aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/ipvs/ip_vs_proto_tcp.c
blob: de8ed73997c7005f40ca61eef6adbe2524ce320a (plain)
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
/*
 * ip_vs_proto_tcp.c:	TCP load balancing support for IPVS
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * Changes:
 *
 */

#include <linux/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>                  /* for tcphdr */
#include <net/ip.h>
#include <net/tcp.h>                    /* for csum_tcpudp_magic */
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#include <net/ip_vs.h>


static struct ip_vs_conn *
tcp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
		const struct ip_vs_iphdr *iph, unsigned int proto_off,
		int inverse)
{
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		return ip_vs_conn_in_get(af, iph->protocol,
					 &iph->saddr, pptr[0],
					 &iph->daddr, pptr[1]);
	} else {
		return ip_vs_conn_in_get(af, iph->protocol,
					 &iph->daddr, pptr[1],
					 &iph->saddr, pptr[0]);
	}
}

static struct ip_vs_conn *
tcp_conn_out_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
		 const struct ip_vs_iphdr *iph, unsigned int proto_off,
		 int inverse)
{
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		return ip_vs_conn_out_get(af, iph->protocol,
					  &iph->saddr, pptr[0],
					  &iph->daddr, pptr[1]);
	} else {
		return ip_vs_conn_out_get(af, iph->protocol,
					  &iph->daddr, pptr[1],
					  &iph->saddr, pptr[0]);
	}
}


static int
tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
		  int *verdict, struct ip_vs_conn **cpp)
{
	struct ip_vs_service *svc;
	struct tcphdr _tcph, *th;
	struct ip_vs_iphdr iph;

	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);

	th = skb_header_pointer(skb, iph.len, sizeof(_tcph), &_tcph);
	if (th == NULL) {
		*verdict = NF_DROP;
		return 0;
	}

	if (th->syn &&
	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr,
				     th->dest))) {
		if (ip_vs_todrop()) {
			/*
			 * It seems that we are very loaded.
			 * We have to drop this packet :(
			 */
			ip_vs_service_put(svc);
			*verdict = NF_DROP;
			return 0;
		}

		/*
		 * Let the virtual server select a real server for the
		 * incoming connection, and create a connection entry.
		 */
		*cpp = ip_vs_schedule(svc, skb);
		if (!*cpp) {
			*verdict = ip_vs_leave(svc, skb, pp);
			return 0;
		}
		ip_vs_service_put(svc);
	}
	return 1;
}


static inline void
tcp_fast_csum_update(int af, struct tcphdr *tcph,
		     const union nf_inet_addr *oldip,
		     const union nf_inet_addr *newip,
		     __be16 oldport, __be16 newport)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		tcph->check =
			csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6,
					 ip_vs_check_diff2(oldport, newport,
						~csum_unfold(tcph->check))));
	else
#endif
	tcph->check =
		csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip,
				 ip_vs_check_diff2(oldport, newport,
						~csum_unfold(tcph->check))));
}


static int
tcp_snat_handler(struct sk_buff *skb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct tcphdr *tcph;
	unsigned int tcphoff;

#ifdef CONFIG_IP_VS_IPV6
	if (cp->af == AF_INET6)
		tcphoff = sizeof(struct ipv6hdr);
	else
#endif
		tcphoff = ip_hdrlen(skb);

	/* csum_check requires unshared skb */
	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
			return 0;

		/* Call application helper if needed */
		if (!ip_vs_app_pkt_out(cp, skb))
			return 0;
	}

	tcph = (void *)skb_network_header(skb) + tcphoff;
	tcph->source = cp->vport;

	/* Adjust TCP checksums */
	if (!cp->app) {
		/* Only port and addr are changed, do fast csum update */
		tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr,
				     cp->dport, cp->vport);
		if (skb->ip_summed == CHECKSUM_COMPLETE)
			skb->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		tcph->check = 0;
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
#ifdef CONFIG_IP_VS_IPV6
		if (cp->af == AF_INET6)
			tcph->check = csum_ipv6_magic(&cp->vaddr.in6,
						      &cp->caddr.in6,
						      skb->len - tcphoff,
						      cp->protocol, skb->csum);
		else
#endif
			tcph->check = csum_tcpudp_magic(cp->vaddr.ip,
							cp->caddr.ip,
							skb->len - tcphoff,
							cp->protocol,
							skb->csum);

		IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
			  pp->name, tcph->check,
			  (char*)&(tcph->check) - (char*)tcph);
	}
	return 1;
}


static int
tcp_dnat_handler(struct sk_buff *skb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct tcphdr *tcph;
	unsigned int tcphoff;

#ifdef CONFIG_IP_VS_IPV6
	if (cp->af == AF_INET6)
		tcphoff = sizeof(struct ipv6hdr);
	else
#endif
		tcphoff = ip_hdrlen(skb);

	/* csum_check requires unshared skb */
	if (!skb_make_writable(skb, tcphoff+sizeof(*tcph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
			return 0;

		/*
		 *	Attempt ip_vs_app call.
		 *	It will fix ip_vs_conn and iph ack_seq stuff
		 */
		if (!ip_vs_app_pkt_in(cp, skb))
			return 0;
	}

	tcph = (void *)skb_network_header(skb) + tcphoff;
	tcph->dest = cp->dport;

	/*
	 *	Adjust TCP checksums
	 */
	if (!cp->app) {
		/* Only port and addr are changed, do fast csum update */
		tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr,
				     cp->vport, cp->dport);
		if (skb->ip_summed == CHECKSUM_COMPLETE)
			skb->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		tcph->check = 0;
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
#ifdef CONFIG_IP_VS_IPV6
		if (cp->af == AF_INET6)
			tcph->check = csum_ipv6_magic(&cp->caddr.in6,
						      &cp->daddr.in6,
						      skb->len - tcphoff,
						      cp->protocol, skb->csum);
		else
#endif
			tcph->check = csum_tcpudp_magic(cp->caddr.ip,
							cp->daddr.ip,
							skb->len - tcphoff,
							cp->protocol,
							skb->csum);
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}
	return 1;
}


static int
tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
{
	unsigned int tcphoff;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		tcphoff = sizeof(struct ipv6hdr);
	else
#endif
		tcphoff = ip_hdrlen(skb);

	switch (skb->ip_summed) {
	case CHECKSUM_NONE:
		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
	case CHECKSUM_COMPLETE:
#ifdef CONFIG_IP_VS_IPV6
		if (af == AF_INET6) {
			if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
					    &ipv6_hdr(skb)->daddr,
					    skb->len - tcphoff,
					    ipv6_hdr(skb)->nexthdr,
					    skb->csum)) {
				IP_VS_DBG_RL_PKT(0, pp, skb, 0,
						 "Failed checksum for");
				return 0;
			}
		} else
#endif
			if (csum_tcpudp_magic(ip_hdr(skb)->saddr,
					      ip_hdr(skb)->daddr,
					      skb->len - tcphoff,
					      ip_hdr(skb)->protocol,
					      skb->csum)) {
				IP_VS_DBG_RL_PKT(0, pp, skb, 0,
						 "Failed checksum for");
				return 0;
			}
		break;
	default:
		/* No need to checksum. */
		break;
	}

	return 1;
}


#define TCP_DIR_INPUT		0
#define TCP_DIR_OUTPUT		4
#define TCP_DIR_INPUT_ONLY	8

static const int tcp_state_off[IP_VS_DIR_LAST] = {
	[IP_VS_DIR_INPUT]		=	TCP_DIR_INPUT,
	[IP_VS_DIR_OUTPUT]		=	TCP_DIR_OUTPUT,
	[IP_VS_DIR_INPUT_ONLY]		=	TCP_DIR_INPUT_ONLY,
};

/*
 *	Timeout table[state]
 */
static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
	[IP_VS_TCP_S_NONE]		=	2*HZ,
	[IP_VS_TCP_S_ESTABLISHED]	=	15*60*HZ,
	[IP_VS_TCP_S_SYN_SENT]		=	2*60*HZ,
	[IP_VS_TCP_S_SYN_RECV]		=	1*60*HZ,
	[IP_VS_TCP_S_FIN_WAIT]		=	2*60*HZ,
	[IP_VS_TCP_S_TIME_WAIT]		=	2*60*HZ,
	[IP_VS_TCP_S_CLOSE]		=	10*HZ,
	[IP_VS_TCP_S_CLOSE_WAIT]	=	60*HZ,
	[IP_VS_TCP_S_LAST_ACK]		=	30*HZ,
	[IP_VS_TCP_S_LISTEN]		=	2*60*HZ,
	[IP_VS_TCP_S_SYNACK]		=	120*HZ,
	[IP_VS_TCP_S_LAST]		=	2*HZ,
};

static char * tcp_state_name_table[IP_VS_TCP_S_LAST+1] = {
	[IP_VS_TCP_S_NONE]		=	"NONE",
	[IP_VS_TCP_S_ESTABLISHED]	=	"ESTABLISHED",
	[IP_VS_TCP_S_SYN_SENT]		=	"SYN_SENT",
	[IP_VS_TCP_S_SYN_RECV]		=	"SYN_RECV",
	[IP_VS_TCP_S_FIN_WAIT]		=	"FIN_WAIT",
	[IP_VS_TCP_S_TIME_WAIT]		=	"TIME_WAIT",
	[IP_VS_TCP_S_CLOSE]		=	"CLOSE",
	[IP_VS_TCP_S_CLOSE_WAIT]	=	"CLOSE_WAIT",
	[IP_VS_TCP_S_LAST_ACK]		=	"LAST_ACK",
	[IP_VS_TCP_S_LISTEN]		=	"LISTEN",
	[IP_VS_TCP_S_SYNACK]		=	"SYNACK",
	[IP_VS_TCP_S_LAST]		=	"BUG!",
};

#define sNO IP_VS_TCP_S_NONE
#define sES IP_VS_TCP_S_ESTABLISHED
#define sSS IP_VS_TCP_S_SYN_SENT
#define sSR IP_VS_TCP_S_SYN_RECV
#define sFW IP_VS_TCP_S_FIN_WAIT
#define sTW IP_VS_TCP_S_TIME_WAIT
#define sCL IP_VS_TCP_S_CLOSE
#define sCW IP_VS_TCP_S_CLOSE_WAIT
#define sLA IP_VS_TCP_S_LAST_ACK
#define sLI IP_VS_TCP_S_LISTEN
#define sSA IP_VS_TCP_S_SYNACK

struct tcp_states_t {
	int next_state[IP_VS_TCP_S_LAST];
};

static const char * tcp_state_name(int state)
{
	if (state >= IP_VS_TCP_S_LAST)
		return "ERR!";
	return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?";
}

static struct tcp_states_t tcp_states [] = {
/*	INPUT */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
/*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }},
/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }},

/*	OUTPUT */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSS, sES, sSS, sSR, sSS, sSS, sSS, sSS, sSS, sLI, sSR }},
/*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }},
/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }},
/*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }},

/*	INPUT-ONLY */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
/*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};

static struct tcp_states_t tcp_states_dos [] = {
/*	INPUT */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},
/*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }},
/*ack*/ {{sCL, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},

/*	OUTPUT */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSS, sES, sSS, sSA, sSS, sSS, sSS, sSS, sSS, sLI, sSA }},
/*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }},
/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }},
/*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }},

/*	INPUT-ONLY */
/*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
/*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }},
/*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};

static struct tcp_states_t *tcp_state_table = tcp_states;


static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
{
	int on = (flags & 1);		/* secure_tcp */

	/*
	** FIXME: change secure_tcp to independent sysctl var
	** or make it per-service or per-app because it is valid
	** for most if not for all of the applications. Something
	** like "capabilities" (flags) for each object.
	*/
	tcp_state_table = (on? tcp_states_dos : tcp_states);
}

static int
tcp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
{
	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_TCP_S_LAST,
				       tcp_state_name_table, sname, to);
}

static inline int tcp_state_idx(struct tcphdr *th)
{
	if (th->rst)
		return 3;
	if (th->syn)
		return 0;
	if (th->fin)
		return 1;
	if (th->ack)
		return 2;
	return -1;
}

static inline void
set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
	      int direction, struct tcphdr *th)
{
	int state_idx;
	int new_state = IP_VS_TCP_S_CLOSE;
	int state_off = tcp_state_off[direction];

	/*
	 *    Update state offset to INPUT_ONLY if necessary
	 *    or delete NO_OUTPUT flag if output packet detected
	 */
	if (cp->flags & IP_VS_CONN_F_NOOUTPUT) {
		if (state_off == TCP_DIR_OUTPUT)
			cp->flags &= ~IP_VS_CONN_F_NOOUTPUT;
		else
			state_off = TCP_DIR_INPUT_ONLY;
	}

	if ((state_idx = tcp_state_idx(th)) < 0) {
		IP_VS_DBG(8, "tcp_state_idx=%d!!!\n", state_idx);
		goto tcp_state_out;
	}

	new_state = tcp_state_table[state_off+state_idx].next_state[cp->state];

  tcp_state_out:
	if (new_state != cp->state) {
		struct ip_vs_dest *dest = cp->dest;

		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->"
			      "%s:%d state: %s->%s conn->refcnt:%d\n",
			      pp->name,
			      ((state_off == TCP_DIR_OUTPUT) ?
			       "output " : "input "),
			      th->syn ? 'S' : '.',
			      th->fin ? 'F' : '.',
			      th->ack ? 'A' : '.',
			      th->rst ? 'R' : '.',
			      IP_VS_DBG_ADDR(cp->af, &cp->daddr),
			      ntohs(cp->dport),
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      tcp_state_name(cp->state),
			      tcp_state_name(new_state),
			      atomic_read(&cp->refcnt));

		if (dest) {
			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
			    (new_state != IP_VS_TCP_S_ESTABLISHED)) {
				atomic_dec(&dest->activeconns);
				atomic_inc(&dest->inactconns);
				cp->flags |= IP_VS_CONN_F_INACTIVE;
			} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
				   (new_state == IP_VS_TCP_S_ESTABLISHED)) {
				atomic_inc(&dest->activeconns);
				atomic_dec(&dest->inactconns);
				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
			}
		}
	}

	cp->timeout = pp->timeout_table[cp->state = new_state];
}


/*
 *	Handle state transitions
 */
static int
tcp_state_transition(struct ip_vs_conn *cp, int direction,
		     const struct sk_buff *skb,
		     struct ip_vs_protocol *pp)
{
	struct tcphdr _tcph, *th;

#ifdef CONFIG_IP_VS_IPV6
	int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
#else
	int ihl = ip_hdrlen(skb);
#endif

	th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph);
	if (th == NULL)
		return 0;

	spin_lock(&cp->lock);
	set_tcp_state(pp, cp, direction, th);
	spin_unlock(&cp->lock);

	return 1;
}


/*
 *	Hash table for TCP application incarnations
 */
#define	TCP_APP_TAB_BITS	4
#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)

static struct list_head tcp_apps[TCP_APP_TAB_SIZE];
static DEFINE_SPINLOCK(tcp_app_lock);

static inline __u16 tcp_app_hashkey(__be16 port)
{
	return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port)
		& TCP_APP_TAB_MASK;
}


static int tcp_register_app(struct ip_vs_app *inc)
{
	struct ip_vs_app *i;
	__u16 hash;
	__be16 port = inc->port;
	int ret = 0;

	hash = tcp_app_hashkey(port);

	spin_lock_bh(&tcp_app_lock);
	list_for_each_entry(i, &tcp_apps[hash], p_list) {
		if (i->port == port) {
			ret = -EEXIST;
			goto out;
		}
	}
	list_add(&inc->p_list, &tcp_apps[hash]);
	atomic_inc(&ip_vs_protocol_tcp.appcnt);

  out:
	spin_unlock_bh(&tcp_app_lock);
	return ret;
}


static void
tcp_unregister_app(struct ip_vs_app *inc)
{
	spin_lock_bh(&tcp_app_lock);
	atomic_dec(&ip_vs_protocol_tcp.appcnt);
	list_del(&inc->p_list);
	spin_unlock_bh(&tcp_app_lock);
}


static int
tcp_app_conn_bind(struct ip_vs_conn *cp)
{
	int hash;
	struct ip_vs_app *inc;
	int result = 0;

	/* Default binding: bind app only for NAT */
	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
		return 0;

	/* Lookup application incarnations and bind the right one */
	hash = tcp_app_hashkey(cp->vport);

	spin_lock(&tcp_app_lock);
	list_for_each_entry(inc, &tcp_apps[hash], p_list) {
		if (inc->port == cp->vport) {
			if (unlikely(!ip_vs_app_inc_get(inc)))
				break;
			spin_unlock(&tcp_app_lock);

			IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->"
				      "%s:%u to app %s on port %u\n",
				      __func__,
				      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
				      ntohs(cp->cport),
				      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
				      ntohs(cp->vport),
				      inc->name, ntohs(inc->port));

			cp->app = inc;
			if (inc->init_conn)
				result = inc->init_conn(inc, cp);
			goto out;
		}
	}
	spin_unlock(&tcp_app_lock);

  out:
	return result;
}


/*
 *	Set LISTEN timeout. (ip_vs_conn_put will setup timer)
 */
void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp)
{
	spin_lock(&cp->lock);
	cp->state = IP_VS_TCP_S_LISTEN;
	cp->timeout = ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_LISTEN];
	spin_unlock(&cp->lock);
}


static void ip_vs_tcp_init(struct ip_vs_protocol *pp)
{
	IP_VS_INIT_HASH_TABLE(tcp_apps);
	pp->timeout_table = tcp_timeouts;
}


static void ip_vs_tcp_exit(struct ip_vs_protocol *pp)
{
}


struct ip_vs_protocol ip_vs_protocol_tcp = {
	.name =			"TCP",
	.protocol =		IPPROTO_TCP,
	.num_states =		IP_VS_TCP_S_LAST,
	.dont_defrag =		0,
	.appcnt =		ATOMIC_INIT(0),
	.init =			ip_vs_tcp_init,
	.exit =			ip_vs_tcp_exit,
	.register_app =		tcp_register_app,
	.unregister_app =	tcp_unregister_app,
	.conn_schedule =	tcp_conn_schedule,
	.conn_in_get =		tcp_conn_in_get,
	.conn_out_get =		tcp_conn_out_get,
	.snat_handler =		tcp_snat_handler,
	.dnat_handler =		tcp_dnat_handler,
	.csum_check =		tcp_csum_check,
	.state_name =		tcp_state_name,
	.state_transition =	tcp_state_transition,
	.app_conn_bind =	tcp_app_conn_bind,
	.debug_packet =		ip_vs_tcpudp_debug_packet,
	.timeout_change =	tcp_timeout_change,
	.set_state_timeout =	tcp_set_state_timeout,
};