ipv6: don't increase size when refragmenting forwarded ipv6 skbs

since commit 6aafeef03b9d ("netfilter: push reasm skb through instead of
original frag skbs") we will end up sometimes re-fragmenting skbs
that we've reassembled.

ipv6 defrag preserves the original skbs using the skb frag list, i.e. as long
as the skb frag list is preserved there is no problem since we keep
original geometry of fragments intact.

However, in the rare case where the frag list is munged or skb
is linearized, we might send larger fragments than what we originally
received.

A router in the path might then send packet-too-big errors even if
sender never sent fragments exceeding the reported mtu:

mtu 1500 - 1500:1400 - 1400:1280 - 1280
     A         R1         R2        B

1 - A sends to B, fragment size 1400
2 - R2 sends pkttoobig error for 1280
3 - A sends to B, fragment size 1280
4 - R2 sends pkttoobig error for 1280 again because it sees fragments of size 1400.

make sure ip6_fragment always caps MTU at largest packet size seen
when defragmented skb is forwarded.

Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 18 insertions, 11 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 61741676b987..d5f7716662db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -564,18 +564,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 	/* We must not fragment if the socket is set to force MTU discovery
 	 * or if the skb it not generated by a local socket.
 	 */
-	if (unlikely(!skb->ignore_df && skb->len > mtu) ||
-		     (IP6CB(skb)->frag_max_size &&
-		      IP6CB(skb)->frag_max_size > mtu)) {
-		if (skb->sk && dst_allfrag(skb_dst(skb)))
-			sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+	if (unlikely(!skb->ignore_df && skb->len > mtu))
+		goto fail_toobig;
 
-		skb->dev = skb_dst(skb)->dev;
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			      IPSTATS_MIB_FRAGFAILS);
-		kfree_skb(skb);
-		return -EMSGSIZE;
+	if (IP6CB(skb)->frag_max_size) {
+		if (IP6CB(skb)->frag_max_size > mtu)
+			goto fail_toobig;
+
+		/* don't send fragments larger than what we received */
+		mtu = IP6CB(skb)->frag_max_size;
+		if (mtu < IPV6_MIN_MTU)
+			mtu = IPV6_MIN_MTU;
 	}
 
 	if (np && np->frag_size < mtu) {
@@ -813,6 +812,14 @@ slow_path:
 	consume_skb(skb);
 	return err;
 
+fail_toobig:
+	if (skb->sk && dst_allfrag(skb_dst(skb)))
+		sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
+	skb->dev = skb_dst(skb)->dev;
+	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+	err = -EMSGSIZE;
+
 fail:
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_FRAGFAILS);