summaryrefslogtreecommitdiffstats
path: root/lib/rhashtable.c
blob: 688693c919be31ea9c2219898242b6f525c8ced4 (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
/*
 * Resizable, Scalable, Concurrent Hash Table
 *
 * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
 * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch>
 * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
 *
 * Code partially derived from nft_hash
 * Rewritten with rehash code from br_multicast plus single list
 * pointer as suggested by Josh Triplett
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/log2.h>
#include <linux/sched.h>
#include <linux/rculist.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <linux/rhashtable.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/rhashtable.h>

#define HASH_DEFAULT_SIZE	64UL
#define HASH_MIN_SIZE		4U
#define BUCKET_LOCKS_PER_CPU	32UL

union nested_table {
	union nested_table __rcu *table;
	struct rhash_head __rcu *bucket;
};

static u32 head_hashfn(struct rhashtable *ht,
		       const struct bucket_table *tbl,
		       const struct rhash_head *he)
{
	return rht_head_hashfn(ht, tbl, he, ht->p);
}

#ifdef CONFIG_PROVE_LOCKING
#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT))

int lockdep_rht_mutex_is_held(struct rhashtable *ht)
{
	return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1;
}
EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);

int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
{
	spinlock_t *lock = rht_bucket_lock(tbl, hash);

	return (debug_locks) ? lockdep_is_held(lock) : 1;
}
EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
#else
#define ASSERT_RHT_MUTEX(HT)
#endif

static void nested_table_free(union nested_table *ntbl, unsigned int size)
{
	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
	const unsigned int len = 1 << shift;
	unsigned int i;

	ntbl = rcu_dereference_raw(ntbl->table);
	if (!ntbl)
		return;

	if (size > len) {
		size >>= shift;
		for (i = 0; i < len; i++)
			nested_table_free(ntbl + i, size);
	}

	kfree(ntbl);
}

static void nested_bucket_table_free(const struct bucket_table *tbl)
{
	unsigned int size = tbl->size >> tbl->nest;
	unsigned int len = 1 << tbl->nest;
	union nested_table *ntbl;
	unsigned int i;

	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);

	for (i = 0; i < len; i++)
		nested_table_free(ntbl + i, size);

	kfree(ntbl);
}

static void bucket_table_free(const struct bucket_table *tbl)
{
	if (tbl->nest)
		nested_bucket_table_free(tbl);

	free_bucket_spinlocks(tbl->locks);
	kvfree(tbl);
}

static void bucket_table_free_rcu(struct rcu_head *head)
{
	bucket_table_free(container_of(head, struct bucket_table, rcu));
}

static union nested_table *nested_table_alloc(struct rhashtable *ht,
					      union nested_table __rcu **prev,
					      unsigned int shifted,
					      unsigned int nhash)
{
	union nested_table *ntbl;
	int i;

	ntbl = rcu_dereference(*prev);
	if (ntbl)
		return ntbl;

	ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC);

	if (ntbl && shifted) {
		for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++)
			INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht,
					    (i << shifted) | nhash);
	}

	rcu_assign_pointer(*prev, ntbl);

	return ntbl;
}

static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
						      size_t nbuckets,
						      gfp_t gfp)
{
	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
	struct bucket_table *tbl;
	size_t size;

	if (nbuckets < (1 << (shift + 1)))
		return NULL;

	size = sizeof(*tbl) + sizeof(tbl->buckets[0]);

	tbl = kzalloc(size, gfp);
	if (!tbl)
		return NULL;

	if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets,
				0, 0)) {
		kfree(tbl);
		return NULL;
	}

	tbl->nest = (ilog2(nbuckets) - 1) % shift + 1;

	return tbl;
}

static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
					       size_t nbuckets,
					       gfp_t gfp)
{
	struct bucket_table *tbl = NULL;
	size_t size, max_locks;
	int i;

	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
	if (gfp != GFP_KERNEL)
		tbl = kzalloc(size, gfp | __GFP_NOWARN | __GFP_NORETRY);
	else
		tbl = kvzalloc(size, gfp);

	size = nbuckets;

	if (tbl == NULL && gfp != GFP_KERNEL) {
		tbl = nested_bucket_table_alloc(ht, nbuckets, gfp);
		nbuckets = 0;
	}
	if (tbl == NULL)
		return NULL;

	tbl->size = size;

	max_locks = size >> 1;
	if (tbl->nest)
		max_locks = min_t(size_t, max_locks, 1U << tbl->nest);

	if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks,
				   ht->p.locks_mul, gfp) < 0) {
		bucket_table_free(tbl);
		return NULL;
	}

	INIT_LIST_HEAD(&tbl->walkers);

	tbl->hash_rnd = get_random_u32();

	for (i = 0; i < nbuckets; i++)
		INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i);

	return tbl;
}

static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
						  struct bucket_table *tbl)
{
	struct bucket_table *new_tbl;

	do {
		new_tbl = tbl;
		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
	} while (tbl);

	return new_tbl;
}

static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
{
	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
	struct bucket_table *new_tbl = rhashtable_last_table(ht,
		rht_dereference_rcu(old_tbl->future_tbl, ht));
	struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
	int err = -EAGAIN;
	struct rhash_head *head, *next, *entry;
	spinlock_t *new_bucket_lock;
	unsigned int new_hash;

	if (new_tbl->nest)
		goto out;

	err = -ENOENT;

	rht_for_each(entry, old_tbl, old_hash) {
		err = 0;
		next = rht_dereference_bucket(entry->next, old_tbl, old_hash);

		if (rht_is_a_nulls(next))
			break;

		pprev = &entry->next;
	}

	if (err)
		goto out;

	new_hash = head_hashfn(ht, new_tbl, entry);

	new_bucket_lock = rht_bucket_lock(new_tbl, new_hash);

	spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING);
	head = rht_dereference_bucket(new_tbl->buckets[new_hash],
				      new_tbl, new_hash);

	RCU_INIT_POINTER(entry->next, head);

	rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
	spin_unlock(new_bucket_lock);

	rcu_assign_pointer(*pprev, next);

out:
	return err;
}

static int rhashtable_rehash_chain(struct rhashtable *ht,
				    unsigned int old_hash)
{
	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
	spinlock_t *old_bucket_lock;
	int err;

	old_bucket_lock = rht_bucket_lock(old_tbl, old_hash);

	spin_lock_bh(old_bucket_lock);
	while (!(err = rhashtable_rehash_one(ht, old_hash)))
		;

	if (err == -ENOENT) {
		old_tbl->rehash++;
		err = 0;
	}
	spin_unlock_bh(old_bucket_lock);

	return err;
}

static int rhashtable_rehash_attach(struct rhashtable *ht,
				    struct bucket_table *old_tbl,
				    struct bucket_table *new_tbl)
{
	/* Protect future_tbl using the first bucket lock. */
	spin_lock_bh(old_tbl->locks);

	/* Did somebody beat us to it? */
	if (rcu_access_pointer(old_tbl->future_tbl)) {
		spin_unlock_bh(old_tbl->locks);
		return -EEXIST;
	}

	/* Make insertions go into the new, empty table right away. Deletions
	 * and lookups will be attempted in both tables until we synchronize.
	 */
	rcu_assign_pointer(old_tbl->future_tbl, new_tbl);

	spin_unlock_bh(old_tbl->locks);

	return 0;
}

static int rhashtable_rehash_table(struct rhashtable *ht)
{
	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
	struct bucket_table *new_tbl;
	struct rhashtable_walker *walker;
	unsigned int old_hash;
	int err;

	new_tbl = rht_dereference(old_tbl->future_tbl, ht);
	if (!new_tbl)
		return 0;

	for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
		err = rhashtable_rehash_chain(ht, old_hash);
		if (err)
			return err;
		cond_resched();
	}

	/* Publish the new table pointer. */
	rcu_assign_pointer(ht->tbl, new_tbl);

	spin_lock(&ht->lock);
	list_for_each_entry(walker, &old_tbl->walkers, list)
		walker->tbl = NULL;
	spin_unlock(&ht->lock);

	/* Wait for readers. All new readers will see the new
	 * table, and thus no references to the old table will
	 * remain.
	 */
	call_rcu(&old_tbl->rcu, bucket_table_free_rcu);

	return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0;
}

static int rhashtable_rehash_alloc(struct rhashtable *ht,
				   struct bucket_table *old_tbl,
				   unsigned int size)
{
	struct bucket_table *new_tbl;
	int err;

	ASSERT_RHT_MUTEX(ht);

	new_tbl = bucket_table_alloc(ht, size, GFP_KERNEL);
	if (new_tbl == NULL)
		return -ENOMEM;

	err = rhashtable_rehash_attach(ht, old_tbl, new_tbl);
	if (err)
		bucket_table_free(new_tbl);

	return err;
}

/**
 * rhashtable_shrink - Shrink hash table while allowing concurrent lookups
 * @ht:		the hash table to shrink
 *
 * This function shrinks the hash table to fit, i.e., the smallest
 * size would not cause it to expand right away automatically.
 *
 * The caller must ensure that no concurrent resizing occurs by holding
 * ht->mutex.
 *
 * The caller must ensure that no concurrent table mutations take place.
 * It is however valid to have concurrent lookups if they are RCU protected.
 *
 * It is valid to have concurrent insertions and deletions protected by per
 * bucket locks or concurrent RCU protected lookups and traversals.
 */
static int rhashtable_shrink(struct rhashtable *ht)
{
	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
	unsigned int nelems = atomic_read(&ht->nelems);
	unsigned int size = 0;

	if (nelems)
		size = roundup_pow_of_two(nelems * 3 / 2);
	if (size < ht->p.min_size)
		size = ht->p.min_size;

	if (old_tbl->size <= size)
		return 0;

	if (rht_dereference(old_tbl->future_tbl, ht))
		return -EEXIST;

	return rhashtable_rehash_alloc(ht, old_tbl, size);
}

static void rht_deferred_worker(struct work_struct *work)
{
	struct rhashtable *ht;
	struct bucket_table *tbl;
	int err = 0;

	ht = container_of(work, struct rhashtable, run_work);
	mutex_lock(&ht->mutex);

	tbl = rht_dereference(ht->tbl, ht);
	tbl = rhashtable_last_table(ht, tbl);

	if (rht_grow_above_75(ht, tbl))
		err = rhashtable_rehash_alloc(ht, tbl, tbl->size * 2);
	else if (ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl))
		err = rhashtable_shrink(ht);
	else if (tbl->nest)
		err = rhashtable_rehash_alloc(ht, tbl, tbl->size);

	if (!err)
		err = rhashtable_rehash_table(ht);

	mutex_unlock(&ht->mutex);

	if (err)
		schedule_work(&ht->run_work);
}

static int rhashtable_insert_rehash(struct rhashtable *ht,
				    struct bucket_table *tbl)
{
	struct bucket_table *old_tbl;
	struct bucket_table *new_tbl;
	unsigned int size;
	int err;

	old_tbl = rht_dereference_rcu(ht->tbl, ht);

	size = tbl->size;

	err = -EBUSY;

	if (rht_grow_above_75(ht, tbl))
		size *= 2;
	/* Do not schedule more than one rehash */
	else if (old_tbl != tbl)
		goto fail;

	err = -ENOMEM;

	new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC);
	if (new_tbl == NULL)
		goto fail;

	err = rhashtable_rehash_attach(ht, tbl, new_tbl);
	if (err) {
		bucket_table_free(new_tbl);
		if (err == -EEXIST)
			err = 0;
	} else
		schedule_work(&ht->run_work);

	return err;

fail:
	/* Do not fail the insert if someone else did a rehash. */
	if (likely(rcu_dereference_raw(tbl->future_tbl)))
		return 0;

	/* Schedule async rehash to retry allocation in process context. */
	if (err == -ENOMEM)
		schedule_work(&ht->run_work);

	return err;
}

static void *rhashtable_lookup_one(struct rhashtable *ht,
				   struct bucket_table *tbl, unsigned int hash,
				   const void *key, struct rhash_head *obj)
{
	struct rhashtable_compare_arg arg = {
		.ht = ht,
		.key = key,
	};
	struct rhash_head __rcu **pprev;
	struct rhash_head *head;
	int elasticity;

	elasticity = RHT_ELASTICITY;
	pprev = rht_bucket_var(tbl, hash);
	rht_for_each_continue(head, *pprev, tbl, hash) {
		struct rhlist_head *list;
		struct rhlist_head *plist;

		elasticity--;
		if (!key ||
		    (ht->p.obj_cmpfn ?
		     ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) :
		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
			pprev = &head->next;
			continue;
		}

		if (!ht->rhlist)
			return rht_obj(ht, head);

		list = container_of(obj, struct rhlist_head, rhead);
		plist = container_of(head, struct rhlist_head, rhead);

		RCU_INIT_POINTER(list->next, plist);
		head = rht_dereference_bucket(head->next, tbl, hash);
		RCU_INIT_POINTER(list->rhead.next, head);
		rcu_assign_pointer(*pprev, obj);

		return NULL;
	}

	if (elasticity <= 0)
		return ERR_PTR(-EAGAIN);

	return ERR_PTR(-ENOENT);
}

static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
						  struct bucket_table *tbl,
						  unsigned int hash,
						  struct rhash_head *obj,
						  void *data)
{
	struct rhash_head __rcu **pprev;
	struct bucket_table *new_tbl;
	struct rhash_head *head;

	if (!IS_ERR_OR_NULL(data))
		return ERR_PTR(-EEXIST);

	if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT)
		return ERR_CAST(data);

	new_tbl = rcu_dereference(tbl->future_tbl);
	if (new_tbl)
		return new_tbl;

	if (PTR_ERR(data) != -ENOENT)
		return ERR_CAST(data);

	if (unlikely(rht_grow_above_max(ht, tbl)))
		return ERR_PTR(-E2BIG);

	if (unlikely(rht_grow_above_100(ht, tbl)))
		return ERR_PTR(-EAGAIN);

	pprev = rht_bucket_insert(ht, tbl, hash);
	if (!pprev)
		return ERR_PTR(-ENOMEM);

	head = rht_dereference_bucket(*pprev, tbl, hash);

	RCU_INIT_POINTER(obj->next, head);
	if (ht->rhlist) {
		struct rhlist_head *list;

		list = container_of(obj, struct rhlist_head, rhead);
		RCU_INIT_POINTER(list->next, NULL);
	}

	rcu_assign_pointer(*pprev, obj);

	atomic_inc(&ht->nelems);
	if (rht_grow_above_75(ht, tbl))
		schedule_work(&ht->run_work);

	return NULL;
}

static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
				   struct rhash_head *obj)
{
	struct bucket_table *new_tbl;
	struct bucket_table *tbl;
	unsigned int hash;
	spinlock_t *lock;
	void *data;

	tbl = rcu_dereference(ht->tbl);

	/* All insertions must grab the oldest table containing
	 * the hashed bucket that is yet to be rehashed.
	 */
	for (;;) {
		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
		lock = rht_bucket_lock(tbl, hash);
		spin_lock_bh(lock);

		if (tbl->rehash <= hash)
			break;

		spin_unlock_bh(lock);
		tbl = rcu_dereference(tbl->future_tbl);
	}

	data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
	new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
	if (PTR_ERR(new_tbl) != -EEXIST)
		data = ERR_CAST(new_tbl);

	while (!IS_ERR_OR_NULL(new_tbl)) {
		tbl = new_tbl;
		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
		spin_lock_nested(rht_bucket_lock(tbl, hash),
				 SINGLE_DEPTH_NESTING);

		data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
		new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
		if (PTR_ERR(new_tbl) != -EEXIST)
			data = ERR_CAST(new_tbl);

		spin_unlock(rht_bucket_lock(tbl, hash));
	}

	spin_unlock_bh(lock);

	if (PTR_ERR(data) == -EAGAIN)
		data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?:
			       -EAGAIN);

	return data;
}

void *rhashtable_insert_slow(struct rhashtable *ht, const void *key,
			     struct rhash_head *obj)
{
	void *data;

	do {
		rcu_read_lock();
		data = rhashtable_try_insert(ht, key, obj);
		rcu_read_unlock();
	} while (PTR_ERR(data) == -EAGAIN);

	return data;
}
EXPORT_SYMBOL_GPL(rhashtable_insert_slow);

/**
 * rhashtable_walk_enter - Initialise an iterator
 * @ht:		Table to walk over
 * @iter:	Hash table Iterator
 *
 * This function prepares a hash table walk.
 *
 * Note that if you restart a walk after rhashtable_walk_stop you
 * may see the same object twice.  Also, you may miss objects if
 * there are removals in between rhashtable_walk_stop and the next
 * call to rhashtable_walk_start.
 *
 * For a completely stable walk you should construct your own data
 * structure outside the hash table.
 *
 * This function may be called from any process context, including
 * non-preemptable context, but cannot be called from softirq or
 * hardirq context.
 *
 * You must call rhashtable_walk_exit after this function returns.
 */
void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter)
{
	iter->ht = ht;
	iter->p = NULL;
	iter->slot = 0;
	iter->skip = 0;
	iter->end_of_table = 0;

	spin_lock(&ht->lock);
	iter->walker.tbl =
		rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock));
	list_add(&iter->walker.list, &iter->walker.tbl->walkers);
	spin_unlock(&ht->lock);
}
EXPORT_SYMBOL_GPL(rhashtable_walk_enter);

/**
 * rhashtable_walk_exit - Free an iterator
 * @iter:	Hash table Iterator
 *
 * This function frees resources allocated by rhashtable_walk_init.
 */
void rhashtable_walk_exit(struct rhashtable_iter *iter)
{
	spin_lock(&iter->ht->lock);
	if (iter->walker.tbl)
		list_del(&iter->walker.list);
	spin_unlock(&iter->ht->lock);
}
EXPORT_SYMBOL_GPL(rhashtable_walk_exit);

/**
 * rhashtable_walk_start_check - Start a hash table walk
 * @iter:	Hash table iterator
 *
 * Start a hash table walk at the current iterator position.  Note that we take
 * the RCU lock in all cases including when we return an error.  So you must
 * always call rhashtable_walk_stop to clean up.
 *
 * Returns zero if successful.
 *
 * Returns -EAGAIN if resize event occured.  Note that the iterator
 * will rewind back to the beginning and you may use it immediately
 * by calling rhashtable_walk_next.
 *
 * rhashtable_walk_start is defined as an inline variant that returns
 * void. This is preferred in cases where the caller would ignore
 * resize events and always continue.
 */
int rhashtable_walk_start_check(struct rhashtable_iter *iter)
	__acquires(RCU)
{
	struct rhashtable *ht = iter->ht;
	bool rhlist = ht->rhlist;

	rcu_read_lock();

	spin_lock(&ht->lock);
	if (iter->walker.tbl)
		list_del(&iter->walker.list);
	spin_unlock(&ht->lock);

	if (iter->end_of_table)
		return 0;
	if (!iter->walker.tbl) {
		iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht);
		iter->slot = 0;
		iter->skip = 0;
		return -EAGAIN;
	}

	if (iter->p && !rhlist) {
		/*
		 * We need to validate that 'p' is still in the table, and
		 * if so, update 'skip'
		 */
		struct rhash_head *p;
		int skip = 0;
		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
			skip++;
			if (p == iter->p) {
				iter->skip = skip;
				goto found;
			}
		}
		iter->p = NULL;
	} else if (iter->p && rhlist) {
		/* Need to validate that 'list' is still in the table, and
		 * if so, update 'skip' and 'p'.
		 */
		struct rhash_head *p;
		struct rhlist_head *list;
		int skip = 0;
		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
			for (list = container_of(p, struct rhlist_head, rhead);
			     list;
			     list = rcu_dereference(list->next)) {
				skip++;
				if (list == iter->list) {
					iter->p = p;
					skip = skip;
					goto found;
				}
			}
		}
		iter->p = NULL;
	}
found:
	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_start_check);

/**
 * __rhashtable_walk_find_next - Find the next element in a table (or the first
 * one in case of a new walk).
 *
 * @iter:	Hash table iterator
 *
 * Returns the found object or NULL when the end of the table is reached.
 *
 * Returns -EAGAIN if resize event occurred.
 */
static void *__rhashtable_walk_find_next(struct rhashtable_iter *iter)
{
	struct bucket_table *tbl = iter->walker.tbl;
	struct rhlist_head *list = iter->list;
	struct rhashtable *ht = iter->ht;
	struct rhash_head *p = iter->p;
	bool rhlist = ht->rhlist;

	if (!tbl)
		return NULL;

	for (; iter->slot < tbl->size; iter->slot++) {
		int skip = iter->skip;

		rht_for_each_rcu(p, tbl, iter->slot) {
			if (rhlist) {
				list = container_of(p, struct rhlist_head,
						    rhead);
				do {
					if (!skip)
						goto next;
					skip--;
					list = rcu_dereference(list->next);
				} while (list);

				continue;
			}
			if (!skip)
				break;
			skip--;
		}

next:
		if (!rht_is_a_nulls(p)) {
			iter->skip++;
			iter->p = p;
			iter->list = list;
			return rht_obj(ht, rhlist ? &list->rhead : p);
		}

		iter->skip = 0;
	}

	iter->p = NULL;

	/* Ensure we see any new tables. */
	smp_rmb();

	iter->walker.tbl = rht_dereference_rcu(tbl->future_tbl, ht);
	if (iter->walker.tbl) {
		iter->slot = 0;
		iter->skip = 0;
		return ERR_PTR(-EAGAIN);
	} else {
		iter->end_of_table = true;
	}

	return NULL;
}

/**
 * rhashtable_walk_next - Return the next object and advance the iterator
 * @iter:	Hash table iterator
 *
 * Note that you must call rhashtable_walk_stop when you are finished
 * with the walk.
 *
 * Returns the next object or NULL when the end of the table is reached.
 *
 * Returns -EAGAIN if resize event occurred.  Note that the iterator
 * will rewind back to the beginning and you may continue to use it.
 */
void *rhashtable_walk_next(struct rhashtable_iter *iter)
{
	struct rhlist_head *list = iter->list;
	struct rhashtable *ht = iter->ht;
	struct rhash_head *p = iter->p;
	bool rhlist = ht->rhlist;

	if (p) {
		if (!rhlist || !(list = rcu_dereference(list->next))) {
			p = rcu_dereference(p->next);
			list = container_of(p, struct rhlist_head, rhead);
		}
		if (!rht_is_a_nulls(p)) {
			iter->skip++;
			iter->p = p;
			iter->list = list;
			return rht_obj(ht, rhlist ? &list->rhead : p);
		}

		/* At the end of this slot, switch to next one and then find
		 * next entry from that point.
		 */
		iter->skip = 0;
		iter->slot++;
	}

	return __rhashtable_walk_find_next(iter);
}
EXPORT_SYMBOL_GPL(rhashtable_walk_next);

/**
 * rhashtable_walk_peek - Return the next object but don't advance the iterator
 * @iter:	Hash table iterator
 *
 * Returns the next object or NULL when the end of the table is reached.
 *
 * Returns -EAGAIN if resize event occurred.  Note that the iterator
 * will rewind back to the beginning and you may continue to use it.
 */
void *rhashtable_walk_peek(struct rhashtable_iter *iter)
{
	struct rhlist_head *list = iter->list;
	struct rhashtable *ht = iter->ht;
	struct rhash_head *p = iter->p;

	if (p)
		return rht_obj(ht, ht->rhlist ? &list->rhead : p);

	/* No object found in current iter, find next one in the table. */

	if (iter->skip) {
		/* A nonzero skip value points to the next entry in the table
		 * beyond that last one that was found. Decrement skip so
		 * we find the current value. __rhashtable_walk_find_next
		 * will restore the original value of skip assuming that
		 * the table hasn't changed.
		 */
		iter->skip--;
	}

	return __rhashtable_walk_find_next(iter);
}
EXPORT_SYMBOL_GPL(rhashtable_walk_peek);

/**
 * rhashtable_walk_stop - Finish a hash table walk
 * @iter:	Hash table iterator
 *
 * Finish a hash table walk.  Does not reset the iterator to the start of the
 * hash table.
 */
void rhashtable_walk_stop(struct rhashtable_iter *iter)
	__releases(RCU)
{
	struct rhashtable *ht;
	struct bucket_table *tbl = iter->walker.tbl;

	if (!tbl)
		goto out;

	ht = iter->ht;

	spin_lock(&ht->lock);
	if (tbl->rehash < tbl->size)
		list_add(&iter->walker.list, &tbl->walkers);
	else
		iter->walker.tbl = NULL;
	spin_unlock(&ht->lock);

out:
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rhashtable_walk_stop);

static size_t rounded_hashtable_size(const struct rhashtable_params *params)
{
	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
		   (unsigned long)params->min_size);
}

static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
{
	return jhash2(key, length, seed);
}

/**
 * rhashtable_init - initialize a new hash table
 * @ht:		hash table to be initialized
 * @params:	configuration parameters
 *
 * Initializes a new hash table based on the provided configuration
 * parameters. A table can be configured either with a variable or
 * fixed length key:
 *
 * Configuration Example 1: Fixed length keys
 * struct test_obj {
 *	int			key;
 *	void *			my_member;
 *	struct rhash_head	node;
 * };
 *
 * struct rhashtable_params params = {
 *	.head_offset = offsetof(struct test_obj, node),
 *	.key_offset = offsetof(struct test_obj, key),
 *	.key_len = sizeof(int),
 *	.hashfn = jhash,
 * };
 *
 * Configuration Example 2: Variable length keys
 * struct test_obj {
 *	[...]
 *	struct rhash_head	node;
 * };
 *
 * u32 my_hash_fn(const void *data, u32 len, u32 seed)
 * {
 *	struct test_obj *obj = data;
 *
 *	return [... hash ...];
 * }
 *
 * struct rhashtable_params params = {
 *	.head_offset = offsetof(struct test_obj, node),
 *	.hashfn = jhash,
 *	.obj_hashfn = my_hash_fn,
 * };
 */
int rhashtable_init(struct rhashtable *ht,
		    const struct rhashtable_params *params)
{
	struct bucket_table *tbl;
	size_t size;

	size = HASH_DEFAULT_SIZE;

	if ((!params->key_len && !params->obj_hashfn) ||
	    (params->obj_hashfn && !params->obj_cmpfn))
		return -EINVAL;

	memset(ht, 0, sizeof(*ht));
	mutex_init(&ht->mutex);
	spin_lock_init(&ht->lock);
	memcpy(&ht->p, params, sizeof(*params));

	if (params->min_size)
		ht->p.min_size = roundup_pow_of_two(params->min_size);

	/* Cap total entries at 2^31 to avoid nelems overflow. */
	ht->max_elems = 1u << 31;

	if (params->max_size) {
		ht->p.max_size = rounddown_pow_of_two(params->max_size);
		if (ht->p.max_size < ht->max_elems / 2)
			ht->max_elems = ht->p.max_size * 2;
	}

	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);

	if (params->nelem_hint)
		size = rounded_hashtable_size(&ht->p);

	if (params->locks_mul)
		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
	else
		ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;

	ht->key_len = ht->p.key_len;
	if (!params->hashfn) {
		ht->p.hashfn = jhash;

		if (!(ht->key_len & (sizeof(u32) - 1))) {
			ht->key_len /= sizeof(u32);
			ht->p.hashfn = rhashtable_jhash2;
		}
	}

	tbl = bucket_table_alloc(ht, size, GFP_KERNEL);
	if (tbl == NULL)
		return -ENOMEM;

	atomic_set(&ht->nelems, 0);

	RCU_INIT_POINTER(ht->tbl, tbl);

	INIT_WORK(&ht->run_work, rht_deferred_worker);

	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_init);

/**
 * rhltable_init - initialize a new hash list table
 * @hlt:	hash list table to be initialized
 * @params:	configuration parameters
 *
 * Initializes a new hash list table.
 *
 * See documentation for rhashtable_init.
 */
int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params)
{
	int err;

	err = rhashtable_init(&hlt->ht, params);
	hlt->ht.rhlist = true;
	return err;
}
EXPORT_SYMBOL_GPL(rhltable_init);

static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj,
				void (*free_fn)(void *ptr, void *arg),
				void *arg)
{
	struct rhlist_head *list;

	if (!ht->rhlist) {
		free_fn(rht_obj(ht, obj), arg);
		return;
	}

	list = container_of(obj, struct rhlist_head, rhead);
	do {
		obj = &list->rhead;
		list = rht_dereference(list->next, ht);
		free_fn(rht_obj(ht, obj), arg);
	} while (list);
}

/**
 * rhashtable_free_and_destroy - free elements and destroy hash table
 * @ht:		the hash table to destroy
 * @free_fn:	callback to release resources of element
 * @arg:	pointer passed to free_fn
 *
 * Stops an eventual async resize. If defined, invokes free_fn for each
 * element to releasal resources. Please note that RCU protected
 * readers may still be accessing the elements. Releasing of resources
 * must occur in a compatible manner. Then frees the bucket array.
 *
 * This function will eventually sleep to wait for an async resize
 * to complete. The caller is responsible that no further write operations
 * occurs in parallel.
 */
void rhashtable_free_and_destroy(struct rhashtable *ht,
				 void (*free_fn)(void *ptr, void *arg),
				 void *arg)
{
	struct bucket_table *tbl;
	unsigned int i;

	cancel_work_sync(&ht->run_work);

	mutex_lock(&ht->mutex);
	tbl = rht_dereference(ht->tbl, ht);
	if (free_fn) {
		for (i = 0; i < tbl->size; i++) {
			struct rhash_head *pos, *next;

			cond_resched();
			for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
			     next = !rht_is_a_nulls(pos) ?
					rht_dereference(pos->next, ht) : NULL;
			     !rht_is_a_nulls(pos);
			     pos = next,
			     next = !rht_is_a_nulls(pos) ?
					rht_dereference(pos->next, ht) : NULL)
				rhashtable_free_one(ht, pos, free_fn, arg);
		}
	}

	bucket_table_free(tbl);
	mutex_unlock(&ht->mutex);
}
EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);

void rhashtable_destroy(struct rhashtable *ht)
{
	return rhashtable_free_and_destroy(ht, NULL, NULL);
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);

struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
					    unsigned int hash)
{
	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
	static struct rhash_head __rcu *rhnull =
		(struct rhash_head __rcu *)NULLS_MARKER(0);
	unsigned int index = hash & ((1 << tbl->nest) - 1);
	unsigned int size = tbl->size >> tbl->nest;
	unsigned int subhash = hash;
	union nested_table *ntbl;

	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
	ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash);
	subhash >>= tbl->nest;

	while (ntbl && size > (1 << shift)) {
		index = subhash & ((1 << shift) - 1);
		ntbl = rht_dereference_bucket_rcu(ntbl[index].table,
						  tbl, hash);
		size >>= shift;
		subhash >>= shift;
	}

	if (!ntbl)
		return &rhnull;

	return &ntbl[subhash].bucket;

}
EXPORT_SYMBOL_GPL(rht_bucket_nested);

struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
						   struct bucket_table *tbl,
						   unsigned int hash)
{
	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
	unsigned int index = hash & ((1 << tbl->nest) - 1);
	unsigned int size = tbl->size >> tbl->nest;
	union nested_table *ntbl;
	unsigned int shifted;
	unsigned int nhash;

	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
	hash >>= tbl->nest;
	nhash = index;
	shifted = tbl->nest;
	ntbl = nested_table_alloc(ht, &ntbl[index].table,
				  size <= (1 << shift) ? shifted : 0, nhash);

	while (ntbl && size > (1 << shift)) {
		index = hash & ((1 << shift) - 1);
		size >>= shift;
		hash >>= shift;
		nhash |= index << shifted;
		shifted += shift;
		ntbl = nested_table_alloc(ht, &ntbl[index].table,
					  size <= (1 << shift) ? shifted : 0,
					  nhash);
	}

	if (!ntbl)
		return NULL;

	return &ntbl[hash].bucket;

}
EXPORT_SYMBOL_GPL(rht_bucket_nested_insert);
OpenPOWER on IntegriCloud