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>

drivers/net/vrf.c

@@ -295,7 +295,6 @@ static struct rtable *vrf_rtable_create(struct net_device *dev)
 		rth->rt_uses_gateway = 0;
 		INIT_LIST_HEAD(&rth->rt_uncached);
 		rth->rt_uncached_list = NULL;
-		rth->rt_lwtstate = NULL;
 	}
 
 	return rth;

drivers/net/vxlan.c

@@ -1909,7 +1909,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	u32 flags = vxlan->flags;
 
 	/* FIXME: Support IPv6 */
-	info = skb_tunnel_info(skb, AF_INET);
+	info = skb_tunnel_info(skb);
 
 	if (rdst) {
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
@@ -2105,7 +2105,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_fdb *f;
 
 	/* FIXME: Support IPv6 */
-	info = skb_tunnel_info(skb, AF_INET);
+	info = skb_tunnel_info(skb);
 
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);

include/net/dst.h

@@ -44,6 +44,7 @@ struct dst_entry {
 #else
 	void			*__pad1;
 #endif
+	struct lwtunnel_state   *lwtstate;
 	int			(*input)(struct sk_buff *);
 	int			(*output)(struct sock *sk, struct sk_buff *skb);
 
@@ -89,7 +90,7 @@ struct dst_entry {
 	 * (L1_CACHE_SIZE would be too much)
 	 */
 #ifdef CONFIG_64BIT
-	long			__pad_to_align_refcnt[2];
+	long			__pad_to_align_refcnt[1];
 #endif
 	/*
 	 * __refcnt wants to be on a different cache line from

include/net/dst_metadata.h

@@ -23,22 +23,17 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
 	return NULL;
 }
 
-static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb,
-						     int family)
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
-	struct rtable *rt;
+	struct dst_entry *dst;
 
 	if (md_dst)
 		return &md_dst->u.tun_info;
 
-	switch (family) {
-	case AF_INET:
-		rt = (struct rtable *)skb_dst(skb);
-		if (rt && rt->rt_lwtstate)
-			return lwt_tun_info(rt->rt_lwtstate);
-		break;
-	}
+	dst = skb_dst(skb);
+	if (dst && dst->lwtstate)
+		return lwt_tun_info(dst->lwtstate);
 
 	return NULL;
 }

include/net/ip6_fib.h

@@ -133,7 +133,6 @@ struct rt6_info {
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
 	u8				rt6i_protocol;
-	struct lwtunnel_state		*rt6i_lwtstate;
 };
 
 static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)

include/net/lwtunnel.h

@@ -87,9 +87,7 @@ int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
 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
 
@@ -164,21 +162,11 @@ static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
 	return -EOPNOTSUPP;
 }
 
-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 */

include/net/route.h

@@ -66,7 +66,6 @@ struct rtable {
 
 	struct list_head	rt_uncached;
 	struct uncached_list	*rt_uncached_list;
-	struct lwtunnel_state   *rt_lwtstate;
 };
 
 static inline bool rt_is_input_route(const struct rtable *rt)

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 @@ struct dst_entry *dst_destroy(struct dst_entry * dst)
 		kfree(dst);
 	else
 		kmem_cache_free(dst->ops->kmem_cachep, dst);
+	lwtstate_put(dst->lwtstate);
 
 	dst = child;
 	if (dst) {

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;

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 @@ int __lwtunnel_output(struct sock *sk, struct sk_buff *skb,
 
 	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 @@ int __lwtunnel_input(struct sk_buff *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/ip_gre.c

@@ -521,7 +521,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 	__be16 df, flags;
 	int err;
 
-	tun_info = skb_tunnel_info(skb, AF_INET);
+	tun_info = skb_tunnel_info(skb);
 	if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX))
 		goto err_free_skb;
 

net/ipv4/route.c

@@ -1359,7 +1359,6 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 		list_del(&rt->rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
-	lwtstate_put(rt->rt_lwtstate);
 }
 
 void rt_flush_dev(struct net_device *dev)
@@ -1408,7 +1407,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
-		rt->rt_lwtstate = lwtstate_get(nh->nh_lwtstate);
+		rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate);
 		if (unlikely(fnhe))
 			cached = rt_bind_exception(rt, fnhe, daddr);
 		else if (!(rt->dst.flags & DST_NOCACHE))
@@ -1494,7 +1493,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
-	rth->rt_lwtstate = NULL;
 	if (our) {
 		rth->dst.input= ip_local_deliver;
 		rth->rt_flags |= RTCF_LOCAL;
@@ -1624,19 +1622,18 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
-	rth->rt_lwtstate = NULL;
 	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
 
 	rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
-	if (lwtunnel_output_redirect(rth->rt_lwtstate)) {
-		rth->rt_lwtstate->orig_output = rth->dst.output;
+	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
+		rth->dst.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;
+	if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
+		rth->dst.lwtstate->orig_input = rth->dst.input;
 		rth->dst.input = lwtunnel_input;
 	}
 	skb_dst_set(skb, &rth->dst);
@@ -1695,7 +1692,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   by fib_lookup.
 	 */
 
-	tun_info = skb_tunnel_info(skb, AF_INET);
+	tun_info = skb_tunnel_info(skb);
 	if (tun_info && tun_info->mode == IP_TUNNEL_INFO_RX)
 		fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id;
 	else
@@ -1815,7 +1812,6 @@ out:	return err;
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
-	rth->rt_lwtstate = NULL;
 
 	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
@@ -2006,7 +2002,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_gateway = 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
-	rth->rt_lwtstate = NULL;
 	RT_CACHE_STAT_INC(out_slow_tot);
 
 	if (flags & RTCF_LOCAL)
@@ -2029,7 +2024,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	}
 
 	rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0);
-	if (lwtunnel_output_redirect(rth->rt_lwtstate))
+	if (lwtunnel_output_redirect(rth->dst.lwtstate))
 		rth->dst.output = lwtunnel_output;
 
 	return rth;
@@ -2293,7 +2288,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_uses_gateway = ort->rt_uses_gateway;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
-		rt->rt_lwtstate = NULL;
 		dst_free(new);
 	}
 

net/ipv6/ila.c

@@ -89,16 +89,13 @@ static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
 static int ila_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	struct rt6_info *rt6 = NULL;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	rt6 = (struct rt6_info *)dst;
+	update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
 
-	update_ipv6_locator(skb, ila_params_lwtunnel(rt6->rt6i_lwtstate));
-
-	return rt6->rt6i_lwtstate->orig_output(sk, skb);
+	return dst->lwtstate->orig_output(sk, skb);
 
 drop:
 	kfree_skb(skb);
@@ -108,16 +105,13 @@ static int ila_output(struct sock *sk, struct sk_buff *skb)
 static int ila_input(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	struct rt6_info *rt6 = NULL;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	rt6 = (struct rt6_info *)dst;
-
-	update_ipv6_locator(skb, ila_params_lwtunnel(rt6->rt6i_lwtstate));
+	update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
 
-	return rt6->rt6i_lwtstate->orig_input(skb);
+	return dst->lwtstate->orig_input(skb);
 
 drop:
 	kfree_skb(skb);

net/ipv6/ip6_fib.c

@@ -178,7 +178,6 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref)) {
-		lwtstate_put(rt->rt6i_lwtstate);
 		rt6_free_pcpu(rt);
 		dst_free(&rt->dst);
 	}