icmp.c 19.4 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *	Internet Control Message Protocol (ICMPv6)
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	$Id: icmp.c,v 1.38 2002/02/08 03:57:19 davem Exp $
 *
 *	Based on net/ipv4/icmp.c
 *
 *	RFC 1885
 *
 *	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.
 */

/*
 *	Changes:
 *
 *	Andi Kleen		:	exception handling
 *	Andi Kleen			add rate limits. never reply to a icmp.
 *					add more length checks and other fixes.
 *	yoshfuji		:	ensure to sent parameter problem for
 *					fragments.
 *	YOSHIFUJI Hideaki @USAGI:	added sysctl for icmp rate limit.
 *	Randy Dunlap and
 *	YOSHIFUJI Hideaki @USAGI:	Per-interface statistics support
 *	Kazunori MIYAZAWA @USAGI:       change output process to use ip6_append_data
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/init.h>
45
#include <linux/netfilter.h>
L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>

#include <net/ip.h>
#include <net/sock.h>

#include <net/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>

#include <asm/uaccess.h>
#include <asm/system.h>

71
DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly;
L
Linus Torvalds 已提交
72 73 74 75 76 77 78 79 80 81 82

/*
 *	The ICMP socket(s). This is the most convenient way to flow control
 *	our ICMP output as well as maintain a clean interface throughout
 *	all layers. All Socketless IP sends will soon be gone.
 *
 *	On SMP we have one ICMP socket per-cpu.
 */
static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL;
#define icmpv6_socket	__get_cpu_var(__icmpv6_socket)

83
static int icmpv6_rcv(struct sk_buff **pskb);
L
Linus Torvalds 已提交
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138

static struct inet6_protocol icmpv6_protocol = {
	.handler	=	icmpv6_rcv,
	.flags		=	INET6_PROTO_FINAL,
};

static __inline__ int icmpv6_xmit_lock(void)
{
	local_bh_disable();

	if (unlikely(!spin_trylock(&icmpv6_socket->sk->sk_lock.slock))) {
		/* This can happen if the output path (f.e. SIT or
		 * ip6ip6 tunnel) signals dst_link_failure() for an
		 * outgoing ICMP6 packet.
		 */
		local_bh_enable();
		return 1;
	}
	return 0;
}

static __inline__ void icmpv6_xmit_unlock(void)
{
	spin_unlock_bh(&icmpv6_socket->sk->sk_lock.slock);
}

/* 
 * Slightly more convenient version of icmpv6_send.
 */
void icmpv6_param_prob(struct sk_buff *skb, int code, int pos)
{
	icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
	kfree_skb(skb);
}

/*
 * Figure out, may we reply to this packet with icmp error.
 *
 * We do not reply, if:
 *	- it was icmp error message.
 *	- it is truncated, so that it is known, that protocol is ICMPV6
 *	  (i.e. in the middle of some exthdr)
 *
 *	--ANK (980726)
 */

static int is_ineligible(struct sk_buff *skb)
{
	int ptr = (u8*)(skb->nh.ipv6h+1) - skb->data;
	int len = skb->len - ptr;
	__u8 nexthdr = skb->nh.ipv6h->nexthdr;

	if (len < 0)
		return 1;

139
	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
L
Linus Torvalds 已提交
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
	if (ptr < 0)
		return 0;
	if (nexthdr == IPPROTO_ICMPV6) {
		u8 _type, *tp;
		tp = skb_header_pointer(skb,
			ptr+offsetof(struct icmp6hdr, icmp6_type),
			sizeof(_type), &_type);
		if (tp == NULL ||
		    !(*tp & ICMPV6_INFOMSG_MASK))
			return 1;
	}
	return 0;
}

static int sysctl_icmpv6_time = 1*HZ; 

/* 
 * Check the ICMP output rate limit 
 */
static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
				     struct flowi *fl)
{
	struct dst_entry *dst;
	int res = 0;

	/* Informational messages are not limited. */
	if (type & ICMPV6_INFOMSG_MASK)
		return 1;

	/* Do not limit pmtu discovery, it would break it. */
	if (type == ICMPV6_PKT_TOOBIG)
		return 1;

	/* 
	 * Look up the output route.
	 * XXX: perhaps the expire for routing entries cloned by
	 * this lookup should be more aggressive (not longer than timeout).
	 */
	dst = ip6_route_output(sk, fl);
	if (dst->error) {
		IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
		res = 1;
	} else {
		struct rt6_info *rt = (struct rt6_info *)dst;
		int tmo = sysctl_icmpv6_time;

		/* Give more bandwidth to wider prefixes. */
		if (rt->rt6i_dst.plen < 128)
			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);

		res = xrlim_allow(dst, tmo);
	}
	dst_release(dst);
	return res;
}

/*
 *	an inline helper for the "simple" if statement below
 *	checks if parameter problem report is caused by an
 *	unrecognized IPv6 option that has the Option Type 
 *	highest-order two bits set to 10
 */

static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset)
{
	u8 _optval, *op;

	offset += skb->nh.raw - skb->data;
	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
	if (op == NULL)
		return 1;
	return (*op & 0xC0) == 0x80;
}

static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len)
{
	struct sk_buff *skb;
	struct icmp6hdr *icmp6h;
	int err = 0;

	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	icmp6h = (struct icmp6hdr*) skb->h.raw;
	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
	icmp6h->icmp6_cksum = 0;

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		skb->csum = csum_partial((char *)icmp6h,
					sizeof(struct icmp6hdr), skb->csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
						      &fl->fl6_dst,
						      len, fl->proto,
						      skb->csum);
	} else {
		u32 tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);
		}

		tmp_csum = csum_partial((char *)icmp6h,
					sizeof(struct icmp6hdr), tmp_csum);
		tmp_csum = csum_ipv6_magic(&fl->fl6_src,
					   &fl->fl6_dst,
					   len, fl->proto, tmp_csum);
		icmp6h->icmp6_cksum = tmp_csum;
	}
	if (icmp6h->icmp6_cksum == 0)
		icmp6h->icmp6_cksum = -1;
	ip6_push_pending_frames(sk);
out:
	return err;
}

struct icmpv6_msg {
	struct sk_buff	*skb;
	int		offset;
259
	uint8_t		type;
L
Linus Torvalds 已提交
260 261 262 263 264 265 266 267 268 269 270
};

static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
	struct sk_buff *org_skb = msg->skb;
	__u32 csum = 0;

	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
				      to, len, csum);
	skb->csum = csum_block_add(skb->csum, csum, odd);
271 272
	if (!(msg->type & ICMPV6_INFOMSG_MASK))
		nf_ct_attach(skb, org_skb);
L
Linus Torvalds 已提交
273 274 275 276 277 278 279 280 281 282 283
	return 0;
}

/*
 *	Send an ICMP message in response to a packet in error
 */
void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, 
		 struct net_device *dev)
{
	struct inet6_dev *idev = NULL;
	struct ipv6hdr *hdr = skb->nh.ipv6h;
284 285
	struct sock *sk;
	struct ipv6_pinfo *np;
L
Linus Torvalds 已提交
286 287 288 289 290 291 292 293
	struct in6_addr *saddr = NULL;
	struct dst_entry *dst;
	struct icmp6hdr tmp_hdr;
	struct flowi fl;
	struct icmpv6_msg msg;
	int iif = 0;
	int addr_type = 0;
	int len;
294
	int hlimit, tclass;
L
Linus Torvalds 已提交
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
	int err = 0;

	if ((u8*)hdr < skb->head || (u8*)(hdr+1) > skb->tail)
		return;

	/*
	 *	Make sure we respect the rules 
	 *	i.e. RFC 1885 2.4(e)
	 *	Rule (e.1) is enforced by not using icmpv6_send
	 *	in any code that processes icmp errors.
	 */
	addr_type = ipv6_addr_type(&hdr->daddr);

	if (ipv6_chk_addr(&hdr->daddr, skb->dev, 0))
		saddr = &hdr->daddr;

	/*
	 *	Dest addr check
	 */

	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
		if (type != ICMPV6_PKT_TOOBIG &&
		    !(type == ICMPV6_PARAMPROB && 
		      code == ICMPV6_UNK_OPTION && 
		      (opt_unrec(skb, info))))
			return;

		saddr = NULL;
	}

	addr_type = ipv6_addr_type(&hdr->saddr);

	/*
	 *	Source addr check
	 */

	if (addr_type & IPV6_ADDR_LINKLOCAL)
		iif = skb->dev->ifindex;

	/*
335 336 337 338
	 *	Must not send error if the source does not uniquely
	 *	identify a single node (RFC2463 Section 2.4).
	 *	We check unspecified / multicast addresses here,
	 *	and anycast addresses will be checked later.
L
Linus Torvalds 已提交
339 340
	 */
	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
341
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n");
L
Linus Torvalds 已提交
342 343 344 345 346 347 348
		return;
	}

	/* 
	 *	Never answer to a ICMP packet.
	 */
	if (is_ineligible(skb)) {
349
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n");
L
Linus Torvalds 已提交
350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
		return;
	}

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_ICMPV6;
	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
	if (saddr)
		ipv6_addr_copy(&fl.fl6_src, saddr);
	fl.oif = iif;
	fl.fl_icmp_type = type;
	fl.fl_icmp_code = code;

	if (icmpv6_xmit_lock())
		return;

365 366 367
	sk = icmpv6_socket->sk;
	np = inet6_sk(sk);

L
Linus Torvalds 已提交
368 369 370 371 372 373 374 375 376 377 378 379 380 381
	if (!icmpv6_xrlim_allow(sk, type, &fl))
		goto out;

	tmp_hdr.icmp6_type = type;
	tmp_hdr.icmp6_code = code;
	tmp_hdr.icmp6_cksum = 0;
	tmp_hdr.icmp6_pointer = htonl(info);

	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
		fl.oif = np->mcast_oif;

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;
382 383 384 385 386 387 388 389 390 391

	/*
	 * We won't send icmp if the destination is known
	 * anycast.
	 */
	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n");
		goto out_dst_release;
	}

L
Linus Torvalds 已提交
392
	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
393
		goto out;
L
Linus Torvalds 已提交
394 395 396 397 398 399 400 401 402 403

	if (ipv6_addr_is_multicast(&fl.fl6_dst))
		hlimit = np->mcast_hops;
	else
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
	if (hlimit < 0)
		hlimit = ipv6_get_hoplimit(dst->dev);

404 405 406 407
	tclass = np->cork.tclass;
	if (tclass < 0)
		tclass = 0;

L
Linus Torvalds 已提交
408 409
	msg.skb = skb;
	msg.offset = skb->nh.raw - skb->data;
410
	msg.type = type;
L
Linus Torvalds 已提交
411 412 413 414

	len = skb->len - msg.offset;
	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
	if (len < 0) {
415
		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
L
Linus Torvalds 已提交
416 417 418 419 420 421 422 423
		goto out_dst_release;
	}

	idev = in6_dev_get(skb->dev);

	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
			      len + sizeof(struct icmp6hdr),
			      sizeof(struct icmp6hdr),
424
			      hlimit, tclass, NULL, &fl, (struct rt6_info*)dst,
L
Linus Torvalds 已提交
425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446
			      MSG_DONTWAIT);
	if (err) {
		ip6_flush_pending_frames(sk);
		goto out_put;
	}
	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, len + sizeof(struct icmp6hdr));

	if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB)
		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_OUTDESTUNREACHS, type - ICMPV6_DEST_UNREACH);
	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS);

out_put:
	if (likely(idev != NULL))
		in6_dev_put(idev);
out_dst_release:
	dst_release(dst);
out:
	icmpv6_xmit_unlock();
}

static void icmpv6_echo_reply(struct sk_buff *skb)
{
447
	struct sock *sk;
L
Linus Torvalds 已提交
448
	struct inet6_dev *idev;
449
	struct ipv6_pinfo *np;
L
Linus Torvalds 已提交
450 451 452 453 454 455 456 457
	struct in6_addr *saddr = NULL;
	struct icmp6hdr *icmph = (struct icmp6hdr *) skb->h.raw;
	struct icmp6hdr tmp_hdr;
	struct flowi fl;
	struct icmpv6_msg msg;
	struct dst_entry *dst;
	int err = 0;
	int hlimit;
458
	int tclass;
L
Linus Torvalds 已提交
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478

	saddr = &skb->nh.ipv6h->daddr;

	if (!ipv6_unicast_destination(skb))
		saddr = NULL;

	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_ICMPV6;
	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
	if (saddr)
		ipv6_addr_copy(&fl.fl6_src, saddr);
	fl.oif = skb->dev->ifindex;
	fl.fl_icmp_type = ICMPV6_ECHO_REPLY;

	if (icmpv6_xmit_lock())
		return;

479 480 481
	sk = icmpv6_socket->sk;
	np = inet6_sk(sk);

L
Linus Torvalds 已提交
482 483 484 485 486 487 488
	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
		fl.oif = np->mcast_oif;

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;
	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
489
		goto out;
L
Linus Torvalds 已提交
490 491 492 493 494 495 496 497 498 499

	if (ipv6_addr_is_multicast(&fl.fl6_dst))
		hlimit = np->mcast_hops;
	else
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
	if (hlimit < 0)
		hlimit = ipv6_get_hoplimit(dst->dev);

500 501 502 503
	tclass = np->cork.tclass;
	if (tclass < 0)
		tclass = 0;

L
Linus Torvalds 已提交
504 505 506 507
	idev = in6_dev_get(skb->dev);

	msg.skb = skb;
	msg.offset = 0;
508
	msg.type = ICMPV6_ECHO_REPLY;
L
Linus Torvalds 已提交
509 510

	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
511
				sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl,
L
Linus Torvalds 已提交
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
				(struct rt6_info*)dst, MSG_DONTWAIT);

	if (err) {
		ip6_flush_pending_frames(sk);
		goto out_put;
	}
	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, skb->len + sizeof(struct icmp6hdr));

        ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTECHOREPLIES);
        ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS);

out_put: 
	if (likely(idev != NULL))
		in6_dev_put(idev);
	dst_release(dst);
out: 
	icmpv6_xmit_unlock();
}

static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
{
	struct in6_addr *saddr, *daddr;
	struct inet6_protocol *ipprot;
	struct sock *sk;
	int inner_offset;
	int hash;
	u8 nexthdr;

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		return;

	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
	if (ipv6_ext_hdr(nexthdr)) {
		/* now skip over extension headers */
546
		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
L
Linus Torvalds 已提交
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
		if (inner_offset<0)
			return;
	} else {
		inner_offset = sizeof(struct ipv6hdr);
	}

	/* Checkin header including 8 bytes of inner protocol header. */
	if (!pskb_may_pull(skb, inner_offset+8))
		return;

	saddr = &skb->nh.ipv6h->saddr;
	daddr = &skb->nh.ipv6h->daddr;

	/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
	   Without this we will not able f.e. to make source routed
	   pmtu discovery.
	   Corresponding argument (opt) to notifiers is already added.
	   --ANK (980726)
	 */

	hash = nexthdr & (MAX_INET_PROTOS - 1);

	rcu_read_lock();
	ipprot = rcu_dereference(inet6_protos[hash]);
	if (ipprot && ipprot->err_handler)
		ipprot->err_handler(skb, NULL, type, code, inner_offset, info);
	rcu_read_unlock();

	read_lock(&raw_v6_lock);
	if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) {
577
		while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr,
578
					    IP6CB(skb)->iif))) {
L
Linus Torvalds 已提交
579 580 581 582 583 584 585 586 587 588 589
			rawv6_err(sk, skb, NULL, type, code, inner_offset, info);
			sk = sk_next(sk);
		}
	}
	read_unlock(&raw_v6_lock);
}
  
/*
 *	Handle icmp messages
 */

590
static int icmpv6_rcv(struct sk_buff **pskb)
L
Linus Torvalds 已提交
591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
{
	struct sk_buff *skb = *pskb;
	struct net_device *dev = skb->dev;
	struct inet6_dev *idev = __in6_dev_get(dev);
	struct in6_addr *saddr, *daddr;
	struct ipv6hdr *orig_hdr;
	struct icmp6hdr *hdr;
	int type;

	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INMSGS);

	saddr = &skb->nh.ipv6h->saddr;
	daddr = &skb->nh.ipv6h->daddr;

	/* Perform checksum. */
606 607 608 609 610 611 612 613 614 615
	switch (skb->ip_summed) {
	case CHECKSUM_HW:
		if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
				     skb->csum))
			break;
		/* fall through */
	case CHECKSUM_NONE:
		skb->csum = ~csum_ipv6_magic(saddr, daddr, skb->len,
					     IPPROTO_ICMPV6, 0);
		if (__skb_checksum_complete(skb)) {
J
Joe Perches 已提交
616
			LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [" NIP6_FMT " > " NIP6_FMT "]\n",
617
				       NIP6(*saddr), NIP6(*daddr));
L
Linus Torvalds 已提交
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
			goto discard_it;
		}
	}

	if (!pskb_pull(skb, sizeof(struct icmp6hdr)))
		goto discard_it;

	hdr = (struct icmp6hdr *) skb->h.raw;

	type = hdr->icmp6_type;

	if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB)
		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INDESTUNREACHS, type - ICMPV6_DEST_UNREACH);
	else if (type >= ICMPV6_ECHO_REQUEST && type <= NDISC_REDIRECT)
		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INECHOS, type - ICMPV6_ECHO_REQUEST);

	switch (type) {
	case ICMPV6_ECHO_REQUEST:
		icmpv6_echo_reply(skb);
		break;

	case ICMPV6_ECHO_REPLY:
		/* we couldn't care less */
		break;

	case ICMPV6_PKT_TOOBIG:
		/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
		   standard destination cache. Seems, only "advanced"
		   destination cache will allow to solve this problem
		   --ANK (980726)
		 */
		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
			goto discard_it;
		hdr = (struct icmp6hdr *) skb->h.raw;
		orig_hdr = (struct ipv6hdr *) (hdr + 1);
		rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
				   ntohl(hdr->icmp6_mtu));

		/*
		 *	Drop through to notify
		 */

	case ICMPV6_DEST_UNREACH:
	case ICMPV6_TIME_EXCEED:
	case ICMPV6_PARAMPROB:
		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
		break;

	case NDISC_ROUTER_SOLICITATION:
	case NDISC_ROUTER_ADVERTISEMENT:
	case NDISC_NEIGHBOUR_SOLICITATION:
	case NDISC_NEIGHBOUR_ADVERTISEMENT:
	case NDISC_REDIRECT:
		ndisc_rcv(skb);
		break;

	case ICMPV6_MGM_QUERY:
		igmp6_event_query(skb);
		break;

	case ICMPV6_MGM_REPORT:
		igmp6_event_report(skb);
		break;

	case ICMPV6_MGM_REDUCTION:
	case ICMPV6_NI_QUERY:
	case ICMPV6_NI_REPLY:
	case ICMPV6_MLD2_REPORT:
	case ICMPV6_DHAAD_REQUEST:
	case ICMPV6_DHAAD_REPLY:
	case ICMPV6_MOBILE_PREFIX_SOL:
	case ICMPV6_MOBILE_PREFIX_ADV:
		break;

	default:
693
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714

		/* informational */
		if (type & ICMPV6_INFOMSG_MASK)
			break;

		/* 
		 * error of unknown type. 
		 * must pass to upper level 
		 */

		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
	};
	kfree_skb(skb);
	return 0;

discard_it:
	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INERRORS);
	kfree_skb(skb);
	return 0;
}

715 716 717 718 719
/*
 * Special lock-class for __icmpv6_socket:
 */
static struct lock_class_key icmpv6_socket_sk_dst_lock_key;

L
Linus Torvalds 已提交
720 721 722 723 724
int __init icmpv6_init(struct net_proto_family *ops)
{
	struct sock *sk;
	int err, i, j;

725
	for_each_possible_cpu(i) {
L
Linus Torvalds 已提交
726 727 728 729 730 731 732 733 734 735 736 737
		err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6,
				       &per_cpu(__icmpv6_socket, i));
		if (err < 0) {
			printk(KERN_ERR
			       "Failed to initialize the ICMP6 control socket "
			       "(err %d).\n",
			       err);
			goto fail;
		}

		sk = per_cpu(__icmpv6_socket, i)->sk;
		sk->sk_allocation = GFP_ATOMIC;
738 739 740 741 742 743 744 745
		/*
		 * Split off their lock-class, because sk->sk_dst_lock
		 * gets used from softirqs, which is safe for
		 * __icmpv6_socket (because those never get directly used
		 * via userspace syscalls), but unsafe for normal sockets.
		 */
		lockdep_set_class(&sk->sk_dst_lock,
				  &icmpv6_socket_sk_dst_lock_key);
L
Linus Torvalds 已提交
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778

		/* Enough space for 2 64K ICMP packets, including
		 * sk_buff struct overhead.
		 */
		sk->sk_sndbuf =
			(2 * ((64 * 1024) + sizeof(struct sk_buff)));

		sk->sk_prot->unhash(sk);
	}


	if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) {
		printk(KERN_ERR "Failed to register ICMP6 protocol\n");
		err = -EAGAIN;
		goto fail;
	}

	return 0;

 fail:
	for (j = 0; j < i; j++) {
		if (!cpu_possible(j))
			continue;
		sock_release(per_cpu(__icmpv6_socket, j));
	}

	return err;
}

void icmpv6_cleanup(void)
{
	int i;

779
	for_each_possible_cpu(i) {
L
Linus Torvalds 已提交
780 781 782 783 784
		sock_release(per_cpu(__icmpv6_socket, i));
	}
	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}

785
static const struct icmp6_err {
L
Linus Torvalds 已提交
786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856
	int err;
	int fatal;
} tab_unreach[] = {
	{	/* NOROUTE */
		.err	= ENETUNREACH,
		.fatal	= 0,
	},
	{	/* ADM_PROHIBITED */
		.err	= EACCES,
		.fatal	= 1,
	},
	{	/* Was NOT_NEIGHBOUR, now reserved */
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* ADDR_UNREACH	*/
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* PORT_UNREACH	*/
		.err	= ECONNREFUSED,
		.fatal	= 1,
	},
};

int icmpv6_err_convert(int type, int code, int *err)
{
	int fatal = 0;

	*err = EPROTO;

	switch (type) {
	case ICMPV6_DEST_UNREACH:
		fatal = 1;
		if (code <= ICMPV6_PORT_UNREACH) {
			*err  = tab_unreach[code].err;
			fatal = tab_unreach[code].fatal;
		}
		break;

	case ICMPV6_PKT_TOOBIG:
		*err = EMSGSIZE;
		break;
		
	case ICMPV6_PARAMPROB:
		*err = EPROTO;
		fatal = 1;
		break;

	case ICMPV6_TIME_EXCEED:
		*err = EHOSTUNREACH;
		break;
	};

	return fatal;
}

#ifdef CONFIG_SYSCTL
ctl_table ipv6_icmp_table[] = {
	{
		.ctl_name	= NET_IPV6_ICMP_RATELIMIT,
		.procname	= "ratelimit",
		.data		= &sysctl_icmpv6_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec
	},
	{ .ctl_name = 0 },
};
#endif