[PATCH bpf v4 1/4] af_unix: Disable MSG_OOB handling for sockets in sockmap/sockhash

[Michal Luczaj <mhal@rbox.co>]

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an OOB packet is moved between sockets, `oob_skb` is left outdated.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().

Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 net/unix/af_unix.c  | 41 ++++++++++++++++++++++++++++++++++++++++-
 net/unix/unix_bpf.c |  3 +++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 142f56770b77..11cb5badafb6 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2667,10 +2667,49 @@ 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,
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index bd84785bf8d6..bca2d86ba97d 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -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;
 
-- 
2.45.2