aboutsummaryrefslogtreecommitdiffstats
path: root/net/sctp/input.c
blob: 28f32243397f3b1b9755f42fcc70fa824d92dea0 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
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
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
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
779
780
781
782
783
784
785
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
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
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
/* SCTP kernel reference Implementation
 * 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
 *
 * This file is part of the SCTP kernel reference Implementation
 *
 * These functions handle all input from the IP layer into SCTP.
 *
 * The SCTP reference implementation 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, or (at your option)
 * any later version.
 *
 * The SCTP reference implementation is distributed in the hope that it
 * 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 */
#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>

/* 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);


/* Calculate the SCTP checksum of an SCTP packet.  */
static inline int sctp_rcv_checksum(struct sk_buff *skb)
{
	struct sctphdr *sh;
	__u32 cmp, val;
	struct sk_buff *list = skb_shinfo(skb)->frag_list;

	sh = (struct sctphdr *) skb->h.raw;
	cmp = ntohl(sh->checksum);

	val = sctp_start_cksum((__u8 *)sh, skb_headlen(skb));

	for (; list; list = list->next)
		val = sctp_update_cksum((__u8 *)list->data, skb_headlen(list),
					val);

	val = sctp_end_cksum(val);

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

/* The free routine for skbuffs that sctp receives */
static void sctp_rfree(struct sk_buff *skb)
{
	atomic_sub(sizeof(struct sctp_chunk),&skb->sk->sk_rmem_alloc);
	sock_rfree(skb);
}

/* The ownership wrapper routine to do receive buffer accounting */
static void sctp_rcv_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_set_owner_r(skb,sk);
	skb->destructor = sctp_rfree;
	atomic_add(sizeof(struct sctp_chunk),&sk->sk_rmem_alloc);
}

struct sctp_input_cb {
	union {
		struct inet_skb_parm	h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		struct inet6_skb_parm	h6;
#endif
	} header;
	struct sctp_chunk *chunk;
};
#define SCTP_INPUT_CB(__skb)	((struct sctp_input_cb *)&((__skb)->cb[0]))

/*
 * 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;
	int ret = 0;

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

	SCTP_INC_STATS_BH(SCTP_MIB_INSCTPPACKS);

	sh = (struct sctphdr *) skb->h.raw;

	/* Pull up the IP and SCTP headers. */
	__skb_pull(skb, skb->h.raw - skb->data);
	if (skb->len < sizeof(struct sctphdr))
		goto discard_it;
	if (sctp_rcv_checksum(skb) < 0)
		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;

	family = ipver2af(skb->nh.iph->version);
	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."
	 */
	if (!af->addr_valid(&src, NULL) || !af->addr_valid(&dest, NULL))
		goto discard_it;

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

	if (!asoc)
		ep = __sctp_rcv_lookup_endpoint(&dest);

	/* 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)))
	{
		sock_put(sk);
		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);
		sock_hold(sk);
		rcvr = &ep->base;
	}

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		goto discard_release;

	/*
	 * 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;
		}
	}

	/* SCTP seems to always need a timestamp right now (FIXME) */
	if (skb->tstamp.off_sec == 0) {
		__net_timestamp(skb);
		sock_enable_timestamp(sk); 
	}

	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
		goto discard_release;

	ret = sk_filter(sk, skb, 1);
	if (ret)
                goto discard_release;

	/* Create an SCTP packet structure. */
	chunk = sctp_chunkify(skb, asoc, sk);
	if (!chunk) {
		ret = -ENOMEM;
		goto discard_release;
	}
	SCTP_INPUT_CB(skb)->chunk = chunk;

	sctp_rcv_set_owner_r(skb,sk);

	/* 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.  */
	sctp_init_addrs(chunk, &src, &dest);

	/* 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);

	if (sock_owned_by_user(sk))
		sk_add_backlog(sk, skb);
	else
		sctp_backlog_rcv(sk, skb);

	/* Release the sock and any reference counts we took in the
	 * lookup calls.
	 */
	sctp_bh_unlock_sock(sk);
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);
	sock_put(sk);
	return ret;

discard_it:
	kfree_skb(skb);
	return ret;

discard_release:
	/* Release any structures we may be holding. */
	sock_put(sk);
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);

	goto discard_it;
}

/* Handle second half of inbound skb processing.  If the sock was busy,
 * we may have need to delay processing until later when the sock is
 * released (on the backlog).   If not busy, we call this routine
 * directly from the bottom half.
 */
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
	struct sctp_inq *inqueue = &chunk->rcvr->inqueue;

	sctp_inq_push(inqueue, chunk);
        return 0;
}

/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
			   struct sctp_transport *t, __u32 pmtu)
{
	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
		printk(KERN_WARNING "%s: Reported pmtu %d too low, "
		       "using default minimum of %d\n", __FUNCTION__, pmtu,
		       SCTP_DEFAULT_MINSEGMENT);
		pmtu = SCTP_DEFAULT_MINSEGMENT;
	}

	if (!sock_owned_by_user(sk) && t && (t->pmtu != pmtu)) {
		t->pmtu = pmtu;
		sctp_assoc_sync_pmtu(asoc);
		sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
	}
}

/*
 * 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,
                           struct sctp_association *asoc,
                           struct sctp_transport *t)
{
	SCTP_DEBUG_PRINTK("%s\n",  __FUNCTION__);

	sctp_do_sm(SCTP_EVENT_T_OTHER,
		   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
		   asoc->state, asoc->ep, asoc, t,
		   GFP_ATOMIC);

}

/* 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;
	struct sctp_association *asoc = NULL;
	struct sctp_transport *transport = NULL;

	*app = NULL; *tpp = NULL;

	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.
	 */
	asoc = __sctp_lookup_association(&saddr, &daddr, &transport);
	if (!asoc)
		return NULL;

	sk = asoc->base.sk;

	if (ntohl(sctphdr->vtag) != asoc->c.peer_vtag) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		goto out;
	}

	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))
		NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);

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

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

/* Common cleanup code for icmp/icmpv6 error handler. */
void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
{
	sctp_bh_unlock_sock(sk);
	sock_put(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)
{
	struct iphdr *iph = (struct iphdr *)skb->data;
	struct sctphdr *sh = (struct sctphdr *)(skb->data + (iph->ihl <<2));
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	struct sock *sk;
	struct sctp_association *asoc;
	struct sctp_transport *transport;
	struct inet_sock *inet;
	char *saveip, *savesctp;
	int err;

	if (skb->len < ((iph->ihl << 2) + 8)) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}

	/* Fix up skb to look at the embedded net header. */
	saveip = skb->nh.raw;
	savesctp  = skb->h.raw;
	skb->nh.iph = iph;
	skb->h.raw = (char *)sh;
	sk = sctp_err_lookup(AF_INET, skb, sh, &asoc, &transport);
	/* Put back, the original pointers. */
	skb->nh.raw = saveip;
	skb->h.raw = savesctp;
	if (!sk) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		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) {
				sctp_icmp_proto_unreachable(sk, asoc,
							    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;
	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:
	sctp_err_finish(sk, asoc);
}

/*
 * 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.
 */
int sctp_rcv_ootb(struct sk_buff *skb)
{
	sctp_chunkhdr_t *ch;
	__u8 *ch_end;
	sctp_errhdr_t *err;

	ch = (sctp_chunkhdr_t *) skb->data;
	ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length));

	/* Scan through all the chunks in the packet.  */
	while (ch_end > (__u8 *)ch && ch_end < skb->tail) {

		/* 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;

		/* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR
		 * or a COOKIE ACK the SCTP Packet should be silently
		 * discarded.
		 */
		if (SCTP_CID_COOKIE_ACK == ch->type)
			goto discard;

		if (SCTP_CID_ERROR == ch->type) {
			sctp_walk_errors(err, ch) {
				if (SCTP_ERROR_STALE_COOKIE == err->cause)
					goto discard;
			}
		}

		ch = (sctp_chunkhdr_t *) ch_end;
	        ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length));
	}

	return 0;

discard:
	return 1;
}

/* Insert endpoint into the hash table.  */
static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
{
	struct sctp_ep_common **epp;
	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);
	epp = &head->chain;
	epb->next = *epp;
	if (epb->next)
		(*epp)->pprev = &epb->next;
	*epp = epb;
	epb->pprev = epp;
	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;

	epb->hashent = sctp_ep_hashfn(epb->bind_addr.port);

	head = &sctp_ep_hashtable[epb->hashent];

	sctp_write_lock(&head->lock);

	if (epb->pprev) {
		if (epb->next)
			epb->next->pprev = epb->pprev;
		*epb->pprev = epb->next;
		epb->pprev = NULL;
	}

	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;
	int hash;

	hash = sctp_ep_hashfn(laddr->v4.sin_port);
	head = &sctp_ep_hashtable[hash];
	read_lock(&head->lock);
	for (epb = head->chain; epb; epb = epb->next) {
		ep = sctp_ep(epb);
		if (sctp_endpoint_is_match(ep, laddr))
			goto hit;
	}

	ep = sctp_sk((sctp_get_ctl_sock()))->ep;
	epb = &ep->base;

hit:
	sctp_endpoint_hold(ep);
	sock_hold(epb->sk);
	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 **epp;
	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);
	epp = &head->chain;
	epb->next = *epp;
	if (epb->next)
		(*epp)->pprev = &epb->next;
	*epp = epb;
	epb->pprev = epp;
	sctp_write_unlock(&head->lock);
}

/* Add an association to the hash. Local BH-safe. */
void sctp_hash_established(struct sctp_association *asoc)
{
	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);

	if (epb->pprev) {
		if (epb->next)
			epb->next->pprev = epb->pprev;
		*epb->pprev = epb->next;
		epb->pprev = NULL;
	}

	sctp_write_unlock(&head->lock);
}

/* Remove association from the hash table.  Local BH-safe. */
void sctp_unhash_established(struct sctp_association *asoc)
{
	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;
	int hash;

	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
	hash = sctp_assoc_hashfn(local->v4.sin_port, peer->v4.sin_port);
	head = &sctp_assoc_hashtable[hash];
	read_lock(&head->lock);
	for (epb = head->chain; epb; epb = epb->next) {
		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);
	sock_hold(epb->sk);
	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;

	if ((asoc = sctp_lookup_association(laddr, paddr, &transport))) {
		sock_put(asoc->base.sk);
		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;
	struct sctphdr *sh = (struct sctphdr *) skb->h.raw;
	sctp_chunkhdr_t *ch;
	union sctp_params params;
	sctp_init_chunk_t *init;
	struct sctp_transport *transport;
	struct sctp_af *af;

	ch = (sctp_chunkhdr_t *) skb->data;

	/* If this is INIT/INIT-ACK look inside the chunk too. */
	switch (ch->type) {
	case SCTP_CID_INIT:
	case SCTP_CID_INIT_ACK:
		break;
	default:
		return NULL;
	}

	/* 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;

	/*
	 * 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;

		af->from_addr_param(paddr, params.addr, ntohs(sh->source), 0);

		asoc = __sctp_lookup_association(laddr, paddr, &transport);
		if (asoc)
			return asoc;
	}

	return NULL;
}

/* 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)
		asoc = __sctp_rcv_init_lookup(skb, laddr, transportp);

	return asoc;
}