aboutsummaryrefslogtreecommitdiffstats
path: root/arch/alpha/kernel/perf_event.c
blob: 56fa4159038164ce4e2fe5fdc53116073ade6001 (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
/*
 * Hardware performance events for the Alpha.
 *
 * We implement HW counts on the EV67 and subsequent CPUs only.
 *
 * (C) 2010 Michael J. Cree
 *
 * Somewhat based on the Sparc code, and to a lesser extent the PowerPC and
 * ARM code, which are copyright by their respective authors.
 */

#include <linux/perf_event.h>
#include <linux/kprobes.h>
#include <linux/kernel.h>
#include <linux/kdebug.h>
#include <linux/mutex.h>

#include <asm/hwrpb.h>
#include <asm/atomic.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/pal.h>
#include <asm/wrperfmon.h>
#include <asm/hw_irq.h>


/* The maximum number of PMCs on any Alpha CPU whatsoever. */
#define MAX_HWEVENTS 3
#define PMC_NO_INDEX -1

/* For tracking PMCs and the hw events they monitor on each CPU. */
struct cpu_hw_events {
	int			enabled;
	/* Number of events scheduled; also number entries valid in arrays below. */
	int			n_events;
	/* Number events added since last hw_perf_disable(). */
	int			n_added;
	/* Events currently scheduled. */
	struct perf_event	*event[MAX_HWEVENTS];
	/* Event type of each scheduled event. */
	unsigned long		evtype[MAX_HWEVENTS];
	/* Current index of each scheduled event; if not yet determined
	 * contains PMC_NO_INDEX.
	 */
	int			current_idx[MAX_HWEVENTS];
	/* The active PMCs' config for easy use with wrperfmon(). */
	unsigned long		config;
	/* The active counters' indices for easy use with wrperfmon(). */
	unsigned long		idx_mask;
};
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);



/*
 * A structure to hold the description of the PMCs available on a particular
 * type of Alpha CPU.
 */
struct alpha_pmu_t {
	/* Mapping of the perf system hw event types to indigenous event types */
	const int *event_map;
	/* The number of entries in the event_map */
	int  max_events;
	/* The number of PMCs on this Alpha */
	int  num_pmcs;
	/*
	 * All PMC counters reside in the IBOX register PCTR.  This is the
	 * LSB of the counter.
	 */
	int  pmc_count_shift[MAX_HWEVENTS];
	/*
	 * The mask that isolates the PMC bits when the LSB of the counter
	 * is shifted to bit 0.
	 */
	unsigned long pmc_count_mask[MAX_HWEVENTS];
	/* The maximum period the PMC can count. */
	unsigned long pmc_max_period[MAX_HWEVENTS];
	/*
	 * The maximum value that may be written to the counter due to
	 * hardware restrictions is pmc_max_period - pmc_left.
	 */
	long pmc_left[3];
	 /* Subroutine for allocation of PMCs.  Enforces constraints. */
	int (*check_constraints)(struct perf_event **, unsigned long *, int);
};

/*
 * The Alpha CPU PMU description currently in operation.  This is set during
 * the boot process to the specific CPU of the machine.
 */
static const struct alpha_pmu_t *alpha_pmu;


#define HW_OP_UNSUPPORTED -1

/*
 * The hardware description of the EV67, EV68, EV69, EV7 and EV79 PMUs
 * follow. Since they are identical we refer to them collectively as the
 * EV67 henceforth.
 */

/*
 * EV67 PMC event types
 *
 * There is no one-to-one mapping of the possible hw event types to the
 * actual codes that are used to program the PMCs hence we introduce our
 * own hw event type identifiers.
 */
enum ev67_pmc_event_type {
	EV67_CYCLES = 1,
	EV67_INSTRUCTIONS,
	EV67_BCACHEMISS,
	EV67_MBOXREPLAY,
	EV67_LAST_ET
};
#define EV67_NUM_EVENT_TYPES (EV67_LAST_ET-EV67_CYCLES)


/* Mapping of the hw event types to the perf tool interface */
static const int ev67_perfmon_event_map[] = {
	[PERF_COUNT_HW_CPU_CYCLES]	 = EV67_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]	 = EV67_INSTRUCTIONS,
	[PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_CACHE_MISSES]	 = EV67_BCACHEMISS,
};

struct ev67_mapping_t {
	int config;
	int idx;
};

/*
 * The mapping used for one event only - these must be in same order as enum
 * ev67_pmc_event_type definition.
 */
static const struct ev67_mapping_t ev67_mapping[] = {
	{EV67_PCTR_INSTR_CYCLES, 1},	 /* EV67_CYCLES, */
	{EV67_PCTR_INSTR_CYCLES, 0},	 /* EV67_INSTRUCTIONS */
	{EV67_PCTR_INSTR_BCACHEMISS, 1}, /* EV67_BCACHEMISS */
	{EV67_PCTR_CYCLES_MBOX, 1}	 /* EV67_MBOXREPLAY */
};


/*
 * Check that a group of events can be simultaneously scheduled on to the
 * EV67 PMU.  Also allocate counter indices and config.
 */
static int ev67_check_constraints(struct perf_event **event,
				unsigned long *evtype, int n_ev)
{
	int idx0;
	unsigned long config;

	idx0 = ev67_mapping[evtype[0]-1].idx;
	config = ev67_mapping[evtype[0]-1].config;
	if (n_ev == 1)
		goto success;

	BUG_ON(n_ev != 2);

	if (evtype[0] == EV67_MBOXREPLAY || evtype[1] == EV67_MBOXREPLAY) {
		/* MBOX replay traps must be on PMC 1 */
		idx0 = (evtype[0] == EV67_MBOXREPLAY) ? 1 : 0;
		/* Only cycles can accompany MBOX replay traps */
		if (evtype[idx0] == EV67_CYCLES) {
			config = EV67_PCTR_CYCLES_MBOX;
			goto success;
		}
	}

	if (evtype[0] == EV67_BCACHEMISS || evtype[1] == EV67_BCACHEMISS) {
		/* Bcache misses must be on PMC 1 */
		idx0 = (evtype[0] == EV67_BCACHEMISS) ? 1 : 0;
		/* Only instructions can accompany Bcache misses */
		if (evtype[idx0] == EV67_INSTRUCTIONS) {
			config = EV67_PCTR_INSTR_BCACHEMISS;
			goto success;
		}
	}

	if (evtype[0] == EV67_INSTRUCTIONS || evtype[1] == EV67_INSTRUCTIONS) {
		/* Instructions must be on PMC 0 */
		idx0 = (evtype[0] == EV67_INSTRUCTIONS) ? 0 : 1;
		/* By this point only cycles can accompany instructions */
		if (evtype[idx0^1] == EV67_CYCLES) {
			config = EV67_PCTR_INSTR_CYCLES;
			goto success;
		}
	}

	/* Otherwise, darn it, there is a conflict.  */
	return -1;

success:
	event[0]->hw.idx = idx0;
	event[0]->hw.config_base = config;
	if (n_ev == 2) {
		event[1]->hw.idx = idx0 ^ 1;
		event[1]->hw.config_base = config;
	}
	return 0;
}


static const struct alpha_pmu_t ev67_pmu = {
	.event_map = ev67_perfmon_event_map,
	.max_events = ARRAY_SIZE(ev67_perfmon_event_map),
	.num_pmcs = 2,
	.pmc_count_shift = {EV67_PCTR_0_COUNT_SHIFT, EV67_PCTR_1_COUNT_SHIFT, 0},
	.pmc_count_mask = {EV67_PCTR_0_COUNT_MASK,  EV67_PCTR_1_COUNT_MASK,  0},
	.pmc_max_period = {(1UL<<20) - 1, (1UL<<20) - 1, 0},
	.pmc_left = {16, 4, 0},
	.check_constraints = ev67_check_constraints
};



/*
 * Helper routines to ensure that we read/write only the correct PMC bits
 * when calling the wrperfmon PALcall.
 */
static inline void alpha_write_pmc(int idx, unsigned long val)
{
	val &= alpha_pmu->pmc_count_mask[idx];
	val <<= alpha_pmu->pmc_count_shift[idx];
	val |= (1<<idx);
	wrperfmon(PERFMON_CMD_WRITE, val);
}

static inline unsigned long alpha_read_pmc(int idx)
{
	unsigned long val;

	val = wrperfmon(PERFMON_CMD_READ, 0);
	val >>= alpha_pmu->pmc_count_shift[idx];
	val &= alpha_pmu->pmc_count_mask[idx];
	return val;
}

/* Set a new period to sample over */
static int alpha_perf_event_set_period(struct perf_event *event,
				struct hw_perf_event *hwc, int idx)
{
	long left = atomic64_read(&hwc->period_left);
	long period = hwc->sample_period;
	int ret = 0;

	if (unlikely(left <= -period)) {
		left = period;
		atomic64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (unlikely(left <= 0)) {
		left += period;
		atomic64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	/*
	 * Hardware restrictions require that the counters must not be
	 * written with values that are too close to the maximum period.
	 */
	if (unlikely(left < alpha_pmu->pmc_left[idx]))
		left = alpha_pmu->pmc_left[idx];

	if (left > (long)alpha_pmu->pmc_max_period[idx])
		left = alpha_pmu->pmc_max_period[idx];

	atomic64_set(&hwc->prev_count, (unsigned long)(-left));

	alpha_write_pmc(idx, (unsigned long)(-left));

	perf_event_update_userpage(event);

	return ret;
}


/*
 * Calculates the count (the 'delta') since the last time the PMC was read.
 *
 * As the PMCs' full period can easily be exceeded within the perf system
 * sampling period we cannot use any high order bits as a guard bit in the
 * PMCs to detect overflow as is done by other architectures.  The code here
 * calculates the delta on the basis that there is no overflow when ovf is
 * zero.  The value passed via ovf by the interrupt handler corrects for
 * overflow.
 *
 * This can be racey on rare occasions -- a call to this routine can occur
 * with an overflowed counter just before the PMI service routine is called.
 * The check for delta negative hopefully always rectifies this situation.
 */
static unsigned long alpha_perf_event_update(struct perf_event *event,
					struct hw_perf_event *hwc, int idx, long ovf)
{
	long prev_raw_count, new_raw_count;
	long delta;

again:
	prev_raw_count = atomic64_read(&hwc->prev_count);
	new_raw_count = alpha_read_pmc(idx);

	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
			     new_raw_count) != prev_raw_count)
		goto again;

	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;

	/* It is possible on very rare occasions that the PMC has overflowed
	 * but the interrupt is yet to come.  Detect and fix this situation.
	 */
	if (unlikely(delta < 0)) {
		delta += alpha_pmu->pmc_max_period[idx] + 1;
	}

	atomic64_add(delta, &event->count);
	atomic64_sub(delta, &hwc->period_left);

	return new_raw_count;
}


/*
 * Collect all HW events into the array event[].
 */
static int collect_events(struct perf_event *group, int max_count,
			  struct perf_event *event[], unsigned long *evtype,
			  int *current_idx)
{
	struct perf_event *pe;
	int n = 0;

	if (!is_software_event(group)) {
		if (n >= max_count)
			return -1;
		event[n] = group;
		evtype[n] = group->hw.event_base;
		current_idx[n++] = PMC_NO_INDEX;
	}
	list_for_each_entry(pe, &group->sibling_list, group_entry) {
		if (!is_software_event(pe) && pe->state != PERF_EVENT_STATE_OFF) {
			if (n >= max_count)
				return -1;
			event[n] = pe;
			evtype[n] = pe->hw.event_base;
			current_idx[n++] = PMC_NO_INDEX;
		}
	}
	return n;
}



/*
 * Check that a group of events can be simultaneously scheduled on to the PMU.
 */
static int alpha_check_constraints(struct perf_event **events,
				   unsigned long *evtypes, int n_ev)
{

	/* No HW events is possible from hw_perf_group_sched_in(). */
	if (n_ev == 0)
		return 0;

	if (n_ev > alpha_pmu->num_pmcs)
		return -1;

	return alpha_pmu->check_constraints(events, evtypes, n_ev);
}


/*
 * If new events have been scheduled then update cpuc with the new
 * configuration.  This may involve shifting cycle counts from one PMC to
 * another.
 */
static void maybe_change_configuration(struct cpu_hw_events *cpuc)
{
	int j;

	if (cpuc->n_added == 0)
		return;

	/* Find counters that are moving to another PMC and update */
	for (j = 0; j < cpuc->n_events; j++) {
		struct perf_event *pe = cpuc->event[j];

		if (cpuc->current_idx[j] != PMC_NO_INDEX &&
			cpuc->current_idx[j] != pe->hw.idx) {
			alpha_perf_event_update(pe, &pe->hw, cpuc->current_idx[j], 0);
			cpuc->current_idx[j] = PMC_NO_INDEX;
		}
	}

	/* Assign to counters all unassigned events. */
	cpuc->idx_mask = 0;
	for (j = 0; j < cpuc->n_events; j++) {
		struct perf_event *pe = cpuc->event[j];
		struct hw_perf_event *hwc = &pe->hw;
		int idx = hwc->idx;

		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
			continue;
		}

		alpha_perf_event_set_period(pe, hwc, idx);
		cpuc->current_idx[j] = idx;
		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
	}
	cpuc->config = cpuc->event[0]->hw.config_base;
}



/* Schedule perf HW event on to PMU.
 *  - this function is called from outside this module via the pmu struct
 *    returned from perf event initialisation.
 */
static int alpha_pmu_enable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int n0;
	int ret;
	unsigned long flags;

	/*
	 * The Sparc code has the IRQ disable first followed by the perf
	 * disable, however this can lead to an overflowed counter with the
	 * PMI disabled on rare occasions.  The alpha_perf_event_update()
	 * routine should detect this situation by noting a negative delta,
	 * nevertheless we disable the PMCs first to enable a potential
	 * final PMI to occur before we disable interrupts.
	 */
	perf_disable();
	local_irq_save(flags);

	/* Default to error to be returned */
	ret = -EAGAIN;

	/* Insert event on to PMU and if successful modify ret to valid return */
	n0 = cpuc->n_events;
	if (n0 < alpha_pmu->num_pmcs) {
		cpuc->event[n0] = event;
		cpuc->evtype[n0] = event->hw.event_base;
		cpuc->current_idx[n0] = PMC_NO_INDEX;

		if (!alpha_check_constraints(cpuc->event, cpuc->evtype, n0+1)) {
			cpuc->n_events++;
			cpuc->n_added++;
			ret = 0;
		}
	}

	local_irq_restore(flags);
	perf_enable();

	return ret;
}



/* Disable performance monitoring unit
 *  - this function is called from outside this module via the pmu struct
 *    returned from perf event initialisation.
 */
static void alpha_pmu_disable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	unsigned long flags;
	int j;

	perf_disable();
	local_irq_save(flags);

	for (j = 0; j < cpuc->n_events; j++) {
		if (event == cpuc->event[j]) {
			int idx = cpuc->current_idx[j];

			/* Shift remaining entries down into the existing
			 * slot.
			 */
			while (++j < cpuc->n_events) {
				cpuc->event[j - 1] = cpuc->event[j];
				cpuc->evtype[j - 1] = cpuc->evtype[j];
				cpuc->current_idx[j - 1] =
					cpuc->current_idx[j];
			}

			/* Absorb the final count and turn off the event. */
			alpha_perf_event_update(event, hwc, idx, 0);
			perf_event_update_userpage(event);

			cpuc->idx_mask &= ~(1UL<<idx);
			cpuc->n_events--;
			break;
		}
	}

	local_irq_restore(flags);
	perf_enable();
}


static void alpha_pmu_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	alpha_perf_event_update(event, hwc, hwc->idx, 0);
}


static void alpha_pmu_unthrottle(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	cpuc->idx_mask |= 1UL<<hwc->idx;
	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
}


/*
 * Check that CPU performance counters are supported.
 * - currently support EV67 and later CPUs.
 * - actually some later revisions of the EV6 have the same PMC model as the
 *     EV67 but we don't do suffiently deep CPU detection to detect them.
 *     Bad luck to the very few people who might have one, I guess.
 */
static int supported_cpu(void)
{
	struct percpu_struct *cpu;
	unsigned long cputype;

	/* Get cpu type from HW */
	cpu = (struct percpu_struct *)((char *)hwrpb + hwrpb->processor_offset);
	cputype = cpu->type & 0xffffffff;
	/* Include all of EV67, EV68, EV7, EV79 and EV69 as supported. */
	return (cputype >= EV67_CPU) && (cputype <= EV69_CPU);
}



static void hw_perf_event_destroy(struct perf_event *event)
{
	/* Nothing to be done! */
	return;
}



static int __hw_perf_event_init(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	struct hw_perf_event *hwc = &event->hw;
	struct perf_event *evts[MAX_HWEVENTS];
	unsigned long evtypes[MAX_HWEVENTS];
	int idx_rubbish_bin[MAX_HWEVENTS];
	int ev;
	int n;

	/* We only support a limited range of HARDWARE event types with one
	 * only programmable via a RAW event type.
	 */
	if (attr->type == PERF_TYPE_HARDWARE) {
		if (attr->config >= alpha_pmu->max_events)
			return -EINVAL;
		ev = alpha_pmu->event_map[attr->config];
	} else if (attr->type == PERF_TYPE_HW_CACHE) {
		return -EOPNOTSUPP;
	} else if (attr->type == PERF_TYPE_RAW) {
		ev = attr->config & 0xff;
	} else {
		return -EOPNOTSUPP;
	}

	if (ev < 0) {
		return ev;
	}

	/* The EV67 does not support mode exclusion */
	if (attr->exclude_kernel || attr->exclude_user
			|| attr->exclude_hv || attr->exclude_idle) {
		return -EPERM;
	}

	/*
	 * We place the event type in event_base here and leave calculation
	 * of the codes to programme the PMU for alpha_pmu_enable() because
	 * it is only then we will know what HW events are actually
	 * scheduled on to the PMU.  At that point the code to programme the
	 * PMU is put into config_base and the PMC to use is placed into
	 * idx.  We initialise idx (below) to PMC_NO_INDEX to indicate that
	 * it is yet to be determined.
	 */
	hwc->event_base = ev;

	/* Collect events in a group together suitable for calling
	 * alpha_check_constraints() to verify that the group as a whole can
	 * be scheduled on to the PMU.
	 */
	n = 0;
	if (event->group_leader != event) {
		n = collect_events(event->group_leader,
				alpha_pmu->num_pmcs - 1,
				evts, evtypes, idx_rubbish_bin);
		if (n < 0)
			return -EINVAL;
	}
	evtypes[n] = hwc->event_base;
	evts[n] = event;

	if (alpha_check_constraints(evts, evtypes, n + 1))
		return -EINVAL;

	/* Indicate that PMU config and idx are yet to be determined. */
	hwc->config_base = 0;
	hwc->idx = PMC_NO_INDEX;

	event->destroy = hw_perf_event_destroy;

	/*
	 * Most architectures reserve the PMU for their use at this point.
	 * As there is no existing mechanism to arbitrate usage and there
	 * appears to be no other user of the Alpha PMU we just assume
	 * that we can just use it, hence a NO-OP here.
	 *
	 * Maybe an alpha_reserve_pmu() routine should be implemented but is
	 * anything else ever going to use it?
	 */

	if (!hwc->sample_period) {
		hwc->sample_period = alpha_pmu->pmc_max_period[0];
		hwc->last_period = hwc->sample_period;
		atomic64_set(&hwc->period_left, hwc->sample_period);
	}

	return 0;
}

static struct pmu pmu = {
	.enable		= alpha_pmu_enable,
	.disable	= alpha_pmu_disable,
	.read		= alpha_pmu_read,
	.unthrottle	= alpha_pmu_unthrottle,
};


/*
 * Main entry point to initialise a HW performance event.
 */
struct pmu *hw_perf_event_init(struct perf_event *event)
{
	int err;

	if (!alpha_pmu)
		return ERR_PTR(-ENODEV);

	/* Do the real initialisation work. */
	err = __hw_perf_event_init(event);

	if (err)
		return ERR_PTR(err);

	return &pmu;
}



/*
 * Main entry point - enable HW performance counters.
 */
void hw_perf_enable(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	if (cpuc->enabled)
		return;

	cpuc->enabled = 1;
	barrier();

	if (cpuc->n_events > 0) {
		/* Update cpuc with information from any new scheduled events. */
		maybe_change_configuration(cpuc);

		/* Start counting the desired events. */
		wrperfmon(PERFMON_CMD_LOGGING_OPTIONS, EV67_PCTR_MODE_AGGREGATE);
		wrperfmon(PERFMON_CMD_DESIRED_EVENTS, cpuc->config);
		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
	}
}


/*
 * Main entry point - disable HW performance counters.
 */

void hw_perf_disable(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	if (!cpuc->enabled)
		return;

	cpuc->enabled = 0;
	cpuc->n_added = 0;

	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
}


/*
 * Main entry point - don't know when this is called but it
 * obviously dumps debug info.
 */
void perf_event_print_debug(void)
{
	unsigned long flags;
	unsigned long pcr;
	int pcr0, pcr1;
	int cpu;

	if (!supported_cpu())
		return;

	local_irq_save(flags);

	cpu = smp_processor_id();

	pcr = wrperfmon(PERFMON_CMD_READ, 0);
	pcr0 = (pcr >> alpha_pmu->pmc_count_shift[0]) & alpha_pmu->pmc_count_mask[0];
	pcr1 = (pcr >> alpha_pmu->pmc_count_shift[1]) & alpha_pmu->pmc_count_mask[1];

	pr_info("CPU#%d: PCTR0[%06x] PCTR1[%06x]\n", cpu, pcr0, pcr1);

	local_irq_restore(flags);
}


/*
 * Performance Monitoring Interrupt Service Routine called when a PMC
 * overflows.  The PMC that overflowed is passed in la_ptr.
 */
static void alpha_perf_event_irq_handler(unsigned long la_ptr,
					struct pt_regs *regs)
{
	struct cpu_hw_events *cpuc;
	struct perf_sample_data data;
	struct perf_event *event;
	struct hw_perf_event *hwc;
	int idx, j;

	__get_cpu_var(irq_pmi_count)++;
	cpuc = &__get_cpu_var(cpu_hw_events);

	/* Completely counting through the PMC's period to trigger a new PMC
	 * overflow interrupt while in this interrupt routine is utterly
	 * disastrous!  The EV6 and EV67 counters are sufficiently large to
	 * prevent this but to be really sure disable the PMCs.
	 */
	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);

	/* la_ptr is the counter that overflowed. */
	if (unlikely(la_ptr >= perf_max_events)) {
		/* This should never occur! */
		irq_err_count++;
		pr_warning("PMI: silly index %ld\n", la_ptr);
		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
		return;
	}

	idx = la_ptr;

	perf_sample_data_init(&data, 0);
	for (j = 0; j < cpuc->n_events; j++) {
		if (cpuc->current_idx[j] == idx)
			break;
	}

	if (unlikely(j == cpuc->n_events)) {
		/* This can occur if the event is disabled right on a PMC overflow. */
		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
		return;
	}

	event = cpuc->event[j];

	if (unlikely(!event)) {
		/* This should never occur! */
		irq_err_count++;
		pr_warning("PMI: No event at index %d!\n", idx);
		wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
		return;
	}

	hwc = &event->hw;
	alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1);
	data.period = event->hw.last_period;

	if (alpha_perf_event_set_period(event, hwc, idx)) {
		if (perf_event_overflow(event, 1, &data, regs)) {
			/* Interrupts coming too quickly; "throttle" the
			 * counter, i.e., disable it for a little while.
			 */
			cpuc->idx_mask &= ~(1UL<<idx);
		}
	}
	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);

	return;
}



/*
 * Init call to initialise performance events at kernel startup.
 */
void __init init_hw_perf_events(void)
{
	pr_info("Performance events: ");

	if (!supported_cpu()) {
		pr_cont("No support for your CPU.\n");
		return;
	}

	pr_cont("Supported CPU type!\n");

	/* Override performance counter IRQ vector */

	perf_irq = alpha_perf_event_irq_handler;

	/* And set up PMU specification */
	alpha_pmu = &ev67_pmu;
	perf_max_events = alpha_pmu->num_pmcs;
}