1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * intel_pstate.c: Native P state management for Intel processors
4 *
5 * (C) Copyright 2012 Intel Corporation
6 * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
7 */
8
9#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
10
11#include <linux/kernel.h>
12#include <linux/kernel_stat.h>
13#include <linux/module.h>
14#include <linux/ktime.h>
15#include <linux/hrtimer.h>
16#include <linux/tick.h>
17#include <linux/slab.h>
18#include <linux/sched/cpufreq.h>
19#include <linux/list.h>
20#include <linux/cpu.h>
21#include <linux/cpufreq.h>
22#include <linux/sysfs.h>
23#include <linux/types.h>
24#include <linux/fs.h>
25#include <linux/acpi.h>
26#include <linux/vmalloc.h>
27#include <linux/pm_qos.h>
28#include <trace/events/power.h>
29
30#include <asm/div64.h>
31#include <asm/msr.h>
32#include <asm/cpu_device_id.h>
33#include <asm/cpufeature.h>
34#include <asm/intel-family.h>
35
36#define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
37
38#define INTEL_CPUFREQ_TRANSITION_LATENCY	20000
39#define INTEL_CPUFREQ_TRANSITION_DELAY_HWP	5000
40#define INTEL_CPUFREQ_TRANSITION_DELAY		500
41
42#ifdef CONFIG_ACPI
43#include <acpi/processor.h>
44#include <acpi/cppc_acpi.h>
45#endif
46
47#define FRAC_BITS 8
48#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
49#define fp_toint(X) ((X) >> FRAC_BITS)
50
51#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3))
52
53#define EXT_BITS 6
54#define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
55#define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
56#define int_ext_tofp(X) ((int64_t)(X) << EXT_FRAC_BITS)
57
58static inline int32_t mul_fp(int32_t x, int32_t y)
59{
60	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
61}
62
63static inline int32_t div_fp(s64 x, s64 y)
64{
65	return div64_s64((int64_t)x << FRAC_BITS, y);
66}
67
68static inline int ceiling_fp(int32_t x)
69{
70	int mask, ret;
71
72	ret = fp_toint(x);
73	mask = (1 << FRAC_BITS) - 1;
74	if (x & mask)
75		ret += 1;
76	return ret;
77}
78
79static inline int32_t percent_fp(int percent)
80{
81	return div_fp(percent, 100);
82}
83
84static inline u64 mul_ext_fp(u64 x, u64 y)
85{
86	return (x * y) >> EXT_FRAC_BITS;
87}
88
89static inline u64 div_ext_fp(u64 x, u64 y)
90{
91	return div64_u64(x << EXT_FRAC_BITS, y);
92}
93
94static inline int32_t percent_ext_fp(int percent)
95{
96	return div_ext_fp(percent, 100);
97}
98
99/**
100 * struct sample -	Store performance sample
101 * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
102 *			performance during last sample period
103 * @busy_scaled:	Scaled busy value which is used to calculate next
104 *			P state. This can be different than core_avg_perf
105 *			to account for cpu idle period
106 * @aperf:		Difference of actual performance frequency clock count
107 *			read from APERF MSR between last and current sample
108 * @mperf:		Difference of maximum performance frequency clock count
109 *			read from MPERF MSR between last and current sample
110 * @tsc:		Difference of time stamp counter between last and
111 *			current sample
112 * @time:		Current time from scheduler
113 *
114 * This structure is used in the cpudata structure to store performance sample
115 * data for choosing next P State.
116 */
117struct sample {
118	int32_t core_avg_perf;
119	int32_t busy_scaled;
120	u64 aperf;
121	u64 mperf;
122	u64 tsc;
123	u64 time;
124};
125
126/**
127 * struct pstate_data - Store P state data
128 * @current_pstate:	Current requested P state
129 * @min_pstate:		Min P state possible for this platform
130 * @max_pstate:		Max P state possible for this platform
131 * @max_pstate_physical:This is physical Max P state for a processor
132 *			This can be higher than the max_pstate which can
133 *			be limited by platform thermal design power limits
134 * @scaling:		Scaling factor to  convert frequency to cpufreq
135 *			frequency units
136 * @turbo_pstate:	Max Turbo P state possible for this platform
137 * @max_freq:		@max_pstate frequency in cpufreq units
138 * @turbo_freq:		@turbo_pstate frequency in cpufreq units
139 *
140 * Stores the per cpu model P state limits and current P state.
141 */
142struct pstate_data {
143	int	current_pstate;
144	int	min_pstate;
145	int	max_pstate;
146	int	max_pstate_physical;
147	int	scaling;
148	int	turbo_pstate;
149	unsigned int max_freq;
150	unsigned int turbo_freq;
151};
152
153/**
154 * struct vid_data -	Stores voltage information data
155 * @min:		VID data for this platform corresponding to
156 *			the lowest P state
157 * @max:		VID data corresponding to the highest P State.
158 * @turbo:		VID data for turbo P state
159 * @ratio:		Ratio of (vid max - vid min) /
160 *			(max P state - Min P State)
161 *
162 * Stores the voltage data for DVFS (Dynamic Voltage and Frequency Scaling)
163 * This data is used in Atom platforms, where in addition to target P state,
164 * the voltage data needs to be specified to select next P State.
165 */
166struct vid_data {
167	int min;
168	int max;
169	int turbo;
170	int32_t ratio;
171};
172
173/**
174 * struct global_params - Global parameters, mostly tunable via sysfs.
175 * @no_turbo:		Whether or not to use turbo P-states.
176 * @turbo_disabled:	Whether or not turbo P-states are available at all,
177 *			based on the MSR_IA32_MISC_ENABLE value and whether or
178 *			not the maximum reported turbo P-state is different from
179 *			the maximum reported non-turbo one.
180 * @turbo_disabled_mf:	The @turbo_disabled value reflected by cpuinfo.max_freq.
181 * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
182 *			P-state capacity.
183 * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
184 *			P-state capacity.
185 */
186struct global_params {
187	bool no_turbo;
188	bool turbo_disabled;
189	bool turbo_disabled_mf;
190	int max_perf_pct;
191	int min_perf_pct;
192};
193
194/**
195 * struct cpudata -	Per CPU instance data storage
196 * @cpu:		CPU number for this instance data
197 * @policy:		CPUFreq policy value
198 * @update_util:	CPUFreq utility callback information
199 * @update_util_set:	CPUFreq utility callback is set
200 * @iowait_boost:	iowait-related boost fraction
201 * @last_update:	Time of the last update.
202 * @pstate:		Stores P state limits for this CPU
203 * @vid:		Stores VID limits for this CPU
204 * @last_sample_time:	Last Sample time
205 * @aperf_mperf_shift:	APERF vs MPERF counting frequency difference
206 * @prev_aperf:		Last APERF value read from APERF MSR
207 * @prev_mperf:		Last MPERF value read from MPERF MSR
208 * @prev_tsc:		Last timestamp counter (TSC) value
209 * @prev_cummulative_iowait: IO Wait time difference from last and
210 *			current sample
211 * @sample:		Storage for storing last Sample data
212 * @min_perf_ratio:	Minimum capacity in terms of PERF or HWP ratios
213 * @max_perf_ratio:	Maximum capacity in terms of PERF or HWP ratios
214 * @acpi_perf_data:	Stores ACPI perf information read from _PSS
215 * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
216 * @epp_powersave:	Last saved HWP energy performance preference
217 *			(EPP) or energy performance bias (EPB),
218 *			when policy switched to performance
219 * @epp_policy:		Last saved policy used to set EPP/EPB
220 * @epp_default:	Power on default HWP energy performance
221 *			preference/bias
222 * @epp_cached		Cached HWP energy-performance preference value
223 * @hwp_req_cached:	Cached value of the last HWP Request MSR
224 * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
225 * @last_io_update:	Last time when IO wake flag was set
226 * @sched_flags:	Store scheduler flags for possible cross CPU update
227 * @hwp_boost_min:	Last HWP boosted min performance
228 * @suspended:		Whether or not the driver has been suspended.
229 *
230 * This structure stores per CPU instance data for all CPUs.
231 */
232struct cpudata {
233	int cpu;
234
235	unsigned int policy;
236	struct update_util_data update_util;
237	bool   update_util_set;
238
239	struct pstate_data pstate;
240	struct vid_data vid;
241
242	u64	last_update;
243	u64	last_sample_time;
244	u64	aperf_mperf_shift;
245	u64	prev_aperf;
246	u64	prev_mperf;
247	u64	prev_tsc;
248	u64	prev_cummulative_iowait;
249	struct sample sample;
250	int32_t	min_perf_ratio;
251	int32_t	max_perf_ratio;
252#ifdef CONFIG_ACPI
253	struct acpi_processor_performance acpi_perf_data;
254	bool valid_pss_table;
255#endif
256	unsigned int iowait_boost;
257	s16 epp_powersave;
258	s16 epp_policy;
259	s16 epp_default;
260	s16 epp_cached;
261	u64 hwp_req_cached;
262	u64 hwp_cap_cached;
263	u64 last_io_update;
264	unsigned int sched_flags;
265	u32 hwp_boost_min;
266	bool suspended;
267};
268
269static struct cpudata **all_cpu_data;
270
271/**
272 * struct pstate_funcs - Per CPU model specific callbacks
273 * @get_max:		Callback to get maximum non turbo effective P state
274 * @get_max_physical:	Callback to get maximum non turbo physical P state
275 * @get_min:		Callback to get minimum P state
276 * @get_turbo:		Callback to get turbo P state
277 * @get_scaling:	Callback to get frequency scaling factor
278 * @get_aperf_mperf_shift: Callback to get the APERF vs MPERF frequency difference
279 * @get_val:		Callback to convert P state to actual MSR write value
280 * @get_vid:		Callback to get VID data for Atom platforms
281 *
282 * Core and Atom CPU models have different way to get P State limits. This
283 * structure is used to store those callbacks.
284 */
285struct pstate_funcs {
286	int (*get_max)(void);
287	int (*get_max_physical)(void);
288	int (*get_min)(void);
289	int (*get_turbo)(void);
290	int (*get_scaling)(void);
291	int (*get_aperf_mperf_shift)(void);
292	u64 (*get_val)(struct cpudata*, int pstate);
293	void (*get_vid)(struct cpudata *);
294};
295
296static struct pstate_funcs pstate_funcs __read_mostly;
297
298static int hwp_active __read_mostly;
299static int hwp_mode_bdw __read_mostly;
300static bool per_cpu_limits __read_mostly;
301static bool hwp_boost __read_mostly;
302
303static struct cpufreq_driver *intel_pstate_driver __read_mostly;
304
305#ifdef CONFIG_ACPI
306static bool acpi_ppc;
307#endif
308
309static struct global_params global;
310
311static DEFINE_MUTEX(intel_pstate_driver_lock);
312static DEFINE_MUTEX(intel_pstate_limits_lock);
313
314#ifdef CONFIG_ACPI
315
316static bool intel_pstate_acpi_pm_profile_server(void)
317{
318	if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
319	    acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
320		return true;
321
322	return false;
323}
324
325static bool intel_pstate_get_ppc_enable_status(void)
326{
327	if (intel_pstate_acpi_pm_profile_server())
328		return true;
329
330	return acpi_ppc;
331}
332
333#ifdef CONFIG_ACPI_CPPC_LIB
334
335/* The work item is needed to avoid CPU hotplug locking issues */
336static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
337{
338	sched_set_itmt_support();
339}
340
341static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);
342
343static void intel_pstate_set_itmt_prio(int cpu)
344{
345	struct cppc_perf_caps cppc_perf;
346	static u32 max_highest_perf = 0, min_highest_perf = U32_MAX;
347	int ret;
348
349	ret = cppc_get_perf_caps(cpu, &cppc_perf);
350	if (ret)
351		return;
352
353	/*
354	 * The priorities can be set regardless of whether or not
355	 * sched_set_itmt_support(true) has been called and it is valid to
356	 * update them at any time after it has been called.
357	 */
358	sched_set_itmt_core_prio(cppc_perf.highest_perf, cpu);
359
360	if (max_highest_perf <= min_highest_perf) {
361		if (cppc_perf.highest_perf > max_highest_perf)
362			max_highest_perf = cppc_perf.highest_perf;
363
364		if (cppc_perf.highest_perf < min_highest_perf)
365			min_highest_perf = cppc_perf.highest_perf;
366
367		if (max_highest_perf > min_highest_perf) {
368			/*
369			 * This code can be run during CPU online under the
370			 * CPU hotplug locks, so sched_set_itmt_support()
371			 * cannot be called from here.  Queue up a work item
372			 * to invoke it.
373			 */
374			schedule_work(&sched_itmt_work);
375		}
376	}
377}
378
379static int intel_pstate_get_cppc_guranteed(int cpu)
380{
381	struct cppc_perf_caps cppc_perf;
382	int ret;
383
384	ret = cppc_get_perf_caps(cpu, &cppc_perf);
385	if (ret)
386		return ret;
387
388	if (cppc_perf.guaranteed_perf)
389		return cppc_perf.guaranteed_perf;
390
391	return cppc_perf.nominal_perf;
392}
393
394#else /* CONFIG_ACPI_CPPC_LIB */
395static void intel_pstate_set_itmt_prio(int cpu)
396{
397}
398#endif /* CONFIG_ACPI_CPPC_LIB */
399
400static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
401{
402	struct cpudata *cpu;
403	int ret;
404	int i;
405
406	if (hwp_active) {
407		intel_pstate_set_itmt_prio(policy->cpu);
408		return;
409	}
410
411	if (!intel_pstate_get_ppc_enable_status())
412		return;
413
414	cpu = all_cpu_data[policy->cpu];
415
416	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
417						  policy->cpu);
418	if (ret)
419		return;
420
421	/*
422	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
423	 * guarantee that the states returned by it map to the states in our
424	 * list directly.
425	 */
426	if (cpu->acpi_perf_data.control_register.space_id !=
427						ACPI_ADR_SPACE_FIXED_HARDWARE)
428		goto err;
429
430	/*
431	 * If there is only one entry _PSS, simply ignore _PSS and continue as
432	 * usual without taking _PSS into account
433	 */
434	if (cpu->acpi_perf_data.state_count < 2)
435		goto err;
436
437	pr_debug("CPU%u - ACPI _PSS perf data\n", policy->cpu);
438	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
439		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
440			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
441			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
442			 (u32) cpu->acpi_perf_data.states[i].power,
443			 (u32) cpu->acpi_perf_data.states[i].control);
444	}
445
446	cpu->valid_pss_table = true;
447	pr_debug("_PPC limits will be enforced\n");
448
449	return;
450
451 err:
452	cpu->valid_pss_table = false;
453	acpi_processor_unregister_performance(policy->cpu);
454}
455
456static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
457{
458	struct cpudata *cpu;
459
460	cpu = all_cpu_data[policy->cpu];
461	if (!cpu->valid_pss_table)
462		return;
463
464	acpi_processor_unregister_performance(policy->cpu);
465}
466#else /* CONFIG_ACPI */
467static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
468{
469}
470
471static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
472{
473}
474
475static inline bool intel_pstate_acpi_pm_profile_server(void)
476{
477	return false;
478}
479#endif /* CONFIG_ACPI */
480
481#ifndef CONFIG_ACPI_CPPC_LIB
482static int intel_pstate_get_cppc_guranteed(int cpu)
483{
484	return -ENOTSUPP;
485}
486#endif /* CONFIG_ACPI_CPPC_LIB */
487
488static inline void update_turbo_state(void)
489{
490	u64 misc_en;
491	struct cpudata *cpu;
492
493	cpu = all_cpu_data[0];
494	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
495	global.turbo_disabled =
496		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
497		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
498}
499
500static int min_perf_pct_min(void)
501{
502	struct cpudata *cpu = all_cpu_data[0];
503	int turbo_pstate = cpu->pstate.turbo_pstate;
504
505	return turbo_pstate ?
506		(cpu->pstate.min_pstate * 100 / turbo_pstate) : 0;
507}
508
509static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
510{
511	u64 epb;
512	int ret;
513
514	if (!boot_cpu_has(X86_FEATURE_EPB))
515		return -ENXIO;
516
517	ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
518	if (ret)
519		return (s16)ret;
520
521	return (s16)(epb & 0x0f);
522}
523
524static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data)
525{
526	s16 epp;
527
528	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
529		/*
530		 * When hwp_req_data is 0, means that caller didn't read
531		 * MSR_HWP_REQUEST, so need to read and get EPP.
532		 */
533		if (!hwp_req_data) {
534			epp = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST,
535					    &hwp_req_data);
536			if (epp)
537				return epp;
538		}
539		epp = (hwp_req_data >> 24) & 0xff;
540	} else {
541		/* When there is no EPP present, HWP uses EPB settings */
542		epp = intel_pstate_get_epb(cpu_data);
543	}
544
545	return epp;
546}
547
548static int intel_pstate_set_epb(int cpu, s16 pref)
549{
550	u64 epb;
551	int ret;
552
553	if (!boot_cpu_has(X86_FEATURE_EPB))
554		return -ENXIO;
555
556	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
557	if (ret)
558		return ret;
559
560	epb = (epb & ~0x0f) | pref;
561	wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, epb);
562
563	return 0;
564}
565
566/*
567 * EPP/EPB display strings corresponding to EPP index in the
568 * energy_perf_strings[]
569 *	index		String
570 *-------------------------------------
571 *	0		default
572 *	1		performance
573 *	2		balance_performance
574 *	3		balance_power
575 *	4		power
576 */
577static const char * const energy_perf_strings[] = {
578	"default",
579	"performance",
580	"balance_performance",
581	"balance_power",
582	"power",
583	NULL
584};
585static const unsigned int epp_values[] = {
586	HWP_EPP_PERFORMANCE,
587	HWP_EPP_BALANCE_PERFORMANCE,
588	HWP_EPP_BALANCE_POWERSAVE,
589	HWP_EPP_POWERSAVE
590};
591
592static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw_epp)
593{
594	s16 epp;
595	int index = -EINVAL;
596
597	*raw_epp = 0;
598	epp = intel_pstate_get_epp(cpu_data, 0);
599	if (epp < 0)
600		return epp;
601
602	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
603		if (epp == HWP_EPP_PERFORMANCE)
604			return 1;
605		if (epp == HWP_EPP_BALANCE_PERFORMANCE)
606			return 2;
607		if (epp == HWP_EPP_BALANCE_POWERSAVE)
608			return 3;
609		if (epp == HWP_EPP_POWERSAVE)
610			return 4;
611		*raw_epp = epp;
612		return 0;
613	} else if (boot_cpu_has(X86_FEATURE_EPB)) {
614		/*
615		 * Range:
616		 *	0x00-0x03	:	Performance
617		 *	0x04-0x07	:	Balance performance
618		 *	0x08-0x0B	:	Balance power
619		 *	0x0C-0x0F	:	Power
620		 * The EPB is a 4 bit value, but our ranges restrict the
621		 * value which can be set. Here only using top two bits
622		 * effectively.
623		 */
624		index = (epp >> 2) + 1;
625	}
626
627	return index;
628}
629
630static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
631{
632	int ret;
633
634	/*
635	 * Use the cached HWP Request MSR value, because in the active mode the
636	 * register itself may be updated by intel_pstate_hwp_boost_up() or
637	 * intel_pstate_hwp_boost_down() at any time.
638	 */
639	u64 value = READ_ONCE(cpu->hwp_req_cached);
640
641	value &= ~GENMASK_ULL(31, 24);
642	value |= (u64)epp << 24;
643	/*
644	 * The only other updater of hwp_req_cached in the active mode,
645	 * intel_pstate_hwp_set(), is called under the same lock as this
646	 * function, so it cannot run in parallel with the update below.
647	 */
648	WRITE_ONCE(cpu->hwp_req_cached, value);
649	ret = wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
650	if (!ret)
651		cpu->epp_cached = epp;
652
653	return ret;
654}
655
656static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
657					      int pref_index, bool use_raw,
658					      u32 raw_epp)
659{
660	int epp = -EINVAL;
661	int ret;
662
663	if (!pref_index)
664		epp = cpu_data->epp_default;
665
666	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
667		if (use_raw)
668			epp = raw_epp;
669		else if (epp == -EINVAL)
670			epp = epp_values[pref_index - 1];
671
672		/*
673		 * To avoid confusion, refuse to set EPP to any values different
674		 * from 0 (performance) if the current policy is "performance",
675		 * because those values would be overridden.
676		 */
677		if (epp > 0 && cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
678			return -EBUSY;
679
680		ret = intel_pstate_set_epp(cpu_data, epp);
681	} else {
682		if (epp == -EINVAL)
683			epp = (pref_index - 1) << 2;
684		ret = intel_pstate_set_epb(cpu_data->cpu, epp);
685	}
686
687	return ret;
688}
689
690static ssize_t show_energy_performance_available_preferences(
691				struct cpufreq_policy *policy, char *buf)
692{
693	int i = 0;
694	int ret = 0;
695
696	while (energy_perf_strings[i] != NULL)
697		ret += sprintf(&buf[ret], "%s ", energy_perf_strings[i++]);
698
699	ret += sprintf(&buf[ret], "\n");
700
701	return ret;
702}
703
704cpufreq_freq_attr_ro(energy_performance_available_preferences);
705
706static struct cpufreq_driver intel_pstate;
707
708static ssize_t store_energy_performance_preference(
709		struct cpufreq_policy *policy, const char *buf, size_t count)
710{
711	struct cpudata *cpu = all_cpu_data[policy->cpu];
712	char str_preference[21];
713	bool raw = false;
714	ssize_t ret;
715	u32 epp = 0;
716
717	ret = sscanf(buf, "%20s", str_preference);
718	if (ret != 1)
719		return -EINVAL;
720
721	ret = match_string(energy_perf_strings, -1, str_preference);
722	if (ret < 0) {
723		if (!boot_cpu_has(X86_FEATURE_HWP_EPP))
724			return ret;
725
726		ret = kstrtouint(buf, 10, &epp);
727		if (ret)
728			return ret;
729
730		if (epp > 255)
731			return -EINVAL;
732
733		raw = true;
734	}
735
736	/*
737	 * This function runs with the policy R/W semaphore held, which
738	 * guarantees that the driver pointer will not change while it is
739	 * running.
740	 */
741	if (!intel_pstate_driver)
742		return -EAGAIN;
743
744	mutex_lock(&intel_pstate_limits_lock);
745
746	if (intel_pstate_driver == &intel_pstate) {
747		ret = intel_pstate_set_energy_pref_index(cpu, ret, raw, epp);
748	} else {
749		/*
750		 * In the passive mode the governor needs to be stopped on the
751		 * target CPU before the EPP update and restarted after it,
752		 * which is super-heavy-weight, so make sure it is worth doing
753		 * upfront.
754		 */
755		if (!raw)
756			epp = ret ? epp_values[ret - 1] : cpu->epp_default;
757
758		if (cpu->epp_cached != epp) {
759			int err;
760
761			cpufreq_stop_governor(policy);
762			ret = intel_pstate_set_epp(cpu, epp);
763			err = cpufreq_start_governor(policy);
764			if (!ret)
765				ret = err;
766		} else {
767			ret = 0;
768		}
769	}
770
771	mutex_unlock(&intel_pstate_limits_lock);
772
773	return ret ?: count;
774}
775
776static ssize_t show_energy_performance_preference(
777				struct cpufreq_policy *policy, char *buf)
778{
779	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
780	int preference, raw_epp;
781
782	preference = intel_pstate_get_energy_pref_index(cpu_data, &raw_epp);
783	if (preference < 0)
784		return preference;
785
786	if (raw_epp)
787		return  sprintf(buf, "%d\n", raw_epp);
788	else
789		return  sprintf(buf, "%s\n", energy_perf_strings[preference]);
790}
791
792cpufreq_freq_attr_rw(energy_performance_preference);
793
794static ssize_t show_base_frequency(struct cpufreq_policy *policy, char *buf)
795{
796	struct cpudata *cpu;
797	u64 cap;
798	int ratio;
799
800	ratio = intel_pstate_get_cppc_guranteed(policy->cpu);
801	if (ratio <= 0) {
802		rdmsrl_on_cpu(policy->cpu, MSR_HWP_CAPABILITIES, &cap);
803		ratio = HWP_GUARANTEED_PERF(cap);
804	}
805
806	cpu = all_cpu_data[policy->cpu];
807
808	return sprintf(buf, "%d\n", ratio * cpu->pstate.scaling);
809}
810
811cpufreq_freq_attr_ro(base_frequency);
812
813static struct freq_attr *hwp_cpufreq_attrs[] = {
814	&energy_performance_preference,
815	&energy_performance_available_preferences,
816	&base_frequency,
817	NULL,
818};
819
820static void intel_pstate_get_hwp_max(struct cpudata *cpu, int *phy_max,
821				     int *current_max)
822{
823	u64 cap;
824
825	rdmsrl_on_cpu(cpu->cpu, MSR_HWP_CAPABILITIES, &cap);
826	WRITE_ONCE(cpu->hwp_cap_cached, cap);
827	if (global.no_turbo || global.turbo_disabled)
828		*current_max = HWP_GUARANTEED_PERF(cap);
829	else
830		*current_max = HWP_HIGHEST_PERF(cap);
831
832	*phy_max = HWP_HIGHEST_PERF(cap);
833}
834
835static void intel_pstate_hwp_set(unsigned int cpu)
836{
837	struct cpudata *cpu_data = all_cpu_data[cpu];
838	int max, min;
839	u64 value;
840	s16 epp;
841
842	max = cpu_data->max_perf_ratio;
843	min = cpu_data->min_perf_ratio;
844
845	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
846		min = max;
847
848	rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
849
850	value &= ~HWP_MIN_PERF(~0L);
851	value |= HWP_MIN_PERF(min);
852
853	value &= ~HWP_MAX_PERF(~0L);
854	value |= HWP_MAX_PERF(max);
855
856	if (cpu_data->epp_policy == cpu_data->policy)
857		goto skip_epp;
858
859	cpu_data->epp_policy = cpu_data->policy;
860
861	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
862		epp = intel_pstate_get_epp(cpu_data, value);
863		cpu_data->epp_powersave = epp;
864		/* If EPP read was failed, then don't try to write */
865		if (epp < 0)
866			goto skip_epp;
867
868		epp = 0;
869	} else {
870		/* skip setting EPP, when saved value is invalid */
871		if (cpu_data->epp_powersave < 0)
872			goto skip_epp;
873
874		/*
875		 * No need to restore EPP when it is not zero. This
876		 * means:
877		 *  - Policy is not changed
878		 *  - user has manually changed
879		 *  - Error reading EPB
880		 */
881		epp = intel_pstate_get_epp(cpu_data, value);
882		if (epp)
883			goto skip_epp;
884
885		epp = cpu_data->epp_powersave;
886	}
887	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
888		value &= ~GENMASK_ULL(31, 24);
889		value |= (u64)epp << 24;
890	} else {
891		intel_pstate_set_epb(cpu, epp);
892	}
893skip_epp:
894	WRITE_ONCE(cpu_data->hwp_req_cached, value);
895	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
896}
897
898static void intel_pstate_hwp_offline(struct cpudata *cpu)
899{
900	u64 value = READ_ONCE(cpu->hwp_req_cached);
901	int min_perf;
902
903	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
904		/*
905		 * In case the EPP has been set to "performance" by the
906		 * active mode "performance" scaling algorithm, replace that
907		 * temporary value with the cached EPP one.
908		 */
909		value &= ~GENMASK_ULL(31, 24);
910		value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached);
911		WRITE_ONCE(cpu->hwp_req_cached, value);
912	}
913
914	value &= ~GENMASK_ULL(31, 0);
915	min_perf = HWP_LOWEST_PERF(cpu->hwp_cap_cached);
916
917	/* Set hwp_max = hwp_min */
918	value |= HWP_MAX_PERF(min_perf);
919	value |= HWP_MIN_PERF(min_perf);
920
921	/* Set EPP to min */
922	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
923		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
924
925	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
926}
927
928#define POWER_CTL_EE_ENABLE	1
929#define POWER_CTL_EE_DISABLE	2
930
931static int power_ctl_ee_state;
932
933static void set_power_ctl_ee_state(bool input)
934{
935	u64 power_ctl;
936
937	mutex_lock(&intel_pstate_driver_lock);
938	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
939	if (input) {
940		power_ctl &= ~BIT(MSR_IA32_POWER_CTL_BIT_EE);
941		power_ctl_ee_state = POWER_CTL_EE_ENABLE;
942	} else {
943		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
944		power_ctl_ee_state = POWER_CTL_EE_DISABLE;
945	}
946	wrmsrl(MSR_IA32_POWER_CTL, power_ctl);
947	mutex_unlock(&intel_pstate_driver_lock);
948}
949
950static void intel_pstate_hwp_enable(struct cpudata *cpudata);
951
952static void intel_pstate_hwp_reenable(struct cpudata *cpu)
953{
954	intel_pstate_hwp_enable(cpu);
955	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, READ_ONCE(cpu->hwp_req_cached));
956}
957
958static int intel_pstate_suspend(struct cpufreq_policy *policy)
959{
960	struct cpudata *cpu = all_cpu_data[policy->cpu];
961
962	pr_debug("CPU %d suspending\n", cpu->cpu);
963
964	cpu->suspended = true;
965
966	return 0;
967}
968
969static int intel_pstate_resume(struct cpufreq_policy *policy)
970{
971	struct cpudata *cpu = all_cpu_data[policy->cpu];
972
973	pr_debug("CPU %d resuming\n", cpu->cpu);
974
975	/* Only restore if the system default is changed */
976	if (power_ctl_ee_state == POWER_CTL_EE_ENABLE)
977		set_power_ctl_ee_state(true);
978	else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE)
979		set_power_ctl_ee_state(false);
980
981	if (cpu->suspended && hwp_active) {
982		mutex_lock(&intel_pstate_limits_lock);
983
984		/* Re-enable HWP, because "online" has not done that. */
985		intel_pstate_hwp_reenable(cpu);
986
987		mutex_unlock(&intel_pstate_limits_lock);
988	}
989
990	cpu->suspended = false;
991
992	return 0;
993}
994
995static void intel_pstate_update_policies(void)
996{
997	int cpu;
998
999	for_each_possible_cpu(cpu)
1000		cpufreq_update_policy(cpu);
1001}
1002
1003static void intel_pstate_update_max_freq(unsigned int cpu)
1004{
1005	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
1006	struct cpudata *cpudata;
1007
1008	if (!policy)
1009		return;
1010
1011	cpudata = all_cpu_data[cpu];
1012	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
1013			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
1014
1015	refresh_frequency_limits(policy);
1016
1017	cpufreq_cpu_release(policy);
1018}
1019
1020static void intel_pstate_update_limits(unsigned int cpu)
1021{
1022	mutex_lock(&intel_pstate_driver_lock);
1023
1024	update_turbo_state();
1025	/*
1026	 * If turbo has been turned on or off globally, policy limits for
1027	 * all CPUs need to be updated to reflect that.
1028	 */
1029	if (global.turbo_disabled_mf != global.turbo_disabled) {
1030		global.turbo_disabled_mf = global.turbo_disabled;
1031		arch_set_max_freq_ratio(global.turbo_disabled);
1032		for_each_possible_cpu(cpu)
1033			intel_pstate_update_max_freq(cpu);
1034	} else {
1035		cpufreq_update_policy(cpu);
1036	}
1037
1038	mutex_unlock(&intel_pstate_driver_lock);
1039}
1040
1041/************************** sysfs begin ************************/
1042#define show_one(file_name, object)					\
1043	static ssize_t show_##file_name					\
1044	(struct kobject *kobj, struct kobj_attribute *attr, char *buf)	\
1045	{								\
1046		return sprintf(buf, "%u\n", global.object);		\
1047	}
1048
1049static ssize_t intel_pstate_show_status(char *buf);
1050static int intel_pstate_update_status(const char *buf, size_t size);
1051
1052static ssize_t show_status(struct kobject *kobj,
1053			   struct kobj_attribute *attr, char *buf)
1054{
1055	ssize_t ret;
1056
1057	mutex_lock(&intel_pstate_driver_lock);
1058	ret = intel_pstate_show_status(buf);
1059	mutex_unlock(&intel_pstate_driver_lock);
1060
1061	return ret;
1062}
1063
1064static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
1065			    const char *buf, size_t count)
1066{
1067	char *p = memchr(buf, '\n', count);
1068	int ret;
1069
1070	mutex_lock(&intel_pstate_driver_lock);
1071	ret = intel_pstate_update_status(buf, p ? p - buf : count);
1072	mutex_unlock(&intel_pstate_driver_lock);
1073
1074	return ret < 0 ? ret : count;
1075}
1076
1077static ssize_t show_turbo_pct(struct kobject *kobj,
1078				struct kobj_attribute *attr, char *buf)
1079{
1080	struct cpudata *cpu;
1081	int total, no_turbo, turbo_pct;
1082	uint32_t turbo_fp;
1083
1084	mutex_lock(&intel_pstate_driver_lock);
1085
1086	if (!intel_pstate_driver) {
1087		mutex_unlock(&intel_pstate_driver_lock);
1088		return -EAGAIN;
1089	}
1090
1091	cpu = all_cpu_data[0];
1092
1093	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
1094	no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1;
1095	turbo_fp = div_fp(no_turbo, total);
1096	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
1097
1098	mutex_unlock(&intel_pstate_driver_lock);
1099
1100	return sprintf(buf, "%u\n", turbo_pct);
1101}
1102
1103static ssize_t show_num_pstates(struct kobject *kobj,
1104				struct kobj_attribute *attr, char *buf)
1105{
1106	struct cpudata *cpu;
1107	int total;
1108
1109	mutex_lock(&intel_pstate_driver_lock);
1110
1111	if (!intel_pstate_driver) {
1112		mutex_unlock(&intel_pstate_driver_lock);
1113		return -EAGAIN;
1114	}
1115
1116	cpu = all_cpu_data[0];
1117	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
1118
1119	mutex_unlock(&intel_pstate_driver_lock);
1120
1121	return sprintf(buf, "%u\n", total);
1122}
1123
1124static ssize_t show_no_turbo(struct kobject *kobj,
1125			     struct kobj_attribute *attr, char *buf)
1126{
1127	ssize_t ret;
1128
1129	mutex_lock(&intel_pstate_driver_lock);
1130
1131	if (!intel_pstate_driver) {
1132		mutex_unlock(&intel_pstate_driver_lock);
1133		return -EAGAIN;
1134	}
1135
1136	update_turbo_state();
1137	if (global.turbo_disabled)
1138		ret = sprintf(buf, "%u\n", global.turbo_disabled);
1139	else
1140		ret = sprintf(buf, "%u\n", global.no_turbo);
1141
1142	mutex_unlock(&intel_pstate_driver_lock);
1143
1144	return ret;
1145}
1146
1147static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
1148			      const char *buf, size_t count)
1149{
1150	unsigned int input;
1151	int ret;
1152
1153	ret = sscanf(buf, "%u", &input);
1154	if (ret != 1)
1155		return -EINVAL;
1156
1157	mutex_lock(&intel_pstate_driver_lock);
1158
1159	if (!intel_pstate_driver) {
1160		mutex_unlock(&intel_pstate_driver_lock);
1161		return -EAGAIN;
1162	}
1163
1164	mutex_lock(&intel_pstate_limits_lock);
1165
1166	update_turbo_state();
1167	if (global.turbo_disabled) {
1168		pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n");
1169		mutex_unlock(&intel_pstate_limits_lock);
1170		mutex_unlock(&intel_pstate_driver_lock);
1171		return -EPERM;
1172	}
1173
1174	global.no_turbo = clamp_t(int, input, 0, 1);
1175
1176	if (global.no_turbo) {
1177		struct cpudata *cpu = all_cpu_data[0];
1178		int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate;
1179
1180		/* Squash the global minimum into the permitted range. */
1181		if (global.min_perf_pct > pct)
1182			global.min_perf_pct = pct;
1183	}
1184
1185	mutex_unlock(&intel_pstate_limits_lock);
1186
1187	intel_pstate_update_policies();
1188
1189	mutex_unlock(&intel_pstate_driver_lock);
1190
1191	return count;
1192}
1193
1194static void update_qos_request(enum freq_qos_req_type type)
1195{
1196	int max_state, turbo_max, freq, i, perf_pct;
1197	struct freq_qos_request *req;
1198	struct cpufreq_policy *policy;
1199
1200	for_each_possible_cpu(i) {
1201		struct cpudata *cpu = all_cpu_data[i];
1202
1203		policy = cpufreq_cpu_get(i);
1204		if (!policy)
1205			continue;
1206
1207		req = policy->driver_data;
1208		cpufreq_cpu_put(policy);
1209
1210		if (!req)
1211			continue;
1212
1213		if (hwp_active)
1214			intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
1215		else
1216			turbo_max = cpu->pstate.turbo_pstate;
1217
1218		if (type == FREQ_QOS_MIN) {
1219			perf_pct = global.min_perf_pct;
1220		} else {
1221			req++;
1222			perf_pct = global.max_perf_pct;
1223		}
1224
1225		freq = DIV_ROUND_UP(turbo_max * perf_pct, 100);
1226		freq *= cpu->pstate.scaling;
1227
1228		if (freq_qos_update_request(req, freq) < 0)
1229			pr_warn("Failed to update freq constraint: CPU%d\n", i);
1230	}
1231}
1232
1233static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
1234				  const char *buf, size_t count)
1235{
1236	unsigned int input;
1237	int ret;
1238
1239	ret = sscanf(buf, "%u", &input);
1240	if (ret != 1)
1241		return -EINVAL;
1242
1243	mutex_lock(&intel_pstate_driver_lock);
1244
1245	if (!intel_pstate_driver) {
1246		mutex_unlock(&intel_pstate_driver_lock);
1247		return -EAGAIN;
1248	}
1249
1250	mutex_lock(&intel_pstate_limits_lock);
1251
1252	global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100);
1253
1254	mutex_unlock(&intel_pstate_limits_lock);
1255
1256	if (intel_pstate_driver == &intel_pstate)
1257		intel_pstate_update_policies();
1258	else
1259		update_qos_request(FREQ_QOS_MAX);
1260
1261	mutex_unlock(&intel_pstate_driver_lock);
1262
1263	return count;
1264}
1265
1266static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
1267				  const char *buf, size_t count)
1268{
1269	unsigned int input;
1270	int ret;
1271
1272	ret = sscanf(buf, "%u", &input);
1273	if (ret != 1)
1274		return -EINVAL;
1275
1276	mutex_lock(&intel_pstate_driver_lock);
1277
1278	if (!intel_pstate_driver) {
1279		mutex_unlock(&intel_pstate_driver_lock);
1280		return -EAGAIN;
1281	}
1282
1283	mutex_lock(&intel_pstate_limits_lock);
1284
1285	global.min_perf_pct = clamp_t(int, input,
1286				      min_perf_pct_min(), global.max_perf_pct);
1287
1288	mutex_unlock(&intel_pstate_limits_lock);
1289
1290	if (intel_pstate_driver == &intel_pstate)
1291		intel_pstate_update_policies();
1292	else
1293		update_qos_request(FREQ_QOS_MIN);
1294
1295	mutex_unlock(&intel_pstate_driver_lock);
1296
1297	return count;
1298}
1299
1300static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
1301				struct kobj_attribute *attr, char *buf)
1302{
1303	return sprintf(buf, "%u\n", hwp_boost);
1304}
1305
1306static ssize_t store_hwp_dynamic_boost(struct kobject *a,
1307				       struct kobj_attribute *b,
1308				       const char *buf, size_t count)
1309{
1310	unsigned int input;
1311	int ret;
1312
1313	ret = kstrtouint(buf, 10, &input);
1314	if (ret)
1315		return ret;
1316
1317	mutex_lock(&intel_pstate_driver_lock);
1318	hwp_boost = !!input;
1319	intel_pstate_update_policies();
1320	mutex_unlock(&intel_pstate_driver_lock);
1321
1322	return count;
1323}
1324
1325static ssize_t show_energy_efficiency(struct kobject *kobj, struct kobj_attribute *attr,
1326				      char *buf)
1327{
1328	u64 power_ctl;
1329	int enable;
1330
1331	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
1332	enable = !!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE));
1333	return sprintf(buf, "%d\n", !enable);
1334}
1335
1336static ssize_t store_energy_efficiency(struct kobject *a, struct kobj_attribute *b,
1337				       const char *buf, size_t count)
1338{
1339	bool input;
1340	int ret;
1341
1342	ret = kstrtobool(buf, &input);
1343	if (ret)
1344		return ret;
1345
1346	set_power_ctl_ee_state(input);
1347
1348	return count;
1349}
1350
1351show_one(max_perf_pct, max_perf_pct);
1352show_one(min_perf_pct, min_perf_pct);
1353
1354define_one_global_rw(status);
1355define_one_global_rw(no_turbo);
1356define_one_global_rw(max_perf_pct);
1357define_one_global_rw(min_perf_pct);
1358define_one_global_ro(turbo_pct);
1359define_one_global_ro(num_pstates);
1360define_one_global_rw(hwp_dynamic_boost);
1361define_one_global_rw(energy_efficiency);
1362
1363static struct attribute *intel_pstate_attributes[] = {
1364	&status.attr,
1365	&no_turbo.attr,
1366	&turbo_pct.attr,
1367	&num_pstates.attr,
1368	NULL
1369};
1370
1371static const struct attribute_group intel_pstate_attr_group = {
1372	.attrs = intel_pstate_attributes,
1373};
1374
1375static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[];
1376
1377static struct kobject *intel_pstate_kobject;
1378
1379static void __init intel_pstate_sysfs_expose_params(void)
1380{
1381	int rc;
1382
1383	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
1384						&cpu_subsys.dev_root->kobj);
1385	if (WARN_ON(!intel_pstate_kobject))
1386		return;
1387
1388	rc = sysfs_create_group(intel_pstate_kobject, &intel_pstate_attr_group);
1389	if (WARN_ON(rc))
1390		return;
1391
1392	/*
1393	 * If per cpu limits are enforced there are no global limits, so
1394	 * return without creating max/min_perf_pct attributes
1395	 */
1396	if (per_cpu_limits)
1397		return;
1398
1399	rc = sysfs_create_file(intel_pstate_kobject, &max_perf_pct.attr);
1400	WARN_ON(rc);
1401
1402	rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr);
1403	WARN_ON(rc);
1404
1405	if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids)) {
1406		rc = sysfs_create_file(intel_pstate_kobject, &energy_efficiency.attr);
1407		WARN_ON(rc);
1408	}
1409}
1410
1411static void __init intel_pstate_sysfs_remove(void)
1412{
1413	if (!intel_pstate_kobject)
1414		return;
1415
1416	sysfs_remove_group(intel_pstate_kobject, &intel_pstate_attr_group);
1417
1418	if (!per_cpu_limits) {
1419		sysfs_remove_file(intel_pstate_kobject, &max_perf_pct.attr);
1420		sysfs_remove_file(intel_pstate_kobject, &min_perf_pct.attr);
1421
1422		if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids))
1423			sysfs_remove_file(intel_pstate_kobject, &energy_efficiency.attr);
1424	}
1425
1426	kobject_put(intel_pstate_kobject);
1427}
1428
1429static void intel_pstate_sysfs_expose_hwp_dynamic_boost(void)
1430{
1431	int rc;
1432
1433	if (!hwp_active)
1434		return;
1435
1436	rc = sysfs_create_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
1437	WARN_ON_ONCE(rc);
1438}
1439
1440static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
1441{
1442	if (!hwp_active)
1443		return;
1444
1445	sysfs_remove_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
1446}
1447
1448/************************** sysfs end ************************/
1449
1450static void intel_pstate_hwp_enable(struct cpudata *cpudata)
1451{
1452	/* First disable HWP notification interrupt as we don't process them */
1453	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
1454		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
1455
1456	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
1457	if (cpudata->epp_default == -EINVAL)
1458		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
1459}
1460
1461static int atom_get_min_pstate(void)
1462{
1463	u64 value;
1464
1465	rdmsrl(MSR_ATOM_CORE_RATIOS, value);
1466	return (value >> 8) & 0x7F;
1467}
1468
1469static int atom_get_max_pstate(void)
1470{
1471	u64 value;
1472
1473	rdmsrl(MSR_ATOM_CORE_RATIOS, value);
1474	return (value >> 16) & 0x7F;
1475}
1476
1477static int atom_get_turbo_pstate(void)
1478{
1479	u64 value;
1480
1481	rdmsrl(MSR_ATOM_CORE_TURBO_RATIOS, value);
1482	return value & 0x7F;
1483}
1484
1485static u64 atom_get_val(struct cpudata *cpudata, int pstate)
1486{
1487	u64 val;
1488	int32_t vid_fp;
1489	u32 vid;
1490
1491	val = (u64)pstate << 8;
1492	if (global.no_turbo && !global.turbo_disabled)
1493		val |= (u64)1 << 32;
1494
1495	vid_fp = cpudata->vid.min + mul_fp(
1496		int_tofp(pstate - cpudata->pstate.min_pstate),
1497		cpudata->vid.ratio);
1498
1499	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
1500	vid = ceiling_fp(vid_fp);
1501
1502	if (pstate > cpudata->pstate.max_pstate)
1503		vid = cpudata->vid.turbo;
1504
1505	return val | vid;
1506}
1507
1508static int silvermont_get_scaling(void)
1509{
1510	u64 value;
1511	int i;
1512	/* Defined in Table 35-6 from SDM (Sept 2015) */
1513	static int silvermont_freq_table[] = {
1514		83300, 100000, 133300, 116700, 80000};
1515
1516	rdmsrl(MSR_FSB_FREQ, value);
1517	i = value & 0x7;
1518	WARN_ON(i > 4);
1519
1520	return silvermont_freq_table[i];
1521}
1522
1523static int airmont_get_scaling(void)
1524{
1525	u64 value;
1526	int i;
1527	/* Defined in Table 35-10 from SDM (Sept 2015) */
1528	static int airmont_freq_table[] = {
1529		83300, 100000, 133300, 116700, 80000,
1530		93300, 90000, 88900, 87500};
1531
1532	rdmsrl(MSR_FSB_FREQ, value);
1533	i = value & 0xF;
1534	WARN_ON(i > 8);
1535
1536	return airmont_freq_table[i];
1537}
1538
1539static void atom_get_vid(struct cpudata *cpudata)
1540{
1541	u64 value;
1542
1543	rdmsrl(MSR_ATOM_CORE_VIDS, value);
1544	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
1545	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
1546	cpudata->vid.ratio = div_fp(
1547		cpudata->vid.max - cpudata->vid.min,
1548		int_tofp(cpudata->pstate.max_pstate -
1549			cpudata->pstate.min_pstate));
1550
1551	rdmsrl(MSR_ATOM_CORE_TURBO_VIDS, value);
1552	cpudata->vid.turbo = value & 0x7f;
1553}
1554
1555static int core_get_min_pstate(void)
1556{
1557	u64 value;
1558
1559	rdmsrl(MSR_PLATFORM_INFO, value);
1560	return (value >> 40) & 0xFF;
1561}
1562
1563static int core_get_max_pstate_physical(void)
1564{
1565	u64 value;
1566
1567	rdmsrl(MSR_PLATFORM_INFO, value);
1568	return (value >> 8) & 0xFF;
1569}
1570
1571static int core_get_tdp_ratio(u64 plat_info)
1572{
1573	/* Check how many TDP levels present */
1574	if (plat_info & 0x600000000) {
1575		u64 tdp_ctrl;
1576		u64 tdp_ratio;
1577		int tdp_msr;
1578		int err;
1579
1580		/* Get the TDP level (0, 1, 2) to get ratios */
1581		err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
1582		if (err)
1583			return err;
1584
1585		/* TDP MSR are continuous starting at 0x648 */
1586		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
1587		err = rdmsrl_safe(tdp_msr, &tdp_ratio);
1588		if (err)
1589			return err;
1590
1591		/* For level 1 and 2, bits[23:16] contain the ratio */
1592		if (tdp_ctrl & 0x03)
1593			tdp_ratio >>= 16;
1594
1595		tdp_ratio &= 0xff; /* ratios are only 8 bits long */
1596		pr_debug("tdp_ratio %x\n", (int)tdp_ratio);
1597
1598		return (int)tdp_ratio;
1599	}
1600
1601	return -ENXIO;
1602}
1603
1604static int core_get_max_pstate(void)
1605{
1606	u64 tar;
1607	u64 plat_info;
1608	int max_pstate;
1609	int tdp_ratio;
1610	int err;
1611
1612	rdmsrl(MSR_PLATFORM_INFO, plat_info);
1613	max_pstate = (plat_info >> 8) & 0xFF;
1614
1615	tdp_ratio = core_get_tdp_ratio(plat_info);
1616	if (tdp_ratio <= 0)
1617		return max_pstate;
1618
1619	if (hwp_active) {
1620		/* Turbo activation ratio is not used on HWP platforms */
1621		return tdp_ratio;
1622	}
1623
1624	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
1625	if (!err) {
1626		int tar_levels;
1627
1628		/* Do some sanity checking for safety */
1629		tar_levels = tar & 0xff;
1630		if (tdp_ratio - 1 == tar_levels) {
1631			max_pstate = tar_levels;
1632			pr_debug("max_pstate=TAC %x\n", max_pstate);
1633		}
1634	}
1635
1636	return max_pstate;
1637}
1638
1639static int core_get_turbo_pstate(void)
1640{
1641	u64 value;
1642	int nont, ret;
1643
1644	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
1645	nont = core_get_max_pstate();
1646	ret = (value) & 255;
1647	if (ret <= nont)
1648		ret = nont;
1649	return ret;
1650}
1651
1652static inline int core_get_scaling(void)
1653{
1654	return 100000;
1655}
1656
1657static u64 core_get_val(struct cpudata *cpudata, int pstate)
1658{
1659	u64 val;
1660
1661	val = (u64)pstate << 8;
1662	if (global.no_turbo && !global.turbo_disabled)
1663		val |= (u64)1 << 32;
1664
1665	return val;
1666}
1667
1668static int knl_get_aperf_mperf_shift(void)
1669{
1670	return 10;
1671}
1672
1673static int knl_get_turbo_pstate(void)
1674{
1675	u64 value;
1676	int nont, ret;
1677
1678	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
1679	nont = core_get_max_pstate();
1680	ret = (((value) >> 8) & 0xFF);
1681	if (ret <= nont)
1682		ret = nont;
1683	return ret;
1684}
1685
1686static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
1687{
1688	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
1689	cpu->pstate.current_pstate = pstate;
1690	/*
1691	 * Generally, there is no guarantee that this code will always run on
1692	 * the CPU being updated, so force the register update to run on the
1693	 * right CPU.
1694	 */
1695	wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
1696		      pstate_funcs.get_val(cpu, pstate));
1697}
1698
1699static void intel_pstate_set_min_pstate(struct cpudata *cpu)
1700{
1701	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
1702}
1703
1704static void intel_pstate_max_within_limits(struct cpudata *cpu)
1705{
1706	int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
1707
1708	update_turbo_state();
1709	intel_pstate_set_pstate(cpu, pstate);
1710}
1711
1712static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
1713{
1714	cpu->pstate.min_pstate = pstate_funcs.get_min();
1715	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
1716	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
1717	cpu->pstate.scaling = pstate_funcs.get_scaling();
1718
1719	if (hwp_active && !hwp_mode_bdw) {
1720		unsigned int phy_max, current_max;
1721
1722		intel_pstate_get_hwp_max(cpu, &phy_max, &current_max);
1723		cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
1724		cpu->pstate.turbo_pstate = phy_max;
1725		cpu->pstate.max_pstate = HWP_GUARANTEED_PERF(READ_ONCE(cpu->hwp_cap_cached));
1726	} else {
1727		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
1728		cpu->pstate.max_pstate = pstate_funcs.get_max();
1729	}
1730	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
1731
1732	if (pstate_funcs.get_aperf_mperf_shift)
1733		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
1734
1735	if (pstate_funcs.get_vid)
1736		pstate_funcs.get_vid(cpu);
1737
1738	intel_pstate_set_min_pstate(cpu);
1739}
1740
1741/*
1742 * Long hold time will keep high perf limits for long time,
1743 * which negatively impacts perf/watt for some workloads,
1744 * like specpower. 3ms is based on experiements on some
1745 * workoads.
1746 */
1747static int hwp_boost_hold_time_ns = 3 * NSEC_PER_MSEC;
1748
1749static inline void intel_pstate_hwp_boost_up(struct cpudata *cpu)
1750{
1751	u64 hwp_req = READ_ONCE(cpu->hwp_req_cached);
1752	u32 max_limit = (hwp_req & 0xff00) >> 8;
1753	u32 min_limit = (hwp_req & 0xff);
1754	u32 boost_level1;
1755
1756	/*
1757	 * Cases to consider (User changes via sysfs or boot time):
1758	 * If, P0 (Turbo max) = P1 (Guaranteed max) = min:
1759	 *	No boost, return.
1760	 * If, P0 (Turbo max) > P1 (Guaranteed max) = min:
1761	 *     Should result in one level boost only for P0.
1762	 * If, P0 (Turbo max) = P1 (Guaranteed max) > min:
1763	 *     Should result in two level boost:
1764	 *         (min + p1)/2 and P1.
1765	 * If, P0 (Turbo max) > P1 (Guaranteed max) > min:
1766	 *     Should result in three level boost:
1767	 *        (min + p1)/2, P1 and P0.
1768	 */
1769
1770	/* If max and min are equal or already at max, nothing to boost */
1771	if (max_limit == min_limit || cpu->hwp_boost_min >= max_limit)
1772		return;
1773
1774	if (!cpu->hwp_boost_min)
1775		cpu->hwp_boost_min = min_limit;
1776
1777	/* level at half way mark between min and guranteed */
1778	boost_level1 = (HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) + min_limit) >> 1;
1779
1780	if (cpu->hwp_boost_min < boost_level1)
1781		cpu->hwp_boost_min = boost_level1;
1782	else if (cpu->hwp_boost_min < HWP_GUARANTEED_PERF(cpu->hwp_cap_cached))
1783		cpu->hwp_boost_min = HWP_GUARANTEED_PERF(cpu->hwp_cap_cached);
1784	else if (cpu->hwp_boost_min == HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) &&
1785		 max_limit != HWP_GUARANTEED_PERF(cpu->hwp_cap_cached))
1786		cpu->hwp_boost_min = max_limit;
1787	else
1788		return;
1789
1790	hwp_req = (hwp_req & ~GENMASK_ULL(7, 0)) | cpu->hwp_boost_min;
1791	wrmsrl(MSR_HWP_REQUEST, hwp_req);
1792	cpu->last_update = cpu->sample.time;
1793}
1794
1795static inline void intel_pstate_hwp_boost_down(struct cpudata *cpu)
1796{
1797	if (cpu->hwp_boost_min) {
1798		bool expired;
1799
1800		/* Check if we are idle for hold time to boost down */
1801		expired = time_after64(cpu->sample.time, cpu->last_update +
1802				       hwp_boost_hold_time_ns);
1803		if (expired) {
1804			wrmsrl(MSR_HWP_REQUEST, cpu->hwp_req_cached);
1805			cpu->hwp_boost_min = 0;
1806		}
1807	}
1808	cpu->last_update = cpu->sample.time;
1809}
1810
1811static inline void intel_pstate_update_util_hwp_local(struct cpudata *cpu,
1812						      u64 time)
1813{
1814	cpu->sample.time = time;
1815
1816	if (cpu->sched_flags & SCHED_CPUFREQ_IOWAIT) {
1817		bool do_io = false;
1818
1819		cpu->sched_flags = 0;
1820		/*
1821		 * Set iowait_boost flag and update time. Since IO WAIT flag
1822		 * is set all the time, we can't just conclude that there is
1823		 * some IO bound activity is scheduled on this CPU with just
1824		 * one occurrence. If we receive at least two in two
1825		 * consecutive ticks, then we treat as boost candidate.
1826		 */
1827		if (time_before64(time, cpu->last_io_update + 2 * TICK_NSEC))
1828			do_io = true;
1829
1830		cpu->last_io_update = time;
1831
1832		if (do_io)
1833			intel_pstate_hwp_boost_up(cpu);
1834
1835	} else {
1836		intel_pstate_hwp_boost_down(cpu);
1837	}
1838}
1839
1840static inline void intel_pstate_update_util_hwp(struct update_util_data *data,
1841						u64 time, unsigned int flags)
1842{
1843	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
1844
1845	cpu->sched_flags |= flags;
1846
1847	if (smp_processor_id() == cpu->cpu)
1848		intel_pstate_update_util_hwp_local(cpu, time);
1849}
1850
1851static inline void intel_pstate_calc_avg_perf(struct cpudata *cpu)
1852{
1853	struct sample *sample = &cpu->sample;
1854
1855	sample->core_avg_perf = div_ext_fp(sample->aperf, sample->mperf);
1856}
1857
1858static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
1859{
1860	u64 aperf, mperf;
1861	unsigned long flags;
1862	u64 tsc;
1863
1864	local_irq_save(flags);
1865	rdmsrl(MSR_IA32_APERF, aperf);
1866	rdmsrl(MSR_IA32_MPERF, mperf);
1867	tsc = rdtsc();
1868	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
1869		local_irq_restore(flags);
1870		return false;
1871	}
1872	local_irq_restore(flags);
1873
1874	cpu->last_sample_time = cpu->sample.time;
1875	cpu->sample.time = time;
1876	cpu->sample.aperf = aperf;
1877	cpu->sample.mperf = mperf;
1878	cpu->sample.tsc =  tsc;
1879	cpu->sample.aperf -= cpu->prev_aperf;
1880	cpu->sample.mperf -= cpu->prev_mperf;
1881	cpu->sample.tsc -= cpu->prev_tsc;
1882
1883	cpu->prev_aperf = aperf;
1884	cpu->prev_mperf = mperf;
1885	cpu->prev_tsc = tsc;
1886	/*
1887	 * First time this function is invoked in a given cycle, all of the
1888	 * previous sample data fields are equal to zero or stale and they must
1889	 * be populated with meaningful numbers for things to work, so assume
1890	 * that sample.time will always be reset before setting the utilization
1891	 * update hook and make the caller skip the sample then.
1892	 */
1893	if (cpu->last_sample_time) {
1894		intel_pstate_calc_avg_perf(cpu);
1895		return true;
1896	}
1897	return false;
1898}
1899
1900static inline int32_t get_avg_frequency(struct cpudata *cpu)
1901{
1902	return mul_ext_fp(cpu->sample.core_avg_perf, cpu_khz);
1903}
1904
1905static inline int32_t get_avg_pstate(struct cpudata *cpu)
1906{
1907	return mul_ext_fp(cpu->pstate.max_pstate_physical,
1908			  cpu->sample.core_avg_perf);
1909}
1910
1911static inline int32_t get_target_pstate(struct cpudata *cpu)
1912{
1913	struct sample *sample = &cpu->sample;
1914	int32_t busy_frac;
1915	int target, avg_pstate;
1916
1917	busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift,
1918			   sample->tsc);
1919
1920	if (busy_frac < cpu->iowait_boost)
1921		busy_frac = cpu->iowait_boost;
1922
1923	sample->busy_scaled = busy_frac * 100;
1924
1925	target = global.no_turbo || global.turbo_disabled ?
1926			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
1927	target += target >> 2;
1928	target = mul_fp(target, busy_frac);
1929	if (target < cpu->pstate.min_pstate)
1930		target = cpu->pstate.min_pstate;
1931
1932	/*
1933	 * If the average P-state during the previous cycle was higher than the
1934	 * current target, add 50% of the difference to the target to reduce
1935	 * possible performance oscillations and offset possible performance
1936	 * loss related to moving the workload from one CPU to another within
1937	 * a package/module.
1938	 */
1939	avg_pstate = get_avg_pstate(cpu);
1940	if (avg_pstate > target)
1941		target += (avg_pstate - target) >> 1;
1942
1943	return target;
1944}
1945
1946static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
1947{
1948	int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
1949	int max_pstate = max(min_pstate, cpu->max_perf_ratio);
1950
1951	return clamp_t(int, pstate, min_pstate, max_pstate);
1952}
1953
1954static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
1955{
1956	if (pstate == cpu->pstate.current_pstate)
1957		return;
1958
1959	cpu->pstate.current_pstate = pstate;
1960	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
1961}
1962
1963static void intel_pstate_adjust_pstate(struct cpudata *cpu)
1964{
1965	int from = cpu->pstate.current_pstate;
1966	struct sample *sample;
1967	int target_pstate;
1968
1969	update_turbo_state();
1970
1971	target_pstate = get_target_pstate(cpu);
1972	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
1973	trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
1974	intel_pstate_update_pstate(cpu, target_pstate);
1975
1976	sample = &cpu->sample;
1977	trace_pstate_sample(mul_ext_fp(100, sample->core_avg_perf),
1978		fp_toint(sample->busy_scaled),
1979		from,
1980		cpu->pstate.current_pstate,
1981		sample->mperf,
1982		sample->aperf,
1983		sample->tsc,
1984		get_avg_frequency(cpu),
1985		fp_toint(cpu->iowait_boost * 100));
1986}
1987
1988static void intel_pstate_update_util(struct update_util_data *data, u64 time,
1989				     unsigned int flags)
1990{
1991	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
1992	u64 delta_ns;
1993
1994	/* Don't allow remote callbacks */
1995	if (smp_processor_id() != cpu->cpu)
1996		return;
1997
1998	delta_ns = time - cpu->last_update;
1999	if (flags & SCHED_CPUFREQ_IOWAIT) {
2000		/* Start over if the CPU may have been idle. */
2001		if (delta_ns > TICK_NSEC) {
2002			cpu->iowait_boost = ONE_EIGHTH_FP;
2003		} else if (cpu->iowait_boost >= ONE_EIGHTH_FP) {
2004			cpu->iowait_boost <<= 1;
2005			if (cpu->iowait_boost > int_tofp(1))
2006				cpu->iowait_boost = int_tofp(1);
2007		} else {
2008			cpu->iowait_boost = ONE_EIGHTH_FP;
2009		}
2010	} else if (cpu->iowait_boost) {
2011		/* Clear iowait_boost if the CPU may have been idle. */
2012		if (delta_ns > TICK_NSEC)
2013			cpu->iowait_boost = 0;
2014		else
2015			cpu->iowait_boost >>= 1;
2016	}
2017	cpu->last_update = time;
2018	delta_ns = time - cpu->sample.time;
2019	if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL)
2020		return;
2021
2022	if (intel_pstate_sample(cpu, time))
2023		intel_pstate_adjust_pstate(cpu);
2024}
2025
2026static struct pstate_funcs core_funcs = {
2027	.get_max = core_get_max_pstate,
2028	.get_max_physical = core_get_max_pstate_physical,
2029	.get_min = core_get_min_pstate,
2030	.get_turbo = core_get_turbo_pstate,
2031	.get_scaling = core_get_scaling,
2032	.get_val = core_get_val,
2033};
2034
2035static const struct pstate_funcs silvermont_funcs = {
2036	.get_max = atom_get_max_pstate,
2037	.get_max_physical = atom_get_max_pstate,
2038	.get_min = atom_get_min_pstate,
2039	.get_turbo = atom_get_turbo_pstate,
2040	.get_val = atom_get_val,
2041	.get_scaling = silvermont_get_scaling,
2042	.get_vid = atom_get_vid,
2043};
2044
2045static const struct pstate_funcs airmont_funcs = {
2046	.get_max = atom_get_max_pstate,
2047	.get_max_physical = atom_get_max_pstate,
2048	.get_min = atom_get_min_pstate,
2049	.get_turbo = atom_get_turbo_pstate,
2050	.get_val = atom_get_val,
2051	.get_scaling = airmont_get_scaling,
2052	.get_vid = atom_get_vid,
2053};
2054
2055static const struct pstate_funcs knl_funcs = {
2056	.get_max = core_get_max_pstate,
2057	.get_max_physical = core_get_max_pstate_physical,
2058	.get_min = core_get_min_pstate,
2059	.get_turbo = knl_get_turbo_pstate,
2060	.get_aperf_mperf_shift = knl_get_aperf_mperf_shift,
2061	.get_scaling = core_get_scaling,
2062	.get_val = core_get_val,
2063};
2064
2065#define X86_MATCH(model, policy)					 \
2066	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
2067					   X86_FEATURE_APERFMPERF, &policy)
2068
2069static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
2070	X86_MATCH(SANDYBRIDGE,		core_funcs),
2071	X86_MATCH(SANDYBRIDGE_X,	core_funcs),
2072	X86_MATCH(ATOM_SILVERMONT,	silvermont_funcs),
2073	X86_MATCH(IVYBRIDGE,		core_funcs),
2074	X86_MATCH(HASWELL,		core_funcs),
2075	X86_MATCH(BROADWELL,		core_funcs),
2076	X86_MATCH(IVYBRIDGE_X,		core_funcs),
2077	X86_MATCH(HASWELL_X,		core_funcs),
2078	X86_MATCH(HASWELL_L,		core_funcs),
2079	X86_MATCH(HASWELL_G,		core_funcs),
2080	X86_MATCH(BROADWELL_G,		core_funcs),
2081	X86_MATCH(ATOM_AIRMONT,		airmont_funcs),
2082	X86_MATCH(SKYLAKE_L,		core_funcs),
2083	X86_MATCH(BROADWELL_X,		core_funcs),
2084	X86_MATCH(SKYLAKE,		core_funcs),
2085	X86_MATCH(BROADWELL_D,		core_funcs),
2086	X86_MATCH(XEON_PHI_KNL,		knl_funcs),
2087	X86_MATCH(XEON_PHI_KNM,		knl_funcs),
2088	X86_MATCH(ATOM_GOLDMONT,	core_funcs),
2089	X86_MATCH(ATOM_GOLDMONT_PLUS,	core_funcs),
2090	X86_MATCH(SKYLAKE_X,		core_funcs),
2091	{}
2092};
2093MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
2094
2095static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
2096	X86_MATCH(BROADWELL_D,		core_funcs),
2097	X86_MATCH(BROADWELL_X,		core_funcs),
2098	X86_MATCH(SKYLAKE_X,		core_funcs),
2099	{}
2100};
2101
2102static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
2103	X86_MATCH(KABYLAKE,		core_funcs),
2104	{}
2105};
2106
2107static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
2108	X86_MATCH(SKYLAKE_X,		core_funcs),
2109	X86_MATCH(SKYLAKE,		core_funcs),
2110	{}
2111};
2112
2113static int intel_pstate_init_cpu(unsigned int cpunum)
2114{
2115	struct cpudata *cpu;
2116
2117	cpu = all_cpu_data[cpunum];
2118
2119	if (!cpu) {
2120		cpu = kzalloc(sizeof(*cpu), GFP_KERNEL);
2121		if (!cpu)
2122			return -ENOMEM;
2123
2124		all_cpu_data[cpunum] = cpu;
2125
2126		cpu->cpu = cpunum;
2127
2128		cpu->epp_default = -EINVAL;
2129
2130		if (hwp_active) {
2131			const struct x86_cpu_id *id;
2132
2133			intel_pstate_hwp_enable(cpu);
2134
2135			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
2136			if (id && intel_pstate_acpi_pm_profile_server())
2137				hwp_boost = true;
2138		}
2139	} else if (hwp_active) {
2140		/*
2141		 * Re-enable HWP in case this happens after a resume from ACPI
2142		 * S3 if the CPU was offline during the whole system/resume
2143		 * cycle.
2144		 */
2145		intel_pstate_hwp_reenable(cpu);
2146	}
2147
2148	cpu->epp_powersave = -EINVAL;
2149	cpu->epp_policy = 0;
2150
2151	intel_pstate_get_cpu_pstates(cpu);
2152
2153	pr_debug("controlling: cpu %d\n", cpunum);
2154
2155	return 0;
2156}
2157
2158static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
2159{
2160	struct cpudata *cpu = all_cpu_data[cpu_num];
2161
2162	if (hwp_active && !hwp_boost)
2163		return;
2164
2165	if (cpu->update_util_set)
2166		return;
2167
2168	/* Prevent intel_pstate_update_util() from using stale data. */
2169	cpu->sample.time = 0;
2170	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
2171				     (hwp_active ?
2172				      intel_pstate_update_util_hwp :
2173				      intel_pstate_update_util));
2174	cpu->update_util_set = true;
2175}
2176
2177static void intel_pstate_clear_update_util_hook(unsigned int cpu)
2178{
2179	struct cpudata *cpu_data = all_cpu_data[cpu];
2180
2181	if (!cpu_data->update_util_set)
2182		return;
2183
2184	cpufreq_remove_update_util_hook(cpu);
2185	cpu_data->update_util_set = false;
2186	synchronize_rcu();
2187}
2188
2189static int intel_pstate_get_max_freq(struct cpudata *cpu)
2190{
2191	return global.turbo_disabled || global.no_turbo ?
2192			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
2193}
2194
2195static void intel_pstate_update_perf_limits(struct cpudata *cpu,
2196					    unsigned int policy_min,
2197					    unsigned int policy_max)
2198{
2199	int32_t max_policy_perf, min_policy_perf;
2200	int max_state, turbo_max;
2201	int max_freq;
2202
2203	/*
2204	 * HWP needs some special consideration, because on BDX the
2205	 * HWP_REQUEST uses abstract value to represent performance
2206	 * rather than pure ratios.
2207	 */
2208	if (hwp_active) {
2209		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
2210	} else {
2211		max_state = global.no_turbo || global.turbo_disabled ?
2212			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
2213		turbo_max = cpu->pstate.turbo_pstate;
2214	}
2215	max_freq = max_state * cpu->pstate.scaling;
2216
2217	max_policy_perf = max_state * policy_max / max_freq;
2218	if (policy_max == policy_min) {
2219		min_policy_perf = max_policy_perf;
2220	} else {
2221		min_policy_perf = max_state * policy_min / max_freq;
2222		min_policy_perf = clamp_t(int32_t, min_policy_perf,
2223					  0, max_policy_perf);
2224	}
2225
2226	pr_debug("cpu:%d max_state %d min_policy_perf:%d max_policy_perf:%d\n",
2227		 cpu->cpu, max_state, min_policy_perf, max_policy_perf);
2228
2229	/* Normalize user input to [min_perf, max_perf] */
2230	if (per_cpu_limits) {
2231		cpu->min_perf_ratio = min_policy_perf;
2232		cpu->max_perf_ratio = max_policy_perf;
2233	} else {
2234		int32_t global_min, global_max;
2235
2236		/* Global limits are in percent of the maximum turbo P-state. */
2237		global_max = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
2238		global_min = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
2239		global_min = clamp_t(int32_t, global_min, 0, global_max);
2240
2241		pr_debug("cpu:%d global_min:%d global_max:%d\n", cpu->cpu,
2242			 global_min, global_max);
2243
2244		cpu->min_perf_ratio = max(min_policy_perf, global_min);
2245		cpu->min_perf_ratio = min(cpu->min_perf_ratio, max_policy_perf);
2246		cpu->max_perf_ratio = min(max_policy_perf, global_max);
2247		cpu->max_perf_ratio = max(min_policy_perf, cpu->max_perf_ratio);
2248
2249		/* Make sure min_perf <= max_perf */
2250		cpu->min_perf_ratio = min(cpu->min_perf_ratio,
2251					  cpu->max_perf_ratio);
2252
2253	}
2254	pr_debug("cpu:%d max_perf_ratio:%d min_perf_ratio:%d\n", cpu->cpu,
2255		 cpu->max_perf_ratio,
2256		 cpu->min_perf_ratio);
2257}
2258
2259static int intel_pstate_set_policy(struct cpufreq_policy *policy)
2260{
2261	struct cpudata *cpu;
2262
2263	if (!policy->cpuinfo.max_freq)
2264		return -ENODEV;
2265
2266	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
2267		 policy->cpuinfo.max_freq, policy->max);
2268
2269	cpu = all_cpu_data[policy->cpu];
2270	cpu->policy = policy->policy;
2271
2272	mutex_lock(&intel_pstate_limits_lock);
2273
2274	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
2275
2276	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
2277		/*
2278		 * NOHZ_FULL CPUs need this as the governor callback may not
2279		 * be invoked on them.
2280		 */
2281		intel_pstate_clear_update_util_hook(policy->cpu);
2282		intel_pstate_max_within_limits(cpu);
2283	} else {
2284		intel_pstate_set_update_util_hook(policy->cpu);
2285	}
2286
2287	if (hwp_active) {
2288		/*
2289		 * When hwp_boost was active before and dynamically it
2290		 * was turned off, in that case we need to clear the
2291		 * update util hook.
2292		 */
2293		if (!hwp_boost)
2294			intel_pstate_clear_update_util_hook(policy->cpu);
2295		intel_pstate_hwp_set(policy->cpu);
2296	}
2297
2298	mutex_unlock(&intel_pstate_limits_lock);
2299
2300	return 0;
2301}
2302
2303static void intel_pstate_adjust_policy_max(struct cpudata *cpu,
2304					   struct cpufreq_policy_data *policy)
2305{
2306	if (!hwp_active &&
2307	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
2308	    policy->max < policy->cpuinfo.max_freq &&
2309	    policy->max > cpu->pstate.max_freq) {
2310		pr_debug("policy->max > max non turbo frequency\n");
2311		policy->max = policy->cpuinfo.max_freq;
2312	}
2313}
2314
2315static void intel_pstate_verify_cpu_policy(struct cpudata *cpu,
2316					   struct cpufreq_policy_data *policy)
2317{
2318	int max_freq;
2319
2320	update_turbo_state();
2321	if (hwp_active) {
2322		int max_state, turbo_max;
2323
2324		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
2325		max_freq = max_state * cpu->pstate.scaling;
2326	} else {
2327		max_freq = intel_pstate_get_max_freq(cpu);
2328	}
2329	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, max_freq);
2330
2331	intel_pstate_adjust_policy_max(cpu, policy);
2332}
2333
2334static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
2335{
2336	intel_pstate_verify_cpu_policy(all_cpu_data[policy->cpu], policy);
2337
2338	return 0;
2339}
2340
2341static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
2342{
2343	struct cpudata *cpu = all_cpu_data[policy->cpu];
2344
2345	pr_debug("CPU %d going offline\n", cpu->cpu);
2346
2347	if (cpu->suspended)
2348		return 0;
2349
2350	/*
2351	 * If the CPU is an SMT thread and it goes offline with the performance
2352	 * settings different from the minimum, it will prevent its sibling
2353	 * from getting to lower performance levels, so force the minimum
2354	 * performance on CPU offline to prevent that from happening.
2355	 */
2356	if (hwp_active)
2357		intel_pstate_hwp_offline(cpu);
2358	else
2359		intel_pstate_set_min_pstate(cpu);
2360
2361	intel_pstate_exit_perf_limits(policy);
2362
2363	return 0;
2364}
2365
2366static int intel_pstate_cpu_online(struct cpufreq_policy *policy)
2367{
2368	struct cpudata *cpu = all_cpu_data[policy->cpu];
2369
2370	pr_debug("CPU %d going online\n", cpu->cpu);
2371
2372	intel_pstate_init_acpi_perf_limits(policy);
2373
2374	if (hwp_active) {
2375		/*
2376		 * Re-enable HWP and clear the "suspended" flag to let "resume"
2377		 * know that it need not do that.
2378		 */
2379		intel_pstate_hwp_reenable(cpu);
2380		cpu->suspended = false;
2381	}
2382
2383	return 0;
2384}
2385
2386static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
2387{
2388	pr_debug("CPU %d stopping\n", policy->cpu);
2389
2390	intel_pstate_clear_update_util_hook(policy->cpu);
2391}
2392
2393static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
2394{
2395	pr_debug("CPU %d exiting\n", policy->cpu);
2396
2397	policy->fast_switch_possible = false;
2398
2399	return 0;
2400}
2401
2402static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
2403{
2404	struct cpudata *cpu;
2405	int rc;
2406
2407	rc = intel_pstate_init_cpu(policy->cpu);
2408	if (rc)
2409		return rc;
2410
2411	cpu = all_cpu_data[policy->cpu];
2412
2413	cpu->max_perf_ratio = 0xFF;
2414	cpu->min_perf_ratio = 0;
2415
2416	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
2417	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
2418
2419	/* cpuinfo and default policy values */
2420	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
2421	update_turbo_state();
2422	global.turbo_disabled_mf = global.turbo_disabled;
2423	policy->cpuinfo.max_freq = global.turbo_disabled ?
2424			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
2425	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
2426
2427	if (hwp_active) {
2428		unsigned int max_freq;
2429
2430		max_freq = global.turbo_disabled ?
2431			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
2432		if (max_freq < policy->cpuinfo.max_freq)
2433			policy->cpuinfo.max_freq = max_freq;
2434	}
2435
2436	intel_pstate_init_acpi_perf_limits(policy);
2437
2438	policy->fast_switch_possible = true;
2439
2440	return 0;
2441}
2442
2443static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
2444{
2445	int ret = __intel_pstate_cpu_init(policy);
2446
2447	if (ret)
2448		return ret;
2449
2450	/*
2451	 * Set the policy to powersave to provide a valid fallback value in case
2452	 * the default cpufreq governor is neither powersave nor performance.
2453	 */
2454	policy->policy = CPUFREQ_POLICY_POWERSAVE;
2455
2456	if (hwp_active) {
2457		struct cpudata *cpu = all_cpu_data[policy->cpu];
2458
2459		cpu->epp_cached = intel_pstate_get_epp(cpu, 0);
2460	}
2461
2462	return 0;
2463}
2464
2465static struct cpufreq_driver intel_pstate = {
2466	.flags		= CPUFREQ_CONST_LOOPS,
2467	.verify		= intel_pstate_verify_policy,
2468	.setpolicy	= intel_pstate_set_policy,
2469	.suspend	= intel_pstate_suspend,
2470	.resume		= intel_pstate_resume,
2471	.init		= intel_pstate_cpu_init,
2472	.exit		= intel_pstate_cpu_exit,
2473	.stop_cpu	= intel_pstate_stop_cpu,
2474	.offline	= intel_pstate_cpu_offline,
2475	.online		= intel_pstate_cpu_online,
2476	.update_limits	= intel_pstate_update_limits,
2477	.name		= "intel_pstate",
2478};
2479
2480static int intel_cpufreq_verify_policy(struct cpufreq_policy_data *policy)
2481{
2482	struct cpudata *cpu = all_cpu_data[policy->cpu];
2483
2484	intel_pstate_verify_cpu_policy(cpu, policy);
2485	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
2486
2487	return 0;
2488}
2489
2490/* Use of trace in passive mode:
2491 *
2492 * In passive mode the trace core_busy field (also known as the
2493 * performance field, and lablelled as such on the graphs; also known as
2494 * core_avg_perf) is not needed and so is re-assigned to indicate if the
2495 * driver call was via the normal or fast switch path. Various graphs
2496 * output from the intel_pstate_tracer.py utility that include core_busy
2497 * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%,
2498 * so we use 10 to indicate the the normal path through the driver, and
2499 * 90 to indicate the fast switch path through the driver.
2500 * The scaled_busy field is not used, and is set to 0.
2501 */
2502
2503#define	INTEL_PSTATE_TRACE_TARGET 10
2504#define	INTEL_PSTATE_TRACE_FAST_SWITCH 90
2505
2506static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, int old_pstate)
2507{
2508	struct sample *sample;
2509
2510	if (!trace_pstate_sample_enabled())
2511		return;
2512
2513	if (!intel_pstate_sample(cpu, ktime_get()))
2514		return;
2515
2516	sample = &cpu->sample;
2517	trace_pstate_sample(trace_type,
2518		0,
2519		old_pstate,
2520		cpu->pstate.current_pstate,
2521		sample->mperf,
2522		sample->aperf,
2523		sample->tsc,
2524		get_avg_frequency(cpu),
2525		fp_toint(cpu->iowait_boost * 100));
2526}
2527
2528static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
2529				     bool strict, bool fast_switch)
2530{
2531	u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
2532
2533	value &= ~HWP_MIN_PERF(~0L);
2534	value |= HWP_MIN_PERF(target_pstate);
2535
2536	/*
2537	 * The entire MSR needs to be updated in order to update the HWP min
2538	 * field in it, so opportunistically update the max too if needed.
2539	 */
2540	value &= ~HWP_MAX_PERF(~0L);
2541	value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio);
2542
2543	if (value == prev)
2544		return;
2545
2546	WRITE_ONCE(cpu->hwp_req_cached, value);
2547	if (fast_switch)
2548		wrmsrl(MSR_HWP_REQUEST, value);
2549	else
2550		wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
2551}
2552
2553static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu,
2554					  u32 target_pstate, bool fast_switch)
2555{
2556	if (fast_switch)
2557		wrmsrl(MSR_IA32_PERF_CTL,
2558		       pstate_funcs.get_val(cpu, target_pstate));
2559	else
2560		wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
2561			      pstate_funcs.get_val(cpu, target_pstate));
2562}
2563
2564static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
2565				       int target_pstate, bool fast_switch)
2566{
2567	struct cpudata *cpu = all_cpu_data[policy->cpu];
2568	int old_pstate = cpu->pstate.current_pstate;
2569
2570	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
2571	if (hwp_active) {
2572		intel_cpufreq_adjust_hwp(cpu, target_pstate,
2573					 policy->strict_target, fast_switch);
2574		cpu->pstate.current_pstate = target_pstate;
2575	} else if (target_pstate != old_pstate) {
2576		intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
2577		cpu->pstate.current_pstate = target_pstate;
2578	}
2579
2580	intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
2581			    INTEL_PSTATE_TRACE_TARGET, old_pstate);
2582
2583	return target_pstate;
2584}
2585
2586static int intel_cpufreq_target(struct cpufreq_policy *policy,
2587				unsigned int target_freq,
2588				unsigned int relation)
2589{
2590	struct cpudata *cpu = all_cpu_data[policy->cpu];
2591	struct cpufreq_freqs freqs;
2592	int target_pstate;
2593
2594	update_turbo_state();
2595
2596	freqs.old = policy->cur;
2597	freqs.new = target_freq;
2598
2599	cpufreq_freq_transition_begin(policy, &freqs);
2600
2601	switch (relation) {
2602	case CPUFREQ_RELATION_L:
2603		target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling);
2604		break;
2605	case CPUFREQ_RELATION_H:
2606		target_pstate = freqs.new / cpu->pstate.scaling;
2607		break;
2608	default:
2609		target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling);
2610		break;
2611	}
2612
2613	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
2614
2615	freqs.new = target_pstate * cpu->pstate.scaling;
2616
2617	cpufreq_freq_transition_end(policy, &freqs, false);
2618
2619	return 0;
2620}
2621
2622static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
2623					      unsigned int target_freq)
2624{
2625	struct cpudata *cpu = all_cpu_data[policy->cpu];
2626	int target_pstate;
2627
2628	update_turbo_state();
2629
2630	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
2631
2632	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
2633
2634	return target_pstate * cpu->pstate.scaling;
2635}
2636
2637static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
2638{
2639	int max_state, turbo_max, min_freq, max_freq, ret;
2640	struct freq_qos_request *req;
2641	struct cpudata *cpu;
2642	struct device *dev;
2643
2644	dev = get_cpu_device(policy->cpu);
2645	if (!dev)
2646		return -ENODEV;
2647
2648	ret = __intel_pstate_cpu_init(policy);
2649	if (ret)
2650		return ret;
2651
2652	policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
2653	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
2654	policy->cur = policy->cpuinfo.min_freq;
2655
2656	req = kcalloc(2, sizeof(*req), GFP_KERNEL);
2657	if (!req) {
2658		ret = -ENOMEM;
2659		goto pstate_exit;
2660	}
2661
2662	cpu = all_cpu_data[policy->cpu];
2663
2664	if (hwp_active) {
2665		u64 value;
2666
2667		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
2668		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;
2669		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
2670		WRITE_ONCE(cpu->hwp_req_cached, value);
2671		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
2672	} else {
2673		turbo_max = cpu->pstate.turbo_pstate;
2674		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
2675	}
2676
2677	min_freq = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
2678	min_freq *= cpu->pstate.scaling;
2679	max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
2680	max_freq *= cpu->pstate.scaling;
2681
2682	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN,
2683				   min_freq);
2684	if (ret < 0) {
2685		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
2686		goto free_req;
2687	}
2688
2689	ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX,
2690				   max_freq);
2691	if (ret < 0) {
2692		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
2693		goto remove_min_req;
2694	}
2695
2696	policy->driver_data = req;
2697
2698	return 0;
2699
2700remove_min_req:
2701	freq_qos_remove_request(req);
2702free_req:
2703	kfree(req);
2704pstate_exit:
2705	intel_pstate_exit_perf_limits(policy);
2706
2707	return ret;
2708}
2709
2710static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy)
2711{
2712	struct freq_qos_request *req;
2713
2714	req = policy->driver_data;
2715
2716	freq_qos_remove_request(req + 1);
2717	freq_qos_remove_request(req);
2718	kfree(req);
2719
2720	return intel_pstate_cpu_exit(policy);
2721}
2722
2723static struct cpufreq_driver intel_cpufreq = {
2724	.flags		= CPUFREQ_CONST_LOOPS,
2725	.verify		= intel_cpufreq_verify_policy,
2726	.target		= intel_cpufreq_target,
2727	.fast_switch	= intel_cpufreq_fast_switch,
2728	.init		= intel_cpufreq_cpu_init,
2729	.exit		= intel_cpufreq_cpu_exit,
2730	.offline	= intel_pstate_cpu_offline,
2731	.online		= intel_pstate_cpu_online,
2732	.suspend	= intel_pstate_suspend,
2733	.resume		= intel_pstate_resume,
2734	.update_limits	= intel_pstate_update_limits,
2735	.name		= "intel_cpufreq",
2736};
2737
2738static struct cpufreq_driver *default_driver;
2739
2740static void intel_pstate_driver_cleanup(void)
2741{
2742	unsigned int cpu;
2743
2744	get_online_cpus();
2745	for_each_online_cpu(cpu) {
2746		if (all_cpu_data[cpu]) {
2747			if (intel_pstate_driver == &intel_pstate)
2748				intel_pstate_clear_update_util_hook(cpu);
2749
2750			kfree(all_cpu_data[cpu]);
2751			all_cpu_data[cpu] = NULL;
2752		}
2753	}
2754	put_online_cpus();
2755
2756	intel_pstate_driver = NULL;
2757}
2758
2759static int intel_pstate_register_driver(struct cpufreq_driver *driver)
2760{
2761	int ret;
2762
2763	if (driver == &intel_pstate)
2764		intel_pstate_sysfs_expose_hwp_dynamic_boost();
2765
2766	memset(&global, 0, sizeof(global));
2767	global.max_perf_pct = 100;
2768
2769	intel_pstate_driver = driver;
2770	ret = cpufreq_register_driver(intel_pstate_driver);
2771	if (ret) {
2772		intel_pstate_driver_cleanup();
2773		return ret;
2774	}
2775
2776	global.min_perf_pct = min_perf_pct_min();
2777
2778	return 0;
2779}
2780
2781static ssize_t intel_pstate_show_status(char *buf)
2782{
2783	if (!intel_pstate_driver)
2784		return sprintf(buf, "off\n");
2785
2786	return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
2787					"active" : "passive");
2788}
2789
2790static int intel_pstate_update_status(const char *buf, size_t size)
2791{
2792	if (size == 3 && !strncmp(buf, "off", size)) {
2793		if (!intel_pstate_driver)
2794			return -EINVAL;
2795
2796		if (hwp_active)
2797			return -EBUSY;
2798
2799		cpufreq_unregister_driver(intel_pstate_driver);
2800		intel_pstate_driver_cleanup();
2801		return 0;
2802	}
2803
2804	if (size == 6 && !strncmp(buf, "active", size)) {
2805		if (intel_pstate_driver) {
2806			if (intel_pstate_driver == &intel_pstate)
2807				return 0;
2808
2809			cpufreq_unregister_driver(intel_pstate_driver);
2810		}
2811
2812		return intel_pstate_register_driver(&intel_pstate);
2813	}
2814
2815	if (size == 7 && !strncmp(buf, "passive", size)) {
2816		if (intel_pstate_driver) {
2817			if (intel_pstate_driver == &intel_cpufreq)
2818				return 0;
2819
2820			cpufreq_unregister_driver(intel_pstate_driver);
2821			intel_pstate_sysfs_hide_hwp_dynamic_boost();
2822		}
2823
2824		return intel_pstate_register_driver(&intel_cpufreq);
2825	}
2826
2827	return -EINVAL;
2828}
2829
2830static int no_load __initdata;
2831static int no_hwp __initdata;
2832static int hwp_only __initdata;
2833static unsigned int force_load __initdata;
2834
2835static int __init intel_pstate_msrs_not_valid(void)
2836{
2837	if (!pstate_funcs.get_max() ||
2838	    !pstate_funcs.get_min() ||
2839	    !pstate_funcs.get_turbo())
2840		return -ENODEV;
2841
2842	return 0;
2843}
2844
2845static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
2846{
2847	pstate_funcs.get_max   = funcs->get_max;
2848	pstate_funcs.get_max_physical = funcs->get_max_physical;
2849	pstate_funcs.get_min   = funcs->get_min;
2850	pstate_funcs.get_turbo = funcs->get_turbo;
2851	pstate_funcs.get_scaling = funcs->get_scaling;
2852	pstate_funcs.get_val   = funcs->get_val;
2853	pstate_funcs.get_vid   = funcs->get_vid;
2854	pstate_funcs.get_aperf_mperf_shift = funcs->get_aperf_mperf_shift;
2855}
2856
2857#ifdef CONFIG_ACPI
2858
2859static bool __init intel_pstate_no_acpi_pss(void)
2860{
2861	int i;
2862
2863	for_each_possible_cpu(i) {
2864		acpi_status status;
2865		union acpi_object *pss;
2866		struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
2867		struct acpi_processor *pr = per_cpu(processors, i);
2868
2869		if (!pr)
2870			continue;
2871
2872		status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
2873		if (ACPI_FAILURE(status))
2874			continue;
2875
2876		pss = buffer.pointer;
2877		if (pss && pss->type == ACPI_TYPE_PACKAGE) {
2878			kfree(pss);
2879			return false;
2880		}
2881
2882		kfree(pss);
2883	}
2884
2885	pr_debug("ACPI _PSS not found\n");
2886	return true;
2887}
2888
2889static bool __init intel_pstate_no_acpi_pcch(void)
2890{
2891	acpi_status status;
2892	acpi_handle handle;
2893
2894	status = acpi_get_handle(NULL, "\\_SB", &handle);
2895	if (ACPI_FAILURE(status))
2896		goto not_found;
2897
2898	if (acpi_has_method(handle, "PCCH"))
2899		return false;
2900
2901not_found:
2902	pr_debug("ACPI PCCH not found\n");
2903	return true;
2904}
2905
2906static bool __init intel_pstate_has_acpi_ppc(void)
2907{
2908	int i;
2909
2910	for_each_possible_cpu(i) {
2911		struct acpi_processor *pr = per_cpu(processors, i);
2912
2913		if (!pr)
2914			continue;
2915		if (acpi_has_method(pr->handle, "_PPC"))
2916			return true;
2917	}
2918	pr_debug("ACPI _PPC not found\n");
2919	return false;
2920}
2921
2922enum {
2923	PSS,
2924	PPC,
2925};
2926
2927/* Hardware vendor-specific info that has its own power management modes */
2928static struct acpi_platform_list plat_info[] __initdata = {
2929	{"HP    ", "ProLiant", 0, ACPI_SIG_FADT, all_versions, NULL, PSS},
2930	{"ORACLE", "X4-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2931	{"ORACLE", "X4-2L   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2932	{"ORACLE", "X4-2B   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2933	{"ORACLE", "X3-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2934	{"ORACLE", "X3-2L   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2935	{"ORACLE", "X3-2B   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2936	{"ORACLE", "X4470M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2937	{"ORACLE", "X4270M3 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2938	{"ORACLE", "X4270M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2939	{"ORACLE", "X4170M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2940	{"ORACLE", "X4170 M3", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2941	{"ORACLE", "X4275 M3", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2942	{"ORACLE", "X6-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2943	{"ORACLE", "Sudbury ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
2944	{ } /* End */
2945};
2946
2947#define BITMASK_OOB	(BIT(8) | BIT(18))
2948
2949static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
2950{
2951	const struct x86_cpu_id *id;
2952	u64 misc_pwr;
2953	int idx;
2954
2955	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
2956	if (id) {
2957		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
2958		if (misc_pwr & BITMASK_OOB) {
2959			pr_debug("Bit 8 or 18 in the MISC_PWR_MGMT MSR set\n");
2960			pr_debug("P states are controlled in Out of Band mode by the firmware/hardware\n");
2961			return true;
2962		}
2963	}
2964
2965	idx = acpi_match_platform_list(plat_info);
2966	if (idx < 0)
2967		return false;
2968
2969	switch (plat_info[idx].data) {
2970	case PSS:
2971		if (!intel_pstate_no_acpi_pss())
2972			return false;
2973
2974		return intel_pstate_no_acpi_pcch();
2975	case PPC:
2976		return intel_pstate_has_acpi_ppc() && !force_load;
2977	}
2978
2979	return false;
2980}
2981
2982static void intel_pstate_request_control_from_smm(void)
2983{
2984	/*
2985	 * It may be unsafe to request P-states control from SMM if _PPC support
2986	 * has not been enabled.
2987	 */
2988	if (acpi_ppc)
2989		acpi_processor_pstate_control();
2990}
2991#else /* CONFIG_ACPI not enabled */
2992static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; }
2993static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
2994static inline void intel_pstate_request_control_from_smm(void) {}
2995#endif /* CONFIG_ACPI */
2996
2997#define INTEL_PSTATE_HWP_BROADWELL	0x01
2998
2999#define X86_MATCH_HWP(model, hwp_mode)					\
3000	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
3001					   X86_FEATURE_HWP, hwp_mode)
3002
3003static const struct x86_cpu_id hwp_support_ids[] __initconst = {
3004	X86_MATCH_HWP(BROADWELL_X,	INTEL_PSTATE_HWP_BROADWELL),
3005	X86_MATCH_HWP(BROADWELL_D,	INTEL_PSTATE_HWP_BROADWELL),
3006	X86_MATCH_HWP(ANY,		0),
3007	{}
3008};
3009
3010static bool intel_pstate_hwp_is_enabled(void)
3011{
3012	u64 value;
3013
3014	rdmsrl(MSR_PM_ENABLE, value);
3015	return !!(value & 0x1);
3016}
3017
3018static int __init intel_pstate_init(void)
3019{
3020	const struct x86_cpu_id *id;
3021	int rc;
3022
3023	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
3024		return -ENODEV;
3025
3026	id = x86_match_cpu(hwp_support_ids);
3027	if (id) {
3028		bool hwp_forced = intel_pstate_hwp_is_enabled();
3029
3030		if (hwp_forced)
3031			pr_info("HWP enabled by BIOS\n");
3032		else if (no_load)
3033			return -ENODEV;
3034
3035		copy_cpu_funcs(&core_funcs);
3036		/*
3037		 * Avoid enabling HWP for processors without EPP support,
3038		 * because that means incomplete HWP implementation which is a
3039		 * corner case and supporting it is generally problematic.
3040		 *
3041		 * If HWP is enabled already, though, there is no choice but to
3042		 * deal with it.
3043		 */
3044		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) {
3045			hwp_active++;
3046			hwp_mode_bdw = id->driver_data;
3047			intel_pstate.attr = hwp_cpufreq_attrs;
3048			intel_cpufreq.attr = hwp_cpufreq_attrs;
3049			intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
3050			if (!default_driver)
3051				default_driver = &intel_pstate;
3052
3053			goto hwp_cpu_matched;
3054		}
3055		pr_info("HWP not enabled\n");
3056	} else {
3057		if (no_load)
3058			return -ENODEV;
3059
3060		id = x86_match_cpu(intel_pstate_cpu_ids);
3061		if (!id) {
3062			pr_info("CPU model not supported\n");
3063			return -ENODEV;
3064		}
3065
3066		copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
3067	}
3068
3069	if (intel_pstate_msrs_not_valid()) {
3070		pr_info("Invalid MSRs\n");
3071		return -ENODEV;
3072	}
3073	/* Without HWP start in the passive mode. */
3074	if (!default_driver)
3075		default_driver = &intel_cpufreq;
3076
3077hwp_cpu_matched:
3078	/*
3079	 * The Intel pstate driver will be ignored if the platform
3080	 * firmware has its own power management modes.
3081	 */
3082	if (intel_pstate_platform_pwr_mgmt_exists()) {
3083		pr_info("P-states controlled by the platform\n");
3084		return -ENODEV;
3085	}
3086
3087	if (!hwp_active && hwp_only)
3088		return -ENOTSUPP;
3089
3090	pr_info("Intel P-state driver initializing\n");
3091
3092	all_cpu_data = vzalloc(array_size(sizeof(void *), num_possible_cpus()));
3093	if (!all_cpu_data)
3094		return -ENOMEM;
3095
3096	intel_pstate_request_control_from_smm();
3097
3098	intel_pstate_sysfs_expose_params();
3099
3100	mutex_lock(&intel_pstate_driver_lock);
3101	rc = intel_pstate_register_driver(default_driver);
3102	mutex_unlock(&intel_pstate_driver_lock);
3103	if (rc) {
3104		intel_pstate_sysfs_remove();
3105		return rc;
3106	}
3107
3108	if (hwp_active) {
3109		const struct x86_cpu_id *id;
3110
3111		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
3112		if (id) {
3113			set_power_ctl_ee_state(false);
3114			pr_info("Disabling energy efficiency optimization\n");
3115		}
3116
3117		pr_info("HWP enabled\n");
3118	}
3119
3120	return 0;
3121}
3122device_initcall(intel_pstate_init);
3123
3124static int __init intel_pstate_setup(char *str)
3125{
3126	if (!str)
3127		return -EINVAL;
3128
3129	if (!strcmp(str, "disable"))
3130		no_load = 1;
3131	else if (!strcmp(str, "active"))
3132		default_driver = &intel_pstate;
3133	else if (!strcmp(str, "passive"))
3134		default_driver = &intel_cpufreq;
3135
3136	if (!strcmp(str, "no_hwp"))
3137		no_hwp = 1;
3138
3139	if (!strcmp(str, "force"))
3140		force_load = 1;
3141	if (!strcmp(str, "hwp_only"))
3142		hwp_only = 1;
3143	if (!strcmp(str, "per_cpu_perf_limits"))
3144		per_cpu_limits = true;
3145
3146#ifdef CONFIG_ACPI
3147	if (!strcmp(str, "support_acpi_ppc"))
3148		acpi_ppc = true;
3149#endif
3150
3151	return 0;
3152}
3153early_param("intel_pstate", intel_pstate_setup);
3154
3155MODULE_AUTHOR("Dirk Brandewie <dirk.j.brandewie@intel.com>");
3156MODULE_DESCRIPTION("'intel_pstate' - P state driver Intel Core processors");
3157MODULE_LICENSE("GPL");
3158