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

Pull ext4 updates from Ted Ts'o:
 "New features for 3.12:

   - Added aggressive extent caching using the extent status tree.  This
     can actually decrease memory usage in read-mostly workloads since
     the information is much more compactly stored in the extent status
     tree than if we had to keep the extent tree metadata blocks in the
     buffer cache.  This also improves Asynchronous I/O since it is it
     makes much less likely that we need to do metadata I/O to lookup
     the extent tree information.

   - Improve the recovery after corrupted allocation bitmaps are found
     when running in errors=ignore mode.

  Also fixed some writeback vs truncate races when using a blocksize
  less than the page size"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (25 commits)
  ext4: allow specifying external journal by pathname mount option
  ext4: mark group corrupt on group descriptor checksum
  ext4: mark block group as corrupt on inode bitmap error
  ext4: mark block group as corrupt on block bitmap error
  ext4: fix type declaration of ext4_validate_block_bitmap
  ext4: error out if verifying the block bitmap fails
  jbd2: Fix endian mixing problems in the checksumming code
  ext4: isolate ext4_extents.h file
  ext4: Fix misspellings using 'codespell' tool
  ext4: convert write_begin methods to stable_page_writes semantics
  ext4: fix use of potentially uninitialized variables in debugging code
  ext4: fix lost truncate due to race with writeback
  ext4: simplify truncation code in ext4_setattr()
  ext4: fix ext4_writepages() in presence of truncate
  ext4: move test whether extent to map can be extended to one place
  ext4: fix warning in ext4_da_update_reserve_space()
  quota: provide interface for readding allocated space into reserved space
  ext4: avoid reusing recently deleted inodes in no journal mode
  ext4: allocate delayed allocation blocks before rename
  ext4: start handle at least possible moment when renaming files
  ...

23 files changed, 816 insertions, 367 deletions

diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index f522425aaa24..bafdd48eefde 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -41,7 +41,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 
 /**
  * Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
  * indexing).
  *
  * Return 1 if it is a dx dir, 0 if not
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ddd715e42a5c..dc5d572ebd6a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -184,6 +184,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
 	int flex_bg = 0;
+	struct ext4_group_info *grp;
 
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
@@ -191,11 +192,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	 * 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);
-		ext4_free_group_clusters_set(sb, gdp, 0);
-		ext4_free_inodes_set(sb, gdp, 0);
-		ext4_itable_unused_set(sb, gdp, 0);
-		memset(bh->b_data, 0xff, sb->s_blocksize);
-		ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
+		grp = ext4_get_group_info(sb, block_group);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
 	memset(bh->b_data, 0, sb->s_blocksize);
@@ -305,7 +304,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
  */
 static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 					    struct ext4_group_desc *desc,
-					    unsigned int block_group,
+					    ext4_group_t block_group,
 					    struct buffer_head *bh)
 {
 	ext4_grpblk_t offset;
@@ -352,10 +351,11 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 
 void ext4_validate_block_bitmap(struct super_block *sb,
 			       struct ext4_group_desc *desc,
-			       unsigned int block_group,
+			       ext4_group_t block_group,
 			       struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
+	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return;
@@ -366,12 +366,14 @@ void ext4_validate_block_bitmap(struct super_block *sb,
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
 			   block_group, blk);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
 	set_buffer_verified(bh);
@@ -445,7 +447,10 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	return bh;
 verify:
 	ext4_validate_block_bitmap(sb, desc, block_group, bh);
-	return bh;
+	if (buffer_verified(bh))
+		return bh;
+	put_bh(bh);
+	return NULL;
 }
 
 /* Returns 0 on success, 1 on error */
@@ -469,7 +474,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 	clear_buffer_new(bh);
 	/* Panic or remount fs read-only if block bitmap is invalid */
 	ext4_validate_block_bitmap(sb, desc, block_group, bh);
-	return 0;
+	/* ...but check for error just in case errors=continue. */
+	return !buffer_verified(bh);
 }
 
 struct buffer_head *
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 3c7d288ae94c..680bb3388919 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -33,7 +33,7 @@ static int ext4_dx_readdir(struct file *, struct dir_context *);
 
 /**
  * Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
  * indexing).
  *
  * Return 1 if it is a dx dir, 0 if not
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0ab26fbf3380..06b488dca666 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -561,6 +561,18 @@ enum {
 #define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
 
 /*
+ * The bit position of these flags must not overlap with any of the
+ * EXT4_GET_BLOCKS_*.  They are used by ext4_ext_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
+
+/*
  * Flags used by ext4_free_blocks
  */
 #define EXT4_FREE_BLOCKS_METADATA	0x0001
@@ -569,6 +581,7 @@ enum {
 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
+#define EXT4_FREE_BLOCKS_RESERVE		0x0040
 
 /*
  * ioctl commands
@@ -590,6 +603,7 @@ enum {
 #define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
 #define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
 #define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
+#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -1375,6 +1389,7 @@ enum {
 					   nolocking */
 	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
 	EXT4_STATE_ORDERED_MODE,	/* data=ordered mode */
+	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -1915,7 +1930,7 @@ extern ext4_group_t ext4_get_group_number(struct super_block *sb,
 
 extern void ext4_validate_block_bitmap(struct super_block *sb,
 				       struct ext4_group_desc *desc,
-				       unsigned int block_group,
+				       ext4_group_t block_group,
 				       struct buffer_head *bh);
 extern unsigned int ext4_block_group(struct super_block *sb,
 			ext4_fsblk_t blocknr);
@@ -2417,16 +2432,32 @@ do {								\
 #define EXT4_FREECLUSTERS_WATERMARK 0
 #endif
 
+/* Update i_disksize. Requires i_mutex to avoid races with truncate */
 static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 {
-	/*
-	 * XXX: replace with spinlock if seen contended -bzzz
-	 */
+	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
+		     !mutex_is_locked(&inode->i_mutex));
 	down_write(&EXT4_I(inode)->i_data_sem);
 	if (newsize > EXT4_I(inode)->i_disksize)
 		EXT4_I(inode)->i_disksize = newsize;
 	up_write(&EXT4_I(inode)->i_data_sem);
-	return ;
+}
+
+/*
+ * Update i_disksize after writeback has been started. Races with truncate
+ * are avoided by checking i_size under i_data_sem.
+ */
+static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+	loff_t i_size;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	i_size = i_size_read(inode);
+	if (newsize > i_size)
+		newsize = i_size;
+	if (newsize > EXT4_I(inode)->i_disksize)
+		EXT4_I(inode)->i_disksize = newsize;
+	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
 struct ext4_group_info {
@@ -2449,9 +2480,15 @@ struct ext4_group_info {
 
 #define EXT4_GROUP_INFO_NEED_INIT_BIT		0
 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
+#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
+	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
+	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
 
 #define EXT4_MB_GRP_WAS_TRIMMED(grp)	\
 	(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
@@ -2655,6 +2692,12 @@ extern int ext4_check_blockref(const char *, unsigned int,
 struct ext4_ext_path;
 struct ext4_extent;
 
+/*
+ * Maximum number of logical blocks in a file; ext4_extent's ee_block is
+ * __le32.
+ */
+#define EXT_MAX_BLOCKS	0xffffffff
+
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
@@ -2684,7 +2727,8 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *,
 				  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 *);
+						  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,
@@ -2693,7 +2737,7 @@ extern int ext4_find_delalloc_range(struct inode *inode,
 extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
-
+extern int ext4_ext_precache(struct inode *inode);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 51bc821ade90..5074fe23f19e 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -134,12 +134,6 @@ struct ext4_ext_path {
  */
 
 /*
- * Maximum number of logical blocks in a file; ext4_extent's ee_block is
- * __le32.
- */
-#define EXT_MAX_BLOCKS	0xffffffff
-
-/*
  * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
  * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
  * MSB of ee_len field in the extent datastructure to signify if this
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 2877258d9497..81cfefa9dc0c 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -197,7 +197,7 @@ static inline void ext4_journal_callback_add(handle_t *handle,
  * ext4_journal_callback_del: delete a registered callback
  * @handle: active journal transaction handle on which callback was registered
  * @jce: registered journal callback entry to unregister
- * Return true if object was sucessfully removed
+ * Return true if object was successfully removed
  */
 static inline bool ext4_journal_callback_try_del(handle_t *handle,
 					     struct ext4_journal_cb_entry *jce)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 72ba4705d4fa..54d52afcdb19 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -407,7 +407,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
 
 static int __ext4_ext_check(const char *function, unsigned int line,
 			    struct inode *inode, struct ext4_extent_header *eh,
-			    int depth)
+			    int depth, ext4_fsblk_t pblk)
 {
 	const char *error_msg;
 	int max = 0;
@@ -447,42 +447,149 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 
 corrupted:
 	ext4_error_inode(inode, function, line, 0,
-			"bad header/extent: %s - magic %x, "
-			"entries %u, max %u(%u), depth %u(%u)",
-			error_msg, le16_to_cpu(eh->eh_magic),
-			le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
-			max, le16_to_cpu(eh->eh_depth), depth);
-
+			 "pblk %llu bad header/extent: %s - magic %x, "
+			 "entries %u, max %u(%u), depth %u(%u)",
+			 (unsigned long long) pblk, error_msg,
+			 le16_to_cpu(eh->eh_magic),
+			 le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+			 max, le16_to_cpu(eh->eh_depth), depth);
 	return -EIO;
 }
 
-#define ext4_ext_check(inode, eh, depth)	\
-	__ext4_ext_check(__func__, __LINE__, inode, eh, depth)
+#define ext4_ext_check(inode, eh, depth, pblk)			\
+	__ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk))
 
 int ext4_ext_check_inode(struct inode *inode)
 {
-	return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode));
+	return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
 }
 
-static int __ext4_ext_check_block(const char *function, unsigned int line,
-				  struct inode *inode,
-				  struct ext4_extent_header *eh,
-				  int depth,
-				  struct buffer_head *bh)
+static struct buffer_head *
+__read_extent_tree_block(const char *function, unsigned int line,
+			 struct inode *inode, ext4_fsblk_t pblk, int depth,
+			 int flags)
 {
-	int ret;
+	struct buffer_head		*bh;
+	int				err;
 
-	if (buffer_verified(bh))
-		return 0;
-	ret = ext4_ext_check(inode, eh, depth);
-	if (ret)
-		return ret;
+	bh = sb_getblk(inode->i_sb, pblk);
+	if (unlikely(!bh))
+		return ERR_PTR(-ENOMEM);
+
+	if (!bh_uptodate_or_lock(bh)) {
+		trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
+		err = bh_submit_read(bh);
+		if (err < 0)
+			goto errout;
+	}
+	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
+		return bh;
+	err = __ext4_ext_check(function, line, inode,
+			       ext_block_hdr(bh), depth, pblk);
+	if (err)
+		goto errout;
 	set_buffer_verified(bh);
-	return ret;
+	/*
+	 * If this is a leaf block, cache all of its entries
+	 */
+	if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
+		struct ext4_extent_header *eh = ext_block_hdr(bh);
+		struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+		ext4_lblk_t prev = 0;
+		int i;
+
+		for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+			unsigned int status = EXTENT_STATUS_WRITTEN;
+			ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+			int len = ext4_ext_get_actual_len(ex);
+
+			if (prev && (prev != lblk))
+				ext4_es_cache_extent(inode, prev,
+						     lblk - prev, ~0,
+						     EXTENT_STATUS_HOLE);
+
+			if (ext4_ext_is_uninitialized(ex))
+				status = EXTENT_STATUS_UNWRITTEN;
+			ext4_es_cache_extent(inode, lblk, len,
+					     ext4_ext_pblock(ex), status);
+			prev = lblk + len;
+		}
+	}
+	return bh;
+errout:
+	put_bh(bh);
+	return ERR_PTR(err);
+
 }
 
-#define ext4_ext_check_block(inode, eh, depth, bh)	\
-	__ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh)
+#define read_extent_tree_block(inode, pblk, depth, flags)		\
+	__read_extent_tree_block(__func__, __LINE__, (inode), (pblk),   \
+				 (depth), (flags))
+
+/*
+ * This function is called to cache a file's extent information in the
+ * extent status tree
+ */
+int ext4_ext_precache(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_ext_path *path = NULL;
+	struct buffer_head *bh;
+	int i = 0, depth, ret = 0;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		return 0;	/* not an extent-mapped inode */
+
+	down_read(&ei->i_data_sem);
+	depth = ext_depth(inode);
+
+	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+		       GFP_NOFS);
+	if (path == NULL) {
+		up_read(&ei->i_data_sem);
+		return -ENOMEM;
+	}
+
+	/* Don't cache anything if there are no external extent blocks */
+	if (depth == 0)
+		goto out;
+	path[0].p_hdr = ext_inode_hdr(inode);
+	ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
+	if (ret)
+		goto out;
+	path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr);
+	while (i >= 0) {
+		/*
+		 * If this is a leaf block or we've reached the end of
+		 * the index block, go up
+		 */
+		if ((i == depth) ||
+		    path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) {
+			brelse(path[i].p_bh);
+			path[i].p_bh = NULL;
+			i--;
+			continue;
+		}
+		bh = read_extent_tree_block(inode,
+					    ext4_idx_pblock(path[i].p_idx++),
+					    depth - i - 1,
+					    EXT4_EX_FORCE_CACHE);
+		if (IS_ERR(bh)) {
+			ret = PTR_ERR(bh);
+			break;
+		}
+		i++;
+		path[i].p_bh = bh;
+		path[i].p_hdr = ext_block_hdr(bh);
+		path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr);
+	}
+	ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
+out:
+	up_read(&ei->i_data_sem);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	return ret;
+}
 
 #ifdef EXT_DEBUG
 static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
@@ -716,7 +823,7 @@ 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)
+		     struct ext4_ext_path *path, int flags)
 {
 	struct ext4_extent_header *eh;
 	struct buffer_head *bh;
@@ -748,20 +855,13 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 		path[ppos].p_depth = i;
 		path[ppos].p_ext = NULL;
 
-		bh = sb_getblk(inode->i_sb, path[ppos].p_block);
-		if (unlikely(!bh)) {
-			ret = -ENOMEM;
+		bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
+					    flags);
+		if (IS_ERR(bh)) {
+			ret = PTR_ERR(bh);
 			goto err;
 		}
-		if (!bh_uptodate_or_lock(bh)) {
-			trace_ext4_ext_load_extent(inode, block,
-						path[ppos].p_block);
-			ret = bh_submit_read(bh);
-			if (ret < 0) {
-				put_bh(bh);
-				goto err;
-			}
-		}
+
 		eh = ext_block_hdr(bh);
 		ppos++;
 		if (unlikely(ppos > depth)) {
@@ -773,11 +873,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 		}
 		path[ppos].p_bh = bh;
 		path[ppos].p_hdr = eh;
-		i--;
-
-		ret = ext4_ext_check_block(inode, eh, i, bh);
-		if (ret < 0)
-			goto err;
 	}
 
 	path[ppos].p_depth = i;
@@ -1198,7 +1293,8 @@ out:
  * if no free index is found, then it requests in-depth growing.
  */
 static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
-				    unsigned int flags,
+				    unsigned int mb_flags,
+				    unsigned int gb_flags,
 				    struct ext4_ext_path *path,
 				    struct ext4_extent *newext)
 {
@@ -1220,7 +1316,7 @@ repeat:
 	if (EXT_HAS_FREE_INDEX(curp)) {
 		/* if we found index with free entry, then use that
 		 * entry: create all needed subtree and add new leaf */
-		err = ext4_ext_split(handle, inode, flags, path, newext, i);
+		err = ext4_ext_split(handle, inode, mb_flags, path, newext, i);
 		if (err)
 			goto out;
 
@@ -1228,12 +1324,12 @@ repeat:
 		ext4_ext_drop_refs(path);
 		path = ext4_ext_find_extent(inode,
 				    (ext4_lblk_t)le32_to_cpu(newext->ee_block),
-				    path);
+				    path, 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, flags, newext);
+		err = ext4_ext_grow_indepth(handle, inode, mb_flags, newext);
 		if (err)
 			goto out;
 
@@ -1241,7 +1337,7 @@ repeat:
 		ext4_ext_drop_refs(path);
 		path = ext4_ext_find_extent(inode,
 				   (ext4_lblk_t)le32_to_cpu(newext->ee_block),
-				    path);
+				    path, gb_flags);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out;
@@ -1412,29 +1508,21 @@ got_index:
 	ix++;
 	block = ext4_idx_pblock(ix);
 	while (++depth < path->p_depth) {
-		bh = sb_bread(inode->i_sb, block);
-		if (bh == NULL)
-			return -EIO;
-		eh = ext_block_hdr(bh);
 		/* subtract from p_depth to get proper eh_depth */
-		if (ext4_ext_check_block(inode, eh,
-					 path->p_depth - depth, bh)) {
-			put_bh(bh);
-			return -EIO;
-		}
+		bh = read_extent_tree_block(inode, block,
+					    path->p_depth - depth, 0);
+		if (IS_ERR(bh))
+			return PTR_ERR(bh);
+		eh = ext_block_hdr(bh);
 		ix = EXT_FIRST_INDEX(eh);
 		block = ext4_idx_pblock(ix);
 		put_bh(bh);
 	}
 
-	bh = sb_bread(inode->i_sb, block);
-	if (bh == NULL)
-		return -EIO;
+	bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	eh = ext_block_hdr(bh);
-	if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) {
-		put_bh(bh);
-		return -EIO;
-	}
 	ex = EXT_FIRST_EXTENT(eh);
 found_extent:
 	*logical = le32_to_cpu(ex->ee_block);
@@ -1705,7 +1793,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
 
 	brelse(path[1].p_bh);
 	ext4_free_blocks(handle, inode, NULL, blk, 1,
-			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET |
+			 EXT4_FREE_BLOCKS_RESERVE);
 }
 
 /*
@@ -1793,7 +1882,7 @@ out:
  */
 int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 				struct ext4_ext_path *path,
-				struct ext4_extent *newext, int flag)
+				struct ext4_extent *newext, int gb_flags)
 {
 	struct ext4_extent_header *eh;
 	struct ext4_extent *ex, *fex;
@@ -1802,7 +1891,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	int depth, len, err;
 	ext4_lblk_t next;
 	unsigned uninitialized = 0;
-	int flags = 0;
+	int mb_flags = 0;
 
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
 		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1817,7 +1906,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	}
 
 	/* try to insert block into found extent and return */
-	if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) {
+	if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) {
 
 		/*
 		 * Try to see whether we should rather test the extent on
@@ -1920,7 +2009,7 @@ 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);
+		npath = ext4_ext_find_extent(inode, next, NULL, 0);
 		if (IS_ERR(npath))
 			return PTR_ERR(npath);
 		BUG_ON(npath->p_depth != path->p_depth);
@@ -1939,9 +2028,10 @@ prepend:
 	 * There is no free space in the found leaf.
 	 * We're gonna add a new leaf in the tree.
 	 */
-	if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL)
-		flags = EXT4_MB_USE_RESERVED;
-	err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
+	if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
+		mb_flags = EXT4_MB_USE_RESERVED;
+	err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
+				       path, newext);
 	if (err)
 		goto cleanup;
 	depth = ext_depth(inode);
@@ -2007,7 +2097,7 @@ has_space:
 
 merge:
 	/* try to merge extents */
-	if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
+	if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO))
 		ext4_ext_try_to_merge(handle, inode, path, nearex);
 
 
@@ -2050,7 +2140,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 			path = NULL;
 		}
 
-		path = ext4_ext_find_extent(inode, block, path);
+		path = ext4_ext_find_extent(inode, block, path, 0);
 		if (IS_ERR(path)) {
 			up_read(&EXT4_I(inode)->i_data_sem);
 			err = PTR_ERR(path);
@@ -2195,8 +2285,8 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 				ext4_lblk_t block)
 {
 	int depth = ext_depth(inode);
-	unsigned long len;
-	ext4_lblk_t lblock;
+	unsigned long len = 0;
+	ext4_lblk_t lblock = 0;
 	struct ext4_extent *ex;
 
 	ex = path[depth].p_ext;
@@ -2233,7 +2323,6 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 			ext4_es_insert_extent(inode, lblock, len, ~0,
 					      EXTENT_STATUS_HOLE);
 	} else {
-		lblock = len = 0;
 		BUG();
 	}
 
@@ -2712,7 +2801,7 @@ again:
 		ext4_lblk_t ee_block;
 
 		/* find extent for this block */
-		path = ext4_ext_find_extent(inode, end, NULL);
+		path = ext4_ext_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
 		if (IS_ERR(path)) {
 			ext4_journal_stop(handle);
 			return PTR_ERR(path);
@@ -2754,6 +2843,7 @@ again:
 			 */
 			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);
 
@@ -2782,7 +2872,7 @@ again:
 		path[0].p_hdr = ext_inode_hdr(inode);
 		i = 0;
 
-		if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+		if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) {
 			err = -EIO;
 			goto out;
 		}
@@ -2829,10 +2919,12 @@ again:
 			ext_debug("move to level %d (block %llu)\n",
 				  i + 1, ext4_idx_pblock(path[i].p_idx));
 			memset(path + i + 1, 0, sizeof(*path));
-			bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx));
-			if (!bh) {
+			bh = read_extent_tree_block(inode,
+				ext4_idx_pblock(path[i].p_idx), depth - i - 1,
+				EXT4_EX_NOCACHE);
+			if (IS_ERR(bh)) {
 				/* should we reset i_size? */
-				err = -EIO;
+				err = PTR_ERR(bh);
 				break;
 			}
 			/* Yield here to deal with large extent trees.
@@ -2842,11 +2934,6 @@ again:
 				err = -EIO;
 				break;
 			}
-			if (ext4_ext_check_block(inode, ext_block_hdr(bh),
-							depth - i - 1, bh)) {
-				err = -EIO;
-				break;
-			}
 			path[i + 1].p_bh = bh;
 
 			/* save actual number of indexes since this
@@ -2961,6 +3048,23 @@ void ext4_ext_release(struct super_block *sb)
 #endif
 }
 
+static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
+{
+	ext4_lblk_t  ee_block;
+	ext4_fsblk_t ee_pblock;
+	unsigned int ee_len;
+
+	ee_block  = le32_to_cpu(ex->ee_block);
+	ee_len    = ext4_ext_get_actual_len(ex);
+	ee_pblock = ext4_ext_pblock(ex);
+
+	if (ee_len == 0)
+		return 0;
+
+	return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+				     EXTENT_STATUS_WRITTEN);
+}
+
 /* FIXME!! we need to try to merge to left or right after zero-out  */
 static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
@@ -3113,7 +3217,7 @@ static int ext4_split_extent_at(handle_t *handle,
 			goto fix_extent_len;
 
 		/* update extent status tree */
-		err = ext4_es_zeroout(inode, &zero_ex);
+		err = ext4_zeroout_es(inode, &zero_ex);
 
 		goto out;
 	} else if (err)
@@ -3133,7 +3237,7 @@ fix_extent_len:
  * ext4_split_extents() splits an extent and mark extent which is covered
  * by @map as split_flags indicates
  *
- * It may result in splitting the extent into multiple extents (upto three)
+ * It may result in splitting the extent into multiple extents (up to three)
  * There are three possibilities:
  *   a> There is no split required
  *   b> Splits in two extents: Split is happening at either end of the extent
@@ -3181,7 +3285,7 @@ static int ext4_split_extent(handle_t *handle,
 	 * result in split of original leaf or extent zeroout.
 	 */
 	ext4_ext_drop_refs(path);
-	path = ext4_ext_find_extent(inode, map->m_lblk, path);
+	path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	depth = ext_depth(inode);
@@ -3464,7 +3568,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 out:
 	/* If we have gotten a failure, don't zero out status tree */
 	if (!err)
-		err = ext4_es_zeroout(inode, &zero_ex);
+		err = ext4_zeroout_es(inode, &zero_ex);
 	return err ? err : allocated;
 }
 
@@ -3565,7 +3669,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 		if (err < 0)
 			goto out;
 		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, map->m_lblk, path);
+		path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out;
@@ -4052,7 +4156,7 @@ 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);
+	path = ext4_ext_find_extent(inode, map->m_lblk, NULL, 0);
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
 		path = NULL;
@@ -4744,6 +4848,12 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return error;
 	}
 
+	if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+		error = ext4_ext_precache(inode);
+		if (error)
+			return error;
+	}
+
 	/* fallback to generic here if not in extents fmt */
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return generic_block_fiemap(inode, fieinfo, start, len,
@@ -4771,6 +4881,6 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		error = ext4_fill_fiemap_extents(inode, start_blk,
 						 len_blks, fieinfo);
 	}
-
+	ext4_es_lru_add(inode);
 	return error;
 }
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 91cb110da1b4..2d1bdbe78c04 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -13,7 +13,6 @@
 #include <linux/list_sort.h>
 #include "ext4.h"
 #include "extents_status.h"
-#include "ext4_extents.h"
 
 #include <trace/events/ext4.h>
 
@@ -263,7 +262,7 @@ void ext4_es_find_delayed_extent_range(struct inode *inode,
 	if (tree->cache_es) {
 		es1 = tree->cache_es;
 		if (in_range(lblk, es1->es_lblk, es1->es_len)) {