net: ipv6: Validate GSO SKB before finish IPv6 processing

There are cases where GSO segment's length exceeds the egress MTU:
 - Forwarding of a TCP GRO skb, when DF flag is not set.
 - Forwarding of an skb that arrived on a virtualisation interface
   (virtio-net/vhost/tap) with TSO/GSO size set by other network
   stack.
 - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
   interface with a smaller MTU.
 - Arriving GRO skb (or GSO skb in a virtualised environment) that is
   bridged to a NETIF_F_TSO tunnel stacked over an interface with an
   insufficient MTU.

If so:
 - Consume the SKB and its segments.
 - Issue an ICMP packet with 'Packet Too Big' message containing the
   MTU, allowing the source host to reduce its Path MTU appropriately.

Note: These cases are handled in the same manner in IPv4 output finish.
This patch aligns the behavior of IPv6 and the one of IPv4.

Fixes: 9e50849 ("netfilter: ipv6: move POSTROUTING invocation before fragmentation")
Signed-off-by: Aya Levin <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: ayalevin

net/ipv6/ip6_output.c

@@ -125,8 +125,43 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	return -EINVAL;
 }
 
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, unsigned int mtu)
+{
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features;
+	int ret = 0;
+
+	/* Please see corresponding comment in ip_finish_output_gso
+	 * describing the cases where GSO segment length exceeds the
+	 * egress MTU.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR_OR_NULL(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -135,7 +170,11 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 	}
 #endif
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	if ((skb->len > mtu && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);