1 files changed, 219 insertions, 645 deletions

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 988f52fba54..62eaa005e14 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -111,206 +111,20 @@
 #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))&0xF)
+static bool log_ecn_error = true;
+module_param(log_ecn_error, bool, 0644);
+MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
 static int ipip_net_id __read_mostly;
-struct ipip_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 ipip_tunnel_init(struct net_device *dev);
-static void ipip_tunnel_setup(struct net_device *dev);
-static void ipip_dev_free(struct net_device *dev);
-
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
-
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	unsigned long	rx_packets;
-	unsigned long	rx_bytes;
-	unsigned long	tx_packets;
-	unsigned long	tx_bytes;
-};
-
-static struct net_device_stats *ipip_get_stats(struct net_device *dev)
-{
-	struct pcpu_tstats sum = { 0 };
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
-		sum.rx_packets += tstats->rx_packets;
-		sum.rx_bytes   += tstats->rx_bytes;
-		sum.tx_packets += tstats->tx_packets;
-		sum.tx_bytes   += tstats->tx_bytes;
-	}
-	dev->stats.rx_packets = sum.rx_packets;
-	dev->stats.rx_bytes   = sum.rx_bytes;
-	dev->stats.tx_packets = sum.tx_packets;
-	dev->stats.tx_bytes   = sum.tx_bytes;
-	return &dev->stats;
-}
-
-static struct ip_tunnel * ipip_tunnel_lookup(struct net *net,
-		__be32 remote, __be32 local)
-{
-	unsigned int h0 = HASH(remote);
-	unsigned int h1 = HASH(local);
-	struct ip_tunnel *t;
-	struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
-	for_each_ip_tunnel_rcu(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(ipn->tunnels_r[h0])
-		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
-			return t;
-
-	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
-		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
-			return t;
-
-	t = rcu_dereference(ipn->tunnels_wc[0]);
-	if (t && (t->dev->flags&IFF_UP))
-		return t;
-	return NULL;
-}
-
-static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
-		struct ip_tunnel_parm *parms)
-{
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	unsigned int h = 0;
-	int prio = 0;
-
-	if (remote) {
-		prio |= 2;
-		h ^= HASH(remote);
-	}
-	if (local) {
-		prio |= 1;
-		h ^= HASH(local);
-	}
-	return &ipn->tunnels[prio][h];
-}
-
-static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
-		struct ip_tunnel *t)
-{
-	return __ipip_bucket(ipn, &t->parms);
-}
-
-static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp;
-	struct ip_tunnel *iter;
-
-	for (tp = ipip_bucket(ipn, t);
-	     (iter = rtnl_dereference(*tp)) != NULL;
-	     tp = &iter->next) {
-		if (t == iter) {
-			rcu_assign_pointer(*tp, t->next);
-			break;
-		}
-	}
-}
-
-static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);
-
-	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
-	rcu_assign_pointer(*tp, t);
-}
-
-static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
-		struct ip_tunnel_parm *parms, int create)
-{
-	__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 ipip_net *ipn = net_generic(net, ipip_net_id);
-
-	for (tp = __ipip_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;
-
-	if (parms->name[0])
-		strlcpy(name, parms->name, IFNAMSIZ);
-	else
-		strcpy(name, "tunl%d");
-
-	dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
-	if (dev == NULL)
-		return NULL;
-
-	dev_net_set(dev, net);
-
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
-	nt = netdev_priv(dev);
-	nt->parms = *parms;
-
-	if (ipip_tunnel_init(dev) < 0)
-		goto failed_free;
-
-	if (register_netdevice(dev) < 0)
-		goto failed_free;
-
-	dev_hold(dev);
-	ipip_tunnel_link(ipn, nt);
-	return nt;
-
-failed_free:
-	ipip_dev_free(dev);
-	return NULL;
-}
-
-/* called with RTNL */
-static void ipip_tunnel_uninit(struct net_device *dev)
-{
-	struct net *net = dev_net(dev);
-	struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
-	if (dev == ipn->fb_tunnel_dev)
-		rcu_assign_pointer(ipn->tunnels_wc[0], NULL);
-	else
-		ipip_tunnel_unlink(ipn, netdev_priv(dev));
-	dev_put(dev);
-}
+static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
@@ -319,45 +133,35 @@ static int ipip_err(struct sk_buff *skb, u32 info)
    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 net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct ip_tunnel *t;
 	int err;
+	const int type = icmp_hdr(skb)->type;
+	const int code = icmp_hdr(skb)->code;
 
-	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;
-		case ICMP_FRAG_NEEDED:
-			/* Soft state for pmtu is maintained by IP core. */
-			return 0;
-		default:
-			/* All others are translated to HOST_UNREACH.
-			   rfc2003 contains "deep thoughts" about NET_UNREACH,
-			   I believe they are just ether pollution. --ANK
-			 */
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return 0;
-		break;
+	err = -ENOENT;
+	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+			     iph->daddr, iph->saddr, 0);
+	if (t == NULL)
+		goto out;
+
+	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;
 	}
 
-	err = -ENOENT;
+	if (type == ICMP_REDIRECT) {
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
+			      IPPROTO_IPIP, 0);
+		err = 0;
+		goto out;
+	}
 
-	rcu_read_lock();
-	t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
-	if (t == NULL || t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0)
 		goto out;
 
 	err = 0;
@@ -369,543 +173,312 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 	else
 		t->err_count = 1;
 	t->err_time = jiffies;
+
 out:
-	rcu_read_unlock();
 	return err;
 }
 
-static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph,
-					struct sk_buff *skb)
-{
-	struct iphdr *inner_iph = ip_hdr(skb);
-
-	if (INET_ECN_is_ce(outer_iph->tos))
-		IP_ECN_set_ce(inner_iph);
-}
+static const struct tnl_ptk_info tpi = {
+	/* no tunnel info required for ipip. */
+	.proto = htons(ETH_P_IP),
+};
 
 static int ipip_rcv(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	struct ip_tunnel *tunnel;
-	const struct iphdr *iph = ip_hdr(skb);
-
-	rcu_read_lock();
-	tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
-	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
-
-		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-			rcu_read_unlock();
-			kfree_skb(skb);
-			return 0;
-		}
-
-		secpath_reset(skb);
-
-		skb->mac_header = skb->network_header;
-		skb_reset_network_header(skb);
-		skb->protocol = htons(ETH_P_IP);
-		skb->pkt_type = PACKET_HOST;
-
-		tstats = this_cpu_ptr(tunnel->dev->tstats);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
-
-		__skb_tunnel_rx(skb, tunnel->dev);
-
-		ipip_ecn_decapsulate(iph, skb);
-
-		netif_rx(skb);
-
-		rcu_read_unlock();
-		return 0;
+	const struct iphdr *iph;
+
+	iph = ip_hdr(skb);
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+			iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
 	}
-	rcu_read_unlock();
 
 	return -1;
+
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 /*
  *	This function assumes it is being called from dev_queue_xmit()
  *	and that skb is filled properly by that function.
  */
-
 static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct pcpu_tstats *tstats;
-	struct iphdr  *tiph = &tunnel->parms.iph;
-	u8     tos = tunnel->parms.iph.tos;
-	__be16 df = tiph->frag_off;
-	struct rtable *rt;     			/* Route to the other host */
-	struct net_device *tdev;		/* Device to other host */
-	struct iphdr  *old_iph = ip_hdr(skb);
-	struct iphdr  *iph;			/* Our new IP header */
-	unsigned int max_headroom;		/* The extra header space needed */
-	__be32 dst = tiph->daddr;
-	int    mtu;
-
-	if (skb->protocol != htons(ETH_P_IP))
-		goto tx_error;
-
-	if (tos & 1)
-		tos = old_iph->tos;
-
-	if (!dst) {
-		/* NBMA tunnel */
-		if ((rt = skb_rtable(skb)) == NULL) {
-			dev->stats.tx_fifo_errors++;
-			goto tx_error;
-		}
-		if ((dst = rt->rt_gateway) == 0)
-			goto tx_error_icmp;
-	}
+	const struct iphdr  *tiph = &tunnel->parms.iph;
 
-	{
-		struct flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = dst,
-			.fl4_src= tiph->saddr,
-			.fl4_tos = RT_TOS(tos),
-			.proto = IPPROTO_IPIP
-		};
-
-		if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
-			dev->stats.tx_carrier_errors++;
-			goto tx_error_icmp;
-		}
-	}
-	tdev = rt->dst.dev;
-
-	if (tdev == dev) {
-		ip_rt_put(rt);
-		dev->stats.collisions++;
+	if (unlikely(skb->protocol != htons(ETH_P_IP)))
 		goto tx_error;
-	}
-
-	df |= old_iph->frag_off & htons(IP_DF);
-
-	if (df) {
-		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
-
-		if (mtu < 68) {
-			dev->stats.collisions++;
-			ip_rt_put(rt);
-			goto tx_error;
-		}
 
-		if (skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
-
-		if ((old_iph->frag_off & htons(IP_DF)) &&
-		    mtu < ntohs(old_iph->tot_len)) {
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
-			ip_rt_put(rt);
-			goto tx_error;
-		}
-	}
-
-	if (tunnel->err_count > 0) {
-		if (time_before(jiffies,
-				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
-			tunnel->err_count--;
-			dst_link_failure(skb);
-		} else
-			tunnel->err_count = 0;
-	}
-
-	/*
-	 * Okay, now see if we can stuff it in the buffer as-is.
-	 */
-	max_headroom = (LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr));
-
-	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
-	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
-		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
-		if (!new_skb) {
-			ip_rt_put(rt);
-			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
-			return NETDEV_TX_OK;
-		}
-		if (skb->sk)
-			skb_set_owner_w(new_skb, skb->sk);
-		dev_kfree_skb(skb);
-		skb = new_skb;
-		old_iph = ip_hdr(skb);
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto out;
 
-	skb->transport_header = skb->network_header;
-	skb_push(skb, sizeof(struct iphdr));
-	skb_reset_network_header(skb);
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-
-	/*
-	 *	Push down and install the IPIP header.
-	 */
-
-	iph 			=	ip_hdr(skb);
-	iph->version		=	4;
-	iph->ihl		=	sizeof(struct iphdr)>>2;
-	iph->frag_off		=	df;
-	iph->protocol		=	IPPROTO_IPIP;
-	iph->tos		=	INET_ECN_encapsulate(tos, old_iph->tos);
-	iph->daddr		=	rt->rt_dst;
-	iph->saddr		=	rt->rt_src;
-
-	if ((iph->ttl = tiph->ttl) == 0)
-		iph->ttl	=	old_iph->ttl;
-
-	nf_reset(skb);
-	tstats = this_cpu_ptr(dev->tstats);
-	__IPTUNNEL_XMIT(tstats, &dev->stats);
+	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
 	return NETDEV_TX_OK;
 
-tx_error_icmp:
-	dst_link_failure(skb);
 tx_error:
+	kfree_skb(skb);
+out:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
-static void ipip_tunnel_bind_dev(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 flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = iph->daddr,
-			.fl4_src = iph->saddr,
-			.fl4_tos = RT_TOS(iph->tos),
-			.proto = IPPROTO_IPIP
-		};
-		struct rtable *rt;
-
-		if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
-			tdev = rt->dst.dev;
-			ip_rt_put(rt);
-		}
-		dev->flags |= IFF_POINTOPOINT;
-	}
-
-	if (!tdev && tunnel->parms.link)
-		tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
-
-	if (tdev) {
-		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
-		dev->mtu = tdev->mtu - sizeof(struct iphdr);
-	}
-	dev->iflink = tunnel->parms.link;
-}
-
 static int
-ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip_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 ipip_net *ipn = net_generic(net, ipip_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 = ipip_tunnel_locate(net, &p, 0);
-		}
-		if (t == NULL)
-			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof(p));
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
-			err = -EFAULT;
-		break;
-
-	case SIOCADDTUNNEL:
-	case SIOCCHGTUNNEL:
-		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
-			goto done;
-
-		err = -EFAULT;
-		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
-			goto done;
-
-		err = -EINVAL;
+
+	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+		return -EFAULT;
+
+	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
 		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
 		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
-			goto done;
-		if (p.iph.ttl)
-			p.iph.frag_off |= htons(IP_DF);
-
-		t = ipip_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);
-				ipip_tunnel_unlink(ipn, t);
-				synchronize_net();
-				t->parms.iph.saddr = p.iph.saddr;
-				t->parms.iph.daddr = p.iph.daddr;
-				memcpy(dev->dev_addr, &p.iph.saddr, 4);
-				memcpy(dev->broadcast, &p.iph.daddr, 4);
-				ipip_tunnel_link(ipn, t);
-				netdev_state_change(dev);
-			}
-		}
-
-		if (t) {
-			err = 0;
-			if (cmd == SIOCCHGTUNNEL) {
-				t->parms.iph.ttl = p.iph.ttl;
-				t->parms.iph.tos = p.iph.tos;
-				t->parms.iph.frag_off = p.iph.frag_off;
-				if (t->parms.link != p.link) {
-					t->parms.link = p.link;
-					ipip_tunnel_bind_dev(dev);
-					netdev_state_change(dev);
-				}
-			}
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
-				err = -EFAULT;
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
-		break;
-
-	case SIOCDELTUNNEL:
-		err = -EPERM;
-		if (!capable(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;
-			if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
-				goto done;
-			err = -EPERM;
-			if (t->dev == ipn->fb_tunnel_dev)
-				goto done;
-			dev = t->dev;
-		}
-		unregister_netdevice(dev);
-		err = 0;
-		break;
-
-	default:
-		err = -EINVAL;
+			return -EINVAL;
 	}
 
-done:
-	return err;
-}
+	p.i_key = p.o_key = p.i_flags = p.o_flags = 0;
+	if (p.iph.ttl)
+		p.iph.frag_off |= htons(IP_DF);
+
+	err = ip_tunnel_ioctl(dev, &p, cmd);
+	if (err)
+		return err;
+
+	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+		return -EFAULT;
 
-static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
-	if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
-		return -EINVAL;
-	dev->mtu = new_mtu;
 	return 0;
 }
 
 static const struct net_device_ops ipip_netdev_ops = {
-	.ndo_uninit	= ipip_tunnel_uninit,
+	.ndo_init       = ipip_tunnel_init,
+	.ndo_uninit     = ip_tunnel_uninit,
 	.ndo_start_xmit	= ipip_tunnel_xmit,
 	.ndo_do_ioctl	= ipip_tunnel_ioctl,
-	.ndo_change_mtu	= ipip_tunnel_change_mtu,
-	.ndo_get_stats  = ipip_get_stats,
+	.ndo_change_mtu = ip_tunnel_change_mtu,
+	.ndo_get_stats64 = ip_tunnel_get_stats64,
 };
 
-static void ipip_dev_free(struct net_device *dev)
-{
-	free_percpu(dev->tstats);
-	free_netdev(dev);
-}
+#define IPIP_FEATURES (NETIF_F_SG |		\
+		       NETIF_F_FRAGLIST |	\
+		       NETIF_F_HIGHDMA |	\
+		       NETIF_F_GSO_SOFTWARE |	\
+		       NETIF_F_HW_CSUM)
 
 static void ipip_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipip_netdev_ops;
-	dev->destructor		= ipip_dev_free;
 
 	dev->type		= ARPHRD_TUNNEL;
-	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
-	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
 	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;
+
+	dev->features		|= IPIP_FEATURES;
+	dev->hw_features	|= IPIP_FEATURES;
+	ip_tunnel_setup(dev, ipip_net_id);
 }
 
 static int ipip_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);
 
-	ipip_tunnel_bind_dev(dev);
-
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	return 0;
+	tunnel->hlen = 0;
+	tunnel->parms.iph.protocol = IPPROTO_IPIP;
+	return ip_tunnel_init(dev);
 }
 
-static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
+static void ipip_netlink_parms(struct nlattr *data[],
+			       struct ip_tunnel_parm *parms)
 {
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct iphdr *iph = &tunnel->parms.iph;
-	struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);
+	memset(parms, 0, sizeof(*parms));
 
-	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
+	parms->iph.version = 4;
+	parms->iph.protocol = IPPROTO_IPIP;
+	parms->iph.ihl = 5;
 
-	iph->version		= 4;
-	iph->protocol		= IPPROTO_IPIP;
-	iph->ihl		= 5;
+	if (!data)
+		return;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
+	if (data[IFLA_IPTUN_LINK])
+		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
 
-	dev_hold(dev);
-	rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
-	return 0;
-}
+	if (data[IFLA_IPTUN_LOCAL])
+		parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);
 
-static struct xfrm_tunnel ipip_handler __read_mostly = {
-	.handler	=	ipip_rcv,
-	.err_handler	=	ipip_err,
-	.priority	=	1,
-};
+	if (data[IFLA_IPTUN_REMOTE])
+		parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);
 
-static const char banner[] __initconst =
-	KERN_INFO "IPv4 over IPv4 tunneling driver\n";
+	if (data[IFLA_IPTUN_TTL]) {
+		parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
+		if (parms->iph.ttl)
+			parms->iph.frag_off = htons(IP_DF);
+	}
 
-static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
+	if (data[IFLA_IPTUN_TOS])
+		parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);
+
+	if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
+		parms->iph.frag_off = htons(IP_DF);
+}
+
+static int ipip_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[])
 {
-	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);
-			}
-		}
-	}
+	struct ip_tunnel_parm p;
+
+	ipip_netlink_parms(data, &p);
+	return ip_tunnel_newlink(dev, tb, &p);
 }
 
-static int __net_init ipip_init_net(struct net *net)
+static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
+			   struct nlattr *data[])
 {
-	struct ipip_net *ipn = net_generic(net, ipip_net_id);
-	int err;
+	struct ip_tunnel_parm p;
 
-	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),
-					   "tunl0",
-					   ipip_tunnel_setup);
-	if (!ipn->fb_tunnel_dev) {
-		err = -ENOMEM;
-		goto err_alloc_dev;
-	}
-	dev_net_set(ipn->fb_tunnel_dev, net);
+	ipip_netlink_parms(data, &p);
 
-	err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
-	if (err)
-		goto err_reg_dev;
+	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
+	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
+		return -EINVAL;
+
+	return ip_tunnel_changelink(dev, tb, &p);
+}
 
-	if ((err = register_netdev(ipn->fb_tunnel_dev)))
-		goto err_reg_dev;
+static size_t ipip_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_IPTUN_LINK */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_LOCAL */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_REMOTE */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_TTL */
+		nla_total_size(1) +
+		/* IFLA_IPTUN_TOS */
+		nla_total_size(1) +
+		/* IFLA_IPTUN_PMTUDISC */
+		nla_total_size(1) +
+		0;
+}
 
+static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct ip_tunnel_parm *parm = &tunnel->parms;
+
+	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
+	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
+	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
+	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
+	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
+	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
+		       !!(parm->iph.frag_off & htons(IP_DF))))
+		goto nla_put_failure;
 	return 0;
 
-err_reg_dev:
-	ipip_dev_free(ipn->fb_tunnel_dev);
-err_alloc_dev:
-	/* nothing */
-	return err;
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = {
+	[IFLA_IPTUN_LINK]		= { .type = NLA_U32 },
+	[IFLA_IPTUN_LOCAL]		= { .type = NLA_U32 },
+	[IFLA_IPTUN_REMOTE]		= { .type = NLA_U32 },
+	[IFLA_IPTUN_TTL]		= { .type = NLA_U8 },
+	[IFLA_IPTUN_TOS]		= { .type = NLA_U8 },
+	[IFLA_IPTUN_PMTUDISC]		= { .type = NLA_U8 },
+};
+
+static struct rtnl_link_ops ipip_link_ops __read_mostly = {
+	.kind		= "ipip",
+	.maxtype	= IFLA_IPTUN_MAX,
+	.policy		= ipip_policy,
+	.priv_size	= sizeof(struct ip_tunnel),
+	.setup		= ipip_tunnel_setup,
+	.newlink	= ipip_newlink,
+	.changelink	= ipip_changelink,
+	.dellink	= ip_tunnel_dellink,
+	.get_size	= ipip_get_size,
+	.fill_info	= ipip_fill_info,
+};
+
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+	.handler	=	ipip_rcv,
+	.err_handler	=	ipip_err,
+	.priority	=	1,
+};
+
+static int __net_init ipip_init_net(struct net *net)
+{
+	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
 }
 
 static void __net_exit ipip_exit_net(struct net *net)
 {
-	struct ipip_net *ipn = net_generic(net, ipip_net_id);
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	ipip_destroy_tunnels(ipn, &list);
-	unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
+	ip_tunnel_delete_net(itn, &ipip_link_ops);
 }
 
 static struct pernet_operations ipip_net_ops = {
 	.init = ipip_init_net,
 	.exit = ipip_exit_net,
 	.id   = &ipip_net_id,
-	.size = sizeof(struct ipip_net),
+	.size = sizeof(struct ip_tunnel_net),
 };
 
 static int __init ipip_init(void)
 {
 	int err;
 
-	printk(banner);
+	pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
 
 	err = register_pernet_device(&ipip_net_ops);
 	if (err < 0)
 		return err;
 	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
 	if (err < 0) {
-		unregister_pernet_device(&ipip_net_ops);
-		printk(KERN_INFO "ipip init: can't register tunnel\n");
+		pr_info("%s: can't register tunnel\n", __func__);
+		goto xfrm_tunnel_failed;
 	}
+	err = rtnl_link_register(&ipip_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
+
+out:
 	return err;
+
+rtnl_link_failed:
+	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+	unregister_pernet_device(&ipip_net_ops);
+	goto out;
 }
 
 static void __exit ipip_fini(void)
 {
+	rtnl_link_unregister(&ipip_link_ops);
 	if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
-		printk(KERN_INFO "ipip close: can't deregister tunnel\n");
+		pr_info("%s: can't deregister tunnel\n", __func__);
 
 	unregister_pernet_device(&ipip_net_ops);
 }
@@ -913,4 +486,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("tunl0");
+MODULE_ALIAS_RTNL_LINK("ipip");
+MODULE_ALIAS_NETDEV("tunl0");