route: move lwtunnel state to dst_entry

Currently, the lwtunnel state resides in per-protocol data. This is
a problem if we encapsulate ipv6 traffic in an ipv4 tunnel (or vice versa).
The xmit function of the tunnel does not know whether the packet has been
routed to it by ipv4 or ipv6, yet it needs the lwtstate data. Moving the
lwtstate data to dst_entry makes such inter-protocol tunneling possible.

As a bonus, this brings a nice diffstat.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 14 insertions, 61 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index f8694d1b8702..50dcdbb0ee46 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -20,6 +20,7 @@
 #include <net/net_namespace.h>
 #include <linux/sched.h>
 #include <linux/prefetch.h>
+#include <net/lwtunnel.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -184,6 +185,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	dst->tclassid = 0;
 #endif
+	dst->lwtstate = NULL;
 	atomic_set(&dst->__refcnt, initial_ref);
 	dst->__use = 0;
 	dst->lastuse = jiffies;
@@ -264,6 +266,7 @@ again:
 		kfree(dst);
 	else
 		kmem_cache_free(dst->ops->kmem_cachep, dst);
+	lwtstate_put(dst->lwtstate);
 
 	dst = child;
 	if (dst) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 379568562ffb..b4adc961413f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1489,7 +1489,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2;
-	struct ip_tunnel_info *info = skb_tunnel_info(skb, AF_INET);
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 
 	if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags || !info))
 		return -EINVAL;
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 3331585174d9..e924c2e08554 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -179,14 +179,16 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
 }
 EXPORT_SYMBOL(lwtunnel_cmp_encap);
 
-int __lwtunnel_output(struct sock *sk, struct sk_buff *skb,
-		      struct lwtunnel_state *lwtstate)
+int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
+	struct lwtunnel_state *lwtstate;
 	int ret = -EINVAL;
 
-	if (!lwtstate)
+	if (!dst)
 		goto drop;
+	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
@@ -209,47 +211,18 @@ drop:
 
 	return ret;
 }
-
-int lwtunnel_output6(struct sock *sk, struct sk_buff *skb)
-{
-	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-	struct lwtunnel_state *lwtstate = NULL;
-
-	if (rt) {
-		lwtstate = rt->rt6i_lwtstate;
-		skb->dev = rt->dst.dev;
-	}
-
-	skb->protocol = htons(ETH_P_IPV6);
-
-	return __lwtunnel_output(sk, skb, lwtstate);
-}
-EXPORT_SYMBOL(lwtunnel_output6);
-
-int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
-{
-	struct rtable *rt = (struct rtable *)skb_dst(skb);
-	struct lwtunnel_state *lwtstate = NULL;
-
-	if (rt) {
-		lwtstate = rt->rt_lwtstate;
-		skb->dev = rt->dst.dev;
-	}
-
-	skb->protocol = htons(ETH_P_IP);
-
-	return __lwtunnel_output(sk, skb, lwtstate);
-}
 EXPORT_SYMBOL(lwtunnel_output);
 
-int __lwtunnel_input(struct sk_buff *skb,
-		     struct lwtunnel_state *lwtstate)
+int lwtunnel_input(struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
+	struct lwtunnel_state *lwtstate;
 	int ret = -EINVAL;
 
-	if (!lwtstate)
+	if (!dst)
 		goto drop;
+	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
@@ -272,27 +245,4 @@ drop:
 
 	return ret;
 }
-
-int lwtunnel_input6(struct sk_buff *skb)
-{
-	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-	struct lwtunnel_state *lwtstate = NULL;
-
-	if (rt)
-		lwtstate = rt->rt6i_lwtstate;
-
-	return __lwtunnel_input(skb, lwtstate);
-}
-EXPORT_SYMBOL(lwtunnel_input6);
-
-int lwtunnel_input(struct sk_buff *skb)
-{
-	struct rtable *rt = (struct rtable *)skb_dst(skb);
-	struct lwtunnel_state *lwtstate = NULL;
-
-	if (rt)
-		lwtstate = rt->rt_lwtstate;
-
-	return __lwtunnel_input(skb, lwtstate);
-}
 EXPORT_SYMBOL(lwtunnel_input);