summaryrefslogtreecommitdiffstats
path: root/net/ipv4/inet_hashtables.c
blob: 48d0d494185b19a5e7282ffb6b33051604c28c9f (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Generic INET transport hashtables
 *
 * Authors:	Lotsa people, from code originally in tcp
 */

#include <linux/module.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
#include <linux/memblock.h>

#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/inet6_hashtables.h>
#endif
#include <net/secure_seq.h>
#include <net/hotdata.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/sock_reuseport.h>

u32 inet_ehashfn(const struct net *net, const __be32 laddr,
		 const __u16 lport, const __be32 faddr,
		 const __be16 fport)
{
	net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));

	return __inet_ehashfn(laddr, lport, faddr, fport,
			      inet_ehash_secret + net_hash_mix(net));
}
EXPORT_SYMBOL_GPL(inet_ehashfn);

/* This function handles inet_sock, but also timewait and request sockets
 * for IPv4/IPv6.
 */
static u32 sk_ehashfn(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6 &&
	    !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
		return inet6_ehashfn(sock_net(sk),
				     &sk->sk_v6_rcv_saddr, sk->sk_num,
				     &sk->sk_v6_daddr, sk->sk_dport);
#endif
	return inet_ehashfn(sock_net(sk),
			    sk->sk_rcv_saddr, sk->sk_num,
			    sk->sk_daddr, sk->sk_dport);
}

/*
 * Allocate and initialize a new local port bind bucket.
 * The bindhash mutex for snum's hash chain must be held here.
 */
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
						 struct net *net,
						 struct inet_bind_hashbucket *head,
						 const unsigned short snum,
						 int l3mdev)
{
	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);

	if (tb) {
		write_pnet(&tb->ib_net, net);
		tb->l3mdev    = l3mdev;
		tb->port      = snum;
		tb->fastreuse = 0;
		tb->fastreuseport = 0;
		INIT_HLIST_HEAD(&tb->bhash2);
		hlist_add_head(&tb->node, &head->chain);
	}
	return tb;
}

/*
 * Caller must hold hashbucket lock for this tb with local BH disabled
 */
void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
{
	if (hlist_empty(&tb->bhash2)) {
		__hlist_del(&tb->node);
		kmem_cache_free(cachep, tb);
	}
}

bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net,
			    unsigned short port, int l3mdev)
{
	return net_eq(ib_net(tb), net) && tb->port == port &&
		tb->l3mdev == l3mdev;
}

static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
				   struct net *net,
				   struct inet_bind_hashbucket *head,
				   struct inet_bind_bucket *tb,
				   const struct sock *sk)
{
	write_pnet(&tb2->ib_net, net);
	tb2->l3mdev = tb->l3mdev;
	tb2->port = tb->port;
#if IS_ENABLED(CONFIG_IPV6)
	BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED));
	if (sk->sk_family == AF_INET6) {
		tb2->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
		tb2->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
	} else {
		tb2->addr_type = IPV6_ADDR_MAPPED;
		ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb2->v6_rcv_saddr);
	}
#else
	tb2->rcv_saddr = sk->sk_rcv_saddr;
#endif
	INIT_HLIST_HEAD(&tb2->owners);
	hlist_add_head(&tb2->node, &head->chain);
	hlist_add_head(&tb2->bhash_node, &tb->bhash2);
}

struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
						   struct net *net,
						   struct inet_bind_hashbucket *head,
						   struct inet_bind_bucket *tb,
						   const struct sock *sk)
{
	struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC);

	if (tb2)
		inet_bind2_bucket_init(tb2, net, head, tb, sk);

	return tb2;
}

/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
	if (hlist_empty(&tb->owners)) {
		__hlist_del(&tb->node);
		__hlist_del(&tb->bhash_node);
		kmem_cache_free(cachep, tb);
	}
}

static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
					 const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);

	if (tb2->addr_type != IPV6_ADDR_MAPPED)
		return false;
#endif
	return tb2->rcv_saddr == sk->sk_rcv_saddr;
}

void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
		    struct inet_bind2_bucket *tb2, unsigned short port)
{
	inet_sk(sk)->inet_num = port;
	inet_csk(sk)->icsk_bind_hash = tb;
	inet_csk(sk)->icsk_bind2_hash = tb2;
	sk_add_bind_node(sk, &tb2->owners);
}

/*
 * Get rid of any references to a local port held by the given sock.
 */
static void __inet_put_port(struct sock *sk)
{
	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
	struct inet_bind_hashbucket *head, *head2;
	struct net *net = sock_net(sk);
	struct inet_bind_bucket *tb;
	int bhash;

	bhash = inet_bhashfn(net, inet_sk(sk)->inet_num, hashinfo->bhash_size);
	head = &hashinfo->bhash[bhash];
	head2 = inet_bhashfn_portaddr(hashinfo, sk, net, inet_sk(sk)->inet_num);

	spin_lock(&head->lock);
	tb = inet_csk(sk)->icsk_bind_hash;
	inet_csk(sk)->icsk_bind_hash = NULL;
	inet_sk(sk)->inet_num = 0;

	spin_lock(&head2->lock);
	if (inet_csk(sk)->icsk_bind2_hash) {
		struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash;

		__sk_del_bind_node(sk);
		inet_csk(sk)->icsk_bind2_hash = NULL;
		inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
	}
	spin_unlock(&head2->lock);

	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
	spin_unlock(&head->lock);
}

void inet_put_port(struct sock *sk)
{
	local_bh_disable();
	__inet_put_port(sk);
	local_bh_enable();
}
EXPORT_SYMBOL(inet_put_port);

int __inet_inherit_port(const struct sock *sk, struct sock *child)
{
	struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk);
	unsigned short port = inet_sk(child)->inet_num;
	struct inet_bind_hashbucket *head, *head2;
	bool created_inet_bind_bucket = false;
	struct net *net = sock_net(sk);
	bool update_fastreuse = false;
	struct inet_bind2_bucket *tb2;
	struct inet_bind_bucket *tb;
	int bhash, l3mdev;

	bhash = inet_bhashfn(net, port, table->bhash_size);
	head = &table->bhash[bhash];
	head2 = inet_bhashfn_portaddr(table, child, net, port);

	spin_lock(&head->lock);
	spin_lock(&head2->lock);
	tb = inet_csk(sk)->icsk_bind_hash;
	tb2 = inet_csk(sk)->icsk_bind2_hash;
	if (unlikely(!tb || !tb2)) {
		spin_unlock(&head2->lock);
		spin_unlock(&head->lock);
		return -ENOENT;
	}
	if (tb->port != port) {
		l3mdev = inet_sk_bound_l3mdev(sk);

		/* NOTE: using tproxy and redirecting skbs to a proxy
		 * on a different listener port breaks the assumption
		 * that the listener socket's icsk_bind_hash is the same
		 * as that of the child socket. We have to look up or
		 * create a new bind bucket for the child here. */
		inet_bind_bucket_for_each(tb, &head->chain) {
			if (inet_bind_bucket_match(tb, net, port, l3mdev))
				break;
		}
		if (!tb) {
			tb = inet_bind_bucket_create(table->bind_bucket_cachep,
						     net, head, port, l3mdev);
			if (!tb) {
				spin_unlock(&head2->lock);
				spin_unlock(&head->lock);
				return -ENOMEM;
			}
			created_inet_bind_bucket = true;
		}
		update_fastreuse = true;

		goto bhash2_find;
	} else if (!inet_bind2_bucket_addr_match(tb2, child)) {
		l3mdev = inet_sk_bound_l3mdev(sk);

bhash2_find:
		tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child);
		if (!tb2) {
			tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
						       net, head2, tb, child);
			if (!tb2)
				goto error;
		}
	}
	if (update_fastreuse)
		inet_csk_update_fastreuse(tb, child);
	inet_bind_hash(child, tb, tb2, port);
	spin_unlock(&head2->lock);
	spin_unlock(&head->lock);

	return 0;

error:
	if (created_inet_bind_bucket)
		inet_bind_bucket_destroy(table->bind_bucket_cachep, tb);
	spin_unlock(&head2->lock);
	spin_unlock(&head->lock);
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__inet_inherit_port);

static struct inet_listen_hashbucket *
inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk)
{
	u32 hash;

#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		hash = ipv6_portaddr_hash(sock_net(sk),
					  &sk->sk_v6_rcv_saddr,
					  inet_sk(sk)->inet_num);
	else
#endif
		hash = ipv4_portaddr_hash(sock_net(sk),
					  inet_sk(sk)->inet_rcv_saddr,
					  inet_sk(sk)->inet_num);
	return inet_lhash2_bucket(h, hash);
}

static inline int compute_score(struct sock *sk, struct net *net,
				const unsigned short hnum, const __be32 daddr,
				const int dif, const int sdif)
{
	int score = -1;

	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
			!ipv6_only_sock(sk)) {
		if (sk->sk_rcv_saddr != daddr)
			return -1;

		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
			return -1;
		score =  sk->sk_bound_dev_if ? 2 : 1;

		if (sk->sk_family == PF_INET)
			score++;
		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
			score++;
	}
	return score;
}

/**
 * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary.
 * @net: network namespace.
 * @sk: AF_INET socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
 * @skb: context for a potential SK_REUSEPORT program.
 * @doff: header offset.
 * @saddr: source address.
 * @sport: source port.
 * @daddr: destination address.
 * @hnum: destination port in host byte order.
 * @ehashfn: hash function used to generate the fallback hash.
 *
 * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
 *         the selected sock or an error.
 */
struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
				   struct sk_buff *skb, int doff,
				   __be32 saddr, __be16 sport,
				   __be32 daddr, unsigned short hnum,
				   inet_ehashfn_t *ehashfn)
{
	struct sock *reuse_sk = NULL;
	u32 phash;

	if (sk->sk_reuseport) {
		phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn,
					net, daddr, hnum, saddr, sport);
		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
	}
	return reuse_sk;
}
EXPORT_SYMBOL_GPL(inet_lookup_reuseport);

/*
 * Here are some nice properties to exploit here. The BSD API
 * does not allow a listening sock to specify the remote port nor the
 * remote address for the connection. So always assume those are both
 * wildcarded during the search since they can never be otherwise.
 */

/* called with rcu_read_lock() : No refcount taken on the socket */
static struct sock *inet_lhash2_lookup(struct net *net,
				struct inet_listen_hashbucket *ilb2,
				struct sk_buff *skb, int doff,
				const __be32 saddr, __be16 sport,
				const __be32 daddr, const unsigned short hnum,
				const int dif, const int sdif)
{
	struct sock *sk, *result = NULL;
	struct hlist_nulls_node *node;
	int score, hiscore = 0;

	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
		score = compute_score(sk, net, hnum, daddr, dif, sdif);
		if (score > hiscore) {
			result = inet_lookup_reuseport(net, sk, skb, doff,
						       saddr, sport, daddr, hnum, inet_ehashfn);
			if (result)
				return result;

			result = sk;
			hiscore = score;
		}
	}

	return result;
}

struct sock *inet_lookup_run_sk_lookup(struct net *net,
				       int protocol,
				       struct sk_buff *skb, int doff,
				       __be32 saddr, __be16 sport,
				       __be32 daddr, u16 hnum, const int dif,
				       inet_ehashfn_t *ehashfn)
{
	struct sock *sk, *reuse_sk;
	bool no_reuseport;

	no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport,
					    daddr, hnum, dif, &sk);
	if (no_reuseport || IS_ERR_OR_NULL(sk))
		return sk;

	reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
					 ehashfn);
	if (reuse_sk)
		sk = reuse_sk;
	return sk;
}

struct sock *__inet_lookup_listener(struct net *net,
				    struct inet_hashinfo *hashinfo,
				    struct sk_buff *skb, int doff,
				    const __be32 saddr, __be16 sport,
				    const __be32 daddr, const unsigned short hnum,
				    const int dif, const int sdif)
{
	struct inet_listen_hashbucket *ilb2;
	struct sock *result = NULL;
	unsigned int hash2;

	/* Lookup redirect from BPF */
	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
	    hashinfo == net->ipv4.tcp_death_row.hashinfo) {
		result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
						   saddr, sport, daddr, hnum, dif,
						   inet_ehashfn);
		if (result)
			goto done;
	}

	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
	ilb2 = inet_lhash2_bucket(hashinfo, hash2);

	result = inet_lhash2_lookup(net, ilb2, skb, doff,
				    saddr, sport, daddr, hnum,
				    dif, sdif);
	if (result)
		goto done;

	/* Lookup lhash2 with INADDR_ANY */
	hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
	ilb2 = inet_lhash2_bucket(hashinfo, hash2);

	result = inet_lhash2_lookup(net, ilb2, skb, doff,
				    saddr, sport, htonl(INADDR_ANY), hnum,
				    dif, sdif);
done:
	if (IS_ERR(result))
		return NULL;
	return result;
}
EXPORT_SYMBOL_GPL(__inet_lookup_listener);

/* All sockets share common refcount, but have different destructors */
void sock_gen_put(struct sock *sk)
{
	if (!refcount_dec_and_test(&sk->sk_refcnt))
		return;

	if (sk->sk_state == TCP_TIME_WAIT)
		inet_twsk_free(inet_twsk(sk));
	else if (sk->sk_state == TCP_NEW_SYN_RECV)
		reqsk_free(inet_reqsk(sk));
	else
		sk_free(sk);
}
EXPORT_SYMBOL_GPL(sock_gen_put);

void sock_edemux(struct sk_buff *skb)
{
	sock_gen_put(skb->sk);
}
EXPORT_SYMBOL(sock_edemux);

struct sock *__inet_lookup_established(struct net *net,
				  struct inet_hashinfo *hashinfo,
				  const __be32 saddr, const __be16 sport,
				  const __be32 daddr, const u16 hnum,
				  const int dif, const int sdif)
{
	INET_ADDR_COOKIE(acookie, saddr, daddr);
	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
	struct sock *sk;
	const struct hlist_nulls_node *node;
	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
	unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport);
	unsigned int slot = hash & hashinfo->ehash_mask;
	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];

begin:
	sk_nulls_for_each_rcu(sk, node, &head->chain) {
		if (sk->sk_hash != hash)
			continue;
		if (likely(inet_match(net, sk, acookie, ports, dif, sdif))) {
			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
				goto out;
			if (unlikely(!inet_match(net, sk, acookie,
						 ports, dif, sdif))) {
				sock_gen_put(sk);
				goto begin;
			}
			goto found;
		}
	}
	/*
	 * if the nulls value we got at the end of this lookup is
	 * not the expected one, we must restart lookup.
	 * We probably met an item that was moved to another chain.
	 */
	if (get_nulls_value(node) != slot)
		goto begin;
out:
	sk = NULL;
found:
	return sk;
}
EXPORT_SYMBOL_GPL(__inet_lookup_established);

/* called with local bh disabled */
static int __inet_check_established(struct inet_timewait_death_row *death_row,
				    struct sock *sk, __u16 lport,
				    struct inet_timewait_sock **twp)
{
	struct inet_hashinfo *hinfo = death_row->hashinfo;
	struct inet_sock *inet = inet_sk(sk);
	__be32 daddr = inet->inet_rcv_saddr;
	__be32 saddr = inet->inet_daddr;
	int dif = sk->sk_bound_dev_if;
	struct net *net = sock_net(sk);
	int sdif = l3mdev_master_ifindex_by_index(net, dif);
	INET_ADDR_COOKIE(acookie, saddr, daddr);
	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
	unsigned int hash = inet_ehashfn(net, daddr, lport,
					 saddr, inet->inet_dport);
	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
	struct sock *sk2;
	const struct hlist_nulls_node *node;
	struct inet_timewait_sock *tw = NULL;

	spin_lock(lock);

	sk_nulls_for_each(sk2, node, &head->chain) {
		if (sk2->sk_hash != hash)
			continue;

		if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) {
			if (sk2->sk_state == TCP_TIME_WAIT) {
				tw = inet_twsk(sk2);
				if (sk->sk_protocol == IPPROTO_TCP &&
				    tcp_twsk_unique(sk, sk2, twp))
					break;
			}
			goto not_unique;
		}
	}

	/* Must record num and sport now. Otherwise we will see
	 * in hash table socket with a funny identity.
	 */
	inet->inet_num = lport;
	inet->inet_sport = htons(lport);
	sk->sk_hash = hash;
	WARN_ON(!sk_unhashed(sk));
	__sk_nulls_add_node_rcu(sk, &head->chain);
	if (tw) {
		sk_nulls_del_node_init_rcu((struct sock *)tw);
		__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
	}
	spin_unlock(lock);
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);

	if (twp) {
		*twp = tw;
	} else if (tw) {
		/* Silly. Should hash-dance instead... */
		inet_twsk_deschedule_put(tw);
	}
	return 0;

not_unique:
	spin_unlock(lock);
	return -EADDRNOTAVAIL;
}

static u64 inet_sk_port_offset(const struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);

	return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr,
					  inet->inet_daddr,
					  inet->inet_dport);
}

/* Searches for an exsiting socket in the ehash bucket list.
 * Returns true if found, false otherwise.
 */
static bool inet_ehash_lookup_by_sk(struct sock *sk,
				    struct hlist_nulls_head *list)
{
	const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
	const int sdif = sk->sk_bound_dev_if;
	const int dif = sk->sk_bound_dev_if;
	const struct hlist_nulls_node *node;
	struct net *net = sock_net(sk);
	struct sock *esk;

	INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);

	sk_nulls_for_each_rcu(esk, node, list) {
		if (esk->sk_hash != sk->sk_hash)
			continue;
		if (sk->sk_family == AF_INET) {
			if (unlikely(inet_match(net, esk, acookie,
						ports, dif, sdif))) {
				return true;
			}
		}
#if IS_ENABLED(CONFIG_IPV6)
		else if (sk->sk_family == AF_INET6) {
			if (unlikely(inet6_match(net, esk,
						 &sk->sk_v6_daddr,
						 &sk->sk_v6_rcv_saddr,
						 ports, dif, sdif))) {
				return true;
			}
		}
#endif
	}
	return false;
}

/* Insert a socket into ehash, and eventually remove another one
 * (The another one can be a SYN_RECV or TIMEWAIT)
 * If an existing socket already exists, socket sk is not inserted,
 * and sets found_dup_sk parameter to true.
 */
bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
	struct inet_ehash_bucket *head;
	struct hlist_nulls_head *list;
	spinlock_t *lock;
	bool ret = true;

	WARN_ON_ONCE(!sk_unhashed(sk));

	sk->sk_hash = sk_ehashfn(sk);
	head = inet_ehash_bucket(hashinfo, sk->sk_hash);
	list = &head->chain;
	lock = inet_ehash_lockp(hashinfo, sk->sk_hash);

	spin_lock(lock);
	if (osk) {
		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
		ret = sk_nulls_del_node_init_rcu(osk);
	} else if (found_dup_sk) {
		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
		if (*found_dup_sk)
			ret = false;
	}

	if (ret)
		__sk_nulls_add_node_rcu(sk, list);

	spin_unlock(lock);

	return ret;
}

bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
	bool ok = inet_ehash_insert(sk, osk, found_dup_sk);

	if (ok) {
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
	} else {
		this_cpu_inc(*sk->sk_prot->orphan_count);
		inet_sk_set_state(sk, TCP_CLOSE);
		sock_set_flag(sk, SOCK_DEAD);
		inet_csk_destroy_sock(sk);
	}
	return ok;
}
EXPORT_SYMBOL_GPL(inet_ehash_nolisten);

static int inet_reuseport_add_sock(struct sock *sk,
				   struct inet_listen_hashbucket *ilb)
{
	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
	const struct hlist_nulls_node *node;
	struct sock *sk2;
	kuid_t uid = sock_i_uid(sk);

	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
		if (sk2 != sk &&
		    sk2->sk_family == sk->sk_family &&
		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
		    sk2->sk_bound_dev_if == sk->sk_bound_dev_if &&
		    inet_csk(sk2)->icsk_bind_hash == tb &&
		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
		    inet_rcv_saddr_equal(sk, sk2, false))
			return reuseport_add_sock(sk, sk2,
						  inet_rcv_saddr_any(sk));
	}

	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
}

int __inet_hash(struct sock *sk, struct sock *osk)
{
	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
	struct inet_listen_hashbucket *ilb2;
	int err = 0;

	if (sk->sk_state != TCP_LISTEN) {
		local_bh_disable();
		inet_ehash_nolisten(sk, osk, NULL);
		local_bh_enable();
		return 0;
	}
	WARN_ON(!sk_unhashed(sk));
	ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);

	spin_lock(&ilb2->lock);
	if (sk->sk_reuseport) {
		err = inet_reuseport_add_sock(sk, ilb2);
		if (err)
			goto unlock;
	}
	sock_set_flag(sk, SOCK_RCU_FREE);
	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
		sk->sk_family == AF_INET6)
		__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
	else
		__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
unlock:
	spin_unlock(&ilb2->lock);

	return err;
}
EXPORT_SYMBOL(__inet_hash);

int inet_hash(struct sock *sk)
{
	int err = 0;

	if (sk->sk_state != TCP_CLOSE)
		err = __inet_hash(sk, NULL);

	return err;
}
EXPORT_SYMBOL_GPL(inet_hash);

void inet_unhash(struct sock *sk)
{
	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);

	if (sk_unhashed(sk))
		return;

	if (sk->sk_state == TCP_LISTEN) {
		struct inet_listen_hashbucket *ilb2;

		ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);
		/* Don't disable bottom halves while acquiring the lock to
		 * avoid circular locking dependency on PREEMPT_RT.
		 */
		spin_lock(&ilb2->lock);
		if (sk_unhashed(sk)) {
			spin_unlock(&ilb2->lock);
			return;
		}

		if (rcu_access_pointer(sk->sk_reuseport_cb))
			reuseport_stop_listen_sock(sk);

		__sk_nulls_del_node_init_rcu(sk);
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
		spin_unlock(&ilb2->lock);
	} else {
		spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);

		spin_lock_bh(lock);
		if (sk_unhashed(sk)) {
			spin_unlock_bh(lock);
			return;
		}
		__sk_nulls_del_node_init_rcu(sk);
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
		spin_unlock_bh(lock);
	}
}
EXPORT_SYMBOL_GPL(inet_unhash);

static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
				    const struct net *net, unsigned short port,
				    int l3mdev, const struct sock *sk)
{
	if (!net_eq(ib2_net(tb), net) || tb->port != port ||
	    tb->l3mdev != l3mdev)
		return false;

	return inet_bind2_bucket_addr_match(tb, sk);
}

bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
				      unsigned short port, int l3mdev, const struct sock *sk)
{
	if (!net_eq(ib2_net(tb), net) || tb->port != port ||
	    tb->l3mdev != l3mdev)
		return false;

#if IS_ENABLED(CONFIG_IPV6)
	if (tb->addr_type == IPV6_ADDR_ANY)
		return true;

	if (tb->addr_type != IPV6_ADDR_MAPPED)
		return false;

	if (sk->sk_family == AF_INET6 &&
	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
		return false;
#endif
	return tb->rcv_saddr == 0;
}

/* The socket's bhash2 hashbucket spinlock must be held when this is called */
struct inet_bind2_bucket *
inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net *net,
		       unsigned short port, int l3mdev, const struct sock *sk)
{
	struct inet_bind2_bucket *bhash2 = NULL;

	inet_bind_bucket_for_each(bhash2, &head->chain)
		if (inet_bind2_bucket_match(bhash2, net, port, l3mdev, sk))
			break;

	return bhash2;
}

struct inet_bind_hashbucket *
inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port)
{
	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
	u32 hash;

#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		hash = ipv6_portaddr_hash(net, &in6addr_any, port);
	else
#endif
		hash = ipv4_portaddr_hash(net, 0, port);

	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
}

static void inet_update_saddr(struct sock *sk, void *saddr, int family)
{
	if (family == AF_INET) {
		inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
		sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
	}
#if IS_ENABLED(CONFIG_IPV6)
	else {
		sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
	}
#endif
}

static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
{
	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
	struct inet_bind_hashbucket *head, *head2;
	struct inet_bind2_bucket *tb2, *new_tb2;
	int l3mdev = inet_sk_bound_l3mdev(sk);
	int port = inet_sk(sk)->inet_num;
	struct net *net = sock_net(sk);
	int bhash;

	if (!inet_csk(sk)->icsk_bind2_hash) {
		/* Not bind()ed before. */
		if (reset)
			inet_reset_saddr(sk);
		else
			inet_update_saddr(sk, saddr, family);

		return 0;
	}

	/* Allocate a bind2 bucket ahead of time to avoid permanently putting
	 * the bhash2 table in an inconsistent state if a new tb2 bucket
	 * allocation fails.
	 */
	new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
	if (!new_tb2) {
		if (reset) {
			/* The (INADDR_ANY, port) bucket might have already
			 * been freed, then we cannot fixup icsk_bind2_hash,
			 * so we give up and unlink sk from bhash/bhash2 not
			 * to leave inconsistency in bhash2.
			 */
			inet_put_port(sk);
			inet_reset_saddr(sk);
		}

		return -ENOMEM;
	}

	bhash = inet_bhashfn(net, port, hinfo->bhash_size);
	head = &hinfo->bhash[bhash];
	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);

	/* If we change saddr locklessly, another thread
	 * iterating over bhash might see corrupted address.
	 */
	spin_lock_bh(&head->lock);

	spin_lock(&head2->lock);
	__sk_del_bind_node(sk);
	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
	spin_unlock(&head2->lock);

	if (reset)
		inet_reset_saddr(sk);
	else
		inet_update_saddr(sk, saddr, family);

	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);

	spin_lock(&head2->lock);
	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
	if (!tb2) {
		tb2 = new_tb2;
		inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
	}
	inet_csk(sk)->icsk_bind2_hash = tb2;
	sk_add_bind_node(sk, &tb2->owners);
	spin_unlock(&head2->lock);

	spin_unlock_bh(&head->lock);

	if (tb2 != new_tb2)
		kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);

	return 0;
}

int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
{
	return __inet_bhash2_update_saddr(sk, saddr, family, false);
}
EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);

void inet_bhash2_reset_saddr(struct sock *sk)
{
	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		__inet_bhash2_update_saddr(sk, NULL, 0, true);
}
EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);

/* RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm
 * Note that we use 32bit integers (vs RFC 'short integers')
 * because 2^16 is not a multiple of num_ephemeral and this
 * property might be used by clever attacker.
 *
 * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
 * attacks were since demonstrated, thus we use 65536 by default instead
 * to really give more isolation and privacy, at the expense of 256kB
 * of kernel memory.
 */
#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
static u32 *table_perturb;

int __inet_hash_connect(struct inet_timewait_death_row *death_row,
		struct sock *sk, u64 port_offset,
		int (*check_established)(struct inet_timewait_death_row *,
			struct sock *, __u16, struct inet_timewait_sock **))
{
	struct inet_hashinfo *hinfo = death_row->hashinfo;
	struct inet_bind_hashbucket *head, *head2;
	struct inet_timewait_sock *tw = NULL;
	int port = inet_sk(sk)->inet_num;
	struct net *net = sock_net(sk);
	struct inet_bind2_bucket *tb2;
	struct inet_bind_bucket *tb;
	bool tb_created = false;
	u32 remaining, offset;
	int ret, i, low, high;
	bool local_ports;
	int step, l3mdev;
	u32 index;

	if (port) {
		local_bh_disable();
		ret = check_established(death_row, sk, port, NULL);
		local_bh_enable();
		return ret;
	}

	l3mdev = inet_sk_bound_l3mdev(sk);

	local_ports = inet_sk_get_local_port_range(sk, &low, &high);
	step = local_ports ? 1 : 2;

	high++; /* [32768, 60999] -> [32768, 61000[ */
	remaining = high - low;
	if (!local_ports && remaining > 1)
		remaining &= ~1U;

	get_random_sleepable_once(table_perturb,
				  INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
	index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);

	offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
	offset %= remaining;

	/* In first pass we try ports of @low parity.
	 * inet_csk_get_port() does the opposite choice.
	 */
	if (!local_ports)
		offset &= ~1U;
other_parity_scan:
	port = low + offset;
	for (i = 0; i < remaining; i += step, port += step) {
		if (unlikely(port >= high))
			port -= remaining;
		if (inet_is_local_reserved_port(net, port))
			continue;
		head = &hinfo->bhash[inet_bhashfn(net, port,
						  hinfo->bhash_size)];
		spin_lock_bh(&head->lock);

		/* Does not bother with rcv_saddr checks, because
		 * the established check is already unique enough.
		 */
		inet_bind_bucket_for_each(tb, &head->chain) {
			if (inet_bind_bucket_match(tb, net, port, l3mdev)) {
				if (tb->fastreuse >= 0 ||
				    tb->fastreuseport >= 0)
					goto next_port;
				WARN_ON(hlist_empty(&tb->bhash2));
				if (!check_established(death_row, sk,
						       port, &tw))
					goto ok;
				goto next_port;
			}
		}

		tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
					     net, head, port, l3mdev);
		if (!tb) {
			spin_unlock_bh(&head->lock);
			return -ENOMEM;
		}
		tb_created = true;
		tb->fastreuse = -1;
		tb->fastreuseport = -1;
		goto ok;
next_port:
		spin_unlock_bh(&head->lock);
		cond_resched();
	}

	if (!local_ports) {
		offset++;
		if ((offset & 1) && remaining > 1)
			goto other_parity_scan;
	}
	return -EADDRNOTAVAIL;

ok:
	/* Find the corresponding tb2 bucket since we need to
	 * add the socket to the bhash2 table as well
	 */
	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
	spin_lock(&head2->lock);

	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
	if (!tb2) {
		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
					       head2, tb, sk);
		if (!tb2)
			goto error;
	}

	/* Here we want to add a little bit of randomness to the next source
	 * port that will be chosen. We use a max() with a random here so that
	 * on low contention the randomness is maximal and on high contention
	 * it may be inexistent.
	 */
	i = max_t(int, i, get_random_u32_below(8) * step);
	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step);

	/* Head lock still held and bh's disabled */
	inet_bind_hash(sk, tb, tb2, port);

	if (sk_unhashed(sk)) {
		inet_sk(sk)->inet_sport = htons(port);
		inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
	}
	if (tw)
		inet_twsk_bind_unhash(tw, hinfo);

	spin_unlock(&head2->lock);
	spin_unlock(&head->lock);

	if (tw)
		inet_twsk_deschedule_put(tw);
	local_bh_enable();
	return 0;

error:
	if (sk_hashed(sk)) {
		spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash);

		sock_prot_inuse_add(net, sk->sk_prot, -1);

		spin_lock(lock);
		__sk_nulls_del_node_init_rcu(sk);
		spin_unlock(lock);

		sk->sk_hash = 0;
		inet_sk(sk)->inet_sport = 0;
		inet_sk(sk)->inet_num = 0;

		if (tw)
			inet_twsk_bind_unhash(tw, hinfo);
	}

	spin_unlock(&head2->lock);
	if (tb_created)
		inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
	spin_unlock(&head->lock);

	if (tw)
		inet_twsk_deschedule_put(tw);

	local_bh_enable();

	return -ENOMEM;
}

/*
 * Bind a port for a connect operation and hash it.
 */
int inet_hash_connect(struct inet_timewait_death_row *death_row,
		      struct sock *sk)
{
	u64 port_offset = 0;

	if (!inet_sk(sk)->inet_num)
		port_offset = inet_sk_port_offset(sk);
	return __inet_hash_connect(death_row, sk, port_offset,
				   __inet_check_established);
}
EXPORT_SYMBOL_GPL(inet_hash_connect);

static void init_hashinfo_lhash2(struct inet_hashinfo *h)
{
	int i;

	for (i = 0; i <= h->lhash2_mask; i++) {
		spin_lock_init(&h->lhash2[i].lock);
		INIT_HLIST_NULLS_HEAD(&h->lhash2[i].nulls_head,
				      i + LISTENING_NULLS_BASE);
	}
}

void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
				unsigned long numentries, int scale,
				unsigned long low_limit,
				unsigned long high_limit)
{
	h->lhash2 = alloc_large_system_hash(name,
					    sizeof(*h->lhash2),
					    numentries,
					    scale,
					    0,
					    NULL,
					    &h->lhash2_mask,
					    low_limit,
					    high_limit);
	init_hashinfo_lhash2(h);

	/* this one is used for source ports of outgoing connections */
	table_perturb = alloc_large_system_hash("Table-perturb",
						sizeof(*table_perturb),
						INET_TABLE_PERTURB_SIZE,
						0, 0, NULL, NULL,
						INET_TABLE_PERTURB_SIZE,
						INET_TABLE_PERTURB_SIZE);
}

int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
{
	h->lhash2 = kmalloc_array(INET_LHTABLE_SIZE, sizeof(*h->lhash2), GFP_KERNEL);
	if (!h->lhash2)
		return -ENOMEM;

	h->lhash2_mask = INET_LHTABLE_SIZE - 1;
	/* INET_LHTABLE_SIZE must be a power of 2 */
	BUG_ON(INET_LHTABLE_SIZE & h->lhash2_mask);

	init_hashinfo_lhash2(h);
	return 0;
}
EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod);

int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
	unsigned int locksz = sizeof(spinlock_t);
	unsigned int i, nblocks = 1;

	if (locksz != 0) {
		/* allocate 2 cache lines or at least one spinlock per cpu */
		nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
		nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());

		/* no more locks than number of hash buckets */
		nblocks = min(nblocks, hashinfo->ehash_mask + 1);

		hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
		if (!hashinfo->ehash_locks)
			return -ENOMEM;

		for (i = 0; i < nblocks; i++)
			spin_lock_init(&hashinfo->ehash_locks[i]);
	}
	hashinfo->ehash_locks_mask = nblocks - 1;
	return 0;
}
EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc);

struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo,
						 unsigned int ehash_entries)
{
	struct inet_hashinfo *new_hashinfo;
	int i;

	new_hashinfo = kmemdup(hashinfo, sizeof(*hashinfo), GFP_KERNEL);
	if (!new_hashinfo)
		goto err;

	new_hashinfo->ehash = vmalloc_huge(ehash_entries * sizeof(struct inet_ehash_bucket),
					   GFP_KERNEL_ACCOUNT);
	if (!new_hashinfo->ehash)
		goto free_hashinfo;

	new_hashinfo->ehash_mask = ehash_entries - 1;

	if (inet_ehash_locks_alloc(new_hashinfo))
		goto free_ehash;

	for (i = 0; i < ehash_entries; i++)
		INIT_HLIST_NULLS_HEAD(&new_hashinfo->ehash[i].chain, i);

	new_hashinfo->pernet = true;

	return new_hashinfo;

free_ehash:
	vfree(new_hashinfo->ehash);
free_hashinfo:
	kfree(new_hashinfo);
err:
	return NULL;
}
EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc);

void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo)
{
	if (!hashinfo->pernet)
		return;

	inet_ehash_locks_free(hashinfo);
	vfree(hashinfo->ehash);
	kfree(hashinfo);
}
EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free);