Proposed 3.0-stable bug patches

cover

	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
---
 fs/xfs/linux-2.6/xfs_discard.c |   20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)
index 572494f..286a051 100644
@@ -38,7 +38,7 @@ xfs_trim_extents(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	xfs_fsblock_t		start,
-	xfs_fsblock_t		len,
+	xfs_fsblock_t		end,
 	xfs_fsblock_t		minlen,
 	__uint64_t		*blocks_trimmed)
 {

@@ -100,7 +100,7 @@ xfs_trim_extents(
 		 * down partially overlapping ranges for now.
 		 */
 		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
-		    XFS_AGB_TO_FSB(mp, agno, fbno) >= start + len) {
+		    XFS_AGB_TO_FSB(mp, agno, fbno) > end) {
 			trace_xfs_discard_exclude(mp, agno, fbno, flen);
 			goto next_extent;
 		}

@@ -145,7 +145,7 @@ xfs_ioc_trim(
 	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
-	xfs_fsblock_t		start, len, minlen;
+	xfs_fsblock_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
 	__uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;

@@ -165,19 +165,19 @@ xfs_ioc_trim(
 	 * matter as trimming blocks is an advisory interface.
 	 */
 	start = XFS_B_TO_FSBT(mp, range.start);
-	len = XFS_B_TO_FSBT(mp, range.len);
+	end = start + XFS_B_TO_FSBT(mp, range.len) - 1;
 	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
 
-	start_agno = XFS_FSB_TO_AGNO(mp, start);
-	if (start_agno >= mp->m_sb.sb_agcount)
+	if (start >= mp->m_sb.sb_dblocks)
 		return -XFS_ERROR(EINVAL);
+	if (end > mp->m_sb.sb_dblocks - 1)
+		end = mp->m_sb.sb_dblocks - 1;
 
-	end_agno = XFS_FSB_TO_AGNO(mp, start + len);
-	if (end_agno >= mp->m_sb.sb_agcount)
-		end_agno = mp->m_sb.sb_agcount - 1;
+	start_agno = XFS_FSB_TO_AGNO(mp, start);
+	end_agno = XFS_FSB_TO_AGNO(mp, end);
 
 	for (agno = start_agno; agno <= end_agno; agno++) {
-		error = -xfs_trim_extents(mp, agno, start, len, minlen,
+		error = -xfs_trim_extents(mp, agno, start, end, minlen,
 					  &blocks_trimmed);
 		if (error)
 			last_error = error;

---
 fs/xfs/xfs_bmap.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
Index: b/fs/xfs/xfs_bmap.c
===================================================================
@@ -4453,8 +4453,18 @@ xfs_bmapi(
 					xfs_bmbt_get_all(ep, &prev);
 				}
 			} else {
-				alen = (xfs_extlen_t)
-					XFS_FILBLKS_MIN(len, MAXEXTLEN);
+				/*
+				 * There's a 32/64 bit type mismatch between the
+				 * allocation length request (which can be 64
+				 * bits in length) and the bma length request,
+				 * which is xfs_extlen_t and therefore 32 bits.
+				 * Hence we have to check for 32-bit overflows
+				 * and handle them here.
+				 */
+				if (len > (xfs_filblks_t)MAXEXTLEN)
+					alen = MAXEXTLEN;
+				else
+					alen = len;
 				if (!eof)
 					alen = (xfs_extlen_t)
 						XFS_FILBLKS_MIN(alen,

---
 fs/xfs/linux-2.6/xfs_super.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
index e6ac98c..04dd4d4 100644
@@ -1617,12 +1617,12 @@ STATIC int __init
 xfs_init_workqueues(void)
 {
 	/*
-	 * max_active is set to 8 to give enough concurency to allow
-	 * multiple work operations on each CPU to run. This allows multiple
-	 * filesystems to be running sync work concurrently, and scales with
-	 * the number of CPUs in the system.
+	 * We never want to the same work item to run twice, reclaiming inodes
+	 * or idling the log is not going to get any faster by multiple CPUs
+	 * competing for ressources.  Use the default large max_active value
+	 * so that even lots of filesystems can perform these task in parallel.
 	 */
-	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8);
+	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_NON_REENTRANT, 0);
 	if (!xfs_syncd_wq)
 		return -ENOMEM;
 	return 0;

---
 fs/xfs/xfs_trans.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
index efc147f..9b4437d 100644
@@ -1151,8 +1151,8 @@ xfs_trans_add_item(
 {
 	struct xfs_log_item_desc *lidp;
 
-	ASSERT(lip->li_mountp = tp->t_mountp);
-	ASSERT(lip->li_ailp = tp->t_mountp->m_ail);
+	ASSERT(lip->li_mountp == tp->t_mountp);
+	ASSERT(lip->li_ailp == tp->t_mountp->m_ail);
 
 	lidp = kmem_zone_zalloc(xfs_log_item_desc_zone, KM_SLEEP | KM_NOFS);
 

---
 fs/xfs/linux-2.6/xfs_sync.c |   10 ++++------
 fs/xfs/xfs_iget.c           |    9 +++++++++
 2 files changed, 13 insertions(+), 6 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_sync.c
===================================================================
@@ -921,17 +921,15 @@ reclaim:
 	 * can reference the inodes in the cache without taking references.
 	 *
 	 * We make that OK here by ensuring that we wait until the inode is
-	 * unlocked after the lookup before we go ahead and free it.  We get
-	 * both the ilock and the iolock because the code may need to drop the
-	 * ilock one but will still hold the iolock.
+	 * unlocked after the lookup before we go ahead and free it.
 	 */
-	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_qm_dqdetach(ip);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	xfs_inode_free(ip);
-	return error;
 
+	return error;
 }
 
 /*

Index: b/fs/xfs/xfs_iget.c
===================================================================
@@ -430,6 +430,15 @@ xfs_iget(
 	xfs_perag_t	*pag;
 	xfs_agino_t	agino;
 
+	/*
+	 * xfs_reclaim_inode() uses the ILOCK to ensure an inode
+	 * doesn't get freed while it's being referenced during a
+	 * radix tree traversal here.  It assumes this function
+	 * aqcuires only the ILOCK (and therefore it has no need to
+	 * involve the IOLOCK in this synchronization).
+	 */
+	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
+
 	/* reject inode numbers outside existing AGs */
 	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
 		return EINVAL;

---
 fs/xfs/linux-2.6/xfs_ioctl.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)
index acca2c5..ada7da9 100644
@@ -450,9 +450,12 @@ xfs_attrmulti_attr_get(
 
 	if (*len > XATTR_SIZE_MAX)
 		return EINVAL;
-	kbuf = kmalloc(*len, GFP_KERNEL);
-	if (!kbuf)
-		return ENOMEM;
+	kbuf = kmem_zalloc(*len, KM_SLEEP | KM_MAYFAIL);
+	if (!kbuf) {
+		kbuf = kmem_zalloc_large(*len);
+		if (!kbuf)
+			return ENOMEM;
+	}
 
 	error = xfs_attr_get(XFS_I(inode), name, kbuf, (int *)len, flags);
 	if (error)

@@ -462,7 +465,10 @@ xfs_attrmulti_attr_get(
 		error = EFAULT;
 
  out_kfree:
-	kfree(kbuf);
+	if (is_vmalloc_addr(kbuf))
+		kmem_free_large(kbuf);
+	else
+		kmem_free(kbuf);
 	return error;
 }
 

---
 fs/xfs/xfs_bmap.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)
Index: b/fs/xfs/xfs_bmap.c
===================================================================
@@ -5457,8 +5457,12 @@ xfs_getbmap(
 	if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
 		return XFS_ERROR(ENOMEM);
 	out = kmem_zalloc(bmv->bmv_count * sizeof(struct getbmapx), KM_MAYFAIL);
-	if (!out)
-		return XFS_ERROR(ENOMEM);
+	if (!out) {
+		out = kmem_zalloc_large(bmv->bmv_count *
+					sizeof(struct getbmapx));
+		if (!out)
+			return XFS_ERROR(ENOMEM);
+	}
 
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {

@@ -5583,7 +5587,10 @@ xfs_getbmap(
 			break;
 	}
 
-	kmem_free(out);
+	if (is_vmalloc_addr(out))
+		kmem_free_large(out);
+	else
+		kmem_free(out);
 	return error;
 }
 

---
 fs/xfs/xfs_bmap.c    |    9 +++++++++
 fs/xfs/xfs_rtalloc.c |    9 ++++-----
 2 files changed, 13 insertions(+), 5 deletions(-)
Index: b/fs/xfs/xfs_bmap.c
===================================================================
@@ -5041,6 +5041,15 @@ xfs_bunmapi(
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
+
+	if (isrt) {
+		/*
+		 * Synchronize by locking the bitmap inode.
+		 */
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, mp->m_rbmip);
+	}
+
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
 	       (nexts == 0 || extno < nexts)) {

Index: b/fs/xfs/xfs_rtalloc.c
===================================================================
@@ -183,6 +183,7 @@ error_cancel:
 		oblocks = map.br_startoff + map.br_blockcount;
 	}
 	return 0;
+
 error:
 	return error;
 }

@@ -2149,11 +2150,9 @@ xfs_rtfree_extent(
 	xfs_buf_t	*sumbp;		/* summary file block buffer */
 
 	mp = tp->t_mountp;
-	/*
-	 * Synchronize by locking the bitmap inode.
-	 */
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin_ref(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
+	ASSERT(mp->m_rbmip->i_itemp != NULL);
+	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
 #if defined(__KERNEL__) && defined(DEBUG)
 	/*

---
 fs/xfs/linux-2.6/xfs_ioctl.c |   14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)
index ada7da9..b27fb6d 100644
@@ -209,6 +209,7 @@ xfs_open_by_handle(
 	struct file		*filp;
 	struct inode		*inode;
 	struct dentry		*dentry;
+	fmode_t			fmode;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -XFS_ERROR(EPERM);

@@ -228,26 +229,21 @@ xfs_open_by_handle(
 	hreq->oflags |= O_LARGEFILE;
 #endif
 
-	/* Put open permission in namei format. */
 	permflag = hreq->oflags;
-	if ((permflag+1) & O_ACCMODE)
-		permflag++;
-	if (permflag & O_TRUNC)
-		permflag |= 2;
-
+	fmode = OPEN_FMODE(permflag);
 	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
-	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
+	    (fmode & FMODE_WRITE) && IS_APPEND(inode)) {
 		error = -XFS_ERROR(EPERM);
 		goto out_dput;
 	}
 
-	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
+	if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
 		error = -XFS_ERROR(EACCES);
 		goto out_dput;
 	}
 
 	/* Can't write directories. */
-	if (S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
+	if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
 		error = -XFS_ERROR(EISDIR);
 		goto out_dput;
 	}

---
 fs/xfs/xfs_log.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
Index: b/fs/xfs/xfs_log.c
===================================================================
@@ -531,8 +531,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 				.lv_iovecp = &reg,
 			};
 
-			/* remove inited flag */
+			/* remove inited flag, and account for space used */
 			tic->t_flags = 0;
+			tic->t_curr_res -= sizeof(magic);
 			error = xlog_write(log, &vec, tic, &lsn,
 					   NULL, XLOG_UNMOUNT_TRANS);
 			/*

---
 fs/xfs/linux-2.6/xfs_discard.c |   61 +++++++++++++++++++++++++----------------
 fs/xfs/xfs_alloc.c             |    2 -
 fs/xfs/xfs_alloc.h             |    7 ++++
 3 files changed, 46 insertions(+), 24 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_discard.c
===================================================================
@@ -37,9 +37,9 @@ STATIC int
 xfs_trim_extents(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
-	xfs_fsblock_t		start,
-	xfs_fsblock_t		end,
-	xfs_fsblock_t		minlen,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen,
 	__uint64_t		*blocks_trimmed)
 {
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;

@@ -67,7 +67,7 @@ xfs_trim_extents(
 	/*
 	 * Look up the longest btree in the AGF and start with it.
 	 */
-	error = xfs_alloc_lookup_le(cur, 0,
+	error = xfs_alloc_lookup_ge(cur, 0,
 			    be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i);
 	if (error)
 		goto out_del_cursor;

@@ -77,8 +77,10 @@ xfs_trim_extents(
 	 * enough to be worth discarding.
 	 */
 	while (i) {
-		xfs_agblock_t fbno;
-		xfs_extlen_t flen;
+		xfs_agblock_t	fbno;
+		xfs_extlen_t	flen;
+		xfs_daddr_t	dbno;
+		xfs_extlen_t	dlen;
 
 		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
 		if (error)

@@ -87,9 +89,17 @@ xfs_trim_extents(
 		ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest));
 
 		/*
+		 * use daddr format for all range/len calculations as that is
+		 * the format the range/len variables are supplied in by
+		 * userspace.
+		 */
+		dbno = XFS_AGB_TO_DADDR(mp, agno, fbno);
+		dlen = XFS_FSB_TO_BB(mp, flen);
+
+		/*
 		 * Too small?  Give up.
 		 */
-		if (flen < minlen) {
+		if (dlen < minlen) {
 			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
 			goto out_del_cursor;
 		}

@@ -99,8 +109,7 @@ xfs_trim_extents(
 		 * supposed to discard skip it.  Do not bother to trim
 		 * down partially overlapping ranges for now.
 		 */
-		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
-		    XFS_AGB_TO_FSB(mp, agno, fbno) > end) {
+		if (dbno + dlen < start || dbno > end) {
 			trace_xfs_discard_exclude(mp, agno, fbno, flen);
 			goto next_extent;
 		}

@@ -115,10 +124,7 @@ xfs_trim_extents(
 		}
 
 		trace_xfs_discard_extent(mp, agno, fbno, flen);
-		error = -blkdev_issue_discard(bdev,
-				XFS_AGB_TO_DADDR(mp, agno, fbno),
-				XFS_FSB_TO_BB(mp, flen),
-				GFP_NOFS, 0);
+		error = -blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0);
 		if (error)
 			goto out_del_cursor;
 		*blocks_trimmed += flen;

@@ -137,6 +143,15 @@ out_put_perag:
 	return error;
 }
 
+/*
+ * trim a range of the filesystem.
+ *
+ * Note: the parameters passed from userspace are byte ranges into the
+ * filesystem which does not match to the format we use for filesystem block
+ * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
+ * is a linear address range. Hence we need to use DADDR based conversions and
+ * comparisons for determining the correct offset and regions to trim.
+ */
 int
 xfs_ioc_trim(
 	struct xfs_mount		*mp,

@@ -145,7 +160,7 @@ xfs_ioc_trim(
 	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
-	xfs_fsblock_t		start, end, minlen;
+	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
 	__uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;

@@ -159,22 +174,22 @@ xfs_ioc_trim(
 
 	/*
 	 * Truncating down the len isn't actually quite correct, but using
-	 * XFS_B_TO_FSB would mean we trivially get overflows for values
+	 * BBTOB would mean we trivially get overflows for values
 	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
 	 * used by the fstrim application.  In the end it really doesn't
 	 * matter as trimming blocks is an advisory interface.
 	 */
-	start = XFS_B_TO_FSBT(mp, range.start);
-	end = start + XFS_B_TO_FSBT(mp, range.len) - 1;
-	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
+	start = BTOBB(range.start);
+	end = start + BTOBBT(range.len) - 1;
+	minlen = BTOBB(max_t(u64, granularity, range.minlen));
 
-	if (start >= mp->m_sb.sb_dblocks)
+	if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks)
 		return -XFS_ERROR(EINVAL);
-	if (end > mp->m_sb.sb_dblocks - 1)
-		end = mp->m_sb.sb_dblocks - 1;
+	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
+		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
 
-	start_agno = XFS_FSB_TO_AGNO(mp, start);
-	end_agno = XFS_FSB_TO_AGNO(mp, end);
+	start_agno = xfs_daddr_to_agno(mp, start);
+	end_agno = xfs_daddr_to_agno(mp, end);
 
 	for (agno = start_agno; agno <= end_agno; agno++) {
 		error = -xfs_trim_extents(mp, agno, start, end, minlen,

Index: b/fs/xfs/xfs_alloc.c
===================================================================
@@ -68,7 +68,7 @@ xfs_alloc_lookup_eq(
  * Lookup the first record greater than or equal to [bno, len]
  * in the btree given by cur.
  */
-STATIC int				/* error */
+int				/* error */
 xfs_alloc_lookup_ge(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */

Index: b/fs/xfs/xfs_alloc.h
===================================================================
@@ -243,6 +243,13 @@ xfs_alloc_lookup_le(
 	xfs_extlen_t		len,	/* length of extent */
 	int			*stat);	/* success/failure */
 
+int				/* error */
+xfs_alloc_lookup_ge(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat);	/* success/failure */
+
 int					/* error */
 xfs_alloc_get_rec(
 	struct xfs_btree_cur	*cur,	/* btree cursor */

---
 fs/xfs/linux-2.6/xfs_super.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
Index: b/fs/xfs/linux-2.6/xfs_super.c
===================================================================
@@ -1091,7 +1091,7 @@ 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);

---
 fs/xfs/linux-2.6/xfs_super.c |   17 +++++++++--------
 fs/xfs/linux-2.6/xfs_sync.c  |   19 +++++++++----------
 2 files changed, 18 insertions(+), 18 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_super.c
===================================================================
@@ -994,7 +994,6 @@ xfs_fs_put_super(
 	 * structure so we don't have memory reclaim racing with us here.
 	 */
 	xfs_inode_shrinker_unregister(mp);
-	xfs_syncd_stop(mp);
 
 	/*
 	 * Blow away any referenced inode in the filestreams cache.

@@ -1006,6 +1005,7 @@ xfs_fs_put_super(
 	XFS_bflush(mp->m_ddev_targp);
 
 	xfs_unmountfs(mp);
+	xfs_syncd_stop(mp);
 	xfs_freesb(mp);
 	xfs_icsb_destroy_counters(mp);
 	xfs_close_devices(mp);

@@ -1378,22 +1378,22 @@ xfs_fs_fill_super(
 
 	xfs_inode_shrinker_register(mp);
 
-	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_alloc_root(root);
 	if (!sb->s_root) {

@@ -1403,6 +1403,8 @@ xfs_fs_fill_super(
 
 	return 0;
 
+ out_syncd_stop:
+	xfs_syncd_stop(mp);
  out_filestream_unmount:
 	xfs_inode_shrinker_unregister(mp);
 	xfs_filestream_unmount(mp);

@@ -1420,8 +1422,6 @@ xfs_fs_fill_super(
 
  out_iput:
 	iput(root);
- out_syncd_stop:
-	xfs_syncd_stop(mp);
  out_unmount:
 	xfs_inode_shrinker_unregister(mp);
 

@@ -1435,6 +1435,7 @@ xfs_fs_fill_super(
 	XFS_bflush(mp->m_ddev_targp);
 
 	xfs_unmountfs(mp);
+	xfs_syncd_stop(mp);
 	goto out_free_sb;
 }
 

Index: b/fs/xfs/linux-2.6/xfs_sync.c
===================================================================
@@ -502,7 +502,15 @@ xfs_sync_worker(
 					struct xfs_mount, m_sync_work);
 	int		error;
 
-	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+	/*
+	 * 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. hence use the MS_ACTIVE flag to avoid doing
+	 * anything in these periods.
+	 */
+	if (!(mp->m_super->s_flags & MS_ACTIVE) &&
+	    !(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		/* dgc: errors ignored here */
 		if (mp->m_super->s_frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))

@@ -531,14 +539,6 @@ 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,

@@ -607,7 +607,6 @@ 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;
 }

---
 fs/xfs/linux-2.6/xfs_aops.c |   30 +++++++++++++++++++++++++----
 fs/xfs/xfs_iomap.c          |   45 ++++++++++++++++++--------------------------
 2 files changed, 45 insertions(+), 30 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1158,7 +1158,14 @@ __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 {

@@ -1181,22 +1188,37 @@ __xfs_get_blocks(
 	     (imap.br_startblock == HOLESTARTBLOCK ||
 	      imap.br_startblock == DELAYSTARTBLOCK))) {
 		if (direct) {
+			/*
+			 * 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;
 		} else {
+			/*
+			 * Delalloc reservations do not require a transaction,
+			 * we can go on without dropping the lock here.
+			 */
 			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) {

 xfs_ilock:             flags ILOCK_EXCL caller xfs_iomap_write_delay
 xfs_iext_insert:       state  idx 3 offset 3072 block 4503599627239432 count 1 flag 0 caller xfs_bmap_add_extent_hole_delay
 xfs_get_blocks_alloc:  size 0x180000 offset 0x180000 count 512 type  startoff 0xc00 startblock -1 blockcount 0x1
 xfs_ilock:             flags ILOCK_EXCL caller __xfs_get_blocks
                                                ^^^^^^^^^^^^^^^^^^^
[  132.606693] ino 0x80e48: vwf to 0x181000, sze 0x180000
[  132.609573] start_fsb 0xc01, end_fsb 0xc08
---
 fs/xfs/linux-2.6/xfs_aops.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1421,7 +1421,7 @@ xfs_vm_write_failed(
 		 * 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;
+		start_fsb = XFS_B_TO_FSB(ip->i_mount, inode->i_size);
 		end_fsb = XFS_B_TO_FSB(ip->i_mount, to);
 		if (end_fsb <= start_fsb)
 			return;

---
 fs/xfs/linux-2.6/xfs_aops.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -636,7 +636,7 @@ xfs_map_at_offset(
  * or delayed allocate extent.
  */
 STATIC int
-xfs_is_delayed_page(
+xfs_check_page_type(
 	struct page		*page,
 	unsigned int		type)
 {

@@ -650,11 +650,11 @@ 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);

@@ -697,7 +697,7 @@ 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;
 
 	/*

@@ -847,7 +847,7 @@ 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))

[ 5012.329024] ino 0xa0026: vwf to 0x17000, sze 0x1c85ae
[ 5015.867162] ino 0xa0026: blks: 0x83 delay blocks 0x1, size 0x2538c0
[ 5015.868293] ext 0: off 0x4a, fsb 0x50306, len 0x1
[ 5015.869095] ext 1: off 0x4b, fsb 0x7899, len 0x6b
[ 5015.869900] ext 2: off 0xb6, fsb 0xffffffffe0008, len 0x1
                                    ^^^^^^^^^^^^^^^
[ 5015.871027] ext 3: off 0x36e, fsb 0x7a27, len 0xd
[ 5015.872206] ext 4: off 0x4cf, fsb 0x7a1d, len 0xa
    +------+------+------+------+------+------+------+------+
      UMA    UMA    UMA    UMA    UMA    UMA    UND    FAIL
    +------+------+------+------+------+------+------+------+
      UMD    UMD    UMD    UMD    UMD    UMD    UND    FAIL
---
 fs/xfs/linux-2.6/xfs_aops.c |  173 ++++++++++++++++++++++++++++++++------------
 1 file changed, 126 insertions(+), 47 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1199,11 +1199,18 @@ __xfs_get_blocks(
 						       &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.
+			 * 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;

@@ -1394,53 +1401,90 @@ xfs_vm_direct_IO(
 	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;
+
+	ASSERT(block_offset + from == pos);
+
+	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;
+		/* 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 (to > inode->i_size) {
-		/*
-		 * punch out the delalloc blocks we have already allocated. We
-		 * don't call xfs_setattr() to do this as we may be in the
-		 * middle of a multi-iovec write and so the vfs inode->i_size
-		 * will not match the xfs ip->i_size and so it will zero too
-		 * much. Hence we jus truncate the page cache to zero what is
-		 * necessary and punch the delalloc blocks directly.
-		 */
-		struct xfs_inode	*ip = XFS_I(inode);
-		xfs_fileoff_t		start_fsb;
-		xfs_fileoff_t		end_fsb;
-		int			error;
+		if (!buffer_delay(bh))
+			continue;
 
-		truncate_pagecache(inode, to, inode->i_size);
+		if (!buffer_new(bh) && block_offset < i_size_read(inode))
+			continue;
 
-		/*
-		 * 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);
-		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);
+		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,

@@ -1451,15 +1495,40 @@ 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,

@@ -1472,9 +1541,19 @@ 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_bmap.c  |   19 +++++++++++++++----
 fs/xfs/xfs_inode.h |    8 ++++++--
 2 files changed, 21 insertions(+), 6 deletions(-)
Index: b/fs/xfs/xfs_bmap.c
===================================================================
@@ -53,7 +53,6 @@
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 
-
 #ifdef DEBUG
 STATIC void
 xfs_bmap_check_leaf_extents(xfs_btree_cur_t *cur, xfs_inode_t *ip, int whichfork);

@@ -5543,9 +5542,21 @@ 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));
-                        if (map[i].br_startblock == HOLESTARTBLOCK &&
+
+			/*
+			 * 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 */
 				out[cur_ext].bmv_oflags |= BMV_OF_LAST;

Index: b/fs/xfs/xfs_inode.h
===================================================================
@@ -264,8 +264,12 @@ typedef struct xfs_inode {
 	struct inode		i_vnode;	/* embedded VFS inode */
 } xfs_inode_t;
 
-#define XFS_ISIZE(ip)	(((ip)->i_d.di_mode & S_IFMT) == S_IFREG) ? \
-				(ip)->i_size : (ip)->i_d.di_size;
+static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
+{
+	if (S_ISREG(ip->i_d.di_mode))
+		return ip->i_size;
+	return ip->i_d.di_size;
+}
 
 /* Convert from vfs inode to xfs inode */
 static inline struct xfs_inode *XFS_I(struct inode *inode)

---
 fs/xfs/xfs_iomap.c |    9 +++++++++
 1 file changed, 9 insertions(+)
Index: b/fs/xfs/xfs_iomap.c
===================================================================
@@ -417,6 +417,15 @@ 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;
 	firstblock = NULLFSBLOCK;
 	error = xfs_bmapi(NULL, ip, offset_fsb,

---
 fs/xfs/linux-2.6/xfs_aops.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1187,7 +1187,7 @@ __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

     samples  pcnt function                    DSO
     _______ _____ ___________________________ _________________

     8111.00  9.1% _xfs_buf_find               [kernel.kallsyms]
     4380.00  4.9% __memcpy                    [kernel.kallsyms]
     4341.00  4.8% __ticket_spin_lock          [kernel.kallsyms]
     3401.00  3.8% kmem_cache_alloc            [kernel.kallsyms]
     2856.00  3.2% xfs_log_commit_cil          [kernel.kallsyms]
     2625.00  2.9% __kmalloc                   [kernel.kallsyms]
     2380.00  2.7% kfree                       [kernel.kallsyms]
     2016.00  2.3% kmem_cache_free             [kernel.kallsyms]
---
 fs/xfs/linux-2.6/xfs_buf.c |   48 ++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 20 deletions(-)
index 5e68099..6a2ab95 100644
@@ -481,8 +481,6 @@ _xfs_buf_find(
 
 	/* No match found */
 	if (new_bp) {
-		_xfs_buf_initialize(new_bp, btp, range_base,
-				range_length, flags);
 		rb_link_node(&new_bp->b_rbnode, parent, rbp);
 		rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree);
 		/* the buffer keeps the perag reference until it is freed */

@@ -527,35 +525,53 @@ found:
 }
 
 /*
- *	Assembles a buffer covering the specified range.
- *	Storage in memory for all portions of the buffer will be allocated,
- *	although backing storage may not be.
+ * Assembles a buffer covering the specified range. The code is optimised for
+ * cache hits, as metadata intensive workloads will see 3 orders of magnitude
+ * more hits than misses.
  */
-xfs_buf_t *
+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_buf_flags_t		flags)
 {
-	xfs_buf_t		*bp, *new_bp;
+	struct xfs_buf		*bp;
+	struct xfs_buf		*new_bp;
 	int			error = 0;
 
+	bp = _xfs_buf_find(target, ioff, isize, flags, NULL);
+	if (likely(bp))
+		goto found;
+
 	new_bp = xfs_buf_allocate(flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
+	_xfs_buf_initialize(new_bp, target,
+			    ioff << BBSHIFT, isize << BBSHIFT, flags);
+
 	bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
+	if (!bp) {
+		xfs_buf_deallocate(new_bp);
+		return NULL;
+	}
+
 	if (bp == new_bp) {
 		error = xfs_buf_allocate_memory(bp, flags);
 		if (error)
 			goto no_buffer;
-	} else {
+	} else
 		xfs_buf_deallocate(new_bp);
-		if (unlikely(bp == NULL))
-			return NULL;
-	}
 
+	/*
+	 * 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;
+
+found:
 	if (!(bp->b_flags & XBF_MAPPED)) {
 		error = _xfs_buf_map_pages(bp, flags);
 		if (unlikely(error)) {

@@ -566,18 +582,10 @@ xfs_buf_get(
 	}
 
 	XFS_STATS_INC(xb_get);
-
-	/*
-	 * Always fill in the block number now, the mapped cases can do
-	 * their own overlay of this later.
-	 */
-	bp->b_bn = ioff;
-	bp->b_count_desired = bp->b_buffer_length;
-
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
 
- no_buffer:
+no_buffer:
 	if (flags & (XBF_LOCK | XBF_TRYLOCK))
 		xfs_buf_unlock(bp);
 	xfs_buf_rele(bp);

---
 fs/xfs/linux-2.6/xfs_buf.c |   50 ++++++++++++++++-----------------------------
 fs/xfs/linux-2.6/xfs_buf.h |    3 +-
 fs/xfs/xfs_log.c           |    2 -
 3 files changed, 21 insertions(+), 34 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_buf.c
===================================================================
@@ -66,10 +66,6 @@ struct workqueue_struct *xfsconvertd_wor
 #define xb_to_km(flags) \
 	 (((flags) & XBF_DONT_BLOCK) ? KM_NOFS : KM_SLEEP)
 
-#define xfs_buf_allocate(flags) \
-	kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags))
-#define xfs_buf_deallocate(bp) \
-	kmem_zone_free(xfs_buf_zone, (bp));
 
 static inline int
 xfs_buf_is_vmapped(

@@ -167,14 +163,19 @@ xfs_buf_stale(
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
 }
 
-STATIC void
-_xfs_buf_initialize(
-	xfs_buf_t		*bp,
-	xfs_buftarg_t		*target,
+struct xfs_buf *
+xfs_buf_alloc(
+	struct xfs_buftarg	*target,
 	xfs_off_t		range_base,
 	size_t			range_length,
 	xfs_buf_flags_t		flags)
 {
+	struct xfs_buf		*bp;
+
+	bp = kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags));
+	if (unlikely(!bp))
+		return NULL;
+
 	/*
 	 * We don't want certain flags to appear in b_flags.
 	 */

@@ -203,8 +204,9 @@ _xfs_buf_initialize(
 	init_waitqueue_head(&bp->b_waiters);
 
 	XFS_STATS_INC(xb_create);
-
 	trace_xfs_buf_init(bp, _RET_IP_);
+
+	return bp;
 }
 
 /*

@@ -277,7 +279,7 @@ xfs_buf_free(
 	} else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
 	_xfs_buf_free_pages(bp);
-	xfs_buf_deallocate(bp);
+	kmem_zone_free(xfs_buf_zone, bp);
 }
 
 /*

@@ -544,16 +546,14 @@ xfs_buf_get(
 	if (likely(bp))
 		goto found;
 
-	new_bp = xfs_buf_allocate(flags);
+	new_bp = xfs_buf_alloc(target, ioff << BBSHIFT, isize << BBSHIFT,
+			       flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
-	_xfs_buf_initialize(new_bp, target,
-			    ioff << BBSHIFT, isize << BBSHIFT, flags);
-
 	bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
 	if (!bp) {
-		xfs_buf_deallocate(new_bp);
+		kmem_zone_free(xfs_buf_zone, new_bp);
 		return NULL;
 	}
 

@@ -562,7 +562,7 @@ xfs_buf_get(
 		if (error)
 			goto no_buffer;
 	} else
-		xfs_buf_deallocate(new_bp);
+		kmem_zone_free(xfs_buf_zone, new_bp);
 
 	/*
 	 * Now we have a workable buffer, fill in the block number so

@@ -703,19 +703,6 @@ xfs_buf_read_uncached(
 	return bp;
 }
 
-xfs_buf_t *
-xfs_buf_get_empty(
-	size_t			len,
-	xfs_buftarg_t		*target)
-{
-	xfs_buf_t		*bp;
-
-	bp = xfs_buf_allocate(0);
-	if (bp)
-		_xfs_buf_initialize(bp, target, 0, len, 0);
-	return bp;
-}
-
 /*
  * Return a buffer allocated as an empty buffer and associated to external
  * memory via xfs_buf_associate_memory() back to it's empty state.

@@ -801,10 +788,9 @@ xfs_buf_get_uncached(
 	int			error, i;
 	xfs_buf_t		*bp;
 
-	bp = xfs_buf_allocate(0);
+	bp = xfs_buf_alloc(target, 0, len, 0);
 	if (unlikely(bp == NULL))
 		goto fail;
-	_xfs_buf_initialize(bp, target, 0, len, 0);
 
 	error = _xfs_buf_get_pages(bp, page_count, 0);
 	if (error)

@@ -834,7 +820,7 @@ xfs_buf_get_uncached(
 		__free_page(bp->b_pages[i]);
 	_xfs_buf_free_pages(bp);
  fail_free_buf:
-	xfs_buf_deallocate(bp);
+	kmem_zone_free(xfs_buf_zone, bp);
  fail:
 	return NULL;
 }

Index: b/fs/xfs/linux-2.6/xfs_buf.h
===================================================================
@@ -177,7 +177,8 @@ extern xfs_buf_t *xfs_buf_get(xfs_buftar
 extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
 				xfs_buf_flags_t);
 
-extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_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);

Index: b/fs/xfs/xfs_log.c
===================================================================
@@ -1054,7 +1054,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	xlog_get_iclog_buffer_size(mp, log);
 
 	error = ENOMEM;
-	bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp);
+	bp = xfs_buf_alloc(mp->m_logdev_targp, 0, log->l_iclog_size, 0);
 	if (!bp)
 		goto out_free_log;
 	XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone);

---
 fs/xfs/linux-2.6/xfs_buf.c |   16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_buf.c
===================================================================
@@ -551,18 +551,20 @@ xfs_buf_get(
 	if (unlikely(!new_bp))
 		return NULL;
 
+	error = xfs_buf_allocate_memory(new_bp, flags);
+	if (error) {
+		kmem_zone_free(xfs_buf_zone, new_bp);
+		return NULL;
+	}
+
 	bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
 	if (!bp) {
-		kmem_zone_free(xfs_buf_zone, new_bp);
+		xfs_buf_free(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);
+	if (bp != new_bp)
+		xfs_buf_free(new_bp);
 
 	/*
 	 * Now we have a workable buffer, fill in the block number so

---
 fs/xfs/xfs_vnodeops.c |   21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)
Index: b/fs/xfs/xfs_vnodeops.c
===================================================================
@@ -2781,17 +2781,32 @@ 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(ip, &iattr, attr_flags);
+		error = xfs_setattr(ip, &iattr, attr_flags | XFS_ATTR_NOLOCK);
+		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
 		if (error)
 			return error;

---
 fs/xfs/linux-2.6/xfs_buf.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_buf.c
===================================================================
@@ -177,9 +177,11 @@ xfs_buf_alloc(
 		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_LOCK | XBF_MAPPED | XBF_DONT_BLOCK |
+		   XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
 
 	memset(bp, 0, sizeof(xfs_buf_t));
 	atomic_set(&bp->b_hold, 1);

---
 fs/xfs/xfs_mount.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
index 2f011fd..beb9968 100644
@@ -1297,7 +1297,7 @@ 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;
 	}
 
 	/*

@@ -1324,7 +1324,7 @@ 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;
 	}
 
 	/*

@@ -1448,6 +1448,10 @@ 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:

    [exception RIP: xlog_get_lowest_lsn+0x30]
    RIP: ffffffffa04a9910  RSP: ffff88016fdffd10  RFLAGS: 00010246
    RAX: ffffc90014e48000  RBX: ffff88014d879980  RCX: ffff88014d879980
    RDX: ffff8802214ee4c0  RSI: 0000000000000000  RDI: 0000000000000000
    RBP: ffff88016fdffd10   R8: ffff88014d879a80   R9: 0000000000000000
    R10: 0000000000000001  R11: 0000000000000000  R12: ffff8802214ee400
    R13: ffff88014d879980  R14: 0000000000000000  R15: ffff88022fd96605
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
---
 fs/xfs/linux-2.6/xfs_sync.c |   29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_sync.c
===================================================================
@@ -506,21 +506,24 @@ xfs_sync_worker(
 	 * 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. hence use the MS_ACTIVE flag to avoid doing
-	 * anything in these periods.
+	 * during these times.  Use the s_umount semaphore to provide exclusion
+	 * with unmount.
 	 */
-	if (!(mp->m_super->s_flags & MS_ACTIVE) &&
-	    !(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);
-		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
+	if (down_read_trylock(&mp->m_super->s_umount)) {
+		if (!(mp->m_super->s_flags & MS_ACTIVE) &&
+		    !(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);
+			error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 
-		/* start pushing all the metadata that is currently dirty */
-		xfs_ail_push_all(mp->m_ail);
+			/* 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 */

---
 fs/xfs/xfs_iget.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
Index: b/fs/xfs/xfs_iget.c
===================================================================
@@ -340,9 +340,10 @@ 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;
 	}

buffer  content
0       empty  b_state = 0
1       DATA   b_state = 0x1023 Uptodate,Dirty,Mapped,Unwritten
2       DATA   b_state = 0x1023 Uptodate,Dirty,Mapped,Unwritten
3       empty  b_state = 0
4       empty  b_state = 0
5       DATA   b_state = 0x1023 Uptodate,Dirty,Mapped,Unwritten
6       DATA   b_state = 0x1023 Uptodate,Dirty,Mapped,Unwritten
7       empty  b_state = 0
---
 fs/xfs/linux-2.6/xfs_aops.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1008,10 +1008,15 @@ xfs_vm_writepage(
 				imap_valid = 0;
 			}
 		} else {
-			if (PageUptodate(page)) {
+			if (PageUptodate(page))
 				ASSERT(buffer_mapped(bh));
-				imap_valid = 0;
-			}
+			/*
+			 * This buffer is not uptodate and will not be
+			 * written to disk.  Ensure that we will put any
+			 * subsequent writeable buffers into a new
+			 * ioend.
+			 */
+			imap_valid = 0;
 			continue;
 		}
 

---
 fs/xfs/xfs_alloc.c |    1 +
 1 file changed, 1 insertion(+)
Index: b/fs/xfs/xfs_alloc.c
===================================================================
@@ -1086,6 +1086,7 @@ restart:
 			goto restart;
 		}
 
+		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 		trace_xfs_alloc_size_neither(args);
 		args->agbno = NULLAGBLOCK;
 		return 0;

---
 fs/xfs/linux-2.6/xfs_sync.c |   31 +++++++++++++++----------------
 fs/xfs/xfs_log.c            |    1 +
 2 files changed, 16 insertions(+), 16 deletions(-)
Index: b/fs/xfs/linux-2.6/xfs_sync.c
===================================================================
@@ -506,24 +506,23 @@ xfs_sync_worker(
 	 * 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.
+	 * during these times.  Use the MS_ACTIVE flag to avoid doing anything
+	 * during mount.  Doing work during unmount is avoided by calling
+	 * cancel_delayed_work_sync on this work queue before tearing down
+	 * the ail and the log in xfs_log_unmount.
 	 */
-	if (down_read_trylock(&mp->m_super->s_umount)) {
-		if (!(mp->m_super->s_flags & MS_ACTIVE) &&
-		    !(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);
-			error = xfs_qm_sync(mp, SYNC_TRYLOCK);
+	if (!(mp->m_super->s_flags & MS_ACTIVE) &&
+	    !(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);
+		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 
-			/* start pushing all the metadata that is currently dirty */
-			xfs_ail_push_all(mp->m_ail);
-		}
-		up_read(&mp->m_super->s_umount);
+		/* start pushing all the metadata that is currently dirty */
+		xfs_ail_push_all(mp->m_ail);
 	}
 
 	/* queue us up again */

Index: b/fs/xfs/xfs_log.c
===================================================================
@@ -618,6 +618,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 void
 xfs_log_unmount(xfs_mount_t *mp)
 {
+	cancel_delayed_work_sync(&mp->m_sync_work);
 	xfs_trans_ail_destroy(mp);
 	xlog_dealloc_log(mp->m_log);
 }

---
 fs/xfs/xfs_alloc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
Index: b/fs/xfs/xfs_alloc.c
===================================================================
@@ -1080,13 +1080,13 @@ restart:
 	 * If we couldn't get anything, give up.
 	 */
 	if (bno_cur_lt == NULL && bno_cur_gt == NULL) {
+		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+
 		if (!forced++) {
 			trace_xfs_alloc_near_busy(args);
 			xfs_log_force(args->mp, XFS_LOG_SYNC);
 			goto restart;
 		}
-
-		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 		trace_xfs_alloc_size_neither(args);
 		args->agbno = NULLAGBLOCK;
 		return 0;

---
 fs/xfs/xfs_inode_item.c |   26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)
Index: b/fs/xfs/xfs_inode_item.c
===================================================================
@@ -588,6 +588,21 @@ 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) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return XFS_ITEM_PINNED;
+	}
+
+	/* Stale items should force out the iclog */
+	if (ip->i_flags & XFS_ISTALE) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return XFS_ITEM_PINNED;
+	}
+
 	if (!xfs_iflock_nowait(ip)) {
 		/*
 		 * inode has already been flushed to the backing buffer,

@@ -597,17 +612,6 @@ xfs_inode_item_trylock(
 		return XFS_ITEM_PUSHBUF;
 	}
 
-	/* Stale items should force out the iclog */
-	if (ip->i_flags & XFS_ISTALE) {
-		xfs_ifunlock(ip);
-		/*
-		 * we hold the AIL lock - notify the unlock routine of this
-		 * so it doesn't try to get the lock again.
-		 */
-		xfs_iunlock(ip, XFS_ILOCK_SHARED|XFS_IUNLOCK_NONOTIFY);
-		return XFS_ITEM_PINNED;
-	}
-
 #ifdef DEBUG
 	if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		ASSERT(iip->ili_format.ilf_fields != 0);

    xfs: stop the sync worker before xfs_unmountfs

    
    Cancel work of the xfs_sync_worker before teardown of the log in
    xfs_unmountfs.  This prevents occasional crashes on unmount like so:
    
    PID: 21602  TASK: ee9df060  CPU: 0   COMMAND: "kworker/0:3"
     #0 [c5377d28] crash_kexec at c0292c94
     #1 [c5377d80] oops_end at c07090c2
     #2 [c5377d98] no_context at c06f614e
     #3 [c5377dbc] __bad_area_nosemaphore at c06f6281
     #4 [c5377df4] bad_area_nosemaphore at c06f629b
     #5 [c5377e00] do_page_fault at c070b0cb
     #6 [c5377e7c] error_code (via page_fault) at c070892c
        EAX: f300c6a8  EBX: f300c6a8  ECX: 000000c0  EDX: 000000c0  EBP: c5377ed0
        DS:  007b      ESI: 00000000  ES:  007b      EDI: 00000001  GS:  ffffad20
        CS:  0060      EIP: c0481ad0  ERR: ffffffff  EFLAGS: 00010246
     #7 [c5377eb0] atomic64_read_cx8 at c0481ad0
     #8 [c5377ebc] xlog_assign_tail_lsn_locked at f7cc7c6e [xfs]
     #9 [c5377ed4] xfs_trans_ail_delete_bulk at f7ccd520 [xfs]
    #10 [c5377f0c] xfs_buf_iodone at f7ccb602 [xfs]
    #11 [c5377f24] xfs_buf_do_callbacks at f7cca524 [xfs]
    #12 [c5377f30] xfs_buf_iodone_callbacks at f7cca5da [xfs]
    #13 [c5377f4c] xfs_buf_iodone_work at f7c718d0 [xfs]
    #14 [c5377f58] process_one_work at c024ee4c
    #15 [c5377f98] worker_thread at c024f43d
    #16 [c5377fbc] kthread at c025326b
    #17 [c5377fe8] kernel_thread_helper at c070e834
    
    PID: 26653  TASK: e79143b0  CPU: 3   COMMAND: "umount"
     #0 [cde0fda0] __schedule at c0706595
     #1 [cde0fe28] schedule at c0706b89
     #2 [cde0fe30] schedule_timeout at c0705600
     #3 [cde0fe94] __down_common at c0706098
     #4 [cde0fec8] __down at c0706122
     #5 [cde0fed0] down at c025936f
     #6 [cde0fee0] xfs_buf_lock at f7c7131d [xfs]
     #7 [cde0ff00] xfs_freesb at f7cc2236 [xfs]
     #8 [cde0ff10] xfs_fs_put_super at f7c80f21 [xfs]
     #9 [cde0ff1c] generic_shutdown_super at c0333d7a
    #10 [cde0ff38] kill_block_super at c0333e0f
    #11 [cde0ff48] deactivate_locked_super at c0334218
    #12 [cde0ff58] deactivate_super at c033495d
    #13 [cde0ff68] mntput_no_expire at c034bc13
    #14 [cde0ff7c] sys_umount at c034cc69
    #15 [cde0ffa0] sys_oldumount at c034ccd4
    #16 [cde0ffb0] system_call at c0707e66
    
    commit 11159a05 added this to xfs_log_unmount and needs to be cleaned up
    at a later date.
    
    Signed-off-by: Ben Myers <[email protected]>
    Reviewed-by: Dave Chinner <[email protected]>
    Reviewed-by: Mark Tinguely <[email protected]>
---
 fs/xfs/linux-2.6/xfs_super.c |    1 +
 1 file changed, 1 insertion(+)
Index: b/fs/xfs/linux-2.6/xfs_super.c
===================================================================
@@ -1004,6 +1004,7 @@ xfs_fs_put_super(
 
 	XFS_bflush(mp->m_ddev_targp);
 
+	cancel_delayed_work_sync(&mp->m_sync_work);
 	xfs_unmountfs(mp);
 	xfs_syncd_stop(mp);
 	xfs_freesb(mp);

---
 fs/xfs/xfs_alloc.c  |    1 +
 fs/xfs/xfs_bmap.c   |    3 +++
 fs/xfs/xfs_ialloc.c |    1 +
 3 files changed, 5 insertions(+)
Index: b/fs/xfs/xfs_alloc.c
===================================================================
@@ -1872,6 +1872,7 @@ xfs_alloc_fix_freelist(
 	/*
 	 * Initialize the args structure.
 	 */
+	memset(&targs, 0, sizeof(targs));
 	targs.tp = tp;
 	targs.mp = mp;
 	targs.agbp = agbp;

Index: b/fs/xfs/xfs_bmap.c
===================================================================
@@ -2561,6 +2561,7 @@ xfs_bmap_btalloc(
 	 * Normal allocation, done through xfs_alloc_vextent.
 	 */
 	tryagain = isaligned = 0;
+	memset(&args, 0, sizeof(args));
 	args.tp = ap->tp;
 	args.mp = mp;
 	args.fsbno = ap->rval;

@@ -3194,6 +3195,7 @@ xfs_bmap_extents_to_btree(
 	 * Convert to a btree with two levels, one record in root.
 	 */
 	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
+	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = mp;
 	args.firstblock = *firstblock;

@@ -3355,6 +3357,7 @@ xfs_bmap_local_to_extents(
 		xfs_buf_t	*bp;	/* buffer for extent block */
 		xfs_bmbt_rec_host_t *ep;/* extent record pointer */
 
+		memset(&args, 0, sizeof(args));
 		args.tp = tp;
 		args.mp = ip->i_mount;
 		args.firstblock = *firstblock;

Index: b/fs/xfs/xfs_ialloc.c
===================================================================
@@ -251,6 +251,7 @@ xfs_ialloc_ag_alloc(
 					/* boundary */
 	struct xfs_perag *pag;
 
+	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = tp->t_mountp;
 

---
 fs/xfs/xfs_log.c |   19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)
Index: b/fs/xfs/xfs_log.c
===================================================================
@@ -2216,14 +2216,27 @@ xlog_state_do_callback(
 
 
 				/*
-				 * update the last_sync_lsn before we drop the
+				 * Completion of a iclog IO does not imply that
+				 * a transaction has completed, as transactions
+				 * can be large enough to span many iclogs. We
+				 * cannot change the tail of the log half way
+				 * through a transaction as this may be the only
+				 * transaction in the log and moving th etail to
+				 * point to the middle of it will prevent
+				 * recovery from finding the start of the
+				 * transaction. Hence we should only update the
+				 * last_sync_lsn if this iclog contains
+				 * transaction completion callbacks on it.
+				 *
+				 * We have to do this before we drop the
 				 * icloglock to ensure we are the only one that
 				 * can update it.
 				 */
 				ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn),
 					be64_to_cpu(iclog->ic_header.h_lsn)) <= 0);
-				atomic64_set(&log->l_last_sync_lsn,
-					be64_to_cpu(iclog->ic_header.h_lsn));
+				if (iclog->ic_callback)
+					atomic64_set(&log->l_last_sync_lsn,
+						be64_to_cpu(iclog->ic_header.h_lsn));
 
 			} else
 				ioerrors++;

	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00002.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00167.html
	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00002.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00167.html
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
	http://oss.sgi.com/archives/xfs/2012-08/msg00255.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00002.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00167.html
	http://oss.sgi.com/archives/xfs/2012-09/msg00002.html
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs