From ca584ba070864c606f3a54faaafe774726d5b4a1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:27 -0700 Subject: [PATCH] tcp: bpf: Add TCP_BPF_RTO_MIN for bpf_setsockopt This patch adds bpf_setsockopt(TCP_BPF_RTO_MIN) to allow bpf prog to set the min rto of a connection. It could be used together with the earlier patch which has added bpf_setsockopt(TCP_BPF_DELACK_MAX). A later selftest patch will communicate the max delay ack in a bpf tcp header option and then the receiving side can use bpf_setsockopt(TCP_BPF_RTO_MIN) to set a shorter rto. 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/20200820190027.2884170-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/net/tcp.h | 2 +- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 7 +++++++ net/ipv4/tcp.c | 2 ++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 13 insertions(+), 1 deletion(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index da7264a1ebfc..c738abeb3265 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..dda778c782fe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -699,7 +699,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7b905cb0213e..1ae20058b574 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4258,6 +4258,7 @@ 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 */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ }; struct bpf_perf_event_value { diff --git a/net/core/filter.c b/net/core/filter.c index 80fe7420f609..075ab71b985c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4488,6 +4488,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = 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 44c353a39ad4..6075cb091a20 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -418,6 +418,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -2686,6 +2687,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7b905cb0213e..1ae20058b574 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4258,6 +4258,7 @@ 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 */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ }; struct bpf_perf_event_value {