summaryrefslogtreecommitdiffstats
path: root/arch/x86/events/amd/power.c
blob: 43b09e9c93a275a58e433f604b90114cdcea09a6 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Performance events - AMD Processor Power Reporting Mechanism
 *
 * Copyright (C) 2016 Advanced Micro Devices, Inc.
 *
 * Author: Huang Rui <ray.huang@amd.com>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <asm/cpu_device_id.h>
#include "../perf_event.h"

#define MSR_F15H_CU_PWR_ACCUMULATOR     0xc001007a
#define MSR_F15H_CU_MAX_PWR_ACCUMULATOR 0xc001007b
#define MSR_F15H_PTSC			0xc0010280

/* Event code: LSB 8 bits, passed in attr->config any other bit is reserved. */
#define AMD_POWER_EVENT_MASK		0xFFULL

/*
 * Accumulated power status counters.
 */
#define AMD_POWER_EVENTSEL_PKG		1

/*
 * The ratio of compute unit power accumulator sample period to the
 * PTSC period.
 */
static unsigned int cpu_pwr_sample_ratio;

/* Maximum accumulated power of a compute unit. */
static u64 max_cu_acc_power;

static struct pmu pmu_class;

/*
 * Accumulated power represents the sum of each compute unit's (CU) power
 * consumption. On any core of each CU we read the total accumulated power from
 * MSR_F15H_CU_PWR_ACCUMULATOR. cpu_mask represents CPU bit map of all cores
 * which are picked to measure the power for the CUs they belong to.
 */
static cpumask_t cpu_mask;

static void event_update(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	u64 prev_pwr_acc, new_pwr_acc, prev_ptsc, new_ptsc;
	u64 delta, tdelta;

	prev_pwr_acc = hwc->pwr_acc;
	prev_ptsc = hwc->ptsc;
	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
	rdmsrl(MSR_F15H_PTSC, new_ptsc);

	/*
	 * Calculate the CU power consumption over a time period, the unit of
	 * final value (delta) is micro-Watts. Then add it to the event count.
	 */
	if (new_pwr_acc < prev_pwr_acc) {
		delta = max_cu_acc_power + new_pwr_acc;
		delta -= prev_pwr_acc;
	} else
		delta = new_pwr_acc - prev_pwr_acc;

	delta *= cpu_pwr_sample_ratio * 1000;
	tdelta = new_ptsc - prev_ptsc;

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

static void __pmu_event_start(struct perf_event *event)
{
	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
		return;

	event->hw.state = 0;

	rdmsrl(MSR_F15H_PTSC, event->hw.ptsc);
	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
}

static void pmu_event_start(struct perf_event *event, int mode)
{
	__pmu_event_start(event);
}

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

	/* Mark event as deactivated and stopped. */
	if (!(hwc->state & PERF_HES_STOPPED))
		hwc->state |= PERF_HES_STOPPED;

	/* Check if software counter update is necessary. */
	if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
		/*
		 * Drain the remaining delta count out of an event
		 * that we are disabling:
		 */
		event_update(event);
		hwc->state |= PERF_HES_UPTODATE;
	}
}

static int pmu_event_add(struct perf_event *event, int mode)
{
	struct hw_perf_event *hwc = &event->hw;

	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;

	if (mode & PERF_EF_START)
		__pmu_event_start(event);

	return 0;
}

static void pmu_event_del(struct perf_event *event, int flags)
{
	pmu_event_stop(event, PERF_EF_UPDATE);
}

static int pmu_event_init(struct perf_event *event)
{
	u64 cfg = event->attr.config & AMD_POWER_EVENT_MASK;

	/* Only look at AMD power events. */
	if (event->attr.type != pmu_class.type)
		return -ENOENT;

	/* Unsupported modes and filters. */
	if (event->attr.sample_period)
		return -EINVAL;

	if (cfg != AMD_POWER_EVENTSEL_PKG)
		return -EINVAL;

	return 0;
}

static void pmu_event_read(struct perf_event *event)
{
	event_update(event);
}

static ssize_t
get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf)
{
	return cpumap_print_to_pagebuf(true, buf, &cpu_mask);
}

static DEVICE_ATTR(cpumask, S_IRUGO, get_attr_cpumask, NULL);

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

static struct attribute_group pmu_attr_group = {
	.attrs = pmu_attrs,
};

/*
 * Currently it only supports to report the power of each
 * processor/package.
 */
EVENT_ATTR_STR(power-pkg, power_pkg, "event=0x01");

EVENT_ATTR_STR(power-pkg.unit, power_pkg_unit, "mWatts");

/* Convert the count from micro-Watts to milli-Watts. */
EVENT_ATTR_STR(power-pkg.scale, power_pkg_scale, "1.000000e-3");

static struct attribute *events_attr[] = {
	EVENT_PTR(power_pkg),
	EVENT_PTR(power_pkg_unit),
	EVENT_PTR(power_pkg_scale),
	NULL,
};

static struct attribute_group pmu_events_group = {
	.name	= "events",
	.attrs	= events_attr,
};

PMU_FORMAT_ATTR(event, "config:0-7");

static struct attribute *formats_attr[] = {
	&format_attr_event.attr,
	NULL,
};

static struct attribute_group pmu_format_group = {
	.name	= "format",
	.attrs	= formats_attr,
};

static const struct attribute_group *attr_groups[] = {
	&pmu_attr_group,
	&pmu_format_group,
	&pmu_events_group,
	NULL,
};

static struct pmu pmu_class = {
	.attr_groups	= attr_groups,
	/* system-wide only */
	.task_ctx_nr	= perf_invalid_context,
	.event_init	= pmu_event_init,
	.add		= pmu_event_add,
	.del		= pmu_event_del,
	.start		= pmu_event_start,
	.stop		= pmu_event_stop,
	.read		= pmu_event_read,
	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
};

static int power_cpu_exit(unsigned int cpu)
{
	int target;

	if (!cpumask_test_and_clear_cpu(cpu, &cpu_mask))
		return 0;

	/*
	 * Find a new CPU on the same compute unit, if was set in cpumask
	 * and still some CPUs on compute unit. Then migrate event and
	 * context to new CPU.
	 */
	target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
	if (target < nr_cpumask_bits) {
		cpumask_set_cpu(target, &cpu_mask);
		perf_pmu_migrate_context(&pmu_class, cpu, target);
	}
	return 0;
}

static int power_cpu_init(unsigned int cpu)
{
	int target;

	/*
	 * 1) If any CPU is set at cpu_mask in the same compute unit, do
	 * nothing.
	 * 2) If no CPU is set at cpu_mask in the same compute unit,
	 * set current ONLINE CPU.
	 *
	 * Note: if there is a CPU aside of the new one already in the
	 * sibling mask, then it is also in cpu_mask.
	 */
	target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
	if (target >= nr_cpumask_bits)
		cpumask_set_cpu(cpu, &cpu_mask);
	return 0;
}

static const struct x86_cpu_id cpu_match[] = {
	X86_MATCH_VENDOR_FAM(AMD, 0x15, NULL),
	{},
};

static int __init amd_power_pmu_init(void)
{
	int ret;

	if (!x86_match_cpu(cpu_match))
		return -ENODEV;

	if (!boot_cpu_has(X86_FEATURE_ACC_POWER))
		return -ENODEV;

	cpu_pwr_sample_ratio = cpuid_ecx(0x80000007);

	if (rdmsrl_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
		pr_err("Failed to read max compute unit power accumulator MSR\n");
		return -ENODEV;
	}


	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
			  "perf/x86/amd/power:online",
			  power_cpu_init, power_cpu_exit);

	ret = perf_pmu_register(&pmu_class, "power", -1);
	if (WARN_ON(ret)) {
		pr_warn("AMD Power PMU registration failed\n");
		return ret;
	}

	pr_info("AMD Power PMU detected\n");
	return ret;
}
module_init(amd_power_pmu_init);

static void __exit amd_power_pmu_exit(void)
{
	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE);
	perf_pmu_unregister(&pmu_class);
}
module_exit(amd_power_pmu_exit);

MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
MODULE_DESCRIPTION("AMD Processor Power Reporting Mechanism");
MODULE_LICENSE("GPL v2");