aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter/ipvs/ip_vs_xmit.c
blob: bf66a8657a5f7c7e1a2d3adbde3a05245c598249 (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
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
/*
 * ip_vs_xmit.c: various packet transmitters 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:
 *
 * Description of forwarding methods:
 * - all transmitters are called from LOCAL_IN (remote clients) and
 * LOCAL_OUT (local clients) but for ICMP can be called from FORWARD
 * - not all connections have destination server, for example,
 * connections in backup server when fwmark is used
 * - bypass connections use daddr from packet
 * - we can use dst without ref while sending in RCU section, we use
 * ref when returning NF_ACCEPT for NAT-ed packet via loopback
 * LOCAL_OUT rules:
 * - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING)
 * - skb->pkt_type is not set yet
 * - the only place where we can see skb->sk != NULL
 */

#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/tcp.h>                  /* for tcphdr */
#include <net/ip.h>
#include <net/tcp.h>                    /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h>                   /* for icmp_send */
#include <net/route.h>                  /* for ip_route_output */
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/ip_tunnels.h>
#include <net/addrconf.h>
#include <linux/icmpv6.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#include <net/ip_vs.h>

enum {
	IP_VS_RT_MODE_LOCAL	= 1, /* Allow local dest */
	IP_VS_RT_MODE_NON_LOCAL	= 2, /* Allow non-local dest */
	IP_VS_RT_MODE_RDR	= 4, /* Allow redirect from remote daddr to
				      * local
				      */
	IP_VS_RT_MODE_CONNECT	= 8, /* Always bind route to saddr */
	IP_VS_RT_MODE_KNOWN_NH	= 16,/* Route via remote addr */
	IP_VS_RT_MODE_TUNNEL	= 32,/* Tunnel mode */
};

static inline struct ip_vs_dest_dst *ip_vs_dest_dst_alloc(void)
{
	return kmalloc(sizeof(struct ip_vs_dest_dst), GFP_ATOMIC);
}

static inline void ip_vs_dest_dst_free(struct ip_vs_dest_dst *dest_dst)
{
	kfree(dest_dst);
}

/*
 *      Destination cache to speed up outgoing route lookup
 */
static inline void
__ip_vs_dst_set(struct ip_vs_dest *dest, struct ip_vs_dest_dst *dest_dst,
		struct dst_entry *dst, u32 dst_cookie)
{
	struct ip_vs_dest_dst *old;

	old = rcu_dereference_protected(dest->dest_dst,
					lockdep_is_held(&dest->dst_lock));

	if (dest_dst) {
		dest_dst->dst_cache = dst;
		dest_dst->dst_cookie = dst_cookie;
	}
	rcu_assign_pointer(dest->dest_dst, dest_dst);

	if (old)
		call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
}

static inline struct ip_vs_dest_dst *
__ip_vs_dst_check(struct ip_vs_dest *dest)
{
	struct ip_vs_dest_dst *dest_dst = rcu_dereference(dest->dest_dst);
	struct dst_entry *dst;

	if (!dest_dst)
		return NULL;
	dst = dest_dst->dst_cache;
	if (dst->obsolete &&
	    dst->ops->check(dst, dest_dst->dst_cookie) == NULL)
		return NULL;
	return dest_dst;
}

static inline bool
__mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
{
	if (IP6CB(skb)->frag_max_size) {
		/* frag_max_size tell us that, this packet have been
		 * defragmented by netfilter IPv6 conntrack module.
		 */
		if (IP6CB(skb)->frag_max_size > mtu)
			return true; /* largest fragment violate MTU */
	}
	else if (skb->len > mtu && !skb_is_gso(skb)) {
		return true; /* Packet size violate MTU size */
	}
	return false;
}

/* Get route to daddr, update *saddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
				       int rt_mode, __be32 *saddr)
{
	struct flowi4 fl4;
	struct rtable *rt;
	int loop = 0;

	memset(&fl4, 0, sizeof(fl4));
	fl4.daddr = daddr;
	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
			   FLOWI_FLAG_KNOWN_NH : 0;

retry:
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt)) {
		/* Invalid saddr ? */
		if (PTR_ERR(rt) == -EINVAL && *saddr &&
		    rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
			*saddr = 0;
			flowi4_update_output(&fl4, 0, 0, daddr, 0);
			goto retry;
		}
		IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
		return NULL;
	} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
		ip_rt_put(rt);
		*saddr = fl4.saddr;
		flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
		loop++;
		goto retry;
	}
	*saddr = fl4.saddr;
	return rt;
}

#ifdef CONFIG_IP_VS_IPV6
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
	return rt->dst.dev && rt->dst.dev->flags & IFF_LOOPBACK;
}
#endif

static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb,
						int rt_mode,
						bool new_rt_is_local)
{
	bool rt_mode_allow_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
	bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
	bool rt_mode_allow_redirect = !!(rt_mode & IP_VS_RT_MODE_RDR);
	bool source_is_loopback;
	bool old_rt_is_local;

#ifdef CONFIG_IP_VS_IPV6
	if (skb_af == AF_INET6) {
		int addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr);

		source_is_loopback =
			(!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
			(addr_type & IPV6_ADDR_LOOPBACK);
		old_rt_is_local = __ip_vs_is_local_route6(
			(struct rt6_info *)skb_dst(skb));
	} else
#endif
	{
		source_is_loopback = ipv4_is_loopback(ip_hdr(skb)->saddr);
		old_rt_is_local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
	}

	if (unlikely(new_rt_is_local)) {
		if (!rt_mode_allow_local)
			return true;
		if (!rt_mode_allow_redirect && !old_rt_is_local)
			return true;
	} else {
		if (!rt_mode_allow_non_local)
			return true;
		if (source_is_loopback)
			return true;
	}
	return false;
}

static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
{
	struct sock *sk = skb->sk;
	struct rtable *ort = skb_rtable(skb);

	if (!skb->dev && sk && sk_fullsock(sk))
		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}

static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
					  struct ip_vs_iphdr *ipvsh,
					  struct sk_buff *skb, int mtu)
{
#ifdef CONFIG_IP_VS_IPV6
	if (skb_af == AF_INET6) {
		struct net *net = dev_net(skb_dst(skb)->dev);

		if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
			if (!skb->dev)
				skb->dev = net->loopback_dev;
			/* only send ICMP too big on first fragment */
			if (!ipvsh->fragoffs)
				icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
			IP_VS_DBG(1, "frag needed for %pI6c\n",
				  &ipv6_hdr(skb)->saddr);
			return false;
		}
	} else
#endif
	{
		struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));

		/* If we're going to tunnel the packet and pmtu discovery
		 * is disabled, we'll just fragment it anyway
		 */
		if ((rt_mode & IP_VS_RT_MODE_TUNNEL) && !sysctl_pmtu_disc(ipvs))
			return true;

		if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) &&
			     skb->len > mtu && !skb_is_gso(skb))) {
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));
			IP_VS_DBG(1, "frag needed for %pI4\n",
				  &ip_hdr(skb)->saddr);
			return false;
		}
	}

	return true;
}

/* Get route to destination or remote server */
static int
__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
		   __be32 daddr, int rt_mode, __be32 *ret_saddr,
		   struct ip_vs_iphdr *ipvsh)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	struct ip_vs_dest_dst *dest_dst;
	struct rtable *rt;			/* Route to the other host */
	int mtu;
	int local, noref = 1;

	if (dest) {
		dest_dst = __ip_vs_dst_check(dest);
		if (likely(dest_dst))
			rt = (struct rtable *) dest_dst->dst_cache;
		else {
			dest_dst = ip_vs_dest_dst_alloc();
			spin_lock_bh(&dest->dst_lock);
			if (!dest_dst) {
				__ip_vs_dst_set(dest, NULL, NULL, 0);
				spin_unlock_bh(&dest->dst_lock);
				goto err_unreach;
			}
			rt = do_output_route4(net, dest->addr.ip, rt_mode,
					      &dest_dst->dst_saddr.ip);
			if (!rt) {
				__ip_vs_dst_set(dest, NULL, NULL, 0);
				spin_unlock_bh(&dest->dst_lock);
				ip_vs_dest_dst_free(dest_dst);
				goto err_unreach;
			}
			__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
			spin_unlock_bh(&dest->dst_lock);
			IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
				  &dest->addr.ip, &dest_dst->dst_saddr.ip,
				  atomic_read(&rt->dst.__refcnt));
		}
		if (ret_saddr)
			*ret_saddr = dest_dst->dst_saddr.ip;
	} else {
		__be32 saddr = htonl(INADDR_ANY);

		noref = 0;

		/* For such unconfigured boxes avoid many route lookups
		 * for performance reasons because we do not remember saddr
		 */
		rt_mode &= ~IP_VS_RT_MODE_CONNECT;
		rt = do_output_route4(net, daddr, rt_mode, &saddr);
		if (!rt)
			goto err_unreach;
		if (ret_saddr)
			*ret_saddr = saddr;
	}

	local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
	if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
						  local))) {
		IP_VS_DBG_RL("We are crossing local and non-local addresses"
			     " daddr=%pI4\n", &daddr);
		goto err_put;
	}

	if (unlikely(local)) {
		/* skb to local stack, preserve old route */
		if (!noref)
			ip_rt_put(rt);
		return local;
	}

	if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
		mtu = dst_mtu(&rt->dst);
	} else {
		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
		if (mtu < 68) {
			IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
			goto err_put;
		}
		maybe_update_pmtu(skb_af, skb, mtu);
	}

	if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
		goto err_put;

	skb_dst_drop(skb);
	if (noref) {
		if (!local)
			skb_dst_set_noref(skb, &rt->dst);
		else
			skb_dst_set(skb, dst_clone(&rt->dst));
	} else
		skb_dst_set(skb, &rt->dst);

	return local;

err_put:
	if (!noref)
		ip_rt_put(rt);
	return -1;

err_unreach:
	dst_link_failure(skb);
	return -1;
}

#ifdef CONFIG_IP_VS_IPV6
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
			struct in6_addr *ret_saddr, int do_xfrm, int rt_mode)
{
	struct dst_entry *dst;
	struct flowi6 fl6 = {
		.daddr = *daddr,
	};

	if (rt_mode & IP_VS_RT_MODE_KNOWN_NH)
		fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;

	dst = ip6_route_output(net, NULL, &fl6);
	if (dst->error)
		goto out_err;
	if (!ret_saddr)
		return dst;
	if (ipv6_addr_any(&fl6.saddr) &&
	    ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
			       &fl6.daddr, 0, &fl6.saddr) < 0)
		goto out_err;
	if (do_xfrm) {
		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
		if (IS_ERR(dst)) {
			dst = NULL;
			goto out_err;
		}
	}
	*ret_saddr = fl6.saddr;
	return dst;

out_err:
	dst_release(dst);
	IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
	return NULL;
}

/*
 * Get route to destination or remote server
 */
static int
__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
		      struct in6_addr *daddr, struct in6_addr *ret_saddr,
		      struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	struct ip_vs_dest_dst *dest_dst;
	struct rt6_info *rt;			/* Route to the other host */
	struct dst_entry *dst;
	int mtu;
	int local, noref = 1;

	if (dest) {
		dest_dst = __ip_vs_dst_check(dest);
		if (likely(dest_dst))
			rt = (struct rt6_info *) dest_dst->dst_cache;
		else {
			u32 cookie;

			dest_dst = ip_vs_dest_dst_alloc();
			spin_lock_bh(&dest->dst_lock);
			if (!dest_dst) {
				__ip_vs_dst_set(dest, NULL, NULL, 0);
				spin_unlock_bh(&dest->dst_lock);
				goto err_unreach;
			}
			dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
						      &dest_dst->dst_saddr.in6,
						      do_xfrm, rt_mode);
			if (!dst) {
				__ip_vs_dst_set(dest, NULL, NULL, 0);
				spin_unlock_bh(&dest->dst_lock);
				ip_vs_dest_dst_free(dest_dst);
				goto err_unreach;
			}
			rt = (struct rt6_info *) dst;
			cookie = rt6_get_cookie(rt);
			__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
			spin_unlock_bh(&dest->dst_lock);
			IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
				  &dest->addr.in6, &dest_dst->dst_saddr.in6,
				  atomic_read(&rt->dst.__refcnt));
		}
		if (ret_saddr)
			*ret_saddr = dest_dst->dst_saddr.in6;
	} else {
		noref = 0;
		dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm,
					      rt_mode);
		if (!dst)
			goto err_unreach;
		rt = (struct rt6_info *) dst;
	}

	local = __ip_vs_is_local_route6(rt);

	if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
						  local))) {
		IP_VS_DBG_RL("We are crossing local and non-local addresses"
			     " daddr=%pI6\n", daddr);
		goto err_put;
	}

	if (unlikely(local)) {
		/* skb to local stack, preserve old route */
		if (!noref)
			dst_release(&rt->dst);
		return local;
	}

	/* MTU checking */
	if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL)))
		mtu = dst_mtu(&rt->dst);
	else {
		mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
		if (mtu < IPV6_MIN_MTU) {
			IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
				     IPV6_MIN_MTU);
			goto err_put;
		}
		maybe_update_pmtu(skb_af, skb, mtu);
	}

	if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
		goto err_put;

	skb_dst_drop(skb);
	if (noref) {
		if (!local)
			skb_dst_set_noref(skb, &rt->dst);
		else
			skb_dst_set(skb, dst_clone(&rt->dst));
	} else
		skb_dst_set(skb, &rt->dst);

	return local;

err_put:
	if (!noref)
		dst_release(&rt->dst);
	return -1;

err_unreach:
	dst_link_failure(skb);
	return -1;
}
#endif


/* return NF_ACCEPT to allow forwarding or other NF_xxx on error */
static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
					    struct ip_vs_conn *cp)
{
	int ret = NF_ACCEPT;

	skb->ipvs_property = 1;
	if (unlikely(cp->flags & IP_VS_CONN_F_NFCT))
		ret = ip_vs_confirm_conntrack(skb);
	if (ret == NF_ACCEPT) {
		nf_reset(skb);
		skb_forward_csum(skb);
	}
	return ret;
}

/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
					 struct ip_vs_conn *cp, int local)
{
	int ret = NF_STOLEN;

	skb->ipvs_property = 1;
	if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
		ip_vs_notrack(skb);
	else
		ip_vs_update_conntrack(skb, cp, 1);
	if (!local) {
		skb_forward_csum(skb);
		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
			NULL, skb_dst(skb)->dev, dst_output_sk);
	} else
		ret = NF_ACCEPT;
	return ret;
}

/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
				     struct ip_vs_conn *cp, int local)
{
	int ret = NF_STOLEN;

	skb->ipvs_property = 1;
	if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
		ip_vs_notrack(skb);
	if (!local) {
		skb_forward_csum(skb);
		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
			NULL, skb_dst(skb)->dev, dst_output_sk);
	} else
		ret = NF_ACCEPT;
	return ret;
}


/*
 *      NULL transmitter (do nothing except return NF_ACCEPT)
 */
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	/* we do not touch skb and do not need pskb ptr */
	return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}


/*
 *      Bypass transmitter
 *      Let packets bypass the destination when the destination is not
 *      available, it may be only used in transparent cache cluster.
 */
int
ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	struct iphdr  *iph = ip_hdr(skb);

	EnterFunction(10);

	rcu_read_lock();
	if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr,
			       IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0)
		goto tx_error;

	ip_send_check(iph);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
	rcu_read_unlock();

	LeaveFunction(10);
	return NF_STOLEN;

 tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}

#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	EnterFunction(10);

	rcu_read_lock();
	if (__ip_vs_get_out_rt_v6(cp->af, skb, NULL, &ipvsh->daddr.in6, NULL,
				  ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
		goto tx_error;

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
	rcu_read_unlock();

	LeaveFunction(10);
	return NF_STOLEN;

 tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}
#endif

/*
 *      NAT transmitter (only for outside-to-inside nat forwarding)
 *      Not used for related ICMP
 */
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	       struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	struct rtable *rt;		/* Route to the other host */
	int local, rc, was_input;

	EnterFunction(10);

	rcu_read_lock();
	/* check if it is a connection of no-client-port */
	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
		__be16 _pt, *p;

		p = skb_header_pointer(skb, ipvsh->len, sizeof(_pt), &_pt);
		if (p == NULL)
			goto tx_error;
		ip_vs_conn_fill_cport(cp, *p);
		IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
	}

	was_input = rt_is_input_route(skb_rtable(skb));
	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
				   IP_VS_RT_MODE_LOCAL |
				   IP_VS_RT_MODE_NON_LOCAL |
				   IP_VS_RT_MODE_RDR, NULL, ipvsh);
	if (local < 0)
		goto tx_error;
	rt = skb_rtable(skb);
	/*
	 * Avoid duplicate tuple in reply direction for NAT traffic
	 * to local address when connection is sync-ed
	 */
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
		enum ip_conntrack_info ctinfo;
		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);

		if (ct && !nf_ct_is_untracked(ct)) {
			IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
					 "ip_vs_nat_xmit(): "
					 "stopping DNAT to local address");
			goto tx_error;
		}
	}
#endif

	/* From world but DNAT to loopback address? */
	if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
		IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
				 "stopping DNAT to loopback address");
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!skb_make_writable(skb, sizeof(struct iphdr)))
		goto tx_error;

	if (skb_cow(skb, rt->dst.dev->hard_header_len))
		goto tx_error;

	/* mangle the packet */
	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
		goto tx_error;
	ip_hdr(skb)->daddr = cp->daddr.ip;
	ip_send_check(ip_hdr(skb));

	IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");

	/* FIXME: when application helper enlarges the packet and the length
	   is larger than the MTU of outgoing device, there will be still
	   MTU problem. */

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
	rcu_read_unlock();

	LeaveFunction(10);
	return rc;

  tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}

#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	struct rt6_info *rt;		/* Route to the other host */
	int local, rc;

	EnterFunction(10);

	rcu_read_lock();
	/* check if it is a connection of no-client-port */
	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) {
		__be16 _pt, *p;
		p = skb_header_pointer(skb, ipvsh->len, sizeof(_pt), &_pt);
		if (p == NULL)
			goto tx_error;
		ip_vs_conn_fill_cport(cp, *p);
		IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
	}

	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
				      NULL, ipvsh, 0,
				      IP_VS_RT_MODE_LOCAL |
				      IP_VS_RT_MODE_NON_LOCAL |
				      IP_VS_RT_MODE_RDR);
	if (local < 0)
		goto tx_error;
	rt = (struct rt6_info *) skb_dst(skb);
	/*
	 * Avoid duplicate tuple in reply direction for NAT traffic
	 * to local address when connection is sync-ed
	 */
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
		enum ip_conntrack_info ctinfo;
		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);

		if (ct && !nf_ct_is_untracked(ct)) {
			IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
					 "ip_vs_nat_xmit_v6(): "
					 "stopping DNAT to local address");
			goto tx_error;
		}
	}
#endif

	/* From world but DNAT to loopback address? */
	if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
	    ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
		IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
				 "ip_vs_nat_xmit_v6(): "
				 "stopping DNAT to loopback address");
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
		goto tx_error;

	if (skb_cow(skb, rt->dst.dev->hard_header_len))
		goto tx_error;

	/* mangle the packet */
	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
		goto tx_error;
	ipv6_hdr(skb)->daddr = cp->daddr.in6;

	IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");

	/* FIXME: when application helper enlarges the packet and the length
	   is larger than the MTU of outgoing device, there will be still
	   MTU problem. */

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
	rcu_read_unlock();

	LeaveFunction(10);
	return rc;

tx_error:
	LeaveFunction(10);
	kfree_skb(skb);
	rcu_read_unlock();
	return NF_STOLEN;
}
#endif

/* When forwarding a packet, we must ensure that we've got enough headroom
 * for the encapsulation packet in the skb.  This also gives us an
 * opportunity to figure out what the payload_len, dsfield, ttl, and df
 * values should be, so that we won't need to look at the old ip header
 * again
 */
static struct sk_buff *
ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
			   unsigned int max_headroom, __u8 *next_protocol,
			   __u32 *payload_len, __u8 *dsfield, __u8 *ttl,
			   __be16 *df)
{
	struct sk_buff *new_skb = NULL;
	struct iphdr *old_iph = NULL;
#ifdef CONFIG_IP_VS_IPV6
	struct ipv6hdr *old_ipv6h = NULL;
#endif

	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
		new_skb = skb_realloc_headroom(skb, max_headroom);
		if (!new_skb)
			goto error;
		if (skb->sk)
			skb_set_owner_w(new_skb, skb->sk);
		consume_skb(skb);
		skb = new_skb;
	}

#ifdef CONFIG_IP_VS_IPV6
	if (skb_af == AF_INET6) {
		old_ipv6h = ipv6_hdr(skb);
		*next_protocol = IPPROTO_IPV6;
		if (payload_len)
			*payload_len =
				ntohs(old_ipv6h->payload_len) +
				sizeof(*old_ipv6h);
		*dsfield = ipv6_get_dsfield(old_ipv6h);
		*ttl = old_ipv6h->hop_limit;
		if (df)
			*df = 0;
	} else
#endif
	{
		old_iph = ip_hdr(skb);
		/* Copy DF, reset fragment offset and MF */
		if (df)
			*df = (old_iph->frag_off & htons(IP_DF));
		*next_protocol = IPPROTO_IPIP;

		/* fix old IP header checksum */
		ip_send_check(old_iph);
		*dsfield = ipv4_get_dsfield(old_iph);
		*ttl = old_iph->ttl;
		if (payload_len)
			*payload_len = ntohs(old_iph->tot_len);
	}

	return skb;
error:
	kfree_skb(skb);
	return ERR_PTR(-ENOMEM);
}

static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
{
	if (encaps_af == AF_INET) {
		if (orig_af == AF_INET)
			return SKB_GSO_IPIP;

		return SKB_GSO_SIT;
	}

	/* GSO: we need to provide proper SKB_GSO_ value for IPv6:
	 * SKB_GSO_SIT/IPV6
	 */
	return 0;
}

/*
 *   IP Tunneling transmitter
 *
 *   This function encapsulates the packet in a new IP packet, its
 *   destination will be set to cp->daddr. Most code of this function
 *   is taken from ipip.c.
 *
 *   It is used in VS/TUN cluster. The load balancer selects a real
 *   server from a cluster based on a scheduling algorithm,
 *   encapsulates the request packet and forwards it to the selected
 *   server. For example, all real servers are configured with
 *   "ifconfig tunl0 <Virtual IP Address> up". When the server receives
 *   the encapsulated packet, it will decapsulate the packet, processe
 *   the request and return the response packets directly to the client
 *   without passing the load balancer. This can greatly increase the
 *   scalability of virtual server.
 *
 *   Used for ANY protocol
 */
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	struct net *net = skb_net(skb);
	struct netns_ipvs *ipvs = net_ipvs(net);
	struct rtable *rt;			/* Route to the other host */
	__be32 saddr;				/* Source for tunnel */
	struct net_device *tdev;		/* Device to other host */
	__u8 next_protocol = 0;
	__u8 dsfield = 0;
	__u8 ttl = 0;
	__be16 df = 0;
	__be16 *dfp = NULL;
	struct iphdr  *iph;			/* Our new IP header */
	unsigned int max_headroom;		/* The extra header space needed */
	int ret, local;

	EnterFunction(10);

	rcu_read_lock();
	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
				   IP_VS_RT_MODE_LOCAL |
				   IP_VS_RT_MODE_NON_LOCAL |
				   IP_VS_RT_MODE_CONNECT |
				   IP_VS_RT_MODE_TUNNEL, &saddr, ipvsh);
	if (local < 0)
		goto tx_error;
	if (local) {
		rcu_read_unlock();
		return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
	}

	rt = skb_rtable(skb);
	tdev = rt->dst.dev;

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);

	/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
	dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
					 &next_protocol, NULL, &dsfield,
					 &ttl, dfp);
	if (IS_ERR(skb))
		goto tx_error;

	skb = iptunnel_handle_offloads(
		skb, false, __tun_gso_type_mask(AF_INET, cp->af));
	if (IS_ERR(skb))
		goto tx_error;

	skb->transport_header = skb->network_header;

	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));

	/*
	 *	Push down and install the IPIP header.
	 */
	iph			=	ip_hdr(skb);
	iph->version		=	4;
	iph->ihl		=	sizeof(struct iphdr)>>2;
	iph->frag_off		=	df;
	iph->protocol		=	next_protocol;
	iph->tos		=	dsfield;
	iph->daddr		=	cp->daddr.ip;
	iph->saddr		=	saddr;
	iph->ttl		=	ttl;
	ip_select_ident(net, skb, NULL);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
	if (ret == NF_ACCEPT)
		ip_local_out(skb);
	else if (ret == NF_DROP)
		kfree_skb(skb);
	rcu_read_unlock();

	LeaveFunction(10);

	return NF_STOLEN;

  tx_error:
	if (!IS_ERR(skb))
		kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}

#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	struct rt6_info *rt;		/* Route to the other host */
	struct in6_addr saddr;		/* Source for tunnel */
	struct net_device *tdev;	/* Device to other host */
	__u8 next_protocol = 0;
	__u32 payload_len = 0;
	__u8 dsfield = 0;
	__u8 ttl = 0;
	struct ipv6hdr  *iph;		/* Our new IP header */
	unsigned int max_headroom;	/* The extra header space needed */
	int ret, local;

	EnterFunction(10);

	rcu_read_lock();
	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
				      &saddr, ipvsh, 1,
				      IP_VS_RT_MODE_LOCAL |
				      IP_VS_RT_MODE_NON_LOCAL |
				      IP_VS_RT_MODE_TUNNEL);
	if (local < 0)
		goto tx_error;
	if (local) {
		rcu_read_unlock();
		return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
	}

	rt = (struct rt6_info *) skb_dst(skb);
	tdev = rt->dst.dev;

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);

	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
					 &next_protocol, &payload_len,
					 &dsfield, &ttl, NULL);
	if (IS_ERR(skb))
		goto tx_error;

	skb = iptunnel_handle_offloads(
		skb, false, __tun_gso_type_mask(AF_INET6, cp->af));
	if (IS_ERR(skb))
		goto tx_error;

	skb->transport_header = skb->network_header;

	skb_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));

	/*
	 *	Push down and install the IPIP header.
	 */
	iph			=	ipv6_hdr(skb);
	iph->version		=	6;
	iph->nexthdr		=	next_protocol;
	iph->payload_len	=	htons(payload_len);
	memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
	ipv6_change_dsfield(iph, 0, dsfield);
	iph->daddr = cp->daddr.in6;
	iph->saddr = saddr;
	iph->hop_limit		=	ttl;

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
	if (ret == NF_ACCEPT)
		ip6_local_out(skb);
	else if (ret == NF_DROP)
		kfree_skb(skb);
	rcu_read_unlock();

	LeaveFunction(10);

	return NF_STOLEN;

tx_error:
	if (!IS_ERR(skb))
		kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}
#endif


/*
 *      Direct Routing transmitter
 *      Used for ANY protocol
 */
int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	      struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	int local;

	EnterFunction(10);

	rcu_read_lock();
	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
				   IP_VS_RT_MODE_LOCAL |
				   IP_VS_RT_MODE_NON_LOCAL |
				   IP_VS_RT_MODE_KNOWN_NH, NULL, ipvsh);
	if (local < 0)
		goto tx_error;
	if (local) {
		rcu_read_unlock();
		return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
	}

	ip_send_check(ip_hdr(skb));

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
	rcu_read_unlock();

	LeaveFunction(10);
	return NF_STOLEN;

  tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}

#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		 struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
	int local;

	EnterFunction(10);

	rcu_read_lock();
	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
				      NULL, ipvsh, 0,
				      IP_VS_RT_MODE_LOCAL |
				      IP_VS_RT_MODE_NON_LOCAL |
				      IP_VS_RT_MODE_KNOWN_NH);
	if (local < 0)
		goto tx_error;
	if (local) {
		rcu_read_unlock();
		return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
	}

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
	rcu_read_unlock();

	LeaveFunction(10);
	return NF_STOLEN;

tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	LeaveFunction(10);
	return NF_STOLEN;
}
#endif


/*
 *	ICMP packet transmitter
 *	called by the ip_vs_in_icmp
 */
int
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
		struct ip_vs_iphdr *iph)
{
	struct rtable	*rt;	/* Route to the other host */
	int rc;
	int local;
	int rt_mode, was_input;

	EnterFunction(10);

	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
	   forwarded directly here, because there is no need to
	   translate address/port back */
	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
		if (cp->packet_xmit)
			rc = cp->packet_xmit(skb, cp, pp, iph);
		else
			rc = NF_ACCEPT;
		/* do not touch skb anymore */
		atomic_inc(&cp->in_pkts);
		goto out;
	}

	/*
	 * mangle and send the packet here (only for VS/NAT)
	 */
	was_input = rt_is_input_route(skb_rtable(skb));

	/* LOCALNODE from FORWARD hook is not supported */
	rt_mode = (hooknum != NF_INET_FORWARD) ?
		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
	rcu_read_lock();
	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
				   NULL, iph);
	if (local < 0)
		goto tx_error;
	rt = skb_rtable(skb);

	/*
	 * Avoid duplicate tuple in reply direction for NAT traffic
	 * to local address when connection is sync-ed
	 */
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
		enum ip_conntrack_info ctinfo;
		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);

		if (ct && !nf_ct_is_untracked(ct)) {
			IP_VS_DBG(10, "%s(): "
				  "stopping DNAT to local address %pI4\n",
				  __func__, &cp->daddr.ip);
			goto tx_error;
		}
	}
#endif

	/* From world but DNAT to loopback address? */
	if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
		IP_VS_DBG(1, "%s(): "
			  "stopping DNAT to loopback %pI4\n",
			  __func__, &cp->daddr.ip);
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!skb_make_writable(skb, offset))
		goto tx_error;

	if (skb_cow(skb, rt->dst.dev->hard_header_len))
		goto tx_error;

	ip_vs_nat_icmp(skb, pp, cp, 0);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
	rcu_read_unlock();
	goto out;

  tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	rc = NF_STOLEN;
  out:
	LeaveFunction(10);
	return rc;
}

#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
		struct ip_vs_iphdr *ipvsh)
{
	struct rt6_info	*rt;	/* Route to the other host */
	int rc;
	int local;
	int rt_mode;

	EnterFunction(10);

	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
	   forwarded directly here, because there is no need to
	   translate address/port back */
	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
		if (cp->packet_xmit)
			rc = cp->packet_xmit(skb, cp, pp, ipvsh);
		else
			rc = NF_ACCEPT;
		/* do not touch skb anymore */
		atomic_inc(&cp->in_pkts);
		goto out;
	}

	/*
	 * mangle and send the packet here (only for VS/NAT)
	 */

	/* LOCALNODE from FORWARD hook is not supported */
	rt_mode = (hooknum != NF_INET_FORWARD) ?
		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
	rcu_read_lock();
	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
				      NULL, ipvsh, 0, rt_mode);
	if (local < 0)
		goto tx_error;
	rt = (struct rt6_info *) skb_dst(skb);
	/*
	 * Avoid duplicate tuple in reply direction for NAT traffic
	 * to local address when connection is sync-ed
	 */
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
		enum ip_conntrack_info ctinfo;
		struct nf_conn *ct = nf_ct_get(skb, &ctinfo);

		if (ct && !nf_ct_is_untracked(ct)) {
			IP_VS_DBG(10, "%s(): "
				  "stopping DNAT to local address %pI6\n",
				  __func__, &cp->daddr.in6);
			goto tx_error;
		}
	}
#endif

	/* From world but DNAT to loopback address? */
	if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
	    ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
		IP_VS_DBG(1, "%s(): "
			  "stopping DNAT to loopback %pI6\n",
			  __func__, &cp->daddr.in6);
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!skb_make_writable(skb, offset))
		goto tx_error;

	if (skb_cow(skb, rt->dst.dev->hard_header_len))
		goto tx_error;

	ip_vs_nat_icmp_v6(skb, pp, cp, 0);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->ignore_df = 1;

	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
	rcu_read_unlock();
	goto out;

tx_error:
	kfree_skb(skb);
	rcu_read_unlock();
	rc = NF_STOLEN;
out:
	LeaveFunction(10);
	return rc;
}
#endif

Privacy Policy