tcp: uniform the set up of sockets after successful connection

Currently in the TCP code, the initialization sequence for cached
metrics, congestion control, BPF, etc, after successful connection
is very inconsistent. This introduces inconsistent bevhavior and is
prone to bugs. The current call sequence is as follows:

(1) for active case (tcp_finish_connect() case):
        tcp_mtup_init(sk);
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_init_metrics(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_init_buffer_space(sk);

(2) for passive case (tcp_rcv_state_process() TCP_SYN_RECV case):
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_mtup_init(sk);
        tcp_init_buffer_space(sk);
        tcp_init_metrics(sk);

(3) for TFO passive case (tcp_fastopen_create_child()):
        inet_csk(child)->icsk_af_ops->rebuild_header(child);
        tcp_init_congestion_control(child);
        tcp_mtup_init(child);
        tcp_init_metrics(child);
        tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
        tcp_init_buffer_space(child);

This commit uniforms the above functions to have the following sequence:
        tcp_mtup_init(sk);
        icsk->icsk_af_ops->rebuild_header(sk);
        tcp_init_metrics(sk);
        tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE/PASSIVE_ESTABLISHED_CB);
        tcp_init_congestion_control(sk);
        tcp_init_buffer_space(sk);
This sequence is the same as the (1) active case. We pick this sequence
because this order correctly allows BPF to override the settings
including congestion control module and initial cwnd, etc from
the route, and then allows the CC module to see those settings.

Suggested-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 18 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index db9bb46b5776..bd3a35f5dbf2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5513,20 +5513,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		security_inet_conn_established(sk, skb);
 	}
 
-	/* Make sure socket is routed, for correct metrics.  */
-	icsk->icsk_af_ops->rebuild_header(sk);
-
-	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
-	tcp_init_congestion_control(sk);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
 	 */
 	tp->lsndtime = tcp_jiffies32;
 
-	tcp_init_buffer_space(sk);
-
 	if (sock_flag(sk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
 
@@ -5693,7 +5686,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		if (tcp_is_sack(tp) && sysctl_tcp_fack)
 			tcp_enable_fack(tp);
 
-		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -5920,14 +5912,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			inet_csk(sk)->icsk_retransmits = 0;
 			reqsk_fastopen_remove(sk, req, false);
 		} else {
-			/* Make sure socket is routed, for correct metrics. */
-			icsk->icsk_af_ops->rebuild_header(sk);
-			tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tcp_init_congestion_control(sk);
-
-			tcp_mtup_init(sk);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tp->copied_seq = tp->rcv_nxt;
-			tcp_init_buffer_space(sk);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
@@ -5957,8 +5943,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			 * are sent out.
 			 */
 			tcp_rearm_rto(sk);
-		} else
-			tcp_init_metrics(sk);
+		}
 
 		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
 			tcp_update_pacing_rate(sk);