ceph: defer stopping mdsc delayed_work

[ Upstream commit e7e607bd00 ]

Flushing the dirty buffer may take a long time if the cluster is
overloaded or if there is network issue. So we should ping the
MDSs periodically to keep alive, else the MDS will blocklist
the kclient.

Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/61843
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

fs/ceph/mds_client.c

@@ -4074,7 +4074,7 @@ static void delayed_work(struct work_struct *work)
 
 	dout("mdsc delayed_work\n");
 
-	if (mdsc->stopping)
+	if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED)
 		return;
 
 	mutex_lock(&mdsc->mutex);
@@ -4246,7 +4246,7 @@ static void wait_requests(struct ceph_mds_client *mdsc)
 void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
 {
 	dout("pre_umount\n");
-	mdsc->stopping = 1;
+	mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN;
 
 	lock_unlock_sessions(mdsc);
 	ceph_flush_dirty_caps(mdsc);

fs/ceph/mds_client.h

@@ -348,6 +348,11 @@ struct cap_wait {
 	int			want;
 };
 
+enum {
+       CEPH_MDSC_STOPPING_BEGIN = 1,
+       CEPH_MDSC_STOPPING_FLUSHED = 2,
+};
+
 /*
  * mds client state
  */

fs/ceph/super.c

@@ -1180,6 +1180,16 @@ static void ceph_kill_sb(struct super_block *s)
 	ceph_mdsc_pre_umount(fsc->mdsc);
 	flush_fs_workqueues(fsc);
 
+	/*
+	 * Though the kill_anon_super() will finally trigger the
+	 * sync_filesystem() anyway, we still need to do it here
+	 * and then bump the stage of shutdown to stop the work
+	 * queue as earlier as possible.
+	 */
+	sync_filesystem(s);
+
+	fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
+
 	kill_anon_super(s);
 
 	fsc->client->extra_mon_dispatch = NULL;