Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

Pull XFS update from Ben Myers:

 - Removal of xfsbufd
 - Background CIL flushes have been moved to a workqueue.
 - Fix to xfs_check_page_type applicable to filesystems where
   blocksize < page size
 - Fix for stale data exposure when extsize hints are used.
 - A series of xfs_buf cache cleanups.
 - Fix for XFS_IOC_ALLOCSP
 - Cleanups for includes and removal of xfs_lrw.[ch].
 - Moved all busy extent handling to it's own file so that it is easier
   to merge with userspace.
 - Fix for log mount failure.
 - Fix to enable inode reclaim during quotacheck at mount time.
 - Fix for delalloc quota accounting.
 - Fix for memory reclaim deadlock on agi buffer.
 - Fixes for failed writes and to clean up stale delalloc blocks.
 - Fix to use GFP_NOFS in blkdev_issue_flush
 - SEEK_DATA/SEEK_HOLE support

* 'for-linus' of git://oss.sgi.com/xfs/xfs: (57 commits)
  xfs: add trace points for log forces
  xfs: fix memory reclaim deadlock on agi buffer
  xfs: fix delalloc quota accounting on failure
  xfs: protect xfs_sync_worker with s_umount semaphore
  xfs: introduce SEEK_DATA/SEEK_HOLE support
  xfs: make xfs_extent_busy_trim not static
  xfs: make XBF_MAPPED the default behaviour
  xfs: flush outstanding buffers on log mount failure
  xfs: Properly exclude IO type flags from buffer flags
  xfs: clean up xfs_bit.h includes
  xfs: move xfs_do_force_shutdown() and kill xfs_rw.c
  xfs: move xfs_get_extsz_hint() and kill xfs_rw.h
  xfs: move xfs_fsb_to_db to xfs_bmap.h
  xfs: clean up busy extent naming
  xfs: move busy extent handling to it's own file
  xfs: move xfsagino_t to xfs_types.h
  xfs: use iolock on XFS_IOC_ALLOCSP calls
  xfs: kill XBF_DONTBLOCK
  xfs: kill xfs_read_buf()
  xfs: kill XBF_LOCK
  ...

MAINTAINERS

@@ -7623,7 +7623,7 @@ XFS FILESYSTEM
 P:	Silicon Graphics Inc
 M:	Ben Myers <bpm@sgi.com>
 M:	Alex Elder <elder@kernel.org>
-M:	xfs-masters@oss.sgi.com
+M:	xfs@oss.sgi.com
 L:	xfs@oss.sgi.com
 W:	http://oss.sgi.com/projects/xfs
 T:	git git://oss.sgi.com/xfs/xfs.git

fs/xfs/Makefile

@@ -33,6 +33,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_discard.o \
 				   xfs_error.o \
 				   xfs_export.o \
+				   xfs_extent_busy.o \
 				   xfs_file.o \
 				   xfs_filestream.o \
 				   xfs_fsops.o \
@@ -49,7 +50,6 @@ xfs-y				+= xfs_aops.o \
 				   xfs_sync.o \
 				   xfs_xattr.o \
 				   xfs_rename.o \
-				   xfs_rw.o \
 				   xfs_utils.o \
 				   xfs_vnodeops.o \
 				   kmem.o \

fs/xfs/xfs_ag.h

@@ -174,24 +174,6 @@ typedef struct xfs_agfl {
 	__be32		agfl_bno[1];	/* actually XFS_AGFL_SIZE(mp) */
 } xfs_agfl_t;
 
-/*
- * Busy block/extent entry.  Indexed by a rbtree in perag to mark blocks that
- * have been freed but whose transactions aren't committed to disk yet.
- *
- * Note that we use the transaction ID to record the transaction, not the
- * transaction structure itself. See xfs_alloc_busy_insert() for details.
- */
-struct xfs_busy_extent {
-	struct rb_node	rb_node;	/* ag by-bno indexed search tree */
-	struct list_head list;		/* transaction busy extent list */
-	xfs_agnumber_t	agno;
-	xfs_agblock_t	bno;
-	xfs_extlen_t	length;
-	unsigned int	flags;
-#define XFS_ALLOC_BUSY_DISCARDED	0x01	/* undergoing a discard op. */
-#define XFS_ALLOC_BUSY_SKIP_DISCARD	0x02	/* do not discard */
-};
-
 /*
  * Per-ag incore structure, copies of information in agf and agi,
  * to improve the performance of allocation group selection.

fs/xfs/xfs_alloc.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -32,6 +31,7 @@
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_alloc.h"
+#include "xfs_extent_busy.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 
@@ -47,8 +47,6 @@ STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *,
 		xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *);
-STATIC void xfs_alloc_busy_trim(struct xfs_alloc_arg *,
-		xfs_agblock_t, xfs_extlen_t, xfs_agblock_t *, xfs_extlen_t *);
 
 /*
  * Lookup the record equal to [bno, len] in the btree given by cur.
@@ -152,7 +150,7 @@ xfs_alloc_compute_aligned(
 	xfs_extlen_t	len;
 
 	/* Trim busy sections out of found extent */
-	xfs_alloc_busy_trim(args, foundbno, foundlen, &bno, &len);
+	xfs_extent_busy_trim(args, foundbno, foundlen, &bno, &len);
 
 	if (args->alignment > 1 && len >= args->minlen) {
 		xfs_agblock_t	aligned_bno = roundup(bno, args->alignment);
@@ -536,7 +534,7 @@ xfs_alloc_ag_vextent(
 		if (error)
 			return error;
 
-		ASSERT(!xfs_alloc_busy_search(args->mp, args->agno,
+		ASSERT(!xfs_extent_busy_search(args->mp, args->agno,
 					      args->agbno, args->len));
 	}
 
@@ -603,7 +601,7 @@ xfs_alloc_ag_vextent_exact(
 	/*
 	 * Check for overlapping busy extents.
 	 */
-	xfs_alloc_busy_trim(args, fbno, flen, &tbno, &tlen);
+	xfs_extent_busy_trim(args, fbno, flen, &tbno, &tlen);
 
 	/*
 	 * Give up if the start of the extent is busy, or the freespace isn't
@@ -1391,7 +1389,7 @@ xfs_alloc_ag_vextent_small(
 		if (error)
 			goto error0;
 		if (fbno != NULLAGBLOCK) {
-			xfs_alloc_busy_reuse(args->mp, args->agno, fbno, 1,
+			xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1,
 					     args->userdata);
 
 			if (args->userdata) {
@@ -2496,579 +2494,8 @@ xfs_free_extent(
 
 	error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
 	if (!error)
-		xfs_alloc_busy_insert(tp, args.agno, args.agbno, len, 0);
+		xfs_extent_busy_insert(tp, args.agno, args.agbno, len, 0);
 error0:
 	xfs_perag_put(args.pag);
 	return error;
 }
-
-void
-xfs_alloc_busy_insert(
-	struct xfs_trans	*tp,
-	xfs_agnumber_t		agno,
-	xfs_agblock_t		bno,
-	xfs_extlen_t		len,
-	unsigned int		flags)
-{
-	struct xfs_busy_extent	*new;
-	struct xfs_busy_extent	*busyp;
-	struct xfs_perag	*pag;
-	struct rb_node		**rbp;
-	struct rb_node		*parent = NULL;
-
-	new = kmem_zalloc(sizeof(struct xfs_busy_extent), KM_MAYFAIL);
-	if (!new) {
-		/*
-		 * No Memory!  Since it is now not possible to track the free
-		 * block, make this a synchronous transaction to insure that
-		 * the block is not reused before this transaction commits.
-		 */
-		trace_xfs_alloc_busy_enomem(tp->t_mountp, agno, bno, len);
-		xfs_trans_set_sync(tp);
-		return;
-	}
-
-	new->agno = agno;
-	new->bno = bno;
-	new->length = len;
-	INIT_LIST_HEAD(&new->list);
-	new->flags = flags;
-
-	/* trace before insert to be able to see failed inserts */
-	trace_xfs_alloc_busy(tp->t_mountp, agno, bno, len);
-
-	pag = xfs_perag_get(tp->t_mountp, new->agno);
-	spin_lock(&pag->pagb_lock);
-	rbp = &pag->pagb_tree.rb_node;
-	while (*rbp) {
-		parent = *rbp;
-		busyp = rb_entry(parent, struct xfs_busy_extent, rb_node);
-
-		if (new->bno < busyp->bno) {
-			rbp = &(*rbp)->rb_left;
-			ASSERT(new->bno + new->length <= busyp->bno);
-		} else if (new->bno > busyp->bno) {
-			rbp = &(*rbp)->rb_right;
-			ASSERT(bno >= busyp->bno + busyp->length);
-		} else {
-			ASSERT(0);
-		}
-	}
-
-	rb_link_node(&new->rb_node, parent, rbp);
-	rb_insert_color(&new->rb_node, &pag->pagb_tree);
-
-	list_add(&new->list, &tp->t_busy);
-	spin_unlock(&pag->pagb_lock);
-	xfs_perag_put(pag);
-}
-
-/*
- * Search for a busy extent within the range of the extent we are about to
- * allocate.  You need to be holding the busy extent tree lock when calling
- * xfs_alloc_busy_search(). This function returns 0 for no overlapping busy
- * extent, -1 for an overlapping but not exact busy extent, and 1 for an exact
- * match. This is done so that a non-zero return indicates an overlap that
- * will require a synchronous transaction, but it can still be
- * used to distinguish between a partial or exact match.
- */
-int
-xfs_alloc_busy_search(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno,
-	xfs_agblock_t		bno,
-	xfs_extlen_t		len)
-{
-	struct xfs_perag	*pag;
-	struct rb_node		*rbp;
-	struct xfs_busy_extent	*busyp;
-	int			match = 0;
-
-	pag = xfs_perag_get(mp, agno);
-	spin_lock(&pag->pagb_lock);
-
-	rbp = pag->pagb_tree.rb_node;
-
-	/* find closest start bno overlap */
-	while (rbp) {
-		busyp = rb_entry(rbp, struct xfs_busy_extent, rb_node);
-		if (bno < busyp->bno) {
-			/* may overlap, but exact start block is lower */
-			if (bno + len > busyp->bno)
-				match = -1;
-			rbp = rbp->rb_left;
-		} else if (bno > busyp->bno) {
-			/* may overlap, but exact start block is higher */
-			if (bno < busyp->bno + busyp->length)
-				match = -1;
-			rbp = rbp->rb_right;
-		} else {
-			/* bno matches busyp, length determines exact match */
-			match = (busyp->length == len) ? 1 : -1;
-			break;
-		}
-	}
-	spin_unlock(&pag->pagb_lock);
-	xfs_perag_put(pag);
-	return match;
-}
-
-/*
- * The found free extent [fbno, fend] overlaps part or all of the given busy
- * extent.  If the overlap covers the beginning, the end, or all of the busy
- * extent, the overlapping portion can be made unbusy and used for the
- * allocation.  We can't split a busy extent because we can't modify a
- * transaction/CIL context busy list, but we can update an entries block
- * number or length.
- *
- * Returns true if the extent can safely be reused, or false if the search
- * needs to be restarted.
- */
-STATIC bool
-xfs_alloc_busy_update_extent(
-	struct xfs_mount	*mp,
-	struct xfs_perag	*pag,
-	struct xfs_busy_extent	*busyp,
-	xfs_agblock_t		fbno,
-	xfs_extlen_t		flen,
-	bool			userdata)
-{
-	xfs_agblock_t		fend = fbno + flen;
-	xfs_agblock_t		bbno = busyp->bno;
-	xfs_agblock_t		bend = bbno + busyp->length;
-
-	/*
-	 * This extent is currently being discarded.  Give the thread
-	 * performing the discard a chance to mark the extent unbusy
-	 * and retry.
-	 */
-	if (busyp->flags & XFS_ALLOC_BUSY_DISCARDED) {
-		spin_unlock(&pag->pagb_lock);
-		delay(1);
-		spin_lock(&pag->pagb_lock);
-		return false;
-	}
-
-	/*
-	 * If there is a busy extent overlapping a user allocation, we have
-	 * no choice but to force the log and retry the search.
-	 *
-	 * Fortunately this does not happen during normal operation, but
-	 * only if the filesystem is very low on space and has to dip into
-	 * the AGFL for normal allocations.
-	 */
-	if (userdata)
-		goto out_force_log;
-
-	if (bbno < fbno && bend > fend) {
-		/*
-		 * Case 1:
-		 *    bbno           bend
-		 *    +BBBBBBBBBBBBBBBBB+
-		 *        +---------+
-		 *        fbno   fend
-		 */
-
-		/*
-		 * We would have to split the busy extent to be able to track
-		 * it correct, which we cannot do because we would have to
-		 * modify the list of busy extents attached to the transaction
-		 * or CIL context, which is immutable.
-		 *
-		 * Force out the log to clear the busy extent and retry the
-		 * search.
-		 */
-		goto out_force_log;
-	} else if (bbno >= fbno && bend <= fend) {
-		/*
-		 * Case 2:
-		 *    bbno           bend
-		 *    +BBBBBBBBBBBBBBBBB+
-		 *    +-----------------+
-		 *    fbno           fend
-		 *
-		 * Case 3:
-		 *    bbno           bend
-		 *    +BBBBBBBBBBBBBBBBB+
-		 *    +--------------------------+
-		 *    fbno                    fend
-		 *
-		 * Case 4:
-		 *             bbno           bend
-		 *             +BBBBBBBBBBBBBBBBB+
-		 *    +--------------------------+
-		 *    fbno                    fend
-		 *
-		 * Case 5:
-		 *             bbno           bend
-		 *             +BBBBBBBBBBBBBBBBB+
-		 *    +-----------------------------------+
-		 *    fbno                             fend
-		 *
-		 */
-
-		/*
-		 * The busy extent is fully covered by the extent we are
-		 * allocating, and can simply be removed from the rbtree.
-		 * However we cannot remove it from the immutable list
-		 * tracking busy extents in the transaction or CIL context,
-		 * so set the length to zero to mark it invalid.
-		 *
-		 * We also need to restart the busy extent search from the
-		 * tree root, because erasing the node can rearrange the
-		 * tree topology.
-		 */
-		rb_erase(&busyp->rb_node, &pag->pagb_tree);
-		busyp->length = 0;
-		return false;
-	} else if (fend < bend) {
-		/*
-		 * Case 6:
-		 *              bbno           bend
-		 *             +BBBBBBBBBBBBBBBBB+
-		 *             +---------+
-		 *             fbno   fend
-		 *
-		 * Case 7:
-		 *             bbno           bend
-		 *             +BBBBBBBBBBBBBBBBB+
-		 *    +------------------+
-		 *    fbno            fend
-		 *
-		 */
-		busyp->bno = fend;
-	} else if (bbno < fbno) {
-		/*
-		 * Case 8:
-		 *    bbno           bend
-		 *    +BBBBBBBBBBBBBBBBB+
-		 *        +-------------+
-		 *        fbno       fend
-		 *
-		 * Case 9:
-		 *    bbno           bend
-		 *    +BBBBBBBBBBBBBBBBB+
-		 *        +----------------------+
-		 *        fbno                fend
-		 */
-		busyp->length = fbno - busyp->bno;
-	} else {
-		ASSERT(0);
-	}
-
-	trace_xfs_alloc_busy_reuse(mp, pag->pag_agno, fbno, flen);
-	return true;
-
-out_force_log:
-	spin_unlock(&pag->pagb_lock);
-	xfs_log_force(mp, XFS_LOG_SYNC);
-	trace_xfs_alloc_busy_force(mp, pag->pag_agno, fbno, flen);
-	spin_lock(&pag->pagb_lock);
-	return false;
-}
-
-
-/*
- * For a given extent [fbno, flen], make sure we can reuse it safely.
- */
-void
-xfs_alloc_busy_reuse(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno,
-	xfs_agblock_t		fbno,
-	xfs_extlen_t		flen,
-	bool			userdata)
-{
-	struct xfs_perag	*pag;
-	struct rb_node		*rbp;
-
-	ASSERT(flen > 0);
-
-	pag = xfs_perag_get(mp, agno);
-	spin_lock(&pag->pagb_lock);
-restart:
-	rbp = pag->pagb_tree.rb_node;
-	while (rbp) {
-		struct xfs_busy_extent *busyp =
-			rb_entry(rbp, struct xfs_busy_extent, rb_node);
-		xfs_agblock_t	bbno = busyp->bno;
-		xfs_agblock_t	bend = bbno + busyp->length;
-
-		if (fbno + flen <= bbno) {
-			rbp = rbp->rb_left;
-			continue;
-		} else if (fbno >= bend) {
-			rbp = rbp->rb_right;
-			continue;
-		}
-
-		if (!xfs_alloc_busy_update_extent(mp, pag, busyp, fbno, flen,
-						  userdata))
-			goto restart;
-	}
-	spin_unlock(&pag->pagb_lock);
-	xfs_perag_put(pag);
-}
-
-/*
- * For a given extent [fbno, flen], search the busy extent list to find a
- * subset of the extent that is not busy.  If *rlen is smaller than
- * args->minlen no suitable extent could be found, and the higher level
- * code needs to force out the log and retry the allocation.
- */
-STATIC void
-xfs_alloc_busy_trim(
-	struct xfs_alloc_arg	*args,
-	xfs_agblock_t		bno,
-	xfs_extlen_t		len,
-	xfs_agblock_t		*rbno,
-	xfs_extlen_t		*rlen)
-{
-	xfs_agblock_t		fbno;
-	xfs_extlen_t		flen;
-	struct rb_node		*rbp;
-
-	ASSERT(len > 0);
-
-	spin_lock(&args->pag->pagb_lock);
-restart:
-	fbno = bno;
-	flen = len;
-	rbp = args->pag->pagb_tree.rb_node;
-	while (rbp && flen >= args->minlen) {
-		struct xfs_busy_extent *busyp =
-			rb_entry(rbp, struct xfs_busy_extent, rb_node);
-		xfs_agblock_t	fend = fbno + flen;
-		xfs_agblock_t	bbno = busyp->bno;
-		xfs_agblock_t	bend = bbno + busyp->length;
-
-		if (fend <= bbno) {
-			rbp = rbp->rb_left;
-			continue;
-		} else if (fbno >= bend) {
-			rbp = rbp->rb_right;
-			continue;
-		}
-
-		/*
-		 * If this is a metadata allocation, try to reuse the busy
-		 * extent instead of trimming the allocation.
-		 */
-		if (!args->userdata &&
-		    !(busyp->flags & XFS_ALLOC_BUSY_DISCARDED)) {
-			if (!xfs_alloc_busy_update_extent(args->mp, args->pag,
-							  busyp, fbno, flen,
-							  false))
-				goto restart;
-			continue;
-		}
-
-		if (bbno <= fbno) {
-			/* start overlap */
-
-			/*
-			 * Case 1:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *        +---------+
-			 *        fbno   fend
-			 *
-			 * Case 2:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *    +-------------+
-			 *    fbno       fend
-			 *
-			 * Case 3:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *        +-------------+
-			 *        fbno       fend
-			 *
-			 * Case 4:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *    +-----------------+
-			 *    fbno           fend
-			 *
-			 * No unbusy region in extent, return failure.
-			 */
-			if (fend <= bend)
-				goto fail;
-
-			/*
-			 * Case 5:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *        +----------------------+
-			 *        fbno                fend
-			 *
-			 * Case 6:
-			 *    bbno           bend
-			 *    +BBBBBBBBBBBBBBBBB+
-			 *    +--------------------------+
-			 *    fbno                    fend
-			 *
-			 * Needs to be trimmed to:
-			 *                       +-------+
-			 *                       fbno fend
-			 */
-			fbno = bend;
-		} else if (bend >= fend) {
-			/* end overlap */
-
-			/*
-			 * Case 7:
-			 *             bbno           bend
-			 *             +BBBBBBBBBBBBBBBBB+
-			 *    +------------------+
-			 *    fbno            fend
-			 *
-			 * Case 8:
-			 *             bbno           bend
-			 *             +BBBBBBBBBBBBBBBBB+
-			 *    +--------------------------+
-			 *    fbno                    fend
-			 *
-			 * Needs to be trimmed to:
-			 *    +-------+
-			 *    fbno fend
-			 */
-			fend = bbno;
-		} else {
-			/* middle overlap */
-
-			/*
-			 * Case 9:
-			 *             bbno           bend
-			 *             +BBBBBBBBBBBBBBBBB+
-			 *    +-----------------------------------+
-			 *    fbno                             fend
-			 *
-			 * Can be trimmed to:
-			 *    +-------+        OR         +-------+
-			 *    fbno fend                   fbno fend
-			 *
-			 * Backward allocation leads to significant
-			 * fragmentation of directories, which degrades
-			 * directory performance, therefore we always want to
-			 * choose the option that produces forward allocation
-			 * patterns.
-			 * Preferring the lower bno extent will make the next
-			 * request use "fend" as the start of the next
-			 * allocation;  if the segment is no longer busy at
-			 * that point, we'll get a contiguous allocation, but
-			 * even if it is still busy, we will get a forward
-			 * allocation.
-			 * We try to avoid choosing the segment at "bend",
-			 * because that can lead to the next allocation
-			 * taking the segment at "fbno", which would be a
-			 * backward allocation.  We only use the segment at
-			 * "fbno" if it is much larger than the current
-			 * requested size, because in that case there's a
-			 * good chance subsequent allocations will be
-			 * contiguous.
-			 */
-			if (bbno - fbno >= args->maxlen) {
-				/* left candidate fits perfect */
-				fend = bbno;
-			} else if (fend - bend >= args->maxlen * 4) {
-				/* right candidate has enough free space */
-				fbno = bend;
-			} else if (bbno - fbno >= args->minlen) {
-				/* left candidate fits minimum requirement */
-				fend = bbno;
-			} else {
-				goto fail;
-			}
-		}
-
-		flen = fend - fbno;
-	}
-	spin_unlock(&args->pag->pagb_lock);
-
-	if (fbno != bno || flen != len) {
-		trace_xfs_alloc_busy_trim(args->mp, args->agno, bno, len,
-					  fbno, flen);
-	}
-	*rbno = fbno;
-	*rlen = flen;
-	return;
-fail:
-	/*
-	 * Return a zero extent length as failure indications.  All callers
-	 * re-check if the trimmed extent satisfies the minlen requirement.
-	 */
-	spin_unlock(&args->pag->pagb_lock);
-	trace_xfs_alloc_busy_trim(args->mp, args->agno, bno, len, fbno, 0);
-	*rbno = fbno;
-	*rlen = 0;
-}
-
-static void
-xfs_alloc_busy_clear_one(
-	struct xfs_mount	*mp,
-	struct xfs_perag	*pag,
-	struct xfs_busy_extent	*busyp)
-{
-	if (busyp->length) {
-		trace_xfs_alloc_busy_clear(mp, busyp->agno, busyp->bno,
-						busyp->length);
-		rb_erase(&busyp->rb_node, &pag->pagb_tree);
-	}
-
-	list_del_init(&busyp->list);
-	kmem_free(busyp);
-}
-
-/*
- * Remove all extents on the passed in list from the busy extents tree.
- * If do_discard is set skip extents that need to be discarded, and mark
- * these as undergoing a discard operation instead.
- */
-void
-xfs_alloc_busy_clear(
-	struct xfs_mount	*mp,
-	struct list_head	*list,
-	bool			do_discard)
-{
-	struct xfs_busy_extent	*busyp, *n;
-	struct xfs_perag	*pag = NULL;
-	xfs_agnumber_t		agno = NULLAGNUMBER;
-
-	list_for_each_entry_safe(busyp, n, list, list) {
-		if (busyp->agno != agno) {
-			if (pag) {
-				spin_unlock(&pag->pagb_lock);
-				xfs_perag_put(pag);
-			}
-			pag = xfs_perag_get(mp, busyp->agno);
-			spin_lock(&pag->pagb_lock);
-			agno = busyp->agno;
-		}
-
-		if (do_discard && busyp->length &&
-		    !(busyp->flags & XFS_ALLOC_BUSY_SKIP_DISCARD))
-			busyp->flags = XFS_ALLOC_BUSY_DISCARDED;
-		else
-			xfs_alloc_busy_clear_one(mp, pag, busyp);
-	}
-
-	if (pag) {
-		spin_unlock(&pag->pagb_lock);
-		xfs_perag_put(pag);
-	}
-}
-
-/*
- * Callback for list_sort to sort busy extents by the AG they reside in.
- */
-int
-xfs_busy_extent_ag_cmp(
-	void			*priv,
-	struct list_head	*a,
-	struct list_head	*b)
-{
-	return container_of(a, struct xfs_busy_extent, list)->agno -
-		container_of(b, struct xfs_busy_extent, list)->agno;
-}

fs/xfs/xfs_alloc.h

@@ -23,7 +23,6 @@ struct xfs_btree_cur;
 struct xfs_mount;
 struct xfs_perag;
 struct xfs_trans;
-struct xfs_busy_extent;
 
 extern struct workqueue_struct *xfs_alloc_wq;
 
@@ -139,33 +138,6 @@ xfs_extlen_t
 xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 		struct xfs_perag *pag);
 
-#ifdef __KERNEL__
-void
-xfs_alloc_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno,
-	xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
-
-void
-xfs_alloc_busy_clear(struct xfs_mount *mp, struct list_head *list,
-	bool do_discard);
-
-int
-xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
-	xfs_agblock_t bno, xfs_extlen_t len);
-
-void
-xfs_alloc_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno,
-	xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
-
-int
-xfs_busy_extent_ag_cmp(void *priv, struct list_head *a, struct list_head *b);
-
-static inline void xfs_alloc_busy_sort(struct list_head *list)
-{
-	list_sort(NULL, list, xfs_busy_extent_ag_cmp);
-}
-
-#endif	/* __KERNEL__ */
-
 /*
  * Compute and fill in value of m_ag_maxlevels.
  */

fs/xfs/xfs_alloc_btree.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -32,6 +30,7 @@
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_alloc.h"
+#include "xfs_extent_busy.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 
@@ -94,7 +93,7 @@ xfs_allocbt_alloc_block(
 		return 0;
 	}
 
-	xfs_alloc_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false);
+	xfs_extent_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false);
 
 	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
@@ -119,8 +118,8 @@ xfs_allocbt_free_block(
 	if (error)
 		return error;
 
-	xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
-			      XFS_ALLOC_BUSY_SKIP_DISCARD);
+	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
+			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 	return 0;
 }

fs/xfs/xfs_aops.c

@@ -16,9 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_trans.h"
@@ -29,7 +27,6 @@
 #include "xfs_inode_item.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
-#include "xfs_rw.h"
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
@@ -623,7 +620,7 @@ xfs_map_at_offset(
  * or delayed allocate extent.
  */
 STATIC int
-xfs_is_delayed_page(
+xfs_check_page_type(
 	struct page		*page,
 	unsigned int		type)
 {
@@ -637,11 +634,11 @@ xfs_is_delayed_page(
 		bh = head = page_buffers(page);
 		do {
 			if (buffer_unwritten(bh))
-				acceptable = (type == IO_UNWRITTEN);
+				acceptable += (type == IO_UNWRITTEN);
 			else if (buffer_delay(bh))
-				acceptable = (type == IO_DELALLOC);
+				acceptable += (type == IO_DELALLOC);
 			else if (buffer_dirty(bh) && buffer_mapped(bh))
-				acceptable = (type == IO_OVERWRITE);
+				acceptable += (type == IO_OVERWRITE);
 			else
 				break;
 		} while ((bh = bh->b_this_page) != head);
@@ -684,7 +681,7 @@ xfs_convert_page(
 		goto fail_unlock_page;
 	if (page->mapping != inode->i_mapping)
 		goto fail_unlock_page;
-	if (!xfs_is_delayed_page(page, (*ioendp)->io_type))
+	if (!xfs_check_page_type(page, (*ioendp)->io_type))
 		goto fail_unlock_page;
 
 	/*
@@ -834,7 +831,7 @@ xfs_aops_discard_page(
 	struct buffer_head	*bh, *head;
 	loff_t			offset = page_offset(page);
 
-	if (!xfs_is_delayed_page(page, IO_DELALLOC))
+	if (!xfs_check_page_type(page, IO_DELALLOC))
 		goto out_invalidate;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -1146,7 +1143,14 @@ __xfs_get_blocks(
 	if (!create && direct && offset >= i_size_read(inode))
 		return 0;
 
-	if (create) {
+	/*
+	 * Direct I/O is usually done on preallocated files, so try getting
+	 * a block mapping without an exclusive lock first.  For buffered
+	 * writes we already have the exclusive iolock anyway, so avoiding
+	 * a lock roundtrip here by taking the ilock exclusive from the
+	 * beginning is a useful micro optimization.
+	 */
+	if (create && !direct) {
 		lockmode = XFS_ILOCK_EXCL;
 		xfs_ilock(ip, lockmode);
 	} else {
@@ -1168,23 +1172,45 @@ __xfs_get_blocks(
 	    (!nimaps ||
 	     (imap.br_startblock == HOLESTARTBLOCK ||
 	      imap.br_startblock == DELAYSTARTBLOCK))) {
-		if (direct) {
+		if (direct || xfs_get_extsz_hint(ip)) {
+			/*
+			 * Drop the ilock in preparation for starting the block
+			 * allocation transaction.  It will be retaken
+			 * exclusively inside xfs_iomap_write_direct for the
+			 * actual allocation.
+			 */
+			xfs_iunlock(ip, lockmode);
 			error = xfs_iomap_write_direct(ip, offset, size,
 						       &imap, nimaps);
+			if (error)
+				return -error;
+			new = 1;
 		} else {
+			/*
+			 * Delalloc reservations do not require a transaction,
+			 * we can go on without dropping the lock here. If we
+			 * are allocating a new delalloc block, make sure that
+			 * we set the new flag so that we mark the buffer new so
+			 * that we know that it is newly allocated if the write
+			 * fails.
+			 */
+			if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
+				new = 1;
 			error = xfs_iomap_write_delay(ip, offset, size, &imap);
+			if (error)
+				goto out_unlock;
+
+			xfs_iunlock(ip, lockmode);
 		}
-		if (error)
-			goto out_unlock;
 
 		trace_xfs_get_blocks_alloc(ip, offset, size, 0, &imap);
 	} else if (nimaps) {
 		trace_xfs_get_blocks_found(ip, offset, size, 0, &imap);
+		xfs_iunlock(ip, lockmode);
 	} else {
 		trace_xfs_get_blocks_notfound(ip, offset, size);
 		goto out_unlock;
 	}
-	xfs_iunlock(ip, lockmode);
 
 	if (imap.br_startblock != HOLESTARTBLOCK &&
 	    imap.br_startblock != DELAYSTARTBLOCK) {
@@ -1386,52 +1412,91 @@ out_destroy_ioend:
 	return ret;
 }
 
+/*
+ * Punch out the delalloc blocks we have already allocated.
+ *
+ * Don't bother with xfs_setattr given that nothing can have made it to disk yet
+ * as the page is still locked at this point.
+ */
+STATIC void
+xfs_vm_kill_delalloc_range(
+	struct inode		*inode,
+	loff_t			start,
+	loff_t			end)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	xfs_fileoff_t		start_fsb;
+	xfs_fileoff_t		end_fsb;
+	int			error;
+
+	start_fsb = XFS_B_TO_FSB(ip->i_mount, start);
+	end_fsb = XFS_B_TO_FSB(ip->i_mount, end);
+	if (end_fsb <= start_fsb)
+		return;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
+						end_fsb - start_fsb);
+	if (error) {
+		/* something screwed, just bail */
+		if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+			xfs_alert(ip->i_mount,
+		"xfs_vm_write_failed: unable to clean up ino %lld",
+					ip->i_ino);
+		}
+	}
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+}
+
 STATIC void
 xfs_vm_write_failed(
-	struct address_space	*mapping,
-	loff_t			to)
+	struct inode		*inode,
+	struct page		*page,
+	loff_t			pos,
+	unsigned		len)
 {
-	struct inode		*inode = mapping->host;
+	loff_t			block_offset = pos & PAGE_MASK;
+	loff_t			block_start;
+	loff_t			block_end;
+	loff_t			from = pos & (PAGE_CACHE_SIZE - 1);
+	loff_t			to = from + len;
+	struct buffer_head	*bh, *head;
 
-	if (to > inode->i_size) {
-		/*
-		 * Punch out the delalloc blocks we have already allocated.
-		 *
-		 * Don't bother with xfs_setattr given that nothing can have
-		 * made it to disk yet as the page is still locked at this
-		 * point.
-		 */
-		struct xfs_inode	*ip = XFS_I(inode);
-		xfs_fileoff_t		start_fsb;
-		xfs_fileoff_t		end_fsb;
-		int			error;
+	ASSERT(block_offset + from == pos);
 
-		truncate_pagecache(inode, to, inode->i_size);
+	head = page_buffers(page);
+	block_start = 0;
+	for (bh = head; bh != head || !block_start;
+	     bh = bh->b_this_page, block_start = block_end,
+				   block_offset += bh->b_size) {
+		block_end = block_start + bh->b_size;
 
-		/*
-		 * Check if there are any blocks that are outside of i_size
-		 * that need to be trimmed back.
-		 */
-		start_fsb = XFS_B_TO_FSB(ip->i_mount, inode->i_size) + 1;
-		end_fsb = XFS_B_TO_FSB(ip->i_mount, to);
-		if (end_fsb <= start_fsb)
-			return;
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-							end_fsb - start_fsb);
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"xfs_vm_write_failed: unable to clean up ino %lld",
-						ip->i_ino);
-			}
-		}
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		/* skip buffers before the write */
+		if (block_end <= from)
+			continue;
+
+		/* if the buffer is after the write, we're done */
+		if (block_start >= to)
+			break;
+
+		if (!buffer_delay(bh))
+			continue;
+
+		if (!buffer_new(bh) && block_offset < i_size_read(inode))
+			continue;
+
+		xfs_vm_kill_delalloc_range(inode, block_offset,
+					   block_offset + bh->b_size);
 	}
+
 }
 
+/*
+ * This used to call block_write_begin(), but it unlocks and releases the page
+ * on error, and we need that page to be able to punch stale delalloc blocks out
+ * on failure. hence we copy-n-waste it here and call xfs_vm_write_failed() at
+ * the appropriate point.
+ */
 STATIC int
 xfs_vm_write_begin(
 	struct file		*file,
@@ -1442,15 +1507,40 @@ xfs_vm_write_begin(
 	struct page		**pagep,
 	void			**fsdata)
 {
-	int			ret;
+	pgoff_t			index = pos >> PAGE_CACHE_SHIFT;
+	struct page		*page;
+	int			status;
 
-	ret = block_write_begin(mapping, pos, len, flags | AOP_FLAG_NOFS,
-				pagep, xfs_get_blocks);
-	if (unlikely(ret))
-		xfs_vm_write_failed(mapping, pos + len);
-	return ret;
+	ASSERT(len <= PAGE_CACHE_SIZE);
+
+	page = grab_cache_page_write_begin(mapping, index,
+					   flags | AOP_FLAG_NOFS);
+	if (!page)
+		return -ENOMEM;
+
+	status = __block_write_begin(page, pos, len, xfs_get_blocks);
+	if (unlikely(status)) {
+		struct inode	*inode = mapping->host;
+
+		xfs_vm_write_failed(inode, page, pos, len);
+		unlock_page(page);
+
+		if (pos + len > i_size_read(inode))
+			truncate_pagecache(inode, pos + len, i_size_read(inode));
+
+		page_cache_release(page);
+		page = NULL;
+	}
+
+	*pagep = page;
+	return status;
 }
 
+/*
+ * On failure, we only need to kill delalloc blocks beyond EOF because they
+ * will never be written. For blocks within EOF, generic_write_end() zeros them
+ * so they are safe to leave alone and be written with all the other valid data.
+ */
 STATIC int
 xfs_vm_write_end(
 	struct file		*file,
@@ -1463,9 +1553,19 @@ xfs_vm_write_end(
 {
 	int			ret;
 
+	ASSERT(len <= PAGE_CACHE_SIZE);
+
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (unlikely(ret < len))
-		xfs_vm_write_failed(mapping, pos + len);
+	if (unlikely(ret < len)) {
+		struct inode	*inode = mapping->host;
+		size_t		isize = i_size_read(inode);
+		loff_t		to = pos + len;
+
+		if (to > isize) {
+			truncate_pagecache(inode, to, isize);
+			xfs_vm_kill_delalloc_range(inode, isize, to);
+		}
+	}
 	return ret;
 }
 

fs/xfs/xfs_attr.c

@@ -21,7 +21,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -39,7 +38,6 @@
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
-#include "xfs_rw.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 
@@ -1987,14 +1985,12 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
 			       (map[i].br_startblock != HOLESTARTBLOCK));
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno,
-					     blkcnt, XBF_LOCK | XBF_DONT_BLOCK,
-					     &bp);
+			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
+						   dblkno, blkcnt, 0, &bp);
 			if (error)
 				return(error);
 
-			tmp = (valuelen < XFS_BUF_SIZE(bp))
-				? valuelen : XFS_BUF_SIZE(bp);
+			tmp = min_t(int, valuelen, BBTOB(bp->b_length));
 			xfs_buf_iomove(bp, 0, tmp, dst, XBRW_READ);
 			xfs_buf_relse(bp);
 			dst += tmp;
@@ -2097,6 +2093,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 	lblkno = args->rmtblkno;
 	valuelen = args->valuelen;
 	while (valuelen > 0) {
+		int buflen;
+
 		/*
 		 * Try to remember where we decided to put the value.
 		 */
@@ -2114,15 +2112,16 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 		dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
 		blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
 
-		bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt,
-				 XBF_LOCK | XBF_DONT_BLOCK);
+		bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt, 0);
 		if (!bp)
 			return ENOMEM;
-		tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen :
-							XFS_BUF_SIZE(bp);
+
+		buflen = BBTOB(bp->b_length);
+		tmp = min_t(int, valuelen, buflen);
 		xfs_buf_iomove(bp, 0, tmp, src, XBRW_WRITE);
-		if (tmp < XFS_BUF_SIZE(bp))
-			xfs_buf_zero(bp, tmp, XFS_BUF_SIZE(bp) - tmp);
+		if (tmp < buflen)
+			xfs_buf_zero(bp, tmp, buflen - tmp);
+
 		error = xfs_bwrite(bp);	/* GROT: NOTE: synchronous write */
 		xfs_buf_relse(bp);
 		if (error)

fs/xfs/xfs_attr_leaf.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -2983,7 +2982,7 @@ xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
 						map.br_blockcount);
 			bp = xfs_trans_get_buf(*trans,
 					dp->i_mount->m_ddev_targp,
-					dblkno, dblkcnt, XBF_LOCK);
+					dblkno, dblkcnt, 0);
 			if (!bp)
 				return ENOMEM;
 			xfs_trans_binval(*trans, bp);

fs/xfs/xfs_bmap.c

@@ -41,7 +41,6 @@
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_attr_leaf.h"
-#include "xfs_rw.h"
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_buf_item.h"
@@ -4527,7 +4526,7 @@ out_unreserve_blocks:
 		xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, alen, 0);
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
-		xfs_trans_unreserve_quota_nblks(NULL, ip, alen, 0, rt ?
+		xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, rt ?
 				XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
 	return error;
 }
@@ -5621,8 +5620,20 @@ xfs_getbmap(
 				XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			out[cur_ext].bmv_unused1 = 0;
 			out[cur_ext].bmv_unused2 = 0;
-			ASSERT(((iflags & BMV_IF_DELALLOC) != 0) ||
-			      (map[i].br_startblock != DELAYSTARTBLOCK));
+
+			/*
+			 * delayed allocation extents that start beyond EOF can
+			 * occur due to speculative EOF allocation when the
+			 * delalloc extent is larger than the largest freespace
+			 * extent at conversion time. These extents cannot be
+			 * converted by data writeback, so can exist here even
+			 * if we are not supposed to be finding delalloc
+			 * extents.
+			 */
+			if (map[i].br_startblock == DELAYSTARTBLOCK &&
+			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
+
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
 			    whichfork == XFS_ATTR_FORK) {
 				/* came to the end of attribute fork */
@@ -6157,3 +6168,16 @@ next_block:
 
 	return error;
 }
+
+/*
+ * Convert the given file system block to a disk block.  We have to treat it
+ * differently based on whether the file is a real time file or not, because the
+ * bmap code does.
+ */
+xfs_daddr_t
+xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
+{
+	return (XFS_IS_REALTIME_INODE(ip) ? \
+		 (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
+		 XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
+}

fs/xfs/xfs_bmap.h

@@ -211,6 +211,9 @@ int	xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
 		int whichfork, int *count);
 int	xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
 		xfs_fileoff_t start_fsb, xfs_fileoff_t length);
+
+xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
+
 #endif	/* __KERNEL__ */
 
 #endif	/* __XFS_BMAP_H__ */

fs/xfs/xfs_bmap_btree.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_btree.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_buf.c

@@ -35,14 +35,12 @@
 #include <linux/freezer.h>
 
 #include "xfs_sb.h"
-#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_trace.h"
 
 static kmem_zone_t *xfs_buf_zone;
-STATIC int xfsbufd(void *);
 
 static struct workqueue_struct *xfslogd_workqueue;
 
@@ -57,11 +55,7 @@ static struct workqueue_struct *xfslogd_workqueue;
 #endif
 
 #define xb_to_gfp(flags) \
-	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : \
-	  ((flags) & XBF_DONT_BLOCK) ? GFP_NOFS : GFP_KERNEL) | __GFP_NOWARN)
-
-#define xb_to_km(flags) \
-	 (((flags) & XBF_DONT_BLOCK) ? KM_NOFS : KM_SLEEP)
+	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
 
 static inline int
@@ -71,11 +65,11 @@ xfs_buf_is_vmapped(
 	/*
 	 * Return true if the buffer is vmapped.
 	 *
-	 * The XBF_MAPPED flag is set if the buffer should be mapped, but the
-	 * code is clever enough to know it doesn't have to map a single page,
-	 * so the check has to be both for XBF_MAPPED and bp->b_page_count > 1.
+	 * b_addr is null if the buffer is not mapped, but the code is clever
+	 * enough to know it doesn't have to map a single page, so the check has
+	 * to be both for b_addr and bp->b_page_count > 1.
 	 */
-	return (bp->b_flags & XBF_MAPPED) && bp->b_page_count > 1;
+	return bp->b_addr && bp->b_page_count > 1;
 }
 
 static inline int
@@ -144,8 +138,17 @@ void
 xfs_buf_stale(
 	struct xfs_buf	*bp)
 {
+	ASSERT(xfs_buf_islocked(bp));
+
 	bp->b_flags |= XBF_STALE;
-	xfs_buf_delwri_dequeue(bp);
+
+	/*
+	 * Clear the delwri status so that a delwri queue walker will not
+	 * flush this buffer to disk now that it is stale. The delwri queue has
+	 * a reference to the buffer, so this is safe to do.
+	 */
+	bp->b_flags &= ~_XBF_DELWRI_Q;
+
 	atomic_set(&(bp)->b_lru_ref, 0);
 	if (!list_empty(&bp->b_lru)) {
 		struct xfs_buftarg *btp = bp->b_target;
@@ -164,22 +167,22 @@ xfs_buf_stale(
 struct xfs_buf *
 xfs_buf_alloc(
 	struct xfs_buftarg	*target,
-	xfs_off_t		range_base,
-	size_t			range_length,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
 
-	bp = kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags));
+	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
 	if (unlikely(!bp))
 		return NULL;
 
 	/*
-	 * We don't want certain flags to appear in b_flags.
+	 * We don't want certain flags to appear in b_flags unless they are
+	 * specifically set by later operations on the buffer.
 	 */
-	flags &= ~(XBF_LOCK|XBF_MAPPED|XBF_DONT_BLOCK|XBF_READ_AHEAD);
+	flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
 
-	memset(bp, 0, sizeof(xfs_buf_t));
 	atomic_set(&bp->b_hold, 1);
 	atomic_set(&bp->b_lru_ref, 1);
 	init_completion(&bp->b_iowait);
@@ -189,14 +192,22 @@ xfs_buf_alloc(
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	XB_SET_OWNER(bp);
 	bp->b_target = target;
-	bp->b_file_offset = range_base;
+
 	/*
-	 * Set buffer_length and count_desired to the same value initially.
-	 * I/O routines should use count_desired, which will be the same in
+	 * Set length and io_length to the same value initially.
+	 * I/O routines should use io_length, which will be the same in
 	 * most cases but may be reset (e.g. XFS recovery).
 	 */
-	bp->b_buffer_length = bp->b_count_desired = range_length;
+	bp->b_length = numblks;
+	bp->b_io_length = numblks;
 	bp->b_flags = flags;
+
+	/*
+	 * We do not set the block number here in the buffer because we have not
+	 * finished initialising the buffer. We insert the buffer into the cache
+	 * in this state, so this ensures that we are unable to do IO on a
+	 * buffer that hasn't been fully initialised.
+	 */
 	bp->b_bn = XFS_BUF_DADDR_NULL;
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
@@ -219,13 +230,12 @@ _xfs_buf_get_pages(
 {
 	/* Make sure that we have a page list */
 	if (bp->b_pages == NULL) {
-		bp->b_offset = xfs_buf_poff(bp->b_file_offset);
 		bp->b_page_count = page_count;
 		if (page_count <= XB_PAGES) {
 			bp->b_pages = bp->b_page_array;
 		} else {
 			bp->b_pages = kmem_alloc(sizeof(struct page *) *
-					page_count, xb_to_km(flags));
+						 page_count, KM_NOFS);
 			if (bp->b_pages == NULL)
 				return -ENOMEM;
 		}
@@ -288,11 +298,11 @@ xfs_buf_allocate_memory(
 	xfs_buf_t		*bp,
 	uint			flags)
 {
-	size_t			size = bp->b_count_desired;
+	size_t			size;
 	size_t			nbytes, offset;
 	gfp_t			gfp_mask = xb_to_gfp(flags);
 	unsigned short		page_count, i;
-	xfs_off_t		end;
+	xfs_off_t		start, end;
 	int			error;
 
 	/*
@@ -300,15 +310,15 @@ xfs_buf_allocate_memory(
 	 * the memory from the heap - there's no need for the complexity of
 	 * page arrays to keep allocation down to order 0.
 	 */
-	if (bp->b_buffer_length < PAGE_SIZE) {
-		bp->b_addr = kmem_alloc(bp->b_buffer_length, xb_to_km(flags));
+	size = BBTOB(bp->b_length);
+	if (size < PAGE_SIZE) {
+		bp->b_addr = kmem_alloc(size, KM_NOFS);
 		if (!bp->b_addr) {
 			/* low memory - use alloc_page loop instead */
 			goto use_alloc_page;
 		}
 
-		if (((unsigned long)(bp->b_addr + bp->b_buffer_length - 1) &
-								PAGE_MASK) !=
+		if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) !=
 		    ((unsigned long)bp->b_addr & PAGE_MASK)) {
 			/* b_addr spans two pages - use alloc_page instead */
 			kmem_free(bp->b_addr);
@@ -319,13 +329,14 @@ xfs_buf_allocate_memory(
 		bp->b_pages = bp->b_page_array;
 		bp->b_pages[0] = virt_to_page(bp->b_addr);
 		bp->b_page_count = 1;
-		bp->b_flags |= XBF_MAPPED | _XBF_KMEM;
+		bp->b_flags |= _XBF_KMEM;
 		return 0;
 	}
 
 use_alloc_page:
-	end = bp->b_file_offset + bp->b_buffer_length;
-	page_count = xfs_buf_btoc(end) - xfs_buf_btoct(bp->b_file_offset);
+	start = BBTOB(bp->b_bn) >> PAGE_SHIFT;
+	end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	page_count = end - start;
 	error = _xfs_buf_get_pages(bp, page_count, flags);
 	if (unlikely(error))
 		return error;
@@ -388,8 +399,9 @@ _xfs_buf_map_pages(
 	if (bp->b_page_count == 1) {
 		/* A single page buffer is always mappable */
 		bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
-		bp->b_flags |= XBF_MAPPED;
-	} else if (flags & XBF_MAPPED) {
+	} else if (flags & XBF_UNMAPPED) {
+		bp->b_addr = NULL;
+	} else {
 		int retried = 0;
 
 		do {
@@ -403,7 +415,6 @@ _xfs_buf_map_pages(
 		if (!bp->b_addr)
 			return -ENOMEM;
 		bp->b_addr += bp->b_offset;
-		bp->b_flags |= XBF_MAPPED;
 	}
 
 	return 0;
@@ -420,29 +431,27 @@ _xfs_buf_map_pages(
  */
 xfs_buf_t *
 _xfs_buf_find(
-	xfs_buftarg_t		*btp,	/* block device target		*/
-	xfs_off_t		ioff,	/* starting offset of range	*/
-	size_t			isize,	/* length of range		*/
+	struct xfs_buftarg	*btp,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
 	xfs_buf_flags_t		flags,
 	xfs_buf_t		*new_bp)
 {
-	xfs_off_t		range_base;
-	size_t			range_length;
+	size_t			numbytes;
 	struct xfs_perag	*pag;
 	struct rb_node		**rbp;
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
 
-	range_base = (ioff << BBSHIFT);
-	range_length = (isize << BBSHIFT);
+	numbytes = BBTOB(numblks);
 
 	/* Check for IOs smaller than the sector size / not sector aligned */
-	ASSERT(!(range_length < (1 << btp->bt_sshift)));
-	ASSERT(!(range_base & (xfs_off_t)btp->bt_smask));
+	ASSERT(!(numbytes < (1 << btp->bt_sshift)));
+	ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask));
 
 	/* get tree root */
 	pag = xfs_perag_get(btp->bt_mount,
-				xfs_daddr_to_agno(btp->bt_mount, ioff));
+				xfs_daddr_to_agno(btp->bt_mount, blkno));
 
 	/* walk tree */
 	spin_lock(&pag->pag_buf_lock);
@@ -453,20 +462,20 @@ _xfs_buf_find(
 		parent = *rbp;
 		bp = rb_entry(parent, struct xfs_buf, b_rbnode);
 
-		if (range_base < bp->b_file_offset)
+		if (blkno < bp->b_bn)
 			rbp = &(*rbp)->rb_left;
-		else if (range_base > bp->b_file_offset)
+		else if (blkno > bp->b_bn)
 			rbp = &(*rbp)->rb_right;
 		else {
 			/*
-			 * found a block offset match. If the range doesn't
+			 * found a block number match. If the range doesn't
 			 * match, the only way this is allowed is if the buffer
 			 * in the cache is stale and the transaction that made
 			 * it stale has not yet committed. i.e. we are
 			 * reallocating a busy extent. Skip this buffer and
 			 * continue searching to the right for an exact match.
 			 */
-			if (bp->b_buffer_length != range_length) {
+			if (bp->b_length != numblks) {
 				ASSERT(bp->b_flags & XBF_STALE);
 				rbp = &(*rbp)->rb_right;
 				continue;
@@ -511,7 +520,7 @@ found:
 	 */
 	if (bp->b_flags & XBF_STALE) {
 		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
-		bp->b_flags &= XBF_MAPPED | _XBF_KMEM | _XBF_PAGES;
+		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
 	}
 
 	trace_xfs_buf_find(bp, flags, _RET_IP_);
@@ -526,63 +535,59 @@ found:
  */
 struct xfs_buf *
 xfs_buf_get(
-	xfs_buftarg_t		*target,/* target for buffer		*/
-	xfs_off_t		ioff,	/* starting offset of range	*/
-	size_t			isize,	/* length of range		*/
+	xfs_buftarg_t		*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
 	struct xfs_buf		*new_bp;
 	int			error = 0;
 
-	bp = _xfs_buf_find(target, ioff, isize, flags, NULL);
+	bp = _xfs_buf_find(target, blkno, numblks, flags, NULL);
 	if (likely(bp))
 		goto found;
 
-	new_bp = xfs_buf_alloc(target, ioff << BBSHIFT, isize << BBSHIFT,
-			       flags);
+	new_bp = xfs_buf_alloc(target, blkno, numblks, flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
-	bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
-	if (!bp) {
+	error = xfs_buf_allocate_memory(new_bp, flags);
+	if (error) {
 		kmem_zone_free(xfs_buf_zone, new_bp);
 		return NULL;
 	}
 
-	if (bp == new_bp) {
-		error = xfs_buf_allocate_memory(bp, flags);
-		if (error)
-			goto no_buffer;
-	} else
-		kmem_zone_free(xfs_buf_zone, new_bp);
+	bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp);
+	if (!bp) {
+		xfs_buf_free(new_bp);
+		return NULL;
+	}
+
+	if (bp != new_bp)
+		xfs_buf_free(new_bp);
 
 	/*
 	 * Now we have a workable buffer, fill in the block number so
 	 * that we can do IO on it.
 	 */
-	bp->b_bn = ioff;
-	bp->b_count_desired = bp->b_buffer_length;
+	bp->b_bn = blkno;
+	bp->b_io_length = bp->b_length;
 
 found:
-	if (!(bp->b_flags & XBF_MAPPED)) {
+	if (!bp->b_addr) {
 		error = _xfs_buf_map_pages(bp, flags);
 		if (unlikely(error)) {
 			xfs_warn(target->bt_mount,
 				"%s: failed to map pages\n", __func__);
-			goto no_buffer;
+			xfs_buf_relse(bp);
+			return NULL;
 		}
 	}
 
 	XFS_STATS_INC(xb_get);
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
-
-no_buffer:
-	if (flags & (XBF_LOCK | XBF_TRYLOCK))
-		xfs_buf_unlock(bp);
-	xfs_buf_rele(bp);
-	return NULL;
 }
 
 STATIC int
@@ -590,32 +595,30 @@ _xfs_buf_read(
 	xfs_buf_t		*bp,
 	xfs_buf_flags_t		flags)
 {
-	int			status;
-
-	ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE)));
+	ASSERT(!(flags & XBF_WRITE));
 	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
 
-	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD);
+	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	status = xfs_buf_iorequest(bp);
-	if (status || bp->b_error || (flags & XBF_ASYNC))
-		return status;
+	xfs_buf_iorequest(bp);
+	if (flags & XBF_ASYNC)
+		return 0;
 	return xfs_buf_iowait(bp);
 }
 
 xfs_buf_t *
 xfs_buf_read(
 	xfs_buftarg_t		*target,
-	xfs_off_t		ioff,
-	size_t			isize,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
 	xfs_buf_flags_t		flags)
 {
 	xfs_buf_t		*bp;
 
 	flags |= XBF_READ;
 
-	bp = xfs_buf_get(target, ioff, isize, flags);
+	bp = xfs_buf_get(target, blkno, numblks, flags);
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
@@ -627,7 +630,8 @@ xfs_buf_read(
 			 * Read ahead call which is already satisfied,
 			 * drop the buffer
 			 */
-			goto no_buffer;
+			xfs_buf_relse(bp);
+			return NULL;
 		} else {
 			/* We do not want read in the flags */
 			bp->b_flags &= ~XBF_READ;
@@ -635,12 +639,6 @@ xfs_buf_read(
 	}
 
 	return bp;
-
- no_buffer:
-	if (flags & (XBF_LOCK | XBF_TRYLOCK))
-		xfs_buf_unlock(bp);
-	xfs_buf_rele(bp);
-	return NULL;
 }
 
 /*
@@ -650,14 +648,14 @@ xfs_buf_read(
 void
 xfs_buf_readahead(
 	xfs_buftarg_t		*target,
-	xfs_off_t		ioff,
-	size_t			isize)
+	xfs_daddr_t		blkno,
+	size_t			numblks)
 {
 	if (bdi_read_congested(target->bt_bdi))
 		return;
 
-	xfs_buf_read(target, ioff, isize,
-		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK);
+	xfs_buf_read(target, blkno, numblks,
+		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
 }
 
 /*
@@ -666,16 +664,15 @@ xfs_buf_readahead(
  */
 struct xfs_buf *
 xfs_buf_read_uncached(
-	struct xfs_mount	*mp,
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		daddr,
-	size_t			length,
+	size_t			numblks,
 	int			flags)
 {
 	xfs_buf_t		*bp;
 	int			error;
 
-	bp = xfs_buf_get_uncached(target, length, flags);
+	bp = xfs_buf_get_uncached(target, numblks, flags);
 	if (!bp)
 		return NULL;
 
@@ -683,9 +680,9 @@ xfs_buf_read_uncached(
 	XFS_BUF_SET_ADDR(bp, daddr);
 	XFS_BUF_READ(bp);
 
-	xfsbdstrat(mp, bp);
+	xfsbdstrat(target->bt_mount, bp);
 	error = xfs_buf_iowait(bp);
-	if (error || bp->b_error) {
+	if (error) {
 		xfs_buf_relse(bp);
 		return NULL;
 	}
@@ -699,7 +696,7 @@ xfs_buf_read_uncached(
 void
 xfs_buf_set_empty(
 	struct xfs_buf		*bp,
-	size_t			len)
+	size_t			numblks)
 {
 	if (bp->b_pages)
 		_xfs_buf_free_pages(bp);
@@ -707,10 +704,9 @@ xfs_buf_set_empty(
 	bp->b_pages = NULL;
 	bp->b_page_count = 0;
 	bp->b_addr = NULL;
-	bp->b_file_offset = 0;
-	bp->b_buffer_length = bp->b_count_desired = len;
+	bp->b_length = numblks;
+	bp->b_io_length = numblks;
 	bp->b_bn = XFS_BUF_DADDR_NULL;
-	bp->b_flags &= ~XBF_MAPPED;
 }
 
 static inline struct page *
@@ -749,7 +745,7 @@ xfs_buf_associate_memory(
 	bp->b_pages = NULL;
 	bp->b_addr = mem;
 
-	rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK);
+	rval = _xfs_buf_get_pages(bp, page_count, 0);
 	if (rval)
 		return rval;
 
@@ -760,9 +756,8 @@ xfs_buf_associate_memory(
 		pageaddr += PAGE_SIZE;
 	}
 
-	bp->b_count_desired = len;
-	bp->b_buffer_length = buflen;
-	bp->b_flags |= XBF_MAPPED;
+	bp->b_io_length = BTOBB(len);
+	bp->b_length = BTOBB(buflen);
 
 	return 0;
 }
@@ -770,17 +765,18 @@ xfs_buf_associate_memory(
 xfs_buf_t *
 xfs_buf_get_uncached(
 	struct xfs_buftarg	*target,
-	size_t			len,
+	size_t			numblks,
 	int			flags)
 {
-	unsigned long		page_count = PAGE_ALIGN(len) >> PAGE_SHIFT;
+	unsigned long		page_count;
 	int			error, i;
 	xfs_buf_t		*bp;
 
-	bp = xfs_buf_alloc(target, 0, len, 0);
+	bp = xfs_buf_alloc(target, 0, numblks, 0);
 	if (unlikely(bp == NULL))
 		goto fail;
 
+	page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT;
 	error = _xfs_buf_get_pages(bp, page_count, 0);
 	if (error)
 		goto fail_free_buf;
@@ -792,7 +788,7 @@ xfs_buf_get_uncached(
 	}
 	bp->b_flags |= _XBF_PAGES;
 
-	error = _xfs_buf_map_pages(bp, XBF_MAPPED);
+	error = _xfs_buf_map_pages(bp, 0);
 	if (unlikely(error)) {
 		xfs_warn(target->bt_mount,
 			"%s: failed to map pages\n", __func__);
@@ -855,7 +851,7 @@ xfs_buf_rele(
 			spin_unlock(&pag->pag_buf_lock);
 		} else {
 			xfs_buf_lru_del(bp);
-			ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)));
+			ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
 			rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
 			spin_unlock(&pag->pag_buf_lock);
 			xfs_perag_put(pag);
@@ -915,13 +911,6 @@ xfs_buf_lock(
 	trace_xfs_buf_lock_done(bp, _RET_IP_);
 }
 
-/*
- *	Releases the lock on the buffer object.
- *	If the buffer is marked delwri but is not queued, do so before we
- *	unlock the buffer as we need to set flags correctly.  We also need to
- *	take a reference for the delwri queue because the unlocker is going to
- *	drop their's and they don't know we just queued it.
- */
 void
 xfs_buf_unlock(
 	struct xfs_buf		*bp)
@@ -1008,9 +997,8 @@ xfs_buf_ioerror_alert(
 	const char		*func)
 {
 	xfs_alert(bp->b_target->bt_mount,
-"metadata I/O error: block 0x%llx (\"%s\") error %d buf count %zd",
-		(__uint64_t)XFS_BUF_ADDR(bp), func,
-		bp->b_error, XFS_BUF_COUNT(bp));
+"metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d",
+		(__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length);
 }
 
 int
@@ -1019,10 +1007,11 @@ xfs_bwrite(
 {
 	int			error;
 
+	ASSERT(xfs_buf_islocked(bp));
+
 	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ);
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
 
-	xfs_buf_delwri_dequeue(bp);
 	xfs_bdstrat_cb(bp);
 
 	error = xfs_buf_iowait(bp);
@@ -1181,7 +1170,7 @@ _xfs_buf_ioapply(
 	int			rw, map_i, total_nr_pages, nr_pages;
 	struct bio		*bio;
 	int			offset = bp->b_offset;
-	int			size = bp->b_count_desired;
+	int			size = BBTOB(bp->b_io_length);
 	sector_t		sector = bp->b_bn;
 
 	total_nr_pages = bp->b_page_count;
@@ -1229,7 +1218,7 @@ next_chunk:
 			break;
 
 		offset = 0;
-		sector += nbytes >> BBSHIFT;
+		sector += BTOBB(nbytes);
 		size -= nbytes;
 		total_nr_pages--;
 	}
@@ -1248,13 +1237,13 @@ next_chunk:
 	}
 }
 
-int
+void
 xfs_buf_iorequest(
 	xfs_buf_t		*bp)
 {
 	trace_xfs_buf_iorequest(bp, _RET_IP_);
 
-	ASSERT(!(bp->b_flags & XBF_DELWRI));
+	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
 
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
@@ -1269,13 +1258,12 @@ xfs_buf_iorequest(
 	_xfs_buf_ioend(bp, 0);
 
 	xfs_buf_rele(bp);
-	return 0;
 }
 
 /*
- *	Waits for I/O to complete on the buffer supplied.
- *	It returns immediately if no I/O is pending.
- *	It returns the I/O error code, if any, or 0 if there was no error.
+ * Waits for I/O to complete on the buffer supplied.  It returns immediately if
+ * no I/O is pending or there is already a pending error on the buffer.  It
+ * returns the I/O error code, if any, or 0 if there was no error.
  */
 int
 xfs_buf_iowait(
@@ -1283,7 +1271,8 @@ xfs_buf_iowait(
 {
 	trace_xfs_buf_iowait(bp, _RET_IP_);
 
-	wait_for_completion(&bp->b_iowait);
+	if (!bp->b_error)
+		wait_for_completion(&bp->b_iowait);
 
 	trace_xfs_buf_iowait_done(bp, _RET_IP_);
 	return bp->b_error;
@@ -1296,7 +1285,7 @@ xfs_buf_offset(
 {
 	struct page		*page;
 
-	if (bp->b_flags & XBF_MAPPED)
+	if (bp->b_addr)
 		return bp->b_addr + offset;
 
 	offset += bp->b_offset;
@@ -1315,27 +1304,30 @@ xfs_buf_iomove(
 	void			*data,	/* data address			*/
 	xfs_buf_rw_t		mode)	/* read/write/zero flag		*/
 {
-	size_t			bend, cpoff, csize;
-	struct page		*page;
+	size_t			bend;
 
 	bend = boff + bsize;
 	while (boff < bend) {
-		page = bp->b_pages[xfs_buf_btoct(boff + bp->b_offset)];
-		cpoff = xfs_buf_poff(boff + bp->b_offset);
-		csize = min_t(size_t,
-			      PAGE_SIZE-cpoff, bp->b_count_desired-boff);
+		struct page	*page;
+		int		page_index, page_offset, csize;
+
+		page_index = (boff + bp->b_offset) >> PAGE_SHIFT;
+		page_offset = (boff + bp->b_offset) & ~PAGE_MASK;
+		page = bp->b_pages[page_index];
+		csize = min_t(size_t, PAGE_SIZE - page_offset,
+				      BBTOB(bp->b_io_length) - boff);
 
-		ASSERT(((csize + cpoff) <= PAGE_SIZE));
+		ASSERT((csize + page_offset) <= PAGE_SIZE);
 
 		switch (mode) {
 		case XBRW_ZERO:
-			memset(page_address(page) + cpoff, 0, csize);
+			memset(page_address(page) + page_offset, 0, csize);
 			break;
 		case XBRW_READ:
-			memcpy(data, page_address(page) + cpoff, csize);
+			memcpy(data, page_address(page) + page_offset, csize);
 			break;
 		case XBRW_WRITE:
-			memcpy(page_address(page) + cpoff, data, csize);
+			memcpy(page_address(page) + page_offset, data, csize);
 		}
 
 		boff += csize;
@@ -1435,11 +1427,9 @@ xfs_free_buftarg(
 {
 	unregister_shrinker(&btp->bt_shrinker);
 
-	xfs_flush_buftarg(btp, 1);
 	if (mp->m_flags & XFS_MOUNT_BARRIER)
 		xfs_blkdev_issue_flush(btp);
 
-	kthread_stop(btp->bt_task);
 	kmem_free(btp);
 }
 
@@ -1491,20 +1481,6 @@ xfs_setsize_buftarg(
 	return xfs_setsize_buftarg_flags(btp, blocksize, sectorsize, 1);
 }
 
-STATIC int
-xfs_alloc_delwri_queue(
-	xfs_buftarg_t		*btp,
-	const char		*fsname)
-{
-	INIT_LIST_HEAD(&btp->bt_delwri_queue);
-	spin_lock_init(&btp->bt_delwri_lock);
-	btp->bt_flags = 0;
-	btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd/%s", fsname);
-	if (IS_ERR(btp->bt_task))
-		return PTR_ERR(btp->bt_task);
-	return 0;
-}
-
 xfs_buftarg_t *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
@@ -1527,8 +1503,6 @@ xfs_alloc_buftarg(
 	spin_lock_init(&btp->bt_lru_lock);
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
-	if (xfs_alloc_delwri_queue(btp, fsname))
-		goto error;
 	btp->bt_shrinker.shrink = xfs_buftarg_shrink;
 	btp->bt_shrinker.seeks = DEFAULT_SEEKS;
 	register_shrinker(&btp->bt_shrinker);
@@ -1539,125 +1513,52 @@ error:
 	return NULL;
 }
 
-
 /*
- *	Delayed write buffer handling
+ * Add a buffer to the delayed write list.
+ *
+ * This queues a buffer for writeout if it hasn't already been.  Note that
+ * neither this routine nor the buffer list submission functions perform
+ * any internal synchronization.  It is expected that the lists are thread-local
+ * to the callers.
+ *
+ * Returns true if we queued up the buffer, or false if it already had
+ * been on the buffer list.
  */
-void
+bool
 xfs_buf_delwri_queue(
-	xfs_buf_t		*bp)
+	struct xfs_buf		*bp,
+	struct list_head	*list)
 {
-	struct xfs_buftarg	*btp = bp->b_target;
-
-	trace_xfs_buf_delwri_queue(bp, _RET_IP_);
-
+	ASSERT(xfs_buf_islocked(bp));
 	ASSERT(!(bp->b_flags & XBF_READ));
 
-	spin_lock(&btp->bt_delwri_lock);
-	if (!list_empty(&bp->b_list)) {
-		/* if already in the queue, move it to the tail */
-		ASSERT(bp->b_flags & _XBF_DELWRI_Q);
-		list_move_tail(&bp->b_list, &btp->bt_delwri_queue);
-	} else {
-		/* start xfsbufd as it is about to have something to do */
-		if (list_empty(&btp->bt_delwri_queue))
-			wake_up_process(bp->b_target->bt_task);
-
-		atomic_inc(&bp->b_hold);
-		bp->b_flags |= XBF_DELWRI | _XBF_DELWRI_Q | XBF_ASYNC;
-		list_add_tail(&bp->b_list, &btp->bt_delwri_queue);
-	}
-	bp->b_queuetime = jiffies;
-	spin_unlock(&btp->bt_delwri_lock);
-}
-
-void
-xfs_buf_delwri_dequeue(
-	xfs_buf_t		*bp)
-{
-	int			dequeued = 0;
-
-	spin_lock(&bp->b_target->bt_delwri_lock);
-	if ((bp->b_flags & XBF_DELWRI) && !list_empty(&bp->b_list)) {
-		ASSERT(bp->b_flags & _XBF_DELWRI_Q);
-		list_del_init(&bp->b_list);
-		dequeued = 1;
+	/*
+	 * If the buffer is already marked delwri it already is queued up
+	 * by someone else for imediate writeout.  Just ignore it in that
+	 * case.
+	 */
+	if (bp->b_flags & _XBF_DELWRI_Q) {
+		trace_xfs_buf_delwri_queued(bp, _RET_IP_);
+		return false;
 	}
-	bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q);
-	spin_unlock(&bp->b_target->bt_delwri_lock);
-
-	if (dequeued)
-		xfs_buf_rele(bp);
-
-	trace_xfs_buf_delwri_dequeue(bp, _RET_IP_);
-}
-
-/*
- * If a delwri buffer needs to be pushed before it has aged out, then promote
- * it to the head of the delwri queue so that it will be flushed on the next
- * xfsbufd run. We do this by resetting the queuetime of the buffer to be older
- * than the age currently needed to flush the buffer. Hence the next time the
- * xfsbufd sees it is guaranteed to be considered old enough to flush.
- */
-void
-xfs_buf_delwri_promote(
-	struct xfs_buf	*bp)
-{
-	struct xfs_buftarg *btp = bp->b_target;
-	long		age = xfs_buf_age_centisecs * msecs_to_jiffies(10) + 1;
 
-	ASSERT(bp->b_flags & XBF_DELWRI);
-	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+	trace_xfs_buf_delwri_queue(bp, _RET_IP_);
 
 	/*
-	 * Check the buffer age before locking the delayed write queue as we
-	 * don't need to promote buffers that are already past the flush age.
+	 * If a buffer gets written out synchronously or marked stale while it
+	 * is on a delwri list we lazily remove it. To do this, the other party
+	 * clears the  _XBF_DELWRI_Q flag but otherwise leaves the buffer alone.
+	 * It remains referenced and on the list.  In a rare corner case it
+	 * might get readded to a delwri list after the synchronous writeout, in
+	 * which case we need just need to re-add the flag here.
 	 */
-	if (bp->b_queuetime < jiffies - age)
-		return;
-	bp->b_queuetime = jiffies - age;
-	spin_lock(&btp->bt_delwri_lock);
-	list_move(&bp->b_list, &btp->bt_delwri_queue);
-	spin_unlock(&btp->bt_delwri_lock);
-}
-
-/*
- * Move as many buffers as specified to the supplied list
- * idicating if we skipped any buffers to prevent deadlocks.
- */
-STATIC int
-xfs_buf_delwri_split(
-	xfs_buftarg_t	*target,
-	struct list_head *list,
-	unsigned long	age)
-{
-	xfs_buf_t	*bp, *n;
-	int		skipped = 0;
-	int		force;
-
-	force = test_and_clear_bit(XBT_FORCE_FLUSH, &target->bt_flags);
-	INIT_LIST_HEAD(list);
-	spin_lock(&target->bt_delwri_lock);
-	list_for_each_entry_safe(bp, n, &target->bt_delwri_queue, b_list) {
-		ASSERT(bp->b_flags & XBF_DELWRI);
-
-		if (!xfs_buf_ispinned(bp) && xfs_buf_trylock(bp)) {
-			if (!force &&
-			    time_before(jiffies, bp->b_queuetime + age)) {
-				xfs_buf_unlock(bp);
-				break;
-			}
-
-			bp->b_flags &= ~(XBF_DELWRI | _XBF_DELWRI_Q);
-			bp->b_flags |= XBF_WRITE;
-			list_move_tail(&bp->b_list, list);
-			trace_xfs_buf_delwri_split(bp, _RET_IP_);
-		} else
-			skipped++;
+	bp->b_flags |= _XBF_DELWRI_Q;
+	if (list_empty(&bp->b_list)) {
+		atomic_inc(&bp->b_hold);
+		list_add_tail(&bp->b_list, list);
 	}
 
-	spin_unlock(&target->bt_delwri_lock);
-	return skipped;
+	return true;
 }
 
 /*
@@ -1683,99 +1584,109 @@ xfs_buf_cmp(
 	return 0;
 }
 
-STATIC int
-xfsbufd(
-	void		*data)
+static int
+__xfs_buf_delwri_submit(
+	struct list_head	*buffer_list,
+	struct list_head	*io_list,
+	bool			wait)
 {
-	xfs_buftarg_t   *target = (xfs_buftarg_t *)data;
-
-	current->flags |= PF_MEMALLOC;
-
-	set_freezable();
+	struct blk_plug		plug;
+	struct xfs_buf		*bp, *n;
+	int			pinned = 0;
+
+	list_for_each_entry_safe(bp, n, buffer_list, b_list) {
+		if (!wait) {
+			if (xfs_buf_ispinned(bp)) {
+				pinned++;
+				continue;
+			}
+			if (!xfs_buf_trylock(bp))
+				continue;
+		} else {
+			xfs_buf_lock(bp);
+		}
 
-	do {
-		long	age = xfs_buf_age_centisecs * msecs_to_jiffies(10);
-		long	tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10);
-		struct list_head tmp;
-		struct blk_plug plug;
+		/*
+		 * Someone else might have written the buffer synchronously or
+		 * marked it stale in the meantime.  In that case only the
+		 * _XBF_DELWRI_Q flag got cleared, and we have to drop the
+		 * reference and remove it from the list here.
+		 */
+		if (!(bp->b_flags & _XBF_DELWRI_Q)) {
+			list_del_init(&bp->b_list);
+			xfs_buf_relse(bp);
+			continue;
+		}
 
-		if (unlikely(freezing(current)))
-			try_to_freeze();
+		list_move_tail(&bp->b_list, io_list);
+		trace_xfs_buf_delwri_split(bp, _RET_IP_);
+	}
 
-		/* sleep for a long time if there is nothing to do. */
-		if (list_empty(&target->bt_delwri_queue))
-			tout = MAX_SCHEDULE_TIMEOUT;
-		schedule_timeout_interruptible(tout);
+	list_sort(NULL, io_list, xfs_buf_cmp);
 
-		xfs_buf_delwri_split(target, &tmp, age);
-		list_sort(NULL, &tmp, xfs_buf_cmp);
+	blk_start_plug(&plug);
+	list_for_each_entry_safe(bp, n, io_list, b_list) {
+		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+		bp->b_flags |= XBF_WRITE;
 
-		blk_start_plug(&plug);
-		while (!list_empty(&tmp)) {
-			struct xfs_buf *bp;
-			bp = list_first_entry(&tmp, struct xfs_buf, b_list);
+		if (!wait) {
+			bp->b_flags |= XBF_ASYNC;
 			list_del_init(&bp->b_list);
-			xfs_bdstrat_cb(bp);
 		}
-		blk_finish_plug(&plug);
-	} while (!kthread_should_stop());
+		xfs_bdstrat_cb(bp);
+	}
+	blk_finish_plug(&plug);
 
-	return 0;
+	return pinned;
 }
 
 /*
- *	Go through all incore buffers, and release buffers if they belong to
- *	the given device. This is used in filesystem error handling to
- *	preserve the consistency of its metadata.
+ * Write out a buffer list asynchronously.
+ *
+ * This will take the @buffer_list, write all non-locked and non-pinned buffers
+ * out and not wait for I/O completion on any of the buffers.  This interface
+ * is only safely useable for callers that can track I/O completion by higher
+ * level means, e.g. AIL pushing as the @buffer_list is consumed in this
+ * function.
  */
 int
-xfs_flush_buftarg(
-	xfs_buftarg_t	*target,
-	int		wait)
+xfs_buf_delwri_submit_nowait(
+	struct list_head	*buffer_list)
 {
-	xfs_buf_t	*bp;
-	int		pincount = 0;
-	LIST_HEAD(tmp_list);
-	LIST_HEAD(wait_list);
-	struct blk_plug plug;
+	LIST_HEAD		(io_list);
+	return __xfs_buf_delwri_submit(buffer_list, &io_list, false);
+}
 
-	flush_workqueue(xfslogd_workqueue);
+/*
+ * Write out a buffer list synchronously.
+ *
+ * This will take the @buffer_list, write all buffers out and wait for I/O
+ * completion on all of the buffers. @buffer_list is consumed by the function,
+ * so callers must have some other way of tracking buffers if they require such
+ * functionality.
+ */
+int
+xfs_buf_delwri_submit(
+	struct list_head	*buffer_list)
+{
+	LIST_HEAD		(io_list);
+	int			error = 0, error2;
+	struct xfs_buf		*bp;
 
-	set_bit(XBT_FORCE_FLUSH, &target->bt_flags);
-	pincount = xfs_buf_delwri_split(target, &tmp_list, 0);
+	__xfs_buf_delwri_submit(buffer_list, &io_list, true);
 
-	/*
-	 * Dropped the delayed write list lock, now walk the temporary list.
-	 * All I/O is issued async and then if we need to wait for completion
-	 * we do that after issuing all the IO.
-	 */
-	list_sort(NULL, &tmp_list, xfs_buf_cmp);
+	/* Wait for IO to complete. */
+	while (!list_empty(&io_list)) {
+		bp = list_first_entry(&io_list, struct xfs_buf, b_list);
 
-	blk_start_plug(&plug);
-	while (!list_empty(&tmp_list)) {
-		bp = list_first_entry(&tmp_list, struct xfs_buf, b_list);
-		ASSERT(target == bp->b_target);
 		list_del_init(&bp->b_list);
-		if (wait) {
-			bp->b_flags &= ~XBF_ASYNC;
-			list_add(&bp->b_list, &wait_list);
-		}
-		xfs_bdstrat_cb(bp);
-	}
-	blk_finish_plug(&plug);
-
-	if (wait) {
-		/* Wait for IO to complete. */
-		while (!list_empty(&wait_list)) {
-			bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
-
-			list_del_init(&bp->b_list);
-			xfs_buf_iowait(bp);
-			xfs_buf_relse(bp);
-		}
+		error2 = xfs_buf_iowait(bp);
+		xfs_buf_relse(bp);
+		if (!error)
+			error = error2;
 	}
 
-	return pincount;
+	return error;
 }
 
 int __init

fs/xfs/xfs_buf.h

@@ -32,11 +32,6 @@
 
 #define XFS_BUF_DADDR_NULL	((xfs_daddr_t) (-1LL))
 
-#define xfs_buf_ctob(pp)	((pp) * PAGE_CACHE_SIZE)
-#define xfs_buf_btoc(dd)	(((dd) + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT)
-#define xfs_buf_btoct(dd)	((dd) >> PAGE_CACHE_SHIFT)
-#define xfs_buf_poff(aa)	((aa) & ~PAGE_CACHE_MASK)
-
 typedef enum {
 	XBRW_READ = 1,			/* transfer into target memory */
 	XBRW_WRITE = 2,			/* transfer from target memory */
@@ -46,11 +41,9 @@ typedef enum {
 #define XBF_READ	(1 << 0) /* buffer intended for reading from device */
 #define XBF_WRITE	(1 << 1) /* buffer intended for writing to device */
 #define XBF_READ_AHEAD	(1 << 2) /* asynchronous read-ahead */
-#define XBF_MAPPED	(1 << 3) /* buffer mapped (b_addr valid) */
 #define XBF_ASYNC	(1 << 4) /* initiator will not wait for completion */
 #define XBF_DONE	(1 << 5) /* all pages in the buffer uptodate */
-#define XBF_DELWRI	(1 << 6) /* buffer has dirty pages */
-#define XBF_STALE	(1 << 7) /* buffer has been staled, do not find it */
+#define XBF_STALE	(1 << 6) /* buffer has been staled, do not find it */
 
 /* I/O hints for the BIO layer */
 #define XBF_SYNCIO	(1 << 10)/* treat this buffer as synchronous I/O */
@@ -58,14 +51,13 @@ typedef enum {
 #define XBF_FLUSH	(1 << 12)/* flush the disk cache before a write */
 
 /* flags used only as arguments to access routines */
-#define XBF_LOCK	(1 << 15)/* lock requested */
 #define XBF_TRYLOCK	(1 << 16)/* lock requested, but do not wait */
-#define XBF_DONT_BLOCK	(1 << 17)/* do not block in current thread */
+#define XBF_UNMAPPED	(1 << 17)/* do not map the buffer */
 
 /* flags used only internally */
 #define _XBF_PAGES	(1 << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	(1 << 21)/* backed by heap memory */
-#define _XBF_DELWRI_Q	(1 << 22)/* buffer on delwri queue */
+#define _XBF_DELWRI_Q	(1 << 22)/* buffer on a delwri queue */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -73,25 +65,18 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_READ,		"READ" }, \
 	{ XBF_WRITE,		"WRITE" }, \
 	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
-	{ XBF_MAPPED,		"MAPPED" }, \
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
-	{ XBF_DELWRI,		"DELWRI" }, \
 	{ XBF_STALE,		"STALE" }, \
 	{ XBF_SYNCIO,		"SYNCIO" }, \
 	{ XBF_FUA,		"FUA" }, \
 	{ XBF_FLUSH,		"FLUSH" }, \
-	{ XBF_LOCK,		"LOCK" },  	/* should never be set */\
-	{ XBF_TRYLOCK,		"TRYLOCK" }, 	/* ditto */\
-	{ XBF_DONT_BLOCK,	"DONT_BLOCK" },	/* ditto */\
+	{ XBF_TRYLOCK,		"TRYLOCK" }, 	/* should never be set */\
+	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
 
-typedef enum {
-	XBT_FORCE_FLUSH = 0,
-} xfs_buftarg_flags_t;
-
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
@@ -101,12 +86,6 @@ typedef struct xfs_buftarg {
 	unsigned int		bt_sshift;
 	size_t			bt_smask;
 
-	/* per device delwri queue */
-	struct task_struct	*bt_task;
-	struct list_head	bt_delwri_queue;
-	spinlock_t		bt_delwri_lock;
-	unsigned long		bt_flags;
-
 	/* LRU control structures */
 	struct shrinker		bt_shrinker;
 	struct list_head	bt_lru;
@@ -128,8 +107,8 @@ typedef struct xfs_buf {
 	 * fast-path on locking.
 	 */
 	struct rb_node		b_rbnode;	/* rbtree node */
-	xfs_off_t		b_file_offset;	/* offset in file */
-	size_t			b_buffer_length;/* size of buffer in bytes */
+	xfs_daddr_t		b_bn;		/* block number for I/O */
+	int			b_length;	/* size of buffer in BBs */
 	atomic_t		b_hold;		/* reference count */
 	atomic_t		b_lru_ref;	/* lru reclaim ref count */
 	xfs_buf_flags_t		b_flags;	/* status flags */
@@ -140,8 +119,6 @@ typedef struct xfs_buf {
 	struct list_head	b_list;
 	struct xfs_perag	*b_pag;		/* contains rbtree root */
 	xfs_buftarg_t		*b_target;	/* buffer target (device) */
-	xfs_daddr_t		b_bn;		/* block number for I/O */
-	size_t			b_count_desired;/* desired transfer size */
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_iodone_work;
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
@@ -150,7 +127,7 @@ typedef struct xfs_buf {
 	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
-	unsigned long		b_queuetime;	/* time buffer was queued */
+	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
 	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
 	unsigned int		b_page_count;	/* size of page array */
@@ -163,26 +140,30 @@ typedef struct xfs_buf {
 
 
 /* Finding and Reading Buffers */
-extern xfs_buf_t *_xfs_buf_find(xfs_buftarg_t *, xfs_off_t, size_t,
-				xfs_buf_flags_t, xfs_buf_t *);
+struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno,
+				size_t numblks, xfs_buf_flags_t flags,
+				struct xfs_buf *new_bp);
 #define xfs_incore(buftarg,blkno,len,lockit) \
 	_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
 
-extern xfs_buf_t *xfs_buf_get(xfs_buftarg_t *, xfs_off_t, size_t,
-				xfs_buf_flags_t);
-extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
-				xfs_buf_flags_t);
-
-struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *, xfs_off_t, size_t,
-			      xfs_buf_flags_t);
-extern void xfs_buf_set_empty(struct xfs_buf *bp, size_t len);
-extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int);
-extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t);
-extern void xfs_buf_hold(xfs_buf_t *);
-extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t);
-struct xfs_buf *xfs_buf_read_uncached(struct xfs_mount *mp,
-				struct xfs_buftarg *target,
-				xfs_daddr_t daddr, size_t length, int flags);
+struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
+				size_t numblks, xfs_buf_flags_t flags);
+struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno,
+				size_t numblks, xfs_buf_flags_t flags);
+void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
+				size_t numblks);
+
+struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
+struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno,
+				size_t numblks, xfs_buf_flags_t flags);
+void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
+int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
+
+struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
+				int flags);
+struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
+				xfs_daddr_t daddr, size_t numblks, int flags);
+void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
 extern void xfs_buf_free(xfs_buf_t *);
@@ -204,7 +185,7 @@ extern int xfs_bdstrat_cb(struct xfs_buf *);
 extern void xfs_buf_ioend(xfs_buf_t *,	int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern int xfs_buf_iorequest(xfs_buf_t *);
+extern void xfs_buf_iorequest(xfs_buf_t *);
 extern int xfs_buf_iowait(xfs_buf_t *);
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
@@ -220,24 +201,22 @@ static inline int xfs_buf_geterror(xfs_buf_t *bp)
 extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
 
 /* Delayed Write Buffer Routines */
-extern void xfs_buf_delwri_queue(struct xfs_buf *);
-extern void xfs_buf_delwri_dequeue(struct xfs_buf *);
-extern void xfs_buf_delwri_promote(struct xfs_buf *);
+extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
+extern int xfs_buf_delwri_submit(struct list_head *);
+extern int xfs_buf_delwri_submit_nowait(struct list_head *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);
 extern void xfs_buf_terminate(void);
 
 #define XFS_BUF_ZEROFLAGS(bp) \
-	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \
+	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
 			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
 
 void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
 #define XFS_BUF_ISSTALE(bp)	((bp)->b_flags & XBF_STALE)
 
-#define XFS_BUF_ISDELAYWRITE(bp)	((bp)->b_flags & XBF_DELWRI)
-
 #define XFS_BUF_DONE(bp)	((bp)->b_flags |= XBF_DONE)
 #define XFS_BUF_UNDONE(bp)	((bp)->b_flags &= ~XBF_DONE)
 #define XFS_BUF_ISDONE(bp)	((bp)->b_flags & XBF_DONE)
@@ -256,12 +235,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 
 #define XFS_BUF_ADDR(bp)		((bp)->b_bn)
 #define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_bn = (xfs_daddr_t)(bno))
-#define XFS_BUF_OFFSET(bp)		((bp)->b_file_offset)
-#define XFS_BUF_SET_OFFSET(bp, off)	((bp)->b_file_offset = (off))
-#define XFS_BUF_COUNT(bp)		((bp)->b_count_desired)
-#define XFS_BUF_SET_COUNT(bp, cnt)	((bp)->b_count_desired = (cnt))
-#define XFS_BUF_SIZE(bp)		((bp)->b_buffer_length)
-#define XFS_BUF_SET_SIZE(bp, cnt)	((bp)->b_buffer_length = (cnt))
 
 static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {
@@ -287,7 +260,6 @@ extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
 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);
-extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
 
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)

fs/xfs/xfs_buf_item.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -123,11 +122,11 @@ xfs_buf_item_log_check(
 	ASSERT(bip->bli_logged != NULL);
 
 	bp = bip->bli_buf;
-	ASSERT(XFS_BUF_COUNT(bp) > 0);
+	ASSERT(bp->b_length > 0);
 	ASSERT(bp->b_addr != NULL);
 	orig = bip->bli_orig;
 	buffer = bp->b_addr;
-	for (x = 0; x < XFS_BUF_COUNT(bp); x++) {
+	for (x = 0; x < BBTOB(bp->b_length); x++) {
 		if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
 			xfs_emerg(bp->b_mount,
 				"%s: bip %x buffer %x orig %x index %d",
@@ -418,7 +417,6 @@ xfs_buf_item_unpin(
 	if (freed && stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
-		ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
 		ASSERT(XFS_BUF_ISSTALE(bp));
 		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
 
@@ -455,42 +453,42 @@ xfs_buf_item_unpin(
 			bp->b_iodone = NULL;
 		} else {
 			spin_lock(&ailp->xa_lock);
-			xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
+			xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
 			ASSERT(bp->b_fspriv == NULL);
 		}
 		xfs_buf_relse(bp);
+	} else if (freed && remove) {
+		xfs_buf_lock(bp);
+		xfs_buf_ioerror(bp, EIO);
+		XFS_BUF_UNDONE(bp);
+		xfs_buf_stale(bp);
+		xfs_buf_ioend(bp, 0);
 	}
 }
 
-/*
- * This is called to attempt to lock the buffer associated with this
- * buf log item.  Don't sleep on the buffer lock.  If we can't get
- * the lock right away, return 0.  If we can get the lock, take a
- * reference to the buffer. If this is a delayed write buffer that
- * needs AIL help to be written back, invoke the pushbuf routine
- * rather than the normal success path.
- */
 STATIC uint
-xfs_buf_item_trylock(
-	struct xfs_log_item	*lip)
+xfs_buf_item_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
+	uint			rval = XFS_ITEM_SUCCESS;
 
 	if (xfs_buf_ispinned(bp))
 		return XFS_ITEM_PINNED;
 	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
 
-	/* take a reference to the buffer.  */
-	xfs_buf_hold(bp);
-
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	trace_xfs_buf_item_trylock(bip);
-	if (XFS_BUF_ISDELAYWRITE(bp))
-		return XFS_ITEM_PUSHBUF;
-	return XFS_ITEM_SUCCESS;
+
+	trace_xfs_buf_item_push(bip);
+
+	if (!xfs_buf_delwri_queue(bp, buffer_list))
+		rval = XFS_ITEM_FLUSHING;
+	xfs_buf_unlock(bp);
+	return rval;
 }
 
 /*
@@ -603,49 +601,6 @@ xfs_buf_item_committed(
 	return lsn;
 }
 
-/*
- * The buffer is locked, but is not a delayed write buffer. This happens
- * if we race with IO completion and hence we don't want to try to write it
- * again. Just release the buffer.
- */
-STATIC void
-xfs_buf_item_push(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
-	struct xfs_buf		*bp = bip->bli_buf;
-
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!XFS_BUF_ISDELAYWRITE(bp));
-
-	trace_xfs_buf_item_push(bip);
-
-	xfs_buf_relse(bp);
-}
-
-/*
- * The buffer is locked and is a delayed write buffer. Promote the buffer
- * in the delayed write queue as the caller knows that they must invoke
- * the xfsbufd to get this buffer written. We have to unlock the buffer
- * to allow the xfsbufd to write it, too.
- */
-STATIC bool
-xfs_buf_item_pushbuf(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
-	struct xfs_buf		*bp = bip->bli_buf;
-
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(XFS_BUF_ISDELAYWRITE(bp));
-
-	trace_xfs_buf_item_pushbuf(bip);
-
-	xfs_buf_delwri_promote(bp);
-	xfs_buf_relse(bp);
-	return true;
-}
-
 STATIC void
 xfs_buf_item_committing(
 	struct xfs_log_item	*lip,
@@ -661,11 +616,9 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_format	= xfs_buf_item_format,
 	.iop_pin	= xfs_buf_item_pin,
 	.iop_unpin	= xfs_buf_item_unpin,
-	.iop_trylock	= xfs_buf_item_trylock,
 	.iop_unlock	= xfs_buf_item_unlock,
 	.iop_committed	= xfs_buf_item_committed,
 	.iop_push	= xfs_buf_item_push,
-	.iop_pushbuf	= xfs_buf_item_pushbuf,
 	.iop_committing = xfs_buf_item_committing
 };
 
@@ -703,7 +656,8 @@ xfs_buf_item_init(
 	 * truncate any pieces.  map_size is the size of the
 	 * bitmap needed to describe the chunks of the buffer.
 	 */
-	chunks = (int)((XFS_BUF_COUNT(bp) + (XFS_BLF_CHUNK - 1)) >> XFS_BLF_SHIFT);
+	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
+								XFS_BLF_SHIFT);
 	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
 
 	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
@@ -713,7 +667,7 @@ xfs_buf_item_init(
 	xfs_buf_hold(bp);
 	bip->bli_format.blf_type = XFS_LI_BUF;
 	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)BTOBB(XFS_BUF_COUNT(bp));
+	bip->bli_format.blf_len = (ushort)bp->b_length;
 	bip->bli_format.blf_map_size = map_size;
 
 #ifdef XFS_TRANS_DEBUG
@@ -725,9 +679,9 @@ xfs_buf_item_init(
 	 * the buffer to indicate which bytes the callers have asked
 	 * to have logged.
 	 */
-	bip->bli_orig = (char *)kmem_alloc(XFS_BUF_COUNT(bp), KM_SLEEP);
-	memcpy(bip->bli_orig, bp->b_addr, XFS_BUF_COUNT(bp));
-	bip->bli_logged = (char *)kmem_zalloc(XFS_BUF_COUNT(bp) / NBBY, KM_SLEEP);
+	bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP);
+	memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length));
+	bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP);
 #endif
 
 	/*
@@ -984,20 +938,27 @@ xfs_buf_iodone_callbacks(
 	 * If the write was asynchronous then no one will be looking for the
 	 * error.  Clear the error state and write the buffer out again.
 	 *
-	 * During sync or umount we'll write all pending buffers again
-	 * synchronous, which will catch these errors if they keep hanging
-	 * around.
+	 * XXX: This helps against transient write errors, but we need to find
+	 * a way to shut the filesystem down if the writes keep failing.
+	 *
+	 * In practice we'll shut the filesystem down soon as non-transient
+	 * erorrs tend to affect the whole device and a failing log write
+	 * will make us give up.  But we really ought to do better here.
 	 */
 	if (XFS_BUF_ISASYNC(bp)) {
+		ASSERT(bp->b_iodone != NULL);
+
+		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+
 		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
 
 		if (!XFS_BUF_ISSTALE(bp)) {
-			xfs_buf_delwri_queue(bp);
-			XFS_BUF_DONE(bp);
+			bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+			xfs_bdstrat_cb(bp);
+		} else {
+			xfs_buf_relse(bp);
 		}
-		ASSERT(bp->b_iodone != NULL);
-		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
-		xfs_buf_relse(bp);
+
 		return;
 	}
 
@@ -1045,6 +1006,6 @@ xfs_buf_iodone(
 	 * Either way, AIL is useless if we're forcing a shutdown.
 	 */
 	spin_lock(&ailp->xa_lock);
-	xfs_trans_ail_delete(ailp, lip);
+	xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
 	xfs_buf_item_free(BUF_ITEM(lip));
 }

fs/xfs/xfs_da_btree.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -2277,20 +2276,20 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
 	if (nbuf == 1) {
 		dabuf->nbuf = 1;
 		bp = bps[0];
-		dabuf->bbcount = (short)BTOBB(XFS_BUF_COUNT(bp));
+		dabuf->bbcount = bp->b_length;
 		dabuf->data = bp->b_addr;
 		dabuf->bps[0] = bp;
 	} else {
 		dabuf->nbuf = nbuf;
 		for (i = 0, dabuf->bbcount = 0; i < nbuf; i++) {
 			dabuf->bps[i] = bp = bps[i];
-			dabuf->bbcount += BTOBB(XFS_BUF_COUNT(bp));
+			dabuf->bbcount += bp->b_length;
 		}
 		dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP);
-		for (i = off = 0; i < nbuf; i++, off += XFS_BUF_COUNT(bp)) {
+		for (i = off = 0; i < nbuf; i++, off += BBTOB(bp->b_length)) {
 			bp = bps[i];
 			memcpy((char *)dabuf->data + off, bp->b_addr,
-				XFS_BUF_COUNT(bp));
+				BBTOB(bp->b_length));
 		}
 	}
 	return dabuf;
@@ -2310,10 +2309,10 @@ xfs_da_buf_clean(xfs_dabuf_t *dabuf)
 		ASSERT(dabuf->nbuf > 1);
 		dabuf->dirty = 0;
 		for (i = off = 0; i < dabuf->nbuf;
-				i++, off += XFS_BUF_COUNT(bp)) {
+				i++, off += BBTOB(bp->b_length)) {
 			bp = dabuf->bps[i];
 			memcpy(bp->b_addr, dabuf->data + off,
-						XFS_BUF_COUNT(bp));
+						BBTOB(bp->b_length));
 		}
 	}
 }
@@ -2356,10 +2355,10 @@ xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
 	}
 	dabuf->dirty = 1;
 	ASSERT(first <= last);
-	for (i = off = 0; i < dabuf->nbuf; i++, off += XFS_BUF_COUNT(bp)) {
+	for (i = off = 0; i < dabuf->nbuf; i++, off += BBTOB(bp->b_length)) {
 		bp = dabuf->bps[i];
 		f = off;
-		l = f + XFS_BUF_COUNT(bp) - 1;
+		l = f + BBTOB(bp->b_length) - 1;
 		if (f < first)
 			f = first;
 		if (l > last)

fs/xfs/xfs_dfrag.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_dir2.c

@@ -18,7 +18,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"

fs/xfs/xfs_dir2_block.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_dir2_data.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_dir2_leaf.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_dir2_node.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_dir2_sf.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_discard.c

@@ -17,7 +17,6 @@
  */
 #include "xfs.h"
 #include "xfs_sb.h"
-#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
@@ -30,6 +29,7 @@
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
+#include "xfs_extent_busy.h"
 #include "xfs_discard.h"
 #include "xfs_trace.h"
 
@@ -118,7 +118,7 @@ xfs_trim_extents(
 		 * If any blocks in the range are still busy, skip the
 		 * discard and try again the next time.
 		 */
-		if (xfs_alloc_busy_search(mp, agno, fbno, flen)) {
+		if (xfs_extent_busy_search(mp, agno, fbno, flen)) {
 			trace_xfs_discard_busy(mp, agno, fbno, flen);
 			goto next_extent;
 		}
@@ -212,7 +212,7 @@ xfs_discard_extents(
 	struct xfs_mount	*mp,
 	struct list_head	*list)
 {
-	struct xfs_busy_extent	*busyp;
+	struct xfs_extent_busy	*busyp;
 	int			error = 0;
 
 	list_for_each_entry(busyp, list, list) {

fs/xfs/xfs_dquot.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -857,7 +856,7 @@ xfs_qm_dqflush_done(
 		/* xfs_trans_ail_delete() drops the AIL lock. */
 		spin_lock(&ailp->xa_lock);
 		if (lip->li_lsn == qip->qli_flush_lsn)
-			xfs_trans_ail_delete(ailp, lip);
+			xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
 		else
 			spin_unlock(&ailp->xa_lock);
 	}
@@ -878,8 +877,8 @@ xfs_qm_dqflush_done(
  */
 int
 xfs_qm_dqflush(
-	xfs_dquot_t		*dqp,
-	uint			flags)
+	struct xfs_dquot	*dqp,
+	struct xfs_buf		**bpp)
 {
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_buf		*bp;
@@ -891,25 +890,30 @@ xfs_qm_dqflush(
 
 	trace_xfs_dqflush(dqp);
 
-	/*
-	 * If not dirty, or it's pinned and we are not supposed to block, nada.
-	 */
-	if (!XFS_DQ_IS_DIRTY(dqp) ||
-	    ((flags & SYNC_TRYLOCK) && atomic_read(&dqp->q_pincount) > 0)) {
-		xfs_dqfunlock(dqp);
-		return 0;
-	}
+	*bpp = NULL;
+
 	xfs_qm_dqunpin_wait(dqp);
 
 	/*
 	 * This may have been unpinned because the filesystem is shutting
 	 * down forcibly. If that's the case we must not write this dquot
-	 * to disk, because the log record didn't make it to disk!
+	 * to disk, because the log record didn't make it to disk.
+	 *
+	 * We also have to remove the log item from the AIL in this case,
+	 * as we wait for an emptry AIL as part of the unmount process.
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp)) {
+		struct xfs_log_item	*lip = &dqp->q_logitem.qli_item;
 		dqp->dq_flags &= ~XFS_DQ_DIRTY;
-		xfs_dqfunlock(dqp);
-		return XFS_ERROR(EIO);
+
+		spin_lock(&mp->m_ail->xa_lock);
+		if (lip->li_flags & XFS_LI_IN_AIL)
+			xfs_trans_ail_delete(mp->m_ail, lip,
+					     SHUTDOWN_CORRUPT_INCORE);
+		else
+			spin_unlock(&mp->m_ail->xa_lock);
+		error = XFS_ERROR(EIO);
+		goto out_unlock;
 	}
 
 	/*
@@ -917,11 +921,8 @@ xfs_qm_dqflush(
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
 				   mp->m_quotainfo->qi_dqchunklen, 0, &bp);
-	if (error) {
-		ASSERT(error != ENOENT);
-		xfs_dqfunlock(dqp);
-		return error;
-	}
+	if (error)
+		goto out_unlock;
 
 	/*
 	 * Calculate the location of the dquot inside the buffer.
@@ -967,20 +968,13 @@ xfs_qm_dqflush(
 		xfs_log_force(mp, 0);
 	}
 
-	if (flags & SYNC_WAIT)
-		error = xfs_bwrite(bp);
-	else
-		xfs_buf_delwri_queue(bp);
-
-	xfs_buf_relse(bp);
-
 	trace_xfs_dqflush_done(dqp);
+	*bpp = bp;
+	return 0;
 
-	/*
-	 * dqp is still locked, but caller is free to unlock it now.
-	 */
-	return error;
-
+out_unlock:
+	xfs_dqfunlock(dqp);
+	return XFS_ERROR(EIO);
 }
 
 /*
@@ -1011,39 +1005,6 @@ xfs_dqlock2(
 	}
 }
 
-/*
- * Give the buffer a little push if it is incore and
- * wait on the flush lock.
- */
-void
-xfs_dqflock_pushbuf_wait(
-	xfs_dquot_t	*dqp)
-{
-	xfs_mount_t	*mp = dqp->q_mount;
-	xfs_buf_t	*bp;
-
-	/*
-	 * Check to see if the dquot has been flushed delayed
-	 * write.  If so, grab its buffer and send it
-	 * out immediately.  We'll be able to acquire
-	 * the flush lock when the I/O completes.
-	 */
-	bp = xfs_incore(mp->m_ddev_targp, dqp->q_blkno,
-			mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
-	if (!bp)
-		goto out_lock;
-
-	if (XFS_BUF_ISDELAYWRITE(bp)) {
-		if (xfs_buf_ispinned(bp))
-			xfs_log_force(mp, 0);
-		xfs_buf_delwri_promote(bp);
-		wake_up_process(bp->b_target->bt_task);
-	}
-	xfs_buf_relse(bp);
-out_lock:
-	xfs_dqflock(dqp);
-}
-
 int __init
 xfs_qm_init(void)
 {

fs/xfs/xfs_dquot.h

@@ -141,7 +141,7 @@ static inline xfs_dquot_t *xfs_inode_dquot(struct xfs_inode *ip, int type)
 extern int		xfs_qm_dqread(struct xfs_mount *, xfs_dqid_t, uint,
 					uint, struct xfs_dquot	**);
 extern void		xfs_qm_dqdestroy(xfs_dquot_t *);
-extern int		xfs_qm_dqflush(xfs_dquot_t *, uint);
+extern int		xfs_qm_dqflush(struct xfs_dquot *, struct xfs_buf **);
 extern void		xfs_qm_dqunpin_wait(xfs_dquot_t *);
 extern void		xfs_qm_adjust_dqtimers(xfs_mount_t *,
 					xfs_disk_dquot_t *);
@@ -152,7 +152,6 @@ extern int		xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *,
 extern void		xfs_qm_dqput(xfs_dquot_t *);
 
 extern void		xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
-extern void		xfs_dqflock_pushbuf_wait(struct xfs_dquot *dqp);
 
 static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
 {

fs/xfs/xfs_dquot_item.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -108,38 +106,6 @@ xfs_qm_dquot_logitem_unpin(
 		wake_up(&dqp->q_pinwait);
 }
 
-/*
- * Given the logitem, this writes the corresponding dquot entry to disk
- * asynchronously. This is called with the dquot entry securely locked;
- * we simply get xfs_qm_dqflush() to do the work, and unlock the dquot
- * at the end.
- */
-STATIC void
-xfs_qm_dquot_logitem_push(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_dquot	*dqp = DQUOT_ITEM(lip)->qli_dquot;
-	int			error;
-
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	ASSERT(!completion_done(&dqp->q_flush));
-
-	/*
-	 * Since we were able to lock the dquot's flush lock and
-	 * we found it on the AIL, the dquot must be dirty.  This
-	 * is because the dquot is removed from the AIL while still
-	 * holding the flush lock in xfs_dqflush_done().  Thus, if
-	 * we found it in the AIL and were able to obtain the flush
-	 * lock without sleeping, then there must not have been
-	 * anyone in the process of flushing the dquot.
-	 */
-	error = xfs_qm_dqflush(dqp, SYNC_TRYLOCK);
-	if (error)
-		xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
-			__func__, error, dqp);
-	xfs_dqunlock(dqp);
-}
-
 STATIC xfs_lsn_t
 xfs_qm_dquot_logitem_committed(
 	struct xfs_log_item	*lip,
@@ -171,67 +137,15 @@ xfs_qm_dqunpin_wait(
 	wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
 }
 
-/*
- * This is called when IOP_TRYLOCK returns XFS_ITEM_PUSHBUF to indicate that
- * the dquot is locked by us, but the flush lock isn't. So, here we are
- * going to see if the relevant dquot buffer is incore, waiting on DELWRI.
- * If so, we want to push it out to help us take this item off the AIL as soon
- * as possible.
- *
- * We must not be holding the AIL lock at this point. Calling incore() to
- * search the buffer cache can be a time consuming thing, and AIL lock is a
- * spinlock.
- */
-STATIC bool
-xfs_qm_dquot_logitem_pushbuf(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_dq_logitem	*qlip = DQUOT_ITEM(lip);
-	struct xfs_dquot	*dqp = qlip->qli_dquot;
-	struct xfs_buf		*bp;
-	bool			ret = true;
-
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-
-	/*
-	 * If flushlock isn't locked anymore, chances are that the
-	 * inode flush completed and the inode was taken off the AIL.
-	 * So, just get out.
-	 */
-	if (completion_done(&dqp->q_flush) ||
-	    !(lip->li_flags & XFS_LI_IN_AIL)) {
-		xfs_dqunlock(dqp);
-		return true;
-	}
-
-	bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno,
-			dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
-	xfs_dqunlock(dqp);
-	if (!bp)
-		return true;
-	if (XFS_BUF_ISDELAYWRITE(bp))
-		xfs_buf_delwri_promote(bp);
-	if (xfs_buf_ispinned(bp))
-		ret = false;
-	xfs_buf_relse(bp);
-	return ret;
-}
-
-/*
- * This is called to attempt to lock the dquot associated with this
- * dquot log item.  Don't sleep on the dquot lock or the flush lock.
- * If the flush lock is already held, indicating that the dquot has
- * been or is in the process of being flushed, then see if we can
- * find the dquot's buffer in the buffer cache without sleeping.  If
- * we can and it is marked delayed write, then we want to send it out.
- * We delay doing so until the push routine, though, to avoid sleeping
- * in any device strategy routines.
- */
 STATIC uint
-xfs_qm_dquot_logitem_trylock(
-	struct xfs_log_item	*lip)
+xfs_qm_dquot_logitem_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	struct xfs_dquot	*dqp = DQUOT_ITEM(lip)->qli_dquot;
+	struct xfs_buf		*bp = NULL;
+	uint			rval = XFS_ITEM_SUCCESS;
+	int			error;
 
 	if (atomic_read(&dqp->q_pincount) > 0)
 		return XFS_ITEM_PINNED;
@@ -239,16 +153,41 @@ xfs_qm_dquot_logitem_trylock(
 	if (!xfs_dqlock_nowait(dqp))
 		return XFS_ITEM_LOCKED;
 
+	/*
+	 * Re-check the pincount now that we stabilized the value by
+	 * taking the quota lock.
+	 */
+	if (atomic_read(&dqp->q_pincount) > 0) {
+		rval = XFS_ITEM_PINNED;
+		goto out_unlock;
+	}
+
+	/*
+	 * Someone else is already flushing the dquot.  Nothing we can do
+	 * here but wait for the flush to finish and remove the item from
+	 * the AIL.
+	 */
 	if (!xfs_dqflock_nowait(dqp)) {
-		/*
-		 * dquot has already been flushed to the backing buffer,
-		 * leave it locked, pushbuf routine will unlock it.
-		 */
-		return XFS_ITEM_PUSHBUF;
+		rval = XFS_ITEM_FLUSHING;
+		goto out_unlock;
 	}
 
-	ASSERT(lip->li_flags & XFS_LI_IN_AIL);
-	return XFS_ITEM_SUCCESS;
+	spin_unlock(&lip->li_ailp->xa_lock);
+
+	error = xfs_qm_dqflush(dqp, &bp);
+	if (error) {
+		xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
+			__func__, error, dqp);
+	} else {
+		if (!xfs_buf_delwri_queue(bp, buffer_list))
+			rval = XFS_ITEM_FLUSHING;
+		xfs_buf_relse(bp);
+	}
+
+	spin_lock(&lip->li_ailp->xa_lock);
+out_unlock:
+	xfs_dqunlock(dqp);
+	return rval;
 }
 
 /*
@@ -299,11 +238,9 @@ static const struct xfs_item_ops xfs_dquot_item_ops = {
 	.iop_format	= xfs_qm_dquot_logitem_format,
 	.iop_pin	= xfs_qm_dquot_logitem_pin,
 	.iop_unpin	= xfs_qm_dquot_logitem_unpin,
-	.iop_trylock	= xfs_qm_dquot_logitem_trylock,
 	.iop_unlock	= xfs_qm_dquot_logitem_unlock,
 	.iop_committed	= xfs_qm_dquot_logitem_committed,
 	.iop_push	= xfs_qm_dquot_logitem_push,
-	.iop_pushbuf	= xfs_qm_dquot_logitem_pushbuf,
 	.iop_committing = xfs_qm_dquot_logitem_committing
 };
 
@@ -398,11 +335,13 @@ xfs_qm_qoff_logitem_unpin(
 }
 
 /*
- * Quotaoff items have no locking, so just return success.
+ * There isn't much you can do to push a quotaoff item.  It is simply
+ * stuck waiting for the log to be flushed to disk.
  */
 STATIC uint
-xfs_qm_qoff_logitem_trylock(
-	struct xfs_log_item	*lip)
+xfs_qm_qoff_logitem_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	return XFS_ITEM_LOCKED;
 }
@@ -429,17 +368,6 @@ xfs_qm_qoff_logitem_committed(
 	return lsn;
 }
 
-/*
- * There isn't much you can do to push on an quotaoff item.  It is simply
- * stuck waiting for the log to be flushed to disk.
- */
-STATIC void
-xfs_qm_qoff_logitem_push(
-	struct xfs_log_item	*lip)
-{
-}
-
-
 STATIC xfs_lsn_t
 xfs_qm_qoffend_logitem_committed(
 	struct xfs_log_item	*lip,
@@ -454,7 +382,7 @@ xfs_qm_qoffend_logitem_committed(
 	 * xfs_trans_ail_delete() drops the AIL lock.
 	 */
 	spin_lock(&ailp->xa_lock);
-	xfs_trans_ail_delete(ailp, (xfs_log_item_t *)qfs);
+	xfs_trans_ail_delete(ailp, &qfs->qql_item, SHUTDOWN_LOG_IO_ERROR);
 
 	kmem_free(qfs);
 	kmem_free(qfe);
@@ -487,7 +415,6 @@ static const struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
 	.iop_format	= xfs_qm_qoff_logitem_format,
 	.iop_pin	= xfs_qm_qoff_logitem_pin,
 	.iop_unpin	= xfs_qm_qoff_logitem_unpin,
-	.iop_trylock	= xfs_qm_qoff_logitem_trylock,
 	.iop_unlock	= xfs_qm_qoff_logitem_unlock,
 	.iop_committed	= xfs_qm_qoffend_logitem_committed,
 	.iop_push	= xfs_qm_qoff_logitem_push,
@@ -502,7 +429,6 @@ static const struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
 	.iop_format	= xfs_qm_qoff_logitem_format,
 	.iop_pin	= xfs_qm_qoff_logitem_pin,
 	.iop_unpin	= xfs_qm_qoff_logitem_unpin,
-	.iop_trylock	= xfs_qm_qoff_logitem_trylock,
 	.iop_unlock	= xfs_qm_qoff_logitem_unlock,
 	.iop_committed	= xfs_qm_qoff_logitem_committed,
 	.iop_push	= xfs_qm_qoff_logitem_push,

fs/xfs/xfs_error.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_export.c

@@ -17,7 +17,6 @@
  */
 #include "xfs.h"
 #include "xfs_types.h"
-#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"

fs/xfs/xfs_extent_busy.c

@@ -0,0 +1,603 @@
+/*
+ * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2010 David Chinner.
+ * Copyright (c) 2011 Christoph Hellwig.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_types.h"
+#include "xfs_log.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_inode.h"
+#include "xfs_extent_busy.h"
+#include "xfs_trace.h"
+
+void
+xfs_extent_busy_insert(
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	unsigned int		flags)
+{
+	struct xfs_extent_busy	*new;
+	struct xfs_extent_busy	*busyp;
+	struct xfs_perag	*pag;
+	struct rb_node		**rbp;
+	struct rb_node		*parent = NULL;
+
+	new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_MAYFAIL);
+	if (!new) {
+		/*
+		 * No Memory!  Since it is now not possible to track the free
+		 * block, make this a synchronous transaction to insure that
+		 * the block is not reused before this transaction commits.
+		 */
+		trace_xfs_extent_busy_enomem(tp->t_mountp, agno, bno, len);
+		xfs_trans_set_sync(tp);
+		return;
+	}
+
+	new->agno = agno;
+	new->bno = bno;
+	new->length = len;
+	INIT_LIST_HEAD(&new->list);
+	new->flags = flags;
+
+	/* trace before insert to be able to see failed inserts */
+	trace_xfs_extent_busy(tp->t_mountp, agno, bno, len);
+
+	pag = xfs_perag_get(tp->t_mountp, new->agno);
+	spin_lock(&pag->pagb_lock);
+	rbp = &pag->pagb_tree.rb_node;
+	while (*rbp) {
+		parent = *rbp;
+		busyp = rb_entry(parent, struct xfs_extent_busy, rb_node);
+
+		if (new->bno < busyp->bno) {
+			rbp = &(*rbp)->rb_left;
+			ASSERT(new->bno + new->length <= busyp->bno);
+		} else if (new->bno > busyp->bno) {
+			rbp = &(*rbp)->rb_right;
+			ASSERT(bno >= busyp->bno + busyp->length);
+		} else {
+			ASSERT(0);
+		}
+	}
+
+	rb_link_node(&new->rb_node, parent, rbp);
+	rb_insert_color(&new->rb_node, &pag->pagb_tree);
+
+	list_add(&new->list, &tp->t_busy);
+	spin_unlock(&pag->pagb_lock);
+	xfs_perag_put(pag);
+}
+
+/*
+ * Search for a busy extent within the range of the extent we are about to
+ * allocate.  You need to be holding the busy extent tree lock when calling
+ * xfs_extent_busy_search(). This function returns 0 for no overlapping busy
+ * extent, -1 for an overlapping but not exact busy extent, and 1 for an exact
+ * match. This is done so that a non-zero return indicates an overlap that
+ * will require a synchronous transaction, but it can still be
+ * used to distinguish between a partial or exact match.
+ */
+int
+xfs_extent_busy_search(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len)
+{
+	struct xfs_perag	*pag;
+	struct rb_node		*rbp;
+	struct xfs_extent_busy	*busyp;
+	int			match = 0;
+
+	pag = xfs_perag_get(mp, agno);
+	spin_lock(&pag->pagb_lock);
+
+	rbp = pag->pagb_tree.rb_node;
+
+	/* find closest start bno overlap */
+	while (rbp) {
+		busyp = rb_entry(rbp, struct xfs_extent_busy, rb_node);
+		if (bno < busyp->bno) {
+			/* may overlap, but exact start block is lower */
+			if (bno + len > busyp->bno)
+				match = -1;
+			rbp = rbp->rb_left;
+		} else if (bno > busyp->bno) {
+			/* may overlap, but exact start block is higher */
+			if (bno < busyp->bno + busyp->length)
+				match = -1;
+			rbp = rbp->rb_right;
+		} else {
+			/* bno matches busyp, length determines exact match */
+			match = (busyp->length == len) ? 1 : -1;
+			break;
+		}
+	}
+	spin_unlock(&pag->pagb_lock);
+	xfs_perag_put(pag);
+	return match;
+}
+
+/*
+ * The found free extent [fbno, fend] overlaps part or all of the given busy
+ * extent.  If the overlap covers the beginning, the end, or all of the busy
+ * extent, the overlapping portion can be made unbusy and used for the
+ * allocation.  We can't split a busy extent because we can't modify a
+ * transaction/CIL context busy list, but we can update an entries block
+ * number or length.
+ *
+ * Returns true if the extent can safely be reused, or false if the search
+ * needs to be restarted.
+ */
+STATIC bool
+xfs_extent_busy_update_extent(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	struct xfs_extent_busy	*busyp,
+	xfs_agblock_t		fbno,
+	xfs_extlen_t		flen,
+	bool			userdata)
+{
+	xfs_agblock_t		fend = fbno + flen;
+	xfs_agblock_t		bbno = busyp->bno;
+	xfs_agblock_t		bend = bbno + busyp->length;
+
+	/*
+	 * This extent is currently being discarded.  Give the thread
+	 * performing the discard a chance to mark the extent unbusy
+	 * and retry.
+	 */
+	if (busyp->flags & XFS_EXTENT_BUSY_DISCARDED) {
+		spin_unlock(&pag->pagb_lock);
+		delay(1);
+		spin_lock(&pag->pagb_lock);
+		return false;
+	}
+
+	/*
+	 * If there is a busy extent overlapping a user allocation, we have
+	 * no choice but to force the log and retry the search.
+	 *
+	 * Fortunately this does not happen during normal operation, but
+	 * only if the filesystem is very low on space and has to dip into
+	 * the AGFL for normal allocations.
+	 */
+	if (userdata)
+		goto out_force_log;
+
+	if (bbno < fbno && bend > fend) {
+		/*
+		 * Case 1:
+		 *    bbno           bend
+		 *    +BBBBBBBBBBBBBBBBB+
+		 *        +---------+
+		 *        fbno   fend
+		 */
+
+		/*
+		 * We would have to split the busy extent to be able to track
+		 * it correct, which we cannot do because we would have to
+		 * modify the list of busy extents attached to the transaction
+		 * or CIL context, which is immutable.
+		 *
+		 * Force out the log to clear the busy extent and retry the
+		 * search.
+		 */
+		goto out_force_log;
+	} else if (bbno >= fbno && bend <= fend) {
+		/*
+		 * Case 2:
+		 *    bbno           bend
+		 *    +BBBBBBBBBBBBBBBBB+
+		 *    +-----------------+
+		 *    fbno           fend
+		 *
+		 * Case 3:
+		 *    bbno           bend
+		 *    +BBBBBBBBBBBBBBBBB+
+		 *    +--------------------------+
+		 *    fbno                    fend
+		 *
+		 * Case 4:
+		 *             bbno           bend
+		 *             +BBBBBBBBBBBBBBBBB+
+		 *    +--------------------------+
+		 *    fbno                    fend
+		 *
+		 * Case 5:
+		 *             bbno           bend
+		 *             +BBBBBBBBBBBBBBBBB+
+		 *    +-----------------------------------+
+		 *    fbno                             fend
+		 *
+		 */
+
+		/*
+		 * The busy extent is fully covered by the extent we are
+		 * allocating, and can simply be removed from the rbtree.
+		 * However we cannot remove it from the immutable list
+		 * tracking busy extents in the transaction or CIL context,
+		 * so set the length to zero to mark it invalid.
+		 *
+		 * We also need to restart the busy extent search from the
+		 * tree root, because erasing the node can rearrange the
+		 * tree topology.
+		 */
+		rb_erase(&busyp->rb_node, &pag->pagb_tree);
+		busyp->length = 0;
+		return false;
+	} else if (fend < bend) {
+		/*
+		 * Case 6:
+		 *              bbno           bend
+		 *             +BBBBBBBBBBBBBBBBB+
+		 *             +---------+
+		 *             fbno   fend
+		 *
+		 * Case 7:
+		 *             bbno           bend
+		 *             +BBBBBBBBBBBBBBBBB+
+		 *    +------------------+
+		 *    fbno            fend
+		 *
+		 */
+		busyp->bno = fend;
+	} else if (bbno < fbno) {
+		/*
+		 * Case 8:
+		 *    bbno           bend
+		 *    +BBBBBBBBBBBBBBBBB+
+		 *        +-------------+
+		 *        fbno       fend
+		 *
+		 * Case 9:
+		 *    bbno           bend
+		 *    +BBBBBBBBBBBBBBBBB+
+		 *        +----------------------+
+		 *        fbno                fend
+		 */
+		busyp->length = fbno - busyp->bno;
+	} else {
+		ASSERT(0);
+	}
+
+	trace_xfs_extent_busy_reuse(mp, pag->pag_agno, fbno, flen);
+	return true;
+
+out_force_log:
+	spin_unlock(&pag->pagb_lock);
+	xfs_log_force(mp, XFS_LOG_SYNC);
+	trace_xfs_extent_busy_force(mp, pag->pag_agno, fbno, flen);
+	spin_lock(&pag->pagb_lock);
+	return false;
+}
+
+
+/*
+ * For a given extent [fbno, flen], make sure we can reuse it safely.
+ */
+void
+xfs_extent_busy_reuse(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		fbno,
+	xfs_extlen_t		flen,
+	bool			userdata)
+{
+	struct xfs_perag	*pag;
+	struct rb_node		*rbp;
+
+	ASSERT(flen > 0);
+
+	pag = xfs_perag_get(mp, agno);
+	spin_lock(&pag->pagb_lock);
+restart:
+	rbp = pag->pagb_tree.rb_node;
+	while (rbp) {
+		struct xfs_extent_busy *busyp =
+			rb_entry(rbp, struct xfs_extent_busy, rb_node);
+		xfs_agblock_t	bbno = busyp->bno;
+		xfs_agblock_t	bend = bbno + busyp->length;
+
+		if (fbno + flen <= bbno) {
+			rbp = rbp->rb_left;
+			continue;
+		} else if (fbno >= bend) {
+			rbp = rbp->rb_right;
+			continue;
+		}
+
+		if (!xfs_extent_busy_update_extent(mp, pag, busyp, fbno, flen,
+						  userdata))
+			goto restart;
+	}
+	spin_unlock(&pag->pagb_lock);
+	xfs_perag_put(pag);
+}
+
+/*
+ * For a given extent [fbno, flen], search the busy extent list to find a
+ * subset of the extent that is not busy.  If *rlen is smaller than
+ * args->minlen no suitable extent could be found, and the higher level
+ * code needs to force out the log and retry the allocation.
+ */
+void
+xfs_extent_busy_trim(
+	struct xfs_alloc_arg	*args,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	xfs_agblock_t		*rbno,
+	xfs_extlen_t		*rlen)
+{
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	struct rb_node		*rbp;
+
+	ASSERT(len > 0);
+
+	spin_lock(&args->pag->pagb_lock);
+restart:
+	fbno = bno;
+	flen = len;
+	rbp = args->pag->pagb_tree.rb_node;
+	while (rbp && flen >= args->minlen) {
+		struct xfs_extent_busy *busyp =
+			rb_entry(rbp, struct xfs_extent_busy, rb_node);
+		xfs_agblock_t	fend = fbno + flen;
+		xfs_agblock_t	bbno = busyp->bno;
+		xfs_agblock_t	bend = bbno + busyp->length;
+
+		if (fend <= bbno) {
+			rbp = rbp->rb_left;
+			continue;
+		} else if (fbno >= bend) {
+			rbp = rbp->rb_right;
+			continue;
+		}
+
+		/*
+		 * If this is a metadata allocation, try to reuse the busy
+		 * extent instead of trimming the allocation.
+		 */
+		if (!args->userdata &&
+		    !(busyp->flags & XFS_EXTENT_BUSY_DISCARDED)) {
+			if (!xfs_extent_busy_update_extent(args->mp, args->pag,
+							  busyp, fbno, flen,
+							  false))
+				goto restart;
+			continue;
+		}
+
+		if (bbno <= fbno) {
+			/* start overlap */
+
+			/*
+			 * Case 1:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *        +---------+
+			 *        fbno   fend
+			 *
+			 * Case 2:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *    +-------------+
+			 *    fbno       fend
+			 *
+			 * Case 3:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *        +-------------+
+			 *        fbno       fend
+			 *
+			 * Case 4:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *    +-----------------+
+			 *    fbno           fend
+			 *
+			 * No unbusy region in extent, return failure.
+			 */
+			if (fend <= bend)
+				goto fail;
+
+			/*
+			 * Case 5:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *        +----------------------+
+			 *        fbno                fend
+			 *
+			 * Case 6:
+			 *    bbno           bend
+			 *    +BBBBBBBBBBBBBBBBB+
+			 *    +--------------------------+
+			 *    fbno                    fend
+			 *
+			 * Needs to be trimmed to:
+			 *                       +-------+
+			 *                       fbno fend
+			 */
+			fbno = bend;
+		} else if (bend >= fend) {
+			/* end overlap */
+
+			/*
+			 * Case 7:
+			 *             bbno           bend
+			 *             +BBBBBBBBBBBBBBBBB+
+			 *    +------------------+
+			 *    fbno            fend
+			 *
+			 * Case 8:
+			 *             bbno           bend
+			 *             +BBBBBBBBBBBBBBBBB+
+			 *    +--------------------------+
+			 *    fbno                    fend
+			 *
+			 * Needs to be trimmed to:
+			 *    +-------+
+			 *    fbno fend
+			 */
+			fend = bbno;
+		} else {
+			/* middle overlap */
+
+			/*
+			 * Case 9:
+			 *             bbno           bend
+			 *             +BBBBBBBBBBBBBBBBB+
+			 *    +-----------------------------------+
+			 *    fbno                             fend
+			 *
+			 * Can be trimmed to:
+			 *    +-------+        OR         +-------+
+			 *    fbno fend                   fbno fend
+			 *
+			 * Backward allocation leads to significant
+			 * fragmentation of directories, which degrades
+			 * directory performance, therefore we always want to
+			 * choose the option that produces forward allocation
+			 * patterns.
+			 * Preferring the lower bno extent will make the next
+			 * request use "fend" as the start of the next
+			 * allocation;  if the segment is no longer busy at
+			 * that point, we'll get a contiguous allocation, but
+			 * even if it is still busy, we will get a forward
+			 * allocation.
+			 * We try to avoid choosing the segment at "bend",
+			 * because that can lead to the next allocation
+			 * taking the segment at "fbno", which would be a
+			 * backward allocation.  We only use the segment at
+			 * "fbno" if it is much larger than the current
+			 * requested size, because in that case there's a
+			 * good chance subsequent allocations will be
+			 * contiguous.
+			 */
+			if (bbno - fbno >= args->maxlen) {
+				/* left candidate fits perfect */
+				fend = bbno;
+			} else if (fend - bend >= args->maxlen * 4) {
+				/* right candidate has enough free space */
+				fbno = bend;
+			} else if (bbno - fbno >= args->minlen) {
+				/* left candidate fits minimum requirement */
+				fend = bbno;
+			} else {
+				goto fail;
+			}
+		}
+
+		flen = fend - fbno;
+	}
+	spin_unlock(&args->pag->pagb_lock);
+
+	if (fbno != bno || flen != len) {
+		trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len,
+					  fbno, flen);
+	}
+	*rbno = fbno;
+	*rlen = flen;
+	return;
+fail:
+	/*
+	 * Return a zero extent length as failure indications.  All callers
+	 * re-check if the trimmed extent satisfies the minlen requirement.
+	 */
+	spin_unlock(&args->pag->pagb_lock);
+	trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, fbno, 0);
+	*rbno = fbno;
+	*rlen = 0;
+}
+
+STATIC void
+xfs_extent_busy_clear_one(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	struct xfs_extent_busy	*busyp)
+{
+	if (busyp->length) {
+		trace_xfs_extent_busy_clear(mp, busyp->agno, busyp->bno,
+						busyp->length);
+		rb_erase(&busyp->rb_node, &pag->pagb_tree);
+	}
+
+	list_del_init(&busyp->list);
+	kmem_free(busyp);
+}
+
+/*
+ * Remove all extents on the passed in list from the busy extents tree.
+ * If do_discard is set skip extents that need to be discarded, and mark
+ * these as undergoing a discard operation instead.
+ */
+void
+xfs_extent_busy_clear(
+	struct xfs_mount	*mp,
+	struct list_head	*list,
+	bool			do_discard)
+{
+	struct xfs_extent_busy	*busyp, *n;
+	struct xfs_perag	*pag = NULL;
+	xfs_agnumber_t		agno = NULLAGNUMBER;
+
+	list_for_each_entry_safe(busyp, n, list, list) {
+		if (busyp->agno != agno) {
+			if (pag) {
+				spin_unlock(&pag->pagb_lock);
+				xfs_perag_put(pag);
+			}
+			pag = xfs_perag_get(mp, busyp->agno);
+			spin_lock(&pag->pagb_lock);
+			agno = busyp->agno;
+		}
+
+		if (do_discard && busyp->length &&
+		    !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD))
+			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
+		else
+			xfs_extent_busy_clear_one(mp, pag, busyp);
+	}
+
+	if (pag) {
+		spin_unlock(&pag->pagb_lock);
+		xfs_perag_put(pag);
+	}
+}
+
+/*
+ * Callback for list_sort to sort busy extents by the AG they reside in.
+ */
+int
+xfs_extent_busy_ag_cmp(
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
+{
+	return container_of(a, struct xfs_extent_busy, list)->agno -
+		container_of(b, struct xfs_extent_busy, list)->agno;
+}

fs/xfs/xfs_extent_busy.h

@@ -0,0 +1,69 @@
+/*
+ * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2010 David Chinner.
+ * Copyright (c) 2011 Christoph Hellwig.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_EXTENT_BUSY_H__
+#define	__XFS_EXTENT_BUSY_H__
+
+/*
+ * Busy block/extent entry.  Indexed by a rbtree in perag to mark blocks that
+ * have been freed but whose transactions aren't committed to disk yet.
+ *
+ * Note that we use the transaction ID to record the transaction, not the
+ * transaction structure itself. See xfs_extent_busy_insert() for details.
+ */
+struct xfs_extent_busy {
+	struct rb_node	rb_node;	/* ag by-bno indexed search tree */
+	struct list_head list;		/* transaction busy extent list */
+	xfs_agnumber_t	agno;
+	xfs_agblock_t	bno;
+	xfs_extlen_t	length;
+	unsigned int	flags;
+#define XFS_EXTENT_BUSY_DISCARDED	0x01	/* undergoing a discard op. */
+#define XFS_EXTENT_BUSY_SKIP_DISCARD	0x02	/* do not discard */
+};
+
+void
+xfs_extent_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno,
+	xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
+
+void
+xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list,
+	bool do_discard);
+
+int
+xfs_extent_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
+	xfs_agblock_t bno, xfs_extlen_t len);
+
+void
+xfs_extent_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno,
+	xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
+
+void
+xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t bno,
+	xfs_extlen_t len, xfs_agblock_t *rbno, xfs_extlen_t *rlen);
+
+int
+xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b);
+
+static inline void xfs_extent_busy_sort(struct list_head *list)
+{
+	list_sort(NULL, list, xfs_extent_busy_ag_cmp);
+}
+
+#endif /* __XFS_EXTENT_BUSY_H__ */

fs/xfs/xfs_extfree_item.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_sb.h"
@@ -64,7 +63,8 @@ __xfs_efi_release(
 	if (!test_and_clear_bit(XFS_EFI_COMMITTED, &efip->efi_flags)) {
 		spin_lock(&ailp->xa_lock);
 		/* xfs_trans_ail_delete() drops the AIL lock. */
-		xfs_trans_ail_delete(ailp, &efip->efi_item);
+		xfs_trans_ail_delete(ailp, &efip->efi_item,
+				     SHUTDOWN_LOG_IO_ERROR);
 		xfs_efi_item_free(efip);
 	}
 }
@@ -147,22 +147,20 @@ xfs_efi_item_unpin(
 }
 
 /*
- * Efi items have no locking or pushing.  However, since EFIs are
- * pulled from the AIL when their corresponding EFDs are committed
- * to disk, their situation is very similar to being pinned.  Return
- * XFS_ITEM_PINNED so that the caller will eventually flush the log.
- * This should help in getting the EFI out of the AIL.
+ * Efi items have no locking or pushing.  However, since EFIs are pulled from
+ * the AIL when their corresponding EFDs are committed to disk, their situation
+ * is very similar to being pinned.  Return XFS_ITEM_PINNED so that the caller
+ * will eventually flush the log.  This should help in getting the EFI out of
+ * the AIL.
  */
 STATIC uint
-xfs_efi_item_trylock(
-	struct xfs_log_item	*lip)
+xfs_efi_item_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	return XFS_ITEM_PINNED;
 }
 
-/*
- * Efi items have no locking, so just return.
- */
 STATIC void
 xfs_efi_item_unlock(
 	struct xfs_log_item	*lip)
@@ -189,17 +187,6 @@ xfs_efi_item_committed(
 	return lsn;
 }
 
-/*
- * There isn't much you can do to push on an efi item.  It is simply
- * stuck waiting for all of its corresponding efd items to be
- * committed to disk.
- */
-STATIC void
-xfs_efi_item_push(
-	struct xfs_log_item	*lip)
-{
-}
-
 /*
  * The EFI dependency tracking op doesn't do squat.  It can't because
  * it doesn't know where the free extent is coming from.  The dependency
@@ -222,7 +209,6 @@ static const struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_format	= xfs_efi_item_format,
 	.iop_pin	= xfs_efi_item_pin,
 	.iop_unpin	= xfs_efi_item_unpin,
-	.iop_trylock	= xfs_efi_item_trylock,
 	.iop_unlock	= xfs_efi_item_unlock,
 	.iop_committed	= xfs_efi_item_committed,
 	.iop_push	= xfs_efi_item_push,
@@ -404,19 +390,17 @@ xfs_efd_item_unpin(
 }
 
 /*
- * Efd items have no locking, so just return success.
+ * There isn't much you can do to push on an efd item.  It is simply stuck
+ * waiting for the log to be flushed to disk.
  */
 STATIC uint
-xfs_efd_item_trylock(
-	struct xfs_log_item	*lip)
+xfs_efd_item_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
-	return XFS_ITEM_LOCKED;
+	return XFS_ITEM_PINNED;
 }
 
-/*
- * Efd items have no locking or pushing, so return failure
- * so that the caller doesn't bother with us.
- */
 STATIC void
 xfs_efd_item_unlock(
 	struct xfs_log_item	*lip)
@@ -450,16 +434,6 @@ xfs_efd_item_committed(
 	return (xfs_lsn_t)-1;
 }
 
-/*
- * There isn't much you can do to push on an efd item.  It is simply
- * stuck waiting for the log to be flushed to disk.
- */
-STATIC void
-xfs_efd_item_push(
-	struct xfs_log_item	*lip)
-{
-}
-
 /*
  * The EFD dependency tracking op doesn't do squat.  It can't because
  * it doesn't know where the free extent is coming from.  The dependency
@@ -482,7 +456,6 @@ static const struct xfs_item_ops xfs_efd_item_ops = {
 	.iop_format	= xfs_efd_item_format,
 	.iop_pin	= xfs_efd_item_pin,
 	.iop_unpin	= xfs_efd_item_unpin,
-	.iop_trylock	= xfs_efd_item_trylock,
 	.iop_unlock	= xfs_efd_item_unlock,
 	.iop_committed	= xfs_efd_item_committed,
 	.iop_push	= xfs_efd_item_push,

fs/xfs/xfs_file.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_trans.h"
@@ -396,114 +394,96 @@ xfs_file_splice_write(
 }
 
 /*
- * This routine is called to handle zeroing any space in the last
- * block of the file that is beyond the EOF.  We do this since the
- * size is being increased without writing anything to that block
- * and we don't want anyone to read the garbage on the disk.
+ * This routine is called to handle zeroing any space in the last block of the
+ * file that is beyond the EOF.  We do this since the size is being increased
+ * without writing anything to that block and we don't want to read the
+ * garbage on the disk.
  */
 STATIC int				/* error (positive) */
 xfs_zero_last_block(
-	xfs_inode_t	*ip,
-	xfs_fsize_t	offset,
-	xfs_fsize_t	isize)
+	struct xfs_inode	*ip,
+	xfs_fsize_t		offset,
+	xfs_fsize_t		isize)
 {
-	xfs_fileoff_t	last_fsb;
-	xfs_mount_t	*mp = ip->i_mount;
-	int		nimaps;
-	int		zero_offset;
-	int		zero_len;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	zero_offset = XFS_B_FSB_OFFSET(mp, isize);
-	if (zero_offset == 0) {
-		/*
-		 * There are no extra bytes in the last block on disk to
-		 * zero, so return.
-		 */
-		return 0;
-	}
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
+	int			zero_offset = XFS_B_FSB_OFFSET(mp, isize);
+	int			zero_len;
+	int			nimaps = 1;
+	int			error = 0;
+	struct xfs_bmbt_irec	imap;
 
-	last_fsb = XFS_B_TO_FSBT(mp, isize);
-	nimaps = 1;
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
+
 	ASSERT(nimaps > 0);
+
 	/*
 	 * If the block underlying isize is just a hole, then there
 	 * is nothing to zero.
 	 */
-	if (imap.br_startblock == HOLESTARTBLOCK) {
+	if (imap.br_startblock == HOLESTARTBLOCK)
 		return 0;
-	}
-	/*
-	 * Zero the part of the last block beyond the EOF, and write it
-	 * out sync.  We need to drop the ilock while we do this so we
-	 * don't deadlock when the buffer cache calls back to us.
-	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
 	if (isize + zero_len > offset)
 		zero_len = offset - isize;
-	error = xfs_iozero(ip, isize, zero_len);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
+	return xfs_iozero(ip, isize, zero_len);
 }
 
 /*
- * Zero any on disk space between the current EOF and the new,
- * larger EOF.  This handles the normal case of zeroing the remainder
- * of the last block in the file and the unusual case of zeroing blocks
- * out beyond the size of the file.  This second case only happens
- * with fixed size extents and when the system crashes before the inode
- * size was updated but after blocks were allocated.  If fill is set,
- * then any holes in the range are filled and zeroed.  If not, the holes
- * are left alone as holes.
+ * Zero any on disk space between the current EOF and the new, larger EOF.
+ *
+ * This handles the normal case of zeroing the remainder of the last block in
+ * the file and the unusual case of zeroing blocks out beyond the size of the
+ * file.  This second case only happens with fixed size extents and when the
+ * system crashes before the inode size was updated but after blocks were
+ * allocated.
+ *
+ * Expects the iolock to be held exclusive, and will take the ilock internally.
  */
-
 int					/* error (positive) */
 xfs_zero_eof(
-	xfs_inode_t	*ip,
-	xfs_off_t	offset,		/* starting I/O offset */
-	xfs_fsize_t	isize)		/* current inode size */
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,		/* starting I/O offset */
+	xfs_fsize_t		isize)		/* current inode size */
 {
-	xfs_mount_t	*mp = ip->i_mount;
-	xfs_fileoff_t	start_zero_fsb;
-	xfs_fileoff_t	end_zero_fsb;
-	xfs_fileoff_t	zero_count_fsb;
-	xfs_fileoff_t	last_fsb;
-	xfs_fileoff_t	zero_off;
-	xfs_fsize_t	zero_len;
-	int		nimaps;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		start_zero_fsb;
+	xfs_fileoff_t		end_zero_fsb;
+	xfs_fileoff_t		zero_count_fsb;
+	xfs_fileoff_t		last_fsb;
+	xfs_fileoff_t		zero_off;
+	xfs_fsize_t		zero_len;
+	int			nimaps;
+	int			error = 0;
+	struct xfs_bmbt_irec	imap;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(offset > isize);
 
 	/*
 	 * First handle zeroing the block on which isize resides.
+	 *
 	 * We only zero a part of that block so it is handled specially.
 	 */
-	error = xfs_zero_last_block(ip, offset, isize);
-	if (error) {
-		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-		return error;
+	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
+		error = xfs_zero_last_block(ip, offset, isize);
+		if (error)
+			return error;
 	}
 
 	/*
-	 * Calculate the range between the new size and the old
-	 * where blocks needing to be zeroed may exist.  To get the
-	 * block where the last byte in the file currently resides,
-	 * we need to subtract one from the size and truncate back
-	 * to a block boundary.  We subtract 1 in case the size is
-	 * exactly on a block boundary.
+	 * Calculate the range between the new size and the old where blocks
+	 * needing to be zeroed may exist.
+	 *
+	 * To get the block where the last byte in the file currently resides,
+	 * we need to subtract one from the size and truncate back to a block
+	 * boundary.  We subtract 1 in case the size is exactly on a block
+	 * boundary.
 	 */
 	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
 	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
@@ -521,23 +501,18 @@ xfs_zero_eof(
 	while (start_zero_fsb <= end_zero_fsb) {
 		nimaps = 1;
 		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
+
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
 					  &imap, &nimaps, 0);
-		if (error) {
-			ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (error)
 			return error;
-		}
+
 		ASSERT(nimaps > 0);
 
 		if (imap.br_state == XFS_EXT_UNWRITTEN ||
 		    imap.br_startblock == HOLESTARTBLOCK) {
-			/*
-			 * This loop handles initializing pages that were
-			 * partially initialized by the code below this
-			 * loop. It basically zeroes the part of the page
-			 * that sits on a hole and sets the page as P_HOLE
-			 * and calls remapf if it is a mapped file.
-			 */
 			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
 			continue;
@@ -545,11 +520,7 @@ xfs_zero_eof(
 
 		/*
 		 * There are blocks we need to zero.
-		 * Drop the inode lock while we're doing the I/O.
-		 * We'll still have the iolock to protect us.
 		 */
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
 		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
 
@@ -557,22 +528,14 @@ xfs_zero_eof(
 			zero_len = offset - zero_off;
 
 		error = xfs_iozero(ip, zero_off, zero_len);
-		if (error) {
-			goto out_lock;
-		}
+		if (error)
+			return error;
 
 		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
 	}
 
 	return 0;
-
-out_lock:
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
 }
 
 /*
@@ -593,35 +556,29 @@ xfs_file_aio_write_checks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error = 0;
 
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
 restart:
 	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
-	if (error) {
-		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	if (error)
 		return error;
-	}
 
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
 	 * write.  If zeroing is needed and we are currently holding the
-	 * iolock shared, we need to update it to exclusive which involves
-	 * dropping all locks and relocking to maintain correct locking order.
-	 * If we do this, restart the function to ensure all checks and values
-	 * are still valid.
+	 * iolock shared, we need to update it to exclusive which implies
+	 * having to redo all checks before.
 	 */
 	if (*pos > i_size_read(inode)) {
 		if (*iolock == XFS_IOLOCK_SHARED) {
-			xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
+			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
-			xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
 		error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
+		if (error)
+			return error;
 	}
-	xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		return error;
 
 	/*
 	 * Updating the timestamps will grab the ilock again from
@@ -638,7 +595,6 @@ restart:
 	 * people from modifying setuid and setgid binaries.
 	 */
 	return file_remove_suid(file);
-
 }
 
 /*
@@ -1007,8 +963,149 @@ xfs_vm_page_mkwrite(
 	return block_page_mkwrite(vma, vmf, xfs_get_blocks);
 }
 
+STATIC loff_t
+xfs_seek_data(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	map[2];
+	int			nmap = 2;
+	loff_t			uninitialized_var(offset);
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	xfs_filblks_t		end;
+	uint			lock;
+	int			error;
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+
+	/*
+	 * Try to read extents from the first block indicated
+	 * by fsbno to the end block of the file.
+	 */
+	end = XFS_B_TO_FSB(mp, isize);
+
+	error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+			       XFS_BMAPI_ENTIRE);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * Treat unwritten extent as data extent since it might
+	 * contains dirty data in page cache.
+	 */
+	if (map[0].br_startblock != HOLESTARTBLOCK) {
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[0].br_startoff));
+	} else {
+		if (nmap == 1) {
+			error = ENXIO;
+			goto out_unlock;
+		}
+
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[1].br_startoff));
+	}
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_seek_hole(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	loff_t			uninitialized_var(offset);
+	loff_t			holeoff;
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	uint			lock;
+	int			error;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -XFS_ERROR(EIO);
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+	error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
+
+	holeoff = XFS_FSB_TO_B(mp, fsbno);
+	if (holeoff <= start)
+		offset = start;
+	else {
+		/*
+		 * xfs_bmap_first_unused() could return a value bigger than
+		 * isize if there are no more holes past the supplied offset.
+		 */
+		offset = min_t(loff_t, holeoff, isize);
+	}
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_file_llseek(
+	struct file	*file,
+	loff_t		offset,
+	int		origin)
+{
+	switch (origin) {
+	case SEEK_END:
+	case SEEK_CUR:
+	case SEEK_SET:
+		return generic_file_llseek(file, offset, origin);
+	case SEEK_DATA:
+		return xfs_seek_data(file, offset, origin);
+	case SEEK_HOLE:
+		return xfs_seek_hole(file, offset, origin);
+	default:
+		return -EINVAL;
+	}
+}
+
 const struct file_operations xfs_file_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= xfs_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= xfs_file_aio_read,

fs/xfs/xfs_fsops.c

@@ -18,8 +18,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
-#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
@@ -39,7 +37,6 @@
 #include "xfs_itable.h"
 #include "xfs_trans_space.h"
 #include "xfs_rtalloc.h"
-#include "xfs_rw.h"
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 
@@ -147,9 +144,9 @@ xfs_growfs_data_private(
 	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
 		return error;
 	dpct = pct - mp->m_sb.sb_imax_pct;
-	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-				BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
+				XFS_FSS_TO_BB(mp, 1), 0);
 	if (!bp)
 		return EIO;
 	xfs_buf_relse(bp);
@@ -193,7 +190,7 @@ xfs_growfs_data_private(
 		 */
 		bp = xfs_buf_get(mp->m_ddev_targp,
 				 XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-				 XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED);
+				 XFS_FSS_TO_BB(mp, 1), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
@@ -230,7 +227,7 @@ xfs_growfs_data_private(
 		 */
 		bp = xfs_buf_get(mp->m_ddev_targp,
 				 XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-				 XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED);
+				 XFS_FSS_TO_BB(mp, 1), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
@@ -259,8 +256,7 @@ xfs_growfs_data_private(
 		 */
 		bp = xfs_buf_get(mp->m_ddev_targp,
 				 XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize),
-				 XBF_LOCK | XBF_MAPPED);
+				 BTOBB(mp->m_sb.sb_blocksize), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
@@ -286,8 +282,7 @@ xfs_growfs_data_private(
 		 */
 		bp = xfs_buf_get(mp->m_ddev_targp,
 				 XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize),
-				 XBF_LOCK | XBF_MAPPED);
+				 BTOBB(mp->m_sb.sb_blocksize), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
@@ -314,8 +309,7 @@ xfs_growfs_data_private(
 		 */
 		bp = xfs_buf_get(mp->m_ddev_targp,
 				 XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize),
-				 XBF_LOCK | XBF_MAPPED);
+				 BTOBB(mp->m_sb.sb_blocksize), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
@@ -405,7 +399,7 @@ xfs_growfs_data_private(
 
 	/* update secondary superblocks. */
 	for (agno = 1; agno < nagcount; agno++) {
-		error = xfs_read_buf(mp, mp->m_ddev_targp,
+		error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
 				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
 				  XFS_FSS_TO_BB(mp, 1), 0, &bp);
 		if (error) {
@@ -693,3 +687,63 @@ xfs_fs_goingdown(
 
 	return 0;
 }
+
+/*
+ * Force a shutdown of the filesystem instantly while keeping the filesystem
+ * consistent. We don't do an unmount here; just shutdown the shop, make sure
+ * that absolutely nothing persistent happens to this filesystem after this
+ * point.
+ */
+void
+xfs_do_force_shutdown(
+	xfs_mount_t	*mp,
+	int		flags,
+	char		*fname,
+	int		lnnum)
+{
+	int		logerror;
+
+	logerror = flags & SHUTDOWN_LOG_IO_ERROR;
+
+	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+		xfs_notice(mp,
+	"%s(0x%x) called from line %d of file %s.  Return address = 0x%p",
+			__func__, flags, lnnum, fname, __return_address);
+	}
+	/*
+	 * No need to duplicate efforts.
+	 */
+	if (XFS_FORCED_SHUTDOWN(mp) && !logerror)
+		return;
+
+	/*
+	 * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't
+	 * queue up anybody new on the log reservations, and wakes up
+	 * everybody who's sleeping on log reservations to tell them
+	 * the bad news.
+	 */
+	if (xfs_log_force_umount(mp, logerror))
+		return;
+
+	if (flags & SHUTDOWN_CORRUPT_INCORE) {
+		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+    "Corruption of in-memory data detected.  Shutting down filesystem");
+		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+			xfs_stack_trace();
+	} else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+		if (logerror) {
+			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
+		"Log I/O Error Detected.  Shutting down filesystem");
+		} else if (flags & SHUTDOWN_DEVICE_REQ) {
+			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+		"All device paths lost.  Shutting down filesystem");
+		} else if (!(flags & SHUTDOWN_REMOTE_REQ)) {
+			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+		"I/O Error Detected. Shutting down filesystem");
+		}
+	}
+	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+		xfs_alert(mp,
+	"Please umount the filesystem and rectify the problem(s)");
+	}
+}

fs/xfs/xfs_ialloc.c

@@ -200,8 +200,7 @@ xfs_ialloc_inode_init(
 		 */
 		d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * blks_per_cluster));
 		fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
-					 mp->m_bsize * blks_per_cluster,
-					 XBF_LOCK);
+					 mp->m_bsize * blks_per_cluster, 0);
 		if (!fbuf)
 			return ENOMEM;
 		/*
@@ -610,6 +609,13 @@ xfs_ialloc_get_rec(
 /*
  * Visible inode allocation functions.
  */
+/*
+ * Find a free (set) bit in the inode bitmask.
+ */
+static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
+{
+	return xfs_lowbit64(*fp);
+}
 
 /*
  * Allocate an inode on disk.

fs/xfs/xfs_ialloc.h

@@ -46,15 +46,6 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
 		(xfs_buf_offset(b, o << (mp)->m_sb.sb_inodelog));
 }
 
-/*
- * Find a free (set) bit in the inode bitmask.
- */
-static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
-{
-	return xfs_lowbit64(*fp);
-}
-
-
 /*
  * Allocate an inode on disk.
  * Mode is used to tell whether the new inode will need space, and whether

fs/xfs/xfs_ialloc_btree.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_iget.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_acl.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
@@ -123,23 +122,7 @@ xfs_inode_free(
 		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
 
 	if (ip->i_itemp) {
-		/*
-		 * Only if we are shutting down the fs will we see an
-		 * inode still in the AIL. If it is there, we should remove
-		 * it to prevent a use-after-free from occurring.
-		 */
-		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
-		struct xfs_ail	*ailp = lip->li_ailp;
-
-		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
-				       XFS_FORCED_SHUTDOWN(ip->i_mount));
-		if (lip->li_flags & XFS_LI_IN_AIL) {
-			spin_lock(&ailp->xa_lock);
-			if (lip->li_flags & XFS_LI_IN_AIL)
-				xfs_trans_ail_delete(ailp, lip);
-			else
-				spin_unlock(&ailp->xa_lock);
-		}
+		ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
 		xfs_inode_item_destroy(ip);
 		ip->i_itemp = NULL;
 	}
@@ -334,9 +317,10 @@ xfs_iget_cache_miss(
 	/*
 	 * Preload the radix tree so we can insert safely under the
 	 * write spinlock. Note that we cannot sleep inside the preload
-	 * region.
+	 * region. Since we can be called from transaction context, don't
+	 * recurse into the file system.
 	 */
-	if (radix_tree_preload(GFP_KERNEL)) {
+	if (radix_tree_preload(GFP_NOFS)) {
 		error = EAGAIN;
 		goto out_destroy;
 	}

fs/xfs/xfs_inode.c

@@ -20,7 +20,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
@@ -61,6 +60,20 @@ STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
 STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
 STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);
 
+/*
+ * helper function to extract extent size hint from inode
+ */
+xfs_extlen_t
+xfs_get_extsz_hint(
+	struct xfs_inode	*ip)
+{
+	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
+		return ip->i_d.di_extsize;
+	if (XFS_IS_REALTIME_INODE(ip))
+		return ip->i_mount->m_sb.sb_rextsize;
+	return 0;
+}
+
 #ifdef DEBUG
 /*
  * Make sure that the extents in the given memory buffer
@@ -137,6 +150,7 @@ xfs_imap_to_bp(
 	int		ni;
 	xfs_buf_t	*bp;
 
+	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
 				   (int)imap->im_len, buf_flags, &bp);
 	if (error) {
@@ -226,7 +240,7 @@ xfs_inotobp(
 	if (error)
 		return error;
 
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XBF_LOCK, imap_flags);
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, 0, imap_flags);
 	if (error)
 		return error;
 
@@ -782,8 +796,7 @@ xfs_iread(
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp,
-			       XBF_LOCK, iget_flags);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, 0, iget_flags);
 	if (error)
 		return error;
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -1342,7 +1355,7 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error)
 			return error;
 
@@ -1423,7 +1436,7 @@ xfs_iunlink_remove(
 		 * of dealing with the buffer when there is no need to
 		 * change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error) {
 			xfs_warn(mp, "%s: xfs_itobp() returned error %d.",
 				__func__, error);
@@ -1484,7 +1497,7 @@ xfs_iunlink_remove(
 		 * Now last_ibp points to the buffer previous to us on
 		 * the unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error) {
 			xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.",
 				__func__, error);
@@ -1566,8 +1579,7 @@ xfs_ifree_cluster(
 		 * to mark all the active inodes on the buffer stale.
 		 */
 		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-					mp->m_bsize * blks_per_cluster,
-					XBF_LOCK);
+					mp->m_bsize * blks_per_cluster, 0);
 
 		if (!bp)
 			return ENOMEM;
@@ -1737,7 +1749,7 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XBF_LOCK);
+	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0);
 	if (error)
 		return error;
 
@@ -2347,11 +2359,11 @@ cluster_corrupt_out:
 	 */
 	rcu_read_unlock();
 	/*
-	 * Clean up the buffer.  If it was B_DELWRI, just release it --
+	 * Clean up the buffer.  If it was delwri, just release it --
 	 * brelse can handle it with no problems.  If not, shut down the
 	 * filesystem before releasing the buffer.
 	 */
-	bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
+	bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
 	if (bufwasdelwri)
 		xfs_buf_relse(bp);
 
@@ -2377,30 +2389,29 @@ cluster_corrupt_out:
 	/*
 	 * Unlocks the flush lock
 	 */
-	xfs_iflush_abort(iq);
+	xfs_iflush_abort(iq, false);
 	kmem_free(ilist);
 	xfs_perag_put(pag);
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
 /*
- * xfs_iflush() will write a modified inode's changes out to the
- * inode's on disk home.  The caller must have the inode lock held
- * in at least shared mode and the inode flush completion must be
- * active as well.  The inode lock will still be held upon return from
- * the call and the caller is free to unlock it.
- * The inode flush will be completed when the inode reaches the disk.
- * The flags indicate how the inode's buffer should be written out.
+ * Flush dirty inode metadata into the backing buffer.
+ *
+ * The caller must have the inode lock and the inode flush lock held.  The
+ * inode lock will still be held upon return to the caller, and the inode
+ * flush lock will be released after the inode has reached the disk.
+ *
+ * The caller must write out the buffer returned in *bpp and release it.
  */
 int
 xfs_iflush(
-	xfs_inode_t		*ip,
-	uint			flags)
+	struct xfs_inode	*ip,
+	struct xfs_buf		**bpp)
 {
-	xfs_inode_log_item_t	*iip;
-	xfs_buf_t		*bp;
-	xfs_dinode_t		*dip;
-	xfs_mount_t		*mp;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_buf		*bp;
+	struct xfs_dinode	*dip;
 	int			error;
 
 	XFS_STATS_INC(xs_iflush_count);
@@ -2410,25 +2421,8 @@ xfs_iflush(
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 
-	iip = ip->i_itemp;
-	mp = ip->i_mount;
+	*bpp = NULL;
 
-	/*
-	 * We can't flush the inode until it is unpinned, so wait for it if we
-	 * are allowed to block.  We know no one new can pin it, because we are
-	 * holding the inode lock shared and you need to hold it exclusively to
-	 * pin the inode.
-	 *
-	 * If we are not allowed to block, force the log out asynchronously so
-	 * that when we come back the inode will be unpinned. If other inodes
-	 * in the same cluster are dirty, they will probably write the inode
-	 * out for us if they occur after the log force completes.
-	 */
-	if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
-		xfs_iunpin(ip);
-		xfs_ifunlock(ip);
-		return EAGAIN;
-	}
 	xfs_iunpin_wait(ip);
 
 	/*
@@ -2447,20 +2441,20 @@ xfs_iflush(
 	/*
 	 * This may have been unpinned because the filesystem is shutting
 	 * down forcibly. If that's the case we must not write this inode
-	 * to disk, because the log record didn't make it to disk!
+	 * to disk, because the log record didn't make it to disk.
+	 *
+	 * We also have to remove the log item from the AIL in this case,
+	 * as we wait for an empty AIL as part of the unmount process.
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp)) {
-		if (iip)
-			iip->ili_fields = 0;
-		xfs_ifunlock(ip);
-		return XFS_ERROR(EIO);
+		error = XFS_ERROR(EIO);
+		goto abort_out;
 	}
 
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				(flags & SYNC_TRYLOCK) ? XBF_TRYLOCK : XBF_LOCK);
+	error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
@@ -2488,23 +2482,20 @@ xfs_iflush(
 	if (error)
 		goto cluster_corrupt_out;
 
-	if (flags & SYNC_WAIT)
-		error = xfs_bwrite(bp);
-	else
-		xfs_buf_delwri_queue(bp);
-
-	xfs_buf_relse(bp);
-	return error;
+	*bpp = bp;
+	return 0;
 
 corrupt_out:
 	xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 cluster_corrupt_out:
+	error = XFS_ERROR(EFSCORRUPTED);
+abort_out:
 	/*
 	 * Unlocks the flush lock
 	 */
-	xfs_iflush_abort(ip);
-	return XFS_ERROR(EFSCORRUPTED);
+	xfs_iflush_abort(ip, false);
+	return error;
 }
 
 
@@ -2706,27 +2697,6 @@ corrupt_out:
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
-void
-xfs_promote_inode(
-	struct xfs_inode	*ip)
-{
-	struct xfs_buf		*bp;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-
-	bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
-			ip->i_imap.im_len, XBF_TRYLOCK);
-	if (!bp)
-		return;
-
-	if (XFS_BUF_ISDELAYWRITE(bp)) {
-		xfs_buf_delwri_promote(bp);
-		wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
-	}
-
-	xfs_buf_relse(bp);
-}
-
 /*
  * Return a pointer to the extent record at file index idx.
  */

fs/xfs/xfs_inode.h

@@ -529,11 +529,12 @@ int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 void		xfs_iunpin_wait(xfs_inode_t *);
-int		xfs_iflush(xfs_inode_t *, uint);
-void		xfs_promote_inode(struct xfs_inode *);
+int		xfs_iflush(struct xfs_inode *, struct xfs_buf **);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
+xfs_extlen_t	xfs_get_extsz_hint(struct xfs_inode *ip);
+
 #define IHOLD(ip) \
 do { \
 	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \

fs/xfs/xfs_inode_item.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -480,25 +478,16 @@ xfs_inode_item_unpin(
 		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
 }
 
-/*
- * This is called to attempt to lock the inode associated with this
- * inode log item, in preparation for the push routine which does the actual
- * iflush.  Don't sleep on the inode lock or the flush lock.
- *
- * If the flush lock is already held, indicating that the inode has
- * been or is in the process of being flushed, then (ideally) we'd like to
- * see if the inode's buffer is still incore, and if so give it a nudge.
- * We delay doing so until the pushbuf routine, though, to avoid holding
- * the AIL lock across a call to the blackhole which is the buffer cache.
- * Also we don't want to sleep in any device strategy routines, which can happen
- * if we do the subsequent bawrite in here.
- */
 STATIC uint
-xfs_inode_item_trylock(
-	struct xfs_log_item	*lip)
+xfs_inode_item_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
+	struct xfs_buf		*bp = NULL;
+	uint			rval = XFS_ITEM_SUCCESS;
+	int			error;
 
 	if (xfs_ipincount(ip) > 0)
 		return XFS_ITEM_PINNED;
@@ -506,30 +495,50 @@ xfs_inode_item_trylock(
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
 		return XFS_ITEM_LOCKED;
 
+	/*
+	 * Re-check the pincount now that we stabilized the value by
+	 * taking the ilock.
+	 */
+	if (xfs_ipincount(ip) > 0) {
+		rval = XFS_ITEM_PINNED;
+		goto out_unlock;
+	}
+
+	/*
+	 * Someone else is already flushing the inode.  Nothing we can do
+	 * here but wait for the flush to finish and remove the item from
+	 * the AIL.
+	 */
 	if (!xfs_iflock_nowait(ip)) {
-		/*
-		 * inode has already been flushed to the backing buffer,
-		 * leave it locked in shared mode, pushbuf routine will
-		 * unlock it.
-		 */
-		return XFS_ITEM_PUSHBUF;
+		rval = XFS_ITEM_FLUSHING;
+		goto out_unlock;
 	}
 
-	/* Stale items should force out the iclog */
+	/*
+	 * Stale inode items should force out the iclog.
+	 */
 	if (ip->i_flags & XFS_ISTALE) {
 		xfs_ifunlock(ip);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		return XFS_ITEM_PINNED;
 	}
 
-#ifdef DEBUG
-	if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		ASSERT(iip->ili_fields != 0);
-		ASSERT(iip->ili_logged == 0);
-		ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+	ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
+	ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
+
+	spin_unlock(&lip->li_ailp->xa_lock);
+
+	error = xfs_iflush(ip, &bp);
+	if (!error) {
+		if (!xfs_buf_delwri_queue(bp, buffer_list))
+			rval = XFS_ITEM_FLUSHING;
+		xfs_buf_relse(bp);
 	}
-#endif
-	return XFS_ITEM_SUCCESS;
+
+	spin_lock(&lip->li_ailp->xa_lock);
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return rval;
 }
 
 /*
@@ -613,86 +622,6 @@ xfs_inode_item_committed(
 	return lsn;
 }
 
-/*
- * This gets called by xfs_trans_push_ail(), when IOP_TRYLOCK
- * failed to get the inode flush lock but did get the inode locked SHARED.
- * Here we're trying to see if the inode buffer is incore, and if so whether it's
- * marked delayed write. If that's the case, we'll promote it and that will
- * allow the caller to write the buffer by triggering the xfsbufd to run.
- */
-STATIC bool
-xfs_inode_item_pushbuf(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
-	struct xfs_inode	*ip = iip->ili_inode;
-	struct xfs_buf		*bp;
-	bool			ret = true;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
-
-	/*
-	 * If a flush is not in progress anymore, chances are that the
-	 * inode was taken off the AIL. So, just get out.
-	 */
-	if (!xfs_isiflocked(ip) ||
-	    !(lip->li_flags & XFS_LI_IN_AIL)) {
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		return true;
-	}
-
-	bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
-			iip->ili_format.ilf_len, XBF_TRYLOCK);
-
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	if (!bp)
-		return true;
-	if (XFS_BUF_ISDELAYWRITE(bp))
-		xfs_buf_delwri_promote(bp);
-	if (xfs_buf_ispinned(bp))
-		ret = false;
-	xfs_buf_relse(bp);
-	return ret;
-}
-
-/*
- * This is called to asynchronously write the inode associated with this
- * inode log item out to disk. The inode will already have been locked by
- * a successful call to xfs_inode_item_trylock().
- */
-STATIC void
-xfs_inode_item_push(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
-	struct xfs_inode	*ip = iip->ili_inode;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
-
-	/*
-	 * Since we were able to lock the inode's flush lock and
-	 * we found it on the AIL, the inode must be dirty.  This
-	 * is because the inode is removed from the AIL while still
-	 * holding the flush lock in xfs_iflush_done().  Thus, if
-	 * we found it in the AIL and were able to obtain the flush
-	 * lock without sleeping, then there must not have been
-	 * anyone in the process of flushing the inode.
-	 */
-	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || iip->ili_fields != 0);
-
-	/*
-	 * Push the inode to it's backing buffer. This will not remove the
-	 * inode from the AIL - a further push will be required to trigger a
-	 * buffer push. However, this allows all the dirty inodes to be pushed
-	 * to the buffer before it is pushed to disk. The buffer IO completion
-	 * will pull the inode from the AIL, mark it clean and unlock the flush
-	 * lock.
-	 */
-	(void) xfs_iflush(ip, SYNC_TRYLOCK);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-}
-
 /*
  * XXX rcc - this one really has to do something.  Probably needs
  * to stamp in a new field in the incore inode.
@@ -713,11 +642,9 @@ static const struct xfs_item_ops xfs_inode_item_ops = {
 	.iop_format	= xfs_inode_item_format,
 	.iop_pin	= xfs_inode_item_pin,
 	.iop_unpin	= xfs_inode_item_unpin,
-	.iop_trylock	= xfs_inode_item_trylock,
 	.iop_unlock	= xfs_inode_item_unlock,
 	.iop_committed	= xfs_inode_item_committed,
 	.iop_push	= xfs_inode_item_push,
-	.iop_pushbuf	= xfs_inode_item_pushbuf,
 	.iop_committing = xfs_inode_item_committing
 };
 
@@ -848,7 +775,8 @@ xfs_iflush_done(
 			ASSERT(i <= need_ail);
 		}
 		/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
-		xfs_trans_ail_delete_bulk(ailp, log_items, i);
+		xfs_trans_ail_delete_bulk(ailp, log_items, i,
+					  SHUTDOWN_CORRUPT_INCORE);
 	}
 
 
@@ -869,16 +797,15 @@ xfs_iflush_done(
 }
 
 /*
- * This is the inode flushing abort routine.  It is called
- * from xfs_iflush when the filesystem is shutting down to clean
- * up the inode state.
- * It is responsible for removing the inode item
- * from the AIL if it has not been re-logged, and unlocking the inode's
- * flush lock.
+ * This is the inode flushing abort routine.  It is called from xfs_iflush when
+ * the filesystem is shutting down to clean up the inode state.  It is
+ * responsible for removing the inode item from the AIL if it has not been
+ * re-logged, and unlocking the inode's flush lock.
  */
 void
 xfs_iflush_abort(
-	xfs_inode_t		*ip)
+	xfs_inode_t		*ip,
+	bool			stale)
 {
 	xfs_inode_log_item_t	*iip = ip->i_itemp;
 
@@ -888,7 +815,10 @@ xfs_iflush_abort(
 			spin_lock(&ailp->xa_lock);
 			if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
 				/* xfs_trans_ail_delete() drops the AIL lock. */
-				xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip);
+				xfs_trans_ail_delete(ailp, &iip->ili_item,
+						stale ?
+						     SHUTDOWN_LOG_IO_ERROR :
+						     SHUTDOWN_CORRUPT_INCORE);
 			} else
 				spin_unlock(&ailp->xa_lock);
 		}
@@ -915,7 +845,7 @@ xfs_istale_done(
 	struct xfs_buf		*bp,
 	struct xfs_log_item	*lip)
 {
-	xfs_iflush_abort(INODE_ITEM(lip)->ili_inode);
+	xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true);
 }
 
 /*

fs/xfs/xfs_inode_item.h

@@ -165,7 +165,7 @@ extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);
 extern void xfs_inode_item_destroy(struct xfs_inode *);
 extern void xfs_iflush_done(struct xfs_buf *, struct xfs_log_item *);
 extern void xfs_istale_done(struct xfs_buf *, struct xfs_log_item *);
-extern void xfs_iflush_abort(struct xfs_inode *);
+extern void xfs_iflush_abort(struct xfs_inode *, bool);
 extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
 					 xfs_inode_log_format_t *);
 

fs/xfs/xfs_inum.h

@@ -26,11 +26,6 @@
  * high agno_log-agblklog-inopblog bits - 0
  */
 
-typedef	__uint32_t	xfs_agino_t;	/* within allocation grp inode number */
-
-#define	NULLFSINO	((xfs_ino_t)-1)
-#define	NULLAGINO	((xfs_agino_t)-1)
-
 struct xfs_mount;
 
 #define	XFS_INO_MASK(k)			(__uint32_t)((1ULL << (k)) - 1)

fs/xfs/xfs_ioctl.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_ioctl32.c

@@ -22,9 +22,7 @@
 #include <asm/uaccess.h>
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_iomap.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -37,7 +35,6 @@
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_itable.h"
-#include "xfs_rw.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_space.h"
@@ -142,11 +139,7 @@ xfs_iomap_write_direct(
 	int		committed;
 	int		error;
 
-	/*
-	 * Make sure that the dquots are there. This doesn't hold
-	 * the ilock across a disk read.
-	 */
-	error = xfs_qm_dqattach_locked(ip, 0);
+	error = xfs_qm_dqattach(ip, 0);
 	if (error)
 		return XFS_ERROR(error);
 
@@ -158,7 +151,7 @@ xfs_iomap_write_direct(
 	if ((offset + count) > XFS_ISIZE(ip)) {
 		error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb);
 		if (error)
-			goto error_out;
+			return XFS_ERROR(error);
 	} else {
 		if (nmaps && (imap->br_startblock == HOLESTARTBLOCK))
 			last_fsb = MIN(last_fsb, (xfs_fileoff_t)
@@ -190,7 +183,6 @@ xfs_iomap_write_direct(
 	/*
 	 * Allocate and setup the transaction
 	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
 	error = xfs_trans_reserve(tp, resblks,
 			XFS_WRITE_LOG_RES(mp), resrtextents,
@@ -199,15 +191,16 @@ xfs_iomap_write_direct(
 	/*
 	 * Check for running out of space, note: need lock to return
 	 */
-	if (error)
+	if (error) {
 		xfs_trans_cancel(tp, 0);
+		return XFS_ERROR(error);
+	}
+
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		goto error_out;
 
 	error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag);
 	if (error)
-		goto error1;
+		goto out_trans_cancel;
 
 	xfs_trans_ijoin(tp, ip, 0);
 
@@ -224,42 +217,39 @@ xfs_iomap_write_direct(
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flag,
 				&firstfsb, 0, imap, &nimaps, &free_list);
 	if (error)
-		goto error0;
+		goto out_bmap_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error)
-		goto error0;
+		goto out_bmap_cancel;
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 	if (error)
-		goto error_out;
+		goto out_unlock;
 
 	/*
 	 * Copy any maps to caller's array and return any error.
 	 */
 	if (nimaps == 0) {
-		error = ENOSPC;
-		goto error_out;
+		error = XFS_ERROR(ENOSPC);
+		goto out_unlock;
 	}
 
-	if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip))) {
+	if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip)))
 		error = xfs_alert_fsblock_zero(ip, imap);
-		goto error_out;
-	}
 
-	return 0;
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
 
-error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
+out_bmap_cancel:
 	xfs_bmap_cancel(&free_list);
-	xfs_trans_unreserve_quota_nblks(tp, ip, qblocks, 0, quota_flag);
-
-error1:	/* Just cancel transaction */
+	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
+out_trans_cancel:
 	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-
-error_out:
-	return XFS_ERROR(error);
+	goto out_unlock;
 }
 
 /*
@@ -422,6 +412,15 @@ retry:
 			return error;
 	}
 
+	/*
+	 * Make sure preallocation does not create extents beyond the range we
+	 * actually support in this filesystem.
+	 */
+	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_maxioffset))
+		last_fsb = XFS_B_TO_FSB(mp, mp->m_maxioffset);
+
+	ASSERT(last_fsb > offset_fsb);
+
 	nimaps = XFS_WRITE_IMAPS;
 	error = xfs_bmapi_delay(ip, offset_fsb, last_fsb - offset_fsb,
 				imap, &nimaps, XFS_BMAPI_ENTIRE);

fs/xfs/xfs_iops.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_acl.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -34,7 +32,6 @@
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_itable.h"
-#include "xfs_rw.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
@@ -700,7 +697,7 @@ xfs_setattr_size(
 	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
 	int			error;
-	uint			lock_flags;
+	uint			lock_flags = 0;
 	uint			commit_flags = 0;
 
 	trace_xfs_setattr(ip);
@@ -720,10 +717,10 @@ xfs_setattr_size(
 			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
 			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
-	lock_flags = XFS_ILOCK_EXCL;
-	if (!(flags & XFS_ATTR_NOLOCK))
+	if (!(flags & XFS_ATTR_NOLOCK)) {
 		lock_flags |= XFS_IOLOCK_EXCL;
-	xfs_ilock(ip, lock_flags);
+		xfs_ilock(ip, lock_flags);
+	}
 
 	oldsize = inode->i_size;
 	newsize = iattr->ia_size;
@@ -746,7 +743,7 @@ xfs_setattr_size(
 	/*
 	 * Make sure that the dquots are attached to the inode.
 	 */
-	error = xfs_qm_dqattach_locked(ip, 0);
+	error = xfs_qm_dqattach(ip, 0);
 	if (error)
 		goto out_unlock;
 
@@ -768,8 +765,6 @@ xfs_setattr_size(
 		if (error)
 			goto out_unlock;
 	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	lock_flags &= ~XFS_ILOCK_EXCL;
 
 	/*
 	 * We are going to log the inode size change in this transaction so

fs/xfs/xfs_itable.c

@@ -18,7 +18,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"

fs/xfs/xfs_log.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -35,7 +33,6 @@
 #include "xfs_trans_priv.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_rw.h"
 #include "xfs_trace.h"
 
 kmem_zone_t	*xfs_log_ticket_zone;
@@ -916,27 +913,42 @@ xfs_log_need_covered(xfs_mount_t *mp)
  * We may be holding the log iclog lock upon entering this routine.
  */
 xfs_lsn_t
-xlog_assign_tail_lsn(
+xlog_assign_tail_lsn_locked(
 	struct xfs_mount	*mp)
 {
-	xfs_lsn_t		tail_lsn;
 	struct log		*log = mp->m_log;
+	struct xfs_log_item	*lip;
+	xfs_lsn_t		tail_lsn;
+
+	assert_spin_locked(&mp->m_ail->xa_lock);
 
 	/*
 	 * To make sure we always have a valid LSN for the log tail we keep
 	 * track of the last LSN which was committed in log->l_last_sync_lsn,
-	 * and use that when the AIL was empty and xfs_ail_min_lsn returns 0.
-	 *
-	 * If the AIL has been emptied we also need to wake any process
-	 * waiting for this condition.
+	 * and use that when the AIL was empty.
 	 */
-	tail_lsn = xfs_ail_min_lsn(mp->m_ail);
-	if (!tail_lsn)
+	lip = xfs_ail_min(mp->m_ail);
+	if (lip)
+		tail_lsn = lip->li_lsn;
+	else
 		tail_lsn = atomic64_read(&log->l_last_sync_lsn);
 	atomic64_set(&log->l_tail_lsn, tail_lsn);
 	return tail_lsn;
 }
 
+xfs_lsn_t
+xlog_assign_tail_lsn(
+	struct xfs_mount	*mp)
+{
+	xfs_lsn_t		tail_lsn;
+
+	spin_lock(&mp->m_ail->xa_lock);
+	tail_lsn = xlog_assign_tail_lsn_locked(mp);
+	spin_unlock(&mp->m_ail->xa_lock);
+
+	return tail_lsn;
+}
+
 /*
  * Return the space in the log between the tail and the head.  The head
  * is passed in the cycle/bytes formal parms.  In the special case where
@@ -1172,7 +1184,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	xlog_get_iclog_buffer_size(mp, log);
 
 	error = ENOMEM;
-	bp = xfs_buf_alloc(mp->m_logdev_targp, 0, log->l_iclog_size, 0);
+	bp = xfs_buf_alloc(mp->m_logdev_targp, 0, BTOBB(log->l_iclog_size), 0);
 	if (!bp)
 		goto out_free_log;
 	bp->b_iodone = xlog_iodone;
@@ -1182,9 +1194,6 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	spin_lock_init(&log->l_icloglock);
 	init_waitqueue_head(&log->l_flush_wait);
 
-	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
-	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
-
 	iclogp = &log->l_iclog;
 	/*
 	 * The amount of memory to allocate for the iclog structure is
@@ -1204,7 +1213,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		prev_iclog = iclog;
 
 		bp = xfs_buf_get_uncached(mp->m_logdev_targp,
-						log->l_iclog_size, 0);
+						BTOBB(log->l_iclog_size), 0);
 		if (!bp)
 			goto out_free_iclog;
 
@@ -1224,7 +1233,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		head->h_fmt = cpu_to_be32(XLOG_FMT);
 		memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t));
 
-		iclog->ic_size = XFS_BUF_SIZE(bp) - log->l_iclog_hsize;
+		iclog->ic_size = BBTOB(bp->b_length) - log->l_iclog_hsize;
 		iclog->ic_state = XLOG_STATE_ACTIVE;
 		iclog->ic_log = log;
 		atomic_set(&iclog->ic_refcnt, 0);
@@ -1475,7 +1484,7 @@ xlog_sync(xlog_t		*log,
 	} else {
 		iclog->ic_bwritecnt = 1;
 	}
-	XFS_BUF_SET_COUNT(bp, count);
+	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_ASYNC(bp);
@@ -1573,7 +1582,7 @@ xlog_dealloc_log(xlog_t *log)
 	 * always need to ensure that the extra buffer does not point to memory
 	 * owned by another log buffer before we free it.
 	 */
-	xfs_buf_set_empty(log->l_xbuf, log->l_iclog_size);
+	xfs_buf_set_empty(log->l_xbuf, BTOBB(log->l_iclog_size));
 	xfs_buf_free(log->l_xbuf);
 
 	iclog = log->l_iclog;
@@ -2932,6 +2941,7 @@ xfs_log_force(
 {
 	int	error;
 
+	trace_xfs_log_force(mp, 0);
 	error = _xfs_log_force(mp, flags, NULL);
 	if (error)
 		xfs_warn(mp, "%s: error %d returned.", __func__, error);
@@ -3080,6 +3090,7 @@ xfs_log_force_lsn(
 {
 	int	error;
 
+	trace_xfs_log_force(mp, lsn);
 	error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
 	if (error)
 		xfs_warn(mp, "%s: error %d returned.", __func__, error);

fs/xfs/xfs_log.h

@@ -152,6 +152,7 @@ int	  xfs_log_mount(struct xfs_mount	*mp,
 			int		 	num_bblocks);
 int	  xfs_log_mount_finish(struct xfs_mount *mp);
 xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp);
+xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp);
 void	  xfs_log_space_wake(struct xfs_mount *mp);
 int	  xfs_log_notify(struct xfs_mount	*mp,
 			 struct xlog_in_core	*iclog,

fs/xfs/xfs_log_cil.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
 #include "xfs_log_priv.h"
@@ -29,60 +27,9 @@
 #include "xfs_mount.h"
 #include "xfs_error.h"
 #include "xfs_alloc.h"
+#include "xfs_extent_busy.h"
 #include "xfs_discard.h"
 
-/*
- * Perform initial CIL structure initialisation.
- */
-int
-xlog_cil_init(
-	struct log	*log)
-{
-	struct xfs_cil	*cil;
-	struct xfs_cil_ctx *ctx;
-
-	cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL);
-	if (!cil)
-		return ENOMEM;
-
-	ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL);
-	if (!ctx) {
-		kmem_free(cil);
-		return ENOMEM;
-	}
-
-	INIT_LIST_HEAD(&cil->xc_cil);
-	INIT_LIST_HEAD(&cil->xc_committing);
-	spin_lock_init(&cil->xc_cil_lock);
-	init_rwsem(&cil->xc_ctx_lock);
-	init_waitqueue_head(&cil->xc_commit_wait);
-
-	INIT_LIST_HEAD(&ctx->committing);
-	INIT_LIST_HEAD(&ctx->busy_extents);
-	ctx->sequence = 1;
-	ctx->cil = cil;
-	cil->xc_ctx = ctx;
-	cil->xc_current_sequence = ctx->sequence;
-
-	cil->xc_log = log;
-	log->l_cilp = cil;
-	return 0;
-}
-
-void
-xlog_cil_destroy(
-	struct log	*log)
-{
-	if (log->l_cilp->xc_ctx) {
-		if (log->l_cilp->xc_ctx->ticket)
-			xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket);
-		kmem_free(log->l_cilp->xc_ctx);
-	}
-
-	ASSERT(list_empty(&log->l_cilp->xc_cil));
-	kmem_free(log->l_cilp);
-}
-
 /*
  * Allocate a new ticket. Failing to get a new ticket makes it really hard to
  * recover, so we don't allow failure here. Also, we allocate in a context that
@@ -390,8 +337,8 @@ xlog_cil_committed(
 	xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, ctx->lv_chain,
 					ctx->start_lsn, abort);
 
-	xfs_alloc_busy_sort(&ctx->busy_extents);
-	xfs_alloc_busy_clear(mp, &ctx->busy_extents,
+	xfs_extent_busy_sort(&ctx->busy_extents);
+	xfs_extent_busy_clear(mp, &ctx->busy_extents,
 			     (mp->m_flags & XFS_MOUNT_DISCARD) && !abort);
 
 	spin_lock(&ctx->cil->xc_cil_lock);
@@ -404,7 +351,7 @@ xlog_cil_committed(
 		ASSERT(mp->m_flags & XFS_MOUNT_DISCARD);
 
 		xfs_discard_extents(mp, &ctx->busy_extents);
-		xfs_alloc_busy_clear(mp, &ctx->busy_extents, false);
+		xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
 	}
 
 	kmem_free(ctx);
@@ -426,8 +373,7 @@ xlog_cil_committed(
  */
 STATIC int
 xlog_cil_push(
-	struct log		*log,
-	xfs_lsn_t		push_seq)
+	struct log		*log)
 {
 	struct xfs_cil		*cil = log->l_cilp;
 	struct xfs_log_vec	*lv;
@@ -443,39 +389,36 @@ xlog_cil_push(
 	struct xfs_log_iovec	lhdr;
 	struct xfs_log_vec	lvhdr = { NULL };
 	xfs_lsn_t		commit_lsn;
+	xfs_lsn_t		push_seq;
 
 	if (!cil)
 		return 0;
 
-	ASSERT(!push_seq || push_seq <= cil->xc_ctx->sequence);
-
 	new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
 	new_ctx->ticket = xlog_cil_ticket_alloc(log);
 
-	/*
-	 * Lock out transaction commit, but don't block for background pushes
-	 * unless we are well over the CIL space limit. See the definition of
-	 * XLOG_CIL_HARD_SPACE_LIMIT() for the full explanation of the logic
-	 * used here.
-	 */
-	if (!down_write_trylock(&cil->xc_ctx_lock)) {
-		if (!push_seq &&
-		    cil->xc_ctx->space_used < XLOG_CIL_HARD_SPACE_LIMIT(log))
-			goto out_free_ticket;
-		down_write(&cil->xc_ctx_lock);
-	}
+	down_write(&cil->xc_ctx_lock);
 	ctx = cil->xc_ctx;
 
-	/* check if we've anything to push */
-	if (list_empty(&cil->xc_cil))
-		goto out_skip;
+	spin_lock(&cil->xc_cil_lock);
+	push_seq = cil->xc_push_seq;
+	ASSERT(push_seq <= ctx->sequence);
 
-	/* check for spurious background flush */
-	if (!push_seq && cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log))
+	/*
+	 * Check if we've anything to push. If there is nothing, then we don't
+	 * move on to a new sequence number and so we have to be able to push
+	 * this sequence again later.
+	 */
+	if (list_empty(&cil->xc_cil)) {
+		cil->xc_push_seq = 0;
+		spin_unlock(&cil->xc_cil_lock);
 		goto out_skip;
+	}
+	spin_unlock(&cil->xc_cil_lock);
+
 
 	/* check for a previously pushed seqeunce */
-	if (push_seq && push_seq < cil->xc_ctx->sequence)
+	if (push_seq < cil->xc_ctx->sequence)
 		goto out_skip;
 
 	/*
@@ -629,7 +572,6 @@ restart:
 
 out_skip:
 	up_write(&cil->xc_ctx_lock);
-out_free_ticket:
 	xfs_log_ticket_put(new_ctx->ticket);
 	kmem_free(new_ctx);
 	return 0;
@@ -641,6 +583,82 @@ out_abort:
 	return XFS_ERROR(EIO);
 }
 
+static void
+xlog_cil_push_work(
+	struct work_struct	*work)
+{
+	struct xfs_cil		*cil = container_of(work, struct xfs_cil,
+							xc_push_work);
+	xlog_cil_push(cil->xc_log);
+}
+
+/*
+ * We need to push CIL every so often so we don't cache more than we can fit in
+ * the log. The limit really is that a checkpoint can't be more than half the
+ * log (the current checkpoint is not allowed to overwrite the previous
+ * checkpoint), but commit latency and memory usage limit this to a smaller
+ * size.
+ */
+static void
+xlog_cil_push_background(
+	struct log	*log)
+{
+	struct xfs_cil	*cil = log->l_cilp;
+
+	/*
+	 * The cil won't be empty because we are called while holding the
+	 * context lock so whatever we added to the CIL will still be there
+	 */
+	ASSERT(!list_empty(&cil->xc_cil));
+
+	/*
+	 * don't do a background push if we haven't used up all the
+	 * space available yet.
+	 */
+	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log))
+		return;
+
+	spin_lock(&cil->xc_cil_lock);
+	if (cil->xc_push_seq < cil->xc_current_sequence) {
+		cil->xc_push_seq = cil->xc_current_sequence;
+		queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work);
+	}
+	spin_unlock(&cil->xc_cil_lock);
+
+}
+
+static void
+xlog_cil_push_foreground(
+	struct log	*log,
+	xfs_lsn_t	push_seq)
+{
+	struct xfs_cil	*cil = log->l_cilp;
+
+	if (!cil)
+		return;
+
+	ASSERT(push_seq && push_seq <= cil->xc_current_sequence);
+
+	/* start on any pending background push to minimise wait time on it */
+	flush_work(&cil->xc_push_work);
+
+	/*
+	 * If the CIL is empty or we've already pushed the sequence then
+	 * there's no work we need to do.
+	 */
+	spin_lock(&cil->xc_cil_lock);
+	if (list_empty(&cil->xc_cil) || push_seq <= cil->xc_push_seq) {
+		spin_unlock(&cil->xc_cil_lock);
+		return;
+	}
+
+	cil->xc_push_seq = push_seq;
+	spin_unlock(&cil->xc_cil_lock);
+
+	/* do the push now */
+	xlog_cil_push(log);
+}
+
 /*
  * Commit a transaction with the given vector to the Committed Item List.
  *
@@ -667,7 +685,6 @@ xfs_log_commit_cil(
 {
 	struct log		*log = mp->m_log;
 	int			log_flags = 0;
-	int			push = 0;
 	struct xfs_log_vec	*log_vector;
 
 	if (flags & XFS_TRANS_RELEASE_LOG_RES)
@@ -719,21 +736,9 @@ xfs_log_commit_cil(
 	 */
 	xfs_trans_free_items(tp, *commit_lsn, 0);
 
-	/* check for background commit before unlock */
-	if (log->l_cilp->xc_ctx->space_used > XLOG_CIL_SPACE_LIMIT(log))
-		push = 1;
+	xlog_cil_push_background(log);
 
 	up_read(&log->l_cilp->xc_ctx_lock);
-
-	/*
-	 * We need to push CIL every so often so we don't cache more than we
-	 * can fit in the log. The limit really is that a checkpoint can't be
-	 * more than half the log (the current checkpoint is not allowed to
-	 * overwrite the previous checkpoint), but commit latency and memory
-	 * usage limit this to a smaller size in most cases.
-	 */
-	if (push)
-		xlog_cil_push(log, 0);
 	return 0;
 }
 
@@ -746,9 +751,6 @@ xfs_log_commit_cil(
  *
  * We return the current commit lsn to allow the callers to determine if a
  * iclog flush is necessary following this call.
- *
- * XXX: Initially, just push the CIL unconditionally and return whatever
- * commit lsn is there. It'll be empty, so this is broken for now.
  */
 xfs_lsn_t
 xlog_cil_force_lsn(
@@ -766,8 +768,7 @@ xlog_cil_force_lsn(
 	 * xlog_cil_push() handles racing pushes for the same sequence,
 	 * so no need to deal with it here.
 	 */
-	if (sequence == cil->xc_current_sequence)
-		xlog_cil_push(log, sequence);
+	xlog_cil_push_foreground(log, sequence);
 
 	/*
 	 * See if we can find a previous sequence still committing.
@@ -826,3 +827,57 @@ xfs_log_item_in_current_chkpt(
 		return false;
 	return true;
 }
+
+/*
+ * Perform initial CIL structure initialisation.
+ */
+int
+xlog_cil_init(
+	struct log	*log)
+{
+	struct xfs_cil	*cil;
+	struct xfs_cil_ctx *ctx;
+
+	cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL);
+	if (!cil)
+		return ENOMEM;
+
+	ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL);
+	if (!ctx) {
+		kmem_free(cil);
+		return ENOMEM;
+	}
+
+	INIT_WORK(&cil->xc_push_work, xlog_cil_push_work);
+	INIT_LIST_HEAD(&cil->xc_cil);
+	INIT_LIST_HEAD(&cil->xc_committing);
+	spin_lock_init(&cil->xc_cil_lock);
+	init_rwsem(&cil->xc_ctx_lock);
+	init_waitqueue_head(&cil->xc_commit_wait);
+
+	INIT_LIST_HEAD(&ctx->committing);
+	INIT_LIST_HEAD(&ctx->busy_extents);
+	ctx->sequence = 1;
+	ctx->cil = cil;
+	cil->xc_ctx = ctx;
+	cil->xc_current_sequence = ctx->sequence;
+
+	cil->xc_log = log;
+	log->l_cilp = cil;
+	return 0;
+}
+
+void
+xlog_cil_destroy(
+	struct log	*log)
+{
+	if (log->l_cilp->xc_ctx) {
+		if (log->l_cilp->xc_ctx->ticket)
+			xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket);
+		kmem_free(log->l_cilp->xc_ctx);
+	}
+
+	ASSERT(list_empty(&log->l_cilp->xc_cil));
+	kmem_free(log->l_cilp);
+}
+

fs/xfs/xfs_log_priv.h

@@ -417,6 +417,8 @@ struct xfs_cil {
 	struct list_head	xc_committing;
 	wait_queue_head_t	xc_commit_wait;
 	xfs_lsn_t		xc_current_sequence;
+	struct work_struct	xc_push_work;
+	xfs_lsn_t		xc_push_seq;
 };
 
 /*

fs/xfs/xfs_log_recover.c

@@ -40,7 +40,6 @@
 #include "xfs_extfree_item.h"
 #include "xfs_trans_priv.h"
 #include "xfs_quota.h"
-#include "xfs_rw.h"
 #include "xfs_utils.h"
 #include "xfs_trace.h"
 
@@ -120,7 +119,7 @@ xlog_get_bp(
 		nbblks += log->l_sectBBsize;
 	nbblks = round_up(nbblks, log->l_sectBBsize);
 
-	bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, BBTOB(nbblks), 0);
+	bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, nbblks, 0);
 	if (bp)
 		xfs_buf_unlock(bp);
 	return bp;
@@ -146,7 +145,7 @@ xlog_align(
 {
 	xfs_daddr_t	offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1);
 
-	ASSERT(BBTOB(offset + nbblks) <= XFS_BUF_SIZE(bp));
+	ASSERT(offset + nbblks <= bp->b_length);
 	return bp->b_addr + BBTOB(offset);
 }
 
@@ -174,11 +173,12 @@ xlog_bread_noalign(
 	nbblks = round_up(nbblks, log->l_sectBBsize);
 
 	ASSERT(nbblks > 0);
-	ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp));
+	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
 	XFS_BUF_READ(bp);
-	XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
+	bp->b_io_length = nbblks;
+	bp->b_error = 0;
 
 	xfsbdstrat(log->l_mp, bp);
 	error = xfs_buf_iowait(bp);
@@ -218,7 +218,7 @@ xlog_bread_offset(
 	xfs_caddr_t	offset)
 {
 	xfs_caddr_t	orig_offset = bp->b_addr;
-	int		orig_len = bp->b_buffer_length;
+	int		orig_len = BBTOB(bp->b_length);
 	int		error, error2;
 
 	error = xfs_buf_associate_memory(bp, offset, BBTOB(nbblks));
@@ -259,13 +259,14 @@ xlog_bwrite(
 	nbblks = round_up(nbblks, log->l_sectBBsize);
 
 	ASSERT(nbblks > 0);
-	ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp));
+	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
 	XFS_BUF_ZEROFLAGS(bp);
 	xfs_buf_hold(bp);
 	xfs_buf_lock(bp);
-	XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
+	bp->b_io_length = nbblks;
+	bp->b_error = 0;
 
 	error = xfs_bwrite(bp);
 	if (error)
@@ -440,6 +441,8 @@ xlog_find_verify_cycle(
 	 * a log sector, or we're out of luck.
 	 */
 	bufblks = 1 << ffs(nbblks);
+	while (bufblks > log->l_logBBsize)
+		bufblks >>= 1;
 	while (!(bp = xlog_get_bp(log, bufblks))) {
 		bufblks >>= 1;
 		if (bufblks < log->l_sectBBsize)
@@ -1225,6 +1228,8 @@ xlog_write_log_records(
 	 * log sector, or we're out of luck.
 	 */
 	bufblks = 1 << ffs(blocks);
+	while (bufblks > log->l_logBBsize)
+		bufblks >>= 1;
 	while (!(bp = xlog_get_bp(log, bufblks))) {
 		bufblks >>= 1;
 		if (bufblks < sectbb)
@@ -1772,7 +1777,7 @@ xlog_recover_do_inode_buffer(
 
 	trace_xfs_log_recover_buf_inode_buf(mp->m_log, buf_f);
 
-	inodes_per_buf = XFS_BUF_COUNT(bp) >> mp->m_sb.sb_inodelog;
+	inodes_per_buf = BBTOB(bp->b_io_length) >> mp->m_sb.sb_inodelog;
 	for (i = 0; i < inodes_per_buf; i++) {
 		next_unlinked_offset = (i * mp->m_sb.sb_inodesize) +
 			offsetof(xfs_dinode_t, di_next_unlinked);
@@ -1814,7 +1819,8 @@ xlog_recover_do_inode_buffer(
 
 		ASSERT(item->ri_buf[item_index].i_addr != NULL);
 		ASSERT((item->ri_buf[item_index].i_len % XFS_BLF_CHUNK) == 0);
-		ASSERT((reg_buf_offset + reg_buf_bytes) <= XFS_BUF_COUNT(bp));
+		ASSERT((reg_buf_offset + reg_buf_bytes) <=
+							BBTOB(bp->b_io_length));
 
 		/*
 		 * The current logged region contains a copy of the
@@ -1873,8 +1879,8 @@ xlog_recover_do_reg_buffer(
 		ASSERT(nbits > 0);
 		ASSERT(item->ri_buf[i].i_addr != NULL);
 		ASSERT(item->ri_buf[i].i_len % XFS_BLF_CHUNK == 0);
-		ASSERT(XFS_BUF_COUNT(bp) >=
-		       ((uint)bit << XFS_BLF_SHIFT)+(nbits<<XFS_BLF_SHIFT));
+		ASSERT(BBTOB(bp->b_io_length) >=
+		       ((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT));
 
 		/*
 		 * Do a sanity check if this is a dquot buffer. Just checking
@@ -2103,6 +2109,7 @@ xlog_recover_do_dquot_buffer(
 STATIC int
 xlog_recover_buffer_pass2(
 	xlog_t			*log,
+	struct list_head	*buffer_list,
 	xlog_recover_item_t	*item)
 {
 	xfs_buf_log_format_t	*buf_f = item->ri_buf[0].i_addr;
@@ -2123,9 +2130,9 @@ xlog_recover_buffer_pass2(
 
 	trace_xfs_log_recover_buf_recover(log, buf_f);
 
-	buf_flags = XBF_LOCK;
-	if (!(buf_f->blf_flags & XFS_BLF_INODE_BUF))
-		buf_flags |= XBF_MAPPED;
+	buf_flags = 0;
+	if (buf_f->blf_flags & XFS_BLF_INODE_BUF)
+		buf_flags |= XBF_UNMAPPED;
 
 	bp = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len,
 			  buf_flags);
@@ -2166,14 +2173,14 @@ xlog_recover_buffer_pass2(
 	 */
 	if (XFS_DINODE_MAGIC ==
 	    be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) &&
-	    (XFS_BUF_COUNT(bp) != MAX(log->l_mp->m_sb.sb_blocksize,
+	    (BBTOB(bp->b_io_length) != MAX(log->l_mp->m_sb.sb_blocksize,
 			(__uint32_t)XFS_INODE_CLUSTER_SIZE(log->l_mp)))) {
 		xfs_buf_stale(bp);
 		error = xfs_bwrite(bp);
 	} else {
 		ASSERT(bp->b_target->bt_mount == mp);
 		bp->b_iodone = xlog_recover_iodone;
-		xfs_buf_delwri_queue(bp);
+		xfs_buf_delwri_queue(bp, buffer_list);
 	}
 
 	xfs_buf_relse(bp);
@@ -2183,6 +2190,7 @@ xlog_recover_buffer_pass2(
 STATIC int
 xlog_recover_inode_pass2(
 	xlog_t			*log,
+	struct list_head	*buffer_list,
 	xlog_recover_item_t	*item)
 {
 	xfs_inode_log_format_t	*in_f;
@@ -2220,8 +2228,7 @@ xlog_recover_inode_pass2(
 	}
 	trace_xfs_log_recover_inode_recover(log, in_f);
 
-	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len,
-			  XBF_LOCK);
+	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0);
 	if (!bp) {
 		error = ENOMEM;
 		goto error;
@@ -2436,7 +2443,7 @@ xlog_recover_inode_pass2(
 write_inode_buffer:
 	ASSERT(bp->b_target->bt_mount == mp);
 	bp->b_iodone = xlog_recover_iodone;
-	xfs_buf_delwri_queue(bp);
+	xfs_buf_delwri_queue(bp, buffer_list);
 	xfs_buf_relse(bp);
 error:
 	if (need_free)
@@ -2477,6 +2484,7 @@ xlog_recover_quotaoff_pass1(
 STATIC int
 xlog_recover_dquot_pass2(
 	xlog_t			*log,
+	struct list_head	*buffer_list,
 	xlog_recover_item_t	*item)
 {
 	xfs_mount_t		*mp = log->l_mp;
@@ -2530,14 +2538,11 @@ xlog_recover_dquot_pass2(
 		return XFS_ERROR(EIO);
 	ASSERT(dq_f->qlf_len == 1);
 
-	error = xfs_read_buf(mp, mp->m_ddev_targp,
-			     dq_f->qlf_blkno,
-			     XFS_FSB_TO_BB(mp, dq_f->qlf_len),
-			     0, &bp);
-	if (error) {
-		xfs_buf_ioerror_alert(bp, "xlog_recover_do..(read#3)");
+	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dq_f->qlf_blkno,
+				   XFS_FSB_TO_BB(mp, dq_f->qlf_len), 0, &bp);
+	if (error)
 		return error;
-	}
+
 	ASSERT(bp);
 	ddq = (xfs_disk_dquot_t *)xfs_buf_offset(bp, dq_f->qlf_boffset);
 
@@ -2558,7 +2563,7 @@ xlog_recover_dquot_pass2(
 	ASSERT(dq_f->qlf_size == 2);
 	ASSERT(bp->b_target->bt_mount == mp);
 	bp->b_iodone = xlog_recover_iodone;
-	xfs_buf_delwri_queue(bp);
+	xfs_buf_delwri_queue(bp, buffer_list);
 	xfs_buf_relse(bp);
 
 	return (0);
@@ -2642,7 +2647,8 @@ xlog_recover_efd_pass2(
 				 * xfs_trans_ail_delete() drops the
 				 * AIL lock.
 				 */
-				xfs_trans_ail_delete(ailp, lip);
+				xfs_trans_ail_delete(ailp, lip,
+						     SHUTDOWN_CORRUPT_INCORE);
 				xfs_efi_item_free(efip);
 				spin_lock(&ailp->xa_lock);
 				break;
@@ -2712,21 +2718,22 @@ STATIC int
 xlog_recover_commit_pass2(
 	struct log		*log,
 	struct xlog_recover	*trans,
+	struct list_head	*buffer_list,
 	xlog_recover_item_t	*item)
 {
 	trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS2);
 
 	switch (ITEM_TYPE(item)) {
 	case XFS_LI_BUF:
-		return xlog_recover_buffer_pass2(log, item);
+		return xlog_recover_buffer_pass2(log, buffer_list, item);
 	case XFS_LI_INODE:
-		return xlog_recover_inode_pass2(log, item);
+		return xlog_recover_inode_pass2(log, buffer_list, item);
 	case XFS_LI_EFI:
 		return xlog_recover_efi_pass2(log, item, trans->r_lsn);
 	case XFS_LI_EFD:
 		return xlog_recover_efd_pass2(log, item);
 	case XFS_LI_DQUOT:
-		return xlog_recover_dquot_pass2(log, item);
+		return xlog_recover_dquot_pass2(log, buffer_list, item);
 	case XFS_LI_QUOTAOFF:
 		/* nothing to do in pass2 */
 		return 0;
@@ -2750,8 +2757,9 @@ xlog_recover_commit_trans(
 	struct xlog_recover	*trans,
 	int			pass)
 {
-	int			error = 0;
+	int			error = 0, error2;
 	xlog_recover_item_t	*item;
+	LIST_HEAD		(buffer_list);
 
 	hlist_del(&trans->r_list);
 
@@ -2760,16 +2768,27 @@ xlog_recover_commit_trans(
 		return error;
 
 	list_for_each_entry(item, &trans->r_itemq, ri_list) {
-		if (pass == XLOG_RECOVER_PASS1)
+		switch (pass) {
+		case XLOG_RECOVER_PASS1:
 			error = xlog_recover_commit_pass1(log, trans, item);
-		else
-			error = xlog_recover_commit_pass2(log, trans, item);
+			break;
+		case XLOG_RECOVER_PASS2:
+			error = xlog_recover_commit_pass2(log, trans,
+							  &buffer_list, item);
+			break;
+		default:
+			ASSERT(0);
+		}
+
 		if (error)
-			return error;
+			goto out;
 	}
 
 	xlog_recover_free_trans(trans);
-	return 0;
+
+out:
+	error2 = xfs_buf_delwri_submit(&buffer_list);
+	return error ? error : error2;
 }
 
 STATIC int
@@ -3079,7 +3098,7 @@ xlog_recover_process_one_iunlink(
 	/*
 	 * Get the on disk inode to find the next inode in the bucket.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XBF_LOCK);
+	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, 0);
 	if (error)
 		goto fail_iput;
 
@@ -3639,11 +3658,8 @@ xlog_do_recover(
 	 * First replay the images in the log.
 	 */
 	error = xlog_do_log_recovery(log, head_blk, tail_blk);
-	if (error) {
+	if (error)
 		return error;
-	}
-
-	xfs_flush_buftarg(log->l_mp->m_ddev_targp, 1);
 
 	/*
 	 * If IO errors happened during recovery, bail out.
@@ -3670,7 +3686,6 @@ xlog_do_recover(
 	bp = xfs_getsb(log->l_mp, 0);
 	XFS_BUF_UNDONE(bp);
 	ASSERT(!(XFS_BUF_ISWRITE(bp)));
-	ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
 	xfsbdstrat(log->l_mp, bp);

fs/xfs/xfs_message.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_mount.c

@@ -22,6 +22,7 @@
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
+#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_dir2.h"
@@ -37,7 +38,6 @@
 #include "xfs_rtalloc.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
-#include "xfs_rw.h"
 #include "xfs_quota.h"
 #include "xfs_fsops.h"
 #include "xfs_utils.h"
@@ -683,8 +683,8 @@ xfs_readsb(xfs_mount_t *mp, int flags)
 	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
 
 reread:
-	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
-					XFS_SB_DADDR, sector_size, 0);
+	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+					BTOBB(sector_size), 0);
 	if (!bp) {
 		if (loud)
 			xfs_warn(mp, "SB buffer read failed");
@@ -1032,9 +1032,9 @@ xfs_check_sizes(xfs_mount_t *mp)
 		xfs_warn(mp, "filesystem size mismatch detected");
 		return XFS_ERROR(EFBIG);
 	}
-	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
+					XFS_FSS_TO_BB(mp, 1), 0);
 	if (!bp) {
 		xfs_warn(mp, "last sector read failed");
 		return EIO;
@@ -1047,9 +1047,9 @@ xfs_check_sizes(xfs_mount_t *mp)
 			xfs_warn(mp, "log size mismatch detected");
 			return XFS_ERROR(EFBIG);
 		}
-		bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp,
+		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_B(mp, 1), 0);
+					XFS_FSB_TO_BB(mp, 1), 0);
 		if (!bp) {
 			xfs_warn(mp, "log device read failed");
 			return EIO;
@@ -1288,7 +1288,7 @@ xfs_mountfs(
 			      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
 	if (error) {
 		xfs_warn(mp, "log mount failed");
-		goto out_free_perag;
+		goto out_fail_wait;
 	}
 
 	/*
@@ -1315,7 +1315,7 @@ xfs_mountfs(
 	     !mp->m_sb.sb_inprogress) {
 		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
 		if (error)
-			goto out_free_perag;
+			goto out_fail_wait;
 	}
 
 	/*
@@ -1439,6 +1439,10 @@ xfs_mountfs(
 	IRELE(rip);
  out_log_dealloc:
 	xfs_log_unmount(mp);
+ out_fail_wait:
+	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
+		xfs_wait_buftarg(mp->m_logdev_targp);
+	xfs_wait_buftarg(mp->m_ddev_targp);
  out_free_perag:
 	xfs_free_perag(mp);
  out_remove_uuid:
@@ -1475,15 +1479,15 @@ xfs_unmountfs(
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
 	/*
-	 * Do a delwri reclaim pass first so that as many dirty inodes are
-	 * queued up for IO as possible. Then flush the buffers before making
-	 * a synchronous path to catch all the remaining inodes are reclaimed.
-	 * This makes the reclaim process as quick as possible by avoiding
-	 * synchronous writeout and blocking on inodes already in the delwri
-	 * state as much as possible.
+	 * Flush all pending changes from the AIL.
+	 */
+	xfs_ail_push_all_sync(mp->m_ail);
+
+	/*
+	 * And reclaim all inodes.  At this point there should be no dirty
+	 * inode, and none should be pinned or locked, but use synchronous
+	 * reclaim just to be sure.
 	 */
-	xfs_reclaim_inodes(mp, 0);
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
 
 	xfs_qm_unmount(mp);
@@ -1519,15 +1523,12 @@ xfs_unmountfs(
 	if (error)
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
-	xfs_unmountfs_writesb(mp);
 
 	/*
-	 * Make sure all buffers have been flushed and completed before
-	 * unmounting the log.
+	 * At this point we might have modified the superblock again and thus
+	 * added an item to the AIL, thus flush it again.
 	 */
-	error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
-	if (error)
-		xfs_warn(mp, "%d busy buffers during unmount.", error);
+	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_wait_buftarg(mp->m_ddev_targp);
 
 	xfs_log_unmount_write(mp);
@@ -1588,36 +1589,6 @@ xfs_log_sbcount(xfs_mount_t *mp)
 	return error;
 }
 
-int
-xfs_unmountfs_writesb(xfs_mount_t *mp)
-{
-	xfs_buf_t	*sbp;
-	int		error = 0;
-
-	/*
-	 * skip superblock write if fs is read-only, or
-	 * if we are doing a forced umount.
-	 */
-	if (!((mp->m_flags & XFS_MOUNT_RDONLY) ||
-		XFS_FORCED_SHUTDOWN(mp))) {
-
-		sbp = xfs_getsb(mp, 0);
-
-		XFS_BUF_UNDONE(sbp);
-		XFS_BUF_UNREAD(sbp);
-		xfs_buf_delwri_dequeue(sbp);
-		XFS_BUF_WRITE(sbp);
-		XFS_BUF_UNASYNC(sbp);
-		ASSERT(sbp->b_target == mp->m_ddev_targp);
-		xfsbdstrat(mp, sbp);
-		error = xfs_buf_iowait(sbp);
-		if (error)
-			xfs_buf_ioerror_alert(sbp, __func__);
-		xfs_buf_relse(sbp);
-	}
-	return error;
-}
-
 /*
  * xfs_mod_sb() can be used to copy arbitrary changes to the
  * in-core superblock into the superblock buffer to be logged.

fs/xfs/xfs_mount.h

@@ -214,6 +214,7 @@ typedef struct xfs_mount {
 
 	struct workqueue_struct	*m_data_workqueue;
 	struct workqueue_struct	*m_unwritten_workqueue;
+	struct workqueue_struct	*m_cil_workqueue;
 } xfs_mount_t;
 
 /*
@@ -378,7 +379,6 @@ extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 
 extern void	xfs_unmountfs(xfs_mount_t *);
-extern int	xfs_unmountfs_writesb(xfs_mount_t *);
 extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 			uint, int);

fs/xfs/xfs_qm.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -65,7 +64,8 @@ STATIC int
 xfs_qm_dquot_walk(
 	struct xfs_mount	*mp,
 	int			type,
-	int			(*execute)(struct xfs_dquot *dqp))
+	int			(*execute)(struct xfs_dquot *dqp, void *data),
+	void			*data)
 {
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	struct radix_tree_root	*tree = XFS_DQUOT_TREE(qi, type);
@@ -97,7 +97,7 @@ restart:
 
 			next_index = be32_to_cpu(dqp->q_core.d_id) + 1;
 
-			error = execute(batch[i]);
+			error = execute(batch[i], data);
 			if (error == EAGAIN) {
 				skipped++;
 				continue;
@@ -129,7 +129,8 @@ restart:
  */
 STATIC int
 xfs_qm_dqpurge(
-	struct xfs_dquot	*dqp)
+	struct xfs_dquot	*dqp,
+	void			*data)
 {
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
@@ -153,21 +154,7 @@ xfs_qm_dqpurge(
 
 	dqp->dq_flags |= XFS_DQ_FREEING;
 
-	/*
-	 * If we're turning off quotas, we have to make sure that, for
-	 * example, we don't delete quota disk blocks while dquots are
-	 * in the process of getting written to those disk blocks.
-	 * This dquot might well be on AIL, and we can't leave it there
-	 * if we're turning off quotas. Basically, we need this flush
-	 * lock, and are willing to block on it.
-	 */
-	if (!xfs_dqflock_nowait(dqp)) {
-		/*
-		 * Block on the flush lock after nudging dquot buffer,
-		 * if it is incore.
-		 */
-		xfs_dqflock_pushbuf_wait(dqp);
-	}
+	xfs_dqflock(dqp);
 
 	/*
 	 * If we are turning this type of quotas off, we don't care
@@ -175,16 +162,21 @@ xfs_qm_dqpurge(
 	 * we're unmounting, we do care, so we flush it and wait.
 	 */
 	if (XFS_DQ_IS_DIRTY(dqp)) {
-		int	error;
+		struct xfs_buf	*bp = NULL;
+		int		error;
 
 		/*
 		 * We don't care about getting disk errors here. We need
 		 * to purge this dquot anyway, so we go ahead regardless.
 		 */
-		error = xfs_qm_dqflush(dqp, SYNC_WAIT);
-		if (error)
+		error = xfs_qm_dqflush(dqp, &bp);
+		if (error) {
 			xfs_warn(mp, "%s: dquot %p flush failed",
 				__func__, dqp);
+		} else {
+			error = xfs_bwrite(bp);
+			xfs_buf_relse(bp);
+		}
 		xfs_dqflock(dqp);
 	}
 
@@ -226,11 +218,11 @@ xfs_qm_dqpurge_all(
 	uint			flags)
 {
 	if (flags & XFS_QMOPT_UQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge);
+		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_GQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge);
+		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_PQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge);
+		xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge, NULL);
 }
 
 /*
@@ -483,6 +475,23 @@ done:
 	xfs_dqunlock(udq);
 }
 
+static bool
+xfs_qm_need_dqattach(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return false;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return false;
+	if (!XFS_NOT_DQATTACHED(mp, ip))
+		return false;
+	if (ip->i_ino == mp->m_sb.sb_uquotino ||
+	    ip->i_ino == mp->m_sb.sb_gquotino)
+		return false;
+	return true;
+}
 
 /*
  * Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
@@ -500,11 +509,7 @@ xfs_qm_dqattach_locked(
 	uint		nquotas = 0;
 	int		error = 0;
 
-	if (!XFS_IS_QUOTA_RUNNING(mp) ||
-	    !XFS_IS_QUOTA_ON(mp) ||
-	    !XFS_NOT_DQATTACHED(mp, ip) ||
-	    ip->i_ino == mp->m_sb.sb_uquotino ||
-	    ip->i_ino == mp->m_sb.sb_gquotino)
+	if (!xfs_qm_need_dqattach(ip))
 		return 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -575,6 +580,9 @@ xfs_qm_dqattach(
 {
 	int			error;
 
+	if (!xfs_qm_need_dqattach(ip))
+		return 0;
+
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_qm_dqattach_locked(ip, flags);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -855,15 +863,16 @@ xfs_qm_reset_dqcounts(
 
 STATIC int
 xfs_qm_dqiter_bufs(
-	xfs_mount_t	*mp,
-	xfs_dqid_t	firstid,
-	xfs_fsblock_t	bno,
-	xfs_filblks_t	blkcnt,
-	uint		flags)
+	struct xfs_mount	*mp,
+	xfs_dqid_t		firstid,
+	xfs_fsblock_t		bno,
+	xfs_filblks_t		blkcnt,
+	uint			flags,
+	struct list_head	*buffer_list)
 {
-	xfs_buf_t	*bp;
-	int		error;
-	int		type;
+	struct xfs_buf		*bp;
+	int			error;
+	int			type;
 
 	ASSERT(blkcnt > 0);
 	type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER :
@@ -887,7 +896,7 @@ xfs_qm_dqiter_bufs(
 			break;
 
 		xfs_qm_reset_dqcounts(mp, bp, firstid, type);
-		xfs_buf_delwri_queue(bp);
+		xfs_buf_delwri_queue(bp, buffer_list);
 		xfs_buf_relse(bp);
 		/*
 		 * goto the next block.
@@ -895,6 +904,7 @@ xfs_qm_dqiter_bufs(
 		bno++;
 		firstid += mp->m_quotainfo->qi_dqperchunk;
 	}
+
 	return error;
 }
 
@@ -904,11 +914,12 @@ xfs_qm_dqiter_bufs(
  */
 STATIC int
 xfs_qm_dqiterate(
-	xfs_mount_t	*mp,
-	xfs_inode_t	*qip,
-	uint		flags)
+	struct xfs_mount	*mp,
+	struct xfs_inode	*qip,
+	uint			flags,
+	struct list_head	*buffer_list)
 {
-	xfs_bmbt_irec_t		*map;
+	struct xfs_bmbt_irec	*map;
 	int			i, nmaps;	/* number of map entries */
 	int			error;		/* return value */
 	xfs_fileoff_t		lblkno;
@@ -975,21 +986,17 @@ xfs_qm_dqiterate(
 			 * Iterate thru all the blks in the extent and
 			 * reset the counters of all the dquots inside them.
 			 */
-			if ((error = xfs_qm_dqiter_bufs(mp,
-						       firstid,
-						       map[i].br_startblock,
-						       map[i].br_blockcount,
-						       flags))) {
-				break;
-			}
+			error = xfs_qm_dqiter_bufs(mp, firstid,
+						   map[i].br_startblock,
+						   map[i].br_blockcount,
+						   flags, buffer_list);
+			if (error)
+				goto out;
 		}
-
-		if (error)
-			break;
 	} while (nmaps > 0);
 
+out:
 	kmem_free(map);
-
 	return error;
 }
 
@@ -1182,8 +1189,11 @@ error0:
 
 STATIC int
 xfs_qm_flush_one(
-	struct xfs_dquot	*dqp)
+	struct xfs_dquot	*dqp,
+	void			*data)
 {
+	struct list_head	*buffer_list = data;
+	struct xfs_buf		*bp = NULL;
 	int			error = 0;
 
 	xfs_dqlock(dqp);
@@ -1192,11 +1202,13 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	if (!xfs_dqflock_nowait(dqp))
-		xfs_dqflock_pushbuf_wait(dqp);
-
-	error = xfs_qm_dqflush(dqp, 0);
+	xfs_dqflock(dqp);
+	error = xfs_qm_dqflush(dqp, &bp);
+	if (error)
+		goto out_unlock;
 
+	xfs_buf_delwri_queue(bp, buffer_list);
+	xfs_buf_relse(bp);
 out_unlock:
 	xfs_dqunlock(dqp);
 	return error;
@@ -1215,6 +1227,7 @@ xfs_qm_quotacheck(
 	size_t		structsz;
 	xfs_inode_t	*uip, *gip;
 	uint		flags;
+	LIST_HEAD	(buffer_list);
 
 	count = INT_MAX;
 	structsz = 1;
@@ -1233,7 +1246,8 @@ xfs_qm_quotacheck(
 	 */
 	uip = mp->m_quotainfo->qi_uquotaip;
 	if (uip) {
-		error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA);
+		error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA,
+					 &buffer_list);
 		if (error)
 			goto error_return;
 		flags |= XFS_UQUOTA_CHKD;
@@ -1242,7 +1256,8 @@ xfs_qm_quotacheck(
 	gip = mp->m_quotainfo->qi_gquotaip;
 	if (gip) {
 		error = xfs_qm_dqiterate(mp, gip, XFS_IS_GQUOTA_ON(mp) ?
-					XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA);
+					 XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA,
+					 &buffer_list);
 		if (error)
 			goto error_return;
 		flags |= XFS_OQUOTA_CHKD;
@@ -1265,19 +1280,27 @@ xfs_qm_quotacheck(
 	 * We've made all the changes that we need to make incore.  Flush them
 	 * down to disk buffers if everything was updated successfully.
 	 */
-	if (XFS_IS_UQUOTA_ON(mp))
-		error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one);
+	if (XFS_IS_UQUOTA_ON(mp)) {
+		error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one,
+					  &buffer_list);
+	}
 	if (XFS_IS_GQUOTA_ON(mp)) {
-		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one);
+		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one,
+					   &buffer_list);
 		if (!error)
 			error = error2;
 	}
 	if (XFS_IS_PQUOTA_ON(mp)) {
-		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one);
+		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one,
+					   &buffer_list);
 		if (!error)
 			error = error2;
 	}
 
+	error2 = xfs_buf_delwri_submit(&buffer_list);
+	if (!error)
+		error = error2;
+
 	/*
 	 * We can get this error if we couldn't do a dquot allocation inside
 	 * xfs_qm_dqusage_adjust (via bulkstat). We don't care about the
@@ -1290,15 +1313,6 @@ xfs_qm_quotacheck(
 		goto error_return;
 	}
 
-	/*
-	 * We didn't log anything, because if we crashed, we'll have to
-	 * start the quotacheck from scratch anyway. However, we must make
-	 * sure that our dquot changes are secure before we put the
-	 * quotacheck'd stamp on the superblock. So, here we do a synchronous
-	 * flush.
-	 */
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
 	/*
 	 * If one type of quotas is off, then it will lose its
 	 * quotachecked status, since we won't be doing accounting for
@@ -1308,6 +1322,13 @@ xfs_qm_quotacheck(
 	mp->m_qflags |= flags;
 
  error_return:
+	while (!list_empty(&buffer_list)) {
+		struct xfs_buf *bp =
+			list_first_entry(&buffer_list, struct xfs_buf, b_list);
+		list_del_init(&bp->b_list);
+		xfs_buf_relse(bp);
+	}
+
 	if (error) {
 		xfs_warn(mp,
 	"Quotacheck: Unsuccessful (Error %d): Disabling quotas.",
@@ -1424,6 +1445,7 @@ xfs_qm_dqfree_one(
 STATIC void
 xfs_qm_dqreclaim_one(
 	struct xfs_dquot	*dqp,
+	struct list_head	*buffer_list,
 	struct list_head	*dispose_list)
 {
 	struct xfs_mount	*mp = dqp->q_mount;
@@ -1456,25 +1478,20 @@ xfs_qm_dqreclaim_one(
 	if (!xfs_dqflock_nowait(dqp))
 		goto out_busy;
 
-	/*
-	 * We have the flush lock so we know that this is not in the
-	 * process of being flushed. So, if this is dirty, flush it
-	 * DELWRI so that we don't get a freelist infested with
-	 * dirty dquots.
-	 */
 	if (XFS_DQ_IS_DIRTY(dqp)) {
+		struct xfs_buf	*bp = NULL;
+
 		trace_xfs_dqreclaim_dirty(dqp);
 
-		/*
-		 * We flush it delayed write, so don't bother releasing the
-		 * freelist lock.
-		 */
-		error = xfs_qm_dqflush(dqp, 0);
+		error = xfs_qm_dqflush(dqp, &bp);
 		if (error) {
 			xfs_warn(mp, "%s: dquot %p flush failed",
 				 __func__, dqp);
+			goto out_busy;
 		}
 
+		xfs_buf_delwri_queue(bp, buffer_list);
+		xfs_buf_relse(bp);
 		/*
 		 * Give the dquot another try on the freelist, as the
 		 * flushing will take some time.
@@ -1518,8 +1535,10 @@ xfs_qm_shake(
 	struct xfs_quotainfo	*qi =
 		container_of(shrink, struct xfs_quotainfo, qi_shrinker);
 	int			nr_to_scan = sc->nr_to_scan;
+	LIST_HEAD		(buffer_list);
 	LIST_HEAD		(dispose_list);
 	struct xfs_dquot	*dqp;
+	int			error;
 
 	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
 		return 0;
@@ -1532,15 +1551,20 @@ xfs_qm_shake(
 			break;
 		dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot,
 				       q_lru);
-		xfs_qm_dqreclaim_one(dqp, &dispose_list);
+		xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list);
 	}
 	mutex_unlock(&qi->qi_lru_lock);
 
+	error = xfs_buf_delwri_submit(&buffer_list);
+	if (error)
+		xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
+
 	while (!list_empty(&dispose_list)) {
 		dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru);
 		list_del_init(&dqp->q_lru);
 		xfs_qm_dqfree_one(dqp);
 	}
+
 out:
 	return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure;
 }

fs/xfs/xfs_qm_bhv.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_qm_syscalls.c

@@ -22,7 +22,6 @@
 #include "xfs_fs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_quotaops.c

@@ -17,7 +17,6 @@
  */
 #include "xfs.h"
 #include "xfs_sb.h"
-#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"

fs/xfs/xfs_rename.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_rtalloc.c

@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -34,7 +33,6 @@
 #include "xfs_rtalloc.h"
 #include "xfs_fsops.h"
 #include "xfs_error.h"
-#include "xfs_rw.h"
 #include "xfs_inode_item.h"
 #include "xfs_trans_space.h"
 #include "xfs_utils.h"
@@ -1872,9 +1870,9 @@ xfs_growfs_rt(
 	/*
 	 * Read in the last block of the device, make sure it exists.
 	 */
-	bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp,
+	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
 				XFS_FSB_TO_BB(mp, nrblocks - 1),
-				XFS_FSB_TO_B(mp, 1), 0);
+				XFS_FSB_TO_BB(mp, 1), 0);
 	if (!bp)
 		return EIO;
 	xfs_buf_relse(bp);
@@ -2219,9 +2217,9 @@ xfs_rtmount_init(
 			(unsigned long long) mp->m_sb.sb_rblocks);
 		return XFS_ERROR(EFBIG);
 	}
-	bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp,
+	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_B(mp, 1), 0);
+					XFS_FSB_TO_BB(mp, 1), 0);
 	if (!bp) {
 		xfs_warn(mp, "realtime device size check failed");
 		return EIO;

fs/xfs/xfs_rw.c

@@ -1,156 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include "xfs.h"
-#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
-#include "xfs_error.h"
-#include "xfs_rw.h"
-
-/*
- * Force a shutdown of the filesystem instantly while keeping
- * the filesystem consistent. We don't do an unmount here; just shutdown
- * the shop, make sure that absolutely nothing persistent happens to
- * this filesystem after this point.
- */
-void
-xfs_do_force_shutdown(
-	xfs_mount_t	*mp,
-	int		flags,
-	char		*fname,
-	int		lnnum)
-{
-	int		logerror;
-
-	logerror = flags & SHUTDOWN_LOG_IO_ERROR;
-
-	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-		xfs_notice(mp,
-	"%s(0x%x) called from line %d of file %s.  Return address = 0x%p",
-			__func__, flags, lnnum, fname, __return_address);
-	}
-	/*
-	 * No need to duplicate efforts.
-	 */
-	if (XFS_FORCED_SHUTDOWN(mp) && !logerror)
-		return;
-
-	/*
-	 * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't
-	 * queue up anybody new on the log reservations, and wakes up
-	 * everybody who's sleeping on log reservations to tell them
-	 * the bad news.
-	 */
-	if (xfs_log_force_umount(mp, logerror))
-		return;
-
-	if (flags & SHUTDOWN_CORRUPT_INCORE) {
-		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
-    "Corruption of in-memory data detected.  Shutting down filesystem");
-		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
-			xfs_stack_trace();
-	} else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-		if (logerror) {
-			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
-		"Log I/O Error Detected.  Shutting down filesystem");
-		} else if (flags & SHUTDOWN_DEVICE_REQ) {
-			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
-		"All device paths lost.  Shutting down filesystem");
-		} else if (!(flags & SHUTDOWN_REMOTE_REQ)) {
-			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
-		"I/O Error Detected. Shutting down filesystem");
-		}
-	}
-	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-		xfs_alert(mp,
-	"Please umount the filesystem and rectify the problem(s)");
-	}
-}
-
-/*
- * This isn't an absolute requirement, but it is
- * just a good idea to call xfs_read_buf instead of
- * directly doing a read_buf call. For one, we shouldn't
- * be doing this disk read if we are in SHUTDOWN state anyway,
- * so this stops that from happening. Secondly, this does all
- * the error checking stuff and the brelse if appropriate for
- * the caller, so the code can be a little leaner.
- */
-
-int
-xfs_read_buf(
-	struct xfs_mount *mp,
-	xfs_buftarg_t	 *target,
-	xfs_daddr_t	 blkno,
-	int              len,
-	uint             flags,
-	xfs_buf_t	 **bpp)
-{
-	xfs_buf_t	 *bp;
-	int		 error;
-
-	if (!flags)
-		flags = XBF_LOCK | XBF_MAPPED;
-
-	bp = xfs_buf_read(target, blkno, len, flags);
-	if (!bp)
-		return XFS_ERROR(EIO);
-	error = bp->b_error;
-	if (!error && !XFS_FORCED_SHUTDOWN(mp)) {
-		*bpp = bp;
-	} else {
-		*bpp = NULL;
-		if (error) {
-			xfs_buf_ioerror_alert(bp, __func__);
-		} else {
-			error = XFS_ERROR(EIO);
-		}
-		if (bp) {
-			XFS_BUF_UNDONE(bp);
-			xfs_buf_stale(bp);
-			/*
-			 * brelse clears B_ERROR and b_error
-			 */
-			xfs_buf_relse(bp);
-		}
-	}
-	return (error);
-}
-
-/*
- * helper function to extract extent size hint from inode
- */
-xfs_extlen_t
-xfs_get_extsz_hint(
-	struct xfs_inode	*ip)
-{
-	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
-		return ip->i_d.di_extsize;
-	if (XFS_IS_REALTIME_INODE(ip))
-		return ip->i_mount->m_sb.sb_rextsize;
-	return 0;
-}

fs/xfs/xfs_rw.h

@@ -1,47 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef	__XFS_RW_H__
-#define	__XFS_RW_H__
-
-struct xfs_buf;
-struct xfs_inode;
-struct xfs_mount;
-
-/*
- * Convert the given file system block to a disk block.
- * We have to treat it differently based on whether the
- * file is a real time file or not, because the bmap code
- * does.
- */
-static inline xfs_daddr_t
-xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
-{
-	return (XFS_IS_REALTIME_INODE(ip) ? \
-		 (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
-		 XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
-}
-
-/*
- * Prototypes for functions in xfs_rw.c.
- */
-extern int xfs_read_buf(struct xfs_mount *mp, xfs_buftarg_t *btp,
-			xfs_daddr_t blkno, int len, uint flags,
-			struct xfs_buf **bpp);
-extern xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
-
-#endif /* __XFS_RW_H__ */

fs/xfs/xfs_super.c

@@ -17,7 +17,6 @@
  */
 
 #include "xfs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
@@ -622,7 +621,7 @@ void
 xfs_blkdev_issue_flush(
 	xfs_buftarg_t		*buftarg)
 {
-	blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL);
+	blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL);
 }
 
 STATIC void
@@ -773,8 +772,14 @@ xfs_init_mount_workqueues(
 	if (!mp->m_unwritten_workqueue)
 		goto out_destroy_data_iodone_queue;
 
+	mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
+			WQ_MEM_RECLAIM, 0, mp->m_fsname);
+	if (!mp->m_cil_workqueue)
+		goto out_destroy_unwritten;
 	return 0;
 
+out_destroy_unwritten:
+	destroy_workqueue(mp->m_unwritten_workqueue);
 out_destroy_data_iodone_queue:
 	destroy_workqueue(mp->m_data_workqueue);
 out:
@@ -785,6 +790,7 @@ STATIC void
 xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	destroy_workqueue(mp->m_cil_workqueue);
 	destroy_workqueue(mp->m_data_workqueue);
 	destroy_workqueue(mp->m_unwritten_workqueue);
 }
@@ -981,18 +987,9 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	xfs_syncd_stop(mp);
-
-	/*
-	 * Blow away any referenced inode in the filestreams cache.
-	 * This can and will cause log traffic as inodes go inactive
-	 * here.
-	 */
 	xfs_filestream_unmount(mp);
-
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
 	xfs_unmountfs(mp);
+	xfs_syncd_stop(mp);
 	xfs_freesb(mp);
 	xfs_icsb_destroy_counters(mp);
 	xfs_destroy_mount_workqueues(mp);
@@ -1072,7 +1069,7 @@ xfs_fs_statfs(
 
 	spin_unlock(&mp->m_sb_lock);
 
-	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) ||
+	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
 	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD))) ==
 			      (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD))
 		xfs_qm_statvfs(ip, statp);
@@ -1362,31 +1359,32 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
-	error = xfs_mountfs(mp);
+	error = xfs_syncd_init(mp);
 	if (error)
 		goto out_filestream_unmount;
 
-	error = xfs_syncd_init(mp);
+	error = xfs_mountfs(mp);
 	if (error)
-		goto out_unmount;
+		goto out_syncd_stop;
 
 	root = igrab(VFS_I(mp->m_rootip));
 	if (!root) {
 		error = ENOENT;
-		goto out_syncd_stop;
+		goto out_unmount;
 	}
 	if (is_bad_inode(root)) {
 		error = EINVAL;
-		goto out_syncd_stop;
+		goto out_unmount;
 	}
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		error = ENOMEM;
-		goto out_syncd_stop;
+		goto out_unmount;
 	}
 
 	return 0;
-
+ out_syncd_stop:
+	xfs_syncd_stop(mp);
  out_filestream_unmount:
 	xfs_filestream_unmount(mp);
  out_free_sb:
@@ -1403,19 +1401,10 @@ out_destroy_workqueues:
  out:
 	return -error;
 
- out_syncd_stop:
-	xfs_syncd_stop(mp);
  out_unmount:
-	/*
-	 * Blow away any referenced inode in the filestreams cache.
-	 * This can and will cause log traffic as inodes go inactive
-	 * here.
-	 */
 	xfs_filestream_unmount(mp);
-
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
 	xfs_unmountfs(mp);
+	xfs_syncd_stop(mp);
 	goto out_free_sb;
 }
 

fs/xfs/xfs_sync.c

@@ -18,7 +18,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
@@ -241,45 +240,6 @@ xfs_sync_inode_data(
 	return error;
 }
 
-STATIC int
-xfs_sync_inode_attr(
-	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	int			flags)
-{
-	int			error = 0;
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_inode_clean(ip))
-		goto out_unlock;
-	if (!xfs_iflock_nowait(ip)) {
-		if (!(flags & SYNC_WAIT))
-			goto out_unlock;
-		xfs_iflock(ip);
-	}
-
-	if (xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		goto out_unlock;
-	}
-
-	error = xfs_iflush(ip, flags);
-
-	/*
-	 * We don't want to try again on non-blocking flushes that can't run
-	 * again immediately. If an inode really must be written, then that's
-	 * what the SYNC_WAIT flag is for.
-	 */
-	if (error == EAGAIN) {
-		ASSERT(!(flags & SYNC_WAIT));
-		error = 0;
-	}
-
- out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	return error;
-}
-
 /*
  * Write out pagecache data for the whole filesystem.
  */
@@ -300,19 +260,6 @@ xfs_sync_data(
 	return 0;
 }
 
-/*
- * Write out inode metadata (attributes) for the whole filesystem.
- */
-STATIC int
-xfs_sync_attr(
-	struct xfs_mount	*mp,
-	int			flags)
-{
-	ASSERT((flags & ~SYNC_WAIT) == 0);
-
-	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags);
-}
-
 STATIC int
 xfs_sync_fsdata(
 	struct xfs_mount	*mp)
@@ -350,7 +297,7 @@ xfs_sync_fsdata(
  * First stage of freeze - no writers will make progress now we are here,
  * so we flush delwri and delalloc buffers here, then wait for all I/O to
  * complete.  Data is frozen at that point. Metadata is not frozen,
- * transactions can still occur here so don't bother flushing the buftarg
+ * transactions can still occur here so don't bother emptying the AIL
  * because it'll just get dirty again.
  */
 int
@@ -365,47 +312,13 @@ xfs_quiesce_data(
 	/* write superblock and hoover up shutdown errors */
 	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_fs_log_dummy(mp);
 
-	/* flush data-only devices */
-	if (mp->m_rtdev_targp)
-		xfs_flush_buftarg(mp->m_rtdev_targp, 1);
-
 	return error ? error : error2;
 }
 
-STATIC void
-xfs_quiesce_fs(
-	struct xfs_mount	*mp)
-{
-	int	count = 0, pincount;
-
-	xfs_reclaim_inodes(mp, 0);
-	xfs_flush_buftarg(mp->m_ddev_targp, 0);
-
-	/*
-	 * This loop must run at least twice.  The first instance of the loop
-	 * will flush most meta data but that will generate more meta data
-	 * (typically directory updates).  Which then must be flushed and
-	 * logged before we can write the unmount record. We also so sync
-	 * reclaim of inodes to catch any that the above delwri flush skipped.
-	 */
-	do {
-		xfs_reclaim_inodes(mp, SYNC_WAIT);
-		xfs_sync_attr(mp, SYNC_WAIT);
-		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
-		if (!pincount) {
-			delay(50);
-			count++;
-		}
-	} while (count < 2);
-}
-
 /*
  * Second stage of a quiesce. The data is already synced, now we have to take
  * care of the metadata. New transactions are already blocked, so we need to
@@ -421,8 +334,12 @@ xfs_quiesce_attr(
 	while (atomic_read(&mp->m_active_trans) > 0)
 		delay(100);
 
-	/* flush inodes and push all remaining buffers out to disk */
-	xfs_quiesce_fs(mp);
+	/* reclaim inodes to do any IO before the freeze completes */
+	xfs_reclaim_inodes(mp, 0);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
+
+	/* flush all pending changes from the AIL */
+	xfs_ail_push_all_sync(mp->m_ail);
 
 	/*
 	 * Just warn here till VFS can correctly support
@@ -436,7 +353,12 @@ xfs_quiesce_attr(
 		xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
 				"Frozen image may not be consistent.");
 	xfs_log_unmount_write(mp);
-	xfs_unmountfs_writesb(mp);
+
+	/*
+	 * At this point we might have modified the superblock again and thus
+	 * added an item to the AIL, thus flush it again.
+	 */
+	xfs_ail_push_all_sync(mp->m_ail);
 }
 
 static void
@@ -460,16 +382,27 @@ xfs_sync_worker(
 					struct xfs_mount, m_sync_work);
 	int		error;
 
-	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		/* dgc: errors ignored here */
-		if (mp->m_super->s_frozen == SB_UNFROZEN &&
-		    xfs_log_need_covered(mp))
-			error = xfs_fs_log_dummy(mp);
-		else
-			xfs_log_force(mp, 0);
-
-		/* start pushing all the metadata that is currently dirty */
-		xfs_ail_push_all(mp->m_ail);
+	/*
+	 * We shouldn't write/force the log if we are in the mount/unmount
+	 * process or on a read only filesystem. The workqueue still needs to be
+	 * active in both cases, however, because it is used for inode reclaim
+	 * during these times.  Use the s_umount semaphore to provide exclusion
+	 * with unmount.
+	 */
+	if (down_read_trylock(&mp->m_super->s_umount)) {
+		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+			/* dgc: errors ignored here */
+			if (mp->m_super->s_frozen == SB_UNFROZEN &&
+			    xfs_log_need_covered(mp))
+				error = xfs_fs_log_dummy(mp);
+			else
+				xfs_log_force(mp, 0);
+
+			/* start pushing all the metadata that is currently
+			 * dirty */
+			xfs_ail_push_all(mp->m_ail);
+		}
+		up_read(&mp->m_super->s_umount);
 	}
 
 	/* queue us up again */
@@ -488,14 +421,6 @@ xfs_syncd_queue_reclaim(
 	struct xfs_mount        *mp)
 {
 
-	/*
-	 * We can have inodes enter reclaim after we've shut down the syncd
-	 * workqueue during unmount, so don't allow reclaim work to be queued
-	 * during unmount.
-	 */
-	if (!(mp->m_super->s_flags & MS_ACTIVE))
-		return;
-
 	rcu_read_lock();
 	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
 		queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work,
@@ -564,7 +489,6 @@ xfs_syncd_init(
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 
 	xfs_syncd_queue_sync(mp);
-	xfs_syncd_queue_reclaim(mp);
 
 	return 0;
 }
@@ -702,11 +626,8 @@ xfs_reclaim_inode_grab(
 }
 
 /*
- * Inodes in different states need to be treated differently, and the return
- * value of xfs_iflush is not sufficient to get this right. The following table
- * lists the inode states and the reclaim actions necessary for non-blocking
- * reclaim:
- *
+ * Inodes in different states need to be treated differently. The following
+ * table lists the inode states and the reclaim actions necessary:
  *
  *	inode state	     iflush ret		required action
  *      ---------------      ----------         ---------------
@@ -716,39 +637,31 @@ xfs_reclaim_inode_grab(
  *	stale, unpinned		0		reclaim
  *	clean, pinned(*)	0		requeue
  *	stale, pinned		EAGAIN		requeue
- *	dirty, delwri ok	0		requeue
- *	dirty, delwri blocked	EAGAIN		requeue
- *	dirty, sync flush	0		reclaim
+ *	dirty, async		-		requeue
+ *	dirty, sync		0		reclaim
  *
  * (*) dgc: I don't think the clean, pinned state is possible but it gets
  * handled anyway given the order of checks implemented.
  *
- * As can be seen from the table, the return value of xfs_iflush() is not
- * sufficient to correctly decide the reclaim action here. The checks in
- * xfs_iflush() might look like duplicates, but they are not.
- *
  * Also, because we get the flush lock first, we know that any inode that has
  * been flushed delwri has had the flush completed by the time we check that
- * the inode is clean. The clean inode check needs to be done before flushing
- * the inode delwri otherwise we would loop forever requeuing clean inodes as
- * we cannot tell apart a successful delwri flush and a clean inode from the
- * return value of xfs_iflush().
+ * the inode is clean.
  *
- * Note that because the inode is flushed delayed write by background
- * writeback, the flush lock may already be held here and waiting on it can
- * result in very long latencies. Hence for sync reclaims, where we wait on the
- * flush lock, the caller should push out delayed write inodes first before
- * trying to reclaim them to minimise the amount of time spent waiting. For
- * background relaim, we just requeue the inode for the next pass.
+ * Note that because the inode is flushed delayed write by AIL pushing, the
+ * flush lock may already be held here and waiting on it can result in very
+ * long latencies.  Hence for sync reclaims, where we wait on the flush lock,
+ * the caller should push the AIL first before trying to reclaim inodes to
+ * minimise the amount of time spent waiting.  For background relaim, we only
+ * bother to reclaim clean inodes anyway.
  *
  * Hence the order of actions after gaining the locks should be:
  *	bad		=> reclaim
  *	shutdown	=> unpin and reclaim
- *	pinned, delwri	=> requeue
+ *	pinned, async	=> requeue
  *	pinned, sync	=> unpin
  *	stale		=> reclaim
  *	clean		=> reclaim
- *	dirty, delwri	=> flush and requeue
+ *	dirty, async	=> requeue
  *	dirty, sync	=> flush, wait and reclaim
  */
 STATIC int
@@ -757,7 +670,8 @@ xfs_reclaim_inode(
 	struct xfs_perag	*pag,
 	int			sync_mode)
 {
-	int	error;
+	struct xfs_buf		*bp = NULL;
+	int			error;
 
 restart:
 	error = 0;
@@ -765,17 +679,6 @@ restart:
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
 			goto out;
-
-		/*
-		 * If we only have a single dirty inode in a cluster there is
-		 * a fair chance that the AIL push may have pushed it into
-		 * the buffer, but xfsbufd won't touch it until 30 seconds
-		 * from now, and thus we will lock up here.
-		 *
-		 * Promote the inode buffer to the front of the delwri list
-		 * and wake up xfsbufd now.
-		 */
-		xfs_promote_inode(ip);
 		xfs_iflock(ip);
 	}
 
@@ -783,13 +686,12 @@ restart:
 		goto reclaim;
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
+		xfs_iflush_abort(ip, false);
 		goto reclaim;
 	}
 	if (xfs_ipincount(ip)) {
-		if (!(sync_mode & SYNC_WAIT)) {
-			xfs_ifunlock(ip);
-			goto out;
-		}
+		if (!(sync_mode & SYNC_WAIT))
+			goto out_ifunlock;
 		xfs_iunpin_wait(ip);
 	}
 	if (xfs_iflags_test(ip, XFS_ISTALE))
@@ -797,61 +699,43 @@ restart:
 	if (xfs_inode_clean(ip))
 		goto reclaim;
 
+	/*
+	 * Never flush out dirty data during non-blocking reclaim, as it would
+	 * just contend with AIL pushing trying to do the same job.
+	 */
+	if (!(sync_mode & SYNC_WAIT))
+		goto out_ifunlock;
+
 	/*
 	 * Now we have an inode that needs flushing.
 	 *
-	 * We do a nonblocking flush here even if we are doing a SYNC_WAIT
-	 * reclaim as we can deadlock with inode cluster removal.
+	 * Note that xfs_iflush will never block on the inode buffer lock, as
 	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
-	 * ip->i_lock, and we are doing the exact opposite here. As a result,
-	 * doing a blocking xfs_itobp() to get the cluster buffer will result
+	 * ip->i_lock, and we are doing the exact opposite here.  As a result,
+	 * doing a blocking xfs_itobp() to get the cluster buffer would result
 	 * in an ABBA deadlock with xfs_ifree_cluster().
 	 *
 	 * As xfs_ifree_cluser() must gather all inodes that are active in the
 	 * cache to mark them stale, if we hit this case we don't actually want
 	 * to do IO here - we want the inode marked stale so we can simply
-	 * reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
-	 * just unlock the inode, back off and try again. Hopefully the next
-	 * pass through will see the stale flag set on the inode.
+	 * reclaim it.  Hence if we get an EAGAIN error here,  just unlock the
+	 * inode, back off and try again.  Hopefully the next pass through will
+	 * see the stale flag set on the inode.
 	 */
-	error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
-	if (sync_mode & SYNC_WAIT) {
-		if (error == EAGAIN) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			/* backoff longer than in xfs_ifree_cluster */
-			delay(2);
-			goto restart;
-		}
-		xfs_iflock(ip);
-		goto reclaim;
+	error = xfs_iflush(ip, &bp);
+	if (error == EAGAIN) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		/* backoff longer than in xfs_ifree_cluster */
+		delay(2);
+		goto restart;
 	}
 
-	/*
-	 * When we have to flush an inode but don't have SYNC_WAIT set, we
-	 * flush the inode out using a delwri buffer and wait for the next
-	 * call into reclaim to find it in a clean state instead of waiting for
-	 * it now. We also don't return errors here - if the error is transient
-	 * then the next reclaim pass will flush the inode, and if the error
-	 * is permanent then the next sync reclaim will reclaim the inode and
-	 * pass on the error.
-	 */
-	if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		xfs_warn(ip->i_mount,
-			"inode 0x%llx background reclaim flush failed with %d",
-			(long long)ip->i_ino, error);
+	if (!error) {
+		error = xfs_bwrite(bp);
+		xfs_buf_relse(bp);
 	}
-out:
-	xfs_iflags_clear(ip, XFS_IRECLAIM);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	/*
-	 * We could return EAGAIN here to make reclaim rescan the inode tree in
-	 * a short while. However, this just burns CPU time scanning the tree
-	 * waiting for IO to complete and xfssyncd never goes back to the idle
-	 * state. Instead, return 0 to let the next scheduled background reclaim
-	 * attempt to reclaim the inode again.
-	 */
-	return 0;
 
+	xfs_iflock(ip);
 reclaim:
 	xfs_ifunlock(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -884,8 +768,21 @@ reclaim:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	xfs_inode_free(ip);
-
 	return error;
+
+out_ifunlock:
+	xfs_ifunlock(ip);
+out:
+	xfs_iflags_clear(ip, XFS_IRECLAIM);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	/*
+	 * We could return EAGAIN here to make reclaim rescan the inode tree in
+	 * a short while. However, this just burns CPU time scanning the tree
+	 * waiting for IO to complete and xfssyncd never goes back to the idle
+	 * state. Instead, return 0 to let the next scheduled background reclaim
+	 * attempt to reclaim the inode again.
+	 */
+	return 0;
 }
 
 /*

fs/xfs/xfs_trace.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_trace.h

@@ -281,7 +281,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_daddr_t, bno)
-		__field(size_t, buffer_length)
+		__field(int, nblks)
 		__field(int, hold)
 		__field(int, pincount)
 		__field(unsigned, lockval)
@@ -291,18 +291,18 @@ DECLARE_EVENT_CLASS(xfs_buf_class,
 	TP_fast_assign(
 		__entry->dev = bp->b_target->bt_dev;
 		__entry->bno = bp->b_bn;
-		__entry->buffer_length = bp->b_buffer_length;
+		__entry->nblks = bp->b_length;
 		__entry->hold = atomic_read(&bp->b_hold);
 		__entry->pincount = atomic_read(&bp->b_pin_count);
 		__entry->lockval = bp->b_sema.count;
 		__entry->flags = bp->b_flags;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+	TP_printk("dev %d:%d bno 0x%llx nblks 0x%x hold %d pincount %d "
 		  "lock %d flags %s caller %pf",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long long)__entry->bno,
-		  __entry->buffer_length,
+		  __entry->nblks,
 		  __entry->hold,
 		  __entry->pincount,
 		  __entry->lockval,
@@ -328,7 +328,7 @@ DEFINE_BUF_EVENT(xfs_buf_unlock);
 DEFINE_BUF_EVENT(xfs_buf_iowait);
 DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
-DEFINE_BUF_EVENT(xfs_buf_delwri_dequeue);
+DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_bdstrat_shut);
@@ -362,7 +362,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class,
 	TP_fast_assign(
 		__entry->dev = bp->b_target->bt_dev;
 		__entry->bno = bp->b_bn;
-		__entry->buffer_length = bp->b_buffer_length;
+		__entry->buffer_length = BBTOB(bp->b_length);
 		__entry->flags = flags;
 		__entry->hold = atomic_read(&bp->b_hold);
 		__entry->pincount = atomic_read(&bp->b_pin_count);
@@ -406,7 +406,7 @@ TRACE_EVENT(xfs_buf_ioerror,
 	TP_fast_assign(
 		__entry->dev = bp->b_target->bt_dev;
 		__entry->bno = bp->b_bn;
-		__entry->buffer_length = bp->b_buffer_length;
+		__entry->buffer_length = BBTOB(bp->b_length);
 		__entry->hold = atomic_read(&bp->b_hold);
 		__entry->pincount = atomic_read(&bp->b_pin_count);
 		__entry->lockval = bp->b_sema.count;
@@ -450,7 +450,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
 		__entry->bli_recur = bip->bli_recur;
 		__entry->bli_refcount = atomic_read(&bip->bli_refcount);
 		__entry->buf_bno = bip->bli_buf->b_bn;
-		__entry->buf_len = bip->bli_buf->b_buffer_length;
+		__entry->buf_len = BBTOB(bip->bli_buf->b_length);
 		__entry->buf_flags = bip->bli_buf->b_flags;
 		__entry->buf_hold = atomic_read(&bip->bli_buf->b_hold);
 		__entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count);
@@ -486,12 +486,10 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_trylock);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pushbuf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf_recur);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb);
@@ -876,15 +874,30 @@ DECLARE_EVENT_CLASS(xfs_log_item_class,
 		  __print_flags(__entry->flags, "|", XFS_LI_FLAGS))
 )
 
+TRACE_EVENT(xfs_log_force,
+	TP_PROTO(struct xfs_mount *mp, xfs_lsn_t lsn),
+	TP_ARGS(mp, lsn),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_lsn_t, lsn)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->lsn = lsn;
+	),
+	TP_printk("dev %d:%d lsn 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->lsn)
+)
+
 #define DEFINE_LOG_ITEM_EVENT(name) \
 DEFINE_EVENT(xfs_log_item_class, name, \
 	TP_PROTO(struct xfs_log_item *lip), \
 	TP_ARGS(lip))
 DEFINE_LOG_ITEM_EVENT(xfs_ail_push);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf_pinned);
 DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned);
 DEFINE_LOG_ITEM_EVENT(xfs_ail_locked);
+DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
 
 
 DECLARE_EVENT_CLASS(xfs_file_class,
@@ -1145,7 +1158,7 @@ TRACE_EVENT(xfs_bunmap,
 
 );
 
-DECLARE_EVENT_CLASS(xfs_busy_class,
+DECLARE_EVENT_CLASS(xfs_extent_busy_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -1168,17 +1181,17 @@ DECLARE_EVENT_CLASS(xfs_busy_class,
 		  __entry->len)
 );
 #define DEFINE_BUSY_EVENT(name) \
-DEFINE_EVENT(xfs_busy_class, name, \
+DEFINE_EVENT(xfs_extent_busy_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(mp, agno, agbno, len))
-DEFINE_BUSY_EVENT(xfs_alloc_busy);
-DEFINE_BUSY_EVENT(xfs_alloc_busy_enomem);
-DEFINE_BUSY_EVENT(xfs_alloc_busy_force);
-DEFINE_BUSY_EVENT(xfs_alloc_busy_reuse);
-DEFINE_BUSY_EVENT(xfs_alloc_busy_clear);
+DEFINE_BUSY_EVENT(xfs_extent_busy);
+DEFINE_BUSY_EVENT(xfs_extent_busy_enomem);
+DEFINE_BUSY_EVENT(xfs_extent_busy_force);
+DEFINE_BUSY_EVENT(xfs_extent_busy_reuse);
+DEFINE_BUSY_EVENT(xfs_extent_busy_clear);
 
-TRACE_EVENT(xfs_alloc_busy_trim,
+TRACE_EVENT(xfs_extent_busy_trim,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len,
 		 xfs_agblock_t tbno, xfs_extlen_t tlen),

fs/xfs/xfs_trans.c

@@ -19,9 +19,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -36,6 +34,7 @@
 #include "xfs_btree.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
+#include "xfs_extent_busy.h"
 #include "xfs_bmap.h"
 #include "xfs_quota.h"
 #include "xfs_trans_priv.h"
@@ -608,8 +607,8 @@ STATIC void
 xfs_trans_free(
 	struct xfs_trans	*tp)
 {
-	xfs_alloc_busy_sort(&tp->t_busy);
-	xfs_alloc_busy_clear(tp->t_mountp, &tp->t_busy, false);
+	xfs_extent_busy_sort(&tp->t_busy);
+	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	atomic_dec(&tp->t_mountp->m_active_trans);
 	xfs_trans_free_dqinfo(tp);

fs/xfs/xfs_trans.h

@@ -345,11 +345,9 @@ struct xfs_item_ops {
 	void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *);
 	void (*iop_pin)(xfs_log_item_t *);
 	void (*iop_unpin)(xfs_log_item_t *, int remove);
-	uint (*iop_trylock)(xfs_log_item_t *);
+	uint (*iop_push)(struct xfs_log_item *, struct list_head *);
 	void (*iop_unlock)(xfs_log_item_t *);
 	xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
-	void (*iop_push)(xfs_log_item_t *);
-	bool (*iop_pushbuf)(xfs_log_item_t *);
 	void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
 };
 
@@ -357,20 +355,18 @@ struct xfs_item_ops {
 #define IOP_FORMAT(ip,vp)	(*(ip)->li_ops->iop_format)(ip, vp)
 #define IOP_PIN(ip)		(*(ip)->li_ops->iop_pin)(ip)
 #define IOP_UNPIN(ip, remove)	(*(ip)->li_ops->iop_unpin)(ip, remove)
-#define IOP_TRYLOCK(ip)		(*(ip)->li_ops->iop_trylock)(ip)
+#define IOP_PUSH(ip, list)	(*(ip)->li_ops->iop_push)(ip, list)
 #define IOP_UNLOCK(ip)		(*(ip)->li_ops->iop_unlock)(ip)
 #define IOP_COMMITTED(ip, lsn)	(*(ip)->li_ops->iop_committed)(ip, lsn)
-#define IOP_PUSH(ip)		(*(ip)->li_ops->iop_push)(ip)
-#define IOP_PUSHBUF(ip)		(*(ip)->li_ops->iop_pushbuf)(ip)
 #define IOP_COMMITTING(ip, lsn) (*(ip)->li_ops->iop_committing)(ip, lsn)
 
 /*
- * Return values for the IOP_TRYLOCK() routines.
+ * Return values for the IOP_PUSH() routines.
  */
-#define	XFS_ITEM_SUCCESS	0
-#define	XFS_ITEM_PINNED		1
-#define	XFS_ITEM_LOCKED		2
-#define XFS_ITEM_PUSHBUF	3
+#define XFS_ITEM_SUCCESS	0
+#define XFS_ITEM_PINNED		1
+#define XFS_ITEM_LOCKED		2
+#define XFS_ITEM_FLUSHING	3
 
 /*
  * This is the type of function which can be given to xfs_trans_callback()

fs/xfs/xfs_trans_ail.c

@@ -20,7 +20,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -79,7 +78,7 @@ xfs_ail_check(
  * Return a pointer to the first item in the AIL.  If the AIL is empty, then
  * return NULL.
  */
-static xfs_log_item_t *
+xfs_log_item_t *
 xfs_ail_min(
 	struct xfs_ail  *ailp)
 {
@@ -364,30 +363,31 @@ xfsaild_push(
 	xfs_log_item_t		*lip;
 	xfs_lsn_t		lsn;
 	xfs_lsn_t		target;
-	long			tout = 10;
+	long			tout;
 	int			stuck = 0;
+	int			flushing = 0;
 	int			count = 0;
-	int			push_xfsbufd = 0;
 
 	/*
-	 * If last time we ran we encountered pinned items, force the log first
-	 * and wait for it before pushing again.
+	 * If we encountered pinned items or did not finish writing out all
+	 * buffers the last time we ran, force the log first and wait for it
+	 * before pushing again.
 	 */
-	spin_lock(&ailp->xa_lock);
-	if (ailp->xa_last_pushed_lsn == 0 && ailp->xa_log_flush &&
-	    !list_empty(&ailp->xa_ail)) {
+	if (ailp->xa_log_flush && ailp->xa_last_pushed_lsn == 0 &&
+	    (!list_empty_careful(&ailp->xa_buf_list) ||
+	     xfs_ail_min_lsn(ailp))) {
 		ailp->xa_log_flush = 0;
-		spin_unlock(&ailp->xa_lock);
+
 		XFS_STATS_INC(xs_push_ail_flush);
 		xfs_log_force(mp, XFS_LOG_SYNC);
-		spin_lock(&ailp->xa_lock);
 	}
 
-	target = ailp->xa_target;
+	spin_lock(&ailp->xa_lock);
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
-	if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
+	if (!lip) {
 		/*
-		 * AIL is empty or our push has reached the end.
+		 * If the AIL is empty or our push has reached the end we are
+		 * done now.
 		 */
 		xfs_trans_ail_cursor_done(ailp, &cur);
 		spin_unlock(&ailp->xa_lock);
@@ -396,54 +396,42 @@ xfsaild_push(
 
 	XFS_STATS_INC(xs_push_ail);
 
-	/*
-	 * While the item we are looking at is below the given threshold
-	 * try to flush it out. We'd like not to stop until we've at least
-	 * tried to push on everything in the AIL with an LSN less than
-	 * the given threshold.
-	 *
-	 * However, we will stop after a certain number of pushes and wait
-	 * for a reduced timeout to fire before pushing further. This
-	 * prevents use from spinning when we can't do anything or there is
-	 * lots of contention on the AIL lists.
-	 */
 	lsn = lip->li_lsn;
+	target = ailp->xa_target;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
 		int	lock_result;
+
 		/*
-		 * If we can lock the item without sleeping, unlock the AIL
-		 * lock and flush the item.  Then re-grab the AIL lock so we
-		 * can look for the next item on the AIL. List changes are
-		 * handled by the AIL lookup functions internally
-		 *
-		 * If we can't lock the item, either its holder will flush it
-		 * or it is already being flushed or it is being relogged.  In
-		 * any of these case it is being taken care of and we can just
-		 * skip to the next item in the list.
+		 * Note that IOP_PUSH may unlock and reacquire the AIL lock.  We
+		 * rely on the AIL cursor implementation to be able to deal with
+		 * the dropped lock.
 		 */
-		lock_result = IOP_TRYLOCK(lip);
-		spin_unlock(&ailp->xa_lock);
+		lock_result = IOP_PUSH(lip, &ailp->xa_buf_list);
 		switch (lock_result) {
 		case XFS_ITEM_SUCCESS:
 			XFS_STATS_INC(xs_push_ail_success);
 			trace_xfs_ail_push(lip);
 
-			IOP_PUSH(lip);
 			ailp->xa_last_pushed_lsn = lsn;
 			break;
 
-		case XFS_ITEM_PUSHBUF:
-			XFS_STATS_INC(xs_push_ail_pushbuf);
-			trace_xfs_ail_pushbuf(lip);
-
-			if (!IOP_PUSHBUF(lip)) {
-				trace_xfs_ail_pushbuf_pinned(lip);
-				stuck++;
-				ailp->xa_log_flush++;
-			} else {
-				ailp->xa_last_pushed_lsn = lsn;
-			}
-			push_xfsbufd = 1;
+		case XFS_ITEM_FLUSHING:
+			/*
+			 * The item or its backing buffer is already beeing
+			 * flushed.  The typical reason for that is that an
+			 * inode buffer is locked because we already pushed the
+			 * updates to it as part of inode clustering.
+			 *
+			 * We do not want to to stop flushing just because lots
+			 * of items are already beeing flushed, but we need to
+			 * re-try the flushing relatively soon if most of the
+			 * AIL is beeing flushed.
+			 */
+			XFS_STATS_INC(xs_push_ail_flushing);
+			trace_xfs_ail_flushing(lip);
+
+			flushing++;
+			ailp->xa_last_pushed_lsn = lsn;
 			break;
 
 		case XFS_ITEM_PINNED:
@@ -453,28 +441,22 @@ xfsaild_push(
 			stuck++;
 			ailp->xa_log_flush++;
 			break;
-
 		case XFS_ITEM_LOCKED:
 			XFS_STATS_INC(xs_push_ail_locked);
 			trace_xfs_ail_locked(lip);
+
 			stuck++;
 			break;
-
 		default:
 			ASSERT(0);
 			break;
 		}
 
-		spin_lock(&ailp->xa_lock);
-		/* should we bother continuing? */
-		if (XFS_FORCED_SHUTDOWN(mp))
-			break;
-		ASSERT(mp->m_log);
-
 		count++;
 
 		/*
 		 * Are there too many items we can't do anything with?
+		 *
 		 * If we we are skipping too many items because we can't flush
 		 * them or they are already being flushed, we back off and
 		 * given them time to complete whatever operation is being
@@ -496,42 +478,36 @@ xfsaild_push(
 	xfs_trans_ail_cursor_done(ailp, &cur);
 	spin_unlock(&ailp->xa_lock);
 
-	if (push_xfsbufd) {
-		/* we've got delayed write buffers to flush */
-		wake_up_process(mp->m_ddev_targp->bt_task);
-	}
+	if (xfs_buf_delwri_submit_nowait(&ailp->xa_buf_list))
+		ailp->xa_log_flush++;
 
-	/* assume we have more work to do in a short while */
+	if (!count || XFS_LSN_CMP(lsn, target) >= 0) {
 out_done:
-	if (!count) {
-		/* We're past our target or empty, so idle */
-		ailp->xa_last_pushed_lsn = 0;
-		ailp->xa_log_flush = 0;
-
-		tout = 50;
-	} else if (XFS_LSN_CMP(lsn, target) >= 0) {
 		/*
-		 * We reached the target so wait a bit longer for I/O to
-		 * complete and remove pushed items from the AIL before we
-		 * start the next scan from the start of the AIL.
+		 * We reached the target or the AIL is empty, so wait a bit
+		 * longer for I/O to complete and remove pushed items from the
+		 * AIL before we start the next scan from the start of the AIL.
 		 */
 		tout = 50;
 		ailp->xa_last_pushed_lsn = 0;
-	} else if ((stuck * 100) / count > 90) {
+	} else if (((stuck + flushing) * 100) / count > 90) {
 		/*
-		 * Either there is a lot of contention on the AIL or we
-		 * are stuck due to operations in progress. "Stuck" in this
-		 * case is defined as >90% of the items we tried to push
-		 * were stuck.
+		 * Either there is a lot of contention on the AIL or we are
+		 * stuck due to operations in progress. "Stuck" in this case
+		 * is defined as >90% of the items we tried to push were stuck.
 		 *
 		 * Backoff a bit more to allow some I/O to complete before
-		 * restarting from the start of the AIL. This prevents us
-		 * from spinning on the same items, and if they are pinned will
-		 * all the restart to issue a log force to unpin the stuck
-		 * items.
+		 * restarting from the start of the AIL. This prevents us from
+		 * spinning on the same items, and if they are pinned will all
+		 * the restart to issue a log force to unpin the stuck items.
 		 */
 		tout = 20;
 		ailp->xa_last_pushed_lsn = 0;
+	} else {
+		/*
+		 * Assume we have more work to do in a short while.
+		 */
+		tout = 10;
 	}
 
 	return tout;
@@ -544,6 +520,8 @@ xfsaild(
 	struct xfs_ail	*ailp = data;
 	long		tout = 0;	/* milliseconds */
 
+	current->flags |= PF_MEMALLOC;
+
 	while (!kthread_should_stop()) {
 		if (tout && tout <= 20)
 			__set_current_state(TASK_KILLABLE);
@@ -610,6 +588,30 @@ xfs_ail_push_all(
 		xfs_ail_push(ailp, threshold_lsn);
 }
 
+/*
+ * Push out all items in the AIL immediately and wait until the AIL is empty.
+ */
+void
+xfs_ail_push_all_sync(
+	struct xfs_ail  *ailp)
+{
+	struct xfs_log_item	*lip;
+	DEFINE_WAIT(wait);
+
+	spin_lock(&ailp->xa_lock);
+	while ((lip = xfs_ail_max(ailp)) != NULL) {
+		prepare_to_wait(&ailp->xa_empty, &wait, TASK_UNINTERRUPTIBLE);
+		ailp->xa_target = lip->li_lsn;
+		wake_up_process(ailp->xa_task);
+		spin_unlock(&ailp->xa_lock);
+		schedule();
+		spin_lock(&ailp->xa_lock);
+	}
+	spin_unlock(&ailp->xa_lock);
+
+	finish_wait(&ailp->xa_empty, &wait);
+}
+
 /*
  * xfs_trans_ail_update - bulk AIL insertion operation.
  *
@@ -667,11 +669,15 @@ xfs_trans_ail_update_bulk(
 
 	if (!list_empty(&tmp))
 		xfs_ail_splice(ailp, cur, &tmp, lsn);
-	spin_unlock(&ailp->xa_lock);
 
-	if (mlip_changed && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) {
-		xlog_assign_tail_lsn(ailp->xa_mount);
+	if (mlip_changed) {
+		if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
+			xlog_assign_tail_lsn_locked(ailp->xa_mount);
+		spin_unlock(&ailp->xa_lock);
+
 		xfs_log_space_wake(ailp->xa_mount);
+	} else {
+		spin_unlock(&ailp->xa_lock);
 	}
 }
 
@@ -700,7 +706,8 @@ void
 xfs_trans_ail_delete_bulk(
 	struct xfs_ail		*ailp,
 	struct xfs_log_item	**log_items,
-	int			nr_items) __releases(ailp->xa_lock)
+	int			nr_items,
+	int			shutdown_type) __releases(ailp->xa_lock)
 {
 	xfs_log_item_t		*mlip;
 	int			mlip_changed = 0;
@@ -718,7 +725,7 @@ xfs_trans_ail_delete_bulk(
 				xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
 		"%s: attempting to delete a log item that is not in the AIL",
 						__func__);
-				xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+				xfs_force_shutdown(mp, shutdown_type);
 			}
 			return;
 		}
@@ -729,28 +736,20 @@ xfs_trans_ail_delete_bulk(
 		if (mlip == lip)
 			mlip_changed = 1;
 	}
-	spin_unlock(&ailp->xa_lock);
 
-	if (mlip_changed && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) {
-		xlog_assign_tail_lsn(ailp->xa_mount);
+	if (mlip_changed) {
+		if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
+			xlog_assign_tail_lsn_locked(ailp->xa_mount);
+		if (list_empty(&ailp->xa_ail))
+			wake_up_all(&ailp->xa_empty);
+		spin_unlock(&ailp->xa_lock);
+
 		xfs_log_space_wake(ailp->xa_mount);
+	} else {
+		spin_unlock(&ailp->xa_lock);
 	}
 }
 
-/*
- * The active item list (AIL) is a doubly linked list of log
- * items sorted by ascending lsn.  The base of the list is
- * a forw/back pointer pair embedded in the xfs mount structure.
- * The base is initialized with both pointers pointing to the
- * base.  This case always needs to be distinguished, because
- * the base has no lsn to look at.  We almost always insert
- * at the end of the list, so on inserts we search from the
- * end of the list to find where the new item belongs.
- */
-
-/*
- * Initialize the doubly linked list to point only to itself.
- */
 int
 xfs_trans_ail_init(
 	xfs_mount_t	*mp)
@@ -765,6 +764,8 @@ xfs_trans_ail_init(
 	INIT_LIST_HEAD(&ailp->xa_ail);
 	INIT_LIST_HEAD(&ailp->xa_cursors);
 	spin_lock_init(&ailp->xa_lock);
+	INIT_LIST_HEAD(&ailp->xa_buf_list);
+	init_waitqueue_head(&ailp->xa_empty);
 
 	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
 			ailp->xa_mount->m_fsname);

fs/xfs/xfs_trans_buf.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -33,7 +31,6 @@
 #include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
-#include "xfs_rw.h"
 #include "xfs_trace.h"
 
 /*
@@ -56,7 +53,7 @@ xfs_trans_buf_item_match(
 		if (blip->bli_item.li_type == XFS_LI_BUF &&
 		    blip->bli_buf->b_target == target &&
 		    XFS_BUF_ADDR(blip->bli_buf) == blkno &&
-		    XFS_BUF_COUNT(blip->bli_buf) == len)
+		    BBTOB(blip->bli_buf->b_length) == len)
 			return blip->bli_buf;
 	}
 
@@ -141,15 +138,11 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;
 
-	if (flags == 0)
-		flags = XBF_LOCK | XBF_MAPPED;
-
 	/*
 	 * Default to a normal get_buf() call if the tp is NULL.
 	 */
 	if (tp == NULL)
-		return xfs_buf_get(target_dev, blkno, len,
-				   flags | XBF_DONT_BLOCK);
+		return xfs_buf_get(target_dev, blkno, len, flags);
 
 	/*
 	 * If we find the buffer in the cache with this transaction
@@ -165,14 +158,6 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 			XFS_BUF_DONE(bp);
 		}
 
-		/*
-		 * If the buffer is stale then it was binval'ed
-		 * since last read.  This doesn't matter since the
-		 * caller isn't allowed to use the data anyway.
-		 */
-		else if (XFS_BUF_ISSTALE(bp))
-			ASSERT(!XFS_BUF_ISDELAYWRITE(bp));
-
 		ASSERT(bp->b_transp == tp);
 		bip = bp->b_fspriv;
 		ASSERT(bip != NULL);
@@ -182,15 +167,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 		return (bp);
 	}
 
-	/*
-	 * We always specify the XBF_DONT_BLOCK flag within a transaction
-	 * so that get_buf does not try to push out a delayed write buffer
-	 * which might cause another transaction to take place (if the
-	 * buffer was delayed alloc).  Such recursive transactions can
-	 * easily deadlock with our current transaction as well as cause
-	 * us to run out of stack space.
-	 */
-	bp = xfs_buf_get(target_dev, blkno, len, flags | XBF_DONT_BLOCK);
+	bp = xfs_buf_get(target_dev, blkno, len, flags);
 	if (bp == NULL) {
 		return NULL;
 	}
@@ -282,14 +259,13 @@ xfs_trans_read_buf(
 	xfs_buf_log_item_t	*bip;
 	int			error;
 
-	if (flags == 0)
-		flags = XBF_LOCK | XBF_MAPPED;
+	*bpp = NULL;
 
 	/*
 	 * Default to a normal get_buf() call if the tp is NULL.
 	 */
 	if (tp == NULL) {
-		bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
+		bp = xfs_buf_read(target, blkno, len, flags);
 		if (!bp)
 			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);
@@ -297,6 +273,8 @@ xfs_trans_read_buf(
 		if (bp->b_error) {
 			error = bp->b_error;
 			xfs_buf_ioerror_alert(bp, __func__);
+			XFS_BUF_UNDONE(bp);
+			xfs_buf_stale(bp);
 			xfs_buf_relse(bp);
 			return error;
 		}
@@ -371,15 +349,7 @@ xfs_trans_read_buf(
 		return 0;
 	}
 
-	/*
-	 * We always specify the XBF_DONT_BLOCK flag within a transaction
-	 * so that get_buf does not try to push out a delayed write buffer
-	 * which might cause another transaction to take place (if the
-	 * buffer was delayed alloc).  Such recursive transactions can
-	 * easily deadlock with our current transaction as well as cause
-	 * us to run out of stack space.
-	 */
-	bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
+	bp = xfs_buf_read(target, blkno, len, flags);
 	if (bp == NULL) {
 		*bpp = NULL;
 		return (flags & XBF_TRYLOCK) ?
@@ -418,19 +388,6 @@ xfs_trans_read_buf(
 	return 0;
 
 shutdown_abort:
-	/*
-	 * the theory here is that buffer is good but we're
-	 * bailing out because the filesystem is being forcibly
-	 * shut down.  So we should leave the b_flags alone since
-	 * the buffer's not staled and just get out.
-	 */
-#if defined(DEBUG)
-	if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
-		xfs_notice(mp, "about to pop assert, bp == 0x%p", bp);
-#endif
-	ASSERT((bp->b_flags & (XBF_STALE|XBF_DELWRI)) !=
-				     (XBF_STALE|XBF_DELWRI));
-
 	trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
 	xfs_buf_relse(bp);
 	*bpp = NULL;
@@ -606,7 +563,7 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
-	ASSERT((first <= last) && (last < XFS_BUF_COUNT(bp)));
+	ASSERT(first <= last && last < BBTOB(bp->b_length));
 	ASSERT(bp->b_iodone == NULL ||
 	       bp->b_iodone == xfs_buf_iodone_callbacks);
 
@@ -626,8 +583,6 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	bp->b_iodone = xfs_buf_iodone_callbacks;
 	bip->bli_item.li_cb = xfs_buf_iodone;
 
-	xfs_buf_delwri_queue(bp);
-
 	trace_xfs_trans_log_buf(bip);
 
 	/*
@@ -651,22 +606,33 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 
 
 /*
- * This called to invalidate a buffer that is being used within
- * a transaction.  Typically this is because the blocks in the
- * buffer are being freed, so we need to prevent it from being
- * written out when we're done.  Allowing it to be written again
- * might overwrite data in the free blocks if they are reallocated
- * to a file.
+ * Invalidate a buffer that is being used within a transaction.
+ *
+ * Typically this is because the blocks in the buffer are being freed, so we
+ * need to prevent it from being written out when we're done.  Allowing it
+ * to be written again might overwrite data in the free blocks if they are
+ * reallocated to a file.
+ *
+ * We prevent the buffer from being written out by marking it stale.  We can't
+ * get rid of the buf log item at this point because the buffer may still be
+ * pinned by another transaction.  If that is the case, then we'll wait until
+ * the buffer is committed to disk for the last time (we can tell by the ref
+ * count) and free it in xfs_buf_item_unpin().  Until that happens we will
+ * keep the buffer locked so that the buffer and buf log item are not reused.
+ *
+ * We also set the XFS_BLF_CANCEL flag in the buf log format structure and log
+ * the buf item.  This will be used at recovery time to determine that copies
+ * of the buffer in the log before this should not be replayed.
  *
- * We prevent the buffer from being written out by clearing the
- * B_DELWRI flag.  We can't always
- * get rid of the buf log item at this point, though, because
- * the buffer may still be pinned by another transaction.  If that
- * is the case, then we'll wait until the buffer is committed to
- * disk for the last time (we can tell by the ref count) and
- * free it in xfs_buf_item_unpin().  Until it is cleaned up we
- * will keep the buffer locked so that the buffer and buf log item
- * are not reused.
+ * We mark the item descriptor and the transaction dirty so that we'll hold
+ * the buffer until after the commit.
+ *
+ * Since we're invalidating the buffer, we also clear the state about which
+ * parts of the buffer have been logged.  We also clear the flag indicating
+ * that this is an inode buffer since the data in the buffer will no longer
+ * be valid.
+ *
+ * We set the stale bit in the buffer as well since we're getting rid of it.
  */
 void
 xfs_trans_binval(
@@ -686,7 +652,6 @@ xfs_trans_binval(
 		 * If the buffer is already invalidated, then
 		 * just return.
 		 */
-		ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
 		ASSERT(XFS_BUF_ISSTALE(bp));
 		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
 		ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_INODE_BUF));
@@ -696,27 +661,8 @@ xfs_trans_binval(
 		return;
 	}
 
-	/*
-	 * Clear the dirty bit in the buffer and set the STALE flag
-	 * in the buf log item.  The STALE flag will be used in
-	 * xfs_buf_item_unpin() to determine if it should clean up
-	 * when the last reference to the buf item is given up.
-	 * We set the XFS_BLF_CANCEL flag in the buf log format structure
-	 * and log the buf item.  This will be used at recovery time
-	 * to determine that copies of the buffer in the log before
-	 * this should not be replayed.
-	 * We mark the item descriptor and the transaction dirty so
-	 * that we'll hold the buffer until after the commit.
-	 *
-	 * Since we're invalidating the buffer, we also clear the state
-	 * about which parts of the buffer have been logged.  We also
-	 * clear the flag indicating that this is an inode buffer since
-	 * the data in the buffer will no longer be valid.
-	 *
-	 * We set the stale bit in the buffer as well since we're getting
-	 * rid of it.
-	 */
 	xfs_buf_stale(bp);
+
 	bip->bli_flags |= XFS_BLI_STALE;
 	bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY);
 	bip->bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;

fs/xfs/xfs_trans_dquot.c

@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_trans_extfree.c

@@ -19,7 +19,6 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_trans_inode.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_trans_priv.h

@@ -71,6 +71,8 @@ struct xfs_ail {
 	spinlock_t		xa_lock;
 	xfs_lsn_t		xa_last_pushed_lsn;
 	int			xa_log_flush;
+	struct list_head	xa_buf_list;
+	wait_queue_head_t	xa_empty;
 };
 
 /*
@@ -90,18 +92,22 @@ xfs_trans_ail_update(
 }
 
 void	xfs_trans_ail_delete_bulk(struct xfs_ail *ailp,
-				struct xfs_log_item **log_items, int nr_items)
+				struct xfs_log_item **log_items, int nr_items,
+				int shutdown_type)
 				__releases(ailp->xa_lock);
 static inline void
 xfs_trans_ail_delete(
 	struct xfs_ail	*ailp,
-	xfs_log_item_t	*lip) __releases(ailp->xa_lock)
+	xfs_log_item_t	*lip,
+	int		shutdown_type) __releases(ailp->xa_lock)
 {
-	xfs_trans_ail_delete_bulk(ailp, &lip, 1);
+	xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type);
 }
 
 void			xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
 void			xfs_ail_push_all(struct xfs_ail *);
+void			xfs_ail_push_all_sync(struct xfs_ail *);
+struct xfs_log_item	*xfs_ail_min(struct xfs_ail  *ailp);
 xfs_lsn_t		xfs_ail_min_lsn(struct xfs_ail *ailp);
 
 struct xfs_log_item *	xfs_trans_ail_cursor_first(struct xfs_ail *ailp,

fs/xfs/xfs_types.h

@@ -57,6 +57,7 @@ typedef __uint64_t __psunsigned_t;
 #endif	/* __KERNEL__ */
 
 typedef __uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef	__uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef	__uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef	__uint32_t	xfs_agnumber_t;	/* allocation group number */
 typedef __int32_t	xfs_extnum_t;	/* # of extents in a file */
@@ -101,6 +102,7 @@ typedef __uint64_t	xfs_fileoff_t;	/* block number in a file */
 typedef __int64_t	xfs_sfiloff_t;	/* signed block number in a file */
 typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 
+
 /*
  * Null values for the types.
  */
@@ -120,6 +122,9 @@ typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 
+#define	NULLFSINO	((xfs_ino_t)-1)
+#define	NULLAGINO	((xfs_agino_t)-1)
+
 /*
  * Max values for extlen, extnum, aextnum.
  */

fs/xfs/xfs_utils.c

@@ -18,9 +18,7 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"

fs/xfs/xfs_vnodeops.c

@@ -21,7 +21,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -39,7 +38,6 @@
 #include "xfs_bmap.h"
 #include "xfs_acl.h"
 #include "xfs_attr.h"
-#include "xfs_rw.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_utils.h"
@@ -81,8 +79,7 @@ xfs_readlink_bmap(
 		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
 		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 
-		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt),
-				  XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK);
+		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0);
 		if (!bp)
 			return XFS_ERROR(ENOMEM);
 		error = bp->b_error;
@@ -1919,7 +1916,7 @@ xfs_alloc_file_space(
 
 error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
 	xfs_bmap_cancel(&free_list);
-	xfs_trans_unreserve_quota_nblks(tp, ip, qblocks, 0, quota_flag);
+	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 
 error1:	/* Just cancel transaction */
 	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
@@ -1966,7 +1963,7 @@ xfs_zero_remaining_bytes(
 
 	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp,
-				mp->m_sb.sb_blocksize, XBF_DONT_BLOCK);
+				  BTOBB(mp->m_sb.sb_blocksize), 0);
 	if (!bp)
 		return XFS_ERROR(ENOMEM);
 
@@ -2315,17 +2312,33 @@ xfs_change_file_space(
 	case XFS_IOC_ALLOCSP64:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_FREESP64:
+		/*
+		 * These operations actually do IO when extending the file, but
+		 * the allocation is done seperately to the zeroing that is
+		 * done. This set of operations need to be serialised against
+		 * other IO operations, such as truncate and buffered IO. We
+		 * need to take the IOLOCK here to serialise the allocation and
+		 * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
+		 * truncate, direct IO) from racing against the transient
+		 * allocated but not written state we can have here.
+		 */
+		xfs_ilock(ip, XFS_IOLOCK_EXCL);
 		if (startoffset > fsize) {
 			error = xfs_alloc_file_space(ip, fsize,
-					startoffset - fsize, 0, attr_flags);
-			if (error)
+					startoffset - fsize, 0,
+					attr_flags | XFS_ATTR_NOLOCK);
+			if (error) {
+				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 				break;
+			}
 		}
 
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = startoffset;
 
-		error = xfs_setattr_size(ip, &iattr, attr_flags);
+		error = xfs_setattr_size(ip, &iattr,
+					 attr_flags | XFS_ATTR_NOLOCK);
+		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
 		if (error)
 			return error;