ip_tunnel: fix ipv4 pmtu check to honor inner ip header df

Frag needed should be sent only if the inner header asked
to not fragment. Currently fragmentation is broken if the
tunnel has df set, but df was not asked in the original
packet. The tunnel's df needs to be still checked to update
internally the pmtu cache.

Commit 23a3647bc4f93bac broke it, and this commit fixes
the ipv4 df check back to the way it was.

Fixes: 23a3647bc4f93bac ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4c2c3ba..626d9e5 100644 (file)
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -586,7 +586,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 EXPORT_SYMBOL(ip_tunnel_encap);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-                           struct rtable *rt, __be16 df)
+                           struct rtable *rt, __be16 df,
+                           const struct iphdr *inner_iph)
 {
        struct ip_tunnel *tunnel = netdev_priv(dev);
        int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -603,7 +604,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
        if (skb->protocol == htons(ETH_P_IP)) {
                if (!skb_is_gso(skb) &&
-                   (df & htons(IP_DF)) && mtu < pkt_size) {
+                   (inner_iph->frag_off & htons(IP_DF)) &&
+                   mtu < pkt_size) {
                        memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
                        icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
                        return -E2BIG;
@@ -737,7 +739,7 @@ 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)) {
+       if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
                ip_rt_put(rt);
                goto tx_error;
        }