Fix race condition between vxlan_sock_add and vxlan_sock_release

Currently, when trying to reuse a socket, vxlan_sock_add will grab
vn->sock_lock, locate a reusable socket, inc refcount and release
vn->sock_lock.

But vxlan_sock_release() will first decrement refcount, and then grab
that lock. refcnt operations are atomic but as currently we have
deferred works which hold vs->refcnt each, this might happen, leading to
a use after free (specially after vxlan_igmp_leave):

  CPU 1                            CPU 2

deferred work                    vxlan_sock_add
  ...                              ...
                                   spin_lock(&vn->sock_lock)
                                   vs = vxlan_find_sock();
  vxlan_sock_release
    dec vs->refcnt, reaches 0
    spin_lock(&vn->sock_lock)
                                   vxlan_sock_hold(vs), refcnt=1
                                   spin_unlock(&vn->sock_lock)
    hlist_del_rcu(&vs->hlist);
    vxlan_notify_del_rx_port(vs)
    spin_unlock(&vn->sock_lock)

So when we look for a reusable socket, we check if it wasn't freed
already before reusing it.

Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Fixes: 7c47cedf43a8b3 ("vxlan: move IGMP join/leave to work queue")
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 31ecb03..49d9f22 100644 (file)
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1985,9 +1985,8 @@ static int vxlan_init(struct net_device *dev)
        spin_lock(&vn->sock_lock);
        vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
                             vxlan->dst_port);
-       if (vs) {
+       if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) {
                /* If we have a socket with same port already, reuse it */
-               atomic_inc(&vs->refcnt);
                vxlan_vs_add_dev(vs, vxlan);
        } else {
                /* otherwise make new socket outside of RTNL */
@@ -2389,12 +2388,9 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 
        spin_lock(&vn->sock_lock);
        vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
-       if (vs) {
-               if (vs->rcv == rcv)
-                       atomic_inc(&vs->refcnt);
-               else
+       if (vs && ((vs->rcv != rcv) ||
+                  !atomic_add_unless(&vs->refcnt, 1, 0)))
                        vs = ERR_PTR(-EBUSY);
-       }
        spin_unlock(&vn->sock_lock);
 
        if (!vs)