diff options
Diffstat (limited to 'drivers/cpufreq/cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 974 |
1 files changed, 577 insertions, 397 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 45f3416988f1..4472bb1ec83c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -25,9 +25,11 @@ #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); @@ -72,6 +74,11 @@ 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); @@ -80,6 +87,8 @@ 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 @@ -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) @@ -246,51 +257,6 @@ void cpufreq_cpu_put(struct cpufreq_policy *policy) } EXPORT_SYMBOL_GPL(cpufreq_cpu_put); -/** - * cpufreq_cpu_release - Unlock a policy and decrement its usage counter. - * @policy: cpufreq policy returned by cpufreq_cpu_acquire(). - */ -void cpufreq_cpu_release(struct cpufreq_policy *policy) -{ - if (WARN_ON(!policy)) - return; - - lockdep_assert_held(&policy->rwsem); - - up_write(&policy->rwsem); - - cpufreq_cpu_put(policy); -} - -/** - * cpufreq_cpu_acquire - Find policy for a CPU, mark it as busy and lock it. - * @cpu: CPU to find the policy for. - * - * Call cpufreq_cpu_get() to get a reference on the cpufreq policy for @cpu and - * if the policy returned by it is not NULL, acquire its rwsem for writing. - * Return the policy if it is active or release it and return NULL otherwise. - * - * The policy returned by this function has to be released with the help of - * cpufreq_cpu_release() in order to release its rwsem and balance its usage - * counter properly. - */ -struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu) -{ - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - - if (!policy) - return NULL; - - down_write(&policy->rwsem); - - if (policy_is_inactive(policy)) { - cpufreq_cpu_release(policy); - return NULL; - } - - return policy; -} - /********************************************************************* * EXTERNALLY AFFECTING FREQUENCY CHANGES * *********************************************************************/ @@ -447,10 +413,12 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy, arch_set_freq_scale(policy->related_cpus, policy->cur, - policy->cpuinfo.max_freq); + 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); } @@ -525,16 +493,18 @@ 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 relation) + unsigned int target_freq, + unsigned int min, unsigned int max, + unsigned int relation) { unsigned int idx; - target_freq = clamp_val(target_freq, policy->min, policy->max); + target_freq = clamp_val(target_freq, min, max); - if (!cpufreq_driver->target_index) + if (!policy->freq_table) return target_freq; - idx = cpufreq_frequency_table_target(policy, target_freq, relation); + 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; @@ -554,7 +524,21 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq) { - return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_L); + unsigned int min = READ_ONCE(policy->min); + unsigned int max = READ_ONCE(policy->max); + + /* + * 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 __resolve_freq(policy, target_freq, min, max, CPUFREQ_RELATION_LE); } EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq); @@ -566,21 +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); @@ -590,31 +564,75 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); static ssize_t show_boost(struct kobject *kobj, 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 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; @@ -646,10 +664,10 @@ unlock: static unsigned int cpufreq_parse_policy(char *str_governor) { - if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) + if (!strncasecmp(str_governor, "performance", strlen("performance"))) return CPUFREQ_POLICY_PERFORMANCE; - if (!strncasecmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) + if (!strncasecmp(str_governor, "powersave", strlen("powersave"))) return CPUFREQ_POLICY_POWERSAVE; return CPUFREQ_POLICY_UNKNOWN; @@ -685,7 +703,7 @@ static struct cpufreq_governor *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); @@ -694,23 +712,31 @@ 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 = arch_freq_get_on_cpu(policy->cpu); - if (freq) - ret = sprintf(buf, "%u\n", freq); + freq = IS_ENABLED(CONFIG_CPUFREQ_ARCH_CUR_FREQ) + ? arch_freq_get_on_cpu(policy->cpu) + : 0; + + if (freq > 0) + ret = sysfs_emit(buf, "%u\n", freq); else if (cpufreq_driver->setpolicy && cpufreq_driver->get) - ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + 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; } @@ -724,9 +750,9 @@ static ssize_t store_##file_name \ unsigned long val; \ int ret; \ \ - ret = sscanf(buf, "%lu", &val); \ - if (ret != 1) \ - return -EINVAL; \ + ret = kstrtoul(buf, 0, &val); \ + if (ret) \ + return ret; \ \ ret = freq_qos_update_request(policy->object##_freq_req, val);\ return ret >= 0 ? count : ret; \ @@ -744,9 +770,22 @@ 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 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); - return sprintf(buf, "<unknown>\n"); + if (avg_freq > 0) + return sysfs_emit(buf, "%u\n", avg_freq); + return avg_freq != 0 ? avg_freq : -EINVAL; } /* @@ -755,12 +794,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, 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; } @@ -770,7 +808,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf) static ssize_t store_scaling_governor(struct cpufreq_policy *policy, const char *buf, size_t count) { - char str_governor[16]; + char str_governor[CPUFREQ_NAME_LEN]; int ret; ret = sscanf(buf, "%15s", str_governor); @@ -819,7 +857,7 @@ 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; } @@ -828,11 +866,11 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char)) - (CPUFREQ_NAME_LEN + 2))) break; - i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name); + 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; } @@ -842,13 +880,15 @@ 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); @@ -874,14 +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); @@ -891,7 +931,7 @@ 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); } @@ -905,11 +945,12 @@ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf) int ret; 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); + 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); @@ -924,10 +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, @@ -938,6 +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) @@ -946,16 +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; if (!fattr->show) return -EIO; - down_read(&policy->rwsem); - ret = fattr->show(policy, buf); - up_read(&policy->rwsem); + guard(cpufreq_policy_read)(policy); - return ret; + if (likely(!policy_is_inactive(policy))) + return fattr->show(policy, buf); + + return -EBUSY; } static ssize_t store(struct kobject *kobj, struct attribute *attr, @@ -963,27 +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; if (!fattr->store) return -EIO; - /* - * 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; + guard(cpufreq_policy_write)(policy); - if (cpu_online(policy->cpu)) { - down_write(&policy->rwsem); - ret = fattr->store(policy, buf, count); - up_write(&policy->rwsem); - } + if (likely(!policy_is_inactive(policy))) + return fattr->store(policy, buf, count); - cpus_read_unlock(); - - return ret; + return -EBUSY; } static void cpufreq_sysfs_release(struct kobject *kobj) @@ -998,16 +1030,15 @@ 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 (unlikely(!dev)) return; @@ -1019,11 +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) @@ -1031,6 +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) { @@ -1045,9 +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); @@ -1055,6 +1104,12 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) return ret; } + if (cpufreq_boost_supported()) { + ret = sysfs_create_file(&policy->kobj, &local_boost.attr); + if (ret) + return ret; + } + return 0; } @@ -1066,7 +1121,8 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) if (has_target()) { /* Update policy governor to the one used before hotplug. */ - gov = get_governor(policy->last_governor); + 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); @@ -1114,7 +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); @@ -1125,7 +1182,7 @@ 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; } @@ -1145,9 +1202,10 @@ static void handle_update(struct work_struct *work) container_of(work, struct cpufreq_policy, update); pr_debug("handle_update for cpu %u called\n", policy->cpu); - down_write(&policy->rwsem); + + guard(cpufreq_policy_write)(policy); + refresh_frequency_limits(policy); - up_write(&policy->rwsem); } static int cpufreq_notifier_min(struct notifier_block *nb, unsigned long freq, @@ -1173,11 +1231,11 @@ 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); + scoped_guard(cpufreq_policy_write, policy) { + cpufreq_stats_free_table(policy); + kobj = &policy->kobj; + cmp = &policy->kobj_unregister; + } kobject_put(kobj); /* @@ -1212,6 +1270,7 @@ 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) { @@ -1225,6 +1284,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) goto err_free_real_cpus; } + init_rwsem(&policy->rwsem); + freq_constraints_init(&policy->constraints); policy->nb_min.notifier_call = cpufreq_notifier_min; @@ -1233,27 +1294,24 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) 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 (%*pbl)\n", - ret, cpumask_pr_args(policy->cpus)); + 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 (%*pbl)\n", - ret, cpumask_pr_args(policy->cpus)); + 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); - init_rwsem(&policy->rwsem); 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: @@ -1278,6 +1336,13 @@ 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); @@ -1296,8 +1361,9 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) if (policy->max_freq_req) { /* - * CPUFREQ_CREATE_POLICY notification is sent only after - * successfully adding max_freq_req request. + * 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); @@ -1314,46 +1380,28 @@ 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); - - /* 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); + guard(cpufreq_policy_write)(policy); - /* 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; if (!new_policy && cpufreq_driver->online) { + /* Recover policy->cpus using related_cpus */ + cpumask_copy(policy->cpus, policy->related_cpus); + ret = cpufreq_driver->online(policy); if (ret) { pr_debug("%s: %d: initialization failed\n", __func__, __LINE__); goto out_exit_policy; } - - /* Recover policy->cpus using related_cpus */ - cpumask_copy(policy->cpus, policy->related_cpus); } else { cpumask_copy(policy->cpus, cpumask_of(cpu)); @@ -1365,7 +1413,7 @@ static int cpufreq_online(unsigned int cpu) if (ret) { pr_debug("%s: %d: initialization failed\n", __func__, __LINE__); - goto out_free_policy; + goto out_clear_policy; } /* @@ -1373,15 +1421,17 @@ static int cpufreq_online(unsigned int cpu) * If there is a problem with its frequency table, take it * offline and drop it. */ - ret = cpufreq_table_validate_and_sort(policy); - if (ret) - goto out_offline_policy; + 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; + } /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); } - down_write(&policy->rwsem); /* * affected cpus must always be the one, which are online. We aren't * managing offline cpus here. @@ -1391,7 +1441,7 @@ static int cpufreq_online(unsigned int cpu) if (new_policy) { 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), @@ -1403,7 +1453,7 @@ static int cpufreq_online(unsigned int cpu) ret = freq_qos_add_request(&policy->constraints, policy->min_freq_req, FREQ_QOS_MIN, - policy->min); + FREQ_QOS_MIN_DEFAULT_VALUE); if (ret < 0) { /* * So we don't call freq_qos_remove_request() for an @@ -1423,7 +1473,7 @@ static int cpufreq_online(unsigned int cpu) ret = freq_qos_add_request(&policy->constraints, policy->max_freq_req, FREQ_QOS_MAX, - policy->max); + FREQ_QOS_MAX_DEFAULT_VALUE); if (ret < 0) { policy->max_freq_req = NULL; goto out_destroy_policy; @@ -1431,6 +1481,10 @@ static int cpufreq_online(unsigned int cpu) blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_CREATE_POLICY, policy); + } else { + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + goto out_destroy_policy; } if (cpufreq_driver->get && has_target()) { @@ -1476,7 +1530,7 @@ static int cpufreq_online(unsigned int cpu) * frequency for longer duration. Hence, a BUG_ON(). */ BUG_ON(ret); - pr_info("%s: CPU%d: Running at unlisted initial frequency: %u KHz, changing to: %u KHz\n", + pr_info("%s: CPU%d: Running at unlisted initial frequency: %u kHz, changing to: %u kHz\n", __func__, policy->cpu, old_freq, policy->cur); } } @@ -1491,6 +1545,19 @@ 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); @@ -1500,26 +1567,11 @@ static int cpufreq_online(unsigned int cpu) 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); - - if (cpufreq_thermal_control_enabled(cpufreq_driver)) - policy->cdev = of_cpufreq_cooling_register(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)); - - up_write(&policy->rwsem); + remove_cpu_dev_symlink(policy, j, get_cpu_device(j)); out_offline_policy: if (cpufreq_driver->offline) @@ -1529,11 +1581,72 @@ 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. @@ -1556,59 +1669,42 @@ 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; - } - - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; + return; } - 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 ->offline() during light-weight tear-down, as @@ -1616,13 +1712,31 @@ static int cpufreq_offline(unsigned int cpu) */ if (cpufreq_driver->offline) { cpufreq_driver->offline(policy); - } else if (cpufreq_driver->exit) { + 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; } @@ -1639,19 +1753,30 @@ 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)) + 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; + } - if (cpumask_empty(policy->real_cpus)) { /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) + if (cpufreq_driver->offline && cpufreq_driver->exit) cpufreq_driver->exit(policy); - - cpufreq_policy_free(policy); } + + cpufreq_policy_free(policy); } /** @@ -1681,6 +1806,9 @@ static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, b { unsigned int new_freq; + if (!cpufreq_driver->get) + return 0; + new_freq = cpufreq_driver->get(policy->cpu); if (!new_freq) return 0; @@ -1693,6 +1821,16 @@ static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, b 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); @@ -1710,27 +1848,25 @@ static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, b */ 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); @@ -1742,15 +1878,11 @@ 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); @@ -1762,15 +1894,11 @@ EXPORT_SYMBOL(cpufreq_quick_get_max); */ __weak unsigned int cpufreq_get_hw_max_freq(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret_freq = 0; - - if (policy) { - ret_freq = policy->cpuinfo.max_freq; - cpufreq_cpu_put(policy); - } + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (policy) + return policy->cpuinfo.max_freq; - return ret_freq; + return 0; } EXPORT_SYMBOL(cpufreq_get_hw_max_freq); @@ -1790,19 +1918,13 @@ 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; + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); + if (!policy) + return 0; - if (policy) { - down_read(&policy->rwsem); - if (cpufreq_driver->get) - ret_freq = __cpufreq_get(policy); - up_read(&policy->rwsem); + guard(cpufreq_policy_read)(policy); - cpufreq_cpu_put(policy); - } - - return ret_freq; + return __cpufreq_get(policy); } EXPORT_SYMBOL(cpufreq_get); @@ -1861,9 +1983,9 @@ 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)) @@ -1901,16 +2023,16 @@ 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); } } } @@ -2089,7 +2211,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, policy->cur = freq; arch_set_freq_scale(policy->related_cpus, freq, - policy->cpuinfo.max_freq); + arch_scale_freq_ref(policy->cpu)); cpufreq_stats_record_transition(policy, freq); if (trace_cpu_frequency_enabled()) { @@ -2236,7 +2358,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, if (cpufreq_disabled()) return -ENODEV; - target_freq = __resolve_freq(policy, target_freq, relation); + 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); @@ -2251,8 +2374,16 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS)) return 0; - if (cpufreq_driver->target) + 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; + return cpufreq_driver->target(policy, target_freq, relation); + } if (!cpufreq_driver->target_index) return -EINVAL; @@ -2265,15 +2396,9 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { - int ret; - - 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); @@ -2353,8 +2478,7 @@ int cpufreq_start_governor(struct cpufreq_policy *policy) pr_debug("%s: for CPU %u\n", __func__, policy->cpu); - if (cpufreq_driver->get) - cpufreq_verify_current_freq(policy, false); + cpufreq_verify_current_freq(policy, false); if (policy->governor->start) { ret = policy->governor->start(policy); @@ -2429,7 +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); @@ -2445,30 +2569,39 @@ 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 - * @cpu: CPU to find the policy for + * 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); /** * cpufreq_set_policy - Modify cpufreq policy parameters. @@ -2514,10 +2647,26 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, if (ret) return ret; - policy->min = new_data.min; - policy->max = new_data.max; + /* + * 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); + 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", @@ -2552,7 +2701,6 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, ret = cpufreq_start_governor(policy); if (!ret) { pr_debug("governor change\n"); - sched_cpufreq_governor_change(policy, old_gov); return 0; } cpufreq_exit_governor(policy); @@ -2562,15 +2710,32 @@ 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 if (cpufreq_start_governor(policy)) { + cpufreq_exit_governor(policy); policy->governor = NULL; - else - cpufreq_start_governor(policy); + } } return ret; } +static void cpufreq_policy_refresh(struct cpufreq_policy *policy) +{ + 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 && has_target() && + (cpufreq_suspended || WARN_ON(!cpufreq_verify_current_freq(policy, false)))) + return; + + refresh_frequency_limits(policy); +} + /** * cpufreq_update_policy - Re-evaluate an existing cpufreq policy. * @cpu: CPU to re-evaluate the policy for. @@ -2582,23 +2747,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, */ void cpufreq_update_policy(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); - + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); if (!policy) return; - /* - * BIOS might change freq behind our back - * -> ask driver for current freq and notify governors about a change - */ - if (cpufreq_driver->get && has_target() && - (cpufreq_suspended || WARN_ON(!cpufreq_verify_current_freq(policy, false)))) - goto unlock; - - refresh_frequency_limits(policy); - -unlock: - cpufreq_cpu_release(policy); + cpufreq_policy_refresh(policy); } EXPORT_SYMBOL(cpufreq_update_policy); @@ -2607,28 +2760,32 @@ EXPORT_SYMBOL(cpufreq_update_policy); * @cpu: CPU to update the policy limits for. * * Invoke the driver's ->update_limits callback if present or call - * cpufreq_update_policy() for @cpu. + * 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(cpu); + cpufreq_driver->update_limits(policy); else - cpufreq_update_policy(cpu); + cpufreq_policy_refresh(policy); } EXPORT_SYMBOL_GPL(cpufreq_update_limits); /********************************************************************* * BOOST * *********************************************************************/ -static int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) +int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) { int ret; if (!policy->freq_table) return -ENXIO; - ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table); + ret = cpufreq_frequency_table_cpuinfo(policy); if (ret) { pr_err("%s: Policy frequency update failed\n", __func__); return ret; @@ -2640,39 +2797,45 @@ static int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) 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); - get_online_cpus(); + cpus_read_lock(); for_each_active_policy(policy) { - ret = cpufreq_driver->set_boost(policy, state); + if (!policy->boost_supported) + continue; + + ret = policy_set_boost(policy, state); if (ret) goto err_reset_state; } - put_online_cpus(); + cpus_read_unlock(); return 0; err_reset_state: - put_online_cpus(); + 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__, state ? "enable" : "disable"); + __func__, str_enable_disable(state)); return ret; } @@ -2700,22 +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; } @@ -2766,12 +2914,11 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) 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->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->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); @@ -2788,15 +2935,6 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) cpufreq_driver = driver_data; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - /* - * 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("supports frequency invariance"); - } - if (driver_data->setpolicy) driver_data->flags |= CPUFREQ_CONST_LOOPS; @@ -2806,6 +2944,15 @@ 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; @@ -2833,6 +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); @@ -2852,12 +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); @@ -2874,26 +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); 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); if (!strlen(default_governor)) - strncpy(default_governor, gov->name, CPUFREQ_NAME_LEN); + 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); |