Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (61 commits)
  jbd2: Add MAINTAINERS entry
  jbd2: fix a potential leak of a journal_head on an error path
  ext4: teach ext4_ext_split to calculate extents efficiently
  ext4: Convert ext4 to new truncate calling convention
  ext4: do not normalize block requests from fallocate()
  ext4: enable "punch hole" functionality
  ext4: add "punch hole" flag to ext4_map_blocks()
  ext4: punch out extents
  ext4: add new function ext4_block_zero_page_range()
  ext4: add flag to ext4_has_free_blocks
  ext4: reserve inodes and feature code for 'quota' feature
  ext4: add support for multiple mount protection
  ext4: ensure f_bfree returned by ext4_statfs() is non-negative
  ext4: protect bb_first_free in ext4_trim_all_free() with group lock
  ext4: only load buddy bitmap in ext4_trim_fs() when it is needed
  jbd2: Fix comment to match the code in jbd2__journal_start()
  ext4: fix waiting and sending of a barrier in ext4_sync_file()
  jbd2: Add function jbd2_trans_will_send_data_barrier()
  jbd2: fix sending of data flush on journal commit
  ext4: fix ext4_ext_fiemap_cb() to handle blocks before request range correctly
  ...

Documentation/filesystems/ext4.txt

@@ -226,10 +226,6 @@ acl			Enables POSIX Access Control Lists support.
 noacl			This option disables POSIX Access Control List
 			support.
 
-reservation
-
-noreservation
-
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
 

MAINTAINERS

@@ -3572,9 +3572,16 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Jan Kara <jack@suse.cz>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
-F:	fs/jbd*/
-F:	include/linux/ext*jbd*.h
-F:	include/linux/jbd*.h
+F:	fs/jbd/
+F:	include/linux/ext3_jbd.h
+F:	include/linux/jbd.h
+
+JOURNALLING LAYER FOR BLOCK DEVICES (JBD2)
+M:	"Theodore Ts'o" <tytso@mit.edu>
+L:	linux-ext4@vger.kernel.org
+S:	Maintained
+F:	fs/jbd2/
+F:	include/linux/jbd2.h
 
 JSM Neo PCI based serial card
 M:	Breno Leitao <leitao@linux.vnet.ibm.com>

fs/ext4/Makefile

@@ -6,7 +6,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
 
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
+		mmp.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o

fs/ext4/balloc.c

@@ -361,130 +361,6 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	return bh;
 }
 
-/**
- * ext4_add_groupblocks() -- Add given blocks to an existing group
- * @handle:			handle to this transaction
- * @sb:				super block
- * @block:			start physcial block to add to the block group
- * @count:			number of blocks to free
- *
- * This marks the blocks as free in the bitmap. We ask the
- * mballoc to reload the buddy after this by setting group
- * EXT4_GROUP_INFO_NEED_INIT_BIT flag
- */
-void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
-			 ext4_fsblk_t block, unsigned long count)
-{
-	struct buffer_head *bitmap_bh = NULL;
-	struct buffer_head *gd_bh;
-	ext4_group_t block_group;
-	ext4_grpblk_t bit;
-	unsigned int i;
-	struct ext4_group_desc *desc;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int err = 0, ret, blk_free_count;
-	ext4_grpblk_t blocks_freed;
-	struct ext4_group_info *grp;
-
-	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
-
-	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
-	grp = ext4_get_group_info(sb, block_group);
-	/*
-	 * Check to see if we are freeing blocks across a group
-	 * boundary.
-	 */
-	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
-		goto error_return;
-	}
-	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
-	if (!bitmap_bh)
-		goto error_return;
-	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
-	if (!desc)
-		goto error_return;
-
-	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
-	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, desc),
-		     sbi->s_itb_per_group)) {
-		ext4_error(sb, "Adding blocks in system zones - "
-			   "Block = %llu, count = %lu",
-			   block, count);
-		goto error_return;
-	}
-
-	/*
-	 * We are about to add blocks to the bitmap,
-	 * so we need undo access.
-	 */
-	BUFFER_TRACE(bitmap_bh, "getting undo access");
-	err = ext4_journal_get_undo_access(handle, bitmap_bh);
-	if (err)
-		goto error_return;
-
-	/*
-	 * We are about to modify some metadata.  Call the journal APIs
-	 * to unshare ->b_data if a currently-committing transaction is
-	 * using it
-	 */
-	BUFFER_TRACE(gd_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, gd_bh);
-	if (err)
-		goto error_return;
-	/*
-	 * make sure we don't allow a parallel init on other groups in the
-	 * same buddy cache
-	 */
-	down_write(&grp->alloc_sem);
-	for (i = 0, blocks_freed = 0; i < count; i++) {
-		BUFFER_TRACE(bitmap_bh, "clear bit");
-		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
-						bit + i, bitmap_bh->b_data)) {
-			ext4_error(sb, "bit already cleared for block %llu",
-				   (ext4_fsblk_t)(block + i));
-			BUFFER_TRACE(bitmap_bh, "bit already cleared");
-		} else {
-			blocks_freed++;
-		}
-	}
-	ext4_lock_group(sb, block_group);
-	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
-	ext4_free_blks_set(sb, desc, blk_free_count);
-	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
-	ext4_unlock_group(sb, block_group);
-	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
-
-	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(blocks_freed,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
-	}
-	/*
-	 * request to reload the buddy with the
-	 * new bitmap information
-	 */
-	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
-	grp->bb_free += blocks_freed;
-	up_write(&grp->alloc_sem);
-
-	/* We dirtied the bitmap block */
-	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
-	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-
-	/* And the group descriptor block */
-	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
-	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
-	if (!err)
-		err = ret;
-
-error_return:
-	brelse(bitmap_bh);
-	ext4_std_error(sb, err);
-	return;
-}
-
 /**
  * ext4_has_free_blocks()
  * @sbi:	in-core super block structure.
@@ -493,7 +369,8 @@ error_return:
  * Check if filesystem has nblocks free & available for allocation.
  * On success return 1, return 0 on failure.
  */
-static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
+static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
+				s64 nblocks, unsigned int flags)
 {
 	s64 free_blocks, dirty_blocks, root_blocks;
 	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
@@ -507,11 +384,6 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 						EXT4_FREEBLOCKS_WATERMARK) {
 		free_blocks  = percpu_counter_sum_positive(fbc);
 		dirty_blocks = percpu_counter_sum_positive(dbc);
-		if (dirty_blocks < 0) {
-			printk(KERN_CRIT "Dirty block accounting "
-					"went wrong %lld\n",
-					(long long)dirty_blocks);
-		}
 	}
 	/* Check whether we have space after
 	 * accounting for current dirty blocks & root reserved blocks.
@@ -522,7 +394,9 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 	/* Hm, nope.  Are (enough) root reserved blocks available? */
 	if (sbi->s_resuid == current_fsuid() ||
 	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
-	    capable(CAP_SYS_RESOURCE)) {
+	    capable(CAP_SYS_RESOURCE) ||
+		(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
+
 		if (free_blocks >= (nblocks + dirty_blocks))
 			return 1;
 	}
@@ -531,9 +405,9 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 }
 
 int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-						s64 nblocks)
+			   s64 nblocks, unsigned int flags)
 {
-	if (ext4_has_free_blocks(sbi, nblocks)) {
+	if (ext4_has_free_blocks(sbi, nblocks, flags)) {
 		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
 		return 0;
 	} else
@@ -554,7 +428,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) ||
+	if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
 	    (*retries)++ > 3 ||
 	    !EXT4_SB(sb)->s_journal)
 		return 0;
@@ -577,7 +451,8 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
  * error stores in errp pointer
  */
 ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
-		ext4_fsblk_t goal, unsigned long *count, int *errp)
+				  ext4_fsblk_t goal, unsigned int flags,
+				  unsigned long *count, int *errp)
 {
 	struct ext4_allocation_request ar;
 	ext4_fsblk_t ret;
@@ -587,6 +462,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	ar.inode = inode;
 	ar.goal = goal;
 	ar.len = count ? *count : 1;
+	ar.flags = flags;
 
 	ret = ext4_mb_new_blocks(handle, &ar, errp);
 	if (count)

fs/ext4/ext4.h

@@ -108,7 +108,8 @@ typedef unsigned int ext4_group_t;
 #define EXT4_MB_DELALLOC_RESERVED	0x0400
 /* We are doing stream allocation */
 #define EXT4_MB_STREAM_ALLOC		0x0800
-
+/* Use reserved root blocks if needed */
+#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
@@ -209,6 +210,8 @@ struct ext4_io_submit {
  */
 #define	EXT4_BAD_INO		 1	/* Bad blocks inode */
 #define EXT4_ROOT_INO		 2	/* Root inode */
+#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
+#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
 #define EXT4_BOOT_LOADER_INO	 5	/* Boot loader inode */
 #define EXT4_UNDEL_DIR_INO	 6	/* Undelete directory inode */
 #define EXT4_RESIZE_INO		 7	/* Reserved group descriptors inode */
@@ -512,6 +515,10 @@ struct ext4_new_group_data {
 	/* 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 */
+#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT		0x0020
+	/* Don't normalize allocation size (used for fallocate) */
+#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
 
 /*
  * Flags used by ext4_free_blocks
@@ -1028,7 +1035,7 @@ struct ext4_super_block {
 	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
 	__le32	s_flags;		/* Miscellaneous flags */
 	__le16  s_raid_stride;		/* RAID stride */
-	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
+	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
 	__le64  s_mmp_block;            /* Block for multi-mount protection */
 	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
 	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
@@ -1144,6 +1151,9 @@ struct ext4_sb_info {
 	unsigned long s_ext_blocks;
 	unsigned long s_ext_extents;
 #endif
+	/* ext4 extent cache stats */
+	unsigned long extent_cache_hits;
+	unsigned long extent_cache_misses;
 
 	/* for buddy allocator */
 	struct ext4_group_info ***s_group_info;
@@ -1201,6 +1211,9 @@ struct ext4_sb_info {
 	struct ext4_li_request *s_li_request;
 	/* Wait multiplier for lazy initialization thread */
 	unsigned int s_li_wait_mult;
+
+	/* Kernel thread for multiple mount protection */
+	struct task_struct *s_mmp_tsk;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1338,6 +1351,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
+#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
@@ -1351,13 +1365,29 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
 #define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
 
+#define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
+#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT4_FEATURE_INCOMPAT_META_BG)
+#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+
+#define EXT3_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
+#define EXT3_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT4_FEATURE_INCOMPAT_RECOVER| \
+					 EXT4_FEATURE_INCOMPAT_META_BG)
+#define EXT3_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+
 #define EXT4_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
 #define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
 					 EXT4_FEATURE_INCOMPAT_RECOVER| \
 					 EXT4_FEATURE_INCOMPAT_META_BG| \
 					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
 					 EXT4_FEATURE_INCOMPAT_64BIT| \
-					 EXT4_FEATURE_INCOMPAT_FLEX_BG)
+					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+					 EXT4_FEATURE_INCOMPAT_MMP)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
 					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
 					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -1590,12 +1620,6 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
  */
 struct ext4_lazy_init {
 	unsigned long		li_state;
-
-	wait_queue_head_t	li_wait_daemon;
-	wait_queue_head_t	li_wait_task;
-	struct timer_list	li_timer;
-	struct task_struct	*li_task;
-
 	struct list_head	li_request_list;
 	struct mutex		li_list_mtx;
 };
@@ -1614,6 +1638,67 @@ struct ext4_features {
 	struct completion f_kobj_unregister;
 };
 
+/*
+ * This structure will be used for multiple mount protection. It will be
+ * written into the block number saved in the s_mmp_block field in the
+ * superblock. Programs that check MMP should assume that if
+ * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
+ * to use the filesystem, regardless of how old the timestamp is.
+ */
+#define EXT4_MMP_MAGIC     0x004D4D50U /* ASCII for MMP */
+#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
+#define EXT4_MMP_SEQ_FSCK  0xE24D4D50U /* mmp_seq value when being fscked */
+#define EXT4_MMP_SEQ_MAX   0xE24D4D4FU /* maximum valid mmp_seq value */
+
+struct mmp_struct {
+	__le32	mmp_magic;		/* Magic number for MMP */
+	__le32	mmp_seq;		/* Sequence no. updated periodically */
+
+	/*
+	 * mmp_time, mmp_nodename & mmp_bdevname are only used for information
+	 * purposes and do not affect the correctness of the algorithm
+	 */
+	__le64	mmp_time;		/* Time last updated */
+	char	mmp_nodename[64];	/* Node which last updated MMP block */
+	char	mmp_bdevname[32];	/* Bdev which last updated MMP block */
+
+	/*
+	 * mmp_check_interval is used to verify if the MMP block has been
+	 * updated on the block device. The value is updated based on the
+	 * maximum time to write the MMP block during an update cycle.
+	 */
+	__le16	mmp_check_interval;
+
+	__le16	mmp_pad1;
+	__le32	mmp_pad2[227];
+};
+
+/* arguments passed to the mmp thread */
+struct mmpd_data {
+	struct buffer_head *bh; /* bh from initial read_mmp_block() */
+	struct super_block *sb;  /* super block of the fs */
+};
+
+/*
+ * Check interval multiplier
+ * The MMP block is written every update interval and initially checked every
+ * update interval x the multiplier (the value is then adapted based on the
+ * write latency). The reason is that writes can be delayed under load and we
+ * don't want readers to incorrectly assume that the filesystem is no longer
+ * in use.
+ */
+#define EXT4_MMP_CHECK_MULT		2UL
+
+/*
+ * Minimum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MIN_CHECK_INTERVAL	5UL
+
+/*
+ * Maximum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MAX_CHECK_INTERVAL	300UL
+
 /*
  * Function prototypes
  */
@@ -1638,10 +1723,12 @@ extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
 extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
 			ext4_group_t group);
 extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t goal, unsigned long *count, int *errp);
-extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
-				ext4_fsblk_t block, unsigned long count);
+					 ext4_fsblk_t goal,
+					 unsigned int flags,
+					 unsigned long *count,
+					 int *errp);
+extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+				  s64 nblocks, unsigned int flags);
 extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
 extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
@@ -1706,6 +1793,8 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     unsigned long count, int flags);
 extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
+extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 
 /* inode.c */
@@ -1729,6 +1818,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
 extern void ext4_truncate(struct inode *);
+extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
@@ -1738,6 +1828,8 @@ extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
+extern int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1788,6 +1880,10 @@ extern void __ext4_warning(struct super_block *, const char *, unsigned int,
 						       __LINE__, ## message)
 extern void ext4_msg(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
+			   const char *, unsigned int, const char *);
+#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
+						       __LINE__, msg)
 extern void __ext4_grp_locked_error(const char *, unsigned int, \
 				    struct super_block *, ext4_group_t, \
 				    unsigned long, ext4_fsblk_t, \
@@ -2064,6 +2160,8 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 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 int ext4_ext_punch_hole(struct file *file, loff_t offset,
+				loff_t length);
 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,
@@ -2092,6 +2190,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       int len,
 			       struct writeback_control *wbc);
 
+/* mmp.c */
+extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
+
 /* BH_Uninit flag: blocks are allocated but uninitialized on disk */
 enum ext4_state_bits {
 	BH_Uninit	/* blocks are allocated but uninitialized on disk */

fs/ext4/ext4_jbd2.c

@@ -6,20 +6,6 @@
 
 #include <trace/events/ext4.h>
 
-int __ext4_journal_get_undo_access(const char *where, unsigned int line,
-				   handle_t *handle, struct buffer_head *bh)
-{
-	int err = 0;
-
-	if (ext4_handle_valid(handle)) {
-		err = jbd2_journal_get_undo_access(handle, bh);
-		if (err)
-			ext4_journal_abort_handle(where, line, __func__, bh,
-						  handle, err);
-	}
-	return err;
-}
-
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh)
 {

fs/ext4/ext4_jbd2.h

@@ -126,9 +126,6 @@ void ext4_journal_abort_handle(const char *caller, unsigned int line,
 			       const char *err_fn,
 		struct buffer_head *bh, handle_t *handle, int err);
 
-int __ext4_journal_get_undo_access(const char *where, unsigned int line,
-				   handle_t *handle, struct buffer_head *bh);
-
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh);
 
@@ -146,8 +143,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 int __ext4_handle_dirty_super(const char *where, unsigned int line,
 			      handle_t *handle, struct super_block *sb);
 
-#define ext4_journal_get_undo_access(handle, bh) \
-	__ext4_journal_get_undo_access(__func__, __LINE__, (handle), (bh))
 #define ext4_journal_get_write_access(handle, bh) \
 	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
 #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \

fs/ext4/extents.c

@@ -46,6 +46,13 @@
 
 #include <trace/events/ext4.h>
 
+static int ext4_split_extent(handle_t *handle,
+				struct inode *inode,
+				struct ext4_ext_path *path,
+				struct ext4_map_blocks *map,
+				int split_flag,
+				int flags);
+
 static int ext4_ext_truncate_extend_restart(handle_t *handle,
 					    struct inode *inode,
 					    int needed)
@@ -192,12 +199,13 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 static ext4_fsblk_t
 ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
 			struct ext4_ext_path *path,
-			struct ext4_extent *ex, int *err)
+			struct ext4_extent *ex, int *err, unsigned int flags)
 {
 	ext4_fsblk_t goal, newblock;
 
 	goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
-	newblock = ext4_new_meta_blocks(handle, inode, goal, NULL, err);
+	newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
+					NULL, err);
 	return newblock;
 }
 
@@ -474,9 +482,43 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
 	}
 	ext_debug("\n");
 }
+
+static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
+			ext4_fsblk_t newblock, int level)
+{
+	int depth = ext_depth(inode);
+	struct ext4_extent *ex;
+
+	if (depth != level) {
+		struct ext4_extent_idx *idx;
+		idx = path[level].p_idx;
+		while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) {
+			ext_debug("%d: move %d:%llu in new index %llu\n", level,
+					le32_to_cpu(idx->ei_block),
+					ext4_idx_pblock(idx),
+					newblock);
+			idx++;
+		}
+
+		return;
+	}
+
+	ex = path[depth].p_ext;
+	while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) {
+		ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
+				le32_to_cpu(ex->ee_block),
+				ext4_ext_pblock(ex),
+				ext4_ext_is_uninitialized(ex),
+				ext4_ext_get_actual_len(ex),
+				newblock);
+		ex++;
+	}
+}
+
 #else
 #define ext4_ext_show_path(inode, path)
 #define ext4_ext_show_leaf(inode, path)
+#define ext4_ext_show_move(inode, path, newblock, level)
 #endif
 
 void ext4_ext_drop_refs(struct ext4_ext_path *path)
@@ -792,14 +834,14 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
  * - initializes subtree
  */
 static int ext4_ext_split(handle_t *handle, struct inode *inode,
-				struct ext4_ext_path *path,
-				struct ext4_extent *newext, int at)
+			  unsigned int flags,
+			  struct ext4_ext_path *path,
+			  struct ext4_extent *newext, int at)
 {
 	struct buffer_head *bh = NULL;
 	int depth = ext_depth(inode);
 	struct ext4_extent_header *neh;
 	struct ext4_extent_idx *fidx;
-	struct ext4_extent *ex;
 	int i = at, k, m, a;
 	ext4_fsblk_t newblock, oldblock;
 	__le32 border;
@@ -847,7 +889,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
 	for (a = 0; a < depth - at; a++) {
 		newblock = ext4_ext_new_meta_block(handle, inode, path,
-						   newext, &err);
+						   newext, &err, flags);
 		if (newblock == 0)
 			goto cleanup;
 		ablocks[a] = newblock;
@@ -876,7 +918,6 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
 	neh->eh_magic = EXT4_EXT_MAGIC;
 	neh->eh_depth = 0;
-	ex = EXT_FIRST_EXTENT(neh);
 
 	/* move remainder of path[depth] to the new leaf */
 	if (unlikely(path[depth].p_hdr->eh_entries !=
@@ -888,25 +929,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		goto cleanup;
 	}
 	/* start copy from next extent */
-	/* TODO: we could do it by single memmove */
-	m = 0;
-	path[depth].p_ext++;
-	while (path[depth].p_ext <=
-			EXT_MAX_EXTENT(path[depth].p_hdr)) {
-		ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
-				le32_to_cpu(path[depth].p_ext->ee_block),
-				ext4_ext_pblock(path[depth].p_ext),
-				ext4_ext_is_uninitialized(path[depth].p_ext),
-				ext4_ext_get_actual_len(path[depth].p_ext),
-				newblock);
-		/*memmove(ex++, path[depth].p_ext++,
-				sizeof(struct ext4_extent));
-		neh->eh_entries++;*/
-		path[depth].p_ext++;
-		m++;
-	}
+	m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++;
+	ext4_ext_show_move(inode, path, newblock, depth);
 	if (m) {
-		memmove(ex, path[depth].p_ext-m, sizeof(struct ext4_extent)*m);
+		struct ext4_extent *ex;
+		ex = EXT_FIRST_EXTENT(neh);
+		memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m);
 		le16_add_cpu(&neh->eh_entries, m);
 	}
 
@@ -968,12 +996,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 
 		ext_debug("int.index at %d (block %llu): %u -> %llu\n",
 				i, newblock, le32_to_cpu(border), oldblock);
-		/* copy indexes */
-		m = 0;
-		path[i].p_idx++;
 
-		ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
-				EXT_MAX_INDEX(path[i].p_hdr));
+		/* move remainder of path[i] to the new index block */
 		if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
 					EXT_LAST_INDEX(path[i].p_hdr))) {
 			EXT4_ERROR_INODE(inode,
@@ -982,20 +1006,13 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 			err = -EIO;
 			goto cleanup;
 		}
-		while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
-			ext_debug("%d: move %d:%llu in new index %llu\n", i,
-					le32_to_cpu(path[i].p_idx->ei_block),
-					ext4_idx_pblock(path[i].p_idx),
-					newblock);
-			/*memmove(++fidx, path[i].p_idx++,
-					sizeof(struct ext4_extent_idx));
-			neh->eh_entries++;
-			BUG_ON(neh->eh_entries > neh->eh_max);*/
-			path[i].p_idx++;
-			m++;
-		}
+		/* start copy indexes */
+		m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++;
+		ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
+				EXT_MAX_INDEX(path[i].p_hdr));
+		ext4_ext_show_move(inode, path, newblock, i);
 		if (m) {
-			memmove(++fidx, path[i].p_idx - m,
+			memmove(++fidx, path[i].p_idx,
 				sizeof(struct ext4_extent_idx) * m);
 			le16_add_cpu(&neh->eh_entries, m);
 		}
@@ -1056,8 +1073,9 @@ cleanup:
  *   just created block
  */
 static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
-					struct ext4_ext_path *path,
-					struct ext4_extent *newext)
+				 unsigned int flags,
+				 struct ext4_ext_path *path,
+				 struct ext4_extent *newext)
 {
 	struct ext4_ext_path *curp = path;
 	struct ext4_extent_header *neh;
@@ -1065,7 +1083,8 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t newblock;
 	int err = 0;
 
-	newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err);
+	newblock = ext4_ext_new_meta_block(handle, inode, path,
+		newext, &err, flags);
 	if (newblock == 0)
 		return err;
 
@@ -1140,8 +1159,9 @@ out:
  * if no free index is found, then it requests in-depth growing.
  */
 static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
-					struct ext4_ext_path *path,
-					struct ext4_extent *newext)
+				    unsigned int flags,
+				    struct ext4_ext_path *path,
+				    struct ext4_extent *newext)
 {
 	struct ext4_ext_path *curp;
 	int depth, i, err = 0;
@@ -1161,7 +1181,7 @@ repeat:
 	if (EXT_HAS_FREE_INDEX(curp)) {
 		/* if we found index with free entry, then use that
 		 * entry: create all needed subtree and add new leaf */
-		err = ext4_ext_split(handle, inode, path, newext, i);
+		err = ext4_ext_split(handle, inode, flags, path, newext, i);
 		if (err)
 			goto out;
 
@@ -1174,7 +1194,8 @@ repeat:
 			err = PTR_ERR(path);
 	} else {
 		/* tree is full, time to grow in depth */
-		err = ext4_ext_grow_indepth(handle, inode, path, newext);
+		err = ext4_ext_grow_indepth(handle, inode, flags,
+					    path, newext);
 		if (err)
 			goto out;
 
@@ -1563,7 +1584,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
  * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns
  * 1 if they got merged.
  */
-static int ext4_ext_try_to_merge(struct inode *inode,
+static int ext4_ext_try_to_merge_right(struct inode *inode,
 				 struct ext4_ext_path *path,
 				 struct ext4_extent *ex)
 {
@@ -1602,6 +1623,31 @@ static int ext4_ext_try_to_merge(struct inode *inode,
 	return merge_done;
 }
 
+/*
+ * This function tries to merge the @ex extent to neighbours in the tree.
+ * return 1 if merge left else 0.
+ */
+static int ext4_ext_try_to_merge(struct inode *inode,
+				  struct ext4_ext_path *path,
+				  struct ext4_extent *ex) {
+	struct ext4_extent_header *eh;
+	unsigned int depth;
+	int merge_done = 0;
+	int ret = 0;
+
+	depth = ext_depth(inode);
+	BUG_ON(path[depth].p_hdr == NULL);
+	eh = path[depth].p_hdr;
+
+	if (ex > EXT_FIRST_EXTENT(eh))
+		merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1);
+
+	if (!merge_done)
+		ret = ext4_ext_try_to_merge_right(inode, path, ex);
+
+	return ret;
+}
+
 /*
  * check if a portion of the "newext" extent overlaps with an
  * existing extent.
@@ -1668,6 +1714,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	int depth, len, err;
 	ext4_lblk_t next;
 	unsigned uninitialized = 0;
+	int flags = 0;
 
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
 		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1742,7 +1789,9 @@ repeat:
 	 * There is no free space in the found leaf.
 	 * We're gonna add a new leaf in the tree.
 	 */
-	err = ext4_ext_create_new_leaf(handle, inode, path, newext);
+	if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT)
+		flags = EXT4_MB_USE_ROOT_BLOCKS;
+	err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
 	if (err)
 		goto cleanup;
 	depth = ext_depth(inode);
@@ -2003,13 +2052,25 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 }
 
 /*
+ * ext4_ext_in_cache()
+ * Checks to see if the given block is in the cache.
+ * If it is, the cached extent is stored in the given
+ * cache extent pointer.  If the cached extent is a hole,
+ * this routine should be used instead of
+ * ext4_ext_in_cache if the calling function needs to
+ * know the size of the hole.
+ *
+ * @inode: The files inode
+ * @block: The block to look for in the cache
+ * @ex:    Pointer where the cached extent will be stored
+ *         if it contains block
+ *
  * Return 0 if cache is invalid; 1 if the cache is valid
  */
-static int
-ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
-			struct ext4_extent *ex)
-{
+static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block,
+	struct ext4_ext_cache *ex){
 	struct ext4_ext_cache *cex;
+	struct ext4_sb_info *sbi;
 	int ret = 0;
 
 	/*
@@ -2017,25 +2078,59 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
 	 */
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 	cex = &EXT4_I(inode)->i_cached_extent;
+	sbi = EXT4_SB(inode->i_sb);
 
 	/* has cache valid data? */
 	if (cex->ec_len == 0)
 		goto errout;
 
 	if (in_range(block, cex->ec_block, cex->ec_len)) {
-		ex->ee_block = cpu_to_le32(cex->ec_block);
-		ext4_ext_store_pblock(ex, cex->ec_start);
-		ex->ee_len = cpu_to_le16(cex->ec_len);
+		memcpy(ex, cex, sizeof(struct ext4_ext_cache));
 		ext_debug("%u cached by %u:%u:%llu\n",
 				block,
 				cex->ec_block, cex->ec_len, cex->ec_start);
 		ret = 1;
 	}
 errout:
+	if (!ret)
+		sbi->extent_cache_misses++;
+	else
+		sbi->extent_cache_hits++;
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 	return ret;
 }
 
+/*
+ * ext4_ext_in_cache()
+ * Checks to see if the given block is in the cache.
+ * If it is, the cached extent is stored in the given
+ * extent pointer.
+ *
+ * @inode: The files inode
+ * @block: The block to look for in the cache
+ * @ex:    Pointer where the cached extent will be stored
+ *         if it contains block
+ *
+ * Return 0 if cache is invalid; 1 if the cache is valid
+ */
+static int
+ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
+			struct ext4_extent *ex)
+{
+	struct ext4_ext_cache cex;
+	int ret = 0;
+
+	if (ext4_ext_check_cache(inode, block, &cex)) {
+		ex->ee_block = cpu_to_le32(cex.ec_block);
+		ext4_ext_store_pblock(ex, cex.ec_start);
+		ex->ee_len = cpu_to_le16(cex.ec_len);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+
 /*
  * ext4_ext_rm_idx:
  * removes index from the index block.
@@ -2163,8 +2258,16 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		ext4_free_blocks(handle, inode, NULL, start, num, flags);
 	} else if (from == le32_to_cpu(ex->ee_block)
 		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
-		printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
-			from, to, le32_to_cpu(ex->ee_block), ee_len);
+		/* head removal */
+		ext4_lblk_t num;
+		ext4_fsblk_t start;
+
+		num = to - from;
+		start = ext4_ext_pblock(ex);
+
+		ext_debug("free first %u blocks starting %llu\n", num, start);
+		ext4_free_blocks(handle, inode, 0, start, num, flags);
+
 	} else {
 		printk(KERN_INFO "strange request: removal(2) "
 				"%u-%u from %u:%u\n",
@@ -2173,9 +2276,22 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
+
+/*
+ * ext4_ext_rm_leaf() Removes the extents associated with the
+ * blocks appearing between "start" and "end", and splits the extents
+ * if "start" and "end" appear in the same extent
+ *
+ * @handle: The journal handle
+ * @inode:  The files inode
+ * @path:   The path to the leaf
+ * @start:  The first block to remove
+ * @end:   The last block to remove
+ */
 static int
 ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
-		struct ext4_ext_path *path, ext4_lblk_t start)
+		struct ext4_ext_path *path, ext4_lblk_t start,
+		ext4_lblk_t end)
 {
 	int err = 0, correct_index = 0;
 	int depth = ext_depth(inode), credits;
@@ -2186,6 +2302,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	unsigned short ex_ee_len;
 	unsigned uninitialized = 0;
 	struct ext4_extent *ex;
+	struct ext4_map_blocks map;
 
 	/* the header must be checked already in ext4_ext_remove_space() */
 	ext_debug("truncate since %u in leaf\n", start);
@@ -2215,31 +2332,95 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		path[depth].p_ext = ex;
 
 		a = ex_ee_block > start ? ex_ee_block : start;
-		b = ex_ee_block + ex_ee_len - 1 < EXT_MAX_BLOCK ?
-			ex_ee_block + ex_ee_len - 1 : EXT_MAX_BLOCK;
+		b = ex_ee_block+ex_ee_len - 1 < end ?
+			ex_ee_block+ex_ee_len - 1 : end;
 
 		ext_debug("  border %u:%u\n", a, b);
 
-		if (a != ex_ee_block && b != ex_ee_block + ex_ee_len - 1) {
-			block = 0;
-			num = 0;
-			BUG();
+		/* If this extent is beyond the end of the hole, skip it */
+		if (end <= ex_ee_block) {
+			ex--;
+			ex_ee_block = le32_to_cpu(ex->ee_block);
+			ex_ee_len = ext4_ext_get_actual_len(ex);
+			continue;
+		} else if (a != ex_ee_block &&
+			b != ex_ee_block + ex_ee_len - 1) {
+			/*
+			 * If this is a truncate, then this condition should
+			 * never happen because at least one of the end points
+			 * needs to be on the edge of the extent.
+			 */
+			if (end == EXT_MAX_BLOCK) {
+				ext_debug("  bad truncate %u:%u\n",
+						start, end);
+				block = 0;
+				num = 0;
+				err = -EIO;
+				goto out;
+			}
+			/*
+			 * else this is a hole punch, so the extent needs to
+			 * be split since neither edge of the hole is on the
+			 * extent edge
+			 */
+			else{
+				map.m_pblk = ext4_ext_pblock(ex);
+				map.m_lblk = ex_ee_block;
+				map.m_len = b - ex_ee_block;
+
+				err = ext4_split_extent(handle,
+					inode, path, &map, 0,
+					EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
+					EXT4_GET_BLOCKS_PRE_IO);
+
+				if (err < 0)
+					goto out;
+
+				ex_ee_len = ext4_ext_get_actual_len(ex);
+
+				b = ex_ee_block+ex_ee_len - 1 < end ?
+					ex_ee_block+ex_ee_len - 1 : end;
+
+				/* Then remove tail of this extent */
+				block = ex_ee_block;
+				num = a - block;
+			}
 		} else if (a != ex_ee_block) {
 			/* remove tail of the extent */
 			block = ex_ee_block;
 			num = a - block;
 		} else if (b != ex_ee_block + ex_ee_len - 1) {
 			/* remove head of the extent */
-			block = a;
-			num = b - a;
-			/* there is no "make a hole" API yet */
-			BUG();
+			block = b;
+			num =  ex_ee_block + ex_ee_len - b;
+
+			/*
+			 * If this is a truncate, this condition
+			 * should never happen
+			 */
+			if (end == EXT_MAX_BLOCK) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
 		} else {
 			/* remove whole extent: excellent! */
 			block = ex_ee_block;
 			num = 0;
-			BUG_ON(a != ex_ee_block);
-			BUG_ON(b != ex_ee_block + ex_ee_len - 1);
+			if (a != ex_ee_block) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
+
+			if (b != ex_ee_block + ex_ee_len - 1) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
 		}
 
 		/*
@@ -2270,7 +2451,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		if (num == 0) {
 			/* this extent is removed; mark slot entirely unused */
 			ext4_ext_store_pblock(ex, 0);
-			le16_add_cpu(&eh->eh_entries, -1);
+		} else if (block != ex_ee_block) {
+			/*
+			 * If this was a head removal, then we need to update
+			 * the physical block since it is now at a different
+			 * location
+			 */
+			ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
 		}
 
 		ex->ee_block = cpu_to_le32(block);
@@ -2286,6 +2473,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		if (err)
 			goto out;
 
+		/*
+		 * If the extent was completely released,
+		 * we need to remove it from the leaf
+		 */
+		if (num == 0) {
+			if (end != EXT_MAX_BLOCK) {
+				/*
+				 * For hole punching, we need to scoot all the
+				 * extents up when an extent is removed so that
+				 * we dont have blank extents in the middle
+				 */
+				memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) *
+					sizeof(struct ext4_extent));
+
+				/* Now get rid of the one at the end */
+				memset(EXT_LAST_EXTENT(eh), 0,
+					sizeof(struct ext4_extent));
+			}
+			le16_add_cpu(&eh->eh_entries, -1);
+		}
+
 		ext_debug("new extent: %u:%u:%llu\n", block, num,
 				ext4_ext_pblock(ex));
 		ex--;
@@ -2326,7 +2534,8 @@ 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)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+				ext4_lblk_t end)
 {
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
@@ -2365,7 +2574,8 @@ again:
 	while (i >= 0 && err == 0) {
 		if (i == depth) {
 			/* this is leaf block */
-			err = ext4_ext_rm_leaf(handle, inode, path, start);
+			err = ext4_ext_rm_leaf(handle, inode, path,
+					start, end);
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
 			path[i].p_bh = NULL;
@@ -2529,6 +2739,195 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 	return ret;
 }
 
+/*
+ * used by extent splitting.
+ */
+#define EXT4_EXT_MAY_ZEROOUT	0x1  /* safe to zeroout if split fails \
+					due to ENOSPC */
+#define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
+#define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
+
+/*
+ * ext4_split_extent_at() splits an extent at given block.
+ *
+ * @handle: the journal handle
+ * @inode: the file inode
+ * @path: the path to the extent
+ * @split: the logical block where the extent is splitted.
+ * @split_flags: indicates if the extent could be zeroout if split fails, and
+ *		 the states(init or uninit) of new extents.
+ * @flags: flags used to insert new extent to extent tree.
+ *
+ *
+ * Splits extent [a, b] into two extents [a, @split) and [@split, b], states
+ * of which are deterimined by split_flag.
+ *
+ * There are two cases:
+ *  a> the extent are splitted into two extent.
+ *  b> split is not needed, and just mark the extent.
+ *
+ * return 0 on success.
+ */
+static int ext4_split_extent_at(handle_t *handle,
+			     struct inode *inode,
+			     struct ext4_ext_path *path,
+			     ext4_lblk_t split,
+			     int split_flag,
+			     int flags)
+{
+	ext4_fsblk_t newblock;
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex, newex, orig_ex;
+	struct ext4_extent *ex2 = NULL;
+	unsigned int ee_len, depth;
+	int err = 0;
+
+	ext_debug("ext4_split_extents_at: inode %lu, logical"
+		"block %llu\n", inode->i_ino, (unsigned long long)split);
+
+	ext4_ext_show_leaf(inode, path);
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+	newblock = split - ee_block + ext4_ext_pblock(ex);
+
+	BUG_ON(split < ee_block || split >= (ee_block + ee_len));
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+
+	if (split == ee_block) {
+		/*
+		 * case b: block @split is the block that the extent begins with
+		 * then we just change the state of the extent, and splitting
+		 * is not needed.
+		 */
+		if (split_flag & EXT4_EXT_MARK_UNINIT2)
+			ext4_ext_mark_uninitialized(ex);
+		else
+			ext4_ext_mark_initialized(ex);
+
+		if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
+			ext4_ext_try_to_merge(inode, path, ex);
+
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
+	}
+
+	/* case a */
+	memcpy(&orig_ex, ex, sizeof(orig_ex));
+	ex->ee_len = cpu_to_le16(split - ee_block);
+	if (split_flag & EXT4_EXT_MARK_UNINIT1)
+		ext4_ext_mark_uninitialized(ex);
+
+	/*
+	 * path may lead to new leaf, not to original leaf any more
+	 * after ext4_ext_insert_extent() returns,
+	 */
+	err = ext4_ext_dirty(handle, inode, path + depth);
+	if (err)
+		goto fix_extent_len;
+
+	ex2 = &newex;
+	ex2->ee_block = cpu_to_le32(split);
+	ex2->ee_len   = cpu_to_le16(ee_len - (split - ee_block));
+	ext4_ext_store_pblock(ex2, newblock);
+	if (split_flag & EXT4_EXT_MARK_UNINIT2)
+		ext4_ext_mark_uninitialized(ex2);
+
+	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+		err = ext4_ext_zeroout(inode, &orig_ex);
+		if (err)
+			goto fix_extent_len;
+		/* update the extent length and mark as initialized */
+		ex->ee_len = cpu_to_le32(ee_len);
+		ext4_ext_try_to_merge(inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
+	} else if (err)
+		goto fix_extent_len;
+
+out:
+	ext4_ext_show_leaf(inode, path);
+	return err;
+
+fix_extent_len:
+	ex->ee_len = orig_ex.ee_len;
+	ext4_ext_dirty(handle, inode, path + depth);
+	return err;
+}
+
+/*
+ * ext4_split_extents() splits an extent and mark extent which is covered
+ * by @map as split_flags indicates
+ *
+ * It may result in splitting the extent into multiple extents (upto three)
+ * There are three possibilities:
+ *   a> There is no split required
+ *   b> Splits in two extents: Split is happening at either end of the extent
+ *   c> Splits in three extents: Somone is splitting in middle of the extent
+ *
+ */
+static int ext4_split_extent(handle_t *handle,
+			      struct inode *inode,
+			      struct ext4_ext_path *path,
+			      struct ext4_map_blocks *map,
+			      int split_flag,
+			      int flags)
+{
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex;
+	unsigned int ee_len, depth;
+	int err = 0;
+	int uninitialized;
+	int split_flag1, flags1;
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+	uninitialized = ext4_ext_is_uninitialized(ex);
+
+	if (map->m_lblk + map->m_len < ee_block + ee_len) {
+		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
+			      EXT4_EXT_MAY_ZEROOUT : 0;
+		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
+		if (uninitialized)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
+				       EXT4_EXT_MARK_UNINIT2;
+		err = ext4_split_extent_at(handle, inode, path,
+				map->m_lblk + map->m_len, split_flag1, flags1);
+		if (err)
+			goto out;
+	}
+
+	ext4_ext_drop_refs(path);
+	path = ext4_ext_find_extent(inode, map->m_lblk, path);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	if (map->m_lblk >= ee_block) {
+		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
+			      EXT4_EXT_MAY_ZEROOUT : 0;
+		if (uninitialized)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+		if (split_flag & EXT4_EXT_MARK_UNINIT2)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT2;
+		err = ext4_split_extent_at(handle, inode, path,
+				map->m_lblk, split_flag1, flags);
+		if (err)
+			goto out;
+	}
+
+	ext4_ext_show_leaf(inode, path);
+out:
+	return err ? err : map->m_len;
+}
+
 #define EXT4_EXT_ZERO_LEN 7
 /*
  * This function is called by ext4_ext_map_blocks() if someone tries to write
@@ -2545,17 +2944,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 					   struct ext4_map_blocks *map,
 					   struct ext4_ext_path *path)
 {
-	struct ext4_extent *ex, newex, orig_ex;
-	struct ext4_extent *ex1 = NULL;
-	struct ext4_extent *ex2 = NULL;
-	struct ext4_extent *ex3 = NULL;
-	struct ext4_extent_header *eh;
+	struct ext4_map_blocks split_map;
+	struct ext4_extent zero_ex;
+	struct ext4_extent *ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int allocated, ee_len, depth;
-	ext4_fsblk_t newblock;
 	int err = 0;
-	int ret = 0;
-	int may_zeroout;
+	int split_flag = 0;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -2567,280 +2962,86 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		eof_block = map->m_lblk + map->m_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);
-	newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
-
-	ex2 = ex;
-	orig_ex.ee_block = ex->ee_block;
-	orig_ex.ee_len   = cpu_to_le16(ee_len);
-	ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
 
+	WARN_ON(map->m_lblk < ee_block);
 	/*
 	 * It is safe to convert extent to initialized via explicit
 	 * zeroout only if extent is fully insde i_size or new_size.
 	 */
-	may_zeroout = ee_block + ee_len <= eof_block;
+	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
 
-	err = ext4_ext_get_access(handle, inode, path + depth);
-	if (err)
-		goto out;
 	/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
-	if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) {
-		err =  ext4_ext_zeroout(inode, &orig_ex);
+	if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
+	    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+		err = ext4_ext_zeroout(inode, ex);
 		if (err)
-			goto fix_extent_len;
-		/* update the extent length and mark as initialized */
-		ex->ee_block = orig_ex.ee_block;
-		ex->ee_len   = orig_ex.ee_len;
-		ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-		ext4_ext_dirty(handle, inode, path + depth);
-		/* zeroed the full extent */
-		return allocated;
-	}
+			goto out;
 
-	/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
-	if (map->m_lblk > ee_block) {
-		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
-		ext4_ext_mark_uninitialized(ex1);
-		ex2 = &newex;
+		err = ext4_ext_get_access(handle, inode, path + depth);
+		if (err)
+			goto out;
+		ext4_ext_mark_initialized(ex);
+		ext4_ext_try_to_merge(inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
 	}
+
 	/*
-	 * for sanity, update the length of the ex2 extent before
-	 * we insert ex3, if ex1 is NULL. This is to avoid temporary
-	 * overlap of blocks.
+	 * four cases:
+	 * 1. split the extent into three extents.
+	 * 2. split the extent into two extents, zeroout the first half.
+	 * 3. split the extent into two extents, zeroout the second half.
+	 * 4. split the extent into two extents with out zeroout.
 	 */
-	if (!ex1 && allocated > map->m_len)
-		ex2->ee_len = cpu_to_le16(map->m_len);
-	/* ex3: to ee_block + ee_len : uninitialised */
-	if (allocated > map->m_len) {
-		unsigned int newdepth;
-		/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
-		if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
-			/*
-			 * map->m_lblk == ee_block is handled by the zerouout
-			 * at the beginning.
-			 * Mark first half uninitialized.
-			 * Mark second half initialized and zero out the
-			 * initialized extent
-			 */
-			ex->ee_block = orig_ex.ee_block;
-			ex->ee_len   = cpu_to_le16(ee_len - allocated);
-			ext4_ext_mark_uninitialized(ex);
-			ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-			ext4_ext_dirty(handle, inode, path + depth);
-
-			ex3 = &newex;
-			ex3->ee_block = cpu_to_le32(map->m_lblk);
-			ext4_ext_store_pblock(ex3, newblock);
-			ex3->ee_len = cpu_to_le16(allocated);
-			err = ext4_ext_insert_extent(handle, inode, path,
-							ex3, 0);
-			if (err == -ENOSPC) {
-				err =  ext4_ext_zeroout(inode, &orig_ex);
-				if (err)
-					goto fix_extent_len;
-				ex->ee_block = orig_ex.ee_block;
-				ex->ee_len   = orig_ex.ee_len;
-				ext4_ext_store_pblock(ex,
-					ext4_ext_pblock(&orig_ex));
-				ext4_ext_dirty(handle, inode, path + depth);
-				/* blocks available from map->m_lblk */
-				return allocated;
-
-			} else if (err)
-				goto fix_extent_len;
+	split_map.m_lblk = map->m_lblk;
+	split_map.m_len = map->m_len;
 
-			/*
-			 * We need to zero out the second half because
-			 * an fallocate request can update file size and
-			 * converting the second half to initialized extent
-			 * implies that we can leak some junk data to user
-			 * space.
-			 */
-			err =  ext4_ext_zeroout(inode, ex3);
-			if (err) {
-				/*
-				 * We should actually mark the
-				 * second half as uninit and return error
-				 * Insert would have changed the extent
-				 */
-				depth = ext_depth(inode);
-				ext4_ext_drop_refs(path);
-				path = ext4_ext_find_extent(inode, map->m_lblk,
-							    path);
-				if (IS_ERR(path)) {
-					err = PTR_ERR(path);
-					return err;
-				}
-				/* get the second half extent details */
-				ex = path[depth].p_ext;
-				err = ext4_ext_get_access(handle, inode,
-								path + depth);
+	if (allocated > map->m_len) {
+		if (allocated <= EXT4_EXT_ZERO_LEN &&
+		    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+			/* case 3 */
+			zero_ex.ee_block =
+					 cpu_to_le32(map->m_lblk);
+			zero_ex.ee_len = cpu_to_le16(allocated);
+			ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex);
+			if (err)
+				goto out;
+			split_map.m_lblk = map->m_lblk;
+			split_map.m_len = allocated;
+		} else if ((map->m_lblk - ee_block + map->m_len <
+			   EXT4_EXT_ZERO_LEN) &&
+			   (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+			/* case 2 */
+			if (map->m_lblk != ee_block) {
+				zero_ex.ee_block = ex->ee_block;
+				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+							ee_block);
+				ext4_ext_store_pblock(&zero_ex,
+						      ext4_ext_pblock(ex));
+				err = ext4_ext_zeroout(inode, &zero_ex);
 				if (err)
-					return err;
-				ext4_ext_mark_uninitialized(ex);
-				ext4_ext_dirty(handle, inode, path + depth);
-				return err;
+					goto out;
 			}
 
-			/* zeroed the second half */
-			return allocated;
-		}
-		ex3 = &newex;
-		ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
-		ext4_ext_store_pblock(ex3, newblock + map->m_len);
-		ex3->ee_len = cpu_to_le16(allocated - map->m_len);
-		ext4_ext_mark_uninitialized(ex3);
-		err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
-		if (err == -ENOSPC && may_zeroout) {
-			err =  ext4_ext_zeroout(inode, &orig_ex);
-			if (err)
-				goto fix_extent_len;
-			/* update the extent length and mark as initialized */
-			ex->ee_block = orig_ex.ee_block;
-			ex->ee_len   = orig_ex.ee_len;
-			ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-			ext4_ext_dirty(handle, inode, path + depth);
-			/* zeroed the full extent */
-			/* blocks available from map->m_lblk */
-			return allocated;
-
-		} else if (err)
-			goto fix_extent_len;
-		/*
-		 * The depth, and hence eh & ex might change
-		 * as part of the insert above.
-		 */
-		newdepth = ext_depth(inode);
-		/*
-		 * update the extent length after successful insert of the
-		 * split extent
-		 */
-		ee_len -= ext4_ext_get_actual_len(ex3);
-		orig_ex.ee_len = cpu_to_le16(ee_len);
-		may_zeroout = ee_block + ee_len <= eof_block;
-
-		depth = newdepth;
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, map->m_lblk, path);
-		if (IS_ERR(path)) {
-			err = PTR_ERR(path);
-			goto out;
+			split_map.m_lblk = ee_block;
+			split_map.m_len = map->m_lblk - ee_block + map->m_len;
+			allocated = map->m_len;
 		}
-		eh = path[depth].p_hdr;
-		ex = path[depth].p_ext;
-		if (ex2 != &newex)
-			ex2 = ex;
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
+	}
 
-		allocated = map->m_len;
+	allocated = ext4_split_extent(handle, inode, path,
+				       &split_map, split_flag, 0);
+	if (allocated < 0)
+		err = allocated;
 
-		/* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
-		 * to insert a extent in the middle zerout directly
-		 * otherwise give the extent a chance to merge to left
-		 */
-		if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
-			map->m_lblk != ee_block && may_zeroout) {
-			err =  ext4_ext_zeroout(inode, &orig_ex);
-			if (err)
-				goto fix_extent_len;
-			/* update the extent length and mark as initialized */
-			ex->ee_block = orig_ex.ee_block;
-			ex->ee_len   = orig_ex.ee_len;
-			ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-			ext4_ext_dirty(handle, inode, path + depth);
-			/* zero out the first half */
-			/* blocks available from map->m_lblk */
-			return allocated;
-		}
-	}
-	/*
-	 * If there was a change of depth as part of the
-	 * insertion of ex3 above, we need to update the length
-	 * of the ex1 extent again here
-	 */
-	if (ex1 && ex1 != ex) {
-		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
-		ext4_ext_mark_uninitialized(ex1);
-		ex2 = &newex;
-	}
-	/* ex2: map->m_lblk to map->m_lblk + maxblocks-1 : initialised */
-	ex2->ee_block = cpu_to_le32(map->m_lblk);
-	ext4_ext_store_pblock(ex2, newblock);
-	ex2->ee_len = cpu_to_le16(allocated);
-	if (ex2 != ex)
-		goto insert;
-	/*
-	 * New (initialized) extent starts from the first block
-	 * in the current extent. i.e., ex2 == ex
-	 * We have to see if it can be merged with the extent
-	 * on the left.
-	 */
-	if (ex2 > EXT_FIRST_EXTENT(eh)) {
-		/*
-		 * To merge left, pass "ex2 - 1" to try_to_merge(),
-		 * since it merges towards right _only_.
-		 */
-		ret = ext4_ext_try_to_merge(inode, path, ex2 - 1);
-		if (ret) {
-			err = ext4_ext_correct_indexes(handle, inode, path);
-			if (err)
-				goto out;
-			depth = ext_depth(inode);
-			ex2--;
-		}
-	}
-	/*
-	 * Try to Merge towards right. This might be required
-	 * only when the whole extent is being written to.
-	 * i.e. ex2 == ex and ex3 == NULL.
-	 */
-	if (!ex3) {
-		ret = ext4_ext_try_to_merge(inode, path, ex2);
-		if (ret) {
-			err = ext4_ext_correct_indexes(handle, inode, path);
-			if (err)
-				goto out;
-		}
-	}
-	/* Mark modified extent as dirty */
-	err = ext4_ext_dirty(handle, inode, path + depth);
-	goto out;
-insert:
-	err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
-	if (err == -ENOSPC && may_zeroout) {
-		err =  ext4_ext_zeroout(inode, &orig_ex);
-		if (err)
-			goto fix_extent_len;
-		/* update the extent length and mark as initialized */
-		ex->ee_block = orig_ex.ee_block;
-		ex->ee_len   = orig_ex.ee_len;
-		ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-		ext4_ext_dirty(handle, inode, path + depth);
-		/* zero out the first half */
-		return allocated;
-	} else if (err)
-		goto fix_extent_len;
 out:
-	ext4_ext_show_leaf(inode, path);
 	return err ? err : allocated;
-
-fix_extent_len:
-	ex->ee_block = orig_ex.ee_block;
-	ex->ee_len   = orig_ex.ee_len;
-	ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-	ext4_ext_mark_uninitialized(ex);
-	ext4_ext_dirty(handle, inode, path + depth);
-	return err;
 }
 
 /*
@@ -2871,15 +3072,11 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 					struct ext4_ext_path *path,
 					int flags)
 {
-	struct ext4_extent *ex, newex, orig_ex;
-	struct ext4_extent *ex1 = NULL;
-	struct ext4_extent *ex2 = NULL;
-	struct ext4_extent *ex3 = NULL;
-	ext4_lblk_t ee_block, eof_block;
-	unsigned int allocated, ee_len, depth;
-	ext4_fsblk_t newblock;
-	int err = 0;
-	int may_zeroout;
+	ext4_lblk_t eof_block;
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex;
+	unsigned int ee_len;
+	int split_flag = 0, depth;
 
 	ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -2889,156 +3086,22 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 		inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map->m_len)
 		eof_block = map->m_lblk + map->m_len;
-
-	depth = ext_depth(inode);
-	ex = path[depth].p_ext;
-	ee_block = le32_to_cpu(ex->ee_block);
-	ee_len = ext4_ext_get_actual_len(ex);
-	allocated = ee_len - (map->m_lblk - ee_block);
-	newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
-
-	ex2 = ex;
-	orig_ex.ee_block = ex->ee_block;
-	orig_ex.ee_len   = cpu_to_le16(ee_len);
-	ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
-
 	/*
 	 * It is safe to convert extent to initialized via explicit
 	 * zeroout only if extent is fully insde i_size or new_size.
 	 */
-	may_zeroout = ee_block + ee_len <= eof_block;
-
-	/*
- 	 * If the uninitialized extent begins at the same logical
- 	 * block where the write begins, and the write completely
- 	 * covers the extent, then we don't need to split it.
- 	 */
-	if ((map->m_lblk == ee_block) && (allocated <= map->m_len))
-		return allocated;
-
-	err = ext4_ext_get_access(handle, inode, path + depth);
-	if (err)
-		goto out;
-	/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
-	if (map->m_lblk > ee_block) {
-		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
-		ext4_ext_mark_uninitialized(ex1);
-		ex2 = &newex;
-	}
-	/*
-	 * for sanity, update the length of the ex2 extent before
-	 * we insert ex3, if ex1 is NULL. This is to avoid temporary
-	 * overlap of blocks.
-	 */
-	if (!ex1 && allocated > map->m_len)
-		ex2->ee_len = cpu_to_le16(map->m_len);
-	/* ex3: to ee_block + ee_len : uninitialised */
-	if (allocated > map->m_len) {
-		unsigned int newdepth;
-		ex3 = &newex;
-		ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
-		ext4_ext_store_pblock(ex3, newblock + map->m_len);
-		ex3->ee_len = cpu_to_le16(allocated - map->m_len);
-		ext4_ext_mark_uninitialized(ex3);
-		err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
-		if (err == -ENOSPC && may_zeroout) {
-			err =  ext4_ext_zeroout(inode, &orig_ex);
-			if (err)
-				goto fix_extent_len;
-			/* update the extent length and mark as initialized */
-			ex->ee_block = orig_ex.ee_block;
-			ex->ee_len   = orig_ex.ee_len;
-			ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-			ext4_ext_dirty(handle, inode, path + depth);
-			/* zeroed the full extent */
-			/* blocks available from map->m_lblk */
-			return allocated;
-
-		} else if (err)
-			goto fix_extent_len;
-		/*
-		 * The depth, and hence eh & ex might change
-		 * as part of the insert above.
-		 */
-		newdepth = ext_depth(inode);
-		/*
-		 * update the extent length after successful insert of the
-		 * split extent
-		 */
-		ee_len -= ext4_ext_get_actual_len(ex3);
-		orig_ex.ee_len = cpu_to_le16(ee_len);
-		may_zeroout = ee_block + ee_len <= eof_block;
-
-		depth = newdepth;
-		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, map->m_lblk, path);
-		if (IS_ERR(path)) {
-			err = PTR_ERR(path);
-			goto out;
-		}
-		ex = path[depth].p_ext;
-		if (ex2 != &newex)
-			ex2 = ex;
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
 
-		allocated = map->m_len;
-	}
-	/*
-	 * If there was a change of depth as part of the
-	 * insertion of ex3 above, we need to update the length
-	 * of the ex1 extent again here
-	 */
-	if (ex1 && ex1 != ex) {
-		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
-		ext4_ext_mark_uninitialized(ex1);
-		ex2 = &newex;
-	}
-	/*
-	 * ex2: map->m_lblk to map->m_lblk + map->m_len-1 : to be written
-	 * using direct I/O, uninitialised still.
-	 */
-	ex2->ee_block = cpu_to_le32(map->m_lblk);
-	ext4_ext_store_pblock(ex2, newblock);
-	ex2->ee_len = cpu_to_le16(allocated);
-	ext4_ext_mark_uninitialized(ex2);
-	if (ex2 != ex)
-		goto insert;
-	/* Mark modified extent as dirty */
-	err = ext4_ext_dirty(handle, inode, path + depth);
-	ext_debug("out here\n");
-	goto out;
-insert:
-	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
-	if (err == -ENOSPC && may_zeroout) {
-		err =  ext4_ext_zeroout(inode, &orig_ex);
-		if (err)
-			goto fix_extent_len;
-		/* update the extent length and mark as initialized */
-		ex->ee_block = orig_ex.ee_block;
-		ex->ee_len   = orig_ex.ee_len;
-		ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-		ext4_ext_dirty(handle, inode, path + depth);
-		/* zero out the first half */
-		return allocated;
-	} else if (err)
-		goto fix_extent_len;
-out:
-	ext4_ext_show_leaf(inode, path);
-	return err ? err : allocated;
+	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
+	split_flag |= EXT4_EXT_MARK_UNINIT2;
 
-fix_extent_len:
-	ex->ee_block = orig_ex.ee_block;
-	ex->ee_len   = orig_ex.ee_len;
-	ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
-	ext4_ext_mark_uninitialized(ex);
-	ext4_ext_dirty(handle, inode, path + depth);
-	return err;
+	flags |= EXT4_GET_BLOCKS_PRE_IO;
+	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
+
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 					      struct inode *inode,
 					      struct ext4_ext_path *path)
@@ -3047,46 +3110,27 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 	struct ext4_extent_header *eh;
 	int depth;
 	int err = 0;
-	int ret = 0;
 
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 
+	ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)le32_to_cpu(ex->ee_block),
+		ext4_ext_get_actual_len(ex));
+
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
 	/* first mark the extent as initialized */
 	ext4_ext_mark_initialized(ex);
 
-	/*
-	 * We have to see if it can be merged with the extent
-	 * on the left.
-	 */
-	if (ex > EXT_FIRST_EXTENT(eh)) {
-		/*
-		 * To merge left, pass "ex - 1" to try_to_merge(),
-		 * since it merges towards right _only_.
-		 */
-		ret = ext4_ext_try_to_merge(inode, path, ex - 1);
-		if (ret) {
-			err = ext4_ext_correct_indexes(handle, inode, path);
-			if (err)
-				goto out;
-			depth = ext_depth(inode);
-			ex--;
-		}
-	}
-	/*
-	 * Try to Merge towards right.
+	/* note: ext4_ext_correct_indexes() isn't needed here because
+	 * borders are not changed
 	 */
-	ret = ext4_ext_try_to_merge(inode, path, ex);
-	if (ret) {
-		err = ext4_ext_correct_indexes(handle, inode, path);
-		if (err)
-			goto out;
-		depth = ext_depth(inode);
-	}
+	ext4_ext_try_to_merge(inode, path, ex);
+
 	/* Mark modified extent as dirty */
 	err = ext4_ext_dirty(handle, inode, path + depth);
 out:
@@ -3302,15 +3346,19 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t newblock = 0;
 	int err = 0, depth, ret;
 	unsigned int allocated = 0;
+	unsigned int punched_out = 0;
+	unsigned int result = 0;
 	struct ext4_allocation_request ar;
 	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+	struct ext4_map_blocks punch_map;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
 		  map->m_lblk, map->m_len, inode->i_ino);
 	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 
 	/* check in cache */
-	if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
+	if (ext4_ext_in_cache(inode, map->m_lblk, &newex) &&
+		((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0)) {
 		if (!newex.ee_start_lo && !newex.ee_start_hi) {
 			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 				/*
@@ -3375,16 +3423,84 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
 				  ee_block, ee_len, newblock);
 
-			/* Do not put uninitialized extent in the cache */
-			if (!ext4_ext_is_uninitialized(ex)) {
-				ext4_ext_put_in_cache(inode, ee_block,
-							ee_len, ee_start);
-				goto out;
+			if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
+				/*
+				 * Do not put uninitialized extent
+				 * in the cache
+				 */
+				if (!ext4_ext_is_uninitialized(ex)) {
+					ext4_ext_put_in_cache(inode, ee_block,
+						ee_len, ee_start);
+					goto out;
+				}
+				ret = ext4_ext_handle_uninitialized_extents(
+					handle, inode, map, path, flags,
+					allocated, newblock);
+				return ret;
 			}
-			ret = ext4_ext_handle_uninitialized_extents(handle,
-					inode, map, path, flags, allocated,
-					newblock);
-			return ret;
+
+			/*
+			 * Punch out the map length, but only to the
+			 * end of the extent
+			 */
+			punched_out = allocated < map->m_len ?
+				allocated : map->m_len;
+
+			/*
+			 * Sense extents need to be converted to
+			 * uninitialized, they must fit in an
+			 * uninitialized extent
+			 */
+			if (punched_out > EXT_UNINIT_MAX_LEN)
+				punched_out = EXT_UNINIT_MAX_LEN;
+
+			punch_map.m_lblk = map->m_lblk;
+			punch_map.m_pblk = newblock;
+			punch_map.m_len = punched_out;
+			punch_map.m_flags = 0;
+
+			/* Check to see if the extent needs to be split */
+			if (punch_map.m_len != ee_len ||
+				punch_map.m_lblk != ee_block) {
+
+				ret = ext4_split_extent(handle, inode,
+				path, &punch_map, 0,
+				EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
+				EXT4_GET_BLOCKS_PRE_IO);
+
+				if (ret < 0) {
+					err = ret;
+					goto out2;
+				}
+				/*
+				 * find extent for the block at
+				 * the start of the hole
+				 */
+				ext4_ext_drop_refs(path);
+				kfree(path);
+
+				path = ext4_ext_find_extent(inode,
+				map->m_lblk, NULL);
+				if (IS_ERR(path)) {
+					err = PTR_ERR(path);
+					path = NULL;
+					goto out2;
+				}
+
+				depth = ext_depth(inode);
+				ex = path[depth].p_ext;
+				ee_len = ext4_ext_get_actual_len(ex);
+				ee_block = le32_to_cpu(ex->ee_block);
+				ee_start = ext4_ext_pblock(ex);
+
+			}
+
+			ext4_ext_mark_uninitialized(ex);
+
+			err = ext4_ext_remove_space(inode, map->m_lblk,
+				map->m_lblk + punched_out);
+
+			goto out2;
 		}
 	}
 
@@ -3446,6 +3562,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	else
 		/* disable in-core preallocation for non-regular files */
 		ar.flags = 0;
+	if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
+		ar.flags |= EXT4_MB_HINT_NOPREALLOC;
 	newblock = ext4_mb_new_blocks(handle, &ar, &err);
 	if (!newblock)
 		goto out2;
@@ -3529,7 +3647,11 @@ out2:
 	}
 	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
 		newblock, map->m_len, err ? err : allocated);
-	return err ? err : allocated;
+
+	result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
+			punched_out : allocated;
+
+	return err ? err : result;
 }
 
 void ext4_ext_truncate(struct inode *inode)
@@ -3577,7 +3699,7 @@ void ext4_ext_truncate(struct inode *inode)
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
-	err = ext4_ext_remove_space(inode, last_block);
+	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCK);
 
 	/* In a multi-transaction truncate, we only make the final
 	 * transaction synchronous.
@@ -3585,8 +3707,9 @@ void ext4_ext_truncate(struct inode *inode)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-out_stop:
 	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.
@@ -3651,10 +3774,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	struct ext4_map_blocks map;
 	unsigned int credits, blkbits = inode->i_blkbits;
 
-	/* We only support the FALLOC_FL_KEEP_SIZE mode */
-	if (mode & ~FALLOC_FL_KEEP_SIZE)
-		return -EOPNOTSUPP;
-
 	/*
 	 * currently supporting (pre)allocate mode for extent-based
 	 * files _only_
@@ -3662,6 +3781,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EOPNOTSUPP;
 
+	/* Return error if mode is not supported */
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		return ext4_punch_hole(file, offset, len);
+
 	trace_ext4_fallocate_enter(inode, offset, len, mode);
 	map.m_lblk = offset >> blkbits;
 	/*
@@ -3691,7 +3817,8 @@ retry:
 			break;
 		}
 		ret = ext4_map_blocks(handle, inode, &map,
-				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
+				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+				      EXT4_GET_BLOCKS_NO_NORMALIZE);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);
@@ -3822,6 +3949,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		pgoff_t		last_offset;
 		pgoff_t		offset;
 		pgoff_t		index;
+		pgoff_t		start_index = 0;
 		struct page	**pages = NULL;
 		struct buffer_head *bh = NULL;
 		struct buffer_head *head = NULL;
@@ -3848,39 +3976,57 @@ out:
 				kfree(pages);
 				return EXT_CONTINUE;
 			}
+			index = 0;
 
+next_page:
 			/* Try to find the 1st mapped buffer. */
-			end = ((__u64)pages[0]->index << PAGE_SHIFT) >>
+			end = ((__u64)pages[index]->index << PAGE_SHIFT) >>
 				  blksize_bits;
-			if (!page_has_buffers(pages[0]))
+			if (!page_has_buffers(pages[index]))
 				goto out;
-			head = page_buffers(pages[0]);
+			head = page_buffers(pages[index]);
 			if (!head)
 				goto out;
 
+			index++;
 			bh = head;
 			do {
-				if (buffer_mapped(bh)) {
+				if (end >= newex->ec_block +
+					newex->ec_len)
+					/* The buffer is out of
+					 * the request range.
+					 */
+					goto out;
+
+				if (buffer_mapped(bh) &&
+				    end >= newex->ec_block) {
+					start_index = index - 1;
 					/* get the 1st mapped buffer. */
-					if (end > newex->ec_block +
-						newex->ec_len)
-						/* The buffer is out of
-						 * the request range.
-						 */
-						goto out;
 					goto found_mapped_buffer;
 				}
+
 				bh = bh->b_this_page;
 				end++;
 			} while (bh != head);
 
-			/* No mapped buffer found. */
-			goto out;
+			/* No mapped buffer in the range found in this page,
+			 * We need to look up next page.
+			 */
+			if (index >= ret) {
+				/* There is no page left, but we need to limit
+				 * newex->ec_len.
+				 */
+				newex->ec_len = end - newex->ec_block;
+				goto out;
+			}
+			goto next_page;
 		} else {
 			/*Find contiguous delayed buffers. */
 			if (ret > 0 && pages[0]->index == last_offset)
 				head = page_buffers(pages[0]);
 			bh = head;
+			index = 1;
+			start_index = 0;
 		}
 
 found_mapped_buffer:
@@ -3903,7 +4049,7 @@ found_mapped_buffer:
 				end++;
 			} while (bh != head);
 
-			for (index = 1; index < ret; index++) {
+			for (; index < ret; index++) {
 				if (!page_has_buffers(pages[index])) {
 					bh = NULL;
 					break;
@@ -3913,8 +4059,10 @@ found_mapped_buffer:
 					bh = NULL;
 					break;
 				}
+
 				if (pages[index]->index !=
-					pages[0]->index + index) {
+				    pages[start_index]->index + index
+				    - start_index) {
 					/* Blocks are not contiguous. */
 					bh = NULL;
 					break;
@@ -4006,6 +4154,177 @@ 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->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_ext_cache cache_ex;
+	ext4_lblk_t first_block, last_block, num_blocks, iblock, max_blocks;
+	struct address_space *mapping = inode->i_mapping;
+	struct ext4_map_blocks map;
+	handle_t *handle;
+	loff_t first_block_offset, last_block_offset, block_len;
+	loff_t first_page, last_page, first_page_offset, last_page_offset;
+	int ret, credits, blocks_released, err = 0;
+
+	first_block = (offset + sb->s_blocksize - 1) >>
+		EXT4_BLOCK_SIZE_BITS(sb);
+	last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+	first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
+	last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
+
+	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;
+
+	/*
+	 * 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,
+			first_page_offset == 0 ? 0 : first_page_offset-1,
+			last_page_offset);
+
+			if (err)
+				return err;
+	}
+
+	/* Now release the pages */
+	if (last_page_offset > first_page_offset) {
+		truncate_inode_pages_range(mapping, first_page_offset,
+					   last_page_offset-1);
+	}
+
+	/* finish any pending end_io work */
+	ext4_flush_completed_IO(inode);
+
+	credits = ext4_writepage_trans_blocks(inode);
+	handle = ext4_journal_start(inode, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	err = ext4_orphan_add(handle, inode);
+	if (err)
+		goto out;
+
+	/*
+	 * Now we need to zero out the un block aligned data.
+	 * If the file is smaller than a block, just
+	 * zero out the middle
+	 */
+	if (first_block > last_block)
+		ext4_block_zero_page_range(handle, mapping, offset, length);
+	else {
+		/* zero out the head of the hole before the first block */
+		block_len  = first_block_offset - offset;
+		if (block_len > 0)
+			ext4_block_zero_page_range(handle, mapping,
+						   offset, block_len);
+
+		/* zero out the tail of the hole after the last block */
+		block_len = offset + length - last_block_offset;
+		if (block_len > 0) {
+			ext4_block_zero_page_range(handle, mapping,
+					last_block_offset, block_len);
+		}
+	}
+
+	/* If there are no blocks to remove, return now */
+	if (first_block >= last_block)
+		goto out;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_ext_invalidate_cache(inode);
+	ext4_discard_preallocations(inode);
+
+	/*
+	 * Loop over all the blocks and identify blocks
+	 * that need to be punched out
+	 */
+	iblock = first_block;
+	blocks_released = 0;
+	while (iblock < last_block) {
+		max_blocks = last_block - iblock;
+		num_blocks = 1;
+		memset(&map, 0, sizeof(map));
+		map.m_lblk = iblock;
+		map.m_len = max_blocks;
+		ret = ext4_ext_map_blocks(handle, inode, &map,
+			EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+
+		if (ret > 0) {
+			blocks_released += ret;
+			num_blocks = ret;
+		} else if (ret == 0) {
+			/*
+			 * If map blocks could not find the block,
+			 * then it is in a hole.  If the hole was
+			 * not already cached, then map blocks should
+			 * put it in the cache.  So we can get the hole
+			 * out of the cache
+			 */
+			memset(&cache_ex, 0, sizeof(cache_ex));
+			if ((ext4_ext_check_cache(inode, iblock, &cache_ex)) &&
+				!cache_ex.ec_start) {
+
+				/* The hole is cached */
+				num_blocks = cache_ex.ec_block +
+				cache_ex.ec_len - iblock;
+
+			} else {
+				/* The block could not be identified */
+				err = -EIO;
+				break;
+			}
+		} else {
+			/* Map blocks error */
+			err = ret;
+			break;
+		}
+
+		if (num_blocks == 0) {
+			/* This condition should never happen */
+			ext_debug("Block lookup failed");
+			err = -EIO;
+			break;
+		}
+
+		iblock += num_blocks;
+	}
+
+	if (blocks_released > 0) {
+		ext4_ext_invalidate_cache(inode);
+		ext4_discard_preallocations(inode);
+	}
+
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+out:
+	ext4_orphan_del(handle, inode);
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+	return err;
+}
 int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len)
 {
@@ -4042,4 +4361,3 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	return error;
 }
-

fs/ext4/file.c

@@ -272,7 +272,6 @@ const struct file_operations ext4_file_operations = {
 };
 
 const struct inode_operations ext4_file_inode_operations = {
-	.truncate	= ext4_truncate,
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
 #ifdef CONFIG_EXT4_FS_XATTR

fs/ext4/fsync.c

@@ -36,7 +36,7 @@
 
 static void dump_completed_IO(struct inode * inode)
 {
-#ifdef	EXT4_DEBUG
+#ifdef	EXT4FS_DEBUG
 	struct list_head *cur, *before, *after;
 	ext4_io_end_t *io, *io0, *io1;
 	unsigned long flags;
@@ -172,6 +172,7 @@ int ext4_sync_file(struct file *file, int datasync)
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 	int ret;
 	tid_t commit_tid;
+	bool needs_barrier = false;
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
@@ -211,22 +212,12 @@ int ext4_sync_file(struct file *file, int datasync)
 	}
 
 	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
-	if (jbd2_log_start_commit(journal, commit_tid)) {
-		/*
-		 * When the journal is on a different device than the
-		 * fs data disk, we need to issue the barrier in
-		 * writeback mode.  (In ordered mode, the jbd2 layer
-		 * will take care of issuing the barrier.  In
-		 * data=journal, all of the data blocks are written to
-		 * the journal device.)
-		 */
-		if (ext4_should_writeback_data(inode) &&
-		    (journal->j_fs_dev != journal->j_dev) &&
-		    (journal->j_flags & JBD2_BARRIER))
-			blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
-					NULL);
-		ret = jbd2_log_wait_commit(journal, commit_tid);
-	} else if (journal->j_flags & JBD2_BARRIER)
+	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_log_wait_commit(journal, commit_tid);
+	if (needs_barrier)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
  out:
 	trace_ext4_sync_file_exit(inode, ret);

fs/ext4/inode.c

@@ -639,8 +639,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	while (target > 0) {
 		count = target;
 		/* allocating blocks for indirect blocks and direct blocks */
-		current_block = ext4_new_meta_blocks(handle, inode,
-							goal, &count, err);
+		current_block = ext4_new_meta_blocks(handle, inode, goal,
+						     0, &count, err);
 		if (*err)
 			goto failed_out;
 
@@ -1930,7 +1930,7 @@ repeat:
 	 * We do still charge estimated metadata to the sb though;
 	 * we cannot afford to run out of free blocks.
 	 */
-	if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+	if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
 		dquot_release_reservation_block(inode, 1);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
@@ -2796,9 +2796,7 @@ static int write_cache_pages_da(struct address_space *mapping,
 				continue;
 			}
 
-			if (PageWriteback(page))
-				wait_on_page_writeback(page);
-
+			wait_on_page_writeback(page);
 			BUG_ON(PageWriteback(page));
 
 			if (mpd->next_page != page->index)
@@ -3513,7 +3511,7 @@ retry:
 			loff_t end = offset + iov_length(iov, nr_segs);
 
 			if (end > isize)
-				vmtruncate(inode, isize);
+				ext4_truncate_failed_write(inode);
 		}
 	}
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -3915,10 +3913,31 @@ void ext4_set_aops(struct inode *inode)
  */
 int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from)
+{
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned length;
+	unsigned blocksize;
+	struct inode *inode = mapping->host;
+
+	blocksize = inode->i_sb->s_blocksize;
+	length = blocksize - (offset & (blocksize - 1));
+
+	return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, length, pos;
+	unsigned blocksize, max, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3931,7 +3950,15 @@ int ext4_block_truncate_page(handle_t *handle,
 		return -EINVAL;
 
 	blocksize = inode->i_sb->s_blocksize;
-	length = blocksize - (offset & (blocksize - 1));
+	max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
 	if (!page_has_buffers(page))
@@ -4380,8 +4407,6 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 
 int ext4_can_truncate(struct inode *inode)
 {
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return 0;
 	if (S_ISREG(inode->i_mode))
 		return 1;
 	if (S_ISDIR(inode->i_mode))
@@ -4391,6 +4416,31 @@ int ext4_can_truncate(struct inode *inode)
 	return 0;
 }
 
+/*
+ * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * associated with the given offset and length
+ *
+ * @inode:  File inode
+ * @offset: The offset where the hole will begin
+ * @len:    The length of the hole
+ *
+ * Returns: 0 on sucess or negative on failure
+ */
+
+int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	if (!S_ISREG(inode->i_mode))
+		return -ENOTSUPP;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		/* TODO: Add support for non extent hole punching */
+		return -ENOTSUPP;
+	}
+
+	return ext4_ext_punch_hole(file, offset, length);
+}
+
 /*
  * ext4_truncate()
  *
@@ -4617,7 +4667,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	/*
 	 * Figure out the offset within the block group inode table
 	 */
-	inodes_per_block = (EXT4_BLOCK_SIZE(sb) / EXT4_INODE_SIZE(sb));
+	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
 	inode_offset = ((inode->i_ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
@@ -5311,8 +5361,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (S_ISREG(inode->i_mode) &&
 	    attr->ia_valid & ATTR_SIZE &&
-	    (attr->ia_size < inode->i_size ||
-	     (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
+	    (attr->ia_size < inode->i_size)) {
 		handle_t *handle;
 
 		handle = ext4_journal_start(inode, 3);
@@ -5346,14 +5395,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				goto err_out;
 			}
 		}
-		/* ext4_truncate will clear the flag */
-		if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
-			ext4_truncate(inode);
 	}
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode))
-		rc = vmtruncate(inode, attr->ia_size);
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (attr->ia_size != i_size_read(inode)) {
+			truncate_setsize(inode, attr->ia_size);
+			ext4_truncate(inode);
+		} else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
+			ext4_truncate(inode);
+	}
 
 	if (!rc) {
 		setattr_copy(inode, attr);
@@ -5811,15 +5861,19 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		goto out_unlock;
 	}
 	ret = 0;
-	if (PageMappedToDisk(page))
-		goto out_unlock;
+
+	lock_page(page);
+	wait_on_page_writeback(page);
+	if (PageMappedToDisk(page)) {
+		up_read(&inode->i_alloc_sem);
+		return VM_FAULT_LOCKED;
+	}
 
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
 	else
 		len = PAGE_CACHE_SIZE;
 
-	lock_page(page);
 	/*
 	 * return if we have all the buffers mapped. This avoid
 	 * the need to call write_begin/write_end which does a
@@ -5829,8 +5883,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (page_has_buffers(page)) {
 		if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
 					ext4_bh_unmapped)) {
-			unlock_page(page);
-			goto out_unlock;
+			up_read(&inode->i_alloc_sem);
+			return VM_FAULT_LOCKED;
 		}
 	}
 	unlock_page(page);
@@ -5850,6 +5904,16 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret < 0)
 		goto out_unlock;
 	ret = 0;
+
+	/*
+	 * write_begin/end might have created a dirty page and someone
+	 * could wander in and start the IO.  Make sure that hasn't
+	 * happened.
+	 */
+	lock_page(page);
+	wait_on_page_writeback(page);
+	up_read(&inode->i_alloc_sem);
+	return VM_FAULT_LOCKED;
 out_unlock:
 	if (ret)
 		ret = VM_FAULT_SIGBUS;

fs/ext4/mballoc.c

@@ -787,6 +787,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	struct inode *inode;
 	char *data;
 	char *bitmap;
+	struct ext4_group_info *grinfo;
 
 	mb_debug(1, "init page %lu\n", page->index);
 
@@ -819,6 +820,18 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 		if (first_group + i >= ngroups)
 			break;
 
+		grinfo = ext4_get_group_info(sb, first_group + i);
+		/*
+		 * If page is uptodate then we came here after online resize
+		 * which added some new uninitialized group info structs, so
+		 * we must skip all initialized uptodate buddies on the page,
+		 * which may be currently in use by an allocating task.
+		 */
+		if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) {
+			bh[i] = NULL;
+			continue;
+		}
+
 		err = -EIO;
 		desc = ext4_get_group_desc(sb, first_group + i, NULL);
 		if (desc == NULL)
@@ -871,26 +884,28 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	}
 
 	/* wait for I/O completion */
-	for (i = 0; i < groups_per_page && bh[i]; i++)
-		wait_on_buffer(bh[i]);
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i])
+			wait_on_buffer(bh[i]);
 
 	err = -EIO;
-	for (i = 0; i < groups_per_page && bh[i]; i++)
-		if (!buffer_uptodate(bh[i]))
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i] && !buffer_uptodate(bh[i]))
 			goto out;
 
 	err = 0;
 	first_block = page->index * blocks_per_page;
-	/* init the page  */
-	memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
 	for (i = 0; i < blocks_per_page; i++) {
 		int group;
-		struct ext4_group_info *grinfo;
 
 		group = (first_block + i) >> 1;
 		if (group >= ngroups)
 			break;
 
+		if (!bh[group - first_group])
+			/* skip initialized uptodate buddy */
+			continue;
+
 		/*
 		 * data carry information regarding this
 		 * particular group in the format specified
@@ -919,6 +934,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 			 * incore got set to the group block bitmap below
 			 */
 			ext4_lock_group(sb, group);
+			/* init the buddy */
+			memset(data, 0xff, blocksize);
 			ext4_mb_generate_buddy(sb, data, incore, group);
 			ext4_unlock_group(sb, group);
 			incore = NULL;
@@ -948,7 +965,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 out:
 	if (bh) {
-		for (i = 0; i < groups_per_page && bh[i]; i++)
+		for (i = 0; i < groups_per_page; i++)
 			brelse(bh[i]);
 		if (bh != &bhs)
 			kfree(bh);
@@ -957,22 +974,21 @@ out:
 }
 
 /*
- * lock the group_info alloc_sem of all the groups
- * belonging to the same buddy cache page. This
- * make sure other parallel operation on the buddy
- * cache doesn't happen  whild holding the buddy cache
- * lock
+ * Lock the buddy and bitmap pages. This make sure other parallel init_group
+ * on the same buddy page doesn't happen whild holding the buddy page lock.
+ * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap
+ * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
  */
-static int ext4_mb_get_buddy_cache_lock(struct super_block *sb,
-					ext4_group_t group)
+static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b)
 {
-	int i;
-	int block, pnum;
+	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
+	int block, pnum, poff;
 	int blocks_per_page;
-	int groups_per_page;
-	ext4_group_t ngroups = ext4_get_groups_count(sb);
-	ext4_group_t first_group;
-	struct ext4_group_info *grp;
+	struct page *page;
+
+	e4b->bd_buddy_page = NULL;
+	e4b->bd_bitmap_page = NULL;
 
 	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
 	/*
@@ -982,57 +998,40 @@ static int ext4_mb_get_buddy_cache_lock(struct super_block *sb,
 	 */
 	block = group * 2;
 	pnum = block / blocks_per_page;
-	first_group = pnum * blocks_per_page / 2;
-
-	groups_per_page = blocks_per_page >> 1;
-	if (groups_per_page == 0)
-		groups_per_page = 1;
-	/* read all groups the page covers into the cache */
-	for (i = 0; i < groups_per_page; i++) {
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_bitmap_page = page;
+	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
 
-		if ((first_group + i) >= ngroups)
-			break;
-		grp = ext4_get_group_info(sb, first_group + i);
-		/* take all groups write allocation
-		 * semaphore. This make sure there is
-		 * no block allocation going on in any
-		 * of that groups
-		 */
-		down_write_nested(&grp->alloc_sem, i);
+	if (blocks_per_page >= 2) {
+		/* buddy and bitmap are on the same page */
+		return 0;
 	}
-	return i;
+
+	block++;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_buddy_page = page;
+	return 0;
 }
 
-static void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
-					 ext4_group_t group, int locked_group)
+static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
 {
-	int i;
-	int block, pnum;
-	int blocks_per_page;
-	ext4_group_t first_group;
-	struct ext4_group_info *grp;
-
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
-	/*
-	 * the buddy cache inode stores the block bitmap
-	 * and buddy information in consecutive blocks.
-	 * So for each group we need two blocks.
-	 */
-	block = group * 2;
-	pnum = block / blocks_per_page;
-	first_group = pnum * blocks_per_page / 2;
-	/* release locks on all the groups */
-	for (i = 0; i < locked_group; i++) {
-
-		grp = ext4_get_group_info(sb, first_group + i);
-		/* take all groups write allocation
-		 * semaphore. This make sure there is
-		 * no block allocation going on in any
-		 * of that groups
-		 */
-		up_write(&grp->alloc_sem);
+	if (e4b->bd_bitmap_page) {
+		unlock_page(e4b->bd_bitmap_page);
+		page_cache_release(e4b->bd_bitmap_page);
+	}
+	if (e4b->bd_buddy_page) {
+		unlock_page(e4b->bd_buddy_page);
+		page_cache_release(e4b->bd_buddy_page);
 	}
-
 }
 
 /*
@@ -1044,93 +1043,60 @@ static noinline_for_stack
 int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 {
 
-	int ret = 0;
-	void *bitmap;
-	int blocks_per_page;
-	int block, pnum, poff;
-	int num_grp_locked = 0;
 	struct ext4_group_info *this_grp;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct inode *inode = sbi->s_buddy_cache;
-	struct page *page = NULL, *bitmap_page = NULL;
+	struct ext4_buddy e4b;
+	struct page *page;
+	int ret = 0;
 
 	mb_debug(1, "init group %u\n", group);
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
 	this_grp = ext4_get_group_info(sb, group);
 	/*
 	 * This ensures that we don't reinit the buddy cache
 	 * page which map to the group from which we are already
 	 * allocating. If we are looking at the buddy cache we would
 	 * have taken a reference using ext4_mb_load_buddy and that
-	 * would have taken the alloc_sem lock.
+	 * would have pinned buddy page to page cache.
 	 */
-	num_grp_locked =  ext4_mb_get_buddy_cache_lock(sb, group);
-	if (!EXT4_MB_GRP_NEED_INIT(this_grp)) {
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
 		/*
 		 * somebody initialized the group
 		 * return without doing anything
 		 */
-		ret = 0;
 		goto err;
 	}
-	/*
-	 * the buddy cache inode stores the block bitmap
-	 * and buddy information in consecutive blocks.
-	 * So for each group we need two blocks.
-	 */
-	block = group * 2;
-	pnum = block / blocks_per_page;
-	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
-	if (page) {
-		BUG_ON(page->mapping != inode->i_mapping);
-		ret = ext4_mb_init_cache(page, NULL);
-		if (ret) {
-			unlock_page(page);
-			goto err;
-		}
-		unlock_page(page);
-	}
-	if (page == NULL || !PageUptodate(page)) {
+
+	page = e4b.bd_bitmap_page;
+	ret = ext4_mb_init_cache(page, NULL);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
 		ret = -EIO;
 		goto err;
 	}
 	mark_page_accessed(page);
-	bitmap_page = page;
-	bitmap = page_address(page) + (poff * sb->s_blocksize);
 
-	/* init buddy cache */
-	block++;
-	pnum = block / blocks_per_page;
-	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
-	if (page == bitmap_page) {
+	if (e4b.bd_buddy_page == NULL) {
 		/*
 		 * If both the bitmap and buddy are in
 		 * the same page we don't need to force
 		 * init the buddy
 		 */
-		unlock_page(page);
-	} else if (page) {
-		BUG_ON(page->mapping != inode->i_mapping);
-		ret = ext4_mb_init_cache(page, bitmap);
-		if (ret) {
-			unlock_page(page);
-			goto err;
-		}
-		unlock_page(page);
+		ret = 0;
+		goto err;
 	}
-	if (page == NULL || !PageUptodate(page)) {
+	/* init buddy cache */
+	page = e4b.bd_buddy_page;
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
 		ret = -EIO;
 		goto err;
 	}
 	mark_page_accessed(page);
 err:
-	ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked);
-	if (bitmap_page)
-		page_cache_release(bitmap_page);
-	if (page)
-		page_cache_release(page);
+	ext4_mb_put_buddy_page_lock(&e4b);
 	return ret;
 }
 
@@ -1164,24 +1130,8 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	e4b->bd_group = group;
 	e4b->bd_buddy_page = NULL;
 	e4b->bd_bitmap_page = NULL;
-	e4b->alloc_semp = &grp->alloc_sem;
-
-	/* Take the read lock on the group alloc
-	 * sem. This would make sure a parallel
-	 * ext4_mb_init_group happening on other
-	 * groups mapped by the page is blocked
-	 * till we are done with allocation
-	 */
-repeat_load_buddy:
-	down_read(e4b->alloc_semp);
 
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		/* we need to check for group need init flag
-		 * with alloc_semp held so that we can be sure
-		 * that new blocks didn't get added to the group
-		 * when we are loading the buddy cache
-		 */
-		up_read(e4b->alloc_semp);
 		/*
 		 * we need full data about the group
 		 * to make a good selection
@@ -1189,7 +1139,6 @@ repeat_load_buddy:
 		ret = ext4_mb_init_group(sb, group);
 		if (ret)
 			return ret;
-		goto repeat_load_buddy;
 	}
 
 	/*
@@ -1273,15 +1222,14 @@ repeat_load_buddy:
 	return 0;
 
 err:
+	if (page)
+		page_cache_release(page);
 	if (e4b->bd_bitmap_page)
 		page_cache_release(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
 		page_cache_release(e4b->bd_buddy_page);
 	e4b->bd_buddy = NULL;
 	e4b->bd_bitmap = NULL;
-
-	/* Done with the buddy cache */
-	up_read(e4b->alloc_semp);
 	return ret;
 }
 
@@ -1291,9 +1239,6 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 		page_cache_release(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
 		page_cache_release(e4b->bd_buddy_page);
-	/* Done with the buddy cache */
-	if (e4b->alloc_semp)
-		up_read(e4b->alloc_semp);
 }
 
 
@@ -1606,9 +1551,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
 	get_page(ac->ac_bitmap_page);
 	ac->ac_buddy_page = e4b->bd_buddy_page;
 	get_page(ac->ac_buddy_page);
-	/* on allocation we use ac to track the held semaphore */
-	ac->alloc_semp =  e4b->alloc_semp;
-	e4b->alloc_semp = NULL;
 	/* store last allocated for subsequent stream allocation */
 	if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
 		spin_lock(&sbi->s_md_lock);
@@ -2659,7 +2601,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 	struct super_block *sb = journal->j_private;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
-	int err, ret, count = 0, count2 = 0;
+	int err, count = 0, count2 = 0;
 	struct ext4_free_data *entry;
 	struct list_head *l, *ltmp;
 
@@ -2669,15 +2611,9 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 		mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
 			 entry->count, entry->group, entry);
 
-		if (test_opt(sb, DISCARD)) {
-			ret = ext4_issue_discard(sb, entry->group,
-					entry->start_blk, entry->count);
-			if (unlikely(ret == -EOPNOTSUPP)) {
-				ext4_warning(sb, "discard not supported, "
-						 "disabling");
-				clear_opt(sb, DISCARD);
-			}
-		}
+		if (test_opt(sb, DISCARD))
+			ext4_issue_discard(sb, entry->group,
+					   entry->start_blk, entry->count);
 
 		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
@@ -4226,15 +4162,12 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			spin_unlock(&pa->pa_lock);
 		}
 	}
-	if (ac->alloc_semp)
-		up_read(ac->alloc_semp);
 	if (pa) {
 		/*
 		 * We want to add the pa to the right bucket.
 		 * Remove it from the list and while adding
 		 * make sure the list to which we are adding
-		 * doesn't grow big.  We need to release
-		 * alloc_semp before calling ext4_mb_add_n_trim()
+		 * doesn't grow big.
 		 */
 		if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) {
 			spin_lock(pa->pa_obj_lock);
@@ -4303,7 +4236,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 		 * there is enough free blocks to do block allocation
 		 * and verify allocation doesn't exceed the quota limits.
 		 */
-		while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+		while (ar->len &&
+			ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+
 			/* let others to free the space */
 			yield();
 			ar->len = ar->len >> 1;
@@ -4313,9 +4248,15 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 			return 0;
 		}
 		reserv_blks = ar->len;
-		while (ar->len && dquot_alloc_block(ar->inode, ar->len)) {
-			ar->flags |= EXT4_MB_HINT_NOPREALLOC;
-			ar->len--;
+		if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
+			dquot_alloc_block_nofail(ar->inode, ar->len);
+		} else {
+			while (ar->len &&
+				dquot_alloc_block(ar->inode, ar->len)) {
+
+				ar->flags |= EXT4_MB_HINT_NOPREALLOC;
+				ar->len--;
+			}
 		}
 		inquota = ar->len;
 		if (ar->len == 0) {
@@ -4703,6 +4644,127 @@ error_return:
 	return;
 }
 
+/**
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
+ * @handle:			handle to this transaction
+ * @sb:				super block
+ * @block:			start physcial block to add to the block group
+ * @count:			number of blocks to free
+ *
+ * This marks the blocks as free in the bitmap and buddy.
+ */
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+			 ext4_fsblk_t block, unsigned long count)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gd_bh;
+	ext4_group_t block_group;
+	ext4_grpblk_t bit;
+	unsigned int i;
+	struct ext4_group_desc *desc;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_buddy e4b;
+	int err = 0, ret, blk_free_count;
+	ext4_grpblk_t blocks_freed;
+	struct ext4_group_info *grp;
+
+	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
+
+	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	grp = ext4_get_group_info(sb, block_group);
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb))
+		goto error_return;
+
+	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!desc)
+		goto error_return;
+
+	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
+	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
+	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
+	    in_range(block + count - 1, ext4_inode_table(sb, desc),
+		     sbi->s_itb_per_group)) {
+		ext4_error(sb, "Adding blocks in system zones - "
+			   "Block = %llu, count = %lu",
+			   block, count);
+		goto error_return;
+	}
+
+	BUFFER_TRACE(bitmap_bh, "getting write access");
+	err = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (err)
+		goto error_return;
+
+	/*
+	 * We are about to modify some metadata.  Call the journal APIs
+	 * to unshare ->b_data if a currently-committing transaction is
+	 * using it
+	 */
+	BUFFER_TRACE(gd_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gd_bh);
+	if (err)
+		goto error_return;
+
+	for (i = 0, blocks_freed = 0; i < count; i++) {
+		BUFFER_TRACE(bitmap_bh, "clear bit");
+		if (!mb_test_bit(bit + i, bitmap_bh->b_data)) {
+			ext4_error(sb, "bit already cleared for block %llu",
+				   (ext4_fsblk_t)(block + i));
+			BUFFER_TRACE(bitmap_bh, "bit already cleared");
+		} else {
+			blocks_freed++;
+		}
+	}
+
+	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	if (err)
+		goto error_return;
+
+	/*
+	 * need to update group_info->bb_free and bitmap
+	 * with group lock held. generate_buddy look at
+	 * them with group lock_held
+	 */
+	ext4_lock_group(sb, block_group);
+	mb_clear_bits(bitmap_bh->b_data, bit, count);
+	mb_free_blocks(NULL, &e4b, bit, count);
+	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
+	ext4_free_blks_set(sb, desc, blk_free_count);
+	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
+	ext4_unlock_group(sb, block_group);
+	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
+		atomic_add(blocks_freed,
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+	}
+
+	ext4_mb_unload_buddy(&e4b);
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+	if (!err)
+		err = ret;
+
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, err);
+	return;
+}
+
 /**
  * ext4_trim_extent -- function to TRIM one single free extent in the group
  * @sb:		super block for the file system
@@ -4715,11 +4777,10 @@ error_return:
  * one will allocate those blocks, mark it as used in buddy bitmap. This must
  * be called with under the group lock.
  */
-static int ext4_trim_extent(struct super_block *sb, int start, int count,
-		ext4_group_t group, struct ext4_buddy *e4b)
+static void ext4_trim_extent(struct super_block *sb, int start, int count,
+			     ext4_group_t group, struct ext4_buddy *e4b)
 {
 	struct ext4_free_extent ex;
-	int ret = 0;
 
 	assert_spin_locked(ext4_group_lock_ptr(sb, group));
 
@@ -4733,12 +4794,9 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-
-	ret = ext4_issue_discard(sb, group, start, count);
-
+	ext4_issue_discard(sb, group, start, count);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
-	return ret;
 }
 
 /**
@@ -4760,21 +4818,26 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
  * the group buddy bitmap. This is done until whole group is scanned.
  */
 static ext4_grpblk_t
-ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
-		ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
+ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
+		   ext4_grpblk_t start, ext4_grpblk_t max,
+		   ext4_grpblk_t minblocks)
 {
 	void *bitmap;
 	ext4_grpblk_t next, count = 0;
-	ext4_group_t group;
-	int ret = 0;
+	struct ext4_buddy e4b;
+	int ret;
 
-	BUG_ON(e4b == NULL);
+	ret = ext4_mb_load_buddy(sb, group, &e4b);
+	if (ret) {
+		ext4_error(sb, "Error in loading buddy "
+				"information for %u", group);
+		return ret;
+	}
+	bitmap = e4b.bd_bitmap;
 
-	bitmap = e4b->bd_bitmap;
-	group = e4b->bd_group;
-	start = (e4b->bd_info->bb_first_free > start) ?
-		e4b->bd_info->bb_first_free : start;
 	ext4_lock_group(sb, group);
+	start = (e4b.bd_info->bb_first_free > start) ?
+		e4b.bd_info->bb_first_free : start;
 
 	while (start < max) {
 		start = mb_find_next_zero_bit(bitmap, max, start);
@@ -4783,10 +4846,8 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
 		next = mb_find_next_bit(bitmap, max, start);
 
 		if ((next - start) >= minblocks) {
-			ret = ext4_trim_extent(sb, start,
-				next - start, group, e4b);
-			if (ret < 0)
-				break;
+			ext4_trim_extent(sb, start,
+					 next - start, group, &e4b);
 			count += next - start;
 		}
 		start = next + 1;
@@ -4802,17 +4863,15 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
 			ext4_lock_group(sb, group);
 		}
 
-		if ((e4b->bd_info->bb_free - count) < minblocks)
+		if ((e4b.bd_info->bb_free - count) < minblocks)
 			break;
 	}
 	ext4_unlock_group(sb, group);
+	ext4_mb_unload_buddy(&e4b);
 
 	ext4_debug("trimmed %d blocks in the group %d\n",
 		count, group);
 
-	if (ret < 0)
-		count = ret;
-
 	return count;
 }
 
@@ -4830,11 +4889,11 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
  */
 int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 {
-	struct ext4_buddy e4b;
+	struct ext4_group_info *grp;
 	ext4_group_t first_group, last_group;
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
 	ext4_grpblk_t cnt = 0, first_block, last_block;
-	uint64_t start, len, minlen, trimmed;
+	uint64_t start, len, minlen, trimmed = 0;
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
 	int ret = 0;
@@ -4842,7 +4901,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	start = range->start >> sb->s_blocksize_bits;
 	len = range->len >> sb->s_blocksize_bits;
 	minlen = range->minlen >> sb->s_blocksize_bits;
-	trimmed = 0;
 
 	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
 		return -EINVAL;
@@ -4863,11 +4921,12 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		return -EINVAL;
 
 	for (group = first_group; group <= last_group; group++) {
-		ret = ext4_mb_load_buddy(sb, group, &e4b);
-		if (ret) {
-			ext4_error(sb, "Error in loading buddy "
-					"information for %u", group);
-			break;
+		grp = ext4_get_group_info(sb, group);
+		/* We only do this if the grp has never been initialized */
+		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+			ret = ext4_mb_init_group(sb, group);
+			if (ret)
+				break;
 		}
 
 		/*
@@ -4880,16 +4939,14 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 			last_block = first_block + len;
 		len -= last_block - first_block;
 
-		if (e4b.bd_info->bb_free >= minlen) {
-			cnt = ext4_trim_all_free(sb, &e4b, first_block,
+		if (grp->bb_free >= minlen) {
+			cnt = ext4_trim_all_free(sb, group, first_block,
 						last_block, minlen);
 			if (cnt < 0) {
 				ret = cnt;
-				ext4_mb_unload_buddy(&e4b);
 				break;
 			}
 		}
-		ext4_mb_unload_buddy(&e4b);
 		trimmed += cnt;
 		first_block = 0;
 	}

fs/ext4/mballoc.h

@@ -193,11 +193,6 @@ struct ext4_allocation_context {
 	__u8 ac_op;		/* operation, for history only */
 	struct page *ac_bitmap_page;
 	struct page *ac_buddy_page;
-	/*
-	 * pointer to the held semaphore upon successful
-	 * block allocation
-	 */
-	struct rw_semaphore *alloc_semp;
 	struct ext4_prealloc_space *ac_pa;
 	struct ext4_locality_group *ac_lg;
 };
@@ -215,7 +210,6 @@ struct ext4_buddy {
 	struct super_block *bd_sb;
 	__u16 bd_blkbits;
 	ext4_group_t bd_group;
-	struct rw_semaphore *alloc_semp;
 };
 #define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
 #define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)

fs/ext4/migrate.c

@@ -376,7 +376,7 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
 	 * We have the extent map build with the tmp inode.
 	 * Now copy the i_data across
 	 */
-	ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS);
+	ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
 	memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
 
 	/*

fs/ext4/mmp.c

@@ -0,0 +1,351 @@
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/buffer_head.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+
+#include "ext4.h"
+
+/*
+ * Write the MMP block using WRITE_SYNC to try to get the block on-disk
+ * faster.
+ */
+static int write_mmp_block(struct buffer_head *bh)
+{
+	mark_buffer_dirty(bh);
+	lock_buffer(bh);
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	submit_bh(WRITE_SYNC, bh);
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh)))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Read the MMP block. It _must_ be read from disk and hence we clear the
+ * uptodate flag on the buffer.
+ */
+static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
+			  ext4_fsblk_t mmp_block)
+{
+	struct mmp_struct *mmp;
+
+	if (*bh)
+		clear_buffer_uptodate(*bh);
+
+	/* This would be sb_bread(sb, mmp_block), except we need to be sure
+	 * that the MD RAID device cache has been bypassed, and that the read
+	 * is not blocked in the elevator. */
+	if (!*bh)
+		*bh = sb_getblk(sb, mmp_block);
+	if (*bh) {
+		get_bh(*bh);
+		lock_buffer(*bh);
+		(*bh)->b_end_io = end_buffer_read_sync;
+		submit_bh(READ_SYNC, *bh);
+		wait_on_buffer(*bh);
+		if (!buffer_uptodate(*bh)) {
+			brelse(*bh);
+			*bh = NULL;
+		}
+	}
+	if (!*bh) {
+		ext4_warning(sb, "Error while reading MMP block %llu",
+			     mmp_block);
+		return -EIO;
+	}
+
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Dump as much information as possible to help the admin.
+ */
+void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
+		    const char *function, unsigned int line, const char *msg)
+{
+	__ext4_warning(sb, function, line, msg);
+	__ext4_warning(sb, function, line,
+		       "MMP failure info: last update time: %llu, last update "
+		       "node: %s, last update device: %s\n",
+		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
+		       mmp->mmp_nodename, mmp->mmp_bdevname);
+}
+
+/*
+ * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
+ */
+static int kmmpd(void *data)
+{
+	struct super_block *sb = ((struct mmpd_data *) data)->sb;
+	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct mmp_struct *mmp;
+	ext4_fsblk_t mmp_block;
+	u32 seq = 0;
+	unsigned long failed_writes = 0;
+	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned mmp_check_interval;
+	unsigned long last_update_time;
+	unsigned long diff;
+	int retval;
+
+	mmp_block = le64_to_cpu(es->s_mmp_block);
+	mmp = (struct mmp_struct *)(bh->b_data);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+	/*
+	 * Start with the higher mmp_check_interval and reduce it if
+	 * the MMP block is being updated on time.
+	 */
+	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
+				 EXT4_MMP_MIN_CHECK_INTERVAL);
+	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	bdevname(bh->b_bdev, mmp->mmp_bdevname);
+
+	memcpy(mmp->mmp_nodename, init_utsname()->sysname,
+	       sizeof(mmp->mmp_nodename));
+
+	while (!kthread_should_stop()) {
+		if (++seq > EXT4_MMP_SEQ_MAX)
+			seq = 1;
+
+		mmp->mmp_seq = cpu_to_le32(seq);
+		mmp->mmp_time = cpu_to_le64(get_seconds());
+		last_update_time = jiffies;
+
+		retval = write_mmp_block(bh);
+		/*
+		 * Don't spew too many error messages. Print one every
+		 * (s_mmp_update_interval * 60) seconds.
+		 */
+		if (retval && (failed_writes % 60) == 0) {
+			ext4_error(sb, "Error writing to MMP block");
+			failed_writes++;
+		}
+
+		if (!(le32_to_cpu(es->s_feature_incompat) &
+		    EXT4_FEATURE_INCOMPAT_MMP)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		if (sb->s_flags & MS_RDONLY) {
+			ext4_warning(sb, "kmmpd being stopped since filesystem "
+				     "has been remounted as readonly.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		diff = jiffies - last_update_time;
+		if (diff < mmp_update_interval * HZ)
+			schedule_timeout_interruptible(mmp_update_interval *
+						       HZ - diff);
+
+		/*
+		 * We need to make sure that more than mmp_check_interval
+		 * seconds have not passed since writing. If that has happened
+		 * we need to check if the MMP block is as we left it.
+		 */
+		diff = jiffies - last_update_time;
+		if (diff > mmp_check_interval * HZ) {
+			struct buffer_head *bh_check = NULL;
+			struct mmp_struct *mmp_check;
+
+			retval = read_mmp_block(sb, &bh_check, mmp_block);
+			if (retval) {
+				ext4_error(sb, "error reading MMP data: %d",
+					   retval);
+
+				EXT4_SB(sb)->s_mmp_tsk = NULL;
+				goto failed;
+			}
+
+			mmp_check = (struct mmp_struct *)(bh_check->b_data);
+			if (mmp->mmp_seq != mmp_check->mmp_seq ||
+			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
+				   sizeof(mmp->mmp_nodename))) {
+				dump_mmp_msg(sb, mmp_check,
+					     "Error while updating MMP info. "
+					     "The filesystem seems to have been"
+					     " multiply mounted.");
+				ext4_error(sb, "abort");
+				goto failed;
+			}
+			put_bh(bh_check);
+		}
+
+		 /*
+		 * Adjust the mmp_check_interval depending on how much time
+		 * it took for the MMP block to be written.
+		 */
+		mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
+					     EXT4_MMP_MAX_CHECK_INTERVAL),
+					 EXT4_MMP_MIN_CHECK_INTERVAL);
+		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	}
+
+	/*
+	 * Unmount seems to be clean.
+	 */
+	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+
+	retval = write_mmp_block(bh);
+
+failed:
+	kfree(data);
+	brelse(bh);
+	return retval;
+}
+
+/*
+ * Get a random new sequence number but make sure it is not greater than
+ * EXT4_MMP_SEQ_MAX.
+ */
+static unsigned int mmp_new_seq(void)
+{
+	u32 new_seq;
+
+	do {
+		get_random_bytes(&new_seq, sizeof(u32));
+	} while (new_seq > EXT4_MMP_SEQ_MAX);
+
+	return new_seq;
+}
+
+/*
+ * Protect the filesystem from being mounted more than once.
+ */
+int ext4_multi_mount_protect(struct super_block *sb,
+				    ext4_fsblk_t mmp_block)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = NULL;
+	struct mmp_struct *mmp = NULL;
+	struct mmpd_data *mmpd_data;
+	u32 seq;
+	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned int wait_time = 0;
+	int retval;
+
+	if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
+	    mmp_block >= ext4_blocks_count(es)) {
+		ext4_warning(sb, "Invalid MMP block in superblock");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+
+	mmp = (struct mmp_struct *)(bh->b_data);
+
+	if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
+		mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
+
+	/*
+	 * If check_interval in MMP block is larger, use that instead of
+	 * update_interval from the superblock.
+	 */
+	if (mmp->mmp_check_interval > mmp_check_interval)
+		mmp_check_interval = mmp->mmp_check_interval;
+
+	seq = le32_to_cpu(mmp->mmp_seq);
+	if (seq == EXT4_MMP_SEQ_CLEAN)
+		goto skip;
+
+	if (seq == EXT4_MMP_SEQ_FSCK) {
+		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		goto failed;
+	}
+
+	wait_time = min(mmp_check_interval * 2 + 1,
+			mmp_check_interval + 60);
+
+	/* Print MMP interval if more than 20 secs. */
+	if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
+		ext4_warning(sb, "MMP interval %u higher than expected, please"
+			     " wait.\n", wait_time * 2);
+
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+skip:
+	/*
+	 * write a new random sequence number.
+	 */
+	mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
+
+	retval = write_mmp_block(bh);
+	if (retval)
+		goto failed;
+
+	/*
+	 * wait for MMP interval and check mmp_seq.
+	 */
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+	mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL);
+	if (!mmpd_data) {
+		ext4_warning(sb, "not enough memory for mmpd_data");
+		goto failed;
+	}
+	mmpd_data->sb = sb;
+	mmpd_data->bh = bh;
+
+	/*
+	 * Start a kernel thread to update the MMP block periodically.
+	 */
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+					     bdevname(bh->b_bdev,
+						      mmp->mmp_bdevname));
+	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
+		EXT4_SB(sb)->s_mmp_tsk = NULL;
+		kfree(mmpd_data);
+		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
+			     sb->s_id);
+		goto failed;
+	}
+
+	return 0;
+
+failed:
+	brelse(bh);
+	return 1;
+}
+
+

fs/ext4/move_extent.c

@@ -876,8 +876,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	 * It needs to call wait_on_page_writeback() to wait for the
 	 * writeback of the page.
 	 */
-	if (PageWriteback(page))
-		wait_on_page_writeback(page);
+	wait_on_page_writeback(page);
 
 	/* Release old bh and drop refs */
 	try_to_release_page(page, 0);

fs/ext4/namei.c

@@ -1413,10 +1413,22 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	frame->at = entries;
 	frame->bh = bh;
 	bh = bh2;
+
+	ext4_handle_dirty_metadata(handle, dir, frame->bh);
+	ext4_handle_dirty_metadata(handle, dir, bh);
+
 	de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
-	dx_release (frames);
-	if (!(de))
+	if (!de) {
+		/*
+		 * Even if the block split failed, we have to properly write
+		 * out all the changes we did so far. Otherwise we can end up
+		 * with corrupted filesystem.
+		 */
+		ext4_mark_inode_dirty(handle, dir);
+		dx_release(frames);
 		return retval;
+	}
+	dx_release(frames);
 
 	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
 	brelse(bh);
@@ -2240,6 +2252,7 @@ static int ext4_symlink(struct inode *dir,
 	handle_t *handle;
 	struct inode *inode;
 	int l, err, retries = 0;
+	int credits;
 
 	l = strlen(symname)+1;
 	if (l > dir->i_sb->s_blocksize)
@@ -2247,10 +2260,26 @@ static int ext4_symlink(struct inode *dir,
 
 	dquot_initialize(dir);
 
+	if (l > EXT4_N_BLOCKS * 4) {
+		/*
+		 * For non-fast symlinks, we just allocate inode and put it on
+		 * orphan list in the first transaction => we need bitmap,
+		 * group descriptor, sb, inode block, quota blocks.
+		 */
+		credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+	} else {
+		/*
+		 * Fast symlink. We have to add entry to directory
+		 * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS),
+		 * allocate new inode (bitmap, group descriptor, inode block,
+		 * quota blocks, sb is already counted in previous macros).
+		 */
+		credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+			  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+			  EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+	}
 retry:
-	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 +
-					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
+	handle = ext4_journal_start(dir, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -2263,21 +2292,44 @@ retry:
 	if (IS_ERR(inode))
 		goto out_stop;
 
-	if (l > sizeof(EXT4_I(inode)->i_data)) {
+	if (l > EXT4_N_BLOCKS * 4) {
 		inode->i_op = &ext4_symlink_inode_operations;
 		ext4_set_aops(inode);
 		/*
-		 * page_symlink() calls into ext4_prepare/commit_write.
-		 * We have a transaction open.  All is sweetness.  It also sets
-		 * i_size in generic_commit_write().
+		 * We cannot call page_symlink() with transaction started
+		 * because it calls into ext4_write_begin() which can wait
+		 * for transaction commit if we are running out of space
+		 * and thus we deadlock. So we have to stop transaction now
+		 * and restart it when symlink contents is written.
+		 * 
+		 * To keep fs consistent in case of crash, we have to put inode
+		 * to orphan list in the mean time.
 		 */
+		drop_nlink(inode);
+		err = ext4_orphan_add(handle, inode);
+		ext4_journal_stop(handle);
+		if (err)
+			goto err_drop_inode;
 		err = __page_symlink(inode, symname, l, 1);
+		if (err)
+			goto err_drop_inode;
+		/*
+		 * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS
+		 * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
+		 */
+		handle = ext4_journal_start(dir,
+				EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+				EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto err_drop_inode;
+		}
+		inc_nlink(inode);
+		err = ext4_orphan_del(handle, inode);
 		if (err) {
+			ext4_journal_stop(handle);
 			clear_nlink(inode);
-			unlock_new_inode(inode);
-			ext4_mark_inode_dirty(handle, inode);
-			iput(inode);
-			goto out_stop;
+			goto err_drop_inode;
 		}
 	} else {
 		/* clear the extent format for fast symlink */
@@ -2293,6 +2345,10 @@ out_stop:
 	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
 		goto retry;
 	return err;
+err_drop_inode:
+	unlock_new_inode(inode);
+	iput(inode);
+	return err;
 }
 
 static int ext4_link(struct dentry *old_dentry,

fs/ext4/page-io.c

@@ -203,46 +203,29 @@ static void ext4_end_bio(struct bio *bio, int error)
 	for (i = 0; i < io_end->num_io_pages; i++) {
 		struct page *page = io_end->pages[i]->p_page;
 		struct buffer_head *bh, *head;
-		int partial_write = 0;
+		loff_t offset;
+		loff_t io_end_offset;
 
-		head = page_buffers(page);
-		if (error)
+		if (error) {
 			SetPageError(page);
-		BUG_ON(!head);
-		if (head->b_size != PAGE_CACHE_SIZE) {
-			loff_t offset;
-			loff_t io_end_offset = io_end->offset + io_end->size;
+			set_bit(AS_EIO, &page->mapping->flags);
+			head = page_buffers(page);
+			BUG_ON(!head);
+
+			io_end_offset = io_end->offset + io_end->size;
 
 			offset = (sector_t) page->index << PAGE_CACHE_SHIFT;
 			bh = head;
 			do {
 				if ((offset >= io_end->offset) &&
-				    (offset+bh->b_size <= io_end_offset)) {
-					if (error)
-						buffer_io_error(bh);
-
-				}
-				if (buffer_delay(bh))
-					partial_write = 1;
-				else if (!buffer_mapped(bh))
-					clear_buffer_dirty(bh);
-				else if (buffer_dirty(bh))
-					partial_write = 1;
+				    (offset+bh->b_size <= io_end_offset))
+					buffer_io_error(bh);
+
 				offset += bh->b_size;
 				bh = bh->b_this_page;
 			} while (bh != head);
 		}
 
-		/*
-		 * If this is a partial write which happened to make
-		 * all buffers uptodate then we can optimize away a
-		 * bogus readpage() for the next read(). Here we
-		 * 'discover' whether the page went uptodate as a
-		 * result of this (potentially partial) write.
-		 */
-		if (!partial_write)
-			SetPageUptodate(page);
-
 		put_io_page(io_end->pages[i]);
 	}
 	io_end->num_io_pages = 0;

fs/ext4/super.c

@@ -75,11 +75,27 @@ static void ext4_write_super(struct super_block *sb);
 static int ext4_freeze(struct super_block *sb);
 static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data);
+static inline int ext2_feature_set_ok(struct super_block *sb);
+static inline int ext3_feature_set_ok(struct super_block *sb);
 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);
 
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext2",
+	.mount		= ext4_mount,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#else
+#define IS_EXT2_SB(sb) (0)
+#endif
+
+
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
 	.owner		= THIS_MODULE,
@@ -806,6 +822,8 @@ static void ext4_put_super(struct super_block *sb)
 		invalidate_bdev(sbi->journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
 	sb->s_fs_info = NULL;
 	/*
 	 * Now that we are completely done shutting down the
@@ -1096,7 +1114,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 
 	if (!test_opt(sb, INIT_INODE_TABLE))
 		seq_puts(seq, ",noinit_inode_table");
-	else if (sbi->s_li_wait_mult)
+	else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
 		seq_printf(seq, ",init_inode_table=%u",
 			   (unsigned) sbi->s_li_wait_mult);
 
@@ -1187,9 +1205,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 				const char *data, size_t len, loff_t off);
 
 static const struct dquot_operations ext4_quota_operations = {
-#ifdef CONFIG_QUOTA
 	.get_reserved_space = ext4_get_reserved_space,
-#endif
 	.write_dquot	= ext4_write_dquot,
 	.acquire_dquot	= ext4_acquire_dquot,
 	.release_dquot	= ext4_release_dquot,
@@ -1900,7 +1916,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		ext4_msg(sb, KERN_WARNING,
 			 "warning: mounting fs with errors, "
 			 "running e2fsck is recommended");
-	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
+	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
 		 le16_to_cpu(es->s_mnt_count) >=
 		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
 		ext4_msg(sb, KERN_WARNING,
@@ -2425,6 +2441,18 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
+static ssize_t extent_cache_hits_show(struct ext4_attr *a,
+				      struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_hits);
+}
+
+static ssize_t extent_cache_misses_show(struct ext4_attr *a,
+					struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_misses);
+}
+
 static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 					  struct ext4_sb_info *sbi,
 					  const char *buf, size_t count)
@@ -2482,6 +2510,8 @@ 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_RO_ATTR(extent_cache_hits);
+EXT4_RO_ATTR(extent_cache_misses);
 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);
@@ -2497,6 +2527,8 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(delayed_allocation_blocks),
 	ATTR_LIST(session_write_kbytes),
 	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(extent_cache_hits),
+	ATTR_LIST(extent_cache_misses),
 	ATTR_LIST(inode_readahead_blks),
 	ATTR_LIST(inode_goal),
 	ATTR_LIST(mb_stats),
@@ -2659,12 +2691,6 @@ static void print_daily_error_info(unsigned long arg)
 	mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);  /* Once a day */
 }
 
-static void ext4_lazyinode_timeout(unsigned long data)
-{
-	struct task_struct *p = (struct task_struct *)data;
-	wake_up_process(p);
-}
-
 /* Find next suitable group and run ext4_init_inode_table */
 static int ext4_run_li_request(struct ext4_li_request *elr)
 {
@@ -2696,11 +2722,8 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
 		if (elr->lr_timeout == 0) {
-			timeout = jiffies - timeout;
-			if (elr->lr_sbi->s_li_wait_mult)
-				timeout *= elr->lr_sbi->s_li_wait_mult;
-			else
-				timeout *= 20;
+			timeout = (jiffies - timeout) *
+				  elr->lr_sbi->s_li_wait_mult;
 			elr->lr_timeout = timeout;
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -2712,7 +2735,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 
 /*
  * Remove lr_request from the list_request and free the
- * request tructure. Should be called with li_list_mtx held
+ * request structure. Should be called with li_list_mtx held
  */
 static void ext4_remove_li_request(struct ext4_li_request *elr)
 {
@@ -2730,14 +2753,16 @@ static void ext4_remove_li_request(struct ext4_li_request *elr)
 
 static void ext4_unregister_li_request(struct super_block *sb)
 {
-	struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
-
-	if (!ext4_li_info)
+	mutex_lock(&ext4_li_mtx);
+	if (!ext4_li_info) {
+		mutex_unlock(&ext4_li_mtx);
 		return;
+	}
 
 	mutex_lock(&ext4_li_info->li_list_mtx);
-	ext4_remove_li_request(elr);
+	ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
 	mutex_unlock(&ext4_li_info->li_list_mtx);
+	mutex_unlock(&ext4_li_mtx);
 }
 
 static struct task_struct *ext4_lazyinit_task;
@@ -2756,17 +2781,10 @@ static int ext4_lazyinit_thread(void *arg)
 	struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
 	struct list_head *pos, *n;
 	struct ext4_li_request *elr;
-	unsigned long next_wakeup;
-	DEFINE_WAIT(wait);
+	unsigned long next_wakeup, cur;
 
 	BUG_ON(NULL == eli);
 
-	eli->li_timer.data = (unsigned long)current;
-	eli->li_timer.function = ext4_lazyinode_timeout;
-
-	eli->li_task = current;
-	wake_up(&eli->li_wait_task);
-
 cont_thread:
 	while (true) {
 		next_wakeup = MAX_JIFFY_OFFSET;
@@ -2797,19 +2815,15 @@ cont_thread:
 		if (freezing(current))
 			refrigerator();
 
-		if ((time_after_eq(jiffies, next_wakeup)) ||
+		cur = jiffies;
+		if ((time_after_eq(cur, next_wakeup)) ||
 		    (MAX_JIFFY_OFFSET == next_wakeup)) {
 			cond_resched();
 			continue;
 		}
 
-		eli->li_timer.expires = next_wakeup;
-		add_timer(&eli->li_timer);
-		prepare_to_wait(&eli->li_wait_daemon, &wait,
-				TASK_INTERRUPTIBLE);
-		if (time_before(jiffies, next_wakeup))
-			schedule();
-		finish_wait(&eli->li_wait_daemon, &wait);
+		schedule_timeout_interruptible(next_wakeup - cur);
+
 		if (kthread_should_stop()) {
 			ext4_clear_request_list();
 			goto exit_thread;
@@ -2833,12 +2847,7 @@ exit_thread:
 		goto cont_thread;
 	}
 	mutex_unlock(&eli->li_list_mtx);
-	del_timer_sync(&ext4_li_info->li_timer);
-	eli->li_task = NULL;
-	wake_up(&eli->li_wait_task);
-
 	kfree(ext4_li_info);
-	ext4_lazyinit_task = NULL;
 	ext4_li_info = NULL;
 	mutex_unlock(&ext4_li_mtx);
 
@@ -2866,7 +2875,6 @@ static int ext4_run_lazyinit_thread(void)
 	if (IS_ERR(ext4_lazyinit_task)) {
 		int err = PTR_ERR(ext4_lazyinit_task);
 		ext4_clear_request_list();
-		del_timer_sync(&ext4_li_info->li_timer);
 		kfree(ext4_li_info);
 		ext4_li_info = NULL;
 		printk(KERN_CRIT "EXT4: error %d creating inode table "
@@ -2875,8 +2883,6 @@ static int ext4_run_lazyinit_thread(void)
 		return err;
 	}
 	ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
-
-	wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
 	return 0;
 }
 
@@ -2911,13 +2917,9 @@ static int ext4_li_info_new(void)
 	if (!eli)
 		return -ENOMEM;
 
-	eli->li_task = NULL;
 	INIT_LIST_HEAD(&eli->li_request_list);
 	mutex_init(&eli->li_list_mtx);
 
-	init_waitqueue_head(&eli->li_wait_daemon);
-	init_waitqueue_head(&eli->li_wait_task);
-	init_timer(&eli->li_timer);
 	eli->li_state |= EXT4_LAZYINIT_QUIT;
 
 	ext4_li_info = eli;
@@ -2960,20 +2962,19 @@ static int ext4_register_li_request(struct super_block *sb,
 	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
 	int ret = 0;
 
-	if (sbi->s_li_request != NULL)
+	if (sbi->s_li_request != NULL) {
+		/*
+		 * Reset timeout so it can be computed again, because
+		 * s_li_wait_mult might have changed.
+		 */
+		sbi->s_li_request->lr_timeout = 0;
 		return 0;
+	}
 
 	if (first_not_zeroed == ngroups ||
 	    (sb->s_flags & MS_RDONLY) ||
-	    !test_opt(sb, INIT_INODE_TABLE)) {
-		sbi->s_li_request = NULL;
+	    !test_opt(sb, INIT_INODE_TABLE))
 		return 0;
-	}
-
-	if (first_not_zeroed == ngroups) {
-		sbi->s_li_request = NULL;
-		return 0;
-	}
 
 	elr = ext4_li_request_new(sb, first_not_zeroed);
 	if (!elr)
@@ -3166,6 +3167,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	    ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
 		set_opt(sb, DELALLOC);
 
+	/*
+	 * set default s_li_wait_mult for lazyinit, for the case there is
+	 * no mount option specified.
+	 */
+	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
+
 	if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
 			   &journal_devnum, &journal_ioprio, NULL, 0)) {
 		ext4_msg(sb, KERN_WARNING,
@@ -3187,6 +3194,28 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		       "feature flags set on rev 0 fs, "
 		       "running e2fsck is recommended");
 
+	if (IS_EXT2_SB(sb)) {
+		if (ext2_feature_set_ok(sb))
+			ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
+				 "using the ext4 subsystem");
+		else {
+			ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due "
+				 "to feature incompatibilities");
+			goto failed_mount;
+		}
+	}
+
+	if (IS_EXT3_SB(sb)) {
+		if (ext3_feature_set_ok(sb))
+			ext4_msg(sb, KERN_INFO, "mounting ext3 file system "
+				 "using the ext4 subsystem");
+		else {
+			ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due "
+				 "to feature incompatibilities");
+			goto failed_mount;
+		}
+	}
+
 	/*
 	 * Check feature flags regardless of the revision level, since we
 	 * previously didn't change the revision level when setting the flags,
@@ -3459,6 +3488,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			  EXT4_HAS_INCOMPAT_FEATURE(sb,
 				    EXT4_FEATURE_INCOMPAT_RECOVER));
 
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
+	    !(sb->s_flags & MS_RDONLY))
+		if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
+			goto failed_mount3;
+
 	/*
 	 * The first inode we look at is the journal inode.  Don't try
 	 * root first: it may be modified in the journal!
@@ -3474,7 +3508,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount_wq;
 	} else {
 		clear_opt(sb, DATA_FLAGS);
-		set_opt(sb, WRITEBACK_DATA);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
@@ -3707,6 +3740,8 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
@@ -4242,7 +4277,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	int enable_quota = 0;
 	ext4_group_t g;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
-	int err;
+	int err = 0;
 #ifdef CONFIG_QUOTA
 	int i;
 #endif
@@ -4368,6 +4403,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 				goto restore_opts;
 			if (!ext4_setup_super(sb, es, 0))
 				sb->s_flags &= ~MS_RDONLY;
+			if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+						     EXT4_FEATURE_INCOMPAT_MMP))
+				if (ext4_multi_mount_protect(sb,
+						le64_to_cpu(es->s_mmp_block))) {
+					err = -EROFS;
+					goto restore_opts;
+				}
 			enable_quota = 1;
 		}
 	}
@@ -4432,6 +4474,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
 	u64 fsid;
+	s64 bfree;
 
 	if (test_opt(sb, MINIX_DF)) {
 		sbi->s_overhead_last = 0;
@@ -4475,8 +4518,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_type = EXT4_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
-	buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+	bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
 		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+	/* prevent underflow in case that few free space is available */
+	buf->f_bfree = max_t(s64, bfree, 0);
 	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
 	if (buf->f_bfree < ext4_r_blocks_count(es))
 		buf->f_bavail = 0;
@@ -4652,6 +4697,9 @@ static int ext4_quota_off(struct super_block *sb, int type)
 	if (test_opt(sb, DELALLOC))
 		sync_filesystem(sb);
 
+	if (!inode)
+		goto out;
+
 	/* Update modification times of quota files when userspace can
 	 * start looking at them */
 	handle = ext4_journal_start(inode, 1);
@@ -4772,14 +4820,6 @@ static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
 }
 
 #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
-static struct file_system_type ext2_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "ext2",
-	.mount		= ext4_mount,
-	.kill_sb	= kill_block_super,
-	.fs_flags	= FS_REQUIRES_DEV,
-};
-
 static inline void register_as_ext2(void)
 {
 	int err = register_filesystem(&ext2_fs_type);
@@ -4792,10 +4832,22 @@ static inline void unregister_as_ext2(void)
 {
 	unregister_filesystem(&ext2_fs_type);
 }
+
+static inline int ext2_feature_set_ok(struct super_block *sb)
+{
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP))
+		return 0;
+	if (sb->s_flags & MS_RDONLY)
+		return 1;
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))
+		return 0;
+	return 1;
+}
 MODULE_ALIAS("ext2");
 #else
 static inline void register_as_ext2(void) { }
 static inline void unregister_as_ext2(void) { }
+static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; }
 #endif
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
@@ -4811,10 +4863,24 @@ static inline void unregister_as_ext3(void)
 {
 	unregister_filesystem(&ext3_fs_type);
 }
+
+static inline int ext3_feature_set_ok(struct super_block *sb)
+{
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))
+		return 0;
+	if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		return 0;
+	if (sb->s_flags & MS_RDONLY)
+		return 1;
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))
+		return 0;
+	return 1;
+}
 MODULE_ALIAS("ext3");
 #else
 static inline void register_as_ext3(void) { }
 static inline void unregister_as_ext3(void) { }
+static inline int ext3_feature_set_ok(struct super_block *sb) { return 0; }
 #endif
 
 static struct file_system_type ext4_fs_type = {
@@ -4898,8 +4964,8 @@ static int __init ext4_init_fs(void)
 	err = init_inodecache();
 	if (err)
 		goto out1;
-	register_as_ext2();
 	register_as_ext3();
+	register_as_ext2();
 	err = register_filesystem(&ext4_fs_type);
 	if (err)
 		goto out;

fs/ext4/xattr.c

@@ -820,8 +820,8 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
-			block = ext4_new_meta_blocks(handle, inode,
-						  goal, NULL, &error);
+			block = ext4_new_meta_blocks(handle, inode, goal, 0,
+						     NULL, &error);
 			if (error)
 				goto cleanup;
 

fs/jbd2/commit.c

@@ -219,7 +219,6 @@ static int journal_submit_data_buffers(journal_t *journal,
 			ret = err;
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
-		commit_transaction->t_flushed_data_blocks = 1;
 		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
 		smp_mb__after_clear_bit();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
@@ -672,12 +671,16 @@ start_journal_io:
 		err = 0;
 	}
 
+	write_lock(&journal->j_state_lock);
+	J_ASSERT(commit_transaction->t_state == T_COMMIT);
+	commit_transaction->t_state = T_COMMIT_DFLUSH;
+	write_unlock(&journal->j_state_lock);
 	/* 
 	 * If the journal is not located on the file system device,
 	 * then we must flush the file system device before we issue
 	 * the commit record
 	 */
-	if (commit_transaction->t_flushed_data_blocks &&
+	if (commit_transaction->t_need_data_flush &&
 	    (journal->j_fs_dev != journal->j_dev) &&
 	    (journal->j_flags & JBD2_BARRIER))
 		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
@@ -754,8 +757,13 @@ wait_for_iobuf:
                    required. */
 		JBUFFER_TRACE(jh, "file as BJ_Forget");
 		jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
-		/* Wake up any transactions which were waiting for this
-		   IO to complete */
+		/*
+		 * Wake up any transactions which were waiting for this IO to
+		 * complete. The barrier must be here so that changes by
+		 * jbd2_journal_file_buffer() take effect before wake_up_bit()
+		 * does the waitqueue check.
+		 */
+		smp_mb();
 		wake_up_bit(&bh->b_state, BH_Unshadow);
 		JBUFFER_TRACE(jh, "brelse shadowed buffer");
 		__brelse(bh);
@@ -794,6 +802,10 @@ wait_for_iobuf:
 		jbd2_journal_abort(journal, err);
 
 	jbd_debug(3, "JBD: commit phase 5\n");
+	write_lock(&journal->j_state_lock);
+	J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH);
+	commit_transaction->t_state = T_COMMIT_JFLUSH;
+	write_unlock(&journal->j_state_lock);
 
 	if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
 				       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
@@ -949,7 +961,7 @@ restart_loop:
 
 	jbd_debug(3, "JBD: commit phase 7\n");
 
-	J_ASSERT(commit_transaction->t_state == T_COMMIT);
+	J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH);
 
 	commit_transaction->t_start = jiffies;
 	stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,

fs/jbd2/journal.c

@@ -479,9 +479,12 @@ int __jbd2_log_space_left(journal_t *journal)
 int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 {
 	/*
-	 * Are we already doing a recent enough commit?
+	 * The only transaction we can possibly wait upon is the
+	 * currently running transaction (if it exists).  Otherwise,
+	 * the target tid must be an old one.
 	 */
-	if (!tid_geq(journal->j_commit_request, target)) {
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == target) {
 		/*
 		 * We want a new commit: OK, mark the request and wakeup the
 		 * commit thread.  We do _not_ do the commit ourselves.
@@ -493,7 +496,15 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 			  journal->j_commit_sequence);
 		wake_up(&journal->j_wait_commit);
 		return 1;
-	}
+	} else if (!tid_geq(journal->j_commit_request, target))
+		/* This should never happen, but if it does, preserve
+		   the evidence before kjournald goes into a loop and
+		   increments j_commit_sequence beyond all recognition. */
+		WARN_ONCE(1, "jbd: bad log_start_commit: %u %u %u %u\n",
+			  journal->j_commit_request,
+			  journal->j_commit_sequence,
+			  target, journal->j_running_transaction ? 
+			  journal->j_running_transaction->t_tid : 0);
 	return 0;
 }
 
@@ -576,6 +587,47 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 	return ret;
 }
 
+/*
+ * Return 1 if a given transaction has not yet sent barrier request
+ * connected with a transaction commit. If 0 is returned, transaction
+ * may or may not have sent the barrier. Used to avoid sending barrier
+ * twice in common cases.
+ */
+int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid)
+{
+	int ret = 0;
+	transaction_t *commit_trans;
+
+	if (!(journal->j_flags & JBD2_BARRIER))
+		return 0;
+	read_lock(&journal->j_state_lock);
+	/* Transaction already committed? */
+	if (tid_geq(journal->j_commit_sequence, tid))
+		goto out;
+	commit_trans = journal->j_committing_transaction;
+	if (!commit_trans || commit_trans->t_tid != tid) {
+		ret = 1;
+		goto out;
+	}
+	/*
+	 * Transaction is being committed and we already proceeded to
+	 * submitting a flush to fs partition?
+	 */
+	if (journal->j_fs_dev != journal->j_dev) {
+		if (!commit_trans->t_need_data_flush ||
+		    commit_trans->t_state >= T_COMMIT_DFLUSH)
+			goto out;
+	} else {
+		if (commit_trans->t_state >= T_COMMIT_JFLUSH)
+			goto out;
+	}
+	ret = 1;
+out:
+	read_unlock(&journal->j_state_lock);
+	return ret;
+}
+EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier);
+
 /*
  * Wait for a specified commit to complete.
  * The caller may not hold the journal lock.

fs/jbd2/transaction.c

@@ -82,7 +82,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
  */
 
 /*
- * Update transiaction's maximum wait time, if debugging is enabled.
+ * Update transaction's maximum wait time, if debugging is enabled.
  *
  * In order for t_max_wait to be reliable, it must be protected by a
  * lock.  But doing so will mean that start_this_handle() can not be
@@ -91,11 +91,10 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
  * means that maximum wait time reported by the jbd2_run_stats
  * tracepoint will always be zero.
  */
-static inline void update_t_max_wait(transaction_t *transaction)
+static inline void update_t_max_wait(transaction_t *transaction,
+				     unsigned long ts)
 {
 #ifdef CONFIG_JBD2_DEBUG
-	unsigned long ts = jiffies;
-
 	if (jbd2_journal_enable_debug &&
 	    time_after(transaction->t_start, ts)) {
 		ts = jbd2_time_diff(ts, transaction->t_start);
@@ -121,6 +120,7 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 	tid_t		tid;
 	int		needed, need_to_start;
 	int		nblocks = handle->h_buffer_credits;
+	unsigned long ts = jiffies;
 
 	if (nblocks > journal->j_max_transaction_buffers) {
 		printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
@@ -271,7 +271,7 @@ repeat:
 	/* OK, account for the buffers that this operation expects to
 	 * use and add the handle to the running transaction. 
 	 */
-	update_t_max_wait(transaction);
+	update_t_max_wait(transaction, ts);
 	handle->h_transaction = transaction;
 	atomic_inc(&transaction->t_updates);
 	atomic_inc(&transaction->t_handle_count);
@@ -316,7 +316,8 @@ static handle_t *new_handle(int nblocks)
  * This function is visible to journal users (like ext3fs), so is not
  * called with the journal already locked.
  *
- * Return a pointer to a newly allocated handle, or NULL on failure
+ * Return a pointer to a newly allocated handle, or an ERR_PTR() value
+ * on failure.
  */
 handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int gfp_mask)
 {
@@ -921,8 +922,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 	 */
 	JBUFFER_TRACE(jh, "cancelling revoke");
 	jbd2_journal_cancel_revoke(handle, jh);
-	jbd2_journal_put_journal_head(jh);
 out:
+	jbd2_journal_put_journal_head(jh);
 	return err;
 }
 
@@ -2147,6 +2148,13 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
 	    jinode->i_next_transaction == transaction)
 		goto done;
 
+	/*
+	 * We only ever set this variable to 1 so the test is safe. Since
+	 * t_need_data_flush is likely to be set, we do the test to save some
+	 * cacheline bouncing
+	 */
+	if (!transaction->t_need_data_flush)
+		transaction->t_need_data_flush = 1;
 	/* On some different transaction's list - should be
 	 * the committing one */
 	if (jinode->i_transaction) {

include/linux/jbd2.h

@@ -529,9 +529,10 @@ struct transaction_s
 	enum {
 		T_RUNNING,
 		T_LOCKED,
-		T_RUNDOWN,
 		T_FLUSH,
 		T_COMMIT,
+		T_COMMIT_DFLUSH,
+		T_COMMIT_JFLUSH,
 		T_FINISHED
 	}			t_state;
 
@@ -658,7 +659,9 @@ struct transaction_s
 	 * waiting for it to finish.
 	 */
 	unsigned int t_synchronous_commit:1;
-	unsigned int t_flushed_data_blocks:1;
+
+	/* Disk flush needs to be sent to fs partition [no locking] */
+	int			t_need_data_flush;
 
 	/*
 	 * For use by the filesystem to store fs-specific data
@@ -1228,6 +1231,7 @@ 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_log_do_checkpoint(journal_t *journal);
+int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
 
 void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);