br_multicast.c 39.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * Bridge multicast support.
 *
 * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option)
 * any later version.
 *
 */

#include <linux/err.h>
#include <linux/if_ether.h>
#include <linux/igmp.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
18
#include <linux/log2.h>
19 20 21 22 23 24 25 26
#include <linux/netdevice.h>
#include <linux/netfilter_bridge.h>
#include <linux/random.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <net/ip.h>
E
Eric Dumazet 已提交
27
#if IS_ENABLED(CONFIG_IPV6)
28 29
#include <net/ipv6.h>
#include <net/mld.h>
30
#include <net/ip6_checksum.h>
31
#endif
32 33 34

#include "br_private.h"

35
static void br_multicast_start_querier(struct net_bridge *br);
C
Cong Wang 已提交
36
unsigned int br_mdb_rehash_seq;
37

38 39 40 41 42 43 44
static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
{
	if (a->proto != b->proto)
		return 0;
	switch (a->proto) {
	case htons(ETH_P_IP):
		return a->u.ip4 == b->u.ip4;
E
Eric Dumazet 已提交
45
#if IS_ENABLED(CONFIG_IPV6)
46 47 48
	case htons(ETH_P_IPV6):
		return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
#endif
49 50 51 52 53
	}
	return 0;
}

static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
54
{
55
	return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
56 57
}

E
Eric Dumazet 已提交
58
#if IS_ENABLED(CONFIG_IPV6)
59 60 61 62 63 64 65
static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
				const struct in6_addr *ip)
{
	return jhash2((__force u32 *)ip->s6_addr32, 4, mdb->secret) & (mdb->max - 1);
}
#endif

66 67 68 69 70 71
static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb,
			     struct br_ip *ip)
{
	switch (ip->proto) {
	case htons(ETH_P_IP):
		return __br_ip4_hash(mdb, ip->u.ip4);
E
Eric Dumazet 已提交
72
#if IS_ENABLED(CONFIG_IPV6)
73 74 75
	case htons(ETH_P_IPV6):
		return __br_ip6_hash(mdb, &ip->u.ip6);
#endif
76 77
	}
	return 0;
78 79 80
}

static struct net_bridge_mdb_entry *__br_mdb_ip_get(
81
	struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash)
82 83 84 85
{
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p;

86
	hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
87
		if (br_ip_equal(&mp->addr, dst))
88 89 90 91 92 93
			return mp;
	}

	return NULL;
}

94 95
struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb,
					   struct br_ip *dst)
96 97 98 99 100 101 102
{
	if (!mdb)
		return NULL;

	return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst));
}

103
static struct net_bridge_mdb_entry *br_mdb_ip4_get(
104 105
	struct net_bridge_mdb_htable *mdb, __be32 dst)
{
106 107 108 109
	struct br_ip br_dst;

	br_dst.u.ip4 = dst;
	br_dst.proto = htons(ETH_P_IP);
110

111
	return br_mdb_ip_get(mdb, &br_dst);
112 113
}

E
Eric Dumazet 已提交
114
#if IS_ENABLED(CONFIG_IPV6)
115 116 117 118
static struct net_bridge_mdb_entry *br_mdb_ip6_get(
	struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst)
{
	struct br_ip br_dst;
119

A
Alexey Dobriyan 已提交
120
	br_dst.u.ip6 = *dst;
121 122
	br_dst.proto = htons(ETH_P_IPV6);

123
	return br_mdb_ip_get(mdb, &br_dst);
124 125 126
}
#endif

127 128 129
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
					struct sk_buff *skb)
{
130
	struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb);
131 132
	struct br_ip ip;

133
	if (br->multicast_disabled)
134 135
		return NULL;

136
	if (BR_INPUT_SKB_CB(skb)->igmp)
137 138
		return NULL;

139 140
	ip.proto = skb->protocol;

141 142
	switch (skb->protocol) {
	case htons(ETH_P_IP):
143 144
		ip.u.ip4 = ip_hdr(skb)->daddr;
		break;
E
Eric Dumazet 已提交
145
#if IS_ENABLED(CONFIG_IPV6)
146
	case htons(ETH_P_IPV6):
A
Alexey Dobriyan 已提交
147
		ip.u.ip6 = ipv6_hdr(skb)->daddr;
148 149
		break;
#endif
150 151
	default:
		return NULL;
152 153
	}

154
	return br_mdb_ip_get(mdb, &ip);
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180
}

static void br_mdb_free(struct rcu_head *head)
{
	struct net_bridge_mdb_htable *mdb =
		container_of(head, struct net_bridge_mdb_htable, rcu);
	struct net_bridge_mdb_htable *old = mdb->old;

	mdb->old = NULL;
	kfree(old->mhash);
	kfree(old);
}

static int br_mdb_copy(struct net_bridge_mdb_htable *new,
		       struct net_bridge_mdb_htable *old,
		       int elasticity)
{
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p;
	int maxlen;
	int len;
	int i;

	for (i = 0; i < old->max; i++)
		hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver])
			hlist_add_head(&mp->hlist[new->ver],
181
				       &new->mhash[br_ip_hash(new, &mp->addr)]);
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197

	if (!elasticity)
		return 0;

	maxlen = 0;
	for (i = 0; i < new->max; i++) {
		len = 0;
		hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver])
			len++;
		if (len > maxlen)
			maxlen = len;
	}

	return maxlen > elasticity ? -EINVAL : 0;
}

198
void br_multicast_free_pg(struct rcu_head *head)
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
{
	struct net_bridge_port_group *p =
		container_of(head, struct net_bridge_port_group, rcu);

	kfree(p);
}

static void br_multicast_free_group(struct rcu_head *head)
{
	struct net_bridge_mdb_entry *mp =
		container_of(head, struct net_bridge_mdb_entry, rcu);

	kfree(mp);
}

static void br_multicast_group_expired(unsigned long data)
{
	struct net_bridge_mdb_entry *mp = (void *)data;
	struct net_bridge *br = mp->br;
	struct net_bridge_mdb_htable *mdb;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || timer_pending(&mp->timer))
		goto out;

224
	mp->mglist = false;
225 226 227 228

	if (mp->ports)
		goto out;

229 230
	mdb = mlock_dereference(br->mdb, br);

231 232 233 234 235 236 237 238 239 240 241 242
	hlist_del_rcu(&mp->hlist[mdb->ver]);
	mdb->size--;

	call_rcu_bh(&mp->rcu, br_multicast_free_group);

out:
	spin_unlock(&br->multicast_lock);
}

static void br_multicast_del_pg(struct net_bridge *br,
				struct net_bridge_port_group *pg)
{
243
	struct net_bridge_mdb_htable *mdb;
244 245
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
246 247 248
	struct net_bridge_port_group __rcu **pp;

	mdb = mlock_dereference(br->mdb, br);
249

250
	mp = br_mdb_ip_get(mdb, &pg->addr);
251 252 253
	if (WARN_ON(!mp))
		return;

254 255 256
	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
257 258 259
		if (p != pg)
			continue;

260
		rcu_assign_pointer(*pp, p->next);
261 262 263 264
		hlist_del_init(&p->mglist);
		del_timer(&p->timer);
		call_rcu_bh(&p->rcu, br_multicast_free_pg);

265
		if (!mp->ports && !mp->mglist &&
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
		    netif_running(br->dev))
			mod_timer(&mp->timer, jiffies);

		return;
	}

	WARN_ON(1);
}

static void br_multicast_port_group_expired(unsigned long data)
{
	struct net_bridge_port_group *pg = (void *)data;
	struct net_bridge *br = pg->port->br;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
	    hlist_unhashed(&pg->mglist))
		goto out;

	br_multicast_del_pg(br, pg);

out:
	spin_unlock(&br->multicast_lock);
}

291
static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max,
292 293
			 int elasticity)
{
294
	struct net_bridge_mdb_htable *old = rcu_dereference_protected(*mdbp, 1);
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
	struct net_bridge_mdb_htable *mdb;
	int err;

	mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC);
	if (!mdb)
		return -ENOMEM;

	mdb->max = max;
	mdb->old = old;

	mdb->mhash = kzalloc(max * sizeof(*mdb->mhash), GFP_ATOMIC);
	if (!mdb->mhash) {
		kfree(mdb);
		return -ENOMEM;
	}

	mdb->size = old ? old->size : 0;
	mdb->ver = old ? old->ver ^ 1 : 0;

	if (!old || elasticity)
		get_random_bytes(&mdb->secret, sizeof(mdb->secret));
	else
		mdb->secret = old->secret;

	if (!old)
		goto out;

	err = br_mdb_copy(mdb, old, elasticity);
	if (err) {
		kfree(mdb->mhash);
		kfree(mdb);
		return err;
	}

C
Cong Wang 已提交
329
	br_mdb_rehash_seq++;
330 331 332 333 334 335 336 337
	call_rcu_bh(&mdb->rcu, br_mdb_free);

out:
	rcu_assign_pointer(*mdbp, mdb);

	return 0;
}

338 339
static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
						    __be32 group)
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
{
	struct sk_buff *skb;
	struct igmphdr *ih;
	struct ethhdr *eth;
	struct iphdr *iph;

	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) +
						 sizeof(*ih) + 4);
	if (!skb)
		goto out;

	skb->protocol = htons(ETH_P_IP);

	skb_reset_mac_header(skb);
	eth = eth_hdr(skb);

	memcpy(eth->h_source, br->dev->dev_addr, 6);
	eth->h_dest[0] = 1;
	eth->h_dest[1] = 0;
	eth->h_dest[2] = 0x5e;
	eth->h_dest[3] = 0;
	eth->h_dest[4] = 0;
	eth->h_dest[5] = 1;
	eth->h_proto = htons(ETH_P_IP);
	skb_put(skb, sizeof(*eth));

	skb_set_network_header(skb, skb->len);
	iph = ip_hdr(skb);

	iph->version = 4;
	iph->ihl = 6;
	iph->tos = 0xc0;
	iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4);
	iph->id = 0;
	iph->frag_off = htons(IP_DF);
	iph->ttl = 1;
	iph->protocol = IPPROTO_IGMP;
	iph->saddr = 0;
	iph->daddr = htonl(INADDR_ALLHOSTS_GROUP);
	((u8 *)&iph[1])[0] = IPOPT_RA;
	((u8 *)&iph[1])[1] = 4;
	((u8 *)&iph[1])[2] = 0;
	((u8 *)&iph[1])[3] = 0;
	ip_send_check(iph);
	skb_put(skb, 24);

	skb_set_transport_header(skb, skb->len);
	ih = igmp_hdr(skb);
	ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
	ih->code = (group ? br->multicast_last_member_interval :
			    br->multicast_query_response_interval) /
		   (HZ / IGMP_TIMER_SCALE);
	ih->group = group;
	ih->csum = 0;
	ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr));
	skb_put(skb, sizeof(*ih));

	__skb_pull(skb, sizeof(*eth));

out:
	return skb;
}

E
Eric Dumazet 已提交
403
#if IS_ENABLED(CONFIG_IPV6)
404
static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
405
						    const struct in6_addr *group)
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
{
	struct sk_buff *skb;
	struct ipv6hdr *ip6h;
	struct mld_msg *mldq;
	struct ethhdr *eth;
	u8 *hopopt;
	unsigned long interval;

	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) +
						 8 + sizeof(*mldq));
	if (!skb)
		goto out;

	skb->protocol = htons(ETH_P_IPV6);

	/* Ethernet header */
	skb_reset_mac_header(skb);
	eth = eth_hdr(skb);

	memcpy(eth->h_source, br->dev->dev_addr, 6);
	eth->h_proto = htons(ETH_P_IPV6);
	skb_put(skb, sizeof(*eth));

	/* IPv6 header + HbH option */
	skb_set_network_header(skb, skb->len);
	ip6h = ipv6_hdr(skb);

	*(__force __be32 *)ip6h = htonl(0x60000000);
434
	ip6h->payload_len = htons(8 + sizeof(*mldq));
435 436
	ip6h->nexthdr = IPPROTO_HOPOPTS;
	ip6h->hop_limit = 1;
437
	ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
438 439 440 441 442
	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
			       &ip6h->saddr)) {
		kfree_skb(skb);
		return NULL;
	}
443
	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
444 445 446 447 448 449 450 451

	hopopt = (u8 *)(ip6h + 1);
	hopopt[0] = IPPROTO_ICMPV6;		/* next hdr */
	hopopt[1] = 0;				/* length of HbH */
	hopopt[2] = IPV6_TLV_ROUTERALERT;	/* Router Alert */
	hopopt[3] = 2;				/* Length of RA Option */
	hopopt[4] = 0;				/* Type = 0x0000 (MLD) */
	hopopt[5] = 0;
452 453
	hopopt[6] = IPV6_TLV_PAD1;		/* Pad1 */
	hopopt[7] = IPV6_TLV_PAD1;		/* Pad1 */
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468

	skb_put(skb, sizeof(*ip6h) + 8);

	/* ICMPv6 */
	skb_set_transport_header(skb, skb->len);
	mldq = (struct mld_msg *) icmp6_hdr(skb);

	interval = ipv6_addr_any(group) ? br->multicast_last_member_interval :
					  br->multicast_query_response_interval;

	mldq->mld_type = ICMPV6_MGM_QUERY;
	mldq->mld_code = 0;
	mldq->mld_cksum = 0;
	mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
	mldq->mld_reserved = 0;
A
Alexey Dobriyan 已提交
469
	mldq->mld_mca = *group;
470 471 472 473 474 475 476 477 478 479 480 481 482 483 484

	/* checksum */
	mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
					  sizeof(*mldq), IPPROTO_ICMPV6,
					  csum_partial(mldq,
						       sizeof(*mldq), 0));
	skb_put(skb, sizeof(*mldq));

	__skb_pull(skb, sizeof(*eth));

out:
	return skb;
}
#endif

485 486 487 488 489 490
static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
						struct br_ip *addr)
{
	switch (addr->proto) {
	case htons(ETH_P_IP):
		return br_ip4_multicast_alloc_query(br, addr->u.ip4);
E
Eric Dumazet 已提交
491
#if IS_ENABLED(CONFIG_IPV6)
492 493 494
	case htons(ETH_P_IPV6):
		return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
#endif
495 496 497 498
	}
	return NULL;
}

499
static struct net_bridge_mdb_entry *br_multicast_get_group(
500 501
	struct net_bridge *br, struct net_bridge_port *port,
	struct br_ip *group, int hash)
502
{
503
	struct net_bridge_mdb_htable *mdb;
504 505
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p;
506 507
	unsigned int count = 0;
	unsigned int max;
508 509 510
	int elasticity;
	int err;

511
	mdb = rcu_dereference_protected(br->mdb, 1);
512 513
	hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
		count++;
514
		if (unlikely(br_ip_equal(group, &mp->addr)))
515 516 517 518 519 520 521 522
			return mp;
	}

	elasticity = 0;
	max = mdb->max;

	if (unlikely(count > br->hash_elasticity && count)) {
		if (net_ratelimit())
523 524 525
			br_info(br, "Multicast hash table "
				"chain limit reached: %s\n",
				port ? port->dev->name : br->dev->name);
526 527 528 529 530 531

		elasticity = br->hash_elasticity;
	}

	if (mdb->size >= max) {
		max *= 2;
532 533 534 535 536
		if (unlikely(max > br->hash_max)) {
			br_warn(br, "Multicast hash table maximum of %d "
				"reached, disabling snooping: %s\n",
				br->hash_max,
				port ? port->dev->name : br->dev->name);
537 538 539 540 541 542 543 544 545 546
			err = -E2BIG;
disable:
			br->multicast_disabled = 1;
			goto err;
		}
	}

	if (max > mdb->max || elasticity) {
		if (mdb->old) {
			if (net_ratelimit())
547 548 549
				br_info(br, "Multicast hash table "
					"on fire: %s\n",
					port ? port->dev->name : br->dev->name);
550 551 552 553 554 555
			err = -EEXIST;
			goto err;
		}

		err = br_mdb_rehash(&br->mdb, max, elasticity);
		if (err) {
556 557 558 559
			br_warn(br, "Cannot rehash multicast "
				"hash table, disabling snooping: %s, %d, %d\n",
				port ? port->dev->name : br->dev->name,
				mdb->size, err);
560 561 562 563 564 565 566 567 568 569 570 571 572 573
			goto disable;
		}

		err = -EAGAIN;
		goto err;
	}

	return NULL;

err:
	mp = ERR_PTR(err);
	return mp;
}

574 575
struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
	struct net_bridge_port *port, struct br_ip *group)
576
{
577
	struct net_bridge_mdb_htable *mdb;
578 579
	struct net_bridge_mdb_entry *mp;
	int hash;
580
	int err;
581

582
	mdb = rcu_dereference_protected(br->mdb, 1);
583
	if (!mdb) {
584 585 586
		err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0);
		if (err)
			return ERR_PTR(err);
587 588 589 590 591 592 593 594 595 596 597
		goto rehash;
	}

	hash = br_ip_hash(mdb, group);
	mp = br_multicast_get_group(br, port, group, hash);
	switch (PTR_ERR(mp)) {
	case 0:
		break;

	case -EAGAIN:
rehash:
598
		mdb = rcu_dereference_protected(br->mdb, 1);
599 600 601 602 603 604 605 606 607
		hash = br_ip_hash(mdb, group);
		break;

	default:
		goto out;
	}

	mp = kzalloc(sizeof(*mp), GFP_ATOMIC);
	if (unlikely(!mp))
608
		return ERR_PTR(-ENOMEM);
609 610

	mp->br = br;
611
	mp->addr = *group;
612 613 614 615 616 617 618 619 620 621
	setup_timer(&mp->timer, br_multicast_group_expired,
		    (unsigned long)mp);

	hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
	mdb->size++;

out:
	return mp;
}

622 623 624
struct net_bridge_port_group *br_multicast_new_port_group(
			struct net_bridge_port *port,
			struct br_ip *group,
625
			struct net_bridge_port_group __rcu *next)
626 627 628 629 630 631 632 633 634
{
	struct net_bridge_port_group *p;

	p = kzalloc(sizeof(*p), GFP_ATOMIC);
	if (unlikely(!p))
		return NULL;

	p->addr = *group;
	p->port = port;
635
	rcu_assign_pointer(p->next, next);
636 637 638 639 640 641
	hlist_add_head(&p->mglist, &port->mglist);
	setup_timer(&p->timer, br_multicast_port_group_expired,
		    (unsigned long)p);
	return p;
}

642
static int br_multicast_add_group(struct net_bridge *br,
643 644
				  struct net_bridge_port *port,
				  struct br_ip *group)
645 646 647
{
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
648
	struct net_bridge_port_group __rcu **pp;
649 650 651 652 653 654 655 656 657 658
	unsigned long now = jiffies;
	int err;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED))
		goto out;

	mp = br_multicast_new_group(br, port, group);
	err = PTR_ERR(mp);
659
	if (IS_ERR(mp))
660 661 662
		goto err;

	if (!port) {
663
		mp->mglist = true;
664 665 666 667
		mod_timer(&mp->timer, now + br->multicast_membership_interval);
		goto out;
	}

668 669 670
	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
671 672 673 674 675 676
		if (p->port == port)
			goto found;
		if ((unsigned long)p->port < (unsigned long)port)
			break;
	}

677
	p = br_multicast_new_port_group(port, group, *pp);
678 679 680
	if (unlikely(!p))
		goto err;
	rcu_assign_pointer(*pp, p);
C
Cong Wang 已提交
681
	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
682 683 684 685 686 687 688 689 690 691 692

found:
	mod_timer(&p->timer, now + br->multicast_membership_interval);
out:
	err = 0;

err:
	spin_unlock(&br->multicast_lock);
	return err;
}

693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
static int br_ip4_multicast_add_group(struct net_bridge *br,
				      struct net_bridge_port *port,
				      __be32 group)
{
	struct br_ip br_group;

	if (ipv4_is_local_multicast(group))
		return 0;

	br_group.u.ip4 = group;
	br_group.proto = htons(ETH_P_IP);

	return br_multicast_add_group(br, port, &br_group);
}

E
Eric Dumazet 已提交
708
#if IS_ENABLED(CONFIG_IPV6)
709 710 711 712 713 714
static int br_ip6_multicast_add_group(struct net_bridge *br,
				      struct net_bridge_port *port,
				      const struct in6_addr *group)
{
	struct br_ip br_group;

715
	if (!ipv6_is_transient_multicast(group))
716 717
		return 0;

A
Alexey Dobriyan 已提交
718
	br_group.u.ip6 = *group;
719
	br_group.proto = htons(ETH_P_IPV6);
720 721 722 723 724

	return br_multicast_add_group(br, port, &br_group);
}
#endif

725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
static void br_multicast_router_expired(unsigned long data)
{
	struct net_bridge_port *port = (void *)data;
	struct net_bridge *br = port->br;

	spin_lock(&br->multicast_lock);
	if (port->multicast_router != 1 ||
	    timer_pending(&port->multicast_router_timer) ||
	    hlist_unhashed(&port->rlist))
		goto out;

	hlist_del_init_rcu(&port->rlist);

out:
	spin_unlock(&br->multicast_lock);
}

static void br_multicast_local_router_expired(unsigned long data)
{
}

746 747
static void br_multicast_querier_expired(unsigned long data)
{
748
	struct net_bridge *br = (void *)data;
749 750 751 752 753 754 755 756 757 758 759

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || br->multicast_disabled)
		goto out;

	br_multicast_start_querier(br);

out:
	spin_unlock(&br->multicast_lock);
}

760 761 762
static void __br_multicast_send_query(struct net_bridge *br,
				      struct net_bridge_port *port,
				      struct br_ip *ip)
763 764 765
{
	struct sk_buff *skb;

766
	skb = br_multicast_alloc_query(br, ip);
767
	if (!skb)
768
		return;
769 770 771 772

	if (port) {
		__skb_push(skb, sizeof(struct ethhdr));
		skb->dev = port->dev;
773
		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
774 775 776
			dev_queue_xmit);
	} else
		netif_rx(skb);
777 778 779 780 781 782 783 784 785
}

static void br_multicast_send_query(struct net_bridge *br,
				    struct net_bridge_port *port, u32 sent)
{
	unsigned long time;
	struct br_ip br_group;

	if (!netif_running(br->dev) || br->multicast_disabled ||
786
	    !br->multicast_querier ||
787 788 789
	    timer_pending(&br->multicast_querier_timer))
		return;

790 791
	memset(&br_group.u, 0, sizeof(br_group.u));

792
	br_group.proto = htons(ETH_P_IP);
793
	__br_multicast_send_query(br, port, &br_group);
794

E
Eric Dumazet 已提交
795
#if IS_ENABLED(CONFIG_IPV6)
796
	br_group.proto = htons(ETH_P_IPV6);
797
	__br_multicast_send_query(br, port, &br_group);
798
#endif
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813

	time = jiffies;
	time += sent < br->multicast_startup_query_count ?
		br->multicast_startup_query_interval :
		br->multicast_query_interval;
	mod_timer(port ? &port->multicast_query_timer :
			 &br->multicast_query_timer, time);
}

static void br_multicast_port_query_expired(unsigned long data)
{
	struct net_bridge_port *port = (void *)data;
	struct net_bridge *br = port->br;

	spin_lock(&br->multicast_lock);
814 815
	if (port->state == BR_STATE_DISABLED ||
	    port->state == BR_STATE_BLOCKING)
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
		goto out;

	if (port->multicast_startup_queries_sent <
	    br->multicast_startup_query_count)
		port->multicast_startup_queries_sent++;

	br_multicast_send_query(port->br, port,
				port->multicast_startup_queries_sent);

out:
	spin_unlock(&br->multicast_lock);
}

void br_multicast_add_port(struct net_bridge_port *port)
{
	port->multicast_router = 1;

	setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
		    (unsigned long)port);
	setup_timer(&port->multicast_query_timer,
		    br_multicast_port_query_expired, (unsigned long)port);
}

void br_multicast_del_port(struct net_bridge_port *port)
{
	del_timer_sync(&port->multicast_router_timer);
}

844 845 846 847 848 849 850 851 852
static void __br_multicast_enable_port(struct net_bridge_port *port)
{
	port->multicast_startup_queries_sent = 0;

	if (try_to_del_timer_sync(&port->multicast_query_timer) >= 0 ||
	    del_timer(&port->multicast_query_timer))
		mod_timer(&port->multicast_query_timer, jiffies);
}

853 854 855 856 857 858 859 860
void br_multicast_enable_port(struct net_bridge_port *port)
{
	struct net_bridge *br = port->br;

	spin_lock(&br->multicast_lock);
	if (br->multicast_disabled || !netif_running(br->dev))
		goto out;

861
	__br_multicast_enable_port(port);
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883

out:
	spin_unlock(&br->multicast_lock);
}

void br_multicast_disable_port(struct net_bridge_port *port)
{
	struct net_bridge *br = port->br;
	struct net_bridge_port_group *pg;
	struct hlist_node *p, *n;

	spin_lock(&br->multicast_lock);
	hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist)
		br_multicast_del_pg(br, pg);

	if (!hlist_unhashed(&port->rlist))
		hlist_del_init_rcu(&port->rlist);
	del_timer(&port->multicast_router_timer);
	del_timer(&port->multicast_query_timer);
	spin_unlock(&br->multicast_lock);
}

884 885 886
static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
					 struct net_bridge_port *port,
					 struct sk_buff *skb)
887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908
{
	struct igmpv3_report *ih;
	struct igmpv3_grec *grec;
	int i;
	int len;
	int num;
	int type;
	int err = 0;
	__be32 group;

	if (!pskb_may_pull(skb, sizeof(*ih)))
		return -EINVAL;

	ih = igmpv3_report_hdr(skb);
	num = ntohs(ih->ngrec);
	len = sizeof(*ih);

	for (i = 0; i < num; i++) {
		len += sizeof(*grec);
		if (!pskb_may_pull(skb, len))
			return -EINVAL;

H
Herbert Xu 已提交
909
		grec = (void *)(skb->data + len - sizeof(*grec));
910 911 912
		group = grec->grec_mca;
		type = grec->grec_type;

E
Eric Dumazet 已提交
913
		len += ntohs(grec->grec_nsrcs) * 4;
914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930
		if (!pskb_may_pull(skb, len))
			return -EINVAL;

		/* We treat this as an IGMPv2 report for now. */
		switch (type) {
		case IGMPV3_MODE_IS_INCLUDE:
		case IGMPV3_MODE_IS_EXCLUDE:
		case IGMPV3_CHANGE_TO_INCLUDE:
		case IGMPV3_CHANGE_TO_EXCLUDE:
		case IGMPV3_ALLOW_NEW_SOURCES:
		case IGMPV3_BLOCK_OLD_SOURCES:
			break;

		default:
			continue;
		}

931
		err = br_ip4_multicast_add_group(br, port, group);
932 933 934 935 936 937 938
		if (err)
			break;
	}

	return err;
}

E
Eric Dumazet 已提交
939
#if IS_ENABLED(CONFIG_IPV6)
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962
static int br_ip6_multicast_mld2_report(struct net_bridge *br,
					struct net_bridge_port *port,
					struct sk_buff *skb)
{
	struct icmp6hdr *icmp6h;
	struct mld2_grec *grec;
	int i;
	int len;
	int num;
	int err = 0;

	if (!pskb_may_pull(skb, sizeof(*icmp6h)))
		return -EINVAL;

	icmp6h = icmp6_hdr(skb);
	num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
	len = sizeof(*icmp6h);

	for (i = 0; i < num; i++) {
		__be16 *nsrcs, _nsrcs;

		nsrcs = skb_header_pointer(skb,
					   len + offsetof(struct mld2_grec,
963
							  grec_nsrcs),
964 965 966 967 968 969
					   sizeof(_nsrcs), &_nsrcs);
		if (!nsrcs)
			return -EINVAL;

		if (!pskb_may_pull(skb,
				   len + sizeof(*grec) +
970
				   sizeof(struct in6_addr) * ntohs(*nsrcs)))
971 972 973
			return -EINVAL;

		grec = (struct mld2_grec *)(skb->data + len);
974 975
		len += sizeof(*grec) +
		       sizeof(struct in6_addr) * ntohs(*nsrcs);
976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999

		/* We treat these as MLDv1 reports for now. */
		switch (grec->grec_type) {
		case MLD2_MODE_IS_INCLUDE:
		case MLD2_MODE_IS_EXCLUDE:
		case MLD2_CHANGE_TO_INCLUDE:
		case MLD2_CHANGE_TO_EXCLUDE:
		case MLD2_ALLOW_NEW_SOURCES:
		case MLD2_BLOCK_OLD_SOURCES:
			break;

		default:
			continue;
		}

		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca);
		if (!err)
			break;
	}

	return err;
}
#endif

1000 1001 1002 1003 1004
/*
 * Add port to rotuer_list
 *  list is maintained ordered by pointer value
 *  and locked by br->multicast_lock and RCU
 */
1005 1006 1007
static void br_multicast_add_router(struct net_bridge *br,
				    struct net_bridge_port *port)
{
1008
	struct net_bridge_port *p;
1009
	struct hlist_node *n, *slot = NULL;
1010

1011
	hlist_for_each_entry(p, n, &br->router_list, rlist) {
1012 1013 1014
		if ((unsigned long) port >= (unsigned long) p)
			break;
		slot = n;
1015 1016
	}

1017 1018
	if (slot)
		hlist_add_after_rcu(slot, &port->rlist);
1019 1020
	else
		hlist_add_head_rcu(&port->rlist, &br->router_list);
1021 1022
}

1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
static void br_multicast_mark_router(struct net_bridge *br,
				     struct net_bridge_port *port)
{
	unsigned long now = jiffies;

	if (!port) {
		if (br->multicast_router == 1)
			mod_timer(&br->multicast_router_timer,
				  now + br->multicast_querier_interval);
		return;
	}

	if (port->multicast_router != 1)
		return;

	if (!hlist_unhashed(&port->rlist))
		goto timer;

1041
	br_multicast_add_router(br, port);
1042 1043 1044 1045 1046 1047 1048 1049

timer:
	mod_timer(&port->multicast_router_timer,
		  now + br->multicast_querier_interval);
}

static void br_multicast_query_received(struct net_bridge *br,
					struct net_bridge_port *port,
1050
					int saddr)
1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
{
	if (saddr)
		mod_timer(&br->multicast_querier_timer,
			  jiffies + br->multicast_querier_interval);
	else if (timer_pending(&br->multicast_querier_timer))
		return;

	br_multicast_mark_router(br, port);
}

1061 1062 1063
static int br_ip4_multicast_query(struct net_bridge *br,
				  struct net_bridge_port *port,
				  struct sk_buff *skb)
1064
{
1065
	const struct iphdr *iph = ip_hdr(skb);
1066 1067 1068 1069
	struct igmphdr *ih = igmp_hdr(skb);
	struct net_bridge_mdb_entry *mp;
	struct igmpv3_query *ih3;
	struct net_bridge_port_group *p;
1070
	struct net_bridge_port_group __rcu **pp;
1071 1072 1073
	unsigned long max_delay;
	unsigned long now = jiffies;
	__be32 group;
1074
	int err = 0;
1075 1076 1077 1078 1079 1080

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED))
		goto out;

1081
	br_multicast_query_received(br, port, !!iph->saddr);
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092

	group = ih->group;

	if (skb->len == sizeof(*ih)) {
		max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);

		if (!max_delay) {
			max_delay = 10 * HZ;
			group = 0;
		}
	} else {
1093 1094 1095 1096
		if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) {
			err = -EINVAL;
			goto out;
		}
1097 1098 1099

		ih3 = igmpv3_query_hdr(skb);
		if (ih3->nsrcs)
1100
			goto out;
1101

1102 1103
		max_delay = ih3->code ?
			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
1104 1105 1106 1107 1108
	}

	if (!group)
		goto out;

1109
	mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group);
1110 1111 1112 1113 1114
	if (!mp)
		goto out;

	max_delay *= br->multicast_last_member_count;

1115
	if (mp->mglist &&
1116 1117 1118 1119 1120
	    (timer_pending(&mp->timer) ?
	     time_after(mp->timer.expires, now + max_delay) :
	     try_to_del_timer_sync(&mp->timer) >= 0))
		mod_timer(&mp->timer, now + max_delay);

1121 1122 1123
	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
1124 1125 1126
		if (timer_pending(&p->timer) ?
		    time_after(p->timer.expires, now + max_delay) :
		    try_to_del_timer_sync(&p->timer) >= 0)
1127
			mod_timer(&p->timer, now + max_delay);
1128 1129 1130 1131
	}

out:
	spin_unlock(&br->multicast_lock);
1132
	return err;
1133 1134
}

E
Eric Dumazet 已提交
1135
#if IS_ENABLED(CONFIG_IPV6)
1136 1137 1138 1139
static int br_ip6_multicast_query(struct net_bridge *br,
				  struct net_bridge_port *port,
				  struct sk_buff *skb)
{
1140
	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
1141
	struct mld_msg *mld;
1142 1143
	struct net_bridge_mdb_entry *mp;
	struct mld2_query *mld2q;
1144 1145
	struct net_bridge_port_group *p;
	struct net_bridge_port_group __rcu **pp;
1146 1147
	unsigned long max_delay;
	unsigned long now = jiffies;
1148
	const struct in6_addr *group = NULL;
1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
	int err = 0;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED))
		goto out;

	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));

	if (skb->len == sizeof(*mld)) {
		if (!pskb_may_pull(skb, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *) icmp6_hdr(skb);
L
Li RongQing 已提交
1164
		max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay));
1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
		if (max_delay)
			group = &mld->mld_mca;
	} else if (skb->len >= sizeof(*mld2q)) {
		if (!pskb_may_pull(skb, sizeof(*mld2q))) {
			err = -EINVAL;
			goto out;
		}
		mld2q = (struct mld2_query *)icmp6_hdr(skb);
		if (!mld2q->mld2q_nsrcs)
			group = &mld2q->mld2q_mca;
1175
		max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(ntohs(mld2q->mld2q_mrc)) : 1;
1176 1177 1178 1179 1180
	}

	if (!group)
		goto out;

1181
	mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group);
1182 1183 1184 1185
	if (!mp)
		goto out;

	max_delay *= br->multicast_last_member_count;
1186
	if (mp->mglist &&
1187 1188 1189 1190 1191
	    (timer_pending(&mp->timer) ?
	     time_after(mp->timer.expires, now + max_delay) :
	     try_to_del_timer_sync(&mp->timer) >= 0))
		mod_timer(&mp->timer, now + max_delay);

1192 1193 1194
	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
1195 1196 1197
		if (timer_pending(&p->timer) ?
		    time_after(p->timer.expires, now + max_delay) :
		    try_to_del_timer_sync(&p->timer) >= 0)
1198
			mod_timer(&p->timer, now + max_delay);
1199 1200 1201 1202 1203 1204 1205 1206
	}

out:
	spin_unlock(&br->multicast_lock);
	return err;
}
#endif

1207 1208
static void br_multicast_leave_group(struct net_bridge *br,
				     struct net_bridge_port *port,
1209
				     struct br_ip *group)
1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222
{
	struct net_bridge_mdb_htable *mdb;
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	unsigned long now;
	unsigned long time;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED) ||
	    timer_pending(&br->multicast_querier_timer))
		goto out;

1223
	mdb = mlock_dereference(br->mdb, br);
1224 1225 1226 1227
	mp = br_mdb_ip_get(mdb, group);
	if (!mp)
		goto out;

1228
	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
		struct net_bridge_port_group __rcu **pp;

		for (pp = &mp->ports;
		     (p = mlock_dereference(*pp, br)) != NULL;
		     pp = &p->next) {
			if (p->port != port)
				continue;

			rcu_assign_pointer(*pp, p->next);
			hlist_del_init(&p->mglist);
			del_timer(&p->timer);
			call_rcu_bh(&p->rcu, br_multicast_free_pg);
C
Cong Wang 已提交
1241
			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
1242 1243 1244 1245 1246 1247 1248 1249

			if (!mp->ports && !mp->mglist &&
			    netif_running(br->dev))
				mod_timer(&mp->timer, jiffies);
		}
		goto out;
	}

1250 1251 1252 1253 1254
	now = jiffies;
	time = now + br->multicast_last_member_count *
		     br->multicast_last_member_interval;

	if (!port) {
1255
		if (mp->mglist &&
1256 1257 1258 1259 1260 1261 1262 1263 1264
		    (timer_pending(&mp->timer) ?
		     time_after(mp->timer.expires, time) :
		     try_to_del_timer_sync(&mp->timer) >= 0)) {
			mod_timer(&mp->timer, time);
		}

		goto out;
	}

1265 1266 1267
	for (p = mlock_dereference(mp->ports, br);
	     p != NULL;
	     p = mlock_dereference(p->next, br)) {
1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284
		if (p->port != port)
			continue;

		if (!hlist_unhashed(&p->mglist) &&
		    (timer_pending(&p->timer) ?
		     time_after(p->timer.expires, time) :
		     try_to_del_timer_sync(&p->timer) >= 0)) {
			mod_timer(&p->timer, time);
		}

		break;
	}

out:
	spin_unlock(&br->multicast_lock);
}

1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299
static void br_ip4_multicast_leave_group(struct net_bridge *br,
					 struct net_bridge_port *port,
					 __be32 group)
{
	struct br_ip br_group;

	if (ipv4_is_local_multicast(group))
		return;

	br_group.u.ip4 = group;
	br_group.proto = htons(ETH_P_IP);

	br_multicast_leave_group(br, port, &br_group);
}

E
Eric Dumazet 已提交
1300
#if IS_ENABLED(CONFIG_IPV6)
1301 1302 1303 1304 1305 1306
static void br_ip6_multicast_leave_group(struct net_bridge *br,
					 struct net_bridge_port *port,
					 const struct in6_addr *group)
{
	struct br_ip br_group;

1307
	if (!ipv6_is_transient_multicast(group))
1308 1309
		return;

A
Alexey Dobriyan 已提交
1310
	br_group.u.ip6 = *group;
1311 1312 1313 1314 1315
	br_group.proto = htons(ETH_P_IPV6);

	br_multicast_leave_group(br, port, &br_group);
}
#endif
1316

1317 1318 1319 1320 1321
static int br_multicast_ipv4_rcv(struct net_bridge *br,
				 struct net_bridge_port *port,
				 struct sk_buff *skb)
{
	struct sk_buff *skb2 = skb;
1322
	const struct iphdr *iph;
1323
	struct igmphdr *ih;
1324 1325
	unsigned int len;
	unsigned int offset;
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
	int err;

	/* We treat OOM as packet loss for now. */
	if (!pskb_may_pull(skb, sizeof(*iph)))
		return -EINVAL;

	iph = ip_hdr(skb);

	if (iph->ihl < 5 || iph->version != 4)
		return -EINVAL;

	if (!pskb_may_pull(skb, ip_hdrlen(skb)))
		return -EINVAL;

	iph = ip_hdr(skb);

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		return -EINVAL;

1345 1346 1347
	if (iph->protocol != IPPROTO_IGMP) {
		if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP)
			BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
1348
		return 0;
1349
	}
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361

	len = ntohs(iph->tot_len);
	if (skb->len < len || len < ip_hdrlen(skb))
		return -EINVAL;

	if (skb->len > len) {
		skb2 = skb_clone(skb, GFP_ATOMIC);
		if (!skb2)
			return -ENOMEM;

		err = pskb_trim_rcsum(skb2, len);
		if (err)
1362
			goto err_out;
1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
	}

	len -= ip_hdrlen(skb2);
	offset = skb_network_offset(skb2) + ip_hdrlen(skb2);
	__skb_pull(skb2, offset);
	skb_reset_transport_header(skb2);

	err = -EINVAL;
	if (!pskb_may_pull(skb2, sizeof(*ih)))
		goto out;

	switch (skb2->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!csum_fold(skb2->csum))
			break;
		/* fall through */
	case CHECKSUM_NONE:
		skb2->csum = 0;
		if (skb_checksum_complete(skb2))
1382
			goto out;
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392
	}

	err = 0;

	BR_INPUT_SKB_CB(skb)->igmp = 1;
	ih = igmp_hdr(skb2);

	switch (ih->type) {
	case IGMP_HOST_MEMBERSHIP_REPORT:
	case IGMPV2_HOST_MEMBERSHIP_REPORT:
1393
		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
1394
		err = br_ip4_multicast_add_group(br, port, ih->group);
1395 1396
		break;
	case IGMPV3_HOST_MEMBERSHIP_REPORT:
1397
		err = br_ip4_multicast_igmp3_report(br, port, skb2);
1398 1399
		break;
	case IGMP_HOST_MEMBERSHIP_QUERY:
1400
		err = br_ip4_multicast_query(br, port, skb2);
1401 1402
		break;
	case IGMP_HOST_LEAVE_MESSAGE:
1403
		br_ip4_multicast_leave_group(br, port, ih->group);
1404 1405 1406 1407 1408
		break;
	}

out:
	__skb_push(skb2, offset);
1409
err_out:
1410 1411 1412 1413 1414
	if (skb2 != skb)
		kfree_skb(skb2);
	return err;
}

E
Eric Dumazet 已提交
1415
#if IS_ENABLED(CONFIG_IPV6)
1416 1417 1418 1419
static int br_multicast_ipv6_rcv(struct net_bridge *br,
				 struct net_bridge_port *port,
				 struct sk_buff *skb)
{
1420
	struct sk_buff *skb2;
1421
	const struct ipv6hdr *ip6h;
1422
	u8 icmp6_type;
1423
	u8 nexthdr;
1424
	__be16 frag_off;
1425
	unsigned int len;
K
Kulikov Vasiliy 已提交
1426
	int offset;
1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444
	int err;

	if (!pskb_may_pull(skb, sizeof(*ip6h)))
		return -EINVAL;

	ip6h = ipv6_hdr(skb);

	/*
	 * We're interested in MLD messages only.
	 *  - Version is 6
	 *  - MLD has always Router Alert hop-by-hop option
	 *  - But we do not support jumbrograms.
	 */
	if (ip6h->version != 6 ||
	    ip6h->nexthdr != IPPROTO_HOPOPTS ||
	    ip6h->payload_len == 0)
		return 0;

1445
	len = ntohs(ip6h->payload_len) + sizeof(*ip6h);
1446 1447 1448 1449
	if (skb->len < len)
		return -EINVAL;

	nexthdr = ip6h->nexthdr;
1450
	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
1451 1452 1453 1454 1455 1456 1457 1458 1459

	if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
		return 0;

	/* Okay, we found ICMPv6 header */
	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (!skb2)
		return -ENOMEM;

1460 1461 1462 1463
	err = -EINVAL;
	if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr)))
		goto out;

1464 1465 1466 1467
	len -= offset - skb_network_offset(skb2);

	__skb_pull(skb2, offset);
	skb_reset_transport_header(skb2);
1468 1469
	skb_postpull_rcsum(skb2, skb_network_header(skb2),
			   skb_network_header_len(skb2));
1470

1471
	icmp6_type = icmp6_hdr(skb2)->icmp6_type;
1472

1473
	switch (icmp6_type) {
1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488
	case ICMPV6_MGM_QUERY:
	case ICMPV6_MGM_REPORT:
	case ICMPV6_MGM_REDUCTION:
	case ICMPV6_MLD2_REPORT:
		break;
	default:
		err = 0;
		goto out;
	}

	/* Okay, we found MLD message. Check further. */
	if (skb2->len > len) {
		err = pskb_trim_rcsum(skb2, len);
		if (err)
			goto out;
1489
		err = -EINVAL;
1490 1491
	}

1492 1493
	ip6h = ipv6_hdr(skb2);

1494 1495
	switch (skb2->ip_summed) {
	case CHECKSUM_COMPLETE:
1496 1497
		if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len,
					IPPROTO_ICMPV6, skb2->csum))
1498 1499 1500
			break;
		/*FALLTHROUGH*/
	case CHECKSUM_NONE:
1501 1502 1503 1504 1505
		skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
							&ip6h->daddr,
							skb2->len,
							IPPROTO_ICMPV6, 0));
		if (__skb_checksum_complete(skb2))
1506 1507 1508 1509 1510 1511 1512
			goto out;
	}

	err = 0;

	BR_INPUT_SKB_CB(skb)->igmp = 1;

1513
	switch (icmp6_type) {
1514 1515
	case ICMPV6_MGM_REPORT:
	    {
1516 1517 1518 1519 1520 1521
		struct mld_msg *mld;
		if (!pskb_may_pull(skb2, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *)skb_transport_header(skb2);
1522
		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533
		err = br_ip6_multicast_add_group(br, port, &mld->mld_mca);
		break;
	    }
	case ICMPV6_MLD2_REPORT:
		err = br_ip6_multicast_mld2_report(br, port, skb2);
		break;
	case ICMPV6_MGM_QUERY:
		err = br_ip6_multicast_query(br, port, skb2);
		break;
	case ICMPV6_MGM_REDUCTION:
	    {
1534 1535 1536 1537 1538 1539
		struct mld_msg *mld;
		if (!pskb_may_pull(skb2, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *)skb_transport_header(skb2);
1540 1541 1542 1543 1544
		br_ip6_multicast_leave_group(br, port, &mld->mld_mca);
	    }
	}

out:
1545
	kfree_skb(skb2);
1546 1547 1548 1549
	return err;
}
#endif

1550 1551 1552
int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
		     struct sk_buff *skb)
{
1553 1554 1555
	BR_INPUT_SKB_CB(skb)->igmp = 0;
	BR_INPUT_SKB_CB(skb)->mrouters_only = 0;

1556 1557 1558 1559 1560 1561
	if (br->multicast_disabled)
		return 0;

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return br_multicast_ipv4_rcv(br, port, skb);
E
Eric Dumazet 已提交
1562
#if IS_ENABLED(CONFIG_IPV6)
1563 1564 1565
	case htons(ETH_P_IPV6):
		return br_multicast_ipv6_rcv(br, port, skb);
#endif
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
	}

	return 0;
}

static void br_multicast_query_expired(unsigned long data)
{
	struct net_bridge *br = (void *)data;

	spin_lock(&br->multicast_lock);
	if (br->multicast_startup_queries_sent <
	    br->multicast_startup_query_count)
		br->multicast_startup_queries_sent++;

	br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent);

	spin_unlock(&br->multicast_lock);
}

void br_multicast_init(struct net_bridge *br)
{
	br->hash_elasticity = 4;
	br->hash_max = 512;

	br->multicast_router = 1;
1591
	br->multicast_querier = 0;
1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
	br->multicast_last_member_count = 2;
	br->multicast_startup_query_count = 2;

	br->multicast_last_member_interval = HZ;
	br->multicast_query_response_interval = 10 * HZ;
	br->multicast_startup_query_interval = 125 * HZ / 4;
	br->multicast_query_interval = 125 * HZ;
	br->multicast_querier_interval = 255 * HZ;
	br->multicast_membership_interval = 260 * HZ;

	spin_lock_init(&br->multicast_lock);
	setup_timer(&br->multicast_router_timer,
		    br_multicast_local_router_expired, 0);
	setup_timer(&br->multicast_querier_timer,
1606
		    br_multicast_querier_expired, (unsigned long)br);
1607 1608
	setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
		    (unsigned long)br);
1609
	br_mdb_init();
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
}

void br_multicast_open(struct net_bridge *br)
{
	br->multicast_startup_queries_sent = 0;

	if (br->multicast_disabled)
		return;

	mod_timer(&br->multicast_query_timer, jiffies);
}

void br_multicast_stop(struct net_bridge *br)
{
	struct net_bridge_mdb_htable *mdb;
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p, *n;
	u32 ver;
	int i;

	del_timer_sync(&br->multicast_router_timer);
	del_timer_sync(&br->multicast_querier_timer);
	del_timer_sync(&br->multicast_query_timer);

	spin_lock_bh(&br->multicast_lock);
1635
	mdb = mlock_dereference(br->mdb, br);
1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651
	if (!mdb)
		goto out;

	br->mdb = NULL;

	ver = mdb->ver;
	for (i = 0; i < mdb->max; i++) {
		hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i],
					  hlist[ver]) {
			del_timer(&mp->timer);
			call_rcu_bh(&mp->rcu, br_multicast_free_group);
		}
	}

	if (mdb->old) {
		spin_unlock_bh(&br->multicast_lock);
1652
		rcu_barrier_bh();
1653 1654 1655 1656 1657 1658 1659 1660 1661 1662
		spin_lock_bh(&br->multicast_lock);
		WARN_ON(mdb->old);
	}

	mdb->old = mdb;
	call_rcu_bh(&mdb->rcu, br_mdb_free);

out:
	spin_unlock_bh(&br->multicast_lock);
}
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

int br_multicast_set_router(struct net_bridge *br, unsigned long val)
{
	int err = -ENOENT;

	spin_lock_bh(&br->multicast_lock);
	if (!netif_running(br->dev))
		goto unlock;

	switch (val) {
	case 0:
	case 2:
		del_timer(&br->multicast_router_timer);
		/* fall through */
	case 1:
		br->multicast_router = val;
		err = 0;
		break;

	default:
		err = -EINVAL;
		break;
	}

unlock:
	spin_unlock_bh(&br->multicast_lock);

	return err;
}

int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
{
	struct net_bridge *br = p->br;
	int err = -ENOENT;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED)
		goto unlock;

	switch (val) {
	case 0:
	case 1:
	case 2:
		p->multicast_router = val;
		err = 0;

		if (val < 2 && !hlist_unhashed(&p->rlist))
			hlist_del_init_rcu(&p->rlist);

		if (val == 1)
			break;

		del_timer(&p->multicast_router_timer);

		if (val == 0)
			break;

		br_multicast_add_router(br, p);
		break;

	default:
		err = -EINVAL;
		break;
	}

unlock:
	spin_unlock(&br->multicast_lock);

	return err;
}
1733

1734
static void br_multicast_start_querier(struct net_bridge *br)
1735 1736
{
	struct net_bridge_port *port;
1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750

	br_multicast_open(br);

	list_for_each_entry(port, &br->port_list, list) {
		if (port->state == BR_STATE_DISABLED ||
		    port->state == BR_STATE_BLOCKING)
			continue;

		__br_multicast_enable_port(port);
	}
}

int br_multicast_toggle(struct net_bridge *br, unsigned long val)
{
1751
	int err = 0;
1752
	struct net_bridge_mdb_htable *mdb;
1753

1754
	spin_lock_bh(&br->multicast_lock);
1755 1756 1757 1758 1759 1760 1761
	if (br->multicast_disabled == !val)
		goto unlock;

	br->multicast_disabled = !val;
	if (br->multicast_disabled)
		goto unlock;

1762 1763 1764
	if (!netif_running(br->dev))
		goto unlock;

1765 1766 1767
	mdb = mlock_dereference(br->mdb, br);
	if (mdb) {
		if (mdb->old) {
1768 1769 1770 1771 1772 1773
			err = -EEXIST;
rollback:
			br->multicast_disabled = !!val;
			goto unlock;
		}

1774
		err = br_mdb_rehash(&br->mdb, mdb->max,
1775 1776 1777 1778 1779
				    br->hash_elasticity);
		if (err)
			goto rollback;
	}

1780
	br_multicast_start_querier(br);
1781 1782

unlock:
1783
	spin_unlock_bh(&br->multicast_lock);
1784 1785 1786

	return err;
}
1787

1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
int br_multicast_set_querier(struct net_bridge *br, unsigned long val)
{
	val = !!val;

	spin_lock_bh(&br->multicast_lock);
	if (br->multicast_querier == val)
		goto unlock;

	br->multicast_querier = val;
	if (val)
		br_multicast_start_querier(br);

unlock:
	spin_unlock_bh(&br->multicast_lock);

	return 0;
}

1806 1807 1808 1809
int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
{
	int err = -ENOENT;
	u32 old;
1810
	struct net_bridge_mdb_htable *mdb;
1811 1812 1813 1814 1815 1816 1817 1818

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev))
		goto unlock;

	err = -EINVAL;
	if (!is_power_of_2(val))
		goto unlock;
1819 1820 1821

	mdb = mlock_dereference(br->mdb, br);
	if (mdb && val < mdb->size)
1822 1823 1824 1825 1826 1827 1828
		goto unlock;

	err = 0;

	old = br->hash_max;
	br->hash_max = val;

1829 1830
	if (mdb) {
		if (mdb->old) {
1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847
			err = -EEXIST;
rollback:
			br->hash_max = old;
			goto unlock;
		}

		err = br_mdb_rehash(&br->mdb, br->hash_max,
				    br->hash_elasticity);
		if (err)
			goto rollback;
	}

unlock:
	spin_unlock(&br->multicast_lock);

	return err;
}