[NETFILTER]: Fix xfrm lookup in ip_route_me_harder/ip6_route_me_harder

ip_route_me_harder doesn't use the port numbers of the xfrm lookup and
uses ip_route_input for non-local addresses which doesn't do a xfrm
lookup, ip6_route_me_harder doesn't do a xfrm lookup at all.

Use xfrm_decode_session and do the lookup manually, make sure both
only do the lookup if the packet hasn't been transformed already.

Makeing sure the lookup only happens once needs a new field in the
IP6CB, which exceeds the size of skb->cb. The size of skb->cb is
increased to 48b. Apparently the IPv6 mobile extensions need some
more room anyway.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 13 insertions, 4 deletions

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 65c3a91ed85e..de16e944777f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -832,7 +832,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
         skb->h.raw = skb->nh.raw;
         skb->nh.raw = skb_push(skb, gre_hlen);
         memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-        IPCB(skb)->flags &= ~IPSKB_XFRM_TUNNEL_SIZE;
+        IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED);
         dst_release(skb->dst);
         skb->dst = &rt->u.dst;
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 078b59be91f4..bbd85f5ec985 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -621,7 +621,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
         skb->h.raw = skb->nh.raw;
         skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
         memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-        IPCB(skb)->flags &= ~IPSKB_XFRM_TUNNEL_SIZE;
+        IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED);
         dst_release(skb->dst);
         skb->dst = &rt->u.dst;
 
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index ae0779d82c5d..4c637a1cbd23 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -7,11 +7,13 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 
+#include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmp.h>
 #include <net/route.h>
-#include <linux/ip.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
 int ip_route_me_harder(struct sk_buff **pskb)
@@ -33,7 +35,6 @@ int ip_route_me_harder(struct sk_buff **pskb)
 #ifdef CONFIG_IP_ROUTE_FWMARK
                 fl.nl_u.ip4_u.fwmark = (*pskb)->nfmark;
 #endif
-                fl.proto = iph->protocol;
                 if (ip_route_output_key(&rt, &fl) != 0)
                         return -1;
 
@@ -60,6 +61,13 @@ int ip_route_me_harder(struct sk_buff **pskb)
         if ((*pskb)->dst->error)
                 return -1;
 
+#ifdef CONFIG_XFRM
+        if (!(IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+            xfrm_decode_session(*pskb, &fl, AF_INET) == 0)
+                if (xfrm_lookup(&(*pskb)->dst, &fl, (*pskb)->sk, 0))
+                        return -1;
+#endif
+
         /* Change in oif may mean change in hh_len. */
         hh_len = (*pskb)->dst->dev->hard_header_len;
         if (skb_headroom(*pskb) < hh_len) {
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 51fabb8f7c54..160c48800ab8 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -140,6 +140,7 @@ static int xfrm4_output_one(struct sk_buff *skb)
                 x = dst->xfrm;
         } while (x && !x->props.mode);
 
+        IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
         err = 0;
 
 out_exit: