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
|
/*
* Performance event support - Freescale Embedded Performance Monitor
*
* Copyright 2008-2009 Paul Mackerras, IBM Corporation.
* Copyright 2010 Freescale Semiconductor, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/perf_event.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <asm/reg_fsl_emb.h>
#include <asm/pmc.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/ptrace.h>
struct cpu_hw_events {
int n_events;
int disabled;
u8 pmcs_enabled;
struct perf_event *event[MAX_HWEVENTS];
};
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
static struct fsl_emb_pmu *ppmu;
/* Number of perf_events counting hardware events */
static atomic_t num_events;
/* Used to avoid races in calling reserve/release_pmc_hardware */
static DEFINE_MUTEX(pmc_reserve_mutex);
/*
* If interrupts were soft-disabled when a PMU interrupt occurs, treat
* it as an NMI.
*/
static inline int perf_intr_is_nmi(struct pt_regs *regs)
{
#ifdef __powerpc64__
return !regs->softe;
#else
return 0;
#endif
}
static void perf_event_interrupt(struct pt_regs *regs);
/*
* Read one performance monitor counter (PMC).
*/
static unsigned long read_pmc(int idx)
{
unsigned long val;
switch (idx) {
case 0:
val = mfpmr(PMRN_PMC0);
break;
case 1:
val = mfpmr(PMRN_PMC1);
break;
case 2:
val = mfpmr(PMRN_PMC2);
break;
case 3:
val = mfpmr(PMRN_PMC3);
break;
default:
printk(KERN_ERR "oops trying to read PMC%d\n", idx);
val = 0;
}
return val;
}
/*
* Write one PMC.
*/
static void write_pmc(int idx, unsigned long val)
{
switch (idx) {
case 0:
mtpmr(PMRN_PMC0, val);
break;
case 1:
mtpmr(PMRN_PMC1, val);
break;
case 2:
mtpmr(PMRN_PMC2, val);
break;
case 3:
mtpmr(PMRN_PMC3, val);
break;
default:
printk(KERN_ERR "oops trying to write PMC%d\n", idx);
}
isync();
}
/*
* Write one local control A register
*/
static void write_pmlca(int idx, unsigned long val)
{
switch (idx) {
case 0:
mtpmr(PMRN_PMLCA0, val);
break;
case 1:
mtpmr(PMRN_PMLCA1, val);
break;
case 2:
mtpmr(PMRN_PMLCA2, val);
break;
case 3:
mtpmr(PMRN_PMLCA3, val);
break;
default:
printk(KERN_ERR "oops trying to write PMLCA%d\n", idx);
}
isync();
}
/*
* Write one local control B register
*/
static void write_pmlcb(int idx, unsigned long val)
{
switch (idx) {
case 0:
mtpmr(PMRN_PMLCB0, val);
break;
case 1:
mtpmr(PMRN_PMLCB1, val);
break;
case 2:
mtpmr(PMRN_PMLCB2, val);
break;
case 3:
mtpmr(PMRN_PMLCB3, val);
break;
default:
printk(KERN_ERR "oops trying to write PMLCB%d\n", idx);
}
isync();
}
static void fsl_emb_pmu_read(struct perf_event *event)
{
s64 val, delta, prev;
/*
* Performance monitor interrupts come even when interrupts
* are soft-disabled, as long as interrupts are hard-enabled.
* Therefore we treat them like NMIs.
*/
do {
prev = local64_read(&event->hw.prev_count);
barrier();
val = read_pmc(event->hw.idx);
} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
/* The counters are only 32 bits wide */
delta = (val - prev) & 0xfffffffful;
local64_add(delta, &event->count);
local64_sub(delta, &event->hw.period_left);
}
/*
* Disable all events to prevent PMU interrupts and to allow
* events to be added or removed.
*/
void hw_perf_disable(void)
{
struct cpu_hw_events *cpuhw;
unsigned long flags;
local_irq_save(flags);
cpuhw = &__get_cpu_var(cpu_hw_events);
if (!cpuhw->disabled) {
cpuhw->disabled = 1;
/*
* Check if we ever enabled the PMU on this cpu.
*/
if (!cpuhw->pmcs_enabled) {
ppc_enable_pmcs();
cpuhw->pmcs_enabled = 1;
}
if (atomic_read(&num_events)) {
/*
* Set the 'freeze all counters' bit, and disable
* interrupts. The barrier is to make sure the
* mtpmr has been executed and the PMU has frozen
* the events before we return.
*/
mtpmr(PMRN_PMGC0, PMGC0_FAC);
isync();
}
}
local_irq_restore(flags);
}
/*
* Re-enable all events if disable == 0.
* If we were previously disabled and events were added, then
* put the new config on the PMU.
*/
void hw_perf_enable(void)
{
struct cpu_hw_events *cpuhw;
unsigned long flags;
local_irq_save(flags);
cpuhw = &__get_cpu_var(cpu_hw_events);
if (!cpuhw->disabled)
goto out;
cpuhw->disabled = 0;
ppc_set_pmu_inuse(cpuhw->n_events != 0);
if (cpuhw->n_events > 0) {
mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
isync();
}
out:
local_irq_restore(flags);
}
static int collect_events(struct perf_event *group, int max_count,
struct perf_event *ctrs[])
{
int n = 0;
struct perf_event *event;
if (!is_software_event(group)) {
if (n >= max_count)
return -1;
ctrs[n] = group;
n++;
}
list_for_each_entry(event, &group->sibling_list, group_entry) {
if (!is_software_event(event) &&
event->state != PERF_EVENT_STATE_OFF) {
if (n >= max_count)
return -1;
ctrs[n] = event;
n++;
}
}
return n;
}
/* perf must be disabled, context locked on entry */
static int fsl_emb_pmu_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuhw;
int ret = -EAGAIN;
int num_counters = ppmu->n_counter;
u64 val;
int i;
cpuhw = &get_cpu_var(cpu_hw_events);
if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
num_counters = ppmu->n_restricted;
/*
* Allocate counters from top-down, so that restricted-capable
* counters are kept free as long as possible.
*/
for (i = num_counters - 1; i >= 0; i--) {
if (cpuhw->event[i])
continue;
break;
}
if (i < 0)
goto out;
event->hw.idx = i;
cpuhw->event[i] = event;
++cpuhw->n_events;
val = 0;
if (event->hw.sample_period) {
s64 left = local64_read(&event->hw.period_left);
if (left < 0x80000000L)
val = 0x80000000L - left;
}
local64_set(&event->hw.prev_count, val);
write_pmc(i, val);
perf_event_update_userpage(event);
write_pmlcb(i, event->hw.config >> 32);
write_pmlca(i, event->hw.config_base);
ret = 0;
out:
put_cpu_var(cpu_hw_events);
return ret;
}
/* perf must be disabled, context locked on entry */
static void fsl_emb_pmu_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuhw;
int i = event->hw.idx;
if (i < 0)
goto out;
fsl_emb_pmu_read(event);
cpuhw = &get_cpu_var(cpu_hw_events);
WARN_ON(event != cpuhw->event[event->hw.idx]);
write_pmlca(i, 0);
write_pmlcb(i, 0);
write_pmc(i, 0);
cpuhw->event[i] = NULL;
event->hw.idx = -1;
/*
* TODO: if at least one restricted event exists, and we
* just freed up a non-restricted-capable counter, and
* there is a restricted-capable counter occupied by
* a non-restricted event, migrate that event to the
* vacated counter.
*/
cpuhw->n_events--;
out:
put_cpu_var(cpu_hw_events);
}
/*
* Re-enable interrupts on a event after they were throttled
* because they were coming too fast.
*
* Context is locked on entry, but perf is not disabled.
*/
static void fsl_emb_pmu_unthrottle(struct perf_event *event)
{
s64 val, left;
unsigned long flags;
if (event->hw.idx < 0 || !event->hw.sample_period)
return;
local_irq_save(flags);
perf_disable();
fsl_emb_pmu_read(event);
left = event->hw.sample_period;
event->hw.last_period = left;
val = 0;
if (left < 0x80000000L)
val = 0x80000000L - left;
write_pmc(event->hw.idx, val);
local64_set(&event->hw.prev_count, val);
local64_set(&event->hw.period_left, left);
perf_event_update_userpage(event);
perf_enable();
local_irq_restore(flags);
}
/*
* Release the PMU if this is the last perf_event.
*/
static void hw_perf_event_destroy(struct perf_event *event)
{
if (!atomic_add_unless(&num_events, -1, 1)) {
mutex_lock(&pmc_reserve_mutex);
if (atomic_dec_return(&num_events) == 0)
release_pmc_hardware();
mutex_unlock(&pmc_reserve_mutex);
}
}
/*
* Translate a generic cache event_id config to a raw event_id code.
*/
static int hw_perf_cache_event(u64 config, u64 *eventp)
{
unsigned long type, op, result;
int ev;
if (!ppmu->cache_events)
return -EINVAL;
/* unpack config */
type = config & 0xff;
op = (config >> 8) & 0xff;
result = (config >> 16) & 0xff;
if (type >= PERF_COUNT_HW_CACHE_MAX ||
op >= PERF_COUNT_HW_CACHE_OP_MAX ||
result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
return -EINVAL;
ev = (*ppmu->cache_events)[type][op][result];
if (ev == 0)
return -EOPNOTSUPP;
if (ev == -1)
return -EINVAL;
*eventp = ev;
return 0;
}
static int fsl_emb_pmu_event_init(struct perf_event *event)
{
u64 ev;
struct perf_event *events[MAX_HWEVENTS];
int n;
int err;
int num_restricted;
int i;
switch (event->attr.type) {
case PERF_TYPE_HARDWARE:
ev = event->attr.config;
if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
return -EOPNOTSUPP;
ev = ppmu->generic_events[ev];
break;
case PERF_TYPE_HW_CACHE:
err = hw_perf_cache_event(event->attr.config, &ev);
if (err)
return err;
break;
case PERF_TYPE_RAW:
ev = event->attr.config;
break;
default:
return -ENOENT;
}
event->hw.config = ppmu->xlate_event(ev);
if (!(event->hw.config & FSL_EMB_EVENT_VALID))
return -EINVAL;
/*
* If this is in a group, check if it can go on with all the
* other hardware events in the group. We assume the event
* hasn't been linked into its leader's sibling list at this point.
*/
n = 0;
if (event->group_leader != event) {
n = collect_events(event->group_leader,
ppmu->n_counter - 1, events);
if (n < 0)
return -EINVAL;
}
if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
num_restricted = 0;
for (i = 0; i < n; i++) {
if (events[i]->hw.config & FSL_EMB_EVENT_RESTRICTED)
num_restricted++;
}
if (num_restricted >= ppmu->n_restricted)
return -EINVAL;
}
event->hw.idx = -1;
event->hw.config_base = PMLCA_CE | PMLCA_FCM1 |
(u32)((ev << 16) & PMLCA_EVENT_MASK);
if (event->attr.exclude_user)
event->hw.config_base |= PMLCA_FCU;
if (event->attr.exclude_kernel)
event->hw.config_base |= PMLCA_FCS;
if (event->attr.exclude_idle)
return -ENOTSUPP;
event->hw.last_period = event->hw.sample_period;
local64_set(&event->hw.period_left, event->hw.last_period);
/*
* See if we need to reserve the PMU.
* If no events are currently in use, then we have to take a
* mutex to ensure that we don't race with another task doing
* reserve_pmc_hardware or release_pmc_hardware.
*/
err = 0;
if (!atomic_inc_not_zero(&num_events)) {
mutex_lock(&pmc_reserve_mutex);
if (atomic_read(&num_events) == 0 &&
reserve_pmc_hardware(perf_event_interrupt))
err = -EBUSY;
else
atomic_inc(&num_events);
mutex_unlock(&pmc_reserve_mutex);
mtpmr(PMRN_PMGC0, PMGC0_FAC);
isync();
}
event->destroy = hw_perf_event_destroy;
return err;
}
static struct pmu fsl_emb_pmu = {
.event_init = fsl_emb_pmu_event_init,
.enable = fsl_emb_pmu_enable,
.disable = fsl_emb_pmu_disable,
.read = fsl_emb_pmu_read,
.unthrottle = fsl_emb_pmu_unthrottle,
};
/*
* A counter has overflowed; update its count and record
* things if requested. Note that interrupts are hard-disabled
* here so there is no possibility of being interrupted.
*/
static void record_and_restart(struct perf_event *event, unsigned long val,
struct pt_regs *regs, int nmi)
{
u64 period = event->hw.sample_period;
s64 prev, delta, left;
int record = 0;
/* we don't have to worry about interrupts here */
prev = local64_read(&event->hw.prev_count);
delta = (val - prev) & 0xfffffffful;
local64_add(delta, &event->count);
/*
* See if the total period for this event has expired,
* and update for the next period.
*/
val = 0;
left = local64_read(&event->hw.period_left) - delta;
if (period) {
if (left <= 0) {
left += period;
if (left <= 0)
left = period;
record = 1;
}
if (left < 0x80000000LL)
val = 0x80000000LL - left;
}
/*
* Finally record data if requested.
*/
if (record) {
struct perf_sample_data data;
perf_sample_data_init(&data, 0);
data.period = event->hw.last_period;
if (perf_event_overflow(event, nmi, &data, regs)) {
/*
* Interrupts are coming too fast - throttle them
* by setting the event to 0, so it will be
* at least 2^30 cycles until the next interrupt
* (assuming each event counts at most 2 counts
* per cycle).
*/
val = 0;
left = ~0ULL >> 1;
}
}
write_pmc(event->hw.idx, val);
local64_set(&event->hw.prev_count, val);
local64_set(&event->hw.period_left, left);
perf_event_update_userpage(event);
}
static void perf_event_interrupt(struct pt_regs *regs)
{
int i;
struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
struct perf_event *event;
unsigned long val;
int found = 0;
int nmi;
nmi = perf_intr_is_nmi(regs);
if (nmi)
nmi_enter();
else
irq_enter();
for (i = 0; i < ppmu->n_counter; ++i) {
event = cpuhw->event[i];
val = read_pmc(i);
if ((int)val < 0) {
if (event) {
/* event has overflowed */
found = 1;
record_and_restart(event, val, regs, nmi);
} else {
/*
* Disabled counter is negative,
* reset it just in case.
*/
write_pmc(i, 0);
}
}
}
/* PMM will keep counters frozen until we return from the interrupt. */
mtmsr(mfmsr() | MSR_PMM);
mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
isync();
if (nmi)
nmi_exit();
else
irq_exit();
}
void hw_perf_event_setup(int cpu)
{
struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
memset(cpuhw, 0, sizeof(*cpuhw));
}
int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
{
if (ppmu)
return -EBUSY; /* something's already registered */
ppmu = pmu;
pr_info("%s performance monitor hardware support registered\n",
pmu->name);
perf_pmu_register(&fsl_emb_pmu);
return 0;
}
|