ceph: reconnect to the export targets on new mdsmaps

In the case where the export MDS has crashed just after the EImportStart
journal is flushed, a standby MDS takes over for it and when replaying
the EImportStart journal the MDS will wait the client to reconnect. That
may never happen because the client may not have registered or opened
the sessions yet.

When receiving a new map, ensure we reconnect to valid export targets as
well if their sessions don't exist yet.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

2 files changed, 65 insertions, 4 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index b1f8a4025195..ba1036f09127 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -11,6 +11,7 @@
 #include <linux/ratelimit.h>
 #include <linux/bits.h>
 #include <linux/ktime.h>
+#include <linux/bitmap.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -4171,13 +4172,21 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			  struct ceph_mdsmap *newmap,
 			  struct ceph_mdsmap *oldmap)
 {
-	int i;
+	int i, j, err;
 	int oldstate, newstate;
 	struct ceph_mds_session *s;
+	unsigned long targets[DIV_ROUND_UP(CEPH_MAX_MDS, sizeof(unsigned long))] = {0};
 
 	dout("check_new_map new %u old %u\n",
 	     newmap->m_epoch, oldmap->m_epoch);
 
+	if (newmap->m_info) {
+		for (i = 0; i < newmap->possible_max_rank; i++) {
+			for (j = 0; j < newmap->m_info[i].num_export_targets; j++)
+				set_bit(newmap->m_info[i].export_targets[j], targets);
+		}
+	}
+
 	for (i = 0; i < oldmap->possible_max_rank && i < mdsc->max_sessions; i++) {
 		if (!mdsc->sessions[i])
 			continue;
@@ -4231,6 +4240,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		if (s->s_state == CEPH_MDS_SESSION_RESTARTING &&
 		    newstate >= CEPH_MDS_STATE_RECONNECT) {
 			mutex_unlock(&mdsc->mutex);
+			clear_bit(i, targets);
 			send_mds_reconnect(mdsc, s);
 			mutex_lock(&mdsc->mutex);
 		}
@@ -4253,6 +4263,51 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		}
 	}
 
+	/*
+	 * Only open and reconnect sessions that don't exist yet.
+	 */
+	for (i = 0; i < newmap->possible_max_rank; i++) {
+		/*
+		 * In case the import MDS is crashed just after
+		 * the EImportStart journal is flushed, so when
+		 * a standby MDS takes over it and is replaying
+		 * the EImportStart journal the new MDS daemon
+		 * will wait the client to reconnect it, but the
+		 * client may never register/open the session yet.
+		 *
+		 * Will try to reconnect that MDS daemon if the
+		 * rank number is in the export targets array and
+		 * is the up:reconnect state.
+		 */
+		newstate = ceph_mdsmap_get_state(newmap, i);
+		if (!test_bit(i, targets) || newstate != CEPH_MDS_STATE_RECONNECT)
+			continue;
+
+		/*
+		 * The session maybe registered and opened by some
+		 * requests which were choosing random MDSes during
+		 * the mdsc->mutex's unlock/lock gap below in rare
+		 * case. But the related MDS daemon will just queue
+		 * that requests and be still waiting for the client's
+		 * reconnection request in up:reconnect state.
+		 */
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (likely(!s)) {
+			s = __open_export_target_session(mdsc, i);
+			if (IS_ERR(s)) {
+				err = PTR_ERR(s);
+				pr_err("failed to open export target session, err %d\n",
+				       err);
+				continue;
+			}
+		}
+		dout("send reconnect to export target mds.%d\n", i);
+		mutex_unlock(&mdsc->mutex);
+		send_mds_reconnect(mdsc, s);
+		ceph_put_mds_session(s);
+		mutex_lock(&mdsc->mutex);
+	}
+
 	for (i = 0; i < newmap->possible_max_rank && i < mdsc->max_sessions; i++) {
 		s = mdsc->sessions[i];
 		if (!s)
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 3c444b9cb17b..61d67cbcb367 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -122,6 +122,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 	int err;
 	u8 mdsmap_v;
 	u16 mdsmap_ev;
+	u32 target;
 
 	m = kzalloc(sizeof(*m), GFP_NOFS);
 	if (!m)
@@ -260,9 +261,14 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 						       sizeof(u32), GFP_NOFS);
 			if (!info->export_targets)
 				goto nomem;
-			for (j = 0; j < num_export_targets; j++)
-				info->export_targets[j] =
-				       ceph_decode_32(&pexport_targets);
+			for (j = 0; j < num_export_targets; j++) {
+				target = ceph_decode_32(&pexport_targets);
+				if (target >= m->possible_max_rank) {
+					err = -EIO;
+					goto corrupt;
+				}
+				info->export_targets[j] = target;
+			}
 		} else {
 			info->export_targets = NULL;
 		}