diff options
Diffstat (limited to 'drivers/cpufreq/cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 1140 | 
1 files changed, 737 insertions, 403 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 04548f7023a..6f024852c6f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -26,7 +26,7 @@  #include <linux/module.h>  #include <linux/mutex.h>  #include <linux/slab.h> -#include <linux/syscore_ops.h> +#include <linux/suspend.h>  #include <linux/tick.h>  #include <trace/events/power.h> @@ -39,57 +39,20 @@ 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); -static DEFINE_MUTEX(cpufreq_governor_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 -/* - * 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(struct rw_semaphore, cpu_policy_rwsem); +/* Flag to suspend/resume CPUFreq governors */ +static bool cpufreq_suspended; -#define lock_policy_rwsem(mode, cpu)					\ -static int lock_policy_rwsem_##mode(int cpu)				\ -{									\ -	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\ -	BUG_ON(!policy);						\ -	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)				\ -{									\ -	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\ -	BUG_ON(!policy);						\ -	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 @@ -135,7 +98,7 @@ static DEFINE_MUTEX(cpufreq_governor_mutex);  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); @@ -183,6 +146,57 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)  }  EXPORT_SYMBOL_GPL(get_cpu_idle_time); +/* + * 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) +{ +	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_generic_init); + +unsigned int cpufreq_generic_get(unsigned int cpu) +{ +	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); + +/* Only for cpufreq core internal use */ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +{ +	return per_cpu(cpufreq_cpu_data, cpu); +} +  struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)  {  	struct cpufreq_policy *policy = NULL; @@ -247,15 +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 @@ -275,7 +288,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,  	freqs->flags = cpufreq_driver->flags;  	pr_debug("notification %u of frequency transition to %u kHz\n", -		state, freqs->new); +		 state, freqs->new);  	switch (state) { @@ -287,9 +300,8 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,  		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;  			}  		} @@ -300,8 +312,8 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,  	case CPUFREQ_POSTCHANGE:  		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs); -		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, -			(unsigned long)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); @@ -319,18 +331,106 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,   * function. It is called twice on all CPU frequency changes that have   * external effects.   */ -void cpufreq_notify_transition(struct cpufreq_policy *policy, +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);  } -EXPORT_SYMBOL_GPL(cpufreq_notify_transition); + +/* 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)  { @@ -363,7 +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); @@ -414,7 +514,7 @@ 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 *policy, +static int cpufreq_set_policy(struct cpufreq_policy *policy,  				struct cpufreq_policy *new_policy);  /** @@ -435,7 +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;					\ @@ -493,11 +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; @@ -525,7 +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;  	} @@ -653,24 +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; +	ssize_t ret;  	if (!down_read_trylock(&cpufreq_rwsem)) -		goto exit; +		return -EINVAL; -	if (lock_policy_rwsem_read(policy->cpu) < 0) -		goto up_read; +	down_read(&policy->rwsem);  	if (fattr->show)  		ret = fattr->show(policy, buf);  	else  		ret = -EIO; -	unlock_policy_rwsem_read(policy->cpu); - -up_read: +	up_read(&policy->rwsem);  	up_read(&cpufreq_rwsem); -exit: +  	return ret;  } @@ -689,17 +782,15 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,  	if (!down_read_trylock(&cpufreq_rwsem))  		goto unlock; -	if (lock_policy_rwsem_write(policy->cpu) < 0) -		goto up_read; +	down_write(&policy->rwsem);  	if (fattr->store)  		ret = fattr->store(policy, buf, count);  	else  		ret = -EIO; -	unlock_policy_rwsem_write(policy->cpu); +	up_write(&policy->rwsem); -up_read:  	up_read(&cpufreq_rwsem);  unlock:  	put_online_cpus(); @@ -815,7 +906,7 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,  		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; @@ -840,18 +931,28 @@ err_out_kobj_put:  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)); -	/* 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; +	/* 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) @@ -861,13 +962,12 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)  #ifdef CONFIG_HOTPLUG_CPU  static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, -				  unsigned int cpu, struct device *dev, -				  bool frozen) +				  unsigned int cpu, struct device *dev)  { -	int ret = 0, has_target = !!cpufreq_driver->target; +	int ret = 0;  	unsigned long flags; -	if (has_target) { +	if (has_target()) {  		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);  		if (ret) {  			pr_err("%s: Failed to stop governor\n", __func__); @@ -875,7 +975,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,  		}  	} -	lock_policy_rwsem_write(policy->cpu); +	down_write(&policy->rwsem);  	write_lock_irqsave(&cpufreq_driver_lock, flags); @@ -883,21 +983,20 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,  	per_cpu(cpufreq_cpu_data, cpu) = policy;  	write_unlock_irqrestore(&cpufreq_driver_lock, flags); -	unlock_policy_rwsem_write(policy->cpu); +	up_write(&policy->rwsem); -	if (has_target) { -		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) || -			(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) { +	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;  		}  	} -	/* Don't touch sysfs links during light-weight init */ -	if (!frozen) -		ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); - -	return ret; +	return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");  }  #endif @@ -912,6 +1011,8 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)  	read_unlock_irqrestore(&cpufreq_driver_lock, flags); +	policy->governor = NULL; +  	return policy;  } @@ -930,6 +1031,10 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)  		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: @@ -940,6 +1045,30 @@ err_free_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); @@ -949,40 +1078,29 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)  static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)  { -	if (cpu == policy->cpu) +	if (WARN_ON(cpu == policy->cpu))  		return; -	/* -	 * Take direct locks as lock_policy_rwsem_write wouldn't work here. -	 * Also lock for last cpu is enough here as contention will happen only -	 * after policy->cpu is changed and after it is changed, other threads -	 * will try to acquire lock for new cpu. And policy is already updated -	 * by then. -	 */ -	down_write(&per_cpu(cpu_policy_rwsem, policy->cpu)); +	down_write(&policy->rwsem);  	policy->last_cpu = policy->cpu;  	policy->cpu = cpu; -	up_write(&per_cpu(cpu_policy_rwsem, policy->last_cpu)); +	up_write(&policy->rwsem); -#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);  } -static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, -			     bool frozen) +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; +	bool recover_policy = cpufreq_suspended;  #ifdef CONFIG_HOTPLUG_CPU  	struct cpufreq_policy *tpolicy; -	struct cpufreq_governor *gov;  #endif  	if (cpu_is_offline(cpu)) @@ -1009,7 +1127,7 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	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, frozen); +			ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev);  			up_read(&cpufreq_rwsem);  			return ret;  		} @@ -1017,15 +1135,17 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	read_unlock_irqrestore(&cpufreq_driver_lock, flags);  #endif -	if (frozen) -		/* Restore the saved policy when doing light-weight init */ -		policy = cpufreq_policy_restore(cpu); -	else +	/* +	 * 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 (!policy) +			goto nomem_out; +	}  	/*  	 * In the resume path, since we restore a saved policy, the assignment @@ -1033,12 +1153,13 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	 * the creation of a brand new one. So we need to perform this update  	 * by invoking update_policy_cpu().  	 */ -	if (frozen && cpu != policy->cpu) +	if (recover_policy && cpu != policy->cpu) {  		update_policy_cpu(policy, cpu); -	else +		WARN_ON(kobject_move(&policy->kobj, &dev->kobj)); +	} else {  		policy->cpu = cpu; +	} -	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;  	cpumask_copy(policy->cpus, cpumask_of(cpu));  	init_completion(&policy->kobj_unregister); @@ -1062,30 +1183,74 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	 */  	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); -	policy->user_policy.min = policy->min; -	policy->user_policy.max = policy->max; - -	blocking_notifier_call_chain(&cpufreq_policy_notifier_list, -				     CPUFREQ_START, policy); - -#ifdef CONFIG_HOTPLUG_CPU -	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); +	if (!recover_policy) { +		policy->user_policy.min = policy->min; +		policy->user_policy.max = policy->max;  	} -#endif +	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 (!frozen) { +	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); + +	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);  	}  	write_lock_irqsave(&cpufreq_driver_lock, flags); @@ -1094,6 +1259,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	cpufreq_init_policy(policy); +	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);  	up_read(&cpufreq_rwsem); @@ -1102,13 +1273,22 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,  	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); +	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); +  nomem_out:  	up_read(&cpufreq_rwsem); @@ -1126,11 +1306,11 @@ nomem_out:   */  static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)  { -	return __cpufreq_add_dev(dev, sif, false); +	return __cpufreq_add_dev(dev, sif);  }  static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, -					   unsigned int old_cpu, bool frozen) +					   unsigned int old_cpu)  {  	struct device *cpu_dev;  	int ret; @@ -1138,18 +1318,14 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,  	/* first sibling now owns the new sysfs dir */  	cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu)); -	/* Don't touch sysfs files during light-weight tear-down */ -	if (frozen) -		return cpu_dev->id; -  	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); +		pr_err("%s: Failed to move kobj: %d\n", __func__, ret); -		WARN_ON(lock_policy_rwsem_write(old_cpu)); +		down_write(&policy->rwsem);  		cpumask_set_cpu(old_cpu, policy->cpus); -		unlock_policy_rwsem_write(old_cpu); +		up_write(&policy->rwsem);  		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,  					"cpufreq"); @@ -1161,8 +1337,7 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,  }  static int __cpufreq_remove_dev_prepare(struct device *dev, -					struct subsys_interface *sif, -					bool frozen) +					struct subsys_interface *sif)  {  	unsigned int cpu = dev->id, cpus;  	int new_cpu, ret; @@ -1176,7 +1351,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,  	policy = per_cpu(cpufreq_cpu_data, cpu);  	/* Save the policy somewhere when doing a light-weight tear-down */ -	if (frozen) +	if (cpufreq_suspended)  		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;  	write_unlock_irqrestore(&cpufreq_driver_lock, flags); @@ -1186,7 +1361,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,  		return -EINVAL;  	} -	if (cpufreq_driver->target) { +	if (has_target()) {  		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);  		if (ret) {  			pr_err("%s: Failed to stop governor\n", __func__); @@ -1194,45 +1369,39 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,  		}  	} -#ifdef CONFIG_HOTPLUG_CPU  	if (!cpufreq_driver->setpolicy)  		strncpy(per_cpu(cpufreq_cpu_governor, cpu),  			policy->governor->name, CPUFREQ_NAME_LEN); -#endif -	lock_policy_rwsem_read(cpu); +	down_read(&policy->rwsem);  	cpus = cpumask_weight(policy->cpus); -	unlock_policy_rwsem_read(cpu); +	up_read(&policy->rwsem);  	if (cpu != policy->cpu) { -		if (!frozen) -			sysfs_remove_link(&dev->kobj, "cpufreq"); +		sysfs_remove_link(&dev->kobj, "cpufreq");  	} else if (cpus > 1) { - -		new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen); +		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); -			} +			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);  	}  	return 0;  }  static int __cpufreq_remove_dev_finish(struct device *dev, -				       struct subsys_interface *sif, -				       bool frozen) +				       struct subsys_interface *sif)  {  	unsigned int cpu = dev->id, cpus;  	int ret;  	unsigned long flags;  	struct cpufreq_policy *policy; -	struct kobject *kobj; -	struct completion *cmp;  	read_lock_irqsave(&cpufreq_driver_lock, flags);  	policy = per_cpu(cpufreq_cpu_data, cpu); @@ -1243,41 +1412,27 @@ static int __cpufreq_remove_dev_finish(struct device *dev,  		return -EINVAL;  	} -	WARN_ON(lock_policy_rwsem_write(cpu)); +	down_write(&policy->rwsem);  	cpus = cpumask_weight(policy->cpus);  	if (cpus > 1)  		cpumask_clear_cpu(cpu, policy->cpus); -	unlock_policy_rwsem_write(cpu); +	up_write(&policy->rwsem);  	/* If cpu is last user of policy, free policy */  	if (cpus == 1) { -		if (cpufreq_driver->target) { +		if (has_target()) {  			ret = __cpufreq_governor(policy,  					CPUFREQ_GOV_POLICY_EXIT);  			if (ret) {  				pr_err("%s: Failed to exit governor\n", -						__func__); +				       __func__);  				return ret;  			}  		} -		if (!frozen) { -			lock_policy_rwsem_read(cpu); -			kobj = &policy->kobj; -			cmp = &policy->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 (!cpufreq_suspended) +			cpufreq_policy_put_kobj(policy);  		/*  		 * Perform the ->exit() even during light-weight tear-down, @@ -1292,16 +1447,16 @@ static int __cpufreq_remove_dev_finish(struct device *dev,  		list_del(&policy->policy_list);  		write_unlock_irqrestore(&cpufreq_driver_lock, flags); -		if (!frozen) +		if (!cpufreq_suspended)  			cpufreq_policy_free(policy); -	} else { -		if (cpufreq_driver->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; -			} +	} 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;  		}  	} @@ -1310,36 +1465,24 @@ static int __cpufreq_remove_dev_finish(struct device *dev,  }  /** - * __cpufreq_remove_dev - remove a CPU device + * 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 inline int __cpufreq_remove_dev(struct device *dev, -				       struct subsys_interface *sif, -				       bool frozen) -{ -	int ret; - -	ret = __cpufreq_remove_dev_prepare(dev, sif, frozen); - -	if (!ret) -		ret = __cpufreq_remove_dev_finish(dev, sif, frozen); - -	return ret; -} -  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, false); -	return retval; +	ret = __cpufreq_remove_dev_prepare(dev, sif); + +	if (!ret) +		ret = __cpufreq_remove_dev_finish(dev, sif); + +	return ret;  }  static void handle_update(struct work_struct *work) @@ -1368,8 +1511,8 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,  	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.old = old_freq;  	freqs.new = new_freq; @@ -1378,8 +1521,8 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,  	policy = per_cpu(cpufreq_cpu_data, cpu);  	read_unlock_irqrestore(&cpufreq_driver_lock, flags); -	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); -	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); +	cpufreq_freq_transition_begin(policy, &freqs); +	cpufreq_freq_transition_end(policy, &freqs, 0);  }  /** @@ -1458,23 +1601,16 @@ static unsigned int __cpufreq_get(unsigned int cpu)   */  unsigned int cpufreq_get(unsigned int cpu)  { +	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);  	unsigned int ret_freq = 0; -	if (cpufreq_disabled() || !cpufreq_driver) -		return -ENOENT; - -	if (!down_read_trylock(&cpufreq_rwsem)) -		return 0; - -	if (unlikely(lock_policy_rwsem_read(cpu))) -		goto out_policy; - -	ret_freq = __cpufreq_get(cpu); - -	unlock_policy_rwsem_read(cpu); +	if (policy) { +		down_read(&policy->rwsem); +		ret_freq = __cpufreq_get(cpu); +		up_read(&policy->rwsem); -out_policy: -	up_read(&cpufreq_rwsem); +		cpufreq_cpu_put(policy); +	}  	return ret_freq;  } @@ -1487,83 +1623,103 @@ 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; - -	int cpu = smp_processor_id();  	struct cpufreq_policy *policy; -	pr_debug("suspending cpu %u\n", cpu); +	if (!cpufreq_driver) +		return; + +	if (!has_target()) +		return; -	/* If there's no policy for the boot CPU, we have nothing to do. */ -	policy = cpufreq_cpu_get(cpu); -	if (!policy) -		return 0; +	pr_debug("%s: Suspending Governors\n", __func__); -	if (cpufreq_driver->suspend) { -		ret = cpufreq_driver->suspend(policy); -		if (ret) -			printk(KERN_ERR "cpufreq: suspend failed in ->suspend " -					"step on CPU %u\n", 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(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 *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. */ -	policy = cpufreq_cpu_get(cpu); -	if (!policy) +	if (!has_target())  		return; -	if (cpufreq_driver->resume) { -		ret = cpufreq_driver->resume(policy); -		if (ret) { -			printk(KERN_ERR "cpufreq: resume failed in ->resume " -					"step on CPU %u\n", policy->cpu); -			goto fail; -		} -	} +	pr_debug("%s: Resuming Governors\n", __func__); -	schedule_work(&policy->update); +	cpufreq_suspended = false; -fail: -	cpufreq_cpu_put(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); -static struct syscore_ops cpufreq_syscore_ops = { -	.suspend	= cpufreq_bp_suspend, -	.resume		= cpufreq_bp_resume, -}; +		/* +		 * 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); +	} +}  /**   *	cpufreq_get_current_driver - return current driver's name @@ -1662,12 +1818,92 @@ 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)  { -	int retval = -EINVAL;  	unsigned int old_target_freq = target_freq; +	int retval = -EINVAL;  	if (cpufreq_disabled())  		return -ENODEV; @@ -1679,14 +1915,48 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,  		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); +		 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); @@ -1697,14 +1967,12 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,  {  	int ret = -EINVAL; -	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:  	return ret;  }  EXPORT_SYMBOL_GPL(cpufreq_driver_target); @@ -1728,17 +1996,18 @@ 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;  		}  	} @@ -1748,7 +2017,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,  			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) @@ -1815,9 +2084,7 @@ EXPORT_SYMBOL_GPL(cpufreq_register_governor);  void cpufreq_unregister_governor(struct cpufreq_governor *governor)  { -#ifdef CONFIG_HOTPLUG_CPU  	int cpu; -#endif  	if (!governor)  		return; @@ -1825,14 +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); @@ -1871,28 +2136,27 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)  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 *policy, +static int cpufreq_set_policy(struct cpufreq_policy *policy,  				struct cpufreq_policy *new_policy)  { -	int ret = 0, failed = 1; +	struct cpufreq_governor *old_gov; +	int ret; -	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu, -		new_policy->min, new_policy->max); +	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", +		 new_policy->cpu, new_policy->min, new_policy->max);  	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo)); -	if (new_policy->min > policy->max || new_policy->max < policy->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(new_policy);  	if (ret) -		goto error_out; +		return ret;  	/* adjust if necessary - all reasons */  	blocking_notifier_call_chain(&cpufreq_policy_notifier_list, @@ -1908,7 +2172,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *policy,  	 */  	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, @@ -1918,63 +2182,53 @@ static int __cpufreq_set_policy(struct cpufreq_policy *policy,  	policy->max = new_policy->max;  	pr_debug("new min and max freqs are %u - %u kHz\n", -					policy->min, policy->max); +		 policy->min, policy->max);  	if (cpufreq_driver->setpolicy) {  		policy->policy = new_policy->policy;  		pr_debug("setting range\n"); -		ret = cpufreq_driver->setpolicy(new_policy); -	} else { -		if (new_policy->governor != policy->governor) { -			/* save old, working values */ -			struct cpufreq_governor *old_gov = policy->governor; - -			pr_debug("governor switch\n"); - -			/* end old governor */ -			if (policy->governor) { -				__cpufreq_governor(policy, CPUFREQ_GOV_STOP); -				unlock_policy_rwsem_write(new_policy->cpu); -				__cpufreq_governor(policy, -						CPUFREQ_GOV_POLICY_EXIT); -				lock_policy_rwsem_write(new_policy->cpu); -			} +		return cpufreq_driver->setpolicy(new_policy); +	} -			/* start new governor */ -			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(new_policy->cpu); -					__cpufreq_governor(policy, -							CPUFREQ_GOV_POLICY_EXIT); -					lock_policy_rwsem_write(new_policy->cpu); -				} -			} +	if (new_policy->governor == policy->governor) +		goto out; -			if (failed) { -				/* 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); -				} -				ret = -EINVAL; -				goto error_out; -			} -			/* might be a policy change, too, so fall through */ -		} -		pr_debug("governor: change or update limits\n"); -		ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); +	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);  	} -error_out: -	return ret; +	/* 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);  }  /** @@ -1990,15 +2244,10 @@ int cpufreq_update_policy(unsigned int cpu)  	struct cpufreq_policy new_policy;  	int ret; -	if (!policy) { -		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(&new_policy, policy, sizeof(*policy)); @@ -2011,25 +2260,29 @@ int cpufreq_update_policy(unsigned int cpu)  	 * BIOS might change freq behind our back  	 * -> ask driver for current freq and notify governors about a change  	 */ -	if (cpufreq_driver->get) { +	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"); +			pr_debug("Driver did not initialize current freq\n");  			policy->cur = new_policy.cur;  		} else { -			if (policy->cur != new_policy.cur && cpufreq_driver->target) +			if (policy->cur != new_policy.cur && has_target())  				cpufreq_out_of_sync(cpu, policy->cur,  								new_policy.cur);  		}  	} -	ret = __cpufreq_set_policy(policy, &new_policy); +	ret = cpufreq_set_policy(policy, &new_policy); -	unlock_policy_rwsem_write(cpu); +unlock: +	up_write(&policy->rwsem); -fail:  	cpufreq_cpu_put(policy); -no_policy:  	return ret;  }  EXPORT_SYMBOL(cpufreq_update_policy); @@ -2039,30 +2292,24 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,  {  	unsigned int cpu = (unsigned long)hcpu;  	struct device *dev; -	bool frozen = false;  	dev = get_cpu_device(cpu);  	if (dev) { - -		if (action & CPU_TASKS_FROZEN) -			frozen = true; -  		switch (action & ~CPU_TASKS_FROZEN) {  		case CPU_ONLINE: -			__cpufreq_add_dev(dev, NULL, frozen); -			cpufreq_update_policy(cpu); +			__cpufreq_add_dev(dev, NULL);  			break;  		case CPU_DOWN_PREPARE: -			__cpufreq_remove_dev_prepare(dev, NULL, frozen); +			__cpufreq_remove_dev_prepare(dev, NULL);  			break;  		case CPU_POST_DEAD: -			__cpufreq_remove_dev_finish(dev, NULL, frozen); +			__cpufreq_remove_dev_finish(dev, NULL);  			break;  		case CPU_DOWN_FAILED: -			__cpufreq_add_dev(dev, NULL, frozen); +			__cpufreq_add_dev(dev, NULL);  			break;  		}  	} @@ -2074,6 +2321,73 @@ static struct notifier_block __refdata cpufreq_cpu_notifier = {  };  /********************************************************************* + *               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                *   *********************************************************************/ @@ -2096,7 +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); @@ -2112,9 +2430,25 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)  	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; @@ -2130,7 +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;  		}  	} @@ -2141,6 +2475,9 @@ 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:  	write_lock_irqsave(&cpufreq_driver_lock, flags);  	cpufreq_driver = NULL; @@ -2167,6 +2504,9 @@ 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);  	down_write(&cpufreq_rwsem); @@ -2183,17 +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) -		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu)); -  	cpufreq_global_kobject = kobject_create();  	BUG_ON(!cpufreq_global_kobject); -	register_syscore_ops(&cpufreq_syscore_ops);  	return 0;  }  | 
