In case of netlink mmap, there can be situations where received frames
have to be placed into the normal receive queue. The ring buffer indicates
this through NL_MMAP_STATUS_COPY, so the user is asked to pick them up
via recvmsg(2) syscall, and to put the slot back to NL_MMAP_STATUS_UNUSED.
Commit 0ef707700f1c ("netlink: rx mmap: fix POLLIN condition") changed
polling, so that we walk in the worst case the whole ring through the
new netlink_has_valid_frame(), for example, when the ring would have no
NL_MMAP_STATUS_VALID, but at least one NL_MMAP_STATUS_COPY frame.
Since we do a datagram_poll() already earlier to pick up a mask that could
possibly contain POLLIN | POLLRDNORM already (due to NL_MMAP_STATUS_COPY),
we can skip checking the rx ring entirely.
In case the kernel is compiled with !CONFIG_NETLINK_MMAP, then all this is
irrelevant anyway as netlink_poll() is just defined as datagram_poll().
Signed-off-by: Daniel Borkmann <dan...@iogearbox.net>
---
net/netlink/af_netlink.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 50889be..72c1330 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -674,12 +674,19 @@ static unsigned int netlink_poll(struct file *file,
struct socket *sock,
mask = datagram_poll(file, sock, wait);
- spin_lock_bh(&sk->sk_receive_queue.lock);
- if (nlk->rx_ring.pg_vec) {
- if (netlink_has_valid_frame(&nlk->rx_ring))
- mask |= POLLIN | POLLRDNORM;
+ /* We could already have received frames in the normal receive
+ * queue, that will show up as NL_MMAP_STATUS_COPY in the ring,
+ * so if mask contains pollin/etc already, there's no point
+ * walking the ring.
+ */
+ if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) {
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ if (nlk->rx_ring.pg_vec) {
+ if (netlink_has_valid_frame(&nlk->rx_ring))
+ mask |= POLLIN | POLLRDNORM;
+ }
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
}
- spin_unlock_bh(&sk->sk_receive_queue.lock);
spin_lock_bh(&sk->sk_write_queue.lock);
if (nlk->tx_ring.pg_vec) {
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
