input.c 31.3 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
 * 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):
32
 *    lksctp developers <linux-sctp@vger.kernel.org>
L
Linus Torvalds 已提交
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55
 *
 * 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

/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
69 70
static struct sctp_association *__sctp_rcv_lookup(struct net *net,
				      struct sk_buff *skb,
L
Linus Torvalds 已提交
71
				      const union sctp_addr *paddr,
72
				      const union sctp_addr *laddr,
L
Linus Torvalds 已提交
73
				      struct sctp_transport **transportp);
74 75
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
						const union sctp_addr *laddr);
L
Linus Torvalds 已提交
76
static struct sctp_association *__sctp_lookup_association(
77
					struct net *net,
L
Linus Torvalds 已提交
78 79 80 81
					const union sctp_addr *local,
					const union sctp_addr *peer,
					struct sctp_transport **pt);

Z
Zhu Yi 已提交
82
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
83

L
Linus Torvalds 已提交
84 85

/* Calculate the SCTP checksum of an SCTP packet.  */
86
static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb)
L
Linus Torvalds 已提交
87
{
88
	struct sctphdr *sh = sctp_hdr(skb);
89
	__le32 cmp = sh->checksum;
90
	__le32 val = sctp_compute_cksum(skb, 0);
L
Linus Torvalds 已提交
91 92 93

	if (val != cmp) {
		/* CRC failure, dump it. */
94
		SCTP_INC_STATS_BH(net, SCTP_MIB_CHECKSUMERRORS);
L
Linus Torvalds 已提交
95 96 97 98 99
		return -1;
	}
	return 0;
}

100 101 102
struct sctp_input_cb {
	union {
		struct inet_skb_parm	h4;
E
Eric Dumazet 已提交
103
#if IS_ENABLED(CONFIG_IPV6)
104 105 106 107 108 109 110
		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
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
/*
 * 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;
127
	struct net *net = dev_net(skb->dev);
L
Linus Torvalds 已提交
128 129 130 131

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

132
	SCTP_INC_STATS_BH(net, SCTP_MIB_INSCTPPACKS);
L
Linus Torvalds 已提交
133

134 135 136
	if (skb_linearize(skb))
		goto discard_it;

137
	sh = sctp_hdr(skb);
L
Linus Torvalds 已提交
138 139

	/* Pull up the IP and SCTP headers. */
140
	__skb_pull(skb, skb_transport_offset(skb));
L
Linus Torvalds 已提交
141 142
	if (skb->len < sizeof(struct sctphdr))
		goto discard_it;
143 144
	if (!net->sctp.checksum_disable && !skb_csum_unnecessary(skb) &&
	    sctp_rcv_checksum(net, skb) < 0)
L
Linus Torvalds 已提交
145 146 147 148 149 150 151 152
		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;

153
	family = ipver2af(ip_hdr(skb)->version);
L
Linus Torvalds 已提交
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
	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."
	 */
173 174
	if (!af->addr_valid(&src, NULL, skb) ||
	    !af->addr_valid(&dest, NULL, skb))
L
Linus Torvalds 已提交
175 176
		goto discard_it;

177
	asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport);
178

179
	if (!asoc)
180
		ep = __sctp_rcv_lookup_endpoint(net, &dest);
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198

	/* 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;
		}
199
		sk = net->sctp.ctl_sock;
200 201 202 203 204
		ep = sctp_sk(sk)->ep;
		sctp_endpoint_hold(ep);
		rcvr = &ep->base;
	}

L
Linus Torvalds 已提交
205 206 207 208 209 210 211 212 213 214
	/*
	 * 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)) {
215
			SCTP_INC_STATS_BH(net, SCTP_MIB_OUTOFBLUES);
L
Linus Torvalds 已提交
216 217 218 219 220 221
			goto discard_release;
		}
	}

	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
		goto discard_release;
222
	nf_reset(skb);
L
Linus Torvalds 已提交
223

224
	if (sk_filter(sk, skb))
225
		goto discard_release;
L
Linus Torvalds 已提交
226 227 228

	/* Create an SCTP packet structure. */
	chunk = sctp_chunkify(skb, asoc, sk);
229
	if (!chunk)
L
Linus Torvalds 已提交
230
		goto discard_release;
231
	SCTP_INPUT_CB(skb)->chunk = chunk;
L
Linus Torvalds 已提交
232 233 234 235 236 237 238 239

	/* 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.  */
240
	sctp_init_addrs(chunk, &src, &dest);
L
Linus Torvalds 已提交
241 242 243 244 245 246 247 248 249 250

	/* 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);

251 252 253 254 255 256 257 258 259 260 261 262 263
	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);
	}

264
	if (sock_owned_by_user(sk)) {
Z
Zhu Yi 已提交
265 266 267 268 269 270
		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;
		}
271
		SCTP_INC_STATS_BH(net, SCTP_MIB_IN_PKT_BACKLOG);
272
	} else {
273
		SCTP_INC_STATS_BH(net, SCTP_MIB_IN_PKT_SOFTIRQ);
274
		sctp_inq_push(&chunk->rcvr->inqueue, chunk);
275
	}
L
Linus Torvalds 已提交
276 277

	sctp_bh_unlock_sock(sk);
278 279 280 281 282 283

	/* Release the asoc/ep ref we took in the lookup calls. */
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);
284

285
	return 0;
L
Linus Torvalds 已提交
286 287

discard_it:
288
	SCTP_INC_STATS_BH(net, SCTP_MIB_IN_PKT_DISCARDS);
L
Linus Torvalds 已提交
289
	kfree_skb(skb);
290
	return 0;
L
Linus Torvalds 已提交
291 292

discard_release:
293
	/* Release the asoc/ep ref we took in the lookup calls. */
294
	if (asoc)
L
Linus Torvalds 已提交
295
		sctp_association_put(asoc);
296
	else
L
Linus Torvalds 已提交
297 298 299 300 301
		sctp_endpoint_put(ep);

	goto discard_it;
}

302 303 304 305
/* 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
306 307 308
 */
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
309
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
310 311
	struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
	struct sctp_ep_common *rcvr = NULL;
312
	int backloged = 0;
313

314
	rcvr = chunk->rcvr;
315

316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
	/* 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)) {
341
			if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
Z
Zhu Yi 已提交
342 343 344
				sctp_chunk_free(chunk);
			else
				backloged = 1;
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
		} 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();

366
	return 0;
L
Linus Torvalds 已提交
367 368
}

Z
Zhu Yi 已提交
369
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
370
{
371 372
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
	struct sctp_ep_common *rcvr = chunk->rcvr;
Z
Zhu Yi 已提交
373
	int ret;
374

375
	ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf);
Z
Zhu Yi 已提交
376 377 378 379 380 381 382 383 384 385 386 387 388
	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;
389

390 391
}

L
Linus Torvalds 已提交
392 393 394 395
/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
			   struct sctp_transport *t, __u32 pmtu)
{
396
	if (!t || (t->pathmtu <= pmtu))
397 398
		return;

399 400 401 402 403 404
	if (sock_owned_by_user(sk)) {
		asoc->pmtu_pending = 1;
		t->pmtu_pending = 1;
		return;
	}

405
	if (t->param_flags & SPP_PMTUD_ENABLE) {
406
		/* Update transports view of the MTU */
407
		sctp_transport_update_pmtu(sk, t, pmtu);
L
Linus Torvalds 已提交
408

409
		/* Update association pmtu. */
410
		sctp_assoc_sync_pmtu(sk, asoc);
L
Linus Torvalds 已提交
411
	}
412 413 414 415 416

	/* 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
417
	 * would not be fragmented, so it must be re-transmitted fragmented.
418 419
	 */
	sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
L
Linus Torvalds 已提交
420 421
}

422 423
void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
			struct sk_buff *skb)
424 425 426 427 428 429
{
	struct dst_entry *dst;

	if (!t)
		return;
	dst = sctp_transport_dst_check(t);
430
	if (dst)
431
		dst->ops->redirect(dst, sk, skb);
432 433
}

L
Linus Torvalds 已提交
434 435 436 437 438 439 440 441 442 443 444 445
/*
 * 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,
446 447
			   struct sctp_association *asoc,
			   struct sctp_transport *t)
L
Linus Torvalds 已提交
448
{
449 450 451 452 453 454 455 456 457
	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 {
458 459
		struct net *net = sock_net(sk);

460 461 462
		pr_debug("%s: unrecognized next header type "
			 "encountered!\n", __func__);

463
		if (del_timer(&t->proto_unreach_timer))
464
			sctp_association_put(asoc);
L
Linus Torvalds 已提交
465

466
		sctp_do_sm(net, SCTP_EVENT_T_OTHER,
467 468 469 470
			   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
			   asoc->state, asoc->ep, asoc, t,
			   GFP_ATOMIC);
	}
L
Linus Torvalds 已提交
471 472 473
}

/* Common lookup code for icmp/icmpv6 error handler. */
474
struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
L
Linus Torvalds 已提交
475 476 477 478 479 480 481 482
			     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;
483
	struct sctp_association *asoc;
L
Linus Torvalds 已提交
484
	struct sctp_transport *transport = NULL;
485 486 487
	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
488

489
	*app = NULL; *tpp = NULL;
L
Linus Torvalds 已提交
490 491 492 493 494 495 496 497 498 499 500 501 502

	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.
	 */
503
	asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport);
504 505
	if (!asoc)
		return NULL;
L
Linus Torvalds 已提交
506

507
	sk = asoc->base.sk;
L
Linus Torvalds 已提交
508

509 510 511 512 513 514 515 516 517 518 519 520 521
	/* 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
522
		chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
523 524 525 526 527 528 529
		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) {
530 531
		goto out;
	}
L
Linus Torvalds 已提交
532 533 534 535 536 537 538

	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))
539
		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
L
Linus Torvalds 已提交
540 541 542 543 544 545 546 547 548 549 550 551

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

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

/* Common cleanup code for icmp/icmpv6 error handler. */
552
void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
L
Linus Torvalds 已提交
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575
{
	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)
{
576
	const struct iphdr *iph = (const struct iphdr *)skb->data;
577
	const int ihlen = iph->ihl * 4;
578 579
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
L
Linus Torvalds 已提交
580
	struct sock *sk;
581
	struct sctp_association *asoc = NULL;
L
Linus Torvalds 已提交
582 583
	struct sctp_transport *transport;
	struct inet_sock *inet;
584
	__u16 saveip, savesctp;
L
Linus Torvalds 已提交
585
	int err;
586
	struct net *net = dev_net(skb->dev);
L
Linus Torvalds 已提交
587

588
	if (skb->len < ihlen + 8) {
589
		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
L
Linus Torvalds 已提交
590 591 592 593
		return;
	}

	/* Fix up skb to look at the embedded net header. */
594 595
	saveip = skb->network_header;
	savesctp = skb->transport_header;
596
	skb_reset_network_header(skb);
597
	skb_set_transport_header(skb, ihlen);
598
	sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
599
	/* Put back, the original values. */
600 601
	skb->network_header = saveip;
	skb->transport_header = savesctp;
L
Linus Torvalds 已提交
602
	if (!sk) {
603
		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
L
Linus Torvalds 已提交
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
		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) {
625
				sctp_icmp_proto_unreachable(sk, asoc,
L
Linus Torvalds 已提交
626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
							    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;
641 642 643 644
	case ICMP_REDIRECT:
		sctp_icmp_redirect(sk, transport, skb);
		err = 0;
		break;
L
Linus Torvalds 已提交
645 646 647 648 649 650 651 652 653 654 655 656 657
	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:
658
	sctp_err_finish(sk, asoc);
L
Linus Torvalds 已提交
659 660 661 662 663 664 665 666 667 668 669 670 671 672
}

/*
 * 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.
 */
673
static int sctp_rcv_ootb(struct sk_buff *skb)
L
Linus Torvalds 已提交
674 675 676 677 678 679 680
{
	sctp_chunkhdr_t *ch;
	__u8 *ch_end;

	ch = (sctp_chunkhdr_t *) skb->data;

	/* Scan through all the chunks in the packet.  */
681 682 683 684 685 686
	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));
687
		if (ch_end > skb_tail_pointer(skb))
688
			break;
L
Linus Torvalds 已提交
689 690 691 692 693 694 695 696 697 698 699 700 701 702 703

		/* 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;

704 705 706 707 708 709 710 711
		/* 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
712
		ch = (sctp_chunkhdr_t *) ch_end;
713
	} while (ch_end < skb_tail_pointer(skb));
L
Linus Torvalds 已提交
714 715 716 717 718 719 720 721 722 723

	return 0;

discard:
	return 1;
}

/* Insert endpoint into the hash table.  */
static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
{
724
	struct net *net = sock_net(ep->base.sk);
L
Linus Torvalds 已提交
725 726 727 728 729
	struct sctp_ep_common *epb;
	struct sctp_hashbucket *head;

	epb = &ep->base;

730
	epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
L
Linus Torvalds 已提交
731 732 733
	head = &sctp_ep_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
734
	hlist_add_head(&epb->node, &head->chain);
L
Linus Torvalds 已提交
735 736 737 738 739 740 741 742 743 744 745 746 747 748
	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)
{
749
	struct net *net = sock_net(ep->base.sk);
L
Linus Torvalds 已提交
750 751 752 753 754
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;

	epb = &ep->base;

755
	epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
L
Linus Torvalds 已提交
756 757 758 759

	head = &sctp_ep_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
760
	hlist_del_init(&epb->node);
L
Linus Torvalds 已提交
761 762 763 764 765 766 767 768 769 770 771 772
	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. */
773 774
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
						const union sctp_addr *laddr)
L
Linus Torvalds 已提交
775 776 777 778 779 780
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;
	struct sctp_endpoint *ep;
	int hash;

781
	hash = sctp_ep_hashfn(net, ntohs(laddr->v4.sin_port));
L
Linus Torvalds 已提交
782 783
	head = &sctp_ep_hashtable[hash];
	read_lock(&head->lock);
784
	sctp_for_each_hentry(epb, &head->chain) {
L
Linus Torvalds 已提交
785
		ep = sctp_ep(epb);
786
		if (sctp_endpoint_is_match(ep, net, laddr))
L
Linus Torvalds 已提交
787 788 789
			goto hit;
	}

790
	ep = sctp_sk(net->sctp.ctl_sock)->ep;
L
Linus Torvalds 已提交
791 792 793 794 795 796 797 798 799 800

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)
{
801
	struct net *net = sock_net(asoc->base.sk);
L
Linus Torvalds 已提交
802 803 804 805 806 807
	struct sctp_ep_common *epb;
	struct sctp_hashbucket *head;

	epb = &asoc->base;

	/* Calculate which chain this entry will belong to. */
808 809
	epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port,
					 asoc->peer.port);
L
Linus Torvalds 已提交
810 811 812 813

	head = &sctp_assoc_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
814
	hlist_add_head(&epb->node, &head->chain);
L
Linus Torvalds 已提交
815 816 817 818 819 820
	sctp_write_unlock(&head->lock);
}

/* Add an association to the hash. Local BH-safe. */
void sctp_hash_established(struct sctp_association *asoc)
{
821 822 823
	if (asoc->temp)
		return;

L
Linus Torvalds 已提交
824 825 826 827 828 829 830 831
	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)
{
832
	struct net *net = sock_net(asoc->base.sk);
L
Linus Torvalds 已提交
833 834 835 836 837
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;

	epb = &asoc->base;

838
	epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port,
L
Linus Torvalds 已提交
839 840 841 842 843
					 asoc->peer.port);

	head = &sctp_assoc_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);
844
	hlist_del_init(&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
	sctp_local_bh_disable();
	__sctp_unhash_established(asoc);
	sctp_local_bh_enable();
}

/* Look up an association. */
static struct sctp_association *__sctp_lookup_association(
861
					struct net *net,
L
Linus Torvalds 已提交
862 863 864 865 866 867 868 869 870 871 872 873 874
					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;
	int hash;

	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
875 876
	hash = sctp_assoc_hashfn(net, ntohs(local->v4.sin_port),
				 ntohs(peer->v4.sin_port));
L
Linus Torvalds 已提交
877 878
	head = &sctp_assoc_hashtable[hash];
	read_lock(&head->lock);
879
	sctp_for_each_hentry(epb, &head->chain) {
L
Linus Torvalds 已提交
880
		asoc = sctp_assoc(epb);
881
		transport = sctp_assoc_is_match(asoc, net, local, peer);
L
Linus Torvalds 已提交
882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
		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. */
898
static
899 900
struct sctp_association *sctp_lookup_association(struct net *net,
						 const union sctp_addr *laddr,
L
Linus Torvalds 已提交
901
						 const union sctp_addr *paddr,
902
						 struct sctp_transport **transportp)
L
Linus Torvalds 已提交
903 904 905 906
{
	struct sctp_association *asoc;

	sctp_local_bh_disable();
907
	asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
L
Linus Torvalds 已提交
908 909 910 911 912 913
	sctp_local_bh_enable();

	return asoc;
}

/* Is there an association matching the given local and peer addresses? */
914 915
int sctp_has_association(struct net *net,
			 const union sctp_addr *laddr,
L
Linus Torvalds 已提交
916 917 918 919 920
			 const union sctp_addr *paddr)
{
	struct sctp_association *asoc;
	struct sctp_transport *transport;

921
	if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) {
L
Linus Torvalds 已提交
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
		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.
 *
 */
947 948
static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
	struct sk_buff *skb,
L
Linus Torvalds 已提交
949 950 951 952 953
	const union sctp_addr *laddr, struct sctp_transport **transportp)
{
	struct sctp_association *asoc;
	union sctp_addr addr;
	union sctp_addr *paddr = &addr;
954
	struct sctphdr *sh = sctp_hdr(skb);
L
Linus Torvalds 已提交
955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985
	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;

986
		af->from_addr_param(paddr, params.addr, sh->source, 0);
L
Linus Torvalds 已提交
987

988
		asoc = __sctp_lookup_association(net, laddr, paddr, &transport);
L
Linus Torvalds 已提交
989 990 991 992 993 994 995
		if (asoc)
			return asoc;
	}

	return NULL;
}

996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010
/* 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(
1011
					struct net *net,
1012 1013
					sctp_chunkhdr_t *ch,
					const union sctp_addr *laddr,
1014
					__be16 peer_port,
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024
					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);

1025
	af = sctp_get_af_specific(param_type2af(param->p.type));
1026 1027 1028 1029 1030
	if (unlikely(!af))
		return NULL;

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

1031
	return __sctp_lookup_association(net, laddr, &paddr, transportp);
1032 1033 1034
}


1035 1036 1037 1038 1039 1040 1041
/* 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
1042
* to be looked at to find this association.
1043
*/
1044 1045
static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net,
				      struct sk_buff *skb,
1046 1047 1048
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
1049 1050 1051 1052 1053 1054 1055 1056
	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.
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
	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:
1086
			    if (have_auth || net->sctp.addip_noauth)
1087 1088
				    asoc = __sctp_rcv_asconf_lookup(
							net, ch, laddr,
1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102
							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;
1103 1104 1105 1106 1107 1108 1109 1110
}

/*
 * 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.
 */
1111 1112
static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net,
				      struct sk_buff *skb,
1113 1114 1115 1116 1117 1118 1119
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
	sctp_chunkhdr_t *ch;

	ch = (sctp_chunkhdr_t *) skb->data;

1120 1121 1122 1123 1124 1125 1126 1127
	/* 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;

1128 1129 1130 1131
	/* If this is INIT/INIT-ACK look inside the chunk too. */
	switch (ch->type) {
	case SCTP_CID_INIT:
	case SCTP_CID_INIT_ACK:
1132
		return __sctp_rcv_init_lookup(net, skb, laddr, transportp);
1133 1134
		break;

1135
	default:
1136
		return __sctp_rcv_walk_lookup(net, skb, laddr, transportp);
1137 1138 1139
		break;
	}

1140

1141 1142 1143
	return NULL;
}

L
Linus Torvalds 已提交
1144
/* Lookup an association for an inbound skb. */
1145 1146
static struct sctp_association *__sctp_rcv_lookup(struct net *net,
				      struct sk_buff *skb,
L
Linus Torvalds 已提交
1147 1148 1149 1150 1151 1152
				      const union sctp_addr *paddr,
				      const union sctp_addr *laddr,
				      struct sctp_transport **transportp)
{
	struct sctp_association *asoc;

1153
	asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
L
Linus Torvalds 已提交
1154 1155 1156 1157 1158 1159

	/* Further lookup for INIT/INIT-ACK packets.
	 * SCTP Implementors Guide, 2.18 Handling of address
	 * parameters within the INIT or INIT-ACK.
	 */
	if (!asoc)
1160
		asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp);
L
Linus Torvalds 已提交
1161 1162 1163

	return asoc;
}