intel_pstate.c 20.6 KB
Newer Older
1
/*
2
 * intel_pstate.c: Native P state management for Intel processors
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
 *
 * (C) Copyright 2012 Intel Corporation
 * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
 *
 * 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; version 2
 * of the License.
 */

#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/ktime.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/list.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
28
#include <linux/acpi.h>
29 30 31 32 33 34 35 36
#include <trace/events/power.h>

#include <asm/div64.h>
#include <asm/msr.h>
#include <asm/cpu_device_id.h>

#define SAMPLE_COUNT		3

37 38
#define BYT_RATIOS	0x66a

39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
#define FRAC_BITS 8
#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
#define fp_toint(X) ((X) >> FRAC_BITS)

static inline int32_t mul_fp(int32_t x, int32_t y)
{
	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
}

static inline int32_t div_fp(int32_t x, int32_t y)
{
	return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
}

struct sample {
54
	int32_t core_pct_busy;
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73
	u64 aperf;
	u64 mperf;
	int freq;
};

struct pstate_data {
	int	current_pstate;
	int	min_pstate;
	int	max_pstate;
	int	turbo_pstate;
};

struct _pid {
	int setpoint;
	int32_t integral;
	int32_t p_gain;
	int32_t i_gain;
	int32_t d_gain;
	int deadband;
74
	int32_t last_err;
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
};

struct cpudata {
	int cpu;

	char name[64];

	struct timer_list timer;

	struct pstate_data pstate;
	struct _pid pid;

	int min_pstate_count;

	u64	prev_aperf;
	u64	prev_mperf;
	int	sample_ptr;
	struct sample samples[SAMPLE_COUNT];
};

static struct cpudata **all_cpu_data;
struct pstate_adjust_policy {
	int sample_rate_ms;
	int deadband;
	int setpoint;
	int p_gain_pct;
	int d_gain_pct;
	int i_gain_pct;
};

105 106 107 108 109
struct pstate_funcs {
	int (*get_max)(void);
	int (*get_min)(void);
	int (*get_turbo)(void);
	void (*set)(int pstate);
110 111
};

112 113 114
struct cpu_defaults {
	struct pstate_adjust_policy pid_policy;
	struct pstate_funcs funcs;
115 116
};

117 118 119
static struct pstate_adjust_policy pid_params;
static struct pstate_funcs pstate_funcs;

120 121 122 123 124 125
struct perf_limits {
	int no_turbo;
	int max_perf_pct;
	int min_perf_pct;
	int32_t max_perf;
	int32_t min_perf;
126 127
	int max_policy_pct;
	int max_sysfs_pct;
128 129 130 131 132 133 134 135
};

static struct perf_limits limits = {
	.no_turbo = 0,
	.max_perf_pct = 100,
	.max_perf = int_tofp(1),
	.min_perf_pct = 0,
	.min_perf = 0,
136 137
	.max_policy_pct = 100,
	.max_sysfs_pct = 100,
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
};

static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
			int deadband, int integral) {
	pid->setpoint = setpoint;
	pid->deadband  = deadband;
	pid->integral  = int_tofp(integral);
	pid->last_err  = setpoint - busy;
}

static inline void pid_p_gain_set(struct _pid *pid, int percent)
{
	pid->p_gain = div_fp(int_tofp(percent), int_tofp(100));
}

static inline void pid_i_gain_set(struct _pid *pid, int percent)
{
	pid->i_gain = div_fp(int_tofp(percent), int_tofp(100));
}

static inline void pid_d_gain_set(struct _pid *pid, int percent)
{

	pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
}

164
static signed int pid_calc(struct _pid *pid, int32_t busy)
165
{
166
	signed int result;
167 168 169
	int32_t pterm, dterm, fp_error;
	int32_t integral_limit;

170
	fp_error = int_tofp(pid->setpoint) - busy;
171

172
	if (abs(fp_error) <= int_tofp(pid->deadband))
173 174 175 176 177 178 179 180 181 182 183 184 185
		return 0;

	pterm = mul_fp(pid->p_gain, fp_error);

	pid->integral += fp_error;

	/* limit the integral term */
	integral_limit = int_tofp(30);
	if (pid->integral > integral_limit)
		pid->integral = integral_limit;
	if (pid->integral < -integral_limit)
		pid->integral = -integral_limit;

186 187
	dterm = mul_fp(pid->d_gain, fp_error - pid->last_err);
	pid->last_err = fp_error;
188 189 190 191 192 193 194 195

	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;

	return (signed int)fp_toint(result);
}

static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
{
196 197 198
	pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct);
	pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
	pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);
199 200

	pid_reset(&cpu->pid,
201
		pid_params.setpoint,
202
		100,
203
		pid_params.deadband,
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
		0);
}

static inline void intel_pstate_reset_all_pid(void)
{
	unsigned int cpu;
	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu])
			intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
	}
}

/************************** debugfs begin ************************/
static int pid_param_set(void *data, u64 val)
{
	*(u32 *)data = val;
	intel_pstate_reset_all_pid();
	return 0;
}
static int pid_param_get(void *data, u64 *val)
{
	*val = *(u32 *)data;
	return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get,
			pid_param_set, "%llu\n");

struct pid_param {
	char *name;
	void *value;
};

static struct pid_param pid_files[] = {
237 238 239 240 241 242
	{"sample_rate_ms", &pid_params.sample_rate_ms},
	{"d_gain_pct", &pid_params.d_gain_pct},
	{"i_gain_pct", &pid_params.i_gain_pct},
	{"deadband", &pid_params.deadband},
	{"setpoint", &pid_params.setpoint},
	{"p_gain_pct", &pid_params.p_gain_pct},
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
	{NULL, NULL}
};

static struct dentry *debugfs_parent;
static void intel_pstate_debug_expose_params(void)
{
	int i = 0;

	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
	if (IS_ERR_OR_NULL(debugfs_parent))
		return;
	while (pid_files[i].name) {
		debugfs_create_file(pid_files[i].name, 0660,
				debugfs_parent, pid_files[i].value,
				&fops_pid_param);
		i++;
	}
}

/************************** debugfs end ************************/

/************************** sysfs begin ************************/
#define show_one(file_name, object)					\
	static ssize_t show_##file_name					\
	(struct kobject *kobj, struct attribute *attr, char *buf)	\
	{								\
		return sprintf(buf, "%u\n", limits.object);		\
	}

static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
				const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;
	limits.no_turbo = clamp_t(int, input, 0 , 1);

	return count;
}

static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
				const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;

294 295
	limits.max_sysfs_pct = clamp_t(int, input, 0 , 100);
	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
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
	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
	return count;
}

static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
				const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;
	limits.min_perf_pct = clamp_t(int, input, 0 , 100);
	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));

	return count;
}

show_one(no_turbo, no_turbo);
show_one(max_perf_pct, max_perf_pct);
show_one(min_perf_pct, min_perf_pct);

define_one_global_rw(no_turbo);
define_one_global_rw(max_perf_pct);
define_one_global_rw(min_perf_pct);

static struct attribute *intel_pstate_attributes[] = {
	&no_turbo.attr,
	&max_perf_pct.attr,
	&min_perf_pct.attr,
	NULL
};

static struct attribute_group intel_pstate_attr_group = {
	.attrs = intel_pstate_attributes,
};
static struct kobject *intel_pstate_kobject;

static void intel_pstate_sysfs_expose_params(void)
{
	int rc;

	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
						&cpu_subsys.dev_root->kobj);
	BUG_ON(!intel_pstate_kobject);
	rc = sysfs_create_group(intel_pstate_kobject,
				&intel_pstate_attr_group);
	BUG_ON(rc);
}

/************************** sysfs end ************************/
347 348 349 350 351 352 353 354 355 356 357 358 359
static int byt_get_min_pstate(void)
{
	u64 value;
	rdmsrl(BYT_RATIOS, value);
	return value & 0xFF;
}

static int byt_get_max_pstate(void)
{
	u64 value;
	rdmsrl(BYT_RATIOS, value);
	return (value >> 16) & 0xFF;
}
360

361
static int core_get_min_pstate(void)
362 363
{
	u64 value;
364
	rdmsrl(MSR_PLATFORM_INFO, value);
365 366 367
	return (value >> 40) & 0xFF;
}

368
static int core_get_max_pstate(void)
369 370
{
	u64 value;
371
	rdmsrl(MSR_PLATFORM_INFO, value);
372 373 374
	return (value >> 8) & 0xFF;
}

375
static int core_get_turbo_pstate(void)
376 377 378
{
	u64 value;
	int nont, ret;
379
	rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
380
	nont = core_get_max_pstate();
381 382 383 384 385 386
	ret = ((value) & 255);
	if (ret <= nont)
		ret = nont;
	return ret;
}

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
static void core_set_pstate(int pstate)
{
	u64 val;

	val = pstate << 8;
	if (limits.no_turbo)
		val |= (u64)1 << 32;

	wrmsrl(MSR_IA32_PERF_CTL, val);
}

static struct cpu_defaults core_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 97,
		.p_gain_pct = 20,
		.d_gain_pct = 0,
		.i_gain_pct = 0,
	},
	.funcs = {
		.get_max = core_get_max_pstate,
		.get_min = core_get_min_pstate,
		.get_turbo = core_get_turbo_pstate,
		.set = core_set_pstate,
	},
};

415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
static struct cpu_defaults byt_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 97,
		.p_gain_pct = 14,
		.d_gain_pct = 0,
		.i_gain_pct = 4,
	},
	.funcs = {
		.get_max = byt_get_max_pstate,
		.get_min = byt_get_min_pstate,
		.get_turbo = byt_get_max_pstate,
		.set = core_set_pstate,
	},
};


433 434 435
static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
{
	int max_perf = cpu->pstate.turbo_pstate;
436
	int max_perf_adj;
437 438 439 440
	int min_perf;
	if (limits.no_turbo)
		max_perf = cpu->pstate.max_pstate;

441 442
	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
	*max = clamp_t(int, max_perf_adj,
443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);

	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
	*min = clamp_t(int, min_perf,
			cpu->pstate.min_pstate, max_perf);
}

static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
{
	int max_perf, min_perf;

	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);

	pstate = clamp_t(int, pstate, min_perf, max_perf);

	if (pstate == cpu->pstate.current_pstate)
		return;

	trace_cpu_frequency(pstate * 100000, cpu->cpu);
462

463 464
	cpu->pstate.current_pstate = pstate;

465
	pstate_funcs.set(pstate);
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
}

static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps)
{
	int target;
	target = cpu->pstate.current_pstate + steps;

	intel_pstate_set_pstate(cpu, target);
}

static inline void intel_pstate_pstate_decrease(struct cpudata *cpu, int steps)
{
	int target;
	target = cpu->pstate.current_pstate - steps;
	intel_pstate_set_pstate(cpu, target);
}

static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
{
	sprintf(cpu->name, "Intel 2nd generation core");

487 488 489
	cpu->pstate.min_pstate = pstate_funcs.get_min();
	cpu->pstate.max_pstate = pstate_funcs.get_max();
	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
490 491 492 493 494 495 496 497 498 499 500 501

	/*
	 * goto max pstate so we don't slow up boot if we are built-in if we are
	 * a module we will take care of it during normal operation
	 */
	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
}

static inline void intel_pstate_calc_busy(struct cpudata *cpu,
					struct sample *sample)
{
	u64 core_pct;
502 503 504
	core_pct = div64_u64(int_tofp(sample->aperf * 100),
			     sample->mperf);
	sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
505

506
	sample->core_pct_busy = core_pct;
507 508 509 510 511 512 513 514
}

static inline void intel_pstate_sample(struct cpudata *cpu)
{
	u64 aperf, mperf;

	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);
515 516 517 518 519 520 521
	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
	cpu->samples[cpu->sample_ptr].aperf = aperf;
	cpu->samples[cpu->sample_ptr].mperf = mperf;
	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;

	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
522 523 524 525 526 527 528 529 530

	cpu->prev_aperf = aperf;
	cpu->prev_mperf = mperf;
}

static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
{
	int sample_time, delay;

531
	sample_time = pid_params.sample_rate_ms;
532 533 534 535
	delay = msecs_to_jiffies(sample_time);
	mod_timer_pinned(&cpu->timer, jiffies + delay);
}

536
static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
537
{
538
	int32_t core_busy, max_pstate, current_pstate;
539

540
	core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
541
	max_pstate = int_tofp(cpu->pstate.max_pstate);
542
	current_pstate = int_tofp(cpu->pstate.current_pstate);
543
	return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
544 545 546 547
}

static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
{
548
	int32_t busy_scaled;
549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569
	struct _pid *pid;
	signed int ctl = 0;
	int steps;

	pid = &cpu->pid;
	busy_scaled = intel_pstate_get_scaled_busy(cpu);

	ctl = pid_calc(pid, busy_scaled);

	steps = abs(ctl);
	if (ctl < 0)
		intel_pstate_pstate_increase(cpu, steps);
	else
		intel_pstate_pstate_decrease(cpu, steps);
}

static void intel_pstate_timer_func(unsigned long __data)
{
	struct cpudata *cpu = (struct cpudata *) __data;

	intel_pstate_sample(cpu);
570
	intel_pstate_adjust_busy_pstate(cpu);
571 572 573 574 575 576 577 578

	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate) {
		cpu->min_pstate_count++;
		if (!(cpu->min_pstate_count % 5)) {
			intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
		}
	} else
		cpu->min_pstate_count = 0;
579

580 581 582 583 584 585 586
	intel_pstate_set_sample_time(cpu);
}

#define ICPU(model, policy) \
	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }

static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
587 588
	ICPU(0x2a, core_params),
	ICPU(0x2d, core_params),
589
	ICPU(0x37, byt_params),
590 591 592 593 594 595
	ICPU(0x3a, core_params),
	ICPU(0x3c, core_params),
	ICPU(0x3e, core_params),
	ICPU(0x3f, core_params),
	ICPU(0x45, core_params),
	ICPU(0x46, core_params),
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
	{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

static int intel_pstate_init_cpu(unsigned int cpunum)
{

	const struct x86_cpu_id *id;
	struct cpudata *cpu;

	id = x86_match_cpu(intel_pstate_cpu_ids);
	if (!id)
		return -ENODEV;

	all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
	if (!all_cpu_data[cpunum])
		return -ENOMEM;

	cpu = all_cpu_data[cpunum];

	intel_pstate_get_cpu_pstates(cpu);

	cpu->cpu = cpunum;
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
	init_timer_deferrable(&cpu->timer);
	cpu->timer.function = intel_pstate_timer_func;
	cpu->timer.data =
		(unsigned long)cpu;
	cpu->timer.expires = jiffies + HZ/100;
	intel_pstate_busy_pid_reset(cpu);
	intel_pstate_sample(cpu);
	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);

	add_timer_on(&cpu->timer, cpunum);

	pr_info("Intel pstate controlling: cpu %d\n", cpunum);

	return 0;
}

static unsigned int intel_pstate_get(unsigned int cpu_num)
{
	struct sample *sample;
	struct cpudata *cpu;

	cpu = all_cpu_data[cpu_num];
	if (!cpu)
		return 0;
	sample = &cpu->samples[cpu->sample_ptr];
	return sample->freq;
}

static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{
	struct cpudata *cpu;

	cpu = all_cpu_data[policy->cpu];

654 655 656
	if (!policy->cpuinfo.max_freq)
		return -ENODEV;

657 658 659 660 661 662
	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
		limits.min_perf_pct = 100;
		limits.min_perf = int_tofp(1);
		limits.max_perf_pct = 100;
		limits.max_perf = int_tofp(1);
		limits.no_turbo = 0;
663
		return 0;
664
	}
665 666 667 668
	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
	limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100);
	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));

669 670 671
	limits.max_policy_pct = policy->max * 100 / policy->cpuinfo.max_freq;
	limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
672
	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
673 674 675 676 677 678

	return 0;
}

static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
{
679
	cpufreq_verify_within_cpu_limits(policy);
680 681 682 683 684 685 686 687

	if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
		(policy->policy != CPUFREQ_POLICY_PERFORMANCE))
		return -EINVAL;

	return 0;
}

688
static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
689 690 691 692 693 694 695 696 697
{
	int cpu = policy->cpu;

	del_timer(&all_cpu_data[cpu]->timer);
	kfree(all_cpu_data[cpu]);
	all_cpu_data[cpu] = NULL;
	return 0;
}

698
static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
699 700
{
	struct cpudata *cpu;
701
	int rc;
702 703 704 705 706 707 708 709 710 711 712 713 714

	rc = intel_pstate_init_cpu(policy->cpu);
	if (rc)
		return rc;

	cpu = all_cpu_data[policy->cpu];

	if (!limits.no_turbo &&
		limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
	else
		policy->policy = CPUFREQ_POLICY_POWERSAVE;

715 716
	policy->min = cpu->pstate.min_pstate * 100000;
	policy->max = cpu->pstate.turbo_pstate * 100000;
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736

	/* cpuinfo and default policy values */
	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
	cpumask_set_cpu(policy->cpu, policy->cpus);

	return 0;
}

static struct cpufreq_driver intel_pstate_driver = {
	.flags		= CPUFREQ_CONST_LOOPS,
	.verify		= intel_pstate_verify_policy,
	.setpolicy	= intel_pstate_set_policy,
	.get		= intel_pstate_get,
	.init		= intel_pstate_cpu_init,
	.exit		= intel_pstate_cpu_exit,
	.name		= "intel_pstate",
};

737 738
static int __initdata no_load;

739 740 741 742 743 744 745 746
static int intel_pstate_msrs_not_valid(void)
{
	/* Check that all the msr's we are using are valid. */
	u64 aperf, mperf, tmp;

	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);

747 748 749
	if (!pstate_funcs.get_max() ||
		!pstate_funcs.get_min() ||
		!pstate_funcs.get_turbo())
750 751 752 753 754 755 756 757 758 759 760 761
		return -ENODEV;

	rdmsrl(MSR_IA32_APERF, tmp);
	if (!(tmp - aperf))
		return -ENODEV;

	rdmsrl(MSR_IA32_MPERF, tmp);
	if (!(tmp - mperf))
		return -ENODEV;

	return 0;
}
762

763
static void copy_pid_params(struct pstate_adjust_policy *policy)
764 765 766 767 768 769 770 771 772
{
	pid_params.sample_rate_ms = policy->sample_rate_ms;
	pid_params.p_gain_pct = policy->p_gain_pct;
	pid_params.i_gain_pct = policy->i_gain_pct;
	pid_params.d_gain_pct = policy->d_gain_pct;
	pid_params.deadband = policy->deadband;
	pid_params.setpoint = policy->setpoint;
}

773
static void copy_cpu_funcs(struct pstate_funcs *funcs)
774 775 776 777 778 779 780
{
	pstate_funcs.get_max   = funcs->get_max;
	pstate_funcs.get_min   = funcs->get_min;
	pstate_funcs.get_turbo = funcs->get_turbo;
	pstate_funcs.set       = funcs->set;
}

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
#if IS_ENABLED(CONFIG_ACPI)
#include <acpi/processor.h>

static bool intel_pstate_no_acpi_pss(void)
{
	int i;

	for_each_possible_cpu(i) {
		acpi_status status;
		union acpi_object *pss;
		struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
		struct acpi_processor *pr = per_cpu(processors, i);

		if (!pr)
			continue;

		status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
		if (ACPI_FAILURE(status))
			continue;

		pss = buffer.pointer;
		if (pss && pss->type == ACPI_TYPE_PACKAGE) {
			kfree(pss);
			return false;
		}

		kfree(pss);
	}

	return true;
}

struct hw_vendor_info {
	u16  valid;
	char oem_id[ACPI_OEM_ID_SIZE];
	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE];
};

/* Hardware vendor-specific info that has its own power management modes */
static struct hw_vendor_info vendor_info[] = {
	{1, "HP    ", "ProLiant"},
	{0, "", ""},
};

static bool intel_pstate_platform_pwr_mgmt_exists(void)
{
	struct acpi_table_header hdr;
	struct hw_vendor_info *v_info;

	if (acpi_disabled
	    || ACPI_FAILURE(acpi_get_table_header(ACPI_SIG_FADT, 0, &hdr)))
		return false;

	for (v_info = vendor_info; v_info->valid; v_info++) {
		if (!strncmp(hdr.oem_id, v_info->oem_id, ACPI_OEM_ID_SIZE)
		    && !strncmp(hdr.oem_table_id, v_info->oem_table_id, ACPI_OEM_TABLE_ID_SIZE)
		    && intel_pstate_no_acpi_pss())
			return true;
	}

	return false;
}
#else /* CONFIG_ACPI not enabled */
static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; }
#endif /* CONFIG_ACPI */

847 848
static int __init intel_pstate_init(void)
{
849
	int cpu, rc = 0;
850
	const struct x86_cpu_id *id;
851
	struct cpu_defaults *cpu_info;
852

853 854 855
	if (no_load)
		return -ENODEV;

856 857 858 859
	id = x86_match_cpu(intel_pstate_cpu_ids);
	if (!id)
		return -ENODEV;

860 861 862 863 864 865 866
	/*
	 * The Intel pstate driver will be ignored if the platform
	 * firmware has its own power management modes.
	 */
	if (intel_pstate_platform_pwr_mgmt_exists())
		return -ENODEV;

867 868 869 870 871
	cpu_info = (struct cpu_defaults *)id->driver_data;

	copy_pid_params(&cpu_info->pid_policy);
	copy_cpu_funcs(&cpu_info->funcs);

872 873 874
	if (intel_pstate_msrs_not_valid())
		return -ENODEV;

875 876
	pr_info("Intel P-state driver initializing.\n");

877
	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
878 879 880 881 882 883 884 885 886 887 888
	if (!all_cpu_data)
		return -ENOMEM;

	rc = cpufreq_register_driver(&intel_pstate_driver);
	if (rc)
		goto out;

	intel_pstate_debug_expose_params();
	intel_pstate_sysfs_expose_params();
	return rc;
out:
889 890 891 892 893 894 895 896 897 898
	get_online_cpus();
	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu]) {
			del_timer_sync(&all_cpu_data[cpu]->timer);
			kfree(all_cpu_data[cpu]);
		}
	}

	put_online_cpus();
	vfree(all_cpu_data);
899 900 901 902
	return -ENODEV;
}
device_initcall(intel_pstate_init);

903 904 905 906 907 908 909 910 911 912 913
static int __init intel_pstate_setup(char *str)
{
	if (!str)
		return -EINVAL;

	if (!strcmp(str, "disable"))
		no_load = 1;
	return 0;
}
early_param("intel_pstate", intel_pstate_setup);

914 915 916
MODULE_AUTHOR("Dirk Brandewie <dirk.j.brandewie@intel.com>");
MODULE_DESCRIPTION("'intel_pstate' - P state driver Intel Core processors");
MODULE_LICENSE("GPL");