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 <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190027.2884170-1-kafai@fb.com

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index da7264a..c738abe 100644 (file)
--- 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 eab6c75..dda778c 100644 (file)
--- 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 7b905cb..1ae2005 100644 (file)
--- 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 80fe742..075ab71 100644 (file)
--- 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 44c353a..6075cb0 100644 (file)
--- 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 7b905cb..1ae2005 100644 (file)
--- 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 {