SUNRPC: Prevent thundering herd when the socket is not connected

commit ed7dc973bd91da234d93aff6d033a5206a6c9885 upstream.

If the socket is not connected, then we want to initiate a reconnect
rather that trying to transmit requests. If there is a large number
of requests queued and waiting for the lock in call_transmit(),
then it can take a while for one of the to loop back and retake
the lock in call_connect.

Fixes: 89f90fe1ad8b ("SUNRPC: Allow calls to xprt_transmit() to drain...")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 17 insertions, 4 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index d7ec6132c046..47d664ce64ba 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1786,7 +1786,12 @@ call_encode(struct rpc_task *task)
 		xprt_request_enqueue_receive(task);
 	xprt_request_enqueue_transmit(task);
 out:
-	task->tk_action = call_bind;
+	task->tk_action = call_transmit;
+	/* Check that the connection is OK */
+	if (!xprt_bound(task->tk_xprt))
+		task->tk_action = call_bind;
+	else if (!xprt_connected(task->tk_xprt))
+		task->tk_action = call_connect;
 }
 
 /*
@@ -1978,13 +1983,19 @@ call_transmit(struct rpc_task *task)
 {
 	dprint_status(task);
 
-	task->tk_status = 0;
+	task->tk_action = call_transmit_status;
 	if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) {
 		if (!xprt_prepare_transmit(task))
 			return;
-		xprt_transmit(task);
+		task->tk_status = 0;
+		if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) {
+			if (!xprt_connected(task->tk_xprt)) {
+				task->tk_status = -ENOTCONN;
+				return;
+			}
+			xprt_transmit(task);
+		}
 	}
-	task->tk_action = call_transmit_status;
 	xprt_end_transmit(task);
 }
 
@@ -2046,6 +2057,8 @@ call_transmit_status(struct rpc_task *task)
 	case -EADDRINUSE:
 	case -ENOTCONN:
 	case -EPIPE:
+		task->tk_action = call_bind;
+		task->tk_status = 0;
 		break;
 	}
 }