diff options
| -rw-r--r-- | include/net/tcp.h | 11 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 6 | ||||
| -rw-r--r-- | net/ipv4/tcp_output.c | 13 |
3 files changed, 23 insertions, 7 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 86b9a8766648..e460ea7f767b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1766,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } +/** + * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue + * @sk: socket + * + * Since the write queue can have a temporary empty skb in it, + * we must not use "return skb_queue_empty(&sk->sk_write_queue)" + */ static inline bool tcp_write_queue_empty(const struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + const struct tcp_sock *tp = tcp_sk(sk); + + return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a39ee794891..716938313a32 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1087,8 +1087,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1419,8 +1418,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b184f03d7437..36902d08473e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have |