Merge branch 'master' into for-2.6.35

Conflicts:
	fs/ext3/fsync.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

13 files changed, 465 insertions, 197 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 0f8b9968a803..089eaca860b4 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -45,6 +45,15 @@
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 
+/*
+ * Types of I/O for bmap clustering and I/O completion tracking.
+ */
+enum {
+	IO_READ,	/* mapping for a read */
+	IO_DELAY,	/* mapping covers delalloc region */
+	IO_UNWRITTEN,	/* mapping covers allocated but uninitialized data */
+	IO_NEW		/* just allocated */
+};
 
 /*
  * Prime number of hash buckets since address is used as the key.
@@ -103,8 +112,9 @@ xfs_count_page_state(
 
 STATIC struct block_device *
 xfs_find_bdev_for_inode(
-	struct xfs_inode	*ip)
+	struct inode		*inode)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 
 	if (XFS_IS_REALTIME_INODE(ip))
@@ -183,7 +193,7 @@ xfs_setfilesize(
 	xfs_fsize_t		isize;
 
 	ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
-	ASSERT(ioend->io_type != IOMAP_READ);
+	ASSERT(ioend->io_type != IO_READ);
 
 	if (unlikely(ioend->io_error))
 		return 0;
@@ -214,7 +224,7 @@ xfs_finish_ioend(
 	if (atomic_dec_and_test(&ioend->io_remaining)) {
 		struct workqueue_struct *wq;
 
-		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+		wq = (ioend->io_type == IO_UNWRITTEN) ?
 			xfsconvertd_workqueue : xfsdatad_workqueue;
 		queue_work(wq, &ioend->io_work);
 		if (wait)
@@ -237,7 +247,7 @@ xfs_end_io(
 	 * For unwritten extents we need to issue transactions to convert a
 	 * range to normal written extens after the data I/O has finished.
 	 */
-	if (ioend->io_type == IOMAP_UNWRITTEN &&
+	if (ioend->io_type == IO_UNWRITTEN &&
 	    likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
 
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
@@ -250,7 +260,7 @@ xfs_end_io(
 	 * We might have to update the on-disk file size after extending
 	 * writes.
 	 */
-	if (ioend->io_type != IOMAP_READ) {
+	if (ioend->io_type != IO_READ) {
 		error = xfs_setfilesize(ioend);
 		ASSERT(!error || error == EAGAIN);
 	}
@@ -309,21 +319,25 @@ xfs_map_blocks(
 	struct inode		*inode,
 	loff_t			offset,
 	ssize_t			count,
-	xfs_iomap_t		*mapp,
+	struct xfs_bmbt_irec	*imap,
 	int			flags)
 {
 	int			nmaps = 1;
+	int			new = 0;
 
-	return -xfs_iomap(XFS_I(inode), offset, count, flags, mapp, &nmaps);
+	return -xfs_iomap(XFS_I(inode), offset, count, flags, imap, &nmaps, &new);
 }
 
 STATIC int
-xfs_iomap_valid(
-	xfs_iomap_t		*iomapp,
-	loff_t			offset)
+xfs_imap_valid(
+	struct inode		*inode,
+	struct xfs_bmbt_irec	*imap,
+	xfs_off_t		offset)
 {
-	return offset >= iomapp->iomap_offset &&
-		offset < iomapp->iomap_offset + iomapp->iomap_bsize;
+	offset >>= inode->i_blkbits;
+
+	return offset >= imap->br_startoff &&
+		offset < imap->br_startoff + imap->br_blockcount;
 }
 
 /*
@@ -554,19 +568,23 @@ xfs_add_to_ioend(
 
 STATIC void
 xfs_map_buffer(
+	struct inode		*inode,
 	struct buffer_head	*bh,
-	xfs_iomap_t		*mp,
-	xfs_off_t		offset,
-	uint			block_bits)
+	struct xfs_bmbt_irec	*imap,
+	xfs_off_t		offset)
 {
 	sector_t		bn;
+	struct xfs_mount	*m = XFS_I(inode)->i_mount;
+	xfs_off_t		iomap_offset = XFS_FSB_TO_B(m, imap->br_startoff);
+	xfs_daddr_t		iomap_bn = xfs_fsb_to_db(XFS_I(inode), imap->br_startblock);
 
-	ASSERT(mp->iomap_bn != IOMAP_DADDR_NULL);
+	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
+	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
 
-	bn = (mp->iomap_bn >> (block_bits - BBSHIFT)) +
-	      ((offset - mp->iomap_offset) >> block_bits);
+	bn = (iomap_bn >> (inode->i_blkbits - BBSHIFT)) +
+	      ((offset - iomap_offset) >> inode->i_blkbits);
 
-	ASSERT(bn || (mp->iomap_flags & IOMAP_REALTIME));
+	ASSERT(bn || XFS_IS_REALTIME_INODE(XFS_I(inode)));
 
 	bh->b_blocknr = bn;
 	set_buffer_mapped(bh);
@@ -574,17 +592,17 @@ xfs_map_buffer(
 
 STATIC void
 xfs_map_at_offset(
+	struct inode		*inode,
 	struct buffer_head	*bh,
-	loff_t			offset,
-	int			block_bits,
-	xfs_iomap_t		*iomapp)
+	struct xfs_bmbt_irec	*imap,
+	xfs_off_t		offset)
 {
-	ASSERT(!(iomapp->iomap_flags & IOMAP_HOLE));
-	ASSERT(!(iomapp->iomap_flags & IOMAP_DELAY));
+	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
+	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
 
 	lock_buffer(bh);
-	xfs_map_buffer(bh, iomapp, offset, block_bits);
-	bh->b_bdev = iomapp->iomap_target->bt_bdev;
+	xfs_map_buffer(inode, bh, imap, offset);
+	bh->b_bdev = xfs_find_bdev_for_inode(inode);
 	set_buffer_mapped(bh);
 	clear_buffer_delay(bh);
 	clear_buffer_unwritten(bh);
@@ -713,11 +731,11 @@ xfs_is_delayed_page(
 		bh = head = page_buffers(page);
 		do {
 			if (buffer_unwritten(bh))
-				acceptable = (type == IOMAP_UNWRITTEN);
+				acceptable = (type == IO_UNWRITTEN);
 			else if (buffer_delay(bh))
-				acceptable = (type == IOMAP_DELAY);
+				acceptable = (type == IO_DELAY);
 			else if (buffer_dirty(bh) && buffer_mapped(bh))
-				acceptable = (type == IOMAP_NEW);
+				acceptable = (type == IO_NEW);
 			else
 				break;
 		} while ((bh = bh->b_this_page) != head);
@@ -740,7 +758,7 @@ xfs_convert_page(
 	struct inode		*inode,
 	struct page		*page,
 	loff_t			tindex,
-	xfs_iomap_t		*mp,
+	struct xfs_bmbt_irec	*imap,
 	xfs_ioend_t		**ioendp,
 	struct writeback_control *wbc,
 	int			startio,
@@ -750,7 +768,6 @@ xfs_convert_page(
 	xfs_off_t		end_offset;
 	unsigned long		p_offset;
 	unsigned int		type;
-	int			bbits = inode->i_blkbits;
 	int			len, page_dirty;
 	int			count = 0, done = 0, uptodate = 1;
  	xfs_off_t		offset = page_offset(page);
@@ -802,19 +819,19 @@ xfs_convert_page(
 
 		if (buffer_unwritten(bh) || buffer_delay(bh)) {
 			if (buffer_unwritten(bh))
-				type = IOMAP_UNWRITTEN;
+				type = IO_UNWRITTEN;
 			else
-				type = IOMAP_DELAY;
+				type = IO_DELAY;
 
-			if (!xfs_iomap_valid(mp, offset)) {
+			if (!xfs_imap_valid(inode, imap, offset)) {
 				done = 1;
 				continue;
 			}
 
-			ASSERT(!(mp->iomap_flags & IOMAP_HOLE));
-			ASSERT(!(mp->iomap_flags & IOMAP_DELAY));
+			ASSERT(imap->br_startblock != HOLESTARTBLOCK);
+			ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
 
-			xfs_map_at_offset(bh, offset, bbits, mp);
+			xfs_map_at_offset(inode, bh, imap, offset);
 			if (startio) {
 				xfs_add_to_ioend(inode, bh, offset,
 						type, ioendp, done);
@@ -826,7 +843,7 @@ xfs_convert_page(
 			page_dirty--;
 			count++;
 		} else {
-			type = IOMAP_NEW;
+			type = IO_NEW;
 			if (buffer_mapped(bh) && all_bh && startio) {
 				lock_buffer(bh);
 				xfs_add_to_ioend(inode, bh, offset,
@@ -866,7 +883,7 @@ STATIC void
 xfs_cluster_write(
 	struct inode		*inode,
 	pgoff_t			tindex,
-	xfs_iomap_t		*iomapp,
+	struct xfs_bmbt_irec	*imap,
 	xfs_ioend_t		**ioendp,
 	struct writeback_control *wbc,
 	int			startio,
@@ -885,7 +902,7 @@ xfs_cluster_write(
 
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			done = xfs_convert_page(inode, pvec.pages[i], tindex++,
-					iomapp, ioendp, wbc, startio, all_bh);
+					imap, ioendp, wbc, startio, all_bh);
 			if (done)
 				break;
 		}
@@ -930,7 +947,7 @@ xfs_aops_discard_page(
 	loff_t			offset = page_offset(page);
 	ssize_t			len = 1 << inode->i_blkbits;
 
-	if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+	if (!xfs_is_delayed_page(page, IO_DELAY))
 		goto out_invalidate;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -1042,15 +1059,15 @@ xfs_page_state_convert(
 	int		unmapped) /* also implies page uptodate */
 {
 	struct buffer_head	*bh, *head;
-	xfs_iomap_t		iomap;
+	struct xfs_bmbt_irec	imap;
 	xfs_ioend_t		*ioend = NULL, *iohead = NULL;
 	loff_t			offset;
 	unsigned long           p_offset = 0;
 	unsigned int		type;
 	__uint64_t              end_offset;
-	pgoff_t                 end_index, last_index, tlast;
+	pgoff_t                 end_index, last_index;
 	ssize_t			size, len;
-	int			flags, err, iomap_valid = 0, uptodate = 1;
+	int			flags, err, imap_valid = 0, uptodate = 1;
 	int			page_dirty, count = 0;
 	int			trylock = 0;
 	int			all_bh = unmapped;
@@ -1097,7 +1114,7 @@ xfs_page_state_convert(
 	bh = head = page_buffers(page);
 	offset = page_offset(page);
 	flags = BMAPI_READ;
-	type = IOMAP_NEW;
+	type = IO_NEW;
 
 	/* TODO: cleanup count and page_dirty */
 
@@ -1111,12 +1128,12 @@ xfs_page_state_convert(
 			 * the iomap is actually still valid, but the ioend
 			 * isn't.  shouldn't happen too often.
 			 */
-			iomap_valid = 0;
+			imap_valid = 0;
 			continue;
 		}
 
-		if (iomap_valid)
-			iomap_valid = xfs_iomap_valid(&iomap, offset);
+		if (imap_valid)
+			imap_valid = xfs_imap_valid(inode, &imap, offset);
 
 		/*
 		 * First case, map an unwritten extent and prepare for
@@ -1137,20 +1154,20 @@ xfs_page_state_convert(
 			 * Make sure we don't use a read-only iomap
 			 */
 			if (flags == BMAPI_READ)
-				iomap_valid = 0;
+				imap_valid = 0;
 
 			if (buffer_unwritten(bh)) {
-				type = IOMAP_UNWRITTEN;
+				type = IO_UNWRITTEN;
 				flags = BMAPI_WRITE | BMAPI_IGNSTATE;
 			} else if (buffer_delay(bh)) {
-				type = IOMAP_DELAY;
+				type = IO_DELAY;
 				flags = BMAPI_ALLOCATE | trylock;
 			} else {
-				type = IOMAP_NEW;
+				type = IO_NEW;
 				flags = BMAPI_WRITE | BMAPI_MMAP;
 			}
 
-			if (!iomap_valid) {
+			if (!imap_valid) {
 				/*
 				 * if we didn't have a valid mapping then we
 				 * need to ensure that we put the new mapping
@@ -1160,7 +1177,7 @@ xfs_page_state_convert(
 				 * for unwritten extent conversion.
 				 */
 				new_ioend = 1;
-				if (type == IOMAP_NEW) {
+				if (type == IO_NEW) {
 					size = xfs_probe_cluster(inode,
 							page, bh, head, 0);
 				} else {
@@ -1168,14 +1185,14 @@ xfs_page_state_convert(
 				}
 
 				err = xfs_map_blocks(inode, offset, size,
-						&iomap, flags);
+						&imap, flags);
 				if (err)
 					goto error;
-				iomap_valid = xfs_iomap_valid(&iomap, offset);
+				imap_valid = xfs_imap_valid(inode, &imap,
+							    offset);
 			}
-			if (iomap_valid) {
-				xfs_map_at_offset(bh, offset,
-						inode->i_blkbits, &iomap);
+			if (imap_valid) {
+				xfs_map_at_offset(inode, bh, &imap, offset);
 				if (startio) {
 					xfs_add_to_ioend(inode, bh, offset,
 							type, &ioend,
@@ -1194,40 +1211,41 @@ xfs_page_state_convert(
 			 * That means it must already have extents allocated
 			 * underneath it. Map the extent by reading it.
 			 */
-			if (!iomap_valid || flags != BMAPI_READ) {
+			if (!imap_valid || flags != BMAPI_READ) {
 				flags = BMAPI_READ;
 				size = xfs_probe_cluster(inode, page, bh,
 								head, 1);
 				err = xfs_map_blocks(inode, offset, size,
-						&iomap, flags);
+						&imap, flags);
 				if (err)
 					goto error;
-				iomap_valid = xfs_iomap_valid(&iomap, offset);
+				imap_valid = xfs_imap_valid(inode, &imap,
+							    offset);
 			}
 
 			/*
-			 * We set the type to IOMAP_NEW in case we are doing a
+			 * We set the type to IO_NEW in case we are doing a
 			 * small write at EOF that is extending the file but
 			 * without needing an allocation. We need to update the
 			 * file size on I/O completion in this case so it is
 			 * the same case as having just allocated a new extent
 			 * that we are writing into for the first time.
 			 */
-			type = IOMAP_NEW;
+			type = IO_NEW;
 			if (trylock_buffer(bh)) {
 				ASSERT(buffer_mapped(bh));
-				if (iomap_valid)
+				if (imap_valid)
 					all_bh = 1;
 				xfs_add_to_ioend(inode, bh, offset, type,
-						&ioend, !iomap_valid);
+						&ioend, !imap_valid);
 				page_dirty--;
 				count++;
 			} else {
-				iomap_valid = 0;
+				imap_valid = 0;
 			}
 		} else if ((buffer_uptodate(bh) || PageUptodate(page)) &&
 			   (unmapped || startio)) {
-			iomap_valid = 0;
+			imap_valid = 0;
 		}
 
 		if (!iohead)
@@ -1241,12 +1259,23 @@ xfs_page_state_convert(
 	if (startio)
 		xfs_start_page_writeback(page, 1, count);
 
-	if (ioend && iomap_valid) {
-		offset = (iomap.iomap_offset + iomap.iomap_bsize - 1) >>
-					PAGE_CACHE_SHIFT;
-		tlast = min_t(pgoff_t, offset, last_index);
-		xfs_cluster_write(inode, page->index + 1, &iomap, &ioend,
-					wbc, startio, all_bh, tlast);
+	if (ioend && imap_valid) {
+		xfs_off_t		end_index;
+
+		end_index = imap.br_startoff + imap.br_blockcount;
+
+		/* to bytes */
+		end_index <<= inode->i_blkbits;
+
+		/* to pages */
+		end_index = (end_index - 1) >> PAGE_CACHE_SHIFT;
+
+		/* check against file size */
+		if (end_index > last_index)
+			end_index = last_index;
+
+		xfs_cluster_write(inode, page->index + 1, &imap, &ioend,
+					wbc, startio, all_bh, end_index);
 	}
 
 	if (iohead)
@@ -1448,10 +1477,11 @@ __xfs_get_blocks(
 	int			direct,
 	bmapi_flags_t		flags)
 {
-	xfs_iomap_t		iomap;
+	struct xfs_bmbt_irec	imap;
 	xfs_off_t		offset;
 	ssize_t			size;
-	int			niomap = 1;
+	int			nimap = 1;
+	int			new = 0;
 	int			error;
 
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
@@ -1462,22 +1492,21 @@ __xfs_get_blocks(
 		return 0;
 
 	error = xfs_iomap(XFS_I(inode), offset, size,
-			     create ? flags : BMAPI_READ, &iomap, &niomap);
+			     create ? flags : BMAPI_READ, &imap, &nimap, &new);
 	if (error)
 		return -error;
-	if (niomap == 0)
+	if (nimap == 0)
 		return 0;
 
-	if (iomap.iomap_bn != IOMAP_DADDR_NULL) {
+	if (imap.br_startblock != HOLESTARTBLOCK &&
+	    imap.br_startblock != DELAYSTARTBLOCK) {
 		/*
 		 * For unwritten extents do not report a disk address on
 		 * the read case (treat as if we're reading into a hole).
 		 */
-		if (create || !(iomap.iomap_flags & IOMAP_UNWRITTEN)) {
-			xfs_map_buffer(bh_result, &iomap, offset,
-				       inode->i_blkbits);
-		}
-		if (create && (iomap.iomap_flags & IOMAP_UNWRITTEN)) {
+		if (create || !ISUNWRITTEN(&imap))
+			xfs_map_buffer(inode, bh_result, &imap, offset);
+		if (create && ISUNWRITTEN(&imap)) {
 			if (direct)
 				bh_result->b_private = inode;
 			set_buffer_unwritten(bh_result);
@@ -1488,7 +1517,7 @@ __xfs_get_blocks(
 	 * If this is a realtime file, data may be on a different device.
 	 * to that pointed to from the buffer_head b_bdev currently.
 	 */
-	bh_result->b_bdev = iomap.iomap_target->bt_bdev;
+	bh_result->b_bdev = xfs_find_bdev_for_inode(inode);
 
 	/*
 	 * If we previously allocated a block out beyond eof and we are now
@@ -1502,10 +1531,10 @@ __xfs_get_blocks(
 	if (create &&
 	    ((!buffer_mapped(bh_result) && !buffer_uptodate(bh_result)) ||
 	     (offset >= i_size_read(inode)) ||
-	     (iomap.iomap_flags & (IOMAP_NEW|IOMAP_UNWRITTEN))))
+	     (new || ISUNWRITTEN(&imap))))
 		set_buffer_new(bh_result);
 
-	if (iomap.iomap_flags & IOMAP_DELAY) {
+	if (imap.br_startblock == DELAYSTARTBLOCK) {
 		BUG_ON(direct);
 		if (create) {
 			set_buffer_uptodate(bh_result);
@@ -1514,11 +1543,23 @@ __xfs_get_blocks(
 		}
 	}
 
+	/*
+	 * If this is O_DIRECT or the mpage code calling tell them how large
+	 * the mapping is, so that we can avoid repeated get_blocks calls.
+	 */
 	if (direct || size > (1 << inode->i_blkbits)) {
-		ASSERT(iomap.iomap_bsize - iomap.iomap_delta > 0);
-		offset = min_t(xfs_off_t,
-				iomap.iomap_bsize - iomap.iomap_delta, size);
-		bh_result->b_size = (ssize_t)min_t(xfs_off_t, LONG_MAX, offset);
+		xfs_off_t		mapping_size;
+
+		mapping_size = imap.br_startoff + imap.br_blockcount - iblock;
+		mapping_size <<= inode->i_blkbits;
+
+		ASSERT(mapping_size > 0);
+		if (mapping_size > size)
+			mapping_size = size;
+		if (mapping_size > LONG_MAX)
+			mapping_size = LONG_MAX;
+
+		bh_result->b_size = mapping_size;
 	}
 
 	return 0;
@@ -1576,7 +1617,7 @@ xfs_end_io_direct(
 	 */
 	ioend->io_offset = offset;
 	ioend->io_size = size;
-	if (ioend->io_type == IOMAP_READ) {
+	if (ioend->io_type == IO_READ) {
 		xfs_finish_ioend(ioend, 0);
 	} else if (private && size > 0) {
 		xfs_finish_ioend(ioend, is_sync_kiocb(iocb));
@@ -1587,7 +1628,7 @@ xfs_end_io_direct(
 		 * didn't map an unwritten extent so switch it's completion
 		 * handler.
 		 */
-		ioend->io_type = IOMAP_NEW;
+		ioend->io_type = IO_NEW;
 		xfs_finish_ioend(ioend, 0);
 	}
 
@@ -1612,10 +1653,10 @@ xfs_vm_direct_IO(
 	struct block_device *bdev;
 	ssize_t		ret;
 
-	bdev = xfs_find_bdev_for_inode(XFS_I(inode));
+	bdev = xfs_find_bdev_for_inode(inode);
 
 	iocb->private = xfs_alloc_ioend(inode, rw == WRITE ?
-					IOMAP_UNWRITTEN : IOMAP_READ);
+					IO_UNWRITTEN : IO_READ);
 
 	ret = blockdev_direct_IO_no_locking(rw, iocb, inode, bdev, iov,
 					    offset, nr_segs,
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 44c2b0ef9a41..f01de3c55c43 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1007,25 +1007,20 @@ xfs_bwrite(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp)
 {
-	int			iowait = (bp->b_flags & XBF_ASYNC) == 0;
-	int			error = 0;
+	int			error;
 
 	bp->b_strat = xfs_bdstrat_cb;
 	bp->b_mount = mp;
 	bp->b_flags |= XBF_WRITE;
-	if (!iowait)
-		bp->b_flags |= _XBF_RUN_QUEUES;
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ);
 
 	xfs_buf_delwri_dequeue(bp);
 	xfs_buf_iostrategy(bp);
 
-	if (iowait) {
-		error = xfs_buf_iowait(bp);
-		if (error)
-			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
-		xfs_buf_relse(bp);
-	}
-
+	error = xfs_buf_iowait(bp);
+	if (error)
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	xfs_buf_relse(bp);
 	return error;
 }
 
@@ -1614,7 +1609,8 @@ xfs_mapping_buftarg(
 
 STATIC int
 xfs_alloc_delwrite_queue(
-	xfs_buftarg_t		*btp)
+	xfs_buftarg_t		*btp,
+	const char		*fsname)
 {
 	int	error = 0;
 
@@ -1622,7 +1618,7 @@ xfs_alloc_delwrite_queue(
 	INIT_LIST_HEAD(&btp->bt_delwrite_queue);
 	spin_lock_init(&btp->bt_delwrite_lock);
 	btp->bt_flags = 0;
-	btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd");
+	btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd/%s", fsname);
 	if (IS_ERR(btp->bt_task)) {
 		error = PTR_ERR(btp->bt_task);
 		goto out_error;
@@ -1635,7 +1631,8 @@ out_error:
 xfs_buftarg_t *
 xfs_alloc_buftarg(
 	struct block_device	*bdev,
-	int			external)
+	int			external,
+	const char		*fsname)
 {
 	xfs_buftarg_t		*btp;
 
@@ -1647,7 +1644,7 @@ xfs_alloc_buftarg(
 		goto error;
 	if (xfs_mapping_buftarg(btp, bdev))
 		goto error;
-	if (xfs_alloc_delwrite_queue(btp))
+	if (xfs_alloc_delwrite_queue(btp, fsname))
 		goto error;
 	xfs_alloc_bufhash(btp, external);
 	return btp;
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 386e7361e50e..5fbecefa5dfd 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -390,7 +390,7 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
 /*
  *	Handling of buftargs.
  */
-extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int);
+extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int, const char *);
 extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 42dd3bcfba6b..d8fb1b5d6cb5 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -115,6 +115,8 @@ xfs_file_fsync(
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
+	xfs_ioend_wait(ip);
+
 	/*
 	 * We always need to make sure that the required inode state is safe on
 	 * disk.  The inode might be clean but we still might need to force the
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 7b26cc2fd284..699b60cbab9c 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -527,6 +527,10 @@ xfs_attrmulti_by_handle(
 	if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	/* overflow check */
+	if (am_hreq.opcount >= INT_MAX / sizeof(xfs_attr_multiop_t))
+		return -E2BIG;
+
 	dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 593c05b4df8d..9287135e9bfc 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -420,6 +420,10 @@ xfs_compat_attrmulti_by_handle(
 			   sizeof(compat_xfs_fsop_attrmulti_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	/* overflow check */
+	if (am_hreq.opcount >= INT_MAX / sizeof(compat_xfs_attr_multiop_t))
+		return -E2BIG;
+
 	dentry = xfs_compat_handlereq_to_dentry(parfilp, &am_hreq.hreq);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index e65a7937f3a4..9c8019c78c92 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -673,7 +673,10 @@ xfs_vn_fiemap(
 		bm.bmv_length = BTOBB(length);
 
 	/* We add one because in getbmap world count includes the header */
-	bm.bmv_count = fieinfo->fi_extents_max + 1;
+	bm.bmv_count = !fieinfo->fi_extents_max ? MAXEXTNUM :
+					fieinfo->fi_extents_max + 1;
+	bm.bmv_count = min_t(__s32, bm.bmv_count,
+			     (PAGE_SIZE * 16 / sizeof(struct getbmapx)));
 	bm.bmv_iflags = BMV_IF_PREALLOC;
 	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
 		bm.bmv_iflags |= BMV_IF_ATTRFORK;
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index 1947514ce1ad..e31bf21fe5d3 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -97,7 +97,7 @@ xfs_fs_set_xstate(
 }
 
 STATIC int
-xfs_fs_get_xquota(
+xfs_fs_get_dqblk(
 	struct super_block	*sb,
 	int			type,
 	qid_t			id,
@@ -114,7 +114,7 @@ xfs_fs_get_xquota(
 }
 
 STATIC int
-xfs_fs_set_xquota(
+xfs_fs_set_dqblk(
 	struct super_block	*sb,
 	int			type,
 	qid_t			id,
@@ -135,6 +135,6 @@ xfs_fs_set_xquota(
 const struct quotactl_ops xfs_quotactl_operations = {
 	.get_xstate		= xfs_fs_get_xstate,
 	.set_xstate		= xfs_fs_set_xstate,
-	.get_xquota		= xfs_fs_get_xquota,
-	.set_xquota		= xfs_fs_set_xquota,
+	.get_dqblk		= xfs_fs_get_dqblk,
+	.set_dqblk		= xfs_fs_set_dqblk,
 };
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 2b177c778ba7..f24dbe5efde3 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -790,18 +790,18 @@ xfs_open_devices(
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0);
+	mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0, mp->m_fsname);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1, mp->m_fsname);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1);
+		mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1, mp->m_fsname);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -903,7 +903,8 @@ xfsaild_start(
 	struct xfs_ail	*ailp)
 {
 	ailp->xa_target = 0;
-	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild");
+	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
+				    ailp->xa_mount->m_fsname);
 	if (IS_ERR(ailp->xa_task))
 		return -PTR_ERR(ailp->xa_task);
 	return 0;
@@ -1093,6 +1094,7 @@ xfs_fs_write_inode(
 		 * the code will only flush the inode if it isn't already
 		 * being flushed.
 		 */
+		xfs_ioend_wait(ip);
 		xfs_ilock(ip, XFS_ILOCK_SHARED);
 		if (ip->i_update_core) {
 			error = xfs_log_inode(ip);
@@ -1210,6 +1212,7 @@ xfs_fs_put_super(
 
 	xfs_unmountfs(mp);
 	xfs_freesb(mp);
+	xfs_inode_shrinker_unregister(mp);
 	xfs_icsb_destroy_counters(mp);
 	xfs_close_devices(mp);
 	xfs_dmops_put(mp);
@@ -1623,6 +1626,8 @@ xfs_fs_fill_super(
 	if (error)
 		goto fail_vnrele;
 
+	xfs_inode_shrinker_register(mp);
+
 	kfree(mtpt);
 	return 0;
 
@@ -1868,6 +1873,7 @@ init_xfs_fs(void)
 		goto out_cleanup_procfs;
 
 	vfs_initquota();
+	xfs_inode_shrinker_init();
 
 	error = register_filesystem(&xfs_fs_type);
 	if (error)
@@ -1895,6 +1901,7 @@ exit_xfs_fs(void)
 {
 	vfs_exitquota();
 	unregister_filesystem(&xfs_fs_type);
+	xfs_inode_shrinker_destroy();
 	xfs_sysctl_unregister();
 	xfs_cleanup_procfs();
 	xfs_buf_terminate();
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index fd9698215759..3884e20bc14e 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -95,7 +95,8 @@ xfs_inode_ag_walk(
 					   struct xfs_perag *pag, int flags),
 	int			flags,
 	int			tag,
-	int			exclusive)
+	int			exclusive,
+	int			*nr_to_scan)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
@@ -134,7 +135,7 @@ restart:
 		if (error == EFSCORRUPTED)
 			break;
 
-	} while (1);
+	} while ((*nr_to_scan)--);
 
 	if (skipped) {
 		delay(1);
@@ -150,12 +151,15 @@ xfs_inode_ag_iterator(
 					   struct xfs_perag *pag, int flags),
 	int			flags,
 	int			tag,
-	int			exclusive)
+	int			exclusive,
+	int			*nr_to_scan)
 {
 	int			error = 0;
 	int			last_error = 0;
 	xfs_agnumber_t		ag;
+	int			nr;
 
+	nr = nr_to_scan ? *nr_to_scan : INT_MAX;
 	for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
 		struct xfs_perag	*pag;
 
@@ -165,14 +169,18 @@ xfs_inode_ag_iterator(
 			continue;
 		}
 		error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
-						exclusive);
+						exclusive, &nr);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
 			if (error == EFSCORRUPTED)
 				break;
 		}
+		if (nr <= 0)
+			break;
 	}
+	if (nr_to_scan)
+		*nr_to_scan = nr;
 	return XFS_ERROR(last_error);
 }
 
@@ -291,7 +299,7 @@ xfs_sync_data(
 	ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
 
 	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags,
-				      XFS_ICI_NO_TAG, 0);
+				      XFS_ICI_NO_TAG, 0, NULL);
 	if (error)
 		return XFS_ERROR(error);
 
@@ -310,7 +318,7 @@ xfs_sync_attr(
 	ASSERT((flags & ~SYNC_WAIT) == 0);
 
 	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags,
-				     XFS_ICI_NO_TAG, 0);
+				     XFS_ICI_NO_TAG, 0, NULL);
 }
 
 STATIC int
@@ -348,68 +356,23 @@ xfs_commit_dummy_trans(
 
 STATIC int
 xfs_sync_fsdata(
-	struct xfs_mount	*mp,
-	int			flags)
+	struct xfs_mount	*mp)
 {
 	struct xfs_buf		*bp;
-	struct xfs_buf_log_item	*bip;
-	int			error = 0;
-
-	/*
-	 * If this is xfssyncd() then only sync the superblock if we can
-	 * lock it without sleeping and it is not pinned.
-	 */
-	if (flags & SYNC_TRYLOCK) {
-		ASSERT(!(flags & SYNC_WAIT));
-
-		bp = xfs_getsb(mp, XBF_TRYLOCK);
-		if (!bp)
-			goto out;
-
-		bip = XFS_BUF_FSPRIVATE(bp, struct xfs_buf_log_item *);
-		if (!bip || !xfs_buf_item_dirty(bip) || XFS_BUF_ISPINNED(bp))
-			goto out_brelse;
-	} else {
-		bp = xfs_getsb(mp, 0);
-
-		/*
-		 * If the buffer is pinned then push on the log so we won't
-		 * get stuck waiting in the write for someone, maybe
-		 * ourselves, to flush the log.
-		 *
-		 * Even though we just pushed the log above, we did not have
-		 * the superblock buffer locked at that point so it can
-		 * become pinned in between there and here.
-		 */
-		if (XFS_BUF_ISPINNED(bp))
-			xfs_log_force(mp, 0);
-	}
-
-
-	if (flags & SYNC_WAIT)
-		XFS_BUF_UNASYNC(bp);
-	else
-		XFS_BUF_ASYNC(bp);
-
-	error = xfs_bwrite(mp, bp);
-	if (error)
-		return error;
 
 	/*
-	 * If this is a data integrity sync make sure all pending buffers
-	 * are flushed out for the log coverage check below.
+	 * If the buffer is pinned then push on the log so we won't get stuck
+	 * waiting in the write for someone, maybe ourselves, to flush the log.
+	 *
+	 * Even though we just pushed the log above, we did not have the
+	 * superblock buffer locked at that point so it can become pinned in
+	 * between there and here.
 	 */
-	if (flags & SYNC_WAIT)
-		xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
-	if (xfs_log_need_covered(mp))
-		error = xfs_commit_dummy_trans(mp, flags);
-	return error;
+	bp = xfs_getsb(mp, 0);
+	if (XFS_BUF_ISPINNED(bp))
+		xfs_log_force(mp, 0);
 
- out_brelse:
-	xfs_buf_relse(bp);
- out:
-	return error;
+	return xfs_bwrite(mp, bp);
 }
 
 /*
@@ -433,7 +396,7 @@ int
 xfs_quiesce_data(
 	struct xfs_mount	*mp)
 {
-	int error;
+	int			error, error2 = 0;
 
 	/* push non-blocking */
 	xfs_sync_data(mp, 0);
@@ -444,13 +407,20 @@ xfs_quiesce_data(
 	xfs_qm_sync(mp, SYNC_WAIT);
 
 	/* write superblock and hoover up shutdown errors */
-	error = xfs_sync_fsdata(mp, SYNC_WAIT);
+	error = xfs_sync_fsdata(mp);
+
+	/* make sure all delwri buffers are written out */
+	xfs_flush_buftarg(mp->m_ddev_targp, 1);
+
+	/* mark the log as covered if needed */
+	if (xfs_log_need_covered(mp))
+		error2 = xfs_commit_dummy_trans(mp, SYNC_WAIT);
 
 	/* flush data-only devices */
 	if (mp->m_rtdev_targp)
 		XFS_bflush(mp->m_rtdev_targp);
 
-	return error;
+	return error ? error : error2;
 }
 
 STATIC void
@@ -573,9 +543,9 @@ xfs_flush_inodes(
 }
 
 /*
- * Every sync period we need to unpin all items, reclaim inodes, sync
- * quota and write out the superblock. We might need to cover the log
- * to indicate it is idle.
+ * Every sync period we need to unpin all items, reclaim inodes and sync
+ * disk quotas.  We might need to cover the log to indicate that the
+ * filesystem is idle.
  */
 STATIC void
 xfs_sync_worker(
@@ -589,7 +559,8 @@ xfs_sync_worker(
 		xfs_reclaim_inodes(mp, 0);
 		/* dgc: errors ignored here */
 		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
-		error = xfs_sync_fsdata(mp, SYNC_TRYLOCK);
+		if (xfs_log_need_covered(mp))
+			error = xfs_commit_dummy_trans(mp, 0);
 	}
 	mp->m_sync_seq++;
 	wake_up(&mp->m_wait_single_sync_task);
@@ -652,7 +623,7 @@ xfs_syncd_init(
 	mp->m_sync_work.w_syncer = xfs_sync_worker;
 	mp->m_sync_work.w_mount = mp;
 	mp->m_sync_work.w_completion = NULL;
-	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
+	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd/%s", mp->m_fsname);
 	if (IS_ERR(mp->m_sync_task))
 		return -PTR_ERR(mp->m_sync_task);
 	return 0;
@@ -673,6 +644,7 @@ __xfs_inode_set_reclaim_tag(
 	radix_tree_tag_set(&pag->pag_ici_root,
 			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
 			   XFS_ICI_RECLAIM_TAG);
+	pag->pag_ici_reclaimable++;
 }
 
 /*
@@ -705,6 +677,7 @@ __xfs_inode_clear_reclaim_tag(
 {
 	radix_tree_tag_clear(&pag->pag_ici_root,
 			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+	pag->pag_ici_reclaimable--;
 }
 
 /*
@@ -854,5 +827,93 @@ xfs_reclaim_inodes(
 	int		mode)
 {
 	return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode,
-					XFS_ICI_RECLAIM_TAG, 1);
+					XFS_ICI_RECLAIM_TAG, 1, NULL);
+}
+
+/*
+ * Shrinker infrastructure.
+ *
+ * This is all far more complex than it needs to be. It adds a global list of
+ * mounts because the shrinkers can only call a global context. We need to make
+ * the shrinkers pass a context to avoid the need for global state.
+ */
+static LIST_HEAD(xfs_mount_list);
+static struct rw_semaphore xfs_mount_list_lock;
+
+static int
+xfs_reclaim_inode_shrink(
+	int		nr_to_scan,
+	gfp_t		gfp_mask)
+{
+	struct xfs_mount *mp;
+	struct xfs_perag *pag;
+	xfs_agnumber_t	ag;
+	int		reclaimable = 0;
+
+	if (nr_to_scan) {
+		if (!(gfp_mask & __GFP_FS))
+			return -1;
+
+		down_read(&xfs_mount_list_lock);
+		list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
+			xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
+					XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan);
+			if (nr_to_scan <= 0)
+				break;
+		}
+		up_read(&xfs_mount_list_lock);
+	}
+
+	down_read(&xfs_mount_list_lock);
+	list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
+		for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
+
+			pag = xfs_perag_get(mp, ag);
+			if (!pag->pag_ici_init) {
+				xfs_perag_put(pag);
+				continue;
+			}
+			reclaimable += pag->pag_ici_reclaimable;
+			xfs_perag_put(pag);
+		}
+	}
+	up_read(&xfs_mount_list_lock);
+	return reclaimable;
+}
+
+static struct shrinker xfs_inode_shrinker = {
+	.shrink = xfs_reclaim_inode_shrink,
+	.seeks = DEFAULT_SEEKS,
+};
+
+void __init
+xfs_inode_shrinker_init(void)
+{
+	init_rwsem(&xfs_mount_list_lock);
+	register_shrinker(&xfs_inode_shrinker);
+}
+
+void
+xfs_inode_shrinker_destroy(void)
+{
+	ASSERT(list_empty(&xfs_mount_list));
+	unregister_shrinker(&xfs_inode_shrinker);
+}
+
+void
+xfs_inode_shrinker_register(
+	struct xfs_mount	*mp)
+{
+	down_write(&xfs_mount_list_lock);
+	list_add_tail(&mp->m_mplist, &xfs_mount_list);
+	up_write(&xfs_mount_list_lock);
+}
+
+void
+xfs_inode_shrinker_unregister(
+	struct xfs_mount	*mp)
+{
+	down_write(&xfs_mount_list_lock);
+	list_del(&mp->m_mplist);
+	up_write(&xfs_mount_list_lock);
 }
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index d480c346cabb..cdcbaaca9880 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -53,6 +53,11 @@ void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
 int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
-	int flags, int tag, int write_lock);
+	int flags, int tag, int write_lock, int *nr_to_scan);
+
+void xfs_inode_shrinker_init(void);
+void xfs_inode_shrinker_destroy(void);
+void xfs_inode_shrinker_register(struct xfs_mount *mp);
+void xfs_inode_shrinker_unregister(struct xfs_mount *mp);
 
 #endif
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/linux-2.6/xfs_trace.c
index 5a107601e969..207fa77f63ae 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/linux-2.6/xfs_trace.c
@@ -41,7 +41,6 @@
 #include "xfs_alloc.h"
 #include "xfs_bmap.h"
 #include "xfs_attr.h"
-#include "xfs_attr_sf.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_log_priv.h"
 #include "xfs_buf_item.h"
@@ -50,6 +49,9 @@
 #include "xfs_aops.h"
 #include "quota/xfs_dquot_item.h"
 #include "quota/xfs_dquot.h"
+#include "xfs_log_recover.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode_item.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index fcaa62f0799e..8a319cfd2901 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -32,6 +32,10 @@ struct xfs_da_node_entry;
 struct xfs_dquot;
 struct xlog_ticket;
 struct log;
+struct xlog_recover;
+struct xlog_recover_item;
+struct xfs_buf_log_format;
+struct xfs_inode_log_format;
 
 DECLARE_EVENT_CLASS(xfs_attr_list_class,
 	TP_PROTO(struct xfs_attr_list_context *ctx),
@@ -562,18 +566,21 @@ DECLARE_EVENT_CLASS(xfs_inode_class,
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
 		__field(int, count)
+		__field(int, pincount)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
 		__entry->count = atomic_read(&VFS_I(ip)->i_count);
+		__entry->pincount = atomic_read(&ip->i_pincount);
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ino 0x%llx count %d caller %pf",
+	TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %pf",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->count,
+		  __entry->pincount,
 		  (char *)__entry->caller_ip)
 )
 
@@ -583,6 +590,10 @@ DEFINE_EVENT(xfs_inode_class, name, \
 	TP_ARGS(ip, caller_ip))
 DEFINE_INODE_EVENT(xfs_ihold);
 DEFINE_INODE_EVENT(xfs_irele);
+DEFINE_INODE_EVENT(xfs_inode_pin);
+DEFINE_INODE_EVENT(xfs_inode_unpin);
+DEFINE_INODE_EVENT(xfs_inode_unpin_nowait);
+
 /* the old xfs_itrace_entry tracer - to be replaced by s.th. in the VFS */
 DEFINE_INODE_EVENT(xfs_inode);
 #define xfs_itrace_entry(ip)    \
@@ -642,8 +653,6 @@ DEFINE_EVENT(xfs_dquot_class, name, \
 	TP_PROTO(struct xfs_dquot *dqp), \
 	TP_ARGS(dqp))
 DEFINE_DQUOT_EVENT(xfs_dqadjust);
-DEFINE_DQUOT_EVENT(xfs_dqshake_dirty);
-DEFINE_DQUOT_EVENT(xfs_dqshake_unlink);
 DEFINE_DQUOT_EVENT(xfs_dqreclaim_want);
 DEFINE_DQUOT_EVENT(xfs_dqreclaim_dirty);
 DEFINE_DQUOT_EVENT(xfs_dqreclaim_unlink);
@@ -658,7 +667,6 @@ DEFINE_DQUOT_EVENT(xfs_dqread_fail);
 DEFINE_DQUOT_EVENT(xfs_dqlookup_found);
 DEFINE_DQUOT_EVENT(xfs_dqlookup_want);
 DEFINE_DQUOT_EVENT(xfs_dqlookup_freelist);
-DEFINE_DQUOT_EVENT(xfs_dqlookup_move);
 DEFINE_DQUOT_EVENT(xfs_dqlookup_done);
 DEFINE_DQUOT_EVENT(xfs_dqget_hit);
 DEFINE_DQUOT_EVENT(xfs_dqget_miss);
@@ -1495,6 +1503,140 @@ DEFINE_EVENT(xfs_swap_extent_class, name, \
 DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before);
 DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after);
 
+DECLARE_EVENT_CLASS(xfs_log_recover_item_class,
+	TP_PROTO(struct log *log, struct xlog_recover *trans,
+		struct xlog_recover_item *item, int pass),
+	TP_ARGS(log, trans, item, pass),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long, item)
+		__field(xlog_tid_t, tid)
+		__field(int, type)
+		__field(int, pass)
+		__field(int, count)
+		__field(int, total)
+	),
+	TP_fast_assign(
+		__entry->dev = log->l_mp->m_super->s_dev;
+		__entry->item = (unsigned long)item;
+		__entry->tid = trans->r_log_tid;
+		__entry->type = ITEM_TYPE(item);
+		__entry->pass = pass;
+		__entry->count = item->ri_cnt;
+		__entry->total = item->ri_total;
+	),
+	TP_printk("dev %d:%d trans 0x%x, pass %d, item 0x%p, item type %s "
+		  "item region count/total %d/%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->tid,
+		  __entry->pass,
+		  (void *)__entry->item,
+		  __print_symbolic(__entry->type, XFS_LI_TYPE_DESC),
+		  __entry->count,
+		  __entry->total)
+)
+
+#define DEFINE_LOG_RECOVER_ITEM(name) \
+DEFINE_EVENT(xfs_log_recover_item_class, name, \
+	TP_PROTO(struct log *log, struct xlog_recover *trans, \
+		struct xlog_recover_item *item, int pass), \
+	TP_ARGS(log, trans, item, pass))
+
+DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_add);
+DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_add_cont);
+DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_head);
+DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_tail);
+DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_recover);
+
+DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class,
+	TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f),
+	TP_ARGS(log, buf_f),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(__int64_t, blkno)
+		__field(unsigned short, len)
+		__field(unsigned short, flags)
+		__field(unsigned short, size)
+		__field(unsigned int, map_size)
+	),
+	TP_fast_assign(
+		__entry->dev = log->l_mp->m_super->s_dev;
+		__entry->blkno = buf_f->blf_blkno;
+		__entry->len = buf_f->blf_len;
+		__entry->flags = buf_f->blf_flags;
+		__entry->size = buf_f->blf_size;
+		__entry->map_size = buf_f->blf_map_size;
+	),
+	TP_printk("dev %d:%d blkno 0x%llx, len %u, flags 0x%x, size %d, "
+			"map_size %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->blkno,
+		  __entry->len,
+		  __entry->flags,
+		  __entry->size,
+		  __entry->map_size)
+)
+
+#define DEFINE_LOG_RECOVER_BUF_ITEM(name) \
+DEFINE_EVENT(xfs_log_recover_buf_item_class, name, \
+	TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), \
+	TP_ARGS(log, buf_f))
+
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_not_cancel);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel_add);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel_ref_inc);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_recover);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_inode_buf);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_reg_buf);
+DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_dquot_buf);
+
+DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class,
+	TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f),
+	TP_ARGS(log, in_f),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(unsigned short, size)
+		__field(int, fields)
+		__field(unsigned short, asize)
+		__field(unsigned short, dsize)
+		__field(__int64_t, blkno)
+		__field(int, len)
+		__field(int, boffset)
+	),
+	TP_fast_assign(
+		__entry->dev = log->l_mp->m_super->s_dev;
+		__entry->ino = in_f->ilf_ino;
+		__entry->size = in_f->ilf_size;
+		__entry->fields = in_f->ilf_fields;
+		__entry->asize = in_f->ilf_asize;
+		__entry->dsize = in_f->ilf_dsize;
+		__entry->blkno = in_f->ilf_blkno;
+		__entry->len = in_f->ilf_len;
+		__entry->boffset = in_f->ilf_boffset;
+	),
+	TP_printk("dev %d:%d ino 0x%llx, size %u, fields 0x%x, asize %d, "
+			"dsize %d, blkno 0x%llx, len %d, boffset %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->fields,
+		  __entry->asize,
+		  __entry->dsize,
+		  __entry->blkno,
+		  __entry->len,
+		  __entry->boffset)
+)
+#define DEFINE_LOG_RECOVER_INO_ITEM(name) \
+DEFINE_EVENT(xfs_log_recover_ino_item_class, name, \
+	TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), \
+	TP_ARGS(log, in_f))
+
+DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover);
+DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_cancel);
+DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_skip);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH