af_unix: fix unix_dgram_poll() behavior for EPOLLOUT event

Alban Crequy reported a problem with connected dgram af_unix sockets and
provided a test program. epoll() would miss to send an EPOLLOUT event
when a thread unqueues a packet from the other peer, making its receive
queue not full.

This is because unix_dgram_poll() fails to call sock_poll_wait(file,
&unix_sk(other)->peer_wait, wait);
if the socket is not writeable at the time epoll_ctl(ADD) is called.

We must call sock_poll_wait(), regardless of 'writable' status, so that
epoll can be notified later of states changes.

Misc: avoids testing twice (sk->sk_shutdown & RCV_SHUTDOWN)

Reported-by: Alban Crequy <alban.crequy@collabora.co.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f33c5958dbb2c839ef74df4be685e6d7d12fc374..e8898758dd316bffe435e8074607b140d746588c 100644 (file)
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2074,13 +2074,12 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
        if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
                mask |= POLLERR;
        if (sk->sk_shutdown & RCV_SHUTDOWN)
-               mask |= POLLRDHUP;
+               mask |= POLLRDHUP | POLLIN | POLLRDNORM;
        if (sk->sk_shutdown == SHUTDOWN_MASK)
                mask |= POLLHUP;
 
        /* readable? */
-       if (!skb_queue_empty(&sk->sk_receive_queue) ||
-           (sk->sk_shutdown & RCV_SHUTDOWN))
+       if (!skb_queue_empty(&sk->sk_receive_queue))
                mask |= POLLIN | POLLRDNORM;
 
        /* Connection-based need to check for termination and startup */
@@ -2092,20 +2091,15 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
                        return mask;
        }
 
-       /* writable? */
        writable = unix_writable(sk);
-       if (writable) {
-               other = unix_peer_get(sk);
-               if (other) {
-                       if (unix_peer(other) != sk) {
-                               sock_poll_wait(file, &unix_sk(other)->peer_wait,
-                                         wait);
-                               if (unix_recvq_full(other))
-                                       writable = 0;
-                       }
-
-                       sock_put(other);
+       other = unix_peer_get(sk);
+       if (other) {
+               if (unix_peer(other) != sk) {
+                       sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
+                       if (unix_recvq_full(other))
+                               writable = 0;
                }
+               sock_put(other);
        }
 
        if (writable)