Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:
	drivers/scsi/fcoe/fcoe.c

18 files changed, 299 insertions, 274 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index c13f67300fe..7ec89fc05b2 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -153,23 +153,6 @@ xfs_find_bdev_for_inode(
 }
 
 /*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
-	xfs_ioend_t	*ioend,
-	int		wait)
-{
-	if (atomic_dec_and_test(&ioend->io_remaining)) {
-		queue_work(xfsdatad_workqueue, &ioend->io_work);
-		if (wait)
-			flush_workqueue(xfsdatad_workqueue);
-	}
-}
-
-/*
  * We're now finished for good with this ioend structure.
  * Update the page state via the associated buffer_heads,
  * release holds on the inode and bio, and finally free
@@ -310,6 +293,27 @@ xfs_end_bio_read(
 }
 
 /*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+	xfs_ioend_t	*ioend,
+	int		wait)
+{
+	if (atomic_dec_and_test(&ioend->io_remaining)) {
+		struct workqueue_struct *wq = xfsdatad_workqueue;
+		if (ioend->io_work.func == xfs_end_bio_unwritten)
+			wq = xfsconvertd_workqueue;
+
+		queue_work(wq, &ioend->io_work);
+		if (wait)
+			flush_workqueue(wq);
+	}
+}
+
+/*
  * Allocate and initialise an IO completion structure.
  * We need to track unwritten extent write completion here initially.
  * We'll need to extend this for updating the ondisk inode size later
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 1dd52884975..221b3e66cee 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -19,6 +19,7 @@
 #define __XFS_AOPS_H__
 
 extern struct workqueue_struct *xfsdatad_workqueue;
+extern struct workqueue_struct *xfsconvertd_workqueue;
 extern mempool_t *xfs_ioend_pool;
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index aa1016bb913..e28800a9f2b 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -51,6 +51,7 @@ static struct shrinker xfs_buf_shake = {
 
 static struct workqueue_struct *xfslogd_workqueue;
 struct workqueue_struct *xfsdatad_workqueue;
+struct workqueue_struct *xfsconvertd_workqueue;
 
 #ifdef XFS_BUF_TRACE
 void
@@ -1775,6 +1776,7 @@ xfs_flush_buftarg(
 	xfs_buf_t	*bp, *n;
 	int		pincount = 0;
 
+	xfs_buf_runall_queues(xfsconvertd_workqueue);
 	xfs_buf_runall_queues(xfsdatad_workqueue);
 	xfs_buf_runall_queues(xfslogd_workqueue);
 
@@ -1831,9 +1833,15 @@ xfs_buf_init(void)
 	if (!xfsdatad_workqueue)
 		goto out_destroy_xfslogd_workqueue;
 
+	xfsconvertd_workqueue = create_workqueue("xfsconvertd");
+	if (!xfsconvertd_workqueue)
+		goto out_destroy_xfsdatad_workqueue;
+
 	register_shrinker(&xfs_buf_shake);
 	return 0;
 
+ out_destroy_xfsdatad_workqueue:
+	destroy_workqueue(xfsdatad_workqueue);
  out_destroy_xfslogd_workqueue:
 	destroy_workqueue(xfslogd_workqueue);
  out_free_buf_zone:
@@ -1849,6 +1857,7 @@ void
 xfs_buf_terminate(void)
 {
 	unregister_shrinker(&xfs_buf_shake);
+	destroy_workqueue(xfsconvertd_workqueue);
 	destroy_workqueue(xfsdatad_workqueue);
 	destroy_workqueue(xfslogd_workqueue);
 	kmem_zone_destroy(xfs_buf_zone);
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index 5aeb7777696..08be36d7326 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -74,14 +74,14 @@ xfs_flush_pages(
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 		xfs_iflags_clear(ip, XFS_ITRUNCATED);
-		ret = filemap_fdatawrite(mapping);
-		if (flags & XFS_B_ASYNC)
-			return -ret;
-		ret2 = filemap_fdatawait(mapping);
-		if (!ret)
-			ret = ret2;
+		ret = -filemap_fdatawrite(mapping);
 	}
-	return -ret;
+	if (flags & XFS_B_ASYNC)
+		return ret;
+	ret2 = xfs_wait_on_pages(ip, first, last);
+	if (!ret)
+		ret = ret2;
+	return ret;
 }
 
 int
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index d0b499418a7..34eaab608e6 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -489,17 +489,12 @@ xfs_attrmulti_attr_set(
 	if (len > XATTR_SIZE_MAX)
 		return EINVAL;
 
-	kbuf = kmalloc(len, GFP_KERNEL);
-	if (!kbuf)
-		return ENOMEM;
-
-	if (copy_from_user(kbuf, ubuf, len))
-		goto out_kfree;
+	kbuf = memdup_user(ubuf, len);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
 
- out_kfree:
-	kfree(kbuf);
 	return error;
 }
 
@@ -540,20 +535,16 @@ xfs_attrmulti_by_handle(
 	if (!size || size > 16 * PAGE_SIZE)
 		goto out_dput;
 
-	error = ENOMEM;
-	ops = kmalloc(size, GFP_KERNEL);
-	if (!ops)
+	ops = memdup_user(am_hreq.ops, size);
+	if (IS_ERR(ops)) {
+		error = PTR_ERR(ops);
 		goto out_dput;
-
-	error = EFAULT;
-	if (copy_from_user(ops, am_hreq.ops, size))
-		goto out_kfree_ops;
+	}
 
 	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
 	if (!attr_name)
 		goto out_kfree_ops;
 
-
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
 		ops[i].am_error = strncpy_from_user(attr_name,
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index c70c4e3db79..0882d166239 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -427,20 +427,16 @@ xfs_compat_attrmulti_by_handle(
 	if (!size || size > 16 * PAGE_SIZE)
 		goto out_dput;
 
-	error = ENOMEM;
-	ops = kmalloc(size, GFP_KERNEL);
-	if (!ops)
+	ops = memdup_user(compat_ptr(am_hreq.ops), size);
+	if (IS_ERR(ops)) {
+		error = PTR_ERR(ops);
 		goto out_dput;
-
-	error = EFAULT;
-	if (copy_from_user(ops, compat_ptr(am_hreq.ops), size))
-		goto out_kfree_ops;
+	}
 
 	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
 	if (!attr_name)
 		goto out_kfree_ops;
 
-
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
 		ops[i].am_error = strncpy_from_user(attr_name,
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 7e90daa0d1d..9142192ccbe 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -751,10 +751,26 @@ start:
 			goto relock;
 		}
 	} else {
+		int enospc = 0;
+		ssize_t ret2 = 0;
+
+write_retry:
 		xfs_rw_enter_trace(XFS_WRITE_ENTER, xip, (void *)iovp, segs,
 				*offset, ioflags);
-		ret = generic_file_buffered_write(iocb, iovp, segs,
+		ret2 = generic_file_buffered_write(iocb, iovp, segs,
 				pos, offset, count, ret);
+		/*
+		 * if we just got an ENOSPC, flush the inode now we
+		 * aren't holding any page locks and retry *once*
+		 */
+		if (ret2 == -ENOSPC && !enospc) {
+			error = xfs_flush_pages(xip, 0, -1, 0, FI_NONE);
+			if (error)
+				goto out_unlock_internal;
+			enospc = 1;
+			goto write_retry;
+		}
+		ret = ret2;
 	}
 
 	current->backing_dev_info = NULL;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index a608e72fa40..f7ba76633c2 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -62,12 +62,6 @@ xfs_sync_inodes_ag(
 	uint32_t	first_index = 0;
 	int		error = 0;
 	int		last_error = 0;
-	int		fflag = XFS_B_ASYNC;
-
-	if (flags & SYNC_DELWRI)
-		fflag = XFS_B_DELWRI;
-	if (flags & SYNC_WAIT)
-		fflag = 0;		/* synchronous overrides all */
 
 	do {
 		struct inode	*inode;
@@ -128,11 +122,23 @@ xfs_sync_inodes_ag(
 		 * If we have to flush data or wait for I/O completion
 		 * we need to hold the iolock.
 		 */
-		if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
-			xfs_ilock(ip, XFS_IOLOCK_SHARED);
-			lock_flags |= XFS_IOLOCK_SHARED;
-			error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
-			if (flags & SYNC_IOWAIT)
+		if (flags & SYNC_DELWRI) {
+			if (VN_DIRTY(inode)) {
+				if (flags & SYNC_TRYLOCK) {
+					if (xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+						lock_flags |= XFS_IOLOCK_SHARED;
+				} else {
+					xfs_ilock(ip, XFS_IOLOCK_SHARED);
+					lock_flags |= XFS_IOLOCK_SHARED;
+				}
+				if (lock_flags & XFS_IOLOCK_SHARED) {
+					error = xfs_flush_pages(ip, 0, -1,
+							(flags & SYNC_WAIT) ? 0
+								: XFS_B_ASYNC,
+							FI_NONE);
+				}
+			}
+			if (VN_CACHED(inode) && (flags & SYNC_IOWAIT))
 				xfs_ioend_wait(ip);
 		}
 		xfs_ilock(ip, XFS_ILOCK_SHARED);
@@ -398,15 +404,17 @@ STATIC void
 xfs_syncd_queue_work(
 	struct xfs_mount *mp,
 	void		*data,
-	void		(*syncer)(struct xfs_mount *, void *))
+	void		(*syncer)(struct xfs_mount *, void *),
+	struct completion *completion)
 {
-	struct bhv_vfs_sync_work *work;
+	struct xfs_sync_work *work;
 
-	work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
+	work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP);
 	INIT_LIST_HEAD(&work->w_list);
 	work->w_syncer = syncer;
 	work->w_data = data;
 	work->w_mount = mp;
+	work->w_completion = completion;
 	spin_lock(&mp->m_sync_lock);
 	list_add_tail(&work->w_list, &mp->m_sync_list);
 	spin_unlock(&mp->m_sync_lock);
@@ -420,49 +428,26 @@ xfs_syncd_queue_work(
  * heads, looking about for more room...
  */
 STATIC void
-xfs_flush_inode_work(
-	struct xfs_mount *mp,
-	void		*arg)
-{
-	struct inode	*inode = arg;
-	filemap_flush(inode->i_mapping);
-	iput(inode);
-}
-
-void
-xfs_flush_inode(
-	xfs_inode_t	*ip)
-{
-	struct inode	*inode = VFS_I(ip);
-
-	igrab(inode);
-	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
-	delay(msecs_to_jiffies(500));
-}
-
-/*
- * This is the "bigger hammer" version of xfs_flush_inode_work...
- * (IOW, "If at first you don't succeed, use a Bigger Hammer").
- */
-STATIC void
-xfs_flush_device_work(
+xfs_flush_inodes_work(
 	struct xfs_mount *mp,
 	void		*arg)
 {
 	struct inode	*inode = arg;
-	sync_blockdev(mp->m_super->s_bdev);
+	xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK);
+	xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK | SYNC_IOWAIT);
 	iput(inode);
 }
 
 void
-xfs_flush_device(
+xfs_flush_inodes(
 	xfs_inode_t	*ip)
 {
 	struct inode	*inode = VFS_I(ip);
+	DECLARE_COMPLETION_ONSTACK(completion);
 
 	igrab(inode);
-	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
-	delay(msecs_to_jiffies(500));
+	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
+	wait_for_completion(&completion);
 	xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
 }
 
@@ -497,7 +482,7 @@ xfssyncd(
 {
 	struct xfs_mount	*mp = arg;
 	long			timeleft;
-	bhv_vfs_sync_work_t	*work, *n;
+	xfs_sync_work_t		*work, *n;
 	LIST_HEAD		(tmp);
 
 	set_freezable();
@@ -532,6 +517,8 @@ xfssyncd(
 			list_del(&work->w_list);
 			if (work == &mp->m_sync_work)
 				continue;
+			if (work->w_completion)
+				complete(work->w_completion);
 			kmem_free(work);
 		}
 	}
@@ -545,6 +532,7 @@ xfs_syncd_init(
 {
 	mp->m_sync_work.w_syncer = xfs_sync_worker;
 	mp->m_sync_work.w_mount = mp;
+	mp->m_sync_work.w_completion = NULL;
 	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
 	if (IS_ERR(mp->m_sync_task))
 		return -PTR_ERR(mp->m_sync_task);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 04f058c848a..308d5bf6dfb 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -21,18 +21,20 @@
 struct xfs_mount;
 struct xfs_perag;
 
-typedef struct bhv_vfs_sync_work {
+typedef struct xfs_sync_work {
 	struct list_head	w_list;
 	struct xfs_mount	*w_mount;
 	void			*w_data;	/* syncer routine argument */
 	void			(*w_syncer)(struct xfs_mount *, void *);
-} bhv_vfs_sync_work_t;
+	struct completion	*w_completion;
+} xfs_sync_work_t;
 
 #define SYNC_ATTR		0x0001	/* sync attributes */
 #define SYNC_DELWRI		0x0002	/* look at delayed writes */
 #define SYNC_WAIT		0x0004	/* wait for i/o to complete */
 #define SYNC_BDFLUSH		0x0008	/* BDFLUSH is calling -- don't block */
 #define SYNC_IOWAIT		0x0010  /* wait for all I/O to complete */
+#define SYNC_TRYLOCK		0x0020  /* only try to lock inodes */
 
 int xfs_syncd_init(struct xfs_mount *mp);
 void xfs_syncd_stop(struct xfs_mount *mp);
@@ -43,8 +45,7 @@ int xfs_sync_fsdata(struct xfs_mount *mp, int flags);
 int xfs_quiesce_data(struct xfs_mount *mp);
 void xfs_quiesce_attr(struct xfs_mount *mp);
 
-void xfs_flush_inode(struct xfs_inode *ip);
-void xfs_flush_device(struct xfs_inode *ip);
+void xfs_flush_inodes(struct xfs_inode *ip);
 
 int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
 int xfs_reclaim_inodes(struct xfs_mount *mp, int noblock, int mode);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3a6ed426327..ca7c6005a48 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5880,7 +5880,7 @@ xfs_getbmap(
 	void			*arg)		/* formatter arg */
 {
 	__int64_t		bmvend;		/* last block requested */
-	int			error;		/* return value */
+	int			error = 0;	/* return value */
 	__int64_t		fixlen;		/* length for -1 case */
 	int			i;		/* extent number */
 	int			lock;		/* lock state */
@@ -5890,39 +5890,18 @@ xfs_getbmap(
 	int			nexleft;	/* # of user extents left */
 	int			subnex;		/* # of bmapi's can do */
 	int			nmap;		/* number of map entries */
-	struct getbmapx		out;		/* output structure */
+	struct getbmapx		*out;		/* output structure */
 	int			whichfork;	/* data or attr fork */
 	int			prealloced;	/* this is a file with
 						 * preallocated data space */
 	int			iflags;		/* interface flags */
 	int			bmapi_flags;	/* flags for xfs_bmapi */
+	int			cur_ext = 0;
 
 	mp = ip->i_mount;
 	iflags = bmv->bmv_iflags;
-
 	whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
 
-	/*	If the BMV_IF_NO_DMAPI_READ interface bit specified, do not
-	 *	generate a DMAPI read event.  Otherwise, if the DM_EVENT_READ
-	 *	bit is set for the file, generate a read event in order
-	 *	that the DMAPI application may do its thing before we return
-	 *	the extents.  Usually this means restoring user file data to
-	 *	regions of the file that look like holes.
-	 *
-	 *	The "old behavior" (from XFS_IOC_GETBMAP) is to not specify
-	 *	BMV_IF_NO_DMAPI_READ so that read events are generated.
-	 *	If this were not true, callers of ioctl( XFS_IOC_GETBMAP )
-	 *	could misinterpret holes in a DMAPI file as true holes,
-	 *	when in fact they may represent offline user data.
-	 */
-	if ((iflags & BMV_IF_NO_DMAPI_READ) == 0 &&
-	    DM_EVENT_ENABLED(ip, DM_EVENT_READ) &&
-	    whichfork == XFS_DATA_FORK) {
-		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, 0, 0, 0, NULL);
-		if (error)
-			return XFS_ERROR(error);
-	}
-
 	if (whichfork == XFS_ATTR_FORK) {
 		if (XFS_IFORK_Q(ip)) {
 			if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
@@ -5936,11 +5915,37 @@ xfs_getbmap(
 					 ip->i_mount);
 			return XFS_ERROR(EFSCORRUPTED);
 		}
-	} else if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
-		   ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
-		   ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
-		return XFS_ERROR(EINVAL);
-	if (whichfork == XFS_DATA_FORK) {
+
+		prealloced = 0;
+		fixlen = 1LL << 32;
+	} else {
+		/*
+		 * If the BMV_IF_NO_DMAPI_READ interface bit specified, do
+		 * not generate a DMAPI read event.  Otherwise, if the
+		 * DM_EVENT_READ bit is set for the file, generate a read
+		 * event in order that the DMAPI application may do its thing
+		 * before we return the extents.  Usually this means restoring
+		 * user file data to regions of the file that look like holes.
+		 *
+		 * The "old behavior" (from XFS_IOC_GETBMAP) is to not specify
+		 * BMV_IF_NO_DMAPI_READ so that read events are generated.
+		 * If this were not true, callers of ioctl(XFS_IOC_GETBMAP)
+		 * could misinterpret holes in a DMAPI file as true holes,
+		 * when in fact they may represent offline user data.
+		 */
+		if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) &&
+		    !(iflags & BMV_IF_NO_DMAPI_READ)) {
+			error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip,
+					      0, 0, 0, NULL);
+			if (error)
+				return XFS_ERROR(error);
+		}
+
+		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
+		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
+		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+			return XFS_ERROR(EINVAL);
+
 		if (xfs_get_extsz_hint(ip) ||
 		    ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
 			prealloced = 1;
@@ -5949,42 +5954,41 @@ xfs_getbmap(
 			prealloced = 0;
 			fixlen = ip->i_size;
 		}
-	} else {
-		prealloced = 0;
-		fixlen = 1LL << 32;
 	}
 
 	if (bmv->bmv_length == -1) {
 		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
-		bmv->bmv_length = MAX( (__int64_t)(fixlen - bmv->bmv_offset),
-					(__int64_t)0);
-	} else if (bmv->bmv_length < 0)
-		return XFS_ERROR(EINVAL);
-	if (bmv->bmv_length == 0) {
+		bmv->bmv_length =
+			max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
+	} else if (bmv->bmv_length == 0) {
 		bmv->bmv_entries = 0;
 		return 0;
+	} else if (bmv->bmv_length < 0) {
+		return XFS_ERROR(EINVAL);
 	}
+
 	nex = bmv->bmv_count - 1;
 	if (nex <= 0)
 		return XFS_ERROR(EINVAL);
 	bmvend = bmv->bmv_offset + bmv->bmv_length;
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 
-	if (((iflags & BMV_IF_DELALLOC) == 0) &&
-	    (whichfork == XFS_DATA_FORK) &&
-	    (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size)) {
-		/* xfs_fsize_t last_byte = xfs_file_last_byte(ip); */
-		error = xfs_flush_pages(ip, (xfs_off_t)0,
-					       -1, 0, FI_REMAPF);
-		if (error) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-		return error;
+	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);
+
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
+		if (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size) {
+			error = xfs_flush_pages(ip, 0, -1, 0, FI_REMAPF);
+			if (error)
+				goto out_unlock_iolock;
 		}
-	}
 
-	ASSERT(whichfork == XFS_ATTR_FORK || (iflags & BMV_IF_DELALLOC) ||
-	       ip->i_delayed_blks == 0);
+		ASSERT(ip->i_delayed_blks == 0);
+	}
 
 	lock = xfs_ilock_map_shared(ip);
 
@@ -5995,23 +5999,25 @@ xfs_getbmap(
 	if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
 		nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
 
-	bmapi_flags = xfs_bmapi_aflag(whichfork) |
-			((iflags & BMV_IF_PREALLOC) ? 0 : XFS_BMAPI_IGSTATE);
+	bmapi_flags = xfs_bmapi_aflag(whichfork);
+	if (!(iflags & BMV_IF_PREALLOC))
+		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
 	/*
 	 * Allocate enough space to handle "subnex" maps at a time.
 	 */
+	error = ENOMEM;
 	subnex = 16;
-	map = kmem_alloc(subnex * sizeof(*map), KM_SLEEP);
+	map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL);
+	if (!map)
+		goto out_unlock_ilock;
 
 	bmv->bmv_entries = 0;
 
-	if ((XFS_IFORK_NEXTENTS(ip, whichfork) == 0)) {
-		if (((iflags & BMV_IF_DELALLOC) == 0) ||
-		    whichfork == XFS_ATTR_FORK) {
-			error = 0;
-			goto unlock_and_return;
-		}
+	if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
+	    (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
+		error = 0;
+		goto out_free_map;
 	}
 
 	nexleft = nex;
@@ -6023,53 +6029,61 @@ xfs_getbmap(
 				  bmapi_flags, NULL, 0, map, &nmap,
 				  NULL, NULL);
 		if (error)
-			goto unlock_and_return;
+			goto out_free_map;
 		ASSERT(nmap <= subnex);
 
 		for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
-			out.bmv_oflags = 0;
+			out[cur_ext].bmv_oflags = 0;
 			if (map[i].br_state == XFS_EXT_UNWRITTEN)
-				out.bmv_oflags |= BMV_OF_PREALLOC;
+				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
 			else if (map[i].br_startblock == DELAYSTARTBLOCK)
-				out.bmv_oflags |= BMV_OF_DELALLOC;
-			out.bmv_offset = XFS_FSB_TO_BB(mp, map[i].br_startoff);
-			out.bmv_length = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			out.bmv_unused1 = out.bmv_unused2 = 0;
+				out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
+			out[cur_ext].bmv_offset =
+				XFS_FSB_TO_BB(mp, map[i].br_startoff);
+			out[cur_ext].bmv_length =
+				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 &&
 			    whichfork == XFS_ATTR_FORK) {
 				/* came to the end of attribute fork */
-				out.bmv_oflags |= BMV_OF_LAST;
-				goto unlock_and_return;
-			} else {
-				int full = 0;	/* user array is full */
-
-				if (!xfs_getbmapx_fix_eof_hole(ip, &out,
-							prealloced, bmvend,
-							map[i].br_startblock)) {
-					goto unlock_and_return;
-				}
-
-				/* format results & advance arg */
-				error = formatter(&arg, &out, &full);
-				if (error || full)
-					goto unlock_and_return;
-				nexleft--;
-				bmv->bmv_offset =
-					out.bmv_offset + out.bmv_length;
-				bmv->bmv_length = MAX((__int64_t)0,
-					(__int64_t)(bmvend - bmv->bmv_offset));
-				bmv->bmv_entries++;
+				out[cur_ext].bmv_oflags |= BMV_OF_LAST;
+				goto out_free_map;
 			}
+
+			if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
+					prealloced, bmvend,
+					map[i].br_startblock))
+				goto out_free_map;
+
+			nexleft--;
+			bmv->bmv_offset =
+				out[cur_ext].bmv_offset +
+				out[cur_ext].bmv_length;
+			bmv->bmv_length =
+				max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
+			bmv->bmv_entries++;
+			cur_ext++;
 		}
 	} while (nmap && nexleft && bmv->bmv_length);
 
-unlock_and_return:
+ out_free_map:
+	kmem_free(map);
+ out_unlock_ilock:
 	xfs_iunlock_map_shared(ip, lock);
+ out_unlock_iolock:
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
-	kmem_free(map);
+	for (i = 0; i < cur_ext; i++) {
+		int full = 0;	/* user array is full */
+
+		/* format results & advance arg */
+		error = formatter(&arg, &out[i], &full);
+		if (error || full)
+			break;
+	}
 
 	return error;
 }
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 478e587087f..89b81eedce6 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -69,15 +69,6 @@ xfs_inode_alloc(
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(completion_done(&ip->i_flush));
 
-	/*
-	 * initialise the VFS inode here to get failures
-	 * out of the way early.
-	 */
-	if (!inode_init_always(mp->m_super, VFS_I(ip))) {
-		kmem_zone_free(xfs_inode_zone, ip);
-		return NULL;
-	}
-
 	/* initialise the xfs inode */
 	ip->i_ino = ino;
 	ip->i_mount = mp;
@@ -113,6 +104,20 @@ xfs_inode_alloc(
 #ifdef XFS_DIR2_TRACE
 	ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
 #endif
+	/*
+	* Now initialise the VFS inode. We do this after the xfs_inode
+	* initialisation as internal failures will result in ->destroy_inode
+	* being called and that will pass down through the reclaim path and
+	* free the XFS inode. This path requires the XFS inode to already be
+	* initialised. Hence if this call fails, the xfs_inode has already
+	* been freed and we should not reference it at all in the error
+	* handling.
+	*/
+	if (!inode_init_always(mp->m_super, VFS_I(ip)))
+		return NULL;
+
+	/* prevent anyone from using this yet */
+	VFS_I(ip)->i_state = I_NEW|I_LOCK;
 
 	return ip;
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index e7ae08d1df4..123b20c8cbf 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1258,8 +1258,10 @@ xfs_file_last_byte(
 	 * necessary.
 	 */
 	if (ip->i_df.if_flags & XFS_IFEXTENTS) {
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
 		error = xfs_bmap_last_offset(NULL, ip, &last_block,
 			XFS_DATA_FORK);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		if (error) {
 			last_block = 0;
 		}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 08ce72316bf..5aaa2d7ec15 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -338,38 +338,6 @@ xfs_iomap_eof_align_last_fsb(
 }
 
 STATIC int
-xfs_flush_space(
-	xfs_inode_t	*ip,
-	int		*fsynced,
-	int		*ioflags)
-{
-	switch (*fsynced) {
-	case 0:
-		if (ip->i_delayed_blks) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			xfs_flush_inode(ip);
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
-			*fsynced = 1;
-		} else {
-			*ioflags |= BMAPI_SYNC;
-			*fsynced = 2;
-		}
-		return 0;
-	case 1:
-		*fsynced = 2;
-		*ioflags |= BMAPI_SYNC;
-		return 0;
-	case 2:
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_flush_device(ip);
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		*fsynced = 3;
-		return 0;
-	}
-	return 1;
-}
-
-STATIC int
 xfs_cmn_err_fsblock_zero(
 	xfs_inode_t	*ip,
 	xfs_bmbt_irec_t	*imap)
@@ -538,15 +506,9 @@ error_out:
 }
 
 /*
- * If the caller is doing a write at the end of the file,
- * then extend the allocation out to the file system's write
- * iosize.  We clean up any extra space left over when the
- * file is closed in xfs_inactive().
- *
- * For sync writes, we are flushing delayed allocate space to
- * try to make additional space available for allocation near
- * the filesystem full boundary - preallocation hurts in that
- * situation, of course.
+ * If the caller is doing a write at the end of the file, then extend the
+ * allocation out to the file system's write iosize.  We clean up any extra
+ * space left over when the file is closed in xfs_inactive().
  */
 STATIC int
 xfs_iomap_eof_want_preallocate(
@@ -565,7 +527,7 @@ xfs_iomap_eof_want_preallocate(
 	int		n, error, imaps;
 
 	*prealloc = 0;
-	if ((ioflag & BMAPI_SYNC) || (offset + count) <= ip->i_size)
+	if ((offset + count) <= ip->i_size)
 		return 0;
 
 	/*
@@ -611,7 +573,7 @@ xfs_iomap_write_delay(
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
-	int		prealloc, fsynced = 0;
+	int		prealloc, flushed = 0;
 	int		error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -627,12 +589,12 @@ xfs_iomap_write_delay(
 	extsz = xfs_get_extsz_hint(ip);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
-retry:
 	error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
 				ioflag, imap, XFS_WRITE_IMAPS, &prealloc);
 	if (error)
 		return error;
 
+retry:
 	if (prealloc) {
 		aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
 		ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
@@ -659,15 +621,22 @@ retry:
 
 	/*
 	 * If bmapi returned us nothing, and if we didn't get back EDQUOT,
-	 * then we must have run out of space - flush delalloc, and retry..
+	 * then we must have run out of space - flush all other inodes with
+	 * delalloc blocks and retry without EOF preallocation.
 	 */
 	if (nimaps == 0) {
 		xfs_iomap_enter_trace(XFS_IOMAP_WRITE_NOSPACE,
 					ip, offset, count);
-		if (xfs_flush_space(ip, &fsynced, &ioflag))
+		if (flushed)
 			return XFS_ERROR(ENOSPC);
 
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xfs_flush_inodes(ip);
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+		flushed = 1;
 		error = 0;
+		prealloc = 0;
 		goto retry;
 	}
 
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index a1cc1322fc0..fdcf7b82747 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -40,8 +40,7 @@ typedef enum {
 	BMAPI_IGNSTATE = (1 << 4),	/* ignore unwritten state on read */
 	BMAPI_DIRECT = (1 << 5),	/* direct instead of buffered write */
 	BMAPI_MMAP = (1 << 6),		/* allocate for mmap write */
-	BMAPI_SYNC = (1 << 7),		/* sync write to flush delalloc space */
-	BMAPI_TRYLOCK = (1 << 8),	/* non-blocking request */
+	BMAPI_TRYLOCK = (1 << 7),	/* non-blocking request */
 } bmapi_flags_t;
 
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f76c6d7cea2..3750f04ede0 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -562,9 +562,8 @@ xfs_log_mount(
 	}
 
 	mp->m_log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks);
-	if (!mp->m_log) {
-		cmn_err(CE_WARN, "XFS: Log allocation failed: No memory!");
-		error = ENOMEM;
+	if (IS_ERR(mp->m_log)) {
+		error = -PTR_ERR(mp->m_log);
 		goto out;
 	}
 
@@ -1180,10 +1179,13 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	xfs_buf_t		*bp;
 	int			i;
 	int			iclogsize;
+	int			error = ENOMEM;
 
 	log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
-	if (!log)
-		return NULL;
+	if (!log) {
+		xlog_warn("XFS: Log allocation failed: No memory!");
+		goto out;
+	}
 
 	log->l_mp	   = mp;
 	log->l_targ	   = log_target;
@@ -1201,19 +1203,35 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	log->l_grant_reserve_cycle = 1;
 	log->l_grant_write_cycle = 1;
 
+	error = EFSCORRUPTED;
 	if (xfs_sb_version_hassector(&mp->m_sb)) {
 		log->l_sectbb_log = mp->m_sb.sb_logsectlog - BBSHIFT;
-		ASSERT(log->l_sectbb_log <= mp->m_sectbb_log);
+		if (log->l_sectbb_log < 0 ||
+		    log->l_sectbb_log > mp->m_sectbb_log) {
+			xlog_warn("XFS: Log sector size (0x%x) out of range.",
+						log->l_sectbb_log);
+			goto out_free_log;
+		}
+
 		/* for larger sector sizes, must have v2 or external log */
-		ASSERT(log->l_sectbb_log == 0 ||
-			log->l_logBBstart == 0 ||
-			xfs_sb_version_haslogv2(&mp->m_sb));
-		ASSERT(mp->m_sb.sb_logsectlog >= BBSHIFT);
+		if (log->l_sectbb_log != 0 &&
+		    (log->l_logBBstart != 0 &&
+		     !xfs_sb_version_haslogv2(&mp->m_sb))) {
+			xlog_warn("XFS: log sector size (0x%x) invalid "
+				  "for configuration.", log->l_sectbb_log);
+			goto out_free_log;
+		}
+		if (mp->m_sb.sb_logsectlog < BBSHIFT) {
+			xlog_warn("XFS: Log sector log (0x%x) too small.",
+						mp->m_sb.sb_logsectlog);
+			goto out_free_log;
+		}
 	}
 	log->l_sectbb_mask = (1 << log->l_sectbb_log) - 1;
 
 	xlog_get_iclog_buffer_size(mp, log);
 
+	error = ENOMEM;
 	bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp);
 	if (!bp)
 		goto out_free_log;
@@ -1313,7 +1331,8 @@ out_free_iclog:
 	xfs_buf_free(log->l_xbuf);
 out_free_log:
 	kmem_free(log);
-	return NULL;
+out:
+	return ERR_PTR(-error);
 }	/* xlog_alloc_log */
 
 
@@ -2541,18 +2560,19 @@ redo:
 			xlog_ins_ticketq(&log->l_reserve_headq, tic);
 		xlog_trace_loggrant(log, tic,
 				    "xlog_grant_log_space: sleep 2");
+		spin_unlock(&log->l_grant_lock);
+		xlog_grant_push_ail(log->l_mp, need_bytes);
+		spin_lock(&log->l_grant_lock);
+
 		XFS_STATS_INC(xs_sleep_logspace);
 		sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s);
 
-		if (XLOG_FORCED_SHUTDOWN(log)) {
-			spin_lock(&log->l_grant_lock);
+		spin_lock(&log->l_grant_lock);
+		if (XLOG_FORCED_SHUTDOWN(log))
 			goto error_return;
-		}
 
 		xlog_trace_loggrant(log, tic,
 				    "xlog_grant_log_space: wake 2");
-		xlog_grant_push_ail(log->l_mp, need_bytes);
-		spin_lock(&log->l_grant_lock);
 		goto redo;
 	} else if (tic->t_flags & XLOG_TIC_IN_Q)
 		xlog_del_ticketq(&log->l_reserve_headq, tic);
@@ -2631,7 +2651,7 @@ xlog_regrant_write_log_space(xlog_t	   *log,
 	 * for more free space, otherwise try to get some space for
 	 * this transaction.
 	 */
-
+	need_bytes = tic->t_unit_res;
 	if ((ntic = log->l_write_headq)) {
 		free_bytes = xlog_space_left(log, log->l_grant_write_cycle,
 					     log->l_grant_write_bytes);
@@ -2651,26 +2671,25 @@ xlog_regrant_write_log_space(xlog_t	   *log,
 
 			xlog_trace_loggrant(log, tic,
 				    "xlog_regrant_write_log_space: sleep 1");
+			spin_unlock(&log->l_grant_lock);
+			xlog_grant_push_ail(log->l_mp, need_bytes);
+			spin_lock(&log->l_grant_lock);
+
 			XFS_STATS_INC(xs_sleep_logspace);
 			sv_wait(&tic->t_wait, PINOD|PLTWAIT,
 				&log->l_grant_lock, s);
 
 			/* If we're shutting down, this tic is already
 			 * off the queue */
-			if (XLOG_FORCED_SHUTDOWN(log)) {
-				spin_lock(&log->l_grant_lock);
+			spin_lock(&log->l_grant_lock);
+			if (XLOG_FORCED_SHUTDOWN(log))
 				goto error_return;
-			}
 
 			xlog_trace_loggrant(log, tic,
 				    "xlog_regrant_write_log_space: wake 1");
-			xlog_grant_push_ail(log->l_mp, tic->t_unit_res);
-			spin_lock(&log->l_grant_lock);
 		}
 	}
 
-	need_bytes = tic->t_unit_res;
-
 redo:
 	if (XLOG_FORCED_SHUTDOWN(log))
 		goto error_return;
@@ -2680,19 +2699,20 @@ redo:
 	if (free_bytes < need_bytes) {
 		if ((tic->t_flags & XLOG_TIC_IN_Q) == 0)
 			xlog_ins_ticketq(&log->l_write_headq, tic);
+		spin_unlock(&log->l_grant_lock);
+		xlog_grant_push_ail(log->l_mp, need_bytes);
+		spin_lock(&log->l_grant_lock);
+
 		XFS_STATS_INC(xs_sleep_logspace);
 		sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s);
 
 		/* If we're shutting down, this tic is already off the queue */
-		if (XLOG_FORCED_SHUTDOWN(log)) {
-			spin_lock(&log->l_grant_lock);
+		spin_lock(&log->l_grant_lock);
+		if (XLOG_FORCED_SHUTDOWN(log))
 			goto error_return;
-		}
 
 		xlog_trace_loggrant(log, tic,
 				    "xlog_regrant_write_log_space: wake 2");
-		xlog_grant_push_ail(log->l_mp, need_bytes);
-		spin_lock(&log->l_grant_lock);
 		goto redo;
 	} else if (tic->t_flags & XLOG_TIC_IN_Q)
 		xlog_del_ticketq(&log->l_write_headq, tic);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index b101990df02..65a99725d0c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -291,14 +291,17 @@ xfs_mount_validate_sb(
 	    sbp->sb_sectsize > XFS_MAX_SECTORSIZE			||
 	    sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG			||
 	    sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG			||
+	    sbp->sb_sectsize != (1 << sbp->sb_sectlog)			||
 	    sbp->sb_blocksize < XFS_MIN_BLOCKSIZE			||
 	    sbp->sb_blocksize > XFS_MAX_BLOCKSIZE			||
 	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
 	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
+	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
 	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
 	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
 	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
+	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
 	    (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)	||
 	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
 	    (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)	||
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 7af44adffc8..d6a64392f98 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -313,7 +313,7 @@ typedef struct xfs_mount {
 #endif
 	struct xfs_mru_cache	*m_filestream;  /* per-mount filestream data */
 	struct task_struct	*m_sync_task;	/* generalised sync thread */
-	bhv_vfs_sync_work_t	m_sync_work;	/* work item for VFS_SYNC */
+	xfs_sync_work_t		m_sync_work;	/* work item for VFS_SYNC */
 	struct list_head	m_sync_list;	/* sync thread work item list */
 	spinlock_t		m_sync_lock;	/* work item list lock */
 	int			m_sync_seq;	/* sync thread generation no. */
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 7394c7af5de..19cf90a9c76 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1457,6 +1457,13 @@ xfs_create(
 	error = xfs_trans_reserve(tp, resblks, log_res, 0,
 			XFS_TRANS_PERM_LOG_RES, log_count);
 	if (error == ENOSPC) {
+		/* flush outstanding delalloc blocks and retry */
+		xfs_flush_inodes(dp);
+		error = xfs_trans_reserve(tp, resblks, XFS_CREATE_LOG_RES(mp), 0,
+			XFS_TRANS_PERM_LOG_RES, XFS_CREATE_LOG_COUNT);
+	}
+	if (error == ENOSPC) {
+		/* No space at all so try a "no-allocation" reservation */
 		resblks = 0;
 		error = xfs_trans_reserve(tp, 0, log_res, 0,
 				XFS_TRANS_PERM_LOG_RES, log_count);