--- zzzz-none-000/linux-3.10.107/drivers/cpufreq/cpufreq.c 2017-06-27 09:49:32.000000000 +0000 +++ vr9-7490-729/linux-3.10.107/drivers/cpufreq/cpufreq.c 2021-11-10 11:53:55.000000000 +0000 @@ -3,6 +3,7 @@ * * Copyright (C) 2001 Russell King * (C) 2002 - 2003 Dominik Brodowski + * (C) 2013 Viresh Kumar * * Oct 2005 - Ashok Raj * Added handling for CPU hotplug @@ -12,26 +13,21 @@ * 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 -#include -#include -#include +#include #include #include -#include -#include #include -#include -#include -#include +#include +#include +#include #include +#include #include - +#include #include /** @@ -41,56 +37,26 @@ */ static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); +static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback); +static DEFINE_RWLOCK(cpufreq_driver_lock); +DEFINE_MUTEX(cpufreq_governor_lock); +static LIST_HEAD(cpufreq_policy_list); + #ifdef CONFIG_HOTPLUG_CPU /* This one keeps track of the previously set governor of a removed CPU */ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); #endif -static DEFINE_RWLOCK(cpufreq_driver_lock); -static DEFINE_MUTEX(cpufreq_governor_lock); - -/* - * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure - * all cpufreq/hotplug/workqueue/etc related lock issues. - * - * The rules for this semaphore: - * - Any routine that wants to read from the policy structure will - * do a down_read on this semaphore. - * - Any routine that will write to the policy structure and/or may take away - * the policy altogether (eg. CPU hotplug), will hold this lock in write - * mode before doing so. - * - * Additional rules: - * - Governor routines that can be called in cpufreq hotplug path should not - * take this sem as top level hotplug notifier handler takes this. - * - Lock should not be held across - * __cpufreq_governor(data, CPUFREQ_GOV_STOP); - */ -static DEFINE_PER_CPU(int, cpufreq_policy_cpu); -static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem); - -#define lock_policy_rwsem(mode, cpu) \ -static int lock_policy_rwsem_##mode(int cpu) \ -{ \ - int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); \ - BUG_ON(policy_cpu == -1); \ - down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \ - \ - return 0; \ -} -lock_policy_rwsem(read, cpu); -lock_policy_rwsem(write, cpu); - -#define unlock_policy_rwsem(mode, cpu) \ -static void unlock_policy_rwsem_##mode(int cpu) \ -{ \ - int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); \ - BUG_ON(policy_cpu == -1); \ - up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \ +static inline bool has_target(void) +{ + return cpufreq_driver->target_index || cpufreq_driver->target; } -unlock_policy_rwsem(read, cpu); -unlock_policy_rwsem(write, cpu); +/* + * rwsem to guarantee that cpufreq driver module doesn't unload during critical + * sections + */ +static DECLARE_RWSEM(cpufreq_rwsem); /* internal prototypes */ static int __cpufreq_governor(struct cpufreq_policy *policy, @@ -131,82 +97,139 @@ bool have_governor_per_policy(void) { - return cpufreq_driver->have_governor_per_policy; + return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY); } +EXPORT_SYMBOL_GPL(have_governor_per_policy); -static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs) +struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy) { - struct cpufreq_policy *data; - unsigned long flags; - - if (cpu >= nr_cpu_ids) - goto err_out; - - /* get the cpufreq driver */ - read_lock_irqsave(&cpufreq_driver_lock, flags); + if (have_governor_per_policy()) + return &policy->kobj; + else + return cpufreq_global_kobject; +} +EXPORT_SYMBOL_GPL(get_governor_parent_kobj); - if (!cpufreq_driver) - goto err_out_unlock; +static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) +{ + u64 idle_time; + u64 cur_wall_time; + u64 busy_time; - if (!try_module_get(cpufreq_driver->owner)) - goto err_out_unlock; + cur_wall_time = jiffies64_to_cputime64(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]; - /* get the CPU */ - data = per_cpu(cpufreq_cpu_data, cpu); + idle_time = cur_wall_time - busy_time; + if (wall) + *wall = cputime_to_usecs(cur_wall_time); - if (!data) - goto err_out_put_module; + return cputime_to_usecs(idle_time); +} - if (!sysfs && !kobject_get(&data->kobj)) - goto err_out_put_module; +u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy) +{ + u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); - return data; + if (idle_time == -1ULL) + return get_cpu_idle_time_jiffy(cpu, wall); + else if (!io_busy) + idle_time += get_cpu_iowait_time_us(cpu, wall); -err_out_put_module: - module_put(cpufreq_driver->owner); -err_out_unlock: - read_unlock_irqrestore(&cpufreq_driver_lock, flags); -err_out: - return NULL; + return idle_time; } +EXPORT_SYMBOL_GPL(get_cpu_idle_time); -struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) +/* + * This is a generic cpufreq init() routine which can be used by cpufreq + * drivers of SMP systems. It will do following: + * - validate & show freq table passed + * - set policies transition latency + * - policy->cpus with all possible CPUs + */ +int cpufreq_generic_init(struct cpufreq_policy *policy, + struct cpufreq_frequency_table *table, + unsigned int transition_latency) { - if (cpufreq_disabled()) - return NULL; + int ret; - return __cpufreq_cpu_get(cpu, false); + ret = cpufreq_table_validate_and_show(policy, table); + if (ret) { + pr_err("%s: invalid frequency table: %d\n", __func__, ret); + return ret; + } + + policy->cpuinfo.transition_latency = transition_latency; + + /* + * The driver only supports the SMP configuartion where all processors + * share the clock and voltage and clock. + */ + cpumask_setall(policy->cpus); + + return 0; } -EXPORT_SYMBOL_GPL(cpufreq_cpu_get); +EXPORT_SYMBOL_GPL(cpufreq_generic_init); -static struct cpufreq_policy *cpufreq_cpu_get_sysfs(unsigned int cpu) +unsigned int cpufreq_generic_get(unsigned int cpu) { - return __cpufreq_cpu_get(cpu, true); + struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); + + if (!policy || IS_ERR(policy->clk)) { + pr_err("%s: No %s associated to cpu: %d\n", __func__, + policy ? "clk" : "policy", cpu); + return 0; + } + + return clk_get_rate(policy->clk) / 1000; } +EXPORT_SYMBOL_GPL(cpufreq_generic_get); -static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs) +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { - if (!sysfs) - kobject_put(&data->kobj); - module_put(cpufreq_driver->owner); + struct cpufreq_policy *policy = NULL; + unsigned long flags; + + if (cpufreq_disabled() || (cpu >= nr_cpu_ids)) + return NULL; + + if (!down_read_trylock(&cpufreq_rwsem)) + return NULL; + + /* get the cpufreq driver */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + + if (cpufreq_driver) { + /* get the CPU */ + policy = per_cpu(cpufreq_cpu_data, cpu); + if (policy) + kobject_get(&policy->kobj); + } + + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + + if (!policy) + up_read(&cpufreq_rwsem); + + return policy; } +EXPORT_SYMBOL_GPL(cpufreq_cpu_get); -void cpufreq_cpu_put(struct cpufreq_policy *data) +void cpufreq_cpu_put(struct cpufreq_policy *policy) { if (cpufreq_disabled()) return; - __cpufreq_cpu_put(data, false); + kobject_put(&policy->kobj); + up_read(&cpufreq_rwsem); } EXPORT_SYMBOL_GPL(cpufreq_cpu_put); -static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data) -{ - __cpufreq_cpu_put(data, true); -} - /********************************************************************* * EXTERNALLY AFFECTING FREQUENCY CHANGES * *********************************************************************/ @@ -221,7 +244,7 @@ */ #ifndef CONFIG_SMP static unsigned long l_p_j_ref; -static unsigned int l_p_j_ref_freq; +static unsigned int l_p_j_ref_freq; static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) { @@ -234,7 +257,7 @@ pr_debug("saving %lu as reference value for loops_per_jiffy; " "freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); } - if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) || + if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) || (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, ci->new); @@ -249,8 +272,7 @@ } #endif - -void __cpufreq_notify_transition(struct cpufreq_policy *policy, +static void __cpufreq_notify_transition(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, unsigned int state) { BUG_ON(irqs_disabled()); @@ -293,8 +315,15 @@ if (likely(policy) && likely(policy->cpu == freqs->cpu)) policy->cur = freqs->new; break; + + case CPUFREQ_NOCHANGE: + srcu_notifier_call_chain( + &cpufreq_transition_notifier_list, + CPUFREQ_NOCHANGE, freqs); + break; } } + /** * cpufreq_notify_transition - call notifier chain and adjust_jiffies * on frequency transition. @@ -311,11 +340,51 @@ } EXPORT_SYMBOL_GPL(cpufreq_notify_transition); +/* Do post notifications when there are chances that transition has failed */ +void cpufreq_notify_post_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, int transition_failed) +{ + cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE); + if (!transition_failed) + return; + + swap(freqs->old, freqs->new); + cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE); + cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE); +} +EXPORT_SYMBOL_GPL(cpufreq_notify_post_transition); /********************************************************************* * SYSFS INTERFACE * *********************************************************************/ +ssize_t show_boost(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); +} + +static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + int ret, enable; + + ret = sscanf(buf, "%d", &enable); + if (ret != 1 || enable < 0 || enable > 1) + return -EINVAL; + + if (cpufreq_boost_trigger_state(enable)) { + pr_err("%s: Cannot %s BOOST!\n", __func__, + enable ? "enable" : "disable"); + return -EINVAL; + } + + pr_debug("%s: cpufreq BOOST %s\n", __func__, + enable ? "enabled" : "disabled"); + + return count; +} +define_one_global_rw(boost); static struct cpufreq_governor *__find_governor(const char *str_governor) { @@ -348,7 +417,7 @@ *policy = CPUFREQ_POLICY_POWERSAVE; err = 0; } - } else if (cpufreq_driver->target) { + } else if (has_target()) { struct cpufreq_governor *t; mutex_lock(&cpufreq_governor_mutex); @@ -377,7 +446,6 @@ return err; } - /** * cpufreq_per_cpu_attr_read() / show_##file_name() - * print out cpufreq information @@ -400,8 +468,8 @@ show_one(scaling_max_freq, max); show_one(scaling_cur_freq, cur); -static int __cpufreq_set_policy(struct cpufreq_policy *data, - struct cpufreq_policy *policy); +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 @@ -410,7 +478,7 @@ static ssize_t store_##file_name \ (struct cpufreq_policy *policy, const char *buf, size_t count) \ { \ - unsigned int ret; \ + int ret; \ struct cpufreq_policy new_policy; \ \ ret = cpufreq_get_policy(&new_policy, policy->cpu); \ @@ -421,7 +489,7 @@ if (ret != 1) \ return -EINVAL; \ \ - ret = __cpufreq_set_policy(policy, &new_policy); \ + ret = cpufreq_set_policy(policy, &new_policy); \ policy->user_policy.object = policy->object; \ \ return ret ? ret : count; \ @@ -444,7 +512,6 @@ return sprintf(buf, "\n"); } - /** * show_scaling_governor - show the current policy for the specified CPU */ @@ -460,14 +527,13 @@ 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) { - unsigned int ret; + int ret; char str_governor[16]; struct cpufreq_policy new_policy; @@ -483,9 +549,7 @@ &new_policy.governor)) return -EINVAL; - /* Do not use cpufreq_set_policy here or the user_policy.max - will be wrongly overridden */ - ret = __cpufreq_set_policy(policy, &new_policy); + ret = cpufreq_set_policy(policy, &new_policy); policy->user_policy.policy = policy->policy; policy->user_policy.governor = policy->governor; @@ -513,7 +577,7 @@ ssize_t i = 0; struct cpufreq_governor *t; - if (!cpufreq_driver->target) { + if (!has_target()) { i += sprintf(buf, "performance powersave"); goto out; } @@ -529,7 +593,7 @@ return i; } -static ssize_t show_cpus(const struct cpumask *mask, char *buf) +ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf) { ssize_t i = 0; unsigned int cpu; @@ -544,6 +608,7 @@ i += sprintf(&buf[i], "\n"); return i; } +EXPORT_SYMBOL_GPL(cpufreq_show_cpus); /** * show_related_cpus - show the CPUs affected by each transition even if @@ -551,7 +616,7 @@ */ static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf) { - return show_cpus(policy->related_cpus, buf); + return cpufreq_show_cpus(policy->related_cpus, buf); } /** @@ -559,7 +624,7 @@ */ static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf) { - return show_cpus(policy->cpus, buf); + return cpufreq_show_cpus(policy->cpus, buf); } static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy, @@ -633,9 +698,6 @@ NULL }; -struct kobject *cpufreq_global_kobject; -EXPORT_SYMBOL(cpufreq_global_kobject); - #define to_policy(k) container_of(k, struct cpufreq_policy, kobj) #define to_attr(a) container_of(a, struct freq_attr, attr) @@ -643,23 +705,21 @@ { struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); - ssize_t ret = -EINVAL; - policy = cpufreq_cpu_get_sysfs(policy->cpu); - if (!policy) - goto no_policy; + ssize_t ret; + + if (!down_read_trylock(&cpufreq_rwsem)) + return -EINVAL; - if (lock_policy_rwsem_read(policy->cpu) < 0) - goto fail; + down_read(&policy->rwsem); if (fattr->show) ret = fattr->show(policy, buf); else ret = -EIO; - unlock_policy_rwsem_read(policy->cpu); -fail: - cpufreq_cpu_put_sysfs(policy); -no_policy: + up_read(&policy->rwsem); + up_read(&cpufreq_rwsem); + return ret; } @@ -669,22 +729,28 @@ struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; - policy = cpufreq_cpu_get_sysfs(policy->cpu); - if (!policy) - goto no_policy; - if (lock_policy_rwsem_write(policy->cpu) < 0) - goto fail; + get_online_cpus(); + + if (!cpu_online(policy->cpu)) + goto unlock; + + if (!down_read_trylock(&cpufreq_rwsem)) + goto unlock; + + down_write(&policy->rwsem); if (fattr->store) ret = fattr->store(policy, buf, count); else ret = -EIO; - unlock_policy_rwsem_write(policy->cpu); -fail: - cpufreq_cpu_put_sysfs(policy); -no_policy: + up_write(&policy->rwsem); + + up_read(&cpufreq_rwsem); +unlock: + put_online_cpus(); + return ret; } @@ -706,42 +772,76 @@ .release = cpufreq_sysfs_release, }; +struct kobject *cpufreq_global_kobject; +EXPORT_SYMBOL(cpufreq_global_kobject); + +static int cpufreq_global_kobject_usage; + +int cpufreq_get_global_kobject(void) +{ + if (!cpufreq_global_kobject_usage++) + return kobject_add(cpufreq_global_kobject, + &cpu_subsys.dev_root->kobj, "%s", "cpufreq"); + + return 0; +} +EXPORT_SYMBOL(cpufreq_get_global_kobject); + +void cpufreq_put_global_kobject(void) +{ + if (!--cpufreq_global_kobject_usage) + kobject_del(cpufreq_global_kobject); +} +EXPORT_SYMBOL(cpufreq_put_global_kobject); + +int cpufreq_sysfs_create_file(const struct attribute *attr) +{ + int ret = cpufreq_get_global_kobject(); + + if (!ret) { + ret = sysfs_create_file(cpufreq_global_kobject, attr); + if (ret) + cpufreq_put_global_kobject(); + } + + return ret; +} +EXPORT_SYMBOL(cpufreq_sysfs_create_file); + +void cpufreq_sysfs_remove_file(const struct attribute *attr) +{ + sysfs_remove_file(cpufreq_global_kobject, attr); + cpufreq_put_global_kobject(); +} +EXPORT_SYMBOL(cpufreq_sysfs_remove_file); + /* symlink affected CPUs */ -static int cpufreq_add_dev_symlink(unsigned int cpu, - struct cpufreq_policy *policy) +static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy) { unsigned int j; int ret = 0; for_each_cpu(j, policy->cpus) { - struct cpufreq_policy *managed_policy; struct device *cpu_dev; - if (j == cpu) + if (j == policy->cpu) continue; - pr_debug("CPU %u already managed, adding link\n", j); - managed_policy = cpufreq_cpu_get(cpu); + pr_debug("Adding link for CPU: %u\n", j); cpu_dev = get_cpu_device(j); ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq"); - if (ret) { - cpufreq_cpu_put(managed_policy); - return ret; - } + if (ret) + break; } return ret; } -static int cpufreq_add_dev_interface(unsigned int cpu, - struct cpufreq_policy *policy, +static int cpufreq_add_dev_interface(struct cpufreq_policy *policy, struct device *dev) { - struct cpufreq_policy new_policy; struct freq_attr **drv_attr; - unsigned long flags; int ret = 0; - unsigned int j; /* prepare interface data */ ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, @@ -762,7 +862,7 @@ if (ret) goto err_out_kobj_put; } - if (cpufreq_driver->target) { + if (has_target()) { ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); if (ret) goto err_out_kobj_put; @@ -773,97 +873,178 @@ goto err_out_kobj_put; } - write_lock_irqsave(&cpufreq_driver_lock, flags); - for_each_cpu(j, policy->cpus) { - per_cpu(cpufreq_cpu_data, j) = policy; - per_cpu(cpufreq_policy_cpu, j) = policy->cpu; - } - write_unlock_irqrestore(&cpufreq_driver_lock, flags); - - ret = cpufreq_add_dev_symlink(cpu, policy); + ret = cpufreq_add_dev_symlink(policy); if (ret) goto err_out_kobj_put; - memcpy(&new_policy, policy, sizeof(struct cpufreq_policy)); - /* assure that the starting sequence is run in __cpufreq_set_policy */ + return ret; + +err_out_kobj_put: + kobject_put(&policy->kobj); + wait_for_completion(&policy->kobj_unregister); + return ret; +} + +static void cpufreq_init_policy(struct cpufreq_policy *policy) +{ + struct cpufreq_policy new_policy; + int ret = 0; + + memcpy(&new_policy, policy, sizeof(*policy)); + + /* Use the default policy if its valid. */ + if (cpufreq_driver->setpolicy) + cpufreq_parse_governor(policy->governor->name, + &new_policy.policy, NULL); + + /* assure that the starting sequence is run in cpufreq_set_policy */ policy->governor = NULL; /* set default policy */ - ret = __cpufreq_set_policy(policy, &new_policy); - policy->user_policy.policy = policy->policy; - policy->user_policy.governor = policy->governor; - + ret = cpufreq_set_policy(policy, &new_policy); if (ret) { pr_debug("setting policy failed\n"); if (cpufreq_driver->exit) cpufreq_driver->exit(policy); } - return ret; - -err_out_kobj_put: - kobject_put(&policy->kobj); - wait_for_completion(&policy->kobj_unregister); - return ret; } #ifdef CONFIG_HOTPLUG_CPU -static int cpufreq_add_policy_cpu(unsigned int cpu, unsigned int sibling, - struct device *dev) +static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, + unsigned int cpu, struct device *dev) { - struct cpufreq_policy *policy; - int ret = 0, has_target = !!cpufreq_driver->target; + int ret = 0; unsigned long flags; - policy = cpufreq_cpu_get(sibling); - WARN_ON(!policy); - - if (has_target) - __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + if (ret) { + pr_err("%s: Failed to stop governor\n", __func__); + return ret; + } + } - lock_policy_rwsem_write(sibling); + down_write(&policy->rwsem); write_lock_irqsave(&cpufreq_driver_lock, flags); cpumask_set_cpu(cpu, policy->cpus); - per_cpu(cpufreq_policy_cpu, cpu) = policy->cpu; per_cpu(cpufreq_cpu_data, cpu) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - unlock_policy_rwsem_write(sibling); - - if (has_target) { - __cpufreq_governor(policy, CPUFREQ_GOV_START); - __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); - } + up_write(&policy->rwsem); - ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); - if (ret) { - cpufreq_cpu_put(policy); - return ret; + if (has_target()) { + if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) || + (ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) { + pr_err("%s: Failed to start governor\n", __func__); + return ret; + } } - return 0; + return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); } #endif -/** - * cpufreq_add_dev - add a CPU device - * - * Adds the cpufreq interface for a CPU device. - * - * The Oracle says: try running cpufreq registration/unregistration concurrently - * with with cpu hotplugging and all hell will break loose. Tried to clean this - * mess up, but more thorough testing is needed. - Mathieu - */ -static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) +static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu) +{ + struct cpufreq_policy *policy; + unsigned long flags; + + read_lock_irqsave(&cpufreq_driver_lock, flags); + + policy = per_cpu(cpufreq_cpu_data_fallback, cpu); + + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + + return policy; +} + +static struct cpufreq_policy *cpufreq_policy_alloc(void) +{ + struct cpufreq_policy *policy; + + policy = kzalloc(sizeof(*policy), GFP_KERNEL); + if (!policy) + return NULL; + + if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL)) + goto err_free_policy; + + if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) + goto err_free_cpumask; + + INIT_LIST_HEAD(&policy->policy_list); + init_rwsem(&policy->rwsem); + + return policy; + +err_free_cpumask: + free_cpumask_var(policy->cpus); +err_free_policy: + kfree(policy); + + return NULL; +} + +static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) +{ + struct kobject *kobj; + struct completion *cmp; + + blocking_notifier_call_chain(&cpufreq_policy_notifier_list, + CPUFREQ_REMOVE_POLICY, policy); + + down_read(&policy->rwsem); + kobj = &policy->kobj; + cmp = &policy->kobj_unregister; + up_read(&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) +{ + free_cpumask_var(policy->related_cpus); + free_cpumask_var(policy->cpus); + kfree(policy); +} + +static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu) +{ + if (WARN_ON(cpu == policy->cpu)) + return; + + down_write(&policy->rwsem); + + policy->last_cpu = policy->cpu; + policy->cpu = cpu; + + up_write(&policy->rwsem); + + cpufreq_frequency_table_update_policy_cpu(policy); + blocking_notifier_call_chain(&cpufreq_policy_notifier_list, + CPUFREQ_UPDATE_POLICY_CPU, policy); +} + +static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, + bool frozen) { unsigned int j, cpu = dev->id; int ret = -ENOMEM; struct cpufreq_policy *policy; unsigned long flags; #ifdef CONFIG_HOTPLUG_CPU + struct cpufreq_policy *tpolicy; struct cpufreq_governor *gov; - int sibling; #endif if (cpu_is_offline(cpu)) @@ -879,43 +1060,51 @@ cpufreq_cpu_put(policy); return 0; } +#endif + + if (!down_read_trylock(&cpufreq_rwsem)) + return 0; #ifdef CONFIG_HOTPLUG_CPU /* Check if this cpu was hot-unplugged earlier and has siblings */ read_lock_irqsave(&cpufreq_driver_lock, flags); - for_each_online_cpu(sibling) { - struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling); - if (cp && cpumask_test_cpu(cpu, cp->related_cpus)) { + list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) { + if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) { read_unlock_irqrestore(&cpufreq_driver_lock, flags); - return cpufreq_add_policy_cpu(cpu, sibling, dev); + ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev); + up_read(&cpufreq_rwsem); + return ret; } } read_unlock_irqrestore(&cpufreq_driver_lock, flags); #endif -#endif - if (!try_module_get(cpufreq_driver->owner)) { - ret = -EINVAL; - goto module_out; + /* + * Restore the saved policy when doing light-weight init and fall back + * to the full init if that fails. + */ + policy = frozen ? cpufreq_policy_restore(cpu) : NULL; + if (!policy) { + frozen = false; + policy = cpufreq_policy_alloc(); + if (!policy) + goto nomem_out; } - policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL); - if (!policy) - goto nomem_out; - - if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL)) - goto err_free_policy; - - if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) - goto err_free_cpumask; + /* + * In the resume path, since we restore a saved policy, the assignment + * to policy->cpu is like an update of the existing policy, rather than + * the creation of a brand new one. So we need to perform this update + * by invoking update_policy_cpu(). + */ + if (frozen && cpu != policy->cpu) + update_policy_cpu(policy, cpu); + else + policy->cpu = cpu; - policy->cpu = cpu; policy->governor = CPUFREQ_DEFAULT_GOVERNOR; cpumask_copy(policy->cpus, cpumask_of(cpu)); - /* Initially set CPU itself as the policy_cpu */ - per_cpu(cpufreq_policy_cpu, cpu) = cpu; - init_completion(&policy->kobj_unregister); INIT_WORK(&policy->update, handle_update); @@ -937,8 +1126,64 @@ */ cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); - policy->user_policy.min = policy->min; - policy->user_policy.max = policy->max; + if (!frozen) { + policy->user_policy.min = policy->min; + policy->user_policy.max = policy->max; + } + + down_write(&policy->rwsem); + write_lock_irqsave(&cpufreq_driver_lock, flags); + for_each_cpu(j, policy->cpus) + per_cpu(cpufreq_cpu_data, j) = policy; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { + policy->cur = cpufreq_driver->get(policy->cpu); + if (!policy->cur) { + pr_err("%s: ->get() failed\n", __func__); + goto err_get_freq; + } + } + + /* + * Sometimes boot loaders set CPU frequency to a value outside of + * frequency table present with cpufreq core. In such cases CPU might be + * unstable if it has to run on that frequency for long duration of time + * and so its better to set it to a frequency which is specified in + * freq-table. This also makes cpufreq stats inconsistent as + * cpufreq-stats would fail to register because current frequency of CPU + * isn't found in freq-table. + * + * Because we don't want this change to effect boot process badly, we go + * for the next freq which is >= policy->cur ('cur' must be set by now, + * otherwise we will end up setting freq to lowest of the table as 'cur' + * is initialized to zero). + * + * We are passing target-freq as "policy->cur - 1" otherwise + * __cpufreq_driver_target() would simply fail, as policy->cur will be + * equal to target-freq. + */ + if ((cpufreq_driver->flags & CPUFREQ_NEED_INITIAL_FREQ_CHECK) + && has_target()) { + /* Are we running at unknown frequency ? */ + ret = cpufreq_frequency_table_get_index(policy, policy->cur); + 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); + + /* + * Reaching here after boot in a few seconds may not + * mean that system will remain stable at "unknown" + * 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); + } + } blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_START, policy); @@ -952,183 +1197,248 @@ } #endif - ret = cpufreq_add_dev_interface(cpu, policy, dev); - if (ret) - goto err_out_unregister; + if (!frozen) { + ret = cpufreq_add_dev_interface(policy, dev); + if (ret) + goto err_out_unregister; + blocking_notifier_call_chain(&cpufreq_policy_notifier_list, + CPUFREQ_CREATE_POLICY, policy); + } + + write_lock_irqsave(&cpufreq_driver_lock, flags); + list_add(&policy->policy_list, &cpufreq_policy_list); + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + cpufreq_init_policy(policy); + + if (!frozen) { + policy->user_policy.policy = policy->policy; + policy->user_policy.governor = policy->governor; + } + up_write(&policy->rwsem); kobject_uevent(&policy->kobj, KOBJ_ADD); - module_put(cpufreq_driver->owner); + up_read(&cpufreq_rwsem); + pr_debug("initialization complete\n"); return 0; err_out_unregister: +err_get_freq: write_lock_irqsave(&cpufreq_driver_lock, flags); for_each_cpu(j, policy->cpus) per_cpu(cpufreq_cpu_data, j) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - kobject_put(&policy->kobj); - wait_for_completion(&policy->kobj_unregister); - + if (cpufreq_driver->exit) + cpufreq_driver->exit(policy); err_set_policy_cpu: - per_cpu(cpufreq_policy_cpu, cpu) = -1; - free_cpumask_var(policy->related_cpus); -err_free_cpumask: - free_cpumask_var(policy->cpus); -err_free_policy: - kfree(policy); + if (frozen) { + /* Do not leave stale fallback data behind. */ + per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL; + cpufreq_policy_put_kobj(policy); + } + cpufreq_policy_free(policy); + nomem_out: - module_put(cpufreq_driver->owner); -module_out: + up_read(&cpufreq_rwsem); + return ret; } -static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu) +/** + * cpufreq_add_dev - add a CPU device + * + * Adds the cpufreq interface for a CPU device. + * + * The Oracle says: try running cpufreq registration/unregistration concurrently + * with with cpu hotplugging and all hell will break loose. Tried to clean this + * mess up, but more thorough testing is needed. - Mathieu + */ +static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) { - int j; + return __cpufreq_add_dev(dev, sif, false); +} - policy->last_cpu = policy->cpu; - policy->cpu = cpu; +static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, + unsigned int old_cpu) +{ + struct device *cpu_dev; + int ret; - for_each_cpu(j, policy->cpus) - per_cpu(cpufreq_policy_cpu, j) = cpu; + /* first sibling now owns the new sysfs dir */ + cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu)); -#ifdef CONFIG_CPU_FREQ_TABLE - cpufreq_frequency_table_update_policy_cpu(policy); -#endif - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_UPDATE_POLICY_CPU, policy); + sysfs_remove_link(&cpu_dev->kobj, "cpufreq"); + ret = kobject_move(&policy->kobj, &cpu_dev->kobj); + if (ret) { + pr_err("%s: Failed to move kobj: %d", __func__, ret); + + down_write(&policy->rwsem); + cpumask_set_cpu(old_cpu, policy->cpus); + up_write(&policy->rwsem); + + ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj, + "cpufreq"); + + return -EINVAL; + } + + return cpu_dev->id; } -/** - * __cpufreq_remove_dev - remove a CPU device - * - * Removes the cpufreq interface for a CPU device. - * Caller should already have policy_rwsem in write mode for this CPU. - * This routine frees the rwsem before returning. - */ -static int __cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) +static int __cpufreq_remove_dev_prepare(struct device *dev, + struct subsys_interface *sif, + bool frozen) { - unsigned int cpu = dev->id, ret, cpus; + unsigned int cpu = dev->id, cpus; + int new_cpu, ret; unsigned long flags; - struct cpufreq_policy *data; - struct kobject *kobj; - struct completion *cmp; - struct device *cpu_dev; + struct cpufreq_policy *policy; pr_debug("%s: unregistering CPU %u\n", __func__, cpu); write_lock_irqsave(&cpufreq_driver_lock, flags); - data = per_cpu(cpufreq_cpu_data, cpu); - per_cpu(cpufreq_cpu_data, cpu) = NULL; + policy = per_cpu(cpufreq_cpu_data, cpu); + + /* Save the policy somewhere when doing a light-weight tear-down */ + if (frozen) + per_cpu(cpufreq_cpu_data_fallback, cpu) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - if (!data) { + if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); return -EINVAL; } - if (cpufreq_driver->target) - __cpufreq_governor(data, CPUFREQ_GOV_STOP); + if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + if (ret) { + pr_err("%s: Failed to stop governor\n", __func__); + return ret; + } + } #ifdef CONFIG_HOTPLUG_CPU if (!cpufreq_driver->setpolicy) strncpy(per_cpu(cpufreq_cpu_governor, cpu), - data->governor->name, CPUFREQ_NAME_LEN); + policy->governor->name, CPUFREQ_NAME_LEN); #endif - WARN_ON(lock_policy_rwsem_write(cpu)); - cpus = cpumask_weight(data->cpus); + down_read(&policy->rwsem); + cpus = cpumask_weight(policy->cpus); + up_read(&policy->rwsem); - if (cpus > 1) - cpumask_clear_cpu(cpu, data->cpus); - unlock_policy_rwsem_write(cpu); - - if (cpu != data->cpu) { + if (cpu != policy->cpu) { sysfs_remove_link(&dev->kobj, "cpufreq"); } else if (cpus > 1) { - /* first sibling now owns the new sysfs dir */ - cpu_dev = get_cpu_device(cpumask_first(data->cpus)); - sysfs_remove_link(&cpu_dev->kobj, "cpufreq"); - ret = kobject_move(&data->kobj, &cpu_dev->kobj); - if (ret) { - pr_err("%s: Failed to move kobj: %d", __func__, ret); - - WARN_ON(lock_policy_rwsem_write(cpu)); - cpumask_set_cpu(cpu, data->cpus); + new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu); + if (new_cpu >= 0) { + update_policy_cpu(policy, new_cpu); + + if (!frozen) { + pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n", + __func__, new_cpu, cpu); + } + } + } - write_lock_irqsave(&cpufreq_driver_lock, flags); - per_cpu(cpufreq_cpu_data, cpu) = data; - write_unlock_irqrestore(&cpufreq_driver_lock, flags); + return 0; +} - unlock_policy_rwsem_write(cpu); +static int __cpufreq_remove_dev_finish(struct device *dev, + struct subsys_interface *sif, + bool frozen) +{ + unsigned int cpu = dev->id, cpus; + int ret; + unsigned long flags; + struct cpufreq_policy *policy; - ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj, - "cpufreq"); - return -EINVAL; - } + read_lock_irqsave(&cpufreq_driver_lock, flags); + policy = per_cpu(cpufreq_cpu_data, cpu); + read_unlock_irqrestore(&cpufreq_driver_lock, flags); - WARN_ON(lock_policy_rwsem_write(cpu)); - update_policy_cpu(data, cpu_dev->id); - unlock_policy_rwsem_write(cpu); - pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n", - __func__, cpu_dev->id, cpu); + if (!policy) { + pr_debug("%s: No cpu_data found\n", __func__); + return -EINVAL; } + down_write(&policy->rwsem); + cpus = cpumask_weight(policy->cpus); + + if (cpus > 1) + cpumask_clear_cpu(cpu, policy->cpus); + up_write(&policy->rwsem); + /* If cpu is last user of policy, free policy */ if (cpus == 1) { - if (cpufreq_driver->target) - __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT); + if (has_target()) { + ret = __cpufreq_governor(policy, + CPUFREQ_GOV_POLICY_EXIT); + if (ret) { + pr_err("%s: Failed to exit governor\n", + __func__); + return ret; + } + } - lock_policy_rwsem_read(cpu); - kobj = &data->kobj; - cmp = &data->kobj_unregister; - unlock_policy_rwsem_read(cpu); - 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"); + if (!frozen) + cpufreq_policy_put_kobj(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. + */ if (cpufreq_driver->exit) - cpufreq_driver->exit(data); + cpufreq_driver->exit(policy); - free_cpumask_var(data->related_cpus); - free_cpumask_var(data->cpus); - kfree(data); + /* Remove policy from list of active policies */ + write_lock_irqsave(&cpufreq_driver_lock, flags); + list_del(&policy->policy_list); + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + if (!frozen) + cpufreq_policy_free(policy); } else { - pr_debug("%s: removing link, cpu: %d\n", __func__, cpu); - cpufreq_cpu_put(data); - if (cpufreq_driver->target) { - __cpufreq_governor(data, CPUFREQ_GOV_START); - __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + if (has_target()) { + if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) || + (ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) { + pr_err("%s: Failed to start governor\n", + __func__); + return ret; + } } } - per_cpu(cpufreq_policy_cpu, cpu) = -1; + per_cpu(cpufreq_cpu_data, cpu) = NULL; return 0; } - +/** + * cpufreq_remove_dev - remove a CPU device + * + * Removes the cpufreq interface for a CPU device. + */ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) { unsigned int cpu = dev->id; - int retval; + int ret; if (cpu_is_offline(cpu)) return 0; - retval = __cpufreq_remove_dev(dev, sif); - return retval; -} + ret = __cpufreq_remove_dev_prepare(dev, sif, false); + if (!ret) + ret = __cpufreq_remove_dev_finish(dev, sif, false); + + return ret; +} static void handle_update(struct work_struct *work) { @@ -1140,7 +1450,8 @@ } /** - * cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're in deep trouble. + * cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're + * in deep trouble. * @cpu: cpu number * @old_freq: CPU frequency the kernel thinks the CPU runs at * @new_freq: CPU frequency the CPU actually runs at @@ -1155,7 +1466,6 @@ struct cpufreq_freqs freqs; unsigned long flags; - pr_debug("Warning: CPU frequency out of sync: cpufreq and timing " "core thinks of %u, is %u kHz.\n", old_freq, new_freq); @@ -1170,7 +1480,6 @@ cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); } - /** * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur * @cpu: CPU number @@ -1216,7 +1525,6 @@ } EXPORT_SYMBOL(cpufreq_quick_get_max); - static unsigned int __cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); @@ -1248,22 +1556,17 @@ */ unsigned int cpufreq_get(unsigned int cpu) { - unsigned int ret_freq = 0; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + unsigned int ret_freq = 0; - if (!policy) - goto out; - - if (unlikely(lock_policy_rwsem_read(cpu))) - goto out_policy; - - ret_freq = __cpufreq_get(cpu); + if (policy) { + down_read(&policy->rwsem); + ret_freq = __cpufreq_get(cpu); + up_read(&policy->rwsem); - unlock_policy_rwsem_read(cpu); + cpufreq_cpu_put(policy); + } -out_policy: - cpufreq_cpu_put(policy); -out: return ret_freq; } EXPORT_SYMBOL(cpufreq_get); @@ -1275,7 +1578,6 @@ .remove_dev = cpufreq_remove_dev, }; - /** * cpufreq_bp_suspend - Prepare the boot CPU for system suspend. * @@ -1287,23 +1589,23 @@ int ret = 0; int cpu = smp_processor_id(); - struct cpufreq_policy *cpu_policy; + struct cpufreq_policy *policy; pr_debug("suspending cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) + policy = cpufreq_cpu_get(cpu); + if (!policy) return 0; if (cpufreq_driver->suspend) { - ret = cpufreq_driver->suspend(cpu_policy); + ret = cpufreq_driver->suspend(policy); if (ret) printk(KERN_ERR "cpufreq: suspend failed in ->suspend " - "step on CPU %u\n", cpu_policy->cpu); + "step on CPU %u\n", policy->cpu); } - cpufreq_cpu_put(cpu_policy); + cpufreq_cpu_put(policy); return ret; } @@ -1325,28 +1627,28 @@ int ret = 0; int cpu = smp_processor_id(); - struct cpufreq_policy *cpu_policy; + struct cpufreq_policy *policy; pr_debug("resuming cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) + policy = cpufreq_cpu_get(cpu); + if (!policy) return; if (cpufreq_driver->resume) { - ret = cpufreq_driver->resume(cpu_policy); + ret = cpufreq_driver->resume(policy); if (ret) { printk(KERN_ERR "cpufreq: resume failed in ->resume " - "step on CPU %u\n", cpu_policy->cpu); + "step on CPU %u\n", policy->cpu); goto fail; } } - schedule_work(&cpu_policy->update); + schedule_work(&policy->update); fail: - cpufreq_cpu_put(cpu_policy); + cpufreq_cpu_put(policy); } static struct syscore_ops cpufreq_syscore_ops = { @@ -1412,11 +1714,10 @@ } 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 + * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER * * Remove a driver from the CPU frequency notifier list. * @@ -1452,7 +1753,6 @@ * GOVERNORS * *********************************************************************/ - int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -1472,12 +1772,66 @@ pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n", policy->cpu, target_freq, relation, old_target_freq); + /* + * This might look like a redundant call as we are checking it again + * after finding index. But it is left intentionally for cases where + * exactly same freq is called again and so we can save on few function + * calls. + */ if (target_freq == policy->cur) return 0; if (cpufreq_driver->target) retval = cpufreq_driver->target(policy, target_freq, relation); + else if (cpufreq_driver->target_index) { + struct cpufreq_frequency_table *freq_table; + struct cpufreq_freqs freqs; + bool notify; + int index; + + freq_table = cpufreq_frequency_get_table(policy->cpu); + if (unlikely(!freq_table)) { + pr_err("%s: Unable to find freq_table\n", __func__); + goto out; + } + + retval = cpufreq_frequency_table_target(policy, freq_table, + target_freq, relation, &index); + if (unlikely(retval)) { + pr_err("%s: Unable to find matching freq\n", __func__); + goto out; + } + + if (freq_table[index].frequency == policy->cur) { + retval = 0; + goto out; + } + notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION); + + if (notify) { + freqs.old = policy->cur; + freqs.new = freq_table[index].frequency; + freqs.flags = 0; + + pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n", + __func__, policy->cpu, freqs.old, + freqs.new); + + cpufreq_notify_transition(policy, &freqs, + CPUFREQ_PRECHANGE); + } + + retval = cpufreq_driver->target_index(policy, index); + if (retval) + pr_err("%s: Failed to change cpu frequency: %d\n", + __func__, retval); + + if (notify) + cpufreq_notify_post_transition(policy, &freqs, retval); + } + +out: return retval; } EXPORT_SYMBOL_GPL(__cpufreq_driver_target); @@ -1488,45 +1842,16 @@ { int ret = -EINVAL; - policy = cpufreq_cpu_get(policy->cpu); - if (!policy) - goto no_policy; - - if (unlikely(lock_policy_rwsem_write(policy->cpu))) - goto fail; + down_write(&policy->rwsem); ret = __cpufreq_driver_target(policy, target_freq, relation); - unlock_policy_rwsem_write(policy->cpu); + up_write(&policy->rwsem); -fail: - cpufreq_cpu_put(policy); -no_policy: return ret; } EXPORT_SYMBOL_GPL(cpufreq_driver_target); -int __cpufreq_driver_getavg(struct cpufreq_policy *policy, unsigned int cpu) -{ - int ret = 0; - - if (cpufreq_disabled()) - return ret; - - if (!cpufreq_driver->getavg) - return 0; - - policy = cpufreq_cpu_get(policy->cpu); - if (!policy) - return -EINVAL; - - ret = cpufreq_driver->getavg(policy, cpu); - - cpufreq_cpu_put(policy); - return ret; -} -EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg); - /* * when "event" is CPUFREQ_GOV_LIMITS */ @@ -1561,15 +1886,17 @@ } } - if (!try_module_get(policy->governor->owner)) - return -EINVAL; + if (event == CPUFREQ_GOV_POLICY_INIT) + if (!try_module_get(policy->governor->owner)) + return -EINVAL; pr_debug("__cpufreq_governor for CPU %u, event %u\n", policy->cpu, event); mutex_lock(&cpufreq_governor_lock); - if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) || - (policy->governor_enabled && (event == CPUFREQ_GOV_START))) { + if ((policy->governor_enabled && event == CPUFREQ_GOV_START) + || (!policy->governor_enabled + && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) { mutex_unlock(&cpufreq_governor_lock); return -EBUSY; } @@ -1598,17 +1925,13 @@ mutex_unlock(&cpufreq_governor_lock); } - /* we keep one module reference alive for - each CPU governed by this CPU */ - if ((event != CPUFREQ_GOV_START) || ret) - module_put(policy->governor->owner); - if ((event == CPUFREQ_GOV_STOP) && !ret) + if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) || + ((event == CPUFREQ_GOV_POLICY_EXIT) && !ret)) module_put(policy->governor->owner); return ret; } - int cpufreq_register_governor(struct cpufreq_governor *governor) { int err; @@ -1633,7 +1956,6 @@ } EXPORT_SYMBOL_GPL(cpufreq_register_governor); - void cpufreq_unregister_governor(struct cpufreq_governor *governor) { #ifdef CONFIG_HOTPLUG_CPU @@ -1663,7 +1985,6 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_governor); - /********************************************************************* * POLICY INTERFACE * *********************************************************************/ @@ -1685,105 +2006,105 @@ if (!cpu_policy) return -EINVAL; - memcpy(policy, cpu_policy, sizeof(struct cpufreq_policy)); + memcpy(policy, cpu_policy, sizeof(*policy)); cpufreq_cpu_put(cpu_policy); return 0; } EXPORT_SYMBOL(cpufreq_get_policy); - /* - * data : current policy. - * policy : policy to be set. + * policy : current policy. + * new_policy: policy to be set. */ -static int __cpufreq_set_policy(struct cpufreq_policy *data, - struct cpufreq_policy *policy) +static int cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_policy *new_policy) { int ret = 0, failed = 1; - pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, - policy->min, policy->max); + pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu, + new_policy->min, new_policy->max); - memcpy(&policy->cpuinfo, &data->cpuinfo, - sizeof(struct cpufreq_cpuinfo)); + memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo)); - if (policy->min > data->max || policy->max < data->min) { + if (new_policy->min > policy->max || new_policy->max < policy->min) { ret = -EINVAL; goto error_out; } /* verify the cpu speed can be set within this limit */ - ret = cpufreq_driver->verify(policy); + ret = cpufreq_driver->verify(new_policy); if (ret) goto error_out; /* adjust if necessary - all reasons */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_ADJUST, policy); + CPUFREQ_ADJUST, new_policy); /* adjust if necessary - hardware incompatibility*/ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_INCOMPATIBLE, policy); + CPUFREQ_INCOMPATIBLE, new_policy); - /* verify the cpu speed can be set within this limit, - which might be different to the first one */ - ret = cpufreq_driver->verify(policy); + /* + * verify the cpu speed can be set within this limit, which might be + * different to the first one + */ + ret = cpufreq_driver->verify(new_policy); if (ret) goto error_out; /* notification of the new policy */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_NOTIFY, policy); + CPUFREQ_NOTIFY, new_policy); - data->min = policy->min; - data->max = policy->max; + policy->min = new_policy->min; + policy->max = new_policy->max; pr_debug("new min and max freqs are %u - %u kHz\n", - data->min, data->max); + policy->min, policy->max); if (cpufreq_driver->setpolicy) { - data->policy = policy->policy; + policy->policy = new_policy->policy; pr_debug("setting range\n"); - ret = cpufreq_driver->setpolicy(policy); + ret = cpufreq_driver->setpolicy(new_policy); } else { - if (policy->governor != data->governor) { + if (new_policy->governor != policy->governor) { /* save old, working values */ - struct cpufreq_governor *old_gov = data->governor; + struct cpufreq_governor *old_gov = policy->governor; pr_debug("governor switch\n"); /* end old governor */ - if (data->governor) { - __cpufreq_governor(data, CPUFREQ_GOV_STOP); - unlock_policy_rwsem_write(policy->cpu); - __cpufreq_governor(data, + if (policy->governor) { + __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + up_write(&policy->rwsem); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(policy->cpu); + down_write(&policy->rwsem); } /* start new governor */ - data->governor = policy->governor; - if (!__cpufreq_governor(data, CPUFREQ_GOV_POLICY_INIT)) { - if (!__cpufreq_governor(data, CPUFREQ_GOV_START)) { + policy->governor = new_policy->governor; + if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) { + if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) { failed = 0; } else { - unlock_policy_rwsem_write(policy->cpu); - __cpufreq_governor(data, + up_write(&policy->rwsem); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(policy->cpu); + down_write(&policy->rwsem); } } if (failed) { /* new governor failed, so re-start old one */ pr_debug("starting governor %s failed\n", - data->governor->name); + policy->governor->name); if (old_gov) { - data->governor = old_gov; - __cpufreq_governor(data, + policy->governor = old_gov; + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT); - __cpufreq_governor(data, + __cpufreq_governor(policy, CPUFREQ_GOV_START); } ret = -EINVAL; @@ -1792,7 +2113,7 @@ /* might be a policy change, too, so fall through */ } pr_debug("governor: change or update limits\n"); - __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); } error_out: @@ -1808,72 +2129,79 @@ */ int cpufreq_update_policy(unsigned int cpu) { - struct cpufreq_policy *data = cpufreq_cpu_get(cpu); - struct cpufreq_policy policy; + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct cpufreq_policy new_policy; int ret; - if (!data) { + if (!policy) { ret = -ENODEV; goto no_policy; } - if (unlikely(lock_policy_rwsem_write(cpu))) { - ret = -EINVAL; - goto fail; - } + down_write(&policy->rwsem); pr_debug("updating policy for CPU %u\n", cpu); - memcpy(&policy, data, sizeof(struct cpufreq_policy)); - policy.min = data->user_policy.min; - policy.max = data->user_policy.max; - policy.policy = data->user_policy.policy; - policy.governor = data->user_policy.governor; + memcpy(&new_policy, policy, sizeof(*policy)); + new_policy.min = policy->user_policy.min; + new_policy.max = policy->user_policy.max; + new_policy.policy = policy->user_policy.policy; + new_policy.governor = policy->user_policy.governor; - /* BIOS might change freq behind our back - -> ask driver for current freq and notify governors about a change */ - if (cpufreq_driver->get) { - policy.cur = cpufreq_driver->get(cpu); - if (!data->cur) { + /* + * 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) { + new_policy.cur = cpufreq_driver->get(cpu); + if (!policy->cur) { pr_debug("Driver did not initialize current freq"); - data->cur = policy.cur; + policy->cur = new_policy.cur; } else { - if (data->cur != policy.cur && cpufreq_driver->target) - cpufreq_out_of_sync(cpu, data->cur, - policy.cur); + if (policy->cur != new_policy.cur && has_target()) + cpufreq_out_of_sync(cpu, policy->cur, + new_policy.cur); } } - ret = __cpufreq_set_policy(data, &policy); + ret = cpufreq_set_policy(policy, &new_policy); - unlock_policy_rwsem_write(cpu); + up_write(&policy->rwsem); -fail: - cpufreq_cpu_put(data); + cpufreq_cpu_put(policy); no_policy: return ret; } EXPORT_SYMBOL(cpufreq_update_policy); -static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb, +static int cpufreq_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct device *dev; + bool frozen = false; dev = get_cpu_device(cpu); if (dev) { - switch (action) { + + if (action & CPU_TASKS_FROZEN) + frozen = true; + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpufreq_add_dev(dev, NULL); + __cpufreq_add_dev(dev, NULL, frozen); + cpufreq_update_policy(cpu); break; + case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - __cpufreq_remove_dev(dev, NULL); + __cpufreq_remove_dev_prepare(dev, NULL, frozen); + break; + + case CPU_POST_DEAD: + __cpufreq_remove_dev_finish(dev, NULL, frozen); break; + case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - cpufreq_add_dev(dev, NULL); + __cpufreq_add_dev(dev, NULL, frozen); break; } } @@ -1881,10 +2209,77 @@ } static struct notifier_block __refdata cpufreq_cpu_notifier = { - .notifier_call = cpufreq_cpu_callback, + .notifier_call = cpufreq_cpu_callback, }; /********************************************************************* + * BOOST * + *********************************************************************/ +static int cpufreq_boost_set_sw(int state) +{ + struct cpufreq_frequency_table *freq_table; + struct cpufreq_policy *policy; + int ret = -EINVAL; + + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + freq_table = cpufreq_frequency_get_table(policy->cpu); + if (freq_table) { + ret = cpufreq_frequency_table_cpuinfo(policy, + freq_table); + if (ret) { + pr_err("%s: Policy frequency update failed\n", + __func__); + break; + } + policy->user_policy.max = policy->max; + __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + } + } + + return ret; +} + +int cpufreq_boost_trigger_state(int state) +{ + unsigned long flags; + int ret = 0; + + if (cpufreq_driver->boost_enabled == state) + return 0; + + 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); + + pr_err("%s: Cannot %s BOOST\n", __func__, + state ? "enable" : "disable"); + } + + return ret; +} + +int cpufreq_boost_supported(void) +{ + if (likely(cpufreq_driver)) + return cpufreq_driver->boost_supported; + + return 0; +} +EXPORT_SYMBOL_GPL(cpufreq_boost_supported); + +int cpufreq_boost_enabled(void) +{ + return cpufreq_driver->boost_enabled; +} +EXPORT_SYMBOL_GPL(cpufreq_boost_enabled); + +/********************************************************************* * REGISTER / UNREGISTER CPUFREQ DRIVER * *********************************************************************/ @@ -1893,7 +2288,7 @@ * @driver_data: A struct cpufreq_driver containing the values# * submitted by the CPU Frequency driver. * - * Registers a CPU Frequency driver to this core code. This code + * Registers a CPU Frequency driver to this core code. This code * returns zero on success, -EBUSY when another driver got here first * (and isn't unregistered in the meantime). * @@ -1907,7 +2302,8 @@ return -ENODEV; if (!driver_data || !driver_data->verify || !driver_data->init || - ((!driver_data->setpolicy) && (!driver_data->target))) + !(driver_data->setpolicy || driver_data->target_index || + driver_data->target)) return -EINVAL; pr_debug("trying to register driver %s\n", driver_data->name); @@ -1918,14 +2314,30 @@ write_lock_irqsave(&cpufreq_driver_lock, flags); if (cpufreq_driver) { write_unlock_irqrestore(&cpufreq_driver_lock, flags); - return -EBUSY; + return -EEXIST; } cpufreq_driver = driver_data; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + if (cpufreq_boost_supported()) { + /* + * Check if driver provides function to enable boost - + * if not, use cpufreq_boost_set_sw as default + */ + if (!cpufreq_driver->set_boost) + cpufreq_driver->set_boost = cpufreq_boost_set_sw; + + ret = cpufreq_sysfs_create_file(&boost.attr); + if (ret) { + pr_err("%s: cannot register global BOOST sysfs file\n", + __func__); + goto err_null_driver; + } + } + ret = subsys_interface_register(&cpufreq_interface); if (ret) - goto err_null_driver; + goto err_boost_unreg; if (!(cpufreq_driver->flags & CPUFREQ_STICKY)) { int i; @@ -1952,6 +2364,9 @@ return 0; err_if_unreg: subsys_interface_unregister(&cpufreq_interface); +err_boost_unreg: + if (cpufreq_boost_supported()) + cpufreq_sysfs_remove_file(&boost.attr); err_null_driver: write_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver = NULL; @@ -1960,11 +2375,10 @@ } 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 + * Unregister the current CPUFreq driver. Only call this if you have * the right to do so, i.e. if you have succeeded in initialising before! * Returns zero if successful, and -EINVAL if the cpufreq_driver is * currently not initialised. @@ -1979,11 +2393,18 @@ pr_debug("unregistering driver %s\n", driver->name); subsys_interface_unregister(&cpufreq_interface); + if (cpufreq_boost_supported()) + cpufreq_sysfs_remove_file(&boost.attr); + unregister_hotcpu_notifier(&cpufreq_cpu_notifier); + down_write(&cpufreq_rwsem); write_lock_irqsave(&cpufreq_driver_lock, flags); + cpufreq_driver = NULL; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + up_write(&cpufreq_rwsem); return 0; } @@ -1991,17 +2412,10 @@ static int __init cpufreq_core_init(void) { - int cpu; - if (cpufreq_disabled()) return -ENODEV; - for_each_possible_cpu(cpu) { - per_cpu(cpufreq_policy_cpu, cpu) = -1; - init_rwsem(&per_cpu(cpu_policy_rwsem, cpu)); - } - - cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj); + cpufreq_global_kobject = kobject_create(); BUG_ON(!cpufreq_global_kobject); register_syscore_ops(&cpufreq_syscore_ops);