From ccce324dabfe2143519daf50ed8b1ef1d0c542f7 Mon Sep 17 00:00:00 2001 From: David Morley Date: Tue, 9 May 2023 18:05:58 +0000 Subject: tcp: make the first N SYN RTO backoffs linear Currently the SYN RTO schedule follows an exponential backoff scheme, which can be unnecessarily conservative in cases where there are link failures. In such cases, it's better to aggressively try to retransmit packets, so it takes routers less time to find a repath with a working link. We chose a default value for this sysctl of 4, to follow the macOS and IOS backoff scheme of 1,1,1,1,1,2,4,8, ... MacOS and IOS have used this backoff schedule for over a decade, since before this 2009 IETF presentation discussed the behavior: https://www.ietf.org/proceedings/75/slides/tcpm-1.pdf This commit makes the SYN RTO schedule start with a number of linear backoffs given by the following sysctl: * tcp_syn_linear_timeouts This changes the SYN RTO scheme to be: init_rto_val for tcp_syn_linear_timeouts, exp backoff starting at init_rto_val For example if init_rto_val = 1 and tcp_syn_linear_timeouts = 2, our backoff scheme would be: 1, 1, 1, 2, 4, 8, 16, ... Signed-off-by: David Morley Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Tested-by: David Morley Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230509180558.2541885-1-morleyd.kernel@gmail.com Signed-off-by: Paolo Abeni --- net/ipv4/tcp_timer.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b839c2f91292..0d93a2573807 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -234,14 +234,19 @@ static int tcp_write_timeout(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool expired = false, do_reset; - int retry_until; + int retry_until, max_retransmits; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); - expired = icsk->icsk_retransmits >= retry_until; + + max_retransmits = retry_until; + if (sk->sk_state == TCP_SYN_SENT) + max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts); + + expired = icsk->icsk_retransmits >= max_retransmits; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ @@ -577,8 +582,12 @@ out_reset_timer: icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); - } else { - /* Use normal (exponential) backoff */ + } else if (sk->sk_state != TCP_SYN_SENT || + icsk->icsk_backoff > + READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) { + /* Use normal (exponential) backoff unless linear timeouts are + * activated. + */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, -- cgit From 30c6f0bf9579debce27e45fac34fdc97e46acacc Mon Sep 17 00:00:00 2001 From: fuyuanli Date: Wed, 31 May 2023 16:01:50 +0800 Subject: 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 Signed-off-by: fuyuanli Signed-off-by: Jason Xing Link: https://lore.kernel.org/netdev/20230529113804.GA20300@didi-ThinkCentre-M920t-N000/ Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230531080150.GA20424@didi-ThinkCentre-M920t-N000 Signed-off-by: Paolo Abeni --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_timer.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/include/net/tcp.h b/include/net/tcp.h index 18a038d16434..5066e4586cf0 100644 --- 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 61b6710f337a..bf8b22218dd4 100644 --- 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 b839c2f91292..39eb947fe392 100644 --- 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); } -- cgit