tcp: TLP retransmits last if failed to send new packet

When TLP fails to send new packet because of receive window
limit, it should fall back to retransmit the last packet instead.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 78fc89c1c43c7e16edb6b77bcc117518540b387a..444ab5beecbd0a35355f312152ef6349d9fa9cf0 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2149,7 +2149,7 @@ repair:
                tcp_cwnd_validate(sk, is_cwnd_limited);
                return false;
        }
-       return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
+       return !tp->packets_out && tcp_send_head(sk);
 }
 
 bool tcp_schedule_loss_probe(struct sock *sk)
@@ -2226,7 +2226,7 @@ static bool skb_still_in_host_queue(const struct sock *sk,
        return false;
 }
 
-/* When probe timeout (PTO) fires, send a new segment if one exists, else
+/* When probe timeout (PTO) fires, try send a new segment if possible, else
  * retransmit the last segment.
  */
 void tcp_send_loss_probe(struct sock *sk)
@@ -2235,11 +2235,19 @@ void tcp_send_loss_probe(struct sock *sk)
        struct sk_buff *skb;
        int pcount;
        int mss = tcp_current_mss(sk);
-       int err = -1;
 
-       if (tcp_send_head(sk)) {
-               err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
-               goto rearm_timer;
+       skb = tcp_send_head(sk);
+       if (skb) {
+               if (tcp_snd_wnd_test(tp, skb, mss)) {
+                       pcount = tp->packets_out;
+                       tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+                       if (tp->packets_out > pcount)
+                               goto probe_sent;
+                       goto rearm_timer;
+               }
+               skb = tcp_write_queue_prev(sk, skb);
+       } else {
+               skb = tcp_write_queue_tail(sk);
        }
 
        /* At most one outstanding TLP retransmission. */
@@ -2247,7 +2255,6 @@ void tcp_send_loss_probe(struct sock *sk)
                goto rearm_timer;
 
        /* Retransmit last segment. */
-       skb = tcp_write_queue_tail(sk);
        if (WARN_ON(!skb))
                goto rearm_timer;
 
@@ -2262,24 +2269,23 @@ void tcp_send_loss_probe(struct sock *sk)
                if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
                                          GFP_ATOMIC)))
                        goto rearm_timer;
-               skb = tcp_write_queue_tail(sk);
+               skb = tcp_write_queue_next(sk, skb);
        }
 
        if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
                goto rearm_timer;
 
-       err = __tcp_retransmit_skb(sk, skb);
+       if (__tcp_retransmit_skb(sk, skb))
+               goto rearm_timer;
 
        /* Record snd_nxt for loss detection. */
-       if (likely(!err))
-               tp->tlp_high_seq = tp->snd_nxt;
+       tp->tlp_high_seq = tp->snd_nxt;
 
+probe_sent:
+       NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
+       /* Reset s.t. tcp_rearm_rto will restart timer from now */
+       inet_csk(sk)->icsk_pending = 0;
 rearm_timer:
-       if (likely(!err)) {
-               NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
-               /* Reset s.t. tcp_rearm_rto will restart timer from now */
-               inet_csk(sk)->icsk_pending = 0;
-       }
        tcp_rearm_rto(sk);
 }