intel_pstate.c

/*
 * intel_pstate.c: Native P state management for Intel processors
 *
 * (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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#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>
#include <linux/acpi.h>
#include <linux/vmalloc.h>
#include <trace/events/power.h>

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

#define ATOM_RATIOS		0x66a
#define ATOM_VIDS		0x66b
#define ATOM_TURBO_RATIOS	0x66c
#define ATOM_TURBO_VIDS		0x66d

#ifdef CONFIG_ACPI
#include <acpi/processor.h>
#endif

#define FRAC_BITS 8
#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
#define fp_toint(X) ((X) >> FRAC_BITS)

#define EXT_BITS 6
#define EXT_FRAC_BITS (EXT_BITS + 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(s64 x, s64 y)
{
	return div64_s64((int64_t)x << FRAC_BITS, y);
}

static inline int ceiling_fp(int32_t x)
{
	int mask, ret;

	ret = fp_toint(x);
	mask = (1 << FRAC_BITS) - 1;
	if (x & mask)
		ret += 1;
	return ret;
}

static inline u64 mul_ext_fp(u64 x, u64 y)
{
	return (x * y) >> EXT_FRAC_BITS;
}

static inline u64 div_ext_fp(u64 x, u64 y)
{
	return div64_u64(x << EXT_FRAC_BITS, y);
}

/**
 * struct sample -	Store performance sample
 * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
 *			performance during last sample period
 * @busy_scaled:	Scaled busy value which is used to calculate next
 *			P state. This can be different than core_avg_perf
 *			to account for cpu idle period
 * @aperf:		Difference of actual performance frequency clock count
 *			read from APERF MSR between last and current sample
 * @mperf:		Difference of maximum performance frequency clock count
 *			read from MPERF MSR between last and current sample
 * @tsc:		Difference of time stamp counter between last and
 *			current sample
 * @freq:		Effective frequency calculated from APERF/MPERF
 * @time:		Current time from scheduler
 *
 * This structure is used in the cpudata structure to store performance sample
 * data for choosing next P State.
 */
struct sample {
	int32_t core_avg_perf;
	int32_t busy_scaled;
	u64 aperf;
	u64 mperf;
	u64 tsc;
	int freq;
	u64 time;
};

/**
 * struct pstate_data - Store P state data
 * @current_pstate:	Current requested P state
 * @min_pstate:		Min P state possible for this platform
 * @max_pstate:		Max P state possible for this platform
 * @max_pstate_physical:This is physical Max P state for a processor
 *			This can be higher than the max_pstate which can
 *			be limited by platform thermal design power limits
 * @scaling:		Scaling factor to  convert frequency to cpufreq
 *			frequency units
 * @turbo_pstate:	Max Turbo P state possible for this platform
 *
 * Stores the per cpu model P state limits and current P state.
 */
struct pstate_data {
	int	current_pstate;
	int	min_pstate;
	int	max_pstate;
	int	max_pstate_physical;
	int	scaling;
	int	turbo_pstate;
};

/**
 * struct vid_data -	Stores voltage information data
 * @min:		VID data for this platform corresponding to
 *			the lowest P state
 * @max:		VID data corresponding to the highest P State.
 * @turbo:		VID data for turbo P state
 * @ratio:		Ratio of (vid max - vid min) /
 *			(max P state - Min P State)
 *
 * Stores the voltage data for DVFS (Dynamic Voltage and Frequency Scaling)
 * This data is used in Atom platforms, where in addition to target P state,
 * the voltage data needs to be specified to select next P State.
 */
struct vid_data {
	int min;
	int max;
	int turbo;
	int32_t ratio;
};

/**
 * struct _pid -	Stores PID data
 * @setpoint:		Target set point for busyness or performance
 * @integral:		Storage for accumulated error values
 * @p_gain:		PID proportional gain
 * @i_gain:		PID integral gain
 * @d_gain:		PID derivative gain
 * @deadband:		PID deadband
 * @last_err:		Last error storage for integral part of PID calculation
 *
 * Stores PID coefficients and last error for PID controller.
 */
struct _pid {
	int setpoint;
	int32_t integral;
	int32_t p_gain;
	int32_t i_gain;
	int32_t d_gain;
	int deadband;
	int32_t last_err;
};

/**
 * struct cpudata -	Per CPU instance data storage
 * @cpu:		CPU number for this instance data
 * @update_util:	CPUFreq utility callback information
 * @update_util_set:	CPUFreq utility callback is set
 * @pstate:		Stores P state limits for this CPU
 * @vid:		Stores VID limits for this CPU
 * @pid:		Stores PID parameters for this CPU
 * @last_sample_time:	Last Sample time
 * @prev_aperf:		Last APERF value read from APERF MSR
 * @prev_mperf:		Last MPERF value read from MPERF MSR
 * @prev_tsc:		Last timestamp counter (TSC) value
 * @prev_cummulative_iowait: IO Wait time difference from last and
 *			current sample
 * @sample:		Storage for storing last Sample data
 * @acpi_perf_data:	Stores ACPI perf information read from _PSS
 * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
 *
 * This structure stores per CPU instance data for all CPUs.
 */
struct cpudata {