tcp: fix tcp_set_congestion_control() use from bpf hook

Neal reported incorrect use of ns_capable() from bpf hook.

bpf_setsockopt(...TCP_CONGESTION...)
  -> tcp_set_congestion_control()
   -> ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)
    -> ns_capable_common()
     -> current_cred()
      -> rcu_dereference_protected(current->cred, 1)

Accessing 'current' in bpf context makes no sense, since packets
are processed from softirq context.

As Neal stated : The capability check in tcp_set_congestion_control()
was written assuming a system call context, and then was reused from
a BPF call site.

The fix is to add a new parameter to tcp_set_congestion_control(),
so that the ns_capable() call is only performed under the right
context.

Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 9 insertions, 6 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cca3c59b98bf..f42d300f0cfa 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1064,7 +1064,8 @@ void tcp_get_default_congestion_control(struct net *net, 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, bool reinit);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin);
 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 0f6854ccf894..4e2a79b2fd77 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4335,7 +4335,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
 			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit);
+							 reinit, true);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7846afacdf0b..776905899ac0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2785,7 +2785,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true);
+		err = tcp_set_congestion_control(sk, name, true, true,
+						 ns_capable(sock_net(sk)->user_ns,
+							    CAP_NET_ADMIN));
 		release_sock(sk);
 		return err;
 	}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index e1862b64a90f..c445a81d144e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -333,7 +333,8 @@ 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, bool reinit)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -369,8 +370,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
 		} else {
 			err = -EBUSY;
 		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
+	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
 		err = -EPERM;
 	} else if (!try_module_get(ca->owner)) {
 		err = -EBUSY;