summaryrefslogtreecommitdiff
path: root/kernel/padata.c
blob: e007b8a4b73887caf8b3b6903939039f14506d8d (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
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
// SPDX-License-Identifier: GPL-2.0
/*
 * padata.c - generic interface to process data streams in parallel
 *
 * See Documentation/core-api/padata.rst for more information.
 *
 * Copyright (C) 2008, 2009 secunet Security Networks AG
 * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
 *
 * Copyright (c) 2020 Oracle and/or its affiliates.
 * Author: Daniel Jordan <daniel.m.jordan@oracle.com>
 */

#include <linux/completion.h>
#include <linux/export.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/sysfs.h>
#include <linux/rcupdate.h>

#define	PADATA_WORK_ONSTACK	1	/* Work's memory is on stack */

struct padata_work {
	struct work_struct	pw_work;
	struct list_head	pw_list;  /* padata_free_works linkage */
	void			*pw_data;
};

static DEFINE_SPINLOCK(padata_works_lock);
static struct padata_work *padata_works;
static LIST_HEAD(padata_free_works);

struct padata_mt_job_state {
	spinlock_t		lock;
	struct completion	completion;
	struct padata_mt_job	*job;
	int			nworks;
	int			nworks_fini;
	unsigned long		chunk_size;
};

static void padata_free_pd(struct parallel_data *pd);
static void __init padata_mt_helper(struct work_struct *work);

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

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

	return target_cpu;
}

static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr)
{
	/*
	 * Hash the sequence numbers to the cpus by taking
	 * seq_nr mod. number of cpus in use.
	 */
	int cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu);

	return padata_index_to_cpu(pd, cpu_index);
}

static struct padata_work *padata_work_alloc(void)
{
	struct padata_work *pw;

	lockdep_assert_held(&padata_works_lock);

	if (list_empty(&padata_free_works))
		return NULL;	/* No more work items allowed to be queued. */

	pw = list_first_entry(&padata_free_works, struct padata_work, pw_list);
	list_del(&pw->pw_list);
	return pw;
}

/*
 * This function is marked __ref because this function may be optimized in such
 * a way that it directly refers to work_fn's address, which causes modpost to
 * complain when work_fn is marked __init. This scenario was observed with clang
 * LTO, where padata_work_init() was optimized to refer directly to
 * padata_mt_helper() because the calls to padata_work_init() with other work_fn
 * values were eliminated or inlined.
 */
static void __ref padata_work_init(struct padata_work *pw, work_func_t work_fn,
				   void *data, int flags)
{
	if (flags & PADATA_WORK_ONSTACK)
		INIT_WORK_ONSTACK(&pw->pw_work, work_fn);
	else
		INIT_WORK(&pw->pw_work, work_fn);
	pw->pw_data = data;
}

static int __init padata_work_alloc_mt(int nworks, void *data,
				       struct list_head *head)
{
	int i;

	spin_lock(&padata_works_lock);
	/* Start at 1 because the current task participates in the job. */
	for (i = 1; i < nworks; ++i) {
		struct padata_work *pw = padata_work_alloc();

		if (!pw)
			break;
		padata_work_init(pw, padata_mt_helper, data, 0);
		list_add(&pw->pw_list, head);
	}
	spin_unlock(&padata_works_lock);

	return i;
}

static void padata_work_free(struct padata_work *pw)
{
	lockdep_assert_held(&padata_works_lock);
	list_add(&pw->pw_list, &padata_free_works);
}

static void __init padata_works_free(struct list_head *works)
{
	struct padata_work *cur, *next;

	if (list_empty(works))
		return;

	spin_lock(&padata_works_lock);
	list_for_each_entry_safe(cur, next, works, pw_list) {
		list_del(&cur->pw_list);
		padata_work_free(cur);
	}
	spin_unlock(&padata_works_lock);
}

static void padata_parallel_worker(struct work_struct *parallel_work)
{
	struct padata_work *pw = container_of(parallel_work, struct padata_work,
					      pw_work);
	struct padata_priv *padata = pw->pw_data;

	local_bh_disable();
	padata->parallel(padata);
	spin_lock(&padata_works_lock);
	padata_work_free(pw);
	spin_unlock(&padata_works_lock);
	local_bh_enable();
}

/**
 * padata_do_parallel - padata parallelization function
 *
 * @ps: padatashell
 * @padata: object to be parallelized
 * @cb_cpu: pointer to the CPU that the serialization callback function should
 *          run on.  If it's not in the serial cpumask of @pinst
 *          (i.e. cpumask.cbcpu), this function selects a fallback CPU and if
 *          none found, returns -EINVAL.
 *
 * 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.
 *
 * Return: 0 on success or else negative error code.
 */
int padata_do_parallel(struct padata_shell *ps,
		       struct padata_priv *padata, int *cb_cpu)
{
	struct padata_instance *pinst = ps->pinst;
	int i, cpu, cpu_index, err;
	struct parallel_data *pd;
	struct padata_work *pw;

	rcu_read_lock_bh();

	pd = rcu_dereference_bh(ps->pd);

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

	if (!cpumask_test_cpu(*cb_cpu, pd->cpumask.cbcpu)) {
		if (cpumask_empty(pd->cpumask.cbcpu))
			goto out;

		/* Select an alternate fallback CPU and notify the caller. */
		cpu_index = *cb_cpu % cpumask_weight(pd->cpumask.cbcpu);

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

		*cb_cpu = cpu;
	}

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

	refcount_inc(&pd->refcnt);
	padata->pd = pd;
	padata->cb_cpu = *cb_cpu;

	spin_lock(&padata_works_lock);
	padata->seq_nr = ++pd->seq_nr;
	pw = padata_work_alloc();
	spin_unlock(&padata_works_lock);

	if (!pw) {
		/* Maximum works limit exceeded, run in the current task. */
		padata->parallel(padata);
	}

	rcu_read_unlock_bh();

	if (pw) {
		padata_work_init(pw, padata_parallel_worker, padata, 0);
		queue_work(pinst->parallel_wq, &pw->pw_work);
	}

	return 0;
out:
	rcu_read_unlock_bh();

	return err;
}
EXPORT_SYMBOL(padata_do_parallel);

/*
 * padata_find_next - Find the next object that needs serialization.
 *
 * Return:
 * * A pointer to the control struct of the next object that needs
 *   serialization, if present in one of the percpu reorder queues.
 * * NULL, 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.
 */
static struct padata_priv *padata_find_next(struct parallel_data *pd,
					    bool remove_object)
{
	struct padata_priv *padata;
	struct padata_list *reorder;
	int cpu = pd->cpu;

	reorder = per_cpu_ptr(pd->reorder_list, cpu);

	spin_lock(&reorder->lock);
	if (list_empty(&reorder->list)) {
		spin_unlock(&reorder->lock);
		return NULL;
	}

	padata = list_entry(reorder->list.next, struct padata_priv, list);

	/*
	 * Checks the rare case where two or more parallel jobs have hashed to
	 * the same CPU and one of the later ones finishes first.
	 */
	if (padata->seq_nr != pd->processed) {
		spin_unlock(&reorder->lock);
		return NULL;
	}

	if (remove_object) {
		list_del_init(&padata->list);
		++pd->processed;
		pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false);
	}

	spin_unlock(&reorder->lock);
	return padata;
}

static void padata_reorder(struct parallel_data *pd)
{
	struct padata_instance *pinst = pd->ps->pinst;
	int cb_cpu;
	struct padata_priv *padata;
	struct padata_serial_queue *squeue;
	struct padata_list *reorder;

	/*
	 * 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_find_next(pd, true);

		/*
		 * If 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)
			break;

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

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

		queue_work_on(cb_cpu, pinst->serial_wq, &squeue->work);
	}

	spin_unlock_bh(&pd->lock);

	/*
	 * The next object that needs serialization might have arrived to
	 * the reorder queues in the meantime.
	 *
	 * Ensure reorder queue is read after pd->lock is dropped so we see
	 * new objects from another task in padata_do_serial.  Pairs with
	 * smp_mb in padata_do_serial.
	 */
	smp_mb();

	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
	if (!list_empty(&reorder->list) && padata_find_next(pd, false))
		queue_work(pinst->serial_wq, &pd->reorder_work);
}

static void invoke_padata_reorder(struct work_struct *work)
{
	struct parallel_data *pd;

	local_bh_disable();
	pd = container_of(work, struct parallel_data, reorder_work);
	padata_reorder(pd);
	local_bh_enable();
}

static void padata_serial_worker(struct work_struct *serial_work)
{
	struct padata_serial_queue *squeue;
	struct parallel_data *pd;
	LIST_HEAD(local_list);
	int cnt;

	local_bh_disable();
	squeue = container_of(serial_work, struct padata_serial_queue, work);
	pd = squeue->pd;

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

	cnt = 0;

	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);
		cnt++;
	}
	local_bh_enable();

	if (refcount_sub_and_test(cnt, &pd->refcnt))
		padata_free_pd(pd);
}

/**
 * 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)
{
	struct parallel_data *pd = padata->pd;
	int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr);
	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
	struct padata_priv *cur;
	struct list_head *pos;

	spin_lock(&reorder->lock);
	/* Sort in ascending order of sequence number. */
	list_for_each_prev(pos, &reorder->list) {
		cur = list_entry(pos, struct padata_priv, list);
		if (cur->seq_nr < padata->seq_nr)
			break;
	}
	list_add(&padata->list, pos);
	spin_unlock(&reorder->lock);

	/*
	 * Ensure the addition to the reorder list is ordered correctly
	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
	 * in padata_reorder.
	 */
	smp_mb();

	padata_reorder(pd);
}
EXPORT_SYMBOL(padata_do_serial);

static int padata_setup_cpumasks(struct padata_instance *pinst)
{
	struct workqueue_attrs *attrs;
	int err;

	attrs = alloc_workqueue_attrs();
	if (!attrs)
		return -ENOMEM;

	/* Restrict parallel_wq workers to pd->cpumask.pcpu. */
	cpumask_copy(attrs->cpumask, pinst->cpumask.pcpu);
	err = apply_workqueue_attrs(pinst->parallel_wq, attrs);
	free_workqueue_attrs(attrs);

	return err;
}

static void __init padata_mt_helper(struct work_struct *w)
{
	struct padata_work *pw = container_of(w, struct padata_work, pw_work);
	struct padata_mt_job_state *ps = pw->pw_data;
	struct padata_mt_job *job = ps->job;
	bool done;

	spin_lock(&ps->lock);

	while (job->size > 0) {
		unsigned long start, size, end;

		start = job->start;
		/* So end is chunk size aligned if enough work remains. */
		size = roundup(start + 1, ps->chunk_size) - start;
		size = min(size, job->size);
		end = start + size;

		job->start = end;
		job->size -= size;

		spin_unlock(&ps->lock);
		job->thread_fn(start, end, job->fn_arg);
		spin_lock(&ps->lock);
	}

	++ps->nworks_fini;
	done = (ps->nworks_fini == ps->nworks);
	spin_unlock(&ps->lock);

	if (done)
		complete(&ps->completion);
}

/**
 * padata_do_multithreaded - run a multithreaded job
 * @job: Description of the job.
 *
 * See the definition of struct padata_mt_job for more details.
 */
void __init padata_do_multithreaded(struct padata_mt_job *job)
{
	/* In case threads finish at different times. */
	static const unsigned long load_balance_factor = 4;
	struct padata_work my_work, *pw;
	struct padata_mt_job_state ps;
	LIST_HEAD(works);
	int nworks;

	if (job->size == 0)
		return;

	/* Ensure at least one thread when size < min_chunk. */
	nworks = max(job->size / job->min_chunk, 1ul);
	nworks = min(nworks, job->max_threads);

	if (nworks == 1) {
		/* Single thread, no coordination needed, cut to the chase. */
		job->thread_fn(job->start, job->start + job->size, job->fn_arg);
		return;
	}

	spin_lock_init(&ps.lock);
	init_completion(&ps.completion);
	ps.job	       = job;
	ps.nworks      = padata_work_alloc_mt(nworks, &ps, &works);
	ps.nworks_fini = 0;

	/*
	 * Chunk size is the amount of work a helper does per call to the
	 * thread function.  Load balance large jobs between threads by
	 * increasing the number of chunks, guarantee at least the minimum
	 * chunk size from the caller, and honor the caller's alignment.
	 */
	ps.chunk_size = job->size / (ps.nworks * load_balance_factor);
	ps.chunk_size = max(ps.chunk_size, job->min_chunk);
	ps.chunk_size = roundup(ps.chunk_size, job->align);

	list_for_each_entry(pw, &works, pw_list)
		queue_work(system_unbound_wq, &pw->pw_work);

	/* Use the current thread, which saves starting a workqueue worker. */
	padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
	padata_mt_helper(&my_work.pw_work);

	/* Wait for all the helpers to finish. */
	wait_for_completion(&ps.completion);

	destroy_work_on_stack(&my_work.pw_work);
	padata_works_free(&works);
}

static void __padata_list_init(struct padata_list *pd_list)
{
	INIT_LIST_HEAD(&pd_list->list);
	spin_lock_init(&pd_list->lock);
}

/* Initialize all percpu queues used by serial workers */
static void padata_init_squeues(struct parallel_data *pd)
{
	int cpu;
	struct padata_serial_queue *squeue;

	for_each_cpu(cpu, pd->cpumask.cbcpu) {
		squeue = per_cpu_ptr(pd->squeue, cpu);
		squeue->pd = pd;
		__padata_list_init(&squeue->serial);
		INIT_WORK(&squeue->work, padata_serial_worker);
	}
}

/* Initialize per-CPU reorder lists */
static void padata_init_reorder_list(struct parallel_data *pd)
{
	int cpu;
	struct padata_list *list;

	for_each_cpu(cpu, pd->cpumask.pcpu) {
		list = per_cpu_ptr(pd->reorder_list, cpu);
		__padata_list_init(list);
	}
}

/* Allocate and initialize the internal cpumask dependend resources. */
static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
{
	struct padata_instance *pinst = ps->pinst;
	struct parallel_data *pd;

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

	pd->reorder_list = alloc_percpu(struct padata_list);
	if (!pd->reorder_list)
		goto err_free_pd;

	pd->squeue = alloc_percpu(struct padata_serial_queue);
	if (!pd->squeue)
		goto err_free_reorder_list;

	pd->ps = ps;

	if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
		goto err_free_squeue;
	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
		goto err_free_pcpu;

	cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask);
	cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask);

	padata_init_reorder_list(pd);
	padata_init_squeues(pd);
	pd->seq_nr = -1;
	refcount_set(&pd->refcnt, 1);
	spin_lock_init(&pd->lock);
	pd->cpu = cpumask_first(pd->cpumask.pcpu);
	INIT_WORK(&pd->reorder_work, invoke_padata_reorder);

	return pd;

err_free_pcpu:
	free_cpumask_var(pd->cpumask.pcpu);
err_free_squeue:
	free_percpu(pd->squeue);
err_free_reorder_list:
	free_percpu(pd->reorder_list);
err_free_pd:
	kfree(pd);
err:
	return NULL;
}

static void padata_free_pd(struct parallel_data *pd)
{
	free_cpumask_var(pd->cpumask.pcpu);
	free_cpumask_var(pd->cpumask.cbcpu);
	free_percpu(pd->reorder_list);
	free_percpu(pd->squeue);
	kfree(pd);
}

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();
}

/* Replace the internal control structure with a new one. */
static int padata_replace_one(struct padata_shell *ps)
{
	struct parallel_data *pd_new;

	pd_new = padata_alloc_pd(ps);
	if (!pd_new)
		return -ENOMEM;

	ps->opd = rcu_dereference_protected(ps->pd, 1);
	rcu_assign_pointer(ps->pd, pd_new);

	return 0;
}

static int padata_replace(struct padata_instance *pinst)
{
	struct padata_shell *ps;
	int err = 0;

	pinst->flags |= PADATA_RESET;

	list_for_each_entry(ps, &pinst->pslist, list) {
		err = padata_replace_one(ps);
		if (err)
			break;
	}

	synchronize_rcu();

	list_for_each_entry_continue_reverse(ps, &pinst->pslist, list)
		if (refcount_dec_and_test(&ps->opd->refcnt))
			padata_free_pd(ps->opd);

	pinst->flags &= ~PADATA_RESET;

	return err;
}

/* 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_online_mask)) {
		pinst->flags |= PADATA_INVALID;
		return false;
	}

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

static int __padata_set_cpumasks(struct padata_instance *pinst,
				 cpumask_var_t pcpumask,
				 cpumask_var_t cbcpumask)
{
	int valid;
	int err;

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

	valid = padata_validate_cpumask(pinst, cbcpumask);
	if (!valid)
		__padata_stop(pinst);

out_replace:
	cpumask_copy(pinst->cpumask.pcpu, pcpumask);
	cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);

	err = padata_setup_cpumasks(pinst) ?: padata_replace(pinst);

	if (valid)
		__padata_start(pinst);

	return err;
}

/**
 * padata_set_cpumask - Sets specified by @cpumask_type cpumask to the value
 *                      equivalent to @cpumask.
 * @pinst: padata instance
 * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding
 *                to parallel and serial cpumasks respectively.
 * @cpumask: the cpumask to use
 *
 * Return: 0 on success or negative error code
 */
int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
		       cpumask_var_t cpumask)
{
	struct cpumask *serial_mask, *parallel_mask;
	int err = -EINVAL;

	cpus_read_lock();
	mutex_lock(&pinst->lock);

	switch (cpumask_type) {
	case PADATA_CPU_PARALLEL:
		serial_mask = pinst->cpumask.cbcpu;
		parallel_mask = cpumask;
		break;
	case PADATA_CPU_SERIAL:
		parallel_mask = pinst->cpumask.pcpu;
		serial_mask = cpumask;
		break;
	default:
		 goto out;
	}

	err =  __padata_set_cpumasks(pinst, parallel_mask, serial_mask);

out:
	mutex_unlock(&pinst->lock);
	cpus_read_unlock();

	return err;
}
EXPORT_SYMBOL(padata_set_cpumask);

#ifdef CONFIG_HOTPLUG_CPU

static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
{
	int err = 0;

	if (cpumask_test_cpu(cpu, cpu_online_mask)) {
		err = padata_replace(pinst);

		if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) &&
		    padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
			__padata_start(pinst);
	}

	return err;
}

static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
{
	int err = 0;

	if (!cpumask_test_cpu(cpu, cpu_online_mask)) {
		if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) ||
		    !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
			__padata_stop(pinst);

		err = padata_replace(pinst);
	}

	return err;
}

static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu)
{
	return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) ||
		cpumask_test_cpu(cpu, pinst->cpumask.cbcpu);
}

static int padata_cpu_online(unsigned int cpu, struct hlist_node *node)
{
	struct padata_instance *pinst;
	int ret;

	pinst = hlist_entry_safe(node, struct padata_instance, cpu_online_node);
	if (!pinst_has_cpu(pinst, cpu))
		return 0;

	mutex_lock(&pinst->lock);
	ret = __padata_add_cpu(pinst, cpu);
	mutex_unlock(&pinst->lock);
	return ret;
}

static int padata_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
	struct padata_instance *pinst;
	int ret;

	pinst = hlist_entry_safe(node, struct padata_instance, cpu_dead_node);
	if (!pinst_has_cpu(pinst, cpu))
		return 0;

	mutex_lock(&pinst->lock);
	ret = __padata_remove_cpu(pinst, cpu);
	mutex_unlock(&pinst->lock);
	return ret;
}

static enum cpuhp_state hp_online;
#endif

static void __padata_free(struct padata_instance *pinst)
{
#ifdef CONFIG_HOTPLUG_CPU
	cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD,
					    &pinst->cpu_dead_node);
	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpu_online_node);
#endif

	WARN_ON(!list_empty(&pinst->pslist));

	free_cpumask_var(pinst->cpumask.pcpu);
	free_cpumask_var(pinst->cpumask.cbcpu);
	destroy_workqueue(pinst->serial_wq);
	destroy_workqueue(pinst->parallel_wq);
	kfree(pinst);
}

#define kobj2pinst(_kobj)					\
	container_of(_kobj, struct padata_instance, kobj)
#define attr2pentry(_attr)					\
	container_of(_attr, struct padata_sysfs_entry, attr)

static void padata_sysfs_release(struct kobject *kobj)
{
	struct padata_instance *pinst = kobj2pinst(kobj);
	__padata_free(pinst);
}

struct padata_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct padata_instance *, struct attribute *, char *);
	ssize_t (*store)(struct padata_instance *, struct attribute *,
			 const char *, size_t);
};

static ssize_t show_cpumask(struct padata_instance *pinst,
			    struct attribute *attr,  char *buf)
{
	struct cpumask *cpumask;
	ssize_t len;

	mutex_lock(&pinst->lock);
	if (!strcmp(attr->name, "serial_cpumask"))
		cpumask = pinst->cpumask.cbcpu;
	else
		cpumask = pinst->cpumask.pcpu;

	len = snprintf(buf, PAGE_SIZE, "%*pb\n",
		       nr_cpu_ids, cpumask_bits(cpumask));
	mutex_unlock(&pinst->lock);
	return len < PAGE_SIZE ? len : -EINVAL;
}

static ssize_t store_cpumask(struct padata_instance *pinst,
			     struct attribute *attr,
			     const char *buf, size_t count)
{
	cpumask_var_t new_cpumask;
	ssize_t ret;
	int mask_type;

	if (!alloc_cpumask_var(&new_cpumask, GFP_KERNEL))
		return -ENOMEM;

	ret = bitmap_parse(buf, count, cpumask_bits(new_cpumask),
			   nr_cpumask_bits);
	if (ret < 0)
		goto out;

	mask_type = !strcmp(attr->name, "serial_cpumask") ?
		PADATA_CPU_SERIAL : PADATA_CPU_PARALLEL;
	ret = padata_set_cpumask(pinst, mask_type, new_cpumask);
	if (!ret)
		ret = count;

out:
	free_cpumask_var(new_cpumask);
	return ret;
}

#define PADATA_ATTR_RW(_name, _show_name, _store_name)		\
	static struct padata_sysfs_entry _name##_attr =		\
		__ATTR(_name, 0644, _show_name, _store_name)
#define PADATA_ATTR_RO(_name, _show_name)		\
	static struct padata_sysfs_entry _name##_attr = \
		__ATTR(_name, 0400, _show_name, NULL)

PADATA_ATTR_RW(serial_cpumask, show_cpumask, store_cpumask);
PADATA_ATTR_RW(parallel_cpumask, show_cpumask, store_cpumask);

/*
 * Padata sysfs provides the following objects:
 * serial_cpumask   [RW] - cpumask for serial workers
 * parallel_cpumask [RW] - cpumask for parallel workers
 */
static struct attribute *padata_default_attrs[] = {
	&serial_cpumask_attr.attr,
	&parallel_cpumask_attr.attr,
	NULL,
};
ATTRIBUTE_GROUPS(padata_default);

static ssize_t padata_sysfs_show(struct kobject *kobj,
				 struct attribute *attr, char *buf)
{
	struct padata_instance *pinst;
	struct padata_sysfs_entry *pentry;
	ssize_t ret = -EIO;

	pinst = kobj2pinst(kobj);
	pentry = attr2pentry(attr);
	if (pentry->show)
		ret = pentry->show(pinst, attr, buf);

	return ret;
}

static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr,
				  const char *buf, size_t count)
{
	struct padata_instance *pinst;
	struct padata_sysfs_entry *pentry;
	ssize_t ret = -EIO;

	pinst = kobj2pinst(kobj);
	pentry = attr2pentry(attr);
	if (pentry->show)
		ret = pentry->store(pinst, attr, buf, count);

	return ret;
}

static const struct sysfs_ops padata_sysfs_ops = {
	.show = padata_sysfs_show,
	.store = padata_sysfs_store,
};

static struct kobj_type padata_attr_type = {
	.sysfs_ops = &padata_sysfs_ops,
	.default_groups = padata_default_groups,
	.release = padata_sysfs_release,
};

/**
 * padata_alloc - allocate and initialize a padata instance
 * @name: used to identify the instance
 *
 * Return: new instance on success, NULL on error
 */
struct padata_instance *padata_alloc(const char *name)
{
	struct padata_instance *pinst;

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

	pinst->parallel_wq = alloc_workqueue("%s_parallel", WQ_UNBOUND, 0,
					     name);
	if (!pinst->parallel_wq)
		goto err_free_inst;

	cpus_read_lock();

	pinst->serial_wq = alloc_workqueue("%s_serial", WQ_MEM_RECLAIM |
					   WQ_CPU_INTENSIVE, 1, name);
	if (!pinst->serial_wq)
		goto err_put_cpus;

	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
		goto err_free_serial_wq;
	if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
		free_cpumask_var(pinst->cpumask.pcpu);
		goto err_free_serial_wq;
	}

	INIT_LIST_HEAD(&pinst->pslist);

	cpumask_copy(pinst->cpumask.pcpu, cpu_possible_mask);
	cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask);

	if (padata_setup_cpumasks(pinst))
		goto err_free_masks;

	__padata_start(pinst);

	kobject_init(&pinst->kobj, &padata_attr_type);
	mutex_init(&pinst->lock);

#ifdef CONFIG_HOTPLUG_CPU
	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online,
						    &pinst->cpu_online_node);
	cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD,
						    &pinst->cpu_dead_node);
#endif

	cpus_read_unlock();

	return pinst;

err_free_masks:
	free_cpumask_var(pinst->cpumask.pcpu);
	free_cpumask_var(pinst->cpumask.cbcpu);
err_free_serial_wq:
	destroy_workqueue(pinst->serial_wq);
err_put_cpus:
	cpus_read_unlock();
	destroy_workqueue(pinst->parallel_wq);
err_free_inst:
	kfree(pinst);
err:
	return NULL;
}
EXPORT_SYMBOL(padata_alloc);

/**
 * padata_free - free a padata instance
 *
 * @pinst: padata instance to free
 */
void padata_free(struct padata_instance *pinst)
{
	kobject_put(&pinst->kobj);
}
EXPORT_SYMBOL(padata_free);

/**
 * padata_alloc_shell - Allocate and initialize padata shell.
 *
 * @pinst: Parent padata_instance object.
 *
 * Return: new shell on success, NULL on error
 */
struct padata_shell *padata_alloc_shell(struct padata_instance *pinst)
{
	struct parallel_data *pd;
	struct padata_shell *ps;

	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
	if (!ps)
		goto out;

	ps->pinst = pinst;

	cpus_read_lock();
	pd = padata_alloc_pd(ps);
	cpus_read_unlock();

	if (!pd)
		goto out_free_ps;

	mutex_lock(&pinst->lock);
	RCU_INIT_POINTER(ps->pd, pd);
	list_add(&ps->list, &pinst->pslist);
	mutex_unlock(&pinst->lock);

	return ps;

out_free_ps:
	kfree(ps);
out:
	return NULL;
}
EXPORT_SYMBOL(padata_alloc_shell);

/**
 * padata_free_shell - free a padata shell
 *
 * @ps: padata shell to free
 */
void padata_free_shell(struct padata_shell *ps)
{
	if (!ps)
		return;

	mutex_lock(&ps->pinst->lock);
	list_del(&ps->list);
	padata_free_pd(rcu_dereference_protected(ps->pd, 1));
	mutex_unlock(&ps->pinst->lock);

	kfree(ps);
}
EXPORT_SYMBOL(padata_free_shell);

void __init padata_init(void)
{
	unsigned int i, possible_cpus;
#ifdef CONFIG_HOTPLUG_CPU
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online",
				      padata_cpu_online, NULL);
	if (ret < 0)
		goto err;
	hp_online = ret;

	ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead",
				      NULL, padata_cpu_dead);
	if (ret < 0)
		goto remove_online_state;
#endif

	possible_cpus = num_possible_cpus();
	padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work),
				     GFP_KERNEL);
	if (!padata_works)
		goto remove_dead_state;

	for (i = 0; i < possible_cpus; ++i)
		list_add(&padata_works[i].pw_list, &padata_free_works);

	return;

remove_dead_state:
#ifdef CONFIG_HOTPLUG_CPU
	cpuhp_remove_multi_state(CPUHP_PADATA_DEAD);
remove_online_state:
	cpuhp_remove_multi_state(hp_online);
err:
#endif
	pr_warn("padata: initialization failed\n");
}