summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/perf/isa207-common.c
blob: e79fb5fb817dbe21cd19f633d89ca3bbbf51ad0c (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
/*
 * Common Performance counter support functions for PowerISA v2.07 processors.
 *
 * Copyright 2009 Paul Mackerras, IBM Corporation.
 * Copyright 2013 Michael Ellerman, IBM Corporation.
 * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
 *
 * 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 "isa207-common.h"

PMU_FORMAT_ATTR(event,		"config:0-49");
PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
PMU_FORMAT_ATTR(mark,		"config:8");
PMU_FORMAT_ATTR(combine,	"config:11");
PMU_FORMAT_ATTR(unit,		"config:12-15");
PMU_FORMAT_ATTR(pmc,		"config:16-19");
PMU_FORMAT_ATTR(cache_sel,	"config:20-23");
PMU_FORMAT_ATTR(sample_mode,	"config:24-28");
PMU_FORMAT_ATTR(thresh_sel,	"config:29-31");
PMU_FORMAT_ATTR(thresh_stop,	"config:32-35");
PMU_FORMAT_ATTR(thresh_start,	"config:36-39");
PMU_FORMAT_ATTR(thresh_cmp,	"config:40-49");

struct attribute *isa207_pmu_format_attr[] = {
	&format_attr_event.attr,
	&format_attr_pmcxsel.attr,
	&format_attr_mark.attr,
	&format_attr_combine.attr,
	&format_attr_unit.attr,
	&format_attr_pmc.attr,
	&format_attr_cache_sel.attr,
	&format_attr_sample_mode.attr,
	&format_attr_thresh_sel.attr,
	&format_attr_thresh_stop.attr,
	&format_attr_thresh_start.attr,
	&format_attr_thresh_cmp.attr,
	NULL,
};

struct attribute_group isa207_pmu_format_group = {
	.name = "format",
	.attrs = isa207_pmu_format_attr,
};

static inline bool event_is_fab_match(u64 event)
{
	/* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */
	event &= 0xff0fe;

	/* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */
	return (event == 0x30056 || event == 0x4f052);
}

static bool is_event_valid(u64 event)
{
	u64 valid_mask = EVENT_VALID_MASK;

	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
		valid_mask = p9_EVENT_VALID_MASK;

	return !(event & ~valid_mask);
}

static u64 mmcra_sdar_mode(u64 event)
{
	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
		return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;

	return MMCRA_SDAR_MODE_TLB;
}

static u64 thresh_cmp_val(u64 value)
{
	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
		return value << p9_MMCRA_THR_CMP_SHIFT;

	return value << MMCRA_THR_CMP_SHIFT;
}

static unsigned long combine_from_event(u64 event)
{
	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
		return p9_EVENT_COMBINE(event);

	return EVENT_COMBINE(event);
}

static unsigned long combine_shift(unsigned long pmc)
{
	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
		return p9_MMCR1_COMBINE_SHIFT(pmc);

	return MMCR1_COMBINE_SHIFT(pmc);
}

static inline bool event_is_threshold(u64 event)
{
	return (event >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
}

static bool is_thresh_cmp_valid(u64 event)
{
	unsigned int cmp, exp;

	/*
	 * Check the mantissa upper two bits are not zero, unless the
	 * exponent is also zero. See the THRESH_CMP_MANTISSA doc.
	 */
	cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
	exp = cmp >> 7;

	if (exp && (cmp & 0x60) == 0)
		return false;

	return true;
}

int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
{
	unsigned int unit, pmc, cache, ebb;
	unsigned long mask, value;

	mask = value = 0;

	if (!is_event_valid(event))
		return -1;

	pmc   = (event >> EVENT_PMC_SHIFT)        & EVENT_PMC_MASK;
	unit  = (event >> EVENT_UNIT_SHIFT)       & EVENT_UNIT_MASK;
	cache = (event >> EVENT_CACHE_SEL_SHIFT)  & EVENT_CACHE_SEL_MASK;
	ebb   = (event >> EVENT_EBB_SHIFT)        & EVENT_EBB_MASK;

	if (pmc) {
		u64 base_event;

		if (pmc > 6)
			return -1;

		/* Ignore Linux defined bits when checking event below */
		base_event = event & ~EVENT_LINUX_MASK;

		if (pmc >= 5 && base_event != 0x500fa &&
				base_event != 0x600f4)
			return -1;

		mask  |= CNST_PMC_MASK(pmc);
		value |= CNST_PMC_VAL(pmc);
	}

	if (pmc <= 4) {
		/*
		 * Add to number of counters in use. Note this includes events with
		 * a PMC of 0 - they still need a PMC, it's just assigned later.
		 * Don't count events on PMC 5 & 6, there is only one valid event
		 * on each of those counters, and they are handled above.
		 */
		mask  |= CNST_NC_MASK;
		value |= CNST_NC_VAL;
	}

	if (unit >= 6 && unit <= 9) {
		/*
		 * L2/L3 events contain a cache selector field, which is
		 * supposed to be programmed into MMCRC. However MMCRC is only
		 * HV writable, and there is no API for guest kernels to modify
		 * it. The solution is for the hypervisor to initialise the
		 * field to zeroes, and for us to only ever allow events that
		 * have a cache selector of zero. The bank selector (bit 3) is
		 * irrelevant, as long as the rest of the value is 0.
		 */
		if (cache & 0x7)
			return -1;

	} else if (event & EVENT_IS_L1) {
		mask  |= CNST_L1_QUAL_MASK;
		value |= CNST_L1_QUAL_VAL(cache);
	}

	if (event & EVENT_IS_MARKED) {
		mask  |= CNST_SAMPLE_MASK;
		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
	}

	if (cpu_has_feature(CPU_FTR_ARCH_300))  {
		if (event_is_threshold(event) && is_thresh_cmp_valid(event)) {
			mask  |= CNST_THRESH_MASK;
			value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
		}
	} else {
		/*
		 * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
		 * the threshold control bits are used for the match value.
		 */
		if (event_is_fab_match(event)) {
			mask  |= CNST_FAB_MATCH_MASK;
			value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT);
		} else {
			if (!is_thresh_cmp_valid(event))
				return -1;

			mask  |= CNST_THRESH_MASK;
			value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
		}
	}

	if (!pmc && ebb)
		/* EBB events must specify the PMC */
		return -1;

	if (event & EVENT_WANTS_BHRB) {
		if (!ebb)
			/* Only EBB events can request BHRB */
			return -1;

		mask  |= CNST_IFM_MASK;
		value |= CNST_IFM_VAL(event >> EVENT_IFM_SHIFT);
	}

	/*
	 * All events must agree on EBB, either all request it or none.
	 * EBB events are pinned & exclusive, so this should never actually
	 * hit, but we leave it as a fallback in case.
	 */
	mask  |= CNST_EBB_VAL(ebb);
	value |= CNST_EBB_MASK;

	*maskp = mask;
	*valp = value;

	return 0;
}

int isa207_compute_mmcr(u64 event[], int n_ev,
			       unsigned int hwc[], unsigned long mmcr[],
			       struct perf_event *pevents[])
{
	unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
	unsigned int pmc, pmc_inuse;
	int i;

	pmc_inuse = 0;

	/* First pass to count resource use */
	for (i = 0; i < n_ev; ++i) {
		pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
		if (pmc)
			pmc_inuse |= 1 << pmc;
	}

	mmcra = mmcr1 = mmcr2 = 0;

	/* Second pass: assign PMCs, set all MMCR1 fields */
	for (i = 0; i < n_ev; ++i) {
		pmc     = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
		unit    = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
		combine = combine_from_event(event[i]);
		psel    =  event[i] & EVENT_PSEL_MASK;

		if (!pmc) {
			for (pmc = 1; pmc <= 4; ++pmc) {
				if (!(pmc_inuse & (1 << pmc)))
					break;
			}

			pmc_inuse |= 1 << pmc;
		}

		if (pmc <= 4) {
			mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc);
			mmcr1 |= combine << combine_shift(pmc);
			mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc);
		}

		/* In continuous sampling mode, update SDAR on TLB miss */
		mmcra |= mmcra_sdar_mode(event[i]);

		if (event[i] & EVENT_IS_L1) {
			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
			mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
			cache >>= 1;
			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
		}

		if (event[i] & EVENT_IS_MARKED) {
			mmcra |= MMCRA_SAMPLE_ENABLE;

			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
			if (val) {
				mmcra |= (val &  3) << MMCRA_SAMP_MODE_SHIFT;
				mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT;
			}
		}

		/*
		 * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
		 * the threshold bits are used for the match value.
		 */
		if (!cpu_has_feature(CPU_FTR_ARCH_300) && event_is_fab_match(event[i])) {
			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
		} else {
			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
			mmcra |= val << MMCRA_THR_CTL_SHIFT;
			val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
			mmcra |= val << MMCRA_THR_SEL_SHIFT;
			val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
			mmcra |= thresh_cmp_val(val);
		}

		if (event[i] & EVENT_WANTS_BHRB) {
			val = (event[i] >> EVENT_IFM_SHIFT) & EVENT_IFM_MASK;
			mmcra |= val << MMCRA_IFM_SHIFT;
		}

		if (pevents[i]->attr.exclude_user)
			mmcr2 |= MMCR2_FCP(pmc);

		if (pevents[i]->attr.exclude_hv)
			mmcr2 |= MMCR2_FCH(pmc);

		if (pevents[i]->attr.exclude_kernel) {
			if (cpu_has_feature(CPU_FTR_HVMODE))
				mmcr2 |= MMCR2_FCH(pmc);
			else
				mmcr2 |= MMCR2_FCS(pmc);
		}

		hwc[i] = pmc - 1;
	}

	/* Return MMCRx values */
	mmcr[0] = 0;

	/* pmc_inuse is 1-based */
	if (pmc_inuse & 2)
		mmcr[0] = MMCR0_PMC1CE;

	if (pmc_inuse & 0x7c)
		mmcr[0] |= MMCR0_PMCjCE;

	/* If we're not using PMC 5 or 6, freeze them */
	if (!(pmc_inuse & 0x60))
		mmcr[0] |= MMCR0_FC56;

	mmcr[1] = mmcr1;
	mmcr[2] = mmcra;
	mmcr[3] = mmcr2;

	return 0;
}

void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[])
{
	if (pmc <= 3)
		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
}

static int find_alternative(u64 event, const unsigned int ev_alt[][MAX_ALT], int size)
{
	int i, j;

	for (i = 0; i < size; ++i) {
		if (event < ev_alt[i][0])
			break;

		for (j = 0; j < MAX_ALT && ev_alt[i][j]; ++j)
			if (event == ev_alt[i][j])
				return i;
	}

	return -1;
}

int isa207_get_alternatives(u64 event, u64 alt[],
				const unsigned int ev_alt[][MAX_ALT], int size)
{
	int i, j, num_alt = 0;
	u64 alt_event;

	alt[num_alt++] = event;
	i = find_alternative(event, ev_alt, size);
	if (i >= 0) {
		/* Filter out the original event, it's already in alt[0] */
		for (j = 0; j < MAX_ALT; ++j) {
			alt_event = ev_alt[i][j];
			if (alt_event && alt_event != event)
				alt[num_alt++] = alt_event;
		}
	}

	return num_alt;
}