space_left(journal);
@@ -183,58 +178,6 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 	}
 }
 
-/*
- * Clean up transaction's list of buffers submitted for io.
- * We wait for any pending IO to complete and remove any clean
- * buffers. Note that we take the buffers in the opposite ordering
- * from the one in which they were submitted for IO.
- *
- * Return 0 on success, and return <0 if some buffers have failed
- * to be written out.
- *
- * Called with j_list_lock held.
- */
-static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
-{
-	struct journal_head *jh;
-	struct buffer_head *bh;
-	tid_t this_tid;
-	int released = 0;
-	int ret = 0;
-
-	this_tid = transaction->t_tid;
-restart:
-	/* Did somebody clean up the transaction in the meanwhile? */
-	if (journal->j_checkpoint_transactions != transaction ||
-			transaction->t_tid != this_tid)
-		return ret;
-	while (!released && transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
-		bh = jh2bh(jh);
-		get_bh(bh);
-		if (buffer_locked(bh)) {
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
-		if (unlikely(buffer_write_io_error(bh)))
-			ret = -EIO;
-
-		/*
-		 * Now in whatever state the buffer currently is, we know that
-		 * it has been written out and so we can drop it from the list
-		 */
-		released = __jbd2_journal_remove_checkpoint(jh);
-		__brelse(bh);
-	}
-
-	return ret;
-}
-
 static void
 __flush_batch(journal_t *journal, int *batch_count)
 {
@@ -254,81 +197,6 @@ __flush_batch(journal_t *journal, int *batch_count)
 	*batch_count = 0;
 }
 
-/*
- * Try to flush one buffer from the checkpoint list to disk.
- *
- * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list.  Return <0 if the buffer has failed to
- * be written out.
- *
- * Called with j_list_lock held and drops it if 1 is returned
- */
-static int __process_buffer(journal_t *journal, struct journal_head *jh,
-			    int *batch_count, transaction_t *transaction)
-{
-	struct buffer_head *bh = jh2bh(jh);
-	int ret = 0;
-
-	if (buffer_locked(bh)) {
-		get_bh(bh);
-		spin_unlock(&journal->j_list_lock);
-		wait_on_buffer(bh);
-		/* the journal_head may have gone by now */
-		BUFFER_TRACE(bh, "brelse");
-		__brelse(bh);
-		ret = 1;
-	} else if (jh->b_transaction != NULL) {
-		transaction_t *t = jh->b_transaction;
-		tid_t tid = t->t_tid;
-
-		transaction->t_chp_stats.cs_forced_to_close++;
-		spin_unlock(&journal->j_list_lock);
-		if (unlikely(journal->j_flags & JBD2_UNMOUNT))
-			/*
-			 * The journal thread is dead; so starting and
-			 * waiting for a commit to finish will cause
-			 * us to wait for a _very_ long time.
-			 */
-			printk(KERN_ERR "JBD2: %s: "
-			       "Waiting for Godot: block %llu\n",
-			       journal->j_devname,
-			       (unsigned long long) bh->b_blocknr);
-		jbd2_log_start_commit(journal, tid);
-		jbd2_log_wait_commit(journal, tid);
-		ret = 1;
-	} else if (!buffer_dirty(bh)) {
-		ret = 1;
-		if (unlikely(buffer_write_io_error(bh)))
-			ret = -EIO;
-		get_bh(bh);
-		BUFFER_TRACE(bh, "remove from checkpoint");
-		__jbd2_journal_remove_checkpoint(jh);
-		spin_unlock(&journal->j_list_lock);
-		__brelse(bh);
-	} else {
-		/*
-		 * Important: we are about to write the buffer, and
-		 * possibly block, while still holding the journal lock.
-		 * We cannot afford to let the transaction logic start
-		 * messing around with this buffer before we write it to
-		 * disk, as that would break recoverability.
-		 */
-		BUFFER_TRACE(bh, "queue");
-		get_bh(bh);
-		J_ASSERT_BH(bh, !buffer_jwrite(bh));
-		journal->j_chkpt_bhs[*batch_count] = bh;
-		__buffer_relink_io(jh);
-		transaction->t_chp_stats.cs_written++;
-		(*batch_count)++;
-		if (*batch_count == JBD2_NR_BATCH) {
-			spin_unlock(&journal->j_list_lock);
-			__flush_batch(journal, batch_count);
-			ret = 1;
-		}
-	}
-	return ret;
-}
-
 /*
  * Perform an actual checkpoint. We take the first transaction on the
  * list of transactions to be checkpointed and send all its buffers
@@ -339,9 +207,11 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
  */
 int jbd2_log_do_checkpoint(journal_t *journal)
 {
-	transaction_t *transaction;
-	tid_t this_tid;
-	int result;
+	struct journal_head	*jh;
+	struct buffer_head	*bh;
+	transaction_t		*transaction;
+	tid_t			this_tid;
+	int			result, batch_count = 0;
 
 	jbd_debug(1, "Start checkpoint\n");
 
@@ -374,45 +244,117 @@ restart:
 	 * done (maybe it's a new transaction, but it fell at the same
 	 * address).
 	 */
-	if (journal->j_checkpoint_transactions == transaction &&
-			transaction->t_tid == this_tid) {
-		int batch_count = 0;
-		struct journal_head *jh;
-		int retry = 0, err;
-
-		while (!retry && transaction->t_checkpoint_list) {
-			jh = transaction->t_checkpoint_list;
-			retry = __process_buffer(journal, jh, &batch_count,
-						 transaction);
-			if (retry < 0 && !result)
-				result = retry;
-			if (!retry && (need_resched() ||
-				spin_needbreak(&journal->j_list_lock))) {
-				spin_unlock(&journal->j_list_lock);
-				retry = 1;
-				break;
-			}
+	if (journal->j_checkpoint_transactions != transaction ||
+	    transaction->t_tid != this_tid)
+		goto out;
+
+	/* checkpoint all of the transaction's buffers */
+	while (transaction->t_checkpoint_list) {
+		jh = transaction->t_checkpoint_list;
+		bh = jh2bh(jh);
+
+		if (buffer_locked(bh)) {
+			spin_unlock(&journal->j_list_lock);
+			get_bh(bh);
+			wait_on_buffer(bh);
+			/* the journal_head may have gone by now */
+			BUFFER_TRACE(bh, "brelse");
+			__brelse(bh);
+			goto retry;
 		}
+		if (jh->b_transaction != NULL) {
+			transaction_t *t = jh->b_transaction;
+			tid_t tid = t->t_tid;
 
-		if (batch_count) {
-			if (!retry) {
-				spin_unlock(&journal->j_list_lock);
-				retry = 1;
-			}
-			__flush_batch(journal, &batch_count);
+			transaction->t_chp_stats.cs_forced_to_close++;
+			spin_unlock(&journal->j_list_lock);
+			if (unlikely(journal->j_flags & JBD2_UNMOUNT))
+				/*
+				 * The journal thread is dead; so
+				 * starting and waiting for a commit
+				 * to finish will cause us to wait for
+				 * a _very_ long time.
+				 */
+				printk(KERN_ERR
+		"JBD2: %s: Waiting for Godot: block %llu\n",
+		journal->j_devname, (unsigned long long) bh->b_blocknr);
+
+			jbd2_log_start_commit(journal, tid);
+			jbd2_log_wait_commit(journal, tid);
+			goto retry;
+		}
+		if (!buffer_dirty(bh)) {
+			if (unlikely(buffer_write_io_error(bh)) && !result)
+				result = -EIO;
+			BUFFER_TRACE(bh, "remove from checkpoint");
+			if (__jbd2_journal_remove_checkpoint(jh))
+				/* The transaction was released; we're done */
+				goto out;
+			continue;
 		}
+		/*
+		 * Important: we are about to write the buffer, and
+		 * possibly block, while still holding the journal
+		 * lock.  We cannot afford to let the transaction
+		 * logic start messing around with this buffer before
+		 * we write it to disk, as that would break
+		 * recoverability.
+		 */
+		BUFFER_TRACE(bh, "queue");
+		get_bh(bh);
+		J_ASSERT_BH(bh, !buffer_jwrite(bh));
+		journal->j_chkpt_bhs[batch_count++] = bh;
+		__buffer_relink_io(jh);
+		transaction->t_chp_stats.cs_written++;
+		if ((batch_count == JBD2_NR_BATCH) ||
+		    need_resched() ||
+		    spin_needbreak(&journal->j_list_lock))
+			goto unlock_and_flush;
+	}
 
-		if (retry) {
+	if (batch_count) {
+		unlock_and_flush:
+			spin_unlock(&journal->j_list_lock);
+		retry:
+			if (batch_count)
+				__flush_batch(journal, &batch_count);
 			spin_lock(&journal->j_list_lock);
 			goto restart;
+	}
+
+	/*
+	 * Now we issued all of the transaction's buffers, let's deal
+	 * with the buffers that are out for I/O.
+	 */
+restart2:
+	/* Did somebody clean up the transaction in the meanwhile? */
+	if (journal->j_checkpoint_transactions != transaction ||
+	    transaction->t_tid != this_tid)
+		goto out;
+
+	while (transaction->t_checkpoint_io_list) {
+		jh = transaction->t_checkpoint_io_list;
+		bh = jh2bh(jh);
+		if (buffer_locked(bh)) {
+			spin_unlock(&journal->j_list_lock);
+			get_bh(bh);
+			wait_on_buffer(bh);
+			/* the journal_head may have gone by now */
+			BUFFER_TRACE(bh, "brelse");
+			__brelse(bh);
+			spin_lock(&journal->j_list_lock);
+			goto restart2;
 		}
+		if (unlikely(buffer_write_io_error(bh)) && !result)
+			result = -EIO;
+
 		/*
-		 * Now we have cleaned up the first transaction's checkpoint
-		 * list. Let's clean up the second one
+		 * Now in whatever state the buffer currently is, we
+		 * know that it has been written out and so we can
+		 * drop it from the list
 		 */
-		err = __wait_cp_io(journal, transaction);
-		if (!result)
-			result = err;
+		if (__jbd2_journal_remove_checkpoint(jh))
+			break;
 	}
 out:
 	spin_unlock(&journal->j_list_lock);
@@ -478,18 +420,16 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
  * Find all the written-back checkpoint buffers in the given list and
  * release them.
  *
- * Called with the journal locked.
  * Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
+ * Returns 1 if we freed the transaction, 0 otherwise.
  */
-
-static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
+static int journal_clean_one_cp_list(struct journal_head *jh)
 {
 	struct journal_head *last_jh;
 	struct journal_head *next_jh = jh;
-	int ret, freed = 0;
+	int ret;
+	int freed = 0;
 
-	*released = 0;
 	if (!jh)
 		return 0;
 
@@ -498,13 +438,11 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
 		ret = __try_to_free_cp_buf(jh);
-		if (ret) {
-			freed++;
-			if (ret == 2) {
-				*released = 1;
-				return freed;
-			}
-		}
+		if (!ret)
+			return freed;
+		if (ret == 2)
+			return 1;
+		freed = 1;
 		/*
 		 * This function only frees up some memory
 		 * if possible so we dont have an obligation
@@ -523,49 +461,49 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
  *
  * Find all the written-back checkpoint buffers in the journal and release them.
  *
- * Called with the journal locked.
  * Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
  */
-
-int __jbd2_journal_clean_checkpoint_list(journal_t *journal)
+void __jbd2_journal_clean_checkpoint_list(journal_t *journal)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	int ret = 0;
-	int released;
+	int ret;
 
 	transaction = journal->j_checkpoint_transactions;
 	if (!transaction)
-		goto out;
+		return;
 
 	last_transaction = transaction->t_cpprev;
 	next_transaction = transaction;
 	do {
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_list, &released);
+		ret = journal_clean_one_cp_list(transaction->t_checkpoint_list);
 		/*
 		 * This function only frees up some memory if possible so we
 		 * dont have an obligation to finish processing. Bail out if
 		 * preemption requested:
 		 */
 		if (need_resched())
-			goto out;
-		if (released)
+			return;
+		if (ret)
 			continue;
 		/*
 		 * It is essential that we are as careful as in the case of
 		 * t_checkpoint_list with removing the buffer from the list as
 		 * we can possibly see not yet submitted buffers on io_list
 		 */
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_io_list, &released);
+		ret = journal_clean_one_cp_list(transaction->
+				t_checkpoint_io_list);
 		if (need_resched())
-			goto out;
+			return;
+		/*
+		 * Stop scanning if we couldn't free the transaction. This
+		 * avoids pointless scanning of transactions which still
+		 * weren't checkpointed.
+		 */
+		if (!ret)
+			return;
 	} while (transaction != last_transaction);
-out:
-	return ret;
 }
 
 /*

fs/jbd2/journal.c

@@ -1237,7 +1237,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 		goto out_err;
 	}
 
-	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+	bh = getblk_unmovable(journal->j_dev, blocknr, journal->j_blocksize);
 	if (!bh) {
 		printk(KERN_ERR
 		       "%s: Cannot get buffer for journal superblock\n",
@@ -1522,14 +1522,6 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (jbd2_journal_has_csum_v2or3(journal) &&
-	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
-		/* Can't have checksum v1 and v2 on at the same time! */
-		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
-		       "at the same time!\n");
-		goto out;
-	}
-
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
 	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		/* Can't have checksum v2 and v3 at the same time! */
@@ -1538,6 +1530,14 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
+		/* Can't have checksum v1 and v2 on at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;

fs/jbd2/recovery.c

@@ -525,6 +525,7 @@ static int do_one_pass(journal_t *journal,
 			    !jbd2_descr_block_csum_verify(journal,
 							  bh->b_data)) {
 				err = -EIO;
+				brelse(bh);
 				goto failed;
 			}
 

include/linux/buffer_head.h

@@ -175,12 +175,13 @@ void __wait_on_buffer(struct buffer_head *);
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
-struct buffer_head *__getblk(struct block_device *bdev, sector_t block,
-			unsigned size);
+struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
+				  unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
-struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size);
+struct buffer_head *__bread_gfp(struct block_device *,
+				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
@@ -295,7 +296,13 @@ static inline void bforget(struct buffer_head *bh)
 static inline struct buffer_head *
 sb_bread(struct super_block *sb, sector_t block)
 {
-	return __bread(sb->s_bdev, block, sb->s_blocksize);
+	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
+}
+
+static inline struct buffer_head *
+sb_bread_unmovable(struct super_block *sb, sector_t block)
+{
+	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
 }
 
 static inline void
@@ -307,7 +314,7 @@ sb_breadahead(struct super_block *sb, sector_t block)
 static inline struct buffer_head *
 sb_getblk(struct super_block *sb, sector_t block)
 {
-	return __getblk(sb->s_bdev, block, sb->s_blocksize);
+	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
 }
 
 static inline struct buffer_head *
@@ -344,6 +351,36 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
+static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
+						   sector_t block,
+						   unsigned size)
+{
+	return __getblk_gfp(bdev, block, size, 0);
+}
+
+static inline struct buffer_head *__getblk(struct block_device *bdev,
+					   sector_t block,
+					   unsigned size)
+{
+	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
+}
+
+/**
+ *  __bread() - reads a specified block and returns the bh
+ *  @bdev: the block_device to read from
+ *  @block: number of block
+ *  @size: size (in bytes) to read
+ *
+ *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache is allocated from movable area so that it can be migrated.
+ *  It returns NULL if the block was unreadable.
+ */
+static inline struct buffer_head *
+__bread(struct block_device *bdev, sector_t block, unsigned size)
+{
+	return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
+}
+
 extern int __set_page_dirty_buffers(struct page *page);
 
 #else /* CONFIG_BLOCK */

include/linux/jbd2.h

@@ -1042,7 +1042,7 @@ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
 extern void jbd2_journal_commit_transaction(journal_t *);
 
 /* Checkpoint list management */
-int __jbd2_journal_clean_checkpoint_list(journal_t *journal);
+void __jbd2_journal_clean_checkpoint_list(journal_t *journal);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
 

include/linux/mm.h

@@ -1176,6 +1176,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 
 extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);

include/trace/events/ext4.h

@@ -2369,7 +2369,7 @@ TRACE_EVENT(ext4_es_lookup_extent_exit,
 		  show_extent_status(__entry->found ? __entry->status : 0))
 );
 
-TRACE_EVENT(ext4_es_shrink_enter,
+DECLARE_EVENT_CLASS(ext4__es_shrink_enter,
 	TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
 
 	TP_ARGS(sb, nr_to_scan, cache_cnt),
@@ -2391,26 +2391,38 @@ TRACE_EVENT(ext4_es_shrink_enter,
 		  __entry->nr_to_scan, __entry->cache_cnt)
 );
 
-TRACE_EVENT(ext4_es_shrink_exit,
-	TP_PROTO(struct super_block *sb, int shrunk_nr, int cache_cnt),
+DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count,
+	TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
 
-	TP_ARGS(sb, shrunk_nr, cache_cnt),
+	TP_ARGS(sb, nr_to_scan, cache_cnt)
+);
+
+DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter,
+	TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
+
+	TP_ARGS(sb, nr_to_scan, cache_cnt)
+);
+
+TRACE_EVENT(ext4_es_shrink_scan_exit,
+	TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt),
+
+	TP_ARGS(sb, nr_shrunk, cache_cnt),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
-		__field(	int,	shrunk_nr		)
+		__field(	int,	nr_shrunk		)
 		__field(	int,	cache_cnt		)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->shrunk_nr	= shrunk_nr;
+		__entry->nr_shrunk	= nr_shrunk;
 		__entry->cache_cnt	= cache_cnt;
 	),
 
-	TP_printk("dev %d,%d shrunk_nr %d cache_cnt %d",
+	TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->shrunk_nr, __entry->cache_cnt)
+		  __entry->nr_shrunk, __entry->cache_cnt)
 );
 
 TRACE_EVENT(ext4_collapse_range,
@@ -2438,6 +2450,37 @@ TRACE_EVENT(ext4_collapse_range,
 		  __entry->offset, __entry->len)
 );
 
+TRACE_EVENT(ext4_es_shrink,
+	TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time,
+		 int skip_precached, int nr_skipped, int retried),
+
+	TP_ARGS(sb, nr_shrunk, scan_time, skip_precached, nr_skipped, retried),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	int,		nr_shrunk	)
+		__field(	unsigned long long, scan_time	)
+		__field(	int,		skip_precached	)
+		__field(	int,		nr_skipped	)
+		__field(	int,		retried		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->nr_shrunk	= nr_shrunk;
+		__entry->scan_time	= div_u64(scan_time, 1000);
+		__entry->skip_precached = skip_precached;
+		__entry->nr_skipped	= nr_skipped;
+		__entry->retried	= retried;
+	),
+
+	TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu skip_precached %d "
+		  "nr_skipped %d retried %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk,
+		  __entry->scan_time, __entry->skip_precached,
+		  __entry->nr_skipped, __entry->retried)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */

mm/truncate.c

@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 static void clear_exceptional_entry(struct address_space *mapping,
@@ -719,11 +720,67 @@ EXPORT_SYMBOL(truncate_pagecache);
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
+	loff_t oldsize = inode->i_size;
+
 	i_size_write(inode, newsize);
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
+/**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(!mutex_is_locked(&inode->i_mutex));
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
 /**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode