cifs: smbd: avoid reconnect lockup

During transport reconnect, other processes may have registered memory
and blocked on transport. This creates a deadlock situation because the
transport resources can't be freed, and reconnect is blocked.

Fix this by returning to upper layer on timeout. Before returning,
transport status is set to reconnecting so other processes will release
memory registration resources.

Upper layer will retry the reconnect. This is not in fast I/O path so
setting the timeout to 5 seconds.

Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
CC: Stable <stable@vger.kernel.org>

1 files changed, 8 insertions, 4 deletions

diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 5aa0b54b32ce..3f7883e2e14d 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1498,8 +1498,8 @@ int smbd_reconnect(struct TCP_Server_Info *server)
 	log_rdma_event(INFO, "reconnecting rdma session\n");
 
 	if (!server->smbd_conn) {
-		log_rdma_event(ERR, "rdma session already destroyed\n");
-		return -EINVAL;
+		log_rdma_event(INFO, "rdma session already destroyed\n");
+		goto create_conn;
 	}
 
 	/*
@@ -1512,15 +1512,19 @@ int smbd_reconnect(struct TCP_Server_Info *server)
 	}
 
 	/* wait until the transport is destroyed */
-	wait_event(server->smbd_conn->wait_destroy,
-		server->smbd_conn->transport_status == SMBD_DESTROYED);
+	if (!wait_event_timeout(server->smbd_conn->wait_destroy,
+		server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ))
+		return -EAGAIN;
 
 	destroy_workqueue(server->smbd_conn->workqueue);
 	kfree(server->smbd_conn);
 
+create_conn:
 	log_rdma_event(INFO, "creating rdma session\n");
 	server->smbd_conn = smbd_get_connection(
 		server, (struct sockaddr *) &server->dstaddr);
+	log_rdma_event(INFO, "created rdma session info=%p\n",
+		server->smbd_conn);
 
 	return server->smbd_conn ? 0 : -ENOENT;
 }