bpf: Support for per connection SYN/SYN-ACK RTOs

This patch adds support for setting a per connection SYN and
SYN_ACK RTOs from within a BPF_SOCK_OPS program. For example,
to set small RTOs when it is known both hosts are within a
datacenter.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e585008..564af2d 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2057,4 +2057,15 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 }
 #endif
 
+static inline u32 tcp_timeout_init(struct sock *sk)
+{
+       int timeout;
+
+       timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+
+       if (timeout <= 0)
+               timeout = TCP_TIMEOUT_INIT;
+       return timeout;
+}
+
 #endif /* _TCP_H */

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 01cd485..00702b2 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -748,6 +748,9 @@ struct bpf_sock_ops {
  */
 enum {
        BPF_SOCK_OPS_VOID,
+       BPF_SOCK_OPS_TIMEOUT_INIT,      /* Should return SYN-RTO value to use or
+                                        * -1 if default value should be used
+                                        */
 };
 
 #endif /* _UAPI__LINUX_BPF_H__ */

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2ab7e2f..bcc9665 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6406,7 +6406,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
        } else {
                tcp_rsk(req)->tfo_listener = false;
                if (!want_cookie)
-                       inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+                       inet_csk_reqsk_queue_hash_add(sk, req,
+                               tcp_timeout_init((struct sock *)req));
                af_ops->send_synack(sk, dst, &fl, req, &foc,
                                    !want_cookie ? TCP_SYNACK_NORMAL :
                                                   TCP_SYNACK_COOKIE);

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1d79137..47fe075 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3326,7 +3326,7 @@ static void tcp_connect_init(struct sock *sk)
        tp->rcv_wup = tp->rcv_nxt;
        tp->copied_seq = tp->rcv_nxt;
 
-       inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+       inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
        inet_csk(sk)->icsk_retransmits = 0;
        tcp_clear_retrans(tp);
 }