Patchwork [RESEND,net-next,v2] GRE over IPv6

login
register
mail settings
Submitter xeb@mail.ru
Date Aug. 10, 2012, 7:20 a.m.
Message ID <2161896.kaoq3vBP40@dima>
Download mbox | patch
Permalink /patch/176412/
State Changes Requested
Delegated to: David Miller
Headers show

Comments

xeb@mail.ru - Aug. 10, 2012, 7:20 a.m.
GRE over IPv6 implementation.

Signed-off-by: Dmitry Kozlov <xeb@mail.ru>
---
Sorry, previous patch was malformed by mail program.
include/linux/if_arp.h     |    1 +
 include/linux/if_tunnel.h  |    3 +
 include/linux/ip6_tunnel.h |   17 +
 include/net/ip6_tunnel.h   |   41 +-
 include/net/ipv6.h         |    1 +
 net/ipv6/Kconfig           |   16 +
 net/ipv6/Makefile          |    1 +
 net/ipv6/ip6_gre.c         | 1791 ++++++++++++++++++++++++++++++++++++++++++++
 net/ipv6/ip6_tunnel.c      |   89 ++-
 9 files changed, 1934 insertions(+), 26 deletions(-)

Patch

diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index f0e69c6..9adcc29 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -92,6 +92,7 @@ 
 #define ARPHRD_PHONET	820		/* PhoNet media type		*/
 #define ARPHRD_PHONET_PIPE 821		/* PhoNet pipe header		*/
 #define ARPHRD_CAIF	822		/* CAIF media type		*/
+#define ARPHRD_IP6GRE	823		/* GRE over IPv6		*/
 
 #define ARPHRD_VOID	  0xFFFF	/* Void type, nothing is known */
 #define ARPHRD_NONE	  0xFFFE	/* zero header length */
diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index 5efff60..8c5035a 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -75,6 +75,9 @@  enum {
 	IFLA_GRE_TTL,
 	IFLA_GRE_TOS,
 	IFLA_GRE_PMTUDISC,
+	IFLA_GRE_ENCAP_LIMIT,
+	IFLA_GRE_FLOWINFO,
+	IFLA_GRE_FLAGS,
 	__IFLA_GRE_MAX,
 };
 
diff --git a/include/linux/ip6_tunnel.h b/include/linux/ip6_tunnel.h
index bf22b03..48af63c 100644
--- a/include/linux/ip6_tunnel.h
+++ b/include/linux/ip6_tunnel.h
@@ -31,4 +31,21 @@  struct ip6_tnl_parm {
 	struct in6_addr raddr;	/* remote tunnel end-point address */
 };
 
+struct ip6_tnl_parm2 {
+	char name[IFNAMSIZ];	/* name of tunnel device */
+	int link;		/* ifindex of underlying L2 interface */
+	__u8 proto;		/* tunnel protocol */
+	__u8 encap_limit;	/* encapsulation limit for tunnel */
+	__u8 hop_limit;		/* hop limit for tunnel */
+	__be32 flowinfo;	/* traffic class and flowlabel for tunnel */
+	__u32 flags;		/* tunnel flags */
+	struct in6_addr laddr;	/* local tunnel end-point address */
+	struct in6_addr raddr;	/* remote tunnel end-point address */
+
+	__be16			i_flags;
+	__be16			o_flags;
+	__be32			i_key;
+	__be32			o_key;
+};
+
 #endif
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 358fb86..e03047f 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -5,6 +5,8 @@ 
 #include <linux/netdevice.h>
 #include <linux/ip6_tunnel.h>
 
+#define IP6TUNNEL_ERR_TIMEO (30*HZ)
+
 /* capable of sending packets */
 #define IP6_TNL_F_CAP_XMIT 0x10000
 /* capable of receiving packets */
@@ -12,15 +14,40 @@ 
 /* determine capability on a per-packet basis */
 #define IP6_TNL_F_CAP_PER_PACKET 0x40000
 
-/* IPv6 tunnel */
+struct __ip6_tnl_parm {
+	char name[IFNAMSIZ];	/* name of tunnel device */
+	int link;		/* ifindex of underlying L2 interface */
+	__u8 proto;		/* tunnel protocol */
+	__u8 encap_limit;	/* encapsulation limit for tunnel */
+	__u8 hop_limit;		/* hop limit for tunnel */
+	__be32 flowinfo;	/* traffic class and flowlabel for tunnel */
+	__u32 flags;		/* tunnel flags */
+	struct in6_addr laddr;	/* local tunnel end-point address */
+	struct in6_addr raddr;	/* remote tunnel end-point address */
+
+	__be16			i_flags;
+	__be16			o_flags;
+	__be32			i_key;
+	__be32			o_key;
+};
 
+/* IPv6 tunnel */
 struct ip6_tnl {
 	struct ip6_tnl __rcu *next;	/* next tunnel in list */
 	struct net_device *dev;	/* virtual device associated with tunnel */
-	struct ip6_tnl_parm parms;	/* tunnel configuration parameters */
+	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
 	struct flowi fl;	/* flowi template for xmit */
 	struct dst_entry *dst_cache;    /* cached dst */
 	u32 dst_cookie;
+
+	int err_count;
+	unsigned long err_time;
+
+	/* These fields used only by GRE */
+	__u32 i_seqno;	/* The last seen seqno	*/
+	__u32 o_seqno;	/* The last output seqno */
+	int hlen;       /* Precalculated GRE header length */
+	int mlink;
 };
 
 /* Tunnel encapsulation limit destination sub-option */
@@ -31,4 +58,14 @@  struct ipv6_tlv_tnl_enc_lim {
 	__u8 encap_limit;	/* tunnel encapsulation limit   */
 } __packed;
 
+struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t);
+void ip6_tnl_dst_reset(struct ip6_tnl *t);
+void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst);
+int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
+		const struct in6_addr *raddr);
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t);
+__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
+__u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
+			     const struct in6_addr *raddr);
+
 #endif
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 01c34b3..6d01fb0 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -34,6 +34,7 @@ 
 #define NEXTHDR_IPV6		41	/* IPv6 in IPv6 */
 #define NEXTHDR_ROUTING		43	/* Routing header. */
 #define NEXTHDR_FRAGMENT	44	/* Fragmentation/reassembly header. */
+#define NEXTHDR_GRE		47	/* GRE header. */
 #define NEXTHDR_ESP		50	/* Encapsulating security payload. */
 #define NEXTHDR_AUTH		51	/* Authentication header. */
 #define NEXTHDR_ICMP		58	/* ICMP for IPv6. */
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 5728695..4f7fe72 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -201,6 +201,22 @@  config IPV6_TUNNEL
 
 	  If unsure, say N.
 
+config IPV6_GRE
+	tristate "IPv6: GRE tunnel"
+	select IPV6_TUNNEL
+	---help---
+	  Tunneling means encapsulating data of one protocol type within
+	  another protocol and sending it over a channel that understands the
+	  encapsulating protocol. This particular tunneling driver implements
+	  GRE (Generic Routing Encapsulation) and at this time allows
+	  encapsulating of IPv4 or IPv6 over existing IPv6 infrastructure.
+	  This driver is useful if the other endpoint is a Cisco router: Cisco
+	  likes GRE much better than the other Linux tunneling driver ("IP
+	  tunneling" above). In addition, GRE allows multicast redistribution
+	  through the tunnel.
+
+	  Saying M here will produce a module called ip6_gre. If unsure, say N.
+
 config IPV6_MULTIPLE_TABLES
 	bool "IPv6: Multiple Routing Tables"
 	depends on EXPERIMENTAL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 686934a..b6d3f79 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -36,6 +36,7 @@  obj-$(CONFIG_NETFILTER)	+= netfilter/
 
 obj-$(CONFIG_IPV6_SIT) += sit.o
 obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
+obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
 
 obj-y += addrconf_core.o exthdrs_core.o
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
new file mode 100644
index 0000000..4befedc
--- /dev/null
+++ b/net/ipv6/ip6_gre.c
@@ -0,0 +1,1791 @@ 
+/*
+ *	GRE over IPv6 protocol decoder.
+ *
+ *	Authors: Dmitry Kozlov (xeb@mail.ru)
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/mroute.h>
+#include <linux/init.h>
+#include <linux/in6.h>
+#include <linux/inetdevice.h>
+#include <linux/igmp.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/hash.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+#include <net/addrconf.h>
+#include <net/arp.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+
+#include <net/ipv6.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#include <net/ip6_tunnel.h>
+
+
+#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
+#define IPV6_TCLASS_SHIFT 20
+
+#define HASH_SIZE_SHIFT  5
+#define HASH_SIZE (1 << HASH_SIZE_SHIFT)
+
+static int ip6gre_net_id __read_mostly;
+struct ip6gre_net {
+	struct ip6_tnl __rcu *tunnels[4][HASH_SIZE];
+
+	struct net_device *fb_tunnel_dev;
+};
+
+static struct rtnl_link_ops ip6gre_link_ops __read_mostly;
+static int ip6gre_tunnel_init(struct net_device *dev);
+static void ip6gre_tunnel_setup(struct net_device *dev);
+static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
+static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu);
+
+/* Tunnel hash table */
+
+/*
+   4 hash tables:
+
+   3: (remote,local)
+   2: (remote,*)
+   1: (*,local)
+   0: (*,*)
+
+   We require exact key match i.e. if a key is present in packet
+   it will match only tunnel with the same key; if it is not present,
+   it will match only keyless tunnel.
+
+   All keysless packets, if not matched configured keyless tunnels
+   will match fallback tunnel.
+ */
+
+#define HASH_KEY(key) (((__force u32)key^((__force u32)key>>4))&(HASH_SIZE - 1))
+static u32 HASH_ADDR(const struct in6_addr *addr)
+{
+	u32 hash = ipv6_addr_hash(addr);
+
+	return hash_32(hash, HASH_SIZE_SHIFT);
+}
+
+#define tunnels_r_l	tunnels[3]
+#define tunnels_r	tunnels[2]
+#define tunnels_l	tunnels[1]
+#define tunnels_wc	tunnels[0]
+/*
+ * 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 {
+	u64	rx_packets;
+	u64	rx_bytes;
+	u64	tx_packets;
+	u64	tx_bytes;
+	struct u64_stats_sync	syncp;
+};
+
+static struct rtnl_link_stats64 *ip6gre_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;
+}
+
+/* Given src, dst and key, find appropriate for input tunnel. */
+
+static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
+		const struct in6_addr *remote, const struct in6_addr *local,
+		__be32 key, __be16 gre_proto)
+{
+	struct net *net = dev_net(dev);
+	int link = dev->ifindex;
+	unsigned int h0 = HASH_ADDR(remote);
+	unsigned int h1 = HASH_KEY(key);
+	struct ip6_tnl *t, *cand = NULL;
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
+		       ARPHRD_ETHER : ARPHRD_IP6GRE;
+	int score, cand_score = 4;
+
+	for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
+		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
+		    !ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IP6GRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
+		}
+	}
+
+	for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
+		if (!ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IP6GRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
+		}
+	}
+
+	for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
+		if ((!ipv6_addr_equal(local, &t->parms.laddr) &&
+			  (!ipv6_addr_equal(local, &t->parms.raddr) ||
+				 !ipv6_addr_is_multicast(local))) ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IP6GRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
+		}
+	}
+
+	for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
+		if (t->parms.i_key != key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IP6GRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
+		}
+	}
+
+	if (cand != NULL)
+		return cand;
+
+	dev = ign->fb_tunnel_dev;
+	if (dev->flags & IFF_UP)
+		return netdev_priv(dev);
+
+	return NULL;
+}
+
+static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign,
+		const struct __ip6_tnl_parm *p)
+{
+	const struct in6_addr *remote = &p->raddr;
+	const struct in6_addr *local = &p->laddr;
+	unsigned int h = HASH_KEY(p->i_key);
+	int prio = 0;
+
+	if (!ipv6_addr_any(local))
+		prio |= 1;
+	if (!ipv6_addr_any(remote) && !ipv6_addr_is_multicast(remote)) {
+		prio |= 2;
+		h ^= HASH_ADDR(remote);
+	}
+
+	return &ign->tunnels[prio][h];
+}
+
+static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign,
+		const struct ip6_tnl *t)
+{
+	return __ip6gre_bucket(ign, &t->parms);
+}
+
+static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
+
+	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
+	rcu_assign_pointer(*tp, t);
+}
+
+static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	struct ip6_tnl __rcu **tp;
+	struct ip6_tnl *iter;
+
+	for (tp = ip6gre_bucket(ign, t);
+	     (iter = rtnl_dereference(*tp)) != NULL;
+	     tp = &iter->next) {
+		if (t == iter) {
+			rcu_assign_pointer(*tp, t->next);
+			break;
+		}
+	}
+}
+
+static struct ip6_tnl *ip6gre_tunnel_find(struct net *net,
+					   const struct __ip6_tnl_parm *parms,
+					   int type)
+{
+	const struct in6_addr *remote = &parms->raddr;
+	const struct in6_addr *local = &parms->laddr;
+	__be32 key = parms->i_key;
+	int link = parms->link;
+	struct ip6_tnl *t;
+	struct ip6_tnl __rcu **tp;
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	for (tp = __ip6gre_bucket(ign, parms);
+	     (t = rtnl_dereference(*tp)) != NULL;
+	     tp = &t->next)
+		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    key == t->parms.i_key &&
+		    link == t->parms.link &&
+		    type == t->dev->type)
+			break;
+
+	return t;
+}
+
+static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
+		const struct __ip6_tnl_parm *parms, int create)
+{
+	struct ip6_tnl *t, *nt;
+	struct net_device *dev;
+	char name[IFNAMSIZ];
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE);
+	if (t || !create)
+		return t;
+
+	if (parms->name[0])
+		strlcpy(name, parms->name, IFNAMSIZ);
+	else
+		strcpy(name, "ip6gre%d");
+
+	dev = alloc_netdev(sizeof(*t), name, ip6gre_tunnel_setup);
+	if (!dev)
+		return NULL;
+
+	dev_net_set(dev, net);
+
+	nt = netdev_priv(dev);
+	nt->parms = *parms;
+	dev->rtnl_link_ops = &ip6gre_link_ops;
+
+	nt->dev = dev;
+	ip6gre_tnl_link_config(nt, 1);
+
+	if (register_netdevice(dev) < 0)
+		goto failed_free;
+
+	/* Can use a lockless transmit, unless we generate output sequences */
+	if (!(nt->parms.o_flags & GRE_SEQ))
+		dev->features |= NETIF_F_LLTX;
+
+	dev_hold(dev);
+	ip6gre_tunnel_link(ign, nt);
+	return nt;
+
+failed_free:
+	free_netdev(dev);
+	return NULL;
+}
+
+static void ip6gre_tunnel_uninit(struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	ip6gre_tunnel_unlink(ign, netdev_priv(dev));
+	dev_put(dev);
+}
+
+
+static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		u8 type, u8 code, int offset, __be32 info)
+{
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
+	__be16 *p = (__be16 *)(ipv6h + 1);
+	int grehlen = sizeof(ipv6h) + 4;
+	struct ip6_tnl *t;
+	__be16 flags;
+
+	flags = p[0];
+	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
+		if (flags&(GRE_VERSION|GRE_ROUTING))
+			return;
+		if (flags&GRE_KEY) {
+			grehlen += 4;
+			if (flags&GRE_CSUM)
+				grehlen += 4;
+		}
+	}
+
+	/* If only 8 bytes returned, keyed message will be dropped here */
+	if (skb_headlen(skb) < grehlen)
+		return;
+
+	rcu_read_lock();
+
+	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
+				flags & GRE_KEY ?
+				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
+				p[1]);
+	if (t == NULL)
+		goto out;
+
+	switch (type) {
+		__u32 teli;
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		__u32 mtu;
+	case ICMPV6_DEST_UNREACH:
+		net_warn_ratelimited("%s: Path to destination invalid or inactive!\n",
+				     t->parms.name);
+		break;
+	case ICMPV6_TIME_EXCEED:
+		if (code == ICMPV6_EXC_HOPLIMIT) {
+			net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
+					     t->parms.name);
+		}
+		break;
+	case ICMPV6_PARAMPROB:
+		teli = 0;
+		if (code == ICMPV6_HDR_FIELD)
+			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
+
+		if (teli && teli == info - 2) {
+			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
+			if (tel->encap_limit == 0) {
+				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
+						     t->parms.name);
+			}
+		} else {
+			net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
+					     t->parms.name);
+		}
+		break;
+	case ICMPV6_PKT_TOOBIG:
+		mtu = info - offset;
+		if (mtu < IPV6_MIN_MTU)
+			mtu = IPV6_MIN_MTU;
+		t->dev->mtu = mtu;
+		break;
+	}
+
+	if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
+		t->err_count++;
+	else
+		t->err_count = 1;
+	t->err_time = jiffies;
+out:
+	rcu_read_unlock();
+}
+
+static inline void ip6gre_ecn_decapsulate_ipv4(const struct ip6_tnl *t,
+		const struct ipv6hdr *ipv6h, struct sk_buff *skb)
+{
+	__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
+
+	if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
+		ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);
+
+	if (INET_ECN_is_ce(dsfield))
+		IP_ECN_set_ce(ip_hdr(skb));
+}
+
+static inline void ip6gre_ecn_decapsulate_ipv6(const struct ip6_tnl *t,
+		const struct ipv6hdr *ipv6h, struct sk_buff *skb)
+{
+	if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
+		ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));
+
+	if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h)))
+		IP6_ECN_set_ce(ipv6_hdr(skb));
+}
+
+static int ip6gre_rcv(struct sk_buff *skb)
+{
+	const struct ipv6hdr *ipv6h;
+	u8     *h;
+	__be16    flags;
+	__sum16   csum = 0;
+	__be32 key = 0;
+	u32    seqno = 0;
+	struct ip6_tnl *tunnel;
+	int    offset = 4;
+	__be16 gre_proto;
+
+	if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
+		goto drop_nolock;
+
+	ipv6h = ipv6_hdr(skb);
+	h = skb->data;
+	flags = *(__be16 *)h;
+
+	if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
+		/* - Version must be 0.
+		   - We do not support routing headers.
+		 */
+		if (flags&(GRE_VERSION|GRE_ROUTING))
+			goto drop_nolock;
+
+		if (flags&GRE_CSUM) {
+			switch (skb->ip_summed) {
+			case CHECKSUM_COMPLETE:
+				csum = csum_fold(skb->csum);
+				if (!csum)
+					break;
+				/* fall through */
+			case CHECKSUM_NONE:
+				skb->csum = 0;
+				csum = __skb_checksum_complete(skb);
+				skb->ip_summed = CHECKSUM_COMPLETE;
+			}
+			offset += 4;
+		}
+		if (flags&GRE_KEY) {
+			key = *(__be32 *)(h + offset);
+			offset += 4;
+		}
+		if (flags&GRE_SEQ) {
+			seqno = ntohl(*(__be32 *)(h + offset));
+			offset += 4;
+		}
+	}
+
+	gre_proto = *(__be16 *)(h + 2);
+
+	rcu_read_lock();
+	tunnel = ip6gre_tunnel_lookup(skb->dev,
+					  &ipv6h->saddr, &ipv6h->daddr, key,
+					  gre_proto);
+	if (tunnel) {
+		struct pcpu_tstats *tstats;
+
+		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+
+		if (!ip6_tnl_rcv_ctl(tunnel, &ipv6h->daddr, &ipv6h->saddr)) {
+			tunnel->dev->stats.rx_dropped++;
+			goto drop;
+		}
+
+		secpath_reset(skb);
+
+		skb->protocol = gre_proto;
+		/* WCCP version 1 and 2 protocol decoding.
+		 * - Change protocol to IP
+		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
+		 */
+		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
+			skb->protocol = htons(ETH_P_IP);
+			if ((*(h + offset) & 0xF0) != 0x40)
+				offset += 4;
+		}
+
+		skb->mac_header = skb->network_header;
+		__pskb_pull(skb, offset);
+		skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
+		skb->pkt_type = PACKET_HOST;
+
+		if (((flags&GRE_CSUM) && csum) ||
+		    (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
+			tunnel->dev->stats.rx_crc_errors++;
+			tunnel->dev->stats.rx_errors++;
+			goto drop;
+		}
+		if (tunnel->parms.i_flags&GRE_SEQ) {
+			if (!(flags&GRE_SEQ) ||
+			    (tunnel->i_seqno &&
+					(s32)(seqno - tunnel->i_seqno) < 0)) {
+				tunnel->dev->stats.rx_fifo_errors++;
+				tunnel->dev->stats.rx_errors++;
+				goto drop;
+			}
+			tunnel->i_seqno = seqno + 1;
+		}
+
+		/* Warning: All skb pointers will be invalidated! */
+		if (tunnel->dev->type == ARPHRD_ETHER) {
+			if (!pskb_may_pull(skb, ETH_HLEN)) {
+				tunnel->dev->stats.rx_length_errors++;
+				tunnel->dev->stats.rx_errors++;
+				goto drop;
+			}
+
+			ipv6h = ipv6_hdr(skb);
+			skb->protocol = eth_type_trans(skb, tunnel->dev);
+			skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+		}
+
+		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);
+
+		__skb_tunnel_rx(skb, tunnel->dev);
+
+		skb_reset_network_header(skb);
+		if (skb->protocol == htons(ETH_P_IP))
+			ip6gre_ecn_decapsulate_ipv4(tunnel, ipv6h, skb);
+		else if (skb->protocol == htons(ETH_P_IPV6))
+			ip6gre_ecn_decapsulate_ipv6(tunnel, ipv6h, skb);
+
+		netif_rx(skb);
+
+		rcu_read_unlock();
+		return 0;
+	}
+	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+drop:
+	rcu_read_unlock();
+drop_nolock:
+	kfree_skb(skb);
+	return 0;
+}
+
+struct ipv6_tel_txoption {
+	struct ipv6_txoptions ops;
+	__u8 dst_opt[8];
+};
+
+static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
+{
+	memset(opt, 0, sizeof(struct ipv6_tel_txoption));
+
+	opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT;
+	opt->dst_opt[3] = 1;
+	opt->dst_opt[4] = encap_limit;
+	opt->dst_opt[5] = IPV6_TLV_PADN;
+	opt->dst_opt[6] = 1;
+
+	opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt;
+	opt->ops.opt_nflen = 8;
+}
+
+static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
+			 struct net_device *dev,
+			 __u8 dsfield,
+			 struct flowi6 *fl6,
+			 int encap_limit,
+			 __u32 *pmtu)
+{
+	struct net *net = dev_net(dev);
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+	struct net_device *tdev;    /* Device to other host */
+	struct ipv6hdr  *ipv6h;     /* Our new IP header */
+	unsigned int max_headroom;  /* The extra header space needed */
+	int    gre_hlen;
+	struct ipv6_tel_txoption opt;
+	int    mtu;
+	struct dst_entry *dst = NULL, *ndst = NULL;
+	struct net_device_stats *stats = &tunnel->dev->stats;
+	int err = -1;
+	u8 proto;
+	int pkt_len;
+	struct sk_buff *new_skb;
+
+	if (dev->type == ARPHRD_ETHER)
+		IPCB(skb)->flags = 0;
+
+	if (dev->header_ops && dev->type == ARPHRD_IP6GRE) {
+		gre_hlen = 0;
+		ipv6h = (struct ipv6hdr *)skb->data;
+		fl6->daddr = ipv6h->daddr;
+	} else {
+		gre_hlen = tunnel->hlen;
+		fl6->daddr = tunnel->parms.raddr;
+	}
+
+	if (!fl6->flowi6_mark)
+		dst = ip6_tnl_dst_check(tunnel);
+
+	if (!dst) {
+		ndst = ip6_route_output(net, NULL, fl6);
+
+		if (ndst->error)
+			goto tx_err_link_failure;
+		ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0);
+		if (IS_ERR(ndst)) {
+			err = PTR_ERR(ndst);
+			ndst = NULL;
+			goto tx_err_link_failure;
+		}
+		dst = ndst;
+	}
+
+	tdev = dst->dev;
+
+	if (tdev == dev) {
+		stats->collisions++;
+		net_warn_ratelimited("%s: Local routing loop detected!\n",
+				     tunnel->parms.name);
+		goto tx_err_dst_release;
+	}
+
+	mtu = dst_mtu(dst) - sizeof(*ipv6h);
+	if (encap_limit >= 0) {
+		max_headroom += 8;
+		mtu -= 8;
+	}
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+	if (skb_dst(skb))
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	if (skb->len > mtu) {
+		*pmtu = mtu;
+		err = -EMSGSIZE;
+		goto tx_err_dst_release;
+	}
+
+	if (tunnel->err_count > 0) {
+		if (time_before(jiffies,
+				tunnel->err_time + IP6TUNNEL_ERR_TIMEO)) {
+			tunnel->err_count--;
+
+			dst_link_failure(skb);
+		} else
+			tunnel->err_count = 0;
+	}
+
+	max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
+
+	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
+	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
+		new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (max_headroom > dev->needed_headroom)
+			dev->needed_headroom = max_headroom;
+		if (!new_skb)
+			goto tx_err_dst_release;
+
+		if (skb->sk)
+			skb_set_owner_w(new_skb, skb->sk);
+		consume_skb(skb);
+		skb = new_skb;
+	}
+
+	skb_dst_drop(skb);
+
+	if (fl6->flowi6_mark) {
+		skb_dst_set(skb, dst);
+		ndst = NULL;
+	} else {
+		skb_dst_set_noref(skb, dst);
+	}
+
+	skb->transport_header = skb->network_header;
+
+	proto = NEXTHDR_GRE;
+	if (encap_limit >= 0) {
+		init_tel_txopt(&opt, encap_limit);
+		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
+	}
+
+	skb_push(skb, gre_hlen);
+	skb_reset_network_header(skb);
+
+	/*
+	 *	Push down and install the IP header.
+	 */
+	ipv6h = ipv6_hdr(skb);
+	*(__be32 *)ipv6h = fl6->flowlabel | htonl(0x60000000);
+	dsfield = INET_ECN_encapsulate(0, dsfield);
+	ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
+	ipv6h->hop_limit = tunnel->parms.hop_limit;
+	ipv6h->nexthdr = proto;
+	ipv6h->saddr = fl6->saddr;
+	ipv6h->daddr = fl6->daddr;
+
+	((__be16 *)(ipv6h + 1))[0] = tunnel->parms.o_flags;
+	((__be16 *)(ipv6h + 1))[1] = (dev->type == ARPHRD_ETHER) ?
+				   htons(ETH_P_TEB) : skb->protocol;
+
+	if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
+		__be32 *ptr = (__be32 *)(((u8 *)ipv6h) + tunnel->hlen - 4);
+
+		if (tunnel->parms.o_flags&GRE_SEQ) {
+			++tunnel->o_seqno;
+			*ptr = htonl(tunnel->o_seqno);
+			ptr--;
+		}
+		if (tunnel->parms.o_flags&GRE_KEY) {
+			*ptr = tunnel->parms.o_key;
+			ptr--;
+		}
+		if (tunnel->parms.o_flags&GRE_CSUM) {
+			*ptr = 0;
+			*(__sum16 *)ptr = ip_compute_csum((void *)(ipv6h+1),
+				skb->len - sizeof(struct ipv6hdr));
+		}
+	}
+
+	nf_reset(skb);
+	pkt_len = skb->len;
+	err = ip6_local_out(skb);
+
+	if (net_xmit_eval(err) == 0) {
+		struct pcpu_tstats *tstats = this_cpu_ptr(tunnel->dev->tstats);
+
+		tstats->tx_bytes += pkt_len;
+		tstats->tx_packets++;
+	} else {
+		stats->tx_errors++;
+		stats->tx_aborted_errors++;
+	}
+
+	if (ndst)
+		ip6_tnl_dst_store(tunnel, ndst);
+
+	return 0;
+tx_err_link_failure:
+	stats->tx_carrier_errors++;
+	dst_link_failure(skb);
+tx_err_dst_release:
+	dst_release(ndst);
+	return err;
+}
+
+static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	const struct iphdr  *iph = ip_hdr(skb);
+	int encap_limit = -1;
+	struct flowi6 fl6;
+	__u8 dsfield;
+	__u32 mtu;
+	int err;
+
+	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+		encap_limit = t->parms.encap_limit;
+
+	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_IPIP;
+
+	dsfield = ipv4_get_dsfield(iph);
+
+	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+		fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
+					  & IPV6_TCLASS_MASK;
+	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+		fl6.flowi6_mark = skb->mark;
+
+	err = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu);
+	if (err != 0) {
+		/* XXX: send ICMP error even if DF is not set. */
+		if (err == -EMSGSIZE)
+			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				  htonl(mtu));
+		return -1;
+	}
+
+	return 0;
+}
+
+static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	int encap_limit = -1;
+	__u16 offset;
+	struct flowi6 fl6;
+	__u8 dsfield;
+	__u32 mtu;
+	int err;
+
+	if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
+		return -1;
+
+	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+	if (offset > 0) {
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
+		if (tel->encap_limit == 0) {
+			icmpv6_send(skb, ICMPV6_PARAMPROB,
+				    ICMPV6_HDR_FIELD, offset + 2);
+			return -1;
+		}
+		encap_limit = tel->encap_limit - 1;
+	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+		encap_limit = t->parms.encap_limit;
+
+	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_IPV6;
+
+	dsfield = ipv6_get_dsfield(ipv6h);
+	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
+	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
+	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+		fl6.flowi6_mark = skb->mark;
+
+	err = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu);
+	if (err != 0) {
+		if (err == -EMSGSIZE)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		return -1;
+	}
+
+	return 0;
+}
+
+/**
+ * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own
+ *   @t: the outgoing tunnel device
+ *   @hdr: IPv6 header from the incoming packet
+ *
+ * Description:
+ *   Avoid trivial tunneling loop by checking that tunnel exit-point
+ *   doesn't match source of incoming packet.
+ *
+ * Return:
+ *   1 if conflict,
+ *   0 else
+ **/
+
+static inline bool ip6gre_tnl_addr_conflict(const struct ip6_tnl *t,
+	const struct ipv6hdr *hdr)
+{
+	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
+}
+
+static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	int encap_limit = -1;
+	struct flowi6 fl6;
+	__u32 mtu;
+	int err;
+
+	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+		encap_limit = t->parms.encap_limit;
+
+	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+	fl6.flowi6_proto = skb->protocol;
+
+	err = ip6gre_xmit2(skb, dev, 0, &fl6, encap_limit, &mtu);
+
+	return err;
+}
+
+static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
+	struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct net_device_stats *stats = &t->dev->stats;
+	int ret;
+
+	if (!ip6_tnl_xmit_ctl(t))
+		return -1;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		ret = ip6gre_xmit_ipv4(skb, dev);
+		break;
+	case htons(ETH_P_IPV6):
+		ret = ip6gre_xmit_ipv6(skb, dev);
+		break;
+	default:
+		ret = ip6gre_xmit_other(skb, dev);
+		break;
+	}
+
+	if (ret < 0)
+		goto tx_err;
+
+	return NETDEV_TX_OK;
+
+tx_err:
+	stats->tx_errors++;
+	stats->tx_dropped++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+	struct net_device *dev = t->dev;
+	struct __ip6_tnl_parm *p = &t->parms;
+	struct flowi6 *fl6 = &t->fl.u.ip6;
+	int addend = sizeof(struct ipv6hdr) + 4;
+
+	if (dev->type != ARPHRD_ETHER) {
+		memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
+		memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
+	}
+
+	/* Set up flowi template */
+	fl6->saddr = p->laddr;
+	fl6->daddr = p->raddr;
+	fl6->flowi6_oif = p->link;
+	fl6->flowlabel = 0;
+
+	if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
+		fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
+	if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL))
+		fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;
+
+	p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET);
+	p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr);
+
+	if (p->flags&IP6_TNL_F_CAP_XMIT &&
+			p->flags&IP6_TNL_F_CAP_RCV && dev->type != ARPHRD_ETHER)
+		dev->flags |= IFF_POINTOPOINT;
+	else
+		dev->flags &= ~IFF_POINTOPOINT;
+
+	dev->iflink = p->link;
+
+	/* Precalculate GRE options length */
+	if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
+		if (t->parms.o_flags&GRE_CSUM)
+			addend += 4;
+		if (t->parms.o_flags&GRE_KEY)
+			addend += 4;
+		if (t->parms.o_flags&GRE_SEQ)
+			addend += 4;
+	}
+
+	if (p->flags & IP6_TNL_F_CAP_XMIT) {
+		int strict = (ipv6_addr_type(&p->raddr) &
+			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
+
+		struct rt6_info *rt = rt6_lookup(dev_net(dev),
+						 &p->raddr, &p->laddr,
+						 p->link, strict);
+
+		if (rt == NULL)
+			return;
+
+		if (rt->dst.dev) {
+			dev->hard_header_len = rt->dst.dev->hard_header_len + addend;
+
+			if (set_mtu) {
+				dev->mtu = rt->dst.dev->mtu - addend;
+				if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+					dev->mtu -= 8;
+
+				if (dev->mtu < IPV6_MIN_MTU)
+					dev->mtu = IPV6_MIN_MTU;
+			}
+		}
+		dst_release(&rt->dst);
+	}
+
+	t->hlen = addend;
+}
+
+static int ip6gre_tnl_change(struct ip6_tnl *t,
+	const struct __ip6_tnl_parm *p, int set_mtu)
+{
+	t->parms.laddr = p->laddr;
+	t->parms.raddr = p->raddr;
+	t->parms.flags = p->flags;
+	t->parms.hop_limit = p->hop_limit;
+	t->parms.encap_limit = p->encap_limit;
+	t->parms.flowinfo = p->flowinfo;
+	t->parms.link = p->link;
+	t->parms.proto = p->proto;
+	t->parms.i_key = p->i_key;
+	t->parms.o_key = p->o_key;
+	t->parms.i_flags = p->i_flags;
+	t->parms.o_flags = p->o_flags;
+	ip6_tnl_dst_reset(t);
+	ip6gre_tnl_link_config(t, set_mtu);
+	return 0;
+}
+
+static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p,
+	const struct ip6_tnl_parm2 *u)
+{
+	p->laddr = u->laddr;
+	p->raddr = u->raddr;
+	p->flags = u->flags;
+	p->hop_limit = u->hop_limit;
+	p->encap_limit = u->encap_limit;
+	p->flowinfo = u->flowinfo;
+	p->link = u->link;
+	p->i_key = u->i_key;
+	p->o_key = u->o_key;
+	p->i_flags = u->i_flags;
+	p->o_flags = u->o_flags;
+	memcpy(p->name, u->name, sizeof(u->name));
+}
+
+static void ip6gre_tnl_parm_to_user(struct ip6_tnl_parm2 *u,
+	const struct __ip6_tnl_parm *p)
+{
+	u->proto = IPPROTO_GRE;
+	u->laddr = p->laddr;
+	u->raddr = p->raddr;
+	u->flags = p->flags;
+	u->hop_limit = p->hop_limit;
+	u->encap_limit = p->encap_limit;
+	u->flowinfo = p->flowinfo;
+	u->link = p->link;
+	u->i_key = p->i_key;
+	u->o_key = p->o_key;
+	u->i_flags = p->i_flags;
+	u->o_flags = p->o_flags;
+	memcpy(u->name, p->name, sizeof(u->name));
+}
+
+static int ip6gre_tunnel_ioctl(struct net_device *dev,
+	struct ifreq *ifr, int cmd)
+{
+	int err = 0;
+	struct ip6_tnl_parm2 p;
+	struct __ip6_tnl_parm p1;
+	struct ip6_tnl *t;
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	switch (cmd) {
+	case SIOCGETTUNNEL:
+		t = NULL;
+		if (dev == ign->fb_tunnel_dev) {
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
+				err = -EFAULT;
+				break;
+			}
+			ip6gre_tnl_parm_from_user(&p1, &p);
+			t = ip6gre_tunnel_locate(net, &p1, 0);
+		}
+		if (t == NULL)
+			t = netdev_priv(dev);
+		ip6gre_tnl_parm_to_user(&p, &t->parms);
+		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 ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))
+			goto done;
+
+		if (!(p.i_flags&GRE_KEY))
+			p.i_key = 0;
+		if (!(p.o_flags&GRE_KEY))
+			p.o_key = 0;
+
+		ip6gre_tnl_parm_from_user(&p1, &p);
+		t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL);
+
+		if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+			if (t != NULL) {
+				if (t->dev != dev) {
+					err = -EEXIST;
+					break;
+				}
+			} else {
+				t = netdev_priv(dev);
+
+				ip6gre_tunnel_unlink(ign, t);
+				synchronize_net();
+				ip6gre_tnl_change(t, &p1, 1);
+				ip6gre_tunnel_link(ign, t);
+				netdev_state_change(dev);
+			}
+		}
+
+		if (t) {
+			err = 0;
+
+			ip6gre_tnl_parm_to_user(&p, &t->parms);
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+				err = -EFAULT;
+		} else
+			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		break;
+
+	case SIOCDELTUNNEL:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		if (dev == ign->fb_tunnel_dev) {
+			err = -EFAULT;
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+				goto done;
+			err = -ENOENT;
+			ip6gre_tnl_parm_from_user(&p1, &p);
+			t = ip6gre_tunnel_locate(net, &p1, 0);
+			if (t == NULL)
+				goto done;
+			err = -EPERM;
+			if (t == netdev_priv(ign->fb_tunnel_dev))
+				goto done;
+			dev = t->dev;
+		}
+		unregister_netdevice(dev);
+		err = 0;
+		break;
+
+	default:
+		err = -EINVAL;
+	}
+
+done:
+	return err;
+}
+
+static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+	if (new_mtu < 68 ||
+	    new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
+		return -EINVAL;
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
+			unsigned short type,
+			const void *daddr, const void *saddr, unsigned int len)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen);
+	__be16 *p = (__be16 *)(ipv6h+1);
+
+	*(__be32 *)ipv6h = t->fl.u.ip6.flowlabel | htonl(0x60000000);
+	ipv6h->hop_limit = t->parms.hop_limit;
+	ipv6h->nexthdr = NEXTHDR_GRE;
+	ipv6h->saddr = t->parms.laddr;
+	ipv6h->daddr = t->parms.raddr;
+
+	p[0]		= t->parms.o_flags;
+	p[1]		= htons(type);
+
+	/*
+	 *	Set the source hardware address.
+	 */
+
+	if (saddr)
+		memcpy(&ipv6h->saddr, saddr, sizeof(struct in6_addr));
+	if (daddr)
+		memcpy(&ipv6h->daddr, daddr, sizeof(struct in6_addr));
+	if (!ipv6_addr_any(&ipv6h->daddr))
+		return t->hlen;
+
+	return -t->hlen;
+}
+
+static int ip6gre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb_mac_header(skb);
+	memcpy(haddr, &ipv6h->saddr, sizeof(struct in6_addr));
+	return sizeof(struct in6_addr);
+}
+
+static const struct header_ops ip6gre_header_ops = {
+	.create	= ip6gre_header,
+	.parse	= ip6gre_header_parse,
+};
+
+static const struct net_device_ops ip6gre_netdev_ops = {
+	.ndo_init		= ip6gre_tunnel_init,
+	.ndo_uninit		= ip6gre_tunnel_uninit,
+	.ndo_start_xmit		= ip6gre_tunnel_xmit,
+	.ndo_do_ioctl		= ip6gre_tunnel_ioctl,
+	.ndo_change_mtu		= ip6gre_tunnel_change_mtu,
+	.ndo_get_stats64	= ip6gre_get_stats64,
+};
+
+static void ip6gre_dev_free(struct net_device *dev)
+{
+	free_percpu(dev->tstats);
+	free_netdev(dev);
+}
+
+static void ip6gre_tunnel_setup(struct net_device *dev)
+{
+	struct ip6_tnl *t;
+
+	dev->netdev_ops = &ip6gre_netdev_ops;
+	dev->destructor = ip6gre_dev_free;
+
+	dev->type = ARPHRD_IP6GRE;
+	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr) + 4;
+	dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr) - 4;
+	t = netdev_priv(dev);
+	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+		dev->mtu -= 8;
+	dev->flags |= IFF_NOARP;
+	dev->iflink = 0;
+	dev->addr_len = sizeof(struct in6_addr);
+	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+}
+
+static int ip6gre_tunnel_init(struct net_device *dev)
+{
+	struct ip6_tnl *tunnel;
+
+	tunnel = netdev_priv(dev);
+
+	tunnel->dev = dev;
+	strcpy(tunnel->parms.name, dev->name);
+
+	memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
+	memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr));
+
+	if (ipv6_addr_any(&tunnel->parms.raddr))
+		dev->header_ops = &ip6gre_header_ops;
+
+	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void ip6gre_fb_tunnel_init(struct net_device *dev)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+
+	tunnel->dev = dev;
+	strcpy(tunnel->parms.name, dev->name);
+
+	tunnel->hlen		= sizeof(struct ipv6hdr) + 4;
+
+	dev_hold(dev);
+}
+
+
+static struct inet6_protocol ip6gre_protocol __read_mostly = {
+	.handler     = ip6gre_rcv,
+	.err_handler = ip6gre_err,
+	.flags       = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
+};
+
+static void ip6gre_destroy_tunnels(struct ip6gre_net *ign,
+	struct list_head *head)
+{
+	int prio;
+
+	for (prio = 0; prio < 4; prio++) {
+		int h;
+		for (h = 0; h < HASH_SIZE; h++) {
+			struct ip6_tnl *t;
+
+			t = rtnl_dereference(ign->tunnels[prio][h]);
+
+			while (t != NULL) {
+				unregister_netdevice_queue(t->dev, head);
+				t = rtnl_dereference(t->next);
+			}
+		}
+	}
+}
+
+static int __net_init ip6gre_init_net(struct net *net)
+{
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	int err;
+
+	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
+					   ip6gre_tunnel_setup);
+	if (!ign->fb_tunnel_dev) {
+		err = -ENOMEM;
+		goto err_alloc_dev;
+	}
+	dev_net_set(ign->fb_tunnel_dev, net);
+
+	ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
+	ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
+
+	err = register_netdev(ign->fb_tunnel_dev);
+	if (err)
+		goto err_reg_dev;
+
+	rcu_assign_pointer(ign->tunnels_wc[0],
+			   netdev_priv(ign->fb_tunnel_dev));
+	return 0;
+
+err_reg_dev:
+	ip6gre_dev_free(ign->fb_tunnel_dev);
+err_alloc_dev:
+	return err;
+}
+
+static void __net_exit ip6gre_exit_net(struct net *net)
+{
+	struct ip6gre_net *ign;
+	LIST_HEAD(list);
+
+	ign = net_generic(net, ip6gre_net_id);
+	rtnl_lock();
+	ip6gre_destroy_tunnels(ign, &list);
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
+static struct pernet_operations ip6gre_net_ops = {
+	.init = ip6gre_init_net,
+	.exit = ip6gre_exit_net,
+	.id   = &ip6gre_net_id,
+	.size = sizeof(struct ip6gre_net),
+};
+
+static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	__be16 flags;
+
+	if (!data)
+		return 0;
+
+	flags = 0;
+	if (data[IFLA_GRE_IFLAGS])
+		flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]);
+	if (data[IFLA_GRE_OFLAGS])
+		flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
+	if (flags & (GRE_VERSION|GRE_ROUTING))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	struct in6_addr daddr;
+
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (!data)
+		goto out;
+
+	if (data[IFLA_GRE_REMOTE]) {
+		nla_memcpy(&daddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr));
+		if (ipv6_addr_any(&daddr))
+			return -EINVAL;
+	}
+
+out:
+	return ip6gre_tunnel_validate(tb, data);
+}
+
+
+static void ip6gre_netlink_parms(struct nlattr *data[],
+				struct __ip6_tnl_parm *parms)
+{
+	memset(parms, 0, sizeof(*parms));
+
+	if (!data)
+		return;
+
+	if (data[IFLA_GRE_LINK])
+		parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
+
+	if (data[IFLA_GRE_IFLAGS])
+		parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);
+
+	if (data[IFLA_GRE_OFLAGS])
+		parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);
+
+	if (data[IFLA_GRE_IKEY])
+		parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);
+
+	if (data[IFLA_GRE_OKEY])
+		parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);
+
+	if (data[IFLA_GRE_LOCAL])
+		nla_memcpy(&parms->laddr, data[IFLA_GRE_LOCAL], sizeof(struct in6_addr));
+
+	if (data[IFLA_GRE_REMOTE])
+		nla_memcpy(&parms->raddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr));
+
+	if (data[IFLA_GRE_TTL])
+		parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]);
+
+	if (data[IFLA_GRE_ENCAP_LIMIT])
+		parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]);
+
+	if (data[IFLA_GRE_FLOWINFO])
+		parms->flowinfo = nla_get_u32(data[IFLA_GRE_FLOWINFO]);
+
+	if (data[IFLA_GRE_FLAGS])
+		parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]);
+}
+
+static int ip6gre_tap_init(struct net_device *dev)
+{
+	struct ip6_tnl *tunnel;
+
+	tunnel = netdev_priv(dev);
+
+	tunnel->dev = dev;
+	strcpy(tunnel->parms.name, dev->name);
+
+	ip6gre_tnl_link_config(tunnel, 1);
+
+	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static const struct net_device_ops ip6gre_tap_netdev_ops = {
+	.ndo_init = ip6gre_tap_init,
+	.ndo_uninit = ip6gre_tunnel_uninit,
+	.ndo_start_xmit = ip6gre_tunnel_xmit,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_change_mtu = ip6gre_tunnel_change_mtu,
+	.ndo_get_stats64 = ip6gre_get_stats64,
+};
+
+static void ip6gre_tap_setup(struct net_device *dev)
+{
+
+	ether_setup(dev);
+
+	dev->netdev_ops = &ip6gre_tap_netdev_ops;
+	dev->destructor = ip6gre_dev_free;
+
+	dev->iflink = 0;
+	dev->features |= NETIF_F_NETNS_LOCAL;
+}
+
+static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
+	struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ip6_tnl *nt;
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	int err;
+
+	nt = netdev_priv(dev);
+	ip6gre_netlink_parms(data, &nt->parms);
+
+	if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+		return -EEXIST;
+
+	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
+		eth_hw_addr_random(dev);
+
+	nt->dev = dev;
+	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+
+	/* Can use a lockless transmit, unless we generate output sequences */
+	if (!(nt->parms.o_flags & GRE_SEQ))
+		dev->features |= NETIF_F_LLTX;
+
+	err = register_netdevice(dev);
+	if (err)
+		goto out;
+
+	dev_hold(dev);
+	ip6gre_tunnel_link(ign, nt);
+
+out:
+	return err;
+}
+
+static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
+			    struct nlattr *data[])
+{
+	struct ip6_tnl *t, *nt;
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct __ip6_tnl_parm p;
+
+	if (dev == ign->fb_tunnel_dev)
+		return -EINVAL;
+
+	nt = netdev_priv(dev);
+	ip6gre_netlink_parms(data, &p);
+
+	t = ip6gre_tunnel_locate(net, &p, 0);
+
+	if (t) {
+		if (t->dev != dev)
+			return -EEXIST;
+	} else {
+		t = nt;
+
+		ip6gre_tunnel_unlink(ign, t);
+		ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+		ip6gre_tunnel_link(ign, t);
+		netdev_state_change(dev);
+	}
+
+	return 0;
+}
+
+static size_t ip6gre_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_GRE_LINK */
+		nla_total_size(4) +
+		/* IFLA_GRE_IFLAGS */
+		nla_total_size(2) +
+		/* IFLA_GRE_OFLAGS */
+		nla_total_size(2) +
+		/* IFLA_GRE_IKEY */
+		nla_total_size(4) +
+		/* IFLA_GRE_OKEY */
+		nla_total_size(4) +
+		/* IFLA_GRE_LOCAL */
+		nla_total_size(4) +
+		/* IFLA_GRE_REMOTE */
+		nla_total_size(4) +
+		/* IFLA_GRE_TTL */
+		nla_total_size(1) +
+		/* IFLA_GRE_TOS */
+		nla_total_size(1) +
+		/* IFLA_GRE_ENCAP_LIMIT */
+		nla_total_size(1) +
+		/* IFLA_GRE_FLOWINFO */
+		nla_total_size(4) +
+		/* IFLA_GRE_FLAGS */
+		nla_total_size(4) +
+		0;
+}
+
+static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct __ip6_tnl_parm *p = &t->parms;
+
+	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
+	    nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) ||
+	    nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
+	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
+	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
+	    nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) ||
+	    nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) ||
+	    nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) ||
+	    /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/
+	    nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
+	    nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
+	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = {
+	[IFLA_GRE_LINK]        = { .type = NLA_U32 },
+	[IFLA_GRE_IFLAGS]      = { .type = NLA_U16 },
+	[IFLA_GRE_OFLAGS]      = { .type = NLA_U16 },
+	[IFLA_GRE_IKEY]        = { .type = NLA_U32 },
+	[IFLA_GRE_OKEY]        = { .type = NLA_U32 },
+	[IFLA_GRE_LOCAL]       = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) },
+	[IFLA_GRE_REMOTE]      = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) },
+	[IFLA_GRE_TTL]         = { .type = NLA_U8 },
+	[IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 },
+	[IFLA_GRE_FLOWINFO]    = { .type = NLA_U32 },
+	[IFLA_GRE_FLAGS]       = { .type = NLA_U32 },
+};
+
+static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
+	.kind		= "ip6gre",
+	.maxtype	= IFLA_GRE_MAX,
+	.policy		= ip6gre_policy,
+	.priv_size	= sizeof(struct ip6_tnl),
+	.setup		= ip6gre_tunnel_setup,
+	.validate	= ip6gre_tunnel_validate,
+	.newlink	= ip6gre_newlink,
+	.changelink	= ip6gre_changelink,
+	.get_size	= ip6gre_get_size,
+	.fill_info	= ip6gre_fill_info,
+};
+
+static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
+	.kind		= "ip6gretap",
+	.maxtype	= IFLA_GRE_MAX,
+	.policy		= ip6gre_policy,
+	.priv_size	= sizeof(struct ip6_tnl),
+	.setup		= ip6gre_tap_setup,
+	.validate	= ip6gre_tap_validate,
+	.newlink	= ip6gre_newlink,
+	.changelink	= ip6gre_changelink,
+	.get_size	= ip6gre_get_size,
+	.fill_info	= ip6gre_fill_info,
+};
+
+/*
+ *	And now the modules code and kernel interface.
+ */
+
+static int __init ip6gre_init(void)
+{
+	int err;
+
+	pr_info("GRE over IPv6 tunneling driver\n");
+
+	err = register_pernet_device(&ip6gre_net_ops);
+	if (err < 0)
+		return err;
+
+	err = inet6_add_protocol(&ip6gre_protocol, IPPROTO_GRE);
+	if (err < 0) {
+		pr_info("%s: can't add protocol\n", __func__);
+		goto add_proto_failed;
+	}
+
+	err = rtnl_link_register(&ip6gre_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
+
+	err = rtnl_link_register(&ip6gre_tap_ops);
+	if (err < 0)
+		goto tap_ops_failed;
+
+out:
+	return err;
+
+tap_ops_failed:
+	rtnl_link_unregister(&ip6gre_link_ops);
+rtnl_link_failed:
+	inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE);
+add_proto_failed:
+	unregister_pernet_device(&ip6gre_net_ops);
+	goto out;
+}
+
+static void __exit ip6gre_fini(void)
+{
+	rtnl_link_unregister(&ip6gre_tap_ops);
+	rtnl_link_unregister(&ip6gre_link_ops);
+	inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE);
+	unregister_pernet_device(&ip6gre_net_ops);
+}
+
+module_init(ip6gre_init);
+module_exit(ip6gre_fini);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
+MODULE_DESCRIPTION("GRE over IPv6 tunneling device");
+MODULE_ALIAS_RTNL_LINK("ip6gre");
+MODULE_ALIAS_NETDEV("ip6gre0");
+
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9a1d5fe..33d2a0e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -126,7 +126,7 @@  static struct net_device_stats *ip6_get_stats(struct net_device *dev)
  * Locking : hash tables are protected by RCU and RTNL
  */
 
-static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
+struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
 {
 	struct dst_entry *dst = t->dst_cache;
 
@@ -139,20 +139,23 @@  static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
 
 	return dst;
 }
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_check);
 
-static inline void ip6_tnl_dst_reset(struct ip6_tnl *t)
+void ip6_tnl_dst_reset(struct ip6_tnl *t)
 {
 	dst_release(t->dst_cache);
 	t->dst_cache = NULL;
 }
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
 
-static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
+void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
 {
 	struct rt6_info *rt = (struct rt6_info *) dst;
 	t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
 	dst_release(t->dst_cache);
 	t->dst_cache = dst;
 }
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_store);
 
 /**
  * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
@@ -200,7 +203,7 @@  ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
  **/
 
 static struct ip6_tnl __rcu **
-ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p)
+ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p)
 {
 	const struct in6_addr *remote = &p->raddr;
 	const struct in6_addr *local = &p->laddr;
@@ -267,7 +270,7 @@  static void ip6_dev_free(struct net_device *dev)
  *   created tunnel or NULL
  **/
 
-static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
+static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 {
 	struct net_device *dev;
 	struct ip6_tnl *t;
@@ -322,7 +325,7 @@  failed:
  **/
 
 static struct ip6_tnl *ip6_tnl_locate(struct net *net,
-		struct ip6_tnl_parm *p, int create)
+		struct __ip6_tnl_parm *p, int create)
 {
 	const struct in6_addr *remote = &p->raddr;
 	const struct in6_addr *local = &p->laddr;
@@ -374,8 +377,7 @@  ip6_tnl_dev_uninit(struct net_device *dev)
  *   else index to encapsulation limit
  **/
 
-static __u16
-parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
+__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
 	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
 	__u8 nexthdr = ipv6h->nexthdr;
@@ -425,6 +427,7 @@  parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim);
 
 /**
  * ip6_tnl_err - tunnel error handler
@@ -480,7 +483,7 @@  ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	case ICMPV6_PARAMPROB:
 		teli = 0;
 		if ((*code) == ICMPV6_HDR_FIELD)
-			teli = parse_tlv_tnl_enc_lim(skb, skb->data);
+			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
 
 		if (teli && teli == *info - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
@@ -693,11 +696,11 @@  static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
 		IP6_ECN_set_ce(ipv6_hdr(skb));
 }
 
-static __u32 ip6_tnl_get_cap(struct ip6_tnl *t,
+__u32 ip6_tnl_get_cap(struct ip6_tnl *t,
 			     const struct in6_addr *laddr,
 			     const struct in6_addr *raddr)
 {
-	struct ip6_tnl_parm *p = &t->parms;
+	struct __ip6_tnl_parm *p = &t->parms;
 	int ltype = ipv6_addr_type(laddr);
 	int rtype = ipv6_addr_type(raddr);
 	__u32 flags = 0;
@@ -715,13 +718,14 @@  static __u32 ip6_tnl_get_cap(struct ip6_tnl *t,
 	}
 	return flags;
 }
+EXPORT_SYMBOL(ip6_tnl_get_cap);
 
 /* called with rcu_read_lock() */
-static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
+int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 				  const struct in6_addr *laddr,
 				  const struct in6_addr *raddr)
 {
-	struct ip6_tnl_parm *p = &t->parms;
+	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
 	struct net *net = dev_net(t->dev);
 
@@ -740,6 +744,7 @@  static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl);
 
 /**
  * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally
@@ -859,9 +864,9 @@  ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
 	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
 }
 
-static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
 {
-	struct ip6_tnl_parm *p = &t->parms;
+	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
 	struct net *net = dev_net(t->dev);
 
@@ -885,6 +890,8 @@  static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl);
+
 /**
  * ip6_tnl_xmit2 - encapsulate packet and send
  *   @skb: the outgoing socket buffer
@@ -1085,7 +1092,7 @@  ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	    !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
 		return -1;
 
-	offset = parse_tlv_tnl_enc_lim(skb, skb_network_header(skb));
+	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
 		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
@@ -1152,7 +1159,7 @@  tx_err:
 static void ip6_tnl_link_config(struct ip6_tnl *t)
 {
 	struct net_device *dev = t->dev;
-	struct ip6_tnl_parm *p = &t->parms;
+	struct __ip6_tnl_parm *p = &t->parms;
 	struct flowi6 *fl6 = &t->fl.u.ip6;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
@@ -1215,7 +1222,7 @@  static void ip6_tnl_link_config(struct ip6_tnl *t)
  **/
 
 static int
-ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
+ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 {
 	t->parms.laddr = p->laddr;
 	t->parms.raddr = p->raddr;
@@ -1230,6 +1237,34 @@  ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
 	return 0;
 }
 
+static void
+ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u)
+{
+	p->laddr = u->laddr;
+	p->raddr = u->raddr;
+	p->flags = u->flags;
+	p->hop_limit = u->hop_limit;
+	p->encap_limit = u->encap_limit;
+	p->flowinfo = u->flowinfo;
+	p->link = u->link;
+	p->proto = u->proto;
+	memcpy(p->name, u->name, sizeof(u->name));
+}
+
+static void
+ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p)
+{
+	u->laddr = p->laddr;
+	u->raddr = p->raddr;
+	u->flags = p->flags;
+	u->hop_limit = p->hop_limit;
+	u->encap_limit = p->encap_limit;
+	u->flowinfo = p->flowinfo;
+	u->link = p->link;
+	u->proto = p->proto;
+	memcpy(u->name, p->name, sizeof(u->name));
+}
+
 /**
  * ip6_tnl_ioctl - configure ipv6 tunnels from userspace
  *   @dev: virtual device associated with tunnel
@@ -1263,6 +1298,7 @@  ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	int err = 0;
 	struct ip6_tnl_parm p;
+	struct __ip6_tnl_parm p1;
 	struct ip6_tnl *t = NULL;
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -1274,11 +1310,12 @@  ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 				err = -EFAULT;
 				break;
 			}
-			t = ip6_tnl_locate(net, &p, 0);
+			ip6_tnl_parm_from_user(&p1, &p);
+			t = ip6_tnl_locate(net, &p1, 0);
 		}
 		if (t == NULL)
 			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof (p));
+		ip6_tnl_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
 			err = -EFAULT;
 		}
@@ -1295,7 +1332,8 @@  ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
 		    p.proto != 0)
 			break;
-		t = ip6_tnl_locate(net, &p, cmd == SIOCADDTUNNEL);
+		ip6_tnl_parm_from_user(&p1, &p);
+		t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL);
 		if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
 			if (t != NULL) {
 				if (t->dev != dev) {
@@ -1307,13 +1345,14 @@  ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 			ip6_tnl_unlink(ip6n, t);
 			synchronize_net();
-			err = ip6_tnl_change(t, &p);
+			err = ip6_tnl_change(t, &p1);
 			ip6_tnl_link(ip6n, t);
 			netdev_state_change(dev);
 		}
 		if (t) {
 			err = 0;
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof (p)))
+			ip6_tnl_parm_to_user(&p, &t->parms);
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 				err = -EFAULT;
 
 		} else
@@ -1329,7 +1368,9 @@  ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
 				break;
 			err = -ENOENT;
-			if ((t = ip6_tnl_locate(net, &p, 0)) == NULL)
+			ip6_tnl_parm_from_user(&p1, &p);
+			t = ip6_tnl_locate(net, &p1, 0);
+			if (t == NULL)
 				break;
 			err = -EPERM;
 			if (t->dev == ip6n->fb_tnl_dev)