[TCP]: Congestion control initialization.
Change to defer congestion control initialization.
If setsockopt() was used to change TCP_CONGESTION before
connection is established, then protocols that use sequence numbers
to keep track of one RTT interval (vegas, illinois, ...) get confused.
Change the init hook to be called after handshake.
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 5c8caf4..34ae3f1 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -77,18 +77,19 @@
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_congestion_ops *ca;
- if (icsk->icsk_ca_ops != &tcp_init_congestion_ops)
- return;
+ /* if no choice made yet assign the current value set as default */
+ if (icsk->icsk_ca_ops == &tcp_init_congestion_ops) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
+ if (try_module_get(ca->owner)) {
+ icsk->icsk_ca_ops = ca;
+ break;
+ }
- rcu_read_lock();
- list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
- if (try_module_get(ca->owner)) {
- icsk->icsk_ca_ops = ca;
- break;
+ /* fallback to next available */
}
-
+ rcu_read_unlock();
}
- rcu_read_unlock();
if (icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
@@ -236,6 +237,7 @@
rcu_read_lock();
ca = tcp_ca_find(name);
+
/* no change asking for existing value */
if (ca == icsk->icsk_ca_ops)
goto out;
@@ -261,7 +263,8 @@
else {
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
- if (icsk->icsk_ca_ops->init)
+
+ if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
}
out: