/* * drivers/cpufreq/cpufreq_interactive.c * * Copyright (C) 2010 Google, Inc. * * This software is licensed under the terms of the GNU General Public * License version 2, as published by the Free Software Foundation, and * may be copied, distributed, and modified under those terms. * * 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. * * Author: Mike Chan (mike@android.com) * */ #include #include #include #include #include #include #include #include #include #include #include static atomic_t active_count = ATOMIC_INIT(0); struct cpufreq_interactive_cpuinfo { struct timer_list cpu_timer; int timer_idlecancel; u64 time_in_idle; u64 time_in_iowait; u64 idle_exit_time; u64 timer_run_time; int idling; u64 freq_change_time; u64 freq_change_time_in_idle; u64 freq_change_time_in_iowait; struct cpufreq_policy *policy; struct cpufreq_frequency_table *freq_table; unsigned int target_freq; int governor_enabled; }; static DEFINE_PER_CPU(struct cpufreq_interactive_cpuinfo, cpuinfo); /* Workqueues handle frequency scaling */ static struct task_struct *up_task; static struct workqueue_struct *down_wq; static struct work_struct freq_scale_down_work; static cpumask_t up_cpumask; static spinlock_t up_cpumask_lock; static cpumask_t down_cpumask; static spinlock_t down_cpumask_lock; static struct mutex set_speed_lock; /* Go to max speed when CPU load at or above this value. */ #define DEFAULT_GO_MAXSPEED_LOAD 85 static unsigned long go_maxspeed_load; /* Base of exponential raise to max speed; if 0 - jump to maximum */ static unsigned long boost_factor; /* Max frequency boost in Hz; if 0 - no max is enforced */ static unsigned long max_boost; /* Consider IO as busy */ static unsigned long io_is_busy; /* * Targeted sustainable load relatively to current frequency. * If 0, target is set realtively to the max speed */ static unsigned long sustain_load; /* * The minimum amount of time to spend at a frequency before we can ramp down. */ #define DEFAULT_MIN_SAMPLE_TIME 30000; static unsigned long min_sample_time; /* * The sample rate of the timer used to increase frequency */ #define DEFAULT_TIMER_RATE 20000; static unsigned long timer_rate; static int cpufreq_governor_interactive(struct cpufreq_policy *policy, unsigned int event); #ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE static #endif struct cpufreq_governor cpufreq_gov_interactive = { .name = "interactive", .governor = cpufreq_governor_interactive, .max_transition_latency = 10000000, .owner = THIS_MODULE, }; static unsigned int cpufreq_interactive_get_target( int cpu_load, int load_since_change, struct cpufreq_policy *policy) { unsigned int target_freq; /* * Choose greater of short-term load (since last idle timer * started or timer function re-armed itself) or long-term load * (since last frequency change). */ if (load_since_change > cpu_load) cpu_load = load_since_change; if (cpu_load >= go_maxspeed_load) { if (!boost_factor) return policy->max; target_freq = policy->cur * boost_factor; if (max_boost && target_freq > policy->cur + max_boost) target_freq = policy->cur + max_boost; } else { if (!sustain_load) return policy->max * cpu_load / 100; target_freq = policy->cur * cpu_load / sustain_load; } target_freq = min(target_freq, policy->max); return target_freq; } static inline cputime64_t get_cpu_iowait_time( unsigned int cpu, cputime64_t *wall) { u64 iowait_time = get_cpu_iowait_time_us(cpu, wall); if (iowait_time == -1ULL) return 0; return iowait_time; } static void cpufreq_interactive_timer(unsigned long data) { unsigned int delta_idle; unsigned int delta_iowait; unsigned int delta_time; int cpu_load; int load_since_change; u64 time_in_idle; u64 time_in_iowait; u64 idle_exit_time; struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, data); u64 now_idle; u64 now_iowait; unsigned int new_freq; unsigned int index; unsigned long flags; smp_rmb(); if (!pcpu->governor_enabled) goto exit; /* * Once pcpu->timer_run_time is updated to >= pcpu->idle_exit_time, * this lets idle exit know the current idle time sample has * been processed, and idle exit can generate a new sample and * re-arm the timer. This prevents a concurrent idle * exit on that CPU from writing a new set of info at the same time * the timer function runs (the timer function can't use that info * until more time passes). */ time_in_idle = pcpu->time_in_idle; time_in_iowait = pcpu->time_in_iowait; idle_exit_time = pcpu->idle_exit_time; now_idle = get_cpu_idle_time_us(data, &pcpu->timer_run_time); now_iowait = get_cpu_iowait_time(data, NULL); smp_wmb(); /* If we raced with cancelling a timer, skip. */ if (!idle_exit_time) goto exit; delta_idle = (unsigned int) cputime64_sub(now_idle, time_in_idle); delta_iowait = (unsigned int) cputime64_sub(now_iowait, time_in_iowait); delta_time = (unsigned int) cputime64_sub(pcpu->timer_run_time, idle_exit_time); /* * If timer ran less than 1ms after short-term sample started, retry. */ if (delta_time < 1000) goto rearm; if (delta_idle > delta_time) cpu_load = 0; else { if (io_is_busy && delta_idle >= delta_iowait) delta_idle -= delta_iowait; cpu_load = 100 * (delta_time - delta_idle) / delta_time; } delta_idle = (unsigned int) cputime64_sub(now_idle, pcpu->freq_change_time_in_idle); delta_iowait = (unsigned int) cputime64_sub(now_iowait, pcpu->freq_change_time_in_iowait); delta_time = (unsigned int) cputime64_sub(pcpu->timer_run_time, pcpu->freq_change_time); if ((delta_time == 0) || (delta_idle > delta_time)) load_since_change = 0; else { if (io_is_busy && delta_idle >= delta_iowait) delta_idle -= delta_iowait; load_since_change = 100 * (delta_time - delta_idle) / delta_time; } /* * Combine short-term load (since last idle timer started or timer * function re-armed itself) and long-term load (since last frequency * change) to determine new target frequency */ new_freq = cpufreq_interactive_get_target(cpu_load, load_since_change, pcpu->policy); if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table, new_freq, CPUFREQ_RELATION_H, &index)) { pr_warn_once("timer %d: cpufreq_frequency_table_target error\n", (int) data); goto rearm; } new_freq = pcpu->freq_table[index].frequency; if (pcpu->target_freq == new_freq) goto rearm_if_notmax; /* * Do not scale down unless we have been at this frequency for the * minimum sample time. */ if (new_freq < pcpu->target_freq) { if (cputime64_sub(pcpu->timer_run_time, pcpu->freq_change_time) < min_sample_time) goto rearm; } if (new_freq < pcpu->target_freq) { pcpu->target_freq = new_freq; spin_lock_irqsave(&down_cpumask_lock, flags); cpumask_set_cpu(data, &down_cpumask); spin_unlock_irqrestore(&down_cpumask_lock, flags); queue_work(down_wq, &freq_scale_down_work); } else { pcpu->target_freq = new_freq; spin_lock_irqsave(&up_cpumask_lock, flags); cpumask_set_cpu(data, &up_cpumask); spin_unlock_irqrestore(&up_cpumask_lock, flags); wake_up_process(up_task); } rearm_if_notmax: /* * Already set max speed and don't see a need to change that, * wait until next idle to re-evaluate, don't need timer. */ if (pcpu->target_freq == pcpu->policy->max) goto exit; rearm: if (!timer_pending(&pcpu->cpu_timer)) { /* * If already at min: if that CPU is idle, don't set timer. * Else cancel the timer if that CPU goes idle. We don't * need to re-evaluate speed until the next idle exit. */ if (pcpu->target_freq == pcpu->policy->min) { smp_rmb(); if (pcpu->idling) goto exit; pcpu->timer_idlecancel = 1; } pcpu->time_in_idle = get_cpu_idle_time_us( data, &pcpu->idle_exit_time); pcpu->time_in_iowait = get_cpu_iowait_time( data, NULL); mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate)); } exit: return; } static void cpufreq_interactive_idle_start(void) { struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, smp_processor_id()); int pending; if (!pcpu->governor_enabled) return; pcpu->idling = 1; smp_wmb(); pending = timer_pending(&pcpu->cpu_timer); if (pcpu->target_freq != pcpu->policy->min) { #ifdef CONFIG_SMP /* * Entering idle while not at lowest speed. On some * platforms this can hold the other CPU(s) at that speed * even though the CPU is idle. Set a timer to re-evaluate * speed so this idle CPU doesn't hold the other CPUs above * min indefinitely. This should probably be a quirk of * the CPUFreq driver. */ if (!pending) { pcpu->time_in_idle = get_cpu_idle_time_us( smp_processor_id(), &pcpu->idle_exit_time); pcpu->time_in_iowait = get_cpu_iowait_time( smp_processor_id(), NULL); pcpu->timer_idlecancel = 0; mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate)); } #endif } else { /* * If at min speed and entering idle after load has * already been evaluated, and a timer has been set just in * case the CPU suddenly goes busy, cancel that timer. The * CPU didn't go busy; we'll recheck things upon idle exit. */ if (pending && pcpu->timer_idlecancel) { del_timer(&pcpu->cpu_timer); /* * Ensure last timer run time is after current idle * sample start time, so next idle exit will always * start a new idle sampling period. */ pcpu->idle_exit_time = 0; pcpu->timer_idlecancel = 0; } } } static void cpufreq_interactive_idle_end(void) { struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, smp_processor_id()); pcpu->idling = 0; smp_wmb(); /* * Arm the timer for 1-2 ticks later if not already, and if the timer * function has already processed the previous load sampling * interval. (If the timer is not pending but has not processed * the previous interval, it is probably racing with us on another * CPU. Let it compute load based on the previous sample and then * re-arm the timer for another interval when it's done, rather * than updating the interval start time to be "now", which doesn't * give the timer function enough time to make a decision on this * run.) */ if (timer_pending(&pcpu->cpu_timer) == 0 && pcpu->timer_run_time >= pcpu->idle_exit_time && pcpu->governor_enabled) { pcpu->time_in_idle = get_cpu_idle_time_us(smp_processor_id(), &pcpu->idle_exit_time); pcpu->time_in_iowait = get_cpu_iowait_time(smp_processor_id(), NULL); pcpu->timer_idlecancel = 0; mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate)); } } static int cpufreq_interactive_up_task(void *data) { unsigned int cpu; cpumask_t tmp_mask; unsigned long flags; struct cpufreq_interactive_cpuinfo *pcpu; while (1) { set_current_state(TASK_INTERRUPTIBLE); spin_lock_irqsave(&up_cpumask_lock, flags); if (cpumask_empty(&up_cpumask)) { spin_unlock_irqrestore(&up_cpumask_lock, flags); schedule(); if (kthread_should_stop()) break; spin_lock_irqsave(&up_cpumask_lock, flags); } set_current_state(TASK_RUNNING); tmp_mask = up_cpumask; cpumask_clear(&up_cpumask); spin_unlock_irqrestore(&up_cpumask_lock, flags); for_each_cpu(cpu, &tmp_mask) { unsigned int j; unsigned int max_freq = 0; pcpu = &per_cpu(cpuinfo, cpu); smp_rmb(); if (!pcpu->governor_enabled) continue; mutex_lock(&set_speed_lock); for_each_cpu(j, pcpu->policy->cpus) { struct cpufreq_interactive_cpuinfo *pjcpu = &per_cpu(cpuinfo, j); if (pjcpu->target_freq > max_freq) max_freq = pjcpu->target_freq; } __cpufreq_driver_target(pcpu->policy, max_freq, CPUFREQ_RELATION_H); mutex_unlock(&set_speed_lock); pcpu->freq_change_time_in_idle = get_cpu_idle_time_us(cpu, &pcpu->freq_change_time); pcpu->freq_change_time_in_iowait = get_cpu_iowait_time(cpu, NULL); } } return 0; } static void cpufreq_interactive_freq_down(struct work_struct *work) { unsigned int cpu; cpumask_t tmp_mask; unsigned long flags; struct cpufreq_interactive_cpuinfo *pcpu; spin_lock_irqsave(&down_cpumask_lock, flags); tmp_mask = down_cpumask; cpumask_clear(&down_cpumask); spin_unlock_irqrestore(&down_cpumask_lock, flags); for_each_cpu(cpu, &tmp_mask) { unsigned int j; unsigned int max_freq = 0; pcpu = &per_cpu(cpuinfo, cpu); smp_rmb(); if (!pcpu->governor_enabled) continue; mutex_lock(&set_speed_lock); for_each_cpu(j, pcpu->policy->cpus) { struct cpufreq_interactive_cpuinfo *pjcpu = &per_cpu(cpuinfo, j); if (pjcpu->target_freq > max_freq) max_freq = pjcpu->target_freq; } __cpufreq_driver_target(pcpu->policy, max_freq, CPUFREQ_RELATION_H); mutex_unlock(&set_speed_lock); pcpu->freq_change_time_in_idle = get_cpu_idle_time_us(cpu, &pcpu->freq_change_time); pcpu->freq_change_time_in_iowait = get_cpu_iowait_time(cpu, NULL); } } static ssize_t show_go_maxspeed_load(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", go_maxspeed_load); } static ssize_t store_go_maxspeed_load(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; go_maxspeed_load = val; return count; } static struct global_attr go_maxspeed_load_attr = __ATTR(go_maxspeed_load, 0644, show_go_maxspeed_load, store_go_maxspeed_load); static ssize_t show_boost_factor(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", boost_factor); } static ssize_t store_boost_factor(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; boost_factor = val; return count; } static struct global_attr boost_factor_attr = __ATTR(boost_factor, 0644, show_boost_factor, store_boost_factor); static ssize_t show_io_is_busy(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", io_is_busy); } static ssize_t store_io_is_busy(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { if (!strict_strtoul(buf, 0, &io_is_busy)) return count; return -EINVAL; } static struct global_attr io_is_busy_attr = __ATTR(io_is_busy, 0644, show_io_is_busy, store_io_is_busy); static ssize_t show_max_boost(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", max_boost); } static ssize_t store_max_boost(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; max_boost = val; return count; } static struct global_attr max_boost_attr = __ATTR(max_boost, 0644, show_max_boost, store_max_boost); static ssize_t show_sustain_load(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", sustain_load); } static ssize_t store_sustain_load(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; sustain_load = val; return count; } static struct global_attr sustain_load_attr = __ATTR(sustain_load, 0644, show_sustain_load, store_sustain_load); static ssize_t show_min_sample_time(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", min_sample_time); } static ssize_t store_min_sample_time(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; min_sample_time = val; return count; } static struct global_attr min_sample_time_attr = __ATTR(min_sample_time, 0644, show_min_sample_time, store_min_sample_time); static ssize_t show_timer_rate(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%lu\n", timer_rate); } static ssize_t store_timer_rate(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret; unsigned long val; ret = strict_strtoul(buf, 0, &val); if (ret < 0) return ret; timer_rate = val; return count; } static struct global_attr timer_rate_attr = __ATTR(timer_rate, 0644, show_timer_rate, store_timer_rate); static struct attribute *interactive_attributes[] = { &go_maxspeed_load_attr.attr, &boost_factor_attr.attr, &max_boost_attr.attr, &io_is_busy_attr.attr, &sustain_load_attr.attr, &min_sample_time_attr.attr, &timer_rate_attr.attr, NULL, }; static struct attribute_group interactive_attr_group = { .attrs = interactive_attributes, .name = "interactive", }; static int cpufreq_governor_interactive(struct cpufreq_policy *policy, unsigned int event) { int rc; unsigned int j; struct cpufreq_interactive_cpuinfo *pcpu; struct cpufreq_frequency_table *freq_table; switch (event) { case CPUFREQ_GOV_START: if (!cpu_online(policy->cpu)) return -EINVAL; freq_table = cpufreq_frequency_get_table(policy->cpu); for_each_cpu(j, policy->cpus) { pcpu = &per_cpu(cpuinfo, j); pcpu->policy = policy; pcpu->target_freq = policy->cur; pcpu->freq_table = freq_table; pcpu->freq_change_time_in_idle = get_cpu_idle_time_us(j, &pcpu->freq_change_time); pcpu->time_in_idle = pcpu->freq_change_time_in_idle; pcpu->idle_exit_time = pcpu->freq_change_time; pcpu->freq_change_time_in_iowait = get_cpu_iowait_time(j, NULL); pcpu->time_in_iowait = pcpu->freq_change_time_in_iowait; pcpu->timer_idlecancel = 1; pcpu->governor_enabled = 1; smp_wmb(); if (!timer_pending(&pcpu->cpu_timer)) mod_timer(&pcpu->cpu_timer, jiffies + 2); } /* * Do not register the idle hook and create sysfs * entries if we have already done so. */ if (atomic_inc_return(&active_count) > 1) return 0; rc = sysfs_create_group(cpufreq_global_kobject, &interactive_attr_group); if (rc) return rc; break; case CPUFREQ_GOV_STOP: for_each_cpu(j, policy->cpus) { pcpu = &per_cpu(cpuinfo, j); pcpu->governor_enabled = 0; smp_wmb(); del_timer_sync(&pcpu->cpu_timer); /* * Reset idle exit time since we may cancel the timer * before it can run after the last idle exit time, * to avoid tripping the check in idle exit for a timer * that is trying to run. */ pcpu->idle_exit_time = 0; } flush_work(&freq_scale_down_work); if (atomic_dec_return(&active_count) > 0) return 0; sysfs_remove_group(cpufreq_global_kobject, &interactive_attr_group); break; case CPUFREQ_GOV_LIMITS: if (policy->max < policy->cur) __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); else if (policy->min > policy->cur) __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); break; } return 0; } static int cpufreq_interactive_idle_notifier(struct notifier_block *nb, unsigned long val, void *data) { switch (val) { case IDLE_START: cpufreq_interactive_idle_start(); break; case IDLE_END: cpufreq_interactive_idle_end(); break; } return 0; } static struct notifier_block cpufreq_interactive_idle_nb = { .notifier_call = cpufreq_interactive_idle_notifier, }; static int __init cpufreq_interactive_init(void) { unsigned int i; struct cpufreq_interactive_cpuinfo *pcpu; struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; go_maxspeed_load = DEFAULT_GO_MAXSPEED_LOAD; min_sample_time = DEFAULT_MIN_SAMPLE_TIME; timer_rate = DEFAULT_TIMER_RATE; /* Initalize per-cpu timers */ for_each_possible_cpu(i) { pcpu = &per_cpu(cpuinfo, i); init_timer(&pcpu->cpu_timer); pcpu->cpu_timer.function = cpufreq_interactive_timer; pcpu->cpu_timer.data = i; } up_task = kthread_create(cpufreq_interactive_up_task, NULL, "kinteractiveup"); if (IS_ERR(up_task)) return PTR_ERR(up_task); sched_setscheduler_nocheck(up_task, SCHED_FIFO, ¶m); get_task_struct(up_task); /* No rescuer thread, bind to CPU queuing the work for possibly warm cache (probably doesn't matter much). */ down_wq = alloc_workqueue("knteractive_down", 0, 1); if (!down_wq) goto err_freeuptask; INIT_WORK(&freq_scale_down_work, cpufreq_interactive_freq_down); spin_lock_init(&up_cpumask_lock); spin_lock_init(&down_cpumask_lock); mutex_init(&set_speed_lock); idle_notifier_register(&cpufreq_interactive_idle_nb); return cpufreq_register_governor(&cpufreq_gov_interactive); err_freeuptask: put_task_struct(up_task); return -ENOMEM; } #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE fs_initcall(cpufreq_interactive_init); #else module_init(cpufreq_interactive_init); #endif static void __exit cpufreq_interactive_exit(void) { cpufreq_unregister_governor(&cpufreq_gov_interactive); kthread_stop(up_task); put_task_struct(up_task); destroy_workqueue(down_wq); } module_exit(cpufreq_interactive_exit); MODULE_AUTHOR("Mike Chan "); MODULE_DESCRIPTION("'cpufreq_interactive' - A cpufreq governor for " "Latency sensitive workloads"); MODULE_LICENSE("GPL");