summaryrefslogtreecommitdiff
path: root/lib/sbitmap.c
blob: 5e2e93307f0d05f94ee9bde92144ded6f6c733d0 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2016 Facebook
 * Copyright (C) 2013-2014 Jens Axboe
 */

#include <linux/sched.h>
#include <linux/random.h>
#include <linux/sbitmap.h>
#include <linux/seq_file.h>

static int init_alloc_hint(struct sbitmap *sb, gfp_t flags)
{
	unsigned depth = sb->depth;

	sb->alloc_hint = alloc_percpu_gfp(unsigned int, flags);
	if (!sb->alloc_hint)
		return -ENOMEM;

	if (depth && !sb->round_robin) {
		int i;

		for_each_possible_cpu(i)
			*per_cpu_ptr(sb->alloc_hint, i) = get_random_u32_below(depth);
	}
	return 0;
}

static inline unsigned update_alloc_hint_before_get(struct sbitmap *sb,
						    unsigned int depth)
{
	unsigned hint;

	hint = this_cpu_read(*sb->alloc_hint);
	if (unlikely(hint >= depth)) {
		hint = depth ? get_random_u32_below(depth) : 0;
		this_cpu_write(*sb->alloc_hint, hint);
	}

	return hint;
}

static inline void update_alloc_hint_after_get(struct sbitmap *sb,
					       unsigned int depth,
					       unsigned int hint,
					       unsigned int nr)
{
	if (nr == -1) {
		/* If the map is full, a hint won't do us much good. */
		this_cpu_write(*sb->alloc_hint, 0);
	} else if (nr == hint || unlikely(sb->round_robin)) {
		/* Only update the hint if we used it. */
		hint = nr + 1;
		if (hint >= depth - 1)
			hint = 0;
		this_cpu_write(*sb->alloc_hint, hint);
	}
}

/*
 * See if we have deferred clears that we can batch move
 */
static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
		unsigned int depth, unsigned int alloc_hint, bool wrap)
{
	unsigned long mask, word_mask;

	guard(spinlock_irqsave)(&map->swap_lock);

	if (!map->cleared) {
		if (depth == 0)
			return false;

		word_mask = (~0UL) >> (BITS_PER_LONG - depth);
		/*
		 * The current behavior is to always retry after moving
		 * ->cleared to word, and we change it to retry in case
		 * of any free bits. To avoid an infinite loop, we need
		 * to take wrap & alloc_hint into account, otherwise a
		 * soft lockup may occur.
		 */
		if (!wrap && alloc_hint)
			word_mask &= ~((1UL << alloc_hint) - 1);

		return (READ_ONCE(map->word) & word_mask) != word_mask;
	}

	/*
	 * First get a stable cleared mask, setting the old mask to 0.
	 */
	mask = xchg(&map->cleared, 0);

	/*
	 * Now clear the masked bits in our free word
	 */
	atomic_long_andnot(mask, (atomic_long_t *)&map->word);
	BUILD_BUG_ON(sizeof(atomic_long_t) != sizeof(map->word));
	return true;
}

int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
		      gfp_t flags, int node, bool round_robin,
		      bool alloc_hint)
{
	unsigned int bits_per_word;
	int i;

	if (shift < 0)
		shift = sbitmap_calculate_shift(depth);

	bits_per_word = 1U << shift;
	if (bits_per_word > BITS_PER_LONG)
		return -EINVAL;

	sb->shift = shift;
	sb->depth = depth;
	sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
	sb->round_robin = round_robin;

	if (depth == 0) {
		sb->map = NULL;
		return 0;
	}

	if (alloc_hint) {
		if (init_alloc_hint(sb, flags))
			return -ENOMEM;
	} else {
		sb->alloc_hint = NULL;
	}

	sb->map = kvzalloc_node(sb->map_nr * sizeof(*sb->map), flags, node);
	if (!sb->map) {
		free_percpu(sb->alloc_hint);
		return -ENOMEM;
	}

	for (i = 0; i < sb->map_nr; i++)
		spin_lock_init(&sb->map[i].swap_lock);

	return 0;
}
EXPORT_SYMBOL_GPL(sbitmap_init_node);

void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
{
	unsigned int bits_per_word = 1U << sb->shift;
	unsigned int i;

	for (i = 0; i < sb->map_nr; i++)
		sbitmap_deferred_clear(&sb->map[i], 0, 0, 0);

	sb->depth = depth;
	sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
}
EXPORT_SYMBOL_GPL(sbitmap_resize);

static int __sbitmap_get_word(unsigned long *word, unsigned long depth,
			      unsigned int hint, bool wrap)
{
	int nr;

	/* don't wrap if starting from 0 */
	wrap = wrap && hint;

	while (1) {
		nr = find_next_zero_bit(word, depth, hint);
		if (unlikely(nr >= depth)) {
			/*
			 * We started with an offset, and we didn't reset the
			 * offset to 0 in a failure case, so start from 0 to
			 * exhaust the map.
			 */
			if (hint && wrap) {
				hint = 0;
				continue;
			}
			return -1;
		}

		if (!test_and_set_bit_lock(nr, word))
			break;

		hint = nr + 1;
		if (hint >= depth - 1)
			hint = 0;
	}

	return nr;
}

static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
				    unsigned int depth,
				    unsigned int alloc_hint,
				    bool wrap)
{
	int nr;

	do {
		nr = __sbitmap_get_word(&map->word, depth,
					alloc_hint, wrap);
		if (nr != -1)
			break;
		if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
			break;
	} while (1);

	return nr;
}

static int sbitmap_find_bit(struct sbitmap *sb,
			    unsigned int depth,
			    unsigned int index,
			    unsigned int alloc_hint,
			    bool wrap)
{
	unsigned int i;
	int nr = -1;

	for (i = 0; i < sb->map_nr; i++) {
		nr = sbitmap_find_bit_in_word(&sb->map[index],
					      min_t(unsigned int,
						    __map_depth(sb, index),
						    depth),
					      alloc_hint, wrap);

		if (nr != -1) {
			nr += index << sb->shift;
			break;
		}

		/* Jump to next index. */
		alloc_hint = 0;
		if (++index >= sb->map_nr)
			index = 0;
	}

	return nr;
}

static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint)
{
	unsigned int index;

	index = SB_NR_TO_INDEX(sb, alloc_hint);

	/*
	 * Unless we're doing round robin tag allocation, just use the
	 * alloc_hint to find the right word index. No point in looping
	 * twice in find_next_zero_bit() for that case.
	 */
	if (sb->round_robin)
		alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);
	else
		alloc_hint = 0;

	return sbitmap_find_bit(sb, UINT_MAX, index, alloc_hint,
				!sb->round_robin);
}

int sbitmap_get(struct sbitmap *sb)
{
	int nr;
	unsigned int hint, depth;

	if (WARN_ON_ONCE(unlikely(!sb->alloc_hint)))
		return -1;

	depth = READ_ONCE(sb->depth);
	hint = update_alloc_hint_before_get(sb, depth);
	nr = __sbitmap_get(sb, hint);
	update_alloc_hint_after_get(sb, depth, hint, nr);

	return nr;
}
EXPORT_SYMBOL_GPL(sbitmap_get);

static int __sbitmap_get_shallow(struct sbitmap *sb,
				 unsigned int alloc_hint,
				 unsigned long shallow_depth)
{
	unsigned int index;

	index = SB_NR_TO_INDEX(sb, alloc_hint);
	alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);

	return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true);
}

int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
{
	int nr;
	unsigned int hint, depth;

	if (WARN_ON_ONCE(unlikely(!sb->alloc_hint)))
		return -1;

	depth = READ_ONCE(sb->depth);
	hint = update_alloc_hint_before_get(sb, depth);
	nr = __sbitmap_get_shallow(sb, hint, shallow_depth);
	update_alloc_hint_after_get(sb, depth, hint, nr);

	return nr;
}
EXPORT_SYMBOL_GPL(sbitmap_get_shallow);

bool sbitmap_any_bit_set(const struct sbitmap *sb)
{
	unsigned int i;

	for (i = 0; i < sb->map_nr; i++) {
		if (sb->map[i].word & ~sb->map[i].cleared)
			return true;
	}
	return false;
}
EXPORT_SYMBOL_GPL(sbitmap_any_bit_set);

static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set)
{
	unsigned int i, weight = 0;

	for (i = 0; i < sb->map_nr; i++) {
		const struct sbitmap_word *word = &sb->map[i];
		unsigned int word_depth = __map_depth(sb, i);

		if (set)
			weight += bitmap_weight(&word->word, word_depth);
		else
			weight += bitmap_weight(&word->cleared, word_depth);
	}
	return weight;
}

static unsigned int sbitmap_cleared(const struct sbitmap *sb)
{
	return __sbitmap_weight(sb, false);
}

unsigned int sbitmap_weight(const struct sbitmap *sb)
{
	return __sbitmap_weight(sb, true) - sbitmap_cleared(sb);
}
EXPORT_SYMBOL_GPL(sbitmap_weight);

void sbitmap_show(struct sbitmap *sb, struct seq_file *m)
{
	seq_printf(m, "depth=%u\n", sb->depth);
	seq_printf(m, "busy=%u\n", sbitmap_weight(sb));
	seq_printf(m, "cleared=%u\n", sbitmap_cleared(sb));
	seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift);
	seq_printf(m, "map_nr=%u\n", sb->map_nr);
}
EXPORT_SYMBOL_GPL(sbitmap_show);

static inline void emit_byte(struct seq_file *m, unsigned int offset, u8 byte)
{
	if ((offset & 0xf) == 0) {
		if (offset != 0)
			seq_putc(m, '\n');
		seq_printf(m, "%08x:", offset);
	}
	if ((offset & 0x1) == 0)
		seq_putc(m, ' ');
	seq_printf(m, "%02x", byte);
}

void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
{
	u8 byte = 0;
	unsigned int byte_bits = 0;
	unsigned int offset = 0;
	int i;

	for (i = 0; i < sb->map_nr; i++) {
		unsigned long word = READ_ONCE(sb->map[i].word);
		unsigned long cleared = READ_ONCE(sb->map[i].cleared);
		unsigned int word_bits = __map_depth(sb, i);

		word &= ~cleared;

		while (word_bits > 0) {
			unsigned int bits = min(8 - byte_bits, word_bits);

			byte |= (word & (BIT(bits) - 1)) << byte_bits;
			byte_bits += bits;
			if (byte_bits == 8) {
				emit_byte(m, offset, byte);
				byte = 0;
				byte_bits = 0;
				offset++;
			}
			word >>= bits;
			word_bits -= bits;
		}
	}
	if (byte_bits) {
		emit_byte(m, offset, byte);
		offset++;
	}
	if (offset)
		seq_putc(m, '\n');
}
EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);

static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
					unsigned int depth)
{
	unsigned int wake_batch;
	unsigned int shallow_depth;

	/*
	 * Each full word of the bitmap has bits_per_word bits, and there might
	 * be a partial word. There are depth / bits_per_word full words and
	 * depth % bits_per_word bits left over. In bitwise arithmetic:
	 *
	 * bits_per_word = 1 << shift
	 * depth / bits_per_word = depth >> shift
	 * depth % bits_per_word = depth & ((1 << shift) - 1)
	 *
	 * Each word can be limited to sbq->min_shallow_depth bits.
	 */
	shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
	depth = ((depth >> sbq->sb.shift) * shallow_depth +
		 min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
	wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
			     SBQ_WAKE_BATCH);

	return wake_batch;
}

int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
			    int shift, bool round_robin, gfp_t flags, int node)
{
	int ret;
	int i;

	ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node,
				round_robin, true);
	if (ret)
		return ret;

	sbq->min_shallow_depth = UINT_MAX;
	sbq->wake_batch = sbq_calc_wake_batch(sbq, depth);
	atomic_set(&sbq->wake_index, 0);
	atomic_set(&sbq->ws_active, 0);
	atomic_set(&sbq->completion_cnt, 0);
	atomic_set(&sbq->wakeup_cnt, 0);

	sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
	if (!sbq->ws) {
		sbitmap_free(&sbq->sb);
		return -ENOMEM;
	}

	for (i = 0; i < SBQ_WAIT_QUEUES; i++)
		init_waitqueue_head(&sbq->ws[i].wait);

	return 0;
}
EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);

static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
					    unsigned int depth)
{
	unsigned int wake_batch;

	wake_batch = sbq_calc_wake_batch(sbq, depth);
	if (sbq->wake_batch != wake_batch)
		WRITE_ONCE(sbq->wake_batch, wake_batch);
}

void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
					    unsigned int users)
{
	unsigned int wake_batch;
	unsigned int depth = (sbq->sb.depth + users - 1) / users;

	wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES,
			1, SBQ_WAKE_BATCH);

	WRITE_ONCE(sbq->wake_batch, wake_batch);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch);

void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
{
	sbitmap_queue_update_wake_batch(sbq, depth);
	sbitmap_resize(&sbq->sb, depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_resize);

int __sbitmap_queue_get(struct sbitmap_queue *sbq)
{
	return sbitmap_get(&sbq->sb);
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get);

unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
					unsigned int *offset)
{
	struct sbitmap *sb = &sbq->sb;
	unsigned int hint, depth;
	unsigned long index, nr;
	int i;

	if (unlikely(sb->round_robin))
		return 0;

	depth = READ_ONCE(sb->depth);
	hint = update_alloc_hint_before_get(sb, depth);

	index = SB_NR_TO_INDEX(sb, hint);

	for (i = 0; i < sb->map_nr; i++) {
		struct sbitmap_word *map = &sb->map[index];
		unsigned long get_mask;
		unsigned int map_depth = __map_depth(sb, index);
		unsigned long val;

		sbitmap_deferred_clear(map, 0, 0, 0);
		val = READ_ONCE(map->word);
		if (val == (1UL << (map_depth - 1)) - 1)
			goto next;

		nr = find_first_zero_bit(&val, map_depth);
		if (nr + nr_tags <= map_depth) {
			atomic_long_t *ptr = (atomic_long_t *) &map->word;

			get_mask = ((1UL << nr_tags) - 1) << nr;
			while (!atomic_long_try_cmpxchg(ptr, &val,
							  get_mask | val))
				;
			get_mask = (get_mask & ~val) >> nr;
			if (get_mask) {
				*offset = nr + (index << sb->shift);
				update_alloc_hint_after_get(sb, depth, hint,
							*offset + nr_tags - 1);
				return get_mask;
			}
		}
next:
		/* Jump to next index. */
		if (++index >= sb->map_nr)
			index = 0;
	}

	return 0;
}

int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
			      unsigned int shallow_depth)
{
	WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth);

	return sbitmap_get_shallow(&sbq->sb, shallow_depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_get_shallow);

void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
				     unsigned int min_shallow_depth)
{
	sbq->min_shallow_depth = min_shallow_depth;
	sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth);

static void __sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr)
{
	int i, wake_index, woken;

	if (!atomic_read(&sbq->ws_active))
		return;

	wake_index = atomic_read(&sbq->wake_index);
	for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
		struct sbq_wait_state *ws = &sbq->ws[wake_index];

		/*
		 * Advance the index before checking the current queue.
		 * It improves fairness, by ensuring the queue doesn't
		 * need to be fully emptied before trying to wake up
		 * from the next one.
		 */
		wake_index = sbq_index_inc(wake_index);

		if (waitqueue_active(&ws->wait)) {
			woken = wake_up_nr(&ws->wait, nr);
			if (woken == nr)
				break;
			nr -= woken;
		}
	}

	if (wake_index != atomic_read(&sbq->wake_index))
		atomic_set(&sbq->wake_index, wake_index);
}

void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr)
{
	unsigned int wake_batch = READ_ONCE(sbq->wake_batch);
	unsigned int wakeups;

	if (!atomic_read(&sbq->ws_active))
		return;

	atomic_add(nr, &sbq->completion_cnt);
	wakeups = atomic_read(&sbq->wakeup_cnt);

	do {
		if (atomic_read(&sbq->completion_cnt) - wakeups < wake_batch)
			return;
	} while (!atomic_try_cmpxchg(&sbq->wakeup_cnt,
				     &wakeups, wakeups + wake_batch));

	__sbitmap_queue_wake_up(sbq, wake_batch);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);

static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag)
{
	if (likely(!sb->round_robin && tag < sb->depth))
		data_race(*per_cpu_ptr(sb->alloc_hint, cpu) = tag);
}

void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
				int *tags, int nr_tags)
{
	struct sbitmap *sb = &sbq->sb;
	unsigned long *addr = NULL;
	unsigned long mask = 0;
	int i;

	smp_mb__before_atomic();
	for (i = 0; i < nr_tags; i++) {
		const int tag = tags[i] - offset;
		unsigned long *this_addr;

		/* since we're clearing a batch, skip the deferred map */
		this_addr = &sb->map[SB_NR_TO_INDEX(sb, tag)].word;
		if (!addr) {
			addr = this_addr;
		} else if (addr != this_addr) {
			atomic_long_andnot(mask, (atomic_long_t *) addr);
			mask = 0;
			addr = this_addr;
		}
		mask |= (1UL << SB_NR_TO_BIT(sb, tag));
	}

	if (mask)
		atomic_long_andnot(mask, (atomic_long_t *) addr);

	smp_mb__after_atomic();
	sbitmap_queue_wake_up(sbq, nr_tags);
	sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(),
					tags[nr_tags - 1] - offset);
}

void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
			 unsigned int cpu)
{
	/*
	 * Once the clear bit is set, the bit may be allocated out.
	 *
	 * Orders READ/WRITE on the associated instance(such as request
	 * of blk_mq) by this bit for avoiding race with re-allocation,
	 * and its pair is the memory barrier implied in __sbitmap_get_word.
	 *
	 * One invariant is that the clear bit has to be zero when the bit
	 * is in use.
	 */
	smp_mb__before_atomic();
	sbitmap_deferred_clear_bit(&sbq->sb, nr);

	/*
	 * Pairs with the memory barrier in set_current_state() to ensure the
	 * proper ordering of clear_bit_unlock()/waitqueue_active() in the waker
	 * and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
	 * waiter. See the comment on waitqueue_active().
	 */
	smp_mb__after_atomic();
	sbitmap_queue_wake_up(sbq, 1);
	sbitmap_update_cpu_hint(&sbq->sb, cpu, nr);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_clear);

void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
{
	int i, wake_index;

	/*
	 * Pairs with the memory barrier in set_current_state() like in
	 * sbitmap_queue_wake_up().
	 */
	smp_mb();
	wake_index = atomic_read(&sbq->wake_index);
	for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
		struct sbq_wait_state *ws = &sbq->ws[wake_index];

		if (waitqueue_active(&ws->wait))
			wake_up(&ws->wait);

		wake_index = sbq_index_inc(wake_index);
	}
}
EXPORT_SYMBOL_GPL(sbitmap_queue_wake_all);

void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
{
	bool first;
	int i;

	sbitmap_show(&sbq->sb, m);

	seq_puts(m, "alloc_hint={");
	first = true;
	for_each_possible_cpu(i) {
		if (!first)
			seq_puts(m, ", ");
		first = false;
		seq_printf(m, "%u", *per_cpu_ptr(sbq->sb.alloc_hint, i));
	}
	seq_puts(m, "}\n");

	seq_printf(m, "wake_batch=%u\n", sbq->wake_batch);
	seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index));
	seq_printf(m, "ws_active=%d\n", atomic_read(&sbq->ws_active));

	seq_puts(m, "ws={\n");
	for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
		struct sbq_wait_state *ws = &sbq->ws[i];
		seq_printf(m, "\t{.wait=%s},\n",
			   waitqueue_active(&ws->wait) ? "active" : "inactive");
	}
	seq_puts(m, "}\n");

	seq_printf(m, "round_robin=%d\n", sbq->sb.round_robin);
	seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_show);

void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
			    struct sbq_wait_state *ws,
			    struct sbq_wait *sbq_wait)
{
	if (!sbq_wait->sbq) {
		sbq_wait->sbq = sbq;
		atomic_inc(&sbq->ws_active);
		add_wait_queue(&ws->wait, &sbq_wait->wait);
	}
}
EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue);

void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait)
{
	list_del_init(&sbq_wait->wait.entry);
	if (sbq_wait->sbq) {
		atomic_dec(&sbq_wait->sbq->ws_active);
		sbq_wait->sbq = NULL;
	}
}
EXPORT_SYMBOL_GPL(sbitmap_del_wait_queue);

void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq,
			     struct sbq_wait_state *ws,
			     struct sbq_wait *sbq_wait, int state)
{
	if (!sbq_wait->sbq) {
		atomic_inc(&sbq->ws_active);
		sbq_wait->sbq = sbq;
	}
	prepare_to_wait_exclusive(&ws->wait, &sbq_wait->wait, state);
}
EXPORT_SYMBOL_GPL(sbitmap_prepare_to_wait);

void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws,
			 struct sbq_wait *sbq_wait)
{
	finish_wait(&ws->wait, &sbq_wait->wait);
	if (sbq_wait->sbq) {
		atomic_dec(&sbq->ws_active);
		sbq_wait->sbq = NULL;
	}
}
EXPORT_SYMBOL_GPL(sbitmap_finish_wait);