diff options
Diffstat (limited to 'drivers/cpufreq/cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 2026 |
1 files changed, 1301 insertions, 725 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index fb8a5279c5d..6f024852c6f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -3,6 +3,7 @@ * * Copyright (C) 2001 Russell King * (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de> + * (C) 2013 Viresh Kumar <viresh.kumar@linaro.org> * * Oct 2005 - Ashok Raj <ashok.raj@intel.com> * Added handling for CPU hotplug @@ -12,24 +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. - * */ -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/notifier.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/spinlock.h> #include <linux/device.h> -#include <linux/slab.h> -#include <linux/cpu.h> -#include <linux/completion.h> +#include <linux/init.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> #include <linux/mutex.h> -#include <linux/syscore_ops.h> - +#include <linux/slab.h> +#include <linux/suspend.h> +#include <linux/tick.h> #include <trace/events/power.h> /** @@ -39,67 +37,27 @@ */ static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); -#ifdef CONFIG_HOTPLUG_CPU +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); + /* 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_SPINLOCK(cpufreq_driver_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: - * - All holders of the lock should check to make sure that the CPU they - * are concerned with are online after they get the lock. - * - 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)); \ - if (unlikely(!cpu_online(cpu))) { \ - up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \ - return -1; \ - } \ - \ - return 0; \ -} - -lock_policy_rwsem(read, cpu); -lock_policy_rwsem(write, cpu); +/* Flag to suspend/resume CPUFreq governors */ +static bool cpufreq_suspended; -static void unlock_policy_rwsem_read(int cpu) +static inline bool has_target(void) { - int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); - BUG_ON(policy_cpu == -1); - up_read(&per_cpu(cpu_policy_rwsem, policy_cpu)); -} - -static void unlock_policy_rwsem_write(int cpu) -{ - int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); - BUG_ON(policy_cpu == -1); - up_write(&per_cpu(cpu_policy_rwsem, policy_cpu)); + return cpufreq_driver->target_index || cpufreq_driver->target; } +/* + * 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, @@ -127,7 +85,7 @@ static int __init init_cpufreq_transition_notifier_list(void) pure_initcall(init_cpufreq_transition_notifier_list); static int off __read_mostly; -int cpufreq_disabled(void) +static int cpufreq_disabled(void) { return off; } @@ -138,72 +96,146 @@ void disable_cpufreq(void) static LIST_HEAD(cpufreq_governor_list); static DEFINE_MUTEX(cpufreq_governor_mutex); -static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs) +bool have_governor_per_policy(void) { - struct cpufreq_policy *data; - unsigned long flags; - - if (cpu >= nr_cpu_ids) - goto err_out; + return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY); +} +EXPORT_SYMBOL_GPL(have_governor_per_policy); - /* get the cpufreq driver */ - spin_lock_irqsave(&cpufreq_driver_lock, flags); +struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy) +{ + 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); - spin_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: - spin_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) { - return __cpufreq_cpu_get(cpu, false); + int ret; + + 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) +/* Only for cpufreq core internal use */ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) { - if (!sysfs) - kobject_put(&data->kobj); - module_put(cpufreq_driver->owner); + return per_cpu(cpufreq_cpu_data, cpu); } -void cpufreq_cpu_put(struct cpufreq_policy *data) +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { - __cpufreq_cpu_put(data, false); + 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_put); +EXPORT_SYMBOL_GPL(cpufreq_cpu_get); -static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data) +void cpufreq_cpu_put(struct cpufreq_policy *policy) { - __cpufreq_cpu_put(data, true); + if (cpufreq_disabled()) + return; + + kobject_put(&policy->kobj); + up_read(&cpufreq_rwsem); } +EXPORT_SYMBOL_GPL(cpufreq_cpu_put); /********************************************************************* * EXTERNALLY AFFECTING FREQUENCY CHANGES * @@ -219,7 +251,7 @@ static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data) */ #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) { @@ -229,15 +261,14 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) if (!l_p_j_ref_freq) { l_p_j_ref = loops_per_jiffy; l_p_j_ref_freq = ci->old; - 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); + 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) || - (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { + if (val == CPUFREQ_POSTCHANGE && ci->old != ci->new) { loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, ci->new); - pr_debug("scaling loops_per_jiffy to %lu " - "for frequency %u kHz\n", loops_per_jiffy, ci->new); + pr_debug("scaling loops_per_jiffy to %lu for frequency %u kHz\n", + loops_per_jiffy, ci->new); } } #else @@ -247,26 +278,18 @@ static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) } #endif - -/** - * cpufreq_notify_transition - call notifier chain and adjust_jiffies - * on frequency transition. - * - * This function calls the transition notifiers and the "adjust_jiffies" - * function. It is called twice on all CPU frequency changes that have - * external effects. - */ -void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) +static void __cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state) { - struct cpufreq_policy *policy; - BUG_ON(irqs_disabled()); + if (cpufreq_disabled()) + return; + freqs->flags = cpufreq_driver->flags; pr_debug("notification %u of frequency transition to %u kHz\n", - state, freqs->new); + state, freqs->new); - policy = per_cpu(cpufreq_cpu_data, freqs->cpu); switch (state) { case CPUFREQ_PRECHANGE: @@ -277,9 +300,8 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { if ((policy) && (policy->cpu == freqs->cpu) && (policy->cur) && (policy->cur != freqs->old)) { - pr_debug("Warning: CPU frequency is" - " %u, cpufreq assumed %u kHz.\n", - freqs->old, policy->cur); + pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n", + freqs->old, policy->cur); freqs->old = policy->cur; } } @@ -290,9 +312,8 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) case CPUFREQ_POSTCHANGE: adjust_jiffies(CPUFREQ_POSTCHANGE, freqs); - pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, - (unsigned long)freqs->cpu); - trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu); + pr_debug("FREQ: %lu - CPU: %lu\n", + (unsigned long)freqs->new, (unsigned long)freqs->cpu); trace_cpu_frequency(freqs->new, freqs->cpu); srcu_notifier_call_chain(&cpufreq_transition_notifier_list, CPUFREQ_POSTCHANGE, freqs); @@ -301,13 +322,115 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) break; } } -EXPORT_SYMBOL_GPL(cpufreq_notify_transition); +/** + * cpufreq_notify_transition - call notifier chain and adjust_jiffies + * on frequency transition. + * + * This function calls the transition notifiers and the "adjust_jiffies" + * function. It is called twice on all CPU frequency changes that have + * external effects. + */ +static void cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state) +{ + for_each_cpu(freqs->cpu, policy->cpus) + __cpufreq_notify_transition(policy, freqs, state); +} + +/* Do post notifications when there are chances that transition has failed */ +static 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); +} + +void cpufreq_freq_transition_begin(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs) +{ + + /* + * Catch double invocations of _begin() which lead to self-deadlock. + * ASYNC_NOTIFICATION drivers are left out because the cpufreq core + * doesn't invoke _begin() on their behalf, and hence the chances of + * double invocations are very low. Moreover, there are scenarios + * where these checks can emit false-positive warnings in these + * drivers; so we avoid that by skipping them altogether. + */ + WARN_ON(!(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION) + && current == policy->transition_task); + +wait: + wait_event(policy->transition_wait, !policy->transition_ongoing); + + spin_lock(&policy->transition_lock); + + if (unlikely(policy->transition_ongoing)) { + spin_unlock(&policy->transition_lock); + goto wait; + } + + policy->transition_ongoing = true; + policy->transition_task = current; + + spin_unlock(&policy->transition_lock); + + cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE); +} +EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin); + +void cpufreq_freq_transition_end(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, int transition_failed) +{ + if (unlikely(WARN_ON(!policy->transition_ongoing))) + return; + + cpufreq_notify_post_transition(policy, freqs, transition_failed); + + policy->transition_ongoing = false; + policy->transition_task = NULL; + + wake_up(&policy->transition_wait); +} +EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end); /********************************************************************* * SYSFS INTERFACE * *********************************************************************/ +static 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) { @@ -340,7 +463,7 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy, *policy = CPUFREQ_POLICY_POWERSAVE; err = 0; } - } else if (cpufreq_driver->target) { + } else if (has_target()) { struct cpufreq_governor *t; mutex_lock(&cpufreq_governor_mutex); @@ -369,7 +492,6 @@ out: return err; } - /** * cpufreq_per_cpu_attr_read() / show_##file_name() - * print out cpufreq information @@ -392,8 +514,8 @@ show_one(scaling_min_freq, min); 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 @@ -402,7 +524,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, static ssize_t store_##file_name \ (struct cpufreq_policy *policy, const char *buf, size_t count) \ { \ - unsigned int ret = -EINVAL; \ + int ret; \ struct cpufreq_policy new_policy; \ \ ret = cpufreq_get_policy(&new_policy, policy->cpu); \ @@ -413,7 +535,7 @@ static ssize_t store_##file_name \ 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; \ @@ -434,7 +556,6 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, return sprintf(buf, "%u\n", cur_freq); } - /** * show_scaling_governor - show the current policy for the specified CPU */ @@ -445,19 +566,18 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf) else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) return sprintf(buf, "performance\n"); else if (policy->governor) - return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", + return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", policy->governor->name); return -EINVAL; } - /** * store_scaling_governor - store policy for the specified CPU */ static ssize_t store_scaling_governor(struct cpufreq_policy *policy, const char *buf, size_t count) { - unsigned int ret = -EINVAL; + int ret; char str_governor[16]; struct cpufreq_policy new_policy; @@ -473,9 +593,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy, &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; @@ -491,7 +609,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy, */ static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf) { - return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name); + return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name); } /** @@ -503,7 +621,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, ssize_t i = 0; struct cpufreq_governor *t; - if (!cpufreq_driver->target) { + if (!has_target()) { i += sprintf(buf, "performance powersave"); goto out; } @@ -512,14 +630,14 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char)) - (CPUFREQ_NAME_LEN + 2))) goto out; - i += scnprintf(&buf[i], CPUFREQ_NAME_LEN, "%s ", t->name); + i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name); } out: i += sprintf(&buf[i], "\n"); 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; @@ -534,6 +652,7 @@ static ssize_t show_cpus(const struct cpumask *mask, char *buf) 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 @@ -541,9 +660,7 @@ static ssize_t show_cpus(const struct cpumask *mask, char *buf) */ static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf) { - if (cpumask_empty(policy->related_cpus)) - return show_cpus(policy->cpus, buf); - return show_cpus(policy->related_cpus, buf); + return cpufreq_show_cpus(policy->related_cpus, buf); } /** @@ -551,7 +668,7 @@ static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf) */ 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, @@ -581,7 +698,7 @@ static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf) } /** - * show_scaling_driver - show the current cpufreq HW/BIOS limitation + * show_bios_limit - show the current cpufreq HW/BIOS limitation */ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf) { @@ -625,9 +742,6 @@ static struct attribute *default_attrs[] = { 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) @@ -635,23 +749,21 @@ 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 = -EINVAL; - policy = cpufreq_cpu_get_sysfs(policy->cpu); - if (!policy) - goto no_policy; + ssize_t ret; - if (lock_policy_rwsem_read(policy->cpu) < 0) - goto fail; + if (!down_read_trylock(&cpufreq_rwsem)) + return -EINVAL; + + 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; } @@ -661,22 +773,28 @@ 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; - 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; } @@ -698,125 +816,76 @@ static struct kobj_type ktype_cpufreq = { .release = cpufreq_sysfs_release, }; -/* - * Returns: - * Negative: Failure - * 0: Success - * Positive: When we have a managed CPU and the sysfs got symlinked - */ -static int cpufreq_add_dev_policy(unsigned int cpu, - struct cpufreq_policy *policy, - struct device *dev) -{ - int ret = 0; -#ifdef CONFIG_SMP - unsigned long flags; - unsigned int j; -#ifdef CONFIG_HOTPLUG_CPU - struct cpufreq_governor *gov; +struct kobject *cpufreq_global_kobject; +EXPORT_SYMBOL(cpufreq_global_kobject); - gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu)); - if (gov) { - policy->governor = gov; - pr_debug("Restoring governor %s for cpu %d\n", - policy->governor->name, cpu); - } -#endif +static int cpufreq_global_kobject_usage; - for_each_cpu(j, policy->cpus) { - struct cpufreq_policy *managed_policy; +int cpufreq_get_global_kobject(void) +{ + if (!cpufreq_global_kobject_usage++) + return kobject_add(cpufreq_global_kobject, + &cpu_subsys.dev_root->kobj, "%s", "cpufreq"); - if (cpu == j) - continue; + return 0; +} +EXPORT_SYMBOL(cpufreq_get_global_kobject); - /* Check for existing affected CPUs. - * They may not be aware of it due to CPU Hotplug. - * cpufreq_cpu_put is called when the device is removed - * in __cpufreq_remove_dev() - */ - managed_policy = cpufreq_cpu_get(j); - if (unlikely(managed_policy)) { - - /* Set proper policy_cpu */ - unlock_policy_rwsem_write(cpu); - per_cpu(cpufreq_policy_cpu, cpu) = managed_policy->cpu; - - if (lock_policy_rwsem_write(cpu) < 0) { - /* Should not go through policy unlock path */ - if (cpufreq_driver->exit) - cpufreq_driver->exit(policy); - cpufreq_cpu_put(managed_policy); - return -EBUSY; - } +void cpufreq_put_global_kobject(void) +{ + if (!--cpufreq_global_kobject_usage) + kobject_del(cpufreq_global_kobject); +} +EXPORT_SYMBOL(cpufreq_put_global_kobject); - spin_lock_irqsave(&cpufreq_driver_lock, flags); - cpumask_copy(managed_policy->cpus, policy->cpus); - per_cpu(cpufreq_cpu_data, cpu) = managed_policy; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - - pr_debug("CPU already managed, adding link\n"); - ret = sysfs_create_link(&dev->kobj, - &managed_policy->kobj, - "cpufreq"); - if (ret) - cpufreq_cpu_put(managed_policy); - /* - * Success. We only needed to be added to the mask. - * Call driver->exit() because only the cpu parent of - * the kobj needed to call init(). - */ - if (cpufreq_driver->exit) - cpufreq_driver->exit(policy); +int cpufreq_sysfs_create_file(const struct attribute *attr) +{ + int ret = cpufreq_get_global_kobject(); - if (!ret) - return 1; - else - return ret; - } + if (!ret) { + ret = sysfs_create_file(cpufreq_global_kobject, attr); + if (ret) + cpufreq_put_global_kobject(); } -#endif + 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) - continue; - if (!cpu_online(j)) + 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, @@ -837,7 +906,7 @@ static int cpufreq_add_dev_interface(unsigned int cpu, 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; @@ -848,60 +917,190 @@ static int cpufreq_add_dev_interface(unsigned int cpu, goto err_out_kobj_put; } - spin_lock_irqsave(&cpufreq_driver_lock, flags); - for_each_cpu(j, policy->cpus) { - if (!cpu_online(j)) - continue; - per_cpu(cpufreq_cpu_data, j) = policy; - per_cpu(cpufreq_policy_cpu, j) = policy->cpu; - } - spin_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 */ - policy->governor = NULL; + return ret; - /* set default policy */ - ret = __cpufreq_set_policy(policy, &new_policy); - policy->user_policy.policy = policy->policy; - policy->user_policy.governor = policy->governor; +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_governor *gov = NULL; + struct cpufreq_policy new_policy; + int ret = 0; + memcpy(&new_policy, policy, sizeof(*policy)); + + /* Update governor of new_policy to the governor used before hotplug */ + gov = __find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu)); + if (gov) + pr_debug("Restoring governor %s for cpu %d\n", + policy->governor->name, policy->cpu); + else + gov = CPUFREQ_DEFAULT_GOVERNOR; + + new_policy.governor = gov; + + /* Use the default policy if its valid. */ + if (cpufreq_driver->setpolicy) + cpufreq_parse_governor(gov->name, &new_policy.policy, NULL); + + /* set default policy */ + 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(struct cpufreq_policy *policy, + unsigned int cpu, struct device *dev) +{ + int ret = 0; + unsigned long flags; + + if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + if (ret) { + pr_err("%s: Failed to stop governor\n", __func__); + return ret; + } + } + + down_write(&policy->rwsem); + + write_lock_irqsave(&cpufreq_driver_lock, flags); + + cpumask_set_cpu(cpu, policy->cpus); + per_cpu(cpufreq_cpu_data, cpu) = policy; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + up_write(&policy->rwsem); + + if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_START); + if (!ret) + ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + + if (ret) { + pr_err("%s: Failed to start governor\n", __func__); + return ret; + } + } + + return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); } +#endif +static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu) +{ + struct cpufreq_policy *policy; + unsigned long flags; -/** - * 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) + read_lock_irqsave(&cpufreq_driver_lock, flags); + + policy = per_cpu(cpufreq_cpu_data_fallback, cpu); + + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + + policy->governor = NULL; + + return policy; +} + +static struct cpufreq_policy *cpufreq_policy_alloc(void) { - unsigned int cpu = dev->id; - int ret = 0, found = 0; + 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); + spin_lock_init(&policy->transition_lock); + init_waitqueue_head(&policy->transition_wait); + + 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); + + 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) +{ + unsigned int j, cpu = dev->id; + int ret = -ENOMEM; struct cpufreq_policy *policy; unsigned long flags; - unsigned int j; + bool recover_policy = cpufreq_suspended; #ifdef CONFIG_HOTPLUG_CPU - int sibling; + struct cpufreq_policy *tpolicy; #endif if (cpu_is_offline(cpu)) @@ -919,257 +1118,372 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) } #endif - if (!try_module_get(cpufreq_driver->owner)) { - ret = -EINVAL; - goto module_out; - } + if (!down_read_trylock(&cpufreq_rwsem)) + return 0; - ret = -ENOMEM; - policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL); - if (!policy) - goto nomem_out; +#ifdef CONFIG_HOTPLUG_CPU + /* Check if this cpu was hot-unplugged earlier and has siblings */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + 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); + ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev); + up_read(&cpufreq_rwsem); + return ret; + } + } + read_unlock_irqrestore(&cpufreq_driver_lock, flags); +#endif - if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL)) - goto err_free_policy; + /* + * Restore the saved policy when doing light-weight init and fall back + * to the full init if that fails. + */ + policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL; + if (!policy) { + recover_policy = false; + policy = cpufreq_policy_alloc(); + if (!policy) + goto nomem_out; + } - 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 (recover_policy && cpu != policy->cpu) { + update_policy_cpu(policy, cpu); + WARN_ON(kobject_move(&policy->kobj, &dev->kobj)); + } else { + policy->cpu = cpu; + } - policy->cpu = cpu; cpumask_copy(policy->cpus, cpumask_of(cpu)); - /* Initially set CPU itself as the policy_cpu */ - per_cpu(cpufreq_policy_cpu, cpu) = cpu; - ret = (lock_policy_rwsem_write(cpu) < 0); - WARN_ON(ret); - init_completion(&policy->kobj_unregister); INIT_WORK(&policy->update, handle_update); - /* Set governor before ->init, so that driver could check it */ -#ifdef CONFIG_HOTPLUG_CPU - for_each_online_cpu(sibling) { - struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling); - if (cp && cp->governor && - (cpumask_test_cpu(cpu, cp->related_cpus))) { - policy->governor = cp->governor; - found = 1; - break; - } - } -#endif - if (!found) - policy->governor = CPUFREQ_DEFAULT_GOVERNOR; /* call driver. From then on the cpufreq must be able * to accept all calls to ->verify and ->setpolicy for this CPU */ ret = cpufreq_driver->init(policy); if (ret) { pr_debug("initialization failed\n"); - goto err_unlock_policy; + goto err_set_policy_cpu; + } + + /* related cpus should atleast have policy->cpus */ + cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus); + + /* + * affected cpus must always be the one, which are online. We aren't + * managing offline cpus here. + */ + cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); + + if (!recover_policy) { + 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); + } } - policy->user_policy.min = policy->min; - policy->user_policy.max = policy->max; blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_START, policy); - ret = cpufreq_add_dev_policy(cpu, policy, dev); - if (ret) { - if (ret > 0) - /* This is a managed cpu, symlink created, - exit with 0 */ - ret = 0; - goto err_unlock_policy; + if (!recover_policy) { + 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); } - ret = cpufreq_add_dev_interface(cpu, policy, dev); - if (ret) - goto err_out_unregister; + 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); - unlock_policy_rwsem_write(cpu); + if (!recover_policy) { + 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: - spin_lock_irqsave(&cpufreq_driver_lock, flags); +err_get_freq: + write_lock_irqsave(&cpufreq_driver_lock, flags); for_each_cpu(j, policy->cpus) per_cpu(cpufreq_cpu_data, j) = NULL; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + 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: + if (recover_policy) { + /* Do not leave stale fallback data behind. */ + per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL; + cpufreq_policy_put_kobj(policy); + } + cpufreq_policy_free(policy); -err_unlock_policy: - unlock_policy_rwsem_write(cpu); - free_cpumask_var(policy->related_cpus); -err_free_cpumask: - free_cpumask_var(policy->cpus); -err_free_policy: - kfree(policy); nomem_out: - module_put(cpufreq_driver->owner); -module_out: + up_read(&cpufreq_rwsem); + return ret; } - /** - * __cpufreq_remove_dev - remove a CPU device + * cpufreq_add_dev - add 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. + * 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_remove_dev(struct device *dev, struct subsys_interface *sif) +static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) +{ + return __cpufreq_add_dev(dev, sif); +} + +static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, + unsigned int old_cpu) { - unsigned int cpu = dev->id; - unsigned long flags; - struct cpufreq_policy *data; - struct kobject *kobj; - struct completion *cmp; -#ifdef CONFIG_SMP struct device *cpu_dev; - unsigned int j; -#endif + int ret; - pr_debug("unregistering CPU %u\n", cpu); + /* first sibling now owns the new sysfs dir */ + cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu)); - spin_lock_irqsave(&cpufreq_driver_lock, flags); - data = per_cpu(cpufreq_cpu_data, cpu); + 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\n", __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"); - if (!data) { - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - unlock_policy_rwsem_write(cpu); return -EINVAL; } - per_cpu(cpufreq_cpu_data, cpu) = NULL; + return cpu_dev->id; +} -#ifdef CONFIG_SMP - /* if this isn't the CPU which is the parent of the kobj, we - * only need to unlink, put and exit - */ - if (unlikely(cpu != data->cpu)) { - pr_debug("removing link\n"); - cpumask_clear_cpu(cpu, data->cpus); - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - kobj = &dev->kobj; - cpufreq_cpu_put(data); - unlock_policy_rwsem_write(cpu); - sysfs_remove_link(kobj, "cpufreq"); - return 0; - } -#endif +static int __cpufreq_remove_dev_prepare(struct device *dev, + struct subsys_interface *sif) +{ + unsigned int cpu = dev->id, cpus; + int new_cpu, ret; + unsigned long flags; + struct cpufreq_policy *policy; -#ifdef CONFIG_SMP + pr_debug("%s: unregistering CPU %u\n", __func__, cpu); -#ifdef CONFIG_HOTPLUG_CPU - strncpy(per_cpu(cpufreq_cpu_governor, cpu), data->governor->name, - CPUFREQ_NAME_LEN); -#endif + write_lock_irqsave(&cpufreq_driver_lock, flags); - /* if we have other CPUs still registered, we need to unlink them, - * or else wait_for_completion below will lock up. Clean the - * per_cpu(cpufreq_cpu_data) while holding the lock, and remove - * the sysfs links afterwards. - */ - if (unlikely(cpumask_weight(data->cpus) > 1)) { - for_each_cpu(j, data->cpus) { - if (j == cpu) - continue; - per_cpu(cpufreq_cpu_data, j) = NULL; + policy = per_cpu(cpufreq_cpu_data, cpu); + + /* Save the policy somewhere when doing a light-weight tear-down */ + if (cpufreq_suspended) + per_cpu(cpufreq_cpu_data_fallback, cpu) = policy; + + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + if (!policy) { + pr_debug("%s: No cpu_data found\n", __func__); + return -EINVAL; + } + + if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + if (ret) { + pr_err("%s: Failed to stop governor\n", __func__); + return ret; } } - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + if (!cpufreq_driver->setpolicy) + strncpy(per_cpu(cpufreq_cpu_governor, cpu), + policy->governor->name, CPUFREQ_NAME_LEN); - if (unlikely(cpumask_weight(data->cpus) > 1)) { - for_each_cpu(j, data->cpus) { - if (j == cpu) - continue; - pr_debug("removing link for cpu %u\n", j); -#ifdef CONFIG_HOTPLUG_CPU - strncpy(per_cpu(cpufreq_cpu_governor, j), - data->governor->name, CPUFREQ_NAME_LEN); -#endif - cpu_dev = get_cpu_device(j); - kobj = &cpu_dev->kobj; - unlock_policy_rwsem_write(cpu); - sysfs_remove_link(kobj, "cpufreq"); - lock_policy_rwsem_write(cpu); - cpufreq_cpu_put(data); + down_read(&policy->rwsem); + cpus = cpumask_weight(policy->cpus); + up_read(&policy->rwsem); + + if (cpu != policy->cpu) { + sysfs_remove_link(&dev->kobj, "cpufreq"); + } else if (cpus > 1) { + new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu); + if (new_cpu >= 0) { + update_policy_cpu(policy, new_cpu); + + if (!cpufreq_suspended) + pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n", + __func__, new_cpu, cpu); } + } else if (cpufreq_driver->stop_cpu && cpufreq_driver->setpolicy) { + cpufreq_driver->stop_cpu(policy); } -#else - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); -#endif - if (cpufreq_driver->target) - __cpufreq_governor(data, CPUFREQ_GOV_STOP); + return 0; +} - kobj = &data->kobj; - cmp = &data->kobj_unregister; - unlock_policy_rwsem_write(cpu); - kobject_put(kobj); +static int __cpufreq_remove_dev_finish(struct device *dev, + struct subsys_interface *sif) +{ + unsigned int cpu = dev->id, cpus; + int ret; + unsigned long flags; + struct cpufreq_policy *policy; - /* 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"); + read_lock_irqsave(&cpufreq_driver_lock, flags); + policy = per_cpu(cpufreq_cpu_data, cpu); + read_unlock_irqrestore(&cpufreq_driver_lock, flags); - lock_policy_rwsem_write(cpu); - if (cpufreq_driver->exit) - cpufreq_driver->exit(data); - unlock_policy_rwsem_write(cpu); + if (!policy) { + pr_debug("%s: No cpu_data found\n", __func__); + return -EINVAL; + } -#ifdef CONFIG_HOTPLUG_CPU - /* when the CPU which is the parent of the kobj is hotplugged - * offline, check for siblings, and create cpufreq sysfs interface - * and symlinks - */ - if (unlikely(cpumask_weight(data->cpus) > 1)) { - /* first sibling now owns the new sysfs dir */ - cpumask_clear_cpu(cpu, data->cpus); - cpufreq_add_dev(get_cpu_device(cpumask_first(data->cpus)), NULL); + 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 (has_target()) { + ret = __cpufreq_governor(policy, + CPUFREQ_GOV_POLICY_EXIT); + if (ret) { + pr_err("%s: Failed to exit governor\n", + __func__); + return ret; + } + } - /* finally remove our own symlink */ - lock_policy_rwsem_write(cpu); - __cpufreq_remove_dev(dev, sif); - } -#endif + if (!cpufreq_suspended) + 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(policy); + + /* 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); - free_cpumask_var(data->related_cpus); - free_cpumask_var(data->cpus); - kfree(data); + if (!cpufreq_suspended) + cpufreq_policy_free(policy); + } else if (has_target()) { + ret = __cpufreq_governor(policy, CPUFREQ_GOV_START); + if (!ret) + ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); + + if (ret) { + pr_err("%s: Failed to start governor\n", __func__); + return ret; + } + } + 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; - if (unlikely(lock_policy_rwsem_write(cpu))) - BUG(); + ret = __cpufreq_remove_dev_prepare(dev, sif); - retval = __cpufreq_remove_dev(dev, sif); - return retval; -} + if (!ret) + ret = __cpufreq_remove_dev_finish(dev, sif); + return ret; +} static void handle_update(struct work_struct *work) { @@ -1181,7 +1495,8 @@ static void handle_update(struct work_struct *work) } /** - * 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 @@ -1192,18 +1507,23 @@ static void handle_update(struct work_struct *work) static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigned int new_freq) { + struct cpufreq_policy *policy; 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); + pr_debug("Warning: CPU frequency out of sync: cpufreq and timing core thinks of %u, is %u kHz\n", + old_freq, new_freq); - freqs.cpu = cpu; freqs.old = old_freq; freqs.new = new_freq; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); -} + read_lock_irqsave(&cpufreq_driver_lock, flags); + policy = per_cpu(cpufreq_cpu_data, cpu); + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + + cpufreq_freq_transition_begin(policy, &freqs); + cpufreq_freq_transition_end(policy, &freqs, 0); +} /** * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur @@ -1214,9 +1534,13 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, */ unsigned int cpufreq_quick_get(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct cpufreq_policy *policy; unsigned int ret_freq = 0; + if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) + return cpufreq_driver->get(cpu); + + policy = cpufreq_cpu_get(cpu); if (policy) { ret_freq = policy->cur; cpufreq_cpu_put(policy); @@ -1246,7 +1570,6 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu) } EXPORT_SYMBOL(cpufreq_quick_get_max); - static unsigned int __cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); @@ -1278,22 +1601,17 @@ static unsigned int __cpufreq_get(unsigned int cpu) */ 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); @@ -1305,85 +1623,118 @@ static struct subsys_interface cpufreq_interface = { .remove_dev = cpufreq_remove_dev, }; +/* + * In case platform wants some specific frequency to be configured + * during suspend.. + */ +int cpufreq_generic_suspend(struct cpufreq_policy *policy) +{ + int ret; + + if (!policy->suspend_freq) { + pr_err("%s: suspend_freq can't be zero\n", __func__); + return -EINVAL; + } + + pr_debug("%s: Setting suspend-freq: %u\n", __func__, + policy->suspend_freq); + + ret = __cpufreq_driver_target(policy, policy->suspend_freq, + CPUFREQ_RELATION_H); + if (ret) + pr_err("%s: unable to set suspend-freq: %u. err: %d\n", + __func__, policy->suspend_freq, ret); + + return ret; +} +EXPORT_SYMBOL(cpufreq_generic_suspend); /** - * cpufreq_bp_suspend - Prepare the boot CPU for system suspend. + * cpufreq_suspend() - Suspend CPUFreq governors * - * This function is only executed for the boot processor. The other CPUs - * have been put offline by means of CPU hotplug. + * Called during system wide Suspend/Hibernate cycles for suspending governors + * as some platforms can't change frequency after this point in suspend cycle. + * Because some of the devices (like: i2c, regulators, etc) they use for + * changing frequency are suspended quickly after this point. */ -static int cpufreq_bp_suspend(void) +void cpufreq_suspend(void) { - int ret = 0; + struct cpufreq_policy *policy; - int cpu = smp_processor_id(); - struct cpufreq_policy *cpu_policy; + if (!cpufreq_driver) + return; - pr_debug("suspending cpu %u\n", cpu); + if (!has_target()) + return; - /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) - return 0; + pr_debug("%s: Suspending Governors\n", __func__); - if (cpufreq_driver->suspend) { - ret = cpufreq_driver->suspend(cpu_policy); - if (ret) - printk(KERN_ERR "cpufreq: suspend failed in ->suspend " - "step on CPU %u\n", cpu_policy->cpu); + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP)) + pr_err("%s: Failed to stop governor for policy: %p\n", + __func__, policy); + else if (cpufreq_driver->suspend + && cpufreq_driver->suspend(policy)) + pr_err("%s: Failed to suspend driver: %p\n", __func__, + policy); } - cpufreq_cpu_put(cpu_policy); - return ret; + cpufreq_suspended = true; } /** - * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU. + * cpufreq_resume() - Resume CPUFreq governors * - * 1.) resume CPUfreq hardware support (cpufreq_driver->resume()) - * 2.) schedule call cpufreq_update_policy() ASAP as interrupts are - * restored. It will verify that the current freq is in sync with - * what we believe it to be. This is a bit later than when it - * should be, but nonethteless it's better than calling - * cpufreq_driver->get() here which might re-enable interrupts... - * - * This function is only executed for the boot CPU. The other CPUs have not - * been turned on yet. + * Called during system wide Suspend/Hibernate cycle for resuming governors that + * are suspended with cpufreq_suspend(). */ -static void cpufreq_bp_resume(void) +void cpufreq_resume(void) { - 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 (!cpufreq_driver) + return; - /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) + if (!has_target()) return; - if (cpufreq_driver->resume) { - ret = cpufreq_driver->resume(cpu_policy); - if (ret) { - printk(KERN_ERR "cpufreq: resume failed in ->resume " - "step on CPU %u\n", cpu_policy->cpu); - goto fail; - } - } + pr_debug("%s: Resuming Governors\n", __func__); - schedule_work(&cpu_policy->update); + cpufreq_suspended = false; -fail: - cpufreq_cpu_put(cpu_policy); + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) + pr_err("%s: Failed to resume driver: %p\n", __func__, + policy); + else if (__cpufreq_governor(policy, CPUFREQ_GOV_START) + || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS)) + pr_err("%s: Failed to start governor for policy: %p\n", + __func__, policy); + + /* + * schedule call cpufreq_update_policy() for boot CPU, i.e. last + * policy in list. It will verify that the current freq is in + * sync with what we believe it to be. + */ + if (list_is_last(&policy->policy_list, &cpufreq_policy_list)) + schedule_work(&policy->update); + } } -static struct syscore_ops cpufreq_syscore_ops = { - .suspend = cpufreq_bp_suspend, - .resume = cpufreq_bp_resume, -}; +/** + * cpufreq_get_current_driver - return current driver's name + * + * Return the name string of the currently loaded cpufreq driver + * or NULL, if none. + */ +const char *cpufreq_get_current_driver(void) +{ + if (cpufreq_driver) + return cpufreq_driver->name; + return NULL; +} +EXPORT_SYMBOL_GPL(cpufreq_get_current_driver); /********************************************************************* * NOTIFIER LISTS INTERFACE * @@ -1406,6 +1757,9 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list) { int ret; + if (cpufreq_disabled()) + return -EINVAL; + WARN_ON(!init_cpufreq_transition_notifier_list_called); switch (list) { @@ -1425,11 +1779,10 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list) } EXPORT_SYMBOL(cpufreq_register_notifier); - /** * cpufreq_unregister_notifier - unregister a driver with cpufreq * @nb: notifier block to be unregistered - * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER + * @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER * * Remove a driver from the CPU frequency notifier list. * @@ -1440,6 +1793,9 @@ int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list) { int ret; + if (cpufreq_disabled()) + return -EINVAL; + switch (list) { case CPUFREQ_TRANSITION_NOTIFIER: ret = srcu_notifier_chain_unregister( @@ -1462,21 +1818,145 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier); * GOVERNORS * *********************************************************************/ +/* Must set freqs->new to intermediate frequency */ +static int __target_intermediate(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, int index) +{ + int ret; + + freqs->new = cpufreq_driver->get_intermediate(policy, index); + + /* We don't need to switch to intermediate freq */ + if (!freqs->new) + return 0; + + pr_debug("%s: cpu: %d, switching to intermediate freq: oldfreq: %u, intermediate freq: %u\n", + __func__, policy->cpu, freqs->old, freqs->new); + + cpufreq_freq_transition_begin(policy, freqs); + ret = cpufreq_driver->target_intermediate(policy, index); + cpufreq_freq_transition_end(policy, freqs, ret); + + if (ret) + pr_err("%s: Failed to change to intermediate frequency: %d\n", + __func__, ret); + + return ret; +} + +static int __target_index(struct cpufreq_policy *policy, + struct cpufreq_frequency_table *freq_table, int index) +{ + struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0}; + unsigned int intermediate_freq = 0; + int retval = -EINVAL; + bool notify; + + notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION); + if (notify) { + /* Handle switching to intermediate frequency */ + if (cpufreq_driver->get_intermediate) { + retval = __target_intermediate(policy, &freqs, index); + if (retval) + return retval; + + intermediate_freq = freqs.new; + /* Set old freq to intermediate */ + if (intermediate_freq) + freqs.old = freqs.new; + } + + freqs.new = freq_table[index].frequency; + pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n", + __func__, policy->cpu, freqs.old, freqs.new); + + cpufreq_freq_transition_begin(policy, &freqs); + } + + retval = cpufreq_driver->target_index(policy, index); + if (retval) + pr_err("%s: Failed to change cpu frequency: %d\n", __func__, + retval); + + if (notify) { + cpufreq_freq_transition_end(policy, &freqs, retval); + + /* + * Failed after setting to intermediate freq? Driver should have + * reverted back to initial frequency and so should we. Check + * here for intermediate_freq instead of get_intermediate, in + * case we have't switched to intermediate freq at all. + */ + if (unlikely(retval && intermediate_freq)) { + freqs.old = intermediate_freq; + freqs.new = policy->restore_freq; + cpufreq_freq_transition_begin(policy, &freqs); + cpufreq_freq_transition_end(policy, &freqs, 0); + } + } + + return retval; +} int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { + unsigned int old_target_freq = target_freq; int retval = -EINVAL; if (cpufreq_disabled()) return -ENODEV; - pr_debug("target for CPU %u: %u kHz, relation %u\n", policy->cpu, - target_freq, relation); - if (cpu_online(policy->cpu) && cpufreq_driver->target) + /* Make sure that target_freq is within supported range */ + if (target_freq > policy->max) + target_freq = policy->max; + if (target_freq < policy->min) + target_freq = policy->min; + + 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; + + /* Save last value to restore later on errors */ + policy->restore_freq = policy->cur; + + if (cpufreq_driver->target) retval = cpufreq_driver->target(policy, target_freq, relation); + else if (cpufreq_driver->target_index) { + struct cpufreq_frequency_table *freq_table; + 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; + } + + retval = __target_index(policy, freq_table, index); + } +out: return retval; } EXPORT_SYMBOL_GPL(__cpufreq_driver_target); @@ -1487,40 +1967,16 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, { 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; - - policy = cpufreq_cpu_get(policy->cpu); - if (!policy) - return -EINVAL; - - if (cpu_online(cpu) && cpufreq_driver->getavg) - ret = cpufreq_driver->getavg(policy, cpu); - - cpufreq_cpu_put(policy); - return ret; -} -EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg); - /* * when "event" is CPUFREQ_GOV_LIMITS */ @@ -1540,39 +1996,68 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, struct cpufreq_governor *gov = NULL; #endif + /* Don't start any governor operations if we are entering suspend */ + if (cpufreq_suspended) + return 0; + if (policy->governor->max_transition_latency && policy->cpuinfo.transition_latency > policy->governor->max_transition_latency) { if (!gov) return -EINVAL; else { - printk(KERN_WARNING "%s governor failed, too long" - " transition latency of HW, fallback" - " to %s governor\n", - policy->governor->name, - gov->name); + pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n", + policy->governor->name, gov->name); policy->governor = gov; } } - 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); + policy->cpu, event); + + mutex_lock(&cpufreq_governor_lock); + 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; + } + + if (event == CPUFREQ_GOV_STOP) + policy->governor_enabled = false; + else if (event == CPUFREQ_GOV_START) + policy->governor_enabled = true; + + mutex_unlock(&cpufreq_governor_lock); + ret = policy->governor->governor(policy, event); - /* 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 (!ret) { + if (event == CPUFREQ_GOV_POLICY_INIT) + policy->governor->initialized++; + else if (event == CPUFREQ_GOV_POLICY_EXIT) + policy->governor->initialized--; + } else { + /* Restore original values */ + mutex_lock(&cpufreq_governor_lock); + if (event == CPUFREQ_GOV_STOP) + policy->governor_enabled = true; + else if (event == CPUFREQ_GOV_START) + policy->governor_enabled = false; + mutex_unlock(&cpufreq_governor_lock); + } + + 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; @@ -1585,6 +2070,7 @@ int cpufreq_register_governor(struct cpufreq_governor *governor) mutex_lock(&cpufreq_governor_mutex); + governor->initialized = 0; err = -EBUSY; if (__find_governor(governor->name) == NULL) { err = 0; @@ -1596,12 +2082,9 @@ int cpufreq_register_governor(struct cpufreq_governor *governor) } EXPORT_SYMBOL_GPL(cpufreq_register_governor); - void cpufreq_unregister_governor(struct cpufreq_governor *governor) { -#ifdef CONFIG_HOTPLUG_CPU int cpu; -#endif if (!governor) return; @@ -1609,14 +2092,12 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor) if (cpufreq_disabled()) return; -#ifdef CONFIG_HOTPLUG_CPU for_each_present_cpu(cpu) { if (cpu_online(cpu)) continue; if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name)) strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0"); } -#endif mutex_lock(&cpufreq_governor_mutex); list_del(&governor->governor_list); @@ -1626,7 +2107,6 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor) EXPORT_SYMBOL_GPL(cpufreq_unregister_governor); - /********************************************************************* * POLICY INTERFACE * *********************************************************************/ @@ -1648,100 +2128,107 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu) 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; + struct cpufreq_governor *old_gov; + int ret; - 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) { - ret = -EINVAL; - goto error_out; - } + if (new_policy->min > policy->max || new_policy->max < policy->min) + return -EINVAL; /* 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; + return ret; /* 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; + return ret; /* 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); - } else { - if (policy->governor != data->governor) { - /* save old, working values */ - struct cpufreq_governor *old_gov = data->governor; - - pr_debug("governor switch\n"); - - /* end old governor */ - if (data->governor) - __cpufreq_governor(data, CPUFREQ_GOV_STOP); - - /* start new governor */ - data->governor = policy->governor; - if (__cpufreq_governor(data, CPUFREQ_GOV_START)) { - /* new governor failed, so re-start old one */ - pr_debug("starting governor %s failed\n", - data->governor->name); - if (old_gov) { - data->governor = old_gov; - __cpufreq_governor(data, - CPUFREQ_GOV_START); - } - ret = -EINVAL; - goto error_out; - } - /* might be a policy change, too, so fall through */ - } - pr_debug("governor: change or update limits\n"); - __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + return cpufreq_driver->setpolicy(new_policy); } -error_out: - return ret; + if (new_policy->governor == policy->governor) + goto out; + + pr_debug("governor switch\n"); + + /* save old, working values */ + old_gov = policy->governor; + /* end old governor */ + if (old_gov) { + __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + up_write(&policy->rwsem); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); + down_write(&policy->rwsem); + } + + /* start new governor */ + policy->governor = new_policy->governor; + if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) { + if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) + goto out; + + up_write(&policy->rwsem); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); + down_write(&policy->rwsem); + } + + /* new governor failed, so re-start old one */ + pr_debug("starting governor %s failed\n", policy->governor->name); + if (old_gov) { + policy->governor = old_gov; + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT); + __cpufreq_governor(policy, CPUFREQ_GOV_START); + } + + return -EINVAL; + + out: + pr_debug("governor: change or update limits\n"); + return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); } /** @@ -1753,53 +2240,54 @@ error_out: */ 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) { - ret = -ENODEV; - goto no_policy; - } + if (!policy) + return -ENODEV; - 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; - - /* 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) { - pr_debug("Driver did not initialize current freq"); - data->cur = policy.cur; + 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 && !cpufreq_driver->setpolicy) { + new_policy.cur = cpufreq_driver->get(cpu); + if (WARN_ON(!new_policy.cur)) { + ret = -EIO; + goto unlock; + } + + if (!policy->cur) { + pr_debug("Driver did not initialize current freq\n"); + policy->cur = new_policy.cur; } else { - if (data->cur != policy.cur) - 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); +unlock: + up_write(&policy->rwsem); -fail: - cpufreq_cpu_put(data); -no_policy: + cpufreq_cpu_put(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; @@ -1807,21 +2295,21 @@ static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb, dev = get_cpu_device(cpu); if (dev) { - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpufreq_add_dev(dev, NULL); + __cpufreq_add_dev(dev, NULL); break; + case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - if (unlikely(lock_policy_rwsem_write(cpu))) - BUG(); + __cpufreq_remove_dev_prepare(dev, NULL); + break; - __cpufreq_remove_dev(dev, NULL); + case CPU_POST_DEAD: + __cpufreq_remove_dev_finish(dev, NULL); break; + case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - cpufreq_add_dev(dev, NULL); + __cpufreq_add_dev(dev, NULL); break; } } @@ -1829,10 +2317,77 @@ static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb, } 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 * *********************************************************************/ @@ -1841,7 +2396,7 @@ static struct notifier_block __refdata cpufreq_cpu_notifier = { * @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). * @@ -1855,7 +2410,11 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) 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) || + (driver_data->setpolicy && (driver_data->target_index || + driver_data->target)) || + (!!driver_data->get_intermediate != !!driver_data->target_intermediate)) return -EINVAL; pr_debug("trying to register driver %s\n", driver_data->name); @@ -1863,17 +2422,33 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (driver_data->setpolicy) driver_data->flags |= CPUFREQ_CONST_LOOPS; - spin_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); if (cpufreq_driver) { - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - return -EBUSY; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + return -EEXIST; } cpufreq_driver = driver_data; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + 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; @@ -1889,7 +2464,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) /* if all ->init() calls failed, unregister */ if (ret) { pr_debug("no CPU initialized for driver %s\n", - driver_data->name); + driver_data->name); goto err_if_unreg; } } @@ -1900,19 +2475,21 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) 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: - spin_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver = NULL; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + write_unlock_irqrestore(&cpufreq_driver_lock, flags); return ret; } 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. @@ -1927,11 +2504,18 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) 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); - spin_lock_irqsave(&cpufreq_driver_lock, flags); + down_write(&cpufreq_rwsem); + write_lock_irqsave(&cpufreq_driver_lock, flags); + cpufreq_driver = NULL; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + up_write(&cpufreq_rwsem); return 0; } @@ -1939,19 +2523,11 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); 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); return 0; } |