xprtrdma is currently throwing away queued completions during
a reconnect. RPC replies posted just before connection loss, or
successful completions that change the state of an FRMR, can be
missed.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
Tested-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
Tested-by: Shirley Ma <shirley.ma@xxxxxxxxxx>
Tested-by: Devesh Sharma <devesh.sharma@xxxxxxxxxx>
---
net/sunrpc/xprtrdma/verbs.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 0d5187d..7fd457e 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -310,6 +310,13 @@ rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context)
rpcrdma_recvcq_poll(cq, ep);
}
+static void
+rpcrdma_flush_cqs(struct rpcrdma_ep *ep)
+{
+ rpcrdma_recvcq_upcall(ep->rep_attr.recv_cq, ep);
+ rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep);
+}
+
#ifdef RPC_DEBUG
static const char * const conn[] = {
"address resolved",
@@ -872,9 +879,7 @@ retry:
if (rc && rc != -ENOTCONN)
dprintk("RPC: %s: rpcrdma_ep_disconnect"
" status %i\n", __func__, rc);
-
- rpcrdma_clean_cq(ep->rep_attr.recv_cq);
- rpcrdma_clean_cq(ep->rep_attr.send_cq);
+ rpcrdma_flush_cqs(ep);
xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
id = rpcrdma_create_id(xprt, ia,
@@ -985,8 +990,7 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
int rc;
- rpcrdma_clean_cq(ep->rep_attr.recv_cq);
- rpcrdma_clean_cq(ep->rep_attr.send_cq);
+ rpcrdma_flush_cqs(ep);
rc = rdma_disconnect(ia->ri_id);
if (!rc) {
/* returns without wait if not connected */
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
