1 files changed, 38 insertions, 32 deletions

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 3172e31987be..d3cae40749e8 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -16,6 +16,7 @@
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <net/tcp.h>
+#include <trace/events/tcp.h>
 
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
 static LIST_HEAD(tcp_cong_list);
@@ -33,6 +34,17 @@ struct tcp_congestion_ops *tcp_ca_find(const char *name)
 	return NULL;
 }
 
+void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	trace_tcp_cong_state_set(sk, ca_state);
+
+	if (icsk->icsk_ca_ops->set_state)
+		icsk->icsk_ca_ops->set_state(sk, ca_state);
+	icsk->icsk_ca_state = ca_state;
+}
+
 /* Must be called with rcu lock held */
 static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
 						       const char *name)
@@ -135,7 +147,6 @@ u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
 
 	return key;
 }
-EXPORT_SYMBOL_GPL(tcp_ca_get_key_by_name);
 
 char *tcp_ca_get_name_by_key(u32 key, char *buffer)
 {
@@ -151,7 +162,6 @@ char *tcp_ca_get_name_by_key(u32 key, char *buffer)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
 
 /* Assign choice of congestion control. */
 void tcp_assign_congestion_control(struct sock *sk)
@@ -176,7 +186,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +195,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
@@ -197,7 +208,12 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (ca->flags & TCP_CONG_NEEDS_ECN)
+		INET_ECN_xmit(sk);
+	else
+		INET_ECN_dontxmit(sk);
+
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
@@ -224,6 +240,10 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
 		ret = -ENOENT;
 	} else if (!bpf_try_module_get(ca, ca->owner)) {
 		ret = -EBUSY;
+	} else if (!net_eq(net, &init_net) &&
+			!(ca->flags & TCP_CONG_NON_RESTRICTED)) {
+		/* Only init netns can set default to a restricted algorithm */
+		ret = -EPERM;
 	} else {
 		prev = xchg(&net->ipv4.tcp_congestion_control, ca);
 		if (prev)
@@ -340,7 +360,7 @@ out:
  * already initialized.
  */
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin)
+			       bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -361,28 +381,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 		goto out;
 	}
 
-	if (!ca) {
+	if (!ca)
 		err = -ENOENT;
-	} else if (!load) {
-		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
-
-		if (bpf_try_module_get(ca, ca->owner)) {
-			if (reinit) {
-				tcp_reinit_congestion_control(sk, ca);
-			} else {
-				icsk->icsk_ca_ops = ca;
-				bpf_module_put(old_ca, old_ca->owner);
-			}
-		} else {
-			err = -EBUSY;
-		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
+	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin))
 		err = -EPERM;
-	} else if (!bpf_try_module_get(ca, ca->owner)) {
+	else if (!bpf_try_module_get(ca, ca->owner))
 		err = -EBUSY;
-	} else {
+	else
 		tcp_reinit_congestion_control(sk, ca);
-	}
  out:
 	rcu_read_unlock();
 	return err;
@@ -399,10 +405,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
  */
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
-	u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
+	u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh);
 
-	acked -= cwnd - tp->snd_cwnd;
-	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+	acked -= cwnd - tcp_snd_cwnd(tp);
+	tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp));
 
 	return acked;
 }
@@ -416,7 +422,7 @@ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 	/* If credits accumulated at a higher w, apply them gently now. */
 	if (tp->snd_cwnd_cnt >= w) {
 		tp->snd_cwnd_cnt = 0;
-		tp->snd_cwnd++;
+		tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1);
 	}
 
 	tp->snd_cwnd_cnt += acked;
@@ -424,9 +430,9 @@ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 		u32 delta = tp->snd_cwnd_cnt / w;
 
 		tp->snd_cwnd_cnt -= delta * w;
-		tp->snd_cwnd += delta;
+		tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + delta);
 	}
-	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
+	tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), tp->snd_cwnd_clamp));
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 
@@ -451,7 +457,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 			return;
 	}
 	/* In dangerous area, increase slowly. */
-	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+	tcp_cong_avoid_ai(tp, tcp_snd_cwnd(tp), acked);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
@@ -460,7 +466,7 @@ u32 tcp_reno_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
-	return max(tp->snd_cwnd >> 1U, 2U);
+	return max(tcp_snd_cwnd(tp) >> 1U, 2U);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
 
@@ -468,7 +474,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
-	return max(tp->snd_cwnd, tp->prior_cwnd);
+	return max(tcp_snd_cwnd(tp), tp->prior_cwnd);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd);