acpi-cpufreq.c

linux 内核源代码

/*
 * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $)
 *
 *  Copyright (C) 2001, 2002 Andy Grover <[e-mail]>
 *  Copyright (C) 2001, 2002 Paul Diefenbaugh <[e-mail]>
 *  Copyright (C) 2002 - 2004 Dominik Brodowski <[e-mail]>
 *  Copyright (C) 2006       Denis Sadykov <[e-mail]>
 *
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or (at
 *  your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful, but
 *  WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License along
 *  with this program; if not, write to the Free Software Foundation, Inc.,
 *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
 *
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>

#include <linux/acpi.h>
#include <acpi/processor.h>

#include <asm/io.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/delay.h>
#include <asm/uaccess.h>

#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg)

MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
MODULE_LICENSE("GPL");

enum {
	UNDEFINED_CAPABLE = 0,
	SYSTEM_INTEL_MSR_CAPABLE,
	SYSTEM_IO_CAPABLE,
};

#define INTEL_MSR_RANGE		(0xffff)
#define CPUID_6_ECX_APERFMPERF_CAPABILITY	(0x1)

struct acpi_cpufreq_data {
	struct acpi_processor_performance *acpi_data;
	struct cpufreq_frequency_table *freq_table;
	unsigned int max_freq;
	unsigned int resume;
	unsigned int cpu_feature;
};

static struct acpi_cpufreq_data *drv_data[NR_CPUS];
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;

static struct cpufreq_driver acpi_cpufreq_driver;

static unsigned int acpi_pstate_strict;

static int check_est_cpu(unsigned int cpuid)
{
	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);

	if (cpu->x86_vendor != X86_VENDOR_INTEL ||
	    !cpu_has(cpu, X86_FEATURE_EST))
		return 0;

	return 1;
}

static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
{
	struct acpi_processor_performance *perf;
	int i;

	perf = data->acpi_data;

	for (i=0; i<perf->state_count; i++) {
		if (value == perf->states[i].status)
			return data->freq_table[i].frequency;
	}
	return 0;
}

static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
{
	int i;
	struct acpi_processor_performance *perf;

	msr &= INTEL_MSR_RANGE;
	perf = data->acpi_data;

	for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
		if (msr == perf->states[data->freq_table[i].index].status)
			return data->freq_table[i].frequency;
	}
	return data->freq_table[0].frequency;
}

static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
{
	switch (data->cpu_feature) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		return extract_msr(val, data);
	case SYSTEM_IO_CAPABLE:
		return extract_io(val, data);
	default:
		return 0;
	}
}

struct msr_addr {
	u32 reg;
};

struct io_addr {
	u16 port;
	u8 bit_width;
};

typedef union {
	struct msr_addr msr;
	struct io_addr io;
} drv_addr_union;

struct drv_cmd {
	unsigned int type;
	cpumask_t mask;
	drv_addr_union addr;
	u32 val;
};

static void do_drv_read(struct drv_cmd *cmd)
{
	u32 h;

	switch (cmd->type) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		rdmsr(cmd->addr.msr.reg, cmd->val, h);
		break;
	case SYSTEM_IO_CAPABLE:
		acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
				&cmd->val,
				(u32)cmd->addr.io.bit_width);
		break;
	default:
		break;
	}
}

static void do_drv_write(struct drv_cmd *cmd)
{
	u32 lo, hi;

	switch (cmd->type) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		rdmsr(cmd->addr.msr.reg, lo, hi);
		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
		wrmsr(cmd->addr.msr.reg, lo, hi);
		break;
	case SYSTEM_IO_CAPABLE:
		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
				cmd->val,
				(u32)cmd->addr.io.bit_width);
		break;
	default:
		break;
	}
}

static void drv_read(struct drv_cmd *cmd)
{
	cpumask_t saved_mask = current->cpus_allowed;
	cmd->val = 0;

	set_cpus_allowed(current, cmd->mask);
	do_drv_read(cmd);
	set_cpus_allowed(current, saved_mask);
}

static void drv_write(struct drv_cmd *cmd)
{
	cpumask_t saved_mask = current->cpus_allowed;
	unsigned int i;

	for_each_cpu_mask(i, cmd->mask) {
		set_cpus_allowed(current, cpumask_of_cpu(i));
		do_drv_write(cmd);
	}

	set_cpus_allowed(current, saved_mask);
	return;
}

static u32 get_cur_val(cpumask_t mask)
{
	struct acpi_processor_performance *perf;
	struct drv_cmd cmd;

	if (unlikely(cpus_empty(mask)))
		return 0;

	switch (drv_data[first_cpu(mask)]->cpu_feature) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
		break;
	case SYSTEM_IO_CAPABLE:
		cmd.type = SYSTEM_IO_CAPABLE;
		perf = drv_data[first_cpu(mask)]->acpi_data;
		cmd.addr.io.port = perf->control_register.address;
		cmd.addr.io.bit_width = perf->control_register.bit_width;
		break;
	default:
		return 0;
	}

	cmd.mask = mask;

	drv_read(&cmd);

	dprintk("get_cur_val = %u\n", cmd.val);

	return cmd.val;
}

/*
 * Return the measured active (C0) frequency on this CPU since last call
 * to this function.
 * Input: cpu number
 * Return: Average CPU frequency in terms of max frequency (zero on error)
 *
 * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
 * over a period of time, while CPU is in C0 state.
 * IA32_MPERF counts at the rate of max advertised frequency
 * IA32_APERF counts at the rate of actual CPU frequency
 * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
 * no meaning should be associated with absolute values of these MSRs.
 */
static unsigned int get_measured_perf(unsigned int cpu)
{
	union {
		struct {
			u32 lo;
			u32 hi;
		} split;
		u64 whole;
	} aperf_cur, mperf_cur;

	cpumask_t saved_mask;
	unsigned int perf_percent;
	unsigned int retval;

	saved_mask = current->cpus_allowed;
	set_cpus_allowed(current, cpumask_of_cpu(cpu));
	if (get_cpu() != cpu) {
		/* We were not able to run on requested processor */
		put_cpu();
		return 0;
	}

	rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi);
	rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi);

	wrmsr(MSR_IA32_APERF, 0,0);
	wrmsr(MSR_IA32_MPERF, 0,0);

#ifdef __i386__
	/*
	 * We dont want to do 64 bit divide with 32 bit kernel
	 * Get an approximate value. Return failure in case we cannot get
	 * an approximate value.
	 */
	if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) {
		int shift_count;
		u32 h;

		h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi);
		shift_count = fls(h);

		aperf_cur.whole >>= shift_count;
		mperf_cur.whole >>= shift_count;
	}

	if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) {
		int shift_count = 7;
		aperf_cur.split.lo >>= shift_count;
		mperf_cur.split.lo >>= shift_count;
	}

	if (aperf_cur.split.lo && mperf_cur.split.lo)
		perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo;
	else
		perf_percent = 0;

#else
	if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) {
		int shift_count = 7;
		aperf_cur.whole >>= shift_count;
		mperf_cur.whole >>= shift_count;
	}

	if (aperf_cur.whole && mperf_cur.whole)
		perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole;
	else
		perf_percent = 0;

#endif

	retval = drv_data[cpu]->max_freq * perf_percent / 100;

	put_cpu();
	set_cpus_allowed(current, saved_mask);

	dprintk("cpu %d: performance percent %d\n", cpu, perf_percent);
	return retval;
}

static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
	struct acpi_cpufreq_data *data = drv_data[cpu];
	unsigned int freq;

	dprintk("get_cur_freq_on_cpu (%d)\n", cpu);

	if (unlikely(data == NULL ||
		     data->acpi_data == NULL || data->freq_table == NULL)) {
		return 0;
	}

	freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data);
	dprintk("cur freq = %u\n", freq);

	return freq;
}

static unsigned int check_freqs(cpumask_t mask, unsigned int freq,
				struct acpi_cpufreq_data *data)
{
	unsigned int cur_freq;
	unsigned int i;

	for (i=0; i<100; i++) {
		cur_freq = extract_freq(get_cur_val(mask), data);
		if (cur_freq == freq)
			return 1;
		udelay(10);
	}
	return 0;
}

static int acpi_cpufreq_target(struct cpufreq_policy *policy,
			       unsigned int target_freq, unsigned int relation)
{
	struct acpi_cpufreq_data *data = drv_data[policy->cpu];
	struct acpi_processor_performance *perf;
	struct cpufreq_freqs freqs;
	cpumask_t online_policy_cpus;
	struct drv_cmd cmd;
	unsigned int next_state = 0; /* Index into freq_table */
	unsigned int next_perf_state = 0; /* Index into perf table */
	unsigned int i;
	int result = 0;

	dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);

	if (unlikely(data == NULL ||
	     data->acpi_data == NULL || data->freq_table == NULL)) {
		return -ENODEV;
	}

	perf = data->acpi_data;
	result = cpufreq_frequency_table_target(policy,
						data->freq_table,
						target_freq,
						relation, &next_state);
	if (unlikely(result))
		return -ENODEV;

#ifdef CONFIG_HOTPLUG_CPU
	/* cpufreq holds the hotplug lock, so we are safe from here on */
	cpus_and(online_policy_cpus, cpu_online_map, policy->cpus);