ip6_gre.c 41.7 KB
Newer Older
X
xeb@mail.ru 已提交
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 53 54 55 56 57 58
/*
 *	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>


59 60 61 62
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");

X
xeb@mail.ru 已提交
63 64 65 66 67 68 69 70 71 72 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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
#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;
156
	tot->rx_frame_errors = dev->stats.rx_frame_errors;
X
xeb@mail.ru 已提交
157
	tot->rx_errors = dev->stats.rx_errors;
158

X
xeb@mail.ru 已提交
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
	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;
E
Eric Dumazet 已提交
424 425
	__be16 *p = (__be16 *)(skb->data + offset);
	int grehlen = offset + 4;
X
xeb@mail.ru 已提交
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
	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 */
E
Eric Dumazet 已提交
441
	if (!pskb_may_pull(skb, grehlen))
X
xeb@mail.ru 已提交
442
		return;
E
Eric Dumazet 已提交
443 444
	ipv6h = (const struct ipv6hdr *)skb->data;
	p = (__be16 *)(skb->data + offset);
X
xeb@mail.ru 已提交
445 446 447 448 449 450

	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
				flags & GRE_KEY ?
				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
				p[1]);
	if (t == NULL)
451
		return;
X
xeb@mail.ru 已提交
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508

	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;
}

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;
509
	int err;
X
xeb@mail.ru 已提交
510 511

	if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
512
		goto drop;
X
xeb@mail.ru 已提交
513 514 515 516 517 518 519 520 521 522

	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))
523
			goto drop;
X
xeb@mail.ru 已提交
524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612

		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);

	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);
		}

613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
		__skb_tunnel_rx(skb, tunnel->dev);

		skb_reset_network_header(skb);

		err = IP6_ECN_decapsulate(ipv6h, skb);
		if (unlikely(err)) {
			if (log_ecn_error)
				net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n",
						     &ipv6h->saddr,
						     ipv6_get_dsfield(ipv6h));
			if (err > 1) {
				++tunnel->dev->stats.rx_frame_errors;
				++tunnel->dev->stats.rx_errors;
				goto drop;
			}
		}

X
xeb@mail.ru 已提交
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 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 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
		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);

		netif_rx(skb);

		return 0;
	}
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);

drop:
	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;
			}
		}
A
Amerigo Wang 已提交
1072
		ip6_rt_put(rt);
X
xeb@mail.ru 已提交
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 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
	}

	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 const struct header_ops ip6gre_header_ops = {
	.create	= ip6gre_header,
};

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");