[PATCH v3 2/3] ceph/mds_client: stop checking a stale MDS map after dropping mutex

[Max Kellermann]

check_new_map() drops `mdsc->mutex` in several slow paths.  Another
map handler can install a newer map and destroy the map being checked
before the original invocation re-locks the mutex.

Use the `mdsmap->m_epoch` field to identify stale maps.

Signed-off-by: Max Kellermann <max.kellermann@xxxxxxxxx>
---
 fs/ceph/mds_client.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 160f23e2edd3..03809328e4aa 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5782,6 +5782,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			  struct ceph_mdsmap *newmap,
 			  struct ceph_mdsmap *oldmap)
 {
+	u32 map_epoch = newmap->m_epoch;
 	int i, j, err;
 	int oldstate, newstate;
 	struct ceph_mds_session *s;
@@ -5825,6 +5826,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			ceph_put_mds_session(s);
 
 			mutex_lock(&mdsc->mutex);
+			if (mdsc->mdsmap->m_epoch != map_epoch)
+				return;
 			kick_requests(mdsc, i);
 			continue;
 		}
@@ -5836,6 +5839,11 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			mutex_unlock(&mdsc->mutex);
 			mutex_lock(&s->s_mutex);
 			mutex_lock(&mdsc->mutex);
+			if (mdsc->mdsmap->m_epoch != map_epoch) {
+				mutex_unlock(&s->s_mutex);
+				ceph_put_mds_session(s);
+				return;
+			}
 			ceph_con_close(&s->s_con);
 			mutex_unlock(&s->s_mutex);
 			s->s_state = CEPH_MDS_SESSION_RESTARTING;
@@ -5859,6 +5867,10 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 					       "mds%d reconnect failed: %d\n",
 					       i, rc);
 			mutex_lock(&mdsc->mutex);
+			if (mdsc->mdsmap->m_epoch != map_epoch) {
+				ceph_put_mds_session(s);
+				return;
+			}
 		}
 
 		/*
@@ -5874,6 +5886,11 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			mutex_unlock(&mdsc->mutex);
 			mutex_lock(&s->s_mutex);
 			mutex_lock(&mdsc->mutex);
+			if (mdsc->mdsmap->m_epoch != map_epoch) {
+				mutex_unlock(&s->s_mutex);
+				ceph_put_mds_session(s);
+				return;
+			}
 			ceph_kick_flushing_caps(mdsc, s);
 			mutex_unlock(&s->s_mutex);
 			wake_up_session_caps(s, RECONNECT);
@@ -5929,6 +5946,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 				       i, err);
 		ceph_put_mds_session(s);
 		mutex_lock(&mdsc->mutex);
+		if (mdsc->mdsmap->m_epoch != map_epoch)
+			return;
 	}
 
 	for (i = 0; i < newmap->possible_max_rank && i < mdsc->max_sessions; i++) {
-- 
2.47.3