1 files changed, 51 insertions, 11 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6df36ad55a38..4b85e6f636c9 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -252,7 +252,8 @@ static void tcp_delack_timer(unsigned long data)
 		inet_csk(sk)->icsk_ack.blocked = 1;
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
-		set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags);
+		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
 	sock_put(sk);
@@ -304,6 +305,35 @@ static void tcp_probe_timer(struct sock *sk)
 }
 
 /*
+ *	Timer for Fast Open socket to retransmit SYNACK. Note that the
+ *	sk here is the child socket, not the parent (listener) socket.
+ */
+static void tcp_fastopen_synack_timer(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	int max_retries = icsk->icsk_syn_retries ? :
+	    sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
+	struct request_sock *req;
+
+	req = tcp_sk(sk)->fastopen_rsk;
+	req->rsk_ops->syn_ack_timeout(sk, req);
+
+	if (req->num_timeout >= max_retries) {
+		tcp_write_err(sk);
+		return;
+	}
+	/* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error
+	 * returned from rtx_syn_ack() to make it more persistent like
+	 * regular retransmit because if the child socket has been accepted
+	 * it's not good to give up too easily.
+	 */
+	inet_rtx_syn_ack(sk, req);
+	req->num_timeout++;
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			  TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
+}
+
+/*
  *	The TCP retransmit timer.
  */
 
@@ -312,16 +342,22 @@ void tcp_retransmit_timer(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (tp->early_retrans_delayed) {
-		tcp_resume_early_retransmit(sk);
+	if (tp->fastopen_rsk) {
+		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
+			     sk->sk_state != TCP_FIN_WAIT1);
+		tcp_fastopen_synack_timer(sk);
+		/* Before we receive ACK to our SYN-ACK don't retransmit
+		 * anything else (e.g., data or FIN segments).
+		 */
 		return;
 	}
-
 	if (!tp->packets_out)
 		goto out;
 
 	WARN_ON(tcp_write_queue_empty(sk));
 
+	tp->tlp_high_seq = 0;
+
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
 		/* Receiver dastardly shrinks window. Our retransmits
@@ -380,11 +416,7 @@ void tcp_retransmit_timer(struct sock *sk)
 		NET_INC_STATS_BH(sock_net(sk), mib_idx);
 	}
 
-	if (tcp_use_frto(sk)) {
-		tcp_enter_frto(sk);
-	} else {
-		tcp_enter_loss(sk, 0);
-	}
+	tcp_enter_loss(sk, 0);
 
 	if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) {
 		/* Retransmission failed because of local congestion,
@@ -457,13 +489,20 @@ void tcp_write_timer_handler(struct sock *sk)
 	}
 
 	event = icsk->icsk_pending;
-	icsk->icsk_pending = 0;
 
 	switch (event) {
+	case ICSK_TIME_EARLY_RETRANS:
+		tcp_resume_early_retransmit(sk);
+		break;
+	case ICSK_TIME_LOSS_PROBE:
+		tcp_send_loss_probe(sk);
+		break;
 	case ICSK_TIME_RETRANS:
+		icsk->icsk_pending = 0;
 		tcp_retransmit_timer(sk);
 		break;
 	case ICSK_TIME_PROBE0:
+		icsk->icsk_pending = 0;
 		tcp_probe_timer(sk);
 		break;
 	}
@@ -481,7 +520,8 @@ static void tcp_write_timer(unsigned long data)
 		tcp_write_timer_handler(sk);
 	} else {
 		/* deleguate our work to tcp_release_cb() */
-		set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags);
+		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
 	sock_put(sk);