af_mpls.c 26.3 KB
Newer Older
E
Eric W. Biederman 已提交
1 2 3
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
4
#include <linux/sysctl.h>
E
Eric W. Biederman 已提交
5 6 7 8 9
#include <linux/net.h>
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
10
#include <linux/vmalloc.h>
E
Eric W. Biederman 已提交
11 12 13 14 15 16 17 18 19
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include "internal.h"

20
#define LABEL_NOT_SPECIFIED (1<<20)
E
Eric W. Biederman 已提交
21 22 23 24 25 26
#define MAX_NEW_LABELS 2

/* This maximum ha length copied from the definition of struct neighbour */
#define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long)))

struct mpls_route { /* next hop label forwarding entry */
27
	struct net_device __rcu *rt_dev;
E
Eric W. Biederman 已提交
28 29 30
	struct rcu_head		rt_rcu;
	u32			rt_label[MAX_NEW_LABELS];
	u8			rt_protocol; /* routing protocol that set this entry */
31 32 33
	u8			rt_labels;
	u8			rt_via_alen;
	u8			rt_via_table;
E
Eric W. Biederman 已提交
34 35 36
	u8			rt_via[0];
};

37 38 39
static int zero = 0;
static int label_limit = (1 << 20) - 1;

40 41 42 43
static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
		       struct nlmsghdr *nlh, struct net *net, u32 portid,
		       unsigned int nlm_flags);

E
Eric W. Biederman 已提交
44 45 46 47 48 49 50 51 52 53 54 55
static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
{
	struct mpls_route *rt = NULL;

	if (index < net->mpls.platform_labels) {
		struct mpls_route __rcu **platform_label =
			rcu_dereference(net->mpls.platform_label);
		rt = rcu_dereference(platform_label[index]);
	}
	return rt;
}

R
Robert Shearman 已提交
56 57 58 59 60
static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
{
	return rcu_dereference_rtnl(dev->mpls_ptr);
}

E
Eric W. Biederman 已提交
61 62 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
static bool mpls_output_possible(const struct net_device *dev)
{
	return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
}

static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
{
	/* The size of the layer 2.5 labels to be added for this route */
	return rt->rt_labels * sizeof(struct mpls_shim_hdr);
}

static unsigned int mpls_dev_mtu(const struct net_device *dev)
{
	/* The amount of data the layer 2 frame can hold */
	return dev->mtu;
}

static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
	if (skb->len <= mtu)
		return false;

	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
		return false;

	return true;
}

static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
			struct mpls_entry_decoded dec)
{
	/* RFC4385 and RFC5586 encode other packets in mpls such that
	 * they don't conflict with the ip version number, making
	 * decoding by examining the ip version correct in everything
	 * except for the strangest cases.
	 *
	 * The strange cases if we choose to support them will require
	 * manual configuration.
	 */
100
	struct iphdr *hdr4;
E
Eric W. Biederman 已提交
101 102
	bool success = true;

103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
	/* The IPv4 code below accesses through the IPv4 header
	 * checksum, which is 12 bytes into the packet.
	 * The IPv6 code below accesses through the IPv6 hop limit
	 * which is 8 bytes into the packet.
	 *
	 * For all supported cases there should always be at least 12
	 * bytes of packet data present.  The IPv4 header is 20 bytes
	 * without options and the IPv6 header is always 40 bytes
	 * long.
	 */
	if (!pskb_may_pull(skb, 12))
		return false;

	/* Use ip_hdr to find the ip protocol version */
	hdr4 = ip_hdr(skb);
E
Eric W. Biederman 已提交
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
	if (hdr4->version == 4) {
		skb->protocol = htons(ETH_P_IP);
		csum_replace2(&hdr4->check,
			      htons(hdr4->ttl << 8),
			      htons(dec.ttl << 8));
		hdr4->ttl = dec.ttl;
	}
	else if (hdr4->version == 6) {
		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
		skb->protocol = htons(ETH_P_IPV6);
		hdr6->hop_limit = dec.ttl;
	}
	else
		/* version 0 and version 1 are used by pseudo wires */
		success = false;
	return success;
}

static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
			struct packet_type *pt, struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);
	struct mpls_shim_hdr *hdr;
	struct mpls_route *rt;
	struct mpls_entry_decoded dec;
	struct net_device *out_dev;
R
Robert Shearman 已提交
144
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
145 146 147 148 149 150 151
	unsigned int hh_len;
	unsigned int new_header_size;
	unsigned int mtu;
	int err;

	/* Careful this entire function runs inside of an rcu critical section */

R
Robert Shearman 已提交
152
	mdev = mpls_dev_get(dev);
153
	if (!mdev || !mdev->input_enabled)
R
Robert Shearman 已提交
154 155
		goto drop;

E
Eric W. Biederman 已提交
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179
	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
		goto drop;

	if (!pskb_may_pull(skb, sizeof(*hdr)))
		goto drop;

	/* Read and decode the label */
	hdr = mpls_hdr(skb);
	dec = mpls_entry_decode(hdr);

	/* Pop the label */
	skb_pull(skb, sizeof(*hdr));
	skb_reset_network_header(skb);

	skb_orphan(skb);

	rt = mpls_route_input_rcu(net, dec.label);
	if (!rt)
		goto drop;

	/* Find the output device */
180
	out_dev = rcu_dereference(rt->rt_dev);
E
Eric W. Biederman 已提交
181 182 183 184 185 186 187 188 189
	if (!mpls_output_possible(out_dev))
		goto drop;

	if (skb_warn_if_lro(skb))
		goto drop;

	skb_forward_csum(skb);

	/* Verify ttl is valid */
190
	if (dec.ttl <= 1)
E
Eric W. Biederman 已提交
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
		goto drop;
	dec.ttl -= 1;

	/* Verify the destination can hold the packet */
	new_header_size = mpls_rt_header_size(rt);
	mtu = mpls_dev_mtu(out_dev);
	if (mpls_pkt_too_big(skb, mtu - new_header_size))
		goto drop;

	hh_len = LL_RESERVED_SPACE(out_dev);
	if (!out_dev->header_ops)
		hh_len = 0;

	/* Ensure there is enough space for the headers in the skb */
	if (skb_cow(skb, hh_len + new_header_size))
		goto drop;

	skb->dev = out_dev;
	skb->protocol = htons(ETH_P_MPLS_UC);

	if (unlikely(!new_header_size && dec.bos)) {
		/* Penultimate hop popping */
		if (!mpls_egress(rt, skb, dec))
			goto drop;
	} else {
		bool bos;
		int i;
		skb_push(skb, new_header_size);
		skb_reset_network_header(skb);
		/* Push the new labels */
		hdr = mpls_hdr(skb);
		bos = dec.bos;
		for (i = rt->rt_labels - 1; i >= 0; i--) {
			hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos);
			bos = false;
		}
	}

229
	err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb);
E
Eric W. Biederman 已提交
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
	if (err)
		net_dbg_ratelimited("%s: packet transmission failed: %d\n",
				    __func__, err);
	return 0;

drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}

static struct packet_type mpls_packet_type __read_mostly = {
	.type = cpu_to_be16(ETH_P_MPLS_UC),
	.func = mpls_forward,
};

245
static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
246 247 248 249
	[RTA_DST]		= { .type = NLA_U32 },
	[RTA_OIF]		= { .type = NLA_U32 },
};

250 251 252
struct mpls_route_config {
	u32		rc_protocol;
	u32		rc_ifindex;
253
	u16		rc_via_table;
254 255 256 257 258 259 260 261 262
	u16		rc_via_alen;
	u8		rc_via[MAX_VIA_ALEN];
	u32		rc_label;
	u32		rc_output_labels;
	u32		rc_output_label[MAX_NEW_LABELS];
	u32		rc_nlflags;
	struct nl_info	rc_nlinfo;
};

E
Eric W. Biederman 已提交
263 264 265 266
static struct mpls_route *mpls_rt_alloc(size_t alen)
{
	struct mpls_route *rt;

267
	rt = kzalloc(sizeof(*rt) + alen, GFP_KERNEL);
E
Eric W. Biederman 已提交
268 269 270 271 272 273 274 275 276 277 278
	if (rt)
		rt->rt_via_alen = alen;
	return rt;
}

static void mpls_rt_free(struct mpls_route *rt)
{
	if (rt)
		kfree_rcu(rt, rt_rcu);
}

279 280 281 282 283 284 285 286 287 288 289 290 291 292
static void mpls_notify_route(struct net *net, unsigned index,
			      struct mpls_route *old, struct mpls_route *new,
			      const struct nl_info *info)
{
	struct nlmsghdr *nlh = info ? info->nlh : NULL;
	unsigned portid = info ? info->portid : 0;
	int event = new ? RTM_NEWROUTE : RTM_DELROUTE;
	struct mpls_route *rt = new ? new : old;
	unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0;
	/* Ignore reserved labels for now */
	if (rt && (index >= 16))
		rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags);
}

E
Eric W. Biederman 已提交
293 294 295 296
static void mpls_route_update(struct net *net, unsigned index,
			      struct net_device *dev, struct mpls_route *new,
			      const struct nl_info *info)
{
297
	struct mpls_route __rcu **platform_label;
E
Eric W. Biederman 已提交
298 299 300 301
	struct mpls_route *rt, *old = NULL;

	ASSERT_RTNL();

302 303 304 305
	platform_label = rtnl_dereference(net->mpls.platform_label);
	rt = rtnl_dereference(platform_label[index]);
	if (!dev || (rt && (rtnl_dereference(rt->rt_dev) == dev))) {
		rcu_assign_pointer(platform_label[index], new);
E
Eric W. Biederman 已提交
306 307 308
		old = rt;
	}

309 310
	mpls_notify_route(net, index, old, new, info);

E
Eric W. Biederman 已提交
311 312 313 314
	/* If we removed a route free it now */
	mpls_rt_free(old);
}

315 316
static unsigned find_free_label(struct net *net)
{
317 318
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
319
	unsigned index;
320 321 322 323 324

	platform_label = rtnl_dereference(net->mpls.platform_label);
	platform_labels = net->mpls.platform_labels;
	for (index = 16; index < platform_labels; index++) {
		if (!rtnl_dereference(platform_label[index]))
325 326 327 328 329 330 331
			return index;
	}
	return LABEL_NOT_SPECIFIED;
}

static int mpls_route_add(struct mpls_route_config *cfg)
{
332
	struct mpls_route __rcu **platform_label;
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
	struct net *net = cfg->rc_nlinfo.nl_net;
	struct net_device *dev = NULL;
	struct mpls_route *rt, *old;
	unsigned index;
	int i;
	int err = -EINVAL;

	index = cfg->rc_label;

	/* If a label was not specified during insert pick one */
	if ((index == LABEL_NOT_SPECIFIED) &&
	    (cfg->rc_nlflags & NLM_F_CREATE)) {
		index = find_free_label(net);
	}

	/* The first 16 labels are reserved, and may not be set */
	if (index < 16)
		goto errout;

	/* The full 20 bit range may not be supported. */
	if (index >= net->mpls.platform_labels)
		goto errout;

	/* Ensure only a supported number of labels are present */
	if (cfg->rc_output_labels > MAX_NEW_LABELS)
		goto errout;

	err = -ENODEV;
	dev = dev_get_by_index(net, cfg->rc_ifindex);
	if (!dev)
		goto errout;

R
Robert Shearman 已提交
365
	/* Ensure this is a supported device */
366
	err = -EINVAL;
R
Robert Shearman 已提交
367
	if (!mpls_dev_get(dev))
368 369 370
		goto errout;

	err = -EINVAL;
371
	if ((cfg->rc_via_table == NEIGH_LINK_TABLE) &&
372 373 374 375
	    (dev->addr_len != cfg->rc_via_alen))
		goto errout;

	/* Append makes no sense with mpls */
376
	err = -EOPNOTSUPP;
377 378 379 380
	if (cfg->rc_nlflags & NLM_F_APPEND)
		goto errout;

	err = -EEXIST;
381 382
	platform_label = rtnl_dereference(net->mpls.platform_label);
	old = rtnl_dereference(platform_label[index]);
383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402
	if ((cfg->rc_nlflags & NLM_F_EXCL) && old)
		goto errout;

	err = -EEXIST;
	if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old)
		goto errout;

	err = -ENOENT;
	if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old)
		goto errout;

	err = -ENOMEM;
	rt = mpls_rt_alloc(cfg->rc_via_alen);
	if (!rt)
		goto errout;

	rt->rt_labels = cfg->rc_output_labels;
	for (i = 0; i < rt->rt_labels; i++)
		rt->rt_label[i] = cfg->rc_output_label[i];
	rt->rt_protocol = cfg->rc_protocol;
403
	RCU_INIT_POINTER(rt->rt_dev, dev);
404
	rt->rt_via_table = cfg->rc_via_table;
405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
	memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen);

	mpls_route_update(net, index, NULL, rt, &cfg->rc_nlinfo);

	dev_put(dev);
	return 0;

errout:
	if (dev)
		dev_put(dev);
	return err;
}

static int mpls_route_del(struct mpls_route_config *cfg)
{
	struct net *net = cfg->rc_nlinfo.nl_net;
	unsigned index;
	int err = -EINVAL;

	index = cfg->rc_label;

	/* The first 16 labels are reserved, and may not be removed */
	if (index < 16)
		goto errout;

	/* The full 20 bit range may not be supported */
	if (index >= net->mpls.platform_labels)
		goto errout;

	mpls_route_update(net, index, NULL, NULL, &cfg->rc_nlinfo);

	err = 0;
errout:
	return err;
}

441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
#define MPLS_PERDEV_SYSCTL_OFFSET(field)	\
	(&((struct mpls_dev *)0)->field)

static const struct ctl_table mpls_dev_table[] = {
	{
		.procname	= "input",
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.data		= MPLS_PERDEV_SYSCTL_OFFSET(input_enabled),
	},
	{ }
};

static int mpls_dev_sysctl_register(struct net_device *dev,
				    struct mpls_dev *mdev)
{
	char path[sizeof("net/mpls/conf/") + IFNAMSIZ];
	struct ctl_table *table;
	int i;

	table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL);
	if (!table)
		goto out;

	/* Table data contains only offsets relative to the base of
	 * the mdev at this point, so make them absolute.
	 */
	for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++)
		table[i].data = (char *)mdev + (uintptr_t)table[i].data;

	snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);

	mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
	if (!mdev->sysctl)
		goto free;

	return 0;

free:
	kfree(table);
out:
	return -ENOBUFS;
}

static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
{
	struct ctl_table *table;

	table = mdev->sysctl->ctl_table_arg;
	unregister_net_sysctl_table(mdev->sysctl);
	kfree(table);
}

R
Robert Shearman 已提交
495 496 497 498 499 500 501 502 503 504 505
static struct mpls_dev *mpls_add_dev(struct net_device *dev)
{
	struct mpls_dev *mdev;
	int err = -ENOMEM;

	ASSERT_RTNL();

	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
	if (!mdev)
		return ERR_PTR(err);

506 507 508 509
	err = mpls_dev_sysctl_register(dev, mdev);
	if (err)
		goto free;

R
Robert Shearman 已提交
510 511 512
	rcu_assign_pointer(dev->mpls_ptr, mdev);

	return mdev;
513 514 515 516

free:
	kfree(mdev);
	return ERR_PTR(err);
R
Robert Shearman 已提交
517 518
}

E
Eric W. Biederman 已提交
519 520
static void mpls_ifdown(struct net_device *dev)
{
521
	struct mpls_route __rcu **platform_label;
E
Eric W. Biederman 已提交
522
	struct net *net = dev_net(dev);
R
Robert Shearman 已提交
523
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
524 525
	unsigned index;

526
	platform_label = rtnl_dereference(net->mpls.platform_label);
E
Eric W. Biederman 已提交
527
	for (index = 0; index < net->mpls.platform_labels; index++) {
528
		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
E
Eric W. Biederman 已提交
529 530
		if (!rt)
			continue;
531
		if (rtnl_dereference(rt->rt_dev) != dev)
E
Eric W. Biederman 已提交
532 533 534
			continue;
		rt->rt_dev = NULL;
	}
R
Robert Shearman 已提交
535 536 537 538 539

	mdev = mpls_dev_get(dev);
	if (!mdev)
		return;

540 541
	mpls_dev_sysctl_unregister(mdev);

R
Robert Shearman 已提交
542 543 544
	RCU_INIT_POINTER(dev->mpls_ptr, NULL);

	kfree(mdev);
E
Eric W. Biederman 已提交
545 546 547 548 549 550
}

static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
			   void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
R
Robert Shearman 已提交
551
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
552 553

	switch(event) {
R
Robert Shearman 已提交
554 555 556 557 558 559 560 561 562 563
	case NETDEV_REGISTER:
		/* For now just support ethernet devices */
		if ((dev->type == ARPHRD_ETHER) ||
		    (dev->type == ARPHRD_LOOPBACK)) {
			mdev = mpls_add_dev(dev);
			if (IS_ERR(mdev))
				return notifier_from_errno(PTR_ERR(mdev));
		}
		break;

E
Eric W. Biederman 已提交
564 565 566 567 568 569 570 571 572 573 574
	case NETDEV_UNREGISTER:
		mpls_ifdown(dev);
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block mpls_dev_notifier = {
	.notifier_call = mpls_dev_notify,
};

575
static int nla_put_via(struct sk_buff *skb,
576
		       u8 table, const void *addr, int alen)
577
{
578 579 580
	static const int table_to_family[NEIGH_NR_TABLES + 1] = {
		AF_INET, AF_INET6, AF_DECnet, AF_PACKET,
	};
581 582
	struct nlattr *nla;
	struct rtvia *via;
583
	int family = AF_UNSPEC;
584 585 586 587 588

	nla = nla_reserve(skb, RTA_VIA, alen + 2);
	if (!nla)
		return -EMSGSIZE;

589 590 591
	if (table <= NEIGH_NR_TABLES)
		family = table_to_family[table];

592 593 594 595 596 597
	via = nla_data(nla);
	via->rtvia_family = family;
	memcpy(via->rtvia_addr, addr, alen);
	return 0;
}

598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654
int nla_put_labels(struct sk_buff *skb, int attrtype,
		   u8 labels, const u32 label[])
{
	struct nlattr *nla;
	struct mpls_shim_hdr *nla_label;
	bool bos;
	int i;
	nla = nla_reserve(skb, attrtype, labels*4);
	if (!nla)
		return -EMSGSIZE;

	nla_label = nla_data(nla);
	bos = true;
	for (i = labels - 1; i >= 0; i--) {
		nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos);
		bos = false;
	}

	return 0;
}

int nla_get_labels(const struct nlattr *nla,
		   u32 max_labels, u32 *labels, u32 label[])
{
	unsigned len = nla_len(nla);
	unsigned nla_labels;
	struct mpls_shim_hdr *nla_label;
	bool bos;
	int i;

	/* len needs to be an even multiple of 4 (the label size) */
	if (len & 3)
		return -EINVAL;

	/* Limit the number of new labels allowed */
	nla_labels = len/4;
	if (nla_labels > max_labels)
		return -EINVAL;

	nla_label = nla_data(nla);
	bos = true;
	for (i = nla_labels - 1; i >= 0; i--, bos = false) {
		struct mpls_entry_decoded dec;
		dec = mpls_entry_decode(nla_label + i);

		/* Ensure the bottom of stack flag is properly set
		 * and ttl and tc are both clear.
		 */
		if ((dec.bos != bos) || dec.ttl || dec.tc)
			return -EINVAL;

		label[i] = dec.label;
	}
	*labels = nla_labels;
	return 0;
}

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
static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
			       struct mpls_route_config *cfg)
{
	struct rtmsg *rtm;
	struct nlattr *tb[RTA_MAX+1];
	int index;
	int err;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	rtm = nlmsg_data(nlh);
	memset(cfg, 0, sizeof(*cfg));

	if (rtm->rtm_family != AF_MPLS)
		goto errout;
	if (rtm->rtm_dst_len != 20)
		goto errout;
	if (rtm->rtm_src_len != 0)
		goto errout;
	if (rtm->rtm_tos != 0)
		goto errout;
	if (rtm->rtm_table != RT_TABLE_MAIN)
		goto errout;
	/* Any value is acceptable for rtm_protocol */

	/* As mpls uses destination specific addresses
	 * (or source specific address in the case of multicast)
	 * all addresses have universal scope.
	 */
	if (rtm->rtm_scope != RT_SCOPE_UNIVERSE)
		goto errout;
	if (rtm->rtm_type != RTN_UNICAST)
		goto errout;
	if (rtm->rtm_flags != 0)
		goto errout;

	cfg->rc_label		= LABEL_NOT_SPECIFIED;
	cfg->rc_protocol	= rtm->rtm_protocol;
	cfg->rc_nlflags		= nlh->nlmsg_flags;
	cfg->rc_nlinfo.portid	= NETLINK_CB(skb).portid;
	cfg->rc_nlinfo.nlh	= nlh;
	cfg->rc_nlinfo.nl_net	= sock_net(skb->sk);

	for (index = 0; index <= RTA_MAX; index++) {
		struct nlattr *nla = tb[index];
		if (!nla)
			continue;

		switch(index) {
		case RTA_OIF:
			cfg->rc_ifindex = nla_get_u32(nla);
			break;
		case RTA_NEWDST:
			if (nla_get_labels(nla, MAX_NEW_LABELS,
					   &cfg->rc_output_labels,
					   cfg->rc_output_label))
				goto errout;
			break;
		case RTA_DST:
		{
			u32 label_count;
			if (nla_get_labels(nla, 1, &label_count,
					   &cfg->rc_label))
				goto errout;

			/* The first 16 labels are reserved, and may not be set */
			if (cfg->rc_label < 16)
				goto errout;

			break;
		}
		case RTA_VIA:
		{
			struct rtvia *via = nla_data(nla);
732 733 734 735
			if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr))
				goto errout;
			cfg->rc_via_alen   = nla_len(nla) -
				offsetof(struct rtvia, rtvia_addr);
736 737 738 739
			if (cfg->rc_via_alen > MAX_VIA_ALEN)
				goto errout;

			/* Validate the address family */
740
			switch(via->rtvia_family) {
741
			case AF_PACKET:
742
				cfg->rc_via_table = NEIGH_LINK_TABLE;
743 744
				break;
			case AF_INET:
745
				cfg->rc_via_table = NEIGH_ARP_TABLE;
746 747 748 749
				if (cfg->rc_via_alen != 4)
					goto errout;
				break;
			case AF_INET6:
750
				cfg->rc_via_table = NEIGH_ND_TABLE;
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
				if (cfg->rc_via_alen != 16)
					goto errout;
				break;
			default:
				/* Unsupported address family */
				goto errout;
			}

			memcpy(cfg->rc_via, via->rtvia_addr, cfg->rc_via_alen);
			break;
		}
		default:
			/* Unsupported attribute */
			goto errout;
		}
	}

	err = 0;
errout:
	return err;
}

static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	struct mpls_route_config cfg;
	int err;

	err = rtm_to_route_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return mpls_route_del(&cfg);
}


static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	struct mpls_route_config cfg;
	int err;

	err = rtm_to_route_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return mpls_route_add(&cfg);
}

static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
			   u32 label, struct mpls_route *rt, int flags)
{
801
	struct net_device *dev;
802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
	struct nlmsghdr *nlh;
	struct rtmsg *rtm;

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_MPLS;
	rtm->rtm_dst_len = 20;
	rtm->rtm_src_len = 0;
	rtm->rtm_tos = 0;
	rtm->rtm_table = RT_TABLE_MAIN;
	rtm->rtm_protocol = rt->rt_protocol;
	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
	rtm->rtm_type = RTN_UNICAST;
	rtm->rtm_flags = 0;

	if (rt->rt_labels &&
	    nla_put_labels(skb, RTA_NEWDST, rt->rt_labels, rt->rt_label))
		goto nla_put_failure;
823
	if (nla_put_via(skb, rt->rt_via_table, rt->rt_via, rt->rt_via_alen))
824
		goto nla_put_failure;
825 826
	dev = rtnl_dereference(rt->rt_dev);
	if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
827 828 829 830 831 832 833 834 835 836 837 838 839 840 841
		goto nla_put_failure;
	if (nla_put_labels(skb, RTA_DST, 1, &label))
		goto nla_put_failure;

	nlmsg_end(skb, nlh);
	return 0;

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
842 843
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
844 845 846 847 848 849 850 851
	unsigned int index;

	ASSERT_RTNL();

	index = cb->args[0];
	if (index < 16)
		index = 16;

852 853 854
	platform_label = rtnl_dereference(net->mpls.platform_label);
	platform_labels = net->mpls.platform_labels;
	for (; index < platform_labels; index++) {
855
		struct mpls_route *rt;
856
		rt = rtnl_dereference(platform_label[index]);
857 858 859 860 861 862 863 864 865 866 867 868 869
		if (!rt)
			continue;

		if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid,
				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
				    index, rt, NLM_F_MULTI) < 0)
			break;
	}
	cb->args[0] = index;

	return skb->len;
}

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
static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
{
	size_t payload =
		NLMSG_ALIGN(sizeof(struct rtmsg))
		+ nla_total_size(2 + rt->rt_via_alen)	/* RTA_VIA */
		+ nla_total_size(4);			/* RTA_DST */
	if (rt->rt_labels)				/* RTA_NEWDST */
		payload += nla_total_size(rt->rt_labels * 4);
	if (rt->rt_dev)					/* RTA_OIF */
		payload += nla_total_size(4);
	return payload;
}

static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
		       struct nlmsghdr *nlh, struct net *net, u32 portid,
		       unsigned int nlm_flags)
{
	struct sk_buff *skb;
	u32 seq = nlh ? nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in lfib_nlmsg_size */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL);

	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err);
}

910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933
static int resize_platform_label_table(struct net *net, size_t limit)
{
	size_t size = sizeof(struct mpls_route *) * limit;
	size_t old_limit;
	size_t cp_size;
	struct mpls_route __rcu **labels = NULL, **old;
	struct mpls_route *rt0 = NULL, *rt2 = NULL;
	unsigned index;

	if (size) {
		labels = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
		if (!labels)
			labels = vzalloc(size);

		if (!labels)
			goto nolabels;
	}

	/* In case the predefined labels need to be populated */
	if (limit > LABEL_IPV4_EXPLICIT_NULL) {
		struct net_device *lo = net->loopback_dev;
		rt0 = mpls_rt_alloc(lo->addr_len);
		if (!rt0)
			goto nort0;
934
		RCU_INIT_POINTER(rt0->rt_dev, lo);
935
		rt0->rt_protocol = RTPROT_KERNEL;
936
		rt0->rt_via_table = NEIGH_LINK_TABLE;
937 938 939 940 941 942 943
		memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len);
	}
	if (limit > LABEL_IPV6_EXPLICIT_NULL) {
		struct net_device *lo = net->loopback_dev;
		rt2 = mpls_rt_alloc(lo->addr_len);
		if (!rt2)
			goto nort2;
944
		RCU_INIT_POINTER(rt2->rt_dev, lo);
945
		rt2->rt_protocol = RTPROT_KERNEL;
946
		rt2->rt_via_table = NEIGH_LINK_TABLE;
947 948 949 950 951
		memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len);
	}

	rtnl_lock();
	/* Remember the original table */
952
	old = rtnl_dereference(net->mpls.platform_label);
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968
	old_limit = net->mpls.platform_labels;

	/* Free any labels beyond the new table */
	for (index = limit; index < old_limit; index++)
		mpls_route_update(net, index, NULL, NULL, NULL);

	/* Copy over the old labels */
	cp_size = size;
	if (old_limit < limit)
		cp_size = old_limit * sizeof(struct mpls_route *);

	memcpy(labels, old, cp_size);

	/* If needed set the predefined labels */
	if ((old_limit <= LABEL_IPV6_EXPLICIT_NULL) &&
	    (limit > LABEL_IPV6_EXPLICIT_NULL)) {
969
		RCU_INIT_POINTER(labels[LABEL_IPV6_EXPLICIT_NULL], rt2);
970 971 972 973 974
		rt2 = NULL;
	}

	if ((old_limit <= LABEL_IPV4_EXPLICIT_NULL) &&
	    (limit > LABEL_IPV4_EXPLICIT_NULL)) {
975
		RCU_INIT_POINTER(labels[LABEL_IPV4_EXPLICIT_NULL], rt0);
976 977 978 979 980
		rt0 = NULL;
	}

	/* Update the global pointers */
	net->mpls.platform_labels = limit;
981
	rcu_assign_pointer(net->mpls.platform_label, labels);
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

	rtnl_unlock();

	mpls_rt_free(rt2);
	mpls_rt_free(rt0);

	if (old) {
		synchronize_rcu();
		kvfree(old);
	}
	return 0;

nort2:
	mpls_rt_free(rt0);
nort0:
	kvfree(labels);
nolabels:
	return -ENOMEM;
}

static int mpls_platform_labels(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct net *net = table->data;
	int platform_labels = net->mpls.platform_labels;
	int ret;
	struct ctl_table tmp = {
		.procname	= table->procname,
		.data		= &platform_labels,
		.maxlen		= sizeof(int),
		.mode		= table->mode,
		.extra1		= &zero,
		.extra2		= &label_limit,
	};

	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);

	if (write && ret == 0)
		ret = resize_platform_label_table(net, platform_labels);

	return ret;
}

1025
static const struct ctl_table mpls_table[] = {
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035
	{
		.procname	= "platform_labels",
		.data		= NULL,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= mpls_platform_labels,
	},
	{ }
};

E
Eric W. Biederman 已提交
1036 1037
static int mpls_net_init(struct net *net)
{
1038 1039
	struct ctl_table *table;

E
Eric W. Biederman 已提交
1040 1041 1042
	net->mpls.platform_labels = 0;
	net->mpls.platform_label = NULL;

1043 1044 1045 1046 1047 1048 1049 1050 1051
	table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL);
	if (table == NULL)
		return -ENOMEM;

	table[0].data = net;
	net->mpls.ctl = register_net_sysctl(net, "net/mpls", table);
	if (net->mpls.ctl == NULL)
		return -ENOMEM;

E
Eric W. Biederman 已提交
1052 1053 1054 1055 1056
	return 0;
}

static void mpls_net_exit(struct net *net)
{
1057 1058
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
1059
	struct ctl_table *table;
E
Eric W. Biederman 已提交
1060 1061
	unsigned int index;

1062 1063 1064 1065
	table = net->mpls.ctl->ctl_table_arg;
	unregister_net_sysctl_table(net->mpls.ctl);
	kfree(table);

1066 1067
	/* An rcu grace period has passed since there was a device in
	 * the network namespace (and thus the last in flight packet)
E
Eric W. Biederman 已提交
1068 1069 1070 1071 1072 1073 1074 1075
	 * left this network namespace.  This is because
	 * unregister_netdevice_many and netdev_run_todo has completed
	 * for each network device that was in this network namespace.
	 *
	 * As such no additional rcu synchronization is necessary when
	 * freeing the platform_label table.
	 */
	rtnl_lock();
1076 1077 1078 1079 1080
	platform_label = rtnl_dereference(net->mpls.platform_label);
	platform_labels = net->mpls.platform_labels;
	for (index = 0; index < platform_labels; index++) {
		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
		RCU_INIT_POINTER(platform_label[index], NULL);
E
Eric W. Biederman 已提交
1081 1082 1083 1084
		mpls_rt_free(rt);
	}
	rtnl_unlock();

1085
	kvfree(platform_label);
E
Eric W. Biederman 已提交
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
}

static struct pernet_operations mpls_net_ops = {
	.init = mpls_net_init,
	.exit = mpls_net_exit,
};

static int __init mpls_init(void)
{
	int err;

	BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4);

	err = register_pernet_subsys(&mpls_net_ops);
	if (err)
		goto out;

	err = register_netdevice_notifier(&mpls_dev_notifier);
	if (err)
		goto out_unregister_pernet;

	dev_add_pack(&mpls_packet_type);

1109 1110 1111
	rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL);
	rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL);
	rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL);
E
Eric W. Biederman 已提交
1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
	err = 0;
out:
	return err;

out_unregister_pernet:
	unregister_pernet_subsys(&mpls_net_ops);
	goto out;
}
module_init(mpls_init);

static void __exit mpls_exit(void)
{
1124
	rtnl_unregister_all(PF_MPLS);
E
Eric W. Biederman 已提交
1125 1126 1127 1128 1129 1130 1131 1132 1133
	dev_remove_pack(&mpls_packet_type);
	unregister_netdevice_notifier(&mpls_dev_notifier);
	unregister_pernet_subsys(&mpls_net_ops);
}
module_exit(mpls_exit);

MODULE_DESCRIPTION("MultiProtocol Label Switching");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_NETPROTO(PF_MPLS);