summaryrefslogtreecommitdiff
path: root/drivers/perf/arm_cspmu/arm_cspmu.c
blob: e31302ab7e37c3b4decbcf8c230e467e2c836f68 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
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
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
// SPDX-License-Identifier: GPL-2.0
/*
 * ARM CoreSight Architecture PMU driver.
 *
 * This driver adds support for uncore PMU based on ARM CoreSight Performance
 * Monitoring Unit Architecture. The PMU is accessible via MMIO registers and
 * like other uncore PMUs, it does not support process specific events and
 * cannot be used in sampling mode.
 *
 * This code is based on other uncore PMUs like ARM DSU PMU. It provides a
 * generic implementation to operate the PMU according to CoreSight PMU
 * architecture and ACPI ARM PMU table (APMT) documents below:
 *   - ARM CoreSight PMU architecture document number: ARM IHI 0091 A.a-00bet0.
 *   - APMT document number: ARM DEN0117.
 *
 * The user should refer to the vendor technical documentation to get details
 * about the supported events.
 *
 * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 *
 */

#include <linux/acpi.h>
#include <linux/cacheinfo.h>
#include <linux/ctype.h>
#include <linux/interrupt.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/module.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <acpi/processor.h>

#include "arm_cspmu.h"
#include "nvidia_cspmu.h"

#define PMUNAME "arm_cspmu"
#define DRVNAME "arm-cs-arch-pmu"

#define ARM_CSPMU_CPUMASK_ATTR(_name, _config)			\
	ARM_CSPMU_EXT_ATTR(_name, arm_cspmu_cpumask_show,	\
				(unsigned long)_config)

/*
 * CoreSight PMU Arch register offsets.
 */
#define PMEVCNTR_LO					0x0
#define PMEVCNTR_HI					0x4
#define PMEVTYPER					0x400
#define PMCCFILTR					0x47C
#define PMEVFILTR					0xA00
#define PMCNTENSET					0xC00
#define PMCNTENCLR					0xC20
#define PMINTENSET					0xC40
#define PMINTENCLR					0xC60
#define PMOVSCLR					0xC80
#define PMOVSSET					0xCC0
#define PMCFGR						0xE00
#define PMCR						0xE04
#define PMIIDR						0xE08

/* PMCFGR register field */
#define PMCFGR_NCG					GENMASK(31, 28)
#define PMCFGR_HDBG					BIT(24)
#define PMCFGR_TRO					BIT(23)
#define PMCFGR_SS					BIT(22)
#define PMCFGR_FZO					BIT(21)
#define PMCFGR_MSI					BIT(20)
#define PMCFGR_UEN					BIT(19)
#define PMCFGR_NA					BIT(17)
#define PMCFGR_EX					BIT(16)
#define PMCFGR_CCD					BIT(15)
#define PMCFGR_CC					BIT(14)
#define PMCFGR_SIZE					GENMASK(13, 8)
#define PMCFGR_N					GENMASK(7, 0)

/* PMCR register field */
#define PMCR_TRO					BIT(11)
#define PMCR_HDBG					BIT(10)
#define PMCR_FZO					BIT(9)
#define PMCR_NA						BIT(8)
#define PMCR_DP						BIT(5)
#define PMCR_X						BIT(4)
#define PMCR_D						BIT(3)
#define PMCR_C						BIT(2)
#define PMCR_P						BIT(1)
#define PMCR_E						BIT(0)

/* Each SET/CLR register supports up to 32 counters. */
#define ARM_CSPMU_SET_CLR_COUNTER_SHIFT		5
#define ARM_CSPMU_SET_CLR_COUNTER_NUM		\
	(1 << ARM_CSPMU_SET_CLR_COUNTER_SHIFT)

/* Convert counter idx into SET/CLR register number. */
#define COUNTER_TO_SET_CLR_ID(idx)			\
	(idx >> ARM_CSPMU_SET_CLR_COUNTER_SHIFT)

/* Convert counter idx into SET/CLR register bit. */
#define COUNTER_TO_SET_CLR_BIT(idx)			\
	(idx & (ARM_CSPMU_SET_CLR_COUNTER_NUM - 1))

#define ARM_CSPMU_ACTIVE_CPU_MASK		0x0
#define ARM_CSPMU_ASSOCIATED_CPU_MASK		0x1

/* Check if field f in flags is set with value v */
#define CHECK_APMT_FLAG(flags, f, v) \
	((flags & (ACPI_APMT_FLAGS_ ## f)) == (ACPI_APMT_FLAGS_ ## f ## _ ## v))

/* Check and use default if implementer doesn't provide attribute callback */
#define CHECK_DEFAULT_IMPL_OPS(ops, callback)			\
	do {							\
		if (!ops->callback)				\
			ops->callback = arm_cspmu_ ## callback;	\
	} while (0)

/*
 * Maximum poll count for reading counter value using high-low-high sequence.
 */
#define HILOHI_MAX_POLL	1000

/* JEDEC-assigned JEP106 identification code */
#define ARM_CSPMU_IMPL_ID_NVIDIA		0x36B

static unsigned long arm_cspmu_cpuhp_state;

/*
 * In CoreSight PMU architecture, all of the MMIO registers are 32-bit except
 * counter register. The counter register can be implemented as 32-bit or 64-bit
 * register depending on the value of PMCFGR.SIZE field. For 64-bit access,
 * single-copy 64-bit atomic support is implementation defined. APMT node flag
 * is used to identify if the PMU supports 64-bit single copy atomic. If 64-bit
 * single copy atomic is not supported, the driver treats the register as a pair
 * of 32-bit register.
 */

/*
 * Read 64-bit register as a pair of 32-bit registers using hi-lo-hi sequence.
 */
static u64 read_reg64_hilohi(const void __iomem *addr, u32 max_poll_count)
{
	u32 val_lo, val_hi;
	u64 val;

	/* Use high-low-high sequence to avoid tearing */
	do {
		if (max_poll_count-- == 0) {
			pr_err("ARM CSPMU: timeout hi-low-high sequence\n");
			return 0;
		}

		val_hi = readl(addr + 4);
		val_lo = readl(addr);
	} while (val_hi != readl(addr + 4));

	val = (((u64)val_hi << 32) | val_lo);

	return val;
}

/* Check if PMU supports 64-bit single copy atomic. */
static inline bool supports_64bit_atomics(const struct arm_cspmu *cspmu)
{
	return CHECK_APMT_FLAG(cspmu->apmt_node->flags, ATOMIC, SUPP);
}

/* Check if cycle counter is supported. */
static inline bool supports_cycle_counter(const struct arm_cspmu *cspmu)
{
	return (cspmu->pmcfgr & PMCFGR_CC);
}

/* Get counter size, which is (PMCFGR_SIZE + 1). */
static inline u32 counter_size(const struct arm_cspmu *cspmu)
{
	return FIELD_GET(PMCFGR_SIZE, cspmu->pmcfgr) + 1;
}

/* Get counter mask. */
static inline u64 counter_mask(const struct arm_cspmu *cspmu)
{
	return GENMASK_ULL(counter_size(cspmu) - 1, 0);
}

/* Check if counter is implemented as 64-bit register. */
static inline bool use_64b_counter_reg(const struct arm_cspmu *cspmu)
{
	return (counter_size(cspmu) > 32);
}

ssize_t arm_cspmu_sysfs_event_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct dev_ext_attribute *eattr =
		container_of(attr, struct dev_ext_attribute, attr);
	return sysfs_emit(buf, "event=0x%llx\n",
			  (unsigned long long)eattr->var);
}
EXPORT_SYMBOL_GPL(arm_cspmu_sysfs_event_show);

/* Default event list. */
static struct attribute *arm_cspmu_event_attrs[] = {
	ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT),
	NULL,
};

static struct attribute **
arm_cspmu_get_event_attrs(const struct arm_cspmu *cspmu)
{
	struct attribute **attrs;

	attrs = devm_kmemdup(cspmu->dev, arm_cspmu_event_attrs,
		sizeof(arm_cspmu_event_attrs), GFP_KERNEL);

	return attrs;
}

static umode_t
arm_cspmu_event_attr_is_visible(struct kobject *kobj,
				struct attribute *attr, int unused)
{
	struct device *dev = kobj_to_dev(kobj);
	struct arm_cspmu *cspmu = to_arm_cspmu(dev_get_drvdata(dev));
	struct perf_pmu_events_attr *eattr;

	eattr = container_of(attr, typeof(*eattr), attr.attr);

	/* Hide cycle event if not supported */
	if (!supports_cycle_counter(cspmu) &&
	    eattr->id == ARM_CSPMU_EVT_CYCLES_DEFAULT)
		return 0;

	return attr->mode;
}

ssize_t arm_cspmu_sysfs_format_show(struct device *dev,
				struct device_attribute *attr,
				char *buf)
{
	struct dev_ext_attribute *eattr =
		container_of(attr, struct dev_ext_attribute, attr);
	return sysfs_emit(buf, "%s\n", (char *)eattr->var);
}
EXPORT_SYMBOL_GPL(arm_cspmu_sysfs_format_show);

static struct attribute *arm_cspmu_format_attrs[] = {
	ARM_CSPMU_FORMAT_EVENT_ATTR,
	ARM_CSPMU_FORMAT_FILTER_ATTR,
	NULL,
};

static struct attribute **
arm_cspmu_get_format_attrs(const struct arm_cspmu *cspmu)
{
	struct attribute **attrs;

	attrs = devm_kmemdup(cspmu->dev, arm_cspmu_format_attrs,
		sizeof(arm_cspmu_format_attrs), GFP_KERNEL);

	return attrs;
}

static u32 arm_cspmu_event_type(const struct perf_event *event)
{
	return event->attr.config & ARM_CSPMU_EVENT_MASK;
}

static bool arm_cspmu_is_cycle_counter_event(const struct perf_event *event)
{
	return (event->attr.config == ARM_CSPMU_EVT_CYCLES_DEFAULT);
}

static u32 arm_cspmu_event_filter(const struct perf_event *event)
{
	return event->attr.config1 & ARM_CSPMU_FILTER_MASK;
}

static ssize_t arm_cspmu_identifier_show(struct device *dev,
					 struct device_attribute *attr,
					 char *page)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(dev_get_drvdata(dev));

	return sysfs_emit(page, "%s\n", cspmu->identifier);
}

static struct device_attribute arm_cspmu_identifier_attr =
	__ATTR(identifier, 0444, arm_cspmu_identifier_show, NULL);

static struct attribute *arm_cspmu_identifier_attrs[] = {
	&arm_cspmu_identifier_attr.attr,
	NULL,
};

static struct attribute_group arm_cspmu_identifier_attr_group = {
	.attrs = arm_cspmu_identifier_attrs,
};

static const char *arm_cspmu_get_identifier(const struct arm_cspmu *cspmu)
{
	const char *identifier =
		devm_kasprintf(cspmu->dev, GFP_KERNEL, "%x",
			       cspmu->impl.pmiidr);
	return identifier;
}

static const char *arm_cspmu_type_str[ACPI_APMT_NODE_TYPE_COUNT] = {
	"mc",
	"smmu",
	"pcie",
	"acpi",
	"cache",
};

static const char *arm_cspmu_get_name(const struct arm_cspmu *cspmu)
{
	struct device *dev;
	struct acpi_apmt_node *apmt_node;
	u8 pmu_type;
	char *name;
	char acpi_hid_string[ACPI_ID_LEN] = { 0 };
	static atomic_t pmu_idx[ACPI_APMT_NODE_TYPE_COUNT] = { 0 };

	dev = cspmu->dev;
	apmt_node = cspmu->apmt_node;
	pmu_type = apmt_node->type;

	if (pmu_type >= ACPI_APMT_NODE_TYPE_COUNT) {
		dev_err(dev, "unsupported PMU type-%u\n", pmu_type);
		return NULL;
	}

	if (pmu_type == ACPI_APMT_NODE_TYPE_ACPI) {
		memcpy(acpi_hid_string,
			&apmt_node->inst_primary,
			sizeof(apmt_node->inst_primary));
		name = devm_kasprintf(dev, GFP_KERNEL, "%s_%s_%s_%u", PMUNAME,
				      arm_cspmu_type_str[pmu_type],
				      acpi_hid_string,
				      apmt_node->inst_secondary);
	} else {
		name = devm_kasprintf(dev, GFP_KERNEL, "%s_%s_%d", PMUNAME,
				      arm_cspmu_type_str[pmu_type],
				      atomic_fetch_inc(&pmu_idx[pmu_type]));
	}

	return name;
}

static ssize_t arm_cspmu_cpumask_show(struct device *dev,
				      struct device_attribute *attr,
				      char *buf)
{
	struct pmu *pmu = dev_get_drvdata(dev);
	struct arm_cspmu *cspmu = to_arm_cspmu(pmu);
	struct dev_ext_attribute *eattr =
		container_of(attr, struct dev_ext_attribute, attr);
	unsigned long mask_id = (unsigned long)eattr->var;
	const cpumask_t *cpumask;

	switch (mask_id) {
	case ARM_CSPMU_ACTIVE_CPU_MASK:
		cpumask = &cspmu->active_cpu;
		break;
	case ARM_CSPMU_ASSOCIATED_CPU_MASK:
		cpumask = &cspmu->associated_cpus;
		break;
	default:
		return 0;
	}
	return cpumap_print_to_pagebuf(true, buf, cpumask);
}

static struct attribute *arm_cspmu_cpumask_attrs[] = {
	ARM_CSPMU_CPUMASK_ATTR(cpumask, ARM_CSPMU_ACTIVE_CPU_MASK),
	ARM_CSPMU_CPUMASK_ATTR(associated_cpus, ARM_CSPMU_ASSOCIATED_CPU_MASK),
	NULL,
};

static struct attribute_group arm_cspmu_cpumask_attr_group = {
	.attrs = arm_cspmu_cpumask_attrs,
};

struct impl_match {
	u32 pmiidr;
	u32 mask;
	int (*impl_init_ops)(struct arm_cspmu *cspmu);
};

static const struct impl_match impl_match[] = {
	{
	  .pmiidr = ARM_CSPMU_IMPL_ID_NVIDIA,
	  .mask = ARM_CSPMU_PMIIDR_IMPLEMENTER,
	  .impl_init_ops = nv_cspmu_init_ops
	},
	{}
};

static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
{
	int ret;
	struct acpi_apmt_node *apmt_node = cspmu->apmt_node;
	struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
	const struct impl_match *match = impl_match;

	/*
	 * Get PMU implementer and product id from APMT node.
	 * If APMT node doesn't have implementer/product id, try get it
	 * from PMIIDR.
	 */
	cspmu->impl.pmiidr =
		(apmt_node->impl_id) ? apmt_node->impl_id :
				       readl(cspmu->base0 + PMIIDR);

	/* Find implementer specific attribute ops. */
	for (; match->pmiidr; match++) {
		const u32 mask = match->mask;

		if ((match->pmiidr & mask) == (cspmu->impl.pmiidr & mask)) {
			ret = match->impl_init_ops(cspmu);
			if (ret)
				return ret;

			break;
		}
	}

	/* Use default callbacks if implementer doesn't provide one. */
	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_format_attrs);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_identifier);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_name);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, is_cycle_counter_event);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter);
	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible);

	return 0;
}

static struct attribute_group *
arm_cspmu_alloc_event_attr_group(struct arm_cspmu *cspmu)
{
	struct attribute_group *event_group;
	struct device *dev = cspmu->dev;
	const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;

	event_group =
		devm_kzalloc(dev, sizeof(struct attribute_group), GFP_KERNEL);
	if (!event_group)
		return NULL;

	event_group->name = "events";
	event_group->is_visible = impl_ops->event_attr_is_visible;
	event_group->attrs = impl_ops->get_event_attrs(cspmu);

	if (!event_group->attrs)
		return NULL;

	return event_group;
}

static struct attribute_group *
arm_cspmu_alloc_format_attr_group(struct arm_cspmu *cspmu)
{
	struct attribute_group *format_group;
	struct device *dev = cspmu->dev;

	format_group =
		devm_kzalloc(dev, sizeof(struct attribute_group), GFP_KERNEL);
	if (!format_group)
		return NULL;

	format_group->name = "format";
	format_group->attrs = cspmu->impl.ops.get_format_attrs(cspmu);

	if (!format_group->attrs)
		return NULL;

	return format_group;
}

static struct attribute_group **
arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu)
{
	struct attribute_group **attr_groups = NULL;
	struct device *dev = cspmu->dev;
	const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
	int ret;

	ret = arm_cspmu_init_impl_ops(cspmu);
	if (ret)
		return NULL;

	cspmu->identifier = impl_ops->get_identifier(cspmu);
	cspmu->name = impl_ops->get_name(cspmu);

	if (!cspmu->identifier || !cspmu->name)
		return NULL;

	attr_groups = devm_kcalloc(dev, 5, sizeof(struct attribute_group *),
				   GFP_KERNEL);
	if (!attr_groups)
		return NULL;

	attr_groups[0] = arm_cspmu_alloc_event_attr_group(cspmu);
	attr_groups[1] = arm_cspmu_alloc_format_attr_group(cspmu);
	attr_groups[2] = &arm_cspmu_identifier_attr_group;
	attr_groups[3] = &arm_cspmu_cpumask_attr_group;

	if (!attr_groups[0] || !attr_groups[1])
		return NULL;

	return attr_groups;
}

static inline void arm_cspmu_reset_counters(struct arm_cspmu *cspmu)
{
	u32 pmcr = 0;

	pmcr |= PMCR_P;
	pmcr |= PMCR_C;
	writel(pmcr, cspmu->base0 + PMCR);
}

static inline void arm_cspmu_start_counters(struct arm_cspmu *cspmu)
{
	writel(PMCR_E, cspmu->base0 + PMCR);
}

static inline void arm_cspmu_stop_counters(struct arm_cspmu *cspmu)
{
	writel(0, cspmu->base0 + PMCR);
}

static void arm_cspmu_enable(struct pmu *pmu)
{
	bool disabled;
	struct arm_cspmu *cspmu = to_arm_cspmu(pmu);

	disabled = bitmap_empty(cspmu->hw_events.used_ctrs,
				cspmu->num_logical_ctrs);

	if (disabled)
		return;

	arm_cspmu_start_counters(cspmu);
}

static void arm_cspmu_disable(struct pmu *pmu)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(pmu);

	arm_cspmu_stop_counters(cspmu);
}

static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events,
				struct perf_event *event)
{
	int idx;
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);

	if (supports_cycle_counter(cspmu)) {
		if (cspmu->impl.ops.is_cycle_counter_event(event)) {
			/* Search for available cycle counter. */
			if (test_and_set_bit(cspmu->cycle_counter_logical_idx,
					     hw_events->used_ctrs))
				return -EAGAIN;

			return cspmu->cycle_counter_logical_idx;
		}

		/*
		 * Search a regular counter from the used counter bitmap.
		 * The cycle counter divides the bitmap into two parts. Search
		 * the first then second half to exclude the cycle counter bit.
		 */
		idx = find_first_zero_bit(hw_events->used_ctrs,
					  cspmu->cycle_counter_logical_idx);
		if (idx >= cspmu->cycle_counter_logical_idx) {
			idx = find_next_zero_bit(
				hw_events->used_ctrs,
				cspmu->num_logical_ctrs,
				cspmu->cycle_counter_logical_idx + 1);
		}
	} else {
		idx = find_first_zero_bit(hw_events->used_ctrs,
					  cspmu->num_logical_ctrs);
	}

	if (idx >= cspmu->num_logical_ctrs)
		return -EAGAIN;

	set_bit(idx, hw_events->used_ctrs);

	return idx;
}

static bool arm_cspmu_validate_event(struct pmu *pmu,
				 struct arm_cspmu_hw_events *hw_events,
				 struct perf_event *event)
{
	if (is_software_event(event))
		return true;

	/* Reject groups spanning multiple HW PMUs. */
	if (event->pmu != pmu)
		return false;

	return (arm_cspmu_get_event_idx(hw_events, event) >= 0);
}

/*
 * Make sure the group of events can be scheduled at once
 * on the PMU.
 */
static bool arm_cspmu_validate_group(struct perf_event *event)
{
	struct perf_event *sibling, *leader = event->group_leader;
	struct arm_cspmu_hw_events fake_hw_events;

	if (event->group_leader == event)
		return true;

	memset(&fake_hw_events, 0, sizeof(fake_hw_events));

	if (!arm_cspmu_validate_event(event->pmu, &fake_hw_events, leader))
		return false;

	for_each_sibling_event(sibling, leader) {
		if (!arm_cspmu_validate_event(event->pmu, &fake_hw_events,
						  sibling))
			return false;
	}

	return arm_cspmu_validate_event(event->pmu, &fake_hw_events, event);
}

static int arm_cspmu_event_init(struct perf_event *event)
{
	struct arm_cspmu *cspmu;
	struct hw_perf_event *hwc = &event->hw;

	cspmu = to_arm_cspmu(event->pmu);

	/*
	 * Following other "uncore" PMUs, we do not support sampling mode or
	 * attach to a task (per-process mode).
	 */
	if (is_sampling_event(event)) {
		dev_dbg(cspmu->pmu.dev,
			"Can't support sampling events\n");
		return -EOPNOTSUPP;
	}

	if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK) {
		dev_dbg(cspmu->pmu.dev,
			"Can't support per-task counters\n");
		return -EINVAL;
	}

	/*
	 * Make sure the CPU assignment is on one of the CPUs associated with
	 * this PMU.
	 */
	if (!cpumask_test_cpu(event->cpu, &cspmu->associated_cpus)) {
		dev_dbg(cspmu->pmu.dev,
			"Requested cpu is not associated with the PMU\n");
		return -EINVAL;
	}

	/* Enforce the current active CPU to handle the events in this PMU. */
	event->cpu = cpumask_first(&cspmu->active_cpu);
	if (event->cpu >= nr_cpu_ids)
		return -EINVAL;

	if (!arm_cspmu_validate_group(event))
		return -EINVAL;

	/*
	 * The logical counter id is tracked with hw_perf_event.extra_reg.idx.
	 * The physical counter id is tracked with hw_perf_event.idx.
	 * We don't assign an index until we actually place the event onto
	 * hardware. Use -1 to signify that we haven't decided where to put it
	 * yet.
	 */
	hwc->idx = -1;
	hwc->extra_reg.idx = -1;
	hwc->config = cspmu->impl.ops.event_type(event);

	return 0;
}

static inline u32 counter_offset(u32 reg_sz, u32 ctr_idx)
{
	return (PMEVCNTR_LO + (reg_sz * ctr_idx));
}

static void arm_cspmu_write_counter(struct perf_event *event, u64 val)
{
	u32 offset;
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);

	if (use_64b_counter_reg(cspmu)) {
		offset = counter_offset(sizeof(u64), event->hw.idx);

		writeq(val, cspmu->base1 + offset);
	} else {
		offset = counter_offset(sizeof(u32), event->hw.idx);

		writel(lower_32_bits(val), cspmu->base1 + offset);
	}
}

static u64 arm_cspmu_read_counter(struct perf_event *event)
{
	u32 offset;
	const void __iomem *counter_addr;
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);

	if (use_64b_counter_reg(cspmu)) {
		offset = counter_offset(sizeof(u64), event->hw.idx);
		counter_addr = cspmu->base1 + offset;

		return supports_64bit_atomics(cspmu) ?
			       readq(counter_addr) :
			       read_reg64_hilohi(counter_addr, HILOHI_MAX_POLL);
	}

	offset = counter_offset(sizeof(u32), event->hw.idx);
	return readl(cspmu->base1 + offset);
}

/*
 * arm_cspmu_set_event_period: Set the period for the counter.
 *
 * To handle cases of extreme interrupt latency, we program
 * the counter with half of the max count for the counters.
 */
static void arm_cspmu_set_event_period(struct perf_event *event)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	u64 val = counter_mask(cspmu) >> 1ULL;

	local64_set(&event->hw.prev_count, val);
	arm_cspmu_write_counter(event, val);
}

static void arm_cspmu_enable_counter(struct arm_cspmu *cspmu, int idx)
{
	u32 reg_id, reg_bit, inten_off, cnten_off;

	reg_id = COUNTER_TO_SET_CLR_ID(idx);
	reg_bit = COUNTER_TO_SET_CLR_BIT(idx);

	inten_off = PMINTENSET + (4 * reg_id);
	cnten_off = PMCNTENSET + (4 * reg_id);

	writel(BIT(reg_bit), cspmu->base0 + inten_off);
	writel(BIT(reg_bit), cspmu->base0 + cnten_off);
}

static void arm_cspmu_disable_counter(struct arm_cspmu *cspmu, int idx)
{
	u32 reg_id, reg_bit, inten_off, cnten_off;

	reg_id = COUNTER_TO_SET_CLR_ID(idx);
	reg_bit = COUNTER_TO_SET_CLR_BIT(idx);

	inten_off = PMINTENCLR + (4 * reg_id);
	cnten_off = PMCNTENCLR + (4 * reg_id);

	writel(BIT(reg_bit), cspmu->base0 + cnten_off);
	writel(BIT(reg_bit), cspmu->base0 + inten_off);
}

static void arm_cspmu_event_update(struct perf_event *event)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	u64 delta, prev, now;

	do {
		prev = local64_read(&hwc->prev_count);
		now = arm_cspmu_read_counter(event);
	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);

	delta = (now - prev) & counter_mask(cspmu);
	local64_add(delta, &event->count);
}

static inline void arm_cspmu_set_event(struct arm_cspmu *cspmu,
					struct hw_perf_event *hwc)
{
	u32 offset = PMEVTYPER + (4 * hwc->idx);

	writel(hwc->config, cspmu->base0 + offset);
}

static inline void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
					   struct hw_perf_event *hwc,
					   u32 filter)
{
	u32 offset = PMEVFILTR + (4 * hwc->idx);

	writel(filter, cspmu->base0 + offset);
}

static inline void arm_cspmu_set_cc_filter(struct arm_cspmu *cspmu, u32 filter)
{
	u32 offset = PMCCFILTR;

	writel(filter, cspmu->base0 + offset);
}

static void arm_cspmu_start(struct perf_event *event, int pmu_flags)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	u32 filter;

	/* We always reprogram the counter */
	if (pmu_flags & PERF_EF_RELOAD)
		WARN_ON(!(hwc->state & PERF_HES_UPTODATE));

	arm_cspmu_set_event_period(event);

	filter = cspmu->impl.ops.event_filter(event);

	if (event->hw.extra_reg.idx == cspmu->cycle_counter_logical_idx) {
		arm_cspmu_set_cc_filter(cspmu, filter);
	} else {
		arm_cspmu_set_event(cspmu, hwc);
		arm_cspmu_set_ev_filter(cspmu, hwc, filter);
	}

	hwc->state = 0;

	arm_cspmu_enable_counter(cspmu, hwc->idx);
}

static void arm_cspmu_stop(struct perf_event *event, int pmu_flags)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	if (hwc->state & PERF_HES_STOPPED)
		return;

	arm_cspmu_disable_counter(cspmu, hwc->idx);
	arm_cspmu_event_update(event);

	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
}

static inline u32 to_phys_idx(struct arm_cspmu *cspmu, u32 idx)
{
	return (idx == cspmu->cycle_counter_logical_idx) ?
		ARM_CSPMU_CYCLE_CNTR_IDX : idx;
}

static int arm_cspmu_add(struct perf_event *event, int flags)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	struct arm_cspmu_hw_events *hw_events = &cspmu->hw_events;
	struct hw_perf_event *hwc = &event->hw;
	int idx;

	if (WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(),
					   &cspmu->associated_cpus)))
		return -ENOENT;

	idx = arm_cspmu_get_event_idx(hw_events, event);
	if (idx < 0)
		return idx;

	hw_events->events[idx] = event;
	hwc->idx = to_phys_idx(cspmu, idx);
	hwc->extra_reg.idx = idx;
	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;

	if (flags & PERF_EF_START)
		arm_cspmu_start(event, PERF_EF_RELOAD);

	/* Propagate changes to the userspace mapping. */
	perf_event_update_userpage(event);

	return 0;
}

static void arm_cspmu_del(struct perf_event *event, int flags)
{
	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
	struct arm_cspmu_hw_events *hw_events = &cspmu->hw_events;
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->extra_reg.idx;

	arm_cspmu_stop(event, PERF_EF_UPDATE);

	hw_events->events[idx] = NULL;

	clear_bit(idx, hw_events->used_ctrs);

	perf_event_update_userpage(event);
}

static void arm_cspmu_read(struct perf_event *event)
{
	arm_cspmu_event_update(event);
}

static struct arm_cspmu *arm_cspmu_alloc(struct platform_device *pdev)
{
	struct acpi_apmt_node *apmt_node;
	struct arm_cspmu *cspmu;
	struct device *dev;

	dev = &pdev->dev;
	apmt_node = *(struct acpi_apmt_node **)dev_get_platdata(dev);
	if (!apmt_node) {
		dev_err(dev, "failed to get APMT node\n");
		return NULL;
	}

	cspmu = devm_kzalloc(dev, sizeof(*cspmu), GFP_KERNEL);
	if (!cspmu)
		return NULL;

	cspmu->dev = dev;
	cspmu->apmt_node = apmt_node;

	platform_set_drvdata(pdev, cspmu);

	return cspmu;
}

static int arm_cspmu_init_mmio(struct arm_cspmu *cspmu)
{
	struct device *dev;
	struct platform_device *pdev;
	struct acpi_apmt_node *apmt_node;

	dev = cspmu->dev;
	pdev = to_platform_device(dev);
	apmt_node = cspmu->apmt_node;

	/* Base address for page 0. */
	cspmu->base0 = devm_platform_ioremap_resource(pdev, 0);
	if (IS_ERR(cspmu->base0)) {
		dev_err(dev, "ioremap failed for page-0 resource\n");
		return PTR_ERR(cspmu->base0);
	}

	/* Base address for page 1 if supported. Otherwise point to page 0. */
	cspmu->base1 = cspmu->base0;
	if (CHECK_APMT_FLAG(apmt_node->flags, DUAL_PAGE, SUPP)) {
		cspmu->base1 = devm_platform_ioremap_resource(pdev, 1);
		if (IS_ERR(cspmu->base1)) {
			dev_err(dev, "ioremap failed for page-1 resource\n");
			return PTR_ERR(cspmu->base1);
		}
	}

	cspmu->pmcfgr = readl(cspmu->base0 + PMCFGR);

	cspmu->num_logical_ctrs = FIELD_GET(PMCFGR_N, cspmu->pmcfgr) + 1;

	cspmu->cycle_counter_logical_idx = ARM_CSPMU_MAX_HW_CNTRS;

	if (supports_cycle_counter(cspmu)) {
		/*
		 * The last logical counter is mapped to cycle counter if
		 * there is a gap between regular and cycle counter. Otherwise,
		 * logical and physical have 1-to-1 mapping.
		 */
		cspmu->cycle_counter_logical_idx =
			(cspmu->num_logical_ctrs <= ARM_CSPMU_CYCLE_CNTR_IDX) ?
				cspmu->num_logical_ctrs - 1 :
				ARM_CSPMU_CYCLE_CNTR_IDX;
	}

	cspmu->num_set_clr_reg =
		DIV_ROUND_UP(cspmu->num_logical_ctrs,
				ARM_CSPMU_SET_CLR_COUNTER_NUM);

	cspmu->hw_events.events =
		devm_kcalloc(dev, cspmu->num_logical_ctrs,
			     sizeof(*cspmu->hw_events.events), GFP_KERNEL);

	if (!cspmu->hw_events.events)
		return -ENOMEM;

	return 0;
}

static inline int arm_cspmu_get_reset_overflow(struct arm_cspmu *cspmu,
					       u32 *pmovs)
{
	int i;
	u32 pmovclr_offset = PMOVSCLR;
	u32 has_overflowed = 0;

	for (i = 0; i < cspmu->num_set_clr_reg; ++i) {
		pmovs[i] = readl(cspmu->base1 + pmovclr_offset);
		has_overflowed |= pmovs[i];
		writel(pmovs[i], cspmu->base1 + pmovclr_offset);
		pmovclr_offset += sizeof(u32);
	}

	return has_overflowed != 0;
}

static irqreturn_t arm_cspmu_handle_irq(int irq_num, void *dev)
{
	int idx, has_overflowed;
	struct perf_event *event;
	struct arm_cspmu *cspmu = dev;
	DECLARE_BITMAP(pmovs, ARM_CSPMU_MAX_HW_CNTRS);
	bool handled = false;

	arm_cspmu_stop_counters(cspmu);

	has_overflowed = arm_cspmu_get_reset_overflow(cspmu, (u32 *)pmovs);
	if (!has_overflowed)
		goto done;

	for_each_set_bit(idx, cspmu->hw_events.used_ctrs,
			cspmu->num_logical_ctrs) {
		event = cspmu->hw_events.events[idx];

		if (!event)
			continue;

		if (!test_bit(event->hw.idx, pmovs))
			continue;

		arm_cspmu_event_update(event);
		arm_cspmu_set_event_period(event);

		handled = true;
	}

done:
	arm_cspmu_start_counters(cspmu);
	return IRQ_RETVAL(handled);
}

static int arm_cspmu_request_irq(struct arm_cspmu *cspmu)
{
	int irq, ret;
	struct device *dev;
	struct platform_device *pdev;
	struct acpi_apmt_node *apmt_node;

	dev = cspmu->dev;
	pdev = to_platform_device(dev);
	apmt_node = cspmu->apmt_node;

	/* Skip IRQ request if the PMU does not support overflow interrupt. */
	if (apmt_node->ovflw_irq == 0)
		return 0;

	irq = platform_get_irq(pdev, 0);
	if (irq < 0)
		return irq;

	ret = devm_request_irq(dev, irq, arm_cspmu_handle_irq,
			       IRQF_NOBALANCING | IRQF_NO_THREAD, dev_name(dev),
			       cspmu);
	if (ret) {
		dev_err(dev, "Could not request IRQ %d\n", irq);
		return ret;
	}

	cspmu->irq = irq;

	return 0;
}

static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
{
	u32 acpi_uid;
	struct device *cpu_dev = get_cpu_device(cpu);
	struct acpi_device *acpi_dev = ACPI_COMPANION(cpu_dev);

	if (!cpu_dev)
		return -ENODEV;

	while (acpi_dev) {
		if (!strcmp(acpi_device_hid(acpi_dev),
			    ACPI_PROCESSOR_CONTAINER_HID) &&
		    !kstrtouint(acpi_device_uid(acpi_dev), 0, &acpi_uid) &&
		    acpi_uid == container_uid)
			return 0;

		acpi_dev = acpi_dev_parent(acpi_dev);
	}

	return -ENODEV;
}

static int arm_cspmu_get_cpus(struct arm_cspmu *cspmu)
{
	struct device *dev;
	struct acpi_apmt_node *apmt_node;
	int affinity_flag;
	int cpu;

	dev = cspmu->pmu.dev;
	apmt_node = cspmu->apmt_node;
	affinity_flag = apmt_node->flags & ACPI_APMT_FLAGS_AFFINITY;

	if (affinity_flag == ACPI_APMT_FLAGS_AFFINITY_PROC) {
		for_each_possible_cpu(cpu) {
			if (apmt_node->proc_affinity ==
			    get_acpi_id_for_cpu(cpu)) {
				cpumask_set_cpu(cpu, &cspmu->associated_cpus);
				break;
			}
		}
	} else {
		for_each_possible_cpu(cpu) {
			if (arm_cspmu_find_cpu_container(
				    cpu, apmt_node->proc_affinity))
				continue;

			cpumask_set_cpu(cpu, &cspmu->associated_cpus);
		}
	}

	if (cpumask_empty(&cspmu->associated_cpus)) {
		dev_dbg(dev, "No cpu associated with the PMU\n");
		return -ENODEV;
	}

	return 0;
}

static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
{
	int ret, capabilities;
	struct attribute_group **attr_groups;

	attr_groups = arm_cspmu_alloc_attr_group(cspmu);
	if (!attr_groups)
		return -ENOMEM;

	ret = cpuhp_state_add_instance(arm_cspmu_cpuhp_state,
				       &cspmu->cpuhp_node);
	if (ret)
		return ret;

	capabilities = PERF_PMU_CAP_NO_EXCLUDE;
	if (cspmu->irq == 0)
		capabilities |= PERF_PMU_CAP_NO_INTERRUPT;

	cspmu->pmu = (struct pmu){
		.task_ctx_nr	= perf_invalid_context,
		.module		= THIS_MODULE,
		.pmu_enable	= arm_cspmu_enable,
		.pmu_disable	= arm_cspmu_disable,
		.event_init	= arm_cspmu_event_init,
		.add		= arm_cspmu_add,
		.del		= arm_cspmu_del,
		.start		= arm_cspmu_start,
		.stop		= arm_cspmu_stop,
		.read		= arm_cspmu_read,
		.attr_groups	= (const struct attribute_group **)attr_groups,
		.capabilities	= capabilities,
	};

	/* Hardware counter init */
	arm_cspmu_stop_counters(cspmu);
	arm_cspmu_reset_counters(cspmu);

	ret = perf_pmu_register(&cspmu->pmu, cspmu->name, -1);
	if (ret) {
		cpuhp_state_remove_instance(arm_cspmu_cpuhp_state,
					    &cspmu->cpuhp_node);
	}

	return ret;
}

static int arm_cspmu_device_probe(struct platform_device *pdev)
{
	int ret;
	struct arm_cspmu *cspmu;

	cspmu = arm_cspmu_alloc(pdev);
	if (!cspmu)
		return -ENOMEM;

	ret = arm_cspmu_init_mmio(cspmu);
	if (ret)
		return ret;

	ret = arm_cspmu_request_irq(cspmu);
	if (ret)
		return ret;

	ret = arm_cspmu_get_cpus(cspmu);
	if (ret)
		return ret;

	ret = arm_cspmu_register_pmu(cspmu);
	if (ret)
		return ret;

	return 0;
}

static int arm_cspmu_device_remove(struct platform_device *pdev)
{
	struct arm_cspmu *cspmu = platform_get_drvdata(pdev);

	perf_pmu_unregister(&cspmu->pmu);
	cpuhp_state_remove_instance(arm_cspmu_cpuhp_state, &cspmu->cpuhp_node);

	return 0;
}

static struct platform_driver arm_cspmu_driver = {
	.driver = {
			.name = DRVNAME,
			.suppress_bind_attrs = true,
		},
	.probe = arm_cspmu_device_probe,
	.remove = arm_cspmu_device_remove,
};

static void arm_cspmu_set_active_cpu(int cpu, struct arm_cspmu *cspmu)
{
	cpumask_set_cpu(cpu, &cspmu->active_cpu);
	WARN_ON(irq_set_affinity(cspmu->irq, &cspmu->active_cpu));
}

static int arm_cspmu_cpu_online(unsigned int cpu, struct hlist_node *node)
{
	struct arm_cspmu *cspmu =
		hlist_entry_safe(node, struct arm_cspmu, cpuhp_node);

	if (!cpumask_test_cpu(cpu, &cspmu->associated_cpus))
		return 0;

	/* If the PMU is already managed, there is nothing to do */
	if (!cpumask_empty(&cspmu->active_cpu))
		return 0;

	/* Use this CPU for event counting */
	arm_cspmu_set_active_cpu(cpu, cspmu);

	return 0;
}

static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
{
	int dst;
	struct cpumask online_supported;

	struct arm_cspmu *cspmu =
		hlist_entry_safe(node, struct arm_cspmu, cpuhp_node);

	/* Nothing to do if this CPU doesn't own the PMU */
	if (!cpumask_test_and_clear_cpu(cpu, &cspmu->active_cpu))
		return 0;

	/* Choose a new CPU to migrate ownership of the PMU to */
	cpumask_and(&online_supported, &cspmu->associated_cpus,
		    cpu_online_mask);
	dst = cpumask_any_but(&online_supported, cpu);
	if (dst >= nr_cpu_ids)
		return 0;

	/* Use this CPU for event counting */
	perf_pmu_migrate_context(&cspmu->pmu, cpu, dst);
	arm_cspmu_set_active_cpu(dst, cspmu);

	return 0;
}

static int __init arm_cspmu_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
					"perf/arm/cspmu:online",
					arm_cspmu_cpu_online,
					arm_cspmu_cpu_teardown);
	if (ret < 0)
		return ret;
	arm_cspmu_cpuhp_state = ret;
	return platform_driver_register(&arm_cspmu_driver);
}

static void __exit arm_cspmu_exit(void)
{
	platform_driver_unregister(&arm_cspmu_driver);
	cpuhp_remove_multi_state(arm_cspmu_cpuhp_state);
}

module_init(arm_cspmu_init);
module_exit(arm_cspmu_exit);

MODULE_LICENSE("GPL v2");