1 files changed, 258 insertions, 697 deletions

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index dbaed69de06..62eaa005e14 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -1,8 +1,6 @@
 /*
  *	Linux NET3:	IP/IP protocol decoder.
  *
- *	Version: $Id: ipip.c,v 1.50 2001/10/02 02:22:36 davem Exp $
- *
  *	Authors:
  *		Sam Lantinga (slouken@cs.ucdavis.edu)  02/01/95
  *
@@ -43,7 +41,7 @@
 		Made the tunnels use dev->name not tunnel: when error reporting.
 		Added tx_dropped stat
 
-		-Alan Cox	(Alan.Cox@linux.org) 21 March 95
+		-Alan Cox	(alan@lxorguk.ukuu.org.uk) 21 March 95
 
 	Reworked:
 		Changed to tunnel to destination gateway in addition to the
@@ -97,6 +95,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
@@ -112,818 +111,380 @@
 #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 int ipip_fb_tunnel_init(struct net_device *dev);
-static int ipip_tunnel_init(struct net_device *dev);
-static void ipip_tunnel_setup(struct net_device *dev);
-
-static struct net_device *ipip_fb_tunnel_dev;
-
-static struct ip_tunnel *tunnels_r_l[HASH_SIZE];
-static struct ip_tunnel *tunnels_r[HASH_SIZE];
-static struct ip_tunnel *tunnels_l[HASH_SIZE];
-static struct ip_tunnel *tunnels_wc[1];
-static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunnels_r_l };
-
-static DEFINE_RWLOCK(ipip_lock);
+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 struct ip_tunnel * ipip_tunnel_lookup(__be32 remote, __be32 local)
-{
-	unsigned h0 = HASH(remote);
-	unsigned h1 = HASH(local);
-	struct ip_tunnel *t;
+static int ipip_net_id __read_mostly;
 
-	for (t = tunnels_r_l[h0^h1]; t; t = t->next) {
-		if (local == t->parms.iph.saddr &&
-		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
-			return t;
-	}
-	for (t = tunnels_r[h0]; t; t = t->next) {
-		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
-			return t;
-	}
-	for (t = tunnels_l[h1]; t; t = t->next) {
-		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
-			return t;
-	}
-	if ((t = tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
-		return t;
-	return NULL;
-}
-
-static struct ip_tunnel **__ipip_bucket(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 &tunnels[prio][h];
-}
-
-static inline struct ip_tunnel **ipip_bucket(struct ip_tunnel *t)
-{
-	return __ipip_bucket(&t->parms);
-}
-
-static void ipip_tunnel_unlink(struct ip_tunnel *t)
-{
-	struct ip_tunnel **tp;
-
-	for (tp = ipip_bucket(t); *tp; tp = &(*tp)->next) {
-		if (t == *tp) {
-			write_lock_bh(&ipip_lock);
-			*tp = t->next;
-			write_unlock_bh(&ipip_lock);
-			break;
-		}
-	}
-}
-
-static void ipip_tunnel_link(struct ip_tunnel *t)
-{
-	struct ip_tunnel **tp = ipip_bucket(t);
-
-	t->next = *tp;
-	write_lock_bh(&ipip_lock);
-	*tp = t;
-	write_unlock_bh(&ipip_lock);
-}
-
-static struct ip_tunnel * ipip_tunnel_locate(struct ip_tunnel_parm *parms, int create)
-{
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	struct ip_tunnel *t, **tp, *nt;
-	struct net_device *dev;
-	char name[IFNAMSIZ];
-
-	for (tp = __ipip_bucket(parms); (t = *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
-		sprintf(name, "tunl%%d");
-
-	dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
-	if (dev == NULL)
-		return NULL;
-
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
-	nt = netdev_priv(dev);
-	dev->init = ipip_tunnel_init;
-	nt->parms = *parms;
-
-	if (register_netdevice(dev) < 0)
-		goto failed_free;
-
-	dev_hold(dev);
-	ipip_tunnel_link(nt);
-	return nt;
-
-failed_free:
-	free_netdev(dev);
-	return NULL;
-}
-
-static void ipip_tunnel_uninit(struct net_device *dev)
-{
-	if (dev == ipip_fb_tunnel_dev) {
-		write_lock_bh(&ipip_lock);
-		tunnels_wc[0] = NULL;
-		write_unlock_bh(&ipip_lock);
-	} else
-		ipip_tunnel_unlink(netdev_priv(dev));
-	dev_put(dev);
-}
+static int ipip_tunnel_init(struct net_device *dev);
+static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-#ifndef I_WISH_WORLD_WERE_PERFECT
 
-/* It is not :-( All the routers (except for Linux) return only
+/* 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 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;
+	}
 
-	read_lock(&ipip_lock);
-	t = ipip_tunnel_lookup(iph->daddr, iph->saddr);
-	if (t == NULL || t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0)
 		goto out;
 
 	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
-	if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
 		t->err_count++;
 	else
 		t->err_count = 1;
 	t->err_time = jiffies;
+
 out:
-	read_unlock(&ipip_lock);
 	return err;
-#else
-	struct iphdr *iph = (struct iphdr*)dp;
-	int hlen = iph->ihl<<2;
-	struct iphdr *eiph;
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	int rel_type = 0;
-	int rel_code = 0;
-	__be32 rel_info = 0;
-	__u32 n = 0;
-	struct sk_buff *skb2;
-	struct flowi fl;
-	struct rtable *rt;
-
-	if (len < hlen + sizeof(struct iphdr))
-		return 0;
-	eiph = (struct iphdr*)(dp + hlen);
-
-	switch (type) {
-	default:
-		return 0;
-	case ICMP_PARAMETERPROB:
-		n = ntohl(icmp_hdr(skb)->un.gateway) >> 24;
-		if (n < hlen)
-			return 0;
-
-		/* So... This guy found something strange INSIDE encapsulated
-		   packet. Well, he is fool, but what can we do ?
-		 */
-		rel_type = ICMP_PARAMETERPROB;
-		rel_info = htonl((n - hlen) << 24);
-		break;
-
-	case ICMP_DEST_UNREACH:
-		switch (code) {
-		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
-			/* Impossible event. */
-			return 0;
-		case ICMP_FRAG_NEEDED:
-			/* And it is the only really necessary thing :-) */
-			n = ntohs(icmp_hdr(skb)->un.frag.mtu);
-			if (n < hlen+68)
-				return 0;
-			n -= hlen;
-			/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
-			if (n > ntohs(eiph->tot_len))
-				return 0;
-			rel_info = htonl(n);
-			break;
-		default:
-			/* All others are translated to HOST_UNREACH.
-			   rfc2003 contains "deep thoughts" about NET_UNREACH,
-			   I believe, it is just ether pollution. --ANK
-			 */
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return 0;
-		break;
-	}
-
-	/* Prepare fake skb to feed it to icmp_send */
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (skb2 == NULL)
-		return 0;
-	dst_release(skb2->dst);
-	skb2->dst = NULL;
-	skb_pull(skb2, skb->data - (u8*)eiph);
-	skb_reset_network_header(skb2);
-
-	/* Try to guess incoming interface */
-	memset(&fl, 0, sizeof(fl));
-	fl.fl4_daddr = eiph->saddr;
-	fl.fl4_tos = RT_TOS(eiph->tos);
-	fl.proto = IPPROTO_IPIP;
-	if (ip_route_output_key(&init_net, &rt, &key)) {
-		kfree_skb(skb2);
-		return 0;
-	}
-	skb2->dev = rt->u.dst.dev;
-
-	/* route "incoming" packet */
-	if (rt->rt_flags&RTCF_LOCAL) {
-		ip_rt_put(rt);
-		rt = NULL;
-		fl.fl4_daddr = eiph->daddr;
-		fl.fl4_src = eiph->saddr;
-		fl.fl4_tos = eiph->tos;
-		if (ip_route_output_key(&init_net, &rt, &fl) ||
-		    rt->u.dst.dev->type != ARPHRD_TUNNEL) {
-			ip_rt_put(rt);
-			kfree_skb(skb2);
-			return 0;
-		}
-	} else {
-		ip_rt_put(rt);
-		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
-		    skb2->dst->dev->type != ARPHRD_TUNNEL) {
-			kfree_skb(skb2);
-			return 0;
-		}
-	}
-
-	/* change mtu on this route */
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		if (n > dst_mtu(skb2->dst)) {
-			kfree_skb(skb2);
-			return 0;
-		}
-		skb2->dst->ops->update_pmtu(skb2->dst, n);
-	} else if (type == ICMP_TIME_EXCEEDED) {
-		struct ip_tunnel *t = netdev_priv(skb2->dev);
-		if (t->parms.iph.ttl) {
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-		}
-	}
-
-	icmp_send(skb2, rel_type, rel_code, rel_info);
-	kfree_skb(skb2);
-	return 0;
-#endif
 }
 
-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);
-
-	read_lock(&ipip_lock);
-	if ((tunnel = ipip_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
-		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-			read_unlock(&ipip_lock);
-			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;
-
-		tunnel->stat.rx_packets++;
-		tunnel->stat.rx_bytes += skb->len;
-		skb->dev = tunnel->dev;
-		dst_release(skb->dst);
-		skb->dst = NULL;
-		nf_reset(skb);
-		ipip_ecn_decapsulate(iph, skb);
-		netif_rx(skb);
-		read_unlock(&ipip_lock);
-		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);
 	}
-	read_unlock(&ipip_lock);
 
 	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 int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct net_device_stats *stats = &tunnel->stat;
-	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 (tunnel->recursion++) {
-		tunnel->stat.collisions++;
-		goto tx_error;
-	}
-
-	if (skb->protocol != htons(ETH_P_IP))
-		goto tx_error;
-
-	if (tos&1)
-		tos = old_iph->tos;
-
-	if (!dst) {
-		/* NBMA tunnel */
-		if ((rt = (struct rtable*)skb->dst) == NULL) {
-			tunnel->stat.tx_fifo_errors++;
-			goto tx_error;
-		}
-		if ((dst = rt->rt_gateway) == 0)
-			goto tx_error_icmp;
-	}
-
-	{
-		struct flowi fl = { .oif = tunnel->parms.link,
-				    .nl_u = { .ip4_u =
-					      { .daddr = dst,
-						.saddr = tiph->saddr,
-						.tos = RT_TOS(tos) } },
-				    .proto = IPPROTO_IPIP };
-		if (ip_route_output_key(&init_net, &rt, &fl)) {
-			tunnel->stat.tx_carrier_errors++;
-			goto tx_error_icmp;
-		}
-	}
-	tdev = rt->u.dst.dev;
-
-	if (tdev == dev) {
-		ip_rt_put(rt);
-		tunnel->stat.collisions++;
-		goto tx_error;
-	}
+	const struct iphdr  *tiph = &tunnel->parms.iph;
 
-	if (tiph->frag_off)
-		mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
-	else
-		mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
-
-	if (mtu < 68) {
-		tunnel->stat.collisions++;
-		ip_rt_put(rt);
-		goto tx_error;
-	}
-	if (skb->dst)
-		skb->dst->ops->update_pmtu(skb->dst, mtu);
-
-	df |= (old_iph->frag_off&htons(IP_DF));
-
-	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);
+	if (unlikely(skb->protocol != htons(ETH_P_IP)))
 		goto tx_error;
-	}
-
-	if (tunnel->err_count > 0) {
-		if (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);
-			stats->tx_dropped++;
-			dev_kfree_skb(skb);
-			tunnel->recursion--;
-			return 0;
-		}
-		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);
-	dst_release(skb->dst);
-	skb->dst = &rt->u.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);
-
-	IPTUNNEL_XMIT();
-	tunnel->recursion--;
-	return 0;
+	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
+	return NETDEV_TX_OK;
 
-tx_error_icmp:
-	dst_link_failure(skb);
 tx_error:
-	stats->tx_errors++;
-	dev_kfree_skb(skb);
-	tunnel->recursion--;
-	return 0;
-}
-
-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,
-				    .nl_u = { .ip4_u =
-					      { .daddr = iph->daddr,
-						.saddr = iph->saddr,
-						.tos = RT_TOS(iph->tos) } },
-				    .proto = IPPROTO_IPIP };
-		struct rtable *rt;
-		if (!ip_route_output_key(&init_net, &rt, &fl)) {
-			tdev = rt->u.dst.dev;
-			ip_rt_put(rt);
-		}
-		dev->flags |= IFF_POINTOPOINT;
-	}
-
-	if (!tdev && tunnel->parms.link)
-		tdev = __dev_get_by_index(&init_net, 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;
+	kfree_skb(skb);
+out:
+	dev->stats.tx_errors++;
+	return NETDEV_TX_OK;
 }
 
 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;
 
-	switch (cmd) {
-	case SIOCGETTUNNEL:
-		t = NULL;
-		if (dev == ipip_fb_tunnel_dev) {
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
-				err = -EFAULT;
-				break;
-			}
-			t = ipip_tunnel_locate(&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(&p, cmd == SIOCADDTUNNEL);
-
-		if (dev != ipip_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(t);
-				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(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 == ipip_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(&p, 0)) == NULL)
-				goto done;
-			err = -EPERM;
-			if (t->dev == ipip_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);
 
-static struct net_device_stats *ipip_tunnel_get_stats(struct net_device *dev)
-{
-	return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
+	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_init       = ipip_tunnel_init,
+	.ndo_uninit     = ip_tunnel_uninit,
+	.ndo_start_xmit	= ipip_tunnel_xmit,
+	.ndo_do_ioctl	= ipip_tunnel_ioctl,
+	.ndo_change_mtu = ip_tunnel_change_mtu,
+	.ndo_get_stats64 = ip_tunnel_get_stats64,
+};
+
+#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->uninit		= ipip_tunnel_uninit;
-	dev->hard_start_xmit	= ipip_tunnel_xmit;
-	dev->get_stats		= ipip_tunnel_get_stats;
-	dev->do_ioctl		= ipip_tunnel_ioctl;
-	dev->change_mtu		= ipip_tunnel_change_mtu;
-	dev->destructor		= free_netdev;
+	dev->netdev_ops		= &ipip_netdev_ops;
 
 	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_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;
-
-	tunnel = netdev_priv(dev);
-
-	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
+	struct ip_tunnel *tunnel = netdev_priv(dev);
 
 	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
 
-	ipip_tunnel_bind_dev(dev);
+	tunnel->hlen = 0;
+	tunnel->parms.iph.protocol = IPPROTO_IPIP;
+	return ip_tunnel_init(dev);
+}
 
-	return 0;
+static void ipip_netlink_parms(struct nlattr *data[],
+			       struct ip_tunnel_parm *parms)
+{
+	memset(parms, 0, sizeof(*parms));
+
+	parms->iph.version = 4;
+	parms->iph.protocol = IPPROTO_IPIP;
+	parms->iph.ihl = 5;
+
+	if (!data)
+		return;
+
+	if (data[IFLA_IPTUN_LINK])
+		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
+
+	if (data[IFLA_IPTUN_LOCAL])
+		parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);
+
+	if (data[IFLA_IPTUN_REMOTE])
+		parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);
+
+	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);
+	}
+
+	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 __init ipip_fb_tunnel_init(struct net_device *dev)
+static int ipip_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[])
 {
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct iphdr *iph = &tunnel->parms.iph;
+	struct ip_tunnel_parm p;
+
+	ipip_netlink_parms(data, &p);
+	return ip_tunnel_newlink(dev, tb, &p);
+}
+
+static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
+			   struct nlattr *data[])
+{
+	struct ip_tunnel_parm p;
 
-	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
+	ipip_netlink_parms(data, &p);
 
-	iph->version		= 4;
-	iph->protocol		= IPPROTO_IPIP;
-	iph->ihl		= 5;
+	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
+	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
+		return -EINVAL;
 
-	dev_hold(dev);
-	tunnels_wc[0]		= tunnel;
+	return ip_tunnel_changelink(dev, tb, &p);
+}
+
+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;
+
+nla_put_failure:
+	return -EMSGSIZE;
 }
 
-static struct xfrm_tunnel ipip_handler = {
+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 char banner[] __initdata =
-	KERN_INFO "IPv4 over IPv4 tunneling driver\n";
+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 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 ip_tunnel_net),
+};
 
 static int __init ipip_init(void)
 {
 	int err;
 
-	printk(banner);
-
-	if (xfrm4_tunnel_register(&ipip_handler, AF_INET)) {
-		printk(KERN_INFO "ipip init: can't register tunnel\n");
-		return -EAGAIN;
-	}
+	pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
 
-	ipip_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
-					   "tunl0",
-					   ipip_tunnel_setup);
-	if (!ipip_fb_tunnel_dev) {
-		err = -ENOMEM;
-		goto err1;
+	err = register_pernet_device(&ipip_net_ops);
+	if (err < 0)
+		return err;
+	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+	if (err < 0) {
+		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;
 
-	ipip_fb_tunnel_dev->init = ipip_fb_tunnel_init;
-
-	if ((err = register_netdev(ipip_fb_tunnel_dev)))
-		goto err2;
- out:
+out:
 	return err;
- err2:
-	free_netdev(ipip_fb_tunnel_dev);
- err1:
+
+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_destroy_tunnels(void)
-{
-	int prio;
-
-	for (prio = 1; prio < 4; prio++) {
-		int h;
-		for (h = 0; h < HASH_SIZE; h++) {
-			struct ip_tunnel *t;
-			while ((t = tunnels[prio][h]) != NULL)
-				unregister_netdevice(t->dev);
-		}
-	}
-}
-
 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__);
 
-	rtnl_lock();
-	ipip_destroy_tunnels();
-	unregister_netdevice(ipip_fb_tunnel_dev);
-	rtnl_unlock();
+	unregister_pernet_device(&ipip_net_ops);
 }
 
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
+MODULE_ALIAS_NETDEV("tunl0");