summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--include/net/tcp.h2
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_cong.c46
-rw-r--r--net/ipv4/tcp_minisocks.c5
4 files changed, 27 insertions, 32 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 02a9a2c366bf..f99b0c072ee5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -824,6 +824,7 @@ struct tcp_congestion_ops {
int tcp_register_congestion_control(struct tcp_congestion_ops *type);
void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
+void tcp_assign_congestion_control(struct sock *sk);
void tcp_init_congestion_control(struct sock *sk);
void tcp_cleanup_congestion_control(struct sock *sk);
int tcp_set_default_congestion_control(const char *name);
@@ -835,7 +836,6 @@ int tcp_set_congestion_control(struct sock *sk, const char *name);
int tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
-extern struct tcp_congestion_ops tcp_init_congestion_ops;
u32 tcp_reno_ssthresh(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 87289e51be00..cf5e508e1ef5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -405,7 +405,7 @@ void tcp_init_sock(struct sock *sk)
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
- icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
@@ -3258,8 +3258,6 @@ void __init tcp_init(void)
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
tcp_metrics_init();
-
- tcp_register_congestion_control(&tcp_reno);
-
+ BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
tcp_tasklet_init();
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 80248f56c89f..a6c8a5775624 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -74,24 +74,34 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
/* Assign choice of congestion control. */
-void tcp_init_congestion_control(struct sock *sk)
+void tcp_assign_congestion_control(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_congestion_ops *ca;
- /* 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;
- }
-
- /* fallback to next available */
+ rcu_read_lock();
+ list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
+ if (likely(try_module_get(ca->owner))) {
+ icsk->icsk_ca_ops = ca;
+ goto out;
}
- rcu_read_unlock();
+ /* Fallback to next available. The last really
+ * guaranteed fallback is Reno from this list.
+ */
}
+out:
+ rcu_read_unlock();
+
+ /* Clear out private data before diag gets it and
+ * the ca has not been initialized.
+ */
+ if (ca->get_info)
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+}
+
+void tcp_init_congestion_control(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
@@ -345,15 +355,3 @@ struct tcp_congestion_ops tcp_reno = {
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
};
-
-/* Initial congestion control used (until SYN)
- * really reno under another name so we can tell difference
- * during tcp_set_default_congestion_control
- */
-struct tcp_congestion_ops tcp_init_congestion_ops = {
- .name = "",
- .owner = THIS_MODULE,
- .ssthresh = tcp_reno_ssthresh,
- .cong_avoid = tcp_reno_cong_avoid,
-};
-EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a058f411d3a6..47b73506b77e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -451,9 +451,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
- !try_module_get(newicsk->icsk_ca_ops->owner))
- newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ if (!try_module_get(newicsk->icsk_ca_ops->owner))
+ tcp_assign_congestion_control(newsk);
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);