summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/net/tcp.h4
-rw-r--r--net/core/filter.c7
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_cong.c19
4 files changed, 18 insertions, 14 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ada65e767b28..f642a39f9eee 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1004,9 +1004,7 @@ void tcp_get_default_congestion_control(char *name);
void tcp_get_available_congestion_control(char *buf, size_t len);
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load);
-void tcp_reinit_congestion_control(struct sock *sk,
- const struct tcp_congestion_ops *ca);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit);
u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
diff --git a/net/core/filter.c b/net/core/filter.c
index 8eb81e5fae08..169974998c76 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2836,15 +2836,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
sk->sk_prot->setsockopt == tcp_setsockopt) {
if (optname == TCP_CONGESTION) {
char name[TCP_CA_NAME_MAX];
+ bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN;
strncpy(name, optval, min_t(long, optlen,
TCP_CA_NAME_MAX-1));
name[TCP_CA_NAME_MAX-1] = 0;
- ret = tcp_set_congestion_control(sk, name, false);
- if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
- /* replacing an existing ca */
- tcp_reinit_congestion_control(sk,
- inet_csk(sk)->icsk_ca_ops);
+ ret = tcp_set_congestion_control(sk, name, false, reinit);
} else {
struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 71ce33decd97..a3e91b552edc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2481,7 +2481,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
name[val] = 0;
lock_sock(sk);
- err = tcp_set_congestion_control(sk, name, true);
+ err = tcp_set_congestion_control(sk, name, true, true);
release_sock(sk);
return err;
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index fde983f6376b..421ea1b918da 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk)
INET_ECN_dontxmit(sk);
}
-void tcp_reinit_congestion_control(struct sock *sk,
- const struct tcp_congestion_ops *ca)
+static void tcp_reinit_congestion_control(struct sock *sk,
+ const struct tcp_congestion_ops *ca)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -338,7 +338,7 @@ out:
* tcp_reinit_congestion_control (if the current congestion control was
* already initialized.
*/
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
{
struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_congestion_ops *ca;
@@ -360,9 +360,18 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
if (!ca) {
err = -ENOENT;
} else if (!load) {
- icsk->icsk_ca_ops = ca;
- if (!try_module_get(ca->owner))
+ const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
+
+ if (try_module_get(ca->owner)) {
+ if (reinit) {
+ tcp_reinit_congestion_control(sk, ca);
+ } else {
+ icsk->icsk_ca_ops = ca;
+ module_put(old_ca->owner);
+ }
+ } else {
err = -EBUSY;
+ }
} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
err = -EPERM;