Merge branch 'master' into pm-sleep

* master: (848 commits)
  SELinux: Fix RCU deref check warning in sel_netport_insert()
  binary_sysctl(): fix memory leak
  mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
  ipmi_watchdog: restore settings when BMC reset
  oom: fix integer overflow of points in oom_badness
  memcg: keep root group unchanged if creation fails
  nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
  nilfs2: unbreak compat ioctl
  cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
  evm: prevent racing during tfm allocation
  evm: key must be set once during initialization
  mmc: vub300: fix type of firmware_rom_wait_states module parameter
  Revert "mmc: enable runtime PM by default"
  mmc: sdhci: remove "state" argument from sdhci_suspend_host
  x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
  IB/qib: Correct sense on freectxts increment and decrement
  RDMA/cma: Verify private data length
  cgroups: fix a css_set not found bug in cgroup_attach_proc
  oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
  Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
  ...

Conflicts:
	kernel/cgroup_freezer.c

9 files changed, 274 insertions, 213 deletions

diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b6c4b37..76e4266 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -42,6 +42,8 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
 	int count, i;
 
 	count = be32_to_cpu(aclp->acl_cnt);
+	if (count > XFS_ACL_MAX_ENTRIES)
+		return ERR_PTR(-EFSCORRUPTED);
 
 	acl = posix_acl_alloc(count, GFP_KERNEL);
 	if (!acl)
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d4906e7..c1b55e5 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -110,6 +110,7 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
 /*
  * Query whether the requested number of additional bytes of extended
  * attribute space will be able to fit inline.
+ *
  * Returns zero if not, else the di_forkoff fork offset to be used in the
  * literal area for attribute data once the new bytes have been added.
  *
@@ -122,7 +123,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	int offset;
 	int minforkoff;	/* lower limit on valid forkoff locations */
 	int maxforkoff;	/* upper limit on valid forkoff locations */
-	int dsize;	
+	int dsize;
 	xfs_mount_t *mp = dp->i_mount;
 
 	offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
@@ -136,47 +137,60 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 		return (offset >= minforkoff) ? minforkoff : 0;
 	}
 
-	if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
-		if (bytes <= XFS_IFORK_ASIZE(dp))
-			return dp->i_d.di_forkoff;
+	/*
+	 * If the requested numbers of bytes is smaller or equal to the
+	 * current attribute fork size we can always proceed.
+	 *
+	 * Note that if_bytes in the data fork might actually be larger than
+	 * the current data fork size is due to delalloc extents. In that
+	 * case either the extent count will go down when they are converted
+	 * to real extents, or the delalloc conversion will take care of the
+	 * literal area rebalancing.
+	 */
+	if (bytes <= XFS_IFORK_ASIZE(dp))
+		return dp->i_d.di_forkoff;
+
+	/*
+	 * For attr2 we can try to move the forkoff if there is space in the
+	 * literal area, but for the old format we are done if there is no
+	 * space in the fixed attribute fork.
+	 */
+	if (!(mp->m_flags & XFS_MOUNT_ATTR2))
 		return 0;
-	}
 
 	dsize = dp->i_df.if_bytes;
-	
+
 	switch (dp->i_d.di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		/* 
+		/*
 		 * If there is no attr fork and the data fork is extents, 
-		 * determine if creating the default attr fork will result 
-		 * in the extents form migrating to btree. If so, the 
-		 * minimum offset only needs to be the space required for 
+		 * determine if creating the default attr fork will result
+		 * in the extents form migrating to btree. If so, the
+		 * minimum offset only needs to be the space required for
 		 * the btree root.
-		 */ 
+		 */
 		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
 		    xfs_default_attroffset(dp))
 			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 		break;
-		
 	case XFS_DINODE_FMT_BTREE:
 		/*
-		 * If have data btree then keep forkoff if we have one,
-		 * otherwise we are adding a new attr, so then we set 
-		 * minforkoff to where the btree root can finish so we have 
+		 * If we have a data btree then keep forkoff if we have one,
+		 * otherwise we are adding a new attr, so then we set
+		 * minforkoff to where the btree root can finish so we have
 		 * plenty of room for attrs
 		 */
 		if (dp->i_d.di_forkoff) {
-			if (offset < dp->i_d.di_forkoff) 
+			if (offset < dp->i_d.di_forkoff)
 				return 0;
-			else 
-				return dp->i_d.di_forkoff;
-		} else
-			dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+			return dp->i_d.di_forkoff;
+		}
+		dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
 		break;
 	}
-	
-	/* 
-	 * A data fork btree root must have space for at least 
+
+	/*
+	 * A data fork btree root must have space for at least
 	 * MINDBTPTRS key/ptr pairs if the data fork is small or empty.
 	 */
 	minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
@@ -186,10 +200,10 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	maxforkoff = maxforkoff >> 3;	/* rounded down */
 
-	if (offset >= minforkoff && offset < maxforkoff)
-		return offset;
 	if (offset >= maxforkoff)
 		return maxforkoff;
+	if (offset >= minforkoff)
+		return offset;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index c68baeb..d0ab788 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2383,6 +2383,8 @@ xfs_bmap_btalloc(
 	int		tryagain;
 	int		error;
 
+	ASSERT(ap->length);
+
 	mp = ap->ip->i_mount;
 	align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
 	if (unlikely(align)) {
@@ -4629,6 +4631,8 @@ xfs_bmapi_allocate(
 	int			error;
 	int			rt;
 
+	ASSERT(bma->length > 0);
+
 	rt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(bma->ip);
 
 	/*
@@ -4849,6 +4853,7 @@ xfs_bmapi_write(
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
 	ASSERT(!(flags & XFS_BMAPI_IGSTATE));
 	ASSERT(tp != NULL);
+	ASSERT(len > 0);
 
 	whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
 		XFS_ATTR_FORK : XFS_DATA_FORK;
@@ -4918,9 +4923,22 @@ xfs_bmapi_write(
 			bma.eof = eof;
 			bma.conv = !!(flags & XFS_BMAPI_CONVERT);
 			bma.wasdel = wasdelay;
-			bma.length = len;
 			bma.offset = bno;
 
+			/*
+			 * 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)
+				bma.length = MAXEXTLEN;
+			else
+				bma.length = len;
+
+			ASSERT(len > 0);
+			ASSERT(bma.length > 0);
 			error = xfs_bmapi_allocate(&bma, flags);
 			if (error)
 				goto error0;
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index da10897..558910f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -98,22 +98,22 @@ xfs_fs_encode_fh(
 	switch (fileid_type) {
 	case FILEID_INO32_GEN_PARENT:
 		spin_lock(&dentry->d_lock);
-		fid->i32.parent_ino = dentry->d_parent->d_inode->i_ino;
+		fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
 		fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation;
 		spin_unlock(&dentry->d_lock);
 		/*FALLTHRU*/
 	case FILEID_INO32_GEN:
-		fid->i32.ino = inode->i_ino;
+		fid->i32.ino = XFS_I(inode)->i_ino;
 		fid->i32.gen = inode->i_generation;
 		break;
 	case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
 		spin_lock(&dentry->d_lock);
-		fid64->parent_ino = dentry->d_parent->d_inode->i_ino;
+		fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
 		fid64->parent_gen = dentry->d_parent->d_inode->i_generation;
 		spin_unlock(&dentry->d_lock);
 		/*FALLTHRU*/
 	case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG:
-		fid64->ino = inode->i_ino;
+		fid64->ino = XFS_I(inode)->i_ino;
 		fid64->gen = inode->i_generation;
 		break;
 	}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0237c6..755ee81 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2835,6 +2835,27 @@ corrupt_out:
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
+void
+xfs_promote_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_buf		*bp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+
+	bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
+			ip->i_imap.im_len, XBF_TRYLOCK);
+	if (!bp)
+		return;
+
+	if (XFS_BUF_ISDELAYWRITE(bp)) {
+		xfs_buf_delwri_promote(bp);
+		wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
+	}
+
+	xfs_buf_relse(bp);
+}
+
 /*
  * Return a pointer to the extent record at file index idx.
  */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 760140d..b4cd473 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -498,6 +498,7 @@ int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 void		xfs_iunpin_wait(xfs_inode_t *);
 int		xfs_iflush(xfs_inode_t *, uint);
+void		xfs_promote_inode(struct xfs_inode *);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a14cd89..34817ad 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -150,6 +150,117 @@ xlog_grant_add_space(
 	} while (head_val != old);
 }
 
+STATIC bool
+xlog_reserveq_wake(
+	struct log		*log,
+	int			*free_bytes)
+{
+	struct xlog_ticket	*tic;
+	int			need_bytes;
+
+	list_for_each_entry(tic, &log->l_reserveq, t_queue) {
+		if (tic->t_flags & XLOG_TIC_PERM_RESERV)
+			need_bytes = tic->t_unit_res * tic->t_cnt;
+		else
+			need_bytes = tic->t_unit_res;
+
+		if (*free_bytes < need_bytes)
+			return false;
+		*free_bytes -= need_bytes;
+
+		trace_xfs_log_grant_wake_up(log, tic);
+		wake_up(&tic->t_wait);
+	}
+
+	return true;
+}
+
+STATIC bool
+xlog_writeq_wake(
+	struct log		*log,
+	int			*free_bytes)
+{
+	struct xlog_ticket	*tic;
+	int			need_bytes;
+
+	list_for_each_entry(tic, &log->l_writeq, t_queue) {
+		ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV);
+
+		need_bytes = tic->t_unit_res;
+
+		if (*free_bytes < need_bytes)
+			return false;
+		*free_bytes -= need_bytes;
+
+		trace_xfs_log_regrant_write_wake_up(log, tic);
+		wake_up(&tic->t_wait);
+	}
+
+	return true;
+}
+
+STATIC int
+xlog_reserveq_wait(
+	struct log		*log,
+	struct xlog_ticket	*tic,
+	int			need_bytes)
+{
+	list_add_tail(&tic->t_queue, &log->l_reserveq);
+
+	do {
+		if (XLOG_FORCED_SHUTDOWN(log))
+			goto shutdown;
+		xlog_grant_push_ail(log, need_bytes);
+
+		XFS_STATS_INC(xs_sleep_logspace);
+		trace_xfs_log_grant_sleep(log, tic);
+
+		xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
+		trace_xfs_log_grant_wake(log, tic);
+
+		spin_lock(&log->l_grant_reserve_lock);
+		if (XLOG_FORCED_SHUTDOWN(log))
+			goto shutdown;
+	} while (xlog_space_left(log, &log->l_grant_reserve_head) < need_bytes);
+
+	list_del_init(&tic->t_queue);
+	return 0;
+shutdown:
+	list_del_init(&tic->t_queue);
+	return XFS_ERROR(EIO);
+}
+
+STATIC int
+xlog_writeq_wait(
+	struct log		*log,
+	struct xlog_ticket	*tic,
+	int			need_bytes)
+{
+	list_add_tail(&tic->t_queue, &log->l_writeq);
+
+	do {
+		if (XLOG_FORCED_SHUTDOWN(log))
+			goto shutdown;
+		xlog_grant_push_ail(log, need_bytes);
+
+		XFS_STATS_INC(xs_sleep_logspace);
+		trace_xfs_log_regrant_write_sleep(log, tic);
+
+		xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
+		trace_xfs_log_regrant_write_wake(log, tic);
+
+		spin_lock(&log->l_grant_write_lock);
+		if (XLOG_FORCED_SHUTDOWN(log))
+			goto shutdown;
+	} while (xlog_space_left(log, &log->l_grant_write_head) < need_bytes);
+
+	list_del_init(&tic->t_queue);
+	return 0;
+shutdown:
+	list_del_init(&tic->t_queue);
+	return XFS_ERROR(EIO);
+}
+
 static void
 xlog_tic_reset_res(xlog_ticket_t *tic)
 {
@@ -350,8 +461,19 @@ xfs_log_reserve(
 		retval = xlog_grant_log_space(log, internal_ticket);
 	}
 
+	if (unlikely(retval)) {
+		/*
+		 * If we are failing, make sure the ticket doesn't have any
+		 * current reservations.  We don't want to add this back
+		 * when the ticket/ transaction gets cancelled.
+		 */
+		internal_ticket->t_curr_res = 0;
+		/* ungrant will give back unit_res * t_cnt. */
+		internal_ticket->t_cnt = 0;
+	}
+
 	return retval;
-}	/* xfs_log_reserve */
+}
 
 
 /*
@@ -2481,8 +2603,8 @@ restart:
 /*
  * Atomically get the log space required for a log ticket.
  *
- * Once a ticket gets put onto the reserveq, it will only return after
- * the needed reservation is satisfied.
+ * Once a ticket gets put onto the reserveq, it will only return after the
+ * needed reservation is satisfied.
  *
  * This function is structured so that it has a lock free fast path. This is
  * necessary because every new transaction reservation will come through this
@@ -2490,113 +2612,53 @@ restart:
  * every pass.
  *
  * As tickets are only ever moved on and off the reserveq under the
- * l_grant_reserve_lock, we only need to take that lock if we are going
- * to add the ticket to the queue and sleep. We can avoid taking the lock if the
- * ticket was never added to the reserveq because the t_queue list head will be
- * empty and we hold the only reference to it so it can safely be checked
- * unlocked.
+ * l_grant_reserve_lock, we only need to take that lock if we are going to add
+ * the ticket to the queue and sleep. We can avoid taking the lock if the ticket
+ * was never added to the reserveq because the t_queue list head will be empty
+ * and we hold the only reference to it so it can safely be checked unlocked.
  */
 STATIC int
-xlog_grant_log_space(xlog_t	   *log,
-		     xlog_ticket_t *tic)
+xlog_grant_log_space(
+	struct log		*log,
+	struct xlog_ticket	*tic)
 {
-	int		 free_bytes;
-	int		 need_bytes;
+	int			free_bytes, need_bytes;
+	int			error = 0;
 
-#ifdef DEBUG
-	if (log->l_flags & XLOG_ACTIVE_RECOVERY)
-		panic("grant Recovery problem");
-#endif
+	ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
 
 	trace_xfs_log_grant_enter(log, tic);
 
+	/*
+	 * If there are other waiters on the queue then give them a chance at
+	 * logspace before us.  Wake up the first waiters, if we do not wake
+	 * up all the waiters then go to sleep waiting for more free space,
+	 * otherwise try to get some space for this transaction.
+	 */
 	need_bytes = tic->t_unit_res;
 	if (tic->t_flags & XFS_LOG_PERM_RESERV)
 		need_bytes *= tic->t_ocnt;
-
-	/* something is already sleeping; insert new transaction at end */
-	if (!list_empty_careful(&log->l_reserveq)) {
-		spin_lock(&log->l_grant_reserve_lock);
-		/* recheck the queue now we are locked */
-		if (list_empty(&log->l_reserveq)) {
-			spin_unlock(&log->l_grant_reserve_lock);
-			goto redo;
-		}
-		list_add_tail(&tic->t_queue, &log->l_reserveq);
-
-		trace_xfs_log_grant_sleep1(log, tic);
-
-		/*
-		 * Gotta check this before going to sleep, while we're
-		 * holding the grant lock.
-		 */
-		if (XLOG_FORCED_SHUTDOWN(log))
-			goto error_return;
-
-		XFS_STATS_INC(xs_sleep_logspace);
-		xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
-		/*
-		 * If we got an error, and the filesystem is shutting down,
-		 * we'll catch it down below. So just continue...
-		 */
-		trace_xfs_log_grant_wake1(log, tic);
-	}
-
-redo:
-	if (XLOG_FORCED_SHUTDOWN(log))
-		goto error_return_unlocked;
-
 	free_bytes = xlog_space_left(log, &log->l_grant_reserve_head);
-	if (free_bytes < need_bytes) {
+	if (!list_empty_careful(&log->l_reserveq)) {
 		spin_lock(&log->l_grant_reserve_lock);
-		if (list_empty(&tic->t_queue))
-			list_add_tail(&tic->t_queue, &log->l_reserveq);
-
-		trace_xfs_log_grant_sleep2(log, tic);
-
-		if (XLOG_FORCED_SHUTDOWN(log))
-			goto error_return;
-
-		xlog_grant_push_ail(log, need_bytes);
-
-		XFS_STATS_INC(xs_sleep_logspace);
-		xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
-		trace_xfs_log_grant_wake2(log, tic);
-		goto redo;
-	}
-
-	if (!list_empty(&tic->t_queue)) {
+		if (!xlog_reserveq_wake(log, &free_bytes) ||
+		    free_bytes < need_bytes)
+			error = xlog_reserveq_wait(log, tic, need_bytes);
+		spin_unlock(&log->l_grant_reserve_lock);
+	} else if (free_bytes < need_bytes) {
 		spin_lock(&log->l_grant_reserve_lock);
-		list_del_init(&tic->t_queue);
+		error = xlog_reserveq_wait(log, tic, need_bytes);
 		spin_unlock(&log->l_grant_reserve_lock);
 	}
+	if (error)
+		return error;
 
-	/* we've got enough space */
 	xlog_grant_add_space(log, &log->l_grant_reserve_head, need_bytes);
 	xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
 	trace_xfs_log_grant_exit(log, tic);
 	xlog_verify_grant_tail(log);
 	return 0;
-
-error_return_unlocked:
-	spin_lock(&log->l_grant_reserve_lock);
-error_return:
-	list_del_init(&tic->t_queue);
-	spin_unlock(&log->l_grant_reserve_lock);
-	trace_xfs_log_grant_error(log, tic);
-
-	/*
-	 * If we are failing, make sure the ticket doesn't have any
-	 * current reservations. We don't want to add this back when
-	 * the ticket/transaction gets cancelled.
-	 */
-	tic->t_curr_res = 0;
-	tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
-	return XFS_ERROR(EIO);
-}	/* xlog_grant_log_space */
-
+}
 
 /*
  * Replenish the byte reservation required by moving the grant write head.
@@ -2605,10 +2667,12 @@ error_return:
  * free fast path.
  */
 STATIC int
-xlog_regrant_write_log_space(xlog_t	   *log,
-			     xlog_ticket_t *tic)
+xlog_regrant_write_log_space(
+	struct log		*log,
+	struct xlog_ticket	*tic)
 {
-	int		free_bytes, need_bytes;
+	int			free_bytes, need_bytes;
+	int			error = 0;
 
 	tic->t_curr_res = tic->t_unit_res;
 	xlog_tic_reset_res(tic);
@@ -2616,104 +2680,38 @@ xlog_regrant_write_log_space(xlog_t	   *log,
 	if (tic->t_cnt > 0)
 		return 0;
 
-#ifdef DEBUG
-	if (log->l_flags & XLOG_ACTIVE_RECOVERY)
-		panic("regrant Recovery problem");
-#endif
+	ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
 
 	trace_xfs_log_regrant_write_enter(log, tic);
-	if (XLOG_FORCED_SHUTDOWN(log))
-		goto error_return_unlocked;
 
-	/* If there are other waiters on the queue then give them a
-	 * chance at logspace before us. Wake up the first waiters,
-	 * if we do not wake up all the waiters then go to sleep waiting
-	 * for more free space, otherwise try to get some space for
-	 * this transaction.
+	/*
+	 * If there are other waiters on the queue then give them a chance at
+	 * logspace before us.  Wake up the first waiters, if we do not wake
+	 * up all the waiters then go to sleep waiting for more free space,
+	 * otherwise try to get some space for this transaction.
 	 */
 	need_bytes = tic->t_unit_res;
-	if (!list_empty_careful(&log->l_writeq)) {
-		struct xlog_ticket *ntic;
-
-		spin_lock(&log->l_grant_write_lock);
-		free_bytes = xlog_space_left(log, &log->l_grant_write_head);
-		list_for_each_entry(ntic, &log->l_writeq, t_queue) {
-			ASSERT(ntic->t_flags & XLOG_TIC_PERM_RESERV);
-
-			if (free_bytes < ntic->t_unit_res)
-				break;
-			free_bytes -= ntic->t_unit_res;
-			wake_up(&ntic->t_wait);
-		}
-
-		if (ntic != list_first_entry(&log->l_writeq,
-						struct xlog_ticket, t_queue)) {
-			if (list_empty(&tic->t_queue))
-				list_add_tail(&tic->t_queue, &log->l_writeq);
-			trace_xfs_log_regrant_write_sleep1(log, tic);
-
-			xlog_grant_push_ail(log, need_bytes);
-
-			XFS_STATS_INC(xs_sleep_logspace);
-			xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
-			trace_xfs_log_regrant_write_wake1(log, tic);
-		} else
-			spin_unlock(&log->l_grant_write_lock);
-	}
-
-redo:
-	if (XLOG_FORCED_SHUTDOWN(log))
-		goto error_return_unlocked;
-
 	free_bytes = xlog_space_left(log, &log->l_grant_write_head);
-	if (free_bytes < need_bytes) {
+	if (!list_empty_careful(&log->l_writeq)) {
 		spin_lock(&log->l_grant_write_lock);
-		if (list_empty(&tic->t_queue))
-			list_add_tail(&tic->t_queue, &log->l_writeq);
-
-		if (XLOG_FORCED_SHUTDOWN(log))
-			goto error_return;
-
-		xlog_grant_push_ail(log, need_bytes);
-
-		XFS_STATS_INC(xs_sleep_logspace);
-		trace_xfs_log_regrant_write_sleep2(log, tic);
-		xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
-
-		trace_xfs_log_regrant_write_wake2(log, tic);
-		goto redo;
-	}
-
-	if (!list_empty(&tic->t_queue)) {
+		if (!xlog_writeq_wake(log, &free_bytes) ||
+		    free_bytes < need_bytes)
+			error = xlog_writeq_wait(log, tic, need_bytes);
+		spin_unlock(&log->l_grant_write_lock);
+	} else if (free_bytes < need_bytes) {
 		spin_lock(&log->l_grant_write_lock);
-		list_del_init(&tic->t_queue);
+		error = xlog_writeq_wait(log, tic, need_bytes);
 		spin_unlock(&log->l_grant_write_lock);
 	}
 
-	/* we've got enough space */
+	if (error)
+		return error;
+
 	xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
 	trace_xfs_log_regrant_write_exit(log, tic);
 	xlog_verify_grant_tail(log);
 	return 0;
-
-
- error_return_unlocked:
-	spin_lock(&log->l_grant_write_lock);
- error_return:
-	list_del_init(&tic->t_queue);
-	spin_unlock(&log->l_grant_write_lock);
-	trace_xfs_log_regrant_write_error(log, tic);
-
-	/*
-	 * If we are failing, make sure the ticket doesn't have any
-	 * current reservations. We don't want to add this back when
-	 * the ticket/transaction gets cancelled.
-	 */
-	tic->t_curr_res = 0;
-	tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
-	return XFS_ERROR(EIO);
-}	/* xlog_regrant_write_log_space */
-
+}
 
 /* The first cnt-1 times through here we don't need to
  * move the grant write head because the permanent
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index aa3dc1a..be5c51d 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -770,6 +770,17 @@ restart:
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
 			goto out;
+
+		/*
+		 * If we only have a single dirty inode in a cluster there is
+		 * a fair chance that the AIL push may have pushed it into
+		 * the buffer, but xfsbufd won't touch it until 30 seconds
+		 * from now, and thus we will lock up here.
+		 *
+		 * Promote the inode buffer to the front of the delwri list
+		 * and wake up xfsbufd now.
+		 */
+		xfs_promote_inode(ip);
 		xfs_iflock(ip);
 	}
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f1d2802..4940357 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -834,18 +834,14 @@ DEFINE_LOGGRANT_EVENT(xfs_log_umount_write);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_exit);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake_up);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_exit);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake_up);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_exit);