lwt: Add support to redirect dst.input

This patch adds the capability to redirect dst input in the same way
that dst output is redirected by LWT.

Also, save the original dst.input and and dst.out when setting up
lwtunnel redirection. These can be called by the client as a pass-
through.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/lwtunnel.h

@@ -11,12 +11,15 @@
 #define LWTUNNEL_HASH_SIZE   (1 << LWTUNNEL_HASH_BITS)
 
 /* lw tunnel state flags */
-#define LWTUNNEL_STATE_OUTPUT_REDIRECT 0x1
+#define LWTUNNEL_STATE_OUTPUT_REDIRECT	BIT(0)
+#define LWTUNNEL_STATE_INPUT_REDIRECT	BIT(1)
 
 struct lwtunnel_state {
 	__u16		type;
 	__u16		flags;
 	atomic_t	refcnt;
+	int		(*orig_output)(struct sock *sk, struct sk_buff *skb);
+	int		(*orig_input)(struct sk_buff *);
 	int             len;
 	__u8            data[0];
 };
@@ -25,6 +28,7 @@ struct lwtunnel_encap_ops {
 	int (*build_state)(struct net_device *dev, struct nlattr *encap,
 			   struct lwtunnel_state **ts);
 	int (*output)(struct sock *sk, struct sk_buff *skb);
+	int (*input)(struct sk_buff *skb);
 	int (*fill_encap)(struct sk_buff *skb,
 			  struct lwtunnel_state *lwtstate);
 	int (*get_encap_size)(struct lwtunnel_state *lwtstate);
@@ -58,6 +62,13 @@ static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
 	return false;
 }
 
+static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate)
+{
+	if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT))
+		return true;
+
+	return false;
+}
 int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
@@ -72,6 +83,8 @@ struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
 int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
 int lwtunnel_output(struct sock *sk, struct sk_buff *skb);
 int lwtunnel_output6(struct sock *sk, struct sk_buff *skb);
+int lwtunnel_input(struct sk_buff *skb);
+int lwtunnel_input6(struct sk_buff *skb);
 
 #else
 
@@ -90,6 +103,11 @@ static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
 	return false;
 }
 
+static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate)
+{
+	return false;
+}
+
 static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 					 unsigned int num)
 {
@@ -142,6 +160,16 @@ static inline int lwtunnel_output6(struct sock *sk, struct sk_buff *skb)
 	return -EOPNOTSUPP;
 }
 
+static inline int lwtunnel_input(struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_input6(struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* __NET_LWTUNNEL_H */

net/core/lwtunnel.c

@@ -241,3 +241,58 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
 	return __lwtunnel_output(sk, skb, lwtstate);
 }
 EXPORT_SYMBOL(lwtunnel_output);
+
+int __lwtunnel_input(struct sk_buff *skb,
+		     struct lwtunnel_state *lwtstate)
+{
+	const struct lwtunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (!lwtstate)
+		goto drop;
+
+	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
+		return 0;
+
+	ret = -EOPNOTSUPP;
+	rcu_read_lock();
+	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
+	if (likely(ops && ops->input))
+		ret = ops->input(skb);
+	rcu_read_unlock();
+
+	if (ret == -EOPNOTSUPP)
+		goto drop;
+
+	return ret;
+
+drop:
+	kfree_skb(skb);
+
+	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);

net/ipv4/route.c

@@ -1631,8 +1631,14 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->dst.output = ip_output;
 
 	rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
-	if (lwtunnel_output_redirect(rth->rt_lwtstate))
+	if (lwtunnel_output_redirect(rth->rt_lwtstate)) {
+		rth->rt_lwtstate->orig_output = rth->dst.output;
 		rth->dst.output = lwtunnel_output;
+	}
+	if (lwtunnel_input_redirect(rth->rt_lwtstate)) {
+		rth->rt_lwtstate->orig_input = rth->dst.input;
+		rth->dst.input = lwtunnel_input;
+	}
 	skb_dst_set(skb, &rth->dst);
 out:
 	err = 0;

net/ipv6/route.c

@@ -1785,8 +1785,14 @@ int ip6_route_add(struct fib6_config *cfg)
 		if (err)
 			goto out;
 		rt->rt6i_lwtstate = lwtstate_get(lwtstate);
-		if (lwtunnel_output_redirect(rt->rt6i_lwtstate))
+		if (lwtunnel_output_redirect(rt->rt6i_lwtstate)) {
+			rt->rt6i_lwtstate->orig_output = rt->dst.output;
 			rt->dst.output = lwtunnel_output6;
+		}
+		if (lwtunnel_input_redirect(rt->rt6i_lwtstate)) {
+			rt->rt6i_lwtstate->orig_input = rt->dst.input;
+			rt->dst.input = lwtunnel_input6;
+		}
 	}
 
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);