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:
  ext4: Fix time encoding with extra epoch bits
  ext4: Add a stub for mpage_da_data in the trace header
  jbd2: Use tracepoints for history file
  ext4: Use tracepoints for mb_history trace file
  ext4, jbd2: Drop unneeded printks at mount and unmount time
  ext4: Handle nested ext4_journal_start/stop calls without a journal
  ext4: Make sure ext4_dirty_inode() updates the inode in no journal mode
  ext4: Avoid updating the inode table bh twice in no journal mode
  ext4: EXT4_IOC_MOVE_EXT: Check for different original and donor inodes first
  ext4: async direct IO for holes and fallocate support
  ext4: Use end_io callback to avoid direct I/O fallback to buffered I/O
  ext4: Split uninitialized extents for direct I/O
  ext4: release reserved quota when block reservation for delalloc retry
  ext4: Adjust ext4_da_writepages() to write out larger contiguous chunks
  ext4: Fix hueristic which avoids group preallocation for closed files
  ext4: Use ext4_msg() for ext4_da_writepage() errors
  ext4: Update documentation about quota mount options

Documentation/filesystems/ext4.txt

@@ -282,9 +282,16 @@ stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data
 			disks *  RAID chunk size in file system blocks.
-delalloc	(*)	Deferring block allocation until write-out time.
-nodelalloc		Disable delayed allocation. Blocks are allocation
-			when data is copied from user to page cache.
+
+delalloc	(*)	Defer block allocation until just before ext4
+			writes out the block(s) in question.  This
+			allows ext4 to better allocation decisions
+			more efficiently.
+nodelalloc		Disable delayed allocation.  Blocks are allocated
+			when the data is copied from userspace to the
+			page cache, either via the write(2) system call
+			or when an mmap'ed page which was previously
+			unallocated is written for the first time.
 
 max_batch_time=usec	Maximum amount of time ext4 should wait for
 			additional filesystem operations to be batch

Documentation/filesystems/proc.txt

@@ -1113,7 +1113,6 @@ Table 1-12: Files in /proc/fs/ext4/<devname>
 ..............................................................................
  File            Content                                        
  mb_groups       details of multiblock allocator buddy cache of free blocks
- mb_history      multiblock allocation history
 ..............................................................................
 
 

fs/ext4/ext4.h

@@ -65,6 +65,12 @@ typedef __u32 ext4_lblk_t;
 /* data type for block group number */
 typedef unsigned int ext4_group_t;
 
+/*
+ * Flags used in mballoc's allocation_context flags field.  
+ *
+ * Also used to show what's going on for debugging purposes when the
+ * flag field is exported via the traceport interface
+ */
 
 /* prefer goal again. length */
 #define EXT4_MB_HINT_MERGE		0x0001
@@ -127,6 +133,16 @@ struct mpage_da_data {
 	int pages_written;
 	int retval;
 };
+#define	DIO_AIO_UNWRITTEN	0x1
+typedef struct ext4_io_end {
+	struct list_head	list;		/* per-file finished AIO list */
+	struct inode		*inode;		/* file being written to */
+	unsigned int		flag;		/* unwritten or not */
+	int			error;		/* I/O error code */
+	ext4_lblk_t		offset;		/* offset in the file */
+	size_t			size;		/* size of the extent */
+	struct work_struct	work;		/* data work queue */
+} ext4_io_end_t;
 
 /*
  * Special inodes numbers
@@ -347,7 +363,16 @@ struct ext4_new_group_data {
 	/* Call ext4_da_update_reserve_space() after successfully 
 	   allocating the blocks */
 #define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE	0x0008
-
+	/* caller is from the direct IO path, request to creation of an
+	unitialized extents if not allocated, split the uninitialized
+	extent if blocks has been preallocated already*/
+#define EXT4_GET_BLOCKS_DIO			0x0010
+#define EXT4_GET_BLOCKS_CONVERT			0x0020
+#define EXT4_GET_BLOCKS_DIO_CREATE_EXT		(EXT4_GET_BLOCKS_DIO|\
+					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+	/* Convert extent to initialized after direct IO complete */
+#define EXT4_GET_BLOCKS_DIO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
+					 EXT4_GET_BLOCKS_DIO_CREATE_EXT)
 
 /*
  * ioctl commands
@@ -500,8 +525,8 @@ struct move_extent {
 static inline __le32 ext4_encode_extra_time(struct timespec *time)
 {
        return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
-			   time->tv_sec >> 32 : 0) |
-			   ((time->tv_nsec << 2) & EXT4_NSEC_MASK));
+			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
+                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
 }
 
 static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
@@ -509,7 +534,7 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
        if (sizeof(time->tv_sec) > 4)
 	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
 			       << 32;
-       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> 2;
+       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
 }
 
 #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
@@ -672,6 +697,11 @@ struct ext4_inode_info {
 	__u16 i_extra_isize;
 
 	spinlock_t i_block_reservation_lock;
+
+	/* completed async DIOs that might need unwritten extents handling */
+	struct list_head i_aio_dio_complete_list;
+	/* current io_end structure for async DIO write*/
+	ext4_io_end_t *cur_aio_dio;
 };
 
 /*
@@ -942,18 +972,11 @@ struct ext4_sb_info {
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
+	unsigned int s_max_writeback_mb_bump;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
 
-	/* history to debug policy */
-	struct ext4_mb_history *s_mb_history;
-	int s_mb_history_cur;
-	int s_mb_history_max;
-	int s_mb_history_num;
-	spinlock_t s_mb_history_lock;
-	int s_mb_history_filter;
-
 	/* stats for buddy allocator */
 	spinlock_t s_mb_pa_lock;
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
@@ -980,6 +1003,9 @@ struct ext4_sb_info {
 
 	unsigned int s_log_groups_per_flex;
 	struct flex_groups *s_flex_groups;
+
+	/* workqueue for dio unwritten */
+	struct workqueue_struct *dio_unwritten_wq;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1397,7 +1423,7 @@ extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
 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 int flush_aio_dio_completed_IO(struct inode *inode);
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1699,6 +1725,8 @@ extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
+extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
+			  loff_t len);
 extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
 			   sector_t block, unsigned int max_blocks,
 			   struct buffer_head *bh, int flags);

fs/ext4/ext4_extents.h

@@ -220,6 +220,11 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
 		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
 }
 
+static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
+{
+	ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
+}
+
 extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
 extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
@@ -235,7 +240,7 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
 				 struct ext4_ext_path *path,
 				 struct ext4_extent *);
 extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
-extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int);
 extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
 							ext_prepare_callback, void *);
 extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,

fs/ext4/ext4_jbd2.h

@@ -161,11 +161,13 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
 int __ext4_journal_stop(const char *where, handle_t *handle);
 
-#define EXT4_NOJOURNAL_HANDLE	((handle_t *) 0x1)
+#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
 
+/* Note:  Do not use this for NULL handles.  This is only to determine if
+ * a properly allocated handle is using a journal or not. */
 static inline int ext4_handle_valid(handle_t *handle)
 {
-	if (handle == EXT4_NOJOURNAL_HANDLE)
+	if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
 		return 0;
 	return 1;
 }

fs/ext4/extents.c

@@ -723,7 +723,7 @@ err:
  * insert new index [@logical;@ptr] into the block at @curp;
  * check where to insert: before @curp or after @curp
  */
-static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
+int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
 				struct ext4_ext_path *curp,
 				int logical, ext4_fsblk_t ptr)
 {
@@ -1586,7 +1586,7 @@ out:
  */
 int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 				struct ext4_ext_path *path,
-				struct ext4_extent *newext)
+				struct ext4_extent *newext, int flag)
 {
 	struct ext4_extent_header *eh;
 	struct ext4_extent *ex, *fex;
@@ -1602,7 +1602,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	BUG_ON(path[depth].p_hdr == NULL);
 
 	/* try to insert block into found extent and return */
-	if (ex && ext4_can_extents_be_merged(inode, ex, newext)) {
+	if (ex && (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+		&& ext4_can_extents_be_merged(inode, ex, newext)) {
 		ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
 				ext4_ext_is_uninitialized(newext),
 				ext4_ext_get_actual_len(newext),
@@ -1722,7 +1723,8 @@ has_space:
 
 merge:
 	/* try to merge extents to the right */
-	ext4_ext_try_to_merge(inode, path, nearex);
+	if (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+		ext4_ext_try_to_merge(inode, path, nearex);
 
 	/* try to merge extents to the left */
 
@@ -2378,6 +2380,7 @@ void ext4_ext_init(struct super_block *sb)
 	 */
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
 		printk(KERN_INFO "EXT4-fs: file extents enabled");
 #ifdef AGGRESSIVE_TEST
 		printk(", aggressive tests");
@@ -2389,6 +2392,7 @@ void ext4_ext_init(struct super_block *sb)
 		printk(", stats");
 #endif
 		printk("\n");
+#endif
 #ifdef EXTENTS_STATS
 		spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
 		EXT4_SB(sb)->s_ext_min = 1 << 30;
@@ -2490,7 +2494,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 }
 
 #define EXT4_EXT_ZERO_LEN 7
-
 /*
  * This function is called by ext4_ext_get_blocks() if someone tries to write
  * to an uninitialized extent. It may result in splitting the uninitialized
@@ -2583,7 +2586,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 			ex3->ee_block = cpu_to_le32(iblock);
 			ext4_ext_store_pblock(ex3, newblock);
 			ex3->ee_len = cpu_to_le16(allocated);
-			err = ext4_ext_insert_extent(handle, inode, path, ex3);
+			err = ext4_ext_insert_extent(handle, inode, path,
+							ex3, 0);
 			if (err == -ENOSPC) {
 				err =  ext4_ext_zeroout(inode, &orig_ex);
 				if (err)
@@ -2639,7 +2643,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		ext4_ext_store_pblock(ex3, newblock + max_blocks);
 		ex3->ee_len = cpu_to_le16(allocated - max_blocks);
 		ext4_ext_mark_uninitialized(ex3);
-		err = ext4_ext_insert_extent(handle, inode, path, ex3);
+		err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
 		if (err == -ENOSPC) {
 			err =  ext4_ext_zeroout(inode, &orig_ex);
 			if (err)
@@ -2757,7 +2761,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	err = ext4_ext_dirty(handle, inode, path + depth);
 	goto out;
 insert:
-	err = ext4_ext_insert_extent(handle, inode, path, &newex);
+	err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
 	if (err == -ENOSPC) {
 		err =  ext4_ext_zeroout(inode, &orig_ex);
 		if (err)
@@ -2784,6 +2788,324 @@ fix_extent_len:
 	return err;
 }
 
+/*
+ * This function is called by ext4_ext_get_blocks() from
+ * ext4_get_blocks_dio_write() when DIO to write
+ * to an uninitialized extent.
+ *
+ * Writing to an uninitized extent may result in splitting the uninitialized
+ * extent into multiple /intialized unintialized extents (up to three)
+ * There are three possibilities:
+ *   a> There is no split required: Entire extent should be uninitialized
+ *   b> Splits in two extents: Write is happening at either end of the extent
+ *   c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * One of more index blocks maybe needed if the extent tree grow after
+ * the unintialized extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the uninitialized extent before DIO submit
+ * the IO. The uninitilized extent called at this time will be split
+ * into three uninitialized extent(at most). After IO complete, the part
+ * being filled will be convert to initialized by the end_io callback function
+ * via ext4_convert_unwritten_extents().
+ */
+static int ext4_split_unwritten_extents(handle_t *handle,
+					struct inode *inode,
+					struct ext4_ext_path *path,
+					ext4_lblk_t iblock,
+					unsigned int max_blocks,
+					int flags)
+{
+	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;
+	ext4_lblk_t ee_block;
+	unsigned int allocated, ee_len, depth;
+	ext4_fsblk_t newblock;
+	int err = 0;
+	int ret = 0;
+
+	ext_debug("ext4_split_unwritten_extents: inode %lu,"
+		  "iblock %llu, max_blocks %u\n", inode->i_ino,
+		  (unsigned long long)iblock, max_blocks);
+	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 - (iblock - ee_block);
+	newblock = iblock - ee_block + 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, ext_pblock(ex));
+
+	/*
+ 	 * if the entire unintialized extent length less than
+ 	 * the size of extent to write, there is no need to split
+ 	 * uninitialized extent
+ 	 */
+ 	if (allocated <= max_blocks)
+		return ret;
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+	/* ex1: ee_block to iblock - 1 : uninitialized */
+	if (iblock > ee_block) {
+		ex1 = ex;
+		ex1->ee_len = cpu_to_le16(iblock - 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 > max_blocks)
+		ex2->ee_len = cpu_to_le16(max_blocks);
+	/* ex3: to ee_block + ee_len : uninitialised */
+	if (allocated > max_blocks) {
+		unsigned int newdepth;
+		ex3 = &newex;
+		ex3->ee_block = cpu_to_le32(iblock + max_blocks);
+		ext4_ext_store_pblock(ex3, newblock + max_blocks);
+		ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+		ext4_ext_mark_uninitialized(ex3);
+		err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
+		if (err == -ENOSPC) {
+			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, ext_pblock(&orig_ex));
+			ext4_ext_dirty(handle, inode, path + depth);
+			/* zeroed the full extent */
+			/* blocks available from iblock */
+			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
+		 */
+		orig_ex.ee_len = cpu_to_le16(ee_len -
+						ext4_ext_get_actual_len(ex3));
+		depth = newdepth;
+		ext4_ext_drop_refs(path);
+		path = ext4_ext_find_extent(inode, iblock, path);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			goto out;
+		}
+		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 = max_blocks;
+	}
+	/*
+	 * 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(iblock - ee_block);
+		ext4_ext_mark_uninitialized(ex1);
+		ex2 = &newex;
+	}
+	/*
+	 * ex2: iblock to iblock + maxblocks-1 : to be direct IO written,
+	 * uninitialised still.
+	 */
+	ex2->ee_block = cpu_to_le32(iblock);
+	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) {
+		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, 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, ext_pblock(&orig_ex));
+	ext4_ext_mark_uninitialized(ex);
+	ext4_ext_dirty(handle, inode, path + depth);
+	return err;
+}
+static int ext4_convert_unwritten_extents_dio(handle_t *handle,
+					      struct inode *inode,
+					      struct ext4_ext_path *path)
+{
+	struct ext4_extent *ex;
+	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;
+
+	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.
+	 */
+	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);
+	}
+	/* Mark modified extent as dirty */
+	err = ext4_ext_dirty(handle, inode, path + depth);
+out:
+	ext4_ext_show_leaf(inode, path);
+	return err;
+}
+
+static int
+ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+			ext4_lblk_t iblock, unsigned int max_blocks,
+			struct ext4_ext_path *path, int flags,
+			unsigned int allocated, struct buffer_head *bh_result,
+			ext4_fsblk_t newblock)
+{
+	int ret = 0;
+	int err = 0;
+	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+
+	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
+		  "block %llu, max_blocks %u, flags %d, allocated %u",
+		  inode->i_ino, (unsigned long long)iblock, max_blocks,
+		  flags, allocated);
+	ext4_ext_show_leaf(inode, path);
+
+	/* DIO get_block() before submit the IO, split the extent */
+	if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+		ret = ext4_split_unwritten_extents(handle,
+						inode, path, iblock,
+						max_blocks, flags);
+		/* flag the io_end struct that we need convert when IO done */
+		if (io)
+			io->flag = DIO_AIO_UNWRITTEN;
+		goto out;
+	}
+	/* DIO end_io complete, convert the filled extent to written */
+	if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
+		ret = ext4_convert_unwritten_extents_dio(handle, inode,
+							path);
+		goto out2;
+	}
+	/* buffered IO case */
+	/*
+	 * repeat fallocate creation request
+	 * we already have an unwritten extent
+	 */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
+		goto map_out;
+
+	/* buffered READ or buffered write_begin() lookup */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		/*
+		 * We have blocks reserved already.  We
+		 * return allocated blocks so that delalloc
+		 * won't do block reservation for us.  But
+		 * the buffer head will be unmapped so that
+		 * a read from the block returns 0s.
+		 */
+		set_buffer_unwritten(bh_result);
+		goto out1;
+	}
+
+	/* buffered write, writepage time, convert*/
+	ret = ext4_ext_convert_to_initialized(handle, inode,
+						path, iblock,
+						max_blocks);
+out:
+	if (ret <= 0) {
+		err = ret;
+		goto out2;
+	} else
+		allocated = ret;
+	set_buffer_new(bh_result);
+map_out:
+	set_buffer_mapped(bh_result);
+out1:
+	if (allocated > max_blocks)
+		allocated = max_blocks;
+	ext4_ext_show_leaf(inode, path);
+	bh_result->b_bdev = inode->i_sb->s_bdev;
+	bh_result->b_blocknr = newblock;
+out2:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+	return err ? err : allocated;
+}
 /*
  * Block allocation/map/preallocation routine for extents based files
  *
@@ -2814,6 +3136,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	int err = 0, depth, ret, cache_type;
 	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
+	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
 
 	__clear_bit(BH_New, &bh_result->b_state);
 	ext_debug("blocks %u/%u requested for inode %lu\n",
@@ -2889,33 +3212,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 							EXT4_EXT_CACHE_EXTENT);
 				goto out;
 			}
-			if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
-				goto out;
-			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
-				if (allocated > max_blocks)
-					allocated = max_blocks;
-				/*
-				 * We have blocks reserved already.  We
-				 * return allocated blocks so that delalloc
-				 * won't do block reservation for us.  But
-				 * the buffer head will be unmapped so that
-				 * a read from the block returns 0s.
-				 */
-				set_buffer_unwritten(bh_result);
-				bh_result->b_bdev = inode->i_sb->s_bdev;
-				bh_result->b_blocknr = newblock;
-				goto out2;
-			}
-
-			ret = ext4_ext_convert_to_initialized(handle, inode,
-								path, iblock,
-								max_blocks);
-			if (ret <= 0) {
-				err = ret;
-				goto out2;
-			} else
-				allocated = ret;
-			goto outnew;
+			ret = ext4_ext_handle_uninitialized_extents(handle,
+					inode, iblock, max_blocks, path,
+					flags, allocated, bh_result, newblock);
+			return ret;
 		}
 	}
 
@@ -2986,9 +3286,21 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
 	newex.ee_len = cpu_to_le16(ar.len);
-	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)  /* Mark uninitialized */
+	/* Mark uninitialized */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
 		ext4_ext_mark_uninitialized(&newex);
-	err = ext4_ext_insert_extent(handle, inode, path, &newex);
+		/*
+		 * io_end structure was created for every async
+		 * direct IO write to the middle of the file.
+		 * To avoid unecessary convertion for every aio dio rewrite
+		 * to the mid of file, here we flag the IO that is really
+		 * need the convertion.
+		 *
+		 */
+		if (io && flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+			io->flag = DIO_AIO_UNWRITTEN;
+	}
+	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err) {
 		/* free data blocks we just allocated */
 		/* not a good idea to call discard here directly,
@@ -3002,7 +3314,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	/* previous routine could use block we allocated */
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
-outnew:
 	set_buffer_new(bh_result);
 
 	/* Cache only when it is _not_ an uninitialized extent */
@@ -3200,6 +3511,63 @@ retry:
 	return ret > 0 ? ret2 : ret;
 }
 
+/*
+ * This function convert a range of blocks to written extents
+ * The caller of this function will pass the start offset and the size.
+ * all unwritten extents within this range will be converted to
+ * written extents.
+ *
+ * This function is called from the direct IO end io call back
+ * function, to convert the fallocated extents after IO is completed.
+ */
+int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
+				    loff_t len)
+{
+	handle_t *handle;
+	ext4_lblk_t block;
+	unsigned int max_blocks;
+	int ret = 0;
+	int ret2 = 0;
+	struct buffer_head map_bh;
+	unsigned int credits, blkbits = inode->i_blkbits;
+
+	block = offset >> blkbits;
+	/*
+	 * We can't just convert len to max_blocks because
+	 * If blocksize = 4096 offset = 3072 and len = 2048
+	 */
+	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
+							- block;
+	/*
+	 * credits to insert 1 extent into extent tree
+	 */
+	credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	while (ret >= 0 && ret < max_blocks) {
+		block = block + ret;
+		max_blocks = max_blocks - ret;
+		handle = ext4_journal_start(inode, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			break;
+		}
+		map_bh.b_state = 0;
+		ret = ext4_get_blocks(handle, inode, block,
+				      max_blocks, &map_bh,
+				      EXT4_GET_BLOCKS_DIO_CONVERT_EXT);
+		if (ret <= 0) {
+			WARN_ON(ret <= 0);
+			printk(KERN_ERR "%s: ext4_ext_get_blocks "
+				    "returned error inode#%lu, block=%u, "
+				    "max_blocks=%u", __func__,
+				    inode->i_ino, block, max_blocks);
+		}
+		ext4_mark_inode_dirty(handle, inode);
+		ret2 = ext4_journal_stop(handle);
+		if (ret <= 0 || ret2 )
+			break;
+	}
+	return ret > 0 ? ret2 : ret;
+}
 /*
  * Callback function called for each extent to gather FIEMAP information.
  */

fs/ext4/fsync.c

@@ -44,6 +44,8 @@
  *
  * What we do is just kick off a commit and wait on it.  This will snapshot the
  * inode to disk.
+ *
+ * i_mutex lock is held when entering and exiting this function
  */
 
 int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
@@ -56,6 +58,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 
 	trace_ext4_sync_file(file, dentry, datasync);
 
+	ret = flush_aio_dio_completed_IO(inode);
+	if (ret < 0)
+		goto out;
 	/*
 	 * data=writeback:
 	 *  The caller's filemap_fdatawrite()/wait will sync the data.

fs/ext4/inode.c

@@ -37,6 +37,7 @@
 #include <linux/namei.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+#include <linux/workqueue.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -1144,6 +1145,64 @@ static int check_block_validity(struct inode *inode, const char *msg,
 	return 0;
 }
 
+/*
+ * Return the number of dirty pages in the given inode starting at
+ * page frame idx.
+ */
+static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
+				    unsigned int max_pages)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t	index;
+	struct pagevec pvec;
+	pgoff_t num = 0;
+	int i, nr_pages, done = 0;
+
+	if (max_pages == 0)
+		return 0;
+	pagevec_init(&pvec, 0);
+	while (!done) {
+		index = idx;
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					      PAGECACHE_TAG_DIRTY,
+					      (pgoff_t)PAGEVEC_SIZE);
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			struct buffer_head *bh, *head;
+
+			lock_page(page);
+			if (unlikely(page->mapping != mapping) ||
+			    !PageDirty(page) ||
+			    PageWriteback(page) ||
+			    page->index != idx) {
+				done = 1;
+				unlock_page(page);
+				break;
+			}
+			head = page_buffers(page);
+			bh = head;
+			do {
+				if (!buffer_delay(bh) &&
+				    !buffer_unwritten(bh)) {
+					done = 1;
+					break;
+				}
+			} while ((bh = bh->b_this_page) != head);
+			unlock_page(page);
+			if (done)
+				break;
+			idx++;
+			num++;
+			if (num >= max_pages)
+				break;
+		}
+		pagevec_release(&pvec);
+	}
+	return num;
+}
+
 /*
  * The ext4_get_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -1175,6 +1234,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 	clear_buffer_mapped(bh);
 	clear_buffer_unwritten(bh);
 
+	ext_debug("ext4_get_blocks(): inode %lu, flag %d, max_blocks %u,"
+		  "logical block %lu\n", inode->i_ino, flags, max_blocks,
+		  (unsigned long)block);
 	/*
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
@@ -1796,11 +1858,11 @@ repeat:
 
 	if (ext4_claim_free_blocks(sbi, total)) {
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+		vfs_dq_release_reservation_block(inode, total);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
 			goto repeat;
 		}
-		vfs_dq_release_reservation_block(inode, total);
 		return -ENOSPC;
 	}
 	EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
@@ -2092,18 +2154,18 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
 static void ext4_print_free_blocks(struct inode *inode)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	printk(KERN_EMERG "Total free blocks count %lld\n",
-			ext4_count_free_blocks(inode->i_sb));
-	printk(KERN_EMERG "Free/Dirty block details\n");
-	printk(KERN_EMERG "free_blocks=%lld\n",
-			(long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
-	printk(KERN_EMERG "dirty_blocks=%lld\n",
-			(long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
-	printk(KERN_EMERG "Block reservation details\n");
-	printk(KERN_EMERG "i_reserved_data_blocks=%u\n",
-			EXT4_I(inode)->i_reserved_data_blocks);
-	printk(KERN_EMERG "i_reserved_meta_blocks=%u\n",
-			EXT4_I(inode)->i_reserved_meta_blocks);
+	printk(KERN_CRIT "Total free blocks count %lld\n",
+	       ext4_count_free_blocks(inode->i_sb));
+	printk(KERN_CRIT "Free/Dirty block details\n");
+	printk(KERN_CRIT "free_blocks=%lld\n",
+	       (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+	printk(KERN_CRIT "dirty_blocks=%lld\n",
+	       (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+	printk(KERN_CRIT "Block reservation details\n");
+	printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
+	       EXT4_I(inode)->i_reserved_data_blocks);
+	printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
+	       EXT4_I(inode)->i_reserved_meta_blocks);
 	return;
 }
 
@@ -2189,14 +2251,14 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 		 * writepage and writepages will again try to write
 		 * the same.
 		 */
-		printk(KERN_EMERG "%s block allocation failed for inode %lu "
-				  "at logical offset %llu with max blocks "
-				  "%zd with error %d\n",
-				  __func__, mpd->inode->i_ino,
-				  (unsigned long long)next,
-				  mpd->b_size >> mpd->inode->i_blkbits, err);
-		printk(KERN_EMERG "This should not happen.!! "
-					"Data will be lost\n");
+		ext4_msg(mpd->inode->i_sb, KERN_CRIT,
+			 "delayed block allocation failed for inode %lu at "
+			 "logical offset %llu with max blocks %zd with "
+			 "error %d\n", mpd->inode->i_ino,
+			 (unsigned long long) next,
+			 mpd->b_size >> mpd->inode->i_blkbits, err);
+		printk(KERN_CRIT "This should not happen!!  "
+		       "Data will be lost\n");
 		if (err == -ENOSPC) {
 			ext4_print_free_blocks(mpd->inode);
 		}
@@ -2743,8 +2805,10 @@ static int ext4_da_writepages(struct address_space *mapping,
 	int no_nrwrite_index_update;
 	int pages_written = 0;
 	long pages_skipped;
+	unsigned int max_pages;
 	int range_cyclic, cycled = 1, io_done = 0;
-	int needed_blocks, ret = 0, nr_to_writebump = 0;
+	int needed_blocks, ret = 0;
+	long desired_nr_to_write, nr_to_writebump = 0;
 	loff_t range_start = wbc->range_start;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
@@ -2771,16 +2835,6 @@ static int ext4_da_writepages(struct address_space *mapping,
 	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
 		return -EROFS;
 
-	/*
-	 * Make sure nr_to_write is >= sbi->s_mb_stream_request
-	 * This make sure small files blocks are allocated in
-	 * single attempt. This ensure that small files
-	 * get less fragmented.
-	 */
-	if (wbc->nr_to_write < sbi->s_mb_stream_request) {
-		nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
-		wbc->nr_to_write = sbi->s_mb_stream_request;
-	}
 	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 		range_whole = 1;
 
@@ -2795,6 +2849,36 @@ static int ext4_da_writepages(struct address_space *mapping,
 	} else
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
+	/*
+	 * This works around two forms of stupidity.  The first is in
+	 * the writeback code, which caps the maximum number of pages
+	 * written to be 1024 pages.  This is wrong on multiple
+	 * levels; different architectues have a different page size,
+	 * which changes the maximum amount of data which gets
+	 * written.  Secondly, 4 megabytes is way too small.  XFS
+	 * forces this value to be 16 megabytes by multiplying
+	 * nr_to_write parameter by four, and then relies on its
+	 * allocator to allocate larger extents to make them
+	 * contiguous.  Unfortunately this brings us to the second
+	 * stupidity, which is that ext4's mballoc code only allocates
+	 * at most 2048 blocks.  So we force contiguous writes up to
+	 * the number of dirty blocks in the inode, or
+	 * sbi->max_writeback_mb_bump whichever is smaller.
+	 */
+	max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
+	if (!range_cyclic && range_whole)
+		desired_nr_to_write = wbc->nr_to_write * 8;
+	else
+		desired_nr_to_write = ext4_num_dirty_pages(inode, index,
+							   max_pages);
+	if (desired_nr_to_write > max_pages)
+		desired_nr_to_write = max_pages;
+
+	if (wbc->nr_to_write < desired_nr_to_write) {
+		nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
+		wbc->nr_to_write = desired_nr_to_write;
+	}
+
 	mpd.wbc = wbc;
 	mpd.inode = mapping->host;
 
@@ -2822,10 +2906,9 @@ retry:
 		handle = ext4_journal_start(inode, needed_blocks);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
-			printk(KERN_CRIT "%s: jbd2_start: "
+			ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
 			       "%ld pages, ino %lu; err %d\n", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
-			dump_stack();
 			goto out_writepages;
 		}
 
@@ -2897,9 +2980,10 @@ retry:
 		goto retry;
 	}
 	if (pages_skipped != wbc->pages_skipped)
-		printk(KERN_EMERG "This should not happen leaving %s "
-				"with nr_to_write = %ld ret = %d\n",
-				__func__, wbc->nr_to_write, ret);
+		ext4_msg(inode->i_sb, KERN_CRIT,
+			 "This should not happen leaving %s "
+			 "with nr_to_write = %ld ret = %d\n",
+			 __func__, wbc->nr_to_write, ret);
 
 	/* Update index */
 	index += pages_written;
@@ -2914,7 +2998,8 @@ retry:
 out_writepages:
 	if (!no_nrwrite_index_update)
 		wbc->no_nrwrite_index_update = 0;
-	wbc->nr_to_write -= nr_to_writebump;
+	if (wbc->nr_to_write > nr_to_writebump)
+		wbc->nr_to_write -= nr_to_writebump;
 	wbc->range_start = range_start;
 	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
 	return ret;
@@ -3272,6 +3357,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 }
 
 /*
+ * O_DIRECT for ext3 (or indirect map) based files
+ *
  * If the O_DIRECT write will extend the file then add this inode to the
  * orphan list.  So recovery will truncate it back to the original size
  * if the machine crashes during the write.
@@ -3280,7 +3367,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
  * crashes then stale disk data _may_ be exposed inside the file. But current
  * VFS code falls back into buffered path in that case so we are safe.
  */
-static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
+static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 			      const struct iovec *iov, loff_t offset,
 			      unsigned long nr_segs)
 {
@@ -3354,6 +3441,359 @@ out:
 	return ret;
 }
 
+/* Maximum number of blocks we map for direct IO at once. */
+
+static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
+{
+	handle_t *handle = NULL;
+	int ret = 0;
+	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int dio_credits;
+
+	ext4_debug("ext4_get_block_dio_write: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	/*
+	 * DIO VFS code passes create = 0 flag for write to
+	 * the middle of file. It does this to avoid block
+	 * allocation for holes, to prevent expose stale data
+	 * out when there is parallel buffered read (which does
+	 * not hold the i_mutex lock) while direct IO write has
+	 * not completed. DIO request on holes finally falls back
+	 * to buffered IO for this reason.
+	 *
+	 * For ext4 extent based file, since we support fallocate,
+	 * new allocated extent as uninitialized, for holes, we
+	 * could fallocate blocks for holes, thus parallel
+	 * buffered IO read will zero out the page when read on
+	 * a hole while parallel DIO write to the hole has not completed.
+	 *
+	 * when we come here, we know it's a direct IO write to
+	 * to the middle of file (<i_size)
+	 * so it's safe to override the create flag from VFS.
+	 */
+	create = EXT4_GET_BLOCKS_DIO_CREATE_EXT;
+
+	if (max_blocks > DIO_MAX_BLOCKS)
+		max_blocks = DIO_MAX_BLOCKS;
+	dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	handle = ext4_journal_start(inode, dio_credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+	ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
+			      create);
+	if (ret > 0) {
+		bh_result->b_size = (ret << inode->i_blkbits);
+		ret = 0;
+	}
+	ext4_journal_stop(handle);
+out:
+	return ret;
+}
+
+static void ext4_free_io_end(ext4_io_end_t *io)
+{
+	BUG_ON(!io);
+	iput(io->inode);
+	kfree(io);
+}
+static void dump_aio_dio_list(struct inode * inode)
+{
+#ifdef	EXT4_DEBUG
+	struct list_head *cur, *before, *after;
+	ext4_io_end_t *io, *io0, *io1;
+
+	if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
+		ext4_debug("inode %lu aio dio list is empty\n", inode->i_ino);
+		return;
+	}
+
+	ext4_debug("Dump inode %lu aio_dio_completed_IO list \n", inode->i_ino);
+	list_for_each_entry(io, &EXT4_I(inode)->i_aio_dio_complete_list, list){
+		cur = &io->list;
+		before = cur->prev;
+		io0 = container_of(before, ext4_io_end_t, list);
+		after = cur->next;
+		io1 = container_of(after, ext4_io_end_t, list);
+
+		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+			    io, inode->i_ino, io0, io1);
+	}
+#endif
+}
+
+/*
+ * check a range of space and convert unwritten extents to written.
+ */
+static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
+{
+	struct inode *inode = io->inode;
+	loff_t offset = io->offset;
+	size_t size = io->size;
+	int ret = 0;
+
+	ext4_debug("end_aio_dio_onlock: io 0x%p from inode %lu,list->next 0x%p,"
+		   "list->prev 0x%p\n",
+	           io, inode->i_ino, io->list.next, io->list.prev);
+
+	if (list_empty(&io->list))
+		return ret;
+
+	if (io->flag != DIO_AIO_UNWRITTEN)
+		return ret;
+
+	if (offset + size <= i_size_read(inode))
+		ret = ext4_convert_unwritten_extents(inode, offset, size);
+
+	if (ret < 0) {
+		printk(KERN_EMERG "%s: failed to convert unwritten"
+			"extents to written extents, error is %d"
+			" io is still on inode %lu aio dio list\n",
+                       __func__, ret, inode->i_ino);
+		return ret;
+	}
+
+	/* clear the DIO AIO unwritten flag */
+	io->flag = 0;
+	return ret;
+}
+/*
+ * work on completed aio dio IO, to convert unwritten extents to extents
+ */
+static void ext4_end_aio_dio_work(struct work_struct *work)
+{
+	ext4_io_end_t *io  = container_of(work, ext4_io_end_t, work);
+	struct inode *inode = io->inode;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+	ret = ext4_end_aio_dio_nolock(io);
+	if (ret >= 0) {
+		if (!list_empty(&io->list))
+			list_del_init(&io->list);
+		ext4_free_io_end(io);
+	}
+	mutex_unlock(&inode->i_mutex);
+}
+/*
+ * This function is called from ext4_sync_file().
+ *
+ * When AIO DIO IO is completed, the work to convert unwritten
+ * extents to written is queued on workqueue but may not get immediately
+ * scheduled. When fsync is called, we need to ensure the
+ * conversion is complete before fsync returns.
+ * The inode keeps track of a list of completed AIO from DIO path
+ * that might needs to do the conversion. This function walks through
+ * the list and convert the related unwritten extents to written.
+ */
+int flush_aio_dio_completed_IO(struct inode *inode)
+{
+	ext4_io_end_t *io;
+	int ret = 0;
+	int ret2 = 0;
+
+	if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list))
+		return ret;
+
+	dump_aio_dio_list(inode);
+	while (!list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
+		io = list_entry(EXT4_I(inode)->i_aio_dio_complete_list.next,
+				ext4_io_end_t, list);
+		/*
+		 * Calling ext4_end_aio_dio_nolock() to convert completed
+		 * IO to written.
+		 *
+		 * When ext4_sync_file() is called, run_queue() may already
+		 * about to flush the work corresponding to this io structure.
+		 * It will be upset if it founds the io structure related
+		 * to the work-to-be schedule is freed.
+		 *
+		 * Thus we need to keep the io structure still valid here after
+		 * convertion finished. The io structure has a flag to
+		 * avoid double converting from both fsync and background work
+		 * queue work.
+		 */
+		ret = ext4_end_aio_dio_nolock(io);
+		if (ret < 0)
+			ret2 = ret;
+		else
+			list_del_init(&io->list);
+	}
+	return (ret2 < 0) ? ret2 : 0;
+}
+
+static ext4_io_end_t *ext4_init_io_end (struct inode *inode)
+{
+	ext4_io_end_t *io = NULL;
+
+	io = kmalloc(sizeof(*io), GFP_NOFS);
+
+	if (io) {
+		igrab(inode);
+		io->inode = inode;
+		io->flag = 0;
+		io->offset = 0;
+		io->size = 0;
+		io->error = 0;
+		INIT_WORK(&io->work, ext4_end_aio_dio_work);
+		INIT_LIST_HEAD(&io->list);
+	}
+
+	return io;
+}
+
+static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+			    ssize_t size, void *private)
+{
+        ext4_io_end_t *io_end = iocb->private;
+	struct workqueue_struct *wq;
+
+	ext_debug("ext4_end_io_dio(): io_end 0x%p"
+		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
+ 		  iocb->private, io_end->inode->i_ino, iocb, offset,
+		  size);
+	/* if not async direct IO or dio with 0 bytes write, just return */
+	if (!io_end || !size)
+		return;
+
+	/* if not aio dio with unwritten extents, just free io and return */
+	if (io_end->flag != DIO_AIO_UNWRITTEN){
+		ext4_free_io_end(io_end);
+		iocb->private = NULL;
+		return;
+	}
+
+	io_end->offset = offset;
+	io_end->size = size;
+	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
+
+	/* queue the work to convert unwritten extents to written */
+	queue_work(wq, &io_end->work);
+
+	/* Add the io_end to per-inode completed aio dio list*/
+	list_add_tail(&io_end->list,
+		 &EXT4_I(io_end->inode)->i_aio_dio_complete_list);
+	iocb->private = NULL;
+}
+/*
+ * For ext4 extent files, ext4 will do direct-io write to holes,
+ * preallocated extents, and those write extend the file, no need to
+ * fall back to buffered IO.
+ *
+ * For holes, we fallocate those blocks, mark them as unintialized
+ * If those blocks were preallocated, we mark sure they are splited, but
+ * still keep the range to write as unintialized.
+ *
+ * The unwrritten extents will be converted to written when DIO is completed.
+ * For async direct IO, since the IO may still pending when return, we
+ * set up an end_io call back function, which will do the convertion
+ * when async direct IO completed.
+ *
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list.  So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ */
+static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+	size_t count = iov_length(iov, nr_segs);
+
+	loff_t final_size = offset + count;
+	if (rw == WRITE && final_size <= inode->i_size) {
+		/*
+ 		 * We could direct write to holes and fallocate.
+		 *
+ 		 * Allocated blocks to fill the hole are marked as uninitialized
+ 		 * to prevent paralel buffered read to expose the stale data
+ 		 * before DIO complete the data IO.
+		 *
+ 		 * As to previously fallocated extents, ext4 get_block
+ 		 * will just simply mark the buffer mapped but still
+ 		 * keep the extents uninitialized.
+ 		 *
+		 * for non AIO case, we will convert those unwritten extents
+		 * to written after return back from blockdev_direct_IO.
+		 *
+		 * for async DIO, the conversion needs to be defered when
+		 * the IO is completed. The ext4 end_io callback function
+		 * will be called to take care of the conversion work.
+		 * Here for async case, we allocate an io_end structure to
+		 * hook to the iocb.
+ 		 */
+		iocb->private = NULL;
+		EXT4_I(inode)->cur_aio_dio = NULL;
+		if (!is_sync_kiocb(iocb)) {
+			iocb->private = ext4_init_io_end(inode);
+			if (!iocb->private)
+				return -ENOMEM;
+			/*
+			 * we save the io structure for current async
+			 * direct IO, so that later ext4_get_blocks()
+			 * could flag the io structure whether there
+			 * is a unwritten extents needs to be converted
+			 * when IO is completed.
+			 */
+			EXT4_I(inode)->cur_aio_dio = iocb->private;
+		}
+
+		ret = blockdev_direct_IO(rw, iocb, inode,
+					 inode->i_sb->s_bdev, iov,
+					 offset, nr_segs,
+					 ext4_get_block_dio_write,
+					 ext4_end_io_dio);
+		if (iocb->private)
+			EXT4_I(inode)->cur_aio_dio = NULL;
+		/*
+		 * The io_end structure takes a reference to the inode,
+		 * that structure needs to be destroyed and the
+		 * reference to the inode need to be dropped, when IO is
+		 * complete, even with 0 byte write, or failed.
+		 *
+		 * In the successful AIO DIO case, the io_end structure will be
+		 * desctroyed and the reference to the inode will be dropped
+		 * after the end_io call back function is called.
+		 *
+		 * In the case there is 0 byte write, or error case, since
+		 * VFS direct IO won't invoke the end_io call back function,
+		 * we need to free the end_io structure here.
+		 */
+		if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+			ext4_free_io_end(iocb->private);
+			iocb->private = NULL;
+		} else if (ret > 0)
+			/*
+			 * for non AIO case, since the IO is already
+			 * completed, we could do the convertion right here
+			 */
+			ret = ext4_convert_unwritten_extents(inode,
+								offset, ret);
+		return ret;
+	}
+
+	/* for write the the end of file case, we fall back to old way */
+	return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+}
+
+static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+
+	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+		return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+
+	return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+}
+
 /*
  * Pages can be marked dirty completely asynchronously from ext4's journalling
  * activity.  By filemap_sync_pte(), try_to_unmap_one(), etc.  We cannot do
@@ -4551,8 +4991,7 @@ static int ext4_inode_blocks_set(handle_t *handle,
  */
 static int ext4_do_update_inode(handle_t *handle,
 				struct inode *inode,
-				struct ext4_iloc *iloc,
-				int do_sync)
+				struct ext4_iloc *iloc)
 {
 	struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -4653,22 +5092,10 @@ static int ext4_do_update_inode(handle_t *handle,
 		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
 	}
 
-	/*
-	 * If we're not using a journal and we were called from
-	 * ext4_write_inode() to sync the inode (making do_sync true),
-	 * we can just use sync_dirty_buffer() directly to do our dirty
-	 * work.  Testing s_journal here is a bit redundant but it's
-	 * worth it to avoid potential future trouble.
-	 */
-	if (EXT4_SB(inode->i_sb)->s_journal == NULL && do_sync) {
-		BUFFER_TRACE(bh, "call sync_dirty_buffer");
-		sync_dirty_buffer(bh);
-	} else {
-		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-		rc = ext4_handle_dirty_metadata(handle, inode, bh);
-		if (!err)
-			err = rc;
-	}
+	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+	rc = ext4_handle_dirty_metadata(handle, inode, bh);
+	if (!err)
+		err = rc;
 	ei->i_state &= ~EXT4_STATE_NEW;
 
 out_brelse:
@@ -4736,8 +5163,16 @@ int ext4_write_inode(struct inode *inode, int wait)
 		err = ext4_get_inode_loc(inode, &iloc);
 		if (err)
 			return err;
-		err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE,
-					   inode, &iloc, wait);
+		if (wait)
+			sync_dirty_buffer(iloc.bh);
+		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+			ext4_error(inode->i_sb, __func__,
+				   "IO error syncing inode, "
+				   "inode=%lu, block=%llu",
+				   inode->i_ino,
+				   (unsigned long long)iloc.bh->b_blocknr);
+			err = -EIO;
+		}
 	}
 	return err;
 }
@@ -5033,7 +5468,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 	get_bh(iloc->bh);
 
 	/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
-	err = ext4_do_update_inode(handle, inode, iloc, 0);
+	err = ext4_do_update_inode(handle, inode, iloc);
 	put_bh(iloc->bh);
 	return err;
 }
@@ -5180,24 +5615,13 @@ void ext4_dirty_inode(struct inode *inode)
 	handle_t *current_handle = ext4_journal_current_handle();
 	handle_t *handle;
 
-	if (!ext4_handle_valid(current_handle)) {
-		ext4_mark_inode_dirty(current_handle, inode);
-		return;
-	}
-
 	handle = ext4_journal_start(inode, 2);
 	if (IS_ERR(handle))
 		goto out;
-	if (current_handle &&
-		current_handle->h_transaction != handle->h_transaction) {
-		/* This task has a transaction open against a different fs */
-		printk(KERN_EMERG "%s: transactions do not match!\n",
-		       __func__);
-	} else {
-		jbd_debug(5, "marking dirty.  outer handle=%p\n",
-				current_handle);
-		ext4_mark_inode_dirty(handle, inode);
-	}
+
+	jbd_debug(5, "marking dirty.  outer handle=%p\n", current_handle);
+	ext4_mark_inode_dirty(handle, inode);
+
 	ext4_journal_stop(handle);
 out:
 	return;

fs/ext4/mballoc.c

@@ -2096,207 +2096,6 @@ out:
 	return err;
 }
 
-#ifdef EXT4_MB_HISTORY
-struct ext4_mb_proc_session {
-	struct ext4_mb_history *history;
-	struct super_block *sb;
-	int start;
-	int max;
-};
-
-static void *ext4_mb_history_skip_empty(struct ext4_mb_proc_session *s,
-					struct ext4_mb_history *hs,
-					int first)
-{
-	if (hs == s->history + s->max)
-		hs = s->history;
-	if (!first && hs == s->history + s->start)
-		return NULL;
-	while (hs->orig.fe_len == 0) {
-		hs++;
-		if (hs == s->history + s->max)
-			hs = s->history;
-		if (hs == s->history + s->start)
-			return NULL;
-	}
-	return hs;
-}
-
-static void *ext4_mb_seq_history_start(struct seq_file *seq, loff_t *pos)
-{
-	struct ext4_mb_proc_session *s = seq->private;
-	struct ext4_mb_history *hs;
-	int l = *pos;
-
-	if (l == 0)
-		return SEQ_START_TOKEN;
-	hs = ext4_mb_history_skip_empty(s, s->history + s->start, 1);
-	if (!hs)
-		return NULL;
-	while (--l && (hs = ext4_mb_history_skip_empty(s, ++hs, 0)) != NULL);
-	return hs;
-}
-
-static void *ext4_mb_seq_history_next(struct seq_file *seq, void *v,
-				      loff_t *pos)
-{
-	struct ext4_mb_proc_session *s = seq->private;
-	struct ext4_mb_history *hs = v;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN)
-		return ext4_mb_history_skip_empty(s, s->history + s->start, 1);
-	else
-		return ext4_mb_history_skip_empty(s, ++hs, 0);
-}
-
-static int ext4_mb_seq_history_show(struct seq_file *seq, void *v)
-{
-	char buf[25], buf2[25], buf3[25], *fmt;
-	struct ext4_mb_history *hs = v;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "%-5s %-8s %-23s %-23s %-23s %-5s "
-				"%-5s %-2s %-6s %-5s %-5s %-6s\n",
-			  "pid", "inode", "original", "goal", "result", "found",
-			   "grps", "cr", "flags", "merge", "tail", "broken");
-		return 0;
-	}
-
-	if (hs->op == EXT4_MB_HISTORY_ALLOC) {
-		fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u "
-			"0x%04x %-5s %-5u %-6u\n";
-		sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group,
-			hs->result.fe_start, hs->result.fe_len,
-			hs->result.fe_logical);
-		sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group,
-			hs->orig.fe_start, hs->orig.fe_len,
-			hs->orig.fe_logical);
-		sprintf(buf3, "%u/%d/%u@%u", hs->goal.fe_group,
-			hs->goal.fe_start, hs->goal.fe_len,
-			hs->goal.fe_logical);
-		seq_printf(seq, fmt, hs->pid, hs->ino, buf, buf3, buf2,
-				hs->found, hs->groups, hs->cr, hs->flags,
-				hs->merged ? "M" : "", hs->tail,
-				hs->buddy ? 1 << hs->buddy : 0);
-	} else if (hs->op == EXT4_MB_HISTORY_PREALLOC) {
-		fmt = "%-5u %-8u %-23s %-23s %-23s\n";
-		sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group,
-			hs->result.fe_start, hs->result.fe_len,
-			hs->result.fe_logical);
-		sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group,
-			hs->orig.fe_start, hs->orig.fe_len,
-			hs->orig.fe_logical);
-		seq_printf(seq, fmt, hs->pid, hs->ino, buf, "", buf2);
-	} else if (hs->op == EXT4_MB_HISTORY_DISCARD) {
-		sprintf(buf2, "%u/%d/%u", hs->result.fe_group,
-			hs->result.fe_start, hs->result.fe_len);
-		seq_printf(seq, "%-5u %-8u %-23s discard\n",
-				hs->pid, hs->ino, buf2);
-	} else if (hs->op == EXT4_MB_HISTORY_FREE) {
-		sprintf(buf2, "%u/%d/%u", hs->result.fe_group,
-			hs->result.fe_start, hs->result.fe_len);
-		seq_printf(seq, "%-5u %-8u %-23s free\n",
-				hs->pid, hs->ino, buf2);
-	}
-	return 0;
-}
-
-static void ext4_mb_seq_history_stop(struct seq_file *seq, void *v)
-{
-}
-
-static const struct seq_operations ext4_mb_seq_history_ops = {
-	.start  = ext4_mb_seq_history_start,
-	.next   = ext4_mb_seq_history_next,
-	.stop   = ext4_mb_seq_history_stop,
-	.show   = ext4_mb_seq_history_show,
-};
-
-static int ext4_mb_seq_history_open(struct inode *inode, struct file *file)
-{
-	struct super_block *sb = PDE(inode)->data;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_mb_proc_session *s;
-	int rc;
-	int size;
-
-	if (unlikely(sbi->s_mb_history == NULL))
-		return -ENOMEM;
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (s == NULL)
-		return -ENOMEM;
-	s->sb = sb;
-	size = sizeof(struct ext4_mb_history) * sbi->s_mb_history_max;
-	s->history = kmalloc(size, GFP_KERNEL);
-	if (s->history == NULL) {
-		kfree(s);
-		return -ENOMEM;
-	}
-
-	spin_lock(&sbi->s_mb_history_lock);
-	memcpy(s->history, sbi->s_mb_history, size);
-	s->max = sbi->s_mb_history_max;
-	s->start = sbi->s_mb_history_cur % s->max;
-	spin_unlock(&sbi->s_mb_history_lock);
-
-	rc = seq_open(file, &ext4_mb_seq_history_ops);
-	if (rc == 0) {
-		struct seq_file *m = (struct seq_file *)file->private_data;
-		m->private = s;
-	} else {
-		kfree(s->history);
-		kfree(s);
-	}
-	return rc;
-
-}
-
-static int ext4_mb_seq_history_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = (struct seq_file *)file->private_data;
-	struct ext4_mb_proc_session *s = seq->private;
-	kfree(s->history);
-	kfree(s);
-	return seq_release(inode, file);
-}
-
-static ssize_t ext4_mb_seq_history_write(struct file *file,
-				const char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	struct seq_file *seq = (struct seq_file *)file->private_data;
-	struct ext4_mb_proc_session *s = seq->private;
-	struct super_block *sb = s->sb;
-	char str[32];
-	int value;
-
-	if (count >= sizeof(str)) {
-		printk(KERN_ERR "EXT4-fs: %s string too long, max %u bytes\n",
-				"mb_history", (int)sizeof(str));
-		return -EOVERFLOW;
-	}
-
-	if (copy_from_user(str, buffer, count))
-		return -EFAULT;
-
-	value = simple_strtol(str, NULL, 0);
-	if (value < 0)
-		return -ERANGE;
-	EXT4_SB(sb)->s_mb_history_filter = value;
-
-	return count;
-}
-
-static const struct file_operations ext4_mb_seq_history_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ext4_mb_seq_history_open,
-	.read		= seq_read,
-	.write		= ext4_mb_seq_history_write,
-	.llseek		= seq_lseek,
-	.release	= ext4_mb_seq_history_release,
-};
-
 static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 {
 	struct super_block *sb = seq->private;
@@ -2396,82 +2195,6 @@ static const struct file_operations ext4_mb_seq_groups_fops = {
 	.release	= seq_release,
 };
 
-static void ext4_mb_history_release(struct super_block *sb)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	if (sbi->s_proc != NULL) {
-		remove_proc_entry("mb_groups", sbi->s_proc);
-		if (sbi->s_mb_history_max)
-			remove_proc_entry("mb_history", sbi->s_proc);
-	}
-	kfree(sbi->s_mb_history);
-}
-
-static void ext4_mb_history_init(struct super_block *sb)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int i;
-
-	if (sbi->s_proc != NULL) {
-		if (sbi->s_mb_history_max)
-			proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
-					 &ext4_mb_seq_history_fops, sb);
-		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
-				 &ext4_mb_seq_groups_fops, sb);
-	}
-
-	sbi->s_mb_history_cur = 0;
-	spin_lock_init(&sbi->s_mb_history_lock);
-	i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history);
-	sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL;
-	/* if we can't allocate history, then we simple won't use it */
-}
-
-static noinline_for_stack void
-ext4_mb_store_history(struct ext4_allocation_context *ac)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
-	struct ext4_mb_history h;
-
-	if (sbi->s_mb_history == NULL)
-		return;
-
-	if (!(ac->ac_op & sbi->s_mb_history_filter))
-		return;
-
-	h.op = ac->ac_op;
-	h.pid = current->pid;
-	h.ino = ac->ac_inode ? ac->ac_inode->i_ino : 0;
-	h.orig = ac->ac_o_ex;
-	h.result = ac->ac_b_ex;
-	h.flags = ac->ac_flags;
-	h.found = ac->ac_found;
-	h.groups = ac->ac_groups_scanned;
-	h.cr = ac->ac_criteria;
-	h.tail = ac->ac_tail;
-	h.buddy = ac->ac_buddy;
-	h.merged = 0;
-	if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) {
-		if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start &&
-				ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group)
-			h.merged = 1;
-		h.goal = ac->ac_g_ex;
-		h.result = ac->ac_f_ex;
-	}
-
-	spin_lock(&sbi->s_mb_history_lock);
-	memcpy(sbi->s_mb_history + sbi->s_mb_history_cur, &h, sizeof(h));
-	if (++sbi->s_mb_history_cur >= sbi->s_mb_history_max)
-		sbi->s_mb_history_cur = 0;
-	spin_unlock(&sbi->s_mb_history_lock);
-}
-
-#else
-#define ext4_mb_history_release(sb)
-#define ext4_mb_history_init(sb)
-#endif
-
 
 /* Create and initialize ext4_group_info data for the given group. */
 int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
@@ -2690,7 +2413,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	sbi->s_mb_stats = MB_DEFAULT_STATS;
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
-	sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT;
 	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
 
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
@@ -2708,12 +2430,12 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 		spin_lock_init(&lg->lg_prealloc_lock);
 	}
 
-	ext4_mb_history_init(sb);
+	if (sbi->s_proc)
+		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
+				 &ext4_mb_seq_groups_fops, sb);
 
 	if (sbi->s_journal)
 		sbi->s_journal->j_commit_callback = release_blocks_on_commit;
-
-	printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
 	return 0;
 }
 
@@ -2790,7 +2512,8 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-	ext4_mb_history_release(sb);
+	if (sbi->s_proc)
+		remove_proc_entry("mb_groups", sbi->s_proc);
 
 	return 0;
 }
@@ -3276,7 +2999,10 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
 			atomic_inc(&sbi->s_bal_breaks);
 	}
 
-	ext4_mb_store_history(ac);
+	if (ac->ac_op == EXT4_MB_HISTORY_ALLOC)
+		trace_ext4_mballoc_alloc(ac);
+	else
+		trace_ext4_mballoc_prealloc(ac);
 }
 
 /*
@@ -3776,7 +3502,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	if (ac) {
 		ac->ac_sb = sb;
 		ac->ac_inode = pa->pa_inode;
-		ac->ac_op = EXT4_MB_HISTORY_DISCARD;
 	}
 
 	while (bit < end) {
@@ -3796,7 +3521,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			ac->ac_b_ex.fe_start = bit;
 			ac->ac_b_ex.fe_len = next - bit;
 			ac->ac_b_ex.fe_logical = 0;
-			ext4_mb_store_history(ac);
+			trace_ext4_mballoc_discard(ac);
 		}
 
 		trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit,
@@ -3831,9 +3556,6 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 
-	if (ac)
-		ac->ac_op = EXT4_MB_HISTORY_DISCARD;
-
 	trace_ext4_mb_release_group_pa(ac, pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
@@ -3848,7 +3570,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 		ac->ac_b_ex.fe_start = bit;
 		ac->ac_b_ex.fe_len = pa->pa_len;
 		ac->ac_b_ex.fe_logical = 0;
-		ext4_mb_store_history(ac);
+		trace_ext4_mballoc_discard(ac);
 	}
 
 	return 0;
@@ -4189,7 +3911,6 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
 		>> bsbits;
-	size = max(size, isize);
 
 	if ((size == isize) &&
 	    !ext4_fs_is_busy(sbi) &&
@@ -4199,6 +3920,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	}
 
 	/* don't use group allocation for large files */
+	size = max(size, isize);
 	if (size >= sbi->s_mb_stream_request) {
 		ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
 		return;
@@ -4739,7 +4461,6 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 	if (ac) {
-		ac->ac_op = EXT4_MB_HISTORY_FREE;
 		ac->ac_inode = inode;
 		ac->ac_sb = sb;
 	}
@@ -4806,7 +4527,7 @@ do_more:
 		ac->ac_b_ex.fe_group = block_group;
 		ac->ac_b_ex.fe_start = bit;
 		ac->ac_b_ex.fe_len = count;
-		ext4_mb_store_history(ac);
+		trace_ext4_mballoc_free(ac);
 	}
 
 	err = ext4_mb_load_buddy(sb, block_group, &e4b);

fs/ext4/mballoc.h

@@ -52,18 +52,8 @@ extern u8 mb_enable_debug;
 #define mb_debug(n, fmt, a...)
 #endif
 
-/*
- * with EXT4_MB_HISTORY mballoc stores last N allocations in memory
- * and you can monitor it in /proc/fs/ext4/<dev>/mb_history
- */
-#define EXT4_MB_HISTORY
 #define EXT4_MB_HISTORY_ALLOC		1	/* allocation */
 #define EXT4_MB_HISTORY_PREALLOC	2	/* preallocated blocks used */
-#define EXT4_MB_HISTORY_DISCARD		4	/* preallocation discarded */
-#define EXT4_MB_HISTORY_FREE		8	/* free */
-
-#define EXT4_MB_HISTORY_DEFAULT		(EXT4_MB_HISTORY_ALLOC | \
-					 EXT4_MB_HISTORY_PREALLOC)
 
 /*
  * How long mballoc can look for a best extent (in found extents)
@@ -84,7 +74,7 @@ extern u8 mb_enable_debug;
  * with 'ext4_mb_stats' allocator will collect stats that will be
  * shown at umount. The collecting costs though!
  */
-#define MB_DEFAULT_STATS		1
+#define MB_DEFAULT_STATS		0
 
 /*
  * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served
@@ -217,22 +207,6 @@ struct ext4_allocation_context {
 #define AC_STATUS_FOUND		2
 #define AC_STATUS_BREAK		3
 
-struct ext4_mb_history {
-	struct ext4_free_extent orig;	/* orig allocation */
-	struct ext4_free_extent goal;	/* goal allocation */
-	struct ext4_free_extent result;	/* result allocation */
-	unsigned pid;
-	unsigned ino;
-	__u16 found;	/* how many extents have been found */
-	__u16 groups;	/* how many groups have been scanned */
-	__u16 tail;	/* what tail broke some buddy */
-	__u16 buddy;	/* buddy the tail ^^^ broke */
-	__u16 flags;
-	__u8 cr:3;	/* which phase the result extent was found at */
-	__u8 op:4;
-	__u8 merged:1;
-};
-
 struct ext4_buddy {
 	struct page *bd_buddy_page;
 	void *bd_buddy;
@@ -247,13 +221,6 @@ struct ext4_buddy {
 #define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
 #define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
 
-#ifndef EXT4_MB_HISTORY
-static inline void ext4_mb_store_history(struct ext4_allocation_context *ac)
-{
-	return;
-}
-#endif
-
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
 static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,

fs/ext4/migrate.c

@@ -75,7 +75,7 @@ static int finish_range(handle_t *handle, struct inode *inode,
 				goto err_out;
 		}
 	}
-	retval = ext4_ext_insert_extent(handle, inode, path, &newext);
+	retval = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
 err_out:
 	if (path) {
 		ext4_ext_drop_refs(path);

fs/ext4/move_extent.c

@@ -322,7 +322,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
 			goto out;
 
 		if (ext4_ext_insert_extent(handle, orig_inode,
-					orig_path, new_ext))
+					orig_path, new_ext, 0))
 			goto out;
 	}
 
@@ -333,7 +333,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
 			goto out;
 
 		if (ext4_ext_insert_extent(handle, orig_inode,
-					   orig_path, end_ext))
+					   orig_path, end_ext, 0))
 			goto out;
 	}
 out:
@@ -1001,14 +1001,6 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EINVAL;
 	}
 
-	/* orig and donor should be different file */
-	if (orig_inode->i_ino == donor_inode->i_ino) {
-		ext4_debug("ext4 move extent: The argument files should not "
-			"be same file [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
 	/* Ext4 move extent supports only extent based file */
 	if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) {
 		ext4_debug("ext4 move extent: orig file is not extents "
@@ -1232,6 +1224,14 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 	int block_len_in_page;
 	int uninit;
 
+	/* orig and donor should be different file */
+	if (orig_inode->i_ino == donor_inode->i_ino) {
+		ext4_debug("ext4 move extent: The argument files should not "
+			"be same file [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
 	/* protect orig and donor against a truncate */
 	ret1 = mext_inode_double_lock(orig_inode, donor_inode);
 	if (ret1 < 0)

fs/ext4/namei.c

@@ -2076,7 +2076,8 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	struct ext4_iloc iloc;
 	int err = 0;
 
-	if (!ext4_handle_valid(handle))
+	/* ext4_handle_valid() assumes a valid handle_t pointer */
+	if (handle && !ext4_handle_valid(handle))
 		return 0;
 
 	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);

fs/ext4/super.c

@@ -50,13 +50,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/ext4.h>
 
-static int default_mb_history_length = 1000;
-
-module_param_named(default_mb_history_length, default_mb_history_length,
-		   int, 0644);
-MODULE_PARM_DESC(default_mb_history_length,
-		 "Default number of entries saved for mb_history");
-
 struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
 
@@ -189,6 +182,36 @@ void ext4_itable_unused_set(struct super_block *sb,
 		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
 }
 
+
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+	handle_t *handle = current->journal_info;
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+	ref_cnt++;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+	return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt == 0);
+
+	ref_cnt--;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+}
+
 /*
  * Wrappers for jbd2_journal_start/end.
  *
@@ -215,11 +238,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 		}
 		return jbd2_journal_start(journal, nblocks);
 	}
-	/*
-	 * We're not journaling, return the appropriate indication.
-	 */
-	current->journal_info = EXT4_NOJOURNAL_HANDLE;
-	return current->journal_info;
+	return ext4_get_nojournal();
 }
 
 /*
@@ -235,11 +254,7 @@ int __ext4_journal_stop(const char *where, handle_t *handle)
 	int rc;
 
 	if (!ext4_handle_valid(handle)) {
-		/*
-		 * Do this here since we don't call jbd2_journal_stop() in
-		 * no-journal mode.
-		 */
-		current->journal_info = NULL;
+		ext4_put_nojournal(handle);
 		return 0;
 	}
 	sb = handle->h_transaction->t_journal->j_private;
@@ -580,6 +595,9 @@ static void ext4_put_super(struct super_block *sb)
 	struct ext4_super_block *es = sbi->s_es;
 	int i, err;
 
+	flush_workqueue(sbi->dio_unwritten_wq);
+	destroy_workqueue(sbi->dio_unwritten_wq);
+
 	lock_super(sb);
 	lock_kernel();
 	if (sb->s_dirt)
@@ -684,6 +702,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_allocated_meta_blocks = 0;
 	ei->i_delalloc_reserved_flag = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
+	INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
+	ei->cur_aio_dio = NULL;
 
 	return &ei->vfs_inode;
 }
@@ -1052,7 +1072,7 @@ enum {
 	Opt_journal_update, Opt_journal_dev,
 	Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
-	Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length,
+	Opt_data_err_abort, Opt_data_err_ignore,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
@@ -1099,7 +1119,6 @@ static const match_table_t tokens = {
 	{Opt_data_writeback, "data=writeback"},
 	{Opt_data_err_abort, "data_err=abort"},
 	{Opt_data_err_ignore, "data_err=ignore"},
-	{Opt_mb_history_length, "mb_history_length=%u"},
 	{Opt_offusrjquota, "usrjquota="},
 	{Opt_usrjquota, "usrjquota=%s"},
 	{Opt_offgrpjquota, "grpjquota="},
@@ -1340,13 +1359,6 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_data_err_ignore:
 			clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
 			break;
-		case Opt_mb_history_length:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			sbi->s_mb_history_max = option;
-			break;
 #ifdef CONFIG_QUOTA
 		case Opt_usrjquota:
 			qtype = USRQUOTA;
@@ -1646,13 +1658,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			EXT4_INODES_PER_GROUP(sb),
 			sbi->s_mount_opt);
 
-	if (EXT4_SB(sb)->s_journal) {
-		ext4_msg(sb, KERN_INFO, "%s journal on %s",
-		       EXT4_SB(sb)->s_journal->j_inode ? "internal" :
-		       "external", EXT4_SB(sb)->s_journal->j_devname);
-	} else {
-		ext4_msg(sb, KERN_INFO, "no journal");
-	}
 	return res;
 }
 
@@ -2197,6 +2202,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
 
 static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(delayed_allocation_blocks),
@@ -2210,6 +2216,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(mb_order2_req),
 	ATTR_LIST(mb_stream_req),
 	ATTR_LIST(mb_group_prealloc),
+	ATTR_LIST(max_writeback_mb_bump),
 	NULL,
 };
 
@@ -2413,7 +2420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
 	sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
 	sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
-	sbi->s_mb_history_max = default_mb_history_length;
 
 	set_opt(sbi->s_mount_opt, BARRIER);
 
@@ -2679,6 +2685,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
+	sbi->s_max_writeback_mb_bump = 128;
 
 	/*
 	 * set up enough so that it can read an inode
@@ -2798,6 +2805,12 @@ no_journal:
 			clear_opt(sbi->s_mount_opt, NOBH);
 		}
 	}
+	EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
+	if (!EXT4_SB(sb)->dio_unwritten_wq) {
+		printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+		goto failed_mount_wq;
+	}
+
 	/*
 	 * The jbd2_journal_load will have done any necessary log recovery,
 	 * so we can safely mount the rest of the filesystem now.
@@ -2849,12 +2862,12 @@ no_journal:
 			 "available");
 	}
 
-	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+	if (test_opt(sb, DELALLOC) &&
+	    (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
 		ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
 			 "requested data journaling mode");
 		clear_opt(sbi->s_mount_opt, DELALLOC);
-	} else if (test_opt(sb, DELALLOC))
-		ext4_msg(sb, KERN_INFO, "delayed allocation enabled");
+	}
 
 	err = ext4_setup_system_zone(sb);
 	if (err) {
@@ -2910,6 +2923,8 @@ cantfind_ext4:
 
 failed_mount4:
 	ext4_msg(sb, KERN_ERR, "mount failed");
+	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+failed_mount_wq:
 	ext4_release_system_zone(sb);
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -3164,9 +3179,7 @@ static int ext4_load_journal(struct super_block *sb,
 			return -EINVAL;
 	}
 
-	if (journal->j_flags & JBD2_BARRIER)
-		ext4_msg(sb, KERN_INFO, "barriers enabled");
-	else
+	if (!(journal->j_flags & JBD2_BARRIER))
 		ext4_msg(sb, KERN_INFO, "barriers disabled");
 
 	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
@@ -3361,11 +3374,13 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 {
 	int ret = 0;
 	tid_t target;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	trace_ext4_sync_fs(sb, wait);
-	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
+	flush_workqueue(sbi->dio_unwritten_wq);
+	if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
 		if (wait)
-			jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
+			jbd2_log_wait_commit(sbi->s_journal, target);
 	}
 	return ret;
 }

fs/jbd2/checkpoint.c

@@ -643,6 +643,7 @@ out:
 
 int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 {
+	struct transaction_chp_stats_s *stats;
 	transaction_t *transaction;
 	journal_t *journal;
 	int ret = 0;
@@ -679,6 +680,12 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 
 	/* OK, that was the last buffer for the transaction: we can now
 	   safely remove this transaction from the log */
+	stats = &transaction->t_chp_stats;
+	if (stats->cs_chp_time)
+		stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time,
+						    jiffies);
+	trace_jbd2_checkpoint_stats(journal->j_fs_dev->bd_dev,
+				    transaction->t_tid, stats);
 
 	__jbd2_journal_drop_transaction(journal, transaction);
 	kfree(transaction);

fs/jbd2/commit.c

@@ -410,10 +410,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	if (commit_transaction->t_synchronous_commit)
 		write_op = WRITE_SYNC_PLUG;
 	trace_jbd2_commit_locking(journal, commit_transaction);
-	stats.u.run.rs_wait = commit_transaction->t_max_wait;
-	stats.u.run.rs_locked = jiffies;
-	stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
-						stats.u.run.rs_locked);
+	stats.run.rs_wait = commit_transaction->t_max_wait;
+	stats.run.rs_locked = jiffies;
+	stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
+					      stats.run.rs_locked);
 
 	spin_lock(&commit_transaction->t_handle_lock);
 	while (commit_transaction->t_updates) {
@@ -486,9 +486,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	jbd2_journal_switch_revoke_table(journal);
 
 	trace_jbd2_commit_flushing(journal, commit_transaction);
-	stats.u.run.rs_flushing = jiffies;
-	stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
-					       stats.u.run.rs_flushing);
+	stats.run.rs_flushing = jiffies;
+	stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,
+					     stats.run.rs_flushing);
 
 	commit_transaction->t_state = T_FLUSH;
 	journal->j_committing_transaction = commit_transaction;
@@ -523,11 +523,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	spin_unlock(&journal->j_state_lock);
 
 	trace_jbd2_commit_logging(journal, commit_transaction);
-	stats.u.run.rs_logging = jiffies;
-	stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
-						 stats.u.run.rs_logging);
-	stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits;
-	stats.u.run.rs_blocks_logged = 0;
+	stats.run.rs_logging = jiffies;
+	stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing,
+					       stats.run.rs_logging);
+	stats.run.rs_blocks = commit_transaction->t_outstanding_credits;
+	stats.run.rs_blocks_logged = 0;
 
 	J_ASSERT(commit_transaction->t_nr_buffers <=
 		 commit_transaction->t_outstanding_credits);
@@ -695,7 +695,7 @@ start_journal_io:
 				submit_bh(write_op, bh);
 			}
 			cond_resched();
-			stats.u.run.rs_blocks_logged += bufs;
+			stats.run.rs_blocks_logged += bufs;
 
 			/* Force a new descriptor to be generated next
                            time round the loop. */
@@ -988,33 +988,30 @@ restart_loop:
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
 
 	commit_transaction->t_start = jiffies;
-	stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging,
-						commit_transaction->t_start);
+	stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,
+					      commit_transaction->t_start);
 
 	/*
-	 * File the transaction for history
+	 * File the transaction statistics
 	 */
-	stats.ts_type = JBD2_STATS_RUN;
 	stats.ts_tid = commit_transaction->t_tid;
-	stats.u.run.rs_handle_count = commit_transaction->t_handle_count;
-	spin_lock(&journal->j_history_lock);
-	memcpy(journal->j_history + journal->j_history_cur, &stats,
-			sizeof(stats));
-	if (++journal->j_history_cur == journal->j_history_max)
-		journal->j_history_cur = 0;
+	stats.run.rs_handle_count = commit_transaction->t_handle_count;
+	trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
+			     commit_transaction->t_tid, &stats.run);
 
 	/*
 	 * Calculate overall stats
 	 */
+	spin_lock(&journal->j_history_lock);
 	journal->j_stats.ts_tid++;
-	journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait;
-	journal->j_stats.u.run.rs_running += stats.u.run.rs_running;
-	journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked;
-	journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing;
-	journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging;
-	journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count;
-	journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks;
-	journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged;
+	journal->j_stats.run.rs_wait += stats.run.rs_wait;
+	journal->j_stats.run.rs_running += stats.run.rs_running;
+	journal->j_stats.run.rs_locked += stats.run.rs_locked;
+	journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+	journal->j_stats.run.rs_logging += stats.run.rs_logging;
+	journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+	journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
 	spin_unlock(&journal->j_history_lock);
 
 	commit_transaction->t_state = T_FINISHED;

fs/jbd2/journal.c

@@ -136,10 +136,6 @@ static int kjournald2(void *arg)
 	journal->j_task = current;
 	wake_up(&journal->j_wait_done_commit);
 
-	printk(KERN_INFO "kjournald2 starting: pid %d, dev %s, "
-	       "commit interval %ld seconds\n", current->pid,
-	       journal->j_devname, journal->j_commit_interval / HZ);
-
 	/*
 	 * And now, wait forever for commit wakeup events.
 	 */
@@ -223,7 +219,8 @@ static int jbd2_journal_start_thread(journal_t *journal)
 {
 	struct task_struct *t;
 
-	t = kthread_run(kjournald2, journal, "kjournald2");
+	t = kthread_run(kjournald2, journal, "jbd2/%s",
+			journal->j_devname);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
@@ -679,153 +676,6 @@ struct jbd2_stats_proc_session {
 	int max;
 };
 
-static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s,
-					struct transaction_stats_s *ts,
-					int first)
-{
-	if (ts == s->stats + s->max)
-		ts = s->stats;
-	if (!first && ts == s->stats + s->start)
-		return NULL;
-	while (ts->ts_type == 0) {
-		ts++;
-		if (ts == s->stats + s->max)
-			ts = s->stats;
-		if (ts == s->stats + s->start)
-			return NULL;
-	}
-	return ts;
-
-}
-
-static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos)
-{
-	struct jbd2_stats_proc_session *s = seq->private;
-	struct transaction_stats_s *ts;
-	int l = *pos;
-
-	if (l == 0)
-		return SEQ_START_TOKEN;
-	ts = jbd2_history_skip_empty(s, s->stats + s->start, 1);
-	if (!ts)
-		return NULL;
-	l--;
-	while (l) {
-		ts = jbd2_history_skip_empty(s, ++ts, 0);
-		if (!ts)
-			break;
-		l--;
-	}
-	return ts;
-}
-
-static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct jbd2_stats_proc_session *s = seq->private;
-	struct transaction_stats_s *ts = v;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN)
-		return jbd2_history_skip_empty(s, s->stats + s->start, 1);
-	else
-		return jbd2_history_skip_empty(s, ++ts, 0);
-}
-
-static int jbd2_seq_history_show(struct seq_file *seq, void *v)
-{
-	struct transaction_stats_s *ts = v;
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s "
-				"%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid",
-				"wait", "run", "lock", "flush", "log", "hndls",
-				"block", "inlog", "ctime", "write", "drop",
-				"close");
-		return 0;
-	}
-	if (ts->ts_type == JBD2_STATS_RUN)
-		seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u "
-				"%-6lu %-5lu %-5lu\n", "R", ts->ts_tid,
-				jiffies_to_msecs(ts->u.run.rs_wait),
-				jiffies_to_msecs(ts->u.run.rs_running),
-				jiffies_to_msecs(ts->u.run.rs_locked),
-				jiffies_to_msecs(ts->u.run.rs_flushing),
-				jiffies_to_msecs(ts->u.run.rs_logging),
-				ts->u.run.rs_handle_count,
-				ts->u.run.rs_blocks,
-				ts->u.run.rs_blocks_logged);
-	else if (ts->ts_type == JBD2_STATS_CHECKPOINT)
-		seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n",
-				"C", ts->ts_tid, " ",
-				jiffies_to_msecs(ts->u.chp.cs_chp_time),
-				ts->u.chp.cs_written, ts->u.chp.cs_dropped,
-				ts->u.chp.cs_forced_to_close);
-	else
-		J_ASSERT(0);
-	return 0;
-}
-
-static void jbd2_seq_history_stop(struct seq_file *seq, void *v)
-{
-}
-
-static const struct seq_operations jbd2_seq_history_ops = {
-	.start  = jbd2_seq_history_start,
-	.next   = jbd2_seq_history_next,
-	.stop   = jbd2_seq_history_stop,
-	.show   = jbd2_seq_history_show,
-};
-
-static int jbd2_seq_history_open(struct inode *inode, struct file *file)
-{
-	journal_t *journal = PDE(inode)->data;
-	struct jbd2_stats_proc_session *s;
-	int rc, size;
-
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (s == NULL)
-		return -ENOMEM;
-	size = sizeof(struct transaction_stats_s) * journal->j_history_max;
-	s->stats = kmalloc(size, GFP_KERNEL);
-	if (s->stats == NULL) {
-		kfree(s);
-		return -ENOMEM;
-	}
-	spin_lock(&journal->j_history_lock);
-	memcpy(s->stats, journal->j_history, size);
-	s->max = journal->j_history_max;
-	s->start = journal->j_history_cur % s->max;
-	spin_unlock(&journal->j_history_lock);
-
-	rc = seq_open(file, &jbd2_seq_history_ops);
-	if (rc == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = s;
-	} else {
-		kfree(s->stats);
-		kfree(s);
-	}
-	return rc;
-
-}
-
-static int jbd2_seq_history_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct jbd2_stats_proc_session *s = seq->private;
-
-	kfree(s->stats);
-	kfree(s);
-	return seq_release(inode, file);
-}
-
-static struct file_operations jbd2_seq_history_fops = {
-	.owner		= THIS_MODULE,
-	.open           = jbd2_seq_history_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = jbd2_seq_history_release,
-};
-
 static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
 {
 	return *pos ? NULL : SEQ_START_TOKEN;
@@ -842,29 +692,29 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v)
 
 	if (v != SEQ_START_TOKEN)
 		return 0;
-	seq_printf(seq, "%lu transaction, each upto %u blocks\n",
+	seq_printf(seq, "%lu transaction, each up to %u blocks\n",
 			s->stats->ts_tid,
 			s->journal->j_max_transaction_buffers);
 	if (s->stats->ts_tid == 0)
 		return 0;
 	seq_printf(seq, "average: \n  %ums waiting for transaction\n",
-	    jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid));
+	    jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid));
 	seq_printf(seq, "  %ums running transaction\n",
-	    jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid));
+	    jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid));
 	seq_printf(seq, "  %ums transaction was being locked\n",
-	    jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid));
+	    jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid));
 	seq_printf(seq, "  %ums flushing data (in ordered mode)\n",
-	    jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
+	    jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid));
 	seq_printf(seq, "  %ums logging transaction\n",
-	    jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
+	    jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid));
 	seq_printf(seq, "  %lluus average transaction commit time\n",
 		   div_u64(s->journal->j_average_commit_time, 1000));
 	seq_printf(seq, "  %lu handles per transaction\n",
-	    s->stats->u.run.rs_handle_count / s->stats->ts_tid);
+	    s->stats->run.rs_handle_count / s->stats->ts_tid);
 	seq_printf(seq, "  %lu blocks per transaction\n",
-	    s->stats->u.run.rs_blocks / s->stats->ts_tid);
+	    s->stats->run.rs_blocks / s->stats->ts_tid);
 	seq_printf(seq, "  %lu logged blocks per transaction\n",
-	    s->stats->u.run.rs_blocks_logged / s->stats->ts_tid);
+	    s->stats->run.rs_blocks_logged / s->stats->ts_tid);
 	return 0;
 }
 
@@ -934,8 +784,6 @@ static void jbd2_stats_proc_init(journal_t *journal)
 {
 	journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
 	if (journal->j_proc_entry) {
-		proc_create_data("history", S_IRUGO, journal->j_proc_entry,
-				 &jbd2_seq_history_fops, journal);
 		proc_create_data("info", S_IRUGO, journal->j_proc_entry,
 				 &jbd2_seq_info_fops, journal);
 	}
@@ -944,27 +792,9 @@ static void jbd2_stats_proc_init(journal_t *journal)
 static void jbd2_stats_proc_exit(journal_t *journal)
 {
 	remove_proc_entry("info", journal->j_proc_entry);
-	remove_proc_entry("history", journal->j_proc_entry);
 	remove_proc_entry(journal->j_devname, proc_jbd2_stats);
 }
 
-static void journal_init_stats(journal_t *journal)
-{
-	int size;
-
-	if (!proc_jbd2_stats)
-		return;
-
-	journal->j_history_max = 100;
-	size = sizeof(struct transaction_stats_s) * journal->j_history_max;
-	journal->j_history = kzalloc(size, GFP_KERNEL);
-	if (!journal->j_history) {
-		journal->j_history_max = 0;
-		return;
-	}
-	spin_lock_init(&journal->j_history_lock);
-}
-
 /*
  * Management for journal control blocks: functions to create and
  * destroy journal_t structures, and to initialise and read existing
@@ -1009,7 +839,7 @@ static journal_t * journal_init_common (void)
 		goto fail;
 	}
 
-	journal_init_stats(journal);
+	spin_lock_init(&journal->j_history_lock);
 
 	return journal;
 fail:
@@ -1115,7 +945,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	while ((p = strchr(p, '/')))
 		*p = '!';
 	p = journal->j_devname + strlen(journal->j_devname);
-	sprintf(p, ":%lu", journal->j_inode->i_ino);
+	sprintf(p, "-%lu", journal->j_inode->i_ino);
 	jbd_debug(1,
 		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
 		  journal, inode->i_sb->s_id, inode->i_ino,

include/linux/jbd2.h

@@ -464,9 +464,9 @@ struct handle_s
  */
 struct transaction_chp_stats_s {
 	unsigned long		cs_chp_time;
-	unsigned long		cs_forced_to_close;
-	unsigned long		cs_written;
-	unsigned long		cs_dropped;
+	__u32			cs_forced_to_close;
+	__u32			cs_written;
+	__u32			cs_dropped;
 };
 
 /* The transaction_t type is the guts of the journaling mechanism.  It
@@ -668,23 +668,16 @@ struct transaction_run_stats_s {
 	unsigned long		rs_flushing;
 	unsigned long		rs_logging;
 
-	unsigned long		rs_handle_count;
-	unsigned long		rs_blocks;
-	unsigned long		rs_blocks_logged;
+	__u32			rs_handle_count;
+	__u32			rs_blocks;
+	__u32			rs_blocks_logged;
 };
 
 struct transaction_stats_s {
-	int 			ts_type;
 	unsigned long		ts_tid;
-	union {
-		struct transaction_run_stats_s run;
-		struct transaction_chp_stats_s chp;
-	} u;
+	struct transaction_run_stats_s run;
 };
 
-#define JBD2_STATS_RUN		1
-#define JBD2_STATS_CHECKPOINT	2
-
 static inline unsigned long
 jbd2_time_diff(unsigned long start, unsigned long end)
 {
@@ -988,12 +981,6 @@ struct journal_s
 	/*
 	 * Journal statistics
 	 */
-	struct transaction_stats_s *j_history;
-	int			j_history_max;
-	int			j_history_cur;
-	/*
-	 * Protect the transactions statistics history
-	 */
 	spinlock_t		j_history_lock;
 	struct proc_dir_entry	*j_proc_entry;
 	struct transaction_stats_s j_stats;

include/trace/events/ext4.h

@@ -11,6 +11,7 @@ struct ext4_allocation_context;
 struct ext4_allocation_request;
 struct ext4_prealloc_space;
 struct ext4_inode_info;
+struct mpage_da_data;
 
 #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
 
@@ -236,6 +237,7 @@ TRACE_EVENT(ext4_da_writepages,
 		__field(	char,	for_kupdate		)
 		__field(	char,	for_reclaim		)
 		__field(	char,	range_cyclic		)
+		__field(       pgoff_t,	writeback_index		)
 	),
 
 	TP_fast_assign(
@@ -249,15 +251,17 @@ TRACE_EVENT(ext4_da_writepages,
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d",
+	TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d writeback_index %lu",
 		  jbd2_dev_to_name(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->nr_to_write,
 		  __entry->pages_skipped, __entry->range_start,
 		  __entry->range_end, __entry->nonblocking,
 		  __entry->for_kupdate, __entry->for_reclaim,
-		  __entry->range_cyclic)
+		  __entry->range_cyclic,
+		  (unsigned long) __entry->writeback_index)
 );
 
 TRACE_EVENT(ext4_da_write_pages,
@@ -309,6 +313,7 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__field(	char,	encountered_congestion	)
 		__field(	char,	more_io			)	
 		__field(	char,	no_nrwrite_index_update )
+		__field(       pgoff_t,	writeback_index		)
 	),
 
 	TP_fast_assign(
@@ -320,14 +325,16 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__entry->encountered_congestion	= wbc->encountered_congestion;
 		__entry->more_io	= wbc->more_io;
 		__entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d",
+	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d writeback_index %lu",
 		  jbd2_dev_to_name(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
 		  __entry->encountered_congestion, __entry->more_io,
-		  __entry->no_nrwrite_index_update)
+		  __entry->no_nrwrite_index_update,
+		  (unsigned long) __entry->writeback_index)
 );
 
 TRACE_EVENT(ext4_da_write_begin,
@@ -737,6 +744,169 @@ TRACE_EVENT(ext4_alloc_da_blocks,
 		  __entry->data_blocks, __entry->meta_blocks)
 );
 
+TRACE_EVENT(ext4_mballoc_alloc,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u16,	found			)
+		__field(	__u16,	groups			)
+		__field(	__u16,	buddy			)
+		__field(	__u16,	flags			)
+		__field(	__u16,	tail			)
+		__field(	__u8,	cr			)
+		__field(	__u32, 	orig_logical		)
+		__field(	  int,	orig_start		)
+		__field(	__u32, 	orig_group		)
+		__field(	  int,	orig_len		)
+		__field(	__u32, 	goal_logical		)
+		__field(	  int,	goal_start		)
+		__field(	__u32, 	goal_group		)
+		__field(	  int,	goal_len		)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_inode->i_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->found		= ac->ac_found;
+		__entry->flags		= ac->ac_flags;
+		__entry->groups		= ac->ac_groups_scanned;
+		__entry->buddy		= ac->ac_buddy;
+		__entry->tail		= ac->ac_tail;
+		__entry->cr		= ac->ac_criteria;
+		__entry->orig_logical	= ac->ac_o_ex.fe_logical;
+		__entry->orig_start	= ac->ac_o_ex.fe_start;
+		__entry->orig_group	= ac->ac_o_ex.fe_group;
+		__entry->orig_len	= ac->ac_o_ex.fe_len;
+		__entry->goal_logical	= ac->ac_g_ex.fe_logical;
+		__entry->goal_start	= ac->ac_g_ex.fe_start;
+		__entry->goal_group	= ac->ac_g_ex.fe_group;
+		__entry->goal_len	= ac->ac_g_ex.fe_len;
+		__entry->result_logical	= ac->ac_f_ex.fe_logical;
+		__entry->result_start	= ac->ac_f_ex.fe_start;
+		__entry->result_group	= ac->ac_f_ex.fe_group;
+		__entry->result_len	= ac->ac_f_ex.fe_len;
+	),
+
+	TP_printk("dev %s inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u "
+		  "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x "
+		  "tail %u broken %u",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->orig_group, __entry->orig_start,
+		  __entry->orig_len, __entry->orig_logical,
+		  __entry->goal_group, __entry->goal_start,
+		  __entry->goal_len, __entry->goal_logical,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical,
+		  __entry->found, __entry->groups, __entry->cr,
+		  __entry->flags, __entry->tail,
+		  __entry->buddy ? 1 << __entry->buddy : 0)
+);
+
+TRACE_EVENT(ext4_mballoc_prealloc,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u32, 	orig_logical		)
+		__field(	  int,	orig_start		)
+		__field(	__u32, 	orig_group		)
+		__field(	  int,	orig_len		)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_inode->i_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->orig_logical	= ac->ac_o_ex.fe_logical;
+		__entry->orig_start	= ac->ac_o_ex.fe_start;
+		__entry->orig_group	= ac->ac_o_ex.fe_group;
+		__entry->orig_len	= ac->ac_o_ex.fe_len;
+		__entry->result_logical	= ac->ac_b_ex.fe_logical;
+		__entry->result_start	= ac->ac_b_ex.fe_start;
+		__entry->result_group	= ac->ac_b_ex.fe_group;
+		__entry->result_len	= ac->ac_b_ex.fe_len;
+	),
+
+	TP_printk("dev %s inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->orig_group, __entry->orig_start,
+		  __entry->orig_len, __entry->orig_logical,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical)
+);
+
+TRACE_EVENT(ext4_mballoc_discard,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_inode->i_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->result_logical	= ac->ac_b_ex.fe_logical;
+		__entry->result_start	= ac->ac_b_ex.fe_start;
+		__entry->result_group	= ac->ac_b_ex.fe_group;
+		__entry->result_len	= ac->ac_b_ex.fe_len;
+	),
+
+	TP_printk("dev %s inode %lu extent %u/%d/%u@%u ",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical)
+);
+
+TRACE_EVENT(ext4_mballoc_free,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_inode->i_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->result_logical	= ac->ac_b_ex.fe_logical;
+		__entry->result_start	= ac->ac_b_ex.fe_start;
+		__entry->result_group	= ac->ac_b_ex.fe_group;
+		__entry->result_len	= ac->ac_b_ex.fe_len;
+	),
+
+	TP_printk("dev %s inode %lu extent %u/%d/%u@%u ",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */

include/trace/events/jbd2.h

@@ -7,6 +7,9 @@
 #include <linux/jbd2.h>
 #include <linux/tracepoint.h>
 
+struct transaction_chp_stats_s;
+struct transaction_run_stats_s;
+
 TRACE_EVENT(jbd2_checkpoint,
 
 	TP_PROTO(journal_t *journal, int result),
@@ -162,6 +165,81 @@ TRACE_EVENT(jbd2_submit_inode_data,
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino)
 );
 
+TRACE_EVENT(jbd2_run_stats,
+	TP_PROTO(dev_t dev, unsigned long tid,
+		 struct transaction_run_stats_s *stats),
+
+	TP_ARGS(dev, tid, stats),
+
+	TP_STRUCT__entry(
+		__field(		dev_t,	dev		)
+		__field(	unsigned long,	tid		)
+		__field(	unsigned long,	wait		)
+		__field(	unsigned long,	running		)
+		__field(	unsigned long,	locked		)
+		__field(	unsigned long,	flushing	)
+		__field(	unsigned long,	logging		)
+		__field(		__u32,	handle_count	)
+		__field(		__u32,	blocks		)
+		__field(		__u32,	blocks_logged	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= dev;
+		__entry->tid		= tid;
+		__entry->wait		= stats->rs_wait;
+		__entry->running	= stats->rs_running;
+		__entry->locked		= stats->rs_locked;
+		__entry->flushing	= stats->rs_flushing;
+		__entry->logging	= stats->rs_logging;
+		__entry->handle_count	= stats->rs_handle_count;
+		__entry->blocks		= stats->rs_blocks;
+		__entry->blocks_logged	= stats->rs_blocks_logged;
+	),
+
+	TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u "
+		  "logging %u handle_count %u blocks %u blocks_logged %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->tid,
+		  jiffies_to_msecs(__entry->wait),
+		  jiffies_to_msecs(__entry->running),
+		  jiffies_to_msecs(__entry->locked),
+		  jiffies_to_msecs(__entry->flushing),
+		  jiffies_to_msecs(__entry->logging),
+		  __entry->handle_count, __entry->blocks,
+		  __entry->blocks_logged)
+);
+
+TRACE_EVENT(jbd2_checkpoint_stats,
+	TP_PROTO(dev_t dev, unsigned long tid,
+		 struct transaction_chp_stats_s *stats),
+
+	TP_ARGS(dev, tid, stats),
+
+	TP_STRUCT__entry(
+		__field(		dev_t,	dev		)
+		__field(	unsigned long,	tid		)
+		__field(	unsigned long,	chp_time	)
+		__field(		__u32,	forced_to_close	)
+		__field(		__u32,	written		)
+		__field(		__u32,	dropped		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= dev;
+		__entry->tid		= tid;
+		__entry->chp_time	= stats->cs_chp_time;
+		__entry->forced_to_close= stats->cs_forced_to_close;
+		__entry->written	= stats->cs_written;
+		__entry->dropped	= stats->cs_dropped;
+	),
+
+	TP_printk("dev %s tid %lu chp_time %u forced_to_close %u "
+		  "written %u dropped %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->tid,
+		  jiffies_to_msecs(__entry->chp_time),
+		  __entry->forced_to_close, __entry->written, __entry->dropped)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */