[mirror_ubuntu-eoan-kernel.git] / net / ipv4 / ip_vti.c

/*
 *	Linux NET3: IP/IP protocol decoder modified to support
 *		    virtual tunnel interface
 *
 *	Authors:
 *		Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012
 *
 *	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.
 *
 */

/*
   This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c

   For comments look at net/ipv4/ip_gre.c --ANK
 */


#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.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/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <linux/icmpv6.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

static struct rtnl_link_ops vti_link_ops __read_mostly;

static unsigned int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);

static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
		     int encap_type)
{
	struct ip_tunnel *tunnel;
	const struct iphdr *iph = ip_hdr(skb);
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);

	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;

		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;

		return xfrm_input(skb, nexthdr, spi, encap_type);
	}

	return -EINVAL;
drop:
	kfree_skb(skb);
	return 0;
}

static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
		     int encap_type)
{
	struct ip_tunnel *tunnel;
	const struct iphdr *iph = ip_hdr(skb);
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);

	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;

		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;

		skb->dev = tunnel->dev;

		return xfrm_input(skb, nexthdr, spi, encap_type);
	}

	return -EINVAL;
drop:
	kfree_skb(skb);
	return 0;
}

static int vti_rcv(struct sk_buff *skb)
{
	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);

	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}

static int vti_rcv_ipip(struct sk_buff *skb)
{
	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);

	return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
}

static int vti_rcv_cb(struct sk_buff *skb, int err)
{
	unsigned short family;
	struct net_device *dev;
	struct pcpu_sw_netstats *tstats;
	struct xfrm_state *x;
	struct xfrm_mode *inner_mode;
	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
	u32 orig_mark = skb->mark;
	int ret;

	if (!tunnel)
		return 1;

	dev = tunnel->dev;

	if (err) {
		dev->stats.rx_errors++;
		dev->stats.rx_dropped++;

		return 0;
	}

	x = xfrm_input_state(skb);

	inner_mode = x->inner_mode;

	if (x->sel.family == AF_UNSPEC) {
		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
		if (inner_mode == NULL) {
			XFRM_INC_STATS(dev_net(skb->dev),
				       LINUX_MIB_XFRMINSTATEMODEERROR);
			return -EINVAL;
		}
	}

	family = inner_mode->afinfo->family;

	skb->mark = be32_to_cpu(tunnel->parms.i_key);
	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
	skb->mark = orig_mark;

	if (!ret)
		return -EPERM;

	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
	skb->dev = dev;

	tstats = this_cpu_ptr(dev->tstats);

	u64_stats_update_begin(&tstats->syncp);
	tstats->rx_packets++;
	tstats->rx_bytes += skb->len;
	u64_stats_update_end(&tstats->syncp);

	return 0;
}

static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
{
	xfrm_address_t *daddr = (xfrm_address_t *)&dst;
	xfrm_address_t *saddr = (xfrm_address_t *)&src;

	/* if there is no transform then this tunnel is not functional.
	 * Or if the xfrm is not mode tunnel.
	 */
	if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
	    x->props.family != AF_INET)
		return false;

	if (!dst)
		return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);

	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
		return false;

	return true;
}

static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
			    struct flowi *fl)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct ip_tunnel_parm *parms = &tunnel->parms;
	struct dst_entry *dst = skb_dst(skb);
	struct net_device *tdev;	/* Device to other host */
	int pkt_len = skb->len;
	int err;
	int mtu;

	if (!dst) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}

	dst_hold(dst);
	dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
	if (IS_ERR(dst)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}

	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
		dev->stats.tx_carrier_errors++;
		dst_release(dst);
		goto tx_error_icmp;
	}

	tdev = dst->dev;

	if (tdev == dev) {
		dst_release(dst);
		dev->stats.collisions++;
		goto tx_error;
	}

	mtu = dst_mtu(dst);
	if (skb->len > mtu) {
		skb_dst_update_pmtu(skb, mtu);
		if (skb->protocol == htons(ETH_P_IP)) {
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));
		} else {
			if (mtu < IPV6_MIN_MTU)
				mtu = IPV6_MIN_MTU;

			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		}

		dst_release(dst);
		goto tx_error;
	}

	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
	skb_dst_set(skb, dst);
	skb->dev = skb_dst(skb)->dev;

	err = dst_output(tunnel->net, skb->sk, skb);
	if (net_xmit_eval(err) == 0)
		err = pkt_len;
	iptunnel_xmit_stats(dev, err);
	return NETDEV_TX_OK;

tx_error_icmp:
	dst_link_failure(skb);
tx_error:
	dev->stats.tx_errors++;
	kfree_skb(skb);
	return NETDEV_TX_OK;
}

/* This function assumes it is being called from dev_queue_xmit()
 * and that skb is filled properly by that function.
 */
static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct flowi fl;

	if (!pskb_inet_may_pull(skb))
		goto tx_err;

	memset(&fl, 0, sizeof(fl));

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		xfrm_decode_session(skb, &fl, AF_INET);
		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
		break;
	case htons(ETH_P_IPV6):
		xfrm_decode_session(skb, &fl, AF_INET6);
		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
		break;
	default:
		goto tx_err;
	}

	/* override mark with tunnel output key */
	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);

	return vti_xmit(skb, dev, &fl);

tx_err:
	dev->stats.tx_errors++;
	kfree_skb(skb);
	return NETDEV_TX_OK;
}

static int vti4_err(struct sk_buff *skb, u32 info)
{
	__be32 spi;
	__u32 mark;
	struct xfrm_state *x;
	struct ip_tunnel *tunnel;
	struct ip_esp_hdr *esph;
	struct ip_auth_hdr *ah ;
	struct ip_comp_hdr *ipch;
	struct net *net = dev_net(skb->dev);
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	int protocol = iph->protocol;
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);

	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
				  iph->daddr, iph->saddr, 0);
	if (!tunnel)
		return -1;

	mark = be32_to_cpu(tunnel->parms.o_key);

	switch (protocol) {
	case IPPROTO_ESP:
		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
		spi = esph->spi;
		break;
	case IPPROTO_AH:
		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
		spi = ah->spi;
		break;
	case IPPROTO_COMP:
		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
		spi = htonl(ntohs(ipch->cpi));
		break;
	default:
		return 0;
	}

	switch (icmp_hdr(skb)->type) {
	case ICMP_DEST_UNREACH:
		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
			return 0;
	case ICMP_REDIRECT:
		break;
	default:
		return 0;
	}

	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
			      spi, protocol, AF_INET);
	if (!x)
		return 0;

	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
		ipv4_update_pmtu(skb, net, info, 0, protocol);
	else
		ipv4_redirect(skb, net, 0, protocol);
	xfrm_state_put(x);

	return 0;
}

static int
vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip_tunnel_parm p;

	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)
			return -EINVAL;
	}

	if (!(p.i_flags & GRE_KEY))
		p.i_key = 0;
	if (!(p.o_flags & GRE_KEY))
		p.o_key = 0;

	p.i_flags = VTI_ISVTI;

	err = ip_tunnel_ioctl(dev, &p, cmd);
	if (err)
		return err;

	if (cmd != SIOCDELTUNNEL) {
		p.i_flags |= GRE_KEY;
		p.o_flags |= GRE_KEY;
	}

	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
		return -EFAULT;
	return 0;
}

static const struct net_device_ops vti_netdev_ops = {
	.ndo_init	= vti_tunnel_init,
	.ndo_uninit	= ip_tunnel_uninit,
	.ndo_start_xmit	= vti_tunnel_xmit,
	.ndo_do_ioctl	= vti_tunnel_ioctl,
	.ndo_change_mtu	= ip_tunnel_change_mtu,
	.ndo_get_stats64 = ip_tunnel_get_stats64,
	.ndo_get_iflink = ip_tunnel_get_iflink,
};

static void vti_tunnel_setup(struct net_device *dev)
{
	dev->netdev_ops		= &vti_netdev_ops;
	dev->type		= ARPHRD_TUNNEL;
	ip_tunnel_setup(dev, vti_net_id);
}

static int vti_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	memcpy(dev->dev_addr, &iph->saddr, 4);
	memcpy(dev->broadcast, &iph->daddr, 4);

	dev->flags		= IFF_NOARP;
	dev->addr_len		= 4;
	dev->features		|= NETIF_F_LLTX;
	netif_keep_dst(dev);

	return ip_tunnel_init(dev);
}

static void __net_init vti_fb_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	iph->version		= 4;
	iph->protocol		= IPPROTO_IPIP;
	iph->ihl		= 5;
}

static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
	.handler	=	vti_rcv,
	.input_handler	=	vti_input,
	.cb_handler	=	vti_rcv_cb,
	.err_handler	=	vti4_err,
	.priority	=	100,
};

static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
	.handler	=	vti_rcv,
	.input_handler	=	vti_input,
	.cb_handler	=	vti_rcv_cb,
	.err_handler	=	vti4_err,
	.priority	=	100,
};

static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
	.handler	=	vti_rcv,
	.input_handler	=	vti_input,
	.cb_handler	=	vti_rcv_cb,
	.err_handler	=	vti4_err,
	.priority	=	100,
};

static struct xfrm_tunnel ipip_handler __read_mostly = {
	.handler	=	vti_rcv_ipip,
	.err_handler	=	vti4_err,
	.priority	=	0,
};

static int __net_init vti_init_net(struct net *net)
{
	int err;
	struct ip_tunnel_net *itn;

	err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
	if (err)
		return err;
	itn = net_generic(net, vti_net_id);
	if (itn->fb_tunnel_dev)
		vti_fb_tunnel_init(itn->fb_tunnel_dev);
	return 0;
}

static void __net_exit vti_exit_batch_net(struct list_head *list_net)
{
	ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
}

static struct pernet_operations vti_net_ops = {
	.init = vti_init_net,
	.exit_batch = vti_exit_batch_net,
	.id   = &vti_net_id,
	.size = sizeof(struct ip_tunnel_net),
};

static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
			       struct netlink_ext_ack *extack)
{
	return 0;
}

static void vti_netlink_parms(struct nlattr *data[],
			      struct ip_tunnel_parm *parms,
			      __u32 *fwmark)
{
	memset(parms, 0, sizeof(*parms));

	parms->iph.protocol = IPPROTO_IPIP;

	if (!data)
		return;

	parms->i_flags = VTI_ISVTI;

	if (data[IFLA_VTI_LINK])
		parms->link = nla_get_u32(data[IFLA_VTI_LINK]);

	if (data[IFLA_VTI_IKEY])
		parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);

	if (data[IFLA_VTI_OKEY])
		parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);

	if (data[IFLA_VTI_LOCAL])
		parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]);

	if (data[IFLA_VTI_REMOTE])
		parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);

	if (data[IFLA_VTI_FWMARK])
		*fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
}

static int vti_newlink(struct net *src_net, struct net_device *dev,
		       struct nlattr *tb[], struct nlattr *data[],
		       struct netlink_ext_ack *extack)
{
	struct ip_tunnel_parm parms;
	__u32 fwmark = 0;

	vti_netlink_parms(data, &parms, &fwmark);
	return ip_tunnel_newlink(dev, tb, &parms, fwmark);
}

static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
			  struct nlattr *data[],
			  struct netlink_ext_ack *extack)
{
	struct ip_tunnel *t = netdev_priv(dev);
	__u32 fwmark = t->fwmark;
	struct ip_tunnel_parm p;

	vti_netlink_parms(data, &p, &fwmark);
	return ip_tunnel_changelink(dev, tb, &p, fwmark);
}

static size_t vti_get_size(const struct net_device *dev)
{
	return
		/* IFLA_VTI_LINK */
		nla_total_size(4) +
		/* IFLA_VTI_IKEY */
		nla_total_size(4) +
		/* IFLA_VTI_OKEY */
		nla_total_size(4) +
		/* IFLA_VTI_LOCAL */
		nla_total_size(4) +
		/* IFLA_VTI_REMOTE */
		nla_total_size(4) +
		/* IFLA_VTI_FWMARK */
		nla_total_size(4) +
		0;
}

static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);
	struct ip_tunnel_parm *p = &t->parms;

	if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) ||
	    nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) ||
	    nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) ||
	    nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) ||
	    nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) ||
	    nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark))
		return -EMSGSIZE;

	return 0;
}

static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
	[IFLA_VTI_LINK]		= { .type = NLA_U32 },
	[IFLA_VTI_IKEY]		= { .type = NLA_U32 },
	[IFLA_VTI_OKEY]		= { .type = NLA_U32 },
	[IFLA_VTI_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
	[IFLA_VTI_REMOTE]	= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
	[IFLA_VTI_FWMARK]	= { .type = NLA_U32 },
};

static struct rtnl_link_ops vti_link_ops __read_mostly = {
	.kind		= "vti",
	.maxtype	= IFLA_VTI_MAX,
	.policy		= vti_policy,
	.priv_size	= sizeof(struct ip_tunnel),
	.setup		= vti_tunnel_setup,
	.validate	= vti_tunnel_validate,
	.newlink	= vti_newlink,
	.changelink	= vti_changelink,
	.dellink        = ip_tunnel_dellink,
	.get_size	= vti_get_size,
	.fill_info	= vti_fill_info,
	.get_link_net	= ip_tunnel_get_link_net,
};

static int __init vti_init(void)
{
	const char *msg;
	int err;

	pr_info("IPv4 over IPsec tunneling driver\n");

	msg = "tunnel device";
	err = register_pernet_device(&vti_net_ops);
	if (err < 0)
		goto pernet_dev_failed;

	msg = "tunnel protocols";
	err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
	if (err < 0)
		goto xfrm_proto_esp_failed;
	err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
	if (err < 0)
		goto xfrm_proto_ah_failed;
	err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
	if (err < 0)
		goto xfrm_proto_comp_failed;

	msg = "ipip tunnel";
	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
	if (err < 0) {
		pr_info("%s: cant't register tunnel\n",__func__);
		goto xfrm_tunnel_failed;
	}

	msg = "netlink interface";
	err = rtnl_link_register(&vti_link_ops);
	if (err < 0)
		goto rtnl_link_failed;

	return err;

rtnl_link_failed:
	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm_tunnel_failed:
	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
xfrm_proto_esp_failed:
	unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
	pr_err("vti init: failed to register %s\n", msg);
	return err;
}

static void __exit vti_fini(void)
{
	rtnl_link_unregister(&vti_link_ops);
	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
	unregister_pernet_device(&vti_net_ops);
}

module_init(vti_init);
module_exit(vti_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");
Commit	Line	Data
1181412c S	1	/*
	2	* Linux NET3: IP/IP protocol decoder modified to support
	3	* virtual tunnel interface
	4	*
	5	* Authors:
	6	* Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012
	7	*
	8	* This program is free software; you can redistribute it and/or
	9	* modify it under the terms of the GNU General Public License
	10	* as published by the Free Software Foundation; either version
	11	* 2 of the License, or (at your option) any later version.
	12	*
	13	*/
	14
	15	/*
	16	This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c
	17
	18	For comments look at net/ipv4/ip_gre.c --ANK
	19	*/
	20
	21
	22	#include <linux/capability.h>
	23	#include <linux/module.h>
	24	#include <linux/types.h>
	25	#include <linux/kernel.h>
	26	#include <linux/uaccess.h>
	27	#include <linux/skbuff.h>
	28	#include <linux/netdevice.h>
	29	#include <linux/in.h>
	30	#include <linux/tcp.h>
	31	#include <linux/udp.h>
	32	#include <linux/if_arp.h>
1181412c S	33	#include <linux/init.h>
	34	#include <linux/netfilter_ipv4.h>
	35	#include <linux/if_ether.h>
78a010cc	36	#include <linux/icmpv6.h>
1181412c S	37
	38	#include <net/sock.h>
	39	#include <net/ip.h>
	40	#include <net/icmp.h>
c5441932	41	#include <net/ip_tunnels.h>
1181412c S	42	#include <net/inet_ecn.h>
	43	#include <net/xfrm.h>
	44	#include <net/net_namespace.h>
	45	#include <net/netns/generic.h>
	46
1181412c S	47	static struct rtnl_link_ops vti_link_ops __read_mostly;
1181412c S	48
c7d03a00	49	static unsigned int vti_net_id __read_mostly;
1181412c	50	static int vti_tunnel_init(struct net_device *dev);
1181412c	51
df3893c1 SK	52	static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
df3893c1 SK	53	int encap_type)
1181412c S	54	{
	55	struct ip_tunnel *tunnel;
	56	const struct iphdr *iph = ip_hdr(skb);
b9959fd3 AW	57	struct net *net = dev_net(skb->dev);
b9959fd3 AW	58	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
1181412c	59
b9959fd3 AW	60	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
b9959fd3 AW	61	iph->saddr, iph->daddr, 0);
00db4124	62	if (tunnel) {
df3893c1 SK	63	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
	64	goto drop;
	65
	66	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
df3893c1 SK	67
	68	return xfrm_input(skb, nexthdr, spi, encap_type);
	69	}
	70
	71	return -EINVAL;
	72	drop:
	73	kfree_skb(skb);
	74	return 0;
	75	}
	76
dd9ee344 SY	77	static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
	78	int encap_type)
	79	{
	80	struct ip_tunnel *tunnel;
	81	const struct iphdr *iph = ip_hdr(skb);
	82	struct net *net = dev_net(skb->dev);
	83	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
	84
	85	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
	86	iph->saddr, iph->daddr, 0);
	87	if (tunnel) {
	88	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
	89	goto drop;
	90
	91	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
	92
	93	skb->dev = tunnel->dev;
	94
	95	return xfrm_input(skb, nexthdr, spi, encap_type);
	96	}
	97
	98	return -EINVAL;
	99	drop:
	100	kfree_skb(skb);
	101	return 0;
	102	}
	103
df3893c1 SK	104	static int vti_rcv(struct sk_buff *skb)
	105	{
	106	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
	107	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
	108
	109	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
	110	}
	111
dd9ee344 SY	112	static int vti_rcv_ipip(struct sk_buff *skb)
	113	{
	114	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
	115	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
	116
	117	return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
	118	}
	119
df3893c1 SK	120	static int vti_rcv_cb(struct sk_buff *skb, int err)
	121	{
	122	unsigned short family;
	123	struct net_device *dev;
	124	struct pcpu_sw_netstats *tstats;
	125	struct xfrm_state *x;
1fb81e09	126	struct xfrm_mode *inner_mode;
df3893c1	127	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
d55c670c AD	128	u32 orig_mark = skb->mark;
d55c670c AD	129	int ret;
df3893c1 SK	130
df3893c1 SK	131	if (!tunnel)
1181412c	132	return 1;
df3893c1 SK	133
	134	dev = tunnel->dev;
	135
	136	if (err) {
	137	dev->stats.rx_errors++;
	138	dev->stats.rx_dropped++;
	139
	140	return 0;
1181412c	141	}
1181412c	142
df3893c1	143	x = xfrm_input_state(skb);
1fb81e09	144
	145	inner_mode = x->inner_mode;
	146
	147	if (x->sel.family == AF_UNSPEC) {
	148	inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
	149	if (inner_mode == NULL) {
	150	XFRM_INC_STATS(dev_net(skb->dev),
	151	LINUX_MIB_XFRMINSTATEMODEERROR);
	152	return -EINVAL;
	153	}
	154	}
	155
	156	family = inner_mode->afinfo->family;
df3893c1	157
d55c670c AD	158	skb->mark = be32_to_cpu(tunnel->parms.i_key);
	159	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
	160	skb->mark = orig_mark;
	161
	162	if (!ret)
df3893c1 SK	163	return -EPERM;
	164
	165	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
	166	skb->dev = dev;
	167
	168	tstats = this_cpu_ptr(dev->tstats);
	169
	170	u64_stats_update_begin(&tstats->syncp);
	171	tstats->rx_packets++;
	172	tstats->rx_bytes += skb->len;
	173	u64_stats_update_end(&tstats->syncp);
	174
	175	return 0;
1181412c S	176	}
1181412c S	177
6e2de802 SK	178	static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
	179	{
	180	xfrm_address_t daddr = (xfrm_address_t )&dst;
	181	xfrm_address_t saddr = (xfrm_address_t )&src;
	182
	183	/* if there is no transform then this tunnel is not functional.
	184	* Or if the xfrm is not mode tunnel.
	185	*/
	186	if (!x \|\| x->props.mode != XFRM_MODE_TUNNEL \|\|
	187	x->props.family != AF_INET)
	188	return false;
	189
	190	if (!dst)
	191	return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
	192
	193	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
	194	return false;
	195
	196	return true;
	197	}
	198
78a010cc SK	199	static netdev_tx_t vti_xmit(struct sk_buff skb, struct net_device dev,
78a010cc SK	200	struct flowi *fl)
1181412c S	201	{
1181412c S	202	struct ip_tunnel *tunnel = netdev_priv(dev);
6e2de802	203	struct ip_tunnel_parm *parms = &tunnel->parms;
a34cd4f3	204	struct dst_entry *dst = skb_dst(skb);
1181412c	205	struct net_device tdev; / Device to other host */
36f6ee22	206	int pkt_len = skb->len;
b9959fd3	207	int err;
d6af1a31	208	int mtu;
1181412c	209
a34cd4f3	210	if (!dst) {
df3893c1 SK	211	dev->stats.tx_carrier_errors++;
	212	goto tx_error_icmp;
	213	}
1181412c	214
a34cd4f3	215	dst_hold(dst);
78a010cc	216	dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
a34cd4f3	217	if (IS_ERR(dst)) {
1181412c S	218	dev->stats.tx_carrier_errors++;
	219	goto tx_error_icmp;
	220	}
df3893c1	221
6e2de802	222	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
1181412c	223	dev->stats.tx_carrier_errors++;
a34cd4f3	224	dst_release(dst);
1181412c S	225	goto tx_error_icmp;
1181412c S	226	}
6e2de802	227
a34cd4f3	228	tdev = dst->dev;
1181412c S	229
1181412c S	230	if (tdev == dev) {
a34cd4f3	231	dst_release(dst);
1181412c S	232	dev->stats.collisions++;
	233	goto tx_error;
	234	}
	235
d6af1a31 SK	236	mtu = dst_mtu(dst);
d6af1a31 SK	237	if (skb->len > mtu) {
f15ca723	238	skb_dst_update_pmtu(skb, mtu);
d6af1a31 SK	239	if (skb->protocol == htons(ETH_P_IP)) {
	240	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
	241	htonl(mtu));
	242	} else {
	243	if (mtu < IPV6_MIN_MTU)
	244	mtu = IPV6_MIN_MTU;
	245
	246	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
	247	}
	248
	249	dst_release(dst);
	250	goto tx_error;
	251	}
	252
df3893c1	253	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
a34cd4f3	254	skb_dst_set(skb, dst);
1181412c S	255	skb->dev = skb_dst(skb)->dev;
1181412c S	256
13206b6b	257	err = dst_output(tunnel->net, skb->sk, skb);
b9959fd3	258	if (net_xmit_eval(err) == 0)
36f6ee22	259	err = pkt_len;
039f5062	260	iptunnel_xmit_stats(dev, err);
1181412c S	261	return NETDEV_TX_OK;
	262
	263	tx_error_icmp:
	264	dst_link_failure(skb);
	265	tx_error:
	266	dev->stats.tx_errors++;
3acfa1e7	267	kfree_skb(skb);
1181412c S	268	return NETDEV_TX_OK;
	269	}
	270
78a010cc SK	271	/* This function assumes it is being called from dev_queue_xmit()
	272	* and that skb is filled properly by that function.
	273	*/
	274	static netdev_tx_t vti_tunnel_xmit(struct sk_buff skb, struct net_device dev)
	275	{
	276	struct ip_tunnel *tunnel = netdev_priv(dev);
	277	struct flowi fl;
	278
cb9f1b78 WB	279	if (!pskb_inet_may_pull(skb))
	280	goto tx_err;
	281
78a010cc SK	282	memset(&fl, 0, sizeof(fl));
78a010cc SK	283
78a010cc SK	284	switch (skb->protocol) {
	285	case htons(ETH_P_IP):
	286	xfrm_decode_session(skb, &fl, AF_INET);
	287	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
	288	break;
	289	case htons(ETH_P_IPV6):
	290	xfrm_decode_session(skb, &fl, AF_INET6);
	291	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
	292	break;
	293	default:
cb9f1b78	294	goto tx_err;
78a010cc SK	295	}
78a010cc SK	296
cd5279c1 AD	297	/* override mark with tunnel output key */
	298	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
	299
78a010cc	300	return vti_xmit(skb, dev, &fl);
cb9f1b78 WB	301
	302	tx_err:
	303	dev->stats.tx_errors++;
	304	kfree_skb(skb);
	305	return NETDEV_TX_OK;
78a010cc SK	306	}
78a010cc SK	307
df3893c1 SK	308	static int vti4_err(struct sk_buff *skb, u32 info)
	309	{
	310	__be32 spi;
6d004d6c	311	__u32 mark;
df3893c1 SK	312	struct xfrm_state *x;
	313	struct ip_tunnel *tunnel;
	314	struct ip_esp_hdr *esph;
	315	struct ip_auth_hdr *ah ;
	316	struct ip_comp_hdr *ipch;
	317	struct net *net = dev_net(skb->dev);
	318	const struct iphdr iph = (const struct iphdr )skb->data;
	319	int protocol = iph->protocol;
	320	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
	321
	322	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
	323	iph->daddr, iph->saddr, 0);
	324	if (!tunnel)
	325	return -1;
	326
6d004d6c SK	327	mark = be32_to_cpu(tunnel->parms.o_key);
6d004d6c SK	328
df3893c1 SK	329	switch (protocol) {
	330	case IPPROTO_ESP:
	331	esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
	332	spi = esph->spi;
	333	break;
	334	case IPPROTO_AH:
	335	ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
	336	spi = ah->spi;
	337	break;
	338	case IPPROTO_COMP:
	339	ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
	340	spi = htonl(ntohs(ipch->cpi));
	341	break;
	342	default:
	343	return 0;
	344	}
	345
	346	switch (icmp_hdr(skb)->type) {
	347	case ICMP_DEST_UNREACH:
	348	if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
	349	return 0;
	350	case ICMP_REDIRECT:
	351	break;
	352	default:
	353	return 0;
	354	}
	355
6d004d6c	356	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
df3893c1 SK	357	spi, protocol, AF_INET);
	358	if (!x)
	359	return 0;
	360
	361	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
d888f396	362	ipv4_update_pmtu(skb, net, info, 0, protocol);
df3893c1	363	else
1042caa7	364	ipv4_redirect(skb, net, 0, protocol);
df3893c1 SK	365	xfrm_state_put(x);
	366
	367	return 0;
	368	}
	369
1181412c S	370	static int
	371	vti_tunnel_ioctl(struct net_device dev, struct ifreq ifr, int cmd)
	372	{
	373	int err = 0;
	374	struct ip_tunnel_parm p;
1181412c	375
b9959fd3 AW	376	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
b9959fd3 AW	377	return -EFAULT;
1181412c	378
b9959fd3	379	if (cmd == SIOCADDTUNNEL \|\| cmd == SIOCCHGTUNNEL) {
1181412c S	380	if (p.iph.version != 4 \|\| p.iph.protocol != IPPROTO_IPIP \|\|
1181412c S	381	p.iph.ihl != 5)
b9959fd3 AW	382	return -EINVAL;
b9959fd3 AW	383	}
1181412c	384
7c8e6b9c DP	385	if (!(p.i_flags & GRE_KEY))
	386	p.i_key = 0;
	387	if (!(p.o_flags & GRE_KEY))
	388	p.o_key = 0;
	389
	390	p.i_flags = VTI_ISVTI;
	391
b9959fd3 AW	392	err = ip_tunnel_ioctl(dev, &p, cmd);
	393	if (err)
	394	return err;
1181412c	395
b9959fd3	396	if (cmd != SIOCDELTUNNEL) {
df3893c1	397	p.i_flags \|= GRE_KEY;
b9959fd3	398	p.o_flags \|= GRE_KEY;
1181412c S	399	}
1181412c S	400
b9959fd3 AW	401	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
b9959fd3 AW	402	return -EFAULT;
1181412c S	403	return 0;
	404	}
	405
	406	static const struct net_device_ops vti_netdev_ops = {
	407	.ndo_init = vti_tunnel_init,
b9959fd3	408	.ndo_uninit = ip_tunnel_uninit,
1181412c S	409	.ndo_start_xmit = vti_tunnel_xmit,
1181412c S	410	.ndo_do_ioctl = vti_tunnel_ioctl,
b9959fd3	411	.ndo_change_mtu = ip_tunnel_change_mtu,
f61dd388	412	.ndo_get_stats64 = ip_tunnel_get_stats64,
1e99584b	413	.ndo_get_iflink = ip_tunnel_get_iflink,
1181412c S	414	};
1181412c S	415
b9959fd3	416	static void vti_tunnel_setup(struct net_device *dev)
1181412c	417	{
b9959fd3	418	dev->netdev_ops = &vti_netdev_ops;
8d89dcdf	419	dev->type = ARPHRD_TUNNEL;
b9959fd3	420	ip_tunnel_setup(dev, vti_net_id);
1181412c S	421	}
1181412c S	422
b9959fd3	423	static int vti_tunnel_init(struct net_device *dev)
1181412c	424	{
b9959fd3 AW	425	struct ip_tunnel *tunnel = netdev_priv(dev);
	426	struct iphdr *iph = &tunnel->parms.iph;
	427
	428	memcpy(dev->dev_addr, &iph->saddr, 4);
	429	memcpy(dev->broadcast, &iph->daddr, 4);
1181412c	430
1181412c	431	dev->flags = IFF_NOARP;
1181412c	432	dev->addr_len = 4;
1181412c	433	dev->features \|= NETIF_F_LLTX;
02875878	434	netif_keep_dst(dev);
1181412c	435
b9959fd3	436	return ip_tunnel_init(dev);
1181412c S	437	}
1181412c S	438
b9959fd3	439	static void __net_init vti_fb_tunnel_init(struct net_device *dev)
1181412c S	440	{
	441	struct ip_tunnel *tunnel = netdev_priv(dev);
	442	struct iphdr *iph = &tunnel->parms.iph;
1181412c	443
1181412c S	444	iph->version = 4;
	445	iph->protocol = IPPROTO_IPIP;
	446	iph->ihl = 5;
1181412c S	447	}
1181412c S	448
df3893c1	449	static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
1181412c	450	.handler = vti_rcv,
df3893c1 SK	451	.input_handler = vti_input,
	452	.cb_handler = vti_rcv_cb,
	453	.err_handler = vti4_err,
	454	.priority = 100,
	455	};
	456
	457	static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
	458	.handler = vti_rcv,
	459	.input_handler = vti_input,
	460	.cb_handler = vti_rcv_cb,
	461	.err_handler = vti4_err,
	462	.priority = 100,
	463	};
	464
	465	static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
	466	.handler = vti_rcv,
	467	.input_handler = vti_input,
	468	.cb_handler = vti_rcv_cb,
	469	.err_handler = vti4_err,
	470	.priority = 100,
1181412c S	471	};
1181412c S	472
dd9ee344 SY	473	static struct xfrm_tunnel ipip_handler __read_mostly = {
	474	.handler = vti_rcv_ipip,
	475	.err_handler = vti4_err,
	476	.priority = 0,
	477	};
	478
1181412c S	479	static int __net_init vti_init_net(struct net *net)
	480	{
	481	int err;
b9959fd3	482	struct ip_tunnel_net *itn;
1181412c	483
b9959fd3	484	err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
1181412c	485	if (err)
b9959fd3 AW	486	return err;
b9959fd3 AW	487	itn = net_generic(net, vti_net_id);
cd1aa9c2 HY	488	if (itn->fb_tunnel_dev)
cd1aa9c2 HY	489	vti_fb_tunnel_init(itn->fb_tunnel_dev);
1181412c	490	return 0;
1181412c S	491	}
1181412c S	492
64bc1781	493	static void __net_exit vti_exit_batch_net(struct list_head *list_net)
1181412c	494	{
64bc1781	495	ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
1181412c S	496	}
	497
	498	static struct pernet_operations vti_net_ops = {
	499	.init = vti_init_net,
64bc1781	500	.exit_batch = vti_exit_batch_net,
1181412c	501	.id = &vti_net_id,
b9959fd3	502	.size = sizeof(struct ip_tunnel_net),
1181412c S	503	};
1181412c S	504
a8b8a889 MS	505	static int vti_tunnel_validate(struct nlattr tb[], struct nlattr data[],
a8b8a889 MS	506	struct netlink_ext_ack *extack)
1181412c S	507	{
	508	return 0;
	509	}
	510
	511	static void vti_netlink_parms(struct nlattr *data[],
9830ad4c CG	512	struct ip_tunnel_parm *parms,
9830ad4c CG	513	__u32 *fwmark)
1181412c S	514	{
	515	memset(parms, 0, sizeof(*parms));
	516
	517	parms->iph.protocol = IPPROTO_IPIP;
	518
	519	if (!data)
	520	return;
	521
df3893c1 SK	522	parms->i_flags = VTI_ISVTI;
df3893c1 SK	523
1181412c S	524	if (data[IFLA_VTI_LINK])
	525	parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
	526
	527	if (data[IFLA_VTI_IKEY])
	528	parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);
	529
	530	if (data[IFLA_VTI_OKEY])
	531	parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
	532
	533	if (data[IFLA_VTI_LOCAL])
67b61f6c	534	parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]);
1181412c S	535
1181412c S	536	if (data[IFLA_VTI_REMOTE])
67b61f6c	537	parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);
1181412c	538
9830ad4c CG	539	if (data[IFLA_VTI_FWMARK])
9830ad4c CG	540	*fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
1181412c S	541	}
	542
	543	static int vti_newlink(struct net src_net, struct net_device dev,
7a3f4a18 MS	544	struct nlattr tb[], struct nlattr data[],
7a3f4a18 MS	545	struct netlink_ext_ack *extack)
1181412c	546	{
b9959fd3	547	struct ip_tunnel_parm parms;
9830ad4c	548	__u32 fwmark = 0;
1181412c	549
9830ad4c CG	550	vti_netlink_parms(data, &parms, &fwmark);
9830ad4c CG	551	return ip_tunnel_newlink(dev, tb, &parms, fwmark);
1181412c S	552	}
	553
	554	static int vti_changelink(struct net_device dev, struct nlattr tb[],
ad744b22 MS	555	struct nlattr *data[],
ad744b22 MS	556	struct netlink_ext_ack *extack)
1181412c	557	{
9830ad4c CG	558	struct ip_tunnel *t = netdev_priv(dev);
9830ad4c CG	559	__u32 fwmark = t->fwmark;
1181412c	560	struct ip_tunnel_parm p;
1181412c	561
9830ad4c CG	562	vti_netlink_parms(data, &p, &fwmark);
9830ad4c CG	563	return ip_tunnel_changelink(dev, tb, &p, fwmark);
1181412c S	564	}
	565
	566	static size_t vti_get_size(const struct net_device *dev)
	567	{
	568	return
	569	/* IFLA_VTI_LINK */
	570	nla_total_size(4) +
	571	/* IFLA_VTI_IKEY */
	572	nla_total_size(4) +
	573	/* IFLA_VTI_OKEY */
	574	nla_total_size(4) +
	575	/* IFLA_VTI_LOCAL */
	576	nla_total_size(4) +
	577	/* IFLA_VTI_REMOTE */
	578	nla_total_size(4) +
9830ad4c CG	579	/* IFLA_VTI_FWMARK */
9830ad4c CG	580	nla_total_size(4) +
1181412c S	581	0;
	582	}
	583
	584	static int vti_fill_info(struct sk_buff skb, const struct net_device dev)
	585	{
	586	struct ip_tunnel *t = netdev_priv(dev);
	587	struct ip_tunnel_parm *p = &t->parms;
	588
8ed508fd HL	589	if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) \|\|
	590	nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) \|\|
	591	nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) \|\|
	592	nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) \|\|
	593	nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) \|\|
	594	nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark))
	595	return -EMSGSIZE;
1181412c S	596
	597	return 0;
	598	}
	599
	600	static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
	601	[IFLA_VTI_LINK] = { .type = NLA_U32 },
	602	[IFLA_VTI_IKEY] = { .type = NLA_U32 },
	603	[IFLA_VTI_OKEY] = { .type = NLA_U32 },
	604	[IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
	605	[IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
9830ad4c	606	[IFLA_VTI_FWMARK] = { .type = NLA_U32 },
1181412c S	607	};
	608
	609	static struct rtnl_link_ops vti_link_ops __read_mostly = {
	610	.kind = "vti",
	611	.maxtype = IFLA_VTI_MAX,
	612	.policy = vti_policy,
	613	.priv_size = sizeof(struct ip_tunnel),
	614	.setup = vti_tunnel_setup,
	615	.validate = vti_tunnel_validate,
	616	.newlink = vti_newlink,
	617	.changelink = vti_changelink,
20ea60ca	618	.dellink = ip_tunnel_dellink,
1181412c S	619	.get_size = vti_get_size,
1181412c S	620	.fill_info = vti_fill_info,
1728d4fa	621	.get_link_net = ip_tunnel_get_link_net,
1181412c S	622	};
	623
	624	static int __init vti_init(void)
	625	{
1990e4f8	626	const char *msg;
1181412c S	627	int err;
1181412c S	628
1990e4f8	629	pr_info("IPv4 over IPsec tunneling driver\n");
1181412c	630
1990e4f8	631	msg = "tunnel device";
1181412c S	632	err = register_pernet_device(&vti_net_ops);
1181412c S	633	if (err < 0)
1990e4f8	634	goto pernet_dev_failed;
df3893c1	635
1990e4f8 MK	636	msg = "tunnel protocols";
	637	err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
	638	if (err < 0)
	639	goto xfrm_proto_esp_failed;
df3893c1	640	err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
1990e4f8 MK	641	if (err < 0)
1990e4f8 MK	642	goto xfrm_proto_ah_failed;
df3893c1	643	err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
1990e4f8 MK	644	if (err < 0)
1990e4f8 MK	645	goto xfrm_proto_comp_failed;
1181412c	646
dd9ee344 SY	647	msg = "ipip tunnel";
	648	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
	649	if (err < 0) {
	650	pr_info("%s: cant't register tunnel\n",__func__);
	651	goto xfrm_tunnel_failed;
	652	}
	653
1990e4f8	654	msg = "netlink interface";
1181412c S	655	err = rtnl_link_register(&vti_link_ops);
	656	if (err < 0)
	657	goto rtnl_link_failed;
	658
	659	return err;
	660
	661	rtnl_link_failed:
df3893c1	662	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
dd9ee344 SY	663	xfrm_tunnel_failed:
dd9ee344 SY	664	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
1990e4f8	665	xfrm_proto_comp_failed:
df3893c1	666	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
1990e4f8	667	xfrm_proto_ah_failed:
df3893c1	668	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
1990e4f8	669	xfrm_proto_esp_failed:
1181412c	670	unregister_pernet_device(&vti_net_ops);
1990e4f8 MK	671	pernet_dev_failed:
1990e4f8 MK	672	pr_err("vti init: failed to register %s\n", msg);
1181412c S	673	return err;
	674	}
	675
	676	static void __exit vti_fini(void)
	677	{
	678	rtnl_link_unregister(&vti_link_ops);
1990e4f8 MK	679	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
	680	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
	681	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
1181412c S	682	unregister_pernet_device(&vti_net_ops);
	683	}
	684
	685	module_init(vti_init);
	686	module_exit(vti_fini);
	687	MODULE_LICENSE("GPL");
	688	MODULE_ALIAS_RTNL_LINK("vti");
	689	MODULE_ALIAS_NETDEV("ip_vti0");