tuntap: synchronize through tfiles array instead of tun->numqueues

[ Upstream commit 9871a9e4 ]

When a queue(tfile) is detached through __tun_detach(), we move the
last enabled tfile to the position where detached one sit but don't
NULL out last position. We expect to synchronize the datapath through
tun->numqueues. Unfortunately, this won't work since we're lacking
sufficient mechanism to order or synchronize the access to
tun->numqueues.

To fix this, NULL out the last position during detaching and check
RCU protected tfile against NULL instead of checking tun->numqueues in
datapath.

Cc: YueHaibing <yuehaibing@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: weiyongjun (A) <weiyongjun1@huawei.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c8d68e6b ("tuntap: multiqueue support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/net/tun.c

@@ -705,6 +705,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
+				   NULL);
 
 		--tun->numqueues;
 		if (clean) {
@@ -1087,7 +1089,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	tfile = rcu_dereference(tun->tfiles[txq]);
 
 	/* Drop packet if interface is not attached */
-	if (txq >= tun->numqueues)
+	if (!tfile)
 		goto drop;
 
 	if (!rcu_dereference(tun->steering_prog))
@@ -1310,6 +1312,7 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	rcu_read_lock();
 
+resample:
 	numqueues = READ_ONCE(tun->numqueues);
 	if (!numqueues) {
 		rcu_read_unlock();
@@ -1318,6 +1321,8 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
 					    numqueues]);
+	if (unlikely(!tfile))
+		goto resample;
 
 	spin_lock(&tfile->tx_ring.producer_lock);
 	for (i = 0; i < n; i++) {