ip6mr.c 36.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47
/*
 *	Linux IPv6 multicast routing support for BSD pim6sd
 *	Based on net/ipv4/ipmr.c.
 *
 *	(c) 2004 Mickael Hoerdt, <hoerdt@clarinet.u-strasbg.fr>
 *		LSIIT Laboratory, Strasbourg, France
 *	(c) 2004 Jean-Philippe Andriot, <jean-philippe.andriot@6WIND.com>
 *		6WIND, Paris, France
 *	Copyright (C)2007,2008 USAGI/WIDE Project
 *		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
 *
 *	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 <asm/system.h>
#include <asm/uaccess.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <linux/notifier.h>
#include <linux/if_arp.h>
#include <net/checksum.h>
#include <net/netlink.h>

#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <linux/mroute6.h>
48
#include <linux/pim.h>
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
#include <net/addrconf.h>
#include <linux/netfilter_ipv6.h>

struct sock *mroute6_socket;


/* Big lock, protecting vif table, mrt cache and mroute socket state.
   Note that the changes are semaphored via rtnl_lock.
 */

static DEFINE_RWLOCK(mrt_lock);

/*
 *	Multicast router control variables
 */

static struct mif_device vif6_table[MAXMIFS];		/* Devices 		*/
static int maxvif;

#define MIF_EXISTS(idx) (vif6_table[idx].dev != NULL)

70 71 72 73 74 75 76
static int mroute_do_assert;				/* Set in PIM assert	*/
#ifdef CONFIG_IPV6_PIMSM_V2
static int mroute_do_pim;
#else
#define mroute_do_pim 0
#endif

77
static struct mfc6_cache *mfc6_cache_array[MFC6_LINES];	/* Forwarding cache	*/
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95

static struct mfc6_cache *mfc_unres_queue;		/* Queue of unresolved entries */
static atomic_t cache_resolve_queue_len;		/* Size of unresolved	*/

/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);

/* We return to original Alan's scheme. Hash table of resolved
   entries is changed only in process context and protected
   with weak lock mrt_lock. Queue of unresolved entries is protected
   with strong spinlock mfc_unres_lock.

   In this case data path is free of exclusive locks at all.
 */

static struct kmem_cache *mrt_cachep __read_mostly;

static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache);
96
static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert);
97 98
static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm);

99 100 101 102
#ifdef CONFIG_IPV6_PIMSM_V2
static struct inet6_protocol pim6_protocol;
#endif

103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
static struct timer_list ipmr_expire_timer;


#ifdef CONFIG_PROC_FS

struct ipmr_mfc_iter {
	struct mfc6_cache **cache;
	int ct;
};


static struct mfc6_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos)
{
	struct mfc6_cache *mfc;

	it->cache = mfc6_cache_array;
	read_lock(&mrt_lock);
	for (it->ct = 0; it->ct < ARRAY_SIZE(mfc6_cache_array); it->ct++)
		for (mfc = mfc6_cache_array[it->ct]; mfc; mfc = mfc->next)
			if (pos-- == 0)
				return mfc;
	read_unlock(&mrt_lock);

	it->cache = &mfc_unres_queue;
	spin_lock_bh(&mfc_unres_lock);
	for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
		if (pos-- == 0)
			return mfc;
	spin_unlock_bh(&mfc_unres_lock);

	it->cache = NULL;
	return NULL;
}




/*
 *	The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif
 */

struct ipmr_vif_iter {
	int ct;
};

static struct mif_device *ip6mr_vif_seq_idx(struct ipmr_vif_iter *iter,
					    loff_t pos)
{
	for (iter->ct = 0; iter->ct < maxvif; ++iter->ct) {
		if (!MIF_EXISTS(iter->ct))
			continue;
		if (pos-- == 0)
			return &vif6_table[iter->ct];
	}
	return NULL;
}

static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(mrt_lock)
{
	read_lock(&mrt_lock);
	return (*pos ? ip6mr_vif_seq_idx(seq->private, *pos - 1)
		: SEQ_START_TOKEN);
}

static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct ipmr_vif_iter *iter = seq->private;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return ip6mr_vif_seq_idx(iter, 0);

	while (++iter->ct < maxvif) {
		if (!MIF_EXISTS(iter->ct))
			continue;
		return &vif6_table[iter->ct];
	}
	return NULL;
}

static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
	__releases(mrt_lock)
{
	read_unlock(&mrt_lock);
}

static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
			 "Interface      BytesIn  PktsIn  BytesOut PktsOut Flags\n");
	} else {
		const struct mif_device *vif = v;
		const char *name = vif->dev ? vif->dev->name : "none";

		seq_printf(seq,
A
Al Viro 已提交
200
			   "%2td %-10s %8ld %7ld  %8ld %7ld %05X\n",
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
			   vif - vif6_table,
			   name, vif->bytes_in, vif->pkt_in,
			   vif->bytes_out, vif->pkt_out,
			   vif->flags);
	}
	return 0;
}

static struct seq_operations ip6mr_vif_seq_ops = {
	.start = ip6mr_vif_seq_start,
	.next  = ip6mr_vif_seq_next,
	.stop  = ip6mr_vif_seq_stop,
	.show  = ip6mr_vif_seq_show,
};

static int ip6mr_vif_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &ip6mr_vif_seq_ops,
				sizeof(struct ipmr_vif_iter));
}

static struct file_operations ip6mr_vif_fops = {
	.owner	 = THIS_MODULE,
	.open    = ip6mr_vif_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
227
	.release = seq_release_private,
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299
};

static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
	return (*pos ? ipmr_mfc_seq_idx(seq->private, *pos - 1)
		: SEQ_START_TOKEN);
}

static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct mfc6_cache *mfc = v;
	struct ipmr_mfc_iter *it = seq->private;

	++*pos;

	if (v == SEQ_START_TOKEN)
		return ipmr_mfc_seq_idx(seq->private, 0);

	if (mfc->next)
		return mfc->next;

	if (it->cache == &mfc_unres_queue)
		goto end_of_list;

	BUG_ON(it->cache != mfc6_cache_array);

	while (++it->ct < ARRAY_SIZE(mfc6_cache_array)) {
		mfc = mfc6_cache_array[it->ct];
		if (mfc)
			return mfc;
	}

	/* exhausted cache_array, show unresolved */
	read_unlock(&mrt_lock);
	it->cache = &mfc_unres_queue;
	it->ct = 0;

	spin_lock_bh(&mfc_unres_lock);
	mfc = mfc_unres_queue;
	if (mfc)
		return mfc;

 end_of_list:
	spin_unlock_bh(&mfc_unres_lock);
	it->cache = NULL;

	return NULL;
}

static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
	struct ipmr_mfc_iter *it = seq->private;

	if (it->cache == &mfc_unres_queue)
		spin_unlock_bh(&mfc_unres_lock);
	else if (it->cache == mfc6_cache_array)
		read_unlock(&mrt_lock);
}

static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
	int n;

	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
			 "Group                            "
			 "Origin                           "
			 "Iif      Pkts  Bytes     Wrong  Oifs\n");
	} else {
		const struct mfc6_cache *mfc = v;
		const struct ipmr_mfc_iter *it = seq->private;

300
		seq_printf(seq, "%pI6 %pI6 %-3hd",
301
			   &mfc->mf6c_mcastgrp, &mfc->mf6c_origin,
302
			   mfc->mf6c_parent);
303 304

		if (it->cache != &mfc_unres_queue) {
305 306 307 308
			seq_printf(seq, " %8lu %8lu %8lu",
				   mfc->mfc_un.res.pkt,
				   mfc->mfc_un.res.bytes,
				   mfc->mfc_un.res.wrong_if);
309 310 311 312 313 314 315 316
			for (n = mfc->mfc_un.res.minvif;
			     n < mfc->mfc_un.res.maxvif; n++) {
				if (MIF_EXISTS(n) &&
				    mfc->mfc_un.res.ttls[n] < 255)
					seq_printf(seq,
						   " %2d:%-3d",
						   n, mfc->mfc_un.res.ttls[n]);
			}
317 318 319 320 321
		} else {
			/* unresolved mfc_caches don't contain
			 * pkt, bytes and wrong_if values
			 */
			seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul);
322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
		}
		seq_putc(seq, '\n');
	}
	return 0;
}

static struct seq_operations ipmr_mfc_seq_ops = {
	.start = ipmr_mfc_seq_start,
	.next  = ipmr_mfc_seq_next,
	.stop  = ipmr_mfc_seq_stop,
	.show  = ipmr_mfc_seq_show,
};

static int ipmr_mfc_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &ipmr_mfc_seq_ops,
				sizeof(struct ipmr_mfc_iter));
}

static struct file_operations ip6mr_mfc_fops = {
	.owner	 = THIS_MODULE,
	.open    = ipmr_mfc_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
346
	.release = seq_release_private,
347 348 349
};
#endif

350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
#ifdef CONFIG_IPV6_PIMSM_V2
static int reg_vif_num = -1;

static int pim6_rcv(struct sk_buff *skb)
{
	struct pimreghdr *pim;
	struct ipv6hdr   *encap;
	struct net_device  *reg_dev = NULL;

	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap)))
		goto drop;

	pim = (struct pimreghdr *)skb_transport_header(skb);
	if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
	    (pim->flags & PIM_NULL_REGISTER) ||
	    (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
366
	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
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
		goto drop;

	/* check if the inner packet is destined to mcast group */
	encap = (struct ipv6hdr *)(skb_transport_header(skb) +
				   sizeof(*pim));

	if (!ipv6_addr_is_multicast(&encap->daddr) ||
	    encap->payload_len == 0 ||
	    ntohs(encap->payload_len) + sizeof(*pim) > skb->len)
		goto drop;

	read_lock(&mrt_lock);
	if (reg_vif_num >= 0)
		reg_dev = vif6_table[reg_vif_num].dev;
	if (reg_dev)
		dev_hold(reg_dev);
	read_unlock(&mrt_lock);

	if (reg_dev == NULL)
		goto drop;

	skb->mac_header = skb->network_header;
	skb_pull(skb, (u8 *)encap - skb->data);
	skb_reset_network_header(skb);
	skb->dev = reg_dev;
	skb->protocol = htons(ETH_P_IP);
	skb->ip_summed = 0;
	skb->pkt_type = PACKET_HOST;
	dst_release(skb->dst);
396 397
	reg_dev->stats.rx_bytes += skb->len;
	reg_dev->stats.rx_packets++;
398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416
	skb->dst = NULL;
	nf_reset(skb);
	netif_rx(skb);
	dev_put(reg_dev);
	return 0;
 drop:
	kfree_skb(skb);
	return 0;
}

static struct inet6_protocol pim6_protocol = {
	.handler	=	pim6_rcv,
};

/* Service routines creating virtual interfaces: PIMREG */

static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
{
	read_lock(&mrt_lock);
417 418
	dev->stats.tx_bytes += skb->len;
	dev->stats.tx_packets++;
419 420 421 422 423 424
	ip6mr_cache_report(skb, reg_vif_num, MRT6MSG_WHOLEPKT);
	read_unlock(&mrt_lock);
	kfree_skb(skb);
	return 0;
}

425 426 427 428
static const struct net_device_ops reg_vif_netdev_ops = {
	.ndo_start_xmit	= reg_vif_xmit,
};

429 430 431 432 433
static void reg_vif_setup(struct net_device *dev)
{
	dev->type		= ARPHRD_PIMREG;
	dev->mtu		= 1500 - sizeof(struct ipv6hdr) - 8;
	dev->flags		= IFF_NOARP;
434
	dev->netdev_ops		= &reg_vif_netdev_ops;
435 436 437 438 439 440 441
	dev->destructor		= free_netdev;
}

static struct net_device *ip6mr_reg_vif(void)
{
	struct net_device *dev;

442
	dev = alloc_netdev(0, "pim6reg", reg_vif_setup);
443 444 445 446 447 448 449 450 451 452 453 454
	if (dev == NULL)
		return NULL;

	if (register_netdevice(dev)) {
		free_netdev(dev);
		return NULL;
	}
	dev->iflink = 0;

	if (dev_open(dev))
		goto failure;

W
Wang Chen 已提交
455
	dev_hold(dev);
456 457 458 459 460 461 462 463 464 465 466 467
	return dev;

failure:
	/* allow the register to be completed before unregistering. */
	rtnl_unlock();
	rtnl_lock();

	unregister_netdevice(dev);
	return NULL;
}
#endif

468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489
/*
 *	Delete a VIF entry
 */

static int mif6_delete(int vifi)
{
	struct mif_device *v;
	struct net_device *dev;
	if (vifi < 0 || vifi >= maxvif)
		return -EADDRNOTAVAIL;

	v = &vif6_table[vifi];

	write_lock_bh(&mrt_lock);
	dev = v->dev;
	v->dev = NULL;

	if (!dev) {
		write_unlock_bh(&mrt_lock);
		return -EADDRNOTAVAIL;
	}

490 491 492 493 494
#ifdef CONFIG_IPV6_PIMSM_V2
	if (vifi == reg_vif_num)
		reg_vif_num = -1;
#endif

495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
	if (vifi + 1 == maxvif) {
		int tmp;
		for (tmp = vifi - 1; tmp >= 0; tmp--) {
			if (MIF_EXISTS(tmp))
				break;
		}
		maxvif = tmp + 1;
	}

	write_unlock_bh(&mrt_lock);

	dev_set_allmulti(dev, -1);

	if (v->flags & MIFF_REGISTER)
		unregister_netdevice(dev);

	dev_put(dev);
	return 0;
}

/* Destroy an unresolved cache entry, killing queued skbs
   and reporting error to netlink readers.
 */

static void ip6mr_destroy_unres(struct mfc6_cache *c)
{
	struct sk_buff *skb;

	atomic_dec(&cache_resolve_queue_len);

	while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
		if (ipv6_hdr(skb)->version == 0) {
			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
			nlh->nlmsg_type = NLMSG_ERROR;
			nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
			skb_trim(skb, nlh->nlmsg_len);
			((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT;
			rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid);
		} else
			kfree_skb(skb);
	}

	kmem_cache_free(mrt_cachep, c);
}


/* Single timer process for all the unresolved queue. */

static void ipmr_do_expire_process(unsigned long dummy)
{
	unsigned long now = jiffies;
	unsigned long expires = 10 * HZ;
	struct mfc6_cache *c, **cp;

	cp = &mfc_unres_queue;

	while ((c = *cp) != NULL) {
		if (time_after(c->mfc_un.unres.expires, now)) {
			/* not yet... */
			unsigned long interval = c->mfc_un.unres.expires - now;
			if (interval < expires)
				expires = interval;
			cp = &c->next;
			continue;
		}

		*cp = c->next;
		ip6mr_destroy_unres(c);
	}

	if (atomic_read(&cache_resolve_queue_len))
		mod_timer(&ipmr_expire_timer, jiffies + expires);
}

static void ipmr_expire_process(unsigned long dummy)
{
	if (!spin_trylock(&mfc_unres_lock)) {
		mod_timer(&ipmr_expire_timer, jiffies + 1);
		return;
	}

	if (atomic_read(&cache_resolve_queue_len))
		ipmr_do_expire_process(dummy);

	spin_unlock(&mfc_unres_lock);
}

/* Fill oifs list. It is called under write locked mrt_lock. */

static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls)
{
	int vifi;

588
	cache->mfc_un.res.minvif = MAXMIFS;
589
	cache->mfc_un.res.maxvif = 0;
590
	memset(cache->mfc_un.res.ttls, 255, MAXMIFS);
591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607

	for (vifi = 0; vifi < maxvif; vifi++) {
		if (MIF_EXISTS(vifi) && ttls[vifi] && ttls[vifi] < 255) {
			cache->mfc_un.res.ttls[vifi] = ttls[vifi];
			if (cache->mfc_un.res.minvif > vifi)
				cache->mfc_un.res.minvif = vifi;
			if (cache->mfc_un.res.maxvif <= vifi)
				cache->mfc_un.res.maxvif = vifi + 1;
		}
	}
}

static int mif6_add(struct mif6ctl *vifc, int mrtsock)
{
	int vifi = vifc->mif6c_mifi;
	struct mif_device *v = &vif6_table[vifi];
	struct net_device *dev;
608
	int err;
609 610 611 612 613 614

	/* Is vif busy ? */
	if (MIF_EXISTS(vifi))
		return -EADDRINUSE;

	switch (vifc->mif6c_flags) {
615 616 617 618 619 620 621 622 623 624 625
#ifdef CONFIG_IPV6_PIMSM_V2
	case MIFF_REGISTER:
		/*
		 * Special Purpose VIF in PIM
		 * All the packets will be sent to the daemon
		 */
		if (reg_vif_num >= 0)
			return -EADDRINUSE;
		dev = ip6mr_reg_vif();
		if (!dev)
			return -ENOBUFS;
626 627 628
		err = dev_set_allmulti(dev, 1);
		if (err) {
			unregister_netdevice(dev);
W
Wang Chen 已提交
629
			dev_put(dev);
630 631
			return err;
		}
632 633
		break;
#endif
634 635 636 637
	case 0:
		dev = dev_get_by_index(&init_net, vifc->mif6c_pifi);
		if (!dev)
			return -EADDRNOTAVAIL;
638
		err = dev_set_allmulti(dev, 1);
W
Wang Chen 已提交
639 640
		if (err) {
			dev_put(dev);
641
			return err;
W
Wang Chen 已提交
642
		}
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
		break;
	default:
		return -EINVAL;
	}

	/*
	 *	Fill in the VIF structures
	 */
	v->rate_limit = vifc->vifc_rate_limit;
	v->flags = vifc->mif6c_flags;
	if (!mrtsock)
		v->flags |= VIFF_STATIC;
	v->threshold = vifc->vifc_threshold;
	v->bytes_in = 0;
	v->bytes_out = 0;
	v->pkt_in = 0;
	v->pkt_out = 0;
	v->link = dev->ifindex;
	if (v->flags & MIFF_REGISTER)
		v->link = dev->iflink;

	/* And finish update writing critical data */
	write_lock_bh(&mrt_lock);
	v->dev = dev;
667 668 669 670
#ifdef CONFIG_IPV6_PIMSM_V2
	if (v->flags & MIFF_REGISTER)
		reg_vif_num = vifi;
#endif
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694
	if (vifi + 1 > maxvif)
		maxvif = vifi + 1;
	write_unlock_bh(&mrt_lock);
	return 0;
}

static struct mfc6_cache *ip6mr_cache_find(struct in6_addr *origin, struct in6_addr *mcastgrp)
{
	int line = MFC6_HASH(mcastgrp, origin);
	struct mfc6_cache *c;

	for (c = mfc6_cache_array[line]; c; c = c->next) {
		if (ipv6_addr_equal(&c->mf6c_origin, origin) &&
		    ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp))
			break;
	}
	return c;
}

/*
 *	Allocate a multicast cache entry
 */
static struct mfc6_cache *ip6mr_cache_alloc(void)
{
695
	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
696 697
	if (c == NULL)
		return NULL;
698
	c->mfc_un.res.minvif = MAXMIFS;
699 700 701 702 703
	return c;
}

static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
{
704
	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
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
	if (c == NULL)
		return NULL;
	skb_queue_head_init(&c->mfc_un.unres.unresolved);
	c->mfc_un.unres.expires = jiffies + 10 * HZ;
	return c;
}

/*
 *	A cache entry has gone into a resolved state from queued
 */

static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c)
{
	struct sk_buff *skb;

	/*
	 *	Play the pending entries through our router
	 */

	while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
		if (ipv6_hdr(skb)->version == 0) {
			int err;
			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));

			if (ip6mr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) {
730
				nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh;
731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
			} else {
				nlh->nlmsg_type = NLMSG_ERROR;
				nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
				skb_trim(skb, nlh->nlmsg_len);
				((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE;
			}
			err = rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid);
		} else
			ip6_mr_forward(skb, c);
	}
}

/*
 *	Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd
 *	expects the following bizarre scheme.
 *
 *	Called under mrt_lock.
 */

750
static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert)
751 752 753 754 755
{
	struct sk_buff *skb;
	struct mrt6msg *msg;
	int ret;

756 757 758 759 760 761 762
#ifdef CONFIG_IPV6_PIMSM_V2
	if (assert == MRT6MSG_WHOLEPKT)
		skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt)
						+sizeof(*msg));
	else
#endif
		skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC);
763 764 765 766 767 768 769 770 771

	if (!skb)
		return -ENOBUFS;

	/* I suppose that internal messages
	 * do not require checksums */

	skb->ip_summed = CHECKSUM_UNNECESSARY;

772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
#ifdef CONFIG_IPV6_PIMSM_V2
	if (assert == MRT6MSG_WHOLEPKT) {
		/* Ugly, but we have no choice with this interface.
		   Duplicate old header, fix length etc.
		   And all this only to mangle msg->im6_msgtype and
		   to set msg->im6_mbz to "mbz" :-)
		 */
		skb_push(skb, -skb_network_offset(pkt));

		skb_push(skb, sizeof(*msg));
		skb_reset_transport_header(skb);
		msg = (struct mrt6msg *)skb_transport_header(skb);
		msg->im6_mbz = 0;
		msg->im6_msgtype = MRT6MSG_WHOLEPKT;
		msg->im6_mif = reg_vif_num;
		msg->im6_pad = 0;
		ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
		ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);

		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else
#endif
	{
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811
	/*
	 *	Copy the IP header
	 */

	skb_put(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr));

	/*
	 *	Add our header
	 */
	skb_put(skb, sizeof(*msg));
	skb_reset_transport_header(skb);
	msg = (struct mrt6msg *)skb_transport_header(skb);

	msg->im6_mbz = 0;
	msg->im6_msgtype = assert;
812
	msg->im6_mif = mifi;
813 814 815 816 817 818 819 820
	msg->im6_pad = 0;
	ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
	ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);

	skb->dst = dst_clone(pkt->dst);
	skb->ip_summed = CHECKSUM_UNNECESSARY;

	skb_pull(skb, sizeof(struct ipv6hdr));
821
	}
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844

	if (mroute6_socket == NULL) {
		kfree_skb(skb);
		return -EINVAL;
	}

	/*
	 *	Deliver to user space multicast routing algorithms
	 */
	if ((ret = sock_queue_rcv_skb(mroute6_socket, skb)) < 0) {
		if (net_ratelimit())
			printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n");
		kfree_skb(skb);
	}

	return ret;
}

/*
 *	Queue a packet for resolution. It gets locked cache entry!
 */

static int
845
ip6mr_cache_unresolved(mifi_t mifi, struct sk_buff *skb)
846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879
{
	int err;
	struct mfc6_cache *c;

	spin_lock_bh(&mfc_unres_lock);
	for (c = mfc_unres_queue; c; c = c->next) {
		if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) &&
		    ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr))
			break;
	}

	if (c == NULL) {
		/*
		 *	Create a new entry if allowable
		 */

		if (atomic_read(&cache_resolve_queue_len) >= 10 ||
		    (c = ip6mr_cache_alloc_unres()) == NULL) {
			spin_unlock_bh(&mfc_unres_lock);

			kfree_skb(skb);
			return -ENOBUFS;
		}

		/*
		 *	Fill in the new cache entry
		 */
		c->mf6c_parent = -1;
		c->mf6c_origin = ipv6_hdr(skb)->saddr;
		c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr;

		/*
		 *	Reflect first query at pim6sd
		 */
880
		if ((err = ip6mr_cache_report(skb, mifi, MRT6MSG_NOCACHE)) < 0) {
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
			/* If the report failed throw the cache entry
			   out - Brad Parker
			 */
			spin_unlock_bh(&mfc_unres_lock);

			kmem_cache_free(mrt_cachep, c);
			kfree_skb(skb);
			return err;
		}

		atomic_inc(&cache_resolve_queue_len);
		c->next = mfc_unres_queue;
		mfc_unres_queue = c;

		ipmr_do_expire_process(1);
	}

	/*
	 *	See if we can append the packet
	 */
	if (c->mfc_un.unres.unresolved.qlen > 3) {
		kfree_skb(skb);
		err = -ENOBUFS;
	} else {
		skb_queue_tail(&c->mfc_un.unres.unresolved, skb);
		err = 0;
	}

	spin_unlock_bh(&mfc_unres_lock);
	return err;
}

/*
 *	MFC6 cache manipulation by user space
 */

static int ip6mr_mfc_delete(struct mf6cctl *mfc)
{
	int line;
	struct mfc6_cache *c, **cp;

	line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);

	for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) {
		if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
		    ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) {
			write_lock_bh(&mrt_lock);
			*cp = c->next;
			write_unlock_bh(&mrt_lock);

			kmem_cache_free(mrt_cachep, c);
			return 0;
		}
	}
	return -ENOENT;
}

static int ip6mr_device_event(struct notifier_block *this,
			      unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;
	struct mif_device *v;
	int ct;

945
	if (!net_eq(dev_net(dev), &init_net))
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
		return NOTIFY_DONE;

	if (event != NETDEV_UNREGISTER)
		return NOTIFY_DONE;

	v = &vif6_table[0];
	for (ct = 0; ct < maxvif; ct++, v++) {
		if (v->dev == dev)
			mif6_delete(ct);
	}
	return NOTIFY_DONE;
}

static struct notifier_block ip6_mr_notifier = {
	.notifier_call = ip6mr_device_event
};

/*
 *	Setup for IP multicast routing
 */

W
Wang Chen 已提交
967
int __init ip6_mr_init(void)
968
{
W
Wang Chen 已提交
969 970
	int err;

971 972 973 974 975
	mrt_cachep = kmem_cache_create("ip6_mrt_cache",
				       sizeof(struct mfc6_cache),
				       0, SLAB_HWCACHE_ALIGN,
				       NULL);
	if (!mrt_cachep)
W
Wang Chen 已提交
976
		return -ENOMEM;
977 978

	setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
W
Wang Chen 已提交
979 980 981 982 983 984 985 986 987 988 989 990
	err = register_netdevice_notifier(&ip6_mr_notifier);
	if (err)
		goto reg_notif_fail;
#ifdef CONFIG_PROC_FS
	err = -ENOMEM;
	if (!proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops))
		goto proc_vif_fail;
	if (!proc_net_fops_create(&init_net, "ip6_mr_cache",
				     0, &ip6mr_mfc_fops))
		goto proc_cache_fail;
#endif
	return 0;
991
#ifdef CONFIG_PROC_FS
W
Wang Chen 已提交
992 993
proc_cache_fail:
	proc_net_remove(&init_net, "ip6_mr_vif");
B
Benjamin Thery 已提交
994 995
proc_vif_fail:
	unregister_netdevice_notifier(&ip6_mr_notifier);
996
#endif
B
Benjamin Thery 已提交
997 998 999
reg_notif_fail:
	del_timer(&ipmr_expire_timer);
	kmem_cache_destroy(mrt_cachep);
W
Wang Chen 已提交
1000
	return err;
1001 1002
}

W
Wang Chen 已提交
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
void ip6_mr_cleanup(void)
{
#ifdef CONFIG_PROC_FS
	proc_net_remove(&init_net, "ip6_mr_cache");
	proc_net_remove(&init_net, "ip6_mr_vif");
#endif
	unregister_netdevice_notifier(&ip6_mr_notifier);
	del_timer(&ipmr_expire_timer);
	kmem_cache_destroy(mrt_cachep);
}
1013 1014 1015 1016 1017

static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock)
{
	int line;
	struct mfc6_cache *uc, *c, **cp;
1018
	unsigned char ttls[MAXMIFS];
1019 1020
	int i;

1021 1022
	memset(ttls, 255, MAXMIFS);
	for (i = 0; i < MAXMIFS; i++) {
1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213
		if (IF_ISSET(i, &mfc->mf6cc_ifset))
			ttls[i] = 1;

	}

	line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);

	for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) {
		if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
		    ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr))
			break;
	}

	if (c != NULL) {
		write_lock_bh(&mrt_lock);
		c->mf6c_parent = mfc->mf6cc_parent;
		ip6mr_update_thresholds(c, ttls);
		if (!mrtsock)
			c->mfc_flags |= MFC_STATIC;
		write_unlock_bh(&mrt_lock);
		return 0;
	}

	if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr))
		return -EINVAL;

	c = ip6mr_cache_alloc();
	if (c == NULL)
		return -ENOMEM;

	c->mf6c_origin = mfc->mf6cc_origin.sin6_addr;
	c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr;
	c->mf6c_parent = mfc->mf6cc_parent;
	ip6mr_update_thresholds(c, ttls);
	if (!mrtsock)
		c->mfc_flags |= MFC_STATIC;

	write_lock_bh(&mrt_lock);
	c->next = mfc6_cache_array[line];
	mfc6_cache_array[line] = c;
	write_unlock_bh(&mrt_lock);

	/*
	 *	Check to see if we resolved a queued list. If so we
	 *	need to send on the frames and tidy up.
	 */
	spin_lock_bh(&mfc_unres_lock);
	for (cp = &mfc_unres_queue; (uc = *cp) != NULL;
	     cp = &uc->next) {
		if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) &&
		    ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) {
			*cp = uc->next;
			if (atomic_dec_and_test(&cache_resolve_queue_len))
				del_timer(&ipmr_expire_timer);
			break;
		}
	}
	spin_unlock_bh(&mfc_unres_lock);

	if (uc) {
		ip6mr_cache_resolve(uc, c);
		kmem_cache_free(mrt_cachep, uc);
	}
	return 0;
}

/*
 *	Close the multicast socket, and clear the vif tables etc
 */

static void mroute_clean_tables(struct sock *sk)
{
	int i;

	/*
	 *	Shut down all active vif entries
	 */
	for (i = 0; i < maxvif; i++) {
		if (!(vif6_table[i].flags & VIFF_STATIC))
			mif6_delete(i);
	}

	/*
	 *	Wipe the cache
	 */
	for (i = 0; i < ARRAY_SIZE(mfc6_cache_array); i++) {
		struct mfc6_cache *c, **cp;

		cp = &mfc6_cache_array[i];
		while ((c = *cp) != NULL) {
			if (c->mfc_flags & MFC_STATIC) {
				cp = &c->next;
				continue;
			}
			write_lock_bh(&mrt_lock);
			*cp = c->next;
			write_unlock_bh(&mrt_lock);

			kmem_cache_free(mrt_cachep, c);
		}
	}

	if (atomic_read(&cache_resolve_queue_len) != 0) {
		struct mfc6_cache *c;

		spin_lock_bh(&mfc_unres_lock);
		while (mfc_unres_queue != NULL) {
			c = mfc_unres_queue;
			mfc_unres_queue = c->next;
			spin_unlock_bh(&mfc_unres_lock);

			ip6mr_destroy_unres(c);

			spin_lock_bh(&mfc_unres_lock);
		}
		spin_unlock_bh(&mfc_unres_lock);
	}
}

static int ip6mr_sk_init(struct sock *sk)
{
	int err = 0;

	rtnl_lock();
	write_lock_bh(&mrt_lock);
	if (likely(mroute6_socket == NULL))
		mroute6_socket = sk;
	else
		err = -EADDRINUSE;
	write_unlock_bh(&mrt_lock);

	rtnl_unlock();

	return err;
}

int ip6mr_sk_done(struct sock *sk)
{
	int err = 0;

	rtnl_lock();
	if (sk == mroute6_socket) {
		write_lock_bh(&mrt_lock);
		mroute6_socket = NULL;
		write_unlock_bh(&mrt_lock);

		mroute_clean_tables(sk);
	} else
		err = -EACCES;
	rtnl_unlock();

	return err;
}

/*
 *	Socket options and virtual interface manipulation. The whole
 *	virtual interface system is a complete heap, but unfortunately
 *	that's how BSD mrouted happens to think. Maybe one day with a proper
 *	MOSPF/PIM router set up we can clean this up.
 */

int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen)
{
	int ret;
	struct mif6ctl vif;
	struct mf6cctl mfc;
	mifi_t mifi;

	if (optname != MRT6_INIT) {
		if (sk != mroute6_socket && !capable(CAP_NET_ADMIN))
			return -EACCES;
	}

	switch (optname) {
	case MRT6_INIT:
		if (sk->sk_type != SOCK_RAW ||
		    inet_sk(sk)->num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		if (optlen < sizeof(int))
			return -EINVAL;

		return ip6mr_sk_init(sk);

	case MRT6_DONE:
		return ip6mr_sk_done(sk);

	case MRT6_ADD_MIF:
		if (optlen < sizeof(vif))
			return -EINVAL;
		if (copy_from_user(&vif, optval, sizeof(vif)))
			return -EFAULT;
1214
		if (vif.mif6c_mifi >= MAXMIFS)
1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
			return -ENFILE;
		rtnl_lock();
		ret = mif6_add(&vif, sk == mroute6_socket);
		rtnl_unlock();
		return ret;

	case MRT6_DEL_MIF:
		if (optlen < sizeof(mifi_t))
			return -EINVAL;
		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
			return -EFAULT;
		rtnl_lock();
		ret = mif6_delete(mifi);
		rtnl_unlock();
		return ret;

	/*
	 *	Manipulate the forwarding caches. These live
	 *	in a sort of kernel/user symbiosis.
	 */
	case MRT6_ADD_MFC:
	case MRT6_DEL_MFC:
		if (optlen < sizeof(mfc))
			return -EINVAL;
		if (copy_from_user(&mfc, optval, sizeof(mfc)))
			return -EFAULT;
		rtnl_lock();
		if (optname == MRT6_DEL_MFC)
			ret = ip6mr_mfc_delete(&mfc);
		else
			ret = ip6mr_mfc_add(&mfc, sk == mroute6_socket);
		rtnl_unlock();
		return ret;

1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263
	/*
	 *	Control PIM assert (to activate pim will activate assert)
	 */
	case MRT6_ASSERT:
	{
		int v;
		if (get_user(v, (int __user *)optval))
			return -EFAULT;
		mroute_do_assert = !!v;
		return 0;
	}

#ifdef CONFIG_IPV6_PIMSM_V2
	case MRT6_PIM:
	{
1264
		int v;
1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286
		if (get_user(v, (int __user *)optval))
			return -EFAULT;
		v = !!v;
		rtnl_lock();
		ret = 0;
		if (v != mroute_do_pim) {
			mroute_do_pim = v;
			mroute_do_assert = v;
			if (mroute_do_pim)
				ret = inet6_add_protocol(&pim6_protocol,
							 IPPROTO_PIM);
			else
				ret = inet6_del_protocol(&pim6_protocol,
							 IPPROTO_PIM);
			if (ret < 0)
				ret = -EAGAIN;
		}
		rtnl_unlock();
		return ret;
	}

#endif
1287
	/*
1288
	 *	Spurious command, or MRT6_VERSION which you cannot
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309
	 *	set.
	 */
	default:
		return -ENOPROTOOPT;
	}
}

/*
 *	Getsock opt support for the multicast routing system.
 */

int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
			  int __user *optlen)
{
	int olr;
	int val;

	switch (optname) {
	case MRT6_VERSION:
		val = 0x0305;
		break;
1310 1311 1312 1313 1314 1315 1316 1317
#ifdef CONFIG_IPV6_PIMSM_V2
	case MRT6_PIM:
		val = mroute_do_pim;
		break;
#endif
	case MRT6_ASSERT:
		val = mroute_do_assert;
		break;
1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393
	default:
		return -ENOPROTOOPT;
	}

	if (get_user(olr, optlen))
		return -EFAULT;

	olr = min_t(int, olr, sizeof(int));
	if (olr < 0)
		return -EINVAL;

	if (put_user(olr, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val, olr))
		return -EFAULT;
	return 0;
}

/*
 *	The IP multicast ioctl support routines.
 */

int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
{
	struct sioc_sg_req6 sr;
	struct sioc_mif_req6 vr;
	struct mif_device *vif;
	struct mfc6_cache *c;

	switch (cmd) {
	case SIOCGETMIFCNT_IN6:
		if (copy_from_user(&vr, arg, sizeof(vr)))
			return -EFAULT;
		if (vr.mifi >= maxvif)
			return -EINVAL;
		read_lock(&mrt_lock);
		vif = &vif6_table[vr.mifi];
		if (MIF_EXISTS(vr.mifi)) {
			vr.icount = vif->pkt_in;
			vr.ocount = vif->pkt_out;
			vr.ibytes = vif->bytes_in;
			vr.obytes = vif->bytes_out;
			read_unlock(&mrt_lock);

			if (copy_to_user(arg, &vr, sizeof(vr)))
				return -EFAULT;
			return 0;
		}
		read_unlock(&mrt_lock);
		return -EADDRNOTAVAIL;
	case SIOCGETSGCNT_IN6:
		if (copy_from_user(&sr, arg, sizeof(sr)))
			return -EFAULT;

		read_lock(&mrt_lock);
		c = ip6mr_cache_find(&sr.src.sin6_addr, &sr.grp.sin6_addr);
		if (c) {
			sr.pktcnt = c->mfc_un.res.pkt;
			sr.bytecnt = c->mfc_un.res.bytes;
			sr.wrong_if = c->mfc_un.res.wrong_if;
			read_unlock(&mrt_lock);

			if (copy_to_user(arg, &sr, sizeof(sr)))
				return -EFAULT;
			return 0;
		}
		read_unlock(&mrt_lock);
		return -EADDRNOTAVAIL;
	default:
		return -ENOIOCTLCMD;
	}
}


static inline int ip6mr_forward2_finish(struct sk_buff *skb)
{
1394 1395
	IP6_INC_STATS_BH(dev_net(skb->dst->dev), ip6_dst_idev(skb->dst),
			 IPSTATS_MIB_OUTFORWDATAGRAMS);
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413
	return dst_output(skb);
}

/*
 *	Processing handlers for ip6mr_forward
 */

static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi)
{
	struct ipv6hdr *ipv6h;
	struct mif_device *vif = &vif6_table[vifi];
	struct net_device *dev;
	struct dst_entry *dst;
	struct flowi fl;

	if (vif->dev == NULL)
		goto out_free;

1414 1415 1416 1417
#ifdef CONFIG_IPV6_PIMSM_V2
	if (vif->flags & MIFF_REGISTER) {
		vif->pkt_out++;
		vif->bytes_out += skb->len;
1418 1419
		vif->dev->stats.tx_bytes += skb->len;
		vif->dev->stats.tx_packets++;
1420 1421 1422 1423 1424 1425
		ip6mr_cache_report(skb, vifi, MRT6MSG_WHOLEPKT);
		kfree_skb(skb);
		return 0;
	}
#endif

1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
	ipv6h = ipv6_hdr(skb);

	fl = (struct flowi) {
		.oif = vif->link,
		.nl_u = { .ip6_u =
				{ .daddr = ipv6h->daddr, }
		}
	};

	dst = ip6_route_output(&init_net, NULL, &fl);
	if (!dst)
		goto out_free;

	dst_release(skb->dst);
	skb->dst = dst;

	/*
	 * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
	 * not only before forwarding, but after forwarding on all output
	 * interfaces. It is clear, if mrouter runs a multicasting
	 * program, it should receive packets not depending to what interface
	 * program is joined.
	 * If we will not make it, the program will have to join on all
	 * interfaces. On the other hand, multihoming host (or router, but
	 * not mrouter) cannot join to more than one interface - it will
	 * result in receiving multiple packets.
	 */
	dev = vif->dev;
	skb->dev = dev;
	vif->pkt_out++;
	vif->bytes_out += skb->len;

	/* We are about to write */
	/* XXX: extension headers? */
	if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(dev)))
		goto out_free;

	ipv6h = ipv6_hdr(skb);
	ipv6h->hop_limit--;

	IP6CB(skb)->flags |= IP6SKB_FORWARDED;

	return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dev,
		       ip6mr_forward2_finish);

out_free:
	kfree_skb(skb);
	return 0;
}

static int ip6mr_find_vif(struct net_device *dev)
{
	int ct;
	for (ct = maxvif - 1; ct >= 0; ct--) {
		if (vif6_table[ct].dev == dev)
			break;
	}
	return ct;
}

static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache)
{
	int psend = -1;
	int vif, ct;

	vif = cache->mf6c_parent;
	cache->mfc_un.res.pkt++;
	cache->mfc_un.res.bytes += skb->len;

1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518
	/*
	 * Wrong interface: drop packet and (maybe) send PIM assert.
	 */
	if (vif6_table[vif].dev != skb->dev) {
		int true_vifi;

		cache->mfc_un.res.wrong_if++;
		true_vifi = ip6mr_find_vif(skb->dev);

		if (true_vifi >= 0 && mroute_do_assert &&
		    /* pimsm uses asserts, when switching from RPT to SPT,
		       so that we cannot check that packet arrived on an oif.
		       It is bad, but otherwise we would need to move pretty
		       large chunk of pimd to kernel. Ough... --ANK
		     */
		    (mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) &&
		    time_after(jiffies,
			       cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
			cache->mfc_un.res.last_assert = jiffies;
			ip6mr_cache_report(skb, true_vifi, MRT6MSG_WRONGMIF);
		}
		goto dont_forward;
	}

1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539
	vif6_table[vif].pkt_in++;
	vif6_table[vif].bytes_in += skb->len;

	/*
	 *	Forward the frame
	 */
	for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) {
		if (ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) {
			if (psend != -1) {
				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
				if (skb2)
					ip6mr_forward2(skb2, cache, psend);
			}
			psend = ct;
		}
	}
	if (psend != -1) {
		ip6mr_forward2(skb, cache, psend);
		return 0;
	}

1540
dont_forward:
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588
	kfree_skb(skb);
	return 0;
}


/*
 *	Multicast packets for forwarding arrive here
 */

int ip6_mr_input(struct sk_buff *skb)
{
	struct mfc6_cache *cache;

	read_lock(&mrt_lock);
	cache = ip6mr_cache_find(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);

	/*
	 *	No usable cache entry
	 */
	if (cache == NULL) {
		int vif;

		vif = ip6mr_find_vif(skb->dev);
		if (vif >= 0) {
			int err = ip6mr_cache_unresolved(vif, skb);
			read_unlock(&mrt_lock);

			return err;
		}
		read_unlock(&mrt_lock);
		kfree_skb(skb);
		return -ENODEV;
	}

	ip6_mr_forward(skb, cache);

	read_unlock(&mrt_lock);

	return 0;
}


static int
ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm)
{
	int ct;
	struct rtnexthop *nhp;
	struct net_device *dev = vif6_table[c->mf6c_parent].dev;
1589
	u8 *b = skb_tail_pointer(skb);
1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608
	struct rtattr *mp_head;

	if (dev)
		RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex);

	mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));

	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
		if (c->mfc_un.res.ttls[ct] < 255) {
			if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
				goto rtattr_failure;
			nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
			nhp->rtnh_flags = 0;
			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
			nhp->rtnh_ifindex = vif6_table[ct].dev->ifindex;
			nhp->rtnh_len = sizeof(*nhp);
		}
	}
	mp_head->rta_type = RTA_MULTIPATH;
1609
	mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head;
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681
	rtm->rtm_type = RTN_MULTICAST;
	return 1;

rtattr_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}

int ip6mr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait)
{
	int err;
	struct mfc6_cache *cache;
	struct rt6_info *rt = (struct rt6_info *)skb->dst;

	read_lock(&mrt_lock);
	cache = ip6mr_cache_find(&rt->rt6i_src.addr, &rt->rt6i_dst.addr);

	if (!cache) {
		struct sk_buff *skb2;
		struct ipv6hdr *iph;
		struct net_device *dev;
		int vif;

		if (nowait) {
			read_unlock(&mrt_lock);
			return -EAGAIN;
		}

		dev = skb->dev;
		if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) {
			read_unlock(&mrt_lock);
			return -ENODEV;
		}

		/* really correct? */
		skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
		if (!skb2) {
			read_unlock(&mrt_lock);
			return -ENOMEM;
		}

		skb_reset_transport_header(skb2);

		skb_put(skb2, sizeof(struct ipv6hdr));
		skb_reset_network_header(skb2);

		iph = ipv6_hdr(skb2);
		iph->version = 0;
		iph->priority = 0;
		iph->flow_lbl[0] = 0;
		iph->flow_lbl[1] = 0;
		iph->flow_lbl[2] = 0;
		iph->payload_len = 0;
		iph->nexthdr = IPPROTO_NONE;
		iph->hop_limit = 0;
		ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr);
		ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr);

		err = ip6mr_cache_unresolved(vif, skb2);
		read_unlock(&mrt_lock);

		return err;
	}

	if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
		cache->mfc_flags |= MFC_NOTIFY;

	err = ip6mr_fill_mroute(skb, cache, rtm);
	read_unlock(&mrt_lock);
	return err;
}