[RFC PATCH net-next 03/15] bpf: Support for per connection SYN/SYN-ACK RTOs

[Lawrence Brakmo]

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

Signed-off-by: Lawrence Brakmo <bra...@fb.com>
---
 include/net/tcp.h        | 11 +++++++++++
 include/uapi/linux/bpf.h |  3 +++
 net/ipv4/tcp_input.c     |  3 ++-
 net/ipv4/tcp_output.c    |  2 +-
 4 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index bc1c92c..8353563 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2019,4 +2019,15 @@ static inline int tcp_call_bpf(struct sock *sk, bool 
is_req_sock, int op)
 }
 #endif
 
+static inline u32 tcp_timeout_init(struct sock *sk, bool is_req_sock)
+{
+       int timeout;
+
+       timeout = tcp_call_bpf(sk, is_req_sock, BPF_SOCKET_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 06e7ee1..c9da55d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -699,6 +699,9 @@ struct bpf_socket_ops {
  */
 enum {
        BPF_SOCKET_OPS_VOID,
+       BPF_SOCKET_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 4ea8ec5..fefc062 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6405,7 +6405,8 @@ 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, true));
                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 e3aab1c..503e478 100644
--- 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, false);
        inet_csk(sk)->icsk_retransmits = 0;
        tcp_clear_retrans(tp);
 }
-- 
2.9.3