ocfs2: o2net: fix packets lost issue when reconnect

index c6b90e6..76ef3d8 100644
@@ -1536,16 +1536,20 @@ static void o2net_idle_timer(unsigned long data)
 #endif
 
 	printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been "
-	       "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc),
-	       msecs / 1000, msecs % 1000);
+	       "idle for %lu.%lu secs.\n",
+	       SC_NODEF_ARGS(sc), msecs / 1000, msecs % 1000);
 
-	/*
-	 * Initialize the nn_timeout so that the next connection attempt
-	 * will continue in o2net_start_connect.
+	/* idle timerout happen, don't shutdown the connection, but
+	 * make fence decision. Maybe the connection can recover before
+	 * the decision is made.
 	 */
 	atomic_set(&nn->nn_timeout, 1);
+	o2quo_conn_err(o2net_num_from_nn(nn));
+	queue_delayed_work(o2net_wq, &nn->nn_still_up,
+			msecs_to_jiffies(O2NET_QUORUM_DELAY_MS));
+
+	o2net_sc_reset_idle_timer(sc);
 
-	o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
 }
 
 static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)

@@ -1560,6 +1564,15 @@ static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)
 
 static void o2net_sc_postpone_idle(struct o2net_sock_container *sc)
 {
+	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+
+	/* clear fence decision since the connection recover from timeout*/
+	if (atomic_read(&nn->nn_timeout)) {
+		o2quo_conn_up(o2net_num_from_nn(nn));
+		cancel_delayed_work(&nn->nn_still_up);
+		atomic_set(&nn->nn_timeout, 0);
+	}
+
 	/* Only push out an existing timer */
 	if (timer_pending(&sc->sc_idle_timeout))
 		o2net_sc_reset_idle_timer(sc);

index 76ef3d8..eae58d8 100644
@@ -1480,6 +1480,14 @@ static int o2net_set_nodelay(struct socket *sock)
 	return ret;
 }
 
+static int o2net_set_usertimeout(struct socket *sock)
+{
+	int user_timeout = O2NET_TCP_USER_TIMEOUT;
+
+	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&user_timeout, sizeof(user_timeout));
+}
+
 static void o2net_initialize_handshake(void)
 {
 	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(

@@ -1663,6 +1671,12 @@ static void o2net_start_connect(struct work_struct *work)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 
 	spin_lock(&nn->nn_lock);

@@ -1842,6 +1856,12 @@ static int o2net_accept_one(struct socket *sock)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(new_sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	slen = sizeof(sin);
 	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin,
 				       &slen, 1);

index 5bada2a..c571e84 100644
@@ -63,6 +63,7 @@ typedef void (o2net_post_msg_handler_func)(int status, void *data,
 #define O2NET_KEEPALIVE_DELAY_MS_DEFAULT	2000
 #define O2NET_IDLE_TIMEOUT_MS_DEFAULT		30000
 
+#define O2NET_TCP_USER_TIMEOUT			0x7fffffff
 
 /* TODO: figure this out.... */
 static inline int o2net_link_down(int err, struct socket *sock)

index 1ec141e..62e8ec6 100644
@@ -160,9 +160,18 @@ static void o2quo_make_decision(struct work_struct *work)
 	}
 
 out:
-	spin_unlock(&qs->qs_lock);
-	if (fence)
+	if (fence) {
+		spin_unlock(&qs->qs_lock);
 		o2quo_fence_self();
+	} else {
+		mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, "
+			"connected: %d, lowest: %d (%sreachable)\n",
+			qs->qs_heartbeating, qs->qs_connected, lowest_hb,
+			lowest_reachable ? "" : "un");
+		spin_unlock(&qs->qs_lock);
+
+	}
+
 }
 
 static void o2quo_set_hold(struct o2quo_state *qs, u8 node)