xfs: replace global xfslogd wq with per-mount wq

The xfslogd workqueue is a global, single-job workqueue for buffer ioend
processing. This means we allow for a single work item at a time for all
possible XFS mounts on a system. fsstress testing in loopback XFS over
XFS configurations has reproduced xfslogd deadlocks due to the single
threaded nature of the queue and dependencies introduced between the
separate XFS instances by online discard (-o discard).

Discard over a loopback device converts the discard request to a hole
punch (fallocate) on the underlying file. Online discard requests are
issued synchronously and from xfslogd context in XFS, hence the xfslogd
workqueue is blocked in the upper fs waiting on a hole punch request to
be servied in the lower fs. If the lower fs issues I/O that depends on
xfslogd to complete, both filesystems end up hung indefinitely. This is
reproduced reliabily by generic/013 on XFS->loop->XFS test devices with
the '-o discard' mount option.

Further, docker implementations appear to use this kind of configuration
for container instance filesystems by default (container fs->dm->
loop->base fs) and therefore are subject to this deadlock when running
on XFS.

Replace the global xfslogd workqueue with a per-mount variant. This
guarantees each mount access to a single worker and prevents deadlocks
due to inter-fs dependencies introduced by discard. Since the queue is
only responsible for buffer iodone processing at this point in time,
rename xfslogd to xfs-buf.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/xfs_buf.c

@@ -44,8 +44,6 @@
 
 static kmem_zone_t *xfs_buf_zone;
 
-static struct workqueue_struct *xfslogd_workqueue;
-
 #ifdef XFS_BUF_LOCK_TRACKING
 # define XB_SET_OWNER(bp)	((bp)->b_last_holder = current->pid)
 # define XB_CLEAR_OWNER(bp)	((bp)->b_last_holder = -1)
@@ -1053,7 +1051,7 @@ xfs_buf_ioend_async(
 	struct xfs_buf	*bp)
 {
 	INIT_WORK(&bp->b_iodone_work, xfs_buf_ioend_work);
-	queue_work(xfslogd_workqueue, &bp->b_iodone_work);
+	queue_work(bp->b_target->bt_mount->m_buf_workqueue, &bp->b_iodone_work);
 }
 
 void
@@ -1882,15 +1880,8 @@ xfs_buf_init(void)
 	if (!xfs_buf_zone)
 		goto out;
 
-	xfslogd_workqueue = alloc_workqueue("xfslogd",
-				WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE, 1);
-	if (!xfslogd_workqueue)
-		goto out_free_buf_zone;
-
 	return 0;
 
- out_free_buf_zone:
-	kmem_zone_destroy(xfs_buf_zone);
  out:
 	return -ENOMEM;
 }
@@ -1898,6 +1889,5 @@ xfs_buf_init(void)
 void
 xfs_buf_terminate(void)
 {
-	destroy_workqueue(xfslogd_workqueue);
 	kmem_zone_destroy(xfs_buf_zone);
 }

fs/xfs/xfs_mount.h

@@ -168,6 +168,7 @@ typedef struct xfs_mount {
 						/* low free space thresholds */
 	struct xfs_kobj		m_kobj;
 
+	struct workqueue_struct *m_buf_workqueue;
 	struct workqueue_struct	*m_data_workqueue;
 	struct workqueue_struct	*m_unwritten_workqueue;
 	struct workqueue_struct	*m_cil_workqueue;

fs/xfs/xfs_super.c

@@ -842,10 +842,16 @@ STATIC int
 xfs_init_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
+			WQ_MEM_RECLAIM|WQ_HIGHPRI|WQ_FREEZABLE, 1,
+			mp->m_fsname);
+	if (!mp->m_buf_workqueue)
+		goto out;
+
 	mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
 			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_data_workqueue)
-		goto out;
+		goto out_destroy_buf;
 
 	mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
 			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
@@ -884,6 +890,8 @@ out_destroy_unwritten:
 	destroy_workqueue(mp->m_unwritten_workqueue);
 out_destroy_data_iodone_queue:
 	destroy_workqueue(mp->m_data_workqueue);
+out_destroy_buf:
+	destroy_workqueue(mp->m_buf_workqueue);
 out:
 	return -ENOMEM;
 }
@@ -898,6 +906,7 @@ xfs_destroy_mount_workqueues(
 	destroy_workqueue(mp->m_cil_workqueue);
 	destroy_workqueue(mp->m_data_workqueue);
 	destroy_workqueue(mp->m_unwritten_workqueue);
+	destroy_workqueue(mp->m_buf_workqueue);
 }
 
 /*