br_multicast.c 29.4 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 27 28 29
#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>

#include "br_private.h"

30 31 32 33 34 35 36 37 38 39 40 41
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;
	}
	return 0;
}

static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
42
{
43
	return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
44 45
}

46 47 48 49 50 51 52 53 54 55
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);
	}
	return 0;
}

56
static struct net_bridge_mdb_entry *__br_mdb_ip_get(
57
	struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash)
58 59 60 61
{
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p;

62
	hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
63
		if (br_ip_equal(&mp->addr, dst))
64 65 66 67 68 69
			return mp;
	}

	return NULL;
}

70
static struct net_bridge_mdb_entry *br_mdb_ip4_get(
71 72
	struct net_bridge_mdb_htable *mdb, __be32 dst)
{
73 74 75 76
	struct br_ip br_dst;

	br_dst.u.ip4 = dst;
	br_dst.proto = htons(ETH_P_IP);
77

78 79 80 81 82 83
	return __br_mdb_ip_get(mdb, &br_dst, __br_ip4_hash(mdb, dst));
}

static struct net_bridge_mdb_entry *br_mdb_ip_get(
	struct net_bridge_mdb_htable *mdb, struct br_ip *dst)
{
84 85 86 87 88 89
	return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst));
}

struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
					struct sk_buff *skb)
{
90 91 92 93 94 95 96
	struct net_bridge_mdb_htable *mdb = br->mdb;
	struct br_ip ip;

	if (!mdb || br->multicast_disabled)
		return NULL;

	if (BR_INPUT_SKB_CB(skb)->igmp)
97 98
		return NULL;

99 100
	ip.proto = skb->protocol;

101 102
	switch (skb->protocol) {
	case htons(ETH_P_IP):
103 104 105 106
		ip.u.ip4 = ip_hdr(skb)->daddr;
		break;
	default:
		return NULL;
107 108
	}

109
	return br_mdb_ip_get(mdb, &ip);
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
}

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],
136
				       &new->mhash[br_ip_hash(new, &mp->addr)]);
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203

	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;
}

static void br_multicast_free_pg(struct rcu_head *head)
{
	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;

	if (!hlist_unhashed(&mp->mglist))
		hlist_del_init(&mp->mglist);

	if (mp->ports)
		goto out;

	mdb = br->mdb;
	hlist_del_rcu(&mp->hlist[mdb->ver]);
	mdb->size--;

	del_timer(&mp->query_timer);
	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)
{
	struct net_bridge_mdb_htable *mdb = br->mdb;
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group **pp;

204
	mp = br_mdb_ip_get(mdb, &pg->addr);
205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
	if (WARN_ON(!mp))
		return;

	for (pp = &mp->ports; (p = *pp); pp = &p->next) {
		if (p != pg)
			continue;

		*pp = p->next;
		hlist_del_init(&p->mglist);
		del_timer(&p->timer);
		del_timer(&p->query_timer);
		call_rcu_bh(&p->rcu, br_multicast_free_pg);

		if (!mp->ports && hlist_unhashed(&mp->mglist) &&
		    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);
}

static int br_mdb_rehash(struct net_bridge_mdb_htable **mdbp, int max,
			 int elasticity)
{
	struct net_bridge_mdb_htable *old = *mdbp;
	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;
	}

	call_rcu_bh(&mdb->rcu, br_mdb_free);

out:
	rcu_assign_pointer(*mdbp, mdb);

	return 0;
}

290 291
static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
						    __be32 group)
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
{
	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;
}

355 356 357 358 359 360 361 362 363 364
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);
	}
	return NULL;
}

365 366 367 368 369
static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp)
{
	struct net_bridge *br = mp->br;
	struct sk_buff *skb;

370
	skb = br_multicast_alloc_query(br, &mp->addr);
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403
	if (!skb)
		goto timer;

	netif_rx(skb);

timer:
	if (++mp->queries_sent < br->multicast_last_member_count)
		mod_timer(&mp->query_timer,
			  jiffies + br->multicast_last_member_interval);
}

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

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) ||
	    mp->queries_sent >= br->multicast_last_member_count)
		goto out;

	br_multicast_send_group_query(mp);

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

static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg)
{
	struct net_bridge_port *port = pg->port;
	struct net_bridge *br = port->br;
	struct sk_buff *skb;

404
	skb = br_multicast_alloc_query(br, &pg->addr);
405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
	if (!skb)
		goto timer;

	br_deliver(port, skb);

timer:
	if (++pg->queries_sent < br->multicast_last_member_count)
		mod_timer(&pg->query_timer,
			  jiffies + br->multicast_last_member_interval);
}

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

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) ||
	    pg->queries_sent >= br->multicast_last_member_count)
		goto out;

	br_multicast_send_port_group_query(pg);

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

static struct net_bridge_mdb_entry *br_multicast_get_group(
434 435
	struct net_bridge *br, struct net_bridge_port *port,
	struct br_ip *group, int hash)
436 437 438 439 440 441 442 443 444 445 446
{
	struct net_bridge_mdb_htable *mdb = br->mdb;
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p;
	unsigned count = 0;
	unsigned max;
	int elasticity;
	int err;

	hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
		count++;
447
		if (unlikely(br_ip_equal(group, &mp->addr)))
448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512
			return mp;
	}

	elasticity = 0;
	max = mdb->max;

	if (unlikely(count > br->hash_elasticity && count)) {
		if (net_ratelimit())
			printk(KERN_INFO "%s: Multicast hash table "
			       "chain limit reached: %s\n",
			       br->dev->name, port ? port->dev->name :
						     br->dev->name);

		elasticity = br->hash_elasticity;
	}

	if (mdb->size >= max) {
		max *= 2;
		if (unlikely(max >= br->hash_max)) {
			printk(KERN_WARNING "%s: Multicast hash table maximum "
			       "reached, disabling snooping: %s, %d\n",
			       br->dev->name, port ? port->dev->name :
						     br->dev->name,
			       max);
			err = -E2BIG;
disable:
			br->multicast_disabled = 1;
			goto err;
		}
	}

	if (max > mdb->max || elasticity) {
		if (mdb->old) {
			if (net_ratelimit())
				printk(KERN_INFO "%s: Multicast hash table "
				       "on fire: %s\n",
				       br->dev->name, port ? port->dev->name :
							     br->dev->name);
			err = -EEXIST;
			goto err;
		}

		err = br_mdb_rehash(&br->mdb, max, elasticity);
		if (err) {
			printk(KERN_WARNING "%s: Cannot rehash multicast "
			       "hash table, disabling snooping: "
			       "%s, %d, %d\n",
			       br->dev->name, port ? port->dev->name :
						     br->dev->name,
			       mdb->size, err);
			goto disable;
		}

		err = -EAGAIN;
		goto err;
	}

	return NULL;

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

static struct net_bridge_mdb_entry *br_multicast_new_group(
513 514
	struct net_bridge *br, struct net_bridge_port *port,
	struct br_ip *group)
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
{
	struct net_bridge_mdb_htable *mdb = br->mdb;
	struct net_bridge_mdb_entry *mp;
	int hash;

	if (!mdb) {
		if (br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0))
			return NULL;
		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:
		mdb = br->mdb;
		hash = br_ip_hash(mdb, group);
		break;

	default:
		goto out;
	}

	mp = kzalloc(sizeof(*mp), GFP_ATOMIC);
	if (unlikely(!mp))
		goto out;

	mp->br = br;
547
	mp->addr = *group;
548 549 550 551 552 553 554 555 556 557 558 559 560
	setup_timer(&mp->timer, br_multicast_group_expired,
		    (unsigned long)mp);
	setup_timer(&mp->query_timer, br_multicast_group_query_expired,
		    (unsigned long)mp);

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

out:
	return mp;
}

static int br_multicast_add_group(struct net_bridge *br,
561 562
				  struct net_bridge_port *port,
				  struct br_ip *group)
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597
{
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group **pp;
	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);
	if (unlikely(IS_ERR(mp) || !mp))
		goto err;

	if (!port) {
		hlist_add_head(&mp->mglist, &br->mglist);
		mod_timer(&mp->timer, now + br->multicast_membership_interval);
		goto out;
	}

	for (pp = &mp->ports; (p = *pp); pp = &p->next) {
		if (p->port == port)
			goto found;
		if ((unsigned long)p->port < (unsigned long)port)
			break;
	}

	p = kzalloc(sizeof(*p), GFP_ATOMIC);
	err = -ENOMEM;
	if (unlikely(!p))
		goto err;

598
	p->addr = *group;
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
	p->port = port;
	p->next = *pp;
	hlist_add_head(&p->mglist, &port->mglist);
	setup_timer(&p->timer, br_multicast_port_group_expired,
		    (unsigned long)p);
	setup_timer(&p->query_timer, br_multicast_port_group_query_expired,
		    (unsigned long)p);

	rcu_assign_pointer(*pp, p);

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

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

619 620 621 622 623 624 625 626 627 628 629 630 631 632 633
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);
}

634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654
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)
{
}

655 656 657
static void __br_multicast_send_query(struct net_bridge *br,
				      struct net_bridge_port *port,
				      struct br_ip *ip)
658 659 660
{
	struct sk_buff *skb;

661
	skb = br_multicast_alloc_query(br, ip);
662
	if (!skb)
663
		return;
664 665 666 667 668 669 670 671

	if (port) {
		__skb_push(skb, sizeof(struct ethhdr));
		skb->dev = port->dev;
		NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
			dev_queue_xmit);
	} else
		netif_rx(skb);
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
}

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 ||
	    timer_pending(&br->multicast_querier_timer))
		return;

	br_group.u.ip4 = 0;
	br_group.proto = htons(ETH_P_IP);

	__br_multicast_send_query(br, port, &br_group);
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702

	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);
703 704
	if (port->state == BR_STATE_DISABLED ||
	    port->state == BR_STATE_BLOCKING)
705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
		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);
}

733 734 735 736 737 738 739 740 741
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);
}

742 743 744 745 746 747 748 749
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;

750
	__br_multicast_enable_port(port);
751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772

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);
}

773 774 775
static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
					 struct net_bridge_port *port,
					 struct sk_buff *skb)
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797
{
	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
798
		grec = (void *)(skb->data + len - sizeof(*grec));
799 800 801
		group = grec->grec_mca;
		type = grec->grec_type;

E
Eric Dumazet 已提交
802
		len += ntohs(grec->grec_nsrcs) * 4;
803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819
		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;
		}

820
		err = br_ip4_multicast_add_group(br, port, group);
821 822 823 824 825 826 827
		if (err)
			break;
	}

	return err;
}

828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847
static void br_multicast_add_router(struct net_bridge *br,
				    struct net_bridge_port *port)
{
	struct hlist_node *p;
	struct hlist_node **h;

	for (h = &br->router_list.first;
	     (p = *h) &&
	     (unsigned long)container_of(p, struct net_bridge_port, rlist) >
	     (unsigned long)port;
	     h = &p->next)
		;

	port->rlist.pprev = h;
	port->rlist.next = p;
	rcu_assign_pointer(*h, &port->rlist);
	if (p)
		p->pprev = &port->rlist.next;
}

848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865
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;

866
	br_multicast_add_router(br, port);
867 868 869 870 871 872 873 874

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,
875
					int saddr)
876 877 878 879 880 881 882 883 884 885
{
	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);
}

886 887 888
static int br_ip4_multicast_query(struct net_bridge *br,
				  struct net_bridge_port *port,
				  struct sk_buff *skb)
889 890 891 892 893 894 895 896 897 898
{
	struct iphdr *iph = ip_hdr(skb);
	struct igmphdr *ih = igmp_hdr(skb);
	struct net_bridge_mdb_entry *mp;
	struct igmpv3_query *ih3;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group **pp;
	unsigned long max_delay;
	unsigned long now = jiffies;
	__be32 group;
899
	int err = 0;
900 901 902 903 904 905

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

906
	br_multicast_query_received(br, port, !!iph->saddr);
907 908 909 910 911 912 913 914 915 916 917

	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 {
918 919 920 921
		if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) {
			err = -EINVAL;
			goto out;
		}
922 923 924

		ih3 = igmpv3_query_hdr(skb);
		if (ih3->nsrcs)
925
			goto out;
926

927 928
		max_delay = ih3->code ?
			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
929 930 931 932 933
	}

	if (!group)
		goto out;

934
	mp = br_mdb_ip4_get(br->mdb, group);
935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954
	if (!mp)
		goto out;

	max_delay *= br->multicast_last_member_count;

	if (!hlist_unhashed(&mp->mglist) &&
	    (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);

	for (pp = &mp->ports; (p = *pp); pp = &p->next) {
		if (timer_pending(&p->timer) ?
		    time_after(p->timer.expires, now + max_delay) :
		    try_to_del_timer_sync(&p->timer) >= 0)
			mod_timer(&mp->timer, now + max_delay);
	}

out:
	spin_unlock(&br->multicast_lock);
955
	return err;
956 957 958 959
}

static void br_multicast_leave_group(struct net_bridge *br,
				     struct net_bridge_port *port,
960
				     struct br_ip *group)
961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017
{
	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;

	mdb = br->mdb;
	mp = br_mdb_ip_get(mdb, group);
	if (!mp)
		goto out;

	now = jiffies;
	time = now + br->multicast_last_member_count *
		     br->multicast_last_member_interval;

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

			mp->queries_sent = 0;
			mod_timer(&mp->query_timer, now);
		}

		goto out;
	}

	for (p = mp->ports; p; p = p->next) {
		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);

			p->queries_sent = 0;
			mod_timer(&p->query_timer, now);
		}

		break;
	}

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

1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
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);
}


1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078
static int br_multicast_ipv4_rcv(struct net_bridge *br,
				 struct net_bridge_port *port,
				 struct sk_buff *skb)
{
	struct sk_buff *skb2 = skb;
	struct iphdr *iph;
	struct igmphdr *ih;
	unsigned len;
	unsigned offset;
	int err;

	BR_INPUT_SKB_CB(skb)->igmp = 0;
	BR_INPUT_SKB_CB(skb)->mrouters_only = 0;

	/* 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;

	if (iph->protocol != IPPROTO_IGMP)
		return 0;

	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)
1079
			goto err_out;
1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098
	}

	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))
1099
			goto out;
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110
	}

	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:
		BR_INPUT_SKB_CB(skb2)->mrouters_only = 1;
1111
		err = br_ip4_multicast_add_group(br, port, ih->group);
1112 1113
		break;
	case IGMPV3_HOST_MEMBERSHIP_REPORT:
1114
		err = br_ip4_multicast_igmp3_report(br, port, skb2);
1115 1116
		break;
	case IGMP_HOST_MEMBERSHIP_QUERY:
1117
		err = br_ip4_multicast_query(br, port, skb2);
1118 1119
		break;
	case IGMP_HOST_LEAVE_MESSAGE:
1120
		br_ip4_multicast_leave_group(br, port, ih->group);
1121 1122 1123 1124 1125
		break;
	}

out:
	__skb_push(skb2, offset);
1126
err_out:
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225
	if (skb2 != skb)
		kfree_skb(skb2);
	return err;
}

int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
		     struct sk_buff *skb)
{
	if (br->multicast_disabled)
		return 0;

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return br_multicast_ipv4_rcv(br, port, skb);
	}

	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;
	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,
		    br_multicast_local_router_expired, 0);
	setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
		    (unsigned long)br);
}

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);
	mdb = br->mdb;
	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);
			del_timer(&mp->query_timer);
			call_rcu_bh(&mp->rcu, br_multicast_free_group);
		}
	}

	if (mdb->old) {
		spin_unlock_bh(&br->multicast_lock);
1226
		rcu_barrier_bh();
1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
		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);
}
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306

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;
}
1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352

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

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

	err = 0;
	if (br->multicast_disabled == !val)
		goto unlock;

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

	if (br->mdb) {
		if (br->mdb->old) {
			err = -EEXIST;
rollback:
			br->multicast_disabled = !!val;
			goto unlock;
		}

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

	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);
	}

unlock:
	spin_unlock(&br->multicast_lock);

	return err;
}
1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392

int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
{
	int err = -ENOENT;
	u32 old;

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

	err = -EINVAL;
	if (!is_power_of_2(val))
		goto unlock;
	if (br->mdb && val < br->mdb->size)
		goto unlock;

	err = 0;

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

	if (br->mdb) {
		if (br->mdb->old) {
			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;
}