net: fix pmtu check in nopmtudisc mode

For some reason ip_tunnel insist on setting the DF bit anyway when the
inner header has the DF bit set, EVEN if the tunnel was configured with
'nopmtudisc'.

This means that the script added in the previous commit
cannot be made to work by adding the 'nopmtudisc' flag to the
ip tunnel configuration. Doing so breaks connectivity even for the
without-conntrack/netfilter scenario.

When nopmtudisc is set, the tunnel will skip the mtu check, so no
icmp error is sent to client. Then, because inner header has DF set,
the outer header gets added with DF bit set as well.

IP stack then sends an error to itself because the packet exceeds
the device MTU.

Fixes: 23a3647bc4f93 ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ee65c9225178d66948a7b70b3d243499eadbc168..64594aa755f0549081185575c5108e753f50749c 100644 (file)
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -759,8 +759,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
                goto tx_error;
        }
 
-       if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-                           0, 0, false)) {
+       df = tnl_params->frag_off;
+       if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+               df |= (inner_iph->frag_off & htons(IP_DF));
+
+       if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
                ip_rt_put(rt);
                goto tx_error;
        }
@@ -788,10 +791,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
                        ttl = ip4_dst_hoplimit(&rt->dst);
        }
 
-       df = tnl_params->frag_off;
-       if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-               df |= (inner_iph->frag_off&htons(IP_DF));
-
        max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
                        + rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
        if (max_headroom > dev->needed_headroom)