summaryrefslogtreecommitdiffstats
path: root/lib/rhashtable.c
blob: c2c39495fac6a038c968fa2791f79e41465397ce (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
/*
 * Resizable, Scalable, Concurrent Hash Table
 *
 * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch>
 * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
 *
 * Based on the following paper:
 * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf
 *
 * Code partially derived from nft_hash
 *
 * 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/kernel.h>
#include <linux/init.h>
#include <linux/log2.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>

#define HASH_DEFAULT_SIZE	64UL
#define HASH_MIN_SIZE		4UL
#define BUCKET_LOCKS_PER_CPU   128UL

/* Base bits plus 1 bit for nulls marker */
#define HASH_RESERVED_SPACE	(RHT_BASE_BITS + 1)

enum {
	RHT_LOCK_NORMAL,
	RHT_LOCK_NESTED,
};

/* The bucket lock is selected based on the hash and protects mutations
 * on a group of hash buckets.
 *
 * A maximum of tbl->size/2 bucket locks is allocated. This ensures that
 * a single lock always covers both buckets which may both contains
 * entries which link to the same bucket of the old table during resizing.
 * This allows to simplify the locking as locking the bucket in both
 * tables during resize always guarantee protection.
 *
 * IMPORTANT: When holding the bucket lock of both the old and new table
 * during expansions and shrinking, the old bucket lock must always be
 * acquired first.
 */
static spinlock_t *bucket_lock(const struct bucket_table *tbl, u32 hash)
{
	return &tbl->locks[hash & tbl->locks_mask];
}

static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
{
	return (void *) he - ht->p.head_offset;
}

static u32 rht_bucket_index(const struct bucket_table *tbl, u32 hash)
{
	return hash & (tbl->size - 1);
}

static u32 obj_raw_hashfn(const struct rhashtable *ht, const void *ptr)
{
	u32 hash;

	if (unlikely(!ht->p.key_len))
		hash = ht->p.obj_hashfn(ptr, ht->p.hash_rnd);
	else
		hash = ht->p.hashfn(ptr + ht->p.key_offset, ht->p.key_len,
				    ht->p.hash_rnd);

	return hash >> HASH_RESERVED_SPACE;
}

static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len)
{
	return ht->p.hashfn(key, len, ht->p.hash_rnd) >> HASH_RESERVED_SPACE;
}

static u32 head_hashfn(const struct rhashtable *ht,
		       const struct bucket_table *tbl,
		       const struct rhash_head *he)
{
	return rht_bucket_index(tbl, obj_raw_hashfn(ht, rht_obj(ht, he)));
}

#ifdef CONFIG_PROVE_LOCKING
static void debug_dump_buckets(const struct rhashtable *ht,
			       const struct bucket_table *tbl)
{
	struct rhash_head *he;
	unsigned int i, hash;

	for (i = 0; i < tbl->size; i++) {
		pr_warn(" [Bucket %d] ", i);
		rht_for_each_rcu(he, tbl, i) {
			hash = head_hashfn(ht, tbl, he);
			pr_cont("[hash = %#x, lock = %p] ",
				hash, bucket_lock(tbl, hash));
		}
		pr_cont("\n");
	}

}

static void debug_dump_table(struct rhashtable *ht,
			     const struct bucket_table *tbl,
			     unsigned int hash)
{
	struct bucket_table *old_tbl, *future_tbl;

	pr_emerg("BUG: lock for hash %#x in table %p not held\n",
		 hash, tbl);

	rcu_read_lock();
	future_tbl = rht_dereference_rcu(ht->future_tbl, ht);
	old_tbl = rht_dereference_rcu(ht->tbl, ht);
	if (future_tbl != old_tbl) {
		pr_warn("Future table %p (size: %zd)\n",
			future_tbl, future_tbl->size);
		debug_dump_buckets(ht, future_tbl);
	}

	pr_warn("Table %p (size: %zd)\n", old_tbl, old_tbl->size);
	debug_dump_buckets(ht, old_tbl);

	rcu_read_unlock();
}

#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT))
#define ASSERT_BUCKET_LOCK(HT, TBL, HASH)				\
	do {								\
		if (unlikely(!lockdep_rht_bucket_is_held(TBL, HASH))) {	\
			debug_dump_table(HT, TBL, HASH);		\
			BUG();						\
		}							\
	} while (0)

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 = 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)
#define ASSERT_BUCKET_LOCK(HT, TBL, HASH)
#endif


static struct rhash_head __rcu **bucket_tail(struct bucket_table *tbl, u32 n)
{
	struct rhash_head __rcu **pprev;

	for (pprev = &tbl->buckets[n];
	     !rht_is_a_nulls(rht_dereference_bucket(*pprev, tbl, n));
	     pprev = &rht_dereference_bucket(*pprev, tbl, n)->next)
		;

	return pprev;
}

static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl)
{
	unsigned int i, size;
#if defined(CONFIG_PROVE_LOCKING)
	unsigned int nr_pcpus = 2;
#else
	unsigned int nr_pcpus = num_possible_cpus();
#endif

	nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
	size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul);

	/* Never allocate more than 0.5 locks per bucket */
	size = min_t(unsigned int, size, tbl->size >> 1);

	if (sizeof(spinlock_t) != 0) {
#ifdef CONFIG_NUMA
		if (size * sizeof(spinlock_t) > PAGE_SIZE)
			tbl->locks = vmalloc(size * sizeof(spinlock_t));
		else
#endif
		tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
					   GFP_KERNEL);
		if (!tbl->locks)
			return -ENOMEM;
		for (i = 0; i < size; i++)
			spin_lock_init(&tbl->locks[i]);
	}
	tbl->locks_mask = size - 1;

	return 0;
}

static void bucket_table_free(const struct bucket_table *tbl)
{
	if (tbl)
		kvfree(tbl->locks);

	kvfree(tbl);
}

static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
					       size_t nbuckets)
{
	struct bucket_table *tbl;
	size_t size;
	int i;

	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
	tbl = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
	if (tbl == NULL)
		tbl = vzalloc(size);

	if (tbl == NULL)
		return NULL;

	tbl->size = nbuckets;

	if (alloc_bucket_locks(ht, tbl) < 0) {
		bucket_table_free(tbl);
		return NULL;
	}

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

	return tbl;
}

/**
 * rht_grow_above_75 - returns true if nelems > 0.75 * table-size
 * @ht:		hash table
 * @new_size:	new table size
 */
bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size)
{
	/* Expand table when exceeding 75% load */
	return atomic_read(&ht->nelems) > (new_size / 4 * 3) &&
	       (ht->p.max_shift && atomic_read(&ht->shift) < ht->p.max_shift);
}
EXPORT_SYMBOL_GPL(rht_grow_above_75);

/**
 * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size
 * @ht:		hash table
 * @new_size:	new table size
 */
bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size)
{
	/* Shrink table beneath 30% load */
	return atomic_read(&ht->nelems) < (new_size * 3 / 10) &&
	       (atomic_read(&ht->shift) > ht->p.min_shift);
}
EXPORT_SYMBOL_GPL(rht_shrink_below_30);

static void lock_buckets(struct bucket_table *new_tbl,
			 struct bucket_table *old_tbl, unsigned int hash)
	__acquires(old_bucket_lock)
{
	spin_lock_bh(bucket_lock(old_tbl, hash));
	if (new_tbl != old_tbl)
		spin_lock_bh_nested(bucket_lock(new_tbl, hash),
				    RHT_LOCK_NESTED);
}

static void unlock_buckets(struct bucket_table *new_tbl,
			   struct bucket_table *old_tbl, unsigned int hash)
	__releases(old_bucket_lock)
{
	if (new_tbl != old_tbl)
		spin_unlock_bh(bucket_lock(new_tbl, hash));
	spin_unlock_bh(bucket_lock(old_tbl, hash));
}

/**
 * Unlink entries on bucket which hash to different bucket.
 *
 * Returns true if no more work needs to be performed on the bucket.
 */
static bool hashtable_chain_unzip(struct rhashtable *ht,
				  const struct bucket_table *new_tbl,
				  struct bucket_table *old_tbl,
				  size_t old_hash)
{
	struct rhash_head *he, *p, *next;
	unsigned int new_hash, new_hash2;

	ASSERT_BUCKET_LOCK(ht, old_tbl, old_hash);

	/* Old bucket empty, no work needed. */
	p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
				   old_hash);
	if (rht_is_a_nulls(p))
		return false;

	new_hash = head_hashfn(ht, new_tbl, p);
	ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash);

	/* Advance the old bucket pointer one or more times until it
	 * reaches a node that doesn't hash to the same bucket as the
	 * previous node p. Call the previous node p;
	 */
	rht_for_each_continue(he, p->next, old_tbl, old_hash) {
		new_hash2 = head_hashfn(ht, new_tbl, he);
		ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash2);

		if (new_hash != new_hash2)
			break;
		p = he;
	}
	rcu_assign_pointer(old_tbl->buckets[old_hash], p->next);

	/* Find the subsequent node which does hash to the same
	 * bucket as node P, or NULL if no such node exists.
	 */
	INIT_RHT_NULLS_HEAD(next, ht, old_hash);
	if (!rht_is_a_nulls(he)) {
		rht_for_each_continue(he, he->next, old_tbl, old_hash) {
			if (head_hashfn(ht, new_tbl, he) == new_hash) {
				next = he;
				break;
			}
		}
	}

	/* Set p's next pointer to that subsequent node pointer,
	 * bypassing the nodes which do not hash to p's bucket
	 */
	rcu_assign_pointer(p->next, next);

	p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
				   old_hash);

	return !rht_is_a_nulls(p);
}

static void link_old_to_new(struct bucket_table *new_tbl,
			    unsigned int new_hash, struct rhash_head *entry)
{
	rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), entry);
}

/**
 * rhashtable_expand - Expand hash table while allowing concurrent lookups
 * @ht:		the hash table to expand
 *
 * A secondary bucket array is allocated and the hash entries are migrated
 * while keeping them on both lists until the end of the RCU grace period.
 *
 * This function may only be called in a context where it is safe to call
 * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
 *
 * The caller must ensure that no concurrent resizing occurs by holding
 * ht->mutex.
 *
 * It is valid to have concurrent insertions and deletions protected by per
 * bucket locks or concurrent RCU protected lookups and traversals.
 */
int rhashtable_expand(struct rhashtable *ht)
{
	struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
	struct rhash_head *he;
	unsigned int new_hash, old_hash;
	bool complete = false;

	ASSERT_RHT_MUTEX(ht);

	new_tbl = bucket_table_alloc(ht, old_tbl->size * 2);
	if (new_tbl == NULL)
		return -ENOMEM;

	atomic_inc(&ht->shift);

	/* Make insertions go into the new, empty table right away. Deletions
	 * and lookups will be attempted in both tables until we synchronize.
	 * The synchronize_rcu() guarantees for the new table to be picked up
	 * so no new additions go into the old table while we relink.
	 */
	rcu_assign_pointer(ht->future_tbl, new_tbl);
	synchronize_rcu();

	/* For each new bucket, search the corresponding old bucket for the
	 * first entry that hashes to the new bucket, and link the end of
	 * newly formed bucket chain (containing entries added to future
	 * table) to that entry. Since all the entries which will end up in
	 * the new bucket appear in the same old bucket, this constructs an
	 * entirely valid new hash table, but with multiple buckets
	 * "zipped" together into a single imprecise chain.
	 */
	for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
		old_hash = rht_bucket_index(old_tbl, new_hash);
		lock_buckets(new_tbl, old_tbl, new_hash);
		rht_for_each(he, old_tbl, old_hash) {
			if (head_hashfn(ht, new_tbl, he) == new_hash) {
				link_old_to_new(new_tbl, new_hash, he);
				break;
			}
		}
		unlock_buckets(new_tbl, old_tbl, new_hash);
	}

	/* Publish the new table pointer. Lookups may now traverse
	 * the new table, but they will not benefit from any
	 * additional efficiency until later steps unzip the buckets.
	 */
	rcu_assign_pointer(ht->tbl, new_tbl);

	/* Unzip interleaved hash chains */
	while (!complete && !ht->being_destroyed) {
		/* Wait for readers. All new readers will see the new
		 * table, and thus no references to the old table will
		 * remain.
		 */
		synchronize_rcu();

		/* For each bucket in the old table (each of which
		 * contains items from multiple buckets of the new
		 * table): ...
		 */
		complete = true;
		for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
			lock_buckets(new_tbl, old_tbl, old_hash);

			if (hashtable_chain_unzip(ht, new_tbl, old_tbl,
						  old_hash))
				complete = false;

			unlock_buckets(new_tbl, old_tbl, old_hash);
		}
	}

	synchronize_rcu();

	bucket_table_free(old_tbl);
	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_expand);

/**
 * rhashtable_shrink - Shrink hash table while allowing concurrent lookups
 * @ht:		the hash table to shrink
 *
 * This function may only be called in a context where it is safe to call
 * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
 *
 * 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.
 */
int rhashtable_shrink(struct rhashtable *ht)
{
	struct bucket_table *new_tbl, *tbl = rht_dereference(ht->tbl, ht);
	unsigned int new_hash;

	ASSERT_RHT_MUTEX(ht);

	new_tbl = bucket_table_alloc(ht, tbl->size / 2);
	if (new_tbl == NULL)
		return -ENOMEM;

	rcu_assign_pointer(ht->future_tbl, new_tbl);
	synchronize_rcu();

	/* Link the first entry in the old bucket to the end of the
	 * bucket in the new table. As entries are concurrently being
	 * added to the new table, lock down the new bucket. As we
	 * always divide the size in half when shrinking, each bucket
	 * in the new table maps to exactly two buckets in the old
	 * table.
	 */
	for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
		lock_buckets(new_tbl, tbl, new_hash);

		rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
				   tbl->buckets[new_hash]);
		rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
				   tbl->buckets[new_hash + new_tbl->size]);

		unlock_buckets(new_tbl, tbl, new_hash);
	}

	/* Publish the new, valid hash table */
	rcu_assign_pointer(ht->tbl, new_tbl);
	atomic_dec(&ht->shift);

	/* Wait for readers. No new readers will have references to the
	 * old hash table.
	 */
	synchronize_rcu();

	bucket_table_free(tbl);

	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_shrink);

static void rht_deferred_worker(struct work_struct *work)
{
	struct rhashtable *ht;
	struct bucket_table *tbl;
	struct rhashtable_walker *walker;

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

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

	list_for_each_entry(walker, &ht->walkers, list)
		walker->resize = true;

	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
		rhashtable_expand(ht);
	else if (ht->p.shrink_decision && ht->p.shrink_decision(ht, tbl->size))
		rhashtable_shrink(ht);

unlock:
	mutex_unlock(&ht->mutex);
}

static void rhashtable_wakeup_worker(struct rhashtable *ht)
{
	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
	struct bucket_table *new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
	size_t size = tbl->size;

	/* Only adjust the table if no resizing is currently in progress. */
	if (tbl == new_tbl &&
	    ((ht->p.grow_decision && ht->p.grow_decision(ht, size)) ||
	     (ht->p.shrink_decision && ht->p.shrink_decision(ht, size))))
		schedule_work(&ht->run_work);
}

static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
				struct bucket_table *tbl, u32 hash)
{
	struct rhash_head *head = rht_dereference_bucket(tbl->buckets[hash],
							 tbl, hash);

	if (rht_is_a_nulls(head))
		INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
	else
		RCU_INIT_POINTER(obj->next, head);

	rcu_assign_pointer(tbl->buckets[hash], obj);

	atomic_inc(&ht->nelems);

	rhashtable_wakeup_worker(ht);
}

/**
 * rhashtable_insert - insert object into hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 *
 * Will take a per bucket spinlock to protect against mutual mutations
 * on the same bucket. Multiple insertions may occur in parallel unless
 * they map to the same bucket lock.
 *
 * It is safe to call this function from atomic context.
 *
 * Will trigger an automatic deferred table resizing if the size grows
 * beyond the watermark indicated by grow_decision() which can be passed
 * to rhashtable_init().
 */
void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
{
	struct bucket_table *tbl, *old_tbl;
	unsigned hash;

	rcu_read_lock();

	tbl = rht_dereference_rcu(ht->future_tbl, ht);
	old_tbl = rht_dereference_rcu(ht->tbl, ht);
	hash = head_hashfn(ht, tbl, obj);

	lock_buckets(tbl, old_tbl, hash);
	__rhashtable_insert(ht, obj, tbl, hash);
	unlock_buckets(tbl, old_tbl, hash);

	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rhashtable_insert);

/**
 * rhashtable_remove - remove object from hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 *
 * Since the hash chain is single linked, the removal operation needs to
 * walk the bucket chain upon removal. The removal operation is thus
 * considerable slow if the hash table is not correctly sized.
 *
 * Will automatically shrink the table via rhashtable_expand() if the
 * shrink_decision function specified at rhashtable_init() returns true.
 *
 * The caller must ensure that no concurrent table mutations occur. It is
 * however valid to have concurrent lookups if they are RCU protected.
 */
bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
{
	struct bucket_table *tbl, *new_tbl, *old_tbl;
	struct rhash_head __rcu **pprev;
	struct rhash_head *he;
	unsigned int hash, new_hash;
	bool ret = false;

	rcu_read_lock();
	tbl = old_tbl = rht_dereference_rcu(ht->tbl, ht);
	new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
	new_hash = head_hashfn(ht, new_tbl, obj);

	lock_buckets(new_tbl, old_tbl, new_hash);
restart:
	hash = rht_bucket_index(tbl, new_hash);
	pprev = &tbl->buckets[hash];
	rht_for_each(he, tbl, hash) {
		if (he != obj) {
			pprev = &he->next;
			continue;
		}

		rcu_assign_pointer(*pprev, obj->next);

		ret = true;
		break;
	}

	/* The entry may be linked in either 'tbl', 'future_tbl', or both.
	 * 'future_tbl' only exists for a short period of time during
	 * resizing. Thus traversing both is fine and the added cost is
	 * very rare.
	 */
	if (tbl != new_tbl) {
		tbl = new_tbl;
		goto restart;
	}

	unlock_buckets(new_tbl, old_tbl, new_hash);

	if (ret) {
		atomic_dec(&ht->nelems);
		rhashtable_wakeup_worker(ht);
	}

	rcu_read_unlock();

	return ret;
}
EXPORT_SYMBOL_GPL(rhashtable_remove);

struct rhashtable_compare_arg {
	struct rhashtable *ht;
	const void *key;
};

static bool rhashtable_compare(void *ptr, void *arg)
{
	struct rhashtable_compare_arg *x = arg;
	struct rhashtable *ht = x->ht;

	return !memcmp(ptr + ht->p.key_offset, x->key, ht->p.key_len);
}

/**
 * rhashtable_lookup - lookup key in hash table
 * @ht:		hash table
 * @key:	pointer to key
 *
 * Computes the hash value for the key and traverses the bucket chain looking
 * for a entry with an identical key. The first matching entry is returned.
 *
 * This lookup function may only be used for fixed key hash table (key_len
 * parameter set). It will BUG() if used inappropriately.
 *
 * Lookups may occur in parallel with hashtable mutations and resizing.
 */
void *rhashtable_lookup(struct rhashtable *ht, const void *key)
{
	struct rhashtable_compare_arg arg = {
		.ht = ht,
		.key = key,
	};

	BUG_ON(!ht->p.key_len);

	return rhashtable_lookup_compare(ht, key, &rhashtable_compare, &arg);
}
EXPORT_SYMBOL_GPL(rhashtable_lookup);

/**
 * rhashtable_lookup_compare - search hash table with compare function
 * @ht:		hash table
 * @key:	the pointer to the key
 * @compare:	compare function, must return true on match
 * @arg:	argument passed on to compare function
 *
 * Traverses the bucket chain behind the provided hash value and calls the
 * specified compare function for each entry.
 *
 * Lookups may occur in parallel with hashtable mutations and resizing.
 *
 * Returns the first entry on which the compare function returned true.
 */
void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key,
				bool (*compare)(void *, void *), void *arg)
{
	const struct bucket_table *tbl, *old_tbl;
	struct rhash_head *he;
	u32 hash;

	rcu_read_lock();

	old_tbl = rht_dereference_rcu(ht->tbl, ht);
	tbl = rht_dereference_rcu(ht->future_tbl, ht);
	hash = key_hashfn(ht, key, ht->p.key_len);
restart:
	rht_for_each_rcu(he, tbl, rht_bucket_index(tbl, hash)) {
		if (!compare(rht_obj(ht, he), arg))
			continue;
		rcu_read_unlock();
		return rht_obj(ht, he);
	}

	if (unlikely(tbl != old_tbl)) {
		tbl = old_tbl;
		goto restart;
	}
	rcu_read_unlock();

	return NULL;
}
EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);

/**
 * rhashtable_lookup_insert - lookup and insert object into hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 *
 * Locks down the bucket chain in both the old and new table if a resize
 * is in progress to ensure that writers can't remove from the old table
 * and can't insert to the new table during the atomic operation of search
 * and insertion. Searches for duplicates in both the old and new table if
 * a resize is in progress.
 *
 * This lookup function may only be used for fixed key hash table (key_len
 * parameter set). It will BUG() if used inappropriately.
 *
 * It is safe to call this function from atomic context.
 *
 * Will trigger an automatic deferred table resizing if the size grows
 * beyond the watermark indicated by grow_decision() which can be passed
 * to rhashtable_init().
 */
bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj)
{
	struct rhashtable_compare_arg arg = {
		.ht = ht,
		.key = rht_obj(ht, obj) + ht->p.key_offset,
	};

	BUG_ON(!ht->p.key_len);

	return rhashtable_lookup_compare_insert(ht, obj, &rhashtable_compare,
						&arg);
}
EXPORT_SYMBOL_GPL(rhashtable_lookup_insert);

/**
 * rhashtable_lookup_compare_insert - search and insert object to hash table
 *                                    with compare function
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 * @compare:	compare function, must return true on match
 * @arg:	argument passed on to compare function
 *
 * Locks down the bucket chain in both the old and new table if a resize
 * is in progress to ensure that writers can't remove from the old table
 * and can't insert to the new table during the atomic operation of search
 * and insertion. Searches for duplicates in both the old and new table if
 * a resize is in progress.
 *
 * Lookups may occur in parallel with hashtable mutations and resizing.
 *
 * Will trigger an automatic deferred table resizing if the size grows
 * beyond the watermark indicated by grow_decision() which can be passed
 * to rhashtable_init().
 */
bool rhashtable_lookup_compare_insert(struct rhashtable *ht,
				      struct rhash_head *obj,
				      bool (*compare)(void *, void *),
				      void *arg)
{
	struct bucket_table *new_tbl, *old_tbl;
	u32 new_hash;
	bool success = true;

	BUG_ON(!ht->p.key_len);

	rcu_read_lock();
	old_tbl = rht_dereference_rcu(ht->tbl, ht);
	new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
	new_hash = head_hashfn(ht, new_tbl, obj);

	lock_buckets(new_tbl, old_tbl, new_hash);

	if (rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset,
				      compare, arg)) {
		success = false;
		goto exit;
	}

	__rhashtable_insert(ht, obj, new_tbl, new_hash);

exit:
	unlock_buckets(new_tbl, old_tbl, new_hash);
	rcu_read_unlock();

	return success;
}
EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert);

/**
 * rhashtable_walk_init - 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 sleep so you must not call it from interrupt
 * context or with spin locks held.
 *
 * You must call rhashtable_walk_exit if this function returns
 * successfully.
 */
int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter)
{
	iter->ht = ht;
	iter->p = NULL;
	iter->slot = 0;
	iter->skip = 0;

	iter->walker = kmalloc(sizeof(*iter->walker), GFP_KERNEL);
	if (!iter->walker)
		return -ENOMEM;

	mutex_lock(&ht->mutex);
	list_add(&iter->walker->list, &ht->walkers);
	mutex_unlock(&ht->mutex);

	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_init);

/**
 * 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)
{
	mutex_lock(&iter->ht->mutex);
	list_del(&iter->walker->list);
	mutex_unlock(&iter->ht->mutex);
	kfree(iter->walker);
}
EXPORT_SYMBOL_GPL(rhashtable_walk_exit);

/**
 * rhashtable_walk_start - Start a hash table walk
 * @iter:	Hash table iterator
 *
 * Start a hash table walk.  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.
 */
int rhashtable_walk_start(struct rhashtable_iter *iter)
{
	rcu_read_lock();

	if (iter->walker->resize) {
		iter->slot = 0;
		iter->skip = 0;
		iter->walker->resize = false;
		return -EAGAIN;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_start);

/**
 * 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 occured.  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)
{
	const struct bucket_table *tbl;
	struct rhashtable *ht = iter->ht;
	struct rhash_head *p = iter->p;
	void *obj = NULL;

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

	if (p) {
		p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot);
		goto next;
	}

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

		rht_for_each_rcu(p, tbl, iter->slot) {
			if (!skip)
				break;
			skip--;
		}

next:
		if (!rht_is_a_nulls(p)) {
			iter->skip++;
			iter->p = p;
			obj = rht_obj(ht, p);
			goto out;
		}

		iter->skip = 0;
	}

	iter->p = NULL;

out:
	if (iter->walker->resize) {
		iter->p = NULL;
		iter->slot = 0;
		iter->skip = 0;
		iter->walker->resize = false;
		return ERR_PTR(-EAGAIN);
	}

	return obj;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_next);

/**
 * rhashtable_walk_stop - Finish a hash table walk
 * @iter:	Hash table iterator
 *
 * Finish a hash table walk.
 */
void rhashtable_walk_stop(struct rhashtable_iter *iter)
{
	rcu_read_unlock();
	iter->p = NULL;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_stop);

static size_t rounded_hashtable_size(struct rhashtable_params *params)
{
	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
		   1UL << params->min_shift);
}

/**
 * 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,
 *	.nulls_base = (1U << RHT_BASE_SHIFT),
 * };
 *
 * Configuration Example 2: Variable length keys
 * struct test_obj {
 *	[...]
 *	struct rhash_head	node;
 * };
 *
 * u32 my_hash_fn(const void *data, 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, struct rhashtable_params *params)
{
	struct bucket_table *tbl;
	size_t size;

	size = HASH_DEFAULT_SIZE;

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

	if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
		return -EINVAL;

	params->min_shift = max_t(size_t, params->min_shift,
				  ilog2(HASH_MIN_SIZE));

	if (params->nelem_hint)
		size = rounded_hashtable_size(params);

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

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

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

	atomic_set(&ht->nelems, 0);
	atomic_set(&ht->shift, ilog2(tbl->size));
	RCU_INIT_POINTER(ht->tbl, tbl);
	RCU_INIT_POINTER(ht->future_tbl, tbl);

	if (!ht->p.hash_rnd)
		get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));

	if (ht->p.grow_decision || ht->p.shrink_decision)
		INIT_WORK(&ht->run_work, rht_deferred_worker);

	return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_init);

/**
 * rhashtable_destroy - destroy hash table
 * @ht:		the hash table to destroy
 *
 * Frees the bucket array. This function is not rcu safe, therefore the caller
 * has to make sure that no resizing may happen by unpublishing the hashtable
 * and waiting for the quiescent cycle before releasing the bucket array.
 */
void rhashtable_destroy(struct rhashtable *ht)
{
	ht->being_destroyed = true;

	if (ht->p.grow_decision || ht->p.shrink_decision)
		cancel_work_sync(&ht->run_work);

	mutex_lock(&ht->mutex);
	bucket_table_free(rht_dereference(ht->tbl, ht));
	mutex_unlock(&ht->mutex);
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);
OpenPOWER on IntegriCloud