tcp: fix mishandling when the sack compression is deferred.

In this patch, we mainly try to handle sending a compressed ack
correctly if it's deferred.

Here are more details in the old logic:
When sack compression is triggered in the tcp_compressed_ack_kick(),
if the sock is owned by user, it will set TCP_DELACK_TIMER_DEFERRED
and then defer to the release cb phrase. Later once user releases
the sock, tcp_delack_timer_handler() should send a ack as expected,
which, however, cannot happen due to lack of ICSK_ACK_TIMER flag.
Therefore, the receiver would not sent an ack until the sender's
retransmission timeout. It definitely increases unnecessary latency.

Fixes: 5d9f4262b7ea ("tcp: add SACK compression")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: fuyuanli <fuyuanli@didiglobal.com>
Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/netdev/20230529113804.GA20300@didi-ThinkCentre-M920t-N000/
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230531080150.GA20424@didi-ThinkCentre-M920t-N000
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 18a038d164344bd8758dbbc91f78a8ee8b9f7f6c..5066e4586cf09dbabfa053dce32fc4d31b98e324 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -632,6 +632,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb);
 void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
 void tcp_fin(struct sock *sk);
 void tcp_check_space(struct sock *sk);
+void tcp_sack_compress_send_ack(struct sock *sk);
 
 /* tcp_timer.c */
 void tcp_init_xmit_timers(struct sock *);

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61b6710f337a3a5c24b3f399cc77a404b7e012f9..bf8b22218dd468632ee39826f9be57abea5018dc 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
        }
 }
 
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
 {
        struct tcp_sock *tp = tcp_sk(sk);
 

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292f7346f33d6dcbf597594473a5aca..39eb947fe3920f7bb21385842089cbbbfbf6dbbd 100644 (file)
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
 void tcp_delack_timer_handler(struct sock *sk)
 {
        struct inet_connection_sock *icsk = inet_csk(sk);
+       struct tcp_sock *tp = tcp_sk(sk);
 
-       if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
-           !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+       if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+               return;
+
+       /* Handling the sack compression case */
+       if (tp->compressed_ack) {
+               tcp_mstamp_refresh(tp);
+               tcp_sack_compress_send_ack(sk);
+               return;
+       }
+
+       if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
                return;
 
        if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
                        inet_csk_exit_pingpong_mode(sk);
                        icsk->icsk_ack.ato      = TCP_ATO_MIN;
                }
-               tcp_mstamp_refresh(tcp_sk(sk));
+               tcp_mstamp_refresh(tp);
                tcp_send_ack(sk);
                __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
        }