xprtrdma: Fix handling of connect errors

Ensure that the connect worker is awoken if an attempt to establish
a connection is unsuccessful. Otherwise the worker waits forever
and the transport workload hangs.

Connect errors should not attempt to destroy the ep, since the
connect worker continues to use it after the handler runs, so these
errors are now handled independently of DISCONNECTED events.

Reported-by: Dan Aloni <dan@kernelim.com>
Fixes: e28ce90083f0 ("xprtrdma: kmalloc rpcrdma_ep separate from rpcrdma_xprt")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 13d671d..75c6467 100644 (file)
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -281,17 +281,19 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
                break;
        case RDMA_CM_EVENT_CONNECT_ERROR:
                ep->re_connect_status = -ENOTCONN;
-               goto disconnected;
+               goto wake_connect_worker;
        case RDMA_CM_EVENT_UNREACHABLE:
                ep->re_connect_status = -ENETUNREACH;
-               goto disconnected;
+               goto wake_connect_worker;
        case RDMA_CM_EVENT_REJECTED:
                dprintk("rpcrdma: connection to %pISpc rejected: %s\n",
                        sap, rdma_reject_msg(id, event->status));
                ep->re_connect_status = -ECONNREFUSED;
                if (event->status == IB_CM_REJ_STALE_CONN)
                        ep->re_connect_status = -ENOTCONN;
-               goto disconnected;
+wake_connect_worker:
+               wake_up_all(&ep->re_connect_wait);
+               return 0;
        case RDMA_CM_EVENT_DISCONNECTED:
                ep->re_connect_status = -ECONNABORTED;
 disconnected: