af_unix: Don't set -ECONNRESET for consumed OOB skb.

Christian Brauner reported that even after MSG_OOB data is consumed,
calling close() on the receiver socket causes the peer's recv() to
return -ECONNRESET:

  1. send() and recv() an OOB data.

    >>> from socket import *
    >>> s1, s2 = socketpair(AF_UNIX, SOCK_STREAM)
    >>> s1.send(b'x', MSG_OOB)
    1
    >>> s2.recv(1, MSG_OOB)
    b'x'

  2. close() for s2 sets ECONNRESET to s1->sk_err even though
     s2 consumed the OOB data

    >>> s2.close()
    >>> s1.recv(10, MSG_DONTWAIT)
    ...
    ConnectionResetError: [Errno 104] Connection reset by peer

Even after being consumed, the skb holding the OOB 1-byte data stays in
the recv queue to mark the OOB boundary and break recv() at that point.

This must be considered while close()ing a socket.

Let's skip the leading consumed OOB skb while checking the -ECONNRESET
condition in unix_release_sock().

Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Reported-by: Christian Brauner <brauner@kernel.org>
Closes: https://lore.kernel.org/netdev/20250529-sinkt-abfeuern-e7b08200c6b0@brauner/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Christian Brauner <brauner@kernel.org>
Link: https://patch.msgid.link/20250619041457.1132791-4-kuni1840@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5392aa53cbc83c069020161fb2f76136788b893a..52b155123985a18632fc12dc986150e38f2fee70 100644 (file)
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -660,6 +660,11 @@ static void unix_sock_destructor(struct sock *sk)
 #endif
 }
 
+static unsigned int unix_skb_len(const struct sk_buff *skb)
+{
+       return skb->len - UNIXCB(skb).consumed;
+}
+
 static void unix_release_sock(struct sock *sk, int embrion)
 {
        struct unix_sock *u = unix_sk(sk);
@@ -694,10 +699,16 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
        if (skpair != NULL) {
                if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
+                       struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+                       if (skb && !unix_skb_len(skb))
+                               skb = skb_peek_next(skb, &sk->sk_receive_queue);
+#endif
                        unix_state_lock(skpair);
                        /* No more writes */
                        WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
-                       if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion)
+                       if (skb || embrion)
                                WRITE_ONCE(skpair->sk_err, ECONNRESET);
                        unix_state_unlock(skpair);
                        skpair->sk_state_change(skpair);
@@ -2661,11 +2672,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
        return timeo;
 }
 
-static unsigned int unix_skb_len(const struct sk_buff *skb)
-{
-       return skb->len - UNIXCB(skb).consumed;
-}
-
 struct unix_stream_read_state {
        int (*recv_actor)(struct sk_buff *, int, int,
                          struct unix_stream_read_state *);