ip6_vti.c 27.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52
/*
 *	IPv6 virtual tunneling interface
 *
 *	Copyright (C) 2013 secunet Security Networks AG
 *
 *	Author:
 *	Steffen Klassert <steffen.klassert@secunet.com>
 *
 *	Based on:
 *	net/ipv6/ip6_tunnel.c
 *
 *	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.
 */

#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.h>
#include <linux/slab.h>
#include <linux/hash.h>

#include <linux/uaccess.h>
#include <linux/atomic.h>

#include <net/icmp.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

53 54
#define IP6_VTI_HASH_SIZE_SHIFT  5
#define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT)
55 56 57 58 59

static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2)
{
	u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2);

60
	return hash_32(hash, IP6_VTI_HASH_SIZE_SHIFT);
61 62 63 64 65 66 67 68 69 70 71
}

static int vti6_dev_init(struct net_device *dev);
static void vti6_dev_setup(struct net_device *dev);
static struct rtnl_link_ops vti6_link_ops __read_mostly;

static int vti6_net_id __read_mostly;
struct vti6_net {
	/* the vti6 tunnel fallback device */
	struct net_device *fb_tnl_dev;
	/* lists for storing tunnels in use */
72
	struct ip6_tnl __rcu *tnls_r_l[IP6_VTI_HASH_SIZE];
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97
	struct ip6_tnl __rcu *tnls_wc[1];
	struct ip6_tnl __rcu **tnls[2];
};

#define for_each_vti6_tunnel_rcu(start) \
	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))

/**
 * vti6_tnl_lookup - fetch tunnel matching the end-point addresses
 *   @net: network namespace
 *   @remote: the address of the tunnel exit-point
 *   @local: the address of the tunnel entry-point
 *
 * Return:
 *   tunnel matching given end-points if found,
 *   else fallback tunnel if its device is up,
 *   else %NULL
 **/
static struct ip6_tnl *
vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
		const struct in6_addr *local)
{
	unsigned int hash = HASH(remote, local);
	struct ip6_tnl *t;
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
98
	struct in6_addr any;
99 100 101 102 103 104 105

	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    ipv6_addr_equal(remote, &t->parms.raddr) &&
		    (t->dev->flags & IFF_UP))
			return t;
	}
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121

	memset(&any, 0, sizeof(any));
	hash = HASH(&any, local);
	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    (t->dev->flags & IFF_UP))
			return t;
	}

	hash = HASH(remote, &any);
	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
		    (t->dev->flags & IFF_UP))
			return t;
	}

122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
	t = rcu_dereference(ip6n->tnls_wc[0]);
	if (t && (t->dev->flags & IFF_UP))
		return t;

	return NULL;
}

/**
 * vti6_tnl_bucket - get head of list matching given tunnel parameters
 *   @p: parameters containing tunnel end-points
 *
 * Description:
 *   vti6_tnl_bucket() returns the head of the list matching the
 *   &struct in6_addr entries laddr and raddr in @p.
 *
 * Return: head of IPv6 tunnel list
 **/
static struct ip6_tnl __rcu **
vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p)
{
	const struct in6_addr *remote = &p->raddr;
	const struct in6_addr *local = &p->laddr;
	unsigned int h = 0;
	int prio = 0;

	if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
		prio = 1;
		h = HASH(remote, local);
	}
	return &ip6n->tnls[prio][h];
}

static void
vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t)
{
	struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms);

	rcu_assign_pointer(t->next , rtnl_dereference(*tp));
	rcu_assign_pointer(*tp, t);
}

static void
vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
{
	struct ip6_tnl __rcu **tp;
	struct ip6_tnl *iter;

	for (tp = vti6_tnl_bucket(ip6n, &t->parms);
	     (iter = rtnl_dereference(*tp)) != NULL;
	     tp = &iter->next) {
		if (t == iter) {
			rcu_assign_pointer(*tp, t->next);
			break;
		}
	}
}

static void vti6_dev_free(struct net_device *dev)
{
	free_percpu(dev->tstats);
	free_netdev(dev);
}

static int vti6_tnl_create2(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net *net = dev_net(dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
	int err;

	err = register_netdevice(dev);
	if (err < 0)
		goto out;

	strcpy(t->parms.name, dev->name);
	dev->rtnl_link_ops = &vti6_link_ops;

	dev_hold(dev);
	vti6_tnl_link(ip6n, t);

	return 0;

out:
	return err;
}

static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
{
	struct net_device *dev;
	struct ip6_tnl *t;
	char name[IFNAMSIZ];
	int err;

	if (p->name[0])
		strlcpy(name, p->name, IFNAMSIZ);
	else
		sprintf(name, "ip6_vti%%d");

220
	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
221
	if (!dev)
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
		goto failed;

	dev_net_set(dev, net);

	t = netdev_priv(dev);
	t->parms = *p;
	t->net = dev_net(dev);

	err = vti6_tnl_create2(dev);
	if (err < 0)
		goto failed_free;

	return t;

failed_free:
	vti6_dev_free(dev);
failed:
	return NULL;
}

/**
 * vti6_locate - find or create tunnel matching given parameters
 *   @net: network namespace
 *   @p: tunnel parameters
 *   @create: != 0 if allowed to create new tunnel if no match found
 *
 * Description:
 *   vti6_locate() first tries to locate an existing tunnel
 *   based on @parms. If this is unsuccessful, but @create is set a new
 *   tunnel device is created and registered for use.
 *
 * Return:
 *   matching tunnel or NULL
 **/
static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
				   int create)
{
	const struct in6_addr *remote = &p->raddr;
	const struct in6_addr *local = &p->laddr;
	struct ip6_tnl __rcu **tp;
	struct ip6_tnl *t;
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	for (tp = vti6_tnl_bucket(ip6n, p);
	     (t = rtnl_dereference(*tp)) != NULL;
	     tp = &t->next) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
269 270 271 272
		    ipv6_addr_equal(remote, &t->parms.raddr)) {
			if (create)
				return NULL;

273
			return t;
274
		}
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
	}
	if (!create)
		return NULL;
	return vti6_tnl_create(net, p);
}

/**
 * vti6_dev_uninit - tunnel device uninitializer
 *   @dev: the device to be destroyed
 *
 * Description:
 *   vti6_dev_uninit() removes tunnel from its list
 **/
static void vti6_dev_uninit(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
Y
Yao Xiwei 已提交
291
	struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
292 293 294 295 296 297 298 299 300 301 302 303 304 305

	if (dev == ip6n->fb_tnl_dev)
		RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
	else
		vti6_tnl_unlink(ip6n, t);
	dev_put(dev);
}

static int vti6_rcv(struct sk_buff *skb)
{
	struct ip6_tnl *t;
	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);

	rcu_read_lock();
306
	t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
307
	if (t) {
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
		if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) {
			rcu_read_unlock();
			goto discard;
		}

		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
			rcu_read_unlock();
			return 0;
		}

		if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) {
			t->dev->stats.rx_dropped++;
			rcu_read_unlock();
			goto discard;
		}

324
		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
325 326

		rcu_read_unlock();
327 328

		return xfrm6_rcv(skb);
329 330
	}
	rcu_read_unlock();
331
	return -EINVAL;
332 333 334 335 336
discard:
	kfree_skb(skb);
	return 0;
}

337 338 339 340 341 342 343
static int vti6_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 ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
344 345
	u32 orig_mark = skb->mark;
	int ret;
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361

	if (!t)
		return 1;

	dev = t->dev;

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

		return 0;
	}

	x = xfrm_input_state(skb);
	family = x->inner_mode->afinfo->family;

362 363 364 365 366
	skb->mark = be32_to_cpu(t->parms.i_key);
	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
	skb->mark = orig_mark;

	if (!ret)
367 368 369 370 371 372 373 374 375 376 377 378 379 380
		return -EPERM;

	skb_scrub_packet(skb, !net_eq(t->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;
}

381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399
/**
 * vti6_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
vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
{
	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}

400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
static bool vti6_state_check(const struct xfrm_state *x,
			     const struct in6_addr *dst,
			     const struct in6_addr *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_INET6)
		return false;

	if (ipv6_addr_any(dst))
		return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6);

	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6))
		return false;

	return true;
}

423 424 425 426
/**
 * vti6_xmit - send a packet
 *   @skb: the outgoing socket buffer
 *   @dev: the outgoing tunnel device
427
 *   @fl: the flow informations for the xfrm_lookup
428
 **/
429 430
static int
vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
431 432 433
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net_device_stats *stats = &t->dev->stats;
434
	struct dst_entry *dst = skb_dst(skb);
435
	struct net_device *tdev;
436
	struct xfrm_state *x;
437
	int err = -1;
438
	int mtu;
439

440 441
	if (!dst)
		goto tx_err_link_failure;
442

443
	dst_hold(dst);
444
	dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
445 446 447 448
	if (IS_ERR(dst)) {
		err = PTR_ERR(dst);
		dst = NULL;
		goto tx_err_link_failure;
449 450
	}

451 452 453 454 455 456
	x = dst->xfrm;
	if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
		goto tx_err_link_failure;

	if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr,
			      (const struct in6_addr *)&x->id.daddr))
457 458 459 460 461 462 463 464 465 466 467
		goto tx_err_link_failure;

	tdev = dst->dev;

	if (tdev == dev) {
		stats->collisions++;
		net_warn_ratelimited("%s: Local routing loop detected!\n",
				     t->parms.name);
		goto tx_err_dst_release;
	}

468 469 470
	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
	skb_dst_set(skb, dst);
	skb->dev = skb_dst(skb)->dev;
471

472 473 474 475 476 477 478 479 480 481 482 483 484
	mtu = dst_mtu(dst);
	if (!skb->ignore_df && skb->len > mtu) {
		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);

		if (skb->protocol == htons(ETH_P_IPV6))
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		else
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));

		return -EMSGSIZE;
	}

485
	err = dst_output(t->net, skb->sk, skb);
486 487 488 489 490 491 492 493 494 495 496
	if (net_xmit_eval(err) == 0) {
		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);

		u64_stats_update_begin(&tstats->syncp);
		tstats->tx_bytes += skb->len;
		tstats->tx_packets++;
		u64_stats_update_end(&tstats->syncp);
	} else {
		stats->tx_errors++;
		stats->tx_aborted_errors++;
	}
497 498 499 500 501 502

	return 0;
tx_err_link_failure:
	stats->tx_carrier_errors++;
	dst_link_failure(skb);
tx_err_dst_release:
503
	dst_release(dst);
504 505 506 507 508 509 510 511
	return err;
}

static netdev_tx_t
vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net_device_stats *stats = &t->dev->stats;
512 513
	struct ipv6hdr *ipv6h;
	struct flowi fl;
514 515
	int ret;

516 517
	memset(&fl, 0, sizeof(fl));

518 519
	switch (skb->protocol) {
	case htons(ETH_P_IPV6):
520 521 522
		ipv6h = ipv6_hdr(skb);

		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
523
		    vti6_addr_conflict(t, ipv6h))
524 525 526 527 528 529 530 531
			goto tx_err;

		xfrm_decode_session(skb, &fl, AF_INET6);
		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
		break;
	case htons(ETH_P_IP):
		xfrm_decode_session(skb, &fl, AF_INET);
		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
532 533 534 535 536
		break;
	default:
		goto tx_err;
	}

537 538 539
	/* override mark with tunnel output key */
	fl.flowi_mark = be32_to_cpu(t->parms.o_key);

540
	ret = vti6_xmit(skb, dev, &fl);
541 542 543 544 545 546 547 548 549 550 551 552
	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;
}

553 554 555 556
static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		    u8 type, u8 code, int offset, __be32 info)
{
	__be32 spi;
557
	__u32 mark;
558 559 560 561 562 563 564 565 566 567 568 569 570
	struct xfrm_state *x;
	struct ip6_tnl *t;
	struct ip_esp_hdr *esph;
	struct ip_auth_hdr *ah;
	struct ip_comp_hdr *ipch;
	struct net *net = dev_net(skb->dev);
	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
	int protocol = iph->nexthdr;

	t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr);
	if (!t)
		return -1;

571 572
	mark = be32_to_cpu(t->parms.o_key);

573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
	switch (protocol) {
	case IPPROTO_ESP:
		esph = (struct ip_esp_hdr *)(skb->data + offset);
		spi = esph->spi;
		break;
	case IPPROTO_AH:
		ah = (struct ip_auth_hdr *)(skb->data + offset);
		spi = ah->spi;
		break;
	case IPPROTO_COMP:
		ipch = (struct ip_comp_hdr *)(skb->data + offset);
		spi = htonl(ntohs(ipch->cpi));
		break;
	default:
		return 0;
	}

	if (type != ICMPV6_PKT_TOOBIG &&
	    type != NDISC_REDIRECT)
		return 0;

594
	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
595 596 597 598 599 600 601 602 603 604 605 606 607
			      spi, protocol, AF_INET6);
	if (!x)
		return 0;

	if (type == NDISC_REDIRECT)
		ip6_redirect(skb, net, skb->dev->ifindex, 0);
	else
		ip6_update_pmtu(skb, net, info, 0, 0);
	xfrm_state_put(x);

	return 0;
}

608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
static void vti6_link_config(struct ip6_tnl *t)
{
	struct net_device *dev = t->dev;
	struct __ip6_tnl_parm *p = &t->parms;

	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));

	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->flags |= IFF_POINTOPOINT;
	else
		dev->flags &= ~IFF_POINTOPOINT;
}

/**
 * vti6_tnl_change - update the tunnel parameters
 *   @t: tunnel to be changed
 *   @p: tunnel configuration parameters
 *
 * Description:
 *   vti6_tnl_change() updates the tunnel parameters
 **/
static int
vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
{
	t->parms.laddr = p->laddr;
	t->parms.raddr = p->raddr;
	t->parms.link = p->link;
	t->parms.i_key = p->i_key;
	t->parms.o_key = p->o_key;
	t->parms.proto = p->proto;
643
	dst_cache_reset(&t->dst_cache);
644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736
	vti6_link_config(t);
	return 0;
}

static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
	struct net *net = dev_net(t->dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
	int err;

	vti6_tnl_unlink(ip6n, t);
	synchronize_net();
	err = vti6_tnl_change(t, p);
	vti6_tnl_link(ip6n, t);
	netdev_state_change(t->dev);
	return err;
}

static void
vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u)
{
	p->laddr = u->laddr;
	p->raddr = u->raddr;
	p->link = u->link;
	p->i_key = u->i_key;
	p->o_key = u->o_key;
	p->proto = u->proto;

	memcpy(p->name, u->name, sizeof(u->name));
}

static void
vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
{
	u->laddr = p->laddr;
	u->raddr = p->raddr;
	u->link = p->link;
	u->i_key = p->i_key;
	u->o_key = p->o_key;
	u->proto = p->proto;

	memcpy(u->name, p->name, sizeof(u->name));
}

/**
 * vti6_tnl_ioctl - configure vti6 tunnels from userspace
 *   @dev: virtual device associated with tunnel
 *   @ifr: parameters passed from userspace
 *   @cmd: command to be performed
 *
 * Description:
 *   vti6_ioctl() is used for managing vti6 tunnels
 *   from userspace.
 *
 *   The possible commands are the following:
 *     %SIOCGETTUNNEL: get tunnel parameters for device
 *     %SIOCADDTUNNEL: add tunnel matching given tunnel parameters
 *     %SIOCCHGTUNNEL: change tunnel parameters to those given
 *     %SIOCDELTUNNEL: delete tunnel
 *
 *   The fallback device "ip6_vti0", created during module
 *   initialization, can be used for creating other tunnel devices.
 *
 * Return:
 *   0 on success,
 *   %-EFAULT if unable to copy data to or from userspace,
 *   %-EPERM if current process hasn't %CAP_NET_ADMIN set
 *   %-EINVAL if passed tunnel parameters are invalid,
 *   %-EEXIST if changing a tunnel's parameters would cause a conflict
 *   %-ENODEV if attempting to change or delete a nonexisting device
 **/
static int
vti6_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 = NULL;
	struct net *net = dev_net(dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	switch (cmd) {
	case SIOCGETTUNNEL:
		if (dev == ip6n->fb_tnl_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
				err = -EFAULT;
				break;
			}
			vti6_parm_from_user(&p1, &p);
			t = vti6_locate(net, &p1, 0);
		} else {
			memset(&p, 0, sizeof(p));
		}
737
		if (!t)
738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
			t = netdev_priv(dev);
		vti6_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 (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			break;
		err = -EFAULT;
		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
			break;
		err = -EINVAL;
		if (p.proto != IPPROTO_IPV6  && p.proto != 0)
			break;
		vti6_parm_from_user(&p1, &p);
		t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL);
		if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
757
			if (t) {
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else
				t = netdev_priv(dev);

			err = vti6_update(t, &p1);
		}
		if (t) {
			err = 0;
			vti6_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 (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			break;

		if (dev == ip6n->fb_tnl_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
				break;
			err = -ENOENT;
			vti6_parm_from_user(&p1, &p);
			t = vti6_locate(net, &p1, 0);
788
			if (!t)
789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
				break;
			err = -EPERM;
			if (t->dev == ip6n->fb_tnl_dev)
				break;
			dev = t->dev;
		}
		err = 0;
		unregister_netdevice(dev);
		break;
	default:
		err = -EINVAL;
	}
	return err;
}

/**
 * vti6_tnl_change_mtu - change mtu manually for tunnel device
 *   @dev: virtual device associated with tunnel
 *   @new_mtu: the new mtu
 *
 * Return:
 *   0 on success,
 *   %-EINVAL if mtu too small
 **/
static int vti6_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < IPV6_MIN_MTU)
		return -EINVAL;

	dev->mtu = new_mtu;
	return 0;
}

static const struct net_device_ops vti6_netdev_ops = {
823
	.ndo_init	= vti6_dev_init,
824 825 826 827
	.ndo_uninit	= vti6_dev_uninit,
	.ndo_start_xmit = vti6_tnl_xmit,
	.ndo_do_ioctl	= vti6_ioctl,
	.ndo_change_mtu = vti6_change_mtu,
828
	.ndo_get_stats64 = ip_tunnel_get_stats64,
829
	.ndo_get_iflink = ip6_tnl_get_iflink,
830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848
};

/**
 * vti6_dev_setup - setup virtual tunnel device
 *   @dev: virtual device associated with tunnel
 *
 * Description:
 *   Initialize function pointers and device parameters
 **/
static void vti6_dev_setup(struct net_device *dev)
{
	dev->netdev_ops = &vti6_netdev_ops;
	dev->destructor = vti6_dev_free;

	dev->type = ARPHRD_TUNNEL6;
	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
	dev->mtu = ETH_DATA_LEN;
	dev->flags |= IFF_NOARP;
	dev->addr_len = sizeof(struct in6_addr);
849
	netif_keep_dst(dev);
850 851 852 853 854 855 856 857 858 859 860 861
}

/**
 * vti6_dev_init_gen - general initializer for all tunnel devices
 *   @dev: virtual device associated with tunnel
 **/
static inline int vti6_dev_init_gen(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);

	t->dev = dev;
	t->net = dev_net(dev);
862
	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918
	if (!dev->tstats)
		return -ENOMEM;
	return 0;
}

/**
 * vti6_dev_init - initializer for all non fallback tunnel devices
 *   @dev: virtual device associated with tunnel
 **/
static int vti6_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	int err = vti6_dev_init_gen(dev);

	if (err)
		return err;
	vti6_link_config(t);
	return 0;
}

/**
 * vti6_fb_tnl_dev_init - initializer for fallback tunnel device
 *   @dev: fallback device
 *
 * Return: 0
 **/
static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net *net = dev_net(dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	t->parms.proto = IPPROTO_IPV6;
	dev_hold(dev);

	rcu_assign_pointer(ip6n->tnls_wc[0], t);
	return 0;
}

static int vti6_validate(struct nlattr *tb[], struct nlattr *data[])
{
	return 0;
}

static void vti6_netlink_parms(struct nlattr *data[],
			       struct __ip6_tnl_parm *parms)
{
	memset(parms, 0, sizeof(*parms));

	if (!data)
		return;

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

	if (data[IFLA_VTI_LOCAL])
919
		parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]);
920 921

	if (data[IFLA_VTI_REMOTE])
922
		parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]);
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947

	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]);
}

static int vti6_newlink(struct net *src_net, struct net_device *dev,
			struct nlattr *tb[], struct nlattr *data[])
{
	struct net *net = dev_net(dev);
	struct ip6_tnl *nt;

	nt = netdev_priv(dev);
	vti6_netlink_parms(data, &nt->parms);

	nt->parms.proto = IPPROTO_IPV6;

	if (vti6_locate(net, &nt->parms, 0))
		return -EEXIST;

	return vti6_tnl_create2(dev);
}

948 949 950 951 952 953 954 955 956
static void vti6_dellink(struct net_device *dev, struct list_head *head)
{
	struct net *net = dev_net(dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	if (dev != ip6n->fb_tnl_dev)
		unregister_netdevice_queue(dev, head);
}

957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
			   struct nlattr *data[])
{
	struct ip6_tnl *t;
	struct __ip6_tnl_parm p;
	struct net *net = dev_net(dev);
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	if (dev == ip6n->fb_tnl_dev)
		return -EINVAL;

	vti6_netlink_parms(data, &p);

	t = vti6_locate(net, &p, 0);

	if (t) {
		if (t->dev != dev)
			return -EEXIST;
	} else
		t = netdev_priv(dev);

	return vti6_update(t, &p);
}

static size_t vti6_get_size(const struct net_device *dev)
{
	return
		/* IFLA_VTI_LINK */
		nla_total_size(4) +
		/* IFLA_VTI_LOCAL */
		nla_total_size(sizeof(struct in6_addr)) +
		/* IFLA_VTI_REMOTE */
		nla_total_size(sizeof(struct in6_addr)) +
		/* IFLA_VTI_IKEY */
		nla_total_size(4) +
		/* IFLA_VTI_OKEY */
		nla_total_size(4) +
		0;
}

static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct ip6_tnl *tunnel = netdev_priv(dev);
	struct __ip6_tnl_parm *parm = &tunnel->parms;

	if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) ||
1003 1004
	    nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) ||
	    nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) ||
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
	    nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) ||
	    nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = {
	[IFLA_VTI_LINK]		= { .type = NLA_U32 },
	[IFLA_VTI_LOCAL]	= { .len = sizeof(struct in6_addr) },
	[IFLA_VTI_REMOTE]	= { .len = sizeof(struct in6_addr) },
	[IFLA_VTI_IKEY]		= { .type = NLA_U32 },
	[IFLA_VTI_OKEY]		= { .type = NLA_U32 },
};

static struct rtnl_link_ops vti6_link_ops __read_mostly = {
	.kind		= "vti6",
	.maxtype	= IFLA_VTI_MAX,
	.policy		= vti6_policy,
	.priv_size	= sizeof(struct ip6_tnl),
	.setup		= vti6_dev_setup,
	.validate	= vti6_validate,
	.newlink	= vti6_newlink,
1030
	.dellink	= vti6_dellink,
1031 1032 1033
	.changelink	= vti6_changelink,
	.get_size	= vti6_get_size,
	.fill_info	= vti6_fill_info,
1034
	.get_link_net	= ip6_tnl_get_link_net,
1035 1036 1037 1038 1039 1040 1041 1042
};

static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
{
	int h;
	struct ip6_tnl *t;
	LIST_HEAD(list);

1043
	for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
1044
		t = rtnl_dereference(ip6n->tnls_r_l[h]);
1045
		while (t) {
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066
			unregister_netdevice_queue(t->dev, &list);
			t = rtnl_dereference(t->next);
		}
	}

	t = rtnl_dereference(ip6n->tnls_wc[0]);
	unregister_netdevice_queue(t->dev, &list);
	unregister_netdevice_many(&list);
}

static int __net_init vti6_init_net(struct net *net)
{
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
	struct ip6_tnl *t = NULL;
	int err;

	ip6n->tnls[0] = ip6n->tnls_wc;
	ip6n->tnls[1] = ip6n->tnls_r_l;

	err = -ENOMEM;
	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0",
1067
					NET_NAME_UNKNOWN, vti6_dev_setup);
1068 1069 1070 1071

	if (!ip6n->fb_tnl_dev)
		goto err_alloc_dev;
	dev_net_set(ip6n->fb_tnl_dev, net);
1072
	ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108

	err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
	if (err < 0)
		goto err_register;

	err = register_netdev(ip6n->fb_tnl_dev);
	if (err < 0)
		goto err_register;

	t = netdev_priv(ip6n->fb_tnl_dev);

	strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
	return 0;

err_register:
	vti6_dev_free(ip6n->fb_tnl_dev);
err_alloc_dev:
	return err;
}

static void __net_exit vti6_exit_net(struct net *net)
{
	struct vti6_net *ip6n = net_generic(net, vti6_net_id);

	rtnl_lock();
	vti6_destroy_tunnels(ip6n);
	rtnl_unlock();
}

static struct pernet_operations vti6_net_ops = {
	.init = vti6_init_net,
	.exit = vti6_exit_net,
	.id   = &vti6_net_id,
	.size = sizeof(struct vti6_net),
};

1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
static struct xfrm6_protocol vti_esp6_protocol __read_mostly = {
	.handler	=	vti6_rcv,
	.cb_handler	=	vti6_rcv_cb,
	.err_handler	=	vti6_err,
	.priority	=	100,
};

static struct xfrm6_protocol vti_ah6_protocol __read_mostly = {
	.handler	=	vti6_rcv,
	.cb_handler	=	vti6_rcv_cb,
	.err_handler	=	vti6_err,
	.priority	=	100,
};

static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
	.handler	=	vti6_rcv,
	.cb_handler	=	vti6_rcv_cb,
	.err_handler	=	vti6_err,
	.priority	=	100,
};

1130 1131 1132 1133 1134 1135 1136
/**
 * vti6_tunnel_init - register protocol and reserve needed resources
 *
 * Return: 0 on success
 **/
static int __init vti6_tunnel_init(void)
{
1137 1138
	const char *msg;
	int err;
1139

1140
	msg = "tunnel device";
1141 1142
	err = register_pernet_device(&vti6_net_ops);
	if (err < 0)
1143
		goto pernet_dev_failed;
1144

1145
	msg = "tunnel protocols";
1146
	err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
1147 1148
	if (err < 0)
		goto xfrm_proto_esp_failed;
1149
	err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
1150 1151
	if (err < 0)
		goto xfrm_proto_ah_failed;
1152
	err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP);
1153 1154
	if (err < 0)
		goto xfrm_proto_comp_failed;
1155

1156
	msg = "netlink interface";
1157 1158 1159 1160 1161 1162 1163
	err = rtnl_link_register(&vti6_link_ops);
	if (err < 0)
		goto rtnl_link_failed;

	return 0;

rtnl_link_failed:
1164
	xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
1165
xfrm_proto_comp_failed:
1166
	xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
1167
xfrm_proto_ah_failed:
1168
	xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
1169
xfrm_proto_esp_failed:
1170
	unregister_pernet_device(&vti6_net_ops);
1171 1172
pernet_dev_failed:
	pr_err("vti6 init: failed to register %s\n", msg);
1173 1174 1175 1176 1177 1178 1179 1180 1181
	return err;
}

/**
 * vti6_tunnel_cleanup - free resources and unregister protocol
 **/
static void __exit vti6_tunnel_cleanup(void)
{
	rtnl_link_unregister(&vti6_link_ops);
1182 1183 1184
	xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
	xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
	xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
1185 1186 1187 1188 1189 1190 1191 1192 1193 1194
	unregister_pernet_device(&vti6_net_ops);
}

module_init(vti6_tunnel_init);
module_exit(vti6_tunnel_cleanup);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti6");
MODULE_ALIAS_NETDEV("ip6_vti0");
MODULE_AUTHOR("Steffen Klassert");
MODULE_DESCRIPTION("IPv6 virtual tunnel interface");