tuntap: fix multiqueue rx

When writing packets to a descriptor associated with a combined queue, the
packets should end up on that queue.

Before this change all packets written to any descriptor associated with a
tap interface end up on rx-0, even when the descriptor is associated with a
different queue.

The rx traffic can be generated by either of the following.
  1. a simple tap program which spins up multiple queues and writes packets
     to each of the file descriptors
  2. tx from a qemu vm with a tap multiqueue netdev

The queue for rx traffic can be observed by either of the following (done
on the hypervisor in the qemu case).
  1. a simple netmap program which opens and reads from per-queue
     descriptors
  2. configuring RPS and doing per-cpu captures with rxtxcpu

Alternatively, if you printk() the return value of skb_get_rx_queue() just
before each instance of netif_receive_skb() in tun.c, you will get 65535
for every skb.

Calling skb_record_rx_queue() to set the rx queue to the queue_index fixes
the association between descriptor and rx queue.

Signed-off-by: Matthew Cover <matthew.cover@stackpath.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/tun.c

@@ -1536,6 +1536,7 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (!rx_batched || (!more && skb_queue_empty(queue))) {
 		local_bh_disable();
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 		return;
@@ -1555,8 +1556,11 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 		struct sk_buff *nskb;
 
 		local_bh_disable();
-		while ((nskb = __skb_dequeue(&process_queue)))
+		while ((nskb = __skb_dequeue(&process_queue))) {
+			skb_record_rx_queue(nskb, tfile->queue_index);
 			netif_receive_skb(nskb);
+		}
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 	}
@@ -2451,6 +2455,7 @@ build:
 	if (!rcu_dereference(tun->steering_prog))
 		rxhash = __skb_get_hash_symmetric(skb);
 
+	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
 	stats = get_cpu_ptr(tun->pcpu_stats);