Commit 638f3260 authored by Michal Luczaj's avatar Michal Luczaj Committed by Daniel Borkmann
Browse files

af_unix: Disable MSG_OOB handling for sockets in sockmap/sockhash 



AF_UNIX socket tracks the most recent OOB packet (in its receive queue)
with an `oob_skb` pointer. BPF redirecting does not account for that: when
an OOB packet is moved between sockets, `oob_skb` is left outdated. This
results in a single skb that may be accessed from two different sockets.

Take the easy way out: silently drop MSG_OOB data targeting any socket that
is in a sockmap or a sockhash. Note that such silent drop is akin to the
fate of redirected skb's scm_fp_list (SCM_RIGHTS, SCM_CREDENTIALS).

For symmetry, forbid MSG_OOB in unix_bpf_recvmsg().

Fixes: 314001f0 ("af_unix: Add OOB support")
Suggested-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: default avatarMichal Luczaj <mhal@rbox.co>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Tested-by: default avatarJakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: default avatarJakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20240713200218.2140950-2-mhal@rbox.co
parent 3c870059

net/unix/af_unix.c

+40 −1
Original line number Diff line number Diff line
@@ -2721,10 +2721,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, 


static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)

{

	struct unix_sock *u = unix_sk(sk);

	struct sk_buff *skb;

	int err;



	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))

		return -ENOTCONN;



	return unix_read_skb(sk, recv_actor);

	mutex_lock(&u->iolock);

	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);

	mutex_unlock(&u->iolock);

	if (!skb)

		return err;



#if IS_ENABLED(CONFIG_AF_UNIX_OOB)

	if (unlikely(skb == READ_ONCE(u->oob_skb))) {

		bool drop = false;



		unix_state_lock(sk);



		if (sock_flag(sk, SOCK_DEAD)) {

			unix_state_unlock(sk);

			kfree_skb(skb);

			return -ECONNRESET;

		}



		spin_lock(&sk->sk_receive_queue.lock);

		if (likely(skb == u->oob_skb)) {

			WRITE_ONCE(u->oob_skb, NULL);

			drop = true;

		}

		spin_unlock(&sk->sk_receive_queue.lock);



		unix_state_unlock(sk);



		if (drop) {

			WARN_ON_ONCE(skb_unref(skb));

			kfree_skb(skb);

			return -EAGAIN;

		}

	}

#endif



	return recv_actor(sk, skb);

}



static int unix_stream_read_generic(struct unix_stream_read_state *state,

net/unix/unix_bpf.c

+3 −0
Original line number Diff line number Diff line
@@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, 
	struct sk_psock *psock;

	int copied;



	if (flags & MSG_OOB)

		return -EOPNOTSUPP;



	if (!len)

		return 0;