ipv4.c 33.6 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
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
/*
 *  net/dccp/ipv4.c
 *
 *  An implementation of the DCCP protocol
 *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 */

#include <linux/config.h>
#include <linux/dccp.h>
#include <linux/icmp.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/random.h>

#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/xfrm.h>

#include "ccid.h"
#include "dccp.h"

struct inet_hashinfo __cacheline_aligned dccp_hashinfo = {
	.lhash_lock	= RW_LOCK_UNLOCKED,
	.lhash_users	= ATOMIC_INIT(0),
	.lhash_wait	= __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait),
	.portalloc_lock	= SPIN_LOCK_UNLOCKED,
	.port_rover	= 1024 - 1,
};

static int dccp_v4_get_port(struct sock *sk, const unsigned short snum)
{
	return inet_csk_get_port(&dccp_hashinfo, sk, snum);
}

static void dccp_v4_hash(struct sock *sk)
{
	inet_hash(&dccp_hashinfo, sk);
}

static void dccp_v4_unhash(struct sock *sk)
{
	inet_unhash(&dccp_hashinfo, sk);
}

/* called with local bh disabled */
static int __dccp_v4_check_established(struct sock *sk, const __u16 lport,
				      struct inet_timewait_sock **twp)
{
	struct inet_sock *inet = inet_sk(sk);
	const u32 daddr = inet->rcv_saddr;
	const u32 saddr = inet->daddr;
	const int dif = sk->sk_bound_dev_if;
	INET_ADDR_COOKIE(acookie, saddr, daddr)
	const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport);
	const int hash = inet_ehashfn(daddr, lport, saddr, inet->dport, dccp_hashinfo.ehash_size);
	struct inet_ehash_bucket *head = &dccp_hashinfo.ehash[hash];
	const struct sock *sk2;
	const struct hlist_node *node;
	struct inet_timewait_sock *tw;

	write_lock(&head->lock);

	/* Check TIME-WAIT sockets first. */
	sk_for_each(sk2, node, &(head + dccp_hashinfo.ehash_size)->chain) {
		tw = inet_twsk(sk2);

		if (INET_TW_MATCH(sk2, acookie, saddr, daddr, ports, dif))
			goto not_unique;
	}
	tw = NULL;

	/* And established part... */
	sk_for_each(sk2, node, &head->chain) {
		if (INET_MATCH(sk2, acookie, saddr, daddr, ports, dif))
			goto not_unique;
	}

	/* Must record num and sport now. Otherwise we will see
	 * in hash table socket with a funny identity. */
	inet->num = lport;
	inet->sport = htons(lport);
	sk->sk_hashent = hash;
	BUG_TRAP(sk_unhashed(sk));
	__sk_add_node(sk, &head->chain);
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(&head->lock);

	if (twp != NULL) {
		*twp = tw;
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
	} else if (tw != NULL) {
		/* Silly. Should hash-dance instead... */
		dccp_tw_deschedule(tw);
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);

		inet_twsk_put(tw);
	}

	return 0;

not_unique:
	write_unlock(&head->lock);
	return -EADDRNOTAVAIL;
}

/*
 * Bind a port for a connect operation and hash it.
 */
static int dccp_v4_hash_connect(struct sock *sk)
{
	const unsigned short snum = inet_sk(sk)->num;
 	struct inet_bind_hashbucket *head;
 	struct inet_bind_bucket *tb;
	int ret;

 	if (snum == 0) {
 		int rover;
 		int low = sysctl_local_port_range[0];
 		int high = sysctl_local_port_range[1];
 		int remaining = (high - low) + 1;
		struct hlist_node *node;
 		struct inet_timewait_sock *tw = NULL;

 		local_bh_disable();

 		/* TODO. Actually it is not so bad idea to remove
 		 * dccp_hashinfo.portalloc_lock before next submission to Linus.
 		 * As soon as we touch this place at all it is time to think.
 		 *
 		 * Now it protects single _advisory_ variable dccp_hashinfo.port_rover,
 		 * hence it is mostly useless.
 		 * Code will work nicely if we just delete it, but
 		 * I am afraid in contented case it will work not better or
 		 * even worse: another cpu just will hit the same bucket
 		 * and spin there.
 		 * So some cpu salt could remove both contention and
 		 * memory pingpong. Any ideas how to do this in a nice way?
 		 */
 		spin_lock(&dccp_hashinfo.portalloc_lock);
 		rover = dccp_hashinfo.port_rover;

 		do {
 			rover++;
 			if ((rover < low) || (rover > high))
 				rover = low;
 			head = &dccp_hashinfo.bhash[inet_bhashfn(rover, dccp_hashinfo.bhash_size)];
 			spin_lock(&head->lock);

 			/* Does not bother with rcv_saddr checks,
 			 * because the established check is already
 			 * unique enough.
 			 */
			inet_bind_bucket_for_each(tb, node, &head->chain) {
 				if (tb->port == rover) {
 					BUG_TRAP(!hlist_empty(&tb->owners));
 					if (tb->fastreuse >= 0)
 						goto next_port;
 					if (!__dccp_v4_check_established(sk,
									 rover,
									 &tw))
 						goto ok;
 					goto next_port;
 				}
 			}

 			tb = inet_bind_bucket_create(dccp_hashinfo.bind_bucket_cachep, head, rover);
 			if (tb == NULL) {
 				spin_unlock(&head->lock);
 				break;
 			}
 			tb->fastreuse = -1;
 			goto ok;

 		next_port:
 			spin_unlock(&head->lock);
 		} while (--remaining > 0);
 		dccp_hashinfo.port_rover = rover;
 		spin_unlock(&dccp_hashinfo.portalloc_lock);

 		local_bh_enable();

 		return -EADDRNOTAVAIL;

ok:
 		/* All locks still held and bhs disabled */
 		dccp_hashinfo.port_rover = rover;
 		spin_unlock(&dccp_hashinfo.portalloc_lock);

 		inet_bind_hash(sk, tb, rover);
		if (sk_unhashed(sk)) {
 			inet_sk(sk)->sport = htons(rover);
 			__inet_hash(&dccp_hashinfo, sk, 0);
 		}
 		spin_unlock(&head->lock);

 		if (tw != NULL) {
 			dccp_tw_deschedule(tw);
 			inet_twsk_put(tw);
 		}

		ret = 0;
		goto out;
 	}

 	head = &dccp_hashinfo.bhash[inet_bhashfn(snum, dccp_hashinfo.bhash_size)];
 	tb   = inet_csk(sk)->icsk_bind_hash;
	spin_lock_bh(&head->lock);
	if (sk_head(&tb->owners) == sk && sk->sk_bind_node.next == NULL) {
		__inet_hash(&dccp_hashinfo, sk, 0);
		spin_unlock_bh(&head->lock);
		return 0;
	} else {
		spin_unlock(&head->lock);
		/* No definite answer... Walk to established hash table */
		ret = __dccp_v4_check_established(sk, snum, NULL);
out:
		local_bh_enable();
		return ret;
	}
}

static int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
			   int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct dccp_sock *dp = dccp_sk(sk);
	const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
	struct rtable *rt;
	u32 daddr, nexthop;
	int tmp;
	int err;

	dp->dccps_role = DCCP_ROLE_CLIENT;

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	nexthop = daddr = usin->sin_addr.s_addr;
	if (inet->opt != NULL && inet->opt->srr) {
		if (daddr == 0)
			return -EINVAL;
		nexthop = inet->opt->faddr;
	}

	tmp = ip_route_connect(&rt, nexthop, inet->saddr,
			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
			       IPPROTO_DCCP,
			       inet->sport, usin->sin_port, sk);
	if (tmp < 0)
		return tmp;

	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
		ip_rt_put(rt);
		return -ENETUNREACH;
	}

	if (inet->opt == NULL || !inet->opt->srr)
		daddr = rt->rt_dst;

	if (inet->saddr == 0)
		inet->saddr = rt->rt_src;
	inet->rcv_saddr = inet->saddr;

	inet->dport = usin->sin_port;
	inet->daddr = daddr;

	dp->dccps_ext_header_len = 0;
	if (inet->opt != NULL)
		dp->dccps_ext_header_len = inet->opt->optlen;
	/*
	 * Socket identity is still unknown (sport may be zero).
	 * However we set state to DCCP_REQUESTING and not releasing socket
	 * lock select source port, enter ourselves into the hash tables and
	 * complete initialization after this.
	 */
	dccp_set_state(sk, DCCP_REQUESTING);
	err = dccp_v4_hash_connect(sk);
	if (err != 0)
		goto failure;

	err = ip_route_newports(&rt, inet->sport, inet->dport, sk);
	if (err != 0)
		goto failure;

	/* OK, now commit destination to socket.  */
	sk_setup_caps(sk, &rt->u.dst);

	dp->dccps_gar =
		dp->dccps_iss = secure_dccp_sequence_number(inet->saddr,
							    inet->daddr,
							    inet->sport,
							    usin->sin_port);
	dccp_update_gss(sk, dp->dccps_iss);

	inet->id = dp->dccps_iss ^ jiffies;

	err = dccp_connect(sk);
	rt = NULL;
	if (err != 0)
		goto failure;
out:
	return err;
failure:
	/* This unhashes the socket and releases the local port, if necessary. */
	dccp_set_state(sk, DCCP_CLOSED);
	ip_rt_put(rt);
	sk->sk_route_caps = 0;
	inet->dport = 0;
	goto out;
}

/*
 * This routine does path mtu discovery as defined in RFC1191.
 */
static inline void dccp_do_pmtu_discovery(struct sock *sk,
					  const struct iphdr *iph,
					  u32 mtu)
{
	struct dst_entry *dst;
	const struct inet_sock *inet = inet_sk(sk);
	const struct dccp_sock *dp = dccp_sk(sk);

	/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
	 * send out by Linux are always < 576bytes so they should go through
	 * unfragmented).
	 */
	if (sk->sk_state == DCCP_LISTEN)
		return;

	/* We don't check in the destentry if pmtu discovery is forbidden
	 * on this route. We just assume that no packet_to_big packets
	 * are send back when pmtu discovery is not active.
     	 * There is a small race when the user changes this flag in the
	 * route, but I think that's acceptable.
	 */
	if ((dst = __sk_dst_check(sk, 0)) == NULL)
		return;

	dst->ops->update_pmtu(dst, mtu);

	/* Something is about to be wrong... Remember soft error
	 * for the case, if this connection will not able to recover.
	 */
	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
		sk->sk_err_soft = EMSGSIZE;

	mtu = dst_mtu(dst);

	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
	    dp->dccps_pmtu_cookie > mtu) {
		dccp_sync_mss(sk, mtu);

		/*
		 * From: draft-ietf-dccp-spec-11.txt
		 *
		 *	DCCP-Sync packets are the best choice for upward probing,
		 *	since DCCP-Sync probes do not risk application data loss.
		 */
		dccp_send_sync(sk, dp->dccps_gsr);
	} /* else let the usual retransmit timer handle it */
}

static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb)
{
	int err;
	struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh;
	const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) +
				     sizeof(struct dccp_hdr_ext) +
				     sizeof(struct dccp_hdr_ack_bits);
	struct sk_buff *skb;

	if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL)
		return;

	skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC);
	if (skb == NULL)
		return;

	/* Reserve space for headers. */
	skb_reserve(skb, MAX_DCCP_HEADER);

	skb->dst = dst_clone(rxskb->dst);

	skb->h.raw = skb_push(skb, dccp_hdr_ack_len);
	dh = dccp_hdr(skb);
	memset(dh, 0, dccp_hdr_ack_len);

	/* Build DCCP header and checksum it. */
	dh->dccph_type	   = DCCP_PKT_ACK;
	dh->dccph_sport	   = rxdh->dccph_dport;
	dh->dccph_dport	   = rxdh->dccph_sport;
	dh->dccph_doff	   = dccp_hdr_ack_len / 4;
	dh->dccph_x	   = 1;

	dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq);
	dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq);

	bh_lock_sock(dccp_ctl_socket->sk);
	err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk,
				    rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL);
	bh_unlock_sock(dccp_ctl_socket->sk);

	if (err == NET_XMIT_CN || err == 0) {
		DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
		DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
	}
}

static void dccp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
{
	dccp_v4_ctl_send_ack(skb);
}

static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
				 struct dst_entry *dst)
{
	int err = -1;
	struct sk_buff *skb;

	/* First, grab a route. */
	
	if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL)
		goto out;

	skb = dccp_make_response(sk, dst, req);
	if (skb != NULL) {
		const struct inet_request_sock *ireq = inet_rsk(req);

		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
					    ireq->rmt_addr,
					    ireq->opt);
		if (err == NET_XMIT_CN)
			err = 0;
	}

out:
	dst_release(dst);
	return err;
}

/*
 * 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 tcp 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 dccp_v4_err(struct sk_buff *skb, u32 info)
{
	const struct iphdr *iph = (struct iphdr *)skb->data;
	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + (iph->ihl << 2));
	struct dccp_sock *dp;
	struct inet_sock *inet;
	const int type = skb->h.icmph->type;
	const int code = skb->h.icmph->code;
	struct sock *sk;
	__u64 seq;
	int err;

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

	sk = inet_lookup(&dccp_hashinfo, iph->daddr, dh->dccph_dport,
			 iph->saddr, dh->dccph_sport, inet_iif(skb));
	if (sk == NULL) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == DCCP_TIME_WAIT) {
		inet_twsk_put((struct inet_timewait_sock *)sk);
		return;
	}

	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);

	if (sk->sk_state == DCCP_CLOSED)
		goto out;

	dp = dccp_sk(sk);
	seq = dccp_hdr_seq(skb);
	if (sk->sk_state != DCCP_LISTEN &&
	    !between48(seq, dp->dccps_swl, dp->dccps_swh)) {
		NET_INC_STATS(LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	switch (type) {
	case ICMP_SOURCE_QUENCH:
		/* Just silently ignore these. */
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out;

		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
			if (!sock_owned_by_user(sk))
				dccp_do_pmtu_discovery(sk, iph, info);
			goto out;
		}

		err = icmp_err_convert[code].errno;
		break;
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	default:
		goto out;
	}

	switch (sk->sk_state) {
		struct request_sock *req , **prev;
	case DCCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;
		req = inet_csk_search_req(sk, &prev, dh->dccph_dport,
					  iph->daddr, iph->saddr);
		if (!req)
			goto out;

		/*
		 * ICMPs are not backlogged, hence we cannot get an established
		 * socket here.
		 */
		BUG_TRAP(!req->sk);

		if (seq != dccp_rsk(req)->dreq_iss) {
			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}
		/*
		 * Still in RESPOND, just remove it silently.
		 * There is no good way to pass the error to the newly
		 * created socket, and POSIX does not want network
		 * errors returned from accept().
		 */
		inet_csk_reqsk_queue_drop(sk, req, prev);
		goto out;

	case DCCP_REQUESTING:
	case DCCP_RESPOND:
		if (!sock_owned_by_user(sk)) {
			DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
			sk->sk_err = err;

			sk->sk_error_report(sk);

			dccp_done(sk);
		} else
			sk->sk_err_soft = err;
		goto out;
	}

	/* If we've already connected we will keep trying
	 * until we time out, or the user gives up.
	 *
	 * rfc1122 4.2.3.9 allows to consider as hard errors
	 * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
	 * but it is obsoleted by pmtu discovery).
	 *
	 * Note, that in modern internet, where routing is unreliable
	 * and in each dark corner broken firewalls sit, sending random
	 * errors ordered by their masters even this two messages finally lose
	 * their original sense (even Linux sends invalid PORT_UNREACHs)
	 *
	 * Now we are in compliance with RFCs.
	 *							--ANK (980905)
	 */

	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:
	bh_unlock_sock(sk);
	sock_put(sk);
}

extern struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, enum dccp_reset_codes code);

int dccp_v4_send_reset(struct sock *sk, enum dccp_reset_codes code)
{
	struct sk_buff *skb;
	/*
	 * FIXME: what if rebuild_header fails?
	 * Should we be doing a rebuild_header here?
	 */
	int err = inet_sk_rebuild_header(sk);

	if (err != 0)
		return err;

	skb = dccp_make_reset(sk, sk->sk_dst_cache, code);
	if (skb != NULL) {
		const struct dccp_sock *dp = dccp_sk(sk);
		const struct inet_sock *inet = inet_sk(sk);

		err = ip_build_and_send_pkt(skb, sk,
					    inet->saddr, inet->daddr, NULL);
		if (err == NET_XMIT_CN)
			err = 0;

		ccid_hc_rx_exit(dp->dccps_hc_rx_ccid, sk);
		ccid_hc_tx_exit(dp->dccps_hc_tx_ccid, sk);
	}

	return err;
}

static inline u64 dccp_v4_init_sequence(const struct sock *sk,
					const struct sk_buff *skb)
{
	return secure_dccp_sequence_number(skb->nh.iph->daddr,
					   skb->nh.iph->saddr,
					   dccp_hdr(skb)->dccph_dport,
					   dccp_hdr(skb)->dccph_sport);
}

int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct inet_request_sock *ireq;
	struct dccp_sock dp;
	struct request_sock *req;
	struct dccp_request_sock *dreq;
	const __u32 saddr = skb->nh.iph->saddr;
	const __u32 daddr = skb->nh.iph->daddr;
	struct dst_entry *dst = NULL;

	/* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */
	if (((struct rtable *)skb->dst)->rt_flags &
	    (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	/*
	 * TW buckets are converted to open requests without
	 * limitations, they conserve resources and peer is
	 * evidently real one.
	 */
	if (inet_csk_reqsk_queue_is_full(sk))
		goto drop;

	/*
	 * Accept backlog is full. If we have already queued enough
	 * of warm entries in syn queue, drop request. It is better than
	 * clogging syn queue with openreqs with exponentially increasing
	 * timeout.
	 */
	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;

	req = reqsk_alloc(sk->sk_prot->rsk_prot);
	if (req == NULL)
		goto drop;

	/* FIXME: process options */

	dccp_openreq_init(req, &dp, skb);

	ireq = inet_rsk(req);
	ireq->loc_addr = daddr;
	ireq->rmt_addr = saddr;
	/* FIXME: Merge Aristeu's option parsing code when ready */
	req->rcv_wnd	= 100; /* Fake, option parsing will get the right value */
	ireq->opt	= NULL;

	/* 
	 * Step 3: Process LISTEN state
	 *
	 * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
	 *
	 * In fact we defer setting S.GSR, S.SWL, S.SWH to
	 * dccp_create_openreq_child.
	 */
	dreq = dccp_rsk(req);
	dreq->dreq_isr = DCCP_SKB_CB(skb)->dccpd_seq;
	dreq->dreq_iss = dccp_v4_init_sequence(sk, skb);
	dreq->dreq_service = dccp_hdr_request(skb)->dccph_req_service;

	if (dccp_v4_send_response(sk, req, dst))
		goto drop_and_free;

	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
	return 0;

drop_and_free:
	/*
	 * FIXME: should be reqsk_free after implementing req->rsk_ops
	 */
	__reqsk_free(req);
drop:
	DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
	return -1;
}

/*
 * The three way handshake has completed - we got a valid ACK or DATAACK -
 * now create the new socket.
 *
 * This is the equivalent of TCP's tcp_v4_syn_recv_sock
 */
struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
				       struct request_sock *req,
				       struct dst_entry *dst)
{
	struct inet_request_sock *ireq;
	struct inet_sock *newinet;
	struct dccp_sock *newdp;
	struct sock *newsk;

	if (sk_acceptq_is_full(sk))
		goto exit_overflow;

	if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL)
		goto exit;

	newsk = dccp_create_openreq_child(sk, req, skb);
	if (newsk == NULL)
		goto exit;

	sk_setup_caps(newsk, dst);

	newdp		   = dccp_sk(newsk);
	newinet		   = inet_sk(newsk);
	ireq		   = inet_rsk(req);
	newinet->daddr	   = ireq->rmt_addr;
	newinet->rcv_saddr = ireq->loc_addr;
	newinet->saddr	   = ireq->loc_addr;
	newinet->opt	   = ireq->opt;
	ireq->opt	   = NULL;
	newinet->mc_index  = inet_iif(skb);
	newinet->mc_ttl	   = skb->nh.iph->ttl;
	newinet->id	   = jiffies;

	dccp_sync_mss(newsk, dst_mtu(dst));

	__inet_hash(&dccp_hashinfo, newsk, 0);
	__inet_inherit_port(&dccp_hashinfo, sk, newsk);

	return newsk;

exit_overflow:
	NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
exit:
	NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
	dst_release(dst);
	return NULL;
}

static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
	const struct dccp_hdr *dh = dccp_hdr(skb);
	const struct iphdr *iph = skb->nh.iph;
	struct sock *nsk;
	struct request_sock **prev;
	/* Find possible connection requests. */
	struct request_sock *req = inet_csk_search_req(sk, &prev,
						       dh->dccph_sport,
						       iph->saddr, iph->daddr);
	if (req != NULL)
		return dccp_check_req(sk, skb, req, prev);

	nsk = __inet_lookup_established(&dccp_hashinfo,
					iph->saddr, dh->dccph_sport,
					iph->daddr, ntohs(dh->dccph_dport),
					inet_iif(skb));
	if (nsk != NULL) {
		if (nsk->sk_state != DCCP_TIME_WAIT) {
			bh_lock_sock(nsk);
			return nsk;
		}
		inet_twsk_put((struct inet_timewait_sock *)nsk);
		return NULL;
	}

	return sk;
}

805
int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, const u32 daddr)
806
{
807
	const struct dccp_hdr* dh = dccp_hdr(skb);
808
809
810
811
812
813
814
815
816
817
818
	int checksum_len;
	u32 tmp;

	if (dh->dccph_cscov == 0)
		checksum_len = skb->len;
	else {
		checksum_len = (dh->dccph_cscov + dh->dccph_x) * sizeof(u32);
		checksum_len = checksum_len < skb->len ? checksum_len : skb->len;
	}

	tmp = csum_partial((unsigned char *)dh, checksum_len, 0);
819
	return csum_tcpudp_magic(saddr, daddr, checksum_len, IPPROTO_DCCP, tmp);
820
821
}

822
823
static int dccp_v4_verify_checksum(struct sk_buff *skb,
				   const u32 saddr, const u32 daddr)
824
{
825
826
827
	struct dccp_hdr *dh = dccp_hdr(skb);
	int checksum_len;
	u32 tmp;
828

829
830
831
832
833
834
835
836
	if (dh->dccph_cscov == 0)
		checksum_len = skb->len;
	else {
		checksum_len = (dh->dccph_cscov + dh->dccph_x) * sizeof(u32);
		checksum_len = checksum_len < skb->len ? checksum_len : skb->len;
	}
	tmp = csum_partial((unsigned char *)dh, checksum_len, 0);
	return csum_tcpudp_magic(saddr, daddr, checksum_len, IPPROTO_DCCP, tmp) == 0 ? 0 : -1;
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
}

static struct dst_entry* dccp_v4_route_skb(struct sock *sk,
					   struct sk_buff *skb)
{
	struct rtable *rt;
	struct flowi fl = { .oif = ((struct rtable *)skb->dst)->rt_iif,
			    .nl_u = { .ip4_u =
				      { .daddr = skb->nh.iph->saddr,
					.saddr = skb->nh.iph->daddr,
					.tos = RT_CONN_FLAGS(sk) } },
			    .proto = sk->sk_protocol,
			    .uli_u = { .ports =
				       { .sport = dccp_hdr(skb)->dccph_dport,
					 .dport = dccp_hdr(skb)->dccph_sport } } };

	if (ip_route_output_flow(&rt, &fl, sk, 0)) {
		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
		return NULL;
	}

	return &rt->u.dst;
}

void dccp_v4_ctl_send_reset(struct sk_buff *rxskb)
{
	int err;
	struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh;
	const int dccp_hdr_reset_len = sizeof(struct dccp_hdr) +
				       sizeof(struct dccp_hdr_ext) +
				       sizeof(struct dccp_hdr_reset);
	struct sk_buff *skb;
	struct dst_entry *dst;

	/* Never send a reset in response to a reset. */
	if (rxdh->dccph_type == DCCP_PKT_RESET)
		return;

	if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL)
		return;

	dst = dccp_v4_route_skb(dccp_ctl_socket->sk, rxskb);
	if (dst == NULL)
		return;

	skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC);
	if (skb == NULL)
		goto out;

	/* Reserve space for headers. */
	skb_reserve(skb, MAX_DCCP_HEADER);
	skb->dst = dst_clone(dst);

	skb->h.raw = skb_push(skb, dccp_hdr_reset_len);
	dh = dccp_hdr(skb);
	memset(dh, 0, dccp_hdr_reset_len);

	/* Build DCCP header and checksum it. */
	dh->dccph_type	   = DCCP_PKT_RESET;
	dh->dccph_sport	   = rxdh->dccph_dport;
	dh->dccph_dport	   = rxdh->dccph_sport;
	dh->dccph_doff	   = dccp_hdr_reset_len / 4;
	dh->dccph_x	   = 1;
	dccp_hdr_reset(skb)->dccph_reset_code = DCCP_SKB_CB(rxskb)->dccpd_reset_code;

	dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq);
	dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq);

905
906
	dh->dccph_checksum = dccp_v4_checksum(skb, rxskb->nh.iph->saddr,
					      rxskb->nh.iph->daddr);
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
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
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000

	bh_lock_sock(dccp_ctl_socket->sk);
	err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk,
				    rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL);
	bh_unlock_sock(dccp_ctl_socket->sk);

	if (err == NET_XMIT_CN || err == 0) {
		DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
		DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
	}
out:
	 dst_release(dst);
}

int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_hdr *dh = dccp_hdr(skb);

	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
		if (dccp_rcv_established(sk, skb, dh, skb->len))
			goto reset;
		return 0;
	}

	/*
	 *  Step 3: Process LISTEN state
	 *     If S.state == LISTEN,
	 *	  If P.type == Request or P contains a valid Init Cookie option,
	 *	     * Must scan the packet's options to check for an Init
	 *		Cookie.  Only the Init Cookie is processed here,
	 *		however; other options are processed in Step 8.  This
	 *		scan need only be performed if the endpoint uses Init
	 *		Cookies *
	 *	     * Generate a new socket and switch to that socket *
	 *	     Set S := new socket for this port pair
	 *	     S.state = RESPOND
	 *	     Choose S.ISS (initial seqno) or set from Init Cookie
	 *	     Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
	 *	     Continue with S.state == RESPOND
	 *	     * A Response packet will be generated in Step 11 *
	 *	  Otherwise,
	 *	     Generate Reset(No Connection) unless P.type == Reset
	 *	     Drop packet and return
	 *
	 * NOTE: the check for the packet types is done in dccp_rcv_state_process
	 */
	if (sk->sk_state == DCCP_LISTEN) {
		struct sock *nsk = dccp_v4_hnd_req(sk, skb);

		if (nsk == NULL)
			goto discard;

		if (nsk != sk) {
			if (dccp_child_process(sk, nsk, skb))
				goto reset;
			return 0;
		}
	}

	if (dccp_rcv_state_process(sk, skb, dh, skb->len))
		goto reset;
	return 0;

reset:
	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
	dccp_v4_ctl_send_reset(skb);
discard:
	kfree_skb(skb);
	return 0;
}

static inline int dccp_invalid_packet(struct sk_buff *skb)
{
	const struct dccp_hdr *dh;

	if (skb->pkt_type != PACKET_HOST)
		return 1;

	if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) {
		dccp_pr_debug("pskb_may_pull failed\n");
		return 1;
	}

	dh = dccp_hdr(skb);

	/* If the packet type is not understood, drop packet and return */
	if (dh->dccph_type >= DCCP_PKT_INVALID) {
		dccp_pr_debug("invalid packet type\n");
		return 1;
	}

	/*
	 * If P.Data Offset is too small for packet type, or too large for
	 * packet, drop packet and return