[IPV6]: Fix IPsec datagram fragmentation

This is a long-standing bug in the IPsec IPv6 code that breaks
when we emit a IPsec tunnel-mode datagram packet.  The problem
is that the code the emits the packet assumes the IPv6 stack
will fragment it later, but the IPv6 stack assumes that whoever
is emitting the packet is going to pre-fragment the packet.

In the long term we need to fix both sides, e.g., to get the
datagram code to pre-fragment as well as to get the IPv6 stack
to fragment locally generated tunnel-mode packet.

For now this patch does the second part which should make it
work for the IPsec host case.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 6 insertions, 2 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9ac6ca2..4e9a2fe 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -621,7 +621,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 * or if the skb it not generated by a local socket.  (This last
 	 * check should be redundant, but it's free.)
 	 */
-	if (!np || np->pmtudisc >= IPV6_PMTUDISC_DO) {
+	if (skb->local_df) {
 		skb->dev = skb->dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
 		IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
@@ -1420,6 +1420,10 @@ int ip6_push_pending_frames(struct sock *sk)
 		tmp_skb->sk = NULL;
 	}
 
+	/* Allow local fragmentation. */
+	if (np->pmtudisc >= IPV6_PMTUDISC_DO)
+		skb->local_df = 1;
+
 	ipv6_addr_copy(final_dst, &fl->fl6_dst);
 	__skb_pull(skb, skb_network_header_len(skb));
 	if (opt && opt->opt_flen)
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index b34c58c..79ccfb0 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -36,7 +36,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (skb->len > mtu) {
+	if (!skb->local_df && skb->len > mtu) {
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
 		ret = -EMSGSIZE;