aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/ipvs/ip_vs_core.c
blob: 3ac7eeca04ac4ca4da81bdc1f6e75cce70316b79 (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
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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the Netfilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Version:     $Id: ip_vs_core.c,v 1.34 2003/05/10 03:05:23 wensong Exp $
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              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.
 *
 * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese,
 * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms
 * and others.
 *
 * Changes:
 *	Paul `Rusty' Russell		properly handle non-linear skbs
 *	Harald Welte			don't use nfcache
 *
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/icmp.h>

#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>                   /* for icmp_send */
#include <net/route.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#include <net/ip_vs.h>


EXPORT_SYMBOL(register_ip_vs_scheduler);
EXPORT_SYMBOL(unregister_ip_vs_scheduler);
EXPORT_SYMBOL(ip_vs_skb_replace);
EXPORT_SYMBOL(ip_vs_proto_name);
EXPORT_SYMBOL(ip_vs_conn_new);
EXPORT_SYMBOL(ip_vs_conn_in_get);
EXPORT_SYMBOL(ip_vs_conn_out_get);
#ifdef CONFIG_IP_VS_PROTO_TCP
EXPORT_SYMBOL(ip_vs_tcp_conn_listen);
#endif
EXPORT_SYMBOL(ip_vs_conn_put);
#ifdef CONFIG_IP_VS_DEBUG
EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif
EXPORT_SYMBOL(ip_vs_make_skb_writable);


/* ID used in ICMP lookups */
#define icmp_id(icmph)          (((icmph)->un).echo.id)

const char *ip_vs_proto_name(unsigned proto)
{
	static char buf[20];

	switch (proto) {
	case IPPROTO_IP:
		return "IP";
	case IPPROTO_UDP:
		return "UDP";
	case IPPROTO_TCP:
		return "TCP";
	case IPPROTO_ICMP:
		return "ICMP";
	default:
		sprintf(buf, "IP_%d", proto);
		return buf;
	}
}

void ip_vs_init_hash_table(struct list_head *table, int rows)
{
	while (--rows >= 0)
		INIT_LIST_HEAD(&table[rows]);
}

static inline void
ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		spin_lock(&dest->stats.lock);
		dest->stats.inpkts++;
		dest->stats.inbytes += skb->len;
		spin_unlock(&dest->stats.lock);

		spin_lock(&dest->svc->stats.lock);
		dest->svc->stats.inpkts++;
		dest->svc->stats.inbytes += skb->len;
		spin_unlock(&dest->svc->stats.lock);

		spin_lock(&ip_vs_stats.lock);
		ip_vs_stats.inpkts++;
		ip_vs_stats.inbytes += skb->len;
		spin_unlock(&ip_vs_stats.lock);
	}
}


static inline void
ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		spin_lock(&dest->stats.lock);
		dest->stats.outpkts++;
		dest->stats.outbytes += skb->len;
		spin_unlock(&dest->stats.lock);

		spin_lock(&dest->svc->stats.lock);
		dest->svc->stats.outpkts++;
		dest->svc->stats.outbytes += skb->len;
		spin_unlock(&dest->svc->stats.lock);

		spin_lock(&ip_vs_stats.lock);
		ip_vs_stats.outpkts++;
		ip_vs_stats.outbytes += skb->len;
		spin_unlock(&ip_vs_stats.lock);
	}
}


static inline void
ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
{
	spin_lock(&cp->dest->stats.lock);
	cp->dest->stats.conns++;
	spin_unlock(&cp->dest->stats.lock);

	spin_lock(&svc->stats.lock);
	svc->stats.conns++;
	spin_unlock(&svc->stats.lock);

	spin_lock(&ip_vs_stats.lock);
	ip_vs_stats.conns++;
	spin_unlock(&ip_vs_stats.lock);
}


static inline int
ip_vs_set_state(struct ip_vs_conn *cp, int direction,
		const struct sk_buff *skb,
		struct ip_vs_protocol *pp)
{
	if (unlikely(!pp->state_transition))
		return 0;
	return pp->state_transition(cp, direction, skb, pp);
}


int ip_vs_make_skb_writable(struct sk_buff **pskb, int writable_len)
{
	struct sk_buff *skb = *pskb;

	/* skb is already used, better copy skb and its payload */
	if (unlikely(skb_shared(skb) || skb->sk))
		goto copy_skb;

	/* skb data is already used, copy it */
	if (unlikely(skb_cloned(skb)))
		goto copy_data;

	return pskb_may_pull(skb, writable_len);

  copy_data:
	if (unlikely(writable_len > skb->len))
		return 0;
	return !pskb_expand_head(skb, 0, 0, GFP_ATOMIC);

  copy_skb:
	if (unlikely(writable_len > skb->len))
		return 0;
	skb = skb_copy(skb, GFP_ATOMIC);
	if (!skb)
		return 0;
	BUG_ON(skb_is_nonlinear(skb));

	/* Rest of kernel will get very unhappy if we pass it a
	   suddenly-orphaned skbuff */
	if ((*pskb)->sk)
		skb_set_owner_w(skb, (*pskb)->sk);
	kfree_skb(*pskb);
	*pskb = skb;
	return 1;
}

/*
 *  IPVS persistent scheduling function
 *  It creates a connection entry according to its template if exists,
 *  or selects a server and creates a connection entry plus a template.
 *  Locking: we are svc user (svc->refcnt), so we hold all dests too
 *  Protocols supported: TCP, UDP
 */
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
		    const struct sk_buff *skb,
		    __u16 ports[2])
{
	struct ip_vs_conn *cp = NULL;
	struct iphdr *iph = skb->nh.iph;
	struct ip_vs_dest *dest;
	struct ip_vs_conn *ct;
	__u16  dport;	 /* destination port to forward */
	__u32  snet;	 /* source network of the client, after masking */

	/* Mask saddr with the netmask to adjust template granularity */
	snet = iph->saddr & svc->netmask;

	IP_VS_DBG(6, "p-schedule: src %u.%u.%u.%u:%u dest %u.%u.%u.%u:%u "
		  "mnet %u.%u.%u.%u\n",
		  NIPQUAD(iph->saddr), ntohs(ports[0]),
		  NIPQUAD(iph->daddr), ntohs(ports[1]),
		  NIPQUAD(snet));

	/*
	 * As far as we know, FTP is a very complicated network protocol, and
	 * it uses control connection and data connections. For active FTP,
	 * FTP server initialize data connection to the client, its source port
	 * is often 20. For passive FTP, FTP server tells the clients the port
	 * that it passively listens to,  and the client issues the data
	 * connection. In the tunneling or direct routing mode, the load
	 * balancer is on the client-to-server half of connection, the port
	 * number is unknown to the load balancer. So, a conn template like
	 * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP
	 * service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
	 * is created for other persistent services.
	 */
	if (ports[1] == svc->port) {
		/* Check if a template already exists */
		if (svc->port != FTPPORT)
			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
					       iph->daddr, ports[1]);
		else
			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
					       iph->daddr, 0);

		if (!ct || !ip_vs_check_template(ct)) {
			/*
			 * No template found or the dest of the connection
			 * template is not available.
			 */
			dest = svc->scheduler->schedule(svc, skb);
			if (dest == NULL) {
				IP_VS_DBG(1, "p-schedule: no dest found.\n");
				return NULL;
			}

			/*
			 * Create a template like <protocol,caddr,0,
			 * vaddr,vport,daddr,dport> for non-ftp service,
			 * and <protocol,caddr,0,vaddr,0,daddr,0>
			 * for ftp service.
			 */
			if (svc->port != FTPPORT)
				ct = ip_vs_conn_new(iph->protocol,
						    snet, 0,
						    iph->daddr,
						    ports[1],
						    dest->addr, dest->port,
						    0,
						    dest);
			else
				ct = ip_vs_conn_new(iph->protocol,
						    snet, 0,
						    iph->daddr, 0,
						    dest->addr, 0,
						    0,
						    dest);
			if (ct == NULL)
				return NULL;

			ct->timeout = svc->timeout;
		} else {
			/* set destination with the found template */
			dest = ct->dest;
		}
		dport = dest->port;
	} else {
		/*
		 * Note: persistent fwmark-based services and persistent
		 * port zero service are handled here.
		 * fwmark template: <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
		 * port zero template: <protocol,caddr,0,vaddr,0,daddr,0>
		 */
		if (svc->fwmark)
			ct = ip_vs_conn_in_get(IPPROTO_IP, snet, 0,
					       htonl(svc->fwmark), 0);
		else
			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
					       iph->daddr, 0);

		if (!ct || !ip_vs_check_template(ct)) {
			/*
			 * If it is not persistent port zero, return NULL,
			 * otherwise create a connection template.
			 */
			if (svc->port)
				return NULL;

			dest = svc->scheduler->schedule(svc, skb);
			if (dest == NULL) {
				IP_VS_DBG(1, "p-schedule: no dest found.\n");
				return NULL;
			}

			/*
			 * Create a template according to the service
			 */
			if (svc->fwmark)
				ct = ip_vs_conn_new(IPPROTO_IP,
						    snet, 0,
						    htonl(svc->fwmark), 0,
						    dest->addr, 0,
						    0,
						    dest);
			else
				ct = ip_vs_conn_new(iph->protocol,
						    snet, 0,
						    iph->daddr, 0,
						    dest->addr, 0,
						    0,
						    dest);
			if (ct == NULL)
				return NULL;

			ct->timeout = svc->timeout;
		} else {
			/* set destination with the found template */
			dest = ct->dest;
		}
		dport = ports[1];
	}

	/*
	 *    Create a new connection according to the template
	 */
	cp = ip_vs_conn_new(iph->protocol,
			    iph->saddr, ports[0],
			    iph->daddr, ports[1],
			    dest->addr, dport,
			    0,
			    dest);
	if (cp == NULL) {
		ip_vs_conn_put(ct);
		return NULL;
	}

	/*
	 *    Add its control
	 */
	ip_vs_control_add(cp, ct);
	ip_vs_conn_put(ct);

	ip_vs_conn_stats(cp, svc);
	return cp;
}


/*
 *  IPVS main scheduling function
 *  It selects a server according to the virtual service, and
 *  creates a connection entry.
 *  Protocols supported: TCP, UDP
 */
struct ip_vs_conn *
ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
	struct ip_vs_conn *cp = NULL;
	struct iphdr *iph = skb->nh.iph;
	struct ip_vs_dest *dest;
	__u16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, iph->ihl*4,
				  sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	/*
	 *    Persistent service
	 */
	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
		return ip_vs_sched_persist(svc, skb, pptr);

	/*
	 *    Non-persistent service
	 */
	if (!svc->fwmark && pptr[1] != svc->port) {
		if (!svc->port)
			IP_VS_ERR("Schedule: port zero only supported "
				  "in persistent services, "
				  "check your ipvs configuration\n");
		return NULL;
	}

	dest = svc->scheduler->schedule(svc, skb);
	if (dest == NULL) {
		IP_VS_DBG(1, "Schedule: no dest found.\n");
		return NULL;
	}

	/*
	 *    Create a connection entry.
	 */
	cp = ip_vs_conn_new(iph->protocol,
			    iph->saddr, pptr[0],
			    iph->daddr, pptr[1],
			    dest->addr, dest->port?dest->port:pptr[1],
			    0,
			    dest);
	if (cp == NULL)
		return NULL;

	IP_VS_DBG(6, "Schedule fwd:%c c:%u.%u.%u.%u:%u v:%u.%u.%u.%u:%u "
		  "d:%u.%u.%u.%u:%u flg:%X cnt:%d\n",
		  ip_vs_fwd_tag(cp),
		  NIPQUAD(cp->caddr), ntohs(cp->cport),
		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
		  NIPQUAD(cp->daddr), ntohs(cp->dport),
		  cp->flags, atomic_read(&cp->refcnt));

	ip_vs_conn_stats(cp, svc);
	return cp;
}


/*
 *  Pass or drop the packet.
 *  Called by ip_vs_in, when the virtual service is available but
 *  no destination is available for a new connection.
 */
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
		struct ip_vs_protocol *pp)
{
	__u16 _ports[2], *pptr;
	struct iphdr *iph = skb->nh.iph;

	pptr = skb_header_pointer(skb, iph->ihl*4,
				  sizeof(_ports), _ports);
	if (pptr == NULL) {
		ip_vs_service_put(svc);
		return NF_DROP;
	}

	/* if it is fwmark-based service, the cache_bypass sysctl is up
	   and the destination is RTN_UNICAST (and not local), then create
	   a cache_bypass connection entry */
	if (sysctl_ip_vs_cache_bypass && svc->fwmark
	    && (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
		int ret, cs;
		struct ip_vs_conn *cp;

		ip_vs_service_put(svc);

		/* create a new connection entry */
		IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
		cp = ip_vs_conn_new(iph->protocol,
				    iph->saddr, pptr[0],
				    iph->daddr, pptr[1],
				    0, 0,
				    IP_VS_CONN_F_BYPASS,
				    NULL);
		if (cp == NULL)
			return NF_DROP;

		/* statistics */
		ip_vs_in_stats(cp, skb);

		/* set state */
		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);

		/* transmit the first SYN packet */
		ret = cp->packet_xmit(skb, cp, pp);
		/* do not touch skb anymore */

		atomic_inc(&cp->in_pkts);
		ip_vs_conn_put(cp);
		return ret;
	}

	/*
	 * When the virtual ftp service is presented, packets destined
	 * for other services on the VIP may get here (except services
	 * listed in the ipvs table), pass the packets, because it is
	 * not ipvs job to decide to drop the packets.
	 */
	if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
		ip_vs_service_put(svc);
		return NF_ACCEPT;
	}

	ip_vs_service_put(svc);

	/*
	 * Notify the client that the destination is unreachable, and
	 * release the socket buffer.
	 * Since it is in IP layer, the TCP socket is not actually
	 * created, the TCP RST packet cannot be sent, instead that
	 * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
	 */
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
	return NF_DROP;
}


/*
 *      It is hooked before NF_IP_PRI_NAT_SRC at the NF_IP_POST_ROUTING
 *      chain, and is used for VS/NAT.
 *      It detects packets for VS/NAT connections and sends the packets
 *      immediately. This can avoid that iptable_nat mangles the packets
 *      for VS/NAT.
 */
static unsigned int ip_vs_post_routing(unsigned int hooknum,
				       struct sk_buff **pskb,
				       const struct net_device *in,
				       const struct net_device *out,
				       int (*okfn)(struct sk_buff *))
{
	if (!((*pskb)->ipvs_property))
		return NF_ACCEPT;

	/* The packet was sent from IPVS, exit this chain */
	(*okfn)(*pskb);

	return NF_STOLEN;
}

u16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
	return (u16) csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
}

static inline struct sk_buff *
ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
{
	skb = ip_defrag(skb, user);
	if (skb)
		ip_send_check(skb->nh.iph);
	return skb;
}

/*
 * Packet has been made sufficiently writable in caller
 * - inout: 1=in->out, 0=out->in
 */
void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int inout)
{
	struct iphdr *iph	 = skb->nh.iph;
	unsigned int icmp_offset = iph->ihl*4;
	struct icmphdr *icmph	 = (struct icmphdr *)(skb->nh.raw + icmp_offset);
	struct iphdr *ciph	 = (struct iphdr *)(icmph + 1);

	if (inout) {
		iph->saddr = cp->vaddr;
		ip_send_check(iph);
		ciph->daddr = cp->vaddr;
		ip_send_check(ciph);
	} else {
		iph->daddr = cp->daddr;
		ip_send_check(iph);
		ciph->saddr = cp->daddr;
		ip_send_check(ciph);
	}

	/* the TCP/UDP port */
	if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol) {
		__u16 *ports = (void *)ciph + ciph->ihl*4;

		if (inout)
			ports[1] = cp->vport;
		else
			ports[0] = cp->dport;
	}

	/* And finally the ICMP checksum */
	icmph->checksum = 0;
	icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset);
	skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (inout)
		IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered outgoing ICMP");
	else
		IP_VS_DBG_PKT(11, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered incoming ICMP");
}

/*
 *	Handle ICMP messages in the inside-to-outside direction (outgoing).
 *	Find any that might be relevant, check against existing connections,
 *	forward to the right destination host if relevant.
 *	Currently handles error types - unreachable, quench, ttl exceeded.
 *	(Only used in VS/NAT)
 */
static int ip_vs_out_icmp(struct sk_buff **pskb, int *related)
{
	struct sk_buff *skb = *pskb;
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	unsigned int offset, ihl, verdict;

	*related = 1;

	/* reassemble IP fragments */
	if (skb->nh.iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) {
		skb = ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT);
		if (!skb)
			return NF_STOLEN;
		*pskb = skb;
	}

	iph = skb->nh.iph;
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %u.%u.%u.%u->%u.%u.%u.%u\n",
		  ic->type, ntohs(icmp_id(ic)),
		  NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	pp = ip_vs_proto_get(cih->protocol);
	if (!pp)
		return NF_ACCEPT;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & __constant_htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, pp, skb, offset, "Checking outgoing ICMP for");

	offset += cih->ihl * 4;

	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_out_get(skb, pp, cih, offset, 1);
	if (!cp)
		return NF_ACCEPT;

	verdict = NF_DROP;

	if (IP_VS_FWD_METHOD(cp) != 0) {
		IP_VS_ERR("shouldn't reach here, because the box is on the"
			  "half connection in the tun/dr module.\n");
	}

	/* Ensure the checksum is correct */
	if (skb->ip_summed != CHECKSUM_UNNECESSARY &&
	    ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG(1, "Forward ICMP: failed checksum from %d.%d.%d.%d!\n",
			  NIPQUAD(iph->saddr));
		goto out;
	}

	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
		offset += 2 * sizeof(__u16);
	if (!ip_vs_make_skb_writable(pskb, offset))
		goto out;
	skb = *pskb;

	ip_vs_nat_icmp(skb, pp, cp, 1);

	/* do the statistics and put it back */
	ip_vs_out_stats(cp, skb);

	skb->ipvs_property = 1;
	verdict = NF_ACCEPT;

  out:
	__ip_vs_conn_put(cp);

	return verdict;
}

static inline int is_tcp_reset(const struct sk_buff *skb)
{
	struct tcphdr _tcph, *th;

	th = skb_header_pointer(skb, skb->nh.iph->ihl * 4,
				sizeof(_tcph), &_tcph);
	if (th == NULL)
		return 0;
	return th->rst;
}

/*
 *	It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
 *	Check if outgoing packet belongs to the established ip_vs_conn,
 *      rewrite addresses of the packet and send it on its way...
 */
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
	  const struct net_device *in, const struct net_device *out,
	  int (*okfn)(struct sk_buff *))
{
	struct sk_buff  *skb = *pskb;
	struct iphdr	*iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_conn *cp;
	int ihl;

	EnterFunction(11);

	if (skb->ipvs_property)
		return NF_ACCEPT;

	iph = skb->nh.iph;
	if (unlikely(iph->protocol == IPPROTO_ICMP)) {
		int related, verdict = ip_vs_out_icmp(pskb, &related);

		if (related)
			return verdict;
		skb = *pskb;
		iph = skb->nh.iph;
	}

	pp = ip_vs_proto_get(iph->protocol);
	if (unlikely(!pp))
		return NF_ACCEPT;

	/* reassemble IP fragments */
	if (unlikely(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET) &&
		     !pp->dont_defrag)) {
		skb = ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT);
		if (!skb)
			return NF_STOLEN;
		iph = skb->nh.iph;
		*pskb = skb;
	}

	ihl = iph->ihl << 2;

	/*
	 * Check if the packet belongs to an existing entry
	 */
	cp = pp->conn_out_get(skb, pp, iph, ihl, 0);

	if (unlikely(!cp)) {
		if (sysctl_ip_vs_nat_icmp_send &&
		    (pp->protocol == IPPROTO_TCP ||
		     pp->protocol == IPPROTO_UDP)) {
			__u16 _ports[2], *pptr;

			pptr = skb_header_pointer(skb, ihl,
						  sizeof(_ports), _ports);
			if (pptr == NULL)
				return NF_ACCEPT;	/* Not for me */
			if (ip_vs_lookup_real_service(iph->protocol,
						      iph->saddr, pptr[0])) {
				/*
				 * Notify the real server: there is no
				 * existing entry if it is not RST
				 * packet or not TCP packet.
				 */
				if (iph->protocol != IPPROTO_TCP
				    || !is_tcp_reset(skb)) {
					icmp_send(skb,ICMP_DEST_UNREACH,
						  ICMP_PORT_UNREACH, 0);
					return NF_DROP;
				}
			}
		}
		IP_VS_DBG_PKT(12, pp, skb, 0,
			      "packet continues traversal as normal");
		return NF_ACCEPT;
	}

	IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet");

	if (!ip_vs_make_skb_writable(pskb, ihl))
		goto drop;

	/* mangle the packet */
	if (pp->snat_handler && !pp->snat_handler(pskb, pp, cp))
		goto drop;
	skb = *pskb;
	skb->nh.iph->saddr = cp->vaddr;
	ip_send_check(skb->nh.iph);

	IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");

	ip_vs_out_stats(cp, skb);
	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
	ip_vs_conn_put(cp);

	skb->ipvs_property = 1;

	LeaveFunction(11);
	return NF_ACCEPT;

  drop:
	ip_vs_conn_put(cp);
	kfree_skb(*pskb);
	return NF_STOLEN;
}


/*
 *	Handle ICMP messages in the outside-to-inside direction (incoming).
 *	Find any that might be relevant, check against existing connections,
 *	forward to the right destination host if relevant.
 *	Currently handles error types - unreachable, quench, ttl exceeded.
 */
static int 
ip_vs_in_icmp(struct sk_buff **pskb, int *related, unsigned int hooknum)
{
	struct sk_buff *skb = *pskb;
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	unsigned int offset, ihl, verdict;

	*related = 1;

	/* reassemble IP fragments */
	if (skb->nh.iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) {
		skb = ip_vs_gather_frags(skb,
		                         hooknum == NF_IP_LOCAL_IN ?
					 IP_DEFRAG_VS_IN : IP_DEFRAG_VS_FWD);
		if (!skb)
			return NF_STOLEN;
		*pskb = skb;
	}

	iph = skb->nh.iph;
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Incoming ICMP (%d,%d) %u.%u.%u.%u->%u.%u.%u.%u\n",
		  ic->type, ntohs(icmp_id(ic)),
		  NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	pp = ip_vs_proto_get(cih->protocol);
	if (!pp)
		return NF_ACCEPT;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & __constant_htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMP for");

	offset += cih->ihl * 4;

	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_in_get(skb, pp, cih, offset, 1);
	if (!cp)
		return NF_ACCEPT;

	verdict = NF_DROP;

	/* Ensure the checksum is correct */
	if (skb->ip_summed != CHECKSUM_UNNECESSARY &&
	    ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %d.%d.%d.%d!\n",
			  NIPQUAD(iph->saddr));
		goto out;
	}

	/* do the statistics and put it back */
	ip_vs_in_stats(cp, skb);
	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
		offset += 2 * sizeof(__u16);
	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset);
	/* do not touch skb anymore */

  out:
	__ip_vs_conn_put(cp);

	return verdict;
}

/*
 *	Check if it's for virtual services, look it up,
 *	and send it on its way...
 */
static unsigned int
ip_vs_in(unsigned int hooknum, struct sk_buff **pskb,
	 const struct net_device *in, const struct net_device *out,
	 int (*okfn)(struct sk_buff *))
{
	struct sk_buff	*skb = *pskb;
	struct iphdr	*iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_conn *cp;
	int ret, restart;
	int ihl;

	/*
	 *	Big tappo: only PACKET_HOST (neither loopback nor mcasts)
	 *	... don't know why 1st test DOES NOT include 2nd (?)
	 */
	if (unlikely(skb->pkt_type != PACKET_HOST
		     || skb->dev == &loopback_dev || skb->sk)) {
		IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n",
			  skb->pkt_type,
			  skb->nh.iph->protocol,
			  NIPQUAD(skb->nh.iph->daddr));
		return NF_ACCEPT;
	}

	iph = skb->nh.iph;
	if (unlikely(iph->protocol == IPPROTO_ICMP)) {
		int related, verdict = ip_vs_in_icmp(pskb, &related, hooknum);

		if (related)
			return verdict;
		skb = *pskb;
		iph = skb->nh.iph;
	}

	/* Protocol supported? */
	pp = ip_vs_proto_get(iph->protocol);
	if (unlikely(!pp))
		return NF_ACCEPT;

	ihl = iph->ihl << 2;

	/*
	 * Check if the packet belongs to an existing connection entry
	 */
	cp = pp->conn_in_get(skb, pp, iph, ihl, 0);

	if (unlikely(!cp)) {
		int v;

		if (!pp->conn_schedule(skb, pp, &v, &cp))
			return v;
	}

	if (unlikely(!cp)) {
		/* sorry, all this trouble for a no-hit :) */
		IP_VS_DBG_PKT(12, pp, skb, 0,
			      "packet continues traversal as normal");
		return NF_ACCEPT;
	}

	IP_VS_DBG_PKT(11, pp, skb, 0, "Incoming packet");

	/* Check the server status */
	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		/* the destination server is not available */

		if (sysctl_ip_vs_expire_nodest_conn) {
			/* try to expire the connection immediately */
			ip_vs_conn_expire_now(cp);
		} else {
			/* don't restart its timer, and silently
			   drop the packet. */
			__ip_vs_conn_put(cp);
		}
		return NF_DROP;
	}

	ip_vs_in_stats(cp, skb);
	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
	if (cp->packet_xmit)
		ret = cp->packet_xmit(skb, cp, pp);
		/* do not touch skb anymore */
	else {
		IP_VS_DBG_RL("warning: packet_xmit is null");
		ret = NF_ACCEPT;
	}

	/* increase its packet counter and check if it is needed
	   to be synchronized */
	atomic_inc(&cp->in_pkts);
	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
	    (cp->protocol != IPPROTO_TCP ||
	     cp->state == IP_VS_TCP_S_ESTABLISHED) &&
	    (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
	     == sysctl_ip_vs_sync_threshold[0]))
		ip_vs_sync_conn(cp);

	ip_vs_conn_put(cp);
	return ret;
}


/*
 *	It is hooked at the NF_IP_FORWARD chain, in order to catch ICMP
 *      related packets destined for 0.0.0.0/0.
 *      When fwmark-based virtual service is used, such as transparent
 *      cache cluster, TCP packets can be marked and routed to ip_vs_in,
 *      but ICMP destined for 0.0.0.0/0 cannot not be easily marked and
 *      sent to ip_vs_in_icmp. So, catch them at the NF_IP_FORWARD chain
 *      and send them to ip_vs_in_icmp.
 */
static unsigned int
ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff **pskb,
		   const struct net_device *in, const struct net_device *out,
		   int (*okfn)(struct sk_buff *))
{
	int r;

	if ((*pskb)->nh.iph->protocol != IPPROTO_ICMP)
		return NF_ACCEPT;

	return ip_vs_in_icmp(pskb, &r, hooknum);
}


/* After packet filtering, forward packet through VS/DR, VS/TUN,
   or VS/NAT(change destination), so that filtering rules can be
   applied to IPVS. */
static struct nf_hook_ops ip_vs_in_ops = {
	.hook		= ip_vs_in,
	.owner		= THIS_MODULE,
	.pf		= PF_INET,
	.hooknum        = NF_IP_LOCAL_IN,
	.priority       = 100,
};

/* After packet filtering, change source only for VS/NAT */
static struct nf_hook_ops ip_vs_out_ops = {
	.hook		= ip_vs_out,
	.owner		= THIS_MODULE,
	.pf		= PF_INET,
	.hooknum        = NF_IP_FORWARD,
	.priority       = 100,
};

/* After packet filtering (but before ip_vs_out_icmp), catch icmp
   destined for 0.0.0.0/0, which is for incoming IPVS connections */
static struct nf_hook_ops ip_vs_forward_icmp_ops = {
	.hook		= ip_vs_forward_icmp,
	.owner		= THIS_MODULE,
	.pf		= PF_INET,
	.hooknum        = NF_IP_FORWARD,
	.priority       = 99,
};

/* Before the netfilter connection tracking, exit from POST_ROUTING */
static struct nf_hook_ops ip_vs_post_routing_ops = {
	.hook		= ip_vs_post_routing,
	.owner		= THIS_MODULE,
	.pf		= PF_INET,
	.hooknum        = NF_IP_POST_ROUTING,
	.priority       = NF_IP_PRI_NAT_SRC-1,
};


/*
 *	Initialize IP Virtual Server
 */
static int __init ip_vs_init(void)
{
	int ret;

	ret = ip_vs_control_init();
	if (ret < 0) {
		IP_VS_ERR("can't setup control.\n");
		goto cleanup_nothing;
	}

	ip_vs_protocol_init();

	ret = ip_vs_app_init();
	if (ret < 0) {
		IP_VS_ERR("can't setup application helper.\n");
		goto cleanup_protocol;
	}

	ret = ip_vs_conn_init();
	if (ret < 0) {
		IP_VS_ERR("can't setup connection table.\n");
		goto cleanup_app;
	}

	ret = nf_register_hook(&ip_vs_in_ops);
	if (ret < 0) {
		IP_VS_ERR("can't register in hook.\n");
		goto cleanup_conn;
	}

	ret = nf_register_hook(&ip_vs_out_ops);
	if (ret < 0) {
		IP_VS_ERR("can't register out hook.\n");
		goto cleanup_inops;
	}
	ret = nf_register_hook(&ip_vs_post_routing_ops);
	if (ret < 0) {
		IP_VS_ERR("can't register post_routing hook.\n");
		goto cleanup_outops;
	}
	ret = nf_register_hook(&ip_vs_forward_icmp_ops);
	if (ret < 0) {
		IP_VS_ERR("can't register forward_icmp hook.\n");
		goto cleanup_postroutingops;
	}

	IP_VS_INFO("ipvs loaded.\n");
	return ret;

  cleanup_postroutingops:
	nf_unregister_hook(&ip_vs_post_routing_ops);
  cleanup_outops:
	nf_unregister_hook(&ip_vs_out_ops);
  cleanup_inops:
	nf_unregister_hook(&ip_vs_in_ops);
  cleanup_conn:
	ip_vs_conn_cleanup();
  cleanup_app:
	ip_vs_app_cleanup();
  cleanup_protocol:
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
  cleanup_nothing:
	return ret;
}

static void __exit ip_vs_cleanup(void)
{
	nf_unregister_hook(&ip_vs_forward_icmp_ops);
	nf_unregister_hook(&ip_vs_post_routing_ops);
	nf_unregister_hook(&ip_vs_out_ops);
	nf_unregister_hook(&ip_vs_in_ops);
	ip_vs_conn_cleanup();
	ip_vs_app_cleanup();
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
	IP_VS_INFO("ipvs unloaded.\n");
}

module_init(ip_vs_init);
module_exit(ip_vs_cleanup);
MODULE_LICENSE("GPL");