1 files changed, 321 insertions, 381 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9aea7d68d8ab..c06129cffba9 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -44,7 +44,6 @@ kmem_zone_t *xfs_inode_zone;
  */
 #define	XFS_ITRUNC_MAX_EXTENTS	2
 
-STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
 STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
 STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
 
@@ -452,7 +451,7 @@ xfs_lock_inodes(
 	/*
 	 * Currently supports between 2 and 5 inodes with exclusive locking.  We
 	 * support an arbitrary depth of locking here, but absolute limits on
-	 * inodes depend on the the type of locking and the limits placed by
+	 * inodes depend on the type of locking and the limits placed by
 	 * lockdep annotations in xfs_lock_inumorder.  These are all checked by
 	 * the asserts.
 	 */
@@ -1740,10 +1739,31 @@ xfs_inactive_ifree(
 		return error;
 	}
 
+	/*
+	 * We do not hold the inode locked across the entire rolling transaction
+	 * here. We only need to hold it for the first transaction that
+	 * xfs_ifree() builds, which may mark the inode XFS_ISTALE if the
+	 * underlying cluster buffer is freed. Relogging an XFS_ISTALE inode
+	 * here breaks the relationship between cluster buffer invalidation and
+	 * stale inode invalidation on cluster buffer item journal commit
+	 * completion, and can result in leaving dirty stale inodes hanging
+	 * around in memory.
+	 *
+	 * We have no need for serialising this inode operation against other
+	 * operations - we freed the inode and hence reallocation is required
+	 * and that will serialise on reallocating the space the deferops need
+	 * to free. Hence we can unlock the inode on the first commit of
+	 * the transaction rather than roll it right through the deferops. This
+	 * avoids relogging the XFS_ISTALE inode.
+	 *
+	 * We check that xfs_ifree() hasn't grown an internal transaction roll
+	 * by asserting that the inode is still locked when it returns.
+	 */
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 	error = xfs_ifree(tp, ip);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
@@ -1756,7 +1776,6 @@ xfs_inactive_ifree(
 			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
 		}
 		xfs_trans_cancel(tp);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		return error;
 	}
 
@@ -1774,7 +1793,6 @@ xfs_inactive_ifree(
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
 			__func__, error);
 
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return 0;
 }
 
@@ -2147,7 +2165,6 @@ xfs_iunlink_update_dinode(
 	xfs_dinode_calc_crc(mp, dip);
 	xfs_trans_inode_buf(tp, ibp);
 	xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
-	xfs_inobp_check(mp, ibp);
 }
 
 /* Set an in-core inode's unlinked pointer and return the old value. */
@@ -2248,7 +2265,6 @@ xfs_iunlink(
 	}
 
 	if (next_agino != NULLAGINO) {
-		struct xfs_perag	*pag;
 		xfs_agino_t		old_agino;
 
 		/*
@@ -2265,9 +2281,7 @@ xfs_iunlink(
 		 * agino has been unlinked, add a backref from the next inode
 		 * back to agino.
 		 */
-		pag = xfs_perag_get(mp, agno);
-		error = xfs_iunlink_add_backref(pag, agino, next_agino);
-		xfs_perag_put(pag);
+		error = xfs_iunlink_add_backref(agibp->b_pag, agino, next_agino);
 		if (error)
 			return error;
 	}
@@ -2403,7 +2417,6 @@ xfs_iunlink_remove(
 	struct xfs_buf		*agibp;
 	struct xfs_buf		*last_ibp;
 	struct xfs_dinode	*last_dip = NULL;
-	struct xfs_perag	*pag = NULL;
 	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
 	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
 	xfs_agino_t		next_agino;
@@ -2447,32 +2460,22 @@ xfs_iunlink_remove(
 	 * this inode's backref to point from the next inode.
 	 */
 	if (next_agino != NULLAGINO) {
-		pag = xfs_perag_get(mp, agno);
-		error = xfs_iunlink_change_backref(pag, next_agino,
+		error = xfs_iunlink_change_backref(agibp->b_pag, next_agino,
 				NULLAGINO);
 		if (error)
-			goto out;
+			return error;
 	}
 
-	if (head_agino == agino) {
-		/* Point the head of the list to the next unlinked inode. */
-		error = xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
-				next_agino);
-		if (error)
-			goto out;
-	} else {
+	if (head_agino != agino) {
 		struct xfs_imap	imap;
 		xfs_agino_t	prev_agino;
 
-		if (!pag)
-			pag = xfs_perag_get(mp, agno);
-
 		/* We need to search the list for the inode being freed. */
 		error = xfs_iunlink_map_prev(tp, agno, head_agino, agino,
 				&prev_agino, &imap, &last_dip, &last_ibp,
-				pag);
+				agibp->b_pag);
 		if (error)
-			goto out;
+			return error;
 
 		/* Point the previous inode on the list to the next inode. */
 		xfs_iunlink_update_dinode(tp, agno, prev_agino, last_ibp,
@@ -2486,29 +2489,29 @@ xfs_iunlink_remove(
 		 * change_backref takes care of deleting the backref if
 		 * next_agino is NULLAGINO.
 		 */
-		error = xfs_iunlink_change_backref(pag, agino, next_agino);
-		if (error)
-			goto out;
+		return xfs_iunlink_change_backref(agibp->b_pag, agino,
+				next_agino);
 	}
 
-out:
-	if (pag)
-		xfs_perag_put(pag);
-	return error;
+	/* Point the head of the list to the next unlinked inode. */
+	return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
+			next_agino);
 }
 
 /*
- * Look up the inode number specified and mark it stale if it is found. If it is
- * dirty, return the inode so it can be attached to the cluster buffer so it can
- * be processed appropriately when the cluster free transaction completes.
+ * Look up the inode number specified and if it is not already marked XFS_ISTALE
+ * mark it stale. We should only find clean inodes in this lookup that aren't
+ * already stale.
  */
-static struct xfs_inode *
-xfs_ifree_get_one_inode(
-	struct xfs_perag	*pag,
+static void
+xfs_ifree_mark_inode_stale(
+	struct xfs_buf		*bp,
 	struct xfs_inode	*free_ip,
 	xfs_ino_t		inum)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_perag	*pag = bp->b_pag;
+	struct xfs_inode_log_item *iip;
 	struct xfs_inode	*ip;
 
 retry:
@@ -2516,8 +2519,10 @@ retry:
 	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));
 
 	/* Inode not in memory, nothing to do */
-	if (!ip)
-		goto out_rcu_unlock;
+	if (!ip) {
+		rcu_read_unlock();
+		return;
+	}
 
 	/*
 	 * because this is an RCU protected lookup, we could find a recently
@@ -2528,9 +2533,9 @@ retry:
 	spin_lock(&ip->i_flags_lock);
 	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
 		spin_unlock(&ip->i_flags_lock);
-		goto out_rcu_unlock;
+		rcu_read_unlock();
+		return;
 	}
-	spin_unlock(&ip->i_flags_lock);
 
 	/*
 	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
@@ -2540,43 +2545,50 @@ retry:
 	 */
 	if (ip != free_ip) {
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+			spin_unlock(&ip->i_flags_lock);
 			rcu_read_unlock();
 			delay(1);
 			goto retry;
 		}
-
-		/*
-		 * Check the inode number again in case we're racing with
-		 * freeing in xfs_reclaim_inode().  See the comments in that
-		 * function for more information as to why the initial check is
-		 * not sufficient.
-		 */
-		if (ip->i_ino != inum) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			goto out_rcu_unlock;
-		}
 	}
+	ip->i_flags |= XFS_ISTALE;
+	spin_unlock(&ip->i_flags_lock);
 	rcu_read_unlock();
 
-	xfs_iflock(ip);
-	xfs_iflags_set(ip, XFS_ISTALE);
+	/*
+	 * If we can't get the flush lock, the inode is already attached.  All
+	 * we needed to do here is mark the inode stale so buffer IO completion
+	 * will remove it from the AIL.
+	 */
+	iip = ip->i_itemp;
+	if (!xfs_iflock_nowait(ip)) {
+		ASSERT(!list_empty(&iip->ili_item.li_bio_list));
+		ASSERT(iip->ili_last_fields);
+		goto out_iunlock;
+	}
 
 	/*
-	 * We don't need to attach clean inodes or those only with unlogged
-	 * changes (which we throw away, anyway).
+	 * Inodes not attached to the buffer can be released immediately.
+	 * Everything else has to go through xfs_iflush_abort() on journal
+	 * commit as the flock synchronises removal of the inode from the
+	 * cluster buffer against inode reclaim.
 	 */
-	if (!ip->i_itemp || xfs_inode_clean(ip)) {
-		ASSERT(ip != free_ip);
+	if (!iip || list_empty(&iip->ili_item.li_bio_list)) {
 		xfs_ifunlock(ip);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		goto out_no_inode;
+		goto out_iunlock;
 	}
-	return ip;
 
-out_rcu_unlock:
-	rcu_read_unlock();
-out_no_inode:
-	return NULL;
+	/* we have a dirty inode in memory that has not yet been flushed. */
+	spin_lock(&iip->ili_lock);
+	iip->ili_last_fields = iip->ili_fields;
+	iip->ili_fields = 0;
+	iip->ili_fsync_fields = 0;
+	spin_unlock(&iip->ili_lock);
+	ASSERT(iip->ili_last_fields);
+
+out_iunlock:
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 }
 
 /*
@@ -2586,26 +2598,20 @@ out_no_inode:
  */
 STATIC int
 xfs_ifree_cluster(
-	xfs_inode_t		*free_ip,
-	xfs_trans_t		*tp,
+	struct xfs_inode	*free_ip,
+	struct xfs_trans	*tp,
 	struct xfs_icluster	*xic)
 {
-	xfs_mount_t		*mp = free_ip->i_mount;
+	struct xfs_mount	*mp = free_ip->i_mount;
+	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	struct xfs_buf		*bp;
+	xfs_daddr_t		blkno;
+	xfs_ino_t		inum = xic->first_ino;
 	int			nbufs;
 	int			i, j;
 	int			ioffset;
-	xfs_daddr_t		blkno;
-	xfs_buf_t		*bp;
-	xfs_inode_t		*ip;
-	struct xfs_inode_log_item *iip;
-	struct xfs_log_item	*lip;
-	struct xfs_perag	*pag;
-	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	xfs_ino_t		inum;
 	int			error;
 
-	inum = xic->first_ino;
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
 	nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster;
 
 	for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) {
@@ -2634,10 +2640,8 @@ xfs_ifree_cluster(
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
 				mp->m_bsize * igeo->blocks_per_cluster,
 				XBF_UNMAPPED, &bp);
-		if (error) {
-			xfs_perag_put(pag);
+		if (error)
 			return error;
-		}
 
 		/*
 		 * This buffer may not have been correctly initialised as we
@@ -2651,60 +2655,16 @@ xfs_ifree_cluster(
 		bp->b_ops = &xfs_inode_buf_ops;
 
 		/*
-		 * Walk the inodes already attached to the buffer and mark them
-		 * stale. These will all have the flush locks held, so an
-		 * in-memory inode walk can't lock them. By marking them all
-		 * stale first, we will not attempt to lock them in the loop
-		 * below as the XFS_ISTALE flag will be set.
+		 * Now we need to set all the cached clean inodes as XFS_ISTALE,
+		 * too. This requires lookups, and will skip inodes that we've
+		 * already marked XFS_ISTALE.
 		 */
-		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
-			if (lip->li_type == XFS_LI_INODE) {
-				iip = (struct xfs_inode_log_item *)lip;
-				ASSERT(iip->ili_logged == 1);
-				lip->li_cb = xfs_istale_done;
-				xfs_trans_ail_copy_lsn(mp->m_ail,
-							&iip->ili_flush_lsn,
-							&iip->ili_item.li_lsn);
-				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
-			}
-		}
-
-
-		/*
-		 * For each inode in memory attempt to add it to the inode
-		 * buffer and set it up for being staled on buffer IO
-		 * completion.  This is safe as we've locked out tail pushing
-		 * and flushing by locking the buffer.
-		 *
-		 * We have already marked every inode that was part of a
-		 * transaction stale above, which means there is no point in
-		 * even trying to lock them.
-		 */
-		for (i = 0; i < igeo->inodes_per_cluster; i++) {
-			ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i);
-			if (!ip)
-				continue;
-
-			iip = ip->i_itemp;
-			iip->ili_last_fields = iip->ili_fields;
-			iip->ili_fields = 0;
-			iip->ili_fsync_fields = 0;
-			iip->ili_logged = 1;
-			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
-						&iip->ili_item.li_lsn);
-
-			xfs_buf_attach_iodone(bp, xfs_istale_done,
-						  &iip->ili_item);
-
-			if (ip != free_ip)
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		}
+		for (i = 0; i < igeo->inodes_per_cluster; i++)
+			xfs_ifree_mark_inode_stale(bp, free_ip, inum + i);
 
 		xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);
 	}
-
-	xfs_perag_put(pag);
 	return 0;
 }
 
@@ -2725,6 +2685,7 @@ xfs_ifree(
 {
 	int			error;
 	struct xfs_icluster	xic = { 0 };
+	struct xfs_inode_log_item *iip = ip->i_itemp;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(VFS_I(ip)->i_nlink == 0);
@@ -2762,7 +2723,9 @@ xfs_ifree(
 	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
 
 	/* Don't attempt to replay owner changes for a deleted inode */
-	ip->i_itemp->ili_fields &= ~(XFS_ILOG_AOWNER|XFS_ILOG_DOWNER);
+	spin_lock(&iip->ili_lock);
+	iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER);
+	spin_unlock(&iip->ili_lock);
 
 	/*
 	 * Bump the generation count so no one will be confused
@@ -3142,7 +3105,7 @@ out_trans_abort:
 /*
  * xfs_rename_alloc_whiteout()
  *
- * Return a referenced, unlinked, unlocked inode that that can be used as a
+ * Return a referenced, unlinked, unlocked inode that can be used as a
  * whiteout in a rename transaction. We use a tmpfile inode here so that if we
  * crash between allocating the inode and linking it into the rename transaction
  * recovery will free the inode and we won't leak it.
@@ -3469,232 +3432,9 @@ out_release_wip:
 	return error;
 }
 
-STATIC int
-xfs_iflush_cluster(
-	struct xfs_inode	*ip,
-	struct xfs_buf		*bp)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_perag	*pag;
-	unsigned long		first_index, mask;
-	int			cilist_size;
-	struct xfs_inode	**cilist;
-	struct xfs_inode	*cip;
-	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	int			error = 0;
-	int			nr_found;
-	int			clcount = 0;
-	int			i;
-
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-
-	cilist_size = igeo->inodes_per_cluster * sizeof(struct xfs_inode *);
-	cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
-	if (!cilist)
-		goto out_put;
-
-	mask = ~(igeo->inodes_per_cluster - 1);
-	first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
-	rcu_read_lock();
-	/* really need a gang lookup range call here */
-	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
-					first_index, igeo->inodes_per_cluster);
-	if (nr_found == 0)
-		goto out_free;
-
-	for (i = 0; i < nr_found; i++) {
-		cip = cilist[i];
-		if (cip == ip)
-			continue;
-
-		/*
-		 * because this is an RCU protected lookup, we could find a
-		 * recently freed or even reallocated inode during the lookup.
-		 * We need to check under the i_flags_lock for a valid inode
-		 * here. Skip it if it is not valid or the wrong inode.
-		 */
-		spin_lock(&cip->i_flags_lock);
-		if (!cip->i_ino ||
-		    __xfs_iflags_test(cip, XFS_ISTALE)) {
-			spin_unlock(&cip->i_flags_lock);
-			continue;
-		}
-
-		/*
-		 * Once we fall off the end of the cluster, no point checking
-		 * any more inodes in the list because they will also all be
-		 * outside the cluster.
-		 */
-		if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
-			spin_unlock(&cip->i_flags_lock);
-			break;
-		}
-		spin_unlock(&cip->i_flags_lock);
-
-		/*
-		 * Do an un-protected check to see if the inode is dirty and
-		 * is a candidate for flushing.  These checks will be repeated
-		 * later after the appropriate locks are acquired.
-		 */
-		if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
-			continue;
-
-		/*
-		 * Try to get locks.  If any are unavailable or it is pinned,
-		 * then this inode cannot be flushed and is skipped.
-		 */
-
-		if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
-			continue;
-		if (!xfs_iflock_nowait(cip)) {
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-		if (xfs_ipincount(cip)) {
-			xfs_ifunlock(cip);
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
-
-		/*
-		 * Check the inode number again, just to be certain we are not
-		 * racing with freeing in xfs_reclaim_inode(). See the comments
-		 * in that function for more information as to why the initial
-		 * check is not sufficient.
-		 */
-		if (!cip->i_ino) {
-			xfs_ifunlock(cip);
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
-		/*
-		 * arriving here means that this inode can be flushed.  First
-		 * re-check that it's dirty before flushing.
-		 */
-		if (!xfs_inode_clean(cip)) {
-			error = xfs_iflush_int(cip, bp);
-			if (error) {
-				xfs_iunlock(cip, XFS_ILOCK_SHARED);
-				goto out_free;
-			}
-			clcount++;
-		} else {
-			xfs_ifunlock(cip);
-		}
-		xfs_iunlock(cip, XFS_ILOCK_SHARED);
-	}
-
-	if (clcount) {
-		XFS_STATS_INC(mp, xs_icluster_flushcnt);
-		XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
-	}
-
-out_free:
-	rcu_read_unlock();
-	kmem_free(cilist);
-out_put:
-	xfs_perag_put(pag);
-	return error;
-}
-
-/*
- * Flush dirty inode metadata into the backing buffer.
- *
- * The caller must have the inode lock and the inode flush lock held.  The
- * inode lock will still be held upon return to the caller, and the inode
- * flush lock will be released after the inode has reached the disk.
- *
- * The caller must write out the buffer returned in *bpp and release it.
- */
-int
+static int
 xfs_iflush(
 	struct xfs_inode	*ip,
-	struct xfs_buf		**bpp)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_buf		*bp = NULL;
-	struct xfs_dinode	*dip;
-	int			error;
-
-	XFS_STATS_INC(mp, xs_iflush_count);
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
-	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
-	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-
-	*bpp = NULL;
-
-	xfs_iunpin_wait(ip);
-
-	/*
-	 * For stale inodes we cannot rely on the backing buffer remaining
-	 * stale in cache for the remaining life of the stale inode and so
-	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
-	 * inodes below. We have to check this after ensuring the inode is
-	 * unpinned so that it is safe to reclaim the stale inode after the
-	 * flush call.
-	 */
-	if (xfs_iflags_test(ip, XFS_ISTALE)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
-	/*
-	 * Get the buffer containing the on-disk inode. We are doing a try-lock
-	 * operation here, so we may get an EAGAIN error. In that case, return
-	 * leaving the inode dirty.
-	 *
-	 * If we get any other error, we effectively have a corruption situation
-	 * and we cannot flush the inode. Abort the flush and shut down.
-	 */
-	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK);
-	if (error == -EAGAIN) {
-		xfs_ifunlock(ip);
-		return error;
-	}
-	if (error)
-		goto abort;
-
-	/*
-	 * If the buffer is pinned then push on the log now so we won't
-	 * get stuck waiting in the write for too long.
-	 */
-	if (xfs_buf_ispinned(bp))
-		xfs_log_force(mp, 0);
-
-	/*
-	 * Flush the provided inode then attempt to gather others from the
-	 * cluster into the write.
-	 *
-	 * Note: Once we attempt to flush an inode, we must run buffer
-	 * completion callbacks on any failure. If this fails, simulate an I/O
-	 * failure on the buffer and shut down.
-	 */
-	error = xfs_iflush_int(ip, bp);
-	if (!error)
-		error = xfs_iflush_cluster(ip, bp);
-	if (error) {
-		bp->b_flags |= XBF_ASYNC;
-		xfs_buf_ioend_fail(bp);
-		goto shutdown;
-	}
-
-	*bpp = bp;
-	return 0;
-
-abort:
-	xfs_iflush_abort(ip);
-shutdown:
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-	return error;
-}
-
-STATIC int
-xfs_iflush_int(
-	struct xfs_inode	*ip,
 	struct xfs_buf		*bp)
 {
 	struct xfs_inode_log_item *iip = ip->i_itemp;
@@ -3706,7 +3446,7 @@ xfs_iflush_int(
 	ASSERT(xfs_isiflocked(ip));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-	ASSERT(iip != NULL && iip->ili_fields != 0);
+	ASSERT(iip->ili_item.li_buf == bp);
 
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
@@ -3801,7 +3541,6 @@ xfs_iflush_int(
 	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
 	if (XFS_IFORK_Q(ip))
 		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
-	xfs_inobp_check(mp, bp);
 
 	/*
 	 * We've recorded everything logged in the inode, so we'd like to clear
@@ -3818,40 +3557,148 @@ xfs_iflush_int(
 	 * know that the information those bits represent is permanently on
 	 * disk.  As long as the flush completes before the inode is logged
 	 * again, then both ili_fields and ili_last_fields will be cleared.
-	 *
-	 * We can play with the ili_fields bits here, because the inode lock
-	 * must be held exclusively in order to set bits there and the flush
-	 * lock protects the ili_last_fields bits.  Set ili_logged so the flush
-	 * done routine can tell whether or not to look in the AIL.  Also, store
-	 * the current LSN of the inode so that we can tell whether the item has
-	 * moved in the AIL from xfs_iflush_done().  In order to read the lsn we
-	 * need the AIL lock, because it is a 64 bit value that cannot be read
-	 * atomically.
 	 */
 	error = 0;
 flush_out:
+	spin_lock(&iip->ili_lock);
 	iip->ili_last_fields = iip->ili_fields;
 	iip->ili_fields = 0;
 	iip->ili_fsync_fields = 0;
-	iip->ili_logged = 1;
+	spin_unlock(&iip->ili_lock);
 
+	/*
+	 * Store the current LSN of the inode so that we can tell whether the
+	 * item has moved in the AIL from xfs_iflush_done().
+	 */
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 				&iip->ili_item.li_lsn);
 
+	/* generate the checksum. */
+	xfs_dinode_calc_crc(mp, dip);
+	return error;
+}
+
+/*
+ * Non-blocking flush of dirty inode metadata into the backing buffer.
+ *
+ * The caller must have a reference to the inode and hold the cluster buffer
+ * locked. The function will walk across all the inodes on the cluster buffer it
+ * can find and lock without blocking, and flush them to the cluster buffer.
+ *
+ * On successful flushing of at least one inode, the caller must write out the
+ * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and
+ * the caller needs to release the buffer. On failure, the filesystem will be
+ * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED
+ * will be returned.
+ */
+int
+xfs_iflush_cluster(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_log_item	*lip, *n;
+	struct xfs_inode	*ip;
+	struct xfs_inode_log_item *iip;
+	int			clcount = 0;
+	int			error = 0;
+
 	/*
-	 * Attach the inode item callback to the buffer whether the flush
-	 * succeeded or not. If not, the caller will shut down and fail I/O
-	 * completion on the buffer to remove the inode from the AIL and release
-	 * the flush lock.
+	 * We must use the safe variant here as on shutdown xfs_iflush_abort()
+	 * can remove itself from the list.
 	 */
-	xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
+	list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
+		iip = (struct xfs_inode_log_item *)lip;
+		ip = iip->ili_inode;
 
-	/* generate the checksum. */
-	xfs_dinode_calc_crc(mp, dip);
+		/*
+		 * Quick and dirty check to avoid locks if possible.
+		 */
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK))
+			continue;
+		if (xfs_ipincount(ip))
+			continue;
+
+		/*
+		 * The inode is still attached to the buffer, which means it is
+		 * dirty but reclaim might try to grab it. Check carefully for
+		 * that, and grab the ilock while still holding the i_flags_lock
+		 * to guarantee reclaim will not be able to reclaim this inode
+		 * once we drop the i_flags_lock.
+		 */
+		spin_lock(&ip->i_flags_lock);
+		ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK)) {
+			spin_unlock(&ip->i_flags_lock);
+			continue;
+		}
+
+		/*
+		 * ILOCK will pin the inode against reclaim and prevent
+		 * concurrent transactions modifying the inode while we are
+		 * flushing the inode.
+		 */
+		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+			spin_unlock(&ip->i_flags_lock);
+			continue;
+		}
+		spin_unlock(&ip->i_flags_lock);
+
+		/*
+		 * Skip inodes that are already flush locked as they have
+		 * already been written to the buffer.
+		 */
+		if (!xfs_iflock_nowait(ip)) {
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			continue;
+		}
+
+		/*
+		 * Abort flushing this inode if we are shut down because the
+		 * inode may not currently be in the AIL. This can occur when
+		 * log I/O failure unpins the inode without inserting into the
+		 * AIL, leaving a dirty/unpinned inode attached to the buffer
+		 * that otherwise looks like it should be flushed.
+		 */
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			xfs_iunpin_wait(ip);
+			/* xfs_iflush_abort() drops the flush lock */
+			xfs_iflush_abort(ip);
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			error = -EIO;
+			continue;
+		}
+
+		/* don't block waiting on a log force to unpin dirty inodes */
+		if (xfs_ipincount(ip)) {
+			xfs_ifunlock(ip);
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			continue;
+		}
+
+		if (!xfs_inode_clean(ip))
+			error = xfs_iflush(ip, bp);
+		else
+			xfs_ifunlock(ip);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		if (error)
+			break;
+		clcount++;
+	}
+
+	if (error) {
+		bp->b_flags |= XBF_ASYNC;
+		xfs_buf_ioend_fail(bp);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		return error;
+	}
+
+	if (!clcount)
+		return -EAGAIN;
+
+	XFS_STATS_INC(mp, xs_icluster_flushcnt);
+	XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
+	return 0;
 
-	ASSERT(!list_empty(&bp->b_li_list));
-	ASSERT(bp->b_iodone != NULL);
-	return error;
 }
 
 /* Release an inode. */
@@ -3881,3 +3728,96 @@ xfs_log_force_inode(
 		return 0;
 	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
 }
+
+/*
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding.  The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
+ */
+static int
+xfs_iolock_two_inodes_and_break_layout(
+	struct inode		*src,
+	struct inode		*dest)
+{
+	int			error;
+
+	if (src > dest)
+		swap(src, dest);
+
+retry:
+	/* Wait to break both inodes' layouts before we start locking. */
+	error = break_layout(src, true);
+	if (error)
+		return error;
+	if (src != dest) {
+		error = break_layout(dest, true);
+		if (error)
+			return error;
+	}
+
+	/* Lock one inode and make sure nobody got in and leased it. */
+	inode_lock(src);
+	error = break_layout(src, false);
+	if (error) {
+		inode_unlock(src);
+		if (error == -EWOULDBLOCK)
+			goto retry;
+		return error;
+	}
+
+	if (src == dest)
+		return 0;
+
+	/* Lock the other inode and make sure nobody got in and leased it. */
+	inode_lock_nested(dest, I_MUTEX_NONDIR2);
+	error = break_layout(dest, false);
+	if (error) {
+		inode_unlock(src);
+		inode_unlock(dest);
+		if (error == -EWOULDBLOCK)
+			goto retry;
+		return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
+ * mmap activity.
+ */
+int
+xfs_ilock2_io_mmap(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	int			ret;
+
+	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
+	if (ret)
+		return ret;
+	if (ip1 == ip2)
+		xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
+	else
+		xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
+				    ip2, XFS_MMAPLOCK_EXCL);
+	return 0;
+}
+
+/* Unlock both inodes to allow IO and mmap activity. */
+void
+xfs_iunlock2_io_mmap(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	bool			same_inode = (ip1 == ip2);
+
+	xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+	if (!same_inode)
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+	inode_unlock(VFS_I(ip2));
+	if (!same_inode)
+		inode_unlock(VFS_I(ip1));
+}