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 <[email protected]>
Tested-by: Neal Cardwell <[email protected]>
Signed-off-by: Wei Wang <[email protected]>
Acked-by: Neal Cardwell <[email protected]>
Acked-by: Yuchung Cheng <[email protected]>
Acked-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7a3a8af56fd69cb0fe5ea851433e4a0963ba7878..426c2e986016abe81563e855579c301a77315741 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -416,6 +416,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 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,

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 23225c98d287bd5ec8c5d9577747ec2fb43bee0c..c115e37ca6083db3a4db16e77d1059222dff3672 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -456,6 +456,18 @@ 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) {

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index de470e7e586f41e5d8f10fd060a2794aeb7fd609..29fff14d5a53db7ba34b0e2f2feaf46dfb55513e 100644 (file)
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -236,12 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
        refcount_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;
 

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index db9bb46b5776f9ee332298c0e95afb0a5966b938..bd3a35f5dbf21171fb58d67db82115946b91be0c 100644 (file)
--- 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);