1 files changed, 274 insertions, 613 deletions

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c3a4233c0ac..b8960f3527f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -34,358 +34,147 @@
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
+#include <linux/icmpv6.h>
 
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
 #include <net/inet_ecn.h>
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
-#define HASH_SIZE  16
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1))
-
 static struct rtnl_link_ops vti_link_ops __read_mostly;
 
 static int vti_net_id __read_mostly;
-struct vti_net {
-	struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
-	struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
-	struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
-	struct ip_tunnel __rcu *tunnels_wc[1];
-	struct ip_tunnel __rcu **tunnels[4];
-
-	struct net_device *fb_tunnel_dev;
-};
-
-static int vti_fb_tunnel_init(struct net_device *dev);
 static int vti_tunnel_init(struct net_device *dev);
-static void vti_tunnel_setup(struct net_device *dev);
-static void vti_dev_free(struct net_device *dev);
-static int vti_tunnel_bind_dev(struct net_device *dev);
-
-#define VTI_XMIT(stats1, stats2) do {				\
-	int err;						\
-	int pkt_len = skb->len;					\
-	err = dst_output(skb);					\
-	if (net_xmit_eval(err) == 0) {				\
-		u64_stats_update_begin(&(stats1)->syncp);	\
-		(stats1)->tx_bytes += pkt_len;			\
-		(stats1)->tx_packets++;				\
-		u64_stats_update_end(&(stats1)->syncp);		\
-	} else {						\
-		(stats2)->tx_errors++;				\
-		(stats2)->tx_aborted_errors++;			\
-	}							\
-} while (0)
-
-
-static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev,
-						 struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
-	}
-
-	tot->multicast = dev->stats.multicast;
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_errors = dev->stats.rx_errors;
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
-
-	return tot;
-}
 
-static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
-					   __be32 remote, __be32 local)
+static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		     int encap_type)
 {
-	unsigned h0 = HASH(remote);
-	unsigned h1 = HASH(local);
-	struct ip_tunnel *t;
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-
-	for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
-		if (local == t->parms.iph.saddr &&
-		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
-			return t;
-	for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
-		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
-			return t;
-
-	for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
-		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
-			return t;
-
-	for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0])
-		if (t && (t->dev->flags&IFF_UP))
-			return t;
-	return NULL;
-}
+	struct ip_tunnel *tunnel;
+	const struct iphdr *iph = ip_hdr(skb);
+	struct net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
 
-static struct ip_tunnel __rcu **__vti_bucket(struct vti_net *ipn,
-					     struct ip_tunnel_parm *parms)
-{
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	unsigned h = 0;
-	int prio = 0;
-
-	if (remote) {
-		prio |= 2;
-		h ^= HASH(remote);
-	}
-	if (local) {
-		prio |= 1;
-		h ^= HASH(local);
-	}
-	return &ipn->tunnels[prio][h];
-}
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel != NULL) {
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
 
-static inline struct ip_tunnel __rcu **vti_bucket(struct vti_net *ipn,
-						  struct ip_tunnel *t)
-{
-	return __vti_bucket(ipn, &t->parms);
-}
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+		skb->mark = be32_to_cpu(tunnel->parms.i_key);
 
-static void vti_tunnel_unlink(struct vti_net *ipn, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp;
-	struct ip_tunnel *iter;
-
-	for (tp = vti_bucket(ipn, t);
-	     (iter = rtnl_dereference(*tp)) != NULL;
-	     tp = &iter->next) {
-		if (t == iter) {
-			rcu_assign_pointer(*tp, t->next);
-			break;
-		}
+		return xfrm_input(skb, nexthdr, spi, encap_type);
 	}
-}
 
-static void vti_tunnel_link(struct vti_net *ipn, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp = vti_bucket(ipn, t);
-
-	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
-	rcu_assign_pointer(*tp, t);
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
-static struct ip_tunnel *vti_tunnel_locate(struct net *net,
-					   struct ip_tunnel_parm *parms,
-					   int create)
+static int vti_rcv(struct sk_buff *skb)
 {
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	struct ip_tunnel *t, *nt;
-	struct ip_tunnel __rcu **tp;
-	struct net_device *dev;
-	char name[IFNAMSIZ];
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-
-	for (tp = __vti_bucket(ipn, parms);
-	     (t = rtnl_dereference(*tp)) != NULL;
-	     tp = &t->next) {
-		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
-			return t;
-	}
-	if (!create)
-		return NULL;
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
 
-	if (parms->name[0])
-		strlcpy(name, parms->name, IFNAMSIZ);
-	else
-		strcpy(name, "vti%d");
-
-	dev = alloc_netdev(sizeof(*t), name, vti_tunnel_setup);
-	if (dev == NULL)
-		return NULL;
-
-	dev_net_set(dev, net);
-
-	nt = netdev_priv(dev);
-	nt->parms = *parms;
-	dev->rtnl_link_ops = &vti_link_ops;
-
-	vti_tunnel_bind_dev(dev);
-
-	if (register_netdevice(dev) < 0)
-		goto failed_free;
-
-	dev_hold(dev);
-	vti_tunnel_link(ipn, nt);
-	return nt;
-
-failed_free:
-	free_netdev(dev);
-	return NULL;
+	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
 }
 
-static void vti_tunnel_uninit(struct net_device *dev)
+static int vti_rcv_cb(struct sk_buff *skb, int err)
 {
-	struct net *net = dev_net(dev);
-	struct vti_net *ipn = net_generic(net, vti_net_id);
+	unsigned short family;
+	struct net_device *dev;
+	struct pcpu_sw_netstats *tstats;
+	struct xfrm_state *x;
+	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
 
-	vti_tunnel_unlink(ipn, netdev_priv(dev));
-	dev_put(dev);
-}
+	if (!tunnel)
+		return 1;
 
-static int vti_err(struct sk_buff *skb, u32 info)
-{
+	dev = tunnel->dev;
 
-	/* All the routers (except for Linux) return only
-	 * 8 bytes of packet payload. It means, that precise relaying of
-	 * ICMP in the real Internet is absolutely infeasible.
-	 */
-	struct iphdr *iph = (struct iphdr *)skb->data;
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	struct ip_tunnel *t;
-	int err;
+	if (err) {
+		dev->stats.rx_errors++;
+		dev->stats.rx_dropped++;
 
-	switch (type) {
-	default:
-	case ICMP_PARAMETERPROB:
 		return 0;
-
-	case ICMP_DEST_UNREACH:
-		switch (code) {
-		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
-			/* Impossible event. */
-			return 0;
-		default:
-			/* All others are translated to HOST_UNREACH. */
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return 0;
-		break;
 	}
 
-	err = -ENOENT;
+	x = xfrm_input_state(skb);
+	family = x->inner_mode->afinfo->family;
 
-	t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
-	if (t == NULL)
-		goto out;
+	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		return -EPERM;
 
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPIP, 0);
-		err = 0;
-		goto out;
-	}
+	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
+	skb->dev = dev;
 
-	err = 0;
-	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
-		goto out;
+	tstats = this_cpu_ptr(dev->tstats);
 
-	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
-		t->err_count++;
-	else
-		t->err_count = 1;
-	t->err_time = jiffies;
-out:
-	return err;
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_packets++;
+	tstats->rx_bytes += skb->len;
+	u64_stats_update_end(&tstats->syncp);
+
+	return 0;
 }
 
-/* We dont digest the packet therefore let the packet pass */
-static int vti_rcv(struct sk_buff *skb)
+static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
 {
-	struct ip_tunnel *tunnel;
-	const struct iphdr *iph = ip_hdr(skb);
-
-	tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
-	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
+	xfrm_address_t *daddr = (xfrm_address_t *)&dst;
+	xfrm_address_t *saddr = (xfrm_address_t *)&src;
 
-		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
-			return -1;
+	/* if there is no transform then this tunnel is not functional.
+	 * Or if the xfrm is not mode tunnel.
+	 */
+	if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
+	    x->props.family != AF_INET)
+		return false;
 
-		tstats = this_cpu_ptr(tunnel->dev->tstats);
-		u64_stats_update_begin(&tstats->syncp);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
-		u64_stats_update_end(&tstats->syncp);
+	if (!dst)
+		return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
 
-		skb->mark = 0;
-		secpath_reset(skb);
-		skb->dev = tunnel->dev;
-		return 1;
-	}
+	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
+		return false;
 
-	return -1;
+	return true;
 }
 
-/* This function assumes it is being called from dev_queue_xmit()
- * and that skb is filled properly by that function.
- */
-
-static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
+			    struct flowi *fl)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct pcpu_tstats *tstats;
-	struct iphdr  *tiph = &tunnel->parms.iph;
-	u8     tos;
-	struct rtable *rt;		/* Route to the other host */
+	struct ip_tunnel_parm *parms = &tunnel->parms;
+	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
-	struct iphdr  *old_iph = ip_hdr(skb);
-	__be32 dst = tiph->daddr;
-	struct flowi4 fl4;
-
-	if (skb->protocol != htons(ETH_P_IP))
-		goto tx_error;
+	int err;
 
-	tos = old_iph->tos;
+	if (!dst) {
+		dev->stats.tx_carrier_errors++;
+		goto tx_error_icmp;
+	}
 
-	memset(&fl4, 0, sizeof(fl4));
-	flowi4_init_output(&fl4, tunnel->parms.link,
-			   be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
-			   RT_SCOPE_UNIVERSE,
-			   IPPROTO_IPIP, 0,
-			   dst, tiph->saddr, 0, 0);
-	rt = ip_route_output_key(dev_net(dev), &fl4);
-	if (IS_ERR(rt)) {
+	dst_hold(dst);
+	dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
+	if (IS_ERR(dst)) {
 		dev->stats.tx_carrier_errors++;
 		goto tx_error_icmp;
 	}
-	/* if there is no transform then this tunnel is not functional.
-	 * Or if the xfrm is not mode tunnel.
-	 */
-	if (!rt->dst.xfrm ||
-	    rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
+
+	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
 		dev->stats.tx_carrier_errors++;
+		dst_release(dst);
 		goto tx_error_icmp;
 	}
-	tdev = rt->dst.dev;
+
+	tdev = dst->dev;
 
 	if (tdev == dev) {
-		ip_rt_put(rt);
+		dst_release(dst);
 		dev->stats.collisions++;
 		goto tx_error;
 	}
@@ -399,61 +188,114 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			tunnel->err_count = 0;
 	}
 
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-	nf_reset(skb);
+	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;
 
-	tstats = this_cpu_ptr(dev->tstats);
-	VTI_XMIT(tstats, &dev->stats);
+	err = dst_output(skb);
+	if (net_xmit_eval(err) == 0)
+		err = skb->len;
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
 
 tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
-static int vti_tunnel_bind_dev(struct net_device *dev)
+/* This function assumes it is being called from dev_queue_xmit()
+ * and that skb is filled properly by that function.
+ */
+static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct net_device *tdev = NULL;
-	struct ip_tunnel *tunnel;
-	struct iphdr *iph;
-
-	tunnel = netdev_priv(dev);
-	iph = &tunnel->parms.iph;
-
-	if (iph->daddr) {
-		struct rtable *rt;
-		struct flowi4 fl4;
-		memset(&fl4, 0, sizeof(fl4));
-		flowi4_init_output(&fl4, tunnel->parms.link,
-				   be32_to_cpu(tunnel->parms.i_key),
-				   RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
-				   IPPROTO_IPIP, 0,
-				   iph->daddr, iph->saddr, 0, 0);
-		rt = ip_route_output_key(dev_net(dev), &fl4);
-		if (!IS_ERR(rt)) {
-			tdev = rt->dst.dev;
-			ip_rt_put(rt);
-		}
-		dev->flags |= IFF_POINTOPOINT;
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(fl));
+
+	skb->mark = be32_to_cpu(tunnel->parms.o_key);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		xfrm_decode_session(skb, &fl, AF_INET);
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		break;
+	case htons(ETH_P_IPV6):
+		xfrm_decode_session(skb, &fl, AF_INET6);
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		break;
+	default:
+		dev->stats.tx_errors++;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
 	}
 
-	if (!tdev && tunnel->parms.link)
-		tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+	return vti_xmit(skb, dev, &fl);
+}
+
+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;
+	struct ip_auth_hdr *ah ;
+	struct ip_comp_hdr *ipch;
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	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,
+				  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));
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
 
-	if (tdev) {
-		dev->hard_header_len = tdev->hard_header_len +
-				       sizeof(struct iphdr);
-		dev->mtu = tdev->mtu;
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return 0;
+	case ICMP_REDIRECT:
+		break;
+	default:
+		return 0;
 	}
-	dev->iflink = tunnel->parms.link;
-	return dev->mtu;
+
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET);
+	if (!x)
+		return 0;
+
+	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;
 }
 
 static int
@@ -461,282 +303,130 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	int err = 0;
 	struct ip_tunnel_parm p;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-
-	switch (cmd) {
-	case SIOCGETTUNNEL:
-		t = NULL;
-		if (dev == ipn->fb_tunnel_dev) {
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data,
-					   sizeof(p))) {
-				err = -EFAULT;
-				break;
-			}
-			t = vti_tunnel_locate(net, &p, 0);
-		}
-		if (t == NULL)
-			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof(p));
-		p.i_flags |= GRE_KEY | VTI_ISVTI;
-		p.o_flags |= GRE_KEY;
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
-			err = -EFAULT;
-		break;
 
-	case SIOCADDTUNNEL:
-	case SIOCCHGTUNNEL:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
+	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+		return -EFAULT;
 
-		err = -EFAULT;
-		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
-			goto done;
-
-		err = -EINVAL;
+	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
 		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
 		    p.iph.ihl != 5)
-			goto done;
-
-		t = vti_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
-		if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
-				if (t->dev != dev) {
-					err = -EEXIST;
-					break;
-				}
-			} else {
-				if (((dev->flags&IFF_POINTOPOINT) &&
-				    !p.iph.daddr) ||
-				    (!(dev->flags&IFF_POINTOPOINT) &&
-				    p.iph.daddr)) {
-					err = -EINVAL;
-					break;
-				}
-				t = netdev_priv(dev);
-				vti_tunnel_unlink(ipn, t);
-				synchronize_net();
-				t->parms.iph.saddr = p.iph.saddr;
-				t->parms.iph.daddr = p.iph.daddr;
-				t->parms.i_key = p.i_key;
-				t->parms.o_key = p.o_key;
-				t->parms.iph.protocol = IPPROTO_IPIP;
-				memcpy(dev->dev_addr, &p.iph.saddr, 4);
-				memcpy(dev->broadcast, &p.iph.daddr, 4);
-				vti_tunnel_link(ipn, t);
-				netdev_state_change(dev);
-			}
-		}
-
-		if (t) {
-			err = 0;
-			if (cmd == SIOCCHGTUNNEL) {
-				t->parms.i_key = p.i_key;
-				t->parms.o_key = p.o_key;
-				if (t->parms.link != p.link) {
-					t->parms.link = p.link;
-					vti_tunnel_bind_dev(dev);
-					netdev_state_change(dev);
-				}
-			}
-			p.i_flags |= GRE_KEY | VTI_ISVTI;
-			p.o_flags |= GRE_KEY;
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms,
-					 sizeof(p)))
-				err = -EFAULT;
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
-		break;
+			return -EINVAL;
+	}
 
-	case SIOCDELTUNNEL:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
-
-		if (dev == ipn->fb_tunnel_dev) {
-			err = -EFAULT;
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data,
-					   sizeof(p)))
-				goto done;
-			err = -ENOENT;
-
-			t = vti_tunnel_locate(net, &p, 0);
-			if (t == NULL)
-				goto done;
-			err = -EPERM;
-			if (t->dev == ipn->fb_tunnel_dev)
-				goto done;
-			dev = t->dev;
-		}
-		unregister_netdevice(dev);
-		err = 0;
-		break;
+	if (!(p.i_flags & GRE_KEY))
+		p.i_key = 0;
+	if (!(p.o_flags & GRE_KEY))
+		p.o_key = 0;
 
-	default:
-		err = -EINVAL;
-	}
+	p.i_flags = VTI_ISVTI;
 
-done:
-	return err;
-}
+	err = ip_tunnel_ioctl(dev, &p, cmd);
+	if (err)
+		return err;
 
-static int vti_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
-	if (new_mtu < 68 || new_mtu > 0xFFF8)
-		return -EINVAL;
-	dev->mtu = new_mtu;
+	if (cmd != SIOCDELTUNNEL) {
+		p.i_flags |= GRE_KEY;
+		p.o_flags |= GRE_KEY;
+	}
+
+	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+		return -EFAULT;
 	return 0;
 }
 
 static const struct net_device_ops vti_netdev_ops = {
 	.ndo_init	= vti_tunnel_init,
-	.ndo_uninit	= vti_tunnel_uninit,
+	.ndo_uninit	= ip_tunnel_uninit,
 	.ndo_start_xmit	= vti_tunnel_xmit,
 	.ndo_do_ioctl	= vti_tunnel_ioctl,
-	.ndo_change_mtu	= vti_tunnel_change_mtu,
-	.ndo_get_stats64 = vti_get_stats64,
+	.ndo_change_mtu	= ip_tunnel_change_mtu,
+	.ndo_get_stats64 = ip_tunnel_get_stats64,
 };
 
-static void vti_dev_free(struct net_device *dev)
+static void vti_tunnel_setup(struct net_device *dev)
 {
-	free_percpu(dev->tstats);
-	free_netdev(dev);
+	dev->netdev_ops		= &vti_netdev_ops;
+	dev->type		= ARPHRD_TUNNEL;
+	ip_tunnel_setup(dev, vti_net_id);
 }
 
-static void vti_tunnel_setup(struct net_device *dev)
+static int vti_tunnel_init(struct net_device *dev)
 {
-	dev->netdev_ops		= &vti_netdev_ops;
-	dev->destructor		= vti_dev_free;
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct iphdr *iph = &tunnel->parms.iph;
+
+	memcpy(dev->dev_addr, &iph->saddr, 4);
+	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_TUNNEL;
 	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
 	dev->features		|= NETIF_F_LLTX;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
-}
-
-static int vti_tunnel_init(struct net_device *dev)
-{
-	struct ip_tunnel *tunnel = netdev_priv(dev);
 
-	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
-
-	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
-	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
-
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	return 0;
+	return ip_tunnel_init(dev);
 }
 
-static int __net_init vti_fb_tunnel_init(struct net_device *dev)
+static void __net_init vti_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
-	struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id);
-
-	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
 
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPIP;
 	iph->ihl		= 5;
-
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	dev_hold(dev);
-	rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
-static struct xfrm_tunnel vti_handler __read_mostly = {
+static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
 	.handler	=	vti_rcv,
-	.err_handler	=	vti_err,
-	.priority	=	1,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
 };
 
-static void vti_destroy_tunnels(struct vti_net *ipn, struct list_head *head)
-{
-	int prio;
-
-	for (prio = 1; prio < 4; prio++) {
-		int h;
-		for (h = 0; h < HASH_SIZE; h++) {
-			struct ip_tunnel *t;
-
-			t = rtnl_dereference(ipn->tunnels[prio][h]);
-			while (t != NULL) {
-				unregister_netdevice_queue(t->dev, head);
-				t = rtnl_dereference(t->next);
-			}
-		}
-	}
-}
+static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
+	.handler	=	vti_rcv,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
+};
+
+static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
+	.handler	=	vti_rcv,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
+};
 
 static int __net_init vti_init_net(struct net *net)
 {
 	int err;
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-
-	ipn->tunnels[0] = ipn->tunnels_wc;
-	ipn->tunnels[1] = ipn->tunnels_l;
-	ipn->tunnels[2] = ipn->tunnels_r;
-	ipn->tunnels[3] = ipn->tunnels_r_l;
-
-	ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
-					  "ip_vti0",
-					  vti_tunnel_setup);
-	if (!ipn->fb_tunnel_dev) {
-		err = -ENOMEM;
-		goto err_alloc_dev;
-	}
-	dev_net_set(ipn->fb_tunnel_dev, net);
-
-	err = vti_fb_tunnel_init(ipn->fb_tunnel_dev);
-	if (err)
-		goto err_reg_dev;
-	ipn->fb_tunnel_dev->rtnl_link_ops = &vti_link_ops;
+	struct ip_tunnel_net *itn;
 
-	err = register_netdev(ipn->fb_tunnel_dev);
+	err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
 	if (err)
-		goto err_reg_dev;
+		return err;
+	itn = net_generic(net, vti_net_id);
+	vti_fb_tunnel_init(itn->fb_tunnel_dev);
 	return 0;
-
-err_reg_dev:
-	vti_dev_free(ipn->fb_tunnel_dev);
-err_alloc_dev:
-	/* nothing */
-	return err;
 }
 
 static void __net_exit vti_exit_net(struct net *net)
 {
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	vti_destroy_tunnels(ipn, &list);
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+	ip_tunnel_delete_net(itn, &vti_link_ops);
 }
 
 static struct pernet_operations vti_net_ops = {
 	.init = vti_init_net,
 	.exit = vti_exit_net,
 	.id   = &vti_net_id,
-	.size = sizeof(struct vti_net),
+	.size = sizeof(struct ip_tunnel_net),
 };
 
 static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -754,6 +444,8 @@ static void vti_netlink_parms(struct nlattr *data[],
 	if (!data)
 		return;
 
+	parms->i_flags = VTI_ISVTI;
+
 	if (data[IFLA_VTI_LINK])
 		parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
 
@@ -774,78 +466,19 @@ static void vti_netlink_parms(struct nlattr *data[],
 static int vti_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
-	struct ip_tunnel *nt;
-	struct net *net = dev_net(dev);
-	struct vti_net *ipn = net_generic(net, vti_net_id);
-	int mtu;
-	int err;
-
-	nt = netdev_priv(dev);
-	vti_netlink_parms(data, &nt->parms);
-
-	if (vti_tunnel_locate(net, &nt->parms, 0))
-		return -EEXIST;
-
-	mtu = vti_tunnel_bind_dev(dev);
-	if (!tb[IFLA_MTU])
-		dev->mtu = mtu;
-
-	err = register_netdevice(dev);
-	if (err)
-		goto out;
-
-	dev_hold(dev);
-	vti_tunnel_link(ipn, nt);
+	struct ip_tunnel_parm parms;
 
-out:
-	return err;
+	vti_netlink_parms(data, &parms);
+	return ip_tunnel_newlink(dev, tb, &parms);
 }
 
 static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
 			  struct nlattr *data[])
 {
-	struct ip_tunnel *t, *nt;
-	struct net *net = dev_net(dev);
-	struct vti_net *ipn = net_generic(net, vti_net_id);
 	struct ip_tunnel_parm p;
-	int mtu;
-
-	if (dev == ipn->fb_tunnel_dev)
-		return -EINVAL;
 
-	nt = netdev_priv(dev);
 	vti_netlink_parms(data, &p);
-
-	t = vti_tunnel_locate(net, &p, 0);
-
-	if (t) {
-		if (t->dev != dev)
-			return -EEXIST;
-	} else {
-		t = nt;
-
-		vti_tunnel_unlink(ipn, t);
-		t->parms.iph.saddr = p.iph.saddr;
-		t->parms.iph.daddr = p.iph.daddr;
-		t->parms.i_key = p.i_key;
-		t->parms.o_key = p.o_key;
-		if (dev->type != ARPHRD_ETHER) {
-			memcpy(dev->dev_addr, &p.iph.saddr, 4);
-			memcpy(dev->broadcast, &p.iph.daddr, 4);
-		}
-		vti_tunnel_link(ipn, t);
-		netdev_state_change(dev);
-	}
-
-	if (t->parms.link != p.link) {
-		t->parms.link = p.link;
-		mtu = vti_tunnel_bind_dev(dev);
-		if (!tb[IFLA_MTU])
-			dev->mtu = mtu;
-		netdev_state_change(dev);
-	}
-
-	return 0;
+	return ip_tunnel_changelink(dev, tb, &p);
 }
 
 static size_t vti_get_size(const struct net_device *dev)
@@ -908,10 +541,31 @@ static int __init vti_init(void)
 	err = register_pernet_device(&vti_net_ops);
 	if (err < 0)
 		return err;
-	err = xfrm4_mode_tunnel_input_register(&vti_handler);
+	err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
 	if (err < 0) {
 		unregister_pernet_device(&vti_net_ops);
-		pr_info(KERN_INFO "vti init: can't register tunnel\n");
+		pr_info("vti init: can't register tunnel\n");
+
+		return err;
+	}
+
+	err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
+	if (err < 0) {
+		xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+		unregister_pernet_device(&vti_net_ops);
+		pr_info("vti init: can't register tunnel\n");
+
+		return err;
+	}
+
+	err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
+	if (err < 0) {
+		xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+		xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+		unregister_pernet_device(&vti_net_ops);
+		pr_info("vti init: can't register tunnel\n");
+
+		return err;
 	}
 
 	err = rtnl_link_register(&vti_link_ops);
@@ -921,7 +575,9 @@ static int __init vti_init(void)
 	return err;
 
 rtnl_link_failed:
-	xfrm4_mode_tunnel_input_deregister(&vti_handler);
+	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
 	unregister_pernet_device(&vti_net_ops);
 	return err;
 }
@@ -929,8 +585,13 @@ rtnl_link_failed:
 static void __exit vti_fini(void)
 {
 	rtnl_link_unregister(&vti_link_ops);
-	if (xfrm4_mode_tunnel_input_deregister(&vti_handler))
+	if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP))
 		pr_info("vti close: can't deregister tunnel\n");
+	if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH))
+		pr_info("vti close: can't deregister tunnel\n");
+	if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP))
+		pr_info("vti close: can't deregister tunnel\n");
+
 
 	unregister_pernet_device(&vti_net_ops);
 }