gro: take care of DODGY packets

Jaroslav reported a recent throughput regression with virtio_net
caused by blamed commit.

It is unclear if DODGY GSO packets coming from user space
can be accepted by GRO engine in the future with minimal
changes, and if there is any expected gain from it.

In the meantime, make sure to detect and flush DODGY packets.

Fixes: 5eddb249 ("gro: add support of (hw)gro packets to gro stack")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-and-bisected-by: NJaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net/core/gro.c

@@ -505,8 +505,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	NAPI_GRO_CB(skb)->count = 1;
 	if (unlikely(skb_is_gso(skb))) {
 		NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
-		/* Only support TCP at the moment. */
-		if (!skb_is_gso_tcp(skb))
+		/* Only support TCP and non DODGY users. */
+		if (!skb_is_gso_tcp(skb) ||
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
 			NAPI_GRO_CB(skb)->flush = 1;
 	}