net: lwtunnel: Handle fragmentation
Today mpls iptunnel lwtunnel_output redirect expects the tunnel
output function to handle fragmentation. This is ok but can be
avoided if we did not do the mpls output redirect too early.
ie we could wait until ip fragmentation is done and then call
mpls output for each ip fragment.
To make this work we will need,
1) the lwtunnel state to carry encap headroom
2) and do the redirect to the encap output handler on the ip fragment
(essentially do the output redirect after fragmentation)
This patch adds tunnel headroom in lwtstate to make sure we
account for tunnel data in mtu calculations during fragmentation
and adds new xmit redirect handler to redirect to lwtunnel xmit func
after ip fragmentation.
This includes IPV6 and some mtu fixes and testing from David Ahern.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1dfc402..993fd96 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -56,6 +56,7 @@
#include <net/checksum.h>
#include <linux/mroute6.h>
#include <net/l3mdev.h>
+#include <net/lwtunnel.h>
static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -104,6 +105,13 @@
}
}
+ if (lwtunnel_xmit_redirect(dst->lwtstate)) {
+ int res = lwtunnel_xmit(skb);
+
+ if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+ return res;
+ }
+
rcu_read_lock_bh();
nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4981755..09d43ff 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1604,7 +1604,9 @@
rcu_read_unlock();
out:
- return min_t(unsigned int, mtu, IP6_MAX_MTU);
+ mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+
+ return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
static struct dst_entry *icmp6_dst_gc_list;