[PATCH ipsec-next 5/7] net: xfrm: Deliver packets to keyed VTI tunnels.

[Lorenzo Colitti <lorenzo@google.com>]

- Input works as follows:
  1. Attempt to match a regular VTI by IP addresses only. If that
     succeeds, use the i_key as the mark to look up the xfrm
     state.
  2. If the match failed, do an XFRM state lookup that ignores
     the mark. If that finds an state, then use the state match's
     mark to find the tunnel by its i_key.
- ICMP errors: similar to input, except the search is for the
  outbound XFRM state and the tunnel is found by o_key instead of
  by i_key.
- The output path is the same as existing VTIs. A routing lookup
  matches a VTI interface. The VTI uses its o_key as the mark to
  select an XFRM state. The state transforms the packet.

Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
 net/ipv4/ip_vti.c  | 52 ++++++++++++++++++++++++++++++------------
 net/ipv6/ip6_vti.c | 67 ++++++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 88 insertions(+), 31 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 21f93e398e..9d28433a60 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -63,6 +63,18 @@ vti4_find_tunnel(struct sk_buff *skb, __be32 spi, struct xfrm_state **x)
 		*x = xfrm_state_lookup(net, be32_to_cpu(tunnel->parms.i_key),
 				       (xfrm_address_t *)&iph->daddr,
 				       spi, iph->protocol, AF_INET);
+	} else {
+		*x = xfrm_state_lookup_loose(net, skb->mark,
+					     (xfrm_address_t *)&iph->daddr,
+					     spi, iph->protocol, AF_INET);
+		if (!*x)
+			return NULL;
+		tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_KEY,
+					  TUNNEL_LOOKUP_NO_KEY,
+					  iph->saddr, iph->daddr,
+					  cpu_to_be32((*x)->mark.v));
+		if (!tunnel)
+			xfrm_state_put(*x);
 	}
 
 	return tunnel;
@@ -302,7 +314,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 static int vti4_err(struct sk_buff *skb, u32 info)
 {
 	__be32 spi;
-	__u32 mark;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel;
 	struct ip_esp_hdr *esph;
@@ -313,13 +324,6 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 	int protocol = iph->protocol;
 	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
 
-	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, 0,
-				  iph->daddr, iph->saddr, 0);
-	if (!tunnel)
-		return -1;
-
-	mark = be32_to_cpu(tunnel->parms.o_key);
-
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
@@ -347,18 +351,38 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 		return 0;
 	}
 
-	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
-			      spi, protocol, AF_INET);
-	if (!x)
-		return 0;
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, 0,
+				  iph->daddr, iph->saddr, 0);
+	if (tunnel) {
+		x = xfrm_state_lookup(net, be32_to_cpu(tunnel->parms.o_key),
+				      (xfrm_address_t *)&iph->daddr,
+				      spi, iph->protocol, AF_INET);
+	} else {
+		x = xfrm_state_lookup_loose(net, skb->mark,
+					    (xfrm_address_t *)&iph->daddr,
+					    spi, iph->protocol, AF_INET);
+		if (!x)
+			goto out;
+		tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_KEY,
+					  TUNNEL_LOOKUP_NO_KEY |
+					  TUNNEL_LOOKUP_OKEY,
+					  iph->daddr, iph->saddr,
+					  cpu_to_be32(x->mark.v));
+	}
+
+	if (!tunnel || !x)
+		goto out;
 
 	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
 		ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
 	else
 		ipv4_redirect(skb, net, 0, 0, protocol, 0);
-	xfrm_state_put(x);
 
-	return 0;
+out:
+	if (x)
+		xfrm_state_put(x);
+
+	return tunnel ? 0 : -1;
 }
 
 static int
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5994fedd19..bf64821b8a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -78,11 +78,21 @@ struct vti6_net {
 #define for_each_vti6_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
+static bool vti6_match_key(const struct ip6_tnl *t, __be32 key, bool in)
+{
+	__be16 tunnel_key = in ? t->parms.i_key : t->parms.o_key;
+	__be16 flags = in ? t->parms.i_flags : t->parms.o_flags;
+
+	return !(flags & TUNNEL_KEY) || tunnel_key == key;
+}
+
 /**
- * vti6_tnl_lookup - fetch tunnel matching the end-point addresses
+ * vti6_tnl_lookup - fetch tunnel matching the end-point addresses and key
  *   @net: network namespace
  *   @remote: the address of the tunnel exit-point
  *   @local: the address of the tunnel entry-point
+ *   @key: the key of the tunnel
+ *   @in: whether to match i_key or i_key
  *
  * Return:
  *   tunnel matching given end-points if found,
@@ -91,7 +101,7 @@ struct vti6_net {
  **/
 static struct ip6_tnl *
 vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
-		const struct in6_addr *local)
+		const struct in6_addr *local, __be32 key, bool in)
 {
 	unsigned int hash = HASH(remote, local);
 	struct ip6_tnl *t;
@@ -101,6 +111,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
 		    ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    vti6_match_key(t, key, in) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -109,6 +120,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	hash = HASH(&any, local);
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    vti6_match_key(t, key, in) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -116,6 +128,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	hash = HASH(remote, &any);
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    vti6_match_key(t, key, in) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -266,7 +279,8 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
 	     (t = rtnl_dereference(*tp)) != NULL;
 	     tp = &t->next) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_equal(remote, &t->parms.raddr)) {
+		    ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    vti6_match_key(t, p->i_key, true)) {
 			if (create)
 				return NULL;
 
@@ -304,11 +318,21 @@ vti6_find_tunnel(struct sk_buff *skb, __be32 spi, struct xfrm_state **x)
 	struct net *net = dev_net(skb->dev);
 	struct ip6_tnl *t;
 
-	t = vti6_tnl_lookup(net, &ipv6h->saddr, &ipv6h->daddr);
+	t = vti6_tnl_lookup(net, &ipv6h->saddr, &ipv6h->daddr, 0, true);
 	if (t) {
 		*x = xfrm_state_lookup(net, be32_to_cpu(t->parms.i_key),
 				       (xfrm_address_t *)&ipv6h->daddr,
 				       spi, ipv6h->nexthdr, AF_INET6);
+	} else {
+		*x = xfrm_state_lookup_loose(net, skb->mark,
+					     (xfrm_address_t *)&ipv6h->daddr,
+					     spi, ipv6h->nexthdr, AF_INET6);
+		if (!*x)
+			return NULL;
+		t =  vti6_tnl_lookup(net, &ipv6h->saddr, &ipv6h->daddr,
+				     cpu_to_be32((*x)->mark.v), true);
+		if (!t)
+			xfrm_state_put(*x);
 	}
 
 	return t;
@@ -613,7 +637,6 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    u8 type, u8 code, int offset, __be32 info)
 {
 	__be32 spi;
-	__u32 mark;
 	struct xfrm_state *x;
 	struct ip6_tnl *t;
 	struct ip_esp_hdr *esph;
@@ -623,12 +646,6 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
 	int protocol = iph->nexthdr;
 
-	t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr);
-	if (!t)
-		return -1;
-
-	mark = be32_to_cpu(t->parms.o_key);
-
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data + offset);
@@ -650,19 +667,35 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	    type != NDISC_REDIRECT)
 		return 0;
 
-	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
-			      spi, protocol, AF_INET6);
-	if (!x)
-		return 0;
+	t = vti6_tnl_lookup(net, &iph->daddr, &iph->saddr, 0, false);
+	if (t) {
+		x = xfrm_state_lookup(net, be32_to_cpu(t->parms.o_key),
+				      (xfrm_address_t *)&iph->daddr,
+				      spi, protocol, AF_INET6);
+	} else {
+		x = xfrm_state_lookup_loose(net, skb->mark,
+					    (xfrm_address_t *)&iph->daddr,
+					    spi, protocol, AF_INET6);
+		if (!x)
+			goto out;
+		t = vti6_tnl_lookup(net, &iph->daddr, &iph->saddr,
+				    cpu_to_be32(x->mark.v), false);
+	}
+
+	if (!t || !x)
+		goto out;
 
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0,
 			     sock_net_uid(net, NULL));
 	else
 		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
-	xfrm_state_put(x);
 
-	return 0;
+out:
+	if (x)
+		xfrm_state_put(x);
+
+	return t ? 0 : -1;
 }
 
 static void vti6_link_config(struct ip6_tnl *t)
-- 
2.15.1.620.gb9897f4670-goog