diff options
Diffstat (limited to 'drivers/cpufreq/cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 1890 |
1 files changed, 1182 insertions, 708 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e35a886e00bc..4472bb1ec83c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/drivers/cpufreq/cpufreq.c * @@ -9,35 +10,30 @@ * Added handling for CPU hotplug * Feb 2006 - Jacob Shin <jacob.shin@amd.com> * Fix handling for CPU hotplug -- affected CPUs - * - * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cpu.h> #include <linux/cpufreq.h> +#include <linux/cpu_cooling.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/init.h> #include <linux/kernel_stat.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/pm_qos.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/tick.h> +#include <linux/units.h> #include <trace/events/power.h> static LIST_HEAD(cpufreq_policy_list); -static inline bool policy_is_inactive(struct cpufreq_policy *policy) -{ - return cpumask_empty(policy->cpus); -} - /* Macros to iterate over CPU policies */ #define for_each_suitable_policy(__policy, __active) \ list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \ @@ -48,15 +44,14 @@ static inline bool policy_is_inactive(struct cpufreq_policy *policy) #define for_each_inactive_policy(__policy) \ for_each_suitable_policy(__policy, false) -#define for_each_policy(__policy) \ - list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) - /* Iterate over governors */ static LIST_HEAD(cpufreq_governor_list); #define for_each_governor(__governor) \ list_for_each_entry(__governor, &cpufreq_governor_list, governor_list) -/** +static char default_governor[CPUFREQ_NAME_LEN]; + +/* * The "cpufreq driver" - the arch- or hardware-dependent low * level driver of CPUFreq support, and its spinlock. This lock * also protects the cpufreq_cpu_data array. @@ -65,6 +60,12 @@ static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_RWLOCK(cpufreq_driver_lock); +static DEFINE_STATIC_KEY_FALSE(cpufreq_freq_invariance); +bool cpufreq_supports_freq_invariance(void) +{ + return static_branch_likely(&cpufreq_freq_invariance); +} + /* Flag to suspend/resume CPUFreq governors */ static bool cpufreq_suspended; @@ -73,15 +74,23 @@ static inline bool has_target(void) return cpufreq_driver->target_index || cpufreq_driver->target; } +bool has_target_index(void) +{ + return !!cpufreq_driver->target_index; +} + /* internal prototypes */ static unsigned int __cpufreq_get(struct cpufreq_policy *policy); static int cpufreq_init_governor(struct cpufreq_policy *policy); static void cpufreq_exit_governor(struct cpufreq_policy *policy); -static int cpufreq_start_governor(struct cpufreq_policy *policy); -static void cpufreq_stop_governor(struct cpufreq_policy *policy); static void cpufreq_governor_limits(struct cpufreq_policy *policy); +static int cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_governor *new_gov, + unsigned int new_pol); +static bool cpufreq_boost_supported(void); +static int cpufreq_boost_trigger_state(int state); -/** +/* * Two notifier lists: the "policy" list is involved in the * validation process for a new CPU frequency policy; the * "transition" list for kernel code that needs to handle @@ -100,6 +109,8 @@ void disable_cpufreq(void) { off = 1; } +EXPORT_SYMBOL_GPL(disable_cpufreq); + static DEFINE_MUTEX(cpufreq_governor_mutex); bool have_governor_per_policy(void) @@ -108,6 +119,8 @@ bool have_governor_per_policy(void) } EXPORT_SYMBOL_GPL(have_governor_per_policy); +static struct kobject *cpufreq_global_kobject; + struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy) { if (have_governor_per_policy()) @@ -119,18 +132,21 @@ EXPORT_SYMBOL_GPL(get_governor_parent_kobj); static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) { - u64 idle_time; + struct kernel_cpustat kcpustat; u64 cur_wall_time; + u64 idle_time; u64 busy_time; cur_wall_time = jiffies64_to_nsecs(get_jiffies_64()); - busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER]; - busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM]; - busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ]; - busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ]; - busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL]; - busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE]; + kcpustat_cpu_fetch(&kcpustat, cpu); + + busy_time = kcpustat.cpustat[CPUTIME_USER]; + busy_time += kcpustat.cpustat[CPUTIME_SYSTEM]; + busy_time += kcpustat.cpustat[CPUTIME_IRQ]; + busy_time += kcpustat.cpustat[CPUTIME_SOFTIRQ]; + busy_time += kcpustat.cpustat[CPUTIME_STEAL]; + busy_time += kcpustat.cpustat[CPUTIME_NICE]; idle_time = cur_wall_time - busy_time; if (wall) @@ -152,12 +168,6 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy) } EXPORT_SYMBOL_GPL(get_cpu_idle_time); -__weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, - unsigned long max_freq) -{ -} -EXPORT_SYMBOL_GPL(arch_set_freq_scale); - /* * This is a generic cpufreq init() routine which can be used by cpufreq * drivers of SMP systems. It will do following: @@ -165,7 +175,7 @@ EXPORT_SYMBOL_GPL(arch_set_freq_scale); * - set policies transition latency * - policy->cpus with all possible CPUs */ -int cpufreq_generic_init(struct cpufreq_policy *policy, +void cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency) { @@ -177,8 +187,6 @@ int cpufreq_generic_init(struct cpufreq_policy *policy, * share the clock and voltage and clock. */ cpumask_setall(policy->cpus); - - return 0; } EXPORT_SYMBOL_GPL(cpufreq_generic_init); @@ -205,17 +213,15 @@ unsigned int cpufreq_generic_get(unsigned int cpu) EXPORT_SYMBOL_GPL(cpufreq_generic_get); /** - * cpufreq_cpu_get: returns policy for a cpu and marks it busy. + * cpufreq_cpu_get - Return policy for a CPU and mark it as busy. + * @cpu: CPU to find the policy for. * - * @cpu: cpu to find policy for. + * Call cpufreq_cpu_get_raw() to obtain a cpufreq policy for @cpu and increment + * the kobject reference counter of that policy. Return a valid policy on + * success or NULL on failure. * - * This returns policy for 'cpu', returns NULL if it doesn't exist. - * It also increments the kobject reference count to mark it busy and so would - * require a corresponding call to cpufreq_cpu_put() to decrement it back. - * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be - * freed as that depends on the kobj count. - * - * Return: A valid policy on success, otherwise NULL on failure. + * The policy returned by this function has to be released with the help of + * cpufreq_cpu_put() to balance its kobject reference counter properly. */ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { @@ -242,12 +248,8 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) EXPORT_SYMBOL_GPL(cpufreq_cpu_get); /** - * cpufreq_cpu_put: Decrements the usage count of a policy - * - * @policy: policy earlier returned by cpufreq_cpu_get(). - * - * This decrements the kobject reference count incremented earlier by calling - * cpufreq_cpu_get(). + * cpufreq_cpu_put - Decrement kobject usage counter for cpufreq policy. + * @policy: cpufreq policy returned by cpufreq_cpu_get(). */ void cpufreq_cpu_put(struct cpufreq_policy *policy) { @@ -260,7 +262,9 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_put); *********************************************************************/ /** - * adjust_jiffies - adjust the system "loops_per_jiffy" + * adjust_jiffies - Adjust the system "loops_per_jiffy". + * @val: CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE. + * @ci: Frequency change information. * * This function alters the system "loops_per_jiffy" for the clock * speed change. Note that loops_per_jiffy cannot be updated on SMP @@ -292,24 +296,27 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) } /** - * cpufreq_notify_transition - Notify frequency transition and adjust_jiffies. + * cpufreq_notify_transition - Notify frequency transition and adjust jiffies. * @policy: cpufreq policy to enable fast frequency switching for. * @freqs: contain details of the frequency update. * @state: set to CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE. * - * This function calls the transition notifiers and the "adjust_jiffies" - * function. It is called twice on all CPU frequency changes that have - * external effects. + * This function calls the transition notifiers and adjust_jiffies(). + * + * It is called twice on all CPU frequency changes that have external effects. */ static void cpufreq_notify_transition(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, unsigned int state) { + int cpu; + BUG_ON(irqs_disabled()); if (cpufreq_disabled()) return; + freqs->policy = policy; freqs->flags = cpufreq_driver->flags; pr_debug("notification %u of frequency transition to %u kHz\n", state, freqs->new); @@ -321,18 +328,14 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy, * which is not equal to what the cpufreq core thinks is * "old frequency". */ - if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - if (policy->cur && (policy->cur != freqs->old)) { - pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n", - freqs->old, policy->cur); - freqs->old = policy->cur; - } + if (policy->cur && policy->cur != freqs->old) { + pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n", + freqs->old, policy->cur); + freqs->old = policy->cur; } - for_each_cpu(freqs->cpu, policy->cpus) { - srcu_notifier_call_chain(&cpufreq_transition_notifier_list, - CPUFREQ_PRECHANGE, freqs); - } + srcu_notifier_call_chain(&cpufreq_transition_notifier_list, + CPUFREQ_PRECHANGE, freqs); adjust_jiffies(CPUFREQ_PRECHANGE, freqs); break; @@ -342,11 +345,11 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy, pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new, cpumask_pr_args(policy->cpus)); - for_each_cpu(freqs->cpu, policy->cpus) { - trace_cpu_frequency(freqs->new, freqs->cpu); - srcu_notifier_call_chain(&cpufreq_transition_notifier_list, - CPUFREQ_POSTCHANGE, freqs); - } + for_each_cpu(cpu, policy->cpus) + trace_cpu_frequency(freqs->new, cpu); + + srcu_notifier_call_chain(&cpufreq_transition_notifier_list, + CPUFREQ_POSTCHANGE, freqs); cpufreq_stats_record_transition(policy, freqs->new); policy->cur = freqs->new; @@ -408,8 +411,14 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy, cpufreq_notify_post_transition(policy, freqs, transition_failed); + arch_set_freq_scale(policy->related_cpus, + policy->cur, + arch_scale_freq_ref(policy->cpu)); + + spin_lock(&policy->transition_lock); policy->transition_ongoing = false; policy->transition_task = NULL; + spin_unlock(&policy->transition_lock); wake_up(&policy->transition_wait); } @@ -431,7 +440,7 @@ static void cpufreq_list_transition_notifiers(void) mutex_lock(&cpufreq_transition_notifier_list.mutex); for (nb = cpufreq_transition_notifier_list.head; nb; nb = nb->next) - pr_info("%pF\n", nb->notifier_call); + pr_info("%pS\n", nb->notifier_call); mutex_unlock(&cpufreq_transition_notifier_list.mutex); } @@ -483,9 +492,28 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy) } EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch); +static unsigned int __resolve_freq(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int min, unsigned int max, + unsigned int relation) +{ + unsigned int idx; + + target_freq = clamp_val(target_freq, min, max); + + if (!policy->freq_table) + return target_freq; + + idx = cpufreq_frequency_table_target(policy, target_freq, min, max, relation); + policy->cached_resolved_idx = idx; + policy->cached_target_freq = target_freq; + return policy->freq_table[idx].frequency; +} + /** * cpufreq_driver_resolve_freq - Map a target frequency to a driver-supported * one. + * @policy: associated policy to interrogate * @target_freq: target frequency to resolve. * * The target to driver frequency mapping is cached in the policy. @@ -496,22 +524,21 @@ EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch); unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq) { - target_freq = clamp_val(target_freq, policy->min, policy->max); - policy->cached_target_freq = target_freq; - - if (cpufreq_driver->target_index) { - int idx; + unsigned int min = READ_ONCE(policy->min); + unsigned int max = READ_ONCE(policy->max); - idx = cpufreq_frequency_table_target(policy, target_freq, - CPUFREQ_RELATION_L); - policy->cached_resolved_idx = idx; - return policy->freq_table[idx].frequency; - } - - if (cpufreq_driver->resolve_freq) - return cpufreq_driver->resolve_freq(policy, target_freq); + /* + * If this function runs in parallel with cpufreq_set_policy(), it may + * read policy->min before the update and policy->max after the update + * or the other way around, so there is no ordering guarantee. + * + * Resolve this by always honoring the max (in case it comes from + * thermal throttling or similar). + */ + if (unlikely(min > max)) + min = max; - return target_freq; + return __resolve_freq(policy, target_freq, min, max, CPUFREQ_RELATION_LE); } EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq); @@ -523,21 +550,11 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy) return policy->transition_delay_us; latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC; - if (latency) { - /* - * For platforms that can change the frequency very fast (< 10 - * us), the above formula gives a decent transition delay. But - * for platforms where transition_latency is in milliseconds, it - * ends up giving unrealistic values. - * - * Cap the default transition delay to 10 ms, which seems to be - * a reasonable amount of time after which we should reevaluate - * the frequency. - */ - return min(latency * LATENCY_MULTIPLIER, (unsigned int)10000); - } + if (latency) + /* Give a 50% breathing room between updates */ + return latency + (latency >> 1); - return LATENCY_MULTIPLIER; + return USEC_PER_MSEC; } EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); @@ -545,33 +562,77 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); * SYSFS INTERFACE * *********************************************************************/ static ssize_t show_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); + return sysfs_emit(buf, "%d\n", cpufreq_driver->boost_enabled); } -static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t count) +static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) { - int ret, enable; + bool enable; - ret = sscanf(buf, "%d", &enable); - if (ret != 1 || enable < 0 || enable > 1) + if (kstrtobool(buf, &enable)) return -EINVAL; if (cpufreq_boost_trigger_state(enable)) { pr_err("%s: Cannot %s BOOST!\n", - __func__, enable ? "enable" : "disable"); + __func__, str_enable_disable(enable)); return -EINVAL; } pr_debug("%s: cpufreq BOOST %s\n", - __func__, enable ? "enabled" : "disabled"); + __func__, str_enabled_disabled(enable)); return count; } define_one_global_rw(boost); +static ssize_t show_local_boost(struct cpufreq_policy *policy, char *buf) +{ + return sysfs_emit(buf, "%d\n", policy->boost_enabled); +} + +static int policy_set_boost(struct cpufreq_policy *policy, bool enable) +{ + int ret; + + if (policy->boost_enabled == enable) + return 0; + + policy->boost_enabled = enable; + + ret = cpufreq_driver->set_boost(policy, enable); + if (ret) + policy->boost_enabled = !policy->boost_enabled; + + return ret; +} + +static ssize_t store_local_boost(struct cpufreq_policy *policy, + const char *buf, size_t count) +{ + int ret; + bool enable; + + if (kstrtobool(buf, &enable)) + return -EINVAL; + + if (!cpufreq_driver->boost_enabled) + return -EINVAL; + + if (!policy->boost_supported) + return -EINVAL; + + ret = policy_set_boost(policy, enable); + if (!ret) + return count; + + return ret; +} + +static struct freq_attr local_boost = __ATTR(boost, 0644, show_local_boost, store_local_boost); + static struct cpufreq_governor *find_governor(const char *str_governor) { struct cpufreq_governor *t; @@ -583,56 +644,54 @@ static struct cpufreq_governor *find_governor(const char *str_governor) return NULL; } -/** - * cpufreq_parse_governor - parse a governor string - */ -static int cpufreq_parse_governor(char *str_governor, - struct cpufreq_policy *policy) +static struct cpufreq_governor *get_governor(const char *str_governor) { - if (cpufreq_driver->setpolicy) { - if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) { - policy->policy = CPUFREQ_POLICY_PERFORMANCE; - return 0; - } + struct cpufreq_governor *t; - if (!strncasecmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) { - policy->policy = CPUFREQ_POLICY_POWERSAVE; - return 0; - } - } else { - struct cpufreq_governor *t; + mutex_lock(&cpufreq_governor_mutex); + t = find_governor(str_governor); + if (!t) + goto unlock; + + if (!try_module_get(t->owner)) + t = NULL; - mutex_lock(&cpufreq_governor_mutex); +unlock: + mutex_unlock(&cpufreq_governor_mutex); - t = find_governor(str_governor); - if (!t) { - int ret; + return t; +} - mutex_unlock(&cpufreq_governor_mutex); +static unsigned int cpufreq_parse_policy(char *str_governor) +{ + if (!strncasecmp(str_governor, "performance", strlen("performance"))) + return CPUFREQ_POLICY_PERFORMANCE; - ret = request_module("cpufreq_%s", str_governor); - if (ret) - return -EINVAL; + if (!strncasecmp(str_governor, "powersave", strlen("powersave"))) + return CPUFREQ_POLICY_POWERSAVE; - mutex_lock(&cpufreq_governor_mutex); + return CPUFREQ_POLICY_UNKNOWN; +} - t = find_governor(str_governor); - } - if (t && !try_module_get(t->owner)) - t = NULL; +/** + * cpufreq_parse_governor - parse a governor string only for has_target() + * @str_governor: Governor name. + */ +static struct cpufreq_governor *cpufreq_parse_governor(char *str_governor) +{ + struct cpufreq_governor *t; - mutex_unlock(&cpufreq_governor_mutex); + t = get_governor(str_governor); + if (t) + return t; - if (t) { - policy->governor = t; - return 0; - } - } + if (request_module("cpufreq_%s", str_governor)) + return NULL; - return -EINVAL; + return get_governor(str_governor); } -/** +/* * cpufreq_per_cpu_attr_read() / show_##file_name() - * print out cpufreq information * @@ -644,7 +703,7 @@ static int cpufreq_parse_governor(char *str_governor, static ssize_t show_##file_name \ (struct cpufreq_policy *policy, char *buf) \ { \ - return sprintf(buf, "%u\n", policy->object); \ + return sysfs_emit(buf, "%u\n", policy->object); \ } show_one(cpuinfo_min_freq, cpuinfo.min_freq); @@ -653,60 +712,56 @@ show_one(cpuinfo_transition_latency, cpuinfo.transition_latency); show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); -__weak unsigned int arch_freq_get_on_cpu(int cpu) +__weak int arch_freq_get_on_cpu(int cpu) { - return 0; + return -EOPNOTSUPP; +} + +static inline bool cpufreq_avg_freq_supported(struct cpufreq_policy *policy) +{ + return arch_freq_get_on_cpu(policy->cpu) != -EOPNOTSUPP; } static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) { ssize_t ret; - unsigned int freq; + int freq; + + freq = IS_ENABLED(CONFIG_CPUFREQ_ARCH_CUR_FREQ) + ? arch_freq_get_on_cpu(policy->cpu) + : 0; - freq = arch_freq_get_on_cpu(policy->cpu); - if (freq) - ret = sprintf(buf, "%u\n", freq); - else if (cpufreq_driver && cpufreq_driver->setpolicy && - cpufreq_driver->get) - ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + if (freq > 0) + ret = sysfs_emit(buf, "%u\n", freq); + else if (cpufreq_driver->setpolicy && cpufreq_driver->get) + ret = sysfs_emit(buf, "%u\n", cpufreq_driver->get(policy->cpu)); else - ret = sprintf(buf, "%u\n", policy->cur); + ret = sysfs_emit(buf, "%u\n", policy->cur); return ret; } -static int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy); - -/** +/* * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access */ #define store_one(file_name, object) \ static ssize_t store_##file_name \ (struct cpufreq_policy *policy, const char *buf, size_t count) \ { \ - int ret, temp; \ - struct cpufreq_policy new_policy; \ + unsigned long val; \ + int ret; \ \ - memcpy(&new_policy, policy, sizeof(*policy)); \ - new_policy.min = policy->user_policy.min; \ - new_policy.max = policy->user_policy.max; \ + ret = kstrtoul(buf, 0, &val); \ + if (ret) \ + return ret; \ \ - ret = sscanf(buf, "%u", &new_policy.object); \ - if (ret != 1) \ - return -EINVAL; \ - \ - temp = new_policy.object; \ - ret = cpufreq_set_policy(policy, &new_policy); \ - if (!ret) \ - policy->user_policy.object = temp; \ - \ - return ret ? ret : count; \ + ret = freq_qos_update_request(policy->object##_freq_req, val);\ + return ret >= 0 ? count : ret; \ } store_one(scaling_min_freq, min); store_one(scaling_max_freq, max); -/** +/* * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware */ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, @@ -715,54 +770,76 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, unsigned int cur_freq = __cpufreq_get(policy); if (cur_freq) - return sprintf(buf, "%u\n", cur_freq); + return sysfs_emit(buf, "%u\n", cur_freq); - return sprintf(buf, "<unknown>\n"); + return sysfs_emit(buf, "<unknown>\n"); } -/** +/* + * show_cpuinfo_avg_freq - average CPU frequency as detected by hardware + */ +static ssize_t show_cpuinfo_avg_freq(struct cpufreq_policy *policy, + char *buf) +{ + int avg_freq = arch_freq_get_on_cpu(policy->cpu); + + if (avg_freq > 0) + return sysfs_emit(buf, "%u\n", avg_freq); + return avg_freq != 0 ? avg_freq : -EINVAL; +} + +/* * show_scaling_governor - show the current policy for the specified CPU */ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf) { if (policy->policy == CPUFREQ_POLICY_POWERSAVE) - return sprintf(buf, "powersave\n"); + return sysfs_emit(buf, "powersave\n"); else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) - return sprintf(buf, "performance\n"); + return sysfs_emit(buf, "performance\n"); else if (policy->governor) - return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", - policy->governor->name); + return sysfs_emit(buf, "%s\n", policy->governor->name); return -EINVAL; } -/** +/* * store_scaling_governor - store policy for the specified CPU */ static ssize_t store_scaling_governor(struct cpufreq_policy *policy, const char *buf, size_t count) { + char str_governor[CPUFREQ_NAME_LEN]; int ret; - char str_governor[16]; - struct cpufreq_policy new_policy; - - memcpy(&new_policy, policy, sizeof(*policy)); ret = sscanf(buf, "%15s", str_governor); if (ret != 1) return -EINVAL; - if (cpufreq_parse_governor(str_governor, &new_policy)) - return -EINVAL; + if (cpufreq_driver->setpolicy) { + unsigned int new_pol; + + new_pol = cpufreq_parse_policy(str_governor); + if (!new_pol) + return -EINVAL; + + ret = cpufreq_set_policy(policy, NULL, new_pol); + } else { + struct cpufreq_governor *new_gov; + + new_gov = cpufreq_parse_governor(str_governor); + if (!new_gov) + return -EINVAL; - ret = cpufreq_set_policy(policy, &new_policy); + ret = cpufreq_set_policy(policy, new_gov, + CPUFREQ_POLICY_UNKNOWN); - if (new_policy.governor) - module_put(new_policy.governor->owner); + module_put(new_gov->owner); + } return ret ? ret : count; } -/** +/* * show_scaling_driver - show the cpufreq driver currently loaded */ static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf) @@ -770,7 +847,7 @@ static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf) return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name); } -/** +/* * show_scaling_available_governors - show the available CPUfreq governors */ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, @@ -780,18 +857,20 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, struct cpufreq_governor *t; if (!has_target()) { - i += sprintf(buf, "performance powersave"); + i += sysfs_emit(buf, "performance powersave"); goto out; } + mutex_lock(&cpufreq_governor_mutex); for_each_governor(t) { if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char)) - (CPUFREQ_NAME_LEN + 2))) - goto out; - i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name); + break; + i += sysfs_emit_at(buf, i, "%s ", t->name); } + mutex_unlock(&cpufreq_governor_mutex); out: - i += sprintf(&buf[i], "\n"); + i += sysfs_emit_at(buf, i, "\n"); return i; } @@ -801,18 +880,20 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf) unsigned int cpu; for_each_cpu(cpu, mask) { - if (i) - i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " "); - i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu); + i += sysfs_emit_at(buf, i, "%u ", cpu); if (i >= (PAGE_SIZE - 5)) break; } - i += sprintf(&buf[i], "\n"); + + /* Remove the extra space at the end */ + i--; + + i += sysfs_emit_at(buf, i, "\n"); return i; } EXPORT_SYMBOL_GPL(cpufreq_show_cpus); -/** +/* * show_related_cpus - show the CPUs affected by each transition even if * hw coordination is in use */ @@ -821,7 +902,7 @@ static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf) return cpufreq_show_cpus(policy->related_cpus, buf); } -/** +/* * show_affected_cpus - show the CPUs affected by each transition */ static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf) @@ -833,14 +914,14 @@ static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy, const char *buf, size_t count) { unsigned int freq = 0; - unsigned int ret; + int ret; if (!policy->governor || !policy->governor->store_setspeed) return -EINVAL; - ret = sscanf(buf, "%u", &freq); - if (ret != 1) - return -EINVAL; + ret = kstrtouint(buf, 0, &freq); + if (ret) + return ret; policy->governor->store_setspeed(policy, freq); @@ -850,27 +931,26 @@ static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy, static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf) { if (!policy->governor || !policy->governor->show_setspeed) - return sprintf(buf, "<unsupported>\n"); + return sysfs_emit(buf, "<unsupported>\n"); return policy->governor->show_setspeed(policy, buf); } -/** +/* * show_bios_limit - show the current cpufreq HW/BIOS limitation */ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf) { unsigned int limit; int ret; - if (cpufreq_driver->bios_limit) { - ret = cpufreq_driver->bios_limit(policy->cpu, &limit); - if (!ret) - return sprintf(buf, "%u\n", limit); - } - return sprintf(buf, "%u\n", policy->cpuinfo.max_freq); + ret = cpufreq_driver->bios_limit(policy->cpu, &limit); + if (!ret) + return sysfs_emit(buf, "%u\n", limit); + return sysfs_emit(buf, "%u\n", policy->cpuinfo.max_freq); } cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400); +cpufreq_freq_attr_ro(cpuinfo_avg_freq); cpufreq_freq_attr_ro(cpuinfo_min_freq); cpufreq_freq_attr_ro(cpuinfo_max_freq); cpufreq_freq_attr_ro(cpuinfo_transition_latency); @@ -885,10 +965,11 @@ cpufreq_freq_attr_rw(scaling_max_freq); cpufreq_freq_attr_rw(scaling_governor); cpufreq_freq_attr_rw(scaling_setspeed); -static struct attribute *default_attrs[] = { +static struct attribute *cpufreq_attrs[] = { &cpuinfo_min_freq.attr, &cpuinfo_max_freq.attr, &cpuinfo_transition_latency.attr, + &scaling_cur_freq.attr, &scaling_min_freq.attr, &scaling_max_freq.attr, &affected_cpus.attr, @@ -899,6 +980,7 @@ static struct attribute *default_attrs[] = { &scaling_setspeed.attr, NULL }; +ATTRIBUTE_GROUPS(cpufreq); #define to_policy(k) container_of(k, struct cpufreq_policy, kobj) #define to_attr(a) container_of(a, struct freq_attr, attr) @@ -907,13 +989,16 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) { struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); - ssize_t ret; - down_read(&policy->rwsem); - ret = fattr->show(policy, buf); - up_read(&policy->rwsem); + if (!fattr->show) + return -EIO; - return ret; + guard(cpufreq_policy_read)(policy); + + if (likely(!policy_is_inactive(policy))) + return fattr->show(policy, buf); + + return -EBUSY; } static ssize_t store(struct kobject *kobj, struct attribute *attr, @@ -921,24 +1006,16 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, { struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); - ssize_t ret = -EINVAL; - /* - * cpus_read_trylock() is used here to work around a circular lock - * dependency problem with respect to the cpufreq_register_driver(). - */ - if (!cpus_read_trylock()) - return -EBUSY; + if (!fattr->store) + return -EIO; - if (cpu_online(policy->cpu)) { - down_write(&policy->rwsem); - ret = fattr->store(policy, buf, count); - up_write(&policy->rwsem); - } + guard(cpufreq_policy_write)(policy); - cpus_read_unlock(); + if (likely(!policy_is_inactive(policy))) + return fattr->store(policy, buf, count); - return ret; + return -EBUSY; } static void cpufreq_sysfs_release(struct kobject *kobj) @@ -953,17 +1030,16 @@ static const struct sysfs_ops sysfs_ops = { .store = store, }; -static struct kobj_type ktype_cpufreq = { +static const struct kobj_type ktype_cpufreq = { .sysfs_ops = &sysfs_ops, - .default_attrs = default_attrs, + .default_groups = cpufreq_groups, .release = cpufreq_sysfs_release, }; -static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu) +static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu, + struct device *dev) { - struct device *dev = get_cpu_device(cpu); - - if (!dev) + if (unlikely(!dev)) return; if (cpumask_test_and_set_cpu(cpu, policy->real_cpus)) @@ -974,11 +1050,12 @@ static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu) dev_err(dev, "cpufreq symlink creation failed\n"); } -static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, +static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu, struct device *dev) { dev_dbg(dev, "%s: Removing symlink\n", __func__); sysfs_remove_link(&dev->kobj, "cpufreq"); + cpumask_clear_cpu(cpu, policy->real_cpus); } static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) @@ -986,6 +1063,21 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) struct freq_attr **drv_attr; int ret = 0; + /* Attributes that need freq_table */ + if (policy->freq_table) { + ret = sysfs_create_file(&policy->kobj, + &cpufreq_freq_attr_scaling_available_freqs.attr); + if (ret) + return ret; + + if (cpufreq_boost_supported()) { + ret = sysfs_create_file(&policy->kobj, + &cpufreq_freq_attr_scaling_boost_freqs.attr); + if (ret) + return ret; + } + } + /* set up files for this cpu device */ drv_attr = cpufreq_driver->attr; while (drv_attr && *drv_attr) { @@ -1000,9 +1092,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) return ret; } - ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); - if (ret) - return ret; + if (cpufreq_avg_freq_supported(policy)) { + ret = sysfs_create_file(&policy->kobj, &cpuinfo_avg_freq.attr); + if (ret) + return ret; + } if (cpufreq_driver->bios_limit) { ret = sysfs_create_file(&policy->kobj, &bios_limit.attr); @@ -1010,43 +1104,62 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) return ret; } - return 0; -} + if (cpufreq_boost_supported()) { + ret = sysfs_create_file(&policy->kobj, &local_boost.attr); + if (ret) + return ret; + } -__weak struct cpufreq_governor *cpufreq_default_governor(void) -{ - return NULL; + return 0; } static int cpufreq_init_policy(struct cpufreq_policy *policy) { struct cpufreq_governor *gov = NULL; - struct cpufreq_policy new_policy; + unsigned int pol = CPUFREQ_POLICY_UNKNOWN; + int ret; - memcpy(&new_policy, policy, sizeof(*policy)); + if (has_target()) { + /* Update policy governor to the one used before hotplug. */ + if (policy->last_governor[0] != '\0') + gov = get_governor(policy->last_governor); + if (gov) { + pr_debug("Restoring governor %s for cpu %d\n", + gov->name, policy->cpu); + } else { + gov = get_governor(default_governor); + } + + if (!gov) { + gov = cpufreq_default_governor(); + __module_get(gov->owner); + } - /* Update governor of new_policy to the governor used before hotplug */ - gov = find_governor(policy->last_governor); - if (gov) { - pr_debug("Restoring governor %s for cpu %d\n", - policy->governor->name, policy->cpu); } else { - gov = cpufreq_default_governor(); - if (!gov) + + /* Use the default policy if there is no last_policy. */ + if (policy->last_policy) { + pol = policy->last_policy; + } else { + pol = cpufreq_parse_policy(default_governor); + /* + * In case the default governor is neither "performance" + * nor "powersave", fall back to the initial policy + * value set by the driver. + */ + if (pol == CPUFREQ_POLICY_UNKNOWN) + pol = policy->policy; + } + if (pol != CPUFREQ_POLICY_PERFORMANCE && + pol != CPUFREQ_POLICY_POWERSAVE) return -ENODATA; } - new_policy.governor = gov; + ret = cpufreq_set_policy(policy, gov, pol); + if (gov) + module_put(gov->owner); - /* Use the default policy if there is no last_policy. */ - if (cpufreq_driver->setpolicy) { - if (policy->last_policy) - new_policy.policy = policy->last_policy; - else - cpufreq_parse_governor(gov->name, &new_policy); - } - /* set default policy */ - return cpufreq_set_policy(policy, &new_policy); + return ret; } static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu) @@ -1057,7 +1170,8 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp if (cpumask_test_cpu(cpu, policy->cpus)) return 0; - down_write(&policy->rwsem); + guard(cpufreq_policy_write)(policy); + if (has_target()) cpufreq_stop_governor(policy); @@ -1068,24 +1182,81 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp if (ret) pr_err("%s: Failed to start governor\n", __func__); } - up_write(&policy->rwsem); + return ret; } +void refresh_frequency_limits(struct cpufreq_policy *policy) +{ + if (!policy_is_inactive(policy)) { + pr_debug("updating policy for CPU %u\n", policy->cpu); + + cpufreq_set_policy(policy, policy->governor, policy->policy); + } +} +EXPORT_SYMBOL(refresh_frequency_limits); + static void handle_update(struct work_struct *work) { struct cpufreq_policy *policy = container_of(work, struct cpufreq_policy, update); - unsigned int cpu = policy->cpu; - pr_debug("handle_update for cpu %u called\n", cpu); - cpufreq_update_policy(cpu); + + pr_debug("handle_update for cpu %u called\n", policy->cpu); + + guard(cpufreq_policy_write)(policy); + + refresh_frequency_limits(policy); +} + +static int cpufreq_notifier_min(struct notifier_block *nb, unsigned long freq, + void *data) +{ + struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_min); + + schedule_work(&policy->update); + return 0; +} + +static int cpufreq_notifier_max(struct notifier_block *nb, unsigned long freq, + void *data) +{ + struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_max); + + schedule_work(&policy->update); + return 0; +} + +static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) +{ + struct kobject *kobj; + struct completion *cmp; + + scoped_guard(cpufreq_policy_write, policy) { + cpufreq_stats_free_table(policy); + kobj = &policy->kobj; + cmp = &policy->kobj_unregister; + } + kobject_put(kobj); + + /* + * We need to make sure that the underlying kobj is + * actually not referenced anymore by anybody before we + * proceed with unloading. + */ + pr_debug("waiting for dropping of refcount\n"); + wait_for_completion(cmp); + pr_debug("wait complete\n"); } static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) { struct cpufreq_policy *policy; + struct device *dev = get_cpu_device(cpu); int ret; + if (!dev) + return NULL; + policy = kzalloc(sizeof(*policy), GFP_KERNEL); if (!policy) return NULL; @@ -1099,23 +1270,55 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) goto err_free_rcpumask; + init_completion(&policy->kobj_unregister); ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, cpufreq_global_kobject, "policy%u", cpu); if (ret) { - pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret); + dev_err(dev, "%s: failed to init policy->kobj: %d\n", __func__, ret); + /* + * The entire policy object will be freed below, but the extra + * memory allocated for the kobject name needs to be freed by + * releasing the kobject. + */ + kobject_put(&policy->kobj); goto err_free_real_cpus; } - INIT_LIST_HEAD(&policy->policy_list); init_rwsem(&policy->rwsem); + + freq_constraints_init(&policy->constraints); + + policy->nb_min.notifier_call = cpufreq_notifier_min; + policy->nb_max.notifier_call = cpufreq_notifier_max; + + ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); + if (ret) { + dev_err(dev, "Failed to register MIN QoS notifier: %d (CPU%u)\n", + ret, cpu); + goto err_kobj_remove; + } + + ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MAX, + &policy->nb_max); + if (ret) { + dev_err(dev, "Failed to register MAX QoS notifier: %d (CPU%u)\n", + ret, cpu); + goto err_min_qos_notifier; + } + + INIT_LIST_HEAD(&policy->policy_list); spin_lock_init(&policy->transition_lock); init_waitqueue_head(&policy->transition_wait); - init_completion(&policy->kobj_unregister); INIT_WORK(&policy->update, handle_update); - policy->cpu = cpu; return policy; +err_min_qos_notifier: + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); +err_kobj_remove: + cpufreq_policy_put_kobj(policy); err_free_real_cpus: free_cpumask_var(policy->real_cpus); err_free_rcpumask: @@ -1128,33 +1331,18 @@ err_free_policy: return NULL; } -static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) -{ - struct kobject *kobj; - struct completion *cmp; - - down_write(&policy->rwsem); - cpufreq_stats_free_table(policy); - kobj = &policy->kobj; - cmp = &policy->kobj_unregister; - up_write(&policy->rwsem); - kobject_put(kobj); - - /* - * We need to make sure that the underlying kobj is - * actually not referenced anymore by anybody before we - * proceed with unloading. - */ - pr_debug("waiting for dropping of refcount\n"); - wait_for_completion(cmp); - pr_debug("wait complete\n"); -} - static void cpufreq_policy_free(struct cpufreq_policy *policy) { unsigned long flags; int cpu; + /* + * The callers must ensure the policy is inactive by now, to avoid any + * races with show()/store() callbacks. + */ + if (unlikely(!policy_is_inactive(policy))) + pr_warn("%s: Freeing active policy\n", __func__); + /* Remove policy from list */ write_lock_irqsave(&cpufreq_driver_lock, flags); list_del(&policy->policy_list); @@ -1163,6 +1351,28 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) per_cpu(cpufreq_cpu_data, cpu) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MAX, + &policy->nb_max); + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); + + /* Cancel any pending policy->update work before freeing the policy. */ + cancel_work_sync(&policy->update); + + if (policy->max_freq_req) { + /* + * Remove max_freq_req after sending CPUFREQ_REMOVE_POLICY + * notification, since CPUFREQ_CREATE_POLICY notification was + * sent after adding max_freq_req earlier. + */ + blocking_notifier_call_chain(&cpufreq_policy_notifier_list, + CPUFREQ_REMOVE_POLICY, policy); + freq_qos_remove_request(policy->max_freq_req); + } + + freq_qos_remove_request(policy->min_freq_req); + kfree(policy->min_freq_req); + cpufreq_policy_put_kobj(policy); free_cpumask_var(policy->real_cpus); free_cpumask_var(policy->related_cpus); @@ -1170,54 +1380,54 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) kfree(policy); } -static int cpufreq_online(unsigned int cpu) +static int cpufreq_policy_online(struct cpufreq_policy *policy, + unsigned int cpu, bool new_policy) { - struct cpufreq_policy *policy; - bool new_policy; unsigned long flags; unsigned int j; int ret; - pr_debug("%s: bringing CPU%u online\n", __func__, cpu); + guard(cpufreq_policy_write)(policy); - /* Check if this CPU already has a policy to manage it */ - policy = per_cpu(cpufreq_cpu_data, cpu); - if (policy) { - WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus)); - if (!policy_is_inactive(policy)) - return cpufreq_add_policy_cpu(policy, cpu); - - /* This is the only online CPU for the policy. Start over. */ - new_policy = false; - down_write(&policy->rwsem); - policy->cpu = cpu; - policy->governor = NULL; - up_write(&policy->rwsem); - } else { - new_policy = true; - policy = cpufreq_policy_alloc(cpu); - if (!policy) - return -ENOMEM; - } + policy->cpu = cpu; + policy->governor = NULL; - cpumask_copy(policy->cpus, cpumask_of(cpu)); + if (!new_policy && cpufreq_driver->online) { + /* Recover policy->cpus using related_cpus */ + cpumask_copy(policy->cpus, policy->related_cpus); - /* call driver. From then on the cpufreq must be able - * to accept all calls to ->verify and ->setpolicy for this CPU - */ - ret = cpufreq_driver->init(policy); - if (ret) { - pr_debug("initialization failed\n"); - goto out_free_policy; - } + ret = cpufreq_driver->online(policy); + if (ret) { + pr_debug("%s: %d: initialization failed\n", __func__, + __LINE__); + goto out_exit_policy; + } + } else { + cpumask_copy(policy->cpus, cpumask_of(cpu)); - ret = cpufreq_table_validate_and_sort(policy); - if (ret) - goto out_exit_policy; + /* + * Call driver. From then on the cpufreq must be able + * to accept all calls to ->verify and ->setpolicy for this CPU. + */ + ret = cpufreq_driver->init(policy); + if (ret) { + pr_debug("%s: %d: initialization failed\n", __func__, + __LINE__); + goto out_clear_policy; + } - down_write(&policy->rwsem); + /* + * The initialization has succeeded and the policy is online. + * If there is a problem with its frequency table, take it + * offline and drop it. + */ + if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING && + policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) { + ret = cpufreq_table_validate_and_sort(policy); + if (ret) + goto out_offline_policy; + } - if (new_policy) { /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); } @@ -1229,21 +1439,58 @@ static int cpufreq_online(unsigned int cpu) cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); if (new_policy) { - policy->user_policy.min = policy->min; - policy->user_policy.max = policy->max; - for_each_cpu(j, policy->related_cpus) { per_cpu(cpufreq_cpu_data, j) = policy; - add_cpu_dev_symlink(policy, j); + add_cpu_dev_symlink(policy, j, get_cpu_device(j)); + } + + policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req), + GFP_KERNEL); + if (!policy->min_freq_req) { + ret = -ENOMEM; + goto out_destroy_policy; } + + ret = freq_qos_add_request(&policy->constraints, + policy->min_freq_req, FREQ_QOS_MIN, + FREQ_QOS_MIN_DEFAULT_VALUE); + if (ret < 0) { + /* + * So we don't call freq_qos_remove_request() for an + * uninitialized request. + */ + kfree(policy->min_freq_req); + policy->min_freq_req = NULL; + goto out_destroy_policy; + } + + /* + * This must be initialized right here to avoid calling + * freq_qos_remove_request() on uninitialized request in case + * of errors. + */ + policy->max_freq_req = policy->min_freq_req + 1; + + ret = freq_qos_add_request(&policy->constraints, + policy->max_freq_req, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + if (ret < 0) { + policy->max_freq_req = NULL; + goto out_destroy_policy; + } + + blocking_notifier_call_chain(&cpufreq_policy_notifier_list, + CPUFREQ_CREATE_POLICY, policy); } else { - policy->min = policy->user_policy.min; - policy->max = policy->user_policy.max; + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + goto out_destroy_policy; } - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { + if (cpufreq_driver->get && has_target()) { policy->cur = cpufreq_driver->get(policy->cpu); if (!policy->cur) { + ret = -EIO; pr_err("%s: ->get() failed\n", __func__); goto out_destroy_policy; } @@ -1269,14 +1516,13 @@ static int cpufreq_online(unsigned int cpu) */ if ((cpufreq_driver->flags & CPUFREQ_NEED_INITIAL_FREQ_CHECK) && has_target()) { + unsigned int old_freq = policy->cur; + /* Are we running at unknown frequency ? */ - ret = cpufreq_frequency_table_get_index(policy, policy->cur); + ret = cpufreq_frequency_table_get_index(policy, old_freq); if (ret == -EINVAL) { - /* Warn user and fix it */ - pr_warn("%s: CPU%d: Running at unlisted freq: %u KHz\n", - __func__, policy->cpu, policy->cur); - ret = __cpufreq_driver_target(policy, policy->cur - 1, - CPUFREQ_RELATION_L); + ret = __cpufreq_driver_target(policy, old_freq - 1, + CPUFREQ_RELATION_L); /* * Reaching here after boot in a few seconds may not @@ -1284,8 +1530,8 @@ static int cpufreq_online(unsigned int cpu) * frequency for longer duration. Hence, a BUG_ON(). */ BUG_ON(ret); - pr_warn("%s: CPU%d: Unlisted initial frequency changed to: %u KHz\n", - __func__, policy->cpu, policy->cur); + pr_info("%s: CPU%d: Running at unlisted initial frequency: %u kHz, changing to: %u kHz\n", + __func__, policy->cpu, old_freq, policy->cur); } } @@ -1299,44 +1545,108 @@ static int cpufreq_online(unsigned int cpu) write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + /* + * Register with the energy model before + * em_rebuild_sched_domains() is called, which will result + * in rebuilding of the sched domains, which should only be done + * once the energy model is properly initialized for the policy + * first. + * + * Also, this should be called before the policy is registered + * with cooling framework. + */ + if (cpufreq_driver->register_em) + cpufreq_driver->register_em(policy); } ret = cpufreq_init_policy(policy); if (ret) { pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n", __func__, cpu, ret); - /* cpufreq_policy_free() will notify based on this */ - new_policy = false; goto out_destroy_policy; } - up_write(&policy->rwsem); - - kobject_uevent(&policy->kobj, KOBJ_ADD); - - /* Callback for handling stuff after policy is ready */ - if (cpufreq_driver->ready) - cpufreq_driver->ready(policy); - - pr_debug("initialization complete\n"); - return 0; out_destroy_policy: for_each_cpu(j, policy->real_cpus) - remove_cpu_dev_symlink(policy, get_cpu_device(j)); + remove_cpu_dev_symlink(policy, j, get_cpu_device(j)); - up_write(&policy->rwsem); +out_offline_policy: + if (cpufreq_driver->offline) + cpufreq_driver->offline(policy); out_exit_policy: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); -out_free_policy: - cpufreq_policy_free(policy); +out_clear_policy: + cpumask_clear(policy->cpus); + return ret; } +static int cpufreq_online(unsigned int cpu) +{ + struct cpufreq_policy *policy; + bool new_policy; + int ret; + + pr_debug("%s: bringing CPU%u online\n", __func__, cpu); + + /* Check if this CPU already has a policy to manage it */ + policy = per_cpu(cpufreq_cpu_data, cpu); + if (policy) { + WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus)); + if (!policy_is_inactive(policy)) + return cpufreq_add_policy_cpu(policy, cpu); + + /* This is the only online CPU for the policy. Start over. */ + new_policy = false; + } else { + new_policy = true; + policy = cpufreq_policy_alloc(cpu); + if (!policy) + return -ENOMEM; + } + + ret = cpufreq_policy_online(policy, cpu, new_policy); + if (ret) { + cpufreq_policy_free(policy); + return ret; + } + + kobject_uevent(&policy->kobj, KOBJ_ADD); + + /* Callback for handling stuff after policy is ready */ + if (cpufreq_driver->ready) + cpufreq_driver->ready(policy); + + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) + policy->cdev = of_cpufreq_cooling_register(policy); + + /* + * Let the per-policy boost flag mirror the cpufreq_driver boost during + * initialization for a new policy. For an existing policy, maintain the + * previous boost value unless global boost is disabled. + */ + if (cpufreq_driver->set_boost && policy->boost_supported && + (new_policy || !cpufreq_boost_enabled())) { + ret = policy_set_boost(policy, cpufreq_boost_enabled()); + if (ret) { + /* If the set_boost fails, the online operation is not affected */ + pr_info("%s: CPU%d: Cannot %s BOOST\n", __func__, policy->cpu, + str_enable_disable(cpufreq_boost_enabled())); + } + } + + pr_debug("initialization complete\n"); + + return 0; +} + /** * cpufreq_add_dev - the cpufreq interface for a CPU device. * @dev: CPU device. @@ -1359,74 +1669,78 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) /* Create sysfs link on CPU registration */ policy = per_cpu(cpufreq_cpu_data, cpu); if (policy) - add_cpu_dev_symlink(policy, cpu); + add_cpu_dev_symlink(policy, cpu, dev); return 0; } -static int cpufreq_offline(unsigned int cpu) +static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) { - struct cpufreq_policy *policy; int ret; - pr_debug("%s: unregistering CPU %u\n", __func__, cpu); - - policy = cpufreq_cpu_get_raw(cpu); - if (!policy) { - pr_debug("%s: No cpu_data found\n", __func__); - return 0; - } - - down_write(&policy->rwsem); if (has_target()) cpufreq_stop_governor(policy); cpumask_clear_cpu(cpu, policy->cpus); - if (policy_is_inactive(policy)) { - if (has_target()) - strncpy(policy->last_governor, policy->governor->name, - CPUFREQ_NAME_LEN); - else - policy->last_policy = policy->policy; - } else if (cpu == policy->cpu) { - /* Nominate new CPU */ - policy->cpu = cpumask_any(policy->cpus); - } - - /* Start governor again for active policy */ if (!policy_is_inactive(policy)) { + /* Nominate a new CPU if necessary. */ + if (cpu == policy->cpu) + policy->cpu = cpumask_any(policy->cpus); + + /* Start the governor again for the active policy. */ if (has_target()) { ret = cpufreq_start_governor(policy); if (ret) pr_err("%s: Failed to start governor\n", __func__); } - goto unlock; + return; } - if (cpufreq_driver->stop_cpu) - cpufreq_driver->stop_cpu(policy); - - if (has_target()) + if (has_target()) { + strscpy(policy->last_governor, policy->governor->name, + CPUFREQ_NAME_LEN); cpufreq_exit_governor(policy); + } else { + policy->last_policy = policy->policy; + } /* - * Perform the ->exit() even during light-weight tear-down, - * since this is a core component, and is essential for the - * subsequent light-weight ->init() to succeed. + * Perform the ->offline() during light-weight tear-down, as + * that allows fast recovery when the CPU comes back. */ - if (cpufreq_driver->exit) { + if (cpufreq_driver->offline) { + cpufreq_driver->offline(policy); + return; + } + + if (cpufreq_driver->exit) cpufreq_driver->exit(policy); - policy->freq_table = NULL; + + policy->freq_table = NULL; +} + +static int cpufreq_offline(unsigned int cpu) +{ + struct cpufreq_policy *policy; + + pr_debug("%s: unregistering CPU %u\n", __func__, cpu); + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) { + pr_debug("%s: No cpu_data found\n", __func__); + return 0; } -unlock: - up_write(&policy->rwsem); + guard(cpufreq_policy_write)(policy); + + __cpufreq_offline(cpu, policy); + return 0; } -/** +/* * cpufreq_remove_dev - remove a CPU device * * Removes the cpufreq interface for a CPU device. @@ -1439,24 +1753,39 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) if (!policy) return; - if (cpu_online(cpu)) - cpufreq_offline(cpu); + scoped_guard(cpufreq_policy_write, policy) { + if (cpu_online(cpu)) + __cpufreq_offline(cpu, policy); - cpumask_clear_cpu(cpu, policy->real_cpus); - remove_cpu_dev_symlink(policy, dev); + remove_cpu_dev_symlink(policy, cpu, dev); - if (cpumask_empty(policy->real_cpus)) - cpufreq_policy_free(policy); + if (!cpumask_empty(policy->real_cpus)) + return; + + /* + * Unregister cpufreq cooling once all the CPUs of the policy + * are removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + + /* We did light-weight exit earlier, do full tear down now */ + if (cpufreq_driver->offline && cpufreq_driver->exit) + cpufreq_driver->exit(policy); + } + + cpufreq_policy_free(policy); } /** - * cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're - * in deep trouble. - * @policy: policy managing CPUs - * @new_freq: CPU frequency the CPU actually runs at + * cpufreq_out_of_sync - Fix up actual and saved CPU frequency difference. + * @policy: Policy managing CPUs. + * @new_freq: New CPU frequency. * - * We adjust to current frequency first, and need to clean up later. - * So either call to cpufreq_update_policy() or schedule handle_update()). + * Adjust to the current frequency first and clean up later by either calling + * cpufreq_update_policy(), or scheduling handle_update(). */ static void cpufreq_out_of_sync(struct cpufreq_policy *policy, unsigned int new_freq) @@ -1473,6 +1802,43 @@ static void cpufreq_out_of_sync(struct cpufreq_policy *policy, cpufreq_freq_transition_end(policy, &freqs, 0); } +static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, bool update) +{ + unsigned int new_freq; + + if (!cpufreq_driver->get) + return 0; + + new_freq = cpufreq_driver->get(policy->cpu); + if (!new_freq) + return 0; + + /* + * If fast frequency switching is used with the given policy, the check + * against policy->cur is pointless, so skip it in that case. + */ + if (policy->fast_switch_enabled || !has_target()) + return new_freq; + + if (policy->cur != new_freq) { + /* + * For some platforms, the frequency returned by hardware may be + * slightly different from what is provided in the frequency + * table, for example hardware may return 499 MHz instead of 500 + * MHz. In such cases it is better to avoid getting into + * unnecessary frequency updates. + */ + if (abs(policy->cur - new_freq) < KHZ_PER_MHZ) + return policy->cur; + + cpufreq_out_of_sync(policy, new_freq); + if (update) + schedule_work(&policy->update); + } + + return new_freq; +} + /** * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur * @cpu: CPU number @@ -1482,27 +1848,25 @@ static void cpufreq_out_of_sync(struct cpufreq_policy *policy, */ unsigned int cpufreq_quick_get(unsigned int cpu) { - struct cpufreq_policy *policy; - unsigned int ret_freq = 0; unsigned long flags; read_lock_irqsave(&cpufreq_driver_lock, flags); if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) { - ret_freq = cpufreq_driver->get(cpu); + unsigned int ret_freq = cpufreq_driver->get(cpu); + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + return ret_freq; } read_unlock_irqrestore(&cpufreq_driver_lock, flags); - policy = cpufreq_cpu_get(cpu); - if (policy) { - ret_freq = policy->cur; - cpufreq_cpu_put(policy); - } + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (policy) + return policy->cur; - return ret_freq; + return 0; } EXPORT_SYMBOL(cpufreq_quick_get); @@ -1514,45 +1878,36 @@ EXPORT_SYMBOL(cpufreq_quick_get); */ unsigned int cpufreq_quick_get_max(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret_freq = 0; - - if (policy) { - ret_freq = policy->max; - cpufreq_cpu_put(policy); - } + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (policy) + return policy->max; - return ret_freq; + return 0; } EXPORT_SYMBOL(cpufreq_quick_get_max); -static unsigned int __cpufreq_get(struct cpufreq_policy *policy) +/** + * cpufreq_get_hw_max_freq - get the max hardware frequency of the CPU + * @cpu: CPU number + * + * The default return value is the max_freq field of cpuinfo. + */ +__weak unsigned int cpufreq_get_hw_max_freq(unsigned int cpu) { - unsigned int ret_freq = 0; - - if (unlikely(policy_is_inactive(policy)) || !cpufreq_driver->get) - return ret_freq; - - ret_freq = cpufreq_driver->get(policy->cpu); + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (policy) + return policy->cpuinfo.max_freq; - /* - * If fast frequency switching is used with the given policy, the check - * against policy->cur is pointless, so skip it in that case too. - */ - if (policy->fast_switch_enabled) - return ret_freq; + return 0; +} +EXPORT_SYMBOL(cpufreq_get_hw_max_freq); - if (ret_freq && policy->cur && - !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - /* verify no discrepancy between actual and - saved value exists */ - if (unlikely(ret_freq != policy->cur)) { - cpufreq_out_of_sync(policy, ret_freq); - schedule_work(&policy->update); - } - } +static unsigned int __cpufreq_get(struct cpufreq_policy *policy) +{ + if (unlikely(policy_is_inactive(policy))) + return 0; - return ret_freq; + return cpufreq_verify_current_freq(policy, true); } /** @@ -1563,38 +1918,15 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy) */ unsigned int cpufreq_get(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret_freq = 0; - - if (policy) { - down_read(&policy->rwsem); - ret_freq = __cpufreq_get(policy); - up_read(&policy->rwsem); - - cpufreq_cpu_put(policy); - } - - return ret_freq; -} -EXPORT_SYMBOL(cpufreq_get); - -static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy) -{ - unsigned int new_freq; - - new_freq = cpufreq_driver->get(policy->cpu); - if (!new_freq) + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (!policy) return 0; - if (!policy->cur) { - pr_debug("cpufreq: Driver did not initialize current freq\n"); - policy->cur = new_freq; - } else if (policy->cur != new_freq && has_target()) { - cpufreq_out_of_sync(policy, new_freq); - } + guard(cpufreq_policy_read)(policy); - return new_freq; + return __cpufreq_get(policy); } +EXPORT_SYMBOL(cpufreq_get); static struct subsys_interface cpufreq_interface = { .name = "cpufreq", @@ -1630,7 +1962,7 @@ int cpufreq_generic_suspend(struct cpufreq_policy *policy) EXPORT_SYMBOL(cpufreq_generic_suspend); /** - * cpufreq_suspend() - Suspend CPUFreq governors + * cpufreq_suspend() - Suspend CPUFreq governors. * * Called during system wide Suspend/Hibernate cycles for suspending governors * as some platforms can't change frequency after this point in suspend cycle. @@ -1651,14 +1983,14 @@ void cpufreq_suspend(void) for_each_active_policy(policy) { if (has_target()) { - down_write(&policy->rwsem); - cpufreq_stop_governor(policy); - up_write(&policy->rwsem); + scoped_guard(cpufreq_policy_write, policy) { + cpufreq_stop_governor(policy); + } } if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy)) - pr_err("%s: Failed to suspend driver: %p\n", __func__, - policy); + pr_err("%s: Failed to suspend driver: %s\n", __func__, + cpufreq_driver->name); } suspend: @@ -1666,7 +1998,7 @@ suspend: } /** - * cpufreq_resume() - Resume CPUFreq governors + * cpufreq_resume() - Resume CPUFreq governors. * * Called during system wide Suspend/Hibernate cycle for resuming governors that * are suspended with cpufreq_suspend(). @@ -1691,25 +2023,37 @@ void cpufreq_resume(void) for_each_active_policy(policy) { if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) { - pr_err("%s: Failed to resume driver: %p\n", __func__, - policy); + pr_err("%s: Failed to resume driver: %s\n", __func__, + cpufreq_driver->name); } else if (has_target()) { - down_write(&policy->rwsem); - ret = cpufreq_start_governor(policy); - up_write(&policy->rwsem); + scoped_guard(cpufreq_policy_write, policy) { + ret = cpufreq_start_governor(policy); + } if (ret) - pr_err("%s: Failed to start governor for policy: %p\n", - __func__, policy); + pr_err("%s: Failed to start governor for CPU%u's policy\n", + __func__, policy->cpu); } } } /** - * cpufreq_get_current_driver - return current driver's name + * cpufreq_driver_test_flags - Test cpufreq driver's flags against given ones. + * @flags: Flags to test against the current cpufreq driver's flags. + * + * Assumes that the driver is there, so callers must ensure that this is the + * case. + */ +bool cpufreq_driver_test_flags(u16 flags) +{ + return !!(cpufreq_driver->flags & flags); +} + +/** + * cpufreq_get_current_driver - Return the current driver's name. * - * Return the name string of the currently loaded cpufreq driver - * or NULL, if none. + * Return the name string of the currently registered cpufreq driver or NULL if + * none. */ const char *cpufreq_get_current_driver(void) { @@ -1721,10 +2065,10 @@ const char *cpufreq_get_current_driver(void) EXPORT_SYMBOL_GPL(cpufreq_get_current_driver); /** - * cpufreq_get_driver_data - return current driver data + * cpufreq_get_driver_data - Return current driver data. * - * Return the private data of the currently loaded cpufreq - * driver, or NULL if no cpufreq driver is loaded. + * Return the private data of the currently registered cpufreq driver, or NULL + * if no cpufreq driver has been registered. */ void *cpufreq_get_driver_data(void) { @@ -1740,17 +2084,16 @@ EXPORT_SYMBOL_GPL(cpufreq_get_driver_data); *********************************************************************/ /** - * cpufreq_register_notifier - register a driver with cpufreq - * @nb: notifier function to register - * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER + * cpufreq_register_notifier - Register a notifier with cpufreq. + * @nb: notifier function to register. + * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER. * - * Add a driver to one of two lists: either a list of drivers that - * are notified about clock rate changes (once before and once after - * the transition), or a list of drivers that are notified about - * changes in cpufreq policy. + * Add a notifier to one of two lists: either a list of notifiers that run on + * clock rate changes (once before and once after every transition), or a list + * of notifiers that ron on cpufreq policy changes. * - * This function may sleep, and has the same return conditions as - * blocking_notifier_chain_register. + * This function may sleep and it has the same return values as + * blocking_notifier_chain_register(). */ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list) { @@ -1787,14 +2130,14 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list) EXPORT_SYMBOL(cpufreq_register_notifier); /** - * cpufreq_unregister_notifier - unregister a driver with cpufreq - * @nb: notifier block to be unregistered - * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER + * cpufreq_unregister_notifier - Unregister a notifier from cpufreq. + * @nb: notifier block to be unregistered. + * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER. * - * Remove a driver from the CPU frequency notifier list. + * Remove a notifier from one of the cpufreq notifier lists. * - * This function may sleep, and has the same return conditions as - * blocking_notifier_chain_unregister. + * This function may sleep and it has the same return values as + * blocking_notifier_chain_unregister(). */ int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list) { @@ -1857,12 +2200,69 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier); unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { + unsigned int freq; + int cpu; + target_freq = clamp_val(target_freq, policy->min, policy->max); + freq = cpufreq_driver->fast_switch(policy, target_freq); - return cpufreq_driver->fast_switch(policy, target_freq); + if (!freq) + return 0; + + policy->cur = freq; + arch_set_freq_scale(policy->related_cpus, freq, + arch_scale_freq_ref(policy->cpu)); + cpufreq_stats_record_transition(policy, freq); + + if (trace_cpu_frequency_enabled()) { + for_each_cpu(cpu, policy->cpus) + trace_cpu_frequency(freq, cpu); + } + + return freq; } EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); +/** + * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go. + * @cpu: Target CPU. + * @min_perf: Minimum (required) performance level (units of @capacity). + * @target_perf: Target (desired) performance level (units of @capacity). + * @capacity: Capacity of the target CPU. + * + * Carry out a fast performance level switch of @cpu without sleeping. + * + * The driver's ->adjust_perf() callback invoked by this function must be + * suitable for being called from within RCU-sched read-side critical sections + * and it is expected to select a suitable performance level equal to or above + * @min_perf and preferably equal to or below @target_perf. + * + * This function must not be called if policy->fast_switch_enabled is unset. + * + * Governors calling this function must guarantee that it will never be invoked + * twice in parallel for the same CPU and that it will never be called in + * parallel with either ->target() or ->target_index() or ->fast_switch() for + * the same CPU. + */ +void cpufreq_driver_adjust_perf(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity) +{ + cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity); +} + +/** + * cpufreq_driver_has_adjust_perf - Check "direct fast switch" callback. + * + * Return 'true' if the ->adjust_perf callback is present for the + * current driver or 'false' otherwise. + */ +bool cpufreq_driver_has_adjust_perf(void) +{ + return !!cpufreq_driver->adjust_perf; +} + /* Must set freqs->new to intermediate frequency */ static int __target_intermediate(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, int index) @@ -1892,7 +2292,7 @@ static int __target_intermediate(struct cpufreq_policy *policy, static int __target_index(struct cpufreq_policy *policy, int index) { struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0}; - unsigned int intermediate_freq = 0; + unsigned int restore_freq, intermediate_freq = 0; unsigned int newfreq = policy->freq_table[index].frequency; int retval = -EINVAL; bool notify; @@ -1900,6 +2300,9 @@ static int __target_index(struct cpufreq_policy *policy, int index) if (newfreq == policy->cur) return 0; + /* Save last value to restore later on errors */ + restore_freq = policy->cur; + notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION); if (notify) { /* Handle switching to intermediate frequency */ @@ -1937,7 +2340,7 @@ static int __target_index(struct cpufreq_policy *policy, int index) */ if (unlikely(retval && intermediate_freq)) { freqs.old = intermediate_freq; - freqs.new = policy->restore_freq; + freqs.new = restore_freq; cpufreq_freq_transition_begin(policy, &freqs); cpufreq_freq_transition_end(policy, &freqs, 0); } @@ -1951,13 +2354,12 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation) { unsigned int old_target_freq = target_freq; - int index; if (cpufreq_disabled()) return -ENODEV; - /* Make sure that target_freq is within supported range */ - target_freq = clamp_val(target_freq, policy->min, policy->max); + target_freq = __resolve_freq(policy, target_freq, policy->min, + policy->max, relation); pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n", policy->cpu, target_freq, relation, old_target_freq); @@ -1968,21 +2370,25 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, * exactly same freq is called again and so we can save on few function * calls. */ - if (target_freq == policy->cur) + if (target_freq == policy->cur && + !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS)) return 0; - /* Save last value to restore later on errors */ - policy->restore_freq = policy->cur; + if (cpufreq_driver->target) { + /* + * If the driver hasn't setup a single inefficient frequency, + * it's unlikely it knows how to decode CPUFREQ_RELATION_E. + */ + if (!policy->efficiencies_available) + relation &= ~CPUFREQ_RELATION_E; - if (cpufreq_driver->target) return cpufreq_driver->target(policy, target_freq, relation); + } if (!cpufreq_driver->target_index) return -EINVAL; - index = cpufreq_frequency_table_target(policy, target_freq, relation); - - return __target_index(policy, index); + return __target_index(policy, policy->cached_resolved_idx); } EXPORT_SYMBOL_GPL(__cpufreq_driver_target); @@ -1990,15 +2396,9 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { - int ret = -EINVAL; - - down_write(&policy->rwsem); - - ret = __cpufreq_driver_target(policy, target_freq, relation); + guard(cpufreq_policy_write)(policy); - up_write(&policy->rwsem); - - return ret; + return __cpufreq_driver_target(policy, target_freq, relation); } EXPORT_SYMBOL_GPL(cpufreq_driver_target); @@ -2022,7 +2422,7 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) return -EINVAL; /* Platform doesn't want dynamic frequency switching ? */ - if (policy->governor->dynamic_switching && + if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING && cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) { struct cpufreq_governor *gov = cpufreq_fallback_governor(); @@ -2048,6 +2448,8 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) } } + policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET); + return 0; } @@ -2064,7 +2466,7 @@ static void cpufreq_exit_governor(struct cpufreq_policy *policy) module_put(policy->governor->owner); } -static int cpufreq_start_governor(struct cpufreq_policy *policy) +int cpufreq_start_governor(struct cpufreq_policy *policy) { int ret; @@ -2076,8 +2478,7 @@ static int cpufreq_start_governor(struct cpufreq_policy *policy) pr_debug("%s: for CPU %u\n", __func__, policy->cpu); - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) - cpufreq_update_current_freq(policy); + cpufreq_verify_current_freq(policy, false); if (policy->governor->start) { ret = policy->governor->start(policy); @@ -2091,7 +2492,7 @@ static int cpufreq_start_governor(struct cpufreq_policy *policy) return 0; } -static void cpufreq_stop_governor(struct cpufreq_policy *policy) +void cpufreq_stop_governor(struct cpufreq_policy *policy) { if (cpufreq_suspended || !policy->governor) return; @@ -2152,7 +2553,7 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor) for_each_inactive_policy(policy) { if (!strcmp(policy->last_governor, governor->name)) { policy->governor = NULL; - strcpy(policy->last_governor, "\0"); + policy->last_governor[0] = '\0'; } } read_unlock_irqrestore(&cpufreq_driver_lock, flags); @@ -2168,90 +2569,117 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_governor); * POLICY INTERFACE * *********************************************************************/ +DEFINE_PER_CPU(unsigned long, cpufreq_pressure); + /** - * cpufreq_get_policy - get the current cpufreq_policy - * @policy: struct cpufreq_policy into which the current cpufreq_policy - * is written + * cpufreq_update_pressure() - Update cpufreq pressure for CPUs + * @policy: cpufreq policy of the CPUs. * - * Reads the current cpufreq policy. + * Update the value of cpufreq pressure for all @cpus in the policy. */ -int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu) +static void cpufreq_update_pressure(struct cpufreq_policy *policy) { - struct cpufreq_policy *cpu_policy; - if (!policy) - return -EINVAL; + unsigned long max_capacity, capped_freq, pressure; + u32 max_freq; + int cpu; - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) - return -EINVAL; + cpu = cpumask_first(policy->related_cpus); + max_freq = arch_scale_freq_ref(cpu); + capped_freq = policy->max; - memcpy(policy, cpu_policy, sizeof(*policy)); + /* + * Handle properly the boost frequencies, which should simply clean + * the cpufreq pressure value. + */ + if (max_freq <= capped_freq) { + pressure = 0; + } else { + max_capacity = arch_scale_cpu_capacity(cpu); + pressure = max_capacity - + mult_frac(max_capacity, capped_freq, max_freq); + } - cpufreq_cpu_put(cpu_policy); - return 0; + for_each_cpu(cpu, policy->related_cpus) + WRITE_ONCE(per_cpu(cpufreq_pressure, cpu), pressure); } -EXPORT_SYMBOL(cpufreq_get_policy); -/* - * policy : current policy. - * new_policy: policy to be set. +/** + * cpufreq_set_policy - Modify cpufreq policy parameters. + * @policy: Policy object to modify. + * @new_gov: Policy governor pointer. + * @new_pol: Policy value (for drivers with built-in governors). + * + * Invoke the cpufreq driver's ->verify() callback to sanity-check the frequency + * limits to be set for the policy, update @policy with the verified limits + * values and either invoke the driver's ->setpolicy() callback (if present) or + * carry out a governor update for @policy. That is, run the current governor's + * ->limits() callback (if @new_gov points to the same object as the one in + * @policy) or replace the governor for @policy with @new_gov. + * + * The cpuinfo part of @policy is not updated by this function. */ static int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy) + struct cpufreq_governor *new_gov, + unsigned int new_pol) { + struct cpufreq_policy_data new_data; struct cpufreq_governor *old_gov; int ret; - pr_debug("setting new policy for CPU %u: %u - %u kHz\n", - new_policy->cpu, new_policy->min, new_policy->max); - - memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo)); - + memcpy(&new_data.cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo)); + new_data.freq_table = policy->freq_table; + new_data.cpu = policy->cpu; /* - * This check works well when we store new min/max freq attributes, - * because new_policy is a copy of policy with one field updated. - */ - if (new_policy->min > new_policy->max) - return -EINVAL; - - /* verify the cpu speed can be set within this limit */ - ret = cpufreq_driver->verify(new_policy); - if (ret) - return ret; + * PM QoS framework collects all the requests from users and provide us + * the final aggregated value here. + */ + new_data.min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN); + new_data.max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX); - /* adjust if necessary - all reasons */ - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_ADJUST, new_policy); + pr_debug("setting new policy for CPU %u: %u - %u kHz\n", + new_data.cpu, new_data.min, new_data.max); /* - * verify the cpu speed can be set within this limit, which might be - * different to the first one + * Verify that the CPU speed can be set within these limits and make sure + * that min <= max. */ - ret = cpufreq_driver->verify(new_policy); + ret = cpufreq_driver->verify(&new_data); if (ret) return ret; - /* notification of the new policy */ - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_NOTIFY, new_policy); + /* + * Resolve policy min/max to available frequencies. It ensures + * no frequency resolution will neither overshoot the requested maximum + * nor undershoot the requested minimum. + * + * Avoid storing intermediate values in policy->max or policy->min and + * compiler optimizations around them because they may be accessed + * concurrently by cpufreq_driver_resolve_freq() during the update. + */ + WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max, + new_data.min, new_data.max, + CPUFREQ_RELATION_H)); + new_data.min = __resolve_freq(policy, new_data.min, new_data.min, + new_data.max, CPUFREQ_RELATION_L); + WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min); - policy->min = new_policy->min; - policy->max = new_policy->max; trace_cpu_frequency_limits(policy); + cpufreq_update_pressure(policy); + policy->cached_target_freq = UINT_MAX; pr_debug("new min and max freqs are %u - %u kHz\n", policy->min, policy->max); if (cpufreq_driver->setpolicy) { - policy->policy = new_policy->policy; + policy->policy = new_pol; pr_debug("setting range\n"); - return cpufreq_driver->setpolicy(new_policy); + return cpufreq_driver->setpolicy(policy); } - if (new_policy->governor == policy->governor) { - pr_debug("cpufreq: governor limits update\n"); + if (new_gov == policy->governor) { + pr_debug("governor limits update\n"); cpufreq_governor_limits(policy); return 0; } @@ -2267,13 +2695,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, } /* start new governor */ - policy->governor = new_policy->governor; + policy->governor = new_gov; ret = cpufreq_init_governor(policy); if (!ret) { ret = cpufreq_start_governor(policy); if (!ret) { - pr_debug("cpufreq: governor change\n"); - sched_cpufreq_governor_change(policy, old_gov); + pr_debug("governor change\n"); return 0; } cpufreq_exit_governor(policy); @@ -2283,119 +2710,139 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, pr_debug("starting governor %s failed\n", policy->governor->name); if (old_gov) { policy->governor = old_gov; - if (cpufreq_init_governor(policy)) + if (cpufreq_init_governor(policy)) { policy->governor = NULL; - else - cpufreq_start_governor(policy); + } else if (cpufreq_start_governor(policy)) { + cpufreq_exit_governor(policy); + policy->governor = NULL; + } } return ret; } -/** - * cpufreq_update_policy - re-evaluate an existing cpufreq policy - * @cpu: CPU which shall be re-evaluated - * - * Useful for policy notifiers which have different necessities - * at different times. - */ -void cpufreq_update_policy(unsigned int cpu) +static void cpufreq_policy_refresh(struct cpufreq_policy *policy) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cpufreq_policy new_policy; - - if (!policy) - return; - - down_write(&policy->rwsem); - - if (policy_is_inactive(policy)) - goto unlock; - - pr_debug("updating policy for CPU %u\n", cpu); - memcpy(&new_policy, policy, sizeof(*policy)); - new_policy.min = policy->user_policy.min; - new_policy.max = policy->user_policy.max; + guard(cpufreq_policy_write)(policy); /* * BIOS might change freq behind our back * -> ask driver for current freq and notify governors about a change */ - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { - if (cpufreq_suspended) - goto unlock; - - new_policy.cur = cpufreq_update_current_freq(policy); - if (WARN_ON(!new_policy.cur)) - goto unlock; - } + if (cpufreq_driver->get && has_target() && + (cpufreq_suspended || WARN_ON(!cpufreq_verify_current_freq(policy, false)))) + return; - cpufreq_set_policy(policy, &new_policy); + refresh_frequency_limits(policy); +} -unlock: - up_write(&policy->rwsem); +/** + * cpufreq_update_policy - Re-evaluate an existing cpufreq policy. + * @cpu: CPU to re-evaluate the policy for. + * + * Update the current frequency for the cpufreq policy of @cpu and use + * cpufreq_set_policy() to re-apply the min and max limits, which triggers the + * evaluation of policy notifiers and the cpufreq driver's ->verify() callback + * for the policy in question, among other things. + */ +void cpufreq_update_policy(unsigned int cpu) +{ + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (!policy) + return; - cpufreq_cpu_put(policy); + cpufreq_policy_refresh(policy); } EXPORT_SYMBOL(cpufreq_update_policy); +/** + * cpufreq_update_limits - Update policy limits for a given CPU. + * @cpu: CPU to update the policy limits for. + * + * Invoke the driver's ->update_limits callback if present or call + * cpufreq_policy_refresh() for @cpu. + */ +void cpufreq_update_limits(unsigned int cpu) +{ + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (!policy) + return; + + if (cpufreq_driver->update_limits) + cpufreq_driver->update_limits(policy); + else + cpufreq_policy_refresh(policy); +} +EXPORT_SYMBOL_GPL(cpufreq_update_limits); + /********************************************************************* * BOOST * *********************************************************************/ -static int cpufreq_boost_set_sw(int state) +int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) { - struct cpufreq_policy *policy; - int ret = -EINVAL; - - for_each_active_policy(policy) { - if (!policy->freq_table) - continue; + int ret; - ret = cpufreq_frequency_table_cpuinfo(policy, - policy->freq_table); - if (ret) { - pr_err("%s: Policy frequency update failed\n", - __func__); - break; - } + if (!policy->freq_table) + return -ENXIO; - down_write(&policy->rwsem); - policy->user_policy.max = policy->max; - cpufreq_governor_limits(policy); - up_write(&policy->rwsem); + ret = cpufreq_frequency_table_cpuinfo(policy); + if (ret) { + pr_err("%s: Policy frequency update failed\n", __func__); + return ret; } - return ret; + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + return ret; + + return 0; } +EXPORT_SYMBOL_GPL(cpufreq_boost_set_sw); -int cpufreq_boost_trigger_state(int state) +static int cpufreq_boost_trigger_state(int state) { + struct cpufreq_policy *policy; unsigned long flags; int ret = 0; - if (cpufreq_driver->boost_enabled == state) - return 0; + /* + * Don't compare 'cpufreq_driver->boost_enabled' with 'state' here to + * make sure all policies are in sync with global boost flag. + */ write_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver->boost_enabled = state; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - ret = cpufreq_driver->set_boost(state); - if (ret) { - write_lock_irqsave(&cpufreq_driver_lock, flags); - cpufreq_driver->boost_enabled = !state; - write_unlock_irqrestore(&cpufreq_driver_lock, flags); + cpus_read_lock(); + for_each_active_policy(policy) { + if (!policy->boost_supported) + continue; - pr_err("%s: Cannot %s BOOST\n", - __func__, state ? "enable" : "disable"); + ret = policy_set_boost(policy, state); + if (ret) + goto err_reset_state; } + cpus_read_unlock(); + + return 0; + +err_reset_state: + cpus_read_unlock(); + + write_lock_irqsave(&cpufreq_driver_lock, flags); + cpufreq_driver->boost_enabled = !state; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + pr_err("%s: Cannot %s BOOST\n", + __func__, str_enable_disable(state)); return ret; } static bool cpufreq_boost_supported(void) { - return likely(cpufreq_driver) && cpufreq_driver->set_boost; + return cpufreq_driver->set_boost; } static int create_boost_sysfs_file(void) @@ -2416,22 +2863,7 @@ static void remove_boost_sysfs_file(void) sysfs_remove_file(cpufreq_global_kobject, &boost.attr); } -int cpufreq_enable_boost_support(void) -{ - if (!cpufreq_driver) - return -EINVAL; - - if (cpufreq_boost_supported()) - return 0; - - cpufreq_driver->set_boost = cpufreq_boost_set_sw; - - /* This will get removed on driver unregister */ - return create_boost_sysfs_file(); -} -EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support); - -int cpufreq_boost_enabled(void) +bool cpufreq_boost_enabled(void) { return cpufreq_driver->boost_enabled; } @@ -2474,12 +2906,19 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (cpufreq_disabled()) return -ENODEV; + /* + * The cpufreq core depends heavily on the availability of device + * structure, make sure they are available before proceeding further. + */ + if (!get_cpu_device(0)) + return -EPROBE_DEFER; + if (!driver_data || !driver_data->verify || !driver_data->init || - !(driver_data->setpolicy || driver_data->target_index || - driver_data->target) || - (driver_data->setpolicy && (driver_data->target_index || - driver_data->target)) || - (!!driver_data->get_intermediate != !!driver_data->target_intermediate)) + (driver_data->target_index && driver_data->target) || + (!!driver_data->setpolicy == (driver_data->target_index || driver_data->target)) || + (!driver_data->get_intermediate != !driver_data->target_intermediate) || + (!driver_data->online != !driver_data->offline) || + (driver_data->adjust_perf && !driver_data->fast_switch)) return -EINVAL; pr_debug("trying to register driver %s\n", driver_data->name); @@ -2505,12 +2944,20 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) goto err_null_driver; } + /* + * Mark support for the scheduler's frequency invariance engine for + * drivers that implement target(), target_index() or fast_switch(). + */ + if (!cpufreq_driver->setpolicy) { + static_branch_enable_cpuslocked(&cpufreq_freq_invariance); + pr_debug("cpufreq: supports frequency invariance\n"); + } + ret = subsys_interface_register(&cpufreq_interface); if (ret) goto err_boost_unreg; - if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && - list_empty(&cpufreq_policy_list)) { + if (unlikely(list_empty(&cpufreq_policy_list))) { /* if all ->init() calls failed, unregister */ ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, @@ -2533,6 +2980,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) err_if_unreg: subsys_interface_unregister(&cpufreq_interface); err_boost_unreg: + if (!cpufreq_driver->setpolicy) + static_branch_disable_cpuslocked(&cpufreq_freq_invariance); remove_boost_sysfs_file(); err_null_driver: write_lock_irqsave(&cpufreq_driver_lock, flags); @@ -2544,7 +2993,7 @@ out: } EXPORT_SYMBOL_GPL(cpufreq_register_driver); -/** +/* * cpufreq_unregister_driver - unregister the current CPUFreq driver * * Unregister the current CPUFreq driver. Only call this if you have @@ -2552,12 +3001,12 @@ EXPORT_SYMBOL_GPL(cpufreq_register_driver); * Returns zero if successful, and -EINVAL if the cpufreq_driver is * currently not initialised. */ -int cpufreq_unregister_driver(struct cpufreq_driver *driver) +void cpufreq_unregister_driver(struct cpufreq_driver *driver) { unsigned long flags; - if (!cpufreq_driver || (driver != cpufreq_driver)) - return -EINVAL; + if (WARN_ON(!cpufreq_driver || (driver != cpufreq_driver))) + return; pr_debug("unregistering driver %s\n", driver->name); @@ -2565,6 +3014,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) cpus_read_lock(); subsys_interface_unregister(&cpufreq_interface); remove_boost_sysfs_file(); + static_branch_disable_cpuslocked(&cpufreq_freq_invariance); cpuhp_remove_state_nocalls_cpuslocked(hp_online); write_lock_irqsave(&cpufreq_driver_lock, flags); @@ -2573,33 +3023,57 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) write_unlock_irqrestore(&cpufreq_driver_lock, flags); cpus_read_unlock(); - - return 0; } EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); -/* - * Stop cpufreq at shutdown to make sure it isn't holding any locks - * or mutexes when secondary CPUs are halted. - */ -static struct syscore_ops cpufreq_syscore_ops = { - .shutdown = cpufreq_suspend, -}; - -struct kobject *cpufreq_global_kobject; -EXPORT_SYMBOL(cpufreq_global_kobject); - static int __init cpufreq_core_init(void) { + struct cpufreq_governor *gov = cpufreq_default_governor(); + struct device *dev_root; + if (cpufreq_disabled()) return -ENODEV; - cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + cpufreq_global_kobject = kobject_create_and_add("cpufreq", &dev_root->kobj); + put_device(dev_root); + } BUG_ON(!cpufreq_global_kobject); - register_syscore_ops(&cpufreq_syscore_ops); + if (!strlen(default_governor)) + strscpy(default_governor, gov->name, CPUFREQ_NAME_LEN); return 0; } + +static bool cpufreq_policy_is_good_for_eas(unsigned int cpu) +{ + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (!policy) { + pr_debug("cpufreq policy not set for CPU: %d\n", cpu); + return false; + } + + return sugov_is_governor(policy); +} + +bool cpufreq_ready_for_eas(const struct cpumask *cpu_mask) +{ + unsigned int cpu; + + /* Do not attempt EAS if schedutil is not being used. */ + for_each_cpu(cpu, cpu_mask) { + if (!cpufreq_policy_is_good_for_eas(cpu)) { + pr_debug("rd %*pbl: schedutil is mandatory for EAS\n", + cpumask_pr_args(cpu_mask)); + return false; + } + } + + return true; +} + module_param(off, int, 0444); +module_param_string(default_governor, default_governor, CPUFREQ_NAME_LEN, 0444); core_initcall(cpufreq_core_init); |