input.c 30.9 KB
Newer Older
1
/* SCTP kernel implementation
L
Linus Torvalds 已提交
2 3 4 5 6 7 8
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001-2003 International Business Machines, Corp.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 *
9
 * This file is part of the SCTP kernel implementation
L
Linus Torvalds 已提交
10 11 12
 *
 * These functions handle all input from the IP layer into SCTP.
 *
13
 * This SCTP implementation is free software;
L
Linus Torvalds 已提交
14 15 16 17 18
 * 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, or (at your option)
 * any later version.
 *
19
 * This SCTP implementation is distributed in the hope that it
L
Linus Torvalds 已提交
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 48 49 50 51 52 53 54 55
 * will be useful, but WITHOUT ANY WARRANTY; without even the implied
 *                 ************************
 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with GNU CC; see the file COPYING.  If not, write to
 * the Free Software Foundation, 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <lksctp-developers@lists.sourceforge.net>
 *
 * Or submit a bug report through the following website:
 *    http://www.sf.net/projects/lksctp
 *
 * Written or modified by:
 *    La Monte H.P. Yarroll <piggy@acm.org>
 *    Karl Knutson <karl@athena.chicago.il.us>
 *    Xingang Guo <xingang.guo@intel.com>
 *    Jon Grimm <jgrimm@us.ibm.com>
 *    Hui Huang <hui.huang@nokia.com>
 *    Daisy Chang <daisyc@us.ibm.com>
 *    Sridhar Samudrala <sri@us.ibm.com>
 *    Ardelle Fan <ardelle.fan@intel.com>
 *
 * Any bugs reported given to us we will try to fix... any fixes shared will
 * be incorporated into the next SCTP release.
 */

#include <linux/types.h>
#include <linux/list.h> /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
#include <linux/time.h> /* For struct timeval */
56
#include <linux/slab.h>
L
Linus Torvalds 已提交
57 58 59 60 61 62 63
#include <net/ip.h>
#include <net/icmp.h>
#include <net/snmp.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
64
#include <net/sctp/checksum.h>
65
#include <net/net_namespace.h>
L
Linus Torvalds 已提交
66 67 68 69 70 71 72 73 74 75 76 77 78

/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
static struct sctp_association *__sctp_rcv_lookup(struct sk_buff *skb,
				      const union sctp_addr *laddr,
				      const union sctp_addr *paddr,
				      struct sctp_transport **transportp);
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *laddr);
static struct sctp_association *__sctp_lookup_association(
					const union sctp_addr *local,
					const union sctp_addr *peer,
					struct sctp_transport **pt);

Z
Zhu Yi 已提交
79
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
80

L
Linus Torvalds 已提交
81 82 83 84

/* Calculate the SCTP checksum of an SCTP packet.  */
static inline int sctp_rcv_checksum(struct sk_buff *skb)
{
85
	struct sctphdr *sh = sctp_hdr(skb);
86
	__le32 cmp = sh->checksum;
87
	struct sk_buff *list;
88 89
	__le32 val;
	__u32 tmp = sctp_start_cksum((__u8 *)sh, skb_headlen(skb));
L
Linus Torvalds 已提交
90

91
	skb_walk_frags(skb, list)
92 93
		tmp = sctp_update_cksum((__u8 *)list->data, skb_headlen(list),
					tmp);
L
Linus Torvalds 已提交
94

95
	val = sctp_end_cksum(tmp);
L
Linus Torvalds 已提交
96 97 98 99 100 101 102 103 104

	if (val != cmp) {
		/* CRC failure, dump it. */
		SCTP_INC_STATS_BH(SCTP_MIB_CHECKSUMERRORS);
		return -1;
	}
	return 0;
}

105 106 107
struct sctp_input_cb {
	union {
		struct inet_skb_parm	h4;
E
Eric Dumazet 已提交
108
#if IS_ENABLED(CONFIG_IPV6)
109 110 111 112 113 114 115
		struct inet6_skb_parm	h6;
#endif
	} header;
	struct sctp_chunk *chunk;
};
#define SCTP_INPUT_CB(__skb)	((struct sctp_input_cb *)&((__skb)->cb[0]))

L
Linus Torvalds 已提交
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
/*
 * This is the routine which IP calls when receiving an SCTP packet.
 */
int sctp_rcv(struct sk_buff *skb)
{
	struct sock *sk;
	struct sctp_association *asoc;
	struct sctp_endpoint *ep = NULL;
	struct sctp_ep_common *rcvr;
	struct sctp_transport *transport = NULL;
	struct sctp_chunk *chunk;
	struct sctphdr *sh;
	union sctp_addr src;
	union sctp_addr dest;
	int family;
	struct sctp_af *af;

	if (skb->pkt_type!=PACKET_HOST)
		goto discard_it;

	SCTP_INC_STATS_BH(SCTP_MIB_INSCTPPACKS);

138 139 140
	if (skb_linearize(skb))
		goto discard_it;

141
	sh = sctp_hdr(skb);
L
Linus Torvalds 已提交
142 143

	/* Pull up the IP and SCTP headers. */
144
	__skb_pull(skb, skb_transport_offset(skb));
L
Linus Torvalds 已提交
145 146
	if (skb->len < sizeof(struct sctphdr))
		goto discard_it;
147 148
	if (!sctp_checksum_disable && !skb_csum_unnecessary(skb) &&
		  sctp_rcv_checksum(skb) < 0)
L
Linus Torvalds 已提交
149 150 151 152 153 154 155 156
		goto discard_it;

	skb_pull(skb, sizeof(struct sctphdr));

	/* Make sure we at least have chunk headers worth of data left. */
	if (skb->len < sizeof(struct sctp_chunkhdr))
		goto discard_it;

157
	family = ipver2af(ip_hdr(skb)->version);
L
Linus Torvalds 已提交
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
	af = sctp_get_af_specific(family);
	if (unlikely(!af))
		goto discard_it;

	/* Initialize local addresses for lookups. */
	af->from_skb(&src, skb, 1);
	af->from_skb(&dest, skb, 0);

	/* If the packet is to or from a non-unicast address,
	 * silently discard the packet.
	 *
	 * This is not clearly defined in the RFC except in section
	 * 8.4 - OOTB handling.  However, based on the book "Stream Control
	 * Transmission Protocol" 2.1, "It is important to note that the
	 * IP address of an SCTP transport address must be a routable
	 * unicast address.  In other words, IP multicast addresses and
	 * IP broadcast addresses cannot be used in an SCTP transport
	 * address."
	 */
177 178
	if (!af->addr_valid(&src, NULL, skb) ||
	    !af->addr_valid(&dest, NULL, skb))
L
Linus Torvalds 已提交
179 180
		goto discard_it;

181
	asoc = __sctp_rcv_lookup(skb, &src, &dest, &transport);
182

183
	if (!asoc)
184
		ep = __sctp_rcv_lookup_endpoint(&dest);
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208

	/* Retrieve the common input handling substructure. */
	rcvr = asoc ? &asoc->base : &ep->base;
	sk = rcvr->sk;

	/*
	 * If a frame arrives on an interface and the receiving socket is
	 * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
	 */
	if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb)))
	{
		if (asoc) {
			sctp_association_put(asoc);
			asoc = NULL;
		} else {
			sctp_endpoint_put(ep);
			ep = NULL;
		}
		sk = sctp_get_ctl_sock();
		ep = sctp_sk(sk)->ep;
		sctp_endpoint_hold(ep);
		rcvr = &ep->base;
	}

L
Linus Torvalds 已提交
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225
	/*
	 * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
	 * An SCTP packet is called an "out of the blue" (OOTB)
	 * packet if it is correctly formed, i.e., passed the
	 * receiver's checksum check, but the receiver is not
	 * able to identify the association to which this
	 * packet belongs.
	 */
	if (!asoc) {
		if (sctp_rcv_ootb(skb)) {
			SCTP_INC_STATS_BH(SCTP_MIB_OUTOFBLUES);
			goto discard_release;
		}
	}

	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
		goto discard_release;
226
	nf_reset(skb);
L
Linus Torvalds 已提交
227

228
	if (sk_filter(sk, skb))
229
		goto discard_release;
L
Linus Torvalds 已提交
230 231 232

	/* Create an SCTP packet structure. */
	chunk = sctp_chunkify(skb, asoc, sk);
233
	if (!chunk)
L
Linus Torvalds 已提交
234
		goto discard_release;
235
	SCTP_INPUT_CB(skb)->chunk = chunk;
L
Linus Torvalds 已提交
236 237 238 239 240 241 242 243

	/* Remember what endpoint is to handle this packet. */
	chunk->rcvr = rcvr;

	/* Remember the SCTP header. */
	chunk->sctp_hdr = sh;

	/* Set the source and destination addresses of the incoming chunk.  */
244
	sctp_init_addrs(chunk, &src, &dest);
L
Linus Torvalds 已提交
245 246 247 248 249 250 251 252 253 254

	/* Remember where we came from.  */
	chunk->transport = transport;

	/* Acquire access to the sock lock. Note: We are safe from other
	 * bottom halves on this lock, but a user may be in the lock too,
	 * so check if it is busy.
	 */
	sctp_bh_lock_sock(sk);

255 256 257 258 259 260 261 262 263 264 265 266 267
	if (sk != rcvr->sk) {
		/* Our cached sk is different from the rcvr->sk.  This is
		 * because migrate()/accept() may have moved the association
		 * to a new socket and released all the sockets.  So now we
		 * are holding a lock on the old socket while the user may
		 * be doing something with the new socket.  Switch our veiw
		 * of the current sk.
		 */
		sctp_bh_unlock_sock(sk);
		sk = rcvr->sk;
		sctp_bh_lock_sock(sk);
	}

268
	if (sock_owned_by_user(sk)) {
Z
Zhu Yi 已提交
269 270 271 272 273 274
		if (sctp_add_backlog(sk, skb)) {
			sctp_bh_unlock_sock(sk);
			sctp_chunk_free(chunk);
			skb = NULL; /* sctp_chunk_free already freed the skb */
			goto discard_release;
		}
275 276 277
		SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_BACKLOG);
	} else {
		SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_SOFTIRQ);
278
		sctp_inq_push(&chunk->rcvr->inqueue, chunk);
279
	}
L
Linus Torvalds 已提交
280 281

	sctp_bh_unlock_sock(sk);
282 283 284 285 286 287

	/* Release the asoc/ep ref we took in the lookup calls. */
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);
288

289
	return 0;
L
Linus Torvalds 已提交
290 291

discard_it:
292
	SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_DISCARDS);
L
Linus Torvalds 已提交
293
	kfree_skb(skb);
294
	return 0;
L
Linus Torvalds 已提交
295 296

discard_release:
297
	/* Release the asoc/ep ref we took in the lookup calls. */
298
	if (asoc)
L
Linus Torvalds 已提交
299
		sctp_association_put(asoc);
300
	else
L
Linus Torvalds 已提交
301 302 303 304 305
		sctp_endpoint_put(ep);

	goto discard_it;
}

306 307 308 309
/* Process the backlog queue of the socket.  Every skb on
 * the backlog holds a ref on an association or endpoint.
 * We hold this ref throughout the state machine to make
 * sure that the structure we need is still around.
L
Linus Torvalds 已提交
310 311 312
 */
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
313
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
314 315
	struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
	struct sctp_ep_common *rcvr = NULL;
316
	int backloged = 0;
317

318
	rcvr = chunk->rcvr;
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
	/* If the rcvr is dead then the association or endpoint
	 * has been deleted and we can safely drop the chunk
	 * and refs that we are holding.
	 */
	if (rcvr->dead) {
		sctp_chunk_free(chunk);
		goto done;
	}

	if (unlikely(rcvr->sk != sk)) {
		/* In this case, the association moved from one socket to
		 * another.  We are currently sitting on the backlog of the
		 * old socket, so we need to move.
		 * However, since we are here in the process context we
		 * need to take make sure that the user doesn't own
		 * the new socket when we process the packet.
		 * If the new socket is user-owned, queue the chunk to the
		 * backlog of the new socket without dropping any refs.
		 * Otherwise, we can safely push the chunk on the inqueue.
		 */

		sk = rcvr->sk;
		sctp_bh_lock_sock(sk);

		if (sock_owned_by_user(sk)) {
345
			if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
Z
Zhu Yi 已提交
346 347 348
				sctp_chunk_free(chunk);
			else
				backloged = 1;
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
		} else
			sctp_inq_push(inqueue, chunk);

		sctp_bh_unlock_sock(sk);

		/* If the chunk was backloged again, don't drop refs */
		if (backloged)
			return 0;
	} else {
		sctp_inq_push(inqueue, chunk);
	}

done:
	/* Release the refs we took in sctp_add_backlog */
	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
		sctp_association_put(sctp_assoc(rcvr));
	else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
		sctp_endpoint_put(sctp_ep(rcvr));
	else
		BUG();

370
	return 0;
L
Linus Torvalds 已提交
371 372
}

Z
Zhu Yi 已提交
373
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
374
{
375 376
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
	struct sctp_ep_common *rcvr = chunk->rcvr;
Z
Zhu Yi 已提交
377
	int ret;
378

379
	ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf);
Z
Zhu Yi 已提交
380 381 382 383 384 385 386 387 388 389 390 391 392
	if (!ret) {
		/* Hold the assoc/ep while hanging on the backlog queue.
		 * This way, we know structures we need will not disappear
		 * from us
		 */
		if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
			sctp_association_hold(sctp_assoc(rcvr));
		else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
			sctp_endpoint_hold(sctp_ep(rcvr));
		else
			BUG();
	}
	return ret;
393

394 395
}

L
Linus Torvalds 已提交
396 397 398 399
/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
			   struct sctp_transport *t, __u32 pmtu)
{
400
	if (!t || (t->pathmtu <= pmtu))
401 402
		return;

403 404 405 406 407 408
	if (sock_owned_by_user(sk)) {
		asoc->pmtu_pending = 1;
		t->pmtu_pending = 1;
		return;
	}

409
	if (t->param_flags & SPP_PMTUD_ENABLE) {
410 411
		/* Update transports view of the MTU */
		sctp_transport_update_pmtu(t, pmtu);
L
Linus Torvalds 已提交
412

413
		/* Update association pmtu. */
L
Linus Torvalds 已提交
414 415
		sctp_assoc_sync_pmtu(asoc);
	}
416 417 418 419 420

	/* Retransmit with the new pmtu setting.
	 * Normally, if PMTU discovery is disabled, an ICMP Fragmentation
	 * Needed will never be sent, but if a message was sent before
	 * PMTU discovery was disabled that was larger than the PMTU, it
421
	 * would not be fragmented, so it must be re-transmitted fragmented.
422 423
	 */
	sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
L
Linus Torvalds 已提交
424 425
}

426 427
void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
			struct sk_buff *skb)
428 429 430 431 432 433
{
	struct dst_entry *dst;

	if (!t)
		return;
	dst = sctp_transport_dst_check(t);
434
	if (dst)
435 436 437
		dst->ops->redirect(dst, skb);
}

L
Linus Torvalds 已提交
438 439 440 441 442 443 444 445 446 447 448 449
/*
 * SCTP Implementer's Guide, 2.37 ICMP handling procedures
 *
 * ICMP8) If the ICMP code is a "Unrecognized next header type encountered"
 *        or a "Protocol Unreachable" treat this message as an abort
 *        with the T bit set.
 *
 * This function sends an event to the state machine, which will abort the
 * association.
 *
 */
void sctp_icmp_proto_unreachable(struct sock *sk,
450 451
			   struct sctp_association *asoc,
			   struct sctp_transport *t)
L
Linus Torvalds 已提交
452
{
453
	SCTP_DEBUG_PRINTK("%s\n",  __func__);
L
Linus Torvalds 已提交
454

455 456 457 458 459 460 461 462 463 464 465 466 467
	if (sock_owned_by_user(sk)) {
		if (timer_pending(&t->proto_unreach_timer))
			return;
		else {
			if (!mod_timer(&t->proto_unreach_timer,
						jiffies + (HZ/20)))
				sctp_association_hold(asoc);
		}
			
	} else {
		if (timer_pending(&t->proto_unreach_timer) &&
		    del_timer(&t->proto_unreach_timer))
			sctp_association_put(asoc);
L
Linus Torvalds 已提交
468

469 470 471 472 473
		sctp_do_sm(SCTP_EVENT_T_OTHER,
			   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
			   asoc->state, asoc->ep, asoc, t,
			   GFP_ATOMIC);
	}
L
Linus Torvalds 已提交
474 475 476 477 478 479 480 481 482 483 484 485
}

/* Common lookup code for icmp/icmpv6 error handler. */
struct sock *sctp_err_lookup(int family, struct sk_buff *skb,
			     struct sctphdr *sctphdr,
			     struct sctp_association **app,
			     struct sctp_transport **tpp)
{
	union sctp_addr saddr;
	union sctp_addr daddr;
	struct sctp_af *af;
	struct sock *sk = NULL;
486
	struct sctp_association *asoc;
L
Linus Torvalds 已提交
487
	struct sctp_transport *transport = NULL;
488 489 490
	struct sctp_init_chunk *chunkhdr;
	__u32 vtag = ntohl(sctphdr->vtag);
	int len = skb->len - ((void *)sctphdr - (void *)skb->data);
L
Linus Torvalds 已提交
491

492
	*app = NULL; *tpp = NULL;
L
Linus Torvalds 已提交
493 494 495 496 497 498 499 500 501 502 503 504 505

	af = sctp_get_af_specific(family);
	if (unlikely(!af)) {
		return NULL;
	}

	/* Initialize local addresses for lookups. */
	af->from_skb(&saddr, skb, 1);
	af->from_skb(&daddr, skb, 0);

	/* Look for an association that matches the incoming ICMP error
	 * packet.
	 */
506
	asoc = __sctp_lookup_association(&saddr, &daddr, &transport);
507 508
	if (!asoc)
		return NULL;
L
Linus Torvalds 已提交
509

510
	sk = asoc->base.sk;
L
Linus Torvalds 已提交
511

512 513 514 515 516 517 518 519 520 521 522 523 524
	/* RFC 4960, Appendix C. ICMP Handling
	 *
	 * ICMP6) An implementation MUST validate that the Verification Tag
	 * contained in the ICMP message matches the Verification Tag of
	 * the peer.  If the Verification Tag is not 0 and does NOT
	 * match, discard the ICMP message.  If it is 0 and the ICMP
	 * message contains enough bytes to verify that the chunk type is
	 * an INIT chunk and that the Initiate Tag matches the tag of the
	 * peer, continue with ICMP7.  If the ICMP message is too short
	 * or the chunk type or the Initiate Tag does not match, silently
	 * discard the packet.
	 */
	if (vtag == 0) {
J
Joe Perches 已提交
525
		chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
526 527 528 529 530 531 532
		if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t)
			  + sizeof(__be32) ||
		    chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) {
			goto out;
		}
	} else if (vtag != asoc->c.peer_vtag) {
533 534
		goto out;
	}
L
Linus Torvalds 已提交
535 536 537 538 539 540 541

	sctp_bh_lock_sock(sk);

	/* If too many ICMPs get dropped on busy
	 * servers this needs to be solved differently.
	 */
	if (sock_owned_by_user(sk))
542
		NET_INC_STATS_BH(&init_net, LINUX_MIB_LOCKDROPPEDICMPS);
L
Linus Torvalds 已提交
543 544 545 546 547 548 549 550 551 552 553 554

	*app = asoc;
	*tpp = transport;
	return sk;

out:
	if (asoc)
		sctp_association_put(asoc);
	return NULL;
}

/* Common cleanup code for icmp/icmpv6 error handler. */
555
void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
L
Linus Torvalds 已提交
556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
{
	sctp_bh_unlock_sock(sk);
	if (asoc)
		sctp_association_put(asoc);
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  After adjustment
 * header points to the first 8 bytes of the sctp header.  We need
 * to find the appropriate port.
 *
 * The locking strategy used here is very "optimistic". When
 * someone else accesses the socket the ICMP is just dropped
 * and for some paths there is no check at all.
 * A more general error queue to queue errors for later handling
 * is probably better.
 *
 */
void sctp_v4_err(struct sk_buff *skb, __u32 info)
{
579
	const struct iphdr *iph = (const struct iphdr *)skb->data;
580
	const int ihlen = iph->ihl * 4;
581 582
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
L
Linus Torvalds 已提交
583
	struct sock *sk;
584
	struct sctp_association *asoc = NULL;
L
Linus Torvalds 已提交
585 586
	struct sctp_transport *transport;
	struct inet_sock *inet;
587
	sk_buff_data_t saveip, savesctp;
L
Linus Torvalds 已提交
588 589
	int err;

590
	if (skb->len < ihlen + 8) {
591
		ICMP_INC_STATS_BH(&init_net, ICMP_MIB_INERRORS);
L
Linus Torvalds 已提交
592 593 594 595
		return;
	}

	/* Fix up skb to look at the embedded net header. */
596 597
	saveip = skb->network_header;
	savesctp = skb->transport_header;
598
	skb_reset_network_header(skb);
599 600
	skb_set_transport_header(skb, ihlen);
	sk = sctp_err_lookup(AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
601
	/* Put back, the original values. */
602 603
	skb->network_header = saveip;
	skb->transport_header = savesctp;
L
Linus Torvalds 已提交
604
	if (!sk) {
605
		ICMP_INC_STATS_BH(&init_net, ICMP_MIB_INERRORS);
L
Linus Torvalds 已提交
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
		return;
	}
	/* Warning:  The sock lock is held.  Remember to call
	 * sctp_err_finish!
	 */

	switch (type) {
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out_unlock;

		/* PMTU discovery (RFC1191) */
		if (ICMP_FRAG_NEEDED == code) {
			sctp_icmp_frag_needed(sk, asoc, transport, info);
			goto out_unlock;
		}
		else {
			if (ICMP_PROT_UNREACH == code) {
627
				sctp_icmp_proto_unreachable(sk, asoc,
L
Linus Torvalds 已提交
628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
							    transport);
				goto out_unlock;
			}
		}
		err = icmp_err_convert[code].errno;
		break;
	case ICMP_TIME_EXCEEDED:
		/* Ignore any time exceeded errors due to fragment reassembly
		 * timeouts.
		 */
		if (ICMP_EXC_FRAGTIME == code)
			goto out_unlock;

		err = EHOSTUNREACH;
		break;
643 644 645 646
	case ICMP_REDIRECT:
		sctp_icmp_redirect(sk, transport, skb);
		err = 0;
		break;
L
Linus Torvalds 已提交
647 648 649 650 651 652 653 654 655 656 657 658 659
	default:
		goto out_unlock;
	}

	inet = inet_sk(sk);
	if (!sock_owned_by_user(sk) && inet->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else {  /* Only an error on timeout */
		sk->sk_err_soft = err;
	}

out_unlock:
660
	sctp_err_finish(sk, asoc);
L
Linus Torvalds 已提交
661 662 663 664 665 666 667 668 669 670 671 672 673 674
}

/*
 * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
 *
 * This function scans all the chunks in the OOTB packet to determine if
 * the packet should be discarded right away.  If a response might be needed
 * for this packet, or, if further processing is possible, the packet will
 * be queued to a proper inqueue for the next phase of handling.
 *
 * Output:
 * Return 0 - If further processing is needed.
 * Return 1 - If the packet can be discarded right away.
 */
675
static int sctp_rcv_ootb(struct sk_buff *skb)
L
Linus Torvalds 已提交
676 677 678 679 680 681 682
{
	sctp_chunkhdr_t *ch;
	__u8 *ch_end;

	ch = (sctp_chunkhdr_t *) skb->data;

	/* Scan through all the chunks in the packet.  */
683 684 685 686 687 688
	do {
		/* Break out if chunk length is less then minimal. */
		if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t))
			break;

		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
689
		if (ch_end > skb_tail_pointer(skb))
690
			break;
L
Linus Torvalds 已提交
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705

		/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the
		 * receiver MUST silently discard the OOTB packet and take no
		 * further action.
		 */
		if (SCTP_CID_ABORT == ch->type)
			goto discard;

		/* RFC 8.4, 6) If the packet contains a SHUTDOWN COMPLETE
		 * chunk, the receiver should silently discard the packet
		 * and take no further action.
		 */
		if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type)
			goto discard;

706 707 708 709 710 711 712 713
		/* RFC 4460, 2.11.2
		 * This will discard packets with INIT chunk bundled as
		 * subsequent chunks in the packet.  When INIT is first,
		 * the normal INIT processing will discard the chunk.
		 */
		if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data)
			goto discard;

L
Linus Torvalds 已提交
714
		ch = (sctp_chunkhdr_t *) ch_end;
715
	} while (ch_end < skb_tail_pointer(skb));
L
Linus Torvalds 已提交
716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734

	return 0;

discard:
	return 1;
}

/* Insert endpoint into the hash table.  */
static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
{
	struct sctp_ep_common *epb;
	struct sctp_hashbucket *head;

	epb = &ep->base;

	epb->hashent = sctp_ep_hashfn(epb->bind_addr.port);
	head = &sctp_ep_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
735
	hlist_add_head(&epb->node, &head->chain);
L
Linus Torvalds 已提交
736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
	sctp_write_unlock(&head->lock);
}

/* Add an endpoint to the hash. Local BH-safe. */
void sctp_hash_endpoint(struct sctp_endpoint *ep)
{
	sctp_local_bh_disable();
	__sctp_hash_endpoint(ep);
	sctp_local_bh_enable();
}

/* Remove endpoint from the hash table.  */
static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;

	epb = &ep->base;

755 756 757
	if (hlist_unhashed(&epb->node))
		return;

L
Linus Torvalds 已提交
758 759 760 761 762
	epb->hashent = sctp_ep_hashfn(epb->bind_addr.port);

	head = &sctp_ep_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
763
	__hlist_del(&epb->node);
L
Linus Torvalds 已提交
764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
	sctp_write_unlock(&head->lock);
}

/* Remove endpoint from the hash.  Local BH-safe. */
void sctp_unhash_endpoint(struct sctp_endpoint *ep)
{
	sctp_local_bh_disable();
	__sctp_unhash_endpoint(ep);
	sctp_local_bh_enable();
}

/* Look up an endpoint. */
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *laddr)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;
	struct sctp_endpoint *ep;
781
	struct hlist_node *node;
L
Linus Torvalds 已提交
782 783
	int hash;

784
	hash = sctp_ep_hashfn(ntohs(laddr->v4.sin_port));
L
Linus Torvalds 已提交
785 786
	head = &sctp_ep_hashtable[hash];
	read_lock(&head->lock);
787
	sctp_for_each_hentry(epb, node, &head->chain) {
L
Linus Torvalds 已提交
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
		ep = sctp_ep(epb);
		if (sctp_endpoint_is_match(ep, laddr))
			goto hit;
	}

	ep = sctp_sk((sctp_get_ctl_sock()))->ep;

hit:
	sctp_endpoint_hold(ep);
	read_unlock(&head->lock);
	return ep;
}

/* Insert association into the hash table.  */
static void __sctp_hash_established(struct sctp_association *asoc)
{
	struct sctp_ep_common *epb;
	struct sctp_hashbucket *head;

	epb = &asoc->base;

	/* Calculate which chain this entry will belong to. */
	epb->hashent = sctp_assoc_hashfn(epb->bind_addr.port, asoc->peer.port);

	head = &sctp_assoc_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
815
	hlist_add_head(&epb->node, &head->chain);
L
Linus Torvalds 已提交
816 817 818 819 820 821
	sctp_write_unlock(&head->lock);
}

/* Add an association to the hash. Local BH-safe. */
void sctp_hash_established(struct sctp_association *asoc)
{
822 823 824
	if (asoc->temp)
		return;

L
Linus Torvalds 已提交
825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843
	sctp_local_bh_disable();
	__sctp_hash_established(asoc);
	sctp_local_bh_enable();
}

/* Remove association from the hash table.  */
static void __sctp_unhash_established(struct sctp_association *asoc)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;

	epb = &asoc->base;

	epb->hashent = sctp_assoc_hashfn(epb->bind_addr.port,
					 asoc->peer.port);

	head = &sctp_assoc_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
844
	__hlist_del(&epb->node);
L
Linus Torvalds 已提交
845 846 847 848 849 850
	sctp_write_unlock(&head->lock);
}

/* Remove association from the hash table.  Local BH-safe. */
void sctp_unhash_established(struct sctp_association *asoc)
{
851 852 853
	if (asoc->temp)
		return;

L
Linus Torvalds 已提交
854 855 856 857 858 859 860 861 862 863 864 865 866 867 868
	sctp_local_bh_disable();
	__sctp_unhash_established(asoc);
	sctp_local_bh_enable();
}

/* Look up an association. */
static struct sctp_association *__sctp_lookup_association(
					const union sctp_addr *local,
					const union sctp_addr *peer,
					struct sctp_transport **pt)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;
	struct sctp_association *asoc;
	struct sctp_transport *transport;
869
	struct hlist_node *node;
L
Linus Torvalds 已提交
870 871 872 873 874
	int hash;

	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
875
	hash = sctp_assoc_hashfn(ntohs(local->v4.sin_port), ntohs(peer->v4.sin_port));
L
Linus Torvalds 已提交
876 877
	head = &sctp_assoc_hashtable[hash];
	read_lock(&head->lock);
878
	sctp_for_each_hentry(epb, node, &head->chain) {
L
Linus Torvalds 已提交
879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917
		asoc = sctp_assoc(epb);
		transport = sctp_assoc_is_match(asoc, local, peer);
		if (transport)
			goto hit;
	}

	read_unlock(&head->lock);

	return NULL;

hit:
	*pt = transport;
	sctp_association_hold(asoc);
	read_unlock(&head->lock);
	return asoc;
}

/* Look up an association. BH-safe. */
SCTP_STATIC
struct sctp_association *sctp_lookup_association(const union sctp_addr *laddr,
						 const union sctp_addr *paddr,
					    struct sctp_transport **transportp)
{
	struct sctp_association *asoc;

	sctp_local_bh_disable();
	asoc = __sctp_lookup_association(laddr, paddr, transportp);
	sctp_local_bh_enable();

	return asoc;
}

/* Is there an association matching the given local and peer addresses? */
int sctp_has_association(const union sctp_addr *laddr,
			 const union sctp_addr *paddr)
{
	struct sctp_association *asoc;
	struct sctp_transport *transport;

918
	if ((asoc = sctp_lookup_association(laddr, paddr, &transport))) {
L
Linus Torvalds 已提交
919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949
		sctp_association_put(asoc);
		return 1;
	}

	return 0;
}

/*
 * SCTP Implementors Guide, 2.18 Handling of address
 * parameters within the INIT or INIT-ACK.
 *
 * D) When searching for a matching TCB upon reception of an INIT
 *    or INIT-ACK chunk the receiver SHOULD use not only the
 *    source address of the packet (containing the INIT or
 *    INIT-ACK) but the receiver SHOULD also use all valid
 *    address parameters contained within the chunk.
 *
 * 2.18.3 Solution description
 *
 * This new text clearly specifies to an implementor the need
 * to look within the INIT or INIT-ACK. Any implementation that
 * does not do this, may not be able to establish associations
 * in certain circumstances.
 *
 */
static struct sctp_association *__sctp_rcv_init_lookup(struct sk_buff *skb,
	const union sctp_addr *laddr, struct sctp_transport **transportp)
{
	struct sctp_association *asoc;
	union sctp_addr addr;
	union sctp_addr *paddr = &addr;
950
	struct sctphdr *sh = sctp_hdr(skb);
L
Linus Torvalds 已提交
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981
	union sctp_params params;
	sctp_init_chunk_t *init;
	struct sctp_transport *transport;
	struct sctp_af *af;

	/*
	 * This code will NOT touch anything inside the chunk--it is
	 * strictly READ-ONLY.
	 *
	 * RFC 2960 3  SCTP packet Format
	 *
	 * Multiple chunks can be bundled into one SCTP packet up to
	 * the MTU size, except for the INIT, INIT ACK, and SHUTDOWN
	 * COMPLETE chunks.  These chunks MUST NOT be bundled with any
	 * other chunk in a packet.  See Section 6.10 for more details
	 * on chunk bundling.
	 */

	/* Find the start of the TLVs and the end of the chunk.  This is
	 * the region we search for address parameters.
	 */
	init = (sctp_init_chunk_t *)skb->data;

	/* Walk the parameters looking for embedded addresses. */
	sctp_walk_params(params, init, init_hdr.params) {

		/* Note: Ignoring hostname addresses. */
		af = sctp_get_af_specific(param_type2af(params.p->type));
		if (!af)
			continue;

982
		af->from_addr_param(paddr, params.addr, sh->source, 0);
L
Linus Torvalds 已提交
983

984
		asoc = __sctp_lookup_association(laddr, paddr, &transport);
L
Linus Torvalds 已提交
985 986 987 988 989 990 991
		if (asoc)
			return asoc;
	}

	return NULL;
}

992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008
/* ADD-IP, Section 5.2
 * When an endpoint receives an ASCONF Chunk from the remote peer
 * special procedures may be needed to identify the association the
 * ASCONF Chunk is associated with. To properly find the association
 * the following procedures SHOULD be followed:
 *
 * D2) If the association is not found, use the address found in the
 * Address Parameter TLV combined with the port number found in the
 * SCTP common header. If found proceed to rule D4.
 *
 * D2-ext) If more than one ASCONF Chunks are packed together, use the
 * address found in the ASCONF Address Parameter TLV of each of the
 * subsequent ASCONF Chunks. If found, proceed to rule D4.
 */
static struct sctp_association *__sctp_rcv_asconf_lookup(
					sctp_chunkhdr_t *ch,
					const union sctp_addr *laddr,
1009
					__be16 peer_port,
1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
					struct sctp_transport **transportp)
{
	sctp_addip_chunk_t *asconf = (struct sctp_addip_chunk *)ch;
	struct sctp_af *af;
	union sctp_addr_param *param;
	union sctp_addr paddr;

	/* Skip over the ADDIP header and find the Address parameter */
	param = (union sctp_addr_param *)(asconf + 1);

1020
	af = sctp_get_af_specific(param_type2af(param->p.type));
1021 1022 1023 1024 1025 1026 1027 1028 1029
	if (unlikely(!af))
		return NULL;

	af->from_addr_param(&paddr, param, peer_port, 0);

	return __sctp_lookup_association(laddr, &paddr, transportp);
}


1030 1031 1032 1033 1034 1035 1036
/* SCTP-AUTH, Section 6.3:
*    If the receiver does not find a STCB for a packet containing an AUTH
*    chunk as the first chunk and not a COOKIE-ECHO chunk as the second
*    chunk, it MUST use the chunks after the AUTH chunk to look up an existing
*    association.
*
* This means that any chunks that can help us identify the association need
L
Lucas De Marchi 已提交
1037
* to be looked at to find this association.
1038
*/
1039
static struct sctp_association *__sctp_rcv_walk_lookup(struct sk_buff *skb,
1040 1041 1042
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
1043 1044 1045 1046 1047 1048 1049 1050
	struct sctp_association *asoc = NULL;
	sctp_chunkhdr_t *ch;
	int have_auth = 0;
	unsigned int chunk_num = 1;
	__u8 *ch_end;

	/* Walk through the chunks looking for AUTH or ASCONF chunks
	 * to help us find the association.
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
	ch = (sctp_chunkhdr_t *) skb->data;
	do {
		/* Break out if chunk length is less then minimal. */
		if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t))
			break;

		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
		if (ch_end > skb_tail_pointer(skb))
			break;

		switch(ch->type) {
		    case SCTP_CID_AUTH:
			    have_auth = chunk_num;
			    break;

		    case SCTP_CID_COOKIE_ECHO:
			    /* If a packet arrives containing an AUTH chunk as
			     * a first chunk, a COOKIE-ECHO chunk as the second
			     * chunk, and possibly more chunks after them, and
			     * the receiver does not have an STCB for that
			     * packet, then authentication is based on
			     * the contents of the COOKIE- ECHO chunk.
			     */
			    if (have_auth == 1 && chunk_num == 2)
				    return NULL;
			    break;

		    case SCTP_CID_ASCONF:
			    if (have_auth || sctp_addip_noauth)
				    asoc = __sctp_rcv_asconf_lookup(ch, laddr,
							sctp_hdr(skb)->source,
							transportp);
		    default:
			    break;
		}

		if (asoc)
			break;

		ch = (sctp_chunkhdr_t *) ch_end;
		chunk_num++;
	} while (ch_end < skb_tail_pointer(skb));

	return asoc;
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111
}

/*
 * There are circumstances when we need to look inside the SCTP packet
 * for information to help us find the association.   Examples
 * include looking inside of INIT/INIT-ACK chunks or after the AUTH
 * chunks.
 */
static struct sctp_association *__sctp_rcv_lookup_harder(struct sk_buff *skb,
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
	sctp_chunkhdr_t *ch;

	ch = (sctp_chunkhdr_t *) skb->data;

1112 1113 1114 1115 1116 1117 1118 1119
	/* The code below will attempt to walk the chunk and extract
	 * parameter information.  Before we do that, we need to verify
	 * that the chunk length doesn't cause overflow.  Otherwise, we'll
	 * walk off the end.
	 */
	if (WORD_ROUND(ntohs(ch->length)) > skb->len)
		return NULL;

1120 1121 1122 1123 1124 1125 1126
	/* If this is INIT/INIT-ACK look inside the chunk too. */
	switch (ch->type) {
	case SCTP_CID_INIT:
	case SCTP_CID_INIT_ACK:
		return __sctp_rcv_init_lookup(skb, laddr, transportp);
		break;

1127 1128
	default:
		return __sctp_rcv_walk_lookup(skb, laddr, transportp);
1129 1130 1131
		break;
	}

1132

1133 1134 1135
	return NULL;
}

L
Linus Torvalds 已提交
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
/* Lookup an association for an inbound skb. */
static struct sctp_association *__sctp_rcv_lookup(struct sk_buff *skb,
				      const union sctp_addr *paddr,
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
	struct sctp_association *asoc;

	asoc = __sctp_lookup_association(laddr, paddr, transportp);

	/* Further lookup for INIT/INIT-ACK packets.
	 * SCTP Implementors Guide, 2.18 Handling of address
	 * parameters within the INIT or INIT-ACK.
	 */
	if (!asoc)
1151
		asoc = __sctp_rcv_lookup_harder(skb, laddr, transportp);
L
Linus Torvalds 已提交
1152 1153 1154

	return asoc;
}