af_mpls.c 35.9 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
#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>
18 19 20 21
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
#endif
R
Roopa Prabhu 已提交
22
#include <net/nexthop.h>
E
Eric W. Biederman 已提交
23 24
#include "internal.h"

25 26 27 28 29
/* Maximum number of labels to look ahead at when selecting a path of
 * a multipath route
 */
#define MAX_MP_SELECT_LABELS 4

30 31 32
static int zero = 0;
static int label_limit = (1 << 20) - 1;

33 34 35 36
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
37 38 39 40 41 42 43 44 45 46 47 48
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
49 50 51 52 53
static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
{
	return rcu_dereference_rtnl(dev->mpls_ptr);
}

54
bool mpls_output_possible(const struct net_device *dev)
E
Eric W. Biederman 已提交
55 56 57
{
	return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
}
58
EXPORT_SYMBOL_GPL(mpls_output_possible);
E
Eric W. Biederman 已提交
59

60 61 62 63 64 65 66 67 68 69 70 71 72 73
static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh)
{
	u8 *nh0_via = PTR_ALIGN((u8 *)&rt->rt_nh[rt->rt_nhn], VIA_ALEN_ALIGN);
	int nh_index = nh - rt->rt_nh;

	return nh0_via + rt->rt_max_alen * nh_index;
}

static const u8 *mpls_nh_via(const struct mpls_route *rt,
			     const struct mpls_nh *nh)
{
	return __mpls_nh_via((struct mpls_route *)rt, (struct mpls_nh *)nh);
}

R
Roopa Prabhu 已提交
74
static unsigned int mpls_nh_header_size(const struct mpls_nh *nh)
E
Eric W. Biederman 已提交
75 76
{
	/* The size of the layer 2.5 labels to be added for this route */
R
Roopa Prabhu 已提交
77
	return nh->nh_labels * sizeof(struct mpls_shim_hdr);
E
Eric W. Biederman 已提交
78 79
}

80
unsigned int mpls_dev_mtu(const struct net_device *dev)
E
Eric W. Biederman 已提交
81 82 83 84
{
	/* The amount of data the layer 2 frame can hold */
	return dev->mtu;
}
85
EXPORT_SYMBOL_GPL(mpls_dev_mtu);
E
Eric W. Biederman 已提交
86

87
bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
E
Eric W. Biederman 已提交
88 89 90 91 92 93 94 95 96
{
	if (skb->len <= mtu)
		return false;

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

	return true;
}
97
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
E
Eric W. Biederman 已提交
98

99 100
static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
					     struct sk_buff *skb, bool bos)
R
Roopa Prabhu 已提交
101
{
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
	struct mpls_entry_decoded dec;
	struct mpls_shim_hdr *hdr;
	bool eli_seen = false;
	int label_index;
	int nh_index = 0;
	u32 hash = 0;

	/* No need to look further into packet if there's only
	 * one path
	 */
	if (rt->rt_nhn == 1)
		goto out;

	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
	     label_index++) {
		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
			break;

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

		/* RFC6790 - reserved labels MUST NOT be used as keys
		 * for the load-balancing function
		 */
		if (likely(dec.label >= MPLS_LABEL_FIRST_UNRESERVED)) {
			hash = jhash_1word(dec.label, hash);

			/* The entropy label follows the entropy label
			 * indicator, so this means that the entropy
			 * label was just added to the hash - no need to
			 * go any deeper either in the label stack or in the
			 * payload
			 */
			if (eli_seen)
				break;
		} else if (dec.label == MPLS_LABEL_ENTROPY) {
			eli_seen = true;
		}

		bos = dec.bos;
		if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index +
					 sizeof(struct iphdr))) {
			const struct iphdr *v4hdr;

			v4hdr = (const struct iphdr *)(mpls_hdr(skb) +
						       label_index);
			if (v4hdr->version == 4) {
				hash = jhash_3words(ntohl(v4hdr->saddr),
						    ntohl(v4hdr->daddr),
						    v4hdr->protocol, hash);
			} else if (v4hdr->version == 6 &&
				pskb_may_pull(skb, sizeof(*hdr) * label_index +
					      sizeof(struct ipv6hdr))) {
				const struct ipv6hdr *v6hdr;

				v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) +
								label_index);

				hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
				hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
				hash = jhash_1word(v6hdr->nexthdr, hash);
			}
		}
	}

	nh_index = hash % rt->rt_nhn;
out:
	return &rt->rt_nh[nh_index];
R
Roopa Prabhu 已提交
171 172
}

E
Eric W. Biederman 已提交
173 174 175
static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
			struct mpls_entry_decoded dec)
{
176 177
	enum mpls_payload_type payload_type;
	bool success = false;
E
Eric W. Biederman 已提交
178

179 180 181 182 183 184 185 186 187 188 189 190 191
	/* 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;

192 193 194 195 196 197 198
	payload_type = rt->rt_payload_type;
	if (payload_type == MPT_UNSPEC)
		payload_type = ip_hdr(skb)->version;

	switch (payload_type) {
	case MPT_IPV4: {
		struct iphdr *hdr4 = ip_hdr(skb);
E
Eric W. Biederman 已提交
199 200 201 202 203
		skb->protocol = htons(ETH_P_IP);
		csum_replace2(&hdr4->check,
			      htons(hdr4->ttl << 8),
			      htons(dec.ttl << 8));
		hdr4->ttl = dec.ttl;
204 205
		success = true;
		break;
E
Eric W. Biederman 已提交
206
	}
207
	case MPT_IPV6: {
E
Eric W. Biederman 已提交
208 209 210
		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
		skb->protocol = htons(ETH_P_IPV6);
		hdr6->hop_limit = dec.ttl;
211 212
		success = true;
		break;
E
Eric W. Biederman 已提交
213
	}
214 215 216 217
	case MPT_UNSPEC:
		break;
	}

E
Eric W. Biederman 已提交
218 219 220 221 222 223 224 225 226
	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;
R
Roopa Prabhu 已提交
227
	struct mpls_nh *nh;
E
Eric W. Biederman 已提交
228 229
	struct mpls_entry_decoded dec;
	struct net_device *out_dev;
R
Robert Shearman 已提交
230
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
231 232 233 234 235 236 237
	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
238
	mdev = mpls_dev_get(dev);
239
	if (!mdev || !mdev->input_enabled)
R
Robert Shearman 已提交
240 241
		goto drop;

E
Eric W. Biederman 已提交
242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264
	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;

265
	nh = mpls_select_multipath(rt, skb, dec.bos);
R
Roopa Prabhu 已提交
266 267 268
	if (!nh)
		goto drop;

E
Eric W. Biederman 已提交
269
	/* Find the output device */
R
Roopa Prabhu 已提交
270
	out_dev = rcu_dereference(nh->nh_dev);
E
Eric W. Biederman 已提交
271 272 273 274 275 276 277 278 279
	if (!mpls_output_possible(out_dev))
		goto drop;

	if (skb_warn_if_lro(skb))
		goto drop;

	skb_forward_csum(skb);

	/* Verify ttl is valid */
280
	if (dec.ttl <= 1)
E
Eric W. Biederman 已提交
281 282 283 284
		goto drop;
	dec.ttl -= 1;

	/* Verify the destination can hold the packet */
R
Roopa Prabhu 已提交
285
	new_header_size = mpls_nh_header_size(nh);
E
Eric W. Biederman 已提交
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
	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;
R
Roopa Prabhu 已提交
313 314 315
		for (i = nh->nh_labels - 1; i >= 0; i--) {
			hdr[i] = mpls_entry_encode(nh->nh_label[i],
						   dec.ttl, 0, bos);
E
Eric W. Biederman 已提交
316 317 318 319
			bos = false;
		}
	}

320
	err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb);
E
Eric W. Biederman 已提交
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
	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,
};

336
static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
337 338 339 340
	[RTA_DST]		= { .type = NLA_U32 },
	[RTA_OIF]		= { .type = NLA_U32 },
};

341
struct mpls_route_config {
342 343
	u32			rc_protocol;
	u32			rc_ifindex;
R
Roopa Prabhu 已提交
344 345
	u8			rc_via_table;
	u8			rc_via_alen;
346 347
	u8			rc_via[MAX_VIA_ALEN];
	u32			rc_label;
R
Roopa Prabhu 已提交
348
	u8			rc_output_labels;
349 350 351 352
	u32			rc_output_label[MAX_NEW_LABELS];
	u32			rc_nlflags;
	enum mpls_payload_type	rc_payload_type;
	struct nl_info		rc_nlinfo;
R
Roopa Prabhu 已提交
353 354
	struct rtnexthop	*rc_mp;
	int			rc_mp_len;
355 356
};

357
static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
E
Eric W. Biederman 已提交
358
{
359
	u8 max_alen_aligned = ALIGN(max_alen, VIA_ALEN_ALIGN);
E
Eric W. Biederman 已提交
360 361
	struct mpls_route *rt;

362 363 364
	rt = kzalloc(ALIGN(sizeof(*rt) + num_nh * sizeof(*rt->rt_nh),
			   VIA_ALEN_ALIGN) +
		     num_nh * max_alen_aligned,
R
Roopa Prabhu 已提交
365
		     GFP_KERNEL);
366
	if (rt) {
R
Roopa Prabhu 已提交
367
		rt->rt_nhn = num_nh;
368 369
		rt->rt_max_alen = max_alen_aligned;
	}
R
Roopa Prabhu 已提交
370

E
Eric W. Biederman 已提交
371 372 373 374 375 376 377 378 379
	return rt;
}

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

380 381 382 383 384 385 386 387 388 389
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 */
390
	if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED))
391 392 393
		rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags);
}

E
Eric W. Biederman 已提交
394
static void mpls_route_update(struct net *net, unsigned index,
R
Roopa Prabhu 已提交
395
			      struct mpls_route *new,
E
Eric W. Biederman 已提交
396 397
			      const struct nl_info *info)
{
398
	struct mpls_route __rcu **platform_label;
R
Roopa Prabhu 已提交
399
	struct mpls_route *rt;
E
Eric W. Biederman 已提交
400 401 402

	ASSERT_RTNL();

403 404
	platform_label = rtnl_dereference(net->mpls.platform_label);
	rt = rtnl_dereference(platform_label[index]);
R
Roopa Prabhu 已提交
405
	rcu_assign_pointer(platform_label[index], new);
E
Eric W. Biederman 已提交
406

R
Roopa Prabhu 已提交
407
	mpls_notify_route(net, index, rt, new, info);
408

E
Eric W. Biederman 已提交
409
	/* If we removed a route free it now */
R
Roopa Prabhu 已提交
410
	mpls_rt_free(rt);
E
Eric W. Biederman 已提交
411 412
}

413 414
static unsigned find_free_label(struct net *net)
{
415 416
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
417
	unsigned index;
418 419 420

	platform_label = rtnl_dereference(net->mpls.platform_label);
	platform_labels = net->mpls.platform_labels;
421 422
	for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels;
	     index++) {
423
		if (!rtnl_dereference(platform_label[index]))
424 425 426 427 428
			return index;
	}
	return LABEL_NOT_SPECIFIED;
}

429
#if IS_ENABLED(CONFIG_INET)
430 431
static struct net_device *inet_fib_lookup_dev(struct net *net,
					      const void *addr)
R
Roopa Prabhu 已提交
432
{
433
	struct net_device *dev;
R
Roopa Prabhu 已提交
434 435 436 437 438 439
	struct rtable *rt;
	struct in_addr daddr;

	memcpy(&daddr, addr, sizeof(struct in_addr));
	rt = ip_route_output(net, daddr.s_addr, 0, 0, 0);
	if (IS_ERR(rt))
440
		return ERR_CAST(rt);
R
Roopa Prabhu 已提交
441 442 443 444 445 446 447

	dev = rt->dst.dev;
	dev_hold(dev);

	ip_rt_put(rt);

	return dev;
448 449
}
#else
450 451
static struct net_device *inet_fib_lookup_dev(struct net *net,
					      const void *addr)
452 453
{
	return ERR_PTR(-EAFNOSUPPORT);
R
Roopa Prabhu 已提交
454
}
455
#endif
R
Roopa Prabhu 已提交
456

457
#if IS_ENABLED(CONFIG_IPV6)
458 459
static struct net_device *inet6_fib_lookup_dev(struct net *net,
					       const void *addr)
R
Roopa Prabhu 已提交
460
{
461
	struct net_device *dev;
R
Roopa Prabhu 已提交
462 463
	struct dst_entry *dst;
	struct flowi6 fl6;
464 465 466 467
	int err;

	if (!ipv6_stub)
		return ERR_PTR(-EAFNOSUPPORT);
R
Roopa Prabhu 已提交
468 469 470

	memset(&fl6, 0, sizeof(fl6));
	memcpy(&fl6.daddr, addr, sizeof(struct in6_addr));
471 472
	err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6);
	if (err)
473
		return ERR_PTR(err);
R
Roopa Prabhu 已提交
474 475 476 477 478 479 480

	dev = dst->dev;
	dev_hold(dev);
	dst_release(dst);

	return dev;
}
481
#else
482 483
static struct net_device *inet6_fib_lookup_dev(struct net *net,
					       const void *addr)
484 485 486 487
{
	return ERR_PTR(-EAFNOSUPPORT);
}
#endif
R
Roopa Prabhu 已提交
488 489

static struct net_device *find_outdev(struct net *net,
490
				      struct mpls_route *rt,
R
Roopa Prabhu 已提交
491
				      struct mpls_nh *nh, int oif)
R
Roopa Prabhu 已提交
492 493 494
{
	struct net_device *dev = NULL;

R
Roopa Prabhu 已提交
495 496
	if (!oif) {
		switch (nh->nh_via_table) {
R
Roopa Prabhu 已提交
497
		case NEIGH_ARP_TABLE:
498
			dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh));
R
Roopa Prabhu 已提交
499 500
			break;
		case NEIGH_ND_TABLE:
501
			dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh));
R
Roopa Prabhu 已提交
502 503 504 505 506
			break;
		case NEIGH_LINK_TABLE:
			break;
		}
	} else {
R
Roopa Prabhu 已提交
507
		dev = dev_get_by_index(net, oif);
R
Roopa Prabhu 已提交
508 509
	}

510 511 512
	if (!dev)
		return ERR_PTR(-ENODEV);

R
Roopa Prabhu 已提交
513 514 515
	/* The caller is holding rtnl anyways, so release the dev reference */
	dev_put(dev);

R
Roopa Prabhu 已提交
516 517 518
	return dev;
}

519 520
static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
			      struct mpls_nh *nh, int oif)
R
Roopa Prabhu 已提交
521 522 523 524
{
	struct net_device *dev = NULL;
	int err = -ENODEV;

525
	dev = find_outdev(net, rt, nh, oif);
R
Roopa Prabhu 已提交
526 527 528 529 530 531 532 533 534 535 536
	if (IS_ERR(dev)) {
		err = PTR_ERR(dev);
		dev = NULL;
		goto errout;
	}

	/* Ensure this is a supported device */
	err = -EINVAL;
	if (!mpls_dev_get(dev))
		goto errout;

537 538 539 540
	if ((nh->nh_via_table == NEIGH_LINK_TABLE) &&
	    (dev->addr_len != nh->nh_via_alen))
		goto errout;

R
Roopa Prabhu 已提交
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
	RCU_INIT_POINTER(nh->nh_dev, dev);

	return 0;

errout:
	return err;
}

static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
				  struct mpls_route *rt)
{
	struct net *net = cfg->rc_nlinfo.nl_net;
	struct mpls_nh *nh = rt->rt_nh;
	int err;
	int i;

	if (!nh)
		return -ENOMEM;

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

	nh->nh_labels = cfg->rc_output_labels;
	for (i = 0; i < nh->nh_labels; i++)
		nh->nh_label[i] = cfg->rc_output_label[i];

	nh->nh_via_table = cfg->rc_via_table;
570
	memcpy(__mpls_nh_via(rt, nh), cfg->rc_via, cfg->rc_via_alen);
R
Roopa Prabhu 已提交
571 572
	nh->nh_via_alen = cfg->rc_via_alen;

573
	err = mpls_nh_assign_dev(net, rt, nh, cfg->rc_ifindex);
R
Roopa Prabhu 已提交
574 575 576 577 578 579 580 581 582
	if (err)
		goto errout;

	return 0;

errout:
	return err;
}

583 584 585
static int mpls_nh_build(struct net *net, struct mpls_route *rt,
			 struct mpls_nh *nh, int oif,
			 struct nlattr *via, struct nlattr *newdst)
R
Roopa Prabhu 已提交
586 587 588 589 590 591 592 593 594 595 596 597 598 599
{
	int err = -ENOMEM;

	if (!nh)
		goto errout;

	if (newdst) {
		err = nla_get_labels(newdst, MAX_NEW_LABELS,
				     &nh->nh_labels, nh->nh_label);
		if (err)
			goto errout;
	}

	err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table,
600
			  __mpls_nh_via(rt, nh));
R
Roopa Prabhu 已提交
601 602 603
	if (err)
		goto errout;

604
	err = mpls_nh_assign_dev(net, rt, nh, oif);
R
Roopa Prabhu 已提交
605 606 607 608 609 610 611 612 613
	if (err)
		goto errout;

	return 0;

errout:
	return err;
}

614 615
static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
			       u8 cfg_via_alen, u8 *max_via_alen)
R
Roopa Prabhu 已提交
616 617 618 619
{
	int nhs = 0;
	int remaining = len;

620 621 622 623 624 625 626
	if (!rtnh) {
		*max_via_alen = cfg_via_alen;
		return 1;
	}

	*max_via_alen = 0;

R
Roopa Prabhu 已提交
627
	while (rtnh_ok(rtnh, remaining)) {
628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
		struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
		int attrlen;

		attrlen = rtnh_attrlen(rtnh);
		nla = nla_find(attrs, attrlen, RTA_VIA);
		if (nla && nla_len(nla) >=
		    offsetof(struct rtvia, rtvia_addr)) {
			int via_alen = nla_len(nla) -
				offsetof(struct rtvia, rtvia_addr);

			if (via_alen <= MAX_VIA_ALEN)
				*max_via_alen = max_t(u16, *max_via_alen,
						      via_alen);
		}

R
Roopa Prabhu 已提交
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
		nhs++;
		rtnh = rtnh_next(rtnh, &remaining);
	}

	/* leftover implies invalid nexthop configuration, discard it */
	return remaining > 0 ? 0 : nhs;
}

static int mpls_nh_build_multi(struct mpls_route_config *cfg,
			       struct mpls_route *rt)
{
	struct rtnexthop *rtnh = cfg->rc_mp;
	struct nlattr *nla_via, *nla_newdst;
	int remaining = cfg->rc_mp_len;
	int nhs = 0;
	int err = 0;

	change_nexthops(rt) {
		int attrlen;

		nla_via = NULL;
		nla_newdst = NULL;

		err = -EINVAL;
		if (!rtnh_ok(rtnh, remaining))
			goto errout;

670 671 672 673 674 675
		/* neither weighted multipath nor any flags
		 * are supported
		 */
		if (rtnh->rtnh_hops || rtnh->rtnh_flags)
			goto errout;

R
Roopa Prabhu 已提交
676 677 678 679 680 681 682 683 684 685 686
		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
			struct nlattr *attrs = rtnh_attrs(rtnh);

			nla_via = nla_find(attrs, attrlen, RTA_VIA);
			nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST);
		}

		if (!nla_via)
			goto errout;

687
		err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
R
Roopa Prabhu 已提交
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
				    rtnh->rtnh_ifindex, nla_via,
				    nla_newdst);
		if (err)
			goto errout;

		rtnh = rtnh_next(rtnh, &remaining);
		nhs++;
	} endfor_nexthops(rt);

	rt->rt_nhn = nhs;

	return 0;

errout:
	return err;
}

705 706
static int mpls_route_add(struct mpls_route_config *cfg)
{
707
	struct mpls_route __rcu **platform_label;
708 709 710
	struct net *net = cfg->rc_nlinfo.nl_net;
	struct mpls_route *rt, *old;
	int err = -EINVAL;
711
	u8 max_via_alen;
R
Roopa Prabhu 已提交
712
	unsigned index;
713
	int nhs;
714 715 716 717 718 719 720 721 722

	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);
	}

723 724
	/* Reserved labels may not be set */
	if (index < MPLS_LABEL_FIRST_UNRESERVED)
725 726 727 728 729 730 731
		goto errout;

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

	/* Append makes no sense with mpls */
732
	err = -EOPNOTSUPP;
733 734 735 736
	if (cfg->rc_nlflags & NLM_F_APPEND)
		goto errout;

	err = -EEXIST;
737 738
	platform_label = rtnl_dereference(net->mpls.platform_label);
	old = rtnl_dereference(platform_label[index]);
739 740 741 742 743 744 745 746 747 748 749
	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;

750 751 752 753 754
	err = -EINVAL;
	nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
				  cfg->rc_via_alen, &max_via_alen);
	if (nhs == 0)
		goto errout;
R
Roopa Prabhu 已提交
755

756
	err = -ENOMEM;
757
	rt = mpls_rt_alloc(nhs, max_via_alen);
758 759 760 761
	if (!rt)
		goto errout;

	rt->rt_protocol = cfg->rc_protocol;
762
	rt->rt_payload_type = cfg->rc_payload_type;
763

R
Roopa Prabhu 已提交
764 765 766 767 768 769 770 771
	if (cfg->rc_mp)
		err = mpls_nh_build_multi(cfg, rt);
	else
		err = mpls_nh_build_from_cfg(cfg, rt);
	if (err)
		goto freert;

	mpls_route_update(net, index, rt, &cfg->rc_nlinfo);
772 773 774

	return 0;

R
Roopa Prabhu 已提交
775 776
freert:
	mpls_rt_free(rt);
777 778 779 780 781 782 783 784 785 786 787 788
errout:
	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;

789 790
	/* Reserved labels may not be removed */
	if (index < MPLS_LABEL_FIRST_UNRESERVED)
791 792 793 794 795 796
		goto errout;

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

R
Roopa Prabhu 已提交
797
	mpls_route_update(net, index, NULL, &cfg->rc_nlinfo);
798 799 800 801 802 803

	err = 0;
errout:
	return err;
}

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
#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
858 859 860 861 862 863 864 865 866 867 868
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);

869 870 871 872
	err = mpls_dev_sysctl_register(dev, mdev);
	if (err)
		goto free;

R
Robert Shearman 已提交
873 874 875
	rcu_assign_pointer(dev->mpls_ptr, mdev);

	return mdev;
876 877 878 879

free:
	kfree(mdev);
	return ERR_PTR(err);
R
Robert Shearman 已提交
880 881
}

E
Eric W. Biederman 已提交
882 883
static void mpls_ifdown(struct net_device *dev)
{
884
	struct mpls_route __rcu **platform_label;
E
Eric W. Biederman 已提交
885
	struct net *net = dev_net(dev);
R
Robert Shearman 已提交
886
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
887 888
	unsigned index;

889
	platform_label = rtnl_dereference(net->mpls.platform_label);
E
Eric W. Biederman 已提交
890
	for (index = 0; index < net->mpls.platform_labels; index++) {
891
		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
E
Eric W. Biederman 已提交
892 893
		if (!rt)
			continue;
R
Roopa Prabhu 已提交
894 895 896 897 898
		for_nexthops(rt) {
			if (rtnl_dereference(nh->nh_dev) != dev)
				continue;
			nh->nh_dev = NULL;
		} endfor_nexthops(rt);
E
Eric W. Biederman 已提交
899
	}
R
Robert Shearman 已提交
900 901 902 903 904

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

905 906
	mpls_dev_sysctl_unregister(mdev);

R
Robert Shearman 已提交
907 908
	RCU_INIT_POINTER(dev->mpls_ptr, NULL);

909
	kfree_rcu(mdev, rcu);
E
Eric W. Biederman 已提交
910 911 912 913 914 915
}

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
916
	struct mpls_dev *mdev;
E
Eric W. Biederman 已提交
917 918

	switch(event) {
R
Robert Shearman 已提交
919 920 921 922 923 924 925 926 927 928
	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
929 930 931
	case NETDEV_UNREGISTER:
		mpls_ifdown(dev);
		break;
932 933 934 935 936 937 938 939 940 941 942
	case NETDEV_CHANGENAME:
		mdev = mpls_dev_get(dev);
		if (mdev) {
			int err;

			mpls_dev_sysctl_unregister(mdev);
			err = mpls_dev_sysctl_register(dev, mdev);
			if (err)
				return notifier_from_errno(err);
		}
		break;
E
Eric W. Biederman 已提交
943 944 945 946 947 948 949 950
	}
	return NOTIFY_OK;
}

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

951
static int nla_put_via(struct sk_buff *skb,
952
		       u8 table, const void *addr, int alen)
953
{
954 955 956
	static const int table_to_family[NEIGH_NR_TABLES + 1] = {
		AF_INET, AF_INET6, AF_DECnet, AF_PACKET,
	};
957 958
	struct nlattr *nla;
	struct rtvia *via;
959
	int family = AF_UNSPEC;
960 961 962 963 964

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

965 966 967
	if (table <= NEIGH_NR_TABLES)
		family = table_to_family[table];

968 969 970 971 972 973
	via = nla_data(nla);
	via->rtvia_family = family;
	memcpy(via->rtvia_addr, addr, alen);
	return 0;
}

974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
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;
}
994
EXPORT_SYMBOL_GPL(nla_put_labels);
995 996

int nla_get_labels(const struct nlattr *nla,
R
Roopa Prabhu 已提交
997
		   u32 max_labels, u8 *labels, u32 label[])
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
{
	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;

1026
		switch (dec.label) {
1027
		case MPLS_LABEL_IMPLNULL:
1028 1029 1030 1031 1032 1033 1034
			/* RFC3032: This is a label that an LSR may
			 * assign and distribute, but which never
			 * actually appears in the encapsulation.
			 */
			return -EINVAL;
		}

1035 1036 1037 1038 1039
		label[i] = dec.label;
	}
	*labels = nla_labels;
	return 0;
}
1040
EXPORT_SYMBOL_GPL(nla_get_labels);
1041

R
Roopa Prabhu 已提交
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 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
int nla_get_via(const struct nlattr *nla, u8 *via_alen,
		u8 *via_table, u8 via_addr[])
{
	struct rtvia *via = nla_data(nla);
	int err = -EINVAL;
	int alen;

	if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr))
		goto errout;
	alen = nla_len(nla) -
			offsetof(struct rtvia, rtvia_addr);
	if (alen > MAX_VIA_ALEN)
		goto errout;

	/* Validate the address family */
	switch (via->rtvia_family) {
	case AF_PACKET:
		*via_table = NEIGH_LINK_TABLE;
		break;
	case AF_INET:
		*via_table = NEIGH_ARP_TABLE;
		if (alen != 4)
			goto errout;
		break;
	case AF_INET6:
		*via_table = NEIGH_ND_TABLE;
		if (alen != 16)
			goto errout;
		break;
	default:
		/* Unsupported address family */
		goto errout;
	}

	memcpy(via_addr, via->rtvia_addr, alen);
	*via_alen = alen;
	err = 0;

errout:
	return err;
}

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
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:
		{
R
Roopa Prabhu 已提交
1147
			u8 label_count;
1148 1149 1150 1151
			if (nla_get_labels(nla, 1, &label_count,
					   &cfg->rc_label))
				goto errout;

1152 1153
			/* Reserved labels may not be set */
			if (cfg->rc_label < MPLS_LABEL_FIRST_UNRESERVED)
1154 1155 1156 1157 1158 1159
				goto errout;

			break;
		}
		case RTA_VIA:
		{
R
Roopa Prabhu 已提交
1160 1161
			if (nla_get_via(nla, &cfg->rc_via_alen,
					&cfg->rc_via_table, cfg->rc_via))
1162
				goto errout;
R
Roopa Prabhu 已提交
1163 1164 1165 1166 1167 1168
			break;
		}
		case RTA_MULTIPATH:
		{
			cfg->rc_mp = nla_data(nla);
			cfg->rc_mp_len = nla_len(nla);
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
			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)
{
1210
	struct net_device *dev;
1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
	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 (nla_put_labels(skb, RTA_DST, 1, &label))
		goto nla_put_failure;
R
Roopa Prabhu 已提交
1231
	if (rt->rt_nhn == 1) {
1232
		const struct mpls_nh *nh = rt->rt_nh;
R
Roopa Prabhu 已提交
1233 1234 1235 1236 1237

		if (nh->nh_labels &&
		    nla_put_labels(skb, RTA_NEWDST, nh->nh_labels,
				   nh->nh_label))
			goto nla_put_failure;
1238 1239 1240
		if ((nh->nh_via_table != NEIGH_ARP_TABLE ||
		     nh->nh_via_alen != 0) &&
		    nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
R
Roopa Prabhu 已提交
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
				nh->nh_via_alen))
			goto nla_put_failure;
		dev = rtnl_dereference(nh->nh_dev);
		if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
			goto nla_put_failure;
	} else {
		struct rtnexthop *rtnh;
		struct nlattr *mp;

		mp = nla_nest_start(skb, RTA_MULTIPATH);
		if (!mp)
			goto nla_put_failure;

		for_nexthops(rt) {
			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
			if (!rtnh)
				goto nla_put_failure;

			dev = rtnl_dereference(nh->nh_dev);
			if (dev)
				rtnh->rtnh_ifindex = dev->ifindex;
			if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST,
							    nh->nh_labels,
							    nh->nh_label))
				goto nla_put_failure;
			if (nla_put_via(skb, nh->nh_via_table,
1267
					mpls_nh_via(rt, nh),
R
Roopa Prabhu 已提交
1268 1269 1270 1271 1272 1273 1274 1275 1276
					nh->nh_via_alen))
				goto nla_put_failure;

			/* length of rtnetlink header + attributes */
			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
		} endfor_nexthops(rt);

		nla_nest_end(skb, mp);
	}
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288

	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);
1289 1290
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
1291 1292 1293 1294 1295
	unsigned int index;

	ASSERT_RTNL();

	index = cb->args[0];
1296 1297
	if (index < MPLS_LABEL_FIRST_UNRESERVED)
		index = MPLS_LABEL_FIRST_UNRESERVED;
1298

1299 1300 1301
	platform_label = rtnl_dereference(net->mpls.platform_label);
	platform_labels = net->mpls.platform_labels;
	for (; index < platform_labels; index++) {
1302
		struct mpls_route *rt;
1303
		rt = rtnl_dereference(platform_label[index]);
1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316
		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;
}

1317 1318 1319 1320 1321
static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
{
	size_t payload =
		NLMSG_ALIGN(sizeof(struct rtmsg))
		+ nla_total_size(4);			/* RTA_DST */
R
Roopa Prabhu 已提交
1322 1323 1324 1325 1326 1327

	if (rt->rt_nhn == 1) {
		struct mpls_nh *nh = rt->rt_nh;

		if (nh->nh_dev)
			payload += nla_total_size(4); /* RTA_OIF */
1328 1329 1330
		if (nh->nh_via_table != NEIGH_ARP_TABLE ||
		    nh->nh_via_alen != 0) /* RTA_VIA */
			payload += nla_total_size(2 + nh->nh_via_alen);
R
Roopa Prabhu 已提交
1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
		if (nh->nh_labels) /* RTA_NEWDST */
			payload += nla_total_size(nh->nh_labels * 4);
	} else {
		/* each nexthop is packed in an attribute */
		size_t nhsize = 0;

		for_nexthops(rt) {
			nhsize += nla_total_size(sizeof(struct rtnexthop));
			nhsize += nla_total_size(2 + nh->nh_via_alen);
			if (nh->nh_labels)
				nhsize += nla_total_size(nh->nh_labels * 4);
		} endfor_nexthops(rt);
		/* nested attribute */
		payload += nla_total_size(nhsize);
	}

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
	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);
}

1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395
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 */
1396
	if (limit > MPLS_LABEL_IPV4NULL) {
1397
		struct net_device *lo = net->loopback_dev;
1398
		rt0 = mpls_rt_alloc(1, lo->addr_len);
1399 1400
		if (!rt0)
			goto nort0;
R
Roopa Prabhu 已提交
1401
		RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
1402
		rt0->rt_protocol = RTPROT_KERNEL;
1403
		rt0->rt_payload_type = MPT_IPV4;
R
Roopa Prabhu 已提交
1404
		rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
1405
		rt0->rt_nh->nh_via_alen = lo->addr_len;
1406 1407
		memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr,
		       lo->addr_len);
1408
	}
1409
	if (limit > MPLS_LABEL_IPV6NULL) {
1410
		struct net_device *lo = net->loopback_dev;
1411
		rt2 = mpls_rt_alloc(1, lo->addr_len);
1412 1413
		if (!rt2)
			goto nort2;
R
Roopa Prabhu 已提交
1414
		RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
1415
		rt2->rt_protocol = RTPROT_KERNEL;
1416
		rt2->rt_payload_type = MPT_IPV6;
R
Roopa Prabhu 已提交
1417
		rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
1418
		rt2->rt_nh->nh_via_alen = lo->addr_len;
1419 1420
		memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr,
		       lo->addr_len);
1421 1422 1423 1424
	}

	rtnl_lock();
	/* Remember the original table */
1425
	old = rtnl_dereference(net->mpls.platform_label);
1426 1427 1428 1429
	old_limit = net->mpls.platform_labels;

	/* Free any labels beyond the new table */
	for (index = limit; index < old_limit; index++)
R
Roopa Prabhu 已提交
1430
		mpls_route_update(net, index, NULL, NULL);
1431 1432 1433 1434 1435 1436 1437 1438 1439

	/* 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 */
1440 1441 1442
	if ((old_limit <= MPLS_LABEL_IPV6NULL) &&
	    (limit > MPLS_LABEL_IPV6NULL)) {
		RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2);
1443 1444 1445
		rt2 = NULL;
	}

1446 1447 1448
	if ((old_limit <= MPLS_LABEL_IPV4NULL) &&
	    (limit > MPLS_LABEL_IPV4NULL)) {
		RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0);
1449 1450 1451 1452 1453
		rt0 = NULL;
	}

	/* Update the global pointers */
	net->mpls.platform_labels = limit;
1454
	rcu_assign_pointer(net->mpls.platform_label, labels);
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

	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;
}

1498
static const struct ctl_table mpls_table[] = {
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508
	{
		.procname	= "platform_labels",
		.data		= NULL,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= mpls_platform_labels,
	},
	{ }
};

E
Eric W. Biederman 已提交
1509 1510
static int mpls_net_init(struct net *net)
{
1511 1512
	struct ctl_table *table;

E
Eric W. Biederman 已提交
1513 1514 1515
	net->mpls.platform_labels = 0;
	net->mpls.platform_label = NULL;

1516 1517 1518 1519 1520 1521
	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);
1522 1523
	if (net->mpls.ctl == NULL) {
		kfree(table);
1524
		return -ENOMEM;
1525
	}
1526

E
Eric W. Biederman 已提交
1527 1528 1529 1530 1531
	return 0;
}

static void mpls_net_exit(struct net *net)
{
1532 1533
	struct mpls_route __rcu **platform_label;
	size_t platform_labels;
1534
	struct ctl_table *table;
E
Eric W. Biederman 已提交
1535 1536
	unsigned int index;

1537 1538 1539 1540
	table = net->mpls.ctl->ctl_table_arg;
	unregister_net_sysctl_table(net->mpls.ctl);
	kfree(table);

1541 1542
	/* 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
1543 1544 1545 1546 1547 1548 1549 1550
	 * 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();
1551 1552 1553 1554 1555
	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
1556 1557 1558 1559
		mpls_rt_free(rt);
	}
	rtnl_unlock();

1560
	kvfree(platform_label);
E
Eric W. Biederman 已提交
1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583
}

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);

1584 1585 1586
	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
1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598
	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)
{
1599
	rtnl_unregister_all(PF_MPLS);
E
Eric W. Biederman 已提交
1600 1601 1602 1603 1604 1605 1606 1607 1608
	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);