aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/padata.c
blob: 450d67d394b0fca3f99c3a9af233c46cde74f82e (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
/*
 * padata.c - generic interface to process data streams in parallel
 *
 * Copyright (C) 2008, 2009 secunet Security Networks AG
 * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
 */

#include <linux/module.h>
#include <linux/cpumask.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/padata.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>

#define MAX_SEQ_NR (INT_MAX - NR_CPUS)
#define MAX_OBJ_NUM 1000

static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
{
	int cpu, target_cpu;

	target_cpu = cpumask_first(pd->cpumask);
	for (cpu = 0; cpu < cpu_index; cpu++)
		target_cpu = cpumask_next(target_cpu, pd->cpumask);

	return target_cpu;
}

static int padata_cpu_hash(struct padata_priv *padata)
{
	int cpu_index;
	struct parallel_data *pd;

	pd =  padata->pd;

	/*
	 * Hash the sequence numbers to the cpus by taking
	 * seq_nr mod. number of cpus in use.
	 */
	cpu_index =  padata->seq_nr % cpumask_weight(pd->cpumask);

	return padata_index_to_cpu(pd, cpu_index);
}

static void padata_parallel_worker(struct work_struct *work)
{
	struct padata_queue *queue;
	struct parallel_data *pd;
	struct padata_instance *pinst;
	LIST_HEAD(local_list);

	local_bh_disable();
	queue = container_of(work, struct padata_queue, pwork);
	pd = queue->pd;
	pinst = pd->pinst;

	spin_lock(&queue->parallel.lock);
	list_replace_init(&queue->parallel.list, &local_list);
	spin_unlock(&queue->parallel.lock);

	while (!list_empty(&local_list)) {
		struct padata_priv *padata;

		padata = list_entry(local_list.next,
				    struct padata_priv, list);

		list_del_init(&padata->list);

		padata->parallel(padata);
	}

	local_bh_enable();
}

/**
 * padata_do_parallel - padata parallelization function
 *
 * @pinst: padata instance
 * @padata: object to be parallelized
 * @cb_cpu: cpu the serialization callback function will run on,
 *          must be in the cpumask of padata.
 *
 * The parallelization callback function will run with BHs off.
 * Note: Every object which is parallelized by padata_do_parallel
 * must be seen by padata_do_serial.
 */
int padata_do_parallel(struct padata_instance *pinst,
		       struct padata_priv *padata, int cb_cpu)
{
	int target_cpu, err;
	struct padata_queue *queue;
	struct parallel_data *pd;

	rcu_read_lock_bh();

	pd = rcu_dereference(pinst->pd);

	err = -EINVAL;
	if (!(pinst->flags & PADATA_INIT))
		goto out;

	if (!cpumask_test_cpu(cb_cpu, pd->cpumask))
		goto out;

	err =  -EBUSY;
	if ((pinst->flags & PADATA_RESET))
		goto out;

	if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
		goto out;

	err = 0;
	atomic_inc(&pd->refcnt);
	padata->pd = pd;
	padata->cb_cpu = cb_cpu;

	if (unlikely(atomic_read(&pd->seq_nr) == pd->max_seq_nr))
		atomic_set(&pd->seq_nr, -1);

	padata->seq_nr = atomic_inc_return(&pd->seq_nr);

	target_cpu = padata_cpu_hash(padata);
	queue = per_cpu_ptr(pd->queue, target_cpu);

	spin_lock(&queue->parallel.lock);
	list_add_tail(&padata->list, &queue->parallel.list);
	spin_unlock(&queue->parallel.lock);

	queue_work_on(target_cpu, pinst->wq, &queue->pwork);

out:
	rcu_read_unlock_bh();

	return err;
}
EXPORT_SYMBOL(padata_do_parallel);

/*
 * padata_get_next - Get the next object that needs serialization.
 *
 * Return values are:
 *
 * A pointer to the control struct of the next object that needs
 * serialization, if present in one of the percpu reorder queues.
 *
 * NULL, if all percpu reorder queues are empty.
 *
 * -EINPROGRESS, if the next object that needs serialization will
 *  be parallel processed by another cpu and is not yet present in
 *  the cpu's reorder queue.
 *
 * -ENODATA, if this cpu has to do the parallel processing for
 *  the next object.
 */
static struct padata_priv *padata_get_next(struct parallel_data *pd)
{
	int cpu, num_cpus;
	int next_nr, next_index;
	struct padata_queue *queue, *next_queue;
	struct padata_priv *padata;
	struct padata_list *reorder;

	num_cpus = cpumask_weight(pd->cpumask);

	/*
	 * Calculate the percpu reorder queue and the sequence
	 * number of the next object.
	 */
	next_nr = pd->processed;
	next_index = next_nr % num_cpus;
	cpu = padata_index_to_cpu(pd, next_index);
	next_queue = per_cpu_ptr(pd->queue, cpu);

	if (unlikely(next_nr > pd->max_seq_nr)) {
		next_nr = next_nr - pd->max_seq_nr - 1;
		next_index = next_nr % num_cpus;
		cpu = padata_index_to_cpu(pd, next_index);
		next_queue = per_cpu_ptr(pd->queue, cpu);
		pd->processed = 0;
	}

	padata = NULL;

	reorder = &next_queue->reorder;

	if (!list_empty(&reorder->list)) {
		padata = list_entry(reorder->list.next,
				    struct padata_priv, list);

		BUG_ON(next_nr != padata->seq_nr);

		spin_lock(&reorder->lock);
		list_del_init(&padata->list);
		atomic_dec(&pd->reorder_objects);
		spin_unlock(&reorder->lock);

		pd->processed++;

		goto out;
	}

	queue = per_cpu_ptr(pd->queue, smp_processor_id());
	if (queue->cpu_index == next_queue->cpu_index) {
		padata = ERR_PTR(-ENODATA);
		goto out;
	}

	padata = ERR_PTR(-EINPROGRESS);
out:
	return padata;
}

static void padata_reorder(struct parallel_data *pd)
{
	struct padata_priv *padata;
	struct padata_queue *queue;
	struct padata_instance *pinst = pd->pinst;

	/*
	 * We need to ensure that only one cpu can work on dequeueing of
	 * the reorder queue the time. Calculating in which percpu reorder
	 * queue the next object will arrive takes some time. A spinlock
	 * would be highly contended. Also it is not clear in which order
	 * the objects arrive to the reorder queues. So a cpu could wait to
	 * get the lock just to notice that there is nothing to do at the
	 * moment. Therefore we use a trylock and let the holder of the lock
	 * care for all the objects enqueued during the holdtime of the lock.
	 */
	if (!spin_trylock_bh(&pd->lock))
		return;

	while (1) {
		padata = padata_get_next(pd);

		/*
		 * All reorder queues are empty, or the next object that needs
		 * serialization is parallel processed by another cpu and is
		 * still on it's way to the cpu's reorder queue, nothing to
		 * do for now.
		 */
		if (!padata || PTR_ERR(padata) == -EINPROGRESS)
			break;

		/*
		 * This cpu has to do the parallel processing of the next
		 * object. It's waiting in the cpu's parallelization queue,
		 * so exit imediately.
		 */
		if (PTR_ERR(padata) == -ENODATA) {
			del_timer(&pd->timer);
			spin_unlock_bh(&pd->lock);
			return;
		}

		queue = per_cpu_ptr(pd->queue, padata->cb_cpu);

		spin_lock(&queue->serial.lock);
		list_add_tail(&padata->list, &queue->serial.list);
		spin_unlock(&queue->serial.lock);

		queue_work_on(padata->cb_cpu, pinst->wq, &queue->swork);
	}

	spin_unlock_bh(&pd->lock);

	/*
	 * The next object that needs serialization might have arrived to
	 * the reorder queues in the meantime, we will be called again
	 * from the timer function if noone else cares for it.
	 */
	if (atomic_read(&pd->reorder_objects)
			&& !(pinst->flags & PADATA_RESET))
		mod_timer(&pd->timer, jiffies + HZ);
	else
		del_timer(&pd->timer);

	return;
}

static void padata_reorder_timer(unsigned long arg)
{
	struct parallel_data *pd = (struct parallel_data *)arg;

	padata_reorder(pd);
}

static void padata_serial_worker(struct work_struct *work)
{
	struct padata_queue *queue;
	struct parallel_data *pd;
	LIST_HEAD(local_list);

	local_bh_disable();
	queue = container_of(work, struct padata_queue, swork);
	pd = queue->pd;

	spin_lock(&queue->serial.lock);
	list_replace_init(&queue->serial.list, &local_list);
	spin_unlock(&queue->serial.lock);

	while (!list_empty(&local_list)) {
		struct padata_priv *padata;

		padata = list_entry(local_list.next,
				    struct padata_priv, list);

		list_del_init(&padata->list);

		padata->serial(padata);
		atomic_dec(&pd->refcnt);
	}
	local_bh_enable();
}

/**
 * padata_do_serial - padata serialization function
 *
 * @padata: object to be serialized.
 *
 * padata_do_serial must be called for every parallelized object.
 * The serialization callback function will run with BHs off.
 */
void padata_do_serial(struct padata_priv *padata)
{
	int cpu;
	struct padata_queue *queue;
	struct parallel_data *pd;

	pd = padata->pd;

	cpu = get_cpu();
	queue = per_cpu_ptr(pd->queue, cpu);

	spin_lock(&queue->reorder.lock);
	atomic_inc(&pd->reorder_objects);
	list_add_tail(&padata->list, &queue->reorder.list);
	spin_unlock(&queue->reorder.lock);

	put_cpu();

	padata_reorder(pd);
}
EXPORT_SYMBOL(padata_do_serial);

/* Allocate and initialize the internal cpumask dependend resources. */
static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
					     const struct cpumask *cpumask)
{
	int cpu, cpu_index, num_cpus;
	struct padata_queue *queue;
	struct parallel_data *pd;

	cpu_index = 0;

	pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
	if (!pd)
		goto err;

	pd->queue = alloc_percpu(struct padata_queue);
	if (!pd->queue)
		goto err_free_pd;

	if (!alloc_cpumask_var(&pd->cpumask, GFP_KERNEL))
		goto err_free_queue;

	cpumask_and(pd->cpumask, cpumask, cpu_active_mask);

	for_each_cpu(cpu, pd->cpumask) {
		queue = per_cpu_ptr(pd->queue, cpu);

		queue->pd = pd;

		queue->cpu_index = cpu_index;
		cpu_index++;

		INIT_LIST_HEAD(&queue->reorder.list);
		INIT_LIST_HEAD(&queue->parallel.list);
		INIT_LIST_HEAD(&queue->serial.list);
		spin_lock_init(&queue->reorder.lock);
		spin_lock_init(&queue->parallel.lock);
		spin_lock_init(&queue->serial.lock);

		INIT_WORK(&queue->pwork, padata_parallel_worker);
		INIT_WORK(&queue->swork, padata_serial_worker);
	}

	num_cpus = cpumask_weight(pd->cpumask);
	pd->max_seq_nr = (MAX_SEQ_NR / num_cpus) * num_cpus - 1;

	setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
	atomic_set(&pd->seq_nr, -1);
	atomic_set(&pd->reorder_objects, 0);
	atomic_set(&pd->refcnt, 0);
	pd->pinst = pinst;
	spin_lock_init(&pd->lock);

	return pd;

err_free_queue:
	free_percpu(pd->queue);
err_free_pd:
	kfree(pd);
err:
	return NULL;
}

static void padata_free_pd(struct parallel_data *pd)
{
	free_cpumask_var(pd->cpumask);
	free_percpu(pd->queue);
	kfree(pd);
}

/* Flush all objects out of the padata queues. */
static void padata_flush_queues(struct parallel_data *pd)
{
	int cpu;
	struct padata_queue *queue;

	for_each_cpu(cpu, pd->cpumask) {
		queue = per_cpu_ptr(pd->queue, cpu);
		flush_work(&queue->pwork);
	}

	del_timer_sync(&pd->timer);

	if (atomic_read(&pd->reorder_objects))
		padata_reorder(pd);

	for_each_cpu(cpu, pd->cpumask) {
		queue = per_cpu_ptr(pd->queue, cpu);
		flush_work(&queue->swork);
	}

	BUG_ON(atomic_read(&pd->refcnt) != 0);
}

static void __padata_start(struct padata_instance *pinst)
{
	pinst->flags |= PADATA_INIT;
}

static void __padata_stop(struct padata_instance *pinst)
{
	if (!(pinst->flags & PADATA_INIT))
		return;

	pinst->flags &= ~PADATA_INIT;

	synchronize_rcu();

	get_online_cpus();
	padata_flush_queues(pinst->pd);
	put_online_cpus();
}

/* Replace the internal control stucture with a new one. */
static void padata_replace(struct padata_instance *pinst,
			   struct parallel_data *pd_new)
{
	struct parallel_data *pd_old = pinst->pd;

	pinst->flags |= PADATA_RESET;

	rcu_assign_pointer(pinst->pd, pd_new);

	synchronize_rcu();

	if (pd_old) {
		padata_flush_queues(pd_old);
		padata_free_pd(pd_old);
	}

	pinst->flags &= ~PADATA_RESET;
}

/* If cpumask contains no active cpu, we mark the instance as invalid. */
static bool padata_validate_cpumask(struct padata_instance *pinst,
				    const struct cpumask *cpumask)
{
	if (!cpumask_intersects(cpumask, cpu_active_mask)) {
		pinst->flags |= PADATA_INVALID;
		return false;
	}

	pinst->flags &= ~PADATA_INVALID;
	return true;
}

/**
 * padata_set_cpumask - set the cpumask that padata should use
 *
 * @pinst: padata instance
 * @cpumask: the cpumask to use
 */
int padata_set_cpumask(struct padata_instance *pinst,
			cpumask_var_t cpumask)
{
	int valid;
	int err = 0;
	struct parallel_data *pd = NULL;

	mutex_lock(&pinst->lock);

	valid = padata_validate_cpumask(pinst, cpumask);
	if (!valid) {
		__padata_stop(pinst);
		goto out_replace;
	}

	get_online_cpus();

	pd = padata_alloc_pd(pinst, cpumask);
	if (!pd) {
		err = -ENOMEM;
		goto out;
	}

out_replace:
	cpumask_copy(pinst->cpumask, cpumask);

	padata_replace(pinst, pd);

	if (valid)
		__padata_start(pinst);

out:
	put_online_cpus();

	mutex_unlock(&pinst->lock);

	return err;
}
EXPORT_SYMBOL(padata_set_cpumask);

static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
{
	struct parallel_data *pd;

	if (cpumask_test_cpu(cpu, cpu_active_mask)) {
		pd = padata_alloc_pd(pinst, pinst->cpumask);
		if (!pd)
			return -ENOMEM;

		padata_replace(pinst, pd);

		if (padata_validate_cpumask(pinst, pinst->cpumask))
			__padata_start(pinst);
	}

	return 0;
}

/**
 * padata_add_cpu - add a cpu to the padata cpumask
 *
 * @pinst: padata instance
 * @cpu: cpu to add
 */
int padata_add_cpu(struct padata_instance *pinst, int cpu)
{
	int err;

	mutex_lock(&pinst->lock);

	get_online_cpus();
	cpumask_set_cpu(cpu, pinst->cpumask);
	err = __padata_add_cpu(pinst, cpu);
	put_online_cpus();

	mutex_unlock(&pinst->lock);

	return err;
}
EXPORT_SYMBOL(padata_add_cpu);

static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
{
	struct parallel_data *pd = NULL;

	if (cpumask_test_cpu(cpu, cpu_online_mask)) {

		if (!padata_validate_cpumask(pinst, pinst->cpumask)) {
			__padata_stop(pinst);
			padata_replace(pinst, pd);
			goto out;
		}

		pd = padata_alloc_pd(pinst, pinst->cpumask);
		if (!pd)
			return -ENOMEM;

		padata_replace(pinst, pd);
	}

out:
	return 0;
}

/**
 * padata_remove_cpu - remove a cpu from the padata cpumask
 *
 * @pinst: padata instance
 * @cpu: cpu to remove
 */
int padata_remove_cpu(struct padata_instance *pinst, int cpu)
{
	int err;

	mutex_lock(&pinst->lock);

	get_online_cpus();
	cpumask_clear_cpu(cpu, pinst->cpumask);
	err = __padata_remove_cpu(pinst, cpu);
	put_online_cpus();

	mutex_unlock(&pinst->lock);

	return err;
}
EXPORT_SYMBOL(padata_remove_cpu);

/**
 * padata_start - start the parallel processing
 *
 * @pinst: padata instance to start
 */
int padata_start(struct padata_instance *pinst)
{
	int err = 0;

	mutex_lock(&pinst->lock);

	if (pinst->flags & PADATA_INVALID)
		err =-EINVAL;

	 __padata_start(pinst);

	mutex_unlock(&pinst->lock);

	return err;
}
EXPORT_SYMBOL(padata_start);

/**
 * padata_stop - stop the parallel processing
 *
 * @pinst: padata instance to stop
 */
void padata_stop(struct padata_instance *pinst)
{
	mutex_lock(&pinst->lock);
	__padata_stop(pinst);
	mutex_unlock(&pinst->lock);
}
EXPORT_SYMBOL(padata_stop);

#ifdef CONFIG_HOTPLUG_CPU
static int padata_cpu_callback(struct notifier_block *nfb,
			       unsigned long action, void *hcpu)
{
	int err;
	struct padata_instance *pinst;
	int cpu = (unsigned long)hcpu;

	pinst = container_of(nfb, struct padata_instance, cpu_notifier);

	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		if (!cpumask_test_cpu(cpu, pinst->cpumask))
			break;
		mutex_lock(&pinst->lock);
		err = __padata_add_cpu(pinst, cpu);
		mutex_unlock(&pinst->lock);
		if (err)
			return NOTIFY_BAD;
		break;

	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		if (!cpumask_test_cpu(cpu, pinst->cpumask))
			break;
		mutex_lock(&pinst->lock);
		err = __padata_remove_cpu(pinst, cpu);
		mutex_unlock(&pinst->lock);
		if (err)
			return NOTIFY_BAD;
		break;

	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		if (!cpumask_test_cpu(cpu, pinst->cpumask))
			break;
		mutex_lock(&pinst->lock);
		__padata_remove_cpu(pinst, cpu);
		mutex_unlock(&pinst->lock);

	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		if (!cpumask_test_cpu(cpu, pinst->cpumask))
			break;
		mutex_lock(&pinst->lock);
		__padata_add_cpu(pinst, cpu);
		mutex_unlock(&pinst->lock);
	}

	return NOTIFY_OK;
}
#endif

/**
 * padata_alloc - allocate and initialize a padata instance
 *
 * @cpumask: cpumask that padata uses for parallelization
 * @wq: workqueue to use for the allocated padata instance
 */
struct padata_instance *padata_alloc(const struct cpumask *cpumask,
				     struct workqueue_struct *wq)
{
	struct padata_instance *pinst;
	struct parallel_data *pd = NULL;

	pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL);
	if (!pinst)
		goto err;

	get_online_cpus();

	if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL))
		goto err_free_inst;

	if (padata_validate_cpumask(pinst, cpumask)) {
		pd = padata_alloc_pd(pinst, cpumask);
		if (!pd)
			goto err_free_mask;
	}

	rcu_assign_pointer(pinst->pd, pd);

	pinst->wq = wq;

	cpumask_copy(pinst->cpumask, cpumask);

	pinst->flags = 0;

#ifdef CONFIG_HOTPLUG_CPU
	pinst->cpu_notifier.notifier_call = padata_cpu_callback;
	pinst->cpu_notifier.priority = 0;
	register_hotcpu_notifier(&pinst->cpu_notifier);
#endif

	put_online_cpus();

	mutex_init(&pinst->lock);

	return pinst;

err_free_mask:
	free_cpumask_var(pinst->cpumask);
err_free_inst:
	kfree(pinst);
	put_online_cpus();
err:
	return NULL;
}
EXPORT_SYMBOL(padata_alloc);

/**
 * padata_free - free a padata instance
 *
 * @padata_inst: padata instance to free
 */
void padata_free(struct padata_instance *pinst)
{
#ifdef CONFIG_HOTPLUG_CPU
	unregister_hotcpu_notifier(&pinst->cpu_notifier);
#endif

	padata_stop(pinst);
	padata_free_pd(pinst->pd);
	free_cpumask_var(pinst->cpumask);
	kfree(pinst);
}
EXPORT_SYMBOL(padata_free);