summaryrefslogtreecommitdiffstats
path: root/drivers/perf/arm_smmuv3_pmu.c
blob: 6ebe72b86266195caf2b89a3a7a8c6ad3bb103c5 (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
// SPDX-License-Identifier: GPL-2.0

/*
 * This driver adds support for perf events to use the Performance
 * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
 * to monitor that node.
 *
 * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
 * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
 * to 4K boundary. For example, the PMCG at 0xff88840000 is named
 * smmuv3_pmcg_ff88840
 *
 * Filtering by stream id is done by specifying filtering parameters
 * with the event. options are:
 *   filter_enable    - 0 = no filtering, 1 = filtering enabled
 *   filter_span      - 0 = exact match, 1 = pattern match
 *   filter_stream_id - pattern to filter against
 *
 * To match a partial StreamID where the X most-significant bits must match
 * but the Y least-significant bits might differ, STREAMID is programmed
 * with a value that contains:
 *  STREAMID[Y - 1] == 0.
 *  STREAMID[Y - 2:0] == 1 (where Y > 1).
 * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
 * contain a value to match from the corresponding bits of event StreamID.
 *
 * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
 *                    filter_span=1,filter_stream_id=0x42/ -a netperf
 * Applies filter pattern 0x42 to transaction events, which means events
 * matching stream ids 0x42 and 0x43 are counted. Further filtering
 * information is available in the SMMU documentation.
 *
 * SMMU events are not attributable to a CPU, so task mode and sampling
 * are not supported.
 */

#include <linux/acpi.h>
#include <linux/acpi_iort.h>
#include <linux/bitfield.h>
#include <linux/bitops.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/msi.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/smp.h>
#include <linux/sysfs.h>
#include <linux/types.h>

#define SMMU_PMCG_EVCNTR0               0x0
#define SMMU_PMCG_EVCNTR(n, stride)     (SMMU_PMCG_EVCNTR0 + (n) * (stride))
#define SMMU_PMCG_EVTYPER0              0x400
#define SMMU_PMCG_EVTYPER(n)            (SMMU_PMCG_EVTYPER0 + (n) * 4)
#define SMMU_PMCG_SID_SPAN_SHIFT        29
#define SMMU_PMCG_SMR0                  0xA00
#define SMMU_PMCG_SMR(n)                (SMMU_PMCG_SMR0 + (n) * 4)
#define SMMU_PMCG_CNTENSET0             0xC00
#define SMMU_PMCG_CNTENCLR0             0xC20
#define SMMU_PMCG_INTENSET0             0xC40
#define SMMU_PMCG_INTENCLR0             0xC60
#define SMMU_PMCG_OVSCLR0               0xC80
#define SMMU_PMCG_OVSSET0               0xCC0
#define SMMU_PMCG_CFGR                  0xE00
#define SMMU_PMCG_CFGR_SID_FILTER_TYPE  BIT(23)
#define SMMU_PMCG_CFGR_MSI              BIT(21)
#define SMMU_PMCG_CFGR_RELOC_CTRS       BIT(20)
#define SMMU_PMCG_CFGR_SIZE             GENMASK(13, 8)
#define SMMU_PMCG_CFGR_NCTR             GENMASK(5, 0)
#define SMMU_PMCG_CR                    0xE04
#define SMMU_PMCG_CR_ENABLE             BIT(0)
#define SMMU_PMCG_CEID0                 0xE20
#define SMMU_PMCG_CEID1                 0xE28
#define SMMU_PMCG_IRQ_CTRL              0xE50
#define SMMU_PMCG_IRQ_CTRL_IRQEN        BIT(0)
#define SMMU_PMCG_IRQ_CFG0              0xE58
#define SMMU_PMCG_IRQ_CFG1              0xE60
#define SMMU_PMCG_IRQ_CFG2              0xE64

/* MSI config fields */
#define MSI_CFG0_ADDR_MASK              GENMASK_ULL(51, 2)
#define MSI_CFG2_MEMATTR_DEVICE_nGnRE   0x1

#define SMMU_PMCG_DEFAULT_FILTER_SPAN   1
#define SMMU_PMCG_DEFAULT_FILTER_SID    GENMASK(31, 0)

#define SMMU_PMCG_MAX_COUNTERS          64
#define SMMU_PMCG_ARCH_MAX_EVENTS       128

#define SMMU_PMCG_PA_SHIFT              12

#define SMMU_PMCG_EVCNTR_RDONLY         BIT(0)
#define SMMU_PMCG_HARDEN_DISABLE        BIT(1)

static int cpuhp_state_num;

struct smmu_pmu {
	struct hlist_node node;
	struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
	DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
	DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
	unsigned int irq;
	unsigned int on_cpu;
	struct pmu pmu;
	unsigned int num_counters;
	struct device *dev;
	void __iomem *reg_base;
	void __iomem *reloc_base;
	u64 counter_mask;
	u32 options;
	bool global_filter;
};

#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))

#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end)        \
	static inline u32 get_##_name(struct perf_event *event)            \
	{                                                                  \
		return FIELD_GET(GENMASK_ULL(_end, _start),                \
				 event->attr._config);                     \
	}                                                                  \

SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);

static inline void smmu_pmu_enable(struct pmu *pmu)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);

	writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
	       smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
	writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
}

static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
				       struct perf_event *event, int idx);

static inline void smmu_pmu_enable_quirk_hip08_09(struct pmu *pmu)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
	unsigned int idx;

	for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters)
		smmu_pmu_apply_event_filter(smmu_pmu, smmu_pmu->events[idx], idx);

	smmu_pmu_enable(pmu);
}

static inline void smmu_pmu_disable(struct pmu *pmu)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);

	writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
	writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
}

static inline void smmu_pmu_disable_quirk_hip08_09(struct pmu *pmu)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
	unsigned int idx;

	/*
	 * The global disable of PMU sometimes fail to stop the counting.
	 * Harden this by writing an invalid event type to each used counter
	 * to forcibly stop counting.
	 */
	for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters)
		writel(0xffff, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));

	smmu_pmu_disable(pmu);
}

static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
					      u32 idx, u64 value)
{
	if (smmu_pmu->counter_mask & BIT(32))
		writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
	else
		writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
}

static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
{
	u64 value;

	if (smmu_pmu->counter_mask & BIT(32))
		value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
	else
		value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));

	return value;
}

static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
{
	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
}

static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
{
	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
}

static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
{
	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
}

static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
					      u32 idx)
{
	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
}

static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
					u32 val)
{
	writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
}

static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
{
	writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
}

static void smmu_pmu_event_update(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	u64 delta, prev, now;
	u32 idx = hwc->idx;

	do {
		prev = local64_read(&hwc->prev_count);
		now = smmu_pmu_counter_get_value(smmu_pmu, idx);
	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);

	/* handle overflow. */
	delta = now - prev;
	delta &= smmu_pmu->counter_mask;

	local64_add(delta, &event->count);
}

static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
				struct hw_perf_event *hwc)
{
	u32 idx = hwc->idx;
	u64 new;

	if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
		/*
		 * On platforms that require this quirk, if the counter starts
		 * at < half_counter value and wraps, the current logic of
		 * handling the overflow may not work. It is expected that,
		 * those platforms will have full 64 counter bits implemented
		 * so that such a possibility is remote(eg: HiSilicon HIP08).
		 */
		new = smmu_pmu_counter_get_value(smmu_pmu, idx);
	} else {
		/*
		 * We limit the max period to half the max counter value
		 * of the counter size, so that even in the case of extreme
		 * interrupt latency the counter will (hopefully) not wrap
		 * past its initial value.
		 */
		new = smmu_pmu->counter_mask >> 1;
		smmu_pmu_counter_set_value(smmu_pmu, idx, new);
	}

	local64_set(&hwc->prev_count, new);
}

static void smmu_pmu_set_event_filter(struct perf_event *event,
				      int idx, u32 span, u32 sid)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	u32 evtyper;

	evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
	smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
	smmu_pmu_set_smr(smmu_pmu, idx, sid);
}

static bool smmu_pmu_check_global_filter(struct perf_event *curr,
					 struct perf_event *new)
{
	if (get_filter_enable(new) != get_filter_enable(curr))
		return false;

	if (!get_filter_enable(new))
		return true;

	return get_filter_span(new) == get_filter_span(curr) &&
	       get_filter_stream_id(new) == get_filter_stream_id(curr);
}

static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
				       struct perf_event *event, int idx)
{
	u32 span, sid;
	unsigned int cur_idx, num_ctrs = smmu_pmu->num_counters;
	bool filter_en = !!get_filter_enable(event);

	span = filter_en ? get_filter_span(event) :
			   SMMU_PMCG_DEFAULT_FILTER_SPAN;
	sid = filter_en ? get_filter_stream_id(event) :
			   SMMU_PMCG_DEFAULT_FILTER_SID;

	cur_idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
	/*
	 * Per-counter filtering, or scheduling the first globally-filtered
	 * event into an empty PMU so idx == 0 and it works out equivalent.
	 */
	if (!smmu_pmu->global_filter || cur_idx == num_ctrs) {
		smmu_pmu_set_event_filter(event, idx, span, sid);
		return 0;
	}

	/* Otherwise, must match whatever's currently scheduled */
	if (smmu_pmu_check_global_filter(smmu_pmu->events[cur_idx], event)) {
		smmu_pmu_set_evtyper(smmu_pmu, idx, get_event(event));
		return 0;
	}

	return -EAGAIN;
}

static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
				  struct perf_event *event)
{
	int idx, err;
	unsigned int num_ctrs = smmu_pmu->num_counters;

	idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
	if (idx == num_ctrs)
		/* The counters are all in use. */
		return -EAGAIN;

	err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
	if (err)
		return err;

	set_bit(idx, smmu_pmu->used_counters);

	return idx;
}

static bool smmu_pmu_events_compatible(struct perf_event *curr,
				       struct perf_event *new)
{
	if (new->pmu != curr->pmu)
		return false;

	if (to_smmu_pmu(new->pmu)->global_filter &&
	    !smmu_pmu_check_global_filter(curr, new))
		return false;

	return true;
}

/*
 * Implementation of abstract pmu functionality required by
 * the core perf events code.
 */

static int smmu_pmu_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	struct device *dev = smmu_pmu->dev;
	struct perf_event *sibling;
	int group_num_events = 1;
	u16 event_id;

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

	if (hwc->sample_period) {
		dev_dbg(dev, "Sampling not supported\n");
		return -EOPNOTSUPP;
	}

	if (event->cpu < 0) {
		dev_dbg(dev, "Per-task mode not supported\n");
		return -EOPNOTSUPP;
	}

	/* Verify specified event is supported on this PMU */
	event_id = get_event(event);
	if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
	    (!test_bit(event_id, smmu_pmu->supported_events))) {
		dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
		return -EINVAL;
	}

	/* Don't allow groups with mixed PMUs, except for s/w events */
	if (!is_software_event(event->group_leader)) {
		if (!smmu_pmu_events_compatible(event->group_leader, event))
			return -EINVAL;

		if (++group_num_events > smmu_pmu->num_counters)
			return -EINVAL;
	}

	for_each_sibling_event(sibling, event->group_leader) {
		if (is_software_event(sibling))
			continue;

		if (!smmu_pmu_events_compatible(sibling, event))
			return -EINVAL;

		if (++group_num_events > smmu_pmu->num_counters)
			return -EINVAL;
	}

	hwc->idx = -1;

	/*
	 * Ensure all events are on the same cpu so all events are in the
	 * same cpu context, to avoid races on pmu_enable etc.
	 */
	event->cpu = smmu_pmu->on_cpu;

	return 0;
}

static void smmu_pmu_event_start(struct perf_event *event, int flags)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	hwc->state = 0;

	smmu_pmu_set_period(smmu_pmu, hwc);

	smmu_pmu_counter_enable(smmu_pmu, idx);
}

static void smmu_pmu_event_stop(struct perf_event *event, int flags)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	if (hwc->state & PERF_HES_STOPPED)
		return;

	smmu_pmu_counter_disable(smmu_pmu, idx);
	/* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
	smmu_pmu_event_update(event);
	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
}

static int smmu_pmu_event_add(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	int idx;
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);

	idx = smmu_pmu_get_event_idx(smmu_pmu, event);
	if (idx < 0)
		return idx;

	hwc->idx = idx;
	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
	smmu_pmu->events[idx] = event;
	local64_set(&hwc->prev_count, 0);

	smmu_pmu_interrupt_enable(smmu_pmu, idx);

	if (flags & PERF_EF_START)
		smmu_pmu_event_start(event, flags);

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

	return 0;
}

static void smmu_pmu_event_del(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
	int idx = hwc->idx;

	smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
	smmu_pmu_interrupt_disable(smmu_pmu, idx);
	smmu_pmu->events[idx] = NULL;
	clear_bit(idx, smmu_pmu->used_counters);

	perf_event_update_userpage(event);
}

static void smmu_pmu_event_read(struct perf_event *event)
{
	smmu_pmu_event_update(event);
}

/* cpumask */

static ssize_t smmu_pmu_cpumask_show(struct device *dev,
				     struct device_attribute *attr,
				     char *buf)
{
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));

	return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
}

static struct device_attribute smmu_pmu_cpumask_attr =
		__ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);

static struct attribute *smmu_pmu_cpumask_attrs[] = {
	&smmu_pmu_cpumask_attr.attr,
	NULL
};

static struct attribute_group smmu_pmu_cpumask_group = {
	.attrs = smmu_pmu_cpumask_attrs,
};

/* Events */

static ssize_t smmu_pmu_event_show(struct device *dev,
				   struct device_attribute *attr, char *page)
{
	struct perf_pmu_events_attr *pmu_attr;

	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);

	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
}

#define SMMU_EVENT_ATTR(name, config) \
	PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
		       config, smmu_pmu_event_show)
SMMU_EVENT_ATTR(cycles, 0);
SMMU_EVENT_ATTR(transaction, 1);
SMMU_EVENT_ATTR(tlb_miss, 2);
SMMU_EVENT_ATTR(config_cache_miss, 3);
SMMU_EVENT_ATTR(trans_table_walk_access, 4);
SMMU_EVENT_ATTR(config_struct_access, 5);
SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);

static struct attribute *smmu_pmu_events[] = {
	&smmu_event_attr_cycles.attr.attr,
	&smmu_event_attr_transaction.attr.attr,
	&smmu_event_attr_tlb_miss.attr.attr,
	&smmu_event_attr_config_cache_miss.attr.attr,
	&smmu_event_attr_trans_table_walk_access.attr.attr,
	&smmu_event_attr_config_struct_access.attr.attr,
	&smmu_event_attr_pcie_ats_trans_rq.attr.attr,
	&smmu_event_attr_pcie_ats_trans_passed.attr.attr,
	NULL
};

static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
					 struct attribute *attr, int unused)
{
	struct device *dev = kobj_to_dev(kobj);
	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
	struct perf_pmu_events_attr *pmu_attr;

	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);

	if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
		return attr->mode;

	return 0;
}

static struct attribute_group smmu_pmu_events_group = {
	.name = "events",
	.attrs = smmu_pmu_events,
	.is_visible = smmu_pmu_event_is_visible,
};

/* Formats */
PMU_FORMAT_ATTR(event,		   "config:0-15");
PMU_FORMAT_ATTR(filter_stream_id,  "config1:0-31");
PMU_FORMAT_ATTR(filter_span,	   "config1:32");
PMU_FORMAT_ATTR(filter_enable,	   "config1:33");

static struct attribute *smmu_pmu_formats[] = {
	&format_attr_event.attr,
	&format_attr_filter_stream_id.attr,
	&format_attr_filter_span.attr,
	&format_attr_filter_enable.attr,
	NULL
};

static struct attribute_group smmu_pmu_format_group = {
	.name = "format",
	.attrs = smmu_pmu_formats,
};

static const struct attribute_group *smmu_pmu_attr_grps[] = {
	&smmu_pmu_cpumask_group,
	&smmu_pmu_events_group,
	&smmu_pmu_format_group,
	NULL
};

/*
 * Generic device handlers
 */

static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
{
	struct smmu_pmu *smmu_pmu;
	unsigned int target;

	smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
	if (cpu != smmu_pmu->on_cpu)
		return 0;

	target = cpumask_any_but(cpu_online_mask, cpu);
	if (target >= nr_cpu_ids)
		return 0;

	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
	smmu_pmu->on_cpu = target;
	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));

	return 0;
}

static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
{
	struct smmu_pmu *smmu_pmu = data;
	u64 ovsr;
	unsigned int idx;

	ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
	if (!ovsr)
		return IRQ_NONE;

	writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);

	for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
		struct perf_event *event = smmu_pmu->events[idx];
		struct hw_perf_event *hwc;

		if (WARN_ON_ONCE(!event))
			continue;

		smmu_pmu_event_update(event);
		hwc = &event->hw;

		smmu_pmu_set_period(smmu_pmu, hwc);
	}

	return IRQ_HANDLED;
}

static void smmu_pmu_free_msis(void *data)
{
	struct device *dev = data;

	platform_msi_domain_free_irqs(dev);
}

static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
{
	phys_addr_t doorbell;
	struct device *dev = msi_desc_to_dev(desc);
	struct smmu_pmu *pmu = dev_get_drvdata(dev);

	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
	doorbell &= MSI_CFG0_ADDR_MASK;

	writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
	writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
	writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
		       pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
}

static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
{
	struct msi_desc *desc;
	struct device *dev = pmu->dev;
	int ret;

	/* Clear MSI address reg */
	writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);

	/* MSI supported or not */
	if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
		return;

	ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
	if (ret) {
		dev_warn(dev, "failed to allocate MSIs\n");
		return;
	}

	desc = first_msi_entry(dev);
	if (desc)
		pmu->irq = desc->irq;

	/* Add callback to free MSIs on teardown */
	devm_add_action(dev, smmu_pmu_free_msis, dev);
}

static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
{
	unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
	int irq, ret = -ENXIO;

	smmu_pmu_setup_msi(pmu);

	irq = pmu->irq;
	if (irq)
		ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
				       flags, "smmuv3-pmu", pmu);
	return ret;
}

static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
{
	u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);

	smmu_pmu_disable(&smmu_pmu->pmu);

	/* Disable counter and interrupt */
	writeq_relaxed(counter_present_mask,
		       smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
	writeq_relaxed(counter_present_mask,
		       smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
	writeq_relaxed(counter_present_mask,
		       smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
}

static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
{
	u32 model;

	model = *(u32 *)dev_get_platdata(smmu_pmu->dev);

	switch (model) {
	case IORT_SMMU_V3_PMCG_HISI_HIP08:
		/* HiSilicon Erratum 162001800 */
		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY | SMMU_PMCG_HARDEN_DISABLE;
		break;
	case IORT_SMMU_V3_PMCG_HISI_HIP09:
		smmu_pmu->options |= SMMU_PMCG_HARDEN_DISABLE;
		break;
	}

	dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
}

static int smmu_pmu_probe(struct platform_device *pdev)
{
	struct smmu_pmu *smmu_pmu;
	struct resource *res_0;
	u32 cfgr, reg_size;
	u64 ceid_64[2];
	int irq, err;
	char *name;
	struct device *dev = &pdev->dev;

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

	smmu_pmu->dev = dev;
	platform_set_drvdata(pdev, smmu_pmu);

	smmu_pmu->pmu = (struct pmu) {
		.module		= THIS_MODULE,
		.task_ctx_nr    = perf_invalid_context,
		.pmu_enable	= smmu_pmu_enable,
		.pmu_disable	= smmu_pmu_disable,
		.event_init	= smmu_pmu_event_init,
		.add		= smmu_pmu_event_add,
		.del		= smmu_pmu_event_del,
		.start		= smmu_pmu_event_start,
		.stop		= smmu_pmu_event_stop,
		.read		= smmu_pmu_event_read,
		.attr_groups	= smmu_pmu_attr_grps,
		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
	};

	smmu_pmu->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res_0);
	if (IS_ERR(smmu_pmu->reg_base))
		return PTR_ERR(smmu_pmu->reg_base);

	cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);

	/* Determine if page 1 is present */
	if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
		smmu_pmu->reloc_base = devm_platform_ioremap_resource(pdev, 1);
		if (IS_ERR(smmu_pmu->reloc_base))
			return PTR_ERR(smmu_pmu->reloc_base);
	} else {
		smmu_pmu->reloc_base = smmu_pmu->reg_base;
	}

	irq = platform_get_irq_optional(pdev, 0);
	if (irq > 0)
		smmu_pmu->irq = irq;

	ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
	ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
	bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
			  SMMU_PMCG_ARCH_MAX_EVENTS);

	smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;

	smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);

	reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
	smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);

	smmu_pmu_reset(smmu_pmu);

	err = smmu_pmu_setup_irq(smmu_pmu);
	if (err) {
		dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
		return err;
	}

	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
			      (res_0->start) >> SMMU_PMCG_PA_SHIFT);
	if (!name) {
		dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
		return -EINVAL;
	}

	smmu_pmu_get_acpi_options(smmu_pmu);

	/*
	 * For platforms suffer this quirk, the PMU disable sometimes fails to
	 * stop the counters. This will leads to inaccurate or error counting.
	 * Forcibly disable the counters with these quirk handler.
	 */
	if (smmu_pmu->options & SMMU_PMCG_HARDEN_DISABLE) {
		smmu_pmu->pmu.pmu_enable = smmu_pmu_enable_quirk_hip08_09;
		smmu_pmu->pmu.pmu_disable = smmu_pmu_disable_quirk_hip08_09;
	}

	/* Pick one CPU to be the preferred one to use */
	smmu_pmu->on_cpu = raw_smp_processor_id();
	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
				      cpumask_of(smmu_pmu->on_cpu)));

	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
					       &smmu_pmu->node);
	if (err) {
		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
			err, &res_0->start);
		goto out_clear_affinity;
	}

	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
	if (err) {
		dev_err(dev, "Error %d registering PMU @%pa\n",
			err, &res_0->start);
		goto out_unregister;
	}

	dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
		 &res_0->start, smmu_pmu->num_counters,
		 smmu_pmu->global_filter ? "Global(Counter0)" :
		 "Individual");

	return 0;

out_unregister:
	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
out_clear_affinity:
	irq_set_affinity_hint(smmu_pmu->irq, NULL);
	return err;
}

static int smmu_pmu_remove(struct platform_device *pdev)
{
	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);

	perf_pmu_unregister(&smmu_pmu->pmu);
	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
	irq_set_affinity_hint(smmu_pmu->irq, NULL);

	return 0;
}

static void smmu_pmu_shutdown(struct platform_device *pdev)
{
	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);

	smmu_pmu_disable(&smmu_pmu->pmu);
}

static struct platform_driver smmu_pmu_driver = {
	.driver = {
		.name = "arm-smmu-v3-pmcg",
		.suppress_bind_attrs = true,
	},
	.probe = smmu_pmu_probe,
	.remove = smmu_pmu_remove,
	.shutdown = smmu_pmu_shutdown,
};

static int __init arm_smmu_pmu_init(void)
{
	int ret;

	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
						  "perf/arm/pmcg:online",
						  NULL,
						  smmu_pmu_offline_cpu);
	if (cpuhp_state_num < 0)
		return cpuhp_state_num;

	ret = platform_driver_register(&smmu_pmu_driver);
	if (ret)
		cpuhp_remove_multi_state(cpuhp_state_num);

	return ret;
}
module_init(arm_smmu_pmu_init);

static void __exit arm_smmu_pmu_exit(void)
{
	platform_driver_unregister(&smmu_pmu_driver);
	cpuhp_remove_multi_state(cpuhp_state_num);
}

module_exit(arm_smmu_pmu_exit);

MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
MODULE_LICENSE("GPL v2");