summaryrefslogtreecommitdiffstats
path: root/include/linux/rhashtable.h
blob: 63bd7601b6dee14074061c147ebeeb7407d6e65a (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
/*
 * 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.
 */

#ifndef _LINUX_RHASHTABLE_H
#define _LINUX_RHASHTABLE_H

#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/jhash.h>
#include <linux/list_nulls.h>
#include <linux/workqueue.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>

/*
 * The end of the chain is marked with a special nulls marks which has
 * the following format:
 *
 * +-------+-----------------------------------------------------+-+
 * | Base  |                      Hash                           |1|
 * +-------+-----------------------------------------------------+-+
 *
 * Base (4 bits) : Reserved to distinguish between multiple tables.
 *                 Specified via &struct rhashtable_params.nulls_base.
 * Hash (27 bits): Full hash (unmasked) of first element added to bucket
 * 1 (1 bit)     : Nulls marker (always set)
 *
 * The remaining bits of the next pointer remain unused for now.
 */
#define RHT_BASE_BITS		4
#define RHT_HASH_BITS		27
#define RHT_BASE_SHIFT		RHT_HASH_BITS

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

struct rhash_head {
	struct rhash_head __rcu		*next;
};

/**
 * struct bucket_table - Table of hash buckets
 * @size: Number of hash buckets
 * @rehash: Current bucket being rehashed
 * @hash_rnd: Random seed to fold into hash
 * @locks_mask: Mask to apply before accessing locks[]
 * @locks: Array of spinlocks protecting individual buckets
 * @walkers: List of active walkers
 * @rcu: RCU structure for freeing the table
 * @future_tbl: Table under construction during rehashing
 * @buckets: size * hash buckets
 */
struct bucket_table {
	unsigned int		size;
	unsigned int		rehash;
	u32			hash_rnd;
	unsigned int		locks_mask;
	spinlock_t		*locks;
	struct list_head	walkers;
	struct rcu_head		rcu;

	struct bucket_table __rcu *future_tbl;

	struct rhash_head __rcu	*buckets[] ____cacheline_aligned_in_smp;
};

/**
 * struct rhashtable_compare_arg - Key for the function rhashtable_compare
 * @ht: Hash table
 * @key: Key to compare against
 */
struct rhashtable_compare_arg {
	struct rhashtable *ht;
	const void *key;
};

typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
			       const void *obj);

struct rhashtable;

/**
 * struct rhashtable_params - Hash table construction parameters
 * @nelem_hint: Hint on number of elements, should be 75% of desired size
 * @key_len: Length of key
 * @key_offset: Offset of key in struct to be hashed
 * @head_offset: Offset of rhash_head in struct to be hashed
 * @insecure_max_entries: Maximum number of entries (may be exceeded)
 * @max_size: Maximum size while expanding
 * @min_size: Minimum size while shrinking
 * @nulls_base: Base value to generate nulls marker
 * @insecure_elasticity: Set to true to disable chain length checks
 * @automatic_shrinking: Enable automatic shrinking of tables
 * @locks_mul: Number of bucket locks to allocate per cpu (default: 128)
 * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
 * @obj_hashfn: Function to hash object
 * @obj_cmpfn: Function to compare key with object
 */
struct rhashtable_params {
	size_t			nelem_hint;
	size_t			key_len;
	size_t			key_offset;
	size_t			head_offset;
	unsigned int		insecure_max_entries;
	unsigned int		max_size;
	unsigned int		min_size;
	u32			nulls_base;
	bool			insecure_elasticity;
	bool			automatic_shrinking;
	size_t			locks_mul;
	rht_hashfn_t		hashfn;
	rht_obj_hashfn_t	obj_hashfn;
	rht_obj_cmpfn_t		obj_cmpfn;
};

/**
 * struct rhashtable - Hash table handle
 * @tbl: Bucket table
 * @nelems: Number of elements in table
 * @key_len: Key length for hashfn
 * @elasticity: Maximum chain length before rehash
 * @p: Configuration parameters
 * @run_work: Deferred worker to expand/shrink asynchronously
 * @mutex: Mutex to protect current/future table swapping
 * @lock: Spin lock to protect walker list
 */
struct rhashtable {
	struct bucket_table __rcu	*tbl;
	atomic_t			nelems;
	unsigned int			key_len;
	unsigned int			elasticity;
	struct rhashtable_params	p;
	struct work_struct		run_work;
	struct mutex                    mutex;
	spinlock_t			lock;
};

/**
 * struct rhashtable_walker - Hash table walker
 * @list: List entry on list of walkers
 * @tbl: The table that we were walking over
 */
struct rhashtable_walker {
	struct list_head list;
	struct bucket_table *tbl;
};

/**
 * struct rhashtable_iter - Hash table iterator, fits into netlink cb
 * @ht: Table to iterate through
 * @p: Current pointer
 * @walker: Associated rhashtable walker
 * @slot: Current slot
 * @skip: Number of entries to skip in slot
 */
struct rhashtable_iter {
	struct rhashtable *ht;
	struct rhash_head *p;
	struct rhashtable_walker *walker;
	unsigned int slot;
	unsigned int skip;
};

static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
{
	return NULLS_MARKER(ht->p.nulls_base + hash);
}

#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \
	((ptr) = (typeof(ptr)) rht_marker(ht, hash))

static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
{
	return ((unsigned long) ptr & 1);
}

static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr)
{
	return ((unsigned long) ptr) >> 1;
}

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

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

static inline unsigned int rht_key_hashfn(
	struct rhashtable *ht, const struct bucket_table *tbl,
	const void *key, const struct rhashtable_params params)
{
	unsigned int hash;

	/* params must be equal to ht->p if it isn't constant. */
	if (!__builtin_constant_p(params.key_len))
		hash = ht->p.hashfn(key, ht->key_len, tbl->hash_rnd);
	else if (params.key_len) {
		unsigned int key_len = params.key_len;

		if (params.hashfn)
			hash = params.hashfn(key, key_len, tbl->hash_rnd);
		else if (key_len & (sizeof(u32) - 1))
			hash = jhash(key, key_len, tbl->hash_rnd);
		else
			hash = jhash2(key, key_len / sizeof(u32),
				      tbl->hash_rnd);
	} else {
		unsigned int key_len = ht->p.key_len;

		if (params.hashfn)
			hash = params.hashfn(key, key_len, tbl->hash_rnd);
		else
			hash = jhash(key, key_len, tbl->hash_rnd);
	}

	return rht_bucket_index(tbl, hash);
}

static inline unsigned int rht_head_hashfn(
	struct rhashtable *ht, const struct bucket_table *tbl,
	const struct rhash_head *he, const struct rhashtable_params params)
{
	const char *ptr = rht_obj(ht, he);

	return likely(params.obj_hashfn) ?
	       rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?:
							    ht->p.key_len,
						       tbl->hash_rnd)) :
	       rht_key_hashfn(ht, tbl, ptr + params.key_offset, params);
}

/**
 * rht_grow_above_75 - returns true if nelems > 0.75 * table-size
 * @ht:		hash table
 * @tbl:	current table
 */
static inline bool rht_grow_above_75(const struct rhashtable *ht,
				     const struct bucket_table *tbl)
{
	/* Expand table when exceeding 75% load */
	return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) &&
	       (!ht->p.max_size || tbl->size < ht->p.max_size);
}

/**
 * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size
 * @ht:		hash table
 * @tbl:	current table
 */
static inline bool rht_shrink_below_30(const struct rhashtable *ht,
				       const struct bucket_table *tbl)
{
	/* Shrink table beneath 30% load */
	return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) &&
	       tbl->size > ht->p.min_size;
}

/**
 * rht_grow_above_100 - returns true if nelems > table-size
 * @ht:		hash table
 * @tbl:	current table
 */
static inline bool rht_grow_above_100(const struct rhashtable *ht,
				      const struct bucket_table *tbl)
{
	return atomic_read(&ht->nelems) > tbl->size &&
		(!ht->p.max_size || tbl->size < ht->p.max_size);
}

/**
 * rht_grow_above_max - returns true if table is above maximum
 * @ht:		hash table
 * @tbl:	current table
 */
static inline bool rht_grow_above_max(const struct rhashtable *ht,
				      const struct bucket_table *tbl)
{
	return ht->p.insecure_max_entries &&
	       atomic_read(&ht->nelems) >= ht->p.insecure_max_entries;
}

/* 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 inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl,
					  unsigned int hash)
{
	return &tbl->locks[hash & tbl->locks_mask];
}

#ifdef CONFIG_PROVE_LOCKING
int lockdep_rht_mutex_is_held(struct rhashtable *ht);
int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
#else
static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht)
{
	return 1;
}

static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
					     u32 hash)
{
	return 1;
}
#endif /* CONFIG_PROVE_LOCKING */

int rhashtable_init(struct rhashtable *ht,
		    const struct rhashtable_params *params);

struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
					    const void *key,
					    struct rhash_head *obj,
					    struct bucket_table *old_tbl);
int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);

int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
void rhashtable_walk_exit(struct rhashtable_iter *iter);
int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU);
void *rhashtable_walk_next(struct rhashtable_iter *iter);
void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU);

void rhashtable_free_and_destroy(struct rhashtable *ht,
				 void (*free_fn)(void *ptr, void *arg),
				 void *arg);
void rhashtable_destroy(struct rhashtable *ht);

#define rht_dereference(p, ht) \
	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))

#define rht_dereference_rcu(p, ht) \
	rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht))

#define rht_dereference_bucket(p, tbl, hash) \
	rcu_dereference_protected(p, lockdep_rht_bucket_is_held(tbl, hash))

#define rht_dereference_bucket_rcu(p, tbl, hash) \
	rcu_dereference_check(p, lockdep_rht_bucket_is_held(tbl, hash))

#define rht_entry(tpos, pos, member) \
	({ tpos = container_of(pos, typeof(*tpos), member); 1; })

/**
 * rht_for_each_continue - continue iterating over hash chain
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @head:	the previous &struct rhash_head to continue from
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 */
#define rht_for_each_continue(pos, head, tbl, hash) \
	for (pos = rht_dereference_bucket(head, tbl, hash); \
	     !rht_is_a_nulls(pos); \
	     pos = rht_dereference_bucket((pos)->next, tbl, hash))

/**
 * rht_for_each - iterate over hash chain
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 */
#define rht_for_each(pos, tbl, hash) \
	rht_for_each_continue(pos, (tbl)->buckets[hash], tbl, hash)

/**
 * rht_for_each_entry_continue - continue iterating over hash chain
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @head:	the previous &struct rhash_head to continue from
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 * @member:	name of the &struct rhash_head within the hashable struct.
 */
#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member)	\
	for (pos = rht_dereference_bucket(head, tbl, hash);		\
	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	\
	     pos = rht_dereference_bucket((pos)->next, tbl, hash))

/**
 * rht_for_each_entry - iterate over hash chain of given type
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 * @member:	name of the &struct rhash_head within the hashable struct.
 */
#define rht_for_each_entry(tpos, pos, tbl, hash, member)		\
	rht_for_each_entry_continue(tpos, pos, (tbl)->buckets[hash],	\
				    tbl, hash, member)

/**
 * rht_for_each_entry_safe - safely iterate over hash chain of given type
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @next:	the &struct rhash_head to use as next in loop cursor.
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 * @member:	name of the &struct rhash_head within the hashable struct.
 *
 * This hash chain list-traversal primitive allows for the looped code to
 * remove the loop cursor from the list.
 */
#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member)	    \
	for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \
	     next = !rht_is_a_nulls(pos) ?				    \
		       rht_dereference_bucket(pos->next, tbl, hash) : NULL; \
	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
	     pos = next,						    \
	     next = !rht_is_a_nulls(pos) ?				    \
		       rht_dereference_bucket(pos->next, tbl, hash) : NULL)

/**
 * rht_for_each_rcu_continue - continue iterating over rcu hash chain
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @head:	the previous &struct rhash_head to continue from
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 *
 * This hash chain list-traversal primitive may safely run concurrently with
 * the _rcu mutation primitives such as rhashtable_insert() as long as the
 * traversal is guarded by rcu_read_lock().
 */
#define rht_for_each_rcu_continue(pos, head, tbl, hash)			\
	for (({barrier(); }),						\
	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		\
	     !rht_is_a_nulls(pos);					\
	     pos = rcu_dereference_raw(pos->next))

/**
 * rht_for_each_rcu - iterate over rcu hash chain
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 *
 * This hash chain list-traversal primitive may safely run concurrently with
 * the _rcu mutation primitives such as rhashtable_insert() as long as the
 * traversal is guarded by rcu_read_lock().
 */
#define rht_for_each_rcu(pos, tbl, hash)				\
	rht_for_each_rcu_continue(pos, (tbl)->buckets[hash], tbl, hash)

/**
 * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @head:	the previous &struct rhash_head to continue from
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 * @member:	name of the &struct rhash_head within the hashable struct.
 *
 * This hash chain list-traversal primitive may safely run concurrently with
 * the _rcu mutation primitives such as rhashtable_insert() as long as the
 * traversal is guarded by rcu_read_lock().
 */
#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \
	for (({barrier(); }),						    \
	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		    \
	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
	     pos = rht_dereference_bucket_rcu(pos->next, tbl, hash))

/**
 * rht_for_each_entry_rcu - iterate over rcu hash chain of given type
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct rhash_head to use as a loop cursor.
 * @tbl:	the &struct bucket_table
 * @hash:	the hash value / bucket index
 * @member:	name of the &struct rhash_head within the hashable struct.
 *
 * This hash chain list-traversal primitive may safely run concurrently with
 * the _rcu mutation primitives such as rhashtable_insert() as long as the
 * traversal is guarded by rcu_read_lock().
 */
#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member)		\
	rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\
					tbl, hash, member)

static inline int rhashtable_compare(struct rhashtable_compare_arg *arg,
				     const void *obj)
{
	struct rhashtable *ht = arg->ht;
	const char *ptr = obj;

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

/**
 * rhashtable_lookup_fast - search hash table, inlined version
 * @ht:		hash table
 * @key:	the pointer to the key
 * @params:	hash table parameters
 *
 * 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.
 *
 * Returns the first entry on which the compare function returned true.
 */
static inline void *rhashtable_lookup_fast(
	struct rhashtable *ht, const void *key,
	const struct rhashtable_params params)
{
	struct rhashtable_compare_arg arg = {
		.ht = ht,
		.key = key,
	};
	const struct bucket_table *tbl;
	struct rhash_head *he;
	unsigned int hash;

	rcu_read_lock();

	tbl = rht_dereference_rcu(ht->tbl, ht);
restart:
	hash = rht_key_hashfn(ht, tbl, key, params);
	rht_for_each_rcu(he, tbl, hash) {
		if (params.obj_cmpfn ?
		    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
		    rhashtable_compare(&arg, rht_obj(ht, he)))
			continue;
		rcu_read_unlock();
		return rht_obj(ht, he);
	}

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

	tbl = rht_dereference_rcu(tbl->future_tbl, ht);
	if (unlikely(tbl))
		goto restart;
	rcu_read_unlock();

	return NULL;
}

/* Internal function, please use rhashtable_insert_fast() instead */
static inline int __rhashtable_insert_fast(
	struct rhashtable *ht, const void *key, struct rhash_head *obj,
	const struct rhashtable_params params)
{
	struct rhashtable_compare_arg arg = {
		.ht = ht,
		.key = key,
	};
	struct bucket_table *tbl, *new_tbl;
	struct rhash_head *head;
	spinlock_t *lock;
	unsigned int elasticity;
	unsigned int hash;
	int err;

restart:
	rcu_read_lock();

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

	/* 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, params);
		lock = rht_bucket_lock(tbl, hash);
		spin_lock_bh(lock);

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

		spin_unlock_bh(lock);
		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
	}

	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
	if (unlikely(new_tbl)) {
		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl);
		if (!IS_ERR_OR_NULL(tbl))
			goto slow_path;

		err = PTR_ERR(tbl);
		goto out;
	}

	err = -E2BIG;
	if (unlikely(rht_grow_above_max(ht, tbl)))
		goto out;

	if (unlikely(rht_grow_above_100(ht, tbl))) {
slow_path:
		spin_unlock_bh(lock);
		err = rhashtable_insert_rehash(ht, tbl);
		rcu_read_unlock();
		if (err)
			return err;

		goto restart;
	}

	err = -EEXIST;
	elasticity = ht->elasticity;
	rht_for_each(head, tbl, hash) {
		if (key &&
		    unlikely(!(params.obj_cmpfn ?
			       params.obj_cmpfn(&arg, rht_obj(ht, head)) :
			       rhashtable_compare(&arg, rht_obj(ht, head)))))
			goto out;
		if (!--elasticity)
			goto slow_path;
	}

	err = 0;

	head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);

	RCU_INIT_POINTER(obj->next, head);

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

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

out:
	spin_unlock_bh(lock);
	rcu_read_unlock();

	return err;
}

/**
 * rhashtable_insert_fast - insert object into hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 * @params:	hash table parameters
 *
 * 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().
 */
static inline int rhashtable_insert_fast(
	struct rhashtable *ht, struct rhash_head *obj,
	const struct rhashtable_params params)
{
	return __rhashtable_insert_fast(ht, NULL, obj, params);
}

/**
 * rhashtable_lookup_insert_fast - lookup and insert object into hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 * @params:	hash table parameters
 *
 * 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().
 */
static inline int rhashtable_lookup_insert_fast(
	struct rhashtable *ht, struct rhash_head *obj,
	const struct rhashtable_params params)
{
	const char *key = rht_obj(ht, obj);

	BUG_ON(ht->p.obj_hashfn);

	return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj,
					params);
}

/**
 * rhashtable_lookup_insert_key - search and insert object to hash table
 *				  with explicit key
 * @ht:		hash table
 * @key:	key
 * @obj:	pointer to hash head inside object
 * @params:	hash table parameters
 *
 * 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().
 *
 * Returns zero on success.
 */
static inline int rhashtable_lookup_insert_key(
	struct rhashtable *ht, const void *key, struct rhash_head *obj,
	const struct rhashtable_params params)
{
	BUG_ON(!ht->p.obj_hashfn || !key);

	return __rhashtable_insert_fast(ht, key, obj, params);
}

/* Internal function, please use rhashtable_remove_fast() instead */
static inline int __rhashtable_remove_fast(
	struct rhashtable *ht, struct bucket_table *tbl,
	struct rhash_head *obj, const struct rhashtable_params params)
{
	struct rhash_head __rcu **pprev;
	struct rhash_head *he;
	spinlock_t * lock;
	unsigned int hash;
	int err = -ENOENT;

	hash = rht_head_hashfn(ht, tbl, obj, params);
	lock = rht_bucket_lock(tbl, hash);

	spin_lock_bh(lock);

	pprev = &tbl->buckets[hash];
	rht_for_each(he, tbl, hash) {
		if (he != obj) {
			pprev = &he->next;
			continue;
		}

		rcu_assign_pointer(*pprev, obj->next);
		err = 0;
		break;
	}

	spin_unlock_bh(lock);

	return err;
}

/**
 * rhashtable_remove_fast - remove object from hash table
 * @ht:		hash table
 * @obj:	pointer to hash head inside object
 * @params:	hash table parameters
 *
 * 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.
 *
 * Returns zero on success, -ENOENT if the entry could not be found.
 */
static inline int rhashtable_remove_fast(
	struct rhashtable *ht, struct rhash_head *obj,
	const struct rhashtable_params params)
{
	struct bucket_table *tbl;
	int err;

	rcu_read_lock();

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

	/* Because we have already taken (and released) the bucket
	 * lock in old_tbl, if we find that future_tbl is not yet
	 * visible then that guarantees the entry to still be in
	 * the old tbl if it exists.
	 */
	while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) &&
	       (tbl = rht_dereference_rcu(tbl->future_tbl, ht)))
		;

	if (err)
		goto out;

	atomic_dec(&ht->nelems);
	if (unlikely(ht->p.automatic_shrinking &&
		     rht_shrink_below_30(ht, tbl)))
		schedule_work(&ht->run_work);

out:
	rcu_read_unlock();

	return err;
}

/* Internal function, please use rhashtable_replace_fast() instead */
static inline int __rhashtable_replace_fast(
	struct rhashtable *ht, struct bucket_table *tbl,
	struct rhash_head *obj_old, struct rhash_head *obj_new,
	const struct rhashtable_params params)
{
	struct rhash_head __rcu **pprev;
	struct rhash_head *he;
	spinlock_t *lock;
	unsigned int hash;
	int err = -ENOENT;

	/* Minimally, the old and new objects must have same hash
	 * (which should mean identifiers are the same).
	 */
	hash = rht_head_hashfn(ht, tbl, obj_old, params);
	if (hash != rht_head_hashfn(ht, tbl, obj_new, params))
		return -EINVAL;

	lock = rht_bucket_lock(tbl, hash);

	spin_lock_bh(lock);

	pprev = &tbl->buckets[hash];
	rht_for_each(he, tbl, hash) {
		if (he != obj_old) {
			pprev = &he->next;
			continue;
		}

		rcu_assign_pointer(obj_new->next, obj_old->next);
		rcu_assign_pointer(*pprev, obj_new);
		err = 0;
		break;
	}

	spin_unlock_bh(lock);

	return err;
}

/**
 * rhashtable_replace_fast - replace an object in hash table
 * @ht:		hash table
 * @obj_old:	pointer to hash head inside object being replaced
 * @obj_new:	pointer to hash head inside object which is new
 * @params:	hash table parameters
 *
 * Replacing an object doesn't affect the number of elements in the hash table
 * or bucket, so we don't need to worry about shrinking or expanding the
 * table here.
 *
 * Returns zero on success, -ENOENT if the entry could not be found,
 * -EINVAL if hash is not the same for the old and new objects.
 */
static inline int rhashtable_replace_fast(
	struct rhashtable *ht, struct rhash_head *obj_old,
	struct rhash_head *obj_new,
	const struct rhashtable_params params)
{
	struct bucket_table *tbl;
	int err;

	rcu_read_lock();

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

	/* Because we have already taken (and released) the bucket
	 * lock in old_tbl, if we find that future_tbl is not yet
	 * visible then that guarantees the entry to still be in
	 * the old tbl if it exists.
	 */
	while ((err = __rhashtable_replace_fast(ht, tbl, obj_old,
						obj_new, params)) &&
	       (tbl = rht_dereference_rcu(tbl->future_tbl, ht)))
		;

	rcu_read_unlock();

	return err;
}

#endif /* _LINUX_RHASHTABLE_H */