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

Pull ext4 updates from Theodore Ts'o:
 "The one new feature added in this patch series is the ability to use
  the "punch hole" functionality for inodes that are not using extent
  maps.

  In the bug fix category, we fixed some races in the AIO and fstrim
  code, and some potential NULL pointer dereferences and memory leaks in
  error handling code paths.

  In the optimization category, we fixed a performance regression in the
  jbd2 layer introduced by commit d9b01934d56a ("jbd: fix fsync() tid
  wraparound bug", introduced in v3.0) which shows up in the AIM7
  benchmark.  We also further optimized jbd2 by minimize the amount of
  time that transaction handles are held active.

  This patch series also features some additional enhancement of the
  extent status tree, which is now used to cache extent information in a
  more efficient/compact form than what we use on-disk."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (65 commits)
  ext4: fix free clusters calculation in bigalloc filesystem
  ext4: no need to remove extent if len is 0 in ext4_es_remove_extent()
  ext4: fix xattr block allocation/release with bigalloc
  ext4: reclaim extents from extent status tree
  ext4: adjust some functions for reclaiming extents from extent status tree
  ext4: remove single extent cache
  ext4: lookup block mapping in extent status tree
  ext4: track all extent status in extent status tree
  ext4: let ext4_ext_map_blocks return EXT4_MAP_UNWRITTEN flag
  ext4: rename and improbe ext4_es_find_extent()
  ext4: add physical block and status member into extent status tree
  ext4: refine extent status tree
  ext4: use ERR_PTR() abstraction for ext4_append()
  ext4: refactor code to read directory blocks into ext4_read_dirblock()
  ext4: add debugging context for warning in ext4_da_update_reserve_space()
  ext4: use KERN_WARNING for warning messages
  jbd2: use module parameters instead of debugfs for jbd_debug
  ext4: use module parameters instead of debugfs for mballoc_debug
  ext4: start handle at the last possible moment when creating inodes
  ext4: fix the number of credits needed for acl ops with inline data
  ...

35 files changed, 2408 insertions, 1684 deletions

diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index e6e0d988439b..39a54a0e9fe4 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -324,8 +324,8 @@ ext4_acl_chmod(struct inode *inode)
 	if (error)
 		return error;
 retry:
-	handle = ext4_journal_start(inode,
-			EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
+				    ext4_jbd2_credits_xattr(inode));
 	if (IS_ERR(handle)) {
 		error = PTR_ERR(handle);
 		ext4_std_error(inode->i_sb, error);
@@ -422,7 +422,8 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
 		acl = NULL;
 
 retry:
-	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
+				    ext4_jbd2_credits_xattr(inode));
 	if (IS_ERR(handle)) {
 		error = PTR_ERR(handle);
 		goto release_and_out;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index cf1821784a16..2f2e0da1a6b7 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -358,7 +358,7 @@ void ext4_validate_block_bitmap(struct super_block *sb,
 }
 
 /**
- * ext4_read_block_bitmap()
+ * ext4_read_block_bitmap_nowait()
  * @sb:			super block
  * @block_group:	given block group
  *
@@ -457,6 +457,8 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct buffer_head *bh;
 
 	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	if (!bh)
+		return NULL;
 	if (ext4_wait_block_bitmap(sb, block_group, bh)) {
 		put_bh(bh);
 		return NULL;
@@ -482,11 +484,16 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
 
 	free_clusters  = percpu_counter_read_positive(fcc);
 	dirty_clusters = percpu_counter_read_positive(dcc);
-	root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
+
+	/*
+	 * r_blocks_count should always be multiple of the cluster ratio so
+	 * we are safe to do a plane bit shift only.
+	 */
+	root_clusters = ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
 
 	if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
 					EXT4_FREECLUSTERS_WATERMARK) {
-		free_clusters  = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
+		free_clusters  = percpu_counter_sum_positive(fcc);
 		dirty_clusters = percpu_counter_sum_positive(dcc);
 	}
 	/* Check whether we have space after accounting for current
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 80a28b297279..3882fbc5e215 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -185,6 +185,7 @@ static int ext4_readdir(struct file *filp,
 					"at offset %llu",
 					(unsigned long long)filp->f_pos);
 			filp->f_pos += sb->s_blocksize - offset;
+			brelse(bh);
 			continue;
 		}
 		set_buffer_verified(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8462eb3c33aa..6e16c1867959 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -194,8 +194,7 @@ struct mpage_da_data {
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 #define EXT4_IO_END_ERROR	0x0002
-#define EXT4_IO_END_QUEUED	0x0004
-#define EXT4_IO_END_DIRECT	0x0008
+#define EXT4_IO_END_DIRECT	0x0004
 
 struct ext4_io_page {
 	struct page	*p_page;
@@ -215,10 +214,8 @@ typedef struct ext4_io_end {
 	struct list_head	list;		/* per-file finished IO list */
 	struct inode		*inode;		/* file being written to */
 	unsigned int		flag;		/* unwritten or not */
-	struct page		*page;		/* for writepage() path */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
-	struct work_struct	work;		/* data work queue */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
 	int			num_io_pages;   /* for writepages() */
@@ -582,6 +579,8 @@ enum {
 #define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
 	/* Do not take i_data_sem locking in ext4_map_blocks */
 #define EXT4_GET_BLOCKS_NO_LOCK			0x0100
+	/* Do not put hole in extent cache */
+#define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
 
 /*
  * Flags used by ext4_free_blocks
@@ -810,17 +809,6 @@ do {									       \
 
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
-/*
- * storage for cached extent
- * If ec_len == 0, then the cache is invalid.
- * If ec_start == 0, then the cache represents a gap (null mapping)
- */
-struct ext4_ext_cache {
-	ext4_fsblk_t	ec_start;
-	ext4_lblk_t	ec_block;
-	__u32		ec_len; /* must be 32bit to return holes */
-};
-
 #include "extents_status.h"
 
 /*
@@ -887,7 +875,6 @@ struct ext4_inode_info {
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
-	struct ext4_ext_cache i_cached_extent;
 	/*
 	 * File creation time. Its function is same as that of
 	 * struct timespec i_{a,c,m}time in the generic inode.
@@ -901,6 +888,8 @@ struct ext4_inode_info {
 	/* extents status tree */
 	struct ext4_es_tree i_es_tree;
 	rwlock_t i_es_lock;
+	struct list_head i_es_lru;
+	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -930,6 +919,7 @@ struct ext4_inode_info {
 	spinlock_t i_completed_io_lock;
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
+	struct work_struct i_unwritten_work;	/* deferred extent conversion */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -985,7 +975,6 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_MBLK_IO_SUBMIT	0x4000000 /* multi-block io submits */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
@@ -1316,6 +1305,11 @@ struct ext4_sb_info {
 
 	/* Precomputed FS UUID checksum for seeding other checksums */
 	__u32 s_csum_seed;
+
+	/* Reclaim extents from extent status tree */
+	struct shrinker s_es_shrinker;
+	struct list_head s_es_lru;
+	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2007,9 +2001,20 @@ extern int ext4fs_dirhash(const char *name, int len, struct
 			  dx_hash_info *hinfo);
 
 /* ialloc.c */
-extern struct inode *ext4_new_inode(handle_t *, struct inode *, umode_t,
-				    const struct qstr *qstr, __u32 goal,
-				    uid_t *owner);
+extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
+				      const struct qstr *qstr, __u32 goal,
+				      uid_t *owner, int handle_type,
+				      unsigned int line_no, int nblocks);
+
+#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \
+	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
+			 0, 0, 0)
+#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
+				    type, nblocks)		    \
+	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
+			 (type), __LINE__, (nblocks))
+
+
 extern void ext4_free_inode(handle_t *, struct inode *);
 extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -2103,6 +2108,7 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
 extern void ext4_ind_truncate(struct inode *inode);
+extern int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -2151,6 +2157,8 @@ extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern void ext4_kvfree(void *ptr);
 extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
+extern const char *ext4_decode_error(struct super_block *sb, int errno,
+				     char nbuf[16]);
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
@@ -2227,6 +2235,8 @@ extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
 				       struct ext4_group_desc *gdp);
 extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
 				     struct ext4_group_desc *gdp);
+extern int ext4_register_li_request(struct super_block *sb,
+				    ext4_group_t first_not_zeroed);
 
 static inline int ext4_has_group_desc_csum(struct super_block *sb)
 {
@@ -2454,6 +2464,75 @@ extern const struct file_operations ext4_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 extern void ext4_unwritten_wait(struct inode *inode);
 
+/* inline.c */
+extern int ext4_has_inline_data(struct inode *inode);
+extern int ext4_get_inline_size(struct inode *inode);
+extern int ext4_get_max_inline_size(struct inode *inode);
+extern int ext4_find_inline_data_nolock(struct inode *inode);
+extern void ext4_write_inline_data(struct inode *inode,
+				   struct ext4_iloc *iloc,
+				   void *buffer, loff_t pos,
+				   unsigned int len);
+extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+				    unsigned int len);
+extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
+				 unsigned int len);
+extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
+
+extern int ext4_readpage_inline(struct inode *inode, struct page *page);
+extern int ext4_try_to_write_inline_data(struct address_space *mapping,
+					 struct inode *inode,
+					 loff_t pos, unsigned len,
+					 unsigned flags,
+					 struct page **pagep);
+extern int ext4_write_inline_data_end(struct inode *inode,
+				      loff_t pos, unsigned len,
+				      unsigned copied,
+				      struct page *page);
+extern struct buffer_head *
+ext4_journalled_write_inline_data(struct inode *inode,
+				  unsigned len,
+				  struct page *page);
+extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
+					   struct inode *inode,
+					   loff_t pos, unsigned len,
+					   unsigned flags,
+					   struct page **pagep,
+					   void **fsdata);
+extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
+					 unsigned len, unsigned copied,
+					 struct page *page);
+extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
+				     struct inode *inode);
+extern int ext4_try_create_inline_dir(handle_t *handle,
+				      struct inode *parent,
+				      struct inode *inode);
+extern int ext4_read_inline_dir(struct file *filp,
+				void *dirent, filldir_t filldir,
+				int *has_inline_data);
+extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+					const struct qstr *d_name,
+					struct ext4_dir_entry_2 **res_dir,
+					int *has_inline_data);
+extern int ext4_delete_inline_entry(handle_t *handle,
+				    struct inode *dir,
+				    struct ext4_dir_entry_2 *de_del,
+				    struct buffer_head *bh,
+				    int *has_inline_data);
+extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
+extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
+					struct ext4_dir_entry_2 **parent_de,
+					int *retval);
+extern int ext4_inline_data_fiemap(struct inode *inode,
+				   struct fiemap_extent_info *fieinfo,
+				   int *has_inline);
+extern int ext4_try_to_evict_inline_data(handle_t *handle,
+					 struct inode *inode,
+					 int needed);
+extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+
+extern int ext4_convert_inline_data(struct inode *inode);
+
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
 extern const struct inode_operations ext4_special_inode_operations;
@@ -2520,6 +2599,9 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
 						  struct ext4_ext_path *);
 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 int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
@@ -2537,6 +2619,7 @@ extern void ext4_exit_pageio(void);
 extern void ext4_ioend_wait(struct inode *);
 extern void ext4_free_io_end(ext4_io_end_t *io);
 extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern void ext4_end_io_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 487fda12bc00..8643ff5bbeb7 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -193,12 +193,6 @@ static inline unsigned short ext_depth(struct inode *inode)
 	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
 }
 
-static inline void
-ext4_ext_invalidate_cache(struct inode *inode)
-{
-	EXT4_I(inode)->i_cached_extent.ec_len = 0;
-}
-
 static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
 {
 	/* We can not have an uninitialized extent of zero length! */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index b4323ba846b5..7058975e3a55 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -6,6 +6,108 @@
 
 #include <trace/events/ext4.h>
 
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+	handle_t *handle = current->journal_info;
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+	ref_cnt++;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+	return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt == 0);
+
+	ref_cnt--;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ */
+handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
+				  int type, int nblocks)
+{
+	journal_t *journal;
+
+	trace_ext4_journal_start(sb, nblocks, _RET_IP_);
+	if (sb->s_flags & MS_RDONLY)
+		return ERR_PTR(-EROFS);
+
+	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
+	journal = EXT4_SB(sb)->s_journal;
+	if (!journal)
+		return ext4_get_nojournal();
+	/*
+	 * Special case here: if the journal has aborted behind our
+	 * backs (eg. EIO in the commit thread), then we still need to
+	 * take the FS itself readonly cleanly.
+	 */
+	if (is_journal_aborted(journal)) {
+		ext4_abort(sb, "Detected aborted journal");
+		return ERR_PTR(-EROFS);
+	}
+	return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line);
+}
+
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
+{
+	struct super_block *sb;
+	int err;
+	int rc;
+
+	if (!ext4_handle_valid(handle)) {
+		ext4_put_nojournal(handle);
+		return 0;
+	}
+	sb = handle->h_transaction->t_journal->j_private;
+	err = handle->h_err;
+	rc = jbd2_journal_stop(handle);
+
+	if (!err)
+		err = rc;
+	if (err)
+		__ext4_std_error(sb, where, line, err);
+	return err;
+}
+
+void ext4_journal_abort_handle(const char *caller, unsigned int line,
+			       const char *err_fn, struct buffer_head *bh,
+			       handle_t *handle, int err)
+{
+	char nbuf[16];
+	const char *errstr = ext4_decode_error(NULL, err, nbuf);
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	if (bh)
+		BUFFER_TRACE(bh, "abort");
+
+	if (!handle->h_err)
+		handle->h_err = err;
+
+	if (is_handle_aborted(handle))
+		return;
+
+	printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
+	       caller, line, errstr, err_fn);
+
+	jbd2_journal_abort_handle(handle);
+}
+
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh)
 {
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 7177f9b21cb2..4c216b1bf20c 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -59,12 +59,6 @@
 #define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
 					EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
 
-/* Delete operations potentially hit one directory's namespace plus an
- * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
- * generous.  We can grow the delete transaction later if necessary. */
-
-#define EXT4_DELETE_TRANS_BLOCKS(sb)	(2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
-
 /* Define an arbitrary limit for the amount of data we will anticipate
  * writing to any given transaction.  For unbounded transactions such as
  * write(2) and truncate(2) we can write more than this, but we always
@@ -110,6 +104,36 @@
 #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
 #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
+static inline int ext4_jbd2_credits_xattr(struct inode *inode)
+{
+	int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
+
+	/*
+	 * In case of inline data, we may push out the data to a block,
+	 * so we need to reserve credits for this eventuality
+	 */
+	if (ext4_has_inline_data(inode))
+		credits += ext4_writepage_trans_blocks(inode) + 1;
+	return credits;
+}
+
+
+/*
+ * Ext4 handle operation types -- for logging purposes
+ */
+#define EXT4_HT_MISC             0
+#define EXT4_HT_INODE            1
+#define EXT4_HT_WRITE_PAGE       2
+#define EXT4_HT_MAP_BLOCKS       3
+#define EXT4_HT_DIR              4
+#define EXT4_HT_TRUNCATE         5
+#define EXT4_HT_QUOTA            6
+#define EXT4_HT_RESIZE           7
+#define EXT4_HT_MIGRATE          8
+#define EXT4_HT_MOVE_EXTENTS     9
+#define EXT4_HT_XATTR           10
+#define EXT4_HT_MAX             11
+
 /**
  *   struct ext4_journal_cb_entry - Base structure for callback information.
  *
@@ -234,7 +258,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
 #define ext4_handle_dirty_super(handle, sb) \
 	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
 
-handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
+handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
+				  int type, int nblocks);
 int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
 
 #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
@@ -268,9 +293,17 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
 	return 1;
 }
 
-static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
+#define ext4_journal_start_sb(sb, type, nblocks)			\
+	__ext4_journal_start_sb((sb), __LINE__, (type), (nblocks))
+
+#define ext4_journal_start(inode, type, nblocks)			\
+	__ext4_journal_start((inode), __LINE__, (type), (nblocks))
+
+static inline handle_t *__ext4_journal_start(struct inode *inode,
+					     unsigned int line, int type,
+					     int nblocks)
 {
-	return ext4_journal_start_sb(inode->i_sb, nblocks);
+	return __ext4_journal_start_sb(inode->i_sb, line, type, nblocks);
 }
 
 #define ext4_journal_stop(handle) \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 5ae1674ec12f..372b2cbee07e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -112,7 +112,7 @@ static int ext4_split_extent_at(handle_t *handle,
 			     int flags);
 
 static int ext4_find_delayed_extent(struct inode *inode,
-				    struct ext4_ext_cache *newex);
+				    struct extent_status *newes);
 
 static int ext4_ext_truncate_extend_restart(handle_t *handle,
 					    struct inode *inode,
@@ -714,7 +714,6 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
 	eh->eh_magic = EXT4_EXT_MAGIC;
 	eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
 	ext4_mark_inode_dirty(handle, inode);
-	ext4_ext_invalidate_cache(inode);
 	return 0;
 }
 
@@ -725,6 +724,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 	struct ext4_extent_header *eh;
 	struct buffer_head *bh;
 	short int depth, i, ppos = 0, alloc = 0;
+	int ret;
 
 	eh = ext_inode_hdr(inode);
 	depth = ext_depth(inode);
@@ -752,12 +752,15 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 		path[ppos].p_ext = NULL;
 
 		bh = sb_getblk(inode->i_sb, path[ppos].p_block);
-		if (unlikely(!bh))
+		if (unlikely(!bh)) {
+			ret = -ENOMEM;
 			goto err;
+		}
 		if (!bh_uptodate_or_lock(bh)) {
 			trace_ext4_ext_load_extent(inode, block,
 						path[ppos].p_block);
-			if (bh_submit_read(bh) < 0) {
+			ret = bh_submit_read(bh);
+			if (ret < 0) {
 				put_bh(bh);
 				goto err;
 			}
@@ -768,13 +771,15 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 			put_bh(bh);
 			EXT4_ERROR_INODE(inode,
 					 "ppos %d > depth %d", ppos, depth);
+			ret = -EIO;
 			goto err;
 		}
 		path[ppos].p_bh = bh;
 		path[ppos].p_hdr = eh;
 		i--;
 
-		if (ext4_ext_check_block(inode, eh, i, bh))
+		ret = ext4_ext_check_block(inode, eh, i, bh);
+		if (ret < 0)
 			goto err;
 	}
 
@@ -796,7 +801,7 @@ err:
 	ext4_ext_drop_refs(path);
 	if (alloc)
 		kfree(path);
-	return ERR_PTR(-EIO);
+	return ERR_PTR(ret);
 }
 
 /*
@@ -950,8 +955,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		goto cleanup;
 	}
 	bh = sb_getblk(inode->i_sb, newblock);
-	if (!bh) {
-		err = -EIO;
+	if (unlikely(!bh)) {
+		err = -ENOMEM;
 		goto cleanup;
 	}
 	lock_buffer(bh);
@@ -1023,8 +1028,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		oldblock = newblock;
 		newblock = ablocks[--a];
 		bh = sb_getblk(inode->i_sb, newblock);
-		if (!bh) {
-			err = -EIO;
+		if (unlikely(!bh)) {
+			err = -ENOMEM;
 			goto cleanup;
 		}
 		lock_buffer(bh);
@@ -1136,11 +1141,8 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 		return err;
 
 	bh = sb_getblk(inode->i_sb, newblock);
-	if (!bh) {
-		err = -EIO;
-		ext4_std_error(inode->i_sb, err);
-		return err;
-	}
+	if (unlikely(!bh))
+		return -ENOMEM;
 	lock_buffer(bh);
 
 	err = ext4_journal_get_create_access(handle, bh);
@@ -1960,7 +1962,6 @@ cleanup:
 		ext4_ext_drop_refs(npath);
 		kfree(npath);
 	}
-	ext4_ext_invalidate_cache(inode);
 	return err;
 }
 
@@ -1969,8 +1970,8 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 				    struct fiemap_extent_info *fieinfo)
 {
 	struct ext4_ext_path *path = NULL;
-	struct ext4_ext_cache newex;
 	struct ext4_extent *ex;
+	struct extent_status es;
 	ext4_lblk_t next, next_del, start = 0, end = 0;
 	ext4_lblk_t last = block + num;
 	int exists, depth = 0, err = 0;
@@ -2044,37 +2045,47 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 		BUG_ON(end <= start);
 
 		if (!exists) {
-			newex.ec_block = start;
-			newex.ec_len = end - start;
-			newex.ec_start = 0;
+			es.es_lblk = start;
+			es.es_len = end - start;
+			es.es_pblk = 0;
 		} else {
-			newex.ec_block = le32_to_cpu(ex->ee_block);
-			newex.ec_len = ext4_ext_get_actual_len(ex);
-			newex.ec_start = ext4_ext_pblock(ex);
+			es.es_lblk = le32_to_cpu(ex->ee_block);
+			es.es_len = ext4_ext_get_actual_len(ex);
+			es.es_pblk = ext4_ext_pblock(ex);
 			if (ext4_ext_is_uninitialized(ex))
 				flags |= FIEMAP_EXTENT_UNWRITTEN;
 		}
 
 		/*
-		 * Find delayed extent and update newex accordingly. We call
-		 * it even in !exists case to find out whether newex is the
+		 * Find delayed extent and update es accordingly. We call
+		 * it even in !exists case to find out whether es is the
 		 * last existing extent or not.
 		 */
-		next_del = ext4_find_delayed_extent(inode, &newex);
+		next_del = ext4_find_delayed_extent(inode, &es);
 		if (!exists && next_del) {
 			exists = 1;
 			flags |= FIEMAP_EXTENT_DELALLOC;
 		}
 		up_read(&EXT4_I(inode)->i_data_sem);
 
-		if (unlikely(newex.ec_len == 0)) {
-			EXT4_ERROR_INODE(inode, "newex.ec_len == 0");
+		if (unlikely(es.es_len == 0)) {
+			EXT4_ERROR_INODE(inode, "es.es_len == 0");
 			err = -EIO;
 			break;
 		}
 
-		/* This is possible iff next == next_del == EXT_MAX_BLOCKS */
-		if (next == next_del) {
+		/*
+		 * This is possible iff next == next_del == EXT_MAX_BLOCKS.
+		 * we need to check next == EXT_MAX_BLOCKS because it is
+		 * possible that an extent is with unwritten and delayed
+		 * status due to when an extent is delayed allocated and
+		 * is allocated by fallocate status tree will track both of
+		 * them in a extent.
+		 *
+		 * So we could return a unwritten and delayed extent, and
+		 * its block is equal to 'next'.
+		 */
+		if (next == next_del && next == EXT_MAX_BLOCKS) {
 			flags |= FIEMAP_EXTENT_LAST;
 			if (unlikely(next_del != EXT_MAX_BLOCKS ||
 				     next != EXT_MAX_BLOCKS)) {
@@ -2089,9 +2100,9 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 
 		if (exists) {
 			err = fiemap_fill_next_extent(fieinfo,
-				(__u64)newex.ec_block << blksize_bits,
-				(__u64)newex.ec_start << blksize_bits,
-				(__u64)newex.ec_len << blksize_bits,
+				(__u64)es.es_lblk << blksize_bits,
+				(__u64)es.es_pblk << blksize_bits,
+				(__u64)es.es_len << blksize_bits,
 				flags);
 			if (err < 0)
 				break;
@@ -2101,7 +2112,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 			}
 		}
 
-		block = newex.ec_block + newex.ec_len;
+		block = es.es_lblk + es.es_len;
 	}
 
 	if (path) {
@@ -2112,21 +2123,6 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 	return err;
 }
 
-static void
-ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
-			__u32 len, ext4_fsblk_t start)
-{
-	struct ext4_ext_cache *cex;
-	BUG_ON(len == 0);
-	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-	trace_ext4_ext_put_in_cache(inode, block, len, start);
-	cex = &EXT4_I(inode)->i_cached_extent;
-	cex->ec_block = block;
-	cex->ec_len = len;
-	cex->ec_start = start;
-	spin_unlock(&EXT4_I(inode)-&g