5 files changed, 53 insertions, 30 deletions

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 61ed2a8764ba..86187dad1440 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -127,7 +127,7 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 
 /*
  * This is the only path that sets tc->t_sock.  Send and receive trust that
- * it is set.  The RDS_CONN_CONNECTED bit protects those paths from being
+ * it is set.  The RDS_CONN_UP bit protects those paths from being
  * called while it isn't set.
  */
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
@@ -216,6 +216,7 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 	if (!tc)
 		return -ENOMEM;
 
+	mutex_init(&tc->t_conn_lock);
 	tc->t_sock = NULL;
 	tc->t_tinc = NULL;
 	tc->t_tinc_hdr_rem = sizeof(struct rds_header);
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 64f873c0c6b6..41c228300525 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -12,6 +12,10 @@ struct rds_tcp_connection {
 
 	struct list_head	t_tcp_node;
 	struct rds_connection   *conn;
+	/* t_conn_lock synchronizes the connection establishment between
+	 * rds_tcp_accept_one and rds_tcp_conn_connect
+	 */
+	struct mutex		t_conn_lock;
 	struct socket		*t_sock;
 	void			*t_orig_write_space;
 	void			*t_orig_data_ready;
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 5cb16875c460..49a3fcfed360 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -78,7 +78,14 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
 	struct socket *sock = NULL;
 	struct sockaddr_in src, dest;
 	int ret;
+	struct rds_tcp_connection *tc = conn->c_transport_data;
+
+	mutex_lock(&tc->t_conn_lock);
 
+	if (rds_conn_up(conn)) {
+		mutex_unlock(&tc->t_conn_lock);
+		return 0;
+	}
 	ret = sock_create_kern(rds_conn_net(conn), PF_INET,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret < 0)
@@ -120,6 +127,7 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
 	}
 
 out:
+	mutex_unlock(&tc->t_conn_lock);
 	if (sock)
 		sock_release(sock);
 	return ret;
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 0936a4a32b47..be263cdf268b 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -76,7 +76,9 @@ int rds_tcp_accept_one(struct socket *sock)
 	struct rds_connection *conn;
 	int ret;
 	struct inet_sock *inet;
-	struct rds_tcp_connection *rs_tcp;
+	struct rds_tcp_connection *rs_tcp = NULL;
+	int conn_state;
+	struct sock *nsk;
 
 	ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
 			       sock->sk->sk_type, sock->sk->sk_protocol,
@@ -115,28 +117,44 @@ int rds_tcp_accept_one(struct socket *sock)
 	 * rds_tcp_state_change() will do that cleanup
 	 */
 	rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
-	if (rs_tcp->t_sock &&
-	    ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
-		struct sock *nsk = new_sock->sk;
-
-		nsk->sk_user_data = NULL;
-		nsk->sk_prot->disconnect(nsk, 0);
-		tcp_done(nsk);
-		new_sock = NULL;
-		ret = 0;
-		goto out;
-	} else if (rs_tcp->t_sock) {
-		rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
-		conn->c_outgoing = 0;
-	}
-
 	rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
+	mutex_lock(&rs_tcp->t_conn_lock);
+	conn_state = rds_conn_state(conn);
+	if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP)
+		goto rst_nsk;
+	if (rs_tcp->t_sock) {
+		/* Need to resolve a duelling SYN between peers.
+		 * We have an outstanding SYN to this peer, which may
+		 * potentially have transitioned to the RDS_CONN_UP state,
+		 * so we must quiesce any send threads before resetting
+		 * c_transport_data.
+		 */
+		wait_event(conn->c_waitq,
+			   !test_bit(RDS_IN_XMIT, &conn->c_flags));
+		if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
+			goto rst_nsk;
+		} else if (rs_tcp->t_sock) {
+			rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
+			conn->c_outgoing = 0;
+		}
+	}
 	rds_tcp_set_callbacks(new_sock, conn);
-	rds_connect_complete(conn);
+	rds_connect_complete(conn); /* marks RDS_CONN_UP */
+	new_sock = NULL;
+	ret = 0;
+	goto out;
+rst_nsk:
+	/* reset the newly returned accept sock and bail */
+	nsk = new_sock->sk;
+	rds_tcp_stats_inc(s_tcp_listen_closed_stale);
+	nsk->sk_user_data = NULL;
+	nsk->sk_prot->disconnect(nsk, 0);
+	tcp_done(nsk);
 	new_sock = NULL;
 	ret = 0;
-
 out:
+	if (rs_tcp)
+		mutex_unlock(&rs_tcp->t_conn_lock);
 	if (new_sock)
 		sock_release(new_sock);
 	return ret;
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 27a992154804..d75d8b56a9e3 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -207,22 +207,14 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		}
 
 		if (left && tc->t_tinc_data_rem) {
-			clone = skb_clone(skb, arg->gfp);
+			to_copy = min(tc->t_tinc_data_rem, left);
+
+			clone = pskb_extract(skb, offset, to_copy, arg->gfp);
 			if (!clone) {
 				desc->error = -ENOMEM;
 				goto out;
 			}
 
-			to_copy = min(tc->t_tinc_data_rem, left);
-			if (!pskb_pull(clone, offset) ||
-			    pskb_trim(clone, to_copy)) {
-				pr_warn("rds_tcp_data_recv: pull/trim failed "
-					"left %zu data_rem %zu skb_len %d\n",
-					left, tc->t_tinc_data_rem, skb->len);
-				kfree_skb(clone);
-				desc->error = -ENOMEM;
-				goto out;
-			}
 			skb_queue_tail(&tinc->ti_skb_list, clone);
 
 			rdsdebug("skb %p data %p len %d off %u to_copy %zu -> "