From: Wei Wang <weiwan@google.com>
Date: Wed, 4 Oct 2017 10:03:44 -0700
Subject: tcp: uniform the set up of sockets after successful connection
Patch-mainline: v4.15-rc1
Git-commit: 27204aaa9dc67b833b77179fdac556288ec3a4bf
References: bsc#1109837

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>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 include/net/tcp.h       |    1 +
 net/ipv4/tcp.c          |   12 ++++++++++++
 net/ipv4/tcp_fastopen.c |    7 +------
 net/ipv4/tcp_input.c    |   21 +++------------------
 4 files changed, 17 insertions(+), 24 deletions(-)

--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -421,6 +421,7 @@ bool tcp_peer_is_proven(struct request_s
 void tcp_disable_fack(struct tcp_sock *tp);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
+void tcp_init_transfer(struct sock *sk, int bpf_op);
 unsigned int tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -423,6 +423,18 @@ void tcp_init_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
+void tcp_init_transfer(struct sock *sk, int bpf_op)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	tcp_mtup_init(sk);
+	icsk->icsk_af_ops->rebuild_header(sk);
+	tcp_init_metrics(sk);
+	tcp_call_bpf(sk, bpf_op);
+	tcp_init_congestion_control(sk);
+	tcp_init_buffer_space(sk);
+}
+
 static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
 {
 	if (tsflags && skb) {
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -217,12 +217,7 @@ static struct sock *tcp_fastopen_create_
 	atomic_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	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);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5501,20 +5501,13 @@ void tcp_finish_connect(struct sock *sk,
 		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));
 
@@ -5682,7 +5675,6 @@ static int tcp_rcv_synsent_state_process
 		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);
 
@@ -5909,14 +5901,8 @@ int tcp_rcv_state_process(struct sock *s
 			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);
@@ -5946,8 +5932,7 @@ int tcp_rcv_state_process(struct sock *s
 			 * 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);