ceph: reduce contention in ceph_check_delayed_caps()

Function ceph_check_delayed_caps() is called from the mdsc->delayed_work
workqueue and it can be kept looping for quite some time if caps keep
being added back to the mdsc->cap_delay_list.  This may result in the
watchdog tainting the kernel with the softlockup flag.

This patch breaks this loop if the caps have been recently (i.e. during
the loop execution).  Any new caps added to the list will be handled in
the next run.

Also, allow schedule_delayed() callers to explicitly set the delay value
instead of defaulting to 5s, so we can ensure that it runs soon
afterward if it looks like there is more work.

Cc: stable@vger.kernel.org
URL: https://tracker.ceph.com/issues/46284
Signed-off-by: Luis Henriques <lhenriques@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 16 insertions, 9 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9db1b39df773..afdc20213876 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4490,22 +4490,29 @@ void inc_session_sequence(struct ceph_mds_session *s)
 }
 
 /*
- * delayed work -- periodically trim expired leases, renew caps with mds
+ * delayed work -- periodically trim expired leases, renew caps with mds.  If
+ * the @delay parameter is set to 0 or if it's more than 5 secs, the default
+ * workqueue delay value of 5 secs will be used.
  */
-static void schedule_delayed(struct ceph_mds_client *mdsc)
+static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay)
 {
-	int delay = 5;
-	unsigned hz = round_jiffies_relative(HZ * delay);
-	schedule_delayed_work(&mdsc->delayed_work, hz);
+	unsigned long max_delay = HZ * 5;
+
+	/* 5 secs default delay */
+	if (!delay || (delay > max_delay))
+		delay = max_delay;
+	schedule_delayed_work(&mdsc->delayed_work,
+			      round_jiffies_relative(delay));
 }
 
 static void delayed_work(struct work_struct *work)
 {
-	int i;
 	struct ceph_mds_client *mdsc =
 		container_of(work, struct ceph_mds_client, delayed_work.work);
+	unsigned long delay;
 	int renew_interval;
 	int renew_caps;
+	int i;
 
 	dout("mdsc delayed_work\n");
 
@@ -4545,7 +4552,7 @@ static void delayed_work(struct work_struct *work)
 	}
 	mutex_unlock(&mdsc->mutex);
 
-	ceph_check_delayed_caps(mdsc);
+	delay = ceph_check_delayed_caps(mdsc);
 
 	ceph_queue_cap_reclaim_work(mdsc);
 
@@ -4553,7 +4560,7 @@ static void delayed_work(struct work_struct *work)
 
 	maybe_recover_session(mdsc);
 
-	schedule_delayed(mdsc);
+	schedule_delayed(mdsc, delay);
 }
 
 int ceph_mdsc_init(struct ceph_fs_client *fsc)
@@ -5030,7 +5037,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 			  mdsc->mdsmap->m_epoch);
 
 	mutex_unlock(&mdsc->mutex);
-	schedule_delayed(mdsc);
+	schedule_delayed(mdsc, 0);
 	return;
 
 bad_unlock: