summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
authorRoopa Prabhu <roopa@cumulusnetworks.com>2016-08-24 20:10:43 -0700
committerDavid S. Miller <davem@davemloft.net>2016-08-30 22:27:18 -0700
commit14972cbd34ff668c390cbd2e6497323484c9e812 (patch)
tree2931fb8d4a03a3ecf457f9789abd802cecdc4fbb /net/ipv4
parent41852497a9205964b958a245a9526040b980926f (diff)
downloadlinux-14972cbd34ff668c390cbd2e6497323484c9e812.tar.bz2
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>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ip_output.c8
-rw-r--r--net/ipv4/route.c4
2 files changed, 11 insertions, 1 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index dde37fb340bf..65569274efb8 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -73,6 +73,7 @@
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
+#include <net/lwtunnel.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
@@ -197,6 +198,13 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
skb = skb2;
}
+ 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 = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a1f2830d8110..3e992783c1d0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1246,7 +1246,9 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = 576;
}
- return min_t(unsigned int, mtu, IP_MAX_MTU);
+ mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
+
+ return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)