Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

[linux-2.6-block.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d3b691f3a9e896ce340ae081a0d24092024361c8..c31badfee806a70d5af6dc033cf9155adb1f9375 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1904,7 +1904,9 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
  * This algorithm is from John Heffner.
  */
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
-                                bool *is_cwnd_limited, u32 max_segs)
+                                bool *is_cwnd_limited,
+                                bool *is_rwnd_limited,
+                                u32 max_segs)
 {
        const struct inet_connection_sock *icsk = inet_csk(sk);
        u32 send_win, cong_win, limit, in_flight;
@@ -1913,9 +1915,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
        int win_divisor;
        s64 delta;
 
-       if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
-               goto send_now;
-
        if (icsk->icsk_ca_state >= TCP_CA_Recovery)
                goto send_now;
 
@@ -1981,10 +1980,27 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
        if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
                goto send_now;
 
-       /* Ok, it looks like it is advisable to defer. */
+       /* Ok, it looks like it is advisable to defer.
+        * Three cases are tracked :
+        * 1) We are cwnd-limited
+        * 2) We are rwnd-limited
+        * 3) We are application limited.
+        */
+       if (cong_win < send_win) {
+               if (cong_win <= skb->len) {
+                       *is_cwnd_limited = true;
+                       return true;
+               }
+       } else {
+               if (send_win <= skb->len) {
+                       *is_rwnd_limited = true;
+                       return true;
+               }
+       }
 
-       if (cong_win < send_win && cong_win <= skb->len)
-               *is_cwnd_limited = true;
+       /* If this packet won't get more data, do not wait. */
+       if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+               goto send_now;
 
        return true;
 
@@ -2365,7 +2381,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                } else {
                        if (!push_one &&
                            tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
-                                                max_segs))
+                                                &is_rwnd_limited, max_segs))
                                break;
                }
 
@@ -2503,15 +2519,18 @@ void tcp_send_loss_probe(struct sock *sk)
                goto rearm_timer;
        }
        skb = skb_rb_last(&sk->tcp_rtx_queue);
+       if (unlikely(!skb)) {
+               WARN_ONCE(tp->packets_out,
+                         "invalid inflight: %u state %u cwnd %u mss %d\n",
+                         tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+               inet_csk(sk)->icsk_pending = 0;
+               return;
+       }
 
        /* At most one outstanding TLP retransmission. */
        if (tp->tlp_high_seq)
                goto rearm_timer;
 
-       /* Retransmit last segment. */
-       if (WARN_ON(!skb))
-               goto rearm_timer;
-
        if (skb_still_in_host_queue(sk, skb))
                goto rearm_timer;
 
@@ -2929,7 +2948,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
                TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
                trace_tcp_retransmit_skb(sk, skb);
        } else if (err != -EBUSY) {
-               NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+               NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
        }
        return err;
 }