From 9768c9f10cbb2297d0c7d36c5a2fe506e09317f1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:21 -0700 Subject: [PATCH] UPSTREAM: tcp: bpf: Add TCP_BPF_DELACK_MAX setsockopt This change is mostly from an internal patch and adapts it from sysctl config to the bpf_setsockopt setup. The bpf_prog can set the max delay ack by using bpf_setsockopt(TCP_BPF_DELACK_MAX). This max delay ack can be communicated to its peer through bpf header option. The receiving peer can then use this max delay ack and set a potentially lower rto by using bpf_setsockopt(TCP_BPF_RTO_MIN) which will be introduced in the next patch. Another later selftest patch will also use it like the above to show how to write and parse bpf tcp header option. Change-Id: Ia2591a16e948ced059df4b1e1447360e7aab9e0f Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190021.2884000-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/uapi/linux/bpf.h | 1 + net/core/filter.c | 8 ++++++++ net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_output.c | 2 ++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 15 insertions(+) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c9f9ed10bf21..ea4b95ba4a47 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -95,6 +95,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c2fe59884c3a..774964f7d4c2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4268,6 +4268,7 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ }; struct bpf_perf_event_value { diff --git a/net/core/filter.c b/net/core/filter.c index 56d145ef14d8..8ac4066c4f4e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4501,6 +4501,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; @@ -4522,6 +4523,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->snd_ssthresh = val; } break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4eb41219339b..90ad0a075c61 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -422,6 +422,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -2656,6 +2657,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b67337507360..bc874496d59d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3721,6 +3721,8 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } + ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + /* Stay within the limit we were given */ timeout = jiffies + ato; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9f988e7119fc..225f7082758b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4161,6 +4161,7 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ }; struct bpf_perf_event_value {