Mostly performance and bug fixes, plus some cleanups. The one new

feature this merge window is a new ioctl EXT4_IOC_SWAP_BOOT which
 allows installation of a hidden inode designed for boot loaders.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABCAAGBQJRfpDwAAoJENNvdpvBGATwsjwP/17V3AN6XTEhZK80p3/qN5YD
 N2QIHeyYIqCGpczLs2TQEkxWX6nqpDggAPXY956wvgeEMQV+pQ+DLO4Ol9+p5WD2
 hrklleYhtOjFQ3Xh4lqrEi5FzKVzWagVDLqgUjALJ+D+hkDB7ZQT/fm2sH45rzot
 xBp3aVqANU8GqAAbEW4/Ng9ZGMx0dpANiU2svbjM71sv2dCLFmWAkz+GgZsMbuJZ
 vnKIZP6I6plwP3LuZzEbVCA7F2PzC4ywEOJKjIEvgHpX6uMDR3FX8pD5Dlo/o6e2
 eP+KLnD43mJMxBmTn22x5Sm0N6DUzJCEELRJWB9wCZoLdEvbEWRxT3qsPXfLWelG
 2jj4bImXF2CqYEsJww5FV2WdXXdnuM57pZym5vMZGAFyKPSCJobA4Y3XRdXkBfXf
 Gq/cFoPYv2EcBIhz3zrRj+tbY8esbO9wOnF6+x+AF10BspD2V7nuoVdWVhOf0A3v
 i9ifGPwLk3e3xHr9oXheo7IWn52oviZeyD77d7D7MLhgn+xU4LaVhW3R63Q+mI4D
 0TXG25R1CVcE7wyFy3gqSVXSCDO0JcQBL5LgcL+wAGXcHPAXqBpN2DFTPo+9fJH2
 g3YMwr+wMbci1XRVQ2vdTt/nBZYjOCh6PgRmg3KjTz11Ra5EsjQvYjKWYwqf2RGn
 QhCgbzd/qtZfNJztLvr7
 =GCT2
 -----END PGP SIGNATURE-----

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

Pull ext4 updates from Ted Ts'o:
 "Mostly performance and bug fixes, plus some cleanups.  The one new
  feature this merge window is a new ioctl EXT4_IOC_SWAP_BOOT which
  allows installation of a hidden inode designed for boot loaders."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (50 commits)
  ext4: fix type-widening bug in inode table readahead code
  ext4: add check for inodes_count overflow in new resize ioctl
  ext4: fix Kconfig documentation for CONFIG_EXT4_DEBUG
  ext4: fix online resizing for ext3-compat file systems
  jbd2: trace when lock_buffer in do_get_write_access takes a long time
  ext4: mark metadata blocks using bh flags
  buffer: add BH_Prio and BH_Meta flags
  ext4: mark all metadata I/O with REQ_META
  ext4: fix readdir error in case inline_data+^dir_index.
  ext4: fix readdir error in the case of inline_data+dir_index
  jbd2: use kmem_cache_zalloc instead of kmem_cache_alloc/memset
  ext4: mext_insert_extents should update extent block checksum
  ext4: move quota initialization out of inode allocation transaction
  ext4: reserve xattr index for Rich ACL support
  jbd2: reduce journal_head size
  ext4: clear buffer_uninit flag when submitting IO
  ext4: use io_end for multiple bios
  ext4: make ext4_bio_write_page() use BH_Async_Write flags
  ext4: Use kstrtoul() instead of parse_strtoul()
  ext4: defragmentation code cleanup
  ...

Documentation/filesystems/ext4.txt

@@ -494,6 +494,17 @@ Files in /sys/fs/ext4/<devname>
  session_write_kbytes         This file is read-only and shows the number of
                               kilobytes of data that have been written to this
                               filesystem since it was mounted.
+
+ reserved_clusters            This is RW file and contains number of reserved
+                              clusters in the file system which will be used
+                              in the specific situations to avoid costly
+                              zeroout, unexpected ENOSPC, or possible data
+                              loss. The default is 2% or 4096 clusters,
+                              whichever is smaller and this can be changed
+                              however it can never exceed number of clusters
+                              in the file system. If there is not enough space
+                              for the reserved space when mounting the file
+                              mount will _not_ fail.
 ..............................................................................
 
 Ioctls
@@ -587,6 +598,16 @@ Table of Ext4 specific ioctls
 			      bitmaps and inode table, the userspace tool thus
 			      just passes the new number of blocks.
 
+EXT4_IOC_SWAP_BOOT	      Swap i_blocks and associated attributes
+			      (like i_blocks, i_size, i_flags, ...) from
+			      the specified inode with inode
+			      EXT4_BOOT_LOADER_INO (#5). This is typically
+			      used to store a boot loader in a secure part of
+			      the filesystem, where it can't be changed by a
+			      normal user by accident.
+			      The data blocks of the previous boot loader
+			      will be associated with the given inode.
+
 ..............................................................................
 
 References

fs/buffer.c

@@ -2987,6 +2987,11 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	/* Take care of bh's that straddle the end of the device */
 	guard_bh_eod(rw, bio, bh);
 
+	if (buffer_meta(bh))
+		rw |= REQ_META;
+	if (buffer_prio(bh))
+		rw |= REQ_PRIO;
+
 	bio_get(bio);
 	submit_bio(rw, bio);
 

fs/ext4/Kconfig

@@ -71,4 +71,5 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
+	  with a command such as:
+		echo 1 > /sys/module/ext4/parameters/mballoc_debug

fs/ext4/balloc.c

@@ -29,6 +29,23 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
  * balloc.c contains the blocks allocation and deallocation routines
  */
 
+/*
+ * Calculate block group number for a given block number
+ */
+ext4_group_t ext4_get_group_number(struct super_block *sb,
+				   ext4_fsblk_t block)
+{
+	ext4_group_t group;
+
+	if (test_opt2(sb, STD_GROUP_SIZE))
+		group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
+			 block) >>
+			(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
+	else
+		ext4_get_group_no_and_offset(sb, block, &group, NULL);
+	return group;
+}
+
 /*
  * Calculate the block group number and offset into the block/cluster
  * allocation bitmap, given a block number
@@ -49,14 +66,18 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 
 }
 
-static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
+/*
+ * Check whether the 'block' lives within the 'block_group'. Returns 1 if so
+ * and 0 otherwise.
+ */
+static inline int ext4_block_in_group(struct super_block *sb,
+				      ext4_fsblk_t block,
 				      ext4_group_t block_group)
 {
 	ext4_group_t actual_group;
-	ext4_get_group_no_and_offset(sb, block, &actual_group, NULL);
+
-	if (actual_group == block_group)
+	actual_group = ext4_get_group_number(sb, block);
-		return 1;
+	return (actual_group == block_group) ? 1 : 0;
-	return 0;
 }
 
 /* Return the number of clusters used for file system metadata; this
@@ -420,7 +441,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	trace_ext4_read_block_bitmap_load(sb, block_group);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(READ, bh);
+	submit_bh(READ | REQ_META | REQ_PRIO, bh);
 	return bh;
 verify:
 	ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -478,20 +499,22 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
 				  s64 nclusters, unsigned int flags)
 {
-	s64 free_clusters, dirty_clusters, root_clusters;
+	s64 free_clusters, dirty_clusters, rsv, resv_clusters;
 	struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
 	struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
 
 	free_clusters  = percpu_counter_read_positive(fcc);
 	dirty_clusters = percpu_counter_read_positive(dcc);
+	resv_clusters = atomic64_read(&sbi->s_resv_clusters);
 
 	/*
 	 * 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;
+	rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) +
+	      resv_clusters;
 
-	if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
+	if (free_clusters - (nclusters + rsv + dirty_clusters) <
 					EXT4_FREECLUSTERS_WATERMARK) {
 		free_clusters  = percpu_counter_sum_positive(fcc);
 		dirty_clusters = percpu_counter_sum_positive(dcc);
@@ -499,7 +522,7 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
 	/* Check whether we have space after accounting for current
 	 * dirty clusters & root reserved clusters.
 	 */
-	if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters))
+	if (free_clusters >= (rsv + nclusters + dirty_clusters))
 		return 1;
 
 	/* Hm, nope.  Are (enough) root reserved clusters available? */
@@ -508,6 +531,12 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
 	    capable(CAP_SYS_RESOURCE) ||
 	    (flags & EXT4_MB_USE_ROOT_BLOCKS)) {
 
+		if (free_clusters >= (nclusters + dirty_clusters +
+				      resv_clusters))
+			return 1;
+	}
+	/* No free blocks. Let's see if we can dip into reserved pool */
+	if (flags & EXT4_MB_USE_RESERVED) {
 		if (free_clusters >= (nclusters + dirty_clusters))
 			return 1;
 	}

fs/ext4/dir.c

@@ -46,7 +46,8 @@ static int is_dx_dir(struct inode *inode)
 	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
 		     EXT4_FEATURE_COMPAT_DIR_INDEX) &&
 	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
-	     ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1) ||
+	     ext4_has_inline_data(inode)))
 		return 1;
 
 	return 0;
@@ -115,14 +116,6 @@ static int ext4_readdir(struct file *filp,
 	int ret = 0;
 	int dir_has_error = 0;
 
-	if (ext4_has_inline_data(inode)) {
-		int has_inline_data = 1;
-		ret = ext4_read_inline_dir(filp, dirent, filldir,
-					   &has_inline_data);
-		if (has_inline_data)
-			return ret;
-	}
-
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(filp, dirent, filldir);
 		if (err != ERR_BAD_DX_DIR) {
@@ -136,6 +129,15 @@ static int ext4_readdir(struct file *filp,
 		ext4_clear_inode_flag(file_inode(filp),
 				      EXT4_INODE_INDEX);
 	}
+
+	if (ext4_has_inline_data(inode)) {
+		int has_inline_data = 1;
+		ret = ext4_read_inline_dir(filp, dirent, filldir,
+					   &has_inline_data);
+		if (has_inline_data)
+			return ret;
+	}
+
 	stored = 0;
 	offset = filp->f_pos & (sb->s_blocksize - 1);
 

fs/ext4/ext4.h

@@ -121,6 +121,8 @@ typedef unsigned int ext4_group_t;
 #define EXT4_MB_STREAM_ALLOC		0x0800
 /* Use reserved root blocks if needed */
 #define EXT4_MB_USE_ROOT_BLOCKS		0x1000
+/* Use blocks from reserved pool */
+#define EXT4_MB_USE_RESERVED		0x2000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
@@ -196,19 +198,8 @@ struct mpage_da_data {
 #define EXT4_IO_END_ERROR	0x0002
 #define EXT4_IO_END_DIRECT	0x0004
 
-struct ext4_io_page {
-	struct page	*p_page;
-	atomic_t	p_count;
-};
-
-#define MAX_IO_PAGES 128
-
 /*
  * For converting uninitialized extents on a work queue.
- *
- * 'page' is only used from the writepage() path; 'pages' is only used for
- * buffered writes; they are used to keep page references until conversion
- * takes place.  For AIO/DIO, neither field is filled in.
  */
 typedef struct ext4_io_end {
 	struct list_head	list;		/* per-file finished IO list */
@@ -218,15 +209,13 @@ typedef struct ext4_io_end {
 	ssize_t			size;		/* size of the extent */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
-	int			num_io_pages;   /* for writepages() */
+	atomic_t		count;		/* reference counter */
-	struct ext4_io_page	*pages[MAX_IO_PAGES]; /* for writepages() */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
 	int			io_op;
 	struct bio		*io_bio;
 	ext4_io_end_t		*io_end;
-	struct ext4_io_page	*io_page;
 	sector_t		io_next_block;
 };
 
@@ -403,7 +392,7 @@ struct flex_groups {
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x004B80FF /* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE		0x004380FF /* User modifiable flags */
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
@@ -557,9 +546,8 @@ enum {
 #define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
 						 EXT4_GET_BLOCKS_CREATE)
-	/* Caller is from the delayed allocation writeout path,
+	/* Caller is from the delayed allocation writeout path
-	   so set the magic i_delalloc_reserve_flag after taking the
+	 * finally doing the actual allocation of delayed blocks */
-	   inode allocation semaphore for */
 #define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
 	/* caller is from the direct IO path, request to creation of an
 	unitialized extents if not allocated, split the uninitialized
@@ -571,8 +559,9 @@ enum {
 	/* Convert extent to initialized after IO complete */
 #define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
 					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
-	/* Punch out blocks of an extent */
+	/* Eventual metadata allocation (due to growing extent tree)
-#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT		0x0020
+	 * should not fail, so try to use reserved blocks for that.*/
+#define EXT4_GET_BLOCKS_METADATA_NOFAIL		0x0020
 	/* Don't normalize allocation size (used for fallocate) */
 #define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
 	/* Request will not result in inode size update (user for fallocate) */
@@ -616,6 +605,7 @@ enum {
 #define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
 #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)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -949,7 +939,7 @@ struct ext4_inode_info {
 #define EXT2_FLAGS_TEST_FILESYS		0x0004	/* to test development code */
 
 /*
- * Mount flags
+ * Mount flags set via mount options or defaults
  */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
@@ -981,8 +971,16 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
 #define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
 
+/*
+ * Mount flags set either automatically (could not be set by mount option)
+ * based on per file system feature or property or in special cases such as
+ * distinguishing between explicit mount option definition and default.
+ */
 #define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
 						      specified delalloc */
+#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
+						      size of blocksize * 8
+						      blocks */
 
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
@@ -1179,6 +1177,7 @@ struct ext4_sb_info {
 	unsigned int s_mount_flags;
 	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
+	atomic64_t s_resv_clusters;
 	kuid_t s_resuid;
 	kgid_t s_resgid;
 	unsigned short s_mount_state;
@@ -1333,6 +1332,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 	return ino == EXT4_ROOT_INO ||
 		ino == EXT4_USR_QUOTA_INO ||
 		ino == EXT4_GRP_QUOTA_INO ||
+		ino == EXT4_BOOT_LOADER_INO ||
 		ino == EXT4_JOURNAL_INO ||
 		ino == EXT4_RESIZE_INO ||
 		(ino >= EXT4_FIRST_INO(sb) &&
@@ -1374,6 +1374,7 @@ enum {
 	EXT4_STATE_DIOREAD_LOCK,	/* Disable support for dio read
 					   nolocking */
 	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
+	EXT4_STATE_ORDERED_MODE,	/* data=ordered mode */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -1784,9 +1785,6 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
  */
 #define ERR_BAD_DX_DIR	-75000
 
-void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
-			ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
-
 /*
  * Timeout and state flag for lazy initialization inode thread.
  */
@@ -1908,6 +1906,13 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 				  struct buffer_head *bh);
 
 /* balloc.c */
+extern void ext4_get_group_no_and_offset(struct super_block *sb,
+					 ext4_fsblk_t blocknr,
+					 ext4_group_t *blockgrpp,
+					 ext4_grpblk_t *offsetp);
+extern ext4_group_t ext4_get_group_number(struct super_block *sb,
+					  ext4_fsblk_t block);
+
 extern void ext4_validate_block_bitmap(struct super_block *sb,
 				       struct ext4_group_desc *desc,
 				       unsigned int block_group,
@@ -2108,8 +2113,9 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 				unsigned long nr_segs);
 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 void ext4_ind_truncate(handle_t *, struct inode *inode);
-extern int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length);
+extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
+				 ext4_lblk_t first, ext4_lblk_t stop);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -2117,6 +2123,7 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* migrate.c */
 extern int ext4_ext_migrate(struct inode *);
+extern int ext4_ind_migrate(struct inode *inode);
 
 /* namei.c */
 extern int ext4_dirent_csum_verify(struct inode *inode,
@@ -2511,6 +2518,11 @@ extern int ext4_try_create_inline_dir(handle_t *handle,
 extern int ext4_read_inline_dir(struct file *filp,
 				void *dirent, filldir_t filldir,
 				int *has_inline_data);
+extern int htree_inlinedir_to_tree(struct file *dir_file,
+				   struct inode *dir, ext4_lblk_t block,
+				   struct dx_hash_info *hinfo,
+				   __u32 start_hash, __u32 start_minor_hash,
+				   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,
@@ -2547,6 +2559,24 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
 extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
+#define S_SHIFT 12
+static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= EXT4_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= EXT4_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= EXT4_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= EXT4_FT_SYMLINK,
+};
+
+static inline void ext4_set_de_type(struct super_block *sb,
+				struct ext4_dir_entry_2 *de,
+				umode_t mode) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE))
+		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+}
+
 
 /* symlink.c */
 extern const struct inode_operations ext4_symlink_inode_operations;
@@ -2573,9 +2603,9 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 				       int chunk);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);
-extern void ext4_ext_truncate(struct inode *);
+extern void ext4_ext_truncate(handle_t *, struct inode *);
-extern int ext4_ext_punch_hole(struct file *file, loff_t offset,
+extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
-				loff_t length);
+				 ext4_lblk_t end);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
@@ -2609,17 +2639,26 @@ extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 
 /* move_extent.c */
+extern void ext4_double_down_write_data_sem(struct inode *first,
+					    struct inode *second);
+extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
+					  struct inode *donor_inode);
+void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
+void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
-extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
 extern void ext4_ioend_shutdown(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 ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
+extern int ext4_put_io_end(ext4_io_end_t *io_end);
+extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
+extern void ext4_io_submit_init(struct ext4_io_submit *io,
+				struct writeback_control *wbc);
 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,

fs/ext4/ext4_extents.h

@@ -270,5 +270,10 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
 				     0xffff);
 }
 
+#define ext4_ext_dirty(handle, inode, path) \
+		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
+		     struct inode *inode, struct ext4_ext_path *path);
+
 #endif /* _EXT4_EXTENTS */
 

fs/ext4/ext4_jbd2.c

@@ -43,6 +43,8 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
 {
 	journal_t *journal;
 
+	might_sleep();
+
 	trace_ext4_journal_start(sb, nblocks, _RET_IP_);
 	if (sb->s_flags & MS_RDONLY)
 		return ERR_PTR(-EROFS);
@@ -113,6 +115,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 {
 	int err = 0;
 
+	might_sleep();
+
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err)
@@ -209,6 +213,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 {
 	int err = 0;
 
+	might_sleep();
+
+	set_buffer_meta(bh);
+	set_buffer_prio(bh);
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_dirty_metadata(handle, bh);
 		if (err) {

fs/ext4/ext4_jbd2.h

@@ -29,11 +29,13 @@
  * block to complete the transaction.
  *
  * For extents-enabled fs we may have to allocate and modify up to
- * 5 levels of tree + root which are stored in the inode. */
+ * 5 levels of tree, data block (for each of these we need bitmap + group
+ * summaries), root which is stored in the inode, sb
+ */
 
 #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
 	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)   \
-	 ? 27U : 8U)
+	 ? 20U : 8U)
 
 /* Extended attribute operations touch at most two data buffers,
  * two bitmap buffers, and two group summaries, in addition to the inode
@@ -194,16 +196,20 @@ 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
  */
-static inline void ext4_journal_callback_del(handle_t *handle,
+static inline bool ext4_journal_callback_try_del(handle_t *handle,
 					     struct ext4_journal_cb_entry *jce)
 {
+	bool deleted;
 	struct ext4_sb_info *sbi =
 			EXT4_SB(handle->h_transaction->t_journal->j_private);
 
 	spin_lock(&sbi->s_md_lock);
+	deleted = !list_empty(&jce->jce_list);
 	list_del_init(&jce->jce_list);
 	spin_unlock(&sbi->s_md_lock);
+	return deleted;
 }
 
 int

fs/ext4/extents.c

@@ -157,11 +157,8 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
  *  - ENOMEM
  *  - EIO
  */
-#define ext4_ext_dirty(handle, inode, path) \
+int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
-		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+		     struct inode *inode, struct ext4_ext_path *path)
-static int __ext4_ext_dirty(const char *where, unsigned int line,
-			    handle_t *handle, struct inode *inode,
-			    struct ext4_ext_path *path)
 {
 	int err;
 	if (path->p_bh) {
@@ -1813,29 +1810,54 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	}
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
+	eh = path[depth].p_hdr;
 	if (unlikely(path[depth].p_hdr == NULL)) {
 		EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
 		return -EIO;
 	}
 
 	/* try to insert block into found extent and return */
-	if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
+	if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) {
-		&& ext4_can_extents_be_merged(inode, ex, newext)) {
+
-		ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n",
+		/*
+		 * 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
+		 * left, or on the right from the searched position. This
+		 * will make merging more effective.
+		 */
+		if (ex < EXT_LAST_EXTENT(eh) &&
+		    (le32_to_cpu(ex->ee_block) +
+		    ext4_ext_get_actual_len(ex) <
+		    le32_to_cpu(newext->ee_block))) {
+			ex += 1;
+			goto prepend;
+		} else if ((ex > EXT_FIRST_EXTENT(eh)) &&
+			   (le32_to_cpu(newext->ee_block) +
+			   ext4_ext_get_actual_len(newext) <
+			   le32_to_cpu(ex->ee_block)))
+			ex -= 1;
+
+		/* Try to append newex to the ex */
+		if (ext4_can_extents_be_merged(inode, ex, newext)) {
+			ext_debug("append [%d]%d block to %u:[%d]%d"
+				  "(from %llu)\n",
 				  ext4_ext_is_uninitialized(newext),
 				  ext4_ext_get_actual_len(newext),
 				  le32_to_cpu(ex->ee_block),
 				  ext4_ext_is_uninitialized(ex),
 				  ext4_ext_get_actual_len(ex),
 				  ext4_ext_pblock(ex));
-		err = ext4_ext_get_access(handle, inode, path + depth);
+			err = ext4_ext_get_access(handle, inode,
+						  path + depth);
 			if (err)
 				return err;
 
 			/*
-		 * ext4_can_extents_be_merged should have checked that either
+			 * ext4_can_extents_be_merged should have checked
-		 * both extents are uninitialized, or both aren't. Thus we
+			 * that either both extents are uninitialized, or
-		 * need to check only one of them here.
+			 * both aren't. Thus we need to check only one of
+			 * them here.
 			 */
 			if (ext4_ext_is_uninitialized(ex))
 				uninitialized = 1;
@@ -1848,6 +1870,43 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 			goto merge;
 		}
 
+prepend:
+		/* Try to prepend newex to the ex */
+		if (ext4_can_extents_be_merged(inode, newext, ex)) {
+			ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
+				  "(from %llu)\n",
+				  le32_to_cpu(newext->ee_block),
+				  ext4_ext_is_uninitialized(newext),
+				  ext4_ext_get_actual_len(newext),
+				  le32_to_cpu(ex->ee_block),
+				  ext4_ext_is_uninitialized(ex),
+				  ext4_ext_get_actual_len(ex),
+				  ext4_ext_pblock(ex));
+			err = ext4_ext_get_access(handle, inode,
+						  path + depth);
+			if (err)
+				return err;
+
+			/*
+			 * ext4_can_extents_be_merged should have checked
+			 * that either both extents are uninitialized, or
+			 * both aren't. Thus we need to check only one of
+			 * them here.
+			 */
+			if (ext4_ext_is_uninitialized(ex))
+				uninitialized = 1;
+			ex->ee_block = newext->ee_block;
+			ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
+			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+					+ ext4_ext_get_actual_len(newext));
+			if (uninitialized)
+				ext4_ext_mark_uninitialized(ex);
+			eh = path[depth].p_hdr;
+			nearex = ex;
+			goto merge;
+		}
+	}
+
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
@@ -1880,8 +1939,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	 * There is no free space in the found leaf.
 	 * We're gonna add a new leaf in the tree.
 	 */
-	if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT)
+	if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL)
-		flags = EXT4_MB_USE_ROOT_BLOCKS;
+		flags = EXT4_MB_USE_RESERVED;
 	err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
 	if (err)
 		goto cleanup;
@@ -2599,7 +2658,7 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
 	return 1;
 }
 
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 			  ext4_lblk_t end)
 {
 	struct super_block *sb = inode->i_sb;
@@ -2667,12 +2726,14 @@ again:
 
 			/*
 			 * Split the extent in two so that 'end' is the last
-			 * block in the first new extent
+			 * 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_GET_BLOCKS_PRE_IO |
-						EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+					EXT4_GET_BLOCKS_METADATA_NOFAIL);
 
 			if (err < 0)
 				goto out;
@@ -3147,35 +3208,35 @@ 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 *path,
+					   int flags)
 {
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
 	struct ext4_extent zero_ex;
-	struct ext4_extent *ex;
+	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
-	unsigned int ee_len, depth;
+	unsigned int ee_len, depth, map_len = map->m_len;
-	int allocated, max_zeroout = 0;
+	int allocated = 0, max_zeroout = 0;
 	int err = 0;
 	int split_flag = 0;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
-		(unsigned long long)map->m_lblk, map->m_len);
+		(unsigned long long)map->m_lblk, map_len);
 
 	sbi = EXT4_SB(inode->i_sb);
 	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
 		inode->i_sb->s_blocksize_bits;
-	if (eof_block < map->m_lblk + map->m_len)
+	if (eof_block < map->m_lblk + map_len)
-		eof_block = map->m_lblk + map->m_len;
+		eof_block = map->m_lblk + map_len;
 
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	allocated = ee_len - (map->m_lblk - ee_block);
 	zero_ex.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
@@ -3186,77 +3247,121 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 
 	/*
 	 * Attempt to transfer newly initialized blocks from the currently
-	 * uninitialized extent to its left neighbor. This is much cheaper
+	 * uninitialized extent to its neighbor. This is much cheaper
 	 * than an insertion followed by a merge as those involve costly
-	 * memmove() calls. This is the common case in steady state for
+	 * memmove() calls. Transferring to the left is the common case in
-	 * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
+	 * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
-	 * writes.
+	 * followed by append writes.
 	 *
 	 * Limitations of the current logic:
-	 *  - L1: we only deal with writes at the start of the extent.
+	 *  - L1: we do not deal with writes covering the whole extent.
-	 *    The approach could be extended to writes at the end
-	 *    of the extent but this scenario was deemed less common.
-	 *  - L2: we do not deal with writes covering the whole extent.
 	 *    This would require removing the extent if the transfer
 	 *    is possible.
-	 *  - L3: we only attempt to merge with an extent stored in the
+	 *  - L2: we only attempt to merge with an extent stored in the
 	 *    same extent tree node.
 	 */
-	if ((map->m_lblk == ee_block) &&	/*L1*/
+	if ((map->m_lblk == ee_block) &&
-		(map->m_len < ee_len) &&	/*L2*/
+		/* See if we can merge left */
-		(ex > EXT_FIRST_EXTENT(eh))) {	/*L3*/
+		(map_len < ee_len) &&		/*L1*/
-		struct ext4_extent *prev_ex;
+		(ex > EXT_FIRST_EXTENT(eh))) {	/*L2*/
 		ext4_lblk_t prev_lblk;
 		ext4_fsblk_t prev_pblk, ee_pblk;
-		unsigned int prev_len, write_len;
+		unsigned int prev_len;
 
-		prev_ex = ex - 1;
+		abut_ex = ex - 1;
-		prev_lblk = le32_to_cpu(prev_ex->ee_block);
+		prev_lblk = le32_to_cpu(abut_ex->ee_block);
-		prev_len = ext4_ext_get_actual_len(prev_ex);
+		prev_len = ext4_ext_get_actual_len(abut_ex);
-		prev_pblk = ext4_ext_pblock(prev_ex);
+		prev_pblk = ext4_ext_pblock(abut_ex);
 		ee_pblk = ext4_ext_pblock(ex);
-		write_len = map->m_len;
 
 		/*
-		 * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+		 * A transfer of blocks from 'ex' to 'abut_ex' is allowed
 		 * upon those conditions:
-		 * - C1: prev_ex is initialized,
+		 * - C1: abut_ex is initialized,
-		 * - C2: prev_ex is logically abutting ex,
+		 * - C2: abut_ex is logically abutting ex,
-		 * - C3: prev_ex is physically abutting ex,
+		 * - C3: abut_ex is physically abutting ex,
-		 * - C4: prev_ex can receive the additional blocks without
+		 * - C4: abut_ex can receive the additional blocks without
 		 *   overflowing the (initialized) length limit.
 		 */
-		if ((!ext4_ext_is_uninitialized(prev_ex)) &&		/*C1*/
+		if ((!ext4_ext_is_uninitialized(abut_ex)) &&		/*C1*/
 			((prev_lblk + prev_len) == ee_block) &&		/*C2*/
 			((prev_pblk + prev_len) == ee_pblk) &&		/*C3*/
-			(prev_len < (EXT_INIT_MAX_LEN - write_len))) {	/*C4*/
+			(prev_len < (EXT_INIT_MAX_LEN - map_len))) {	/*C4*/
 			err = ext4_ext_get_access(handle, inode, path + depth);
 			if (err)
 				goto out;
 
 			trace_ext4_ext_convert_to_initialized_fastpath(inode,
-				map, ex, prev_ex);
+				map, ex, abut_ex);
 
-			/* Shift the start of ex by 'write_len' blocks */
+			/* Shift the start of ex by 'map_len' blocks */
-			ex->ee_block = cpu_to_le32(ee_block + write_len);
+			ex->ee_block = cpu_to_le32(ee_block + map_len);
-			ext4_ext_store_pblock(ex, ee_pblk + write_len);
+			ext4_ext_store_pblock(ex, ee_pblk + map_len);
-			ex->ee_len = cpu_to_le16(ee_len - write_len);
+			ex->ee_len = cpu_to_le16(ee_len - map_len);
 			ext4_ext_mark_uninitialized(ex); /* Restore the flag */
 
-			/* Extend prev_ex by 'write_len' blocks */
+			/* Extend abut_ex by 'map_len' blocks */
-			prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+			abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
 
+			/* Result: number of initialized blocks past m_lblk */
+			allocated = map_len;
+		}
+	} else if (((map->m_lblk + map_len) == (ee_block + ee_len)) &&
+		   (map_len < ee_len) &&	/*L1*/
+		   ex < EXT_LAST_EXTENT(eh)) {	/*L2*/
+		/* See if we can merge right */
+		ext4_lblk_t next_lblk;
+		ext4_fsblk_t next_pblk, ee_pblk;
+		unsigned int next_len;
+
+		abut_ex = ex + 1;
+		next_lblk = le32_to_cpu(abut_ex->ee_block);
+		next_len = ext4_ext_get_actual_len(abut_ex);
+		next_pblk = ext4_ext_pblock(abut_ex);
+		ee_pblk = ext4_ext_pblock(ex);
+
+		/*
+		 * A transfer of blocks from 'ex' to 'abut_ex' is allowed
+		 * upon those conditions:
+		 * - C1: abut_ex is initialized,
+		 * - C2: abut_ex is logically abutting ex,
+		 * - C3: abut_ex is physically abutting ex,
+		 * - C4: abut_ex can receive the additional blocks without
+		 *   overflowing the (initialized) length limit.
+		 */
+		if ((!ext4_ext_is_uninitialized(abut_ex)) &&		/*C1*/
+		    ((map->m_lblk + map_len) == next_lblk) &&		/*C2*/
+		    ((ee_pblk + ee_len) == next_pblk) &&		/*C3*/
+		    (next_len < (EXT_INIT_MAX_LEN - map_len))) {	/*C4*/
+			err = ext4_ext_get_access(handle, inode, path + depth);
+			if (err)
+				goto out;
+
+			trace_ext4_ext_convert_to_initialized_fastpath(inode,
+				map, ex, abut_ex);
+
+			/* Shift the start of abut_ex by 'map_len' blocks */
+			abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
+			ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
+			ex->ee_len = cpu_to_le16(ee_len - map_len);
+			ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+
+			/* Extend abut_ex by 'map_len' blocks */
+			abut_ex->ee_len = cpu_to_le16(next_len + map_len);
+
+			/* Result: number of initialized blocks past m_lblk */
+			allocated = map_len;
+		}
+	}
+	if (allocated) {
 		/* Mark the block containing both extents as dirty */
 		ext4_ext_dirty(handle, inode, path + depth);
 
 		/* Update path to point to the right extent */
-			path[depth].p_ext = prev_ex;
+		path[depth].p_ext = abut_ex;
-
-			/* Result: number of initialized blocks past m_lblk */
-			allocated = write_len;
 		goto out;
-		}
+	} else
-	}
+		allocated = ee_len - (map->m_lblk - ee_block);
 
 	WARN_ON(map->m_lblk < ee_block);
 	/*
@@ -3330,7 +3435,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	}
 
 	allocated = ext4_split_extent(handle, inode, path,
-				      &split_map, split_flag, 0);
+				      &split_map, split_flag, flags);
 	if (allocated < 0)
 		err = allocated;
 
@@ -3650,6 +3755,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
 
+	/*
+	 * When writing into uninitialized space, we should not fail to
+	 * allocate metadata blocks for the new extent block if needed.
+	 */
+	flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
+
 	trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
 						    allocated, newblock);
 
@@ -3713,7 +3824,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	}
 
 	/* buffered write, writepage time, convert*/
-	ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
+	ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags);
 	if (ret >= 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 out:
@@ -4257,47 +4368,12 @@ out3:
 	return err ? err : allocated;
 }
 
-void ext4_ext_truncate(struct inode *inode)
+void ext4_ext_truncate(handle_t *handle, struct inode *inode)
 {
-	struct address_space *mapping = inode->i_mapping;
 	struct super_block *sb = inode->i_sb;
 	ext4_lblk_t last_block;
-	handle_t *handle;
-	loff_t page_len;
 	int err = 0;
 
-	/*
-	 * finish any pending end_io work so we won't run the risk of
-	 * converting any truncated blocks to initialized later
-	 */
-	ext4_flush_unwritten_io(inode);
-
-	/*
-	 * probably first extent we're gonna free will be last in block
-	 */
-	err = ext4_writepage_trans_blocks(inode);
-	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, err);
-	if (IS_ERR(handle))
-		return;
-
-	if (inode->i_size % PAGE_CACHE_SIZE != 0) {
-		page_len = PAGE_CACHE_SIZE -
-			(inode->i_size & (PAGE_CACHE_SIZE - 1));
-
-		err = ext4_discard_partial_page_buffers(handle,
-			mapping, inode->i_size, page_len, 0);
-
-		if (err)
-			goto out_stop;
-	}
-
-	if (ext4_orphan_add(handle, inode))
-		goto out_stop;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-
-	ext4_discard_preallocations(inode);
-
 	/*
 	 * TODO: optimization is possible here.
 	 * Probably we need not scan at all,
@@ -4313,29 +4389,6 @@ void ext4_ext_truncate(struct inode *inode)
 	err = ext4_es_remove_extent(inode, last_block,
 				    EXT_MAX_BLOCKS - last_block);
 	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
-
-	/* In a multi-transaction truncate, we only make the final
-	 * transaction synchronous.
-	 */
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
-	up_write(&EXT4_I(inode)->i_data_sem);
-
-out_stop:
-	/*
-	 * If this was a simple ftruncate() and the file will remain alive,
-	 * then we need to clear up the orphan record which we created above.
-	 * However, if this was a real unlink then we were called by
-	 * ext4_delete_inode(), and we allow that function to clean up the
-	 * orphan info for us.
-	 */
-	if (inode->i_nlink)
-		ext4_orphan_del(handle, inode);
-
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	ext4_journal_stop(handle);
 }
 
 static void ext4_falloc_update_inode(struct inode *inode,
@@ -4623,187 +4676,6 @@ static int ext4_xattr_fiemap(struct inode *inode,
 	return (error < 0 ? error : 0);
 }
 
-/*
- * ext4_ext_punch_hole
- *
- * Punches a hole of "length" bytes in a file starting
- * at byte "offset"
- *
- * @inode:  The inode of the file to punch a hole in
- * @offset: The starting byte offset of the hole
- * @length: The length of the hole
- *
- * Returns the number of blocks removed or negative on err
- */
-int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
-{
-	struct inode *inode = file_inode(file);
-	struct super_block *sb = inode->i_sb;
-	ext4_lblk_t first_block, stop_block;
-	struct address_space *mapping = inode->i_mapping;
-	handle_t *handle;
-	loff_t first_page, last_page, page_len;
-	loff_t first_page_offset, last_page_offset;
-	int credits, err = 0;
-
-	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		err = filemap_write_and_wait_range(mapping,
-			offset, offset + length - 1);
-
-		if (err)
-			return err;
-	}
-
-	mutex_lock(&inode->i_mutex);
-	/* It's not possible punch hole on append only file */
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
-		err = -EPERM;
-		goto out_mutex;
-	}
-	if (IS_SWAPFILE(inode)) {
-		err = -ETXTBSY;
-		goto out_mutex;
-	}
-
-	/* No need to punch hole beyond i_size */
-	if (offset >= inode->i_size)
-		goto out_mutex;
-
-	/*
-	 * If the hole extends beyond i_size, set the hole
-	 * to end after the page that contains i_size
-	 */
-	if (offset + length > inode->i_size) {
-		length = inode->i_size +
-		   PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
-		   offset;
-	}
-
-	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
-
-	first_page_offset = first_page << PAGE_CACHE_SHIFT;
-	last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
-	/* Now release the pages */
-	if (last_page_offset > first_page_offset) {
-		truncate_pagecache_range(inode, first_page_offset,
-					 last_page_offset - 1);
-	}
-
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	err = ext4_flush_unwritten_io(inode);
-	if (err)
-		goto out_dio;
-	inode_dio_wait(inode);
-
-	credits = ext4_writepage_trans_blocks(inode);
-	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
-	if (IS_ERR(handle)) {
-		err = PTR_ERR(handle);
-		goto out_dio;
-	}
-
-
-	/*
-	 * Now we need to zero out the non-page-aligned data in the
-	 * pages at the start and tail of the hole, and unmap the buffer
-	 * heads for the block aligned regions of the page that were
-	 * completely zeroed.
-	 */
-	if (first_page > last_page) {
-		/*
-		 * If the file space being truncated is contained within a page
-		 * just zero out and unmap the middle of that page
-		 */
-		err = ext4_discard_partial_page_buffers(handle,
-			mapping, offset, length, 0);
-
-		if (err)
-			goto out;
-	} else {
-		/*
-		 * zero out and unmap the partial page that contains
-		 * the start of the hole
-		 */
-		page_len  = first_page_offset - offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-						   offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-
-		/*
-		 * zero out and unmap the partial page that contains
-		 * the end of the hole
-		 */
-		page_len = offset + length - last_page_offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-					last_page_offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-	}
-
-	/*
-	 * If i_size is contained in the last page, we need to
-	 * unmap and zero the partial page after i_size
-	 */
-	if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
-	   inode->i_size % PAGE_CACHE_SIZE != 0) {
-
-		page_len = PAGE_CACHE_SIZE -
-			(inode->i_size & (PAGE_CACHE_SIZE - 1));
-
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle,
-			  mapping, inode->i_size, page_len, 0);
-
-			if (err)
-				goto out;
-		}
-	}
-
-	first_block = (offset + sb->s_blocksize - 1) >>
-		EXT4_BLOCK_SIZE_BITS(sb);
-	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
-	/* If there are no blocks to remove, return now */
-	if (first_block >= stop_block)
-		goto out;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
-
-	err = ext4_es_remove_extent(inode, first_block,
-				    stop_block - first_block);
-	err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
-
-	ext4_discard_preallocations(inode);
-
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
-	up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	ext4_journal_stop(handle);
-out_dio:
-	ext4_inode_resume_unlocked_dio(inode);
-out_mutex:
-	mutex_unlock(&inode->i_mutex);
-	return err;
-}
-
 int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len)
 {

fs/ext4/fsync.c

@@ -166,8 +166,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		needs_barrier = true;
-	jbd2_log_start_commit(journal, commit_tid);
+	ret = jbd2_complete_transaction(journal, commit_tid);
-	ret = jbd2_log_wait_commit(journal, commit_tid);
 	if (needs_barrier) {
 		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 		if (!ret)

fs/ext4/ialloc.c

@@ -166,7 +166,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	trace_ext4_load_inode_bitmap(sb, block_group);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(READ, bh);
+	submit_bh(READ | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
@@ -666,6 +666,23 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	ei = EXT4_I(inode);
 	sbi = EXT4_SB(sb);
 
+	/*
+	 * Initalize owners and quota early so that we don't have to account
+	 * for quota initialization worst case in standard inode creating
+	 * transaction
+	 */
+	if (owner) {
+		inode->i_mode = mode;
+		i_uid_write(inode, owner[0]);
+		i_gid_write(inode, owner[1]);
+	} else if (test_opt(sb, GRPID)) {
+		inode->i_mode = mode;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = dir->i_gid;
+	} else
+		inode_init_owner(inode, dir, mode);
+	dquot_initialize(inode);
+
 	if (!goal)
 		goal = sbi->s_inode_goal;
 
@@ -697,7 +714,7 @@ got_group:
 
 		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
 		if (!gdp)
-			goto fail;
+			goto out;
 
 		/*
 		 * Check free inodes count before loading bitmap.
@@ -711,7 +728,7 @@ got_group:
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		if (!inode_bitmap_bh)
-			goto fail;
+			goto out;
 
 repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
@@ -733,13 +750,16 @@ repeat_in_this_group:
 							 handle_type, nblocks);
 			if (IS_ERR(handle)) {
 				err = PTR_ERR(handle);
-				goto fail;
+				ext4_std_error(sb, err);
+				goto out;
 			}
 		}
 		BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
-		if (err)
+		if (err) {
-			goto fail;
+			ext4_std_error(sb, err);
+			goto out;
+		}
 		ext4_lock_group(sb, group);
 		ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
 		ext4_unlock_group(sb, group);
@@ -755,8 +775,10 @@ repeat_in_this_group:
 got:
 	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
-	if (err)
+	if (err) {
-		goto fail;
+		ext4_std_error(sb, err);
+		goto out;
+	}
 
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
@@ -768,7 +790,8 @@ got:
 		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
 			brelse(block_bitmap_bh);
-			goto fail;
+			ext4_std_error(sb, err);
+			goto out;
 		}
 
 		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
@@ -787,14 +810,18 @@ got:
 		ext4_unlock_group(sb, group);
 		brelse(block_bitmap_bh);
 
-		if (err)
+		if (err) {
-			goto fail;
+			ext4_std_error(sb, err);
+			goto out;
+		}
 	}
 
 	BUFFER_TRACE(group_desc_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err)
+	if (err) {
-		goto fail;
+		ext4_std_error(sb, err);
+		goto out;
+	}
 
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
@@ -840,8 +867,10 @@ got:
 
 	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
-	if (err)
+	if (err) {
-		goto fail;
+		ext4_std_error(sb, err);
+		goto out;
+	}
 
 	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
@@ -851,16 +880,6 @@ got:
 		flex_group = ext4_flex_group(sbi, group);
 		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
 	}
-	if (owner) {
-		inode->i_mode = mode;
-		i_uid_write(inode, owner[0]);
-		i_gid_write(inode, owner[1]);
-	} else if (test_opt(sb, GRPID)) {
-		inode->i_mode = mode;
-		inode->i_uid = current_fsuid();
-		inode->i_gid = dir->i_gid;
-	} else
-		inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
 	/* This is the optimal IO size (for stat), not the fs block size */
@@ -889,7 +908,9 @@ got:
 		 * twice.
 		 */
 		err = -EIO;
-		goto fail;
+		ext4_error(sb, "failed to insert inode %lu: doubly allocated?",
+			   inode->i_ino);
+		goto out;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
@@ -899,7 +920,6 @@ got:
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
 		__u32 csum;
-		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 		__le32 inum = cpu_to_le32(inode->i_ino);
 		__le32 gen = cpu_to_le32(inode->i_generation);
 		csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
@@ -918,7 +938,6 @@ got:
 		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 
 	ret = inode;
-	dquot_initialize(inode);
 	err = dquot_alloc_inode(inode);
 	if (err)
 		goto fail_drop;
@@ -952,24 +971,17 @@ got:
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
 	trace_ext4_allocate_inode(inode, dir, mode);
-	goto really_out;
-fail:
-	ext4_std_error(sb, err);
-out:
-	iput(inode);
-	ret = ERR_PTR(err);
-really_out:
 	brelse(inode_bitmap_bh);
 	return ret;
 
 fail_free_drop:
 	dquot_free_inode(inode);
-
 fail_drop:
-	dquot_drop(inode);
-	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
 	unlock_new_inode(inode);
+out:
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
 	iput(inode);
 	brelse(inode_bitmap_bh);
 	return ERR_PTR(err);

fs/ext4/indirect.c

@@ -291,131 +291,6 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
 	return count;
 }
 
-/**
- *	ext4_alloc_blocks: multiple allocate blocks needed for a branch
- *	@handle: handle for this transaction
- *	@inode: inode which needs allocated blocks
- *	@iblock: the logical block to start allocated at
- *	@goal: preferred physical block of allocation
- *	@indirect_blks: the number of blocks need to allocate for indirect
- *			blocks
- *	@blks: number of desired blocks
- *	@new_blocks: on return it will store the new block numbers for
- *	the indirect blocks(if needed) and the first direct block,
- *	@err: on return it will store the error code
- *
- *	This function will return the number of blocks allocated as
- *	requested by the passed-in parameters.
- */
-static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
-			     ext4_lblk_t iblock, ext4_fsblk_t goal,
-			     int indirect_blks, int blks,
-			     ext4_fsblk_t new_blocks[4], int *err)
-{
-	struct ext4_allocation_request ar;
-	int target, i;
-	unsigned long count = 0, blk_allocated = 0;
-	int index = 0;
-	ext4_fsblk_t current_block = 0;
-	int ret = 0;
-
-	/*
-	 * Here we try to allocate the requested multiple blocks at once,
-	 * on a best-effort basis.
-	 * To build a branch, we should allocate blocks for
-	 * the indirect blocks(if not allocated yet), and at least
-	 * the first direct block of this branch.  That's the
-	 * minimum number of blocks need to allocate(required)
-	 */
-	/* first we try to allocate the indirect blocks */
-	target = indirect_blks;
-	while (target > 0) {
-		count = target;
-		/* allocating blocks for indirect blocks and direct blocks */
-		current_block = ext4_new_meta_blocks(handle, inode, goal,
-						     0, &count, err);
-		if (*err)
-			goto failed_out;
-
-		if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
-			EXT4_ERROR_INODE(inode,
-					 "current_block %llu + count %lu > %d!",
-					 current_block, count,
-					 EXT4_MAX_BLOCK_FILE_PHYS);
-			*err = -EIO;
-			goto failed_out;
-		}
-
-		target -= count;
-		/* allocate blocks for indirect blocks */
-		while (index < indirect_blks && count) {
-			new_blocks[index++] = current_block++;
-			count--;
-		}
-		if (count > 0) {
-			/*
-			 * save the new block number
-			 * for the first direct block
-			 */
-			new_blocks[index] = current_block;
-			WARN(1, KERN_INFO "%s returned more blocks than "
-						"requested\n", __func__);
-			break;
-		}
-	}
-
-	target = blks - count ;
-	blk_allocated = count;
-	if (!target)
-		goto allocated;
-	/* Now allocate data blocks */
-	memset(&ar, 0, sizeof(ar));
-	ar.inode = inode;
-	ar.goal = goal;
-	ar.len = target;
-	ar.logical = iblock;
-	if (S_ISREG(inode->i_mode))
-		/* enable in-core preallocation only for regular files */
-		ar.flags = EXT4_MB_HINT_DATA;
-
-	current_block = ext4_mb_new_blocks(handle, &ar, err);
-	if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
-		EXT4_ERROR_INODE(inode,
-				 "current_block %llu + ar.len %d > %d!",
-				 current_block, ar.len,
-				 EXT4_MAX_BLOCK_FILE_PHYS);
-		*err = -EIO;
-		goto failed_out;
-	}
-
-	if (*err && (target == blks)) {
-		/*
-		 * if the allocation failed and we didn't allocate
-		 * any blocks before
-		 */
-		goto failed_out;
-	}
-	if (!*err) {
-		if (target == blks) {
-			/*
-			 * save the new block number
-			 * for the first direct block
-			 */
-			new_blocks[index] = current_block;
-		}
-		blk_allocated += ar.len;
-	}
-allocated:
-	/* total number of blocks allocated for direct blocks */
-	ret = blk_allocated;
-	*err = 0;
-	return ret;
-failed_out:
-	for (i = 0; i < index; i++)
-		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
-	return ret;
-}
-
 /**
  *	ext4_alloc_branch - allocate and set up a chain of blocks.
  *	@handle: handle for this transaction
@@ -448,60 +323,59 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 			     int *blks, ext4_fsblk_t goal,
 			     ext4_lblk_t *offsets, Indirect *branch)
 {
-	int blocksize = inode->i_sb->s_blocksize;
+	struct ext4_allocation_request	ar;
-	int i, n = 0;
-	int err = 0;
 	struct buffer_head *		bh;
-	int num;
+	ext4_fsblk_t			b, new_blocks[4];
-	ext4_fsblk_t new_blocks[4];
+	__le32				*p;
-	ext4_fsblk_t current_block;
+	int				i, j, err, len = 1;
 
-	num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks,
+	/*
-				*blks, new_blocks, &err);
+	 * Set up for the direct block allocation
-	if (err)
+	 */
-		return err;
+	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;
 
-	branch[0].key = cpu_to_le32(new_blocks[0]);
+	for (i = 0; i <= indirect_blks; i++) {
-	/*
+		if (i == indirect_blks) {
-	 * metadata blocks and data blocks are allocated.
+			ar.goal = goal;
-	 */
+			new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err);
-	for (n = 1; n <= indirect_blks;  n++) {
+		} else
-		/*
+			goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode,
-		 * Get buffer_head for parent block, zero it out
+							goal, 0, NULL, &err);
-		 * and set the pointer to new one, then send
+		if (err) {
-		 * parent to disk.
+			i--;
-		 */
+			goto failed;
-		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+		}
+		branch[i].key = cpu_to_le32(new_blocks[i]);
+		if (i == 0)
+			continue;
+
+		bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]);
 		if (unlikely(!bh)) {
 			err = -ENOMEM;
 			goto failed;
 		}
-
-		branch[n].bh = bh;
 		lock_buffer(bh);
 		BUFFER_TRACE(bh, "call get_create_access");
 		err = ext4_journal_get_create_access(handle, bh);
 		if (err) {
-			/* Don't brelse(bh) here; it's done in
-			 * ext4_journal_forget() below */
 			unlock_buffer(bh);
 			goto failed;
 		}
 
-		memset(bh->b_data, 0, blocksize);
+		memset(bh->b_data, 0, bh->b_size);
-		branch[n].p = (__le32 *) bh->b_data + offsets[n];
+		p = branch[i].p = (__le32 *) bh->b_data + offsets[i];
-		branch[n].key = cpu_to_le32(new_blocks[n]);
+		b = new_blocks[i];
-		*branch[n].p = branch[n].key;
+
-		if (n == indirect_blks) {
+		if (i == indirect_blks)
-			current_block = new_blocks[n];
+			len = ar.len;
-			/*
+		for (j = 0; j < len; j++)
-			 * End of chain, update the last new metablock of
+			*p++ = cpu_to_le32(b++);
-			 * the chain to point to the new allocated
+
-			 * data blocks numbers
-			 */
-			for (i = 1; i < num; i++)
-				*(branch[n].p + i) = cpu_to_le32(++current_block);
-		}
 		BUFFER_TRACE(bh, "marking uptodate");
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
@@ -511,25 +385,16 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 		if (err)
 			goto failed;
 	}
-	*blks = num;
+	*blks = ar.len;
-	return err;
+	return 0;
 failed:
-	/* Allocation failed, free what we already allocated */
+	for (; i >= 0; i--) {
-	ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
+		if (i != indirect_blks && branch[i].bh)
-	for (i = 1; i <= n ; i++) {
+			ext4_forget(handle, 1, inode, branch[i].bh,
-		/*
+				    branch[i].bh->b_blocknr);
-		 * branch[i].bh is newly allocated, so there is no
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
-		 * need to revoke the block, which is why we don't
+				 (i == indirect_blks) ? ar.len : 1, 0);
-		 * need to set EXT4_FREE_BLOCKS_METADATA.
-		 */
-		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
-				 EXT4_FREE_BLOCKS_FORGET);
 	}
-	for (i = n+1; i < indirect_blks; i++)
-		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
-
-	ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
-
 	return err;
 }
 
@@ -941,26 +806,9 @@ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk)
  * be able to restart the transaction at a conventient checkpoint to make
  * sure we don't overflow the journal.
  *
- * start_transaction gets us a new handle for a truncate transaction,
+ * Try to extend this transaction for the purposes of truncation.  If
- * and extend_transaction tries to extend the existing one a bit.  If
  * extend fails, we need to propagate the failure up and restart the
  * transaction in the top-level truncate loop. --sct
- */
-static handle_t *start_transaction(struct inode *inode)
-{
-	handle_t *result;
-
-	result = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
-				    ext4_blocks_for_truncate(inode));
-	if (!IS_ERR(result))
-		return result;
-
-	ext4_std_error(inode->i_sb, PTR_ERR(result));
-	return result;
-}
-
-/*
- * Try to extend this transaction for the purposes of truncation.
  *
  * Returns 0 if we managed to create more room.  If we can't create more
  * room, and the transaction must be restarted we return 1.
@@ -1353,68 +1201,30 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 	}
 }
 
-void ext4_ind_truncate(struct inode *inode)
+void ext4_ind_truncate(handle_t *handle, struct inode *inode)
 {
-	handle_t *handle;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	__le32 *i_data = ei->i_data;
 	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-	struct address_space *mapping = inode->i_mapping;
 	ext4_lblk_t offsets[4];
 	Indirect chain[4];
 	Indirect *partial;
 	__le32 nr = 0;
 	int n = 0;
 	ext4_lblk_t last_block, max_block;
-	loff_t page_len;
 	unsigned blocksize = inode->i_sb->s_blocksize;
-	int err;
-
-	handle = start_transaction(inode);
-	if (IS_ERR(handle))
-		return;		/* AKPM: return what? */
 
 	last_block = (inode->i_size + blocksize-1)
 					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
 	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
 					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
 
-	if (inode->i_size % PAGE_CACHE_SIZE != 0) {
-		page_len = PAGE_CACHE_SIZE -
-			(inode->i_size & (PAGE_CACHE_SIZE - 1));
-
-		err = ext4_discard_partial_page_buffers(handle,
-			mapping, inode->i_size, page_len, 0);
-
-		if (err)
-			goto out_stop;
-	}
-
 	if (last_block != max_block) {
 		n = ext4_block_to_path(inode, last_block, offsets, NULL);
 		if (n == 0)
-			goto out_stop;	/* error */
+			return;
 	}
 
-	/*
-	 * OK.  This truncate is going to happen.  We add the inode to the
-	 * orphan list, so that if this truncate spans multiple transactions,
-	 * and we crash, we will resume the truncate when the filesystem
-	 * recovers.  It also marks the inode dirty, to catch the new size.
-	 *
-	 * Implication: the file must always be in a sane, consistent
-	 * truncatable state while each transaction commits.
-	 */
-	if (ext4_orphan_add(handle, inode))
-		goto out_stop;
-
-	/*
-	 * From here we block out all ext4_get_block() callers who want to
-	 * modify the block allocation tree.
-	 */
-	down_write(&ei->i_data_sem);
-
-	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);
 
 	/*
@@ -1431,7 +1241,7 @@ void ext4_ind_truncate(struct inode *inode)
 		 * It is unnecessary to free any data blocks if last_block is
 		 * equal to the indirect block limit.
 		 */
-		goto out_unlock;
+		return;
 	} else if (n == 1) {		/* direct blocks */
 		ext4_free_data(handle, inode, NULL, i_data+offsets[0],
 			       i_data + EXT4_NDIR_BLOCKS);
@@ -1491,31 +1301,6 @@ do_indirects:
 	case EXT4_TIND_BLOCK:
 		;
 	}
-
-out_unlock:
-	up_write(&ei->i_data_sem);
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-
-	/*
-	 * In a multi-transaction truncate, we only make the final transaction
-	 * synchronous
-	 */
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-out_stop:
-	/*
-	 * If this was a simple ftruncate(), and the file will remain alive
-	 * then we need to clear up the orphan record which we created above.
-	 * However, if this was a real unlink then we were called by
-	 * ext4_delete_inode(), and we allow that function to clean up the
-	 * orphan info for us.
-	 */
-	if (inode->i_nlink)
-		ext4_orphan_del(handle, inode);
-
-	ext4_journal_stop(handle);
-	trace_ext4_truncate_exit(inode);
 }
 
 static int free_hole_blocks(handle_t *handle, struct inode *inode,
@@ -1569,7 +1354,7 @@ err:
 	return ret;
 }
 
-static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
+int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
 			  ext4_lblk_t first, ext4_lblk_t stop)
 {
 	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
@@ -1604,157 +1389,3 @@ err:
 	return ret;
 }
 
-int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length)
-{
-	struct inode *inode = file_inode(file);
-	struct super_block *sb = inode->i_sb;
-	ext4_lblk_t first_block, stop_block;
-	struct address_space *mapping = inode->i_mapping;
-	handle_t *handle = NULL;
-	loff_t first_page, last_page, page_len;
-	loff_t first_page_offset, last_page_offset;
-	int err = 0;
-
-	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		err = filemap_write_and_wait_range(mapping,
-			offset, offset + length - 1);
-		if (err)
-			return err;
-	}
-
-	mutex_lock(&inode->i_mutex);
-	/* It's not possible punch hole on append only file */
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
-		err = -EPERM;
-		goto out_mutex;
-	}
-	if (IS_SWAPFILE(inode)) {
-		err = -ETXTBSY;
-		goto out_mutex;
-	}
-
-	/* No need to punch hole beyond i_size */
-	if (offset >= inode->i_size)
-		goto out_mutex;
-
-	/*
-	 * If the hole extents beyond i_size, set the hole
-	 * to end after the page that contains i_size
-	 */
-	if (offset + length > inode->i_size) {
-		length = inode->i_size +
-		    PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
-		    offset;
-	}
-
-	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
-
-	first_page_offset = first_page << PAGE_CACHE_SHIFT;
-	last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
-	/* Now release the pages */
-	if (last_page_offset > first_page_offset) {
-		truncate_pagecache_range(inode, first_page_offset,
-					 last_page_offset - 1);
-	}
-
-	/* Wait all existing dio works, newcomers will block on i_mutex */
-	inode_dio_wait(inode);
-
-	handle = start_transaction(inode);
-	if (IS_ERR(handle))
-		goto out_mutex;
-
-	/*
-	 * Now we need to zero out the non-page-aligned data in the
-	 * pages at the start and tail of the hole, and unmap the buffer
-	 * heads for the block aligned regions of the page that were
-	 * completely zerod.
-	 */
-	if (first_page > last_page) {
-		/*
-		 * If the file space being truncated is contained within a page
-		 * just zero out and unmap the middle of that page
-		 */
-		err = ext4_discard_partial_page_buffers(handle,
-			mapping, offset, length, 0);
-		if (err)
-			goto out;
-	} else {
-		/*
-		 * Zero out and unmap the paritial page that contains
-		 * the start of the hole
-		 */
-		page_len = first_page_offset - offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-							offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-
-		/*
-		 * Zero out and unmap the partial page that contains
-		 * the end of the hole
-		 */
-		page_len = offset + length - last_page_offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-						last_page_offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-	}
-
-	/*
-	 * If i_size contained in the last page, we need to
-	 * unmap and zero the paritial page after i_size
-	 */
-	if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
-	    inode->i_size % PAGE_CACHE_SIZE != 0) {
-		page_len = PAGE_CACHE_SIZE -
-			(inode->i_size & (PAGE_CACHE_SIZE - 1));
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle,
-				mapping, inode->i_size, page_len, 0);
-			if (err)
-				goto out;
-		}
-	}
-
-	first_block = (offset + sb->s_blocksize - 1) >>
-		EXT4_BLOCK_SIZE_BITS(sb);
-	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
-	if (first_block >= stop_block)
-		goto out;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
-
-	err = ext4_es_remove_extent(inode, first_block,
-				    stop_block - first_block);
-	err = ext4_free_hole_blocks(handle, inode, first_block, stop_block);
-
-	ext4_discard_preallocations(inode);
-
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
-	up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	ext4_journal_stop(handle);
-
-out_mutex:
-	mutex_unlock(&inode->i_mutex);
-
-	return err;
-}

fs/ext4/inline.c

@@ -19,6 +19,7 @@
 
 #define EXT4_XATTR_SYSTEM_DATA	"data"
 #define EXT4_MIN_INLINE_DATA_SIZE	((sizeof(__le32) * EXT4_N_BLOCKS))
+#define EXT4_INLINE_DOTDOT_OFFSET	2
 #define EXT4_INLINE_DOTDOT_SIZE		4
 
 int ext4_get_inline_size(struct inode *inode)
@@ -1289,6 +1290,120 @@ out:
 	return ret;
 }
 
+/*
+ * This function fills a red-black tree with information from an
+ * inlined dir.  It returns the number directory entries loaded
+ * into the tree.  If there is an error it is returned in err.
+ */
+int htree_inlinedir_to_tree(struct file *dir_file,
+			    struct inode *dir, ext4_lblk_t block,
+			    struct dx_hash_info *hinfo,
+			    __u32 start_hash, __u32 start_minor_hash,
+			    int *has_inline_data)
+{
+	int err = 0, count = 0;
+	unsigned int parent_ino;
+	int pos;
+	struct ext4_dir_entry_2 *de;
+	struct inode *inode = file_inode(dir_file);
+	int ret, inline_size = 0;
+	struct ext4_iloc iloc;
+	void *dir_buf = NULL;
+	struct ext4_dir_entry_2 fake;
+
+	ret = ext4_get_inode_loc(inode, &iloc);
+	if (ret)
+		return ret;
+
+	down_read(&EXT4_I(inode)->xattr_sem);
+	if (!ext4_has_inline_data(inode)) {
+		up_read(&EXT4_I(inode)->xattr_sem);
+		*has_inline_data = 0;
+		goto out;
+	}
+
+	inline_size = ext4_get_inline_size(inode);
+	dir_buf = kmalloc(inline_size, GFP_NOFS);
+	if (!dir_buf) {
+		ret = -ENOMEM;
+		up_read(&EXT4_I(inode)->xattr_sem);
+		goto out;
+	}
+
+	ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
+	up_read(&EXT4_I(inode)->xattr_sem);
+	if (ret < 0)
+		goto out;
+
+	pos = 0;
+	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
+	while (pos < inline_size) {
+		/*
+		 * As inlined dir doesn't store any information about '.' and
+		 * only the inode number of '..' is stored, we have to handle
+		 * them differently.
+		 */
+		if (pos == 0) {
+			fake.inode = cpu_to_le32(inode->i_ino);
+			fake.name_len = 1;
+			strcpy(fake.name, ".");
+			fake.rec_len = ext4_rec_len_to_disk(
+						EXT4_DIR_REC_LEN(fake.name_len),
+						inline_size);
+			ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
+			de = &fake;
+			pos = EXT4_INLINE_DOTDOT_OFFSET;
+		} else if (pos == EXT4_INLINE_DOTDOT_OFFSET) {
+			fake.inode = cpu_to_le32(parent_ino);
+			fake.name_len = 2;
+			strcpy(fake.name, "..");
+			fake.rec_len = ext4_rec_len_to_disk(
+						EXT4_DIR_REC_LEN(fake.name_len),
+						inline_size);
+			ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
+			de = &fake;
+			pos = EXT4_INLINE_DOTDOT_SIZE;
+		} else {
+			de = (struct ext4_dir_entry_2 *)(dir_buf + pos);
+			pos += ext4_rec_len_from_disk(de->rec_len, inline_size);
+			if (ext4_check_dir_entry(inode, dir_file, de,
+					 iloc.bh, dir_buf,
+					 inline_size, pos)) {
+				ret = count;
+				goto out;
+			}
+		}
+
+		ext4fs_dirhash(de->name, de->name_len, hinfo);
+		if ((hinfo->hash < start_hash) ||
+		    ((hinfo->hash == start_hash) &&
+		     (hinfo->minor_hash < start_minor_hash)))
+			continue;
+		if (de->inode == 0)
+			continue;
+		err = ext4_htree_store_dirent(dir_file,
+				   hinfo->hash, hinfo->minor_hash, de);
+		if (err) {
+			count = err;
+			goto out;
+		}
+		count++;
+	}
+	ret = count;
+out:
+	kfree(dir_buf);
+	brelse(iloc.bh);
+	return ret;
+}
+
+/*
+ * So this function is called when the volume is mkfsed with
+ * dir_index disabled. In order to keep f_pos persistent
+ * after we convert from an inlined dir to a blocked based,
+ * we just pretend that we are a normal dir and return the
+ * offset as if '.' and '..' really take place.
+ *
+ */
 int ext4_read_inline_dir(struct file *filp,
 			 void *dirent, filldir_t filldir,
 			 int *has_inline_data)
@@ -1302,6 +1417,7 @@ int ext4_read_inline_dir(struct file *filp,
 	int ret, inline_size = 0;
 	struct ext4_iloc iloc;
 	void *dir_buf = NULL;
+	int dotdot_offset, dotdot_size, extra_offset, extra_size;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -1330,8 +1446,21 @@ int ext4_read_inline_dir(struct file *filp,
 	sb = inode->i_sb;
 	stored = 0;
 	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
+	offset = filp->f_pos;
 
-	while (!error && !stored && filp->f_pos < inode->i_size) {
+	/*
+	 * dotdot_offset and dotdot_size is the real offset and
+	 * size for ".." and "." if the dir is block based while
+	 * the real size for them are only EXT4_INLINE_DOTDOT_SIZE.
+	 * So we will use extra_offset and extra_size to indicate them
+	 * during the inline dir iteration.
+	 */
+	dotdot_offset = EXT4_DIR_REC_LEN(1);
+	dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
+	extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
+	extra_size = extra_offset + inline_size;
+
+	while (!error && !stored && filp->f_pos < extra_size) {
 revalidate:
 		/*
 		 * If the version has changed since the last call to
@@ -1340,15 +1469,23 @@ revalidate:
 		 * dir to make sure.
 		 */
 		if (filp->f_version != inode->i_version) {
-			for (i = 0;
+			for (i = 0; i < extra_size && i < offset;) {
-			     i < inode->i_size && i < offset;) {
+				/*
+				 * "." is with offset 0 and
+				 * ".." is dotdot_offset.
+				 */
 				if (!i) {
-					/* skip "." and ".." if needed. */
+					i = dotdot_offset;
-					i += EXT4_INLINE_DOTDOT_SIZE;
+					continue;
+				} else if (i == dotdot_offset) {
+					i = dotdot_size;
 					continue;
 				}
+				/* for other entry, the real offset in
+				 * the buf has to be tuned accordingly.
+				 */
 				de = (struct ext4_dir_entry_2 *)
-					(dir_buf + i);
+					(dir_buf + i - extra_offset);
 				/* It's too expensive to do a full
 				 * dirent test each time round this
 				 * loop, but we do have to test at
@@ -1356,43 +1493,47 @@ revalidate:
 				 * failure will be detected in the
 				 * dirent test below. */
 				if (ext4_rec_len_from_disk(de->rec_len,
-					inline_size) < EXT4_DIR_REC_LEN(1))
+					extra_size) < EXT4_DIR_REC_LEN(1))
 					break;
 				i += ext4_rec_len_from_disk(de->rec_len,
-							    inline_size);
+							    extra_size);
 			}
 			offset = i;
 			filp->f_pos = offset;
 			filp->f_version = inode->i_version;
 		}
 
-		while (!error && filp->f_pos < inode->i_size) {
+		while (!error && filp->f_pos < extra_size) {
 			if (filp->f_pos == 0) {
 				error = filldir(dirent, ".", 1, 0, inode->i_ino,
 						DT_DIR);
 				if (error)
 					break;
 				stored++;
+				filp->f_pos = dotdot_offset;
+				continue;
+			}
 
-				error = filldir(dirent, "..", 2, 0, parent_ino,
+			if (filp->f_pos == dotdot_offset) {
-						DT_DIR);
+				error = filldir(dirent, "..", 2,
+						dotdot_offset,
+						parent_ino, DT_DIR);
 				if (error)
 					break;
 				stored++;
 
-				filp->f_pos = offset = EXT4_INLINE_DOTDOT_SIZE;
+				filp->f_pos = dotdot_size;
 				continue;
 			}
 
-			de = (struct ext4_dir_entry_2 *)(dir_buf + offset);
+			de = (struct ext4_dir_entry_2 *)
+				(dir_buf + filp->f_pos - extra_offset);
 			if (ext4_check_dir_entry(inode, filp, de,
 						 iloc.bh, dir_buf,
-						 inline_size, offset)) {
+						 extra_size, filp->f_pos)) {
 				ret = stored;
 				goto out;
 			}
-			offset += ext4_rec_len_from_disk(de->rec_len,
-							 inline_size);
 			if (le32_to_cpu(de->inode)) {
 				/* We might block in the next section
 				 * if the data destination is
@@ -1415,9 +1556,8 @@ revalidate:
 				stored++;
 			}
 			filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
-							      inline_size);
+							      extra_size);
 		}
-		offset = 0;
 	}
 out:
 	kfree(dir_buf);

fs/ext4/inode.c

@@ -55,21 +55,21 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 	__u16 csum_hi = 0;
 	__u32 csum;
 
-	csum_lo = raw->i_checksum_lo;
+	csum_lo = le16_to_cpu(raw->i_checksum_lo);
 	raw->i_checksum_lo = 0;
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
 	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = raw->i_checksum_hi;
+		csum_hi = le16_to_cpu(raw->i_checksum_hi);
 		raw->i_checksum_hi = 0;
 	}
 
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
 			   EXT4_INODE_SIZE(inode->i_sb));
 
-	raw->i_checksum_lo = csum_lo;
+	raw->i_checksum_lo = cpu_to_le16(csum_lo);
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
 	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = csum_hi;
+		raw->i_checksum_hi = cpu_to_le16(csum_hi);
 
 	return csum;
 }
@@ -210,8 +210,7 @@ void ext4_evict_inode(struct inode *inode)
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
-			jbd2_log_start_commit(journal, commit_tid);
+			jbd2_complete_transaction(journal, commit_tid);
-			jbd2_log_wait_commit(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
 		truncate_inode_pages(&inode->i_data, 0);
@@ -1081,20 +1080,42 @@ retry_journal:
 /* For write_end() in data=journal mode */
 static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 {
+	int ret;
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
 	set_buffer_uptodate(bh);
-	return ext4_handle_dirty_metadata(handle, NULL, bh);
+	ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+	clear_buffer_meta(bh);
+	clear_buffer_prio(bh);
+	return ret;
 }
 
-static int ext4_generic_write_end(struct file *file,
+/*
+ * We need to pick up the new inode size which generic_commit_write gave us
+ * `file' can be NULL - eg, when called from page_symlink().
+ *
+ * ext4 never places buffers on inode->i_mapping->private_list.  metadata
+ * buffers are managed internally.
+ */
+static int ext4_write_end(struct file *file,
 			  struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
 			  struct page *page, void *fsdata)
 {
-	int i_size_changed = 0;
-	struct inode *inode = mapping->host;
 	handle_t *handle = ext4_journal_current_handle();
+	struct inode *inode = mapping->host;
+	int ret = 0, ret2;
+	int i_size_changed = 0;
+
+	trace_ext4_write_end(inode, pos, len, copied);
+	if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) {
+		ret = ext4_jbd2_file_inode(handle, inode);
+		if (ret) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto errout;
+		}
+	}
 
 	if (ext4_has_inline_data(inode))
 		copied = ext4_write_inline_data_end(inode, pos, len,
@@ -1105,7 +1126,7 @@ static int ext4_generic_write_end(struct file *file,
 
 	/*
 	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
+	 * cannot change under us because we hole i_mutex.
 	 *
 	 * But it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
@@ -1118,7 +1139,7 @@ static int ext4_generic_write_end(struct file *file,
 	if (pos + copied > EXT4_I(inode)->i_disksize) {
 		/* We need to mark inode dirty even if
 		 * new_i_size is less that inode->i_size
-		 * bu greater than i_disksize.(hint delalloc)
+		 * but greater than i_disksize. (hint delalloc)
 		 */
 		ext4_update_i_disksize(inode, (pos + copied));
 		i_size_changed = 1;
@@ -1135,87 +1156,15 @@ static int ext4_generic_write_end(struct file *file,
 	if (i_size_changed)
 		ext4_mark_inode_dirty(handle, inode);
 
-	return copied;
+	if (copied < 0)
-}
+		ret = copied;
-
-/*
- * We need to pick up the new inode size which generic_commit_write gave us
- * `file' can be NULL - eg, when called from page_symlink().
- *
- * ext4 never places buffers on inode->i_mapping->private_list.  metadata
- * buffers are managed internally.
- */
-static int ext4_ordered_write_end(struct file *file,
-				  struct address_space *mapping,
-				  loff_t pos, unsigned len, unsigned copied,
-				  struct page *page, void *fsdata)
-{
-	handle_t *handle = ext4_journal_current_handle();
-	struct inode *inode = mapping->host;
-	int ret = 0, ret2;
-
-	trace_ext4_ordered_write_end(inode, pos, len, copied);
-	ret = ext4_jbd2_file_inode(handle, inode);
-
-	if (ret == 0) {
-		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-		copied = ret2;
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
 		 */
 		ext4_orphan_add(handle, inode);
-		if (ret2 < 0)
+errout:
-			ret = ret2;
-	} else {
-		unlock_page(page);
-		page_cache_release(page);
-	}
-
-	ret2 = ext4_journal_stop(handle);
-	if (!ret)
-		ret = ret2;
-
-	if (pos + len > inode->i_size) {
-		ext4_truncate_failed_write(inode);
-		/*
-		 * If truncate failed early the inode might still be
-		 * on the orphan list; we need to make sure the inode
-		 * is removed from the orphan list in that case.
-		 */
-		if (inode->i_nlink)
-			ext4_orphan_del(NULL, inode);
-	}
-
-
-	return ret ? ret : copied;
-}
-
-static int ext4_writeback_write_end(struct file *file,
-				    struct address_space *mapping,
-				    loff_t pos, unsigned len, unsigned copied,
-				    struct page *page, void *fsdata)
-{
-	handle_t *handle = ext4_journal_current_handle();
-	struct inode *inode = mapping->host;
-	int ret = 0, ret2;
-
-	trace_ext4_writeback_write_end(inode, pos, len, copied);
-	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-	copied = ret2;
-	if (pos + len > inode->i_size && ext4_can_truncate(inode))
-		/* if we have allocated more blocks and copied
-		 * less. We will have blocks allocated outside
-		 * inode->i_size. So truncate them
-		 */
-		ext4_orphan_add(handle, inode);
-
-	if (ret2 < 0)
-		ret = ret2;
-
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -1538,7 +1487,10 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 	struct ext4_io_submit io_submit;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-	memset(&io_submit, 0, sizeof(io_submit));
+	ext4_io_submit_init(&io_submit, mpd->wbc);
+	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_submit.io_end)
+		return -ENOMEM;
 	/*
 	 * We need to start from the first_page to the next_page - 1
 	 * to make sure we also write the mapped dirty buffer_heads.
@@ -1626,6 +1578,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 		pagevec_release(&pvec);
 	}
 	ext4_io_submit(&io_submit);
+	/* Drop io_end reference we got from init */
+	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
@@ -1670,22 +1624,25 @@ static void ext4_print_free_blocks(struct inode *inode)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct super_block *sb = inode->i_sb;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
 	       EXT4_C2B(EXT4_SB(inode->i_sb),
-			ext4_count_free_clusters(inode->i_sb)));
+			ext4_count_free_clusters(sb)));
 	ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
 	ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
-	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+	       (long long) EXT4_C2B(EXT4_SB(sb),
 		percpu_counter_sum(&sbi->s_freeclusters_counter)));
 	ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
-	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+	       (long long) EXT4_C2B(EXT4_SB(sb),
 		percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
 	ext4_msg(sb, KERN_CRIT, "Block reservation details");
 	ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
-		 EXT4_I(inode)->i_reserved_data_blocks);
+		 ei->i_reserved_data_blocks);
 	ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u",
-	       EXT4_I(inode)->i_reserved_meta_blocks);
+	       ei->i_reserved_meta_blocks);
+	ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u",
+	       ei->i_allocated_meta_blocks);
 	return;
 }
 
@@ -1740,12 +1697,21 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
 	 */
 	map.m_lblk = next;
 	map.m_len = max_blocks;
-	get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
+	/*
+	 * We're in delalloc path and it is possible that we're going to
+	 * need more metadata blocks than previously reserved. However
+	 * we must not fail because we're in writeback and there is
+	 * nothing we can do about it so it might result in data loss.
+	 * So use reserved blocks to allocate metadata if possible.
+	 */
+	get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
+			   EXT4_GET_BLOCKS_METADATA_NOFAIL;
 	if (ext4_should_dioread_nolock(mpd->inode))
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
 	if (mpd->b_state & (1 << BH_Delay))
 		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
 
+
 	blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
 	if (blks < 0) {
 		struct super_block *sb = mpd->inode->i_sb;
@@ -2272,9 +2238,16 @@ static int ext4_writepage(struct page *page,
 		 */
 		return __ext4_journalled_writepage(page, len);
 
-	memset(&io_submit, 0, sizeof(io_submit));
+	ext4_io_submit_init(&io_submit, wbc);
+	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_submit.io_end) {
+		redirty_page_for_writepage(wbc, page);
+		return -ENOMEM;
+	}
 	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
 	ext4_io_submit(&io_submit);
+	/* Drop io_end reference we got from init */
+	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
@@ -2661,7 +2634,7 @@ out_writepages:
 
 static int ext4_nonda_switch(struct super_block *sb)
 {
-	s64 free_blocks, dirty_blocks;
+	s64 free_clusters, dirty_clusters;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	/*
@@ -2672,17 +2645,18 @@ static int ext4_nonda_switch(struct super_block *sb)
 	 * Delalloc need an accurate free block accounting. So switch
 	 * to non delalloc when we are near to error range.
 	 */
-	free_blocks  = EXT4_C2B(sbi,
+	free_clusters =
-		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+		percpu_counter_read_positive(&sbi->s_freeclusters_counter);
-	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
+	dirty_clusters =
+		percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
 	/*
 	 * Start pushing delalloc when 1/2 of free blocks are dirty.
 	 */
-	if (dirty_blocks && (free_blocks < 2 * dirty_blocks))
+	if (dirty_clusters && (free_clusters < 2 * dirty_clusters))
 		try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
 
-	if (2 * free_blocks < 3 * dirty_blocks ||
+	if (2 * free_clusters < 3 * dirty_clusters ||
-		free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
+	    free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) {
 		/*
 		 * free block count is less than 150% of dirty blocks
 		 * or free blocks is less than watermark
@@ -2818,18 +2792,9 @@ static int ext4_da_write_end(struct file *file,
 	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
 
-	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+	if (write_mode == FALL_BACK_TO_NONDELALLOC)
-		switch (ext4_inode_journal_mode(inode)) {
+		return ext4_write_end(file, mapping, pos,
-		case EXT4_INODE_ORDERED_DATA_MODE:
-			return ext4_ordered_write_end(file, mapping, pos,
 				      len, copied, page, fsdata);
-		case EXT4_INODE_WRITEBACK_DATA_MODE:
-			return ext4_writeback_write_end(file, mapping, pos,
-					len, copied, page, fsdata);
-		default:
-			BUG();
-		}
-	}
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
 	start = pos & (PAGE_CACHE_SIZE - 1);
@@ -3113,9 +3078,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	struct inode *inode = file_inode(iocb->ki_filp);
         ext4_io_end_t *io_end = iocb->private;
 
-	/* if not async direct IO or dio with 0 bytes write, just return */
+	/* if not async direct IO just return */
-	if (!io_end || !size)
+	if (!io_end) {
-		goto out;
+		inode_dio_done(inode);
+		if (is_async)
+			aio_complete(iocb, ret, 0);
+		return;
+	}
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3123,25 +3092,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 		  size);
 
 	iocb->private = NULL;
-
-	/* if not aio dio with unwritten extents, just free io and return */
-	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		ext4_free_io_end(io_end);
-out:
-		inode_dio_done(inode);
-		if (is_async)
-			aio_complete(iocb, ret, 0);
-		return;
-	}
-
 	io_end->offset = offset;
 	io_end->size = size;
 	if (is_async) {
 		io_end->iocb = iocb;
 		io_end->result = ret;
 	}
-
+	ext4_put_io_end_defer(io_end);
-	ext4_add_complete_io(io_end);
 }
 
 /*
@@ -3175,6 +3132,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
+	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (rw != WRITE || final_size > inode->i_size)
@@ -3213,13 +3171,16 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	iocb->private = NULL;
 	ext4_inode_aio_set(inode, NULL);
 	if (!is_sync_kiocb(iocb)) {
-		ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
+		io_end = ext4_init_io_end(inode, GFP_NOFS);
 		if (!io_end) {
 			ret = -ENOMEM;
 			goto retake_lock;
 		}
 		io_end->flag |= EXT4_IO_END_DIRECT;
-		iocb->private = io_end;
+		/*
+		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
+		 */
+		iocb->private = ext4_get_io_end(io_end);
 		/*
 		 * we save the io structure for current async direct
 		 * IO, so that later ext4_map_blocks() could flag the
@@ -3243,26 +3204,27 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 				   NULL,
 				   dio_flags);
 
-	if (iocb->private)
-		ext4_inode_aio_set(inode, NULL);
 	/*
-	 * The io_end structure takes a reference to the inode, that
+	 * Put our reference to io_end. This can free the io_end structure e.g.
-	 * structure needs to be destroyed and the reference to the
+	 * in sync IO case or in case of error. It can even perform extent
-	 * inode need to be dropped, when IO is complete, even with 0
+	 * conversion if all bios we submitted finished before we got here.
-	 * byte write, or failed.
+	 * Note that in that case iocb->private can be already set to NULL
-	 *
+	 * here.
-	 * In the successful AIO DIO case, the io_end structure will
-	 * be destroyed and the reference to the inode will be dropped
-	 * after the end_io call back function is called.
-	 *
-	 * In the case there is 0 byte write, or error case, since VFS
-	 * direct IO won't invoke the end_io call back function, we
-	 * need to free the end_io structure here.
 	 */
-	if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+	if (io_end) {
-		ext4_free_io_end(iocb->private);
+		ext4_inode_aio_set(inode, NULL);
+		ext4_put_io_end(io_end);
+		/*
+		 * In case of error or no write ext4_end_io_dio() was not
+		 * called so we have to put iocb's reference.
+		 */
+		if (ret <= 0 && ret != -EIOCBQUEUED) {
+			WARN_ON(iocb->private != io_end);
+			ext4_put_io_end(io_end);
 			iocb->private = NULL;
-	} else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+		}
+	}
+	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 		int err;
 		/*
@@ -3334,27 +3296,12 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 	return __set_page_dirty_nobuffers(page);
 }
 
-static const struct address_space_operations ext4_ordered_aops = {
+static const struct address_space_operations ext4_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
 	.writepage		= ext4_writepage,
 	.write_begin		= ext4_write_begin,
-	.write_end		= ext4_ordered_write_end,
+	.write_end		= ext4_write_end,
-	.bmap			= ext4_bmap,
-	.invalidatepage		= ext4_invalidatepage,
-	.releasepage		= ext4_releasepage,
-	.direct_IO		= ext4_direct_IO,
-	.migratepage		= buffer_migrate_page,
-	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
-};
-
-static const struct address_space_operations ext4_writeback_aops = {
-	.readpage		= ext4_readpage,
-	.readpages		= ext4_readpages,
-	.writepage		= ext4_writepage,
-	.write_begin		= ext4_write_begin,
-	.write_end		= ext4_writeback_write_end,
 	.bmap			= ext4_bmap,
 	.invalidatepage		= ext4_invalidatepage,
 	.releasepage		= ext4_releasepage,
@@ -3399,23 +3346,21 @@ void ext4_set_aops(struct inode *inode)
 {
 	switch (ext4_inode_journal_mode(inode)) {
 	case EXT4_INODE_ORDERED_DATA_MODE:
-		if (test_opt(inode->i_sb, DELALLOC))
+		ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE);
-			inode->i_mapping->a_ops = &ext4_da_aops;
-		else
-			inode->i_mapping->a_ops = &ext4_ordered_aops;
 		break;
 	case EXT4_INODE_WRITEBACK_DATA_MODE:
-		if (test_opt(inode->i_sb, DELALLOC))
+		ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE);
-			inode->i_mapping->a_ops = &ext4_da_aops;
-		else
-			inode->i_mapping->a_ops = &ext4_writeback_aops;
 		break;
 	case EXT4_INODE_JOURNAL_DATA_MODE:
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
-		break;
+		return;
 	default:
 		BUG();
 	}
+	if (test_opt(inode->i_sb, DELALLOC))
+		inode->i_mapping->a_ops = &ext4_da_aops;
+	else
+		inode->i_mapping->a_ops = &ext4_aops;
 }
 
 
@@ -3646,20 +3591,190 @@ int ext4_can_truncate(struct inode *inode)
 int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 {
 	struct inode *inode = file_inode(file);
+	struct super_block *sb = inode->i_sb;
+	ext4_lblk_t first_block, stop_block;
+	struct address_space *mapping = inode->i_mapping;
+	loff_t first_page, last_page, page_len;
+	loff_t first_page_offset, last_page_offset;
+	handle_t *handle;
+	unsigned int credits;
+	int ret = 0;
+
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+	if (EXT4_SB(sb)->s_cluster_ratio > 1) {
-		return ext4_ind_punch_hole(file, offset, length);
-
-	if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
 		/* TODO: Add support for bigalloc file systems */
 		return -EOPNOTSUPP;
 	}
 
 	trace_ext4_punch_hole(inode, offset, length);
 
-	return ext4_ext_punch_hole(file, offset, length);
+	/*
+	 * Write out all dirty pages to avoid race conditions
+	 * Then release them.
+	 */
+	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		ret = filemap_write_and_wait_range(mapping, offset,
+						   offset + length - 1);
+		if (ret)
+			return ret;
+	}
+
+	mutex_lock(&inode->i_mutex);
+	/* It's not possible punch hole on append only file */
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+		ret = -EPERM;
+		goto out_mutex;
+	}
+	if (IS_SWAPFILE(inode)) {
+		ret = -ETXTBSY;
+		goto out_mutex;
+	}
+
+	/* No need to punch hole beyond i_size */
+	if (offset >= inode->i_size)
+		goto out_mutex;
+
+	/*
+	 * If the hole extends beyond i_size, set the hole
+	 * to end after the page that contains i_size
+	 */
+	if (offset + length > inode->i_size) {
+		length = inode->i_size +
+		   PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+		   offset;
+	}
+
+	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
+
+	first_page_offset = first_page << PAGE_CACHE_SHIFT;
+	last_page_offset = last_page << PAGE_CACHE_SHIFT;
+
+	/* Now release the pages */
+	if (last_page_offset > first_page_offset) {
+		truncate_pagecache_range(inode, first_page_offset,
+					 last_page_offset - 1);
+	}
+
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	ret = ext4_flush_unwritten_io(inode);
+	if (ret)
+		goto out_dio;
+	inode_dio_wait(inode);
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		credits = ext4_writepage_trans_blocks(inode);
+	else
+		credits = ext4_blocks_for_truncate(inode);
+	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		ext4_std_error(sb, ret);
+		goto out_dio;
+	}
+
+	/*
+	 * Now we need to zero out the non-page-aligned data in the
+	 * pages at the start and tail of the hole, and unmap the
+	 * buffer heads for the block aligned regions of the page that
+	 * were completely zeroed.
+	 */
+	if (first_page > last_page) {
+		/*
+		 * If the file space being truncated is contained
+		 * within a page just zero out and unmap the middle of
+		 * that page
+		 */
+		ret = ext4_discard_partial_page_buffers(handle,
+			mapping, offset, length, 0);
+
+		if (ret)
+			goto out_stop;
+	} else {
+		/*
+		 * zero out and unmap the partial page that contains
+		 * the start of the hole
+		 */
+		page_len = first_page_offset - offset;
+		if (page_len > 0) {
+			ret = ext4_discard_partial_page_buffers(handle, mapping,
+						offset, page_len, 0);
+			if (ret)
+				goto out_stop;
+		}
+
+		/*
+		 * zero out and unmap the partial page that contains
+		 * the end of the hole
+		 */
+		page_len = offset + length - last_page_offset;
+		if (page_len > 0) {
+			ret = ext4_discard_partial_page_buffers(handle, mapping,
+					last_page_offset, page_len, 0);
+			if (ret)
+				goto out_stop;
+		}
+	}
+
+	/*
+	 * If i_size is contained in the last page, we need to
+	 * unmap and zero the partial page after i_size
+	 */
+	if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+	   inode->i_size % PAGE_CACHE_SIZE != 0) {
+		page_len = PAGE_CACHE_SIZE -
+			(inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+		if (page_len > 0) {
+			ret = ext4_discard_partial_page_buffers(handle,
+					mapping, inode->i_size, page_len, 0);
+
+			if (ret)
+				goto out_stop;
+		}
+	}
+
+	first_block = (offset + sb->s_blocksize - 1) >>
+		EXT4_BLOCK_SIZE_BITS(sb);
+	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+	/* If there are no blocks to remove, return now */
+	if (first_block >= stop_block)
+		goto out_stop;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_discard_preallocations(inode);
+
+	ret = ext4_es_remove_extent(inode, first_block,
+				    stop_block - first_block);
+	if (ret) {
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto out_stop;
+	}
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		ret = ext4_ext_remove_space(inode, first_block,
+					    stop_block - 1);
+	else
+		ret = ext4_free_hole_blocks(handle, inode, first_block,
+					    stop_block);
+
+	ext4_discard_preallocations(inode);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+out_stop:
+	ext4_journal_stop(handle);
+out_dio:
+	ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
 }
 
 /*
@@ -3692,6 +3807,19 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
  */
 void ext4_truncate(struct inode *inode)
 {
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int credits;
+	handle_t *handle;
+	struct address_space *mapping = inode->i_mapping;
+	loff_t page_len;
+
+	/*
+	 * There is a possibility that we're either freeing the inode
+	 * or it completely new indode. In those cases we might not
+	 * have i_mutex locked because it's not necessary.
+	 */
+	if (!(inode->i_state & (I_NEW|I_FREEING)))
+		WARN_ON(!mutex_is_locked(&inode->i_mutex));
 	trace_ext4_truncate_enter(inode);
 
 	if (!ext4_can_truncate(inode))
@@ -3710,10 +3838,72 @@ void ext4_truncate(struct inode *inode)
 			return;
 	}
 
+	/*
+	 * finish any pending end_io work so we won't run the risk of
+	 * converting any truncated blocks to initialized later
+	 */
+	ext4_flush_unwritten_io(inode);
+
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ext4_ext_truncate(inode);
+		credits = ext4_writepage_trans_blocks(inode);
 	else
-		ext4_ind_truncate(inode);
+		credits = ext4_blocks_for_truncate(inode);
+
+	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+	if (IS_ERR(handle)) {
+		ext4_std_error(inode->i_sb, PTR_ERR(handle));
+		return;
+	}
+
+	if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+		page_len = PAGE_CACHE_SIZE -
+			(inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+		if (ext4_discard_partial_page_buffers(handle,
+				mapping, inode->i_size, page_len, 0))
+			goto out_stop;
+	}
+
+	/*
+	 * We add the inode to the orphan list, so that if this
+	 * truncate spans multiple transactions, and we crash, we will
+	 * resume the truncate when the filesystem recovers.  It also
+	 * marks the inode dirty, to catch the new size.
+	 *
+	 * Implication: the file must always be in a sane, consistent
+	 * truncatable state while each transaction commits.
+	 */
+	if (ext4_orphan_add(handle, inode))
+		goto out_stop;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+
+	ext4_discard_preallocations(inode);
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		ext4_ext_truncate(handle, inode);
+	else
+		ext4_ind_truncate(handle, inode);
+
+	up_write(&ei->i_data_sem);
+
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+
+out_stop:
+	/*
+	 * If this was a simple ftruncate() and the file will remain alive,
+	 * then we need to clear up the orphan record which we created above.
+	 * However, if this was a real unlink then we were called by
+	 * ext4_delete_inode(), and we allow that function to clean up the
+	 * orphan info for us.
+	 */
+	if (inode->i_nlink)
+		ext4_orphan_del(handle, inode);
+
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
 
 	trace_ext4_truncate_exit(inode);
 }
@@ -3821,13 +4011,14 @@ make_io:
 		if (EXT4_SB(sb)->s_inode_readahead_blks) {
 			ext4_fsblk_t b, end, table;
 			unsigned num;
+			__u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks;
 
 			table = ext4_inode_table(sb, gdp);
 			/* s_inode_readahead_blks is always a power of 2 */
-			b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
+			b = block & ~((ext4_fsblk_t) ra_blks - 1);
 			if (table > b)
 				b = table;
-			end = b + EXT4_SB(sb)->s_inode_readahead_blks;
+			end = b + ra_blks;
 			num = EXT4_INODES_PER_GROUP(sb);
 			if (ext4_has_group_desc_csum(sb))
 				num -= ext4_itable_unused_count(sb, gdp);
@@ -4024,8 +4215,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	 * NeilBrown 1999oct15
 	 */
 	if (inode->i_nlink == 0) {
-		if (inode->i_mode == 0 ||
+		if ((inode->i_mode == 0 ||
-		    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+		     !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
+		    ino != EXT4_BOOT_LOADER_INO) {
 			/* this inode is deleted */
 			ret = -ESTALE;
 			goto bad_inode;
@@ -4033,7 +4225,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		/* The only unlinked inodes we let through here have
 		 * valid i_mode and are being read by the orphan
 		 * recovery code: that's fine, we're about to complete
-		 * the process of deleting those. */
+		 * the process of deleting those.
+		 * OR it is the EXT4_BOOT_LOADER_INO which is
+		 * not initialized on a new filesystem. */
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
@@ -4153,6 +4347,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		else
 			init_special_inode(inode, inode->i_mode,
 			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+	} else if (ino == EXT4_BOOT_LOADER_INO) {
+		make_bad_inode(inode);
 	} else {
 		ret = -EIO;
 		EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);

fs/ext4/ioctl.c

@@ -17,9 +17,201 @@
 #include <asm/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
+#include "ext4_extents.h"
 
 #define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
 
+/**
+ * Swap memory between @a and @b for @len bytes.
+ *
+ * @a:          pointer to first memory area
+ * @b:          pointer to second memory area
+ * @len:        number of bytes to swap
+ *
+ */
+static void memswap(void *a, void *b, size_t len)
+{
+	unsigned char *ap, *bp;
+	unsigned char tmp;
+
+	ap = (unsigned char *)a;
+	bp = (unsigned char *)b;
+	while (len-- > 0) {
+		tmp = *ap;
+		*ap = *bp;
+		*bp = tmp;
+		ap++;
+		bp++;
+	}
+}
+
+/**
+ * Swap i_data and associated attributes between @inode1 and @inode2.
+ * This function is used for the primary swap between inode1 and inode2
+ * and also to revert this primary swap in case of errors.
+ *
+ * Therefore you have to make sure, that calling this method twice
+ * will revert all changes.
+ *
+ * @inode1:     pointer to first inode
+ * @inode2:     pointer to second inode
+ */
+static void swap_inode_data(struct inode *inode1, struct inode *inode2)
+{
+	loff_t isize;
+	struct ext4_inode_info *ei1;
+	struct ext4_inode_info *ei2;
+
+	ei1 = EXT4_I(inode1);
+	ei2 = EXT4_I(inode2);
+
+	memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags));
+	memswap(&inode1->i_version, &inode2->i_version,
+		  sizeof(inode1->i_version));
+	memswap(&inode1->i_blocks, &inode2->i_blocks,
+		  sizeof(inode1->i_blocks));
+	memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes));
+	memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime));
+	memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime));
+
+	memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
+	memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
+	memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
+	memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
+	memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+
+	isize = i_size_read(inode1);
+	i_size_write(inode1, i_size_read(inode2));
+	i_size_write(inode2, isize);
+}
+
+/**
+ * Swap the information from the given @inode and the inode
+ * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
+ * important fields of the inodes.
+ *
+ * @sb:         the super block of the filesystem
+ * @inode:      the inode to swap with EXT4_BOOT_LOADER_INO
+ *
+ */
+static long swap_inode_boot_loader(struct super_block *sb,
+				struct inode *inode)
+{
+	handle_t *handle;
+	int err;
+	struct inode *inode_bl;
+	struct ext4_inode_info *ei;
+	struct ext4_inode_info *ei_bl;
+	struct ext4_sb_info *sbi;
+
+	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+
+	if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto swap_boot_out;
+	}
+
+	sbi = EXT4_SB(sb);
+	ei = EXT4_I(inode);
+
+	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
+	if (IS_ERR(inode_bl)) {
+		err = PTR_ERR(inode_bl);
+		goto swap_boot_out;
+	}
+	ei_bl = EXT4_I(inode_bl);
+
+	filemap_flush(inode->i_mapping);
+	filemap_flush(inode_bl->i_mapping);
+
+	/* Protect orig inodes against a truncate and make sure,
+	 * that only 1 swap_inode_boot_loader is running. */
+	ext4_inode_double_lock(inode, inode_bl);
+
+	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(&inode_bl->i_data, 0);
+
+	/* Wait for all existing dio workers */
+	ext4_inode_block_unlocked_dio(inode);
+	ext4_inode_block_unlocked_dio(inode_bl);
+	inode_dio_wait(inode);
+	inode_dio_wait(inode_bl);
+
+	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
+	if (IS_ERR(handle)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+
+	/* Protect extent tree against block allocations via delalloc */
+	ext4_double_down_write_data_sem(inode, inode_bl);
+
+	if (inode_bl->i_nlink == 0) {
+		/* this inode has never been used as a BOOT_LOADER */
+		set_nlink(inode_bl, 1);
+		i_uid_write(inode_bl, 0);
+		i_gid_write(inode_bl, 0);
+		inode_bl->i_flags = 0;
+		ei_bl->i_flags = 0;
+		inode_bl->i_version = 1;
+		i_size_write(inode_bl, 0);
+		inode_bl->i_mode = S_IFREG;
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+					      EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+			ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
+			ext4_ext_tree_init(handle, inode_bl);
+		} else
+			memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
+	}
+
+	swap_inode_data(inode, inode_bl);
+
+	inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
+
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	inode_bl->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+
+	ext4_discard_preallocations(inode);
+
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err < 0) {
+		ext4_warning(inode->i_sb,
+			"couldn't mark inode #%lu dirty (err %d)",
+			inode->i_ino, err);
+		/* Revert all changes: */
+		swap_inode_data(inode, inode_bl);
+	} else {
+		err = ext4_mark_inode_dirty(handle, inode_bl);
+		if (err < 0) {
+			ext4_warning(inode_bl->i_sb,
+				"couldn't mark inode #%lu dirty (err %d)",
+				inode_bl->i_ino, err);
+			/* Revert all changes: */
+			swap_inode_data(inode, inode_bl);
+			ext4_mark_inode_dirty(handle, inode);
+		}
+	}
+
+	ext4_journal_stop(handle);
+
+	ext4_double_up_write_data_sem(inode, inode_bl);
+
+	ext4_inode_resume_unlocked_dio(inode);
+	ext4_inode_resume_unlocked_dio(inode_bl);
+
+	ext4_inode_double_unlock(inode, inode_bl);
+
+	iput(inode_bl);
+
+swap_boot_out:
+	return err;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -83,17 +275,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			if (!capable(CAP_SYS_RESOURCE))
 				goto flags_out;
 		}
-		if (oldflags & EXT4_EXTENTS_FL) {
+		if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
-			/* We don't support clearning extent flags */
-			if (!(flags & EXT4_EXTENTS_FL)) {
-				err = -EOPNOTSUPP;
-				goto flags_out;
-			}
-		} else if (flags & EXT4_EXTENTS_FL) {
-			/* migrate the file */
 			migrate = 1;
-			flags &= ~EXT4_EXTENTS_FL;
-		}
 
 		if (flags & EXT4_EOFBLOCKS_FL) {
 			/* we don't support adding EOFBLOCKS flag */
@@ -137,8 +320,13 @@ flags_err:
 			err = ext4_change_inode_journal_flag(inode, jflag);
 		if (err)
 			goto flags_out;
-		if (migrate)
+		if (migrate) {
+			if (flags & EXT4_EXTENTS_FL)
 				err = ext4_ext_migrate(inode);
+			else
+				err = ext4_ind_migrate(inode);
+		}
+
 flags_out:
 		mutex_unlock(&inode->i_mutex);
 		mnt_drop_write_file(filp);
@@ -357,9 +545,13 @@ group_add_out:
 		return err;
 	}
 
+	case EXT4_IOC_SWAP_BOOT:
+		if (!(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+		return swap_inode_boot_loader(sb, inode);
+
 	case EXT4_IOC_RESIZE_FS: {
 		ext4_fsblk_t n_blocks_count;
-		struct super_block *sb = inode->i_sb;
 		int err = 0, err2 = 0;
 		ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
 

fs/ext4/mballoc.c

@@ -405,6 +405,12 @@ static inline void mb_clear_bit(int bit, void *addr)
 	ext4_clear_bit(bit, addr);
 }
 
+static inline int mb_test_and_clear_bit(int bit, void *addr)
+{
+	addr = mb_correct_addr_and_bit(&bit, addr);
+	return ext4_test_and_clear_bit(bit, addr);
+}
+
 static inline int mb_find_next_zero_bit(void *addr, int max, int start)
 {
 	int fix = 0, ret, tmpmax;
@@ -764,6 +770,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	spin_unlock(&EXT4_SB(sb)->s_bal_lock);
 }
 
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+	int count;
+	int order = 1;
+	void *buddy;
+
+	while ((buddy = mb_find_buddy(e4b, order++, &count))) {
+		ext4_set_bits(buddy, 0, count);
+	}
+	e4b->bd_info->bb_fragments = 0;
+	memset(e4b->bd_info->bb_counters, 0,
+		sizeof(*e4b->bd_info->bb_counters) *
+		(e4b->bd_sb->s_blocksize_bits + 2));
+
+	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+		e4b->bd_bitmap, e4b->bd_group);
+}
+
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -860,8 +884,6 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 	first_block = page->index * blocks_per_page;
 	for (i = 0; i < blocks_per_page; i++) {
-		int group;
-
 		group = (first_block + i) >> 1;
 		if (group >= ngroups)
 			break;
@@ -1011,6 +1033,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	struct page *page;
 	int ret = 0;
 
+	might_sleep();
 	mb_debug(1, "init group %u\n", group);
 	this_grp = ext4_get_group_info(sb, group);
 	/*
@@ -1082,6 +1105,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct inode *inode = sbi->s_buddy_cache;
 
+	might_sleep();
 	mb_debug(1, "load group %u\n", group);
 
 	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
@@ -1244,6 +1268,33 @@ static void mb_clear_bits(void *bm, int cur, int len)
 	}
 }
 
+/* clear bits in given range
+ * will return first found zero bit if any, -1 otherwise
+ */
+static int mb_test_and_clear_bits(void *bm, int cur, int len)
+{
+	__u32 *addr;
+	int zero_bit = -1;
+
+	len = cur + len;
+	while (cur < len) {
+		if ((cur & 31) == 0 && (len - cur) >= 32) {
+			/* fast path: clear whole word at once */
+			addr = bm + (cur >> 3);
+			if (*addr != (__u32)(-1) && zero_bit == -1)
+				zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0);
+			*addr = 0;
+			cur += 32;
+			continue;
+		}
+		if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1)
+			zero_bit = cur;
+		cur++;
+	}
+
+	return zero_bit;
+}
+
 void ext4_set_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
@@ -1262,17 +1313,90 @@ void ext4_set_bits(void *bm, int cur, int len)
 	}
 }
 
+/*
+ * _________________________________________________________________ */
+
+static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side)
+{
+	if (mb_test_bit(*bit + side, bitmap)) {
+		mb_clear_bit(*bit, bitmap);
+		(*bit) -= side;
+		return 1;
+	}
+	else {
+		(*bit) += side;
+		mb_set_bit(*bit, bitmap);
+		return -1;
+	}
+}
+
+static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last)
+{
+	int max;
+	int order = 1;
+	void *buddy = mb_find_buddy(e4b, order, &max);
+
+	while (buddy) {
+		void *buddy2;
+
+		/* Bits in range [first; last] are known to be set since
+		 * corresponding blocks were allocated. Bits in range
+		 * (first; last) will stay set because they form buddies on
+		 * upper layer. We just deal with borders if they don't
+		 * align with upper layer and then go up.
+		 * Releasing entire group is all about clearing
+		 * single bit of highest order buddy.
+		 */
+
+		/* Example:
+		 * ---------------------------------
+		 * |   1   |   1   |   1   |   1   |
+		 * ---------------------------------
+		 * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
+		 * ---------------------------------
+		 *   0   1   2   3   4   5   6   7
+		 *      \_____________________/
+		 *
+		 * Neither [1] nor [6] is aligned to above layer.
+		 * Left neighbour [0] is free, so mark it busy,
+		 * decrease bb_counters and extend range to
+		 * [0; 6]
+		 * Right neighbour [7] is busy. It can't be coaleasced with [6], so
+		 * mark [6] free, increase bb_counters and shrink range to
+		 * [0; 5].
+		 * Then shift range to [0; 2], go up and do the same.
+		 */
+
+
+		if (first & 1)
+			e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1);
+		if (!(last & 1))
+			e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1);
+		if (first > last)
+			break;
+		order++;
+
+		if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) {
+			mb_clear_bits(buddy, first, last - first + 1);
+			e4b->bd_info->bb_counters[order - 1] += last - first + 1;
+			break;
+		}
+		first >>= 1;
+		last >>= 1;
+		buddy = buddy2;
+	}
+}
+
 static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 			   int first, int count)
 {
-	int block = 0;
+	int left_is_free = 0;
-	int max = 0;
+	int right_is_free = 0;
-	int order;
+	int block;
-	void *buddy;
+	int last = first + count - 1;
-	void *buddy2;
 	struct super_block *sb = e4b->bd_sb;
 
-	BUG_ON(first + count > (sb->s_blocksize << 3));
+	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
@@ -1281,22 +1405,16 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	if (first < e4b->bd_info->bb_first_free)
 		e4b->bd_info->bb_first_free = first;
 
-	/* let's maintain fragments counter */
+	/* access memory sequentially: check left neighbour,
+	 * clear range and then check right neighbour
+	 */
 	if (first != 0)
-		block = !mb_test_bit(first - 1, e4b->bd_bitmap);
+		left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap);
-	if (first + count < EXT4_SB(sb)->s_mb_maxs[0])
+	block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count);
-		max = !mb_test_bit(first + count, e4b->bd_bitmap);
+	if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0])
-	if (block && max)
+		right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap);
-		e4b->bd_info->bb_fragments--;
-	else if (!block && !max)
-		e4b->bd_info->bb_fragments++;
 
-	/* let's maintain buddy itself */
+	if (unlikely(block != -1)) {
-	while (count-- > 0) {
-		block = first++;
-		order = 0;
-
-		if (!mb_test_bit(block, e4b->bd_bitmap)) {
 		ext4_fsblk_t blocknr;
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1306,42 +1424,35 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 				      blocknr,
 				      "freeing already freed block "
 				      "(bit %u)", block);
+		mb_regenerate_buddy(e4b);
+		goto done;
 	}
-		mb_clear_bit(block, e4b->bd_bitmap);
-		e4b->bd_info->bb_counters[order]++;
 
-		/* start of the buddy */
+	/* let's maintain fragments counter */
-		buddy = mb_find_buddy(e4b, order, &max);
+	if (left_is_free && right_is_free)
+		e4b->bd_info->bb_fragments--;
+	else if (!left_is_free && !right_is_free)
+		e4b->bd_info->bb_fragments++;
 
-		do {
+	/* buddy[0] == bd_bitmap is a special case, so handle
-			block &= ~1UL;
+	 * it right away and let mb_buddy_mark_free stay free of
-			if (mb_test_bit(block, buddy) ||
+	 * zero order checks.
-					mb_test_bit(block + 1, buddy))
+	 * Check if neighbours are to be coaleasced,
-				break;
+	 * adjust bitmap bb_counters and borders appropriately.
-
+	 */
-			/* both the buddies are free, try to coalesce them */
+	if (first & 1) {
-			buddy2 = mb_find_buddy(e4b, order + 1, &max);
+		first += !left_is_free;
-
+		e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1;
-			if (!buddy2)
-				break;
-
-			if (order > 0) {
-				/* for special purposes, we don't set
-				 * free bits in bitmap */
-				mb_set_bit(block, buddy);
-				mb_set_bit(block + 1, buddy);
 	}
-			e4b->bd_info->bb_counters[order]--;
+	if (!(last & 1)) {
-			e4b->bd_info->bb_counters[order]--;
+		last -= !right_is_free;
-
+		e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1;
-			block = block >> 1;
-			order++;
-			e4b->bd_info->bb_counters[order]++;
-
-			mb_clear_bit(block, buddy2);
-			buddy = buddy2;
-		} while (1);
 	}
+
+	if (first <= last)
+		mb_buddy_mark_free(e4b, first >> 1, last >> 1);
+
+done:
 	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_check_buddy(e4b);
 }
@@ -3342,7 +3453,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	if (pa->pa_type == MB_GROUP_PA)
 		grp_blk--;
 
-	ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL);
+	grp = ext4_get_group_number(sb, grp_blk);
 
 	/*
 	 * possible race:
@@ -3807,7 +3918,7 @@ repeat:
 
 	list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) {
 		BUG_ON(pa->pa_type != MB_INODE_PA);
-		ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
+		group = ext4_get_group_number(sb, pa->pa_pstart);
 
 		err = ext4_mb_load_buddy(sb, group, &e4b);
 		if (err) {
@@ -4069,7 +4180,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 
 	list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
 
-		ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
+		group = ext4_get_group_number(sb, pa->pa_pstart);
 		if (ext4_mb_load_buddy(sb, group, &e4b)) {
 			ext4_error(sb, "Error loading buddy information for %u",
 					group);
@@ -4217,6 +4328,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	unsigned int inquota = 0;
 	unsigned int reserv_clstrs = 0;
 
+	might_sleep();
 	sb = ar->inode->i_sb;
 	sbi = EXT4_SB(sb);
 
@@ -4420,11 +4532,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_prev(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(entry, new_entry)) {
+		if (can_merge(entry, new_entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_start_cluster = entry->efd_start_cluster;
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
@@ -4432,10 +4544,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_next(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(new_entry, entry)) {
+		if (can_merge(new_entry, entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
@@ -4470,6 +4582,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	int err = 0;
 	int ret;
 
+	might_sleep();
 	if (bh) {
 		if (block)
 			BUG_ON(block != bh->b_blocknr);

fs/ext4/migrate.c

@@ -426,7 +426,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 			return retval;
 	}
 	return retval;
-
 }
 
 int ext4_ext_migrate(struct inode *inode)
@@ -606,3 +605,64 @@ out:
 
 	return retval;
 }
+
+/*
+ * Migrate a simple extent-based inode to use the i_blocks[] array
+ */
+int ext4_ind_migrate(struct inode *inode)
+{
+	struct ext4_extent_header	*eh;
+	struct ext4_super_block		*es = EXT4_SB(inode->i_sb)->s_es;
+	struct ext4_inode_info		*ei = EXT4_I(inode);
+	struct ext4_extent		*ex;
+	unsigned int			i, len;
+	ext4_fsblk_t			blk;
+	handle_t			*handle;
+	int				ret;
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
+				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
+	    (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return -EINVAL;
+
+	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				       EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+		return -EOPNOTSUPP;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ret = ext4_ext_check_inode(inode);
+	if (ret)
+		goto errout;
+
+	eh = ext_inode_hdr(inode);
+	ex  = EXT_FIRST_EXTENT(eh);
+	if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
+	    eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
+		ret = -EOPNOTSUPP;
+		goto errout;
+	}
+	if (eh->eh_entries == 0)
+		blk = len = 0;
+	else {
+		len = le16_to_cpu(ex->ee_len);
+		blk = ext4_ext_pblock(ex);
+		if (len > EXT4_NDIR_BLOCKS) {
+			ret = -EOPNOTSUPP;
+			goto errout;
+		}
+	}
+
+	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
+	memset(ei->i_data, 0, sizeof(ei->i_data));
+	for (i=0; i < len; i++)
+		ei->i_data[i] = cpu_to_le32(blk++);
+	ext4_mark_inode_dirty(handle, inode);
+errout:
+	ext4_journal_stop(handle);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	return ret;
+}

fs/ext4/mmp.c

@@ -7,7 +7,7 @@
 #include "ext4.h"
 
 /* Checksumming functions */
-static __u32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
+static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int offset = offsetof(struct mmp_struct, mmp_checksum);
@@ -54,7 +54,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(WRITE_SYNC, bh);
+	submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
@@ -86,7 +86,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 		get_bh(*bh);
 		lock_buffer(*bh);
 		(*bh)->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_SYNC, *bh);
+		submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
 		wait_on_buffer(*bh);
 		if (!buffer_uptodate(*bh)) {
 			brelse(*bh);

fs/ext4/move_extent.c

@@ -144,12 +144,13 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 }
 
 /**
- * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
+ * ext4_double_down_write_data_sem - Acquire two inodes' write lock
+ *                                   of i_data_sem
  *
  * Acquire write lock of i_data_sem of the two inodes
  */
-static void
+void
-double_down_write_data_sem(struct inode *first, struct inode *second)
+ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
 {
 	if (first < second) {
 		down_write(&EXT4_I(first)->i_data_sem);
@@ -162,14 +163,15 @@ double_down_write_data_sem(struct inode *first, struct inode *second)
 }
 
 /**
- * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
+ * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem
  *
  * @orig_inode:		original inode structure to be released its lock first
  * @donor_inode:	donor inode structure to be released its lock second
  * Release write lock of i_data_sem of two inodes (orig and donor).
  */
-static void
+void
-double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+ext4_double_up_write_data_sem(struct inode *orig_inode,
+			      struct inode *donor_inode)
 {
 	up_write(&EXT4_I(orig_inode)->i_data_sem);
 	up_write(&EXT4_I(donor_inode)->i_data_sem);
@@ -407,18 +409,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode,
 		mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
 						end_ext, eh, range_to_move);
 
-	if (depth) {
+	return ext4_ext_dirty(handle, orig_inode, orig_path);
-		ret = ext4_handle_dirty_metadata(handle, orig_inode,
-						 orig_path->p_bh);
-		if (ret)
-			return ret;
-	} else {
-		ret = ext4_mark_inode_dirty(handle, orig_inode);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
 }
 
 /**
@@ -737,6 +728,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
 		donor_off += dext_alen;
 		orig_off += dext_alen;
 
+		BUG_ON(replaced_count > count);
 		/* Already moved the expected blocks */
 		if (replaced_count >= count)
 			break;
@@ -814,7 +806,13 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 		page_cache_release(page[0]);
 		return -ENOMEM;
 	}
-
+	/*
+	 * grab_cache_page_write_begin() may not wait on page's writeback if
+	 * BDI not demand that. But it is reasonable to be very conservative
+	 * here and explicitly wait on page's writeback
+	 */
+	wait_on_page_writeback(page[0]);
+	wait_on_page_writeback(page[1]);
 	if (inode1 > inode2) {
 		struct page *tmp;
 		tmp = page[0];
@@ -856,7 +854,6 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 		if (buffer_uptodate(bh))
 			continue;
 		if (!buffer_mapped(bh)) {
-			int err = 0;
 			err = ext4_get_block(inode, block, bh, 0);
 			if (err) {
 				SetPageError(page);
@@ -976,7 +973,7 @@ again:
 	 * necessary, just swap data blocks between orig and donor.
 	 */
 	if (uninit) {
-		double_down_write_data_sem(orig_inode, donor_inode);
+		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		/* If any of extents in range became initialized we have to
 		 * fallback to data copying */
 		uninit = mext_check_coverage(orig_inode, orig_blk_offset,
@@ -990,7 +987,7 @@ again:
 			goto drop_data_sem;
 
 		if (!uninit) {
-			double_up_write_data_sem(orig_inode, donor_inode);
+			ext4_double_up_write_data_sem(orig_inode, donor_inode);
 			goto data_copy;
 		}
 		if ((page_has_private(pagep[0]) &&
@@ -1004,7 +1001,7 @@ again:
 						donor_inode, orig_blk_offset,
 						block_len_in_page, err);
 	drop_data_sem:
-		double_up_write_data_sem(orig_inode, donor_inode);
+		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		goto unlock_pages;
 	}
 data_copy:
@@ -1033,7 +1030,7 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, from + replaced_size,
+	*err = __block_write_begin(pagep[0], from, replaced_size,
 				   ext4_get_block);
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
@@ -1065,11 +1062,11 @@ repair_branches:
 	 * Extents are swapped already, but we are not able to copy data.
 	 * Try to swap extents to it's original places
 	 */
-	double_down_write_data_sem(orig_inode, donor_inode);
+	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);
-	double_up_write_data_sem(orig_inode, donor_inode);
+	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),
 				       "Unable to copy data block,"
@@ -1209,15 +1206,15 @@ mext_check_arguments(struct inode *orig_inode,
 }
 
 /**
- * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
+ * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
  *
  * @inode1:	the inode structure
  * @inode2:	the inode structure
  *
  * Lock two inodes' i_mutex
  */
-static void
+void
-mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
+ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
 {
 	BUG_ON(inode1 == inode2);
 	if (inode1 < inode2) {
@@ -1230,15 +1227,15 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
 }
 
 /**
- * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
+ * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
  *
  * @inode1:     the inode that is released first
  * @inode2:     the inode that is released second
  *
  */
 
-static void
+void
-mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
+ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
 {
 	mutex_unlock(&inode1->i_mutex);
 	mutex_unlock(&inode2->i_mutex);
@@ -1333,7 +1330,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		return -EINVAL;
 	}
 	/* Protect orig and donor inodes against a truncate */
-	mext_inode_double_lock(orig_inode, donor_inode);
+	ext4_inode_double_lock(orig_inode, donor_inode);
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(orig_inode);
@@ -1342,7 +1339,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 	inode_dio_wait(donor_inode);
 
 	/* Protect extent tree against block allocations via delalloc */
-	double_down_write_data_sem(orig_inode, donor_inode);
+	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);
@@ -1466,7 +1463,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		 * b. racing with ->readpage, ->write_begin, and ext4_get_block
 		 *    in move_extent_per_page
 		 */
-		double_up_write_data_sem(orig_inode, donor_inode);
+		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 
 		while (orig_page_offset <= seq_end_page) {
 
@@ -1500,7 +1497,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 				block_len_in_page = rest_blocks;
 		}
 
-		double_down_write_data_sem(orig_inode, donor_inode);
+		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		if (ret < 0)
 			break;
 
@@ -1538,10 +1535,10 @@ out:
 		ext4_ext_drop_refs(holecheck_path);
 		kfree(holecheck_path);
 	}
-	double_up_write_data_sem(orig_inode, donor_inode);
+	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);
-	mext_inode_double_unlock(orig_inode, donor_inode);
+	ext4_inode_double_unlock(orig_inode, donor_inode);
 
 	return ret;
 }

fs/ext4/namei.c

@@ -416,15 +416,16 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	__u32 csum, old_csum;
+	__u32 csum;
+	__le32 save_csum;
 	int size;
 
 	size = count_offset + (count * sizeof(struct dx_entry));
-	old_csum = t->dt_checksum;
+	save_csum = t->dt_checksum;
 	t->dt_checksum = 0;
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
 	csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail));
-	t->dt_checksum = old_csum;
+	t->dt_checksum = save_csum;
 
 	return cpu_to_le32(csum);
 }
@@ -971,6 +972,17 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 			hinfo.hash_version +=
 				EXT4_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+		if (ext4_has_inline_data(dir)) {
+			int has_inline_data = 1;
+			count = htree_inlinedir_to_tree(dir_file, dir, 0,
+							&hinfo, start_hash,
+							start_minor_hash,
+							&has_inline_data);
+			if (has_inline_data) {
+				*next_hash = ~0;
+				return count;
+			}
+		}
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
 		*next_hash = ~0;
@@ -1455,24 +1467,6 @@ struct dentry *ext4_get_parent(struct dentry *child)
 	return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
 }
 
-#define S_SHIFT 12
-static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
-	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
-	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
-	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,
-	[S_IFBLK >> S_SHIFT]	= EXT4_FT_BLKDEV,
-	[S_IFIFO >> S_SHIFT]	= EXT4_FT_FIFO,
-	[S_IFSOCK >> S_SHIFT]	= EXT4_FT_SOCK,
-	[S_IFLNK >> S_SHIFT]	= EXT4_FT_SYMLINK,
-};
-
-static inline void ext4_set_de_type(struct super_block *sb,
-				struct ext4_dir_entry_2 *de,
-				umode_t mode) {
-	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE))
-		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
-}
-
 /*
  * Move count entries from end of map between two memory locations.
  * Returns pointer to last entry moved.
@@ -2251,8 +2245,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	dquot_initialize(dir);
 
 	credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
-		   EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 retry:
 	inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
 					    NULL, EXT4_HT_DIR, credits);
@@ -2286,8 +2279,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 	dquot_initialize(dir);
 
 	credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
-		   EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 retry:
 	inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
 					    NULL, EXT4_HT_DIR, credits);
@@ -2396,8 +2388,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	dquot_initialize(dir);
 
 	credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
-		   EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 retry:
 	inode = ext4_new_inode_start_handle(dir, S_IFDIR | mode,
 					    &dentry->d_name,
@@ -2826,8 +2817,7 @@ static int ext4_symlink(struct inode *dir,
 		 * quota blocks, sb is already counted in previous macros).
 		 */
 		credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-			  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+			  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
-			  EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
 	}
 retry:
 	inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO,

fs/ext4/page-io.c

@@ -29,25 +29,19 @@
 #include "xattr.h"
 #include "acl.h"
 
-static struct kmem_cache *io_page_cachep, *io_end_cachep;
+static struct kmem_cache *io_end_cachep;
 
 int __init ext4_init_pageio(void)
 {
-	io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
-	if (io_page_cachep == NULL)
-		return -ENOMEM;
 	io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
-	if (io_end_cachep == NULL) {
+	if (io_end_cachep == NULL)
-		kmem_cache_destroy(io_page_cachep);
 		return -ENOMEM;
-	}
 	return 0;
 }
 
 void ext4_exit_pageio(void)
 {
 	kmem_cache_destroy(io_end_cachep);
-	kmem_cache_destroy(io_page_cachep);
 }
 
 /*
@@ -67,29 +61,28 @@ void ext4_ioend_shutdown(struct inode *inode)
 		cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
 }
 
-static void put_io_page(struct ext4_io_page *io_page)
+static void ext4_release_io_end(ext4_io_end_t *io_end)
 {
-	if (atomic_dec_and_test(&io_page->p_count)) {
+	BUG_ON(!list_empty(&io_end->list));
-		end_page_writeback(io_page->p_page);
+	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
-		put_page(io_page->p_page);
+
-		kmem_cache_free(io_page_cachep, io_page);
+	if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
-	}
+		wake_up_all(ext4_ioend_wq(io_end->inode));
+	if (io_end->flag & EXT4_IO_END_DIRECT)
+		inode_dio_done(io_end->inode);
+	if (io_end->iocb)
+		aio_complete(io_end->iocb, io_end->result, 0);
+	kmem_cache_free(io_end_cachep, io_end);
 }
 
-void ext4_free_io_end(ext4_io_end_t *io)
+static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 {
-	int i;
+	struct inode *inode = io_end->inode;
 
-	BUG_ON(!io);
+	io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
-	BUG_ON(!list_empty(&io->list));
+	/* Wake up anyone waiting on unwritten extent conversion */
-	BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
+	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-
+		wake_up_all(ext4_ioend_wq(inode));
-	for (i = 0; i < io->num_io_pages; i++)
-		put_io_page(io->pages[i]);
-	io->num_io_pages = 0;
-	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
-		wake_up_all(ext4_ioend_wq(io->inode));
-	kmem_cache_free(io_end_cachep, io);
 }
 
 /* check a range of space and convert unwritten extents to written. */
@@ -112,13 +105,8 @@ static int ext4_end_io(ext4_io_end_t *io)
 			 "(inode %lu, offset %llu, size %zd, error %d)",
 			 inode->i_ino, offset, size, ret);
 	}
-	/* Wake up anyone waiting on unwritten extent conversion */
+	ext4_clear_io_unwritten_flag(io);
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+	ext4_release_io_end(io);
-		wake_up_all(ext4_ioend_wq(inode));
-	if (io->flag & EXT4_IO_END_DIRECT)
-		inode_dio_done(inode);
-	if (io->iocb)
-		aio_complete(io->iocb, io->result, 0);
 	return ret;
 }
 
@@ -149,7 +137,7 @@ static void dump_completed_IO(struct inode *inode)
 }
 
 /* Add the io_end to per-inode completed end_io list. */
-void ext4_add_complete_io(ext4_io_end_t *io_end)
+static void ext4_add_complete_io(ext4_io_end_t *io_end)
 {
 	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
 	struct workqueue_struct *wq;
@@ -186,8 +174,6 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
 		err = ext4_end_io(io);
 		if (unlikely(!ret && err))
 			ret = err;
-		io->flag &= ~EXT4_IO_END_UNWRITTEN;
-		ext4_free_io_end(io);
 	}
 	return ret;
 }
@@ -219,10 +205,43 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 		atomic_inc(&EXT4_I(inode)->i_ioend_count);
 		io->inode = inode;
 		INIT_LIST_HEAD(&io->list);
+		atomic_set(&io->count, 1);
 	}
 	return io;
 }
 
+void ext4_put_io_end_defer(ext4_io_end_t *io_end)
+{
+	if (atomic_dec_and_test(&io_end->count)) {
+		if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
+			ext4_release_io_end(io_end);
+			return;
+		}
+		ext4_add_complete_io(io_end);
+	}
+}
+
+int ext4_put_io_end(ext4_io_end_t *io_end)
+{
+	int err = 0;
+
+	if (atomic_dec_and_test(&io_end->count)) {
+		if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+			err = ext4_convert_unwritten_extents(io_end->inode,
+						io_end->offset, io_end->size);
+			ext4_clear_io_unwritten_flag(io_end);
+		}
+		ext4_release_io_end(io_end);
+	}
+	return err;
+}
+
+ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
+{
+	atomic_inc(&io_end->count);
+	return io_end;
+}
+
 /*
  * Print an buffer I/O error compatible with the fs/buffer.c.  This
  * provides compatibility with dmesg scrapers that look for a specific
@@ -243,45 +262,56 @@ static void ext4_end_bio(struct bio *bio, int error)
 	ext4_io_end_t *io_end = bio->bi_private;
 	struct inode *inode;
 	int i;
+	int blocksize;
 	sector_t bi_sector = bio->bi_sector;
 
 	BUG_ON(!io_end);
+	inode = io_end->inode;
+	blocksize = 1 << inode->i_blkbits;
 	bio->bi_private = NULL;
 	bio->bi_end_io = NULL;
 	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = 0;
-	bio_put(bio);
+	for (i = 0; i < bio->bi_vcnt; i++) {
-
+		struct bio_vec *bvec = &bio->bi_io_vec[i];
-	for (i = 0; i < io_end->num_io_pages; i++) {
+		struct page *page = bvec->bv_page;
-		struct page *page = io_end->pages[i]->p_page;
 		struct buffer_head *bh, *head;
-		loff_t offset;
+		unsigned bio_start = bvec->bv_offset;
-		loff_t io_end_offset;
+		unsigned bio_end = bio_start + bvec->bv_len;
+		unsigned under_io = 0;
+		unsigned long flags;
+
+		if (!page)
+			continue;
 
 		if (error) {
 			SetPageError(page);
 			set_bit(AS_EIO, &page->mapping->flags);
-			head = page_buffers(page);
+		}
-			BUG_ON(!head);
+		bh = head = page_buffers(page);
-
+		/*
-			io_end_offset = io_end->offset + io_end->size;
+		 * We check all buffers in the page under BH_Uptodate_Lock
-
+		 * to avoid races with other end io clearing async_write flags
-			offset = (sector_t) page->index << PAGE_CACHE_SHIFT;
+		 */
-			bh = head;
+		local_irq_save(flags);
+		bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
 		do {
-				if ((offset >= io_end->offset) &&
+			if (bh_offset(bh) < bio_start ||
-				    (offset+bh->b_size <= io_end_offset))
+			    bh_offset(bh) + blocksize > bio_end) {
+				if (buffer_async_write(bh))
+					under_io++;
+				continue;
+			}
+			clear_buffer_async_write(bh);
+			if (error)
 				buffer_io_error(bh);
-
+		} while ((bh = bh->b_this_page) != head);
-				offset += bh->b_size;
+		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-				bh = bh->b_this_page;
+		local_irq_restore(flags);
-			} while (bh != head);
+		if (!under_io)
+			end_page_writeback(page);
 	}
-
+	bio_put(bio);
-		put_io_page(io_end->pages[i]);
-	}
-	io_end->num_io_pages = 0;
-	inode = io_end->inode;
 
 	if (error) {
 		io_end->flag |= EXT4_IO_END_ERROR;
@@ -294,12 +324,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
-	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+	ext4_put_io_end_defer(io_end);
-		ext4_free_io_end(io_end);
-		return;
-	}
-
-	ext4_add_complete_io(io_end);
 }
 
 void ext4_io_submit(struct ext4_io_submit *io)
@@ -313,76 +338,59 @@ void ext4_io_submit(struct ext4_io_submit *io)
 		bio_put(io->io_bio);
 	}
 	io->io_bio = NULL;
-	io->io_op = 0;
+}
+
+void ext4_io_submit_init(struct ext4_io_submit *io,
+			 struct writeback_control *wbc)
+{
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
+	io->io_bio = NULL;
 	io->io_end = NULL;
 }
 
-static int io_submit_init(struct ext4_io_submit *io,
+static int io_submit_init_bio(struct ext4_io_submit *io,
-			  struct inode *inode,
-			  struct writeback_control *wbc,
 			      struct buffer_head *bh)
 {
-	ext4_io_end_t *io_end;
-	struct page *page = bh->b_page;
 	int nvecs = bio_get_nr_vecs(bh->b_bdev);
 	struct bio *bio;
 
-	io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_end)
-		return -ENOMEM;
 	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
 	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
-	bio->bi_private = io->io_end = io_end;
 	bio->bi_end_io = ext4_end_bio;
-
+	bio->bi_private = ext4_get_io_end(io->io_end);
-	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+	if (!io->io_end->size)
-
+		io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT)
+				     + bh_offset(bh);
 	io->io_bio = bio;
-	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 	io->io_next_block = bh->b_blocknr;
 	return 0;
 }
 
 static int io_submit_add_bh(struct ext4_io_submit *io,
-			    struct ext4_io_page *io_page,
 			    struct inode *inode,
-			    struct writeback_control *wbc,
 			    struct buffer_head *bh)
 {
 	ext4_io_end_t *io_end;
 	int ret;
 
-	if (buffer_new(bh)) {
-		clear_buffer_new(bh);
-		unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
-	}
-
 	if (io->io_bio && bh->b_blocknr != io->io_next_block) {
 submit_and_retry:
 		ext4_io_submit(io);
 	}
 	if (io->io_bio == NULL) {
-		ret = io_submit_init(io, inode, wbc, bh);
+		ret = io_submit_init_bio(io, bh);
 		if (ret)
 			return ret;
 	}
-	io_end = io->io_end;
-	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
-	    (io_end->pages[io_end->num_io_pages-1] != io_page))
-		goto submit_and_retry;
-	if (buffer_uninit(bh))
-		ext4_set_io_unwritten_flag(inode, io_end);
-	io->io_end->size += bh->b_size;
-	io->io_next_block++;
 	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
 	if (ret != bh->b_size)
 		goto submit_and_retry;
-	if ((io_end->num_io_pages == 0) ||
+	io_end = io->io_end;
-	    (io_end->pages[io_end->num_io_pages-1] != io_page)) {
+	if (test_clear_buffer_uninit(bh))
-		io_end->pages[io_end->num_io_pages++] = io_page;
+		ext4_set_io_unwritten_flag(inode, io_end);
-		atomic_inc(&io_page->p_count);
+	io_end->size += bh->b_size;
-	}
+	io->io_next_block++;
 	return 0;
 }
 
@@ -392,33 +400,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
-	unsigned block_start, block_end, blocksize;
+	unsigned block_start, blocksize;
-	struct ext4_io_page *io_page;
 	struct buffer_head *bh, *head;
 	int ret = 0;
+	int nr_submitted = 0;
 
 	blocksize = 1 << inode->i_blkbits;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 
-	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
-	if (!io_page) {
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return -ENOMEM;
-	}
-	io_page->p_page = page;
-	atomic_set(&io_page->p_count, 1);
-	get_page(page);
 	set_page_writeback(page);
 	ClearPageError(page);
 
-	for (bh = head = page_buffers(page), block_start = 0;
+	/*
-	     bh != head || !block_start;
+	 * In the first loop we prepare and mark buffers to submit. We have to
-	     block_start = block_end, bh = bh->b_this_page) {
+	 * mark all buffers in the page before submitting so that
-
+	 * end_page_writeback() cannot be called from ext4_bio_end_io() when IO
-		block_end = block_start + blocksize;
+	 * on the first buffer finishes and we are still working on submitting
+	 * the second buffer.
+	 */
+	bh = head = page_buffers(page);
+	do {
+		block_start = bh_offset(bh);
 		if (block_start >= len) {
 			/*
 			 * Comments copied from block_write_full_page_endio:
@@ -431,7 +435,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			 * mapped, and writes to that region are not written
 			 * out to the file."
 			 */
-			zero_user_segment(page, block_start, block_end);
+			zero_user_segment(page, block_start,
+					  block_start + blocksize);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
@@ -445,7 +450,19 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 				ext4_io_submit(io);
 			continue;
 		}
-		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
+		if (buffer_new(bh)) {
+			clear_buffer_new(bh);
+			unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
+		}
+		set_buffer_async_write(bh);
+	} while ((bh = bh->b_this_page) != head);
+
+	/* Now submit buffers to write */
+	bh = head = page_buffers(page);
+	do {
+		if (!buffer_async_write(bh))
+			continue;
+		ret = io_submit_add_bh(io, inode, bh);
 		if (ret) {
 			/*
 			 * We only get here on ENOMEM.  Not much else
@@ -455,17 +472,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			redirty_page_for_writepage(wbc, page);
 			break;
 		}
+		nr_submitted++;
 		clear_buffer_dirty(bh);
+	} while ((bh = bh->b_this_page) != head);
+
+	/* Error stopped previous loop? Clean up buffers... */
+	if (ret) {
+		do {
+			clear_buffer_async_write(bh);
+			bh = bh->b_this_page;
+		} while (bh != head);
 	}
 	unlock_page(page);
-	/*
+	/* Nothing submitted - we have to end page writeback */
-	 * If the page was truncated before we could do the writeback,
+	if (!nr_submitted)
-	 * or we had a memory allocation error while trying to write
+		end_page_writeback(page);
-	 * the first buffer head, we won't have submitted any pages for
-	 * I/O.  In that case we need to make sure we've cleared the
-	 * PageWriteback bit from the page to prevent the system from
-	 * wedging later on.
-	 */
-	put_io_page(io_page);
 	return ret;
 }

fs/ext4/resize.c

@@ -272,7 +272,7 @@ next_group:
 		if (start_blk >= last_blk)
 			goto next_group;
 		group_data[bb_index].block_bitmap = start_blk++;
-		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
+		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
 		if (flexbg_size > 1)
@@ -284,7 +284,7 @@ next_group:
 		if (start_blk >= last_blk)
 			goto next_group;
 		group_data[ib_index].inode_bitmap = start_blk++;
-		ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
+		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
 		if (flexbg_size > 1)
@@ -296,7 +296,7 @@ next_group:
 		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
 			goto next_group;
 		group_data[it_index].inode_table = start_blk;
-		ext4_get_group_no_and_offset(sb, start_blk, &group, NULL);
+		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count -=
 					EXT4_SB(sb)->s_itb_per_group;
@@ -392,7 +392,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 		ext4_group_t group;
 		int err;
 
-		ext4_get_group_no_and_offset(sb, block, &group, NULL);
+		group = ext4_get_group_number(sb, block);
 		start = ext4_group_first_block_no(sb, group);
 		group -= flex_gd->groups[0].group;
 
@@ -1341,6 +1341,8 @@ static void ext4_update_super(struct super_block *sb,
 
 	/* Update the global fs size fields */
 	sbi->s_groups_count += flex_gd->count;
+	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
@@ -1879,7 +1881,11 @@ retry:
 		/* Nothing need to do */
 		return 0;
 
-	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
+	n_group = ext4_get_group_number(sb, n_blocks_count - 1);
+	if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+		ext4_warning(sb, "resize would cause inodes_count overflow");
+		return -EINVAL;
+	}
 	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
 
 	n_desc_blocks = num_desc_blocks(sb, n_group + 1);

fs/ext4/super.c

@@ -81,6 +81,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly);
 static void ext4_destroy_lazyinit_thread(void);
 static void ext4_unregister_li_request(struct super_block *sb);
 static void ext4_clear_request_list(void);
+static int ext4_reserve_clusters(struct ext4_sb_info *, ext4_fsblk_t);
 
 #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext2_fs_type = {
@@ -353,10 +354,13 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	struct super_block		*sb = journal->j_private;
 	struct ext4_sb_info		*sbi = EXT4_SB(sb);
 	int				error = is_journal_aborted(journal);
-	struct ext4_journal_cb_entry	*jce, *tmp;
+	struct ext4_journal_cb_entry	*jce;
 
+	BUG_ON(txn->t_state == T_FINISHED);
 	spin_lock(&sbi->s_md_lock);
-	list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) {
+	while (!list_empty(&txn->t_private_list)) {
+		jce = list_entry(txn->t_private_list.next,
+				 struct ext4_journal_cb_entry, jce_list);
 		list_del_init(&jce->jce_list);
 		spin_unlock(&sbi->s_md_lock);
 		jce->jce_func(sb, jce, error);
@@ -1948,16 +1952,16 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	if ((sbi->s_es->s_feature_ro_compat &
 	     cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) {
 		/* Use new metadata_csum algorithm */
-		__u16 old_csum;
+		__le16 save_csum;
 		__u32 csum32;
 
-		old_csum = gdp->bg_checksum;
+		save_csum = gdp->bg_checksum;
 		gdp->bg_checksum = 0;
 		csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
 				     sizeof(le_group));
 		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
 				     sbi->s_desc_size);
-		gdp->bg_checksum = old_csum;
+		gdp->bg_checksum = save_csum;
 
 		crc = csum32 & 0xFFFF;
 		goto out;
@@ -2379,17 +2383,15 @@ struct ext4_attr {
 	int offset;
 };
 
-static int parse_strtoul(const char *buf,
+static int parse_strtoull(const char *buf,
-		unsigned long max, unsigned long *value)
+		unsigned long long max, unsigned long long *value)
 {
-	char *endp;
+	int ret;
 
-	*value = simple_strtoul(skip_spaces(buf), &endp, 0);
+	ret = kstrtoull(skip_spaces(buf), 0, value);
-	endp = skip_spaces(endp);
+	if (!ret && *value > max)
-	if (*endp || *value > max)
+		ret = -EINVAL;
-		return -EINVAL;
+	return ret;
-
-	return 0;
 }
 
 static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
@@ -2431,11 +2433,13 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 					  const char *buf, size_t count)
 {
 	unsigned long t;
+	int ret;
 
-	if (parse_strtoul(buf, 0x40000000, &t))
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
-		return -EINVAL;
+	if (ret)
+		return ret;
 
-	if (t && !is_power_of_2(t))
+	if (t && (!is_power_of_2(t) || t > 0x40000000))
 		return -EINVAL;
 
 	sbi->s_inode_readahead_blks = t;
@@ -2456,13 +2460,36 @@ static ssize_t sbi_ui_store(struct ext4_attr *a,
 {
 	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
 	unsigned long t;
+	int ret;
 
-	if (parse_strtoul(buf, 0xffffffff, &t))
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
-		return -EINVAL;
+	if (ret)
+		return ret;
 	*ui = t;
 	return count;
 }
 
+static ssize_t reserved_clusters_show(struct ext4_attr *a,
+				  struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long) atomic64_read(&sbi->s_resv_clusters));
+}
+
+static ssize_t reserved_clusters_store(struct ext4_attr *a,
+				   struct ext4_sb_info *sbi,
+				   const char *buf, size_t count)
+{
+	unsigned long long val;
+	int ret;
+
+	if (parse_strtoull(buf, -1ULL, &val))
+		return -EINVAL;
+	ret = ext4_reserve_clusters(sbi, val);
+
+	return ret ? ret : count;
+}
+
 static ssize_t trigger_test_error(struct ext4_attr *a,
 				  struct ext4_sb_info *sbi,
 				  const char *buf, size_t count)
@@ -2500,6 +2527,7 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 EXT4_RO_ATTR(delayed_allocation_blocks);
 EXT4_RO_ATTR(session_write_kbytes);
 EXT4_RO_ATTR(lifetime_write_kbytes);
+EXT4_RW_ATTR(reserved_clusters);
 EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
 		 inode_readahead_blks_store, s_inode_readahead_blks);
 EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
@@ -2517,6 +2545,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(delayed_allocation_blocks),
 	ATTR_LIST(session_write_kbytes),
 	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(reserved_clusters),
 	ATTR_LIST(inode_readahead_blks),
 	ATTR_LIST(inode_goal),
 	ATTR_LIST(mb_stats),
@@ -3192,6 +3221,40 @@ int ext4_calculate_overhead(struct super_block *sb)
 	return 0;
 }
 
+
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+{
+	ext4_fsblk_t resv_clusters;
+
+	/*
+	 * By default we reserve 2% or 4096 clusters, whichever is smaller.
+	 * This should cover the situations where we can not afford to run
+	 * out of space like for example punch hole, or converting
+	 * uninitialized extents in delalloc path. In most cases such
+	 * allocation would require 1, or 2 blocks, higher numbers are
+	 * very rare.
+	 */
+	resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+
+	do_div(resv_clusters, 50);
+	resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
+
+	return resv_clusters;
+}
+
+
+static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count)
+{
+	ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >>
+				sbi->s_cluster_bits;
+
+	if (count >= clusters)
+		return -EINVAL;
+
+	atomic64_set(&sbi->s_resv_clusters, count);
+	return 0;
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	char *orig_data = kstrdup(data, GFP_KERNEL);
@@ -3526,6 +3589,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
 	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
 
+	/* Do we have standard group size of blocksize * 8 blocks ? */
+	if (sbi->s_blocks_per_group == blocksize << 3)
+		set_opt2(sb, STD_GROUP_SIZE);
+
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
@@ -3698,6 +3765,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_err_report.function = print_daily_error_info;
 	sbi->s_err_report.data = (unsigned long) sb;
 
+	/* Register extent status tree shrinker */
+	ext4_es_register_shrinker(sb);
+
 	err = percpu_counter_init(&sbi->s_freeclusters_counter,
 			ext4_count_free_clusters(sb));
 	if (!err) {
@@ -3723,9 +3793,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_max_writeback_mb_bump = 128;
 	sbi->s_extent_max_zeroout_kb = 32;
 
-	/* Register extent status tree shrinker */
-	ext4_es_register_shrinker(sb);
-
 	/*
 	 * set up enough so that it can read an inode
 	 */
@@ -3911,6 +3978,13 @@ no_journal:
 			 "available");
 	}
 
+	err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
+			 "reserved pool", ext4_calculate_resv_clusters(sbi));
+		goto failed_mount4a;
+	}
+
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
@@ -4010,6 +4084,7 @@ failed_mount_wq:
 		sbi->s_journal = NULL;
 	}
 failed_mount3:
+	ext4_es_unregister_shrinker(sb);
 	del_timer(&sbi->s_err_report);
 	if (sbi->s_flex_groups)
 		ext4_kvfree(sbi->s_flex_groups);
@@ -4177,7 +4252,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 		goto out_bdev;
 	}
 	journal->j_private = sb;
-	ll_rw_block(READ, 1, &journal->j_sb_buffer);
+	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer);
 	wait_on_buffer(journal->j_sb_buffer);
 	if (!buffer_uptodate(journal->j_sb_buffer)) {
 		ext4_msg(sb, KERN_ERR, "I/O error on journal device");
@@ -4742,9 +4817,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct super_block *sb = dentry->d_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	ext4_fsblk_t overhead = 0;
+	ext4_fsblk_t overhead = 0, resv_blocks;
 	u64 fsid;
 	s64 bfree;
+	resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
 
 	if (!test_opt(sb, MINIX_DF))
 		overhead = sbi->s_overhead;
@@ -4756,8 +4832,9 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 		percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
 	/* prevent underflow in case that few free space is available */
 	buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
-	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
+	buf->f_bavail = buf->f_bfree -
-	if (buf->f_bfree < ext4_r_blocks_count(es))
+			(ext4_r_blocks_count(es) + resv_blocks);
+	if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks))
 		buf->f_bavail = 0;
 	buf->f_files = le32_to_cpu(es->s_inodes_count);
 	buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
@@ -4945,6 +5022,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 		return PTR_ERR(qf_inode);
 	}
 
+	/* Don't account quota for quota files to avoid recursion */
+	qf_inode->i_flags |= S_NOQUOTA;
 	err = dquot_enable(qf_inode, type, format_id, flags);
 	iput(qf_inode);
 

fs/ext4/xattr.c

@@ -122,17 +122,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 				    struct ext4_xattr_header *hdr)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u32 csum, old;
+	__u32 csum;
+	__le32 save_csum;
+	__le64 dsk_block_nr = cpu_to_le64(block_nr);
 
-	old = hdr->h_checksum;
+	save_csum = hdr->h_checksum;
 	hdr->h_checksum = 0;
-	block_nr = cpu_to_le64(block_nr);
+	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
-	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr,
+			   sizeof(dsk_block_nr));
-			   sizeof(block_nr));
 	csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
 			   EXT4_BLOCK_SIZE(inode->i_sb));
 
-	hdr->h_checksum = old;
+	hdr->h_checksum = save_csum;
 	return cpu_to_le32(csum);
 }
 

fs/ext4/xattr.h

@@ -22,6 +22,7 @@
 #define	EXT4_XATTR_INDEX_LUSTRE			5
 #define EXT4_XATTR_INDEX_SECURITY	        6
 #define EXT4_XATTR_INDEX_SYSTEM			7
+#define EXT4_XATTR_INDEX_RICHACL		8
 
 struct ext4_xattr_header {
 	__le32	h_magic;	/* magic number for identification */

fs/jbd2/commit.c

@@ -382,7 +382,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int space_left = 0;
 	int first_tag = 0;
 	int tag_flag;
-	int i, to_free = 0;
+	int i;
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
@@ -1134,7 +1134,7 @@ restart_loop:
 	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
 	spin_unlock(&journal->j_history_lock);
 
-	commit_transaction->t_state = T_FINISHED;
+	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;
 	journal->j_committing_transaction = NULL;
@@ -1149,13 +1149,9 @@ restart_loop:
 				journal->j_average_commit_time*3) / 4;
 	else
 		journal->j_average_commit_time = commit_time;
+
 	write_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
-		__jbd2_journal_drop_transaction(journal, commit_transaction);
-		to_free = 1;
-	} else {
 	if (journal->j_checkpoint_transactions == NULL) {
 		journal->j_checkpoint_transactions = commit_transaction;
 		commit_transaction->t_cpnext = commit_transaction;
@@ -1170,17 +1166,27 @@ restart_loop:
 		commit_transaction->t_cpprev->t_cpnext =
 				commit_transaction;
 	}
-	}
 	spin_unlock(&journal->j_list_lock);
-
+	/* Drop all spin_locks because commit_callback may be block.
+	 * __journal_remove_checkpoint() can not destroy transaction
+	 * under us because it is not marked as T_FINISHED yet */
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
-	if (to_free)
-		jbd2_journal_free_transaction(commit_transaction);
 
+	write_lock(&journal->j_state_lock);
+	spin_lock(&journal->j_list_lock);
+	commit_transaction->t_state = T_FINISHED;
+	/* Recheck checkpoint lists after j_list_lock was dropped */
+	if (commit_transaction->t_checkpoint_list == NULL &&
+	    commit_transaction->t_checkpoint_io_list == NULL) {
+		__jbd2_journal_drop_transaction(journal, commit_transaction);
+		jbd2_journal_free_transaction(commit_transaction);
+	}
+	spin_unlock(&journal->j_list_lock);
+	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
 }

fs/jbd2/journal.c

@@ -707,6 +707,37 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return err;
 }
 
+/*
+ * When this function returns the transaction corresponding to tid
+ * will be completed.  If the transaction has currently running, start
+ * committing that transaction before waiting for it to complete.  If
+ * the transaction id is stale, it is by definition already completed,
+ * so just return SUCCESS.
+ */
+int jbd2_complete_transaction(journal_t *journal, tid_t tid)
+{
+	int	need_to_wait = 1;
+
+	read_lock(&journal->j_state_lock);
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == tid) {
+		if (journal->j_commit_request != tid) {
+			/* transaction not yet started, so request it */
+			read_unlock(&journal->j_state_lock);
+			jbd2_log_start_commit(journal, tid);
+			goto wait_commit;
+		}
+	} else if (!(journal->j_committing_transaction &&
+		     journal->j_committing_transaction->t_tid == tid))
+		need_to_wait = 0;
+	read_unlock(&journal->j_state_lock);
+	if (!need_to_wait)
+		return 0;
+wait_commit:
+	return jbd2_log_wait_commit(journal, tid);
+}
+EXPORT_SYMBOL(jbd2_complete_transaction);
+
 /*
  * Log buffer allocation routines:
  */

fs/jbd2/transaction.c

@@ -332,7 +332,6 @@ static handle_t *new_handle(int nblocks)
 	handle_t *handle = jbd2_alloc_handle(GFP_NOFS);
 	if (!handle)
 		return NULL;
-	memset(handle, 0, sizeof(*handle));
 	handle->h_buffer_credits = nblocks;
 	handle->h_ref = 1;
 
@@ -640,6 +639,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	int error;
 	char *frozen_buffer = NULL;
 	int need_copy = 0;
+	unsigned long start_lock, time_lock;
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
@@ -655,9 +655,16 @@ repeat:
 
 	/* @@@ Need to check for errors here at some point. */
 
+ 	start_lock = jiffies;
 	lock_buffer(bh);
 	jbd_lock_bh_state(bh);
 
+	/* If it takes too long to lock the buffer, trace it */
+	time_lock = jbd2_time_diff(start_lock, jiffies);
+	if (time_lock > HZ/10)
+		trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev,
+			jiffies_to_msecs(time_lock));
+
 	/* We now hold the buffer lock so it is safe to query the buffer
 	 * state.  Is the buffer dirty?
 	 *

include/linux/buffer_head.h

@@ -34,6 +34,8 @@ enum bh_state_bits {
 	BH_Write_EIO,	/* I/O error on write */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
+	BH_Meta,	/* Buffer contains metadata */
+	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
@@ -124,6 +126,8 @@ BUFFER_FNS(Delay, delay)
 BUFFER_FNS(Boundary, boundary)
 BUFFER_FNS(Write_EIO, write_io_error)
 BUFFER_FNS(Unwritten, unwritten)
+BUFFER_FNS(Meta, meta)
+BUFFER_FNS(Prio, prio)
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
 

include/linux/jbd2.h

@@ -480,6 +480,7 @@ struct transaction_s
 		T_COMMIT,
 		T_COMMIT_DFLUSH,
 		T_COMMIT_JFLUSH,
+		T_COMMIT_CALLBACK,
 		T_FINISHED
 	}			t_state;
 
@@ -1144,7 +1145,7 @@ extern struct kmem_cache *jbd2_handle_cache;
 
 static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
 {
-	return kmem_cache_alloc(jbd2_handle_cache, gfp_flags);
+	return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags);
 }
 
 static inline void jbd2_free_handle(handle_t *handle)
@@ -1200,6 +1201,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
 int jbd2_journal_force_commit_nested(journal_t *journal);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
 

include/linux/journal-head.h

@@ -31,21 +31,14 @@ struct journal_head {
 	/*
 	 * Journalling list for this buffer [jbd_lock_bh_state()]
 	 */
-	unsigned b_jlist;
+	unsigned b_jlist:4;
 
 	/*
 	 * This flag signals the buffer has been modified by
 	 * the currently running transaction
 	 * [jbd_lock_bh_state()]
 	 */
-	unsigned b_modified;
+	unsigned b_modified:1;
-
-	/*
-	 * This feild tracks the last transaction id in which this buffer
-	 * has been cowed
-	 * [jbd_lock_bh_state()]
-	 */
-	tid_t b_cow_tid;
 
 	/*
 	 * Copy of the buffer data frozen for writing to the log.

include/trace/events/ext4.h

@@ -257,15 +257,7 @@ DECLARE_EVENT_CLASS(ext4__write_end,
 		  __entry->pos, __entry->len, __entry->copied)
 );
 
-DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end,
+DEFINE_EVENT(ext4__write_end, ext4_write_end,
-
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int copied),
-
-	TP_ARGS(inode, pos, len, copied)
-);
-
-DEFINE_EVENT(ext4__write_end, ext4_writeback_write_end,
 
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
 		 unsigned int copied),
@@ -1956,7 +1948,7 @@ TRACE_EVENT(ext4_remove_blocks,
 		__entry->to		= to;
 		__entry->partial	= partial_cluster;
 		__entry->ee_pblk	= ext4_ext_pblock(ex);
-		__entry->ee_lblk	= cpu_to_le32(ex->ee_block);
+		__entry->ee_lblk	= le32_to_cpu(ex->ee_block);
 		__entry->ee_len		= ext4_ext_get_actual_len(ex);
 	),
 
@@ -2060,7 +2052,7 @@ TRACE_EVENT(ext4_ext_remove_space,
 
 TRACE_EVENT(ext4_ext_remove_space_done,
 	TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth,
-		ext4_lblk_t partial, unsigned short eh_entries),
+		ext4_lblk_t partial, __le16 eh_entries),
 
 	TP_ARGS(inode, start, depth, partial, eh_entries),
 
@@ -2079,7 +2071,7 @@ TRACE_EVENT(ext4_ext_remove_space_done,
 		__entry->start		= start;
 		__entry->depth		= depth;
 		__entry->partial	= partial;
-		__entry->eh_entries	= eh_entries;
+		__entry->eh_entries	= le16_to_cpu(eh_entries);
 	),
 
 	TP_printk("dev %d,%d ino %lu since %u depth %d partial %u "

include/trace/events/jbd2.h

@@ -358,6 +358,27 @@ TRACE_EVENT(jbd2_write_superblock,
 		  MINOR(__entry->dev), __entry->write_op)
 );
 
+TRACE_EVENT(jbd2_lock_buffer_stall,
+
+	TP_PROTO(dev_t dev, unsigned long stall_ms),
+
+	TP_ARGS(dev, stall_ms),
+
+	TP_STRUCT__entry(
+		__field(        dev_t, dev	)
+		__field(unsigned long, stall_ms	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= dev;
+		__entry->stall_ms	= stall_ms;
+	),
+
+	TP_printk("dev %d,%d stall_ms %lu",
+		MAJOR(__entry->dev), MINOR(__entry->dev),
+		__entry->stall_ms)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */