Merge branch 'pm-cpufreq-sched' into pm-cpufreq

14 files changed, 389 insertions, 182 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index aa403aa2b927..5d74826d75be 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -18,7 +18,11 @@ config CPU_FREQ
 
 if CPU_FREQ
 
+config CPU_FREQ_GOV_ATTR_SET
+	bool
+
 config CPU_FREQ_GOV_COMMON
+	select CPU_FREQ_GOV_ATTR_SET
 	select IRQ_WORK
 	bool
 
@@ -103,6 +107,16 @@ config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 	  Be aware that not all cpufreq drivers support the conservative
 	  governor. If unsure have a look at the help section of the
 	  driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+	bool "schedutil"
+	select CPU_FREQ_GOV_SCHEDUTIL
+	select CPU_FREQ_GOV_PERFORMANCE
+	help
+	  Use the 'schedutil' CPUFreq governor by default. If unsure,
+	  have a look at the help section of that governor. The fallback
+	  governor will be 'performance'.
+
 endchoice
 
 config CPU_FREQ_GOV_PERFORMANCE
@@ -184,6 +198,26 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
+config CPU_FREQ_GOV_SCHEDUTIL
+	tristate "'schedutil' cpufreq policy governor"
+	depends on CPU_FREQ
+	select CPU_FREQ_GOV_ATTR_SET
+	select IRQ_WORK
+	help
+	  This governor makes decisions based on the utilization data provided
+	  by the scheduler.  It sets the CPU frequency to be proportional to
+	  the utilization/capacity ratio coming from the scheduler.  If the
+	  utilization is frequency-invariant, the new frequency is also
+	  proportional to the maximum available frequency.  If that is not the
+	  case, it is proportional to the current frequency of the CPU.  The
+	  frequency tipping point is at utilization/capacity equal to 80% in
+	  both cases.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called cpufreq_schedutil.
+
+	  If in doubt, say N.
+
 comment "CPU frequency scaling drivers"
 
 config CPUFREQ_DT
@@ -297,6 +331,7 @@ endif
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
 	depends on OF && COMMON_CLK && (PPC_E500MC || ARM)
+	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
 	  This adds the CPUFreq driver support for Freescale QorIQ SoCs
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 0031069b64c9..14b1f9393b05 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,10 +84,10 @@ config ARM_KIRKWOOD_CPUFREQ
 	  SoCs.
 
 config ARM_MT8173_CPUFREQ
-	bool "Mediatek MT8173 CPUFreq support"
+	tristate "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
 	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
-	depends on !CPU_THERMAL || THERMAL=y
+	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUFreq driver support for Mediatek MT8173 SoC.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 9e63fb1b09f8..6d1186701a9c 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
 obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
 obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 obj-$(CONFIG_CPU_FREQ_GOV_COMMON)		+= cpufreq_governor.o
+obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET)	+= cpufreq_governor_attr_set.o
 
 obj-$(CONFIG_CPUFREQ_DT)		+= cpufreq-dt.o
 
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index fb5712141040..7f38fb55f223 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -458,6 +458,43 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	return result;
 }
 
+unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
+				      unsigned int target_freq)
+{
+	struct acpi_cpufreq_data *data = policy->driver_data;
+	struct acpi_processor_performance *perf;
+	struct cpufreq_frequency_table *entry;
+	unsigned int next_perf_state, next_freq, freq;
+
+	/*
+	 * Find the closest frequency above target_freq.
+	 *
+	 * The table is sorted in the reverse order with respect to the
+	 * frequency and all of the entries are valid (see the initialization).
+	 */
+	entry = data->freq_table;
+	do {
+		entry++;
+		freq = entry->frequency;
+	} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
+	entry--;
+	next_freq = entry->frequency;
+	next_perf_state = entry->driver_data;
+
+	perf = to_perf_data(data);
+	if (perf->state == next_perf_state) {
+		if (unlikely(data->resume))
+			data->resume = 0;
+		else
+			return next_freq;
+	}
+
+	data->cpu_freq_write(&perf->control_register,
+			     perf->states[next_perf_state].control);
+	perf->state = next_perf_state;
+	return next_freq;
+}
+
 static unsigned long
 acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
 {
@@ -821,6 +858,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 */
 	data->resume = 1;
 
+	policy->fast_switch_possible = !acpi_pstate_strict &&
+		!(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY);
+
 	return result;
 
 err_freqfree:
@@ -843,6 +883,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
+		policy->fast_switch_possible = false;
 		policy->driver_data = NULL;
 		acpi_processor_unregister_performance(data->acpi_perf_cpu);
 		free_cpumask_var(data->freqdomain_cpus);
@@ -876,6 +917,7 @@ static struct freq_attr *acpi_cpufreq_attr[] = {
 static struct cpufreq_driver acpi_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= acpi_cpufreq_target,
+	.fast_switch	= acpi_cpufreq_fast_switch,
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b87596b591b3..77d77a4e3b74 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -78,6 +78,11 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
 static int cpufreq_start_governor(struct cpufreq_policy *policy);
 
+static inline int cpufreq_exit_governor(struct cpufreq_policy *policy)
+{
+	return cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+}
+
 /**
  * Two notifier lists: the "policy" list is involved in the
  * validation process for a new CPU frequency policy; the
@@ -429,6 +434,73 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end);
 
+/*
+ * Fast frequency switching status count.  Positive means "enabled", negative
+ * means "disabled" and 0 means "not decided yet".
+ */
+static int cpufreq_fast_switch_count;
+static DEFINE_MUTEX(cpufreq_fast_switch_lock);
+
+static void cpufreq_list_transition_notifiers(void)
+{
+	struct notifier_block *nb;
+
+	pr_info("Registered transition notifiers:\n");
+
+	mutex_lock(&cpufreq_transition_notifier_list.mutex);
+
+	for (nb = cpufreq_transition_notifier_list.head; nb; nb = nb->next)
+		pr_info("%pF\n", nb->notifier_call);
+
+	mutex_unlock(&cpufreq_transition_notifier_list.mutex);
+}
+
+/**
+ * cpufreq_enable_fast_switch - Enable fast frequency switching for policy.
+ * @policy: cpufreq policy to enable fast frequency switching for.
+ *
+ * Try to enable fast frequency switching for @policy.
+ *
+ * The attempt will fail if there is at least one transition notifier registered
+ * at this point, as fast frequency switching is quite fundamentally at odds
+ * with transition notifiers.  Thus if successful, it will make registration of
+ * transition notifiers fail going forward.
+ */
+void cpufreq_enable_fast_switch(struct cpufreq_policy *policy)
+{
+	lockdep_assert_held(&policy->rwsem);
+
+	if (!policy->fast_switch_possible)
+		return;
+
+	mutex_lock(&cpufreq_fast_switch_lock);
+	if (cpufreq_fast_switch_count >= 0) {
+		cpufreq_fast_switch_count++;
+		policy->fast_switch_enabled = true;
+	} else {
+		pr_warn("CPU%u: Fast frequency switching not enabled\n",
+			policy->cpu);
+		cpufreq_list_transition_notifiers();
+	}
+	mutex_unlock(&cpufreq_fast_switch_lock);
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_fast_switch);
+
+/**
+ * cpufreq_disable_fast_switch - Disable fast frequency switching for policy.
+ * @policy: cpufreq policy to disable fast frequency switching for.
+ */
+void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
+{
+	mutex_lock(&cpufreq_fast_switch_lock);
+	if (policy->fast_switch_enabled) {
+		policy->fast_switch_enabled = false;
+		if (!WARN_ON(cpufreq_fast_switch_count <= 0))
+			cpufreq_fast_switch_count--;
+	}
+	mutex_unlock(&cpufreq_fast_switch_lock);
+}
+EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
@@ -1319,7 +1391,7 @@ static void cpufreq_offline(unsigned int cpu)
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_exit_governor(policy);
 		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
 	}
@@ -1447,8 +1519,12 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
 
-	/* Updating inactive policies is invalid, so avoid doing that. */
-	if (unlikely(policy_is_inactive(policy)))
+	/*
+	 * Updating inactive policies is invalid, so avoid doing that.  Also
+	 * if fast frequency switching is used with the given policy, the check
+	 * against policy->cur is pointless, so skip it in that case too.
+	 */
+	if (unlikely(policy_is_inactive(policy)) || policy->fast_switch_enabled)
 		return ret_freq;
 
 	if (ret_freq && policy->cur &&
@@ -1672,8 +1748,18 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
+		mutex_lock(&cpufreq_fast_switch_lock);
+
+		if (cpufreq_fast_switch_count > 0) {
+			mutex_unlock(&cpufreq_fast_switch_lock);
+			return -EBUSY;
+		}
 		ret = srcu_notifier_chain_register(
 				&cpufreq_transition_notifier_list, nb);
+		if (!ret)
+			cpufreq_fast_switch_count--;
+
+		mutex_unlock(&cpufreq_fast_switch_lock);
 		break;
 	case CPUFREQ_POLICY_NOTIFIER:
 		ret = blocking_notifier_chain_register(
@@ -1706,8 +1792,14 @@ int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
 
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
+		mutex_lock(&cpufreq_fast_switch_lock);
+
 		ret = srcu_notifier_chain_unregister(
 				&cpufreq_transition_notifier_list, nb);
+		if (!ret && !WARN_ON(cpufreq_fast_switch_count >= 0))
+			cpufreq_fast_switch_count++;
+
+		mutex_unlock(&cpufreq_fast_switch_lock);
 		break;
 	case CPUFREQ_POLICY_NOTIFIER:
 		ret = blocking_notifier_chain_unregister(
@@ -1726,6 +1818,37 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
  *                              GOVERNORS                            *
  *********************************************************************/
 
+/**
+ * cpufreq_driver_fast_switch - Carry out a fast CPU frequency switch.
+ * @policy: cpufreq policy to switch the frequency for.
+ * @target_freq: New frequency to set (may be approximate).
+ *
+ * Carry out a fast frequency switch without sleeping.
+ *
+ * The driver's ->fast_switch() callback invoked by this function must be
+ * suitable for being called from within RCU-sched read-side critical sections
+ * and it is expected to select the minimum available frequency greater than or
+ * equal to @target_freq (CPUFREQ_RELATION_L).
+ *
+ * This function must not be called if policy->fast_switch_enabled is unset.
+ *
+ * Governors calling this function must guarantee that it will never be invoked
+ * twice in parallel for the same policy and that it will never be called in
+ * parallel with either ->target() or ->target_index() for the same policy.
+ *
+ * If CPUFREQ_ENTRY_INVALID is returned by the driver's ->fast_switch()
+ * callback to indicate an error condition, the hardware configuration must be
+ * preserved.
+ */
+unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
+					unsigned int target_freq)
+{
+	clamp_val(target_freq, policy->min, policy->max);
+
+	return cpufreq_driver->fast_switch(policy, target_freq);
+}
+EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
+
 /* Must set freqs->new to intermediate frequency */
 static int __target_intermediate(struct cpufreq_policy *policy,
 				 struct cpufreq_freqs *freqs, int index)
@@ -2101,7 +2224,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			return ret;
 		}
 
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_exit_governor(policy);
 		if (ret) {
 			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
 			       __func__, old_gov->name, ret);
@@ -2118,7 +2241,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			pr_debug("cpufreq: governor change\n");
 			return 0;
 		}
-		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		cpufreq_exit_governor(policy);
 	}
 
 	/* new governor failed, so re-start old one */
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index bf4913f6453b..316df247e00d 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -129,9 +129,10 @@ static struct notifier_block cs_cpufreq_notifier_block = {
 /************************** sysfs interface ************************/
 static struct dbs_governor cs_dbs_gov;
 
-static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
+					  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -143,9 +144,10 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_up_threshold(struct gov_attr_set *attr_set,
+				  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
@@ -158,9 +160,10 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_down_threshold(struct gov_attr_set *attr_set,
+				    const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
@@ -175,9 +178,10 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_ignore_nice_load(struct gov_attr_set *attr_set,
+				      const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -199,9 +203,10 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_freq_step(struct gov_attr_set *attr_set, const char *buf,
+			       size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 10a5cfeae8c5..20f0a4e114d1 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -43,9 +43,10 @@ static DEFINE_MUTEX(gov_dbs_data_mutex);
  * This must be called with dbs_data->mutex held, otherwise traversing
  * policy_dbs_list isn't safe.
  */
-ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
 			    size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct policy_dbs_info *policy_dbs;
 	unsigned int rate;
 	int ret;
@@ -59,7 +60,7 @@ ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
 	 * We are operating under dbs_data->mutex and so the list and its
 	 * entries can't be freed concurrently.
 	 */
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
 		mutex_lock(&policy_dbs->timer_mutex);
 		/*
 		 * On 32-bit architectures this may race with the
@@ -96,7 +97,7 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 {
 	struct policy_dbs_info *policy_dbs;
 
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &dbs_data->attr_set.policy_list, list) {
 		unsigned int j;
 
 		for_each_cpu(j, policy_dbs->policy->cpus) {
@@ -111,54 +112,6 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 }
 EXPORT_SYMBOL_GPL(gov_update_cpu_data);
 
-static inline struct dbs_data *to_dbs_data(struct kobject *kobj)
-{
-	return container_of(kobj, struct dbs_data, kobj);
-}
-
-static inline struct governor_attr *to_gov_attr(struct attribute *attr)
-{
-	return container_of(attr, struct governor_attr, attr);
-}
-
-static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
-			     char *buf)
-{
-	struct dbs_data *dbs_data = to_dbs_data(kobj);
-	struct governor_attr *gattr = to_gov_attr(attr);
-
-	return gattr->show(dbs_data, buf);
-}
-
-static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
-			      const char *buf, size_t count)
-{
-	struct dbs_data *dbs_data = to_dbs_data(kobj);
-	struct governor_attr *gattr = to_gov_attr(attr);
-	int ret = -EBUSY;
-
-	mutex_lock(&dbs_data->mutex);
-
-	if (dbs_data->usage_count)
-		ret = gattr->store(dbs_data, buf, count);
-
-	mutex_unlock(&dbs_data->mutex);
-
-	return ret;
-}
-
-/*
- * Sysfs Ops for accessing governor attributes.
- *
- * All show/store invocations for governor specific sysfs attributes, will first
- * call the below show/store callbacks and the attribute specific callback will
- * be called from within it.
- */
-static const struct sysfs_ops governor_sysfs_ops = {
-	.show	= governor_show,
-	.store	= governor_store,
-};
-
 unsigned int dbs_update(struct cpufreq_policy *policy)
 {
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -258,43 +211,6 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(dbs_update);
 
-static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
-				unsigned int delay_us)
-{
-	struct cpufreq_policy *policy = policy_dbs->policy;
-	int cpu;
-
-	gov_update_sample_delay(policy_dbs, delay_us);
-	policy_dbs->last_sample_time = 0;
-
-	for_each_cpu(cpu, policy->cpus) {
-		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
-
-		cpufreq_set_update_util_data(cpu, &cdbs->update_util);
-	}
-}
-
-static inline void gov_clear_update_util(struct cpufreq_policy *policy)
-{
-	int i;
-
-	for_each_cpu(i, policy->cpus)
-		cpufreq_set_update_util_data(i, NULL);
-
-	synchronize_sched();
-}
-
-static void gov_cancel_work(struct cpufreq_policy *policy)
-{
-	struct policy_dbs_info *policy_dbs = policy->governor_data;
-
-	gov_clear_update_util(policy_dbs->policy);
-	irq_work_sync(&policy_dbs->irq_work);
-	cancel_work_sync(&policy_dbs->work);
-	atomic_set(&policy_dbs->work_count, 0);
-	policy_dbs->work_in_progress = false;
-}
-
 static void dbs_work_handler(struct work_struct *work)
 {
 	struct policy_dbs_info *policy_dbs;
@@ -382,6 +298,44 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time,
 	irq_work_queue(&policy_dbs->irq_work);
 }
 
+static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
+				unsigned int delay_us)
+{
+	struct cpufreq_policy *policy = policy_dbs->policy;
+	int cpu;
+
+	gov_update_sample_delay(policy_dbs, delay_us);
+	policy_dbs->last_sample_time = 0;
+
+	for_each_cpu(cpu, policy->cpus) {
+		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
+
+		cpufreq_add_update_util_hook(cpu, &cdbs->update_util,
+					     dbs_update_util_handler);
+	}
+}
+
+static inline void gov_clear_update_util(struct cpufreq_policy *policy)
+{
+	int i;
+
+	for_each_cpu(i, policy->cpus)
+		cpufreq_remove_update_util_hook(i);
+
+	synchronize_sched();
+}
+
+static void gov_cancel_work(struct cpufreq_policy *policy)
+{
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
+}
+
 static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
 						     struct dbs_governor *gov)
 {
@@ -404,7 +358,6 @@ static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *poli
 		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
 		j_cdbs->policy_dbs = policy_dbs;
-		j_cdbs->update_util.func = dbs_update_util_handler;
 	}
 	return policy_dbs;
 }
@@ -453,10 +406,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		policy_dbs->dbs_data = dbs_data;
 		policy->governor_data = policy_dbs;
 
-		mutex_lock(&dbs_data->mutex);
-		dbs_data->usage_count++;
-		list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
-		mutex_unlock(&dbs_data->mutex);
+		gov_attr_set_get(&dbs_data->attr_set, &policy_dbs->list);
 		goto out;
 	}
 
@@ -466,8 +416,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		goto free_policy_dbs_info;
 	}
 
-	INIT_LIST_HEAD(&dbs_data->policy_dbs_list);
-	mutex_init(&dbs_data->mutex);
+	gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list);
 
 	ret = gov->init(dbs_data, !policy->governor->initialized);
 	if (ret)
@@ -487,14 +436,11 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 	if (!have_governor_per_policy())
 		gov->gdbs_data = dbs_data;
 
-	policy->governor_data = policy_dbs;
-
 	policy_dbs->dbs_data = dbs_data;
-	dbs_data->usage_count = 1;
-	list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
+	policy->governor_data = policy_dbs;
 
 	gov->kobj_type.sysfs_ops = &governor_sysfs_ops;
-	ret = kobject_init_and_add(&dbs_data->kobj, &gov->kobj_type,
+	ret = kobject_init_and_add(&dbs_data->attr_set.kobj, &gov->kobj_type,
 				   get_governor_parent_kobj(policy),
 				   "%s", gov->gov.name);
 	if (!ret)
@@ -523,29 +469,21 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct dbs_data *dbs_data = policy_dbs->dbs_data;
-	int count;
+	unsigned int count;
 
 	/* Protect gov->gdbs_data against concurrent updates. */
 	mutex_lock(&gov_dbs_data_mutex);
 
-	mutex_lock(&dbs_data->mutex);
-	list_del(&policy_dbs->list);
-	count = --dbs_data->usage_count;
-	mutex_unlock(&dbs_data->mutex);
-
-	if (!count) {
-		kobject_put(&dbs_data->kobj);
+	count = gov_attr_set_put(&dbs_data->attr_set, &policy_dbs->list);
 
-		policy->governor_data = NULL;
+	policy->governor_data = NULL;
 
+	if (!count) {
 		if (!have_governor_per_policy())
 			gov->gdbs_data = NULL;
 
 		gov->exit(dbs_data, policy->governor->initialized == 1);
-		mutex_destroy(&dbs_data->mutex);
 		kfree(dbs_data);
-	} else {
-		policy->governor_data = NULL;
 	}
 
 	free_policy_dbs_info(policy_dbs, gov);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 61ff82fe0613..3e0eb7c54903 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -24,20 +24,6 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 
-/*
- * The polling frequency depends on the capability of the processor. Default
- * polling frequency is 1000 times the transition latency of the processor. The
- * governor will work on any processor with transition latency <= 10ms, using
- * appropriate sampling rate.
- *
- * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work. All times here are in us (micro seconds).
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(20)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
 /* Ondemand Sampling types */
 enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
@@ -52,7 +38,7 @@ enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
 /* Governor demand based switching data (per-policy or global). */
 struct dbs_data {
-	int usage_count;
+	struct gov_attr_set attr_set;
 	void *tuners;
 	unsigned int min_sampling_rate;
 	unsigned int ignore_nice_load;
@@ -60,37 +46,27 @@ struct dbs_data {
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
 	unsigned int io_is_busy;
-
-	struct kobject kobj;
-	struct list_head policy_dbs_list;
-	/*
-	 * Protect concurrent updates to governor tunables from sysfs,
-	 * policy_dbs_list and usage_count.
-	 */
-	struct mutex mutex;
 };
 
-/* Governor's specific attributes */
-struct dbs_data;
-struct governor_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
-	ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
-			 size_t count);
-};
+static inline struct dbs_data *to_dbs_data(struct gov_attr_set *attr_set)
+{
+	return container_of(attr_set, struct dbs_data, attr_set);
+}
 
 #define gov_show_one(_gov, file_name)					\
 static ssize_t show_##file_name						\
-(struct dbs_data *dbs_data, char *buf)					\
+(struct gov_attr_set *attr_set, char *buf)				\
 {									\
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);		\
 	struct _gov##_dbs_tuners *tuners = dbs_data->tuners;		\
 	return sprintf(buf, "%u\n", tuners->file_name);			\
 }
 
 #define gov_show_one_common(file_name)					\
 static ssize_t show_##file_name						\
-(struct dbs_data *dbs_data, char *buf)					\
+(struct gov_attr_set *attr_set, char *buf)				\
 {									\
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);		\
 	return sprintf(buf, "%u\n", dbs_data->file_name);		\
 }
 
@@ -184,7 +160,7 @@ void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
 void od_unregister_powersave_bias_handler(void);
-ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
 			    size_t count);
 void gov_update_cpu_data(struct dbs_data *dbs_data);
 #endif /* _CPUFREQ_GOVERNOR_H */
diff --git a/drivers/cpufreq/cpufreq_governor_attr_set.c b/drivers/cpufreq/cpufreq_governor_attr_set.c
new file mode 100644
index 000000000000..52841f807a7e
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor_attr_set.c
@@ -0,0 +1,84 @@
+/*
+ * Abstract code for CPUFreq governor tunable sysfs attributes.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * 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 "cpufreq_governor.h"
+
+static inline struct gov_attr_set *to_gov_attr_set(struct kobject *kobj)
+{
+	return container_of(kobj, struct gov_attr_set, kobj);
+}
+
+static inline struct governor_attr *to_gov_attr(struct attribute *attr)
+{
+	return container_of(attr, struct governor_attr, attr);
+}
+
+static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct governor_attr *gattr = to_gov_attr(attr);
+
+	return gattr->show(to_gov_attr_set(kobj), buf);
+}
+
+static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct gov_attr_set *attr_set = to_gov_attr_set(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+	int ret;
+
+	mutex_lock(&attr_set->update_lock);
+	ret = attr_set->usage_count ? gattr->store(attr_set, buf, count) : -EBUSY;
+	mutex_unlock(&attr_set->update_lock);
+	return ret;
+}
+
+const struct sysfs_ops governor_sysfs_ops = {
+	.show	= governor_show,
+	.store	= governor_store,
+};
+EXPORT_SYMBOL_GPL(governor_sysfs_ops);
+
+void gov_attr_set_init(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	INIT_LIST_HEAD(&attr_set->policy_list);
+	mutex_init(&attr_set->update_lock);
+	attr_set->usage_count = 1;
+	list_add(list_node, &attr_set->policy_list);
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_init);
+
+void gov_attr_set_get(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	mutex_lock(&attr_set->update_lock);
+	attr_set->usage_count++;
+	list_add(list_node, &attr_set->policy_list);
+	mutex_unlock(&attr_set->update_lock);
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_get);
+
+unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	unsigned int count;
+
+	mutex_lock(&attr_set->update_lock);
+	list_del(list_node);
+	count = --attr_set->usage_count;
+	mutex_unlock(&attr_set->update_lock);
+	if (count)
+		return count;
+
+	kobject_put(&attr_set->kobj);
+	mutex_destroy(&attr_set->update_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_put);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index acd80272ded6..300163430516 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -207,9 +207,10 @@ static unsigned int od_dbs_timer(struct cpufreq_policy *policy)
 /************************** sysfs interface ************************/
 static struct dbs_governor od_dbs_gov;
 
-static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_io_is_busy(struct gov_attr_set *attr_set, const char *buf,
+				size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -224,9 +225,10 @@ static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_up_threshold(struct gov_attr_set *attr_set,
+				  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -240,9 +242,10 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
+					  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
 	int ret;
@@ -254,7 +257,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	dbs_data->sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
 		/*
 		 * Doing this without locking might lead to using different
 		 * rate_mult values in od_update() and od_dbs_timer().
@@ -267,9 +270,10 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_ignore_nice_load(struct gov_attr_set *attr_set,
+				      const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -291,9 +295,10 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_powersave_bias(struct gov_attr_set *attr_set,
+				    const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
@@ -308,7 +313,7 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 
 	od_tuners->powersave_bias = input;
 
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list)
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list)
 		ondemand_powersave_bias_init(policy_dbs->policy);
 
 	return count;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 8b5a415ee14a..6c7cff13f0ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1242,8 +1242,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	intel_pstate_busy_pid_reset(cpu);
 
-	cpu->update_util.func = intel_pstate_update_util;
-
 	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
 	return 0;
@@ -1267,12 +1265,13 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
-	cpufreq_set_update_util_data(cpu_num, &cpu->update_util);
+	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
+				     intel_pstate_update_util);
 }
 
 static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 {
-	cpufreq_set_update_util_data(cpu, NULL);
+	cpufreq_remove_update_util_hook(cpu);
 	synchronize_sched();
 }
 
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 1efba340456d..2058e6d292ce 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -17,6 +17,7 @@
 #include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index 096377232747..46fee1539cc8 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -319,7 +319,7 @@ static int pxa_set_target(struct cpufreq_policy *policy, unsigned int idx)
 	local_irq_save(flags);
 
 	/* Set new the CCCR and prepare CCLKCFG */
-	CCCR = pxa_freq_settings[idx].cccr;
+	writel(pxa_freq_settings[idx].cccr, CCCR);
 	cclkcfg = pxa_freq_settings[idx].cclkcfg;
 
 	asm volatile("							\n\
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 051a8a8224cd..a145b319d171 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -576,10 +576,8 @@ static struct cpufreq_driver s5pv210_driver = {
 	.get		= cpufreq_generic_get,
 	.init		= s5pv210_cpu_init,
 	.name		= "s5pv210",
-#ifdef CONFIG_PM
 	.suspend	= cpufreq_generic_suspend,
 	.resume		= cpufreq_generic_suspend, /* We need to set SLEEP FREQ again */
-#endif
 };
 
 static struct notifier_block s5pv210_cpufreq_reboot_notifier = {