summaryrefslogtreecommitdiff
path: root/drivers/perf/arm_spe_pmu.c
blob: db670b26589717a4d06c27e7fc604eefd5b7ffe8 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Perf support for the Statistical Profiling Extension, introduced as
 * part of ARMv8.2.
 *
 * Copyright (C) 2016 ARM Limited
 *
 * Author: Will Deacon <will.deacon@arm.com>
 */

#define PMUNAME					"arm_spe"
#define DRVNAME					PMUNAME "_pmu"
#define pr_fmt(fmt)				DRVNAME ": " fmt

#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/capability.h>
#include <linux/cpuhotplug.h>
#include <linux/cpumask.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/perf_event.h>
#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/vmalloc.h>

#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/mmu.h>
#include <asm/sysreg.h>

#define ARM_SPE_BUF_PAD_BYTE			0

struct arm_spe_pmu_buf {
	int					nr_pages;
	bool					snapshot;
	void					*base;
};

struct arm_spe_pmu {
	struct pmu				pmu;
	struct platform_device			*pdev;
	cpumask_t				supported_cpus;
	struct hlist_node			hotplug_node;

	int					irq; /* PPI */
	u16					pmsver;
	u16					min_period;
	u16					counter_sz;

#define SPE_PMU_FEAT_FILT_EVT			(1UL << 0)
#define SPE_PMU_FEAT_FILT_TYP			(1UL << 1)
#define SPE_PMU_FEAT_FILT_LAT			(1UL << 2)
#define SPE_PMU_FEAT_ARCH_INST			(1UL << 3)
#define SPE_PMU_FEAT_LDS			(1UL << 4)
#define SPE_PMU_FEAT_ERND			(1UL << 5)
#define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
	u64					features;

	u16					max_record_sz;
	u16					align;
	struct perf_output_handle __percpu	*handle;
};

#define to_spe_pmu(p) (container_of(p, struct arm_spe_pmu, pmu))

/* Convert a free-running index from perf into an SPE buffer offset */
#define PERF_IDX2OFF(idx, buf)	((idx) % ((buf)->nr_pages << PAGE_SHIFT))

/* Keep track of our dynamic hotplug state */
static enum cpuhp_state arm_spe_pmu_online;

enum arm_spe_pmu_buf_fault_action {
	SPE_PMU_BUF_FAULT_ACT_SPURIOUS,
	SPE_PMU_BUF_FAULT_ACT_FATAL,
	SPE_PMU_BUF_FAULT_ACT_OK,
};

/* This sysfs gunk was really good fun to write. */
enum arm_spe_pmu_capabilities {
	SPE_PMU_CAP_ARCH_INST = 0,
	SPE_PMU_CAP_ERND,
	SPE_PMU_CAP_FEAT_MAX,
	SPE_PMU_CAP_CNT_SZ = SPE_PMU_CAP_FEAT_MAX,
	SPE_PMU_CAP_MIN_IVAL,
};

static int arm_spe_pmu_feat_caps[SPE_PMU_CAP_FEAT_MAX] = {
	[SPE_PMU_CAP_ARCH_INST]	= SPE_PMU_FEAT_ARCH_INST,
	[SPE_PMU_CAP_ERND]	= SPE_PMU_FEAT_ERND,
};

static u32 arm_spe_pmu_cap_get(struct arm_spe_pmu *spe_pmu, int cap)
{
	if (cap < SPE_PMU_CAP_FEAT_MAX)
		return !!(spe_pmu->features & arm_spe_pmu_feat_caps[cap]);

	switch (cap) {
	case SPE_PMU_CAP_CNT_SZ:
		return spe_pmu->counter_sz;
	case SPE_PMU_CAP_MIN_IVAL:
		return spe_pmu->min_period;
	default:
		WARN(1, "unknown cap %d\n", cap);
	}

	return 0;
}

static ssize_t arm_spe_pmu_cap_show(struct device *dev,
				    struct device_attribute *attr,
				    char *buf)
{
	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
	struct dev_ext_attribute *ea =
		container_of(attr, struct dev_ext_attribute, attr);
	int cap = (long)ea->var;

	return sysfs_emit(buf, "%u\n", arm_spe_pmu_cap_get(spe_pmu, cap));
}

#define SPE_EXT_ATTR_ENTRY(_name, _func, _var)				\
	&((struct dev_ext_attribute[]) {				\
		{ __ATTR(_name, S_IRUGO, _func, NULL), (void *)_var }	\
	})[0].attr.attr

#define SPE_CAP_EXT_ATTR_ENTRY(_name, _var)				\
	SPE_EXT_ATTR_ENTRY(_name, arm_spe_pmu_cap_show, _var)

static struct attribute *arm_spe_pmu_cap_attr[] = {
	SPE_CAP_EXT_ATTR_ENTRY(arch_inst, SPE_PMU_CAP_ARCH_INST),
	SPE_CAP_EXT_ATTR_ENTRY(ernd, SPE_PMU_CAP_ERND),
	SPE_CAP_EXT_ATTR_ENTRY(count_size, SPE_PMU_CAP_CNT_SZ),
	SPE_CAP_EXT_ATTR_ENTRY(min_interval, SPE_PMU_CAP_MIN_IVAL),
	NULL,
};

static const struct attribute_group arm_spe_pmu_cap_group = {
	.name	= "caps",
	.attrs	= arm_spe_pmu_cap_attr,
};

/* User ABI */
#define ATTR_CFG_FLD_ts_enable_CFG		config	/* PMSCR_EL1.TS */
#define ATTR_CFG_FLD_ts_enable_LO		0
#define ATTR_CFG_FLD_ts_enable_HI		0
#define ATTR_CFG_FLD_pa_enable_CFG		config	/* PMSCR_EL1.PA */
#define ATTR_CFG_FLD_pa_enable_LO		1
#define ATTR_CFG_FLD_pa_enable_HI		1
#define ATTR_CFG_FLD_pct_enable_CFG		config	/* PMSCR_EL1.PCT */
#define ATTR_CFG_FLD_pct_enable_LO		2
#define ATTR_CFG_FLD_pct_enable_HI		2
#define ATTR_CFG_FLD_jitter_CFG			config	/* PMSIRR_EL1.RND */
#define ATTR_CFG_FLD_jitter_LO			16
#define ATTR_CFG_FLD_jitter_HI			16
#define ATTR_CFG_FLD_branch_filter_CFG		config	/* PMSFCR_EL1.B */
#define ATTR_CFG_FLD_branch_filter_LO		32
#define ATTR_CFG_FLD_branch_filter_HI		32
#define ATTR_CFG_FLD_load_filter_CFG		config	/* PMSFCR_EL1.LD */
#define ATTR_CFG_FLD_load_filter_LO		33
#define ATTR_CFG_FLD_load_filter_HI		33
#define ATTR_CFG_FLD_store_filter_CFG		config	/* PMSFCR_EL1.ST */
#define ATTR_CFG_FLD_store_filter_LO		34
#define ATTR_CFG_FLD_store_filter_HI		34

#define ATTR_CFG_FLD_event_filter_CFG		config1	/* PMSEVFR_EL1 */
#define ATTR_CFG_FLD_event_filter_LO		0
#define ATTR_CFG_FLD_event_filter_HI		63

#define ATTR_CFG_FLD_min_latency_CFG		config2	/* PMSLATFR_EL1.MINLAT */
#define ATTR_CFG_FLD_min_latency_LO		0
#define ATTR_CFG_FLD_min_latency_HI		11

/* Why does everything I do descend into this? */
#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi

#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)

#define GEN_PMU_FORMAT_ATTR(name)					\
	PMU_FORMAT_ATTR(name,						\
	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
			     ATTR_CFG_FLD_##name##_LO,			\
			     ATTR_CFG_FLD_##name##_HI))

#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
	((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0))

#define ATTR_CFG_GET_FLD(attr, name)					\
	_ATTR_CFG_GET_FLD(attr,						\
			  ATTR_CFG_FLD_##name##_CFG,			\
			  ATTR_CFG_FLD_##name##_LO,			\
			  ATTR_CFG_FLD_##name##_HI)

GEN_PMU_FORMAT_ATTR(ts_enable);
GEN_PMU_FORMAT_ATTR(pa_enable);
GEN_PMU_FORMAT_ATTR(pct_enable);
GEN_PMU_FORMAT_ATTR(jitter);
GEN_PMU_FORMAT_ATTR(branch_filter);
GEN_PMU_FORMAT_ATTR(load_filter);
GEN_PMU_FORMAT_ATTR(store_filter);
GEN_PMU_FORMAT_ATTR(event_filter);
GEN_PMU_FORMAT_ATTR(min_latency);

static struct attribute *arm_spe_pmu_formats_attr[] = {
	&format_attr_ts_enable.attr,
	&format_attr_pa_enable.attr,
	&format_attr_pct_enable.attr,
	&format_attr_jitter.attr,
	&format_attr_branch_filter.attr,
	&format_attr_load_filter.attr,
	&format_attr_store_filter.attr,
	&format_attr_event_filter.attr,
	&format_attr_min_latency.attr,
	NULL,
};

static const struct attribute_group arm_spe_pmu_format_group = {
	.name	= "format",
	.attrs	= arm_spe_pmu_formats_attr,
};

static ssize_t cpumask_show(struct device *dev,
			    struct device_attribute *attr, char *buf)
{
	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);

	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
}
static DEVICE_ATTR_RO(cpumask);

static struct attribute *arm_spe_pmu_attrs[] = {
	&dev_attr_cpumask.attr,
	NULL,
};

static const struct attribute_group arm_spe_pmu_group = {
	.attrs	= arm_spe_pmu_attrs,
};

static const struct attribute_group *arm_spe_pmu_attr_groups[] = {
	&arm_spe_pmu_group,
	&arm_spe_pmu_cap_group,
	&arm_spe_pmu_format_group,
	NULL,
};

/* Convert between user ABI and register values */
static u64 arm_spe_event_to_pmscr(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	u64 reg = 0;

	reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT;
	reg |= ATTR_CFG_GET_FLD(attr, pa_enable) << SYS_PMSCR_EL1_PA_SHIFT;
	reg |= ATTR_CFG_GET_FLD(attr, pct_enable) << SYS_PMSCR_EL1_PCT_SHIFT;

	if (!attr->exclude_user)
		reg |= BIT(SYS_PMSCR_EL1_E0SPE_SHIFT);

	if (!attr->exclude_kernel)
		reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);

	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
		reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);

	return reg;
}

static void arm_spe_event_sanitise_period(struct perf_event *event)
{
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
	u64 period = event->hw.sample_period;
	u64 max_period = SYS_PMSIRR_EL1_INTERVAL_MASK
			 << SYS_PMSIRR_EL1_INTERVAL_SHIFT;

	if (period < spe_pmu->min_period)
		period = spe_pmu->min_period;
	else if (period > max_period)
		period = max_period;
	else
		period &= max_period;

	event->hw.sample_period = period;
}

static u64 arm_spe_event_to_pmsirr(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	u64 reg = 0;

	arm_spe_event_sanitise_period(event);

	reg |= ATTR_CFG_GET_FLD(attr, jitter) << SYS_PMSIRR_EL1_RND_SHIFT;
	reg |= event->hw.sample_period;

	return reg;
}

static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	u64 reg = 0;

	reg |= ATTR_CFG_GET_FLD(attr, load_filter) << SYS_PMSFCR_EL1_LD_SHIFT;
	reg |= ATTR_CFG_GET_FLD(attr, store_filter) << SYS_PMSFCR_EL1_ST_SHIFT;
	reg |= ATTR_CFG_GET_FLD(attr, branch_filter) << SYS_PMSFCR_EL1_B_SHIFT;

	if (reg)
		reg |= BIT(SYS_PMSFCR_EL1_FT_SHIFT);

	if (ATTR_CFG_GET_FLD(attr, event_filter))
		reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT);

	if (ATTR_CFG_GET_FLD(attr, min_latency))
		reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT);

	return reg;
}

static u64 arm_spe_event_to_pmsevfr(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	return ATTR_CFG_GET_FLD(attr, event_filter);
}

static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	return ATTR_CFG_GET_FLD(attr, min_latency)
	       << SYS_PMSLATFR_EL1_MINLAT_SHIFT;
}

static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len)
{
	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
	u64 head = PERF_IDX2OFF(handle->head, buf);

	memset(buf->base + head, ARM_SPE_BUF_PAD_BYTE, len);
	if (!buf->snapshot)
		perf_aux_output_skip(handle, len);
}

static u64 arm_spe_pmu_next_snapshot_off(struct perf_output_handle *handle)
{
	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
	u64 head = PERF_IDX2OFF(handle->head, buf);
	u64 limit = buf->nr_pages * PAGE_SIZE;

	/*
	 * The trace format isn't parseable in reverse, so clamp
	 * the limit to half of the buffer size in snapshot mode
	 * so that the worst case is half a buffer of records, as
	 * opposed to a single record.
	 */
	if (head < limit >> 1)
		limit >>= 1;

	/*
	 * If we're within max_record_sz of the limit, we must
	 * pad, move the head index and recompute the limit.
	 */
	if (limit - head < spe_pmu->max_record_sz) {
		arm_spe_pmu_pad_buf(handle, limit - head);
		handle->head = PERF_IDX2OFF(limit, buf);
		limit = ((buf->nr_pages * PAGE_SIZE) >> 1) + handle->head;
	}

	return limit;
}

static u64 __arm_spe_pmu_next_off(struct perf_output_handle *handle)
{
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
	const u64 bufsize = buf->nr_pages * PAGE_SIZE;
	u64 limit = bufsize;
	u64 head, tail, wakeup;

	/*
	 * The head can be misaligned for two reasons:
	 *
	 * 1. The hardware left PMBPTR pointing to the first byte after
	 *    a record when generating a buffer management event.
	 *
	 * 2. We used perf_aux_output_skip to consume handle->size bytes
	 *    and CIRC_SPACE was used to compute the size, which always
	 *    leaves one entry free.
	 *
	 * Deal with this by padding to the next alignment boundary and
	 * moving the head index. If we run out of buffer space, we'll
	 * reduce handle->size to zero and end up reporting truncation.
	 */
	head = PERF_IDX2OFF(handle->head, buf);
	if (!IS_ALIGNED(head, spe_pmu->align)) {
		unsigned long delta = roundup(head, spe_pmu->align) - head;

		delta = min(delta, handle->size);
		arm_spe_pmu_pad_buf(handle, delta);
		head = PERF_IDX2OFF(handle->head, buf);
	}

	/* If we've run out of free space, then nothing more to do */
	if (!handle->size)
		goto no_space;

	/* Compute the tail and wakeup indices now that we've aligned head */
	tail = PERF_IDX2OFF(handle->head + handle->size, buf);
	wakeup = PERF_IDX2OFF(handle->wakeup, buf);

	/*
	 * Avoid clobbering unconsumed data. We know we have space, so
	 * if we see head == tail we know that the buffer is empty. If
	 * head > tail, then there's nothing to clobber prior to
	 * wrapping.
	 */
	if (head < tail)
		limit = round_down(tail, PAGE_SIZE);

	/*
	 * Wakeup may be arbitrarily far into the future. If it's not in
	 * the current generation, either we'll wrap before hitting it,
	 * or it's in the past and has been handled already.
	 *
	 * If there's a wakeup before we wrap, arrange to be woken up by
	 * the page boundary following it. Keep the tail boundary if
	 * that's lower.
	 */
	if (handle->wakeup < (handle->head + handle->size) && head <= wakeup)
		limit = min(limit, round_up(wakeup, PAGE_SIZE));

	if (limit > head)
		return limit;

	arm_spe_pmu_pad_buf(handle, handle->size);
no_space:
	perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
	perf_aux_output_end(handle, 0);
	return 0;
}

static u64 arm_spe_pmu_next_off(struct perf_output_handle *handle)
{
	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(handle->event->pmu);
	u64 limit = __arm_spe_pmu_next_off(handle);
	u64 head = PERF_IDX2OFF(handle->head, buf);

	/*
	 * If the head has come too close to the end of the buffer,
	 * then pad to the end and recompute the limit.
	 */
	if (limit && (limit - head < spe_pmu->max_record_sz)) {
		arm_spe_pmu_pad_buf(handle, limit - head);
		limit = __arm_spe_pmu_next_off(handle);
	}

	return limit;
}

static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle,
					  struct perf_event *event)
{
	u64 base, limit;
	struct arm_spe_pmu_buf *buf;

	/* Start a new aux session */
	buf = perf_aux_output_begin(handle, event);
	if (!buf) {
		event->hw.state |= PERF_HES_STOPPED;
		/*
		 * We still need to clear the limit pointer, since the
		 * profiler might only be disabled by virtue of a fault.
		 */
		limit = 0;
		goto out_write_limit;
	}

	limit = buf->snapshot ? arm_spe_pmu_next_snapshot_off(handle)
			      : arm_spe_pmu_next_off(handle);
	if (limit)
		limit |= BIT(SYS_PMBLIMITR_EL1_E_SHIFT);

	limit += (u64)buf->base;
	base = (u64)buf->base + PERF_IDX2OFF(handle->head, buf);
	write_sysreg_s(base, SYS_PMBPTR_EL1);

out_write_limit:
	write_sysreg_s(limit, SYS_PMBLIMITR_EL1);
}

static void arm_spe_perf_aux_output_end(struct perf_output_handle *handle)
{
	struct arm_spe_pmu_buf *buf = perf_get_aux(handle);
	u64 offset, size;

	offset = read_sysreg_s(SYS_PMBPTR_EL1) - (u64)buf->base;
	size = offset - PERF_IDX2OFF(handle->head, buf);

	if (buf->snapshot)
		handle->head = offset;

	perf_aux_output_end(handle, size);
}

static void arm_spe_pmu_disable_and_drain_local(void)
{
	/* Disable profiling at EL0 and EL1 */
	write_sysreg_s(0, SYS_PMSCR_EL1);
	isb();

	/* Drain any buffered data */
	psb_csync();
	dsb(nsh);

	/* Disable the profiling buffer */
	write_sysreg_s(0, SYS_PMBLIMITR_EL1);
	isb();
}

/* IRQ handling */
static enum arm_spe_pmu_buf_fault_action
arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle)
{
	const char *err_str;
	u64 pmbsr;
	enum arm_spe_pmu_buf_fault_action ret;

	/*
	 * Ensure new profiling data is visible to the CPU and any external
	 * aborts have been resolved.
	 */
	psb_csync();
	dsb(nsh);

	/* Ensure hardware updates to PMBPTR_EL1 are visible */
	isb();

	/* Service required? */
	pmbsr = read_sysreg_s(SYS_PMBSR_EL1);
	if (!(pmbsr & BIT(SYS_PMBSR_EL1_S_SHIFT)))
		return SPE_PMU_BUF_FAULT_ACT_SPURIOUS;

	/*
	 * If we've lost data, disable profiling and also set the PARTIAL
	 * flag to indicate that the last record is corrupted.
	 */
	if (pmbsr & BIT(SYS_PMBSR_EL1_DL_SHIFT))
		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED |
					     PERF_AUX_FLAG_PARTIAL);

	/* Report collisions to userspace so that it can up the period */
	if (pmbsr & BIT(SYS_PMBSR_EL1_COLL_SHIFT))
		perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION);

	/* We only expect buffer management events */
	switch (pmbsr & (SYS_PMBSR_EL1_EC_MASK << SYS_PMBSR_EL1_EC_SHIFT)) {
	case SYS_PMBSR_EL1_EC_BUF:
		/* Handled below */
		break;
	case SYS_PMBSR_EL1_EC_FAULT_S1:
	case SYS_PMBSR_EL1_EC_FAULT_S2:
		err_str = "Unexpected buffer fault";
		goto out_err;
	default:
		err_str = "Unknown error code";
		goto out_err;
	}

	/* Buffer management event */
	switch (pmbsr &
		(SYS_PMBSR_EL1_BUF_BSC_MASK << SYS_PMBSR_EL1_BUF_BSC_SHIFT)) {
	case SYS_PMBSR_EL1_BUF_BSC_FULL:
		ret = SPE_PMU_BUF_FAULT_ACT_OK;
		goto out_stop;
	default:
		err_str = "Unknown buffer status code";
	}

out_err:
	pr_err_ratelimited("%s on CPU %d [PMBSR=0x%016llx, PMBPTR=0x%016llx, PMBLIMITR=0x%016llx]\n",
			   err_str, smp_processor_id(), pmbsr,
			   read_sysreg_s(SYS_PMBPTR_EL1),
			   read_sysreg_s(SYS_PMBLIMITR_EL1));
	ret = SPE_PMU_BUF_FAULT_ACT_FATAL;

out_stop:
	arm_spe_perf_aux_output_end(handle);
	return ret;
}

static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev)
{
	struct perf_output_handle *handle = dev;
	struct perf_event *event = handle->event;
	enum arm_spe_pmu_buf_fault_action act;

	if (!perf_get_aux(handle))
		return IRQ_NONE;

	act = arm_spe_pmu_buf_get_fault_act(handle);
	if (act == SPE_PMU_BUF_FAULT_ACT_SPURIOUS)
		return IRQ_NONE;

	/*
	 * Ensure perf callbacks have completed, which may disable the
	 * profiling buffer in response to a TRUNCATION flag.
	 */
	irq_work_run();

	switch (act) {
	case SPE_PMU_BUF_FAULT_ACT_FATAL:
		/*
		 * If a fatal exception occurred then leaving the profiling
		 * buffer enabled is a recipe waiting to happen. Since
		 * fatal faults don't always imply truncation, make sure
		 * that the profiling buffer is disabled explicitly before
		 * clearing the syndrome register.
		 */
		arm_spe_pmu_disable_and_drain_local();
		break;
	case SPE_PMU_BUF_FAULT_ACT_OK:
		/*
		 * We handled the fault (the buffer was full), so resume
		 * profiling as long as we didn't detect truncation.
		 * PMBPTR might be misaligned, but we'll burn that bridge
		 * when we get to it.
		 */
		if (!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)) {
			arm_spe_perf_aux_output_begin(handle, event);
			isb();
		}
		break;
	case SPE_PMU_BUF_FAULT_ACT_SPURIOUS:
		/* We've seen you before, but GCC has the memory of a sieve. */
		break;
	}

	/* The buffer pointers are now sane, so resume profiling. */
	write_sysreg_s(0, SYS_PMBSR_EL1);
	return IRQ_HANDLED;
}

static u64 arm_spe_pmsevfr_res0(u16 pmsver)
{
	switch (pmsver) {
	case ID_AA64DFR0_PMSVER_8_2:
		return SYS_PMSEVFR_EL1_RES0_8_2;
	case ID_AA64DFR0_PMSVER_8_3:
	/* Return the highest version we support in default */
	default:
		return SYS_PMSEVFR_EL1_RES0_8_3;
	}
}

/* Perf callbacks */
static int arm_spe_pmu_event_init(struct perf_event *event)
{
	u64 reg;
	struct perf_event_attr *attr = &event->attr;
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);

	/* This is, of course, deeply driver-specific */
	if (attr->type != event->pmu->type)
		return -ENOENT;

	if (event->cpu >= 0 &&
	    !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus))
		return -ENOENT;

	if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
		return -EOPNOTSUPP;

	if (attr->exclude_idle)
		return -EOPNOTSUPP;

	/*
	 * Feedback-directed frequency throttling doesn't work when we
	 * have a buffer of samples. We'd need to manually count the
	 * samples in the buffer when it fills up and adjust the event
	 * count to reflect that. Instead, just force the user to specify
	 * a sample period.
	 */
	if (attr->freq)
		return -EINVAL;

	reg = arm_spe_event_to_pmsfcr(event);
	if ((reg & BIT(SYS_PMSFCR_EL1_FE_SHIFT)) &&
	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT))
		return -EOPNOTSUPP;

	if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) &&
	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP))
		return -EOPNOTSUPP;

	if ((reg & BIT(SYS_PMSFCR_EL1_FL_SHIFT)) &&
	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
		return -EOPNOTSUPP;

	reg = arm_spe_event_to_pmscr(event);
	if (!perfmon_capable() &&
	    (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
		    BIT(SYS_PMSCR_EL1_CX_SHIFT) |
		    BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
		return -EACCES;

	return 0;
}

static void arm_spe_pmu_start(struct perf_event *event, int flags)
{
	u64 reg;
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	struct perf_output_handle *handle = this_cpu_ptr(spe_pmu->handle);

	hwc->state = 0;
	arm_spe_perf_aux_output_begin(handle, event);
	if (hwc->state)
		return;

	reg = arm_spe_event_to_pmsfcr(event);
	write_sysreg_s(reg, SYS_PMSFCR_EL1);

	reg = arm_spe_event_to_pmsevfr(event);
	write_sysreg_s(reg, SYS_PMSEVFR_EL1);

	reg = arm_spe_event_to_pmslatfr(event);
	write_sysreg_s(reg, SYS_PMSLATFR_EL1);

	if (flags & PERF_EF_RELOAD) {
		reg = arm_spe_event_to_pmsirr(event);
		write_sysreg_s(reg, SYS_PMSIRR_EL1);
		isb();
		reg = local64_read(&hwc->period_left);
		write_sysreg_s(reg, SYS_PMSICR_EL1);
	}

	reg = arm_spe_event_to_pmscr(event);
	isb();
	write_sysreg_s(reg, SYS_PMSCR_EL1);
}

static void arm_spe_pmu_stop(struct perf_event *event, int flags)
{
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	struct perf_output_handle *handle = this_cpu_ptr(spe_pmu->handle);

	/* If we're already stopped, then nothing to do */
	if (hwc->state & PERF_HES_STOPPED)
		return;

	/* Stop all trace generation */
	arm_spe_pmu_disable_and_drain_local();

	if (flags & PERF_EF_UPDATE) {
		/*
		 * If there's a fault pending then ensure we contain it
		 * to this buffer, since we might be on the context-switch
		 * path.
		 */
		if (perf_get_aux(handle)) {
			enum arm_spe_pmu_buf_fault_action act;

			act = arm_spe_pmu_buf_get_fault_act(handle);
			if (act == SPE_PMU_BUF_FAULT_ACT_SPURIOUS)
				arm_spe_perf_aux_output_end(handle);
			else
				write_sysreg_s(0, SYS_PMBSR_EL1);
		}

		/*
		 * This may also contain ECOUNT, but nobody else should
		 * be looking at period_left, since we forbid frequency
		 * based sampling.
		 */
		local64_set(&hwc->period_left, read_sysreg_s(SYS_PMSICR_EL1));
		hwc->state |= PERF_HES_UPTODATE;
	}

	hwc->state |= PERF_HES_STOPPED;
}

static int arm_spe_pmu_add(struct perf_event *event, int flags)
{
	int ret = 0;
	struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	int cpu = event->cpu == -1 ? smp_processor_id() : event->cpu;

	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
		return -ENOENT;

	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;

	if (flags & PERF_EF_START) {
		arm_spe_pmu_start(event, PERF_EF_RELOAD);
		if (hwc->state & PERF_HES_STOPPED)
			ret = -EINVAL;
	}

	return ret;
}

static void arm_spe_pmu_del(struct perf_event *event, int flags)
{
	arm_spe_pmu_stop(event, PERF_EF_UPDATE);
}

static void arm_spe_pmu_read(struct perf_event *event)
{
}

static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages,
				   int nr_pages, bool snapshot)
{
	int i, cpu = event->cpu;
	struct page **pglist;
	struct arm_spe_pmu_buf *buf;

	/* We need at least two pages for this to work. */
	if (nr_pages < 2)
		return NULL;

	/*
	 * We require an even number of pages for snapshot mode, so that
	 * we can effectively treat the buffer as consisting of two equal
	 * parts and give userspace a fighting chance of getting some
	 * useful data out of it.
	 */
	if (snapshot && (nr_pages & 1))
		return NULL;

	if (cpu == -1)
		cpu = raw_smp_processor_id();

	buf = kzalloc_node(sizeof(*buf), GFP_KERNEL, cpu_to_node(cpu));
	if (!buf)
		return NULL;

	pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL);
	if (!pglist)
		goto out_free_buf;

	for (i = 0; i < nr_pages; ++i)
		pglist[i] = virt_to_page(pages[i]);

	buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL);
	if (!buf->base)
		goto out_free_pglist;

	buf->nr_pages	= nr_pages;
	buf->snapshot	= snapshot;

	kfree(pglist);
	return buf;

out_free_pglist:
	kfree(pglist);
out_free_buf:
	kfree(buf);
	return NULL;
}

static void arm_spe_pmu_free_aux(void *aux)
{
	struct arm_spe_pmu_buf *buf = aux;

	vunmap(buf->base);
	kfree(buf);
}

/* Initialisation and teardown functions */
static int arm_spe_pmu_perf_init(struct arm_spe_pmu *spe_pmu)
{
	static atomic_t pmu_idx = ATOMIC_INIT(-1);

	int idx;
	char *name;
	struct device *dev = &spe_pmu->pdev->dev;

	spe_pmu->pmu = (struct pmu) {
		.module = THIS_MODULE,
		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
		.attr_groups	= arm_spe_pmu_attr_groups,
		/*
		 * We hitch a ride on the software context here, so that
		 * we can support per-task profiling (which is not possible
		 * with the invalid context as it doesn't get sched callbacks).
		 * This requires that userspace either uses a dummy event for
		 * perf_event_open, since the aux buffer is not setup until
		 * a subsequent mmap, or creates the profiling event in a
		 * disabled state and explicitly PERF_EVENT_IOC_ENABLEs it
		 * once the buffer has been created.
		 */
		.task_ctx_nr	= perf_sw_context,
		.event_init	= arm_spe_pmu_event_init,
		.add		= arm_spe_pmu_add,
		.del		= arm_spe_pmu_del,
		.start		= arm_spe_pmu_start,
		.stop		= arm_spe_pmu_stop,
		.read		= arm_spe_pmu_read,
		.setup_aux	= arm_spe_pmu_setup_aux,
		.free_aux	= arm_spe_pmu_free_aux,
	};

	idx = atomic_inc_return(&pmu_idx);
	name = devm_kasprintf(dev, GFP_KERNEL, "%s_%d", PMUNAME, idx);
	if (!name) {
		dev_err(dev, "failed to allocate name for pmu %d\n", idx);
		return -ENOMEM;
	}

	return perf_pmu_register(&spe_pmu->pmu, name, -1);
}

static void arm_spe_pmu_perf_destroy(struct arm_spe_pmu *spe_pmu)
{
	perf_pmu_unregister(&spe_pmu->pmu);
}

static void __arm_spe_pmu_dev_probe(void *info)
{
	int fld;
	u64 reg;
	struct arm_spe_pmu *spe_pmu = info;
	struct device *dev = &spe_pmu->pdev->dev;

	fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64DFR0_EL1),
						   ID_AA64DFR0_PMSVER_SHIFT);
	if (!fld) {
		dev_err(dev,
			"unsupported ID_AA64DFR0_EL1.PMSVer [%d] on CPU %d\n",
			fld, smp_processor_id());
		return;
	}
	spe_pmu->pmsver = (u16)fld;

	/* Read PMBIDR first to determine whether or not we have access */
	reg = read_sysreg_s(SYS_PMBIDR_EL1);
	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) {
		dev_err(dev,
			"profiling buffer owned by higher exception level\n");
		return;
	}

	/* Minimum alignment. If it's out-of-range, then fail the probe */
	fld = reg >> SYS_PMBIDR_EL1_ALIGN_SHIFT & SYS_PMBIDR_EL1_ALIGN_MASK;
	spe_pmu->align = 1 << fld;
	if (spe_pmu->align > SZ_2K) {
		dev_err(dev, "unsupported PMBIDR.Align [%d] on CPU %d\n",
			fld, smp_processor_id());
		return;
	}

	/* It's now safe to read PMSIDR and figure out what we've got */
	reg = read_sysreg_s(SYS_PMSIDR_EL1);
	if (reg & BIT(SYS_PMSIDR_EL1_FE_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_FILT_EVT;

	if (reg & BIT(SYS_PMSIDR_EL1_FT_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_FILT_TYP;

	if (reg & BIT(SYS_PMSIDR_EL1_FL_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_FILT_LAT;

	if (reg & BIT(SYS_PMSIDR_EL1_ARCHINST_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_ARCH_INST;

	if (reg & BIT(SYS_PMSIDR_EL1_LDS_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_LDS;

	if (reg & BIT(SYS_PMSIDR_EL1_ERND_SHIFT))
		spe_pmu->features |= SPE_PMU_FEAT_ERND;

	/* This field has a spaced out encoding, so just use a look-up */
	fld = reg >> SYS_PMSIDR_EL1_INTERVAL_SHIFT & SYS_PMSIDR_EL1_INTERVAL_MASK;
	switch (fld) {
	case 0:
		spe_pmu->min_period = 256;
		break;
	case 2:
		spe_pmu->min_period = 512;
		break;
	case 3:
		spe_pmu->min_period = 768;
		break;
	case 4:
		spe_pmu->min_period = 1024;
		break;
	case 5:
		spe_pmu->min_period = 1536;
		break;
	case 6:
		spe_pmu->min_period = 2048;
		break;
	case 7:
		spe_pmu->min_period = 3072;
		break;
	default:
		dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n",
			 fld);
		fallthrough;
	case 8:
		spe_pmu->min_period = 4096;
	}

	/* Maximum record size. If it's out-of-range, then fail the probe */
	fld = reg >> SYS_PMSIDR_EL1_MAXSIZE_SHIFT & SYS_PMSIDR_EL1_MAXSIZE_MASK;
	spe_pmu->max_record_sz = 1 << fld;
	if (spe_pmu->max_record_sz > SZ_2K || spe_pmu->max_record_sz < 16) {
		dev_err(dev, "unsupported PMSIDR_EL1.MaxSize [%d] on CPU %d\n",
			fld, smp_processor_id());
		return;
	}

	fld = reg >> SYS_PMSIDR_EL1_COUNTSIZE_SHIFT & SYS_PMSIDR_EL1_COUNTSIZE_MASK;
	switch (fld) {
	default:
		dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n",
			 fld);
		fallthrough;
	case 2:
		spe_pmu->counter_sz = 12;
		break;
	case 3:
		spe_pmu->counter_sz = 16;
	}

	dev_info(dev,
		 "probed for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n",
		 cpumask_pr_args(&spe_pmu->supported_cpus),
		 spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features);

	spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED;
}

static void __arm_spe_pmu_reset_local(void)
{
	/*
	 * This is probably overkill, as we have no idea where we're
	 * draining any buffered data to...
	 */
	arm_spe_pmu_disable_and_drain_local();

	/* Reset the buffer base pointer */
	write_sysreg_s(0, SYS_PMBPTR_EL1);
	isb();

	/* Clear any pending management interrupts */
	write_sysreg_s(0, SYS_PMBSR_EL1);
	isb();
}

static void __arm_spe_pmu_setup_one(void *info)
{
	struct arm_spe_pmu *spe_pmu = info;

	__arm_spe_pmu_reset_local();
	enable_percpu_irq(spe_pmu->irq, IRQ_TYPE_NONE);
}

static void __arm_spe_pmu_stop_one(void *info)
{
	struct arm_spe_pmu *spe_pmu = info;

	disable_percpu_irq(spe_pmu->irq);
	__arm_spe_pmu_reset_local();
}

static int arm_spe_pmu_cpu_startup(unsigned int cpu, struct hlist_node *node)
{
	struct arm_spe_pmu *spe_pmu;

	spe_pmu = hlist_entry_safe(node, struct arm_spe_pmu, hotplug_node);
	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
		return 0;

	__arm_spe_pmu_setup_one(spe_pmu);
	return 0;
}

static int arm_spe_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
{
	struct arm_spe_pmu *spe_pmu;

	spe_pmu = hlist_entry_safe(node, struct arm_spe_pmu, hotplug_node);
	if (!cpumask_test_cpu(cpu, &spe_pmu->supported_cpus))
		return 0;

	__arm_spe_pmu_stop_one(spe_pmu);
	return 0;
}

static int arm_spe_pmu_dev_init(struct arm_spe_pmu *spe_pmu)
{
	int ret;
	cpumask_t *mask = &spe_pmu->supported_cpus;

	/* Make sure we probe the hardware on a relevant CPU */
	ret = smp_call_function_any(mask,  __arm_spe_pmu_dev_probe, spe_pmu, 1);
	if (ret || !(spe_pmu->features & SPE_PMU_FEAT_DEV_PROBED))
		return -ENXIO;

	/* Request our PPIs (note that the IRQ is still disabled) */
	ret = request_percpu_irq(spe_pmu->irq, arm_spe_pmu_irq_handler, DRVNAME,
				 spe_pmu->handle);
	if (ret)
		return ret;

	/*
	 * Register our hotplug notifier now so we don't miss any events.
	 * This will enable the IRQ for any supported CPUs that are already
	 * up.
	 */
	ret = cpuhp_state_add_instance(arm_spe_pmu_online,
				       &spe_pmu->hotplug_node);
	if (ret)
		free_percpu_irq(spe_pmu->irq, spe_pmu->handle);

	return ret;
}

static void arm_spe_pmu_dev_teardown(struct arm_spe_pmu *spe_pmu)
{
	cpuhp_state_remove_instance(arm_spe_pmu_online, &spe_pmu->hotplug_node);
	free_percpu_irq(spe_pmu->irq, spe_pmu->handle);
}

/* Driver and device probing */
static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
{
	struct platform_device *pdev = spe_pmu->pdev;
	int irq = platform_get_irq(pdev, 0);

	if (irq < 0)
		return -ENXIO;

	if (!irq_is_percpu(irq)) {
		dev_err(&pdev->dev, "expected PPI but got SPI (%d)\n", irq);
		return -EINVAL;
	}

	if (irq_get_percpu_devid_partition(irq, &spe_pmu->supported_cpus)) {
		dev_err(&pdev->dev, "failed to get PPI partition (%d)\n", irq);
		return -EINVAL;
	}

	spe_pmu->irq = irq;
	return 0;
}

static const struct of_device_id arm_spe_pmu_of_match[] = {
	{ .compatible = "arm,statistical-profiling-extension-v1", .data = (void *)1 },
	{ /* Sentinel */ },
};
MODULE_DEVICE_TABLE(of, arm_spe_pmu_of_match);

static const struct platform_device_id arm_spe_match[] = {
	{ ARMV8_SPE_PDEV_NAME, 0},
	{ }
};
MODULE_DEVICE_TABLE(platform, arm_spe_match);

static int arm_spe_pmu_device_probe(struct platform_device *pdev)
{
	int ret;
	struct arm_spe_pmu *spe_pmu;
	struct device *dev = &pdev->dev;

	/*
	 * If kernelspace is unmapped when running at EL0, then the SPE
	 * buffer will fault and prematurely terminate the AUX session.
	 */
	if (arm64_kernel_unmapped_at_el0()) {
		dev_warn_once(dev, "profiling buffer inaccessible. Try passing \"kpti=off\" on the kernel command line\n");
		return -EPERM;
	}

	spe_pmu = devm_kzalloc(dev, sizeof(*spe_pmu), GFP_KERNEL);
	if (!spe_pmu)
		return -ENOMEM;

	spe_pmu->handle = alloc_percpu(typeof(*spe_pmu->handle));
	if (!spe_pmu->handle)
		return -ENOMEM;

	spe_pmu->pdev = pdev;
	platform_set_drvdata(pdev, spe_pmu);

	ret = arm_spe_pmu_irq_probe(spe_pmu);
	if (ret)
		goto out_free_handle;

	ret = arm_spe_pmu_dev_init(spe_pmu);
	if (ret)
		goto out_free_handle;

	ret = arm_spe_pmu_perf_init(spe_pmu);
	if (ret)
		goto out_teardown_dev;

	return 0;

out_teardown_dev:
	arm_spe_pmu_dev_teardown(spe_pmu);
out_free_handle:
	free_percpu(spe_pmu->handle);
	return ret;
}

static int arm_spe_pmu_device_remove(struct platform_device *pdev)
{
	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);

	arm_spe_pmu_perf_destroy(spe_pmu);
	arm_spe_pmu_dev_teardown(spe_pmu);
	free_percpu(spe_pmu->handle);
	return 0;
}

static struct platform_driver arm_spe_pmu_driver = {
	.id_table = arm_spe_match,
	.driver	= {
		.name		= DRVNAME,
		.of_match_table	= of_match_ptr(arm_spe_pmu_of_match),
		.suppress_bind_attrs = true,
	},
	.probe	= arm_spe_pmu_device_probe,
	.remove	= arm_spe_pmu_device_remove,
};

static int __init arm_spe_pmu_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DRVNAME,
				      arm_spe_pmu_cpu_startup,
				      arm_spe_pmu_cpu_teardown);
	if (ret < 0)
		return ret;
	arm_spe_pmu_online = ret;

	ret = platform_driver_register(&arm_spe_pmu_driver);
	if (ret)
		cpuhp_remove_multi_state(arm_spe_pmu_online);

	return ret;
}

static void __exit arm_spe_pmu_exit(void)
{
	platform_driver_unregister(&arm_spe_pmu_driver);
	cpuhp_remove_multi_state(arm_spe_pmu_online);
}

module_init(arm_spe_pmu_init);
module_exit(arm_spe_pmu_exit);

MODULE_DESCRIPTION("Perf driver for the ARMv8.2 Statistical Profiling Extension");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
MODULE_LICENSE("GPL v2");