diff options
Diffstat (limited to 'drivers/cpufreq')
| -rw-r--r-- | drivers/cpufreq/Kconfig | 24 | ||||
| -rw-r--r-- | drivers/cpufreq/Makefile | 1 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 12 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq_conservative.c | 586 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq_ondemand.c | 180 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq_stats.c | 47 |
6 files changed, 738 insertions, 112 deletions
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 95882bb1950e..60c9be99c6d9 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -46,6 +46,10 @@ config CPU_FREQ_STAT_DETAILS This will show detail CPU frequency translation table in sysfs file system +# Note that it is not currently possible to set the other governors (such as ondemand) +# as the default, since if they fail to initialise, cpufreq will be +# left in an undefined state. + choice prompt "Default CPUFreq governor" default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110 @@ -115,4 +119,24 @@ config CPU_FREQ_GOV_ONDEMAND If in doubt, say N. +config CPU_FREQ_GOV_CONSERVATIVE + tristate "'conservative' cpufreq governor" + depends on CPU_FREQ + help + 'conservative' - this driver is rather similar to the 'ondemand' + governor both in its source code and its purpose, the difference is + its optimisation for better suitability in a battery powered + environment. The frequency is gracefully increased and decreased + rather than jumping to 100% when speed is required. + + If you have a desktop machine then you should really be considering + the 'ondemand' governor instead, however if you are using a laptop, + PDA or even an AMD64 based computer (due to the unacceptable + step-by-step latency issues between the minimum and maximum frequency + transitions in the CPU) you will probably want to use this governor. + + For details, take a look at linux/Documentation/cpu-freq. + + If in doubt, say N. + endif # CPU_FREQ diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 67b16e5a41a7..71fc3b4173f1 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE) += cpufreq_performance.o obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE) += cpufreq_powersave.o obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE) += cpufreq_userspace.o obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND) += cpufreq_ondemand.o +obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE) += cpufreq_conservative.o # CPUfreq cross-arch helpers obj-$(CONFIG_CPU_FREQ_TABLE) += freq_table.o diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 8e561313d094..bf62dfe4976a 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -258,7 +258,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) (likely(cpufreq_cpu_data[freqs->cpu]->cur)) && (unlikely(freqs->old != cpufreq_cpu_data[freqs->cpu]->cur))) { - printk(KERN_WARNING "Warning: CPU frequency is %u, " + dprintk(KERN_WARNING "Warning: CPU frequency is %u, " "cpufreq assumed %u kHz.\n", freqs->old, cpufreq_cpu_data[freqs->cpu]->cur); freqs->old = cpufreq_cpu_data[freqs->cpu]->cur; } @@ -521,7 +521,7 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf) policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->show ? fattr->show(policy,buf) : 0; + ret = fattr->show ? fattr->show(policy,buf) : -EIO; cpufreq_cpu_put(policy); return ret; } @@ -535,7 +535,7 @@ static ssize_t store(struct kobject * kobj, struct attribute * attr, policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->store ? fattr->store(policy,buf,count) : 0; + ret = fattr->store ? fattr->store(policy,buf,count) : -EIO; cpufreq_cpu_put(policy); return ret; } @@ -814,7 +814,7 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigne { struct cpufreq_freqs freqs; - printk(KERN_WARNING "Warning: CPU frequency out of sync: cpufreq and timing " + dprintk(KERN_WARNING "Warning: CPU frequency out of sync: cpufreq and timing " "core thinks of %u, is %u kHz.\n", old_freq, new_freq); freqs.cpu = cpu; @@ -923,7 +923,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, u32 state) struct cpufreq_freqs freqs; if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN)) - printk(KERN_DEBUG "Warning: CPU frequency is %u, " + dprintk(KERN_DEBUG "Warning: CPU frequency is %u, " "cpufreq assumed %u kHz.\n", cur_freq, cpu_policy->cur); @@ -1004,7 +1004,7 @@ static int cpufreq_resume(struct sys_device * sysdev) struct cpufreq_freqs freqs; if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN)) - printk(KERN_WARNING "Warning: CPU frequency" + dprintk(KERN_WARNING "Warning: CPU frequency" "is %u, cpufreq assumed %u kHz.\n", cur_freq, cpu_policy->cur); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c new file mode 100644 index 000000000000..e1df376e709e --- /dev/null +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -0,0 +1,586 @@ +/* + * drivers/cpufreq/cpufreq_conservative.c + * + * Copyright (C) 2001 Russell King + * (C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>. + * Jun Nakajima <jun.nakajima@intel.com> + * (C) 2004 Alexander Clouter <alex-kernel@digriz.org.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/ctype.h> +#include <linux/cpufreq.h> +#include <linux/sysctl.h> +#include <linux/types.h> +#include <linux/fs.h> +#include <linux/sysfs.h> +#include <linux/sched.h> +#include <linux/kmod.h> +#include <linux/workqueue.h> +#include <linux/jiffies.h> +#include <linux/kernel_stat.h> +#include <linux/percpu.h> + +/* + * dbs is used in this file as a shortform for demandbased switching + * It helps to keep variable names smaller, simpler + */ + +#define DEF_FREQUENCY_UP_THRESHOLD (80) +#define MIN_FREQUENCY_UP_THRESHOLD (0) +#define MAX_FREQUENCY_UP_THRESHOLD (100) + +#define DEF_FREQUENCY_DOWN_THRESHOLD (20) +#define MIN_FREQUENCY_DOWN_THRESHOLD (0) +#define MAX_FREQUENCY_DOWN_THRESHOLD (100) + +/* + * The polling frequency of this governor depends on the capability of + * the processor. Default polling frequency is 1000 times the transition + * latency of the processor. The governor will work on any processor with + * transition latency <= 10mS, using appropriate sampling + * rate. + * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL) + * this governor will not work. + * All times here are in uS. + */ +static unsigned int def_sampling_rate; +#define MIN_SAMPLING_RATE (def_sampling_rate / 2) +#define MAX_SAMPLING_RATE (500 * def_sampling_rate) +#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (100000) +#define DEF_SAMPLING_DOWN_FACTOR (5) +#define TRANSITION_LATENCY_LIMIT (10 * 1000) + +static void do_dbs_timer(void *data); + +struct cpu_dbs_info_s { + struct cpufreq_policy *cur_policy; + unsigned int prev_cpu_idle_up; + unsigned int prev_cpu_idle_down; + unsigned int enable; +}; +static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info); + +static unsigned int dbs_enable; /* number of CPUs using this policy */ + +static DECLARE_MUTEX (dbs_sem); +static DECLARE_WORK (dbs_work, do_dbs_timer, NULL); + +struct dbs_tuners { + unsigned int sampling_rate; + unsigned int sampling_down_factor; + unsigned int up_threshold; + unsigned int down_threshold; + unsigned int ignore_nice; + unsigned int freq_step; +}; + +static struct dbs_tuners dbs_tuners_ins = { + .up_threshold = DEF_FREQUENCY_UP_THRESHOLD, + .down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD, + .sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR, +}; + +static inline unsigned int get_cpu_idle_time(unsigned int cpu) +{ + return kstat_cpu(cpu).cpustat.idle + + kstat_cpu(cpu).cpustat.iowait + + ( !dbs_tuners_ins.ignore_nice ? + kstat_cpu(cpu).cpustat.nice : + 0); +} + +/************************** sysfs interface ************************/ +static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf) +{ + return sprintf (buf, "%u\n", MAX_SAMPLING_RATE); +} + +static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf) +{ + return sprintf (buf, "%u\n", MIN_SAMPLING_RATE); +} + +#define define_one_ro(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) + +define_one_ro(sampling_rate_max); +define_one_ro(sampling_rate_min); + +/* cpufreq_conservative Governor Tunables */ +#define show_one(file_name, object) \ +static ssize_t show_##file_name \ +(struct cpufreq_policy *unused, char *buf) \ +{ \ + return sprintf(buf, "%u\n", dbs_tuners_ins.object); \ +} +show_one(sampling_rate, sampling_rate); +show_one(sampling_down_factor, sampling_down_factor); +show_one(up_threshold, up_threshold); +show_one(down_threshold, down_threshold); +show_one(ignore_nice, ignore_nice); +show_one(freq_step, freq_step); + +static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + ret = sscanf (buf, "%u", &input); + if (ret != 1 ) + return -EINVAL; + + down(&dbs_sem); + dbs_tuners_ins.sampling_down_factor = input; + up(&dbs_sem); + + return count; +} + +static ssize_t store_sampling_rate(struct cpufreq_policy *unused, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + ret = sscanf (buf, "%u", &input); + + down(&dbs_sem); + if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) { + up(&dbs_sem); + return -EINVAL; + } + + dbs_tuners_ins.sampling_rate = input; + up(&dbs_sem); + + return count; +} + +static ssize_t store_up_threshold(struct cpufreq_policy *unused, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + ret = sscanf (buf, "%u", &input); + + down(&dbs_sem); + if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || + input < MIN_FREQUENCY_UP_THRESHOLD || + input <= dbs_tuners_ins.down_threshold) { + up(&dbs_sem); + return -EINVAL; + } + + dbs_tuners_ins.up_threshold = input; + up(&dbs_sem); + + return count; +} + +static ssize_t store_down_threshold(struct cpufreq_policy *unused, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + ret = sscanf (buf, "%u", &input); + + down(&dbs_sem); + if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || + input < MIN_FREQUENCY_DOWN_THRESHOLD || + input >= dbs_tuners_ins.up_threshold) { + up(&dbs_sem); + return -EINVAL; + } + + dbs_tuners_ins.down_threshold = input; + up(&dbs_sem); + + return count; +} + +static ssize_t store_ignore_nice(struct cpufreq_policy *policy, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + + unsigned int j; + + ret = sscanf (buf, "%u", &input); + if ( ret != 1 ) + return -EINVAL; + + if ( input > 1 ) + input = 1; + + down(&dbs_sem); + if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */ + up(&dbs_sem); + return count; + } + dbs_tuners_ins.ignore_nice = input; + + /* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */ + for_each_online_cpu(j) { + struct cpu_dbs_info_s *j_dbs_info; + j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j); + j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up; + } + up(&dbs_sem); + + return count; +} + +static ssize_t store_freq_step(struct cpufreq_policy *policy, + const char *buf, size_t count) +{ + unsigned int input; + int ret; + + ret = sscanf (buf, "%u", &input); + + if ( ret != 1 ) + return -EINVAL; + + if ( input > 100 ) + input = 100; + + /* no need to test here if freq_step is zero as the user might actually + * want this, they would be crazy though :) */ + down(&dbs_sem); + dbs_tuners_ins.freq_step = input; + up(&dbs_sem); + + return count; +} + +#define define_one_rw(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) + +define_one_rw(sampling_rate); +define_one_rw(sampling_down_factor); +define_one_rw(up_threshold); +define_one_rw(down_threshold); +define_one_rw(ignore_nice); +define_one_rw(freq_step); + +static struct attribute * dbs_attributes[] = { + &sampling_rate_max.attr, + &sampling_rate_min.attr, + &sampling_rate.attr, + &sampling_down_factor.attr, + &up_threshold.attr, + &down_threshold.attr, + &ignore_nice.attr, + &freq_step.attr, + NULL +}; + +static struct attribute_group dbs_attr_group = { + .attrs = dbs_attributes, + .name = "conservative", +}; + +/************************** sysfs end ************************/ + +static void dbs_check_cpu(int cpu) +{ + unsigned int idle_ticks, up_idle_ticks, down_idle_ticks; + unsigned int freq_step; + unsigned int freq_down_sampling_rate; + static int down_skip[NR_CPUS]; + static int requested_freq[NR_CPUS]; + static unsigned short init_flag = 0; + struct cpu_dbs_info_s *this_dbs_info; + struct cpu_dbs_info_s *dbs_info; + + struct cpufreq_policy *policy; + unsigned int j; + + this_dbs_info = &per_cpu(cpu_dbs_info, cpu); + if (!this_dbs_info->enable) + return; + + policy = this_dbs_info->cur_policy; + + if ( init_flag == 0 ) { + for ( /* NULL */; init_flag < NR_CPUS; init_flag++ ) { + dbs_info = &per_cpu(cpu_dbs_info, init_flag); + requested_freq[cpu] = dbs_info->cur_policy->cur; + } + init_flag = 1; + } + + /* + * The default safe range is 20% to 80% + * Every sampling_rate, we check + * - If current idle time is less than 20%, then we try to + * increase frequency + * Every sampling_rate*sampling_down_factor, we check + * - If current idle time is more than 80%, then we try to + * decrease frequency + * + * Any frequency increase takes it to the maximum frequency. + * Frequency reduction happens at minimum steps of + * 5% (default) of max_frequency + */ + + /* Check for frequency increase */ + + idle_ticks = UINT_MAX; + for_each_cpu_mask(j, policy->cpus) { + unsigned int tmp_idle_ticks, total_idle_ticks; + struct cpu_dbs_info_s *j_dbs_info; + + j_dbs_info = &per_cpu(cpu_dbs_info, j); + /* Check for frequency increase */ + total_idle_ticks = get_cpu_idle_time(j); + tmp_idle_ticks = total_idle_ticks - + j_dbs_info->prev_cpu_idle_up; + j_dbs_info->prev_cpu_idle_up = total_idle_ticks; + + if (tmp_idle_ticks < idle_ticks) + idle_ticks = tmp_idle_ticks; + } + + /* Scale idle ticks by 100 and compare with up and down ticks */ + idle_ticks *= 100; + up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) * + usecs_to_jiffies(dbs_tuners_ins.sampling_rate); + + if (idle_ticks < up_idle_ticks) { + down_skip[cpu] = 0; + for_each_cpu_mask(j, policy->cpus) { + struct cpu_dbs_info_s *j_dbs_info; + + j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info->prev_cpu_idle_down = + j_dbs_info->prev_cpu_idle_up; + } + /* if we are already at full speed then break out early */ + if (requested_freq[cpu] == policy->max) + return; + + freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100; + + /* max freq cannot be less than 100. But who knows.... */ + if (unlikely(freq_step == 0)) + freq_step = 5; + + requested_freq[cpu] += freq_step; + if (requested_freq[cpu] > policy->max) + requested_freq[cpu] = policy->max; + + __cpufreq_driver_target(policy, requested_freq[cpu], + CPUFREQ_RELATION_H); + return; + } + + /* Check for frequency decrease */ + down_skip[cpu]++; + if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor) + return; + + idle_ticks = UINT_MAX; + for_each_cpu_mask(j, policy->cpus) { + unsigned int tmp_idle_ticks, total_idle_ticks; + struct cpu_dbs_info_s *j_dbs_info; + + j_dbs_info = &per_cpu(cpu_dbs_info, j); + total_idle_ticks = j_dbs_info->prev_cpu_idle_up; + tmp_idle_ticks = total_idle_ticks - + j_dbs_info->prev_cpu_idle_down; + j_dbs_info->prev_cpu_idle_down = total_idle_ticks; + + if (tmp_idle_ticks < idle_ticks) + idle_ticks = tmp_idle_ticks; + } + + /* Scale idle ticks by 100 and compare with up and down ticks */ + idle_ticks *= 100; + down_skip[cpu] = 0; + + freq_down_sampling_rate = dbs_tuners_ins.sampling_rate * + dbs_tuners_ins.sampling_down_factor; + down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) * + usecs_to_jiffies(freq_down_sampling_rate); + + if (idle_ticks > down_idle_ticks) { + /* if we are already at the lowest speed then break out early + * or if we 'cannot' reduce the speed as the user might want + * freq_step to be zero */ + if (requested_freq[cpu] == policy->min + || dbs_tuners_ins.freq_step == 0) + return; + + freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100; + + /* max freq cannot be less than 100. But who knows.... */ + if (unlikely(freq_step == 0)) + freq_step = 5; + + requested_freq[cpu] -= freq_step; + if (requested_freq[cpu] < policy->min) + requested_freq[cpu] = policy->min; + + __cpufreq_driver_target(policy, + requested_freq[cpu], + CPUFREQ_RELATION_H); + return; + } +} + +static void do_dbs_timer(void *data) +{ + int i; + down(&dbs_sem); + for_each_online_cpu(i) + dbs_check_cpu(i); + schedule_delayed_work(&dbs_work, + usecs_to_jiffies(dbs_tuners_ins.sampling_rate)); + up(&dbs_sem); +} + +static inline void dbs_timer_init(void) +{ + INIT_WORK(&dbs_work, do_dbs_timer, NULL); + schedule_delayed_work(&dbs_work, + usecs_to_jiffies(dbs_tuners_ins.sampling_rate)); + return; +} + +static inline void dbs_timer_exit(void) +{ + cancel_delayed_work(&dbs_work); + return; +} + +static int cpufreq_governor_dbs(struct cpufreq_policy *policy, + unsigned int event) +{ + unsigned int cpu = policy->cpu; + struct cpu_dbs_info_s *this_dbs_info; + unsigned int j; + + this_dbs_info = &per_cpu(cpu_dbs_info, cpu); + + switch (event) { + case CPUFREQ_GOV_START: + if ((!cpu_online(cpu)) || + (!policy->cur)) + return -EINVAL; + + if (policy->cpuinfo.transition_latency > + (TRANSITION_LATENCY_LIMIT * 1000)) + return -EINVAL; + if (this_dbs_info->enable) /* Already enabled */ + break; + + down(&dbs_sem); + for_each_cpu_mask(j, policy->cpus) { + struct cpu_dbs_info_s *j_dbs_info; + j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info->cur_policy = policy; + + j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j); + j_dbs_info->prev_cpu_idle_down + = j_dbs_info->prev_cpu_idle_up; + } + this_dbs_info->enable = 1; + sysfs_create_group(&policy->kobj, &dbs_attr_group); + dbs_enable++; + /* + * Start the timerschedule work, when this governor + * is used for first time + */ + if (dbs_enable == 1) { + unsigned int latency; + /* policy latency is in nS. Convert it to uS first */ + + latency = policy->cpuinfo.transition_latency; + if (latency < 1000) + latency = 1000; + + def_sampling_rate = (latency / 1000) * + DEF_SAMPLING_RATE_LATENCY_MULTIPLIER; + dbs_tuners_ins.sampling_rate = def_sampling_rate; + dbs_tuners_ins.ignore_nice = 0; + dbs_tuners_ins.freq_step = 5; + + dbs_timer_init(); + } + + up(&dbs_sem); + break; + + case CPUFREQ_GOV_STOP: + down(&dbs_sem); + this_dbs_info->enable = 0; + sysfs_remove_group(&policy->kobj, &dbs_attr_group); + dbs_enable--; + /* + * Stop the timerschedule work, when this governor + * is used for first time + */ + if (dbs_enable == 0) + dbs_timer_exit(); + + up(&dbs_sem); + + break; + + case CPUFREQ_GOV_LIMITS: + down(&dbs_sem); + if (policy->max < this_dbs_info->cur_policy->cur) + __cpufreq_driver_target( + this_dbs_info->cur_policy, + policy->max, CPUFREQ_RELATION_H); + else if (policy->min > this_dbs_info->cur_policy->cur) + __cpufreq_driver_target( + this_dbs_info->cur_policy, + policy->min, CPUFREQ_RELATION_L); + up(&dbs_sem); + break; + } + return 0; +} + +static struct cpufreq_governor cpufreq_gov_dbs = { + .name = "conservative", + .governor = cpufreq_governor_dbs, + .owner = THIS_MODULE, +}; + +static int __init cpufreq_gov_dbs_init(void) +{ + return cpufreq_register_governor(&cpufreq_gov_dbs); +} + +static void __exit cpufreq_gov_dbs_exit(void) +{ + /* Make sure that the scheduled work is indeed not running */ + flush_scheduled_work(); + + cpufreq_unregister_governor(&cpufreq_gov_dbs); +} + + +MODULE_AUTHOR ("Alexander Clouter <alex-kernel@digriz.org.uk>"); +MODULE_DESCRIPTION ("'cpufreq_conservative' - A dynamic cpufreq governor for " + "Low Latency Frequency Transition capable processors " + "optimised for use in a battery environment"); +MODULE_LICENSE ("GPL"); + +module_init(cpufreq_gov_dbs_init); +module_exit(cpufreq_gov_dbs_exit); diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 8d83a21c6477..c1fc9c62bb51 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -34,13 +34,9 @@ */ #define DEF_FREQUENCY_UP_THRESHOLD (80) -#define MIN_FREQUENCY_UP_THRESHOLD (0) +#define MIN_FREQUENCY_UP_THRESHOLD (11) #define MAX_FREQUENCY_UP_THRESHOLD (100) -#define DEF_FREQUENCY_DOWN_THRESHOLD (20) -#define MIN_FREQUENCY_DOWN_THRESHOLD (0) -#define MAX_FREQUENCY_DOWN_THRESHOLD (100) - /* * The polling frequency of this governor depends on the capability of * the processor. Default polling frequency is 1000 times the transition @@ -55,9 +51,9 @@ static unsigned int def_sampling_rate; #define MIN_SAMPLING_RATE (def_sampling_rate / 2) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) -#define DEF_SAMPLING_DOWN_FACTOR (10) +#define DEF_SAMPLING_DOWN_FACTOR (1) +#define MAX_SAMPLING_DOWN_FACTOR (10) #define TRANSITION_LATENCY_LIMIT (10 * 1000) -#define sampling_rate_in_HZ(x) (((x * HZ) < (1000 * 1000))?1:((x * HZ) / (1000 * 1000))) static void do_dbs_timer(void *data); @@ -78,15 +74,23 @@ struct dbs_tuners { unsigned int sampling_rate; unsigned int sampling_down_factor; unsigned int up_threshold; - unsigned int down_threshold; + unsigned int ignore_nice; }; static struct dbs_tuners dbs_tuners_ins = { .up_threshold = DEF_FREQUENCY_UP_THRESHOLD, - .down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD, .sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR, }; +static inline unsigned int get_cpu_idle_time(unsigned int cpu) +{ + return kstat_cpu(cpu).cpustat.idle + + kstat_cpu(cpu).cpustat.iowait + + ( !dbs_tuners_ins.ignore_nice ? + kstat_cpu(cpu).cpustat.nice : + 0); +} + /************************** sysfs interface ************************/ static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf) { @@ -115,7 +119,7 @@ static ssize_t show_##file_name \ show_one(sampling_rate, sampling_rate); show_one(sampling_down_factor, sampling_down_factor); show_one(up_threshold, up_threshold); -show_one(down_threshold, down_threshold); +show_one(ignore_nice, ignore_nice); static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, const char *buf, size_t count) @@ -126,6 +130,9 @@ static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, if (ret != 1 ) return -EINVAL; + if (input > MAX_SAMPLING_DOWN_FACTOR || input < 1) + return -EINVAL; + down(&dbs_sem); dbs_tuners_ins.sampling_down_factor = input; up(&dbs_sem); @@ -161,8 +168,7 @@ static ssize_t store_up_threshold(struct cpufreq_policy *unused, down(&dbs_sem); if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || - input < MIN_FREQUENCY_UP_THRESHOLD || - input <= dbs_tuners_ins.down_threshold) { + input < MIN_FREQUENCY_UP_THRESHOLD) { up(&dbs_sem); return -EINVAL; } @@ -173,22 +179,35 @@ static ssize_t store_up_threshold(struct cpufreq_policy *unused, return count; } -static ssize_t store_down_threshold(struct cpufreq_policy *unused, +static ssize_t store_ignore_nice(struct cpufreq_policy *policy, const char *buf, size_t count) { unsigned int input; int ret; + + unsigned int j; + ret = sscanf (buf, "%u", &input); + if ( ret != 1 ) + return -EINVAL; + if ( input > 1 ) + input = 1; + down(&dbs_sem); - if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || - input < MIN_FREQUENCY_DOWN_THRESHOLD || - input >= dbs_tuners_ins.up_threshold) { + if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */ up(&dbs_sem); - return -EINVAL; + return count; } + dbs_tuners_ins.ignore_nice = input; - dbs_tuners_ins.down_threshold = input; + /* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */ + for_each_online_cpu(j) { + struct cpu_dbs_info_s *j_dbs_info; + j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j); + j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up; + } up(&dbs_sem); return count; @@ -201,7 +220,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name) define_one_rw(sampling_rate); define_one_rw(sampling_down_factor); define_one_rw(up_threshold); -define_one_rw(down_threshold); +define_one_rw(ignore_nice); static struct attribute * dbs_attributes[] = { &sampling_rate_max.attr, @@ -209,7 +228,7 @@ static struct attribute * dbs_attributes[] = { &sampling_rate.attr, &sampling_down_factor.attr, &up_threshold.attr, - &down_threshold.attr, + &ignore_nice.attr, NULL }; @@ -222,9 +241,8 @@ static struct attribute_group dbs_attr_group = { static void dbs_check_cpu(int cpu) { - unsigned int idle_ticks, up_idle_ticks, down_idle_ticks; - unsigned int total_idle_ticks; - unsigned int freq_down_step; + unsigned int idle_ticks, up_idle_ticks, total_ticks; + unsigned int freq_next; unsigned int freq_down_sampling_rate; static int down_skip[NR_CPUS]; struct cpu_dbs_info_s *this_dbs_info; @@ -238,38 +256,25 @@ static void dbs_check_cpu(int cpu) policy = this_dbs_info->cur_policy; /* - * The default safe range is 20% to 80% - * Every sampling_rate, we check - * - If current idle time is less than 20%, then we try to - * increase frequency - * Every sampling_rate*sampling_down_factor, we check - * - If current idle time is more than 80%, then we try to - * decrease frequency + * Every sampling_rate, we check, if current idle time is less + * than 20% (default), then we try to increase frequency + * Every sampling_rate*sampling_down_factor, we look for a the lowest + * frequency which can sustain the load while keeping idle time over + * 30%. If such a frequency exist, we try to decrease to this frequency. * * Any frequency increase takes it to the maximum frequency. * Frequency reduction happens at minimum steps of - * 5% of max_frequency + * 5% (default) of current frequency */ /* Check for frequency increase */ - total_idle_ticks = kstat_cpu(cpu).cpustat.idle + - kstat_cpu(cpu).cpustat.iowait; - idle_ticks = total_idle_ticks - - this_dbs_info->prev_cpu_idle_up; - this_dbs_info->prev_cpu_idle_up = total_idle_ticks; - - + idle_ticks = UINT_MAX; for_each_cpu_mask(j, policy->cpus) { - unsigned int tmp_idle_ticks; + unsigned int tmp_idle_ticks, total_idle_ticks; struct cpu_dbs_info_s *j_dbs_info; - if (j == cpu) - continue; - j_dbs_info = &per_cpu(cpu_dbs_info, j); - /* Check for frequency increase */ - total_idle_ticks = kstat_cpu(j).cpustat.idle + - kstat_cpu(j).cpustat.iowait; + total_idle_ticks = get_cpu_idle_time(j); tmp_idle_ticks = total_idle_ticks - j_dbs_info->prev_cpu_idle_up; j_dbs_info->prev_cpu_idle_up = total_idle_ticks; @@ -281,13 +286,23 @@ static void dbs_check_cpu(int cpu) /* Scale idle ticks by 100 and compare with up and down ticks */ idle_ticks *= 100; up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) * - sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate); + usecs_to_jiffies(dbs_tuners_ins.sampling_rate); if (idle_ticks < up_idle_ticks) { + down_skip[cpu] = 0; + for_each_cpu_mask(j, policy->cpus) { + struct cpu_dbs_info_s *j_dbs_info; + + j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info->prev_cpu_idle_down = + j_dbs_info->prev_cpu_idle_up; + } + /* if we are already at full speed then break out early */ + if (policy->cur == policy->max) + return; + __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); - down_skip[cpu] = 0; - this_dbs_info->prev_cpu_idle_down = total_idle_ticks; return; } @@ -296,23 +311,14 @@ static void dbs_check_cpu(int cpu) if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor) return; - total_idle_ticks = kstat_cpu(cpu).cpustat.idle + - kstat_cpu(cpu).cpustat.iowait; - idle_ticks = total_idle_ticks - - this_dbs_info->prev_cpu_idle_down; - this_dbs_info->prev_cpu_idle_down = total_idle_ticks; - + idle_ticks = UINT_MAX; for_each_cpu_mask(j, policy->cpus) { - unsigned int tmp_idle_ticks; + unsigned int tmp_idle_ticks, total_idle_ticks; struct cpu_dbs_info_s *j_dbs_info; - if (j == cpu) - continue; - j_dbs_info = &per_cpu(cpu_dbs_info, j); - /* Check for frequency increase */ - total_idle_ticks = kstat_cpu(j).cpustat.idle + - kstat_cpu(j).cpustat.iowait; + /* Check for frequency decrease */ + total_idle_ticks = j_dbs_info->prev_cpu_idle_up; tmp_idle_ticks = total_idle_ticks - j_dbs_info->prev_cpu_idle_down; j_dbs_info->prev_cpu_idle_down = total_idle_ticks; @@ -321,38 +327,37 @@ static void dbs_check_cpu(int cpu) idle_ticks = tmp_idle_ticks; } - /* Scale idle ticks by 100 and compare with up and down ticks */ - idle_ticks *= 100; down_skip[cpu] = 0; + /* if we cannot reduce the frequency anymore, break out early */ + if (policy->cur == policy->min) + return; + /* Compute how many ticks there are between two measurements */ freq_down_sampling_rate = dbs_tuners_ins.sampling_rate * dbs_tuners_ins.sampling_down_factor; - down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) * - sampling_rate_in_HZ(freq_down_sampling_rate); + total_ticks = usecs_to_jiffies(freq_down_sampling_rate); - if (idle_ticks > down_idle_ticks ) { - freq_down_step = (5 * policy->max) / 100; - - /* max freq cannot be less than 100. But who knows.... */ - if (unlikely(freq_down_step == 0)) - freq_down_step = 5; + /* + * The optimal frequency is the frequency that is the lowest that + * can support the current CPU usage without triggering the up + * policy. To be safe, we focus 10 points under the threshold. + */ + freq_next = ((total_ticks - idle_ticks) * 100) / total_ticks; + freq_next = (freq_next * policy->cur) / + (dbs_tuners_ins.up_threshold - 10); - __cpufreq_driver_target(policy, - policy->cur - freq_down_step, - CPUFREQ_RELATION_H); - return; - } + if (freq_next <= ((policy->cur * 95) / 100)) + __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L); } static void do_dbs_timer(void *data) { int i; down(&dbs_sem); - for (i = 0; i < NR_CPUS; i++) - if (cpu_online(i)) - dbs_check_cpu(i); + for_each_online_cpu(i) + dbs_check_cpu(i); schedule_delayed_work(&dbs_work, - sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate)); + usecs_to_jiffies(dbs_tuners_ins.sampling_rate)); up(&dbs_sem); } @@ -360,7 +365,7 @@ static inline void dbs_timer_init(void) { INIT_WORK(&dbs_work, do_dbs_timer, NULL); schedule_delayed_work(&dbs_work, - sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate)); + usecs_to_jiffies(dbs_tuners_ins.sampling_rate)); return; } @@ -397,12 +402,9 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, j_dbs_info = &per_cpu(cpu_dbs_info, j); j_dbs_info->cur_policy = policy; - j_dbs_info->prev_cpu_idle_up = - kstat_cpu(j).cpustat.idle + - kstat_cpu(j).cpustat.iowait; - j_dbs_info->prev_cpu_idle_down = - kstat_cpu(j).cpustat.idle + - kstat_cpu(j).cpustat.iowait; + j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j); + j_dbs_info->prev_cpu_idle_down + = j_dbs_info->prev_cpu_idle_up; } this_dbs_info->enable = 1; sysfs_create_group(&policy->kobj, &dbs_attr_group); @@ -422,6 +424,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, def_sampling_rate = (latency / 1000) * DEF_SAMPLING_RATE_LATENCY_MULTIPLIER; dbs_tuners_ins.sampling_rate = def_sampling_rate; + dbs_tuners_ins.ignore_nice = 0; dbs_timer_init(); } @@ -461,12 +464,11 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, return 0; } -struct cpufreq_governor cpufreq_gov_dbs = { +static struct cpufreq_governor cpufreq_gov_dbs = { .name = "ondemand", .governor = cpufreq_governor_dbs, .owner = THIS_MODULE, }; -EXPORT_SYMBOL(cpufreq_gov_dbs); static int __init cpufreq_gov_dbs_init(void) { diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 2084593937c6..741b6b191e6a 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -19,6 +19,7 @@ #include <linux/percpu.h> #include <linux/kobject.h> #include <linux/spinlock.h> +#include <asm/cputime.h> static spinlock_t cpufreq_stats_lock; @@ -29,20 +30,14 @@ static struct freq_attr _attr_##_name = {\ .show = _show,\ }; -static unsigned long -delta_time(unsigned long old, unsigned long new) -{ - return (old > new) ? (old - new): (new + ~old + 1); -} - struct cpufreq_stats { unsigned int cpu; unsigned int total_trans; - unsigned long long last_time; + unsigned long long last_time; unsigned int max_state; unsigned int state_num; unsigned int last_index; - unsigned long long *time_in_state; + cputime64_t *time_in_state; unsigned int *freq_table; #ifdef CONFIG_CPU_FREQ_STAT_DETAILS unsigned int *trans_table; @@ -60,12 +55,16 @@ static int cpufreq_stats_update (unsigned int cpu) { struct cpufreq_stats *stat; + unsigned long long cur_time; + + cur_time = get_jiffies_64(); spin_lock(&cpufreq_stats_lock); stat = cpufreq_stats_table[cpu]; if (stat->time_in_state) - stat->time_in_state[stat->last_index] += - delta_time(stat->last_time, jiffies); - stat->last_time = jiffies; + stat->time_in_state[stat->last_index] = + cputime64_add(stat->time_in_state[stat->last_index], + cputime_sub(cur_time, stat->last_time)); + stat->last_time = cur_time; spin_unlock(&cpufreq_stats_lock); return 0; } @@ -90,8 +89,8 @@ show_time_in_state(struct cpufreq_policy *policy, char *buf) return 0; cpufreq_stats_update(stat->cpu); for (i = 0; i < stat->state_num; i++) { - len += sprintf(buf + len, "%u %llu\n", - stat->freq_table[i], stat->time_in_state[i]); + len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i], + (unsigned long long)cputime64_to_clock_t(stat->time_in_state[i])); } return len; } @@ -107,16 +106,30 @@ show_trans_table(struct cpufreq_policy *policy, char *buf) if(!stat) return 0; cpufreq_stats_update(stat->cpu); + len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); + len += snprintf(buf + len, PAGE_SIZE - len, " : "); + for (i = 0; i < stat->state_num; i++) { + if (len >= PAGE_SIZE) + break; + len += snprintf(buf + len, PAGE_SIZE - len, "%9u ", + stat->freq_table[i]); + } + if (len >= PAGE_SIZE) + return len; + + len += snprintf(buf + len, PAGE_SIZE - len, "\n"); + for (i = 0; i < stat->state_num; i++) { if (len >= PAGE_SIZE) break; - len += snprintf(buf + len, PAGE_SIZE - len, "%9u:\t", + + len += snprintf(buf + len, PAGE_SIZE - len, "%9u: ", stat->freq_table[i]); for (j = 0; j < stat->state_num; j++) { if (len >= PAGE_SIZE) break; - len += snprintf(buf + len, PAGE_SIZE - len, "%u\t", + len += snprintf(buf + len, PAGE_SIZE - len, "%9u ", stat->trans_table[i*stat->max_state+j]); } len += snprintf(buf + len, PAGE_SIZE - len, "\n"); @@ -197,7 +210,7 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy, count++; } - alloc_size = count * sizeof(int) + count * sizeof(long long); + alloc_size = count * sizeof(int) + count * sizeof(cputime64_t); #ifdef CONFIG_CPU_FREQ_STAT_DETAILS alloc_size += count * count * sizeof(int); @@ -224,7 +237,7 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy, } stat->state_num = j; spin_lock(&cpufreq_stats_lock); - stat->last_time = jiffies; + stat->last_time = get_jiffies_64(); stat->last_index = freq_table_get_index(stat, policy->cur); spin_unlock(&cpufreq_stats_lock); cpufreq_cpu_put(data); |