SUNRPC: Don't disconnect more than once if retransmitting NFSv4 requests

NFSv4 requires us to ensure that we break the TCP connection before we're
allowed to retransmit a request. However in the case where we're
retransmitting several requests that have been sent on the same
connection, we need to ensure that we don't interfere with the attempt to
reconnect and/or break the connection again once it has been established.

We therefore introduce a 'connection' cookie that is bumped every time a
connection is broken. This allows requests to track if they need to force a
disconnection.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

3 files changed, 35 insertions, 2 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 3ae560464513..8773b4342c92 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1120,7 +1120,8 @@ call_status(struct rpc_task *task)
 	case -ETIMEDOUT:
 		task->tk_action = call_timeout;
 		if (task->tk_client->cl_discrtry)
-			xprt_force_disconnect(task->tk_xprt);
+			xprt_conditional_disconnect(task->tk_xprt,
+					req->rq_connect_cookie);
 		break;
 	case -ECONNREFUSED:
 	case -ENOTCONN:
@@ -1245,7 +1246,8 @@ out_retry:
 	if (task->tk_rqstp == req) {
 		req->rq_received = req->rq_rcv_buf.len = 0;
 		if (task->tk_client->cl_discrtry)
-			xprt_force_disconnect(task->tk_xprt);
+			xprt_conditional_disconnect(task->tk_xprt,
+					req->rq_connect_cookie);
 	}
 }
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index a0646a3b4a39..75d748eee0eb 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -606,6 +606,34 @@ void xprt_force_disconnect(struct rpc_xprt *xprt)
 	spin_unlock_bh(&xprt->transport_lock);
 }
 
+/**
+ * xprt_conditional_disconnect - force a transport to disconnect
+ * @xprt: transport to disconnect
+ * @cookie: 'connection cookie'
+ *
+ * This attempts to break the connection if and only if 'cookie' matches
+ * the current transport 'connection cookie'. It ensures that we don't
+ * try to break the connection more than once when we need to retransmit
+ * a batch of RPC requests.
+ *
+ */
+void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
+{
+	/* Don't race with the test_bit() in xprt_clear_locked() */
+	spin_lock_bh(&xprt->transport_lock);
+	if (cookie != xprt->connect_cookie)
+		goto out;
+	if (test_bit(XPRT_CLOSING, &xprt->state) || !xprt_connected(xprt))
+		goto out;
+	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
+	/* Try to schedule an autoclose RPC call */
+	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
+		queue_work(rpciod_workqueue, &xprt->task_cleanup);
+	xprt_wake_pending_tasks(xprt, -ENOTCONN);
+out:
+	spin_unlock_bh(&xprt->transport_lock);
+}
+
 static void
 xprt_init_autodisconnect(unsigned long data)
 {
@@ -849,6 +877,7 @@ void xprt_transmit(struct rpc_task *task)
 	} else if (!req->rq_bytes_sent)
 		return;
 
+	req->rq_connect_cookie = xprt->connect_cookie;
 	status = xprt->ops->send_request(task);
 	if (status == 0) {
 		dprintk("RPC: %5u xmit complete\n", task->tk_pid);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 4a567a93e6ad..63d79e347c00 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1142,6 +1142,7 @@ static void xs_tcp_state_change(struct sock *sk)
 		break;
 	case TCP_FIN_WAIT1:
 		/* The client initiated a shutdown of the socket */
+		xprt->connect_cookie++;
 		xprt->reestablish_timeout = 0;
 		set_bit(XPRT_CLOSING, &xprt->state);
 		smp_mb__before_clear_bit();
@@ -1154,6 +1155,7 @@ static void xs_tcp_state_change(struct sock *sk)
 		set_bit(XPRT_CLOSING, &xprt->state);
 		xprt_force_disconnect(xprt);
 	case TCP_SYN_SENT:
+		xprt->connect_cookie++;
 	case TCP_CLOSING:
 		/*
 		 * If the server closed down the connection, make sure that