cpufreq.c

/*
 *  linux/drivers/cpufreq/cpufreq.c
 *
 *  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
 *  Feb 2006 - Jacob Shin <jacob.shin@amd.com>
 *	Fix handling for CPU hotplug -- affected CPUs
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/tick.h>
#include <trace/events/power.h>

static LIST_HEAD(cpufreq_policy_list);

static inline bool policy_is_inactive(struct cpufreq_policy *policy)
{
	return cpumask_empty(policy->cpus);
}

static bool suitable_policy(struct cpufreq_policy *policy, bool active)
{
	return active == !policy_is_inactive(policy);
}

/* Finds Next Acive/Inactive policy */
static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
					  bool active)
{
	do {
		/* No more policies in the list */
		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
			return NULL;

		policy = list_next_entry(policy, policy_list);
	} while (!suitable_policy(policy, active));

	return policy;
}

static struct cpufreq_policy *first_policy(bool active)
{
	struct cpufreq_policy *policy;

	/* No policies in the list */
	if (list_empty(&cpufreq_policy_list))
		return NULL;

	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
				  policy_list);

	if (!suitable_policy(policy, active))
		policy = next_policy(policy, active);

	return policy;
}

/* Macros to iterate over CPU policies */
#define for_each_suitable_policy(__policy, __active)	\
	for (__policy = first_policy(__active);		\
	     __policy;					\
	     __policy = next_policy(__policy, __active))

#define for_each_active_policy(__policy)		\
	for_each_suitable_policy(__policy, true)
#define for_each_inactive_policy(__policy)		\
	for_each_suitable_policy(__policy, false)

#define for_each_policy(__policy)			\
	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)

/* Iterate over governors */
static LIST_HEAD(cpufreq_governor_list);
#define for_each_governor(__governor)				\
	list_for_each_entry(__governor, &cpufreq_governor_list, governor_list)

/**
 * The "cpufreq driver" - the arch- or hardware-dependent low
 * level driver of CPUFreq support, and its spinlock. This lock
 * also protects the cpufreq_cpu_data array.
 */
static struct cpufreq_driver *cpufreq_driver;
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
static DEFINE_RWLOCK(cpufreq_driver_lock);

static DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);

/**
 * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer.
 * @cpu: The CPU to set the pointer for.
 * @data: New pointer value.
 *
 * Set and publish the update_util_data pointer for the given CPU.  That pointer
 * points to a struct update_util_data object containing a callback function
 * to call from cpufreq_update_util().  That function will be called from an RCU
 * read-side critical section, so it must not sleep.
 *
 * Callers must use RCU callbacks to free any memory that might be accessed
 * via the old update_util_data pointer or invoke synchronize_rcu() right after
 * this function to avoid use-after-free.
 */
void cpufreq_set_update_util_data(int cpu, struct update_util_data *data)
{
	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
}
EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data);

/**
 * cpufreq_update_util - Take a note about CPU utilization changes.
 * @time: Current time.
 * @util: Current utilization.
 * @max: Utilization ceiling.
 *
 * This function is called by the scheduler on every invocation of
 * update_load_avg() on the CPU whose utilization is being updated.
 */
void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
{
	struct update_util_data *data;

	rcu_read_lock();

	data = rcu_dereference(*this_cpu_ptr(&cpufreq_update_util_data));
	if (data && data->func)
		data->func(data, time, util, max);

	rcu_read_unlock();
}

/* Flag to suspend/resume CPUFreq governors */
static bool cpufreq_suspended;

static inline bool has_target(void)
{
	return cpufreq_driver->target_index || cpufreq_driver->target;
}

/* internal prototypes */
static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
static unsigned int __cpufreq_get(struct cpufreq_policy *policy);

/**
 * Two notifier lists: the "policy" list is involved in the
 * validation process for a new CPU frequency policy; the
 * "transition" list for kernel code that needs to handle
 * changes to devices when the CPU clock speed changes.
 * The mutex locks both lists.
 */
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
static struct srcu_notifier_head cpufreq_transition_notifier_list;

static bool init_cpufreq_transition_notifier_list_called;
static int __init init_cpufreq_transition_notifier_list(void)
{
	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
	init_cpufreq_transition_notifier_list_called = true;
	return 0;
}
pure_initcall(init_cpufreq_transition_notifier_list);

static int off __read_mostly;
static int cpufreq_disabled(void)
{
	return off;
}
void disable_cpufreq(void)
{
	off = 1;
}
static DEFINE_MUTEX(cpufreq_governor_mutex);

bool have_governor_per_policy(void)
{
	return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY);
}
EXPORT_SYMBOL_GPL(have_governor_per_policy);

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);

struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
{
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);

	return policy && !policy_is_inactive(policy) ?
		policy->freq_table : NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);

static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
{
	u64 idle_time;
	u64 cur_wall_time;
	u64 busy_time;

	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];

	idle_time = cur_wall_time - busy_time;
	if (wall)
		*wall = cputime_to_usecs(cur_wall_time);

	return cputime_to_usecs(idle_time);
}

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);

	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);

	return idle_time;
}
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 configuration where all processors
	 * share the clock and voltage and clock.
	 */
	cpumask_setall(policy->cpus);

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_generic_init);

struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
{
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);

	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get_raw);

unsigned int cpufreq_generic_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(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);

/**
 * cpufreq_cpu_get: returns policy for a cpu and marks it busy.
 *
 * @cpu: cpu to find policy for.
 *
 * This returns policy for 'cpu', returns NULL if it doesn't exist.
 * It also increments the kobject reference count to mark it busy and so would
 * require a corresponding call to cpufreq_cpu_put() to decrement it back.
 * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
 * freed as that depends on the kobj count.
 *
 * Return: A valid policy on success, otherwise NULL on failure.
 */
struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = NULL;
	unsigned long flags;

	if (WARN_ON(cpu >= nr_cpu_ids))
		return NULL;

	/* get the cpufreq driver */
	read_lock_irqsave(&cpufreq_driver_lock, flags);

	if (cpufreq_driver) {
		/* get the CPU */
		policy = cpufreq_cpu_get_raw(cpu);
		if (policy)
			kobject_get(&policy->kobj);
	}

	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	return policy;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get);

/**
 * cpufreq_cpu_put: Decrements the usage count of a policy
 *
 * @policy: policy earlier returned by cpufreq_cpu_get().
 *
 * This decrements the kobject reference count incremented earlier by calling
 * cpufreq_cpu_get().
 */
void cpufreq_cpu_put(struct cpufreq_policy *policy)
{
	kobject_put(&policy->kobj);
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_put);

/*********************************************************************
 *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
 *********************************************************************/

/**
 * adjust_jiffies - adjust the system "loops_per_jiffy"
 *
 * This function alters the system "loops_per_jiffy" for the clock
 * speed change. Note that loops_per_jiffy cannot be updated on SMP
 * systems as each CPU might be scaled differently. So, use the arch
 * per-CPU loops_per_jiffy value wherever possible.
 */
static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
#ifndef CONFIG_SMP
	static unsigned long l_p_j_ref;
	static unsigned int l_p_j_ref_freq;

	if (ci->flags & CPUFREQ_CONST_LOOPS)
		return;

	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);
	}
	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);
	}
#endif
}

static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, unsigned int state)
{
	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);

	switch (state) {

	case CPUFREQ_PRECHANGE:
		/* detect if the driver reported a value as "old frequency"
		 * which is not equal to what the cpufreq core thinks is
		 * "old frequency".
		 */
		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);
				freqs->old = policy->cur;
			}
		}
		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
				CPUFREQ_PRECHANGE, freqs);
		adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
		break;

	case CPUFREQ_POSTCHANGE:
		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
		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);
		if (likely(policy) && likely(policy->cpu == freqs->cpu))
			policy->cur = freqs->new;
		break;
	}
}

/**
 * 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)
{
	struct cpufreq_governor *t;

	for_each_governor(t)
		if (!strncasecmp(str_governor, t->name, CPUFREQ_NAME_LEN))
			return t;

	return NULL;
}

/**
 * cpufreq_parse_governor - parse a governor string
 */
static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
				struct cpufreq_governor **governor)
{
	int err = -EINVAL;

	if (cpufreq_driver->setpolicy) {
		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_PERFORMANCE;
			err = 0;
		} else if (!strncasecmp(str_governor, "powersave",
						CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_POWERSAVE;
			err = 0;
		}
	} else {
		struct cpufreq_governor *t;

		mutex_lock(&cpufreq_governor_mutex);

		t = find_governor(str_governor);

		if (t == NULL) {
			int ret;

			mutex_unlock(&cpufreq_governor_mutex);
			ret = request_module("cpufreq_%s", str_governor);
			mutex_lock(&cpufreq_governor_mutex);

			if (ret == 0)
				t = find_governor(str_governor);
		}

		if (t != NULL) {
			*governor = t;
			err = 0;
		}

		mutex_unlock(&cpufreq_governor_mutex);
	}
	return err;
}

/**
 * cpufreq_per_cpu_attr_read() / show_##file_name() -
 * print out cpufreq information
 *
 * Write out information from cpufreq_driver->policy[cpu]; object must be
 * "unsigned int".
 */

#define show_one(file_name, object)			\
static ssize_t show_##file_name				\
(struct cpufreq_policy *policy, char *buf)		\
{							\
	return sprintf(buf, "%u\n", policy->object);	\
}

show_one(cpuinfo_min_freq, cpuinfo.min_freq);
show_one(cpuinfo_max_freq, cpuinfo.max_freq);
show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
show_one(scaling_min_freq, min);
show_one(scaling_max_freq, max);

static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
{
	ssize_t ret;

	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
	else
		ret = sprintf(buf, "%u\n", policy->cur);
	return ret;
}

static int cpufreq_set_policy(struct cpufreq_policy *policy,
				struct cpufreq_policy *new_policy);

/**
 * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
 */
#define store_one(file_name, object)			\
static ssize_t store_##file_name					\
(struct cpufreq_policy *policy, const char *buf, size_t count)		\
{									\
	int ret, temp;							\
	struct cpufreq_policy new_policy;				\
									\
	memcpy(&new_policy, policy, sizeof(*policy));			\
									\
	ret = sscanf(buf, "%u", &new_policy.object);			\
	if (ret != 1)							\
		return -EINVAL;						\
									\
	temp = new_policy.object;					\
	ret = cpufreq_set_policy(policy, &new_policy);		\
	if (!ret)							\
		policy->user_policy.object = temp;			\
									\
	return ret ? ret : count;					\
}

store_one(scaling_min_freq, min);
store_one(scaling_max_freq, max);

/**
 * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
 */
static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
					char *buf)
{
	unsigned int cur_freq = __cpufreq_get(policy);
	if (!cur_freq)
		return sprintf(buf, "<unknown>");
	return sprintf(buf, "%u\n", cur_freq);
}

/**
 * show_scaling_governor - show the current policy for the specified CPU
 */
static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
{
	if (policy->policy == CPUFREQ_POLICY_POWERSAVE)
		return sprintf(buf, "powersave\n");
	else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
		return sprintf(buf, "performance\n");
	else if (policy->governor)
		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)
{
	int ret;
	char	str_governor[16];
	struct cpufreq_policy new_policy;

	memcpy(&new_policy, policy, sizeof(*policy));

	ret = sscanf(buf, "%15s", str_governor);
	if (ret != 1)
		return -EINVAL;

	if (cpufreq_parse_governor(str_governor, &new_policy.policy,
						&new_policy.governor))
		return -EINVAL;

	ret = cpufreq_set_policy(policy, &new_policy);
	return ret ? ret : count;
}

/**
 * show_scaling_driver - show the cpufreq driver currently loaded
 */
static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
{
	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
}

/**
 * show_scaling_available_governors - show the available CPUfreq governors
 */
static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
						char *buf)
{
	ssize_t i = 0;
	struct cpufreq_governor *t;

	if (!has_target()) {
		i += sprintf(buf, "performance powersave");
		goto out;
	}

	for_each_governor(t) {
		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
		    - (CPUFREQ_NAME_LEN + 2)))
			goto out;
		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
	}
out:
	i += sprintf(&buf[i], "\n");
	return i;
}

ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf)
{
	ssize_t i = 0;
	unsigned int cpu;

	for_each_cpu(cpu, mask) {
		if (i)
			i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " ");
		i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu);
		if (i >= (PAGE_SIZE - 5))
			break;
	}
	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
 * hw coordination is in use
 */
static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->related_cpus, buf);
}

/**
 * show_affected_cpus - show the CPUs affected by each transition
 */
static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->cpus, buf);
}

static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
					const char *buf, size_t count)
{
	unsigned int freq = 0;
	unsigned int ret;

	if (!policy->governor || !policy->governor->store_setspeed)
		return -EINVAL;

	ret = sscanf(buf, "%u", &freq);
	if (ret != 1)
		return -EINVAL;

	policy->governor->store_setspeed(policy, freq);

	return count;
}

static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
{
	if (!policy->governor || !policy->governor->show_setspeed)
		return sprintf(buf, "<unsupported>\n");

	return policy->governor->show_setspeed(policy, buf);
}

/**
 * show_bios_limit - show the current cpufreq HW/BIOS limitation
 */
static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
{
	unsigned int limit;
	int ret;
	if (cpufreq_driver->bios_limit) {
		ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
		if (!ret)
			return sprintf(buf, "%u\n", limit);
	}
	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
}

cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
cpufreq_freq_attr_ro(cpuinfo_min_freq);
cpufreq_freq_attr_ro(cpuinfo_max_freq);
cpufreq_freq_attr_ro(cpuinfo_transition_latency);
cpufreq_freq_attr_ro(scaling_available_governors);
cpufreq_freq_attr_ro(scaling_driver);
cpufreq_freq_attr_ro(scaling_cur_freq);
cpufreq_freq_attr_ro(bios_limit);
cpufreq_freq_attr_ro(related_cpus);
cpufreq_freq_attr_ro(affected_cpus);
cpufreq_freq_attr_rw(scaling_min_freq);
cpufreq_freq_attr_rw(scaling_max_freq);
cpufreq_freq_attr_rw(scaling_governor);
cpufreq_freq_attr_rw(scaling_setspeed);

static struct attribute *default_attrs[] = {
	&cpuinfo_min_freq.attr,
	&cpuinfo_max_freq.attr,
	&cpuinfo_transition_latency.attr,
	&scaling_min_freq.attr,
	&scaling_max_freq.attr,
	&affected_cpus.attr,
	&related_cpus.attr,
	&scaling_governor.attr,
	&scaling_driver.attr,
	&scaling_available_governors.attr,
	&scaling_setspeed.attr,
	NULL
};

#define to_policy(k) container_of(k, struct cpufreq_policy, kobj)
#define to_attr(a) container_of(a, struct freq_attr, attr)

static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret;

	down_read(&policy->rwsem);

	if (fattr->show)
		ret = fattr->show(policy, buf);
	else
		ret = -EIO;

	up_read(&policy->rwsem);

	return ret;
}

static ssize_t store(struct kobject *kobj, struct attribute *attr,
		     const char *buf, size_t count)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret = -EINVAL;

	get_online_cpus();

	if (!cpu_online(policy->cpu))
		goto unlock;

	down_write(&policy->rwsem);

	if (fattr->store)
		ret = fattr->store(policy, buf, count);
	else
		ret = -EIO;

	up_write(&policy->rwsem);
unlock:
	put_online_cpus();

	return ret;
}

static void cpufreq_sysfs_release(struct kobject *kobj)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	pr_debug("last reference is dropped\n");
	complete(&policy->kobj_unregister);
}

static const struct sysfs_ops sysfs_ops = {
	.show	= show,
	.store	= store,
};

static struct kobj_type ktype_cpufreq = {
	.sysfs_ops	= &sysfs_ops,
	.default_attrs	= default_attrs,
	.release	= cpufreq_sysfs_release,
};

static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
{
	struct device *cpu_dev;

	pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);

	if (!policy)
		return 0;

	cpu_dev = get_cpu_device(cpu);
	if (WARN_ON(!cpu_dev))
		return 0;

	return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
}

static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
{
	struct device *cpu_dev;

	pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);

	cpu_dev = get_cpu_device(cpu);
	if (WARN_ON(!cpu_dev))
		return;

	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
}

/* Add/remove symlinks for all related CPUs */
static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
{
	unsigned int j;
	int ret = 0;

	/* Some related CPUs might not be present (physically hotplugged) */
	for_each_cpu(j, policy->real_cpus) {
		ret = add_cpu_dev_symlink(policy, j);
		if (ret)
			break;
	}

	return ret;
}

static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
{
	unsigned int j;

	/* Some related CPUs might not be present (physically hotplugged) */
	for_each_cpu(j, policy->real_cpus)
		remove_cpu_dev_symlink(policy, j);
}

static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
{
	struct freq_attr **drv_attr;
	int ret = 0;

	/* set up files for this cpu device */
	drv_attr = cpufreq_driver->attr;
	while (drv_attr && *drv_attr) {
		ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
		if (ret)
			return ret;
		drv_attr++;
	}
	if (cpufreq_driver->get) {
		ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
		if (ret)
			return ret;
	}

	ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
	if (ret)
		return ret;

	if (cpufreq_driver->bios_limit) {
		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
		if (ret)
			return ret;
	}

	return cpufreq_add_dev_symlink(policy);