summaryrefslogtreecommitdiff
path: root/arch/x86/events/amd/uncore.c
blob: 4ccb8fa483e613af8bade68e3718bda0e91acd38 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2013 Advanced Micro Devices, Inc.
 *
 * Author: Jacob Shin <jacob.shin@amd.com>
 */

#include <linux/perf_event.h>
#include <linux/percpu.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpufeature.h>
#include <linux/smp.h>

#include <asm/perf_event.h>
#include <asm/msr.h>

#define NUM_COUNTERS_NB		4
#define NUM_COUNTERS_L2		4
#define NUM_COUNTERS_L3		6

#define RDPMC_BASE_NB		6
#define RDPMC_BASE_LLC		10

#define COUNTER_SHIFT		16
#define UNCORE_NAME_LEN		16
#define UNCORE_GROUP_MAX	256

#undef pr_fmt
#define pr_fmt(fmt)	"amd_uncore: " fmt

static int pmu_version;

struct amd_uncore_ctx {
	int refcnt;
	int cpu;
	struct perf_event **events;
	struct hlist_node node;
};

struct amd_uncore_pmu {
	char name[UNCORE_NAME_LEN];
	int num_counters;
	int rdpmc_base;
	u32 msr_base;
	int group;
	cpumask_t active_mask;
	struct pmu pmu;
	struct amd_uncore_ctx * __percpu *ctx;
};

enum {
	UNCORE_TYPE_DF,
	UNCORE_TYPE_L3,
	UNCORE_TYPE_UMC,

	UNCORE_TYPE_MAX
};

union amd_uncore_info {
	struct {
		u64	aux_data:32;	/* auxiliary data */
		u64	num_pmcs:8;	/* number of counters */
		u64	gid:8;		/* group id */
		u64	cid:8;		/* context id */
	} split;
	u64		full;
};

struct amd_uncore {
	union amd_uncore_info  __percpu *info;
	struct amd_uncore_pmu *pmus;
	unsigned int num_pmus;
	bool init_done;
	void (*scan)(struct amd_uncore *uncore, unsigned int cpu);
	int  (*init)(struct amd_uncore *uncore, unsigned int cpu);
	void (*move)(struct amd_uncore *uncore, unsigned int cpu);
	void (*free)(struct amd_uncore *uncore, unsigned int cpu);
};

static struct amd_uncore uncores[UNCORE_TYPE_MAX];

static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
{
	return container_of(event->pmu, struct amd_uncore_pmu, pmu);
}

static void amd_uncore_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	u64 prev, new;
	s64 delta;

	/*
	 * since we do not enable counter overflow interrupts,
	 * we do not have to worry about prev_count changing on us
	 */

	prev = local64_read(&hwc->prev_count);

	/*
	 * Some uncore PMUs do not have RDPMC assignments. In such cases,
	 * read counts directly from the corresponding PERF_CTR.
	 */
	if (hwc->event_base_rdpmc < 0)
		rdmsrl(hwc->event_base, new);
	else
		rdpmcl(hwc->event_base_rdpmc, new);

	local64_set(&hwc->prev_count, new);
	delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
	delta >>= COUNTER_SHIFT;
	local64_add(delta, &event->count);
}

static void amd_uncore_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	if (flags & PERF_EF_RELOAD)
		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));

	hwc->state = 0;
	wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
	perf_event_update_userpage(event);
}

static void amd_uncore_stop(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	wrmsrl(hwc->config_base, hwc->config);
	hwc->state |= PERF_HES_STOPPED;

	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
		event->pmu->read(event);
		hwc->state |= PERF_HES_UPTODATE;
	}
}

static int amd_uncore_add(struct perf_event *event, int flags)
{
	int i;
	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
	struct hw_perf_event *hwc = &event->hw;

	/* are we already assigned? */
	if (hwc->idx != -1 && ctx->events[hwc->idx] == event)
		goto out;

	for (i = 0; i < pmu->num_counters; i++) {
		if (ctx->events[i] == event) {
			hwc->idx = i;
			goto out;
		}
	}

	/* if not, take the first available counter */
	hwc->idx = -1;
	for (i = 0; i < pmu->num_counters; i++) {
		if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
			hwc->idx = i;
			break;
		}
	}

out:
	if (hwc->idx == -1)
		return -EBUSY;

	hwc->config_base = pmu->msr_base + (2 * hwc->idx);
	hwc->event_base = pmu->msr_base + 1 + (2 * hwc->idx);
	hwc->event_base_rdpmc = pmu->rdpmc_base + hwc->idx;
	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;

	if (pmu->rdpmc_base < 0)
		hwc->event_base_rdpmc = -1;

	if (flags & PERF_EF_START)
		event->pmu->start(event, PERF_EF_RELOAD);

	return 0;
}

static void amd_uncore_del(struct perf_event *event, int flags)
{
	int i;
	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
	struct hw_perf_event *hwc = &event->hw;

	event->pmu->stop(event, PERF_EF_UPDATE);

	for (i = 0; i < pmu->num_counters; i++) {
		if (cmpxchg(&ctx->events[i], event, NULL) == event)
			break;
	}

	hwc->idx = -1;
}

static int amd_uncore_event_init(struct perf_event *event)
{
	struct amd_uncore_pmu *pmu;
	struct amd_uncore_ctx *ctx;
	struct hw_perf_event *hwc = &event->hw;

	if (event->attr.type != event->pmu->type)
		return -ENOENT;

	if (event->cpu < 0)
		return -EINVAL;

	pmu = event_to_amd_uncore_pmu(event);
	ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
	if (!ctx)
		return -ENODEV;

	/*
	 * NB and Last level cache counters (MSRs) are shared across all cores
	 * that share the same NB / Last level cache.  On family 16h and below,
	 * Interrupts can be directed to a single target core, however, event
	 * counts generated by processes running on other cores cannot be masked
	 * out. So we do not support sampling and per-thread events via
	 * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
	 */
	hwc->config = event->attr.config;
	hwc->idx = -1;

	/*
	 * since request can come in to any of the shared cores, we will remap
	 * to a single common cpu.
	 */
	event->cpu = ctx->cpu;

	return 0;
}

static umode_t
amd_f17h_uncore_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
	return boot_cpu_data.x86 >= 0x17 && boot_cpu_data.x86 < 0x19 ?
	       attr->mode : 0;
}

static umode_t
amd_f19h_uncore_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
	return boot_cpu_data.x86 >= 0x19 ? attr->mode : 0;
}

static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
					    struct device_attribute *attr,
					    char *buf)
{
	struct pmu *ptr = dev_get_drvdata(dev);
	struct amd_uncore_pmu *pmu = container_of(ptr, struct amd_uncore_pmu, pmu);

	return cpumap_print_to_pagebuf(true, buf, &pmu->active_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);

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

static struct attribute_group amd_uncore_attr_group = {
	.attrs = amd_uncore_attrs,
};

#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format)			\
static ssize_t __uncore_##_var##_show(struct device *dev,		\
				struct device_attribute *attr,		\
				char *page)				\
{									\
	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
	return sprintf(page, _format "\n");				\
}									\
static struct device_attribute format_attr_##_var =			\
	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)

DEFINE_UNCORE_FORMAT_ATTR(event12,	event,		"config:0-7,32-35");
DEFINE_UNCORE_FORMAT_ATTR(event14,	event,		"config:0-7,32-35,59-60"); /* F17h+ DF */
DEFINE_UNCORE_FORMAT_ATTR(event14v2,	event,		"config:0-7,32-37");	   /* PerfMonV2 DF */
DEFINE_UNCORE_FORMAT_ATTR(event8,	event,		"config:0-7");		   /* F17h+ L3, PerfMonV2 UMC */
DEFINE_UNCORE_FORMAT_ATTR(umask8,	umask,		"config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask12,	umask,		"config:8-15,24-27");	   /* PerfMonV2 DF */
DEFINE_UNCORE_FORMAT_ATTR(coreid,	coreid,		"config:42-44");	   /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(slicemask,	slicemask,	"config:48-51");	   /* F17h L3 */
DEFINE_UNCORE_FORMAT_ATTR(threadmask8,	threadmask,	"config:56-63");	   /* F17h L3 */
DEFINE_UNCORE_FORMAT_ATTR(threadmask2,	threadmask,	"config:56-57");	   /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(enallslices,	enallslices,	"config:46");		   /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(enallcores,	enallcores,	"config:47");		   /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(sliceid,	sliceid,	"config:48-50");	   /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(rdwrmask,	rdwrmask,	"config:8-9");		   /* PerfMonV2 UMC */

/* Common DF and NB attributes */
static struct attribute *amd_uncore_df_format_attr[] = {
	&format_attr_event12.attr,	/* event */
	&format_attr_umask8.attr,	/* umask */
	NULL,
};

/* Common L2 and L3 attributes */
static struct attribute *amd_uncore_l3_format_attr[] = {
	&format_attr_event12.attr,	/* event */
	&format_attr_umask8.attr,	/* umask */
	NULL,				/* threadmask */
	NULL,
};

/* Common UMC attributes */
static struct attribute *amd_uncore_umc_format_attr[] = {
	&format_attr_event8.attr,       /* event */
	&format_attr_rdwrmask.attr,     /* rdwrmask */
	NULL,
};

/* F17h unique L3 attributes */
static struct attribute *amd_f17h_uncore_l3_format_attr[] = {
	&format_attr_slicemask.attr,	/* slicemask */
	NULL,
};

/* F19h unique L3 attributes */
static struct attribute *amd_f19h_uncore_l3_format_attr[] = {
	&format_attr_coreid.attr,	/* coreid */
	&format_attr_enallslices.attr,	/* enallslices */
	&format_attr_enallcores.attr,	/* enallcores */
	&format_attr_sliceid.attr,	/* sliceid */
	NULL,
};

static struct attribute_group amd_uncore_df_format_group = {
	.name = "format",
	.attrs = amd_uncore_df_format_attr,
};

static struct attribute_group amd_uncore_l3_format_group = {
	.name = "format",
	.attrs = amd_uncore_l3_format_attr,
};

static struct attribute_group amd_f17h_uncore_l3_format_group = {
	.name = "format",
	.attrs = amd_f17h_uncore_l3_format_attr,
	.is_visible = amd_f17h_uncore_is_visible,
};

static struct attribute_group amd_f19h_uncore_l3_format_group = {
	.name = "format",
	.attrs = amd_f19h_uncore_l3_format_attr,
	.is_visible = amd_f19h_uncore_is_visible,
};

static struct attribute_group amd_uncore_umc_format_group = {
	.name = "format",
	.attrs = amd_uncore_umc_format_attr,
};

static const struct attribute_group *amd_uncore_df_attr_groups[] = {
	&amd_uncore_attr_group,
	&amd_uncore_df_format_group,
	NULL,
};

static const struct attribute_group *amd_uncore_l3_attr_groups[] = {
	&amd_uncore_attr_group,
	&amd_uncore_l3_format_group,
	NULL,
};

static const struct attribute_group *amd_uncore_l3_attr_update[] = {
	&amd_f17h_uncore_l3_format_group,
	&amd_f19h_uncore_l3_format_group,
	NULL,
};

static const struct attribute_group *amd_uncore_umc_attr_groups[] = {
	&amd_uncore_attr_group,
	&amd_uncore_umc_format_group,
	NULL,
};

static __always_inline
int amd_uncore_ctx_cid(struct amd_uncore *uncore, unsigned int cpu)
{
	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
	return info->split.cid;
}

static __always_inline
int amd_uncore_ctx_gid(struct amd_uncore *uncore, unsigned int cpu)
{
	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
	return info->split.gid;
}

static __always_inline
int amd_uncore_ctx_num_pmcs(struct amd_uncore *uncore, unsigned int cpu)
{
	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
	return info->split.num_pmcs;
}

static void amd_uncore_ctx_free(struct amd_uncore *uncore, unsigned int cpu)
{
	struct amd_uncore_pmu *pmu;
	struct amd_uncore_ctx *ctx;
	int i;

	if (!uncore->init_done)
		return;

	for (i = 0; i < uncore->num_pmus; i++) {
		pmu = &uncore->pmus[i];
		ctx = *per_cpu_ptr(pmu->ctx, cpu);
		if (!ctx)
			continue;

		if (cpu == ctx->cpu)
			cpumask_clear_cpu(cpu, &pmu->active_mask);

		if (!--ctx->refcnt) {
			kfree(ctx->events);
			kfree(ctx);
		}

		*per_cpu_ptr(pmu->ctx, cpu) = NULL;
	}
}

static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
	struct amd_uncore_ctx *curr, *prev;
	struct amd_uncore_pmu *pmu;
	int node, cid, gid, i, j;

	if (!uncore->init_done || !uncore->num_pmus)
		return 0;

	cid = amd_uncore_ctx_cid(uncore, cpu);
	gid = amd_uncore_ctx_gid(uncore, cpu);

	for (i = 0; i < uncore->num_pmus; i++) {
		pmu = &uncore->pmus[i];
		*per_cpu_ptr(pmu->ctx, cpu) = NULL;
		curr = NULL;

		/* Check for group exclusivity */
		if (gid != pmu->group)
			continue;

		/* Find a sibling context */
		for_each_online_cpu(j) {
			if (cpu == j)
				continue;

			prev = *per_cpu_ptr(pmu->ctx, j);
			if (!prev)
				continue;

			if (cid == amd_uncore_ctx_cid(uncore, j)) {
				curr = prev;
				break;
			}
		}

		/* Allocate context if sibling does not exist */
		if (!curr) {
			node = cpu_to_node(cpu);
			curr = kzalloc_node(sizeof(*curr), GFP_KERNEL, node);
			if (!curr)
				goto fail;

			curr->cpu = cpu;
			curr->events = kzalloc_node(sizeof(*curr->events) *
						    pmu->num_counters,
						    GFP_KERNEL, node);
			if (!curr->events) {
				kfree(curr);
				goto fail;
			}

			cpumask_set_cpu(cpu, &pmu->active_mask);
		}

		curr->refcnt++;
		*per_cpu_ptr(pmu->ctx, cpu) = curr;
	}

	return 0;

fail:
	amd_uncore_ctx_free(uncore, cpu);

	return -ENOMEM;
}

static void amd_uncore_ctx_move(struct amd_uncore *uncore, unsigned int cpu)
{
	struct amd_uncore_ctx *curr, *next;
	struct amd_uncore_pmu *pmu;
	int i, j;

	if (!uncore->init_done)
		return;

	for (i = 0; i < uncore->num_pmus; i++) {
		pmu = &uncore->pmus[i];
		curr = *per_cpu_ptr(pmu->ctx, cpu);
		if (!curr)
			continue;

		/* Migrate to a shared sibling if possible */
		for_each_online_cpu(j) {
			next = *per_cpu_ptr(pmu->ctx, j);
			if (!next || cpu == j)
				continue;

			if (curr == next) {
				perf_pmu_migrate_context(&pmu->pmu, cpu, j);
				cpumask_clear_cpu(cpu, &pmu->active_mask);
				cpumask_set_cpu(j, &pmu->active_mask);
				next->cpu = j;
				break;
			}
		}
	}
}

static int amd_uncore_cpu_starting(unsigned int cpu)
{
	struct amd_uncore *uncore;
	int i;

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		uncore->scan(uncore, cpu);
	}

	return 0;
}

static int amd_uncore_cpu_online(unsigned int cpu)
{
	struct amd_uncore *uncore;
	int i;

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		if (uncore->init(uncore, cpu))
			break;
	}

	return 0;
}

static int amd_uncore_cpu_down_prepare(unsigned int cpu)
{
	struct amd_uncore *uncore;
	int i;

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		uncore->move(uncore, cpu);
	}

	return 0;
}

static int amd_uncore_cpu_dead(unsigned int cpu)
{
	struct amd_uncore *uncore;
	int i;

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		uncore->free(uncore, cpu);
	}

	return 0;
}

static int amd_uncore_df_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int ret = amd_uncore_event_init(event);

	if (ret || pmu_version < 2)
		return ret;

	hwc->config = event->attr.config &
		      (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB :
					  AMD64_RAW_EVENT_MASK_NB);

	return 0;
}

static int amd_uncore_df_add(struct perf_event *event, int flags)
{
	int ret = amd_uncore_add(event, flags & ~PERF_EF_START);
	struct hw_perf_event *hwc = &event->hw;

	if (ret)
		return ret;

	/*
	 * The first four DF counters are accessible via RDPMC index 6 to 9
	 * followed by the L3 counters from index 10 to 15. For processors
	 * with more than four DF counters, the DF RDPMC assignments become
	 * discontiguous as the additional counters are accessible starting
	 * from index 16.
	 */
	if (hwc->idx >= NUM_COUNTERS_NB)
		hwc->event_base_rdpmc += NUM_COUNTERS_L3;

	/* Delayed start after rdpmc base update */
	if (flags & PERF_EF_START)
		amd_uncore_start(event, PERF_EF_RELOAD);

	return 0;
}

static
void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
	union cpuid_0x80000022_ebx ebx;
	union amd_uncore_info info;

	if (!boot_cpu_has(X86_FEATURE_PERFCTR_NB))
		return;

	info.split.aux_data = 0;
	info.split.num_pmcs = NUM_COUNTERS_NB;
	info.split.gid = 0;
	info.split.cid = topology_die_id(cpu);

	if (pmu_version >= 2) {
		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
		info.split.num_pmcs = ebx.split.num_df_pmc;
	}

	*per_cpu_ptr(uncore->info, cpu) = info;
}

static
int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
	struct attribute **df_attr = amd_uncore_df_format_attr;
	struct amd_uncore_pmu *pmu;

	/* Run just once */
	if (uncore->init_done)
		return amd_uncore_ctx_init(uncore, cpu);

	/* No grouping, single instance for a system */
	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
	if (!uncore->pmus) {
		uncore->num_pmus = 0;
		goto done;
	}

	/*
	 * For Family 17h and above, the Northbridge counters are repurposed
	 * as Data Fabric counters. The PMUs are exported based on family as
	 * either NB or DF.
	 */
	pmu = &uncore->pmus[0];
	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
		sizeof(pmu->name));
	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
	pmu->msr_base = MSR_F15H_NB_PERF_CTL;
	pmu->rdpmc_base = RDPMC_BASE_NB;
	pmu->group = amd_uncore_ctx_gid(uncore, cpu);

	if (pmu_version >= 2) {
		*df_attr++ = &format_attr_event14v2.attr;
		*df_attr++ = &format_attr_umask12.attr;
	} else if (boot_cpu_data.x86 >= 0x17) {
		*df_attr = &format_attr_event14.attr;
	}

	pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
	if (!pmu->ctx)
		goto done;

	pmu->pmu = (struct pmu) {
		.task_ctx_nr	= perf_invalid_context,
		.attr_groups	= amd_uncore_df_attr_groups,
		.name		= pmu->name,
		.event_init	= amd_uncore_df_event_init,
		.add		= amd_uncore_df_add,
		.del		= amd_uncore_del,
		.start		= amd_uncore_start,
		.stop		= amd_uncore_stop,
		.read		= amd_uncore_read,
		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
		.module		= THIS_MODULE,
	};

	if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
		free_percpu(pmu->ctx);
		pmu->ctx = NULL;
		goto done;
	}

	pr_info("%d %s%s counters detected\n", pmu->num_counters,
		boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON " : "",
		pmu->pmu.name);

	uncore->num_pmus = 1;

done:
	uncore->init_done = true;

	return amd_uncore_ctx_init(uncore, cpu);
}

static int amd_uncore_l3_event_init(struct perf_event *event)
{
	int ret = amd_uncore_event_init(event);
	struct hw_perf_event *hwc = &event->hw;
	u64 config = event->attr.config;
	u64 mask;

	hwc->config = config & AMD64_RAW_EVENT_MASK_NB;

	/*
	 * SliceMask and ThreadMask need to be set for certain L3 events.
	 * For other events, the two fields do not affect the count.
	 */
	if (ret || boot_cpu_data.x86 < 0x17)
		return ret;

	mask = config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK |
			 AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES |
			 AMD64_L3_COREID_MASK);

	if (boot_cpu_data.x86 <= 0x18)
		mask = ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) |
		       ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK);

	/*
	 * If the user doesn't specify a ThreadMask, they're not trying to
	 * count core 0, so we enable all cores & threads.
	 * We'll also assume that they want to count slice 0 if they specify
	 * a ThreadMask and leave SliceId and EnAllSlices unpopulated.
	 */
	else if (!(config & AMD64_L3_F19H_THREAD_MASK))
		mask = AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES |
		       AMD64_L3_EN_ALL_CORES;

	hwc->config |= mask;

	return 0;
}

static
void amd_uncore_l3_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
	union amd_uncore_info info;

	if (!boot_cpu_has(X86_FEATURE_PERFCTR_LLC))
		return;

	info.split.aux_data = 0;
	info.split.num_pmcs = NUM_COUNTERS_L2;
	info.split.gid = 0;
	info.split.cid = per_cpu_llc_id(cpu);

	if (boot_cpu_data.x86 >= 0x17)
		info.split.num_pmcs = NUM_COUNTERS_L3;

	*per_cpu_ptr(uncore->info, cpu) = info;
}

static
int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
	struct attribute **l3_attr = amd_uncore_l3_format_attr;
	struct amd_uncore_pmu *pmu;

	/* Run just once */
	if (uncore->init_done)
		return amd_uncore_ctx_init(uncore, cpu);

	/* No grouping, single instance for a system */
	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
	if (!uncore->pmus) {
		uncore->num_pmus = 0;
		goto done;
	}

	/*
	 * For Family 17h and above, L3 cache counters are available instead
	 * of L2 cache counters. The PMUs are exported based on family as
	 * either L2 or L3.
	 */
	pmu = &uncore->pmus[0];
	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
		sizeof(pmu->name));
	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
	pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
	pmu->rdpmc_base = RDPMC_BASE_LLC;
	pmu->group = amd_uncore_ctx_gid(uncore, cpu);

	if (boot_cpu_data.x86 >= 0x17) {
		*l3_attr++ = &format_attr_event8.attr;
		*l3_attr++ = &format_attr_umask8.attr;
		*l3_attr++ = boot_cpu_data.x86 >= 0x19 ?
			     &format_attr_threadmask2.attr :
			     &format_attr_threadmask8.attr;
	}

	pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
	if (!pmu->ctx)
		goto done;

	pmu->pmu = (struct pmu) {
		.task_ctx_nr	= perf_invalid_context,
		.attr_groups	= amd_uncore_l3_attr_groups,
		.attr_update	= amd_uncore_l3_attr_update,
		.name		= pmu->name,
		.event_init	= amd_uncore_l3_event_init,
		.add		= amd_uncore_add,
		.del		= amd_uncore_del,
		.start		= amd_uncore_start,
		.stop		= amd_uncore_stop,
		.read		= amd_uncore_read,
		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
		.module		= THIS_MODULE,
	};

	if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
		free_percpu(pmu->ctx);
		pmu->ctx = NULL;
		goto done;
	}

	pr_info("%d %s%s counters detected\n", pmu->num_counters,
		boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON " : "",
		pmu->pmu.name);

	uncore->num_pmus = 1;

done:
	uncore->init_done = true;

	return amd_uncore_ctx_init(uncore, cpu);
}

static int amd_uncore_umc_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int ret = amd_uncore_event_init(event);

	if (ret)
		return ret;

	hwc->config = event->attr.config & AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC;

	return 0;
}

static void amd_uncore_umc_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	if (flags & PERF_EF_RELOAD)
		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));

	hwc->state = 0;
	wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
	perf_event_update_userpage(event);
}

static
void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
	union cpuid_0x80000022_ebx ebx;
	union amd_uncore_info info;
	unsigned int eax, ecx, edx;

	if (pmu_version < 2)
		return;

	cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
	info.split.aux_data = ecx;	/* stash active mask */
	info.split.num_pmcs = ebx.split.num_umc_pmc;
	info.split.gid = topology_die_id(cpu);
	info.split.cid = topology_die_id(cpu);
	*per_cpu_ptr(uncore->info, cpu) = info;
}

static
int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
	DECLARE_BITMAP(gmask, UNCORE_GROUP_MAX) = { 0 };
	u8 group_num_pmus[UNCORE_GROUP_MAX] = { 0 };
	u8 group_num_pmcs[UNCORE_GROUP_MAX] = { 0 };
	union amd_uncore_info info;
	struct amd_uncore_pmu *pmu;
	int index = 0, gid, i;

	if (pmu_version < 2)
		return 0;

	/* Run just once */
	if (uncore->init_done)
		return amd_uncore_ctx_init(uncore, cpu);

	/* Find unique groups */
	for_each_online_cpu(i) {
		info = *per_cpu_ptr(uncore->info, i);
		gid = info.split.gid;
		if (test_bit(gid, gmask))
			continue;

		__set_bit(gid, gmask);
		group_num_pmus[gid] = hweight32(info.split.aux_data);
		group_num_pmcs[gid] = info.split.num_pmcs;
		uncore->num_pmus += group_num_pmus[gid];
	}

	uncore->pmus = kzalloc(sizeof(*uncore->pmus) * uncore->num_pmus,
			       GFP_KERNEL);
	if (!uncore->pmus) {
		uncore->num_pmus = 0;
		goto done;
	}

	for_each_set_bit(gid, gmask, UNCORE_GROUP_MAX) {
		for (i = 0; i < group_num_pmus[gid]; i++) {
			pmu = &uncore->pmus[index];
			snprintf(pmu->name, sizeof(pmu->name), "amd_umc_%d", index);
			pmu->num_counters = group_num_pmcs[gid] / group_num_pmus[gid];
			pmu->msr_base = MSR_F19H_UMC_PERF_CTL + i * pmu->num_counters * 2;
			pmu->rdpmc_base = -1;
			pmu->group = gid;

			pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
			if (!pmu->ctx)
				goto done;

			pmu->pmu = (struct pmu) {
				.task_ctx_nr	= perf_invalid_context,
				.attr_groups	= amd_uncore_umc_attr_groups,
				.name		= pmu->name,
				.event_init	= amd_uncore_umc_event_init,
				.add		= amd_uncore_add,
				.del		= amd_uncore_del,
				.start		= amd_uncore_umc_start,
				.stop		= amd_uncore_stop,
				.read		= amd_uncore_read,
				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
				.module		= THIS_MODULE,
			};

			if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
				free_percpu(pmu->ctx);
				pmu->ctx = NULL;
				goto done;
			}

			pr_info("%d %s counters detected\n", pmu->num_counters,
				pmu->pmu.name);

			index++;
		}
	}

done:
	uncore->num_pmus = index;
	uncore->init_done = true;

	return amd_uncore_ctx_init(uncore, cpu);
}

static struct amd_uncore uncores[UNCORE_TYPE_MAX] = {
	/* UNCORE_TYPE_DF */
	{
		.scan = amd_uncore_df_ctx_scan,
		.init = amd_uncore_df_ctx_init,
		.move = amd_uncore_ctx_move,
		.free = amd_uncore_ctx_free,
	},
	/* UNCORE_TYPE_L3 */
	{
		.scan = amd_uncore_l3_ctx_scan,
		.init = amd_uncore_l3_ctx_init,
		.move = amd_uncore_ctx_move,
		.free = amd_uncore_ctx_free,
	},
	/* UNCORE_TYPE_UMC */
	{
		.scan = amd_uncore_umc_ctx_scan,
		.init = amd_uncore_umc_ctx_init,
		.move = amd_uncore_ctx_move,
		.free = amd_uncore_ctx_free,
	},
};

static int __init amd_uncore_init(void)
{
	struct amd_uncore *uncore;
	int ret = -ENODEV;
	int i;

	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
		return -ENODEV;

	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
		return -ENODEV;

	if (boot_cpu_has(X86_FEATURE_PERFMON_V2))
		pmu_version = 2;

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];

		BUG_ON(!uncore->scan);
		BUG_ON(!uncore->init);
		BUG_ON(!uncore->move);
		BUG_ON(!uncore->free);

		uncore->info = alloc_percpu(union amd_uncore_info);
		if (!uncore->info) {
			ret = -ENOMEM;
			goto fail;
		}
	};

	/*
	 * Install callbacks. Core will call them for each online cpu.
	 */
	ret = cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
				"perf/x86/amd/uncore:prepare",
				NULL, amd_uncore_cpu_dead);
	if (ret)
		goto fail;

	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
				"perf/x86/amd/uncore:starting",
				amd_uncore_cpu_starting, NULL);
	if (ret)
		goto fail_prep;

	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
				"perf/x86/amd/uncore:online",
				amd_uncore_cpu_online,
				amd_uncore_cpu_down_prepare);
	if (ret)
		goto fail_start;

	return 0;

fail_start:
	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
fail:
	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		if (uncore->info) {
			free_percpu(uncore->info);
			uncore->info = NULL;
		}
	}

	return ret;
}

static void __exit amd_uncore_exit(void)
{
	struct amd_uncore *uncore;
	struct amd_uncore_pmu *pmu;
	int i, j;

	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE);
	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);

	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
		uncore = &uncores[i];
		if (!uncore->info)
			continue;

		free_percpu(uncore->info);
		uncore->info = NULL;

		for (j = 0; j < uncore->num_pmus; j++) {
			pmu = &uncore->pmus[j];
			if (!pmu->ctx)
				continue;

			perf_pmu_unregister(&pmu->pmu);
			free_percpu(pmu->ctx);
			pmu->ctx = NULL;
		}

		kfree(uncore->pmus);
		uncore->pmus = NULL;
	}
}

module_init(amd_uncore_init);
module_exit(amd_uncore_exit);

MODULE_DESCRIPTION("AMD Uncore Driver");
MODULE_LICENSE("GPL v2");