Merge back earlier 'pm-cpufreq' material

Documentation/cpu-freq/cpu-drivers.txt

@@ -50,8 +50,6 @@ What shall this struct cpufreq_driver contain?
 
 cpufreq_driver.name -		The name of this driver.
 
-cpufreq_driver.owner -		THIS_MODULE;
-
 cpufreq_driver.init -		A pointer to the per-CPU initialization 
 				function.
 

arch/x86/include/asm/processor.h

@@ -942,35 +942,6 @@ extern int set_tsc_mode(unsigned int val);
 
 extern u16 amd_get_nb_id(int cpu);
 
-struct aperfmperf {
-	u64 aperf, mperf;
-};
-
-static inline void get_aperfmperf(struct aperfmperf *am)
-{
-	WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF));
-
-	rdmsrl(MSR_IA32_APERF, am->aperf);
-	rdmsrl(MSR_IA32_MPERF, am->mperf);
-}
-
-#define APERFMPERF_SHIFT 10
-
-static inline
-unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
-				    struct aperfmperf *new)
-{
-	u64 aperf = new->aperf - old->aperf;
-	u64 mperf = new->mperf - old->mperf;
-	unsigned long ratio = aperf;
-
-	mperf >>= APERFMPERF_SHIFT;
-	if (mperf)
-		ratio = div64_u64(aperf, mperf);
-
-	return ratio;
-}
-
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 

drivers/cpufreq/Makefile

@@ -23,7 +23,7 @@ obj-$(CONFIG_GENERIC_CPUFREQ_CPU0)	+= cpufreq-cpu0.o
 # powernow-k8 can load then. ACPI is preferred to all other hardware-specific drivers.
 # speedstep-* is preferred over p4-clockmod.
 
-obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
+obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o

drivers/cpufreq/acpi-cpufreq.c

@@ -45,7 +45,6 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
-#include "mperf.h"
 
 MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
@@ -710,7 +709,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return blacklisted;
 #endif
 
-	data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -800,7 +799,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_unreg;
 	}
 
-	data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
+	data->freq_table = kmalloc(sizeof(*data->freq_table) *
 		    (perf->state_count+1), GFP_KERNEL);
 	if (!data->freq_table) {
 		result = -ENOMEM;
@@ -861,10 +860,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
 
-	/* Check for APERF/MPERF support in hardware */
-	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
-		acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
-
 	pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
 	for (i = 0; i < perf->state_count; i++)
 		pr_debug("     %cP%d: %d MHz, %d mW, %d uS\n",
@@ -941,7 +936,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.exit		= acpi_cpufreq_cpu_exit,
 	.resume		= acpi_cpufreq_resume,
 	.name		= "acpi-cpufreq",
-	.owner		= THIS_MODULE,
 	.attr		= acpi_cpufreq_attr,
 };
 

drivers/cpufreq/at32ap-cpufreq.c

@@ -108,7 +108,6 @@ static int __init at32_cpufreq_driver_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver at32_driver = {
 	.name		= "at32ap",
-	.owner		= THIS_MODULE,
 	.init		= at32_cpufreq_driver_init,
 	.verify		= at32_verify_speed,
 	.target		= at32_set_target,

drivers/cpufreq/blackfin-cpufreq.c

@@ -225,7 +225,6 @@ static struct cpufreq_driver bfin_driver = {
 	.get = bfin_getfreq_khz,
 	.init = __bfin_cpu_init,
 	.name = "bfin cpufreq",
-	.owner = THIS_MODULE,
 	.attr = bfin_freq_attr,
 };
 

drivers/cpufreq/cpufreq-nforce2.c

@@ -379,7 +379,6 @@ static struct cpufreq_driver nforce2_driver = {
 	.get = nforce2_get,
 	.init = nforce2_cpu_init,
 	.exit = nforce2_cpu_exit,
-	.owner = THIS_MODULE,
 };
 
 #ifdef MODULE

drivers/cpufreq/cpufreq.c

@@ -17,24 +17,17 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <asm/cputime.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/notifier.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/tick.h>
 #include <linux/device.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/completion.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/syscore_ops.h>
-
+#include <linux/tick.h>
 #include <trace/events/power.h>
 
 /**
@@ -44,8 +37,10 @@
  */
 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);
+static LIST_HEAD(cpufreq_policy_list);
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* This one keeps track of the previously set governor of a removed CPU */
@@ -96,6 +91,12 @@ static void unlock_policy_rwsem_##mode(int cpu)				\
 unlock_policy_rwsem(read, cpu);
 unlock_policy_rwsem(write, cpu);
 
+/*
+ * rwsem to guarantee that cpufreq driver module doesn't unload during critical
+ * sections
+ */
+static DECLARE_RWSEM(cpufreq_rwsem);
+
 /* internal prototypes */
 static int __cpufreq_governor(struct cpufreq_policy *policy,
 		unsigned int event);
@@ -183,78 +184,46 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs)
+struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
-	struct cpufreq_policy *data;
+	struct cpufreq_policy *policy = NULL;
 	unsigned long flags;
 
-	if (cpu >= nr_cpu_ids)
-		goto err_out;
+	if (cpufreq_disabled() || (cpu >= nr_cpu_ids))
+		return NULL;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return NULL;
 
 	/* get the cpufreq driver */
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
 
-	if (!cpufreq_driver)
-		goto err_out_unlock;
-
-	if (!try_module_get(cpufreq_driver->owner))
-		goto err_out_unlock;
-
-	/* get the CPU */
-	data = per_cpu(cpufreq_cpu_data, cpu);
-
-	if (!data)
-		goto err_out_put_module;
-
-	if (!sysfs && !kobject_get(&data->kobj))
-		goto err_out_put_module;
+	if (cpufreq_driver) {
+		/* get the CPU */
+		policy = per_cpu(cpufreq_cpu_data, cpu);
+		if (policy)
+			kobject_get(&policy->kobj);
+	}
 
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	return data;
 
-err_out_put_module:
-	module_put(cpufreq_driver->owner);
-err_out_unlock:
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-err_out:
-	return NULL;
-}
-
-struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
-{
-	if (cpufreq_disabled())
-		return NULL;
+	if (!policy)
+		up_read(&cpufreq_rwsem);
 
-	return __cpufreq_cpu_get(cpu, false);
+	return policy;
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
 
-static struct cpufreq_policy *cpufreq_cpu_get_sysfs(unsigned int cpu)
-{
-	return __cpufreq_cpu_get(cpu, true);
-}
-
-static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs)
-{
-	if (!sysfs)
-		kobject_put(&data->kobj);
-	module_put(cpufreq_driver->owner);
-}
-
-void cpufreq_cpu_put(struct cpufreq_policy *data)
+void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	if (cpufreq_disabled())
 		return;
 
-	__cpufreq_cpu_put(data, false);
+	kobject_put(&policy->kobj);
+	up_read(&cpufreq_rwsem);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
-static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data)
-{
-	__cpufreq_cpu_put(data, true);
-}
-
 /*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
@@ -459,8 +428,8 @@ show_one(scaling_min_freq, min);
 show_one(scaling_max_freq, max);
 show_one(scaling_cur_freq, cur);
 
-static int __cpufreq_set_policy(struct cpufreq_policy *data,
-				struct cpufreq_policy *policy);
+static int __cpufreq_set_policy(struct cpufreq_policy *policy,
+				struct cpufreq_policy *new_policy);
 
 /**
  * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
@@ -699,12 +668,12 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	struct cpufreq_policy *policy = to_policy(kobj);
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
-	policy = cpufreq_cpu_get_sysfs(policy->cpu);
-	if (!policy)
-		goto no_policy;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		goto exit;
 
 	if (lock_policy_rwsem_read(policy->cpu) < 0)
-		goto fail;
+		goto up_read;
 
 	if (fattr->show)
 		ret = fattr->show(policy, buf);
@@ -712,9 +681,10 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 		ret = -EIO;
 
 	unlock_policy_rwsem_read(policy->cpu);
-fail:
-	cpufreq_cpu_put_sysfs(policy);
-no_policy:
+
+up_read:
+	up_read(&cpufreq_rwsem);
+exit:
 	return ret;
 }
 
@@ -724,12 +694,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct cpufreq_policy *policy = to_policy(kobj);
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
-	policy = cpufreq_cpu_get_sysfs(policy->cpu);
-	if (!policy)
-		goto no_policy;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		goto exit;
 
 	if (lock_policy_rwsem_write(policy->cpu) < 0)
-		goto fail;
+		goto up_read;
 
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
@@ -737,9 +707,10 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 		ret = -EIO;
 
 	unlock_policy_rwsem_write(policy->cpu);
-fail:
-	cpufreq_cpu_put_sysfs(policy);
-no_policy:
+
+up_read:
+	up_read(&cpufreq_rwsem);
+exit:
 	return ret;
 }
 
@@ -805,41 +776,32 @@ void cpufreq_sysfs_remove_file(const struct attribute *attr)
 EXPORT_SYMBOL(cpufreq_sysfs_remove_file);
 
 /* symlink affected CPUs */
-static int cpufreq_add_dev_symlink(unsigned int cpu,
-				   struct cpufreq_policy *policy)
+static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
 
 	for_each_cpu(j, policy->cpus) {
-		struct cpufreq_policy *managed_policy;
 		struct device *cpu_dev;
 
-		if (j == cpu)
+		if (j == policy->cpu)
 			continue;
 
-		pr_debug("CPU %u already managed, adding link\n", j);
-		managed_policy = cpufreq_cpu_get(cpu);
+		pr_debug("Adding link for CPU: %u\n", j);
 		cpu_dev = get_cpu_device(j);
 		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
 					"cpufreq");
-		if (ret) {
-			cpufreq_cpu_put(managed_policy);
-			return ret;
-		}
+		if (ret)
+			break;
 	}
 	return ret;
 }
 
-static int cpufreq_add_dev_interface(unsigned int cpu,
-				     struct cpufreq_policy *policy,
+static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 				     struct device *dev)
 {
-	struct cpufreq_policy new_policy;
 	struct freq_attr **drv_attr;
-	unsigned long flags;
 	int ret = 0;
-	unsigned int j;
 
 	/* prepare interface data */
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
@@ -871,18 +833,24 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 			goto err_out_kobj_put;
 	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus) {
-		per_cpu(cpufreq_cpu_data, j) = policy;
-		per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
-	}
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	ret = cpufreq_add_dev_symlink(cpu, policy);
+	ret = cpufreq_add_dev_symlink(policy);
 	if (ret)
 		goto err_out_kobj_put;
 
-	memcpy(&new_policy, policy, sizeof(struct cpufreq_policy));
+	return ret;
+
+err_out_kobj_put:
+	kobject_put(&policy->kobj);
+	wait_for_completion(&policy->kobj_unregister);
+	return ret;
+}
+
+static void cpufreq_init_policy(struct cpufreq_policy *policy)
+{
+	struct cpufreq_policy new_policy;
+	int ret = 0;
+
+	memcpy(&new_policy, policy, sizeof(*policy));
 	/* assure that the starting sequence is run in __cpufreq_set_policy */
 	policy->governor = NULL;
 
@@ -896,29 +864,25 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 		if (cpufreq_driver->exit)
 			cpufreq_driver->exit(policy);
 	}
-	return ret;
-
-err_out_kobj_put:
-	kobject_put(&policy->kobj);
-	wait_for_completion(&policy->kobj_unregister);
-	return ret;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int cpufreq_add_policy_cpu(unsigned int cpu, unsigned int sibling,
-				  struct device *dev)
+static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
+				  unsigned int cpu, struct device *dev,
+				  bool frozen)
 {
-	struct cpufreq_policy *policy;
 	int ret = 0, has_target = !!cpufreq_driver->target;
 	unsigned long flags;
 
-	policy = cpufreq_cpu_get(sibling);
-	WARN_ON(!policy);
-
-	if (has_target)
-		__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+	if (has_target) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			pr_err("%s: Failed to stop governor\n", __func__);
+			return ret;
+		}
+	}
 
-	lock_policy_rwsem_write(sibling);
+	lock_policy_rwsem_write(policy->cpu);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
@@ -927,41 +891,86 @@ static int cpufreq_add_policy_cpu(unsigned int cpu, unsigned int sibling,
 	per_cpu(cpufreq_cpu_data, cpu) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	unlock_policy_rwsem_write(sibling);
+	unlock_policy_rwsem_write(policy->cpu);
 
 	if (has_target) {
-		__cpufreq_governor(policy, CPUFREQ_GOV_START);
-		__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+		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;
+		}
 	}
 
-	ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
-	if (ret) {
-		cpufreq_cpu_put(policy);
-		return ret;
-	}
+	/* Don't touch sysfs links during light-weight init */
+	if (!frozen)
+		ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
 
-	return 0;
+	return ret;
 }
 #endif
 
-/**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
- */
-static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
+{
+	struct cpufreq_policy *policy;
+	unsigned long flags;
+
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+
+	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
+
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	return policy;
+}
+
+static struct cpufreq_policy *cpufreq_policy_alloc(void)
+{
+	struct cpufreq_policy *policy;
+
+	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
+	if (!policy)
+		return NULL;
+
+	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
+		goto err_free_policy;
+
+	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
+		goto err_free_cpumask;
+
+	INIT_LIST_HEAD(&policy->policy_list);
+	return policy;
+
+err_free_cpumask:
+	free_cpumask_var(policy->cpus);
+err_free_policy:
+	kfree(policy);
+
+	return NULL;
+}
+
+static void cpufreq_policy_free(struct cpufreq_policy *policy)
+{
+	unsigned long flags;
+
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	list_del(&policy->policy_list);
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	free_cpumask_var(policy->related_cpus);
+	free_cpumask_var(policy->cpus);
+	kfree(policy);
+}
+
+static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
+			     bool frozen)
 {
 	unsigned int j, cpu = dev->id;
 	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
 #ifdef CONFIG_HOTPLUG_CPU
+	struct cpufreq_policy *tpolicy;
 	struct cpufreq_governor *gov;
-	int sibling;
 #endif
 
 	if (cpu_is_offline(cpu))
@@ -978,35 +987,33 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		return 0;
 	}
 
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return 0;
+
 #ifdef CONFIG_HOTPLUG_CPU
 	/* Check if this cpu was hot-unplugged earlier and has siblings */
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_online_cpu(sibling) {
-		struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
-		if (cp && cpumask_test_cpu(cpu, cp->related_cpus)) {
+	list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) {
+		if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) {
 			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-			return cpufreq_add_policy_cpu(cpu, sibling, dev);
+			ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev, frozen);
+			up_read(&cpufreq_rwsem);
+			return ret;
 		}
 	}
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 #endif
 #endif
 
-	if (!try_module_get(cpufreq_driver->owner)) {
-		ret = -EINVAL;
-		goto module_out;
-	}
+	if (frozen)
+		/* Restore the saved policy when doing light-weight init */
+		policy = cpufreq_policy_restore(cpu);
+	else
+		policy = cpufreq_policy_alloc();
 
-	policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL);
 	if (!policy)
 		goto nomem_out;
 
-	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
-		goto err_free_policy;
-
-	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
-		goto err_free_cpumask;
-
 	policy->cpu = cpu;
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
@@ -1050,38 +1057,64 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	}
 #endif
 
-	ret = cpufreq_add_dev_interface(cpu, policy, dev);
-	if (ret)
-		goto err_out_unregister;
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	for_each_cpu(j, policy->cpus) {
+		per_cpu(cpufreq_cpu_data, j) = policy;
+		per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
+	}
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	if (!frozen) {
+		ret = cpufreq_add_dev_interface(policy, dev);
+		if (ret)
+			goto err_out_unregister;
+
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		list_add(&policy->policy_list, &cpufreq_policy_list);
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	}
+
+	cpufreq_init_policy(policy);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
-	module_put(cpufreq_driver->owner);
+	up_read(&cpufreq_rwsem);
+
 	pr_debug("initialization complete\n");
 
 	return 0;
 
 err_out_unregister:
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
+	for_each_cpu(j, policy->cpus) {
 		per_cpu(cpufreq_cpu_data, j) = NULL;
+		if (j != cpu)
+			per_cpu(cpufreq_policy_cpu, j) = -1;
+	}
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	kobject_put(&policy->kobj);
-	wait_for_completion(&policy->kobj_unregister);
-
 err_set_policy_cpu:
 	per_cpu(cpufreq_policy_cpu, cpu) = -1;
-	free_cpumask_var(policy->related_cpus);
-err_free_cpumask:
-	free_cpumask_var(policy->cpus);
-err_free_policy:
-	kfree(policy);
+	cpufreq_policy_free(policy);
 nomem_out:
-	module_put(cpufreq_driver->owner);
-module_out:
+	up_read(&cpufreq_rwsem);
+
 	return ret;
 }
 
+/**
+ * cpufreq_add_dev - add a CPU device
+ *
+ * Adds the cpufreq interface for a CPU device.
+ *
+ * The Oracle says: try running cpufreq registration/unregistration concurrently
+ * with with cpu hotplugging and all hell will break loose. Tried to clean this
+ * mess up, but more thorough testing is needed. - Mathieu
+ */
+static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+{
+	return __cpufreq_add_dev(dev, sif, false);
+}
+
 static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	int j;
@@ -1099,6 +1132,43 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 			CPUFREQ_UPDATE_POLICY_CPU, policy);
 }
 
+static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
+					   unsigned int old_cpu, bool frozen)
+{
+	struct device *cpu_dev;
+	unsigned long flags;
+	int ret;
+
+	/* first sibling now owns the new sysfs dir */
+	cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
+
+	/* 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);
+
+		WARN_ON(lock_policy_rwsem_write(old_cpu));
+		cpumask_set_cpu(old_cpu, policy->cpus);
+
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		per_cpu(cpufreq_cpu_data, old_cpu) = policy;
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+		unlock_policy_rwsem_write(old_cpu);
+
+		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
+					"cpufreq");
+
+		return -EINVAL;
+	}
+
+	return cpu_dev->id;
+}
+
 /**
  * __cpufreq_remove_dev - remove a CPU device
  *
@@ -1107,107 +1177,118 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
  * This routine frees the rwsem before returning.
  */
 static int __cpufreq_remove_dev(struct device *dev,
-		struct subsys_interface *sif)
+				struct subsys_interface *sif, bool frozen)
 {
-	unsigned int cpu = dev->id, ret, cpus;
+	unsigned int cpu = dev->id, cpus;
+	int new_cpu, ret;
 	unsigned long flags;
-	struct cpufreq_policy *data;
+	struct cpufreq_policy *policy;
 	struct kobject *kobj;
 	struct completion *cmp;
-	struct device *cpu_dev;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
-	data = per_cpu(cpufreq_cpu_data, cpu);
+	policy = per_cpu(cpufreq_cpu_data, cpu);
 	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 
+	/* Save the policy somewhere when doing a light-weight tear-down */
+	if (frozen)
+		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
+
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (!data) {
+	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
 	}
 
-	if (cpufreq_driver->target)
-		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
+	if (cpufreq_driver->target) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			pr_err("%s: Failed to stop governor\n", __func__);
+			return ret;
+		}
+	}
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (!cpufreq_driver->setpolicy)
 		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
-			data->governor->name, CPUFREQ_NAME_LEN);
+			policy->governor->name, CPUFREQ_NAME_LEN);
 #endif
 
 	WARN_ON(lock_policy_rwsem_write(cpu));
-	cpus = cpumask_weight(data->cpus);
+	cpus = cpumask_weight(policy->cpus);
 
 	if (cpus > 1)
-		cpumask_clear_cpu(cpu, data->cpus);
+		cpumask_clear_cpu(cpu, policy->cpus);
 	unlock_policy_rwsem_write(cpu);
 
-	if (cpu != data->cpu) {
+	if (cpu != policy->cpu && !frozen) {
 		sysfs_remove_link(&dev->kobj, "cpufreq");
 	} else if (cpus > 1) {
-		/* first sibling now owns the new sysfs dir */
-		cpu_dev = get_cpu_device(cpumask_first(data->cpus));
-		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-		ret = kobject_move(&data->kobj, &cpu_dev->kobj);
-		if (ret) {
-			pr_err("%s: Failed to move kobj: %d", __func__, ret);
 
+		new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen);
+		if (new_cpu >= 0) {
 			WARN_ON(lock_policy_rwsem_write(cpu));
-			cpumask_set_cpu(cpu, data->cpus);
-
-			write_lock_irqsave(&cpufreq_driver_lock, flags);
-			per_cpu(cpufreq_cpu_data, cpu) = data;
-			write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
+			update_policy_cpu(policy, new_cpu);
 			unlock_policy_rwsem_write(cpu);
 
-			ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj,
-					"cpufreq");
-			return -EINVAL;
+			if (!frozen) {
+				pr_debug("%s: policy Kobject moved to cpu: %d "
+					 "from: %d\n",__func__, new_cpu, cpu);
+			}
 		}
-
-		WARN_ON(lock_policy_rwsem_write(cpu));
-		update_policy_cpu(data, cpu_dev->id);
-		unlock_policy_rwsem_write(cpu);
-		pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-				__func__, cpu_dev->id, cpu);
 	}
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target)
-			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
-		lock_policy_rwsem_read(cpu);
-		kobj = &data->kobj;
-		cmp = &data->kobj_unregister;
-		unlock_policy_rwsem_read(cpu);
-		kobject_put(kobj);
-
-		/* we need to make sure that the underlying kobj is actually
-		 * not referenced anymore by anybody before we proceed with
-		 * unloading.
-		 */
-		pr_debug("waiting for dropping of refcount\n");
-		wait_for_completion(cmp);
-		pr_debug("wait complete\n");
+		if (cpufreq_driver->target) {
+			ret = __cpufreq_governor(policy,
+					CPUFREQ_GOV_POLICY_EXIT);
+			if (ret) {
+				pr_err("%s: Failed to exit governor\n",
+						__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");
+		}
+
+		/*
+		 * Perform the ->exit() even during light-weight tear-down,
+		 * since this is a core component, and is essential for the
+		 * subsequent light-weight ->init() to succeed.
+		 */
 		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(data);
+			cpufreq_driver->exit(policy);
 
-		free_cpumask_var(data->related_cpus);
-		free_cpumask_var(data->cpus);
-		kfree(data);
+		if (!frozen)
+			cpufreq_policy_free(policy);
 	} else {
-		pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
-		cpufreq_cpu_put(data);
 		if (cpufreq_driver->target) {
-			__cpufreq_governor(data, CPUFREQ_GOV_START);
-			__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+			if ((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;
+			}
 		}
 	}
 
@@ -1223,7 +1304,7 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (cpu_is_offline(cpu))
 		return 0;
 
-	retval = __cpufreq_remove_dev(dev, sif);
+	retval = __cpufreq_remove_dev(dev, sif, false);
 	return retval;
 }
 
@@ -1344,10 +1425,9 @@ static unsigned int __cpufreq_get(unsigned int cpu)
 unsigned int cpufreq_get(unsigned int cpu)
 {
 	unsigned int ret_freq = 0;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 
-	if (!policy)
-		goto out;
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return 0;
 
 	if (unlikely(lock_policy_rwsem_read(cpu)))
 		goto out_policy;
@@ -1357,8 +1437,8 @@ unsigned int cpufreq_get(unsigned int cpu)
 	unlock_policy_rwsem_read(cpu);
 
 out_policy:
-	cpufreq_cpu_put(policy);
-out:
+	up_read(&cpufreq_rwsem);
+
 	return ret_freq;
 }
 EXPORT_SYMBOL(cpufreq_get);
@@ -1381,23 +1461,23 @@ static int cpufreq_bp_suspend(void)
 	int ret = 0;
 
 	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	struct cpufreq_policy *policy;
 
 	pr_debug("suspending cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
 		return 0;
 
 	if (cpufreq_driver->suspend) {
-		ret = cpufreq_driver->suspend(cpu_policy);
+		ret = cpufreq_driver->suspend(policy);
 		if (ret)
 			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
-					"step on CPU %u\n", cpu_policy->cpu);
+					"step on CPU %u\n", policy->cpu);
 	}
 
-	cpufreq_cpu_put(cpu_policy);
+	cpufreq_cpu_put(policy);
 	return ret;
 }
 
@@ -1419,28 +1499,28 @@ static void cpufreq_bp_resume(void)
 	int ret = 0;
 
 	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	struct cpufreq_policy *policy;
 
 	pr_debug("resuming cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
 		return;
 
 	if (cpufreq_driver->resume) {
-		ret = cpufreq_driver->resume(cpu_policy);
+		ret = cpufreq_driver->resume(policy);
 		if (ret) {
 			printk(KERN_ERR "cpufreq: resume failed in ->resume "
-					"step on CPU %u\n", cpu_policy->cpu);
+					"step on CPU %u\n", policy->cpu);
 			goto fail;
 		}
 	}
 
-	schedule_work(&cpu_policy->update);
+	schedule_work(&policy->update);
 
 fail:
-	cpufreq_cpu_put(cpu_policy);
+	cpufreq_cpu_put(policy);
 }
 
 static struct syscore_ops cpufreq_syscore_ops = {
@@ -1594,18 +1674,6 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_target);
 
-int __cpufreq_driver_getavg(struct cpufreq_policy *policy, unsigned int cpu)
-{
-	if (cpufreq_disabled())
-		return 0;
-
-	if (!cpufreq_driver->getavg)
-		return 0;
-
-	return cpufreq_driver->getavg(policy, cpu);
-}
-EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg);
-
 /*
  * when "event" is CPUFREQ_GOV_LIMITS
  */
@@ -1640,8 +1708,9 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		}
 	}
 
-	if (!try_module_get(policy->governor->owner))
-		return -EINVAL;
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		if (!try_module_get(policy->governor->owner))
+			return -EINVAL;
 
 	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
 						policy->cpu, event);
@@ -1650,6 +1719,8 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) ||
 	    (policy->governor_enabled && (event == CPUFREQ_GOV_START))) {
 		mutex_unlock(&cpufreq_governor_lock);
+		if (event == CPUFREQ_GOV_POLICY_INIT)
+			module_put(policy->governor->owner);
 		return -EBUSY;
 	}
 
@@ -1677,11 +1748,8 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		mutex_unlock(&cpufreq_governor_lock);
 	}
 
-	/* we keep one module reference alive for
-			each CPU governed by this CPU */
-	if ((event != CPUFREQ_GOV_START) || ret)
-		module_put(policy->governor->owner);
-	if ((event == CPUFREQ_GOV_STOP) && !ret)
+	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
+			((event == CPUFREQ_GOV_POLICY_EXIT) && !ret))
 		module_put(policy->governor->owner);
 
 	return ret;
@@ -1761,7 +1829,7 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
 	if (!cpu_policy)
 		return -EINVAL;
 
-	memcpy(policy, cpu_policy, sizeof(struct cpufreq_policy));
+	memcpy(policy, cpu_policy, sizeof(*policy));
 
 	cpufreq_cpu_put(cpu_policy);
 	return 0;
@@ -1772,95 +1840,94 @@ EXPORT_SYMBOL(cpufreq_get_policy);
  * data   : current policy.
  * policy : policy to be set.
  */
-static int __cpufreq_set_policy(struct cpufreq_policy *data,
-				struct cpufreq_policy *policy)
+static int __cpufreq_set_policy(struct cpufreq_policy *policy,
+				struct cpufreq_policy *new_policy)
 {
 	int ret = 0, failed = 1;
 
-	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu,
-		policy->min, policy->max);
+	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu,
+		new_policy->min, new_policy->max);
 
-	memcpy(&policy->cpuinfo, &data->cpuinfo,
-				sizeof(struct cpufreq_cpuinfo));
+	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
-	if (policy->min > data->max || policy->max < data->min) {
+	if (new_policy->min > policy->max || new_policy->max < policy->min) {
 		ret = -EINVAL;
 		goto error_out;
 	}
 
 	/* verify the cpu speed can be set within this limit */
-	ret = cpufreq_driver->verify(policy);
+	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		goto error_out;
 
 	/* adjust if necessary - all reasons */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_ADJUST, policy);
+			CPUFREQ_ADJUST, new_policy);
 
 	/* adjust if necessary - hardware incompatibility*/
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_INCOMPATIBLE, policy);
+			CPUFREQ_INCOMPATIBLE, new_policy);
 
 	/*
 	 * verify the cpu speed can be set within this limit, which might be
 	 * different to the first one
 	 */
-	ret = cpufreq_driver->verify(policy);
+	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		goto error_out;
 
 	/* notification of the new policy */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_NOTIFY, policy);
+			CPUFREQ_NOTIFY, new_policy);
 
-	data->min = policy->min;
-	data->max = policy->max;
+	policy->min = new_policy->min;
+	policy->max = new_policy->max;
 
 	pr_debug("new min and max freqs are %u - %u kHz\n",
-					data->min, data->max);
+					policy->min, policy->max);
 
 	if (cpufreq_driver->setpolicy) {
-		data->policy = policy->policy;
+		policy->policy = new_policy->policy;
 		pr_debug("setting range\n");
-		ret = cpufreq_driver->setpolicy(policy);
+		ret = cpufreq_driver->setpolicy(new_policy);
 	} else {
-		if (policy->governor != data->governor) {
+		if (new_policy->governor != policy->governor) {
 			/* save old, working values */
-			struct cpufreq_governor *old_gov = data->governor;
+			struct cpufreq_governor *old_gov = policy->governor;
 
 			pr_debug("governor switch\n");
 
 			/* end old governor */
-			if (data->governor) {
-				__cpufreq_governor(data, CPUFREQ_GOV_STOP);
-				unlock_policy_rwsem_write(policy->cpu);
-				__cpufreq_governor(data,
+			if (policy->governor) {
+				__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+				unlock_policy_rwsem_write(new_policy->cpu);
+				__cpufreq_governor(policy,
 						CPUFREQ_GOV_POLICY_EXIT);
-				lock_policy_rwsem_write(policy->cpu);
+				lock_policy_rwsem_write(new_policy->cpu);
 			}
 
 			/* start new governor */
-			data->governor = policy->governor;
-			if (!__cpufreq_governor(data, CPUFREQ_GOV_POLICY_INIT)) {
-				if (!__cpufreq_governor(data, CPUFREQ_GOV_START)) {
+			policy->governor = new_policy->governor;
+			if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
+				if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) {
 					failed = 0;
 				} else {
-					unlock_policy_rwsem_write(policy->cpu);
-					__cpufreq_governor(data,
+					unlock_policy_rwsem_write(new_policy->cpu);
+					__cpufreq_governor(policy,
 							CPUFREQ_GOV_POLICY_EXIT);
-					lock_policy_rwsem_write(policy->cpu);
+					lock_policy_rwsem_write(new_policy->cpu);
 				}
 			}
 
 			if (failed) {
 				/* new governor failed, so re-start old one */
 				pr_debug("starting governor %s failed\n",
-							data->governor->name);
+							policy->governor->name);
 				if (old_gov) {
-					data->governor = old_gov;
-					__cpufreq_governor(data,
+					policy->governor = old_gov;
+					__cpufreq_governor(policy,
 							CPUFREQ_GOV_POLICY_INIT);
-					__cpufreq_governor(data,
+					__cpufreq_governor(policy,
 							   CPUFREQ_GOV_START);
 				}
 				ret = -EINVAL;
@@ -1869,7 +1936,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 			/* might be a policy change, too, so fall through */
 		}
 		pr_debug("governor: change or update limits\n");
-		__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 	}
 
 error_out:
@@ -1885,11 +1952,11 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
  */
 int cpufreq_update_policy(unsigned int cpu)
 {
-	struct cpufreq_policy *data = cpufreq_cpu_get(cpu);
-	struct cpufreq_policy policy;
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy new_policy;
 	int ret;
 
-	if (!data) {
+	if (!policy) {
 		ret = -ENODEV;
 		goto no_policy;
 	}
@@ -1900,34 +1967,34 @@ int cpufreq_update_policy(unsigned int cpu)
 	}
 
 	pr_debug("updating policy for CPU %u\n", cpu);
-	memcpy(&policy, data, sizeof(struct cpufreq_policy));
-	policy.min = data->user_policy.min;
-	policy.max = data->user_policy.max;
-	policy.policy = data->user_policy.policy;
-	policy.governor = data->user_policy.governor;
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.min = policy->user_policy.min;
+	new_policy.max = policy->user_policy.max;
+	new_policy.policy = policy->user_policy.policy;
+	new_policy.governor = policy->user_policy.governor;
 
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get) {
-		policy.cur = cpufreq_driver->get(cpu);
-		if (!data->cur) {
+		new_policy.cur = cpufreq_driver->get(cpu);
+		if (!policy->cur) {
 			pr_debug("Driver did not initialize current freq");
-			data->cur = policy.cur;
+			policy->cur = new_policy.cur;
 		} else {
-			if (data->cur != policy.cur && cpufreq_driver->target)
-				cpufreq_out_of_sync(cpu, data->cur,
-								policy.cur);
+			if (policy->cur != new_policy.cur && cpufreq_driver->target)
+				cpufreq_out_of_sync(cpu, policy->cur,
+								new_policy.cur);
 		}
 	}
 
-	ret = __cpufreq_set_policy(data, &policy);
+	ret = __cpufreq_set_policy(policy, &new_policy);
 
 	unlock_policy_rwsem_write(cpu);
 
 fail:
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(policy);
 no_policy:
 	return ret;
 }
@@ -1938,21 +2005,26 @@ 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) {
-		switch (action) {
+
+		if (action & CPU_TASKS_FROZEN)
+			frozen = true;
+
+		switch (action & ~CPU_TASKS_FROZEN) {
 		case CPU_ONLINE:
-		case CPU_ONLINE_FROZEN:
-			cpufreq_add_dev(dev, NULL);
+			__cpufreq_add_dev(dev, NULL, frozen);
+			cpufreq_update_policy(cpu);
 			break;
+
 		case CPU_DOWN_PREPARE:
-		case CPU_DOWN_PREPARE_FROZEN:
-			__cpufreq_remove_dev(dev, NULL);
+			__cpufreq_remove_dev(dev, NULL, frozen);
 			break;
+
 		case CPU_DOWN_FAILED:
-		case CPU_DOWN_FAILED_FROZEN:
-			cpufreq_add_dev(dev, NULL);
+			__cpufreq_add_dev(dev, NULL, frozen);
 			break;
 		}
 	}
@@ -2059,9 +2131,13 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	subsys_interface_unregister(&cpufreq_interface);
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
+	down_write(&cpufreq_rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
+
 	cpufreq_driver = NULL;
+
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	up_write(&cpufreq_rwsem);
 
 	return 0;
 }

drivers/cpufreq/cpufreq_conservative.c

@@ -11,19 +11,7 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/notifier.h>
-#include <linux/percpu-defs.h>
 #include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/types.h>
-
 #include "cpufreq_governor.h"
 
 /* Conservative governor macros */
@@ -329,7 +317,7 @@ static int cs_init(struct dbs_data *dbs_data)
 {
 	struct cs_dbs_tuners *tuners;
 
-	tuners = kzalloc(sizeof(struct cs_dbs_tuners), GFP_KERNEL);
+	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
 	if (!tuners) {
 		pr_err("%s: kzalloc failed\n", __func__);
 		return -ENOMEM;

drivers/cpufreq/cpufreq_governor.c

@@ -16,15 +16,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <asm/cputime.h>
-#include <linux/cpufreq.h>
-#include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
-#include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/workqueue.h>
 
 #include "cpufreq_governor.h"
 
@@ -53,7 +47,7 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 	policy = cdbs->cur_policy;
 
-	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_common_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;
@@ -104,14 +98,6 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 		load = 100 * (wall_time - idle_time) / wall_time;
 
-		if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-			int freq_avg = __cpufreq_driver_getavg(policy, j);
-			if (freq_avg <= 0)
-				freq_avg = policy->cur;
-
-			load *= freq_avg;
-		}
-
 		if (load > max_load)
 			max_load = load;
 	}

drivers/cpufreq/cpufreq_governor.h

@@ -18,10 +18,9 @@
 #define _CPUFREQ_GOVERNOR_H
 
 #include <linux/cpufreq.h>
-#include <linux/kobject.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
-#include <linux/sysfs.h>
 
 /*
  * The polling frequency depends on the capability of the processor. Default
@@ -169,7 +168,6 @@ struct od_dbs_tuners {
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
-	unsigned int adj_up_threshold;
 	unsigned int powersave_bias;
 	unsigned int io_is_busy;
 };
@@ -223,7 +221,7 @@ struct od_ops {
 	void (*powersave_bias_init_cpu)(int cpu);
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
 			unsigned int freq_next, unsigned int relation);
-	void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq);
+	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
 struct cs_ops {

drivers/cpufreq/cpufreq_ondemand.c

@@ -12,28 +12,16 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
+#include <linux/cpu.h>
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
-#include <linux/sysfs.h>
 #include <linux/tick.h>
-#include <linux/types.h>
-#include <linux/cpu.h>
-
 #include "cpufreq_governor.h"
 
 /* On-demand governor macros */
-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
-#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
@@ -144,31 +132,27 @@ static void ondemand_powersave_bias_init(void)
 	}
 }
 
-static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
+static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 {
-	struct dbs_data *dbs_data = p->governor_data;
+	struct dbs_data *dbs_data = policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
 	if (od_tuners->powersave_bias)
-		freq = od_ops.powersave_bias_target(p, freq,
+		freq = od_ops.powersave_bias_target(policy, freq,
 				CPUFREQ_RELATION_H);
-	else if (p->cur == p->max)
+	else if (policy->cur == policy->max)
 		return;
 
-	__cpufreq_driver_target(p, freq, od_tuners->powersave_bias ?
+	__cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ?
 			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
 }
 
 /*
  * Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency. Every sampling_rate, we look
- * for the lowest frequency which can sustain the load while keeping idle time
- * over 30%. If such a frequency exist, we try to decrease to this frequency.
- *
- * Any frequency increase takes it to the maximum frequency. Frequency reduction
- * happens at minimum steps of 5% (default) of current frequency
+ * (default), then we try to increase frequency. Else, we adjust the frequency
+ * proportional to load.
  */
-static void od_check_cpu(int cpu, unsigned int load_freq)
+static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
@@ -178,29 +162,17 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load_freq > od_tuners->up_threshold * policy->cur) {
+	if (load > od_tuners->up_threshold) {
 		/* If switching to max speed, apply sampling_down_factor */
 		if (policy->cur < policy->max)
 			dbs_info->rate_mult =
 				od_tuners->sampling_down_factor;
 		dbs_freq_increase(policy, policy->max);
 		return;
-	}
-
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that can
-	 * support the current CPU usage without triggering the up policy. To be
-	 * safe, we focus 10 points under the threshold.
-	 */
-	if (load_freq < od_tuners->adj_up_threshold
-			* policy->cur) {
+	} else {
+		/* Calculate the next frequency proportional to load */
 		unsigned int freq_next;
-		freq_next = load_freq / od_tuners->adj_up_threshold;
+		freq_next = load * policy->cpuinfo.max_freq / 100;
 
 		/* No longer fully busy, reset rate_mult */
 		dbs_info->rate_mult = 1;
@@ -374,9 +346,6 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	/* Calculate the new adj_up_threshold */
-	od_tuners->adj_up_threshold += input;
-	od_tuners->adj_up_threshold -= od_tuners->up_threshold;
 
 	od_tuners->up_threshold = input;
 	return count;
@@ -513,7 +482,7 @@ static int od_init(struct dbs_data *dbs_data)
 	u64 idle_time;
 	int cpu;
 
-	tuners = kzalloc(sizeof(struct od_dbs_tuners), GFP_KERNEL);
+	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
 	if (!tuners) {
 		pr_err("%s: kzalloc failed\n", __func__);
 		return -ENOMEM;
@@ -525,8 +494,6 @@ static int od_init(struct dbs_data *dbs_data)
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
 		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
-			MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -535,8 +502,6 @@ static int od_init(struct dbs_data *dbs_data)
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
-			DEF_FREQUENCY_DOWN_DIFFERENTIAL;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *

drivers/cpufreq/cpufreq_performance.c

@@ -12,10 +12,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 					unsigned int event)

drivers/cpufreq/cpufreq_powersave.c

@@ -12,10 +12,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 					unsigned int event)

drivers/cpufreq/cpufreq_stats.c

@@ -9,17 +9,10 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/sysfs.h>
 #include <linux/cpufreq.h>
 #include <linux/module.h>
-#include <linux/jiffies.h>
-#include <linux/percpu.h>
-#include <linux/kobject.h>
-#include <linux/spinlock.h>
-#include <linux/notifier.h>
+#include <linux/slab.h>
 #include <asm/cputime.h>
 
 static spinlock_t cpufreq_stats_lock;
@@ -200,22 +193,22 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
 {
 	unsigned int i, j, count = 0, ret = 0;
 	struct cpufreq_stats *stat;
-	struct cpufreq_policy *data;
+	struct cpufreq_policy *current_policy;
 	unsigned int alloc_size;
 	unsigned int cpu = policy->cpu;
 	if (per_cpu(cpufreq_stats_table, cpu))
 		return -EBUSY;
-	stat = kzalloc(sizeof(struct cpufreq_stats), GFP_KERNEL);
+	stat = kzalloc(sizeof(*stat), GFP_KERNEL);
 	if ((stat) == NULL)
 		return -ENOMEM;
 
-	data = cpufreq_cpu_get(cpu);
-	if (data == NULL) {
+	current_policy = cpufreq_cpu_get(cpu);
+	if (current_policy == NULL) {
 		ret = -EINVAL;
 		goto error_get_fail;
 	}
 
-	ret = sysfs_create_group(&data->kobj, &stats_attr_group);
+	ret = sysfs_create_group(&current_policy->kobj, &stats_attr_group);
 	if (ret)
 		goto error_out;
 
@@ -258,10 +251,10 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
 	stat->last_time = get_jiffies_64();
 	stat->last_index = freq_table_get_index(stat, policy->cur);
 	spin_unlock(&cpufreq_stats_lock);
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(current_policy);
 	return 0;
 error_out:
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(current_policy);
 error_get_fail:
 	kfree(stat);
 	per_cpu(cpufreq_stats_table, cpu) = NULL;
@@ -348,16 +341,10 @@ static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
 	unsigned int cpu = (unsigned long)hcpu;
 
 	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		cpufreq_update_policy(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		cpufreq_stats_free_sysfs(cpu);
 		break;
 	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
 		cpufreq_stats_free_table(cpu);
 		break;
 	}
@@ -390,8 +377,6 @@ static int __init cpufreq_stats_init(void)
 		return ret;
 
 	register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
-	for_each_online_cpu(cpu)
-		cpufreq_update_policy(cpu);
 
 	ret = cpufreq_register_notifier(&notifier_trans_block,
 				CPUFREQ_TRANSITION_NOTIFIER);

drivers/cpufreq/cris-artpec3-cpufreq.c

@@ -111,7 +111,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.init	= cris_freq_cpu_init,
 	.exit	= cris_freq_cpu_exit,
 	.name	= "cris_freq",
-	.owner	= THIS_MODULE,
 	.attr	= cris_freq_attr,
 };
 

drivers/cpufreq/cris-etraxfs-cpufreq.c

@@ -108,7 +108,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.init = cris_freq_cpu_init,
 	.exit = cris_freq_cpu_exit,
 	.name = "cris_freq",
-	.owner = THIS_MODULE,
 	.attr = cris_freq_attr,
 };
 

drivers/cpufreq/e_powersaver.c

@@ -54,7 +54,7 @@ static struct acpi_processor_performance *eps_acpi_cpu_perf;
 /* Minimum necessary to get acpi_processor_get_bios_limit() working */
 static int eps_acpi_init(void)
 {
-	eps_acpi_cpu_perf = kzalloc(sizeof(struct acpi_processor_performance),
+	eps_acpi_cpu_perf = kzalloc(sizeof(*eps_acpi_cpu_perf),
 				      GFP_KERNEL);
 	if (!eps_acpi_cpu_perf)
 		return -ENOMEM;
@@ -366,7 +366,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		states = 2;
 
 	/* Allocate private data and frequency table for current cpu */
-	centaur = kzalloc(sizeof(struct eps_cpu_data)
+	centaur = kzalloc(sizeof(*centaur)
 		    + (states + 1) * sizeof(struct cpufreq_frequency_table),
 		    GFP_KERNEL);
 	if (!centaur)
@@ -436,7 +436,6 @@ static struct cpufreq_driver eps_driver = {
 	.exit		= eps_cpu_exit,
 	.get		= eps_get,
 	.name		= "e_powersaver",
-	.owner		= THIS_MODULE,
 	.attr		= eps_attr,
 };
 

drivers/cpufreq/elanfreq.c

@@ -274,7 +274,6 @@ static struct cpufreq_driver elanfreq_driver = {
 	.init		= elanfreq_cpu_init,
 	.exit		= elanfreq_cpu_exit,
 	.name		= "elanfreq",
-	.owner		= THIS_MODULE,
 	.attr		= elanfreq_attr,
 };
 

drivers/cpufreq/exynos-cpufreq.c

@@ -289,7 +289,7 @@ static int __init exynos_cpufreq_init(void)
 {
 	int ret = -EINVAL;
 
-	exynos_info = kzalloc(sizeof(struct exynos_dvfs_info), GFP_KERNEL);
+	exynos_info = kzalloc(sizeof(*exynos_info), GFP_KERNEL);
 	if (!exynos_info)
 		return -ENOMEM;
 

drivers/cpufreq/freq_table.c

@@ -11,10 +11,8 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
 #include <linux/cpufreq.h>
+#include <linux/module.h>
 
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *

drivers/cpufreq/gx-suspmod.c

@@ -446,7 +446,6 @@ static struct cpufreq_driver gx_suspmod_driver = {
 	.target		= cpufreq_gx_target,
 	.init		= cpufreq_gx_cpu_init,
 	.name		= "gx-suspmod",
-	.owner		= THIS_MODULE,
 };
 
 static int __init cpufreq_gx_init(void)
@@ -466,7 +465,7 @@ static int __init cpufreq_gx_init(void)
 
 	pr_debug("geode suspend modulation available.\n");
 
-	params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL);
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (params == NULL)
 		return -ENOMEM;
 

drivers/cpufreq/ia64-acpi-cpufreq.c

@@ -274,7 +274,7 @@ acpi_cpufreq_cpu_init (
 
 	pr_debug("acpi_cpufreq_cpu_init\n");
 
-	data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return (-ENOMEM);
 
@@ -304,7 +304,7 @@ acpi_cpufreq_cpu_init (
 	}
 
 	/* alloc freq_table */
-	data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
+	data->freq_table = kmalloc(sizeof(*data->freq_table) *
 	                           (data->acpi_data.state_count + 1),
 	                           GFP_KERNEL);
 	if (!data->freq_table) {
@@ -409,7 +409,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
 	.name		= "acpi-cpufreq",
-	.owner		= THIS_MODULE,
 	.attr           = acpi_cpufreq_attr,
 };
 

drivers/cpufreq/intel_pstate.c

@@ -665,7 +665,6 @@ static struct cpufreq_driver intel_pstate_driver = {
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.name		= "intel_pstate",
-	.owner		= THIS_MODULE,
 };
 
 static int __initdata no_load;

drivers/cpufreq/kirkwood-cpufreq.c

@@ -158,7 +158,6 @@ static struct cpufreq_driver kirkwood_cpufreq_driver = {
 	.init	= kirkwood_cpufreq_cpu_init,
 	.exit	= kirkwood_cpufreq_cpu_exit,
 	.name	= "kirkwood-cpufreq",
-	.owner	= THIS_MODULE,
 	.attr	= kirkwood_cpufreq_attr,
 };
 

drivers/cpufreq/longhaul.c

@@ -948,7 +948,6 @@ static struct cpufreq_driver longhaul_driver = {
 	.init	= longhaul_cpu_init,
 	.exit	= longhaul_cpu_exit,
 	.name	= "longhaul",
-	.owner	= THIS_MODULE,
 	.attr	= longhaul_attr,
 };
 

drivers/cpufreq/longrun.c

@@ -286,7 +286,6 @@ static struct cpufreq_driver longrun_driver = {
 	.get		= longrun_get,
 	.init		= longrun_cpu_init,
 	.name		= "longrun",
-	.owner		= THIS_MODULE,
 };
 
 static const struct x86_cpu_id longrun_ids[] = {

drivers/cpufreq/loongson2_cpufreq.c

@@ -158,7 +158,6 @@ static struct freq_attr *loongson2_table_attr[] = {
 };
 
 static struct cpufreq_driver loongson2_cpufreq_driver = {
-	.owner = THIS_MODULE,
 	.name = "loongson2",
 	.init = loongson2_cpufreq_cpu_init,
 	.verify = loongson2_cpufreq_verify,

drivers/cpufreq/maple-cpufreq.c

@@ -190,7 +190,6 @@ static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver maple_cpufreq_driver = {
 	.name		= "maple",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= maple_cpufreq_cpu_init,
 	.verify		= maple_cpufreq_verify,

drivers/cpufreq/mperf.c

-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
-
-#include "mperf.h"
-
-static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
-
-/* Called via smp_call_function_single(), on the target CPU */
-static void read_measured_perf_ctrs(void *_cur)
-{
-	struct aperfmperf *am = _cur;
-
-	get_aperfmperf(am);
-}
-
-/*
- * Return the measured active (C0) frequency on this CPU since last call
- * to this function.
- * Input: cpu number
- * Return: Average CPU frequency in terms of max frequency (zero on error)
- *
- * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
- * over a period of time, while CPU is in C0 state.
- * IA32_MPERF counts at the rate of max advertised frequency
- * IA32_APERF counts at the rate of actual CPU frequency
- * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
- * no meaning should be associated with absolute values of these MSRs.
- */
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
-					unsigned int cpu)
-{
-	struct aperfmperf perf;
-	unsigned long ratio;
-	unsigned int retval;
-
-	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
-		return 0;
-
-	ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
-	per_cpu(acfreq_old_perf, cpu) = perf;
-
-	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf);
-MODULE_LICENSE("GPL");

drivers/cpufreq/mperf.h

-/*
- *  (c) 2010 Advanced Micro Devices, Inc.
- *  Your use of this code is subject to the terms and conditions of the
- *  GNU general public license version 2. See "COPYING" or
- *  http://www.gnu.org/licenses/gpl.html
- */
-
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
-					unsigned int cpu);

drivers/cpufreq/p4-clockmod.c

@@ -279,7 +279,6 @@ static struct cpufreq_driver p4clockmod_driver = {
 	.exit		= cpufreq_p4_cpu_exit,
 	.get		= cpufreq_p4_get,
 	.name		= "p4-clockmod",
-	.owner		= THIS_MODULE,
 	.attr		= p4clockmod_attr,
 };
 

drivers/cpufreq/pasemi-cpufreq.c

@@ -297,7 +297,6 @@ static int pas_cpufreq_target(struct cpufreq_policy *policy,
 
 static struct cpufreq_driver pas_cpufreq_driver = {
 	.name		= "pas-cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= pas_cpufreq_cpu_init,
 	.exit		= pas_cpufreq_cpu_exit,

drivers/cpufreq/pcc-cpufreq.c

@@ -587,7 +587,6 @@ static struct cpufreq_driver pcc_cpufreq_driver = {
 	.init = pcc_cpufreq_cpu_init,
 	.exit = pcc_cpufreq_cpu_exit,
 	.name = "pcc-cpufreq",
-	.owner = THIS_MODULE,
 };
 
 static int __init pcc_cpufreq_init(void)

drivers/cpufreq/pmac32-cpufreq.c

@@ -477,7 +477,6 @@ static struct cpufreq_driver pmac_cpufreq_driver = {
 	.flags		= CPUFREQ_PM_NO_WARN,
 	.attr		= pmac_cpu_freqs_attr,
 	.name		= "powermac",
-	.owner		= THIS_MODULE,
 };
 
 

drivers/cpufreq/pmac64-cpufreq.c

@@ -371,7 +371,6 @@ static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver g5_cpufreq_driver = {
 	.name		= "powermac",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= g5_cpufreq_cpu_init,
 	.verify		= g5_cpufreq_verify,
@@ -447,9 +446,8 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 		if (!shdr)
 			goto bail_noprops;
 		g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1];
-		ssize = (shdr->len * sizeof(u32)) -
-			sizeof(struct smu_sdbp_header);
-		g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt);
+		ssize = (shdr->len * sizeof(u32)) - sizeof(*shdr);
+		g5_fvt_count = ssize / sizeof(*g5_fvt_table);
 		g5_fvt_cur = 0;
 
 		/* Sanity checking */

drivers/cpufreq/powernow-k6.c

@@ -207,7 +207,6 @@ static struct cpufreq_driver powernow_k6_driver = {
 	.exit		= powernow_k6_cpu_exit,
 	.get		= powernow_k6_get,
 	.name		= "powernow-k6",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_k6_attr,
 };
 

drivers/cpufreq/powernow-k7.c

@@ -177,7 +177,7 @@ static int get_ranges(unsigned char *pst)
 	unsigned int speed;
 	u8 fid, vid;
 
-	powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
+	powernow_table = kzalloc((sizeof(*powernow_table) *
 				(number_scales + 1)), GFP_KERNEL);
 	if (!powernow_table)
 		return -ENOMEM;
@@ -309,8 +309,7 @@ static int powernow_acpi_init(void)
 		goto err0;
 	}
 
-	acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance),
-				      GFP_KERNEL);
+	acpi_processor_perf = kzalloc(sizeof(*acpi_processor_perf), GFP_KERNEL);
 	if (!acpi_processor_perf) {
 		retval = -ENOMEM;
 		goto err0;
@@ -346,7 +345,7 @@ static int powernow_acpi_init(void)
 		goto err2;
 	}
 
-	powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
+	powernow_table = kzalloc((sizeof(*powernow_table) *
 				(number_scales + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		retval = -ENOMEM;
@@ -497,7 +496,7 @@ static int powernow_decode_bios(int maxfid, int startvid)
 					"relevant to this CPU).\n",
 					psb->numpst);
 
-			p += sizeof(struct psb_s);
+			p += sizeof(*psb);
 
 			pst = (struct pst_s *) p;
 
@@ -510,12 +509,12 @@ static int powernow_decode_bios(int maxfid, int startvid)
 				    (maxfid == pst->maxfid) &&
 				    (startvid == pst->startvid)) {
 					print_pst_entry(pst, j);
-					p = (char *)pst + sizeof(struct pst_s);
+					p = (char *)pst + sizeof(*pst);
 					ret = get_ranges(p);
 					return ret;
 				} else {
 					unsigned int k;
-					p = (char *)pst + sizeof(struct pst_s);
+					p = (char *)pst + sizeof(*pst);
 					for (k = 0; k < number_scales; k++)
 						p += 2;
 				}
@@ -717,7 +716,6 @@ static struct cpufreq_driver powernow_driver = {
 	.init		= powernow_cpu_init,
 	.exit		= powernow_cpu_exit,
 	.name		= "powernow-k7",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_table_attr,
 };
 

drivers/cpufreq/powernow-k8.c

@@ -623,7 +623,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 	if (check_pst_table(data, pst, maxvid))
 		return -EINVAL;
 
-	powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
+	powernow_table = kmalloc((sizeof(*powernow_table)
 		* (data->numps + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		printk(KERN_ERR PFX "powernow_table memory alloc failure\n");
@@ -793,7 +793,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	}
 
 	/* fill in data->powernow_table */
-	powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
+	powernow_table = kmalloc((sizeof(*powernow_table)
 		* (data->acpi_data.state_count + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		pr_debug("powernow_table memory alloc failure\n");
@@ -1106,7 +1106,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc)
 		return -ENODEV;
 
-	data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data) {
 		printk(KERN_ERR PFX "unable to alloc powernow_k8_data");
 		return -ENOMEM;
@@ -1240,7 +1240,6 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
 	.exit		= powernowk8_cpu_exit,
 	.get		= powernowk8_get,
 	.name		= "powernow-k8",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_k8_attr,
 };
 

drivers/cpufreq/ppc-corenet-cpufreq.c

@@ -300,7 +300,6 @@ static struct freq_attr *corenet_cpufreq_attr[] = {
 
 static struct cpufreq_driver ppc_corenet_cpufreq_driver = {
 	.name		= "ppc_cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= corenet_cpufreq_cpu_init,
 	.exit		= __exit_p(corenet_cpufreq_cpu_exit),

drivers/cpufreq/ppc_cbe_cpufreq.c

@@ -181,7 +181,6 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 	.init		= cbe_cpufreq_cpu_init,
 	.exit		= cbe_cpufreq_cpu_exit,
 	.name		= "cbe-cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 };
 

drivers/cpufreq/s3c2416-cpufreq.c

@@ -524,7 +524,6 @@ static struct freq_attr *s3c2416_cpufreq_attr[] = {
 };
 
 static struct cpufreq_driver s3c2416_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.flags          = 0,
 	.verify		= s3c2416_cpufreq_verify_speed,
 	.target		= s3c2416_cpufreq_set_target,

drivers/cpufreq/s3c24xx-cpufreq.c

@@ -522,7 +522,7 @@ int __init s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
 	/* Copy the board information so that each board can make this
 	 * initdata. */
 
-	ours = kzalloc(sizeof(struct s3c_cpufreq_board), GFP_KERNEL);
+	ours = kzalloc(sizeof(*ours), GFP_KERNEL);
 	if (ours == NULL) {
 		printk(KERN_ERR "%s: no memory\n", __func__);
 		return -ENOMEM;
@@ -615,7 +615,7 @@ static int s3c_cpufreq_build_freq(void)
 	size = cpu_cur.info->calc_freqtable(&cpu_cur, NULL, 0);
 	size++;
 
-	ftab = kmalloc(sizeof(struct cpufreq_frequency_table) * size, GFP_KERNEL);
+	ftab = kmalloc(sizeof(*ftab) * size, GFP_KERNEL);
 	if (!ftab) {
 		printk(KERN_ERR "%s: no memory for tables\n", __func__);
 		return -ENOMEM;
@@ -691,7 +691,7 @@ int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
 	struct cpufreq_frequency_table *vals;
 	unsigned int size;
 
-	size = sizeof(struct cpufreq_frequency_table) * (plls_no + 1);
+	size = sizeof(*vals) * (plls_no + 1);
 
 	vals = kmalloc(size, GFP_KERNEL);
 	if (vals) {

drivers/cpufreq/s3c64xx-cpufreq.c

@@ -263,7 +263,6 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver s3c64xx_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.flags          = 0,
 	.verify		= s3c64xx_cpufreq_verify_speed,
 	.target		= s3c64xx_cpufreq_set_target,

drivers/cpufreq/sc520_freq.c

@@ -147,7 +147,6 @@ static struct cpufreq_driver sc520_freq_driver = {
 	.init	= sc520_freq_cpu_init,
 	.exit	= sc520_freq_cpu_exit,
 	.name	= "sc520_freq",
-	.owner	= THIS_MODULE,
 	.attr	= sc520_freq_attr,
 };
 

drivers/cpufreq/sh-cpufreq.c

@@ -160,7 +160,6 @@ static struct freq_attr *sh_freq_attr[] = {
 };
 
 static struct cpufreq_driver sh_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.name		= "sh",
 	.get		= sh_cpufreq_get,
 	.target		= sh_cpufreq_target,

drivers/cpufreq/sparc-us2e-cpufreq.c

@@ -351,12 +351,11 @@ static int __init us2e_freq_init(void)
 		struct cpufreq_driver *driver;
 
 		ret = -ENOMEM;
-		driver = kzalloc(sizeof(struct cpufreq_driver), GFP_KERNEL);
+		driver = kzalloc(sizeof(*driver), GFP_KERNEL);
 		if (!driver)
 			goto err_out;
 
-		us2e_freq_table = kzalloc(
-			(NR_CPUS * sizeof(struct us2e_freq_percpu_info)),
+		us2e_freq_table = kzalloc((NR_CPUS * sizeof(*us2e_freq_table)),
 			GFP_KERNEL);
 		if (!us2e_freq_table)
 			goto err_out;
@@ -366,7 +365,6 @@ static int __init us2e_freq_init(void)
 		driver->target = us2e_freq_target;
 		driver->get = us2e_freq_get;
 		driver->exit = us2e_freq_cpu_exit;
-		driver->owner = THIS_MODULE,
 		strcpy(driver->name, "UltraSPARC-IIe");
 
 		cpufreq_us2e_driver = driver;

drivers/cpufreq/sparc-us3-cpufreq.c

@@ -212,12 +212,11 @@ static int __init us3_freq_init(void)
 		struct cpufreq_driver *driver;
 
 		ret = -ENOMEM;
-		driver = kzalloc(sizeof(struct cpufreq_driver), GFP_KERNEL);
+		driver = kzalloc(sizeof(*driver), GFP_KERNEL);
 		if (!driver)
 			goto err_out;
 
-		us3_freq_table = kzalloc(
-			(NR_CPUS * sizeof(struct us3_freq_percpu_info)),
+		us3_freq_table = kzalloc((NR_CPUS * sizeof(*us3_freq_table)),
 			GFP_KERNEL);
 		if (!us3_freq_table)
 			goto err_out;
@@ -227,7 +226,6 @@ static int __init us3_freq_init(void)
 		driver->target = us3_freq_target;
 		driver->get = us3_freq_get;
 		driver->exit = us3_freq_cpu_exit;
-		driver->owner = THIS_MODULE,
 		strcpy(driver->name, "UltraSPARC-III");
 
 		cpufreq_us3_driver = driver;

drivers/cpufreq/speedstep-centrino.c

@@ -575,7 +575,6 @@ static struct cpufreq_driver centrino_driver = {
 	.target		= centrino_target,
 	.get		= get_cur_freq,
 	.attr           = centrino_attr,
-	.owner		= THIS_MODULE,
 };
 
 /*

drivers/cpufreq/speedstep-ich.c

@@ -378,7 +378,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.init	= speedstep_cpu_init,
 	.exit	= speedstep_cpu_exit,
 	.get	= speedstep_get,
-	.owner	= THIS_MODULE,
 	.attr	= speedstep_attr,
 };
 

drivers/cpufreq/speedstep-smi.c

@@ -375,7 +375,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.exit		= speedstep_cpu_exit,
 	.get		= speedstep_get,
 	.resume		= speedstep_resume,
-	.owner		= THIS_MODULE,
 	.attr		= speedstep_attr,
 };
 

include/linux/cpufreq.h

@@ -11,71 +11,36 @@
 #ifndef _LINUX_CPUFREQ_H
 #define _LINUX_CPUFREQ_H
 
-#include <asm/cputime.h>
-#include <linux/mutex.h>
-#include <linux/notifier.h>
-#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/completion.h>
 #include <linux/kobject.h>
+#include <linux/notifier.h>
 #include <linux/sysfs.h>
-#include <linux/completion.h>
-#include <linux/workqueue.h>
-#include <linux/cpumask.h>
-#include <asm/div64.h>
-
-#define CPUFREQ_NAME_LEN 16
-/* Print length for names. Extra 1 space for accomodating '\n' in prints */
-#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1)
 
 /*********************************************************************
- *                     CPUFREQ NOTIFIER INTERFACE                    *
+ *                        CPUFREQ INTERFACE                          *
  *********************************************************************/
-
-#define CPUFREQ_TRANSITION_NOTIFIER	(0)
-#define CPUFREQ_POLICY_NOTIFIER		(1)
-
-#ifdef CONFIG_CPU_FREQ
-int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
-int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
-extern void disable_cpufreq(void);
-#else		/* CONFIG_CPU_FREQ */
-static inline int cpufreq_register_notifier(struct notifier_block *nb,
-						unsigned int list)
-{
-	return 0;
-}
-static inline int cpufreq_unregister_notifier(struct notifier_block *nb,
-						unsigned int list)
-{
-	return 0;
-}
-static inline void disable_cpufreq(void) { }
-#endif		/* CONFIG_CPU_FREQ */
-
-/* if (cpufreq_driver->target) exists, the ->governor decides what frequency
- * within the limits is used. If (cpufreq_driver->setpolicy> exists, these
- * two generic policies are available:
- */
-
-#define CPUFREQ_POLICY_POWERSAVE	(1)
-#define CPUFREQ_POLICY_PERFORMANCE	(2)
-
-/* Frequency values here are CPU kHz so that hardware which doesn't run
- * with some frequencies can complain without having to guess what per
- * cent / per mille means.
+/*
+ * Frequency values here are CPU kHz
+ *
  * Maximum transition latency is in nanoseconds - if it's unknown,
  * CPUFREQ_ETERNAL shall be used.
  */
 
+#define CPUFREQ_ETERNAL			(-1)
+#define CPUFREQ_NAME_LEN		16
+/* Print length for names. Extra 1 space for accomodating '\n' in prints */
+#define CPUFREQ_NAME_PLEN		(CPUFREQ_NAME_LEN + 1)
+
 struct cpufreq_governor;
 
-/* /sys/devices/system/cpu/cpufreq: entry point for global variables */
-extern struct kobject *cpufreq_global_kobject;
-int cpufreq_get_global_kobject(void);
-void cpufreq_put_global_kobject(void);
-int cpufreq_sysfs_create_file(const struct attribute *attr);
-void cpufreq_sysfs_remove_file(const struct attribute *attr);
+struct cpufreq_freqs {
+	unsigned int cpu;	/* cpu nr */
+	unsigned int old;
+	unsigned int new;
+	u8 flags;		/* flags of cpufreq_driver, see below. */
+};
 
-#define CPUFREQ_ETERNAL			(-1)
 struct cpufreq_cpuinfo {
 	unsigned int		max_freq;
 	unsigned int		min_freq;
@@ -117,123 +82,103 @@ struct cpufreq_policy {
 
 	struct cpufreq_real_policy	user_policy;
 
+	struct list_head        policy_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
 	int			transition_ongoing; /* Tracks transition status */
 };
 
-#define CPUFREQ_ADJUST			(0)
-#define CPUFREQ_INCOMPATIBLE		(1)
-#define CPUFREQ_NOTIFY			(2)
-#define CPUFREQ_START			(3)
-#define CPUFREQ_UPDATE_POLICY_CPU	(4)
-
 /* Only for ACPI */
 #define CPUFREQ_SHARED_TYPE_NONE (0) /* None */
 #define CPUFREQ_SHARED_TYPE_HW	 (1) /* HW does needed coordination */
 #define CPUFREQ_SHARED_TYPE_ALL	 (2) /* All dependent CPUs should set freq */
 #define CPUFREQ_SHARED_TYPE_ANY	 (3) /* Freq can be set from any dependent CPU*/
 
+struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
+void cpufreq_cpu_put(struct cpufreq_policy *policy);
+
 static inline bool policy_is_shared(struct cpufreq_policy *policy)
 {
 	return cpumask_weight(policy->cpus) > 1;
 }
 
-/******************** cpufreq transition notifiers *******************/
-
-#define CPUFREQ_PRECHANGE	(0)
-#define CPUFREQ_POSTCHANGE	(1)
-#define CPUFREQ_RESUMECHANGE	(8)
-#define CPUFREQ_SUSPENDCHANGE	(9)
+/* /sys/devices/system/cpu/cpufreq: entry point for global variables */
+extern struct kobject *cpufreq_global_kobject;
+int cpufreq_get_global_kobject(void);
+void cpufreq_put_global_kobject(void);
+int cpufreq_sysfs_create_file(const struct attribute *attr);
+void cpufreq_sysfs_remove_file(const struct attribute *attr);
 
-struct cpufreq_freqs {
-	unsigned int cpu;	/* cpu nr */
-	unsigned int old;
-	unsigned int new;
-	u8 flags;		/* flags of cpufreq_driver, see below. */
-};
+#ifdef CONFIG_CPU_FREQ
+unsigned int cpufreq_get(unsigned int cpu);
+unsigned int cpufreq_quick_get(unsigned int cpu);
+unsigned int cpufreq_quick_get_max(unsigned int cpu);
+void disable_cpufreq(void);
 
-/**
- * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch
- * safe)
- * @old:   old value
- * @div:   divisor
- * @mult:  multiplier
- *
- *
- * new = old * mult / div
- */
-static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
-		u_int mult)
+u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
+int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
+int cpufreq_update_policy(unsigned int cpu);
+bool have_governor_per_policy(void);
+struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
+#else
+static inline unsigned int cpufreq_get(unsigned int cpu)
 {
-#if BITS_PER_LONG == 32
-
-	u64 result = ((u64) old) * ((u64) mult);
-	do_div(result, div);
-	return (unsigned long) result;
-
-#elif BITS_PER_LONG == 64
-
-	unsigned long result = old * ((u64) mult);
-	result /= div;
-	return result;
-
+	return 0;
+}
+static inline unsigned int cpufreq_quick_get(unsigned int cpu)
+{
+	return 0;
+}
+static inline unsigned int cpufreq_quick_get_max(unsigned int cpu)
+{
+	return 0;
+}
+static inline void disable_cpufreq(void) { }
 #endif
-};
 
 /*********************************************************************
- *                          CPUFREQ GOVERNORS                        *
+ *                      CPUFREQ DRIVER INTERFACE                     *
  *********************************************************************/
 
-#define CPUFREQ_GOV_START	1
-#define CPUFREQ_GOV_STOP	2
-#define CPUFREQ_GOV_LIMITS	3
-#define CPUFREQ_GOV_POLICY_INIT	4
-#define CPUFREQ_GOV_POLICY_EXIT	5
+#define CPUFREQ_RELATION_L 0  /* lowest frequency at or above target */
+#define CPUFREQ_RELATION_H 1  /* highest frequency below or at target */
 
-struct cpufreq_governor {
-	char	name[CPUFREQ_NAME_LEN];
-	int	initialized;
-	int	(*governor)	(struct cpufreq_policy *policy,
-				 unsigned int event);
-	ssize_t	(*show_setspeed)	(struct cpufreq_policy *policy,
-					 char *buf);
-	int	(*store_setspeed)	(struct cpufreq_policy *policy,
-					 unsigned int freq);
-	unsigned int max_transition_latency; /* HW must be able to switch to
-			next freq faster than this value in nano secs or we
-			will fallback to performance governor */
-	struct list_head	governor_list;
-	struct module		*owner;
+struct freq_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct cpufreq_policy *, char *);
+	ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count);
 };
 
-/*
- * Pass a target to the cpufreq driver.
- */
-extern int cpufreq_driver_target(struct cpufreq_policy *policy,
-				 unsigned int target_freq,
-				 unsigned int relation);
-extern int __cpufreq_driver_target(struct cpufreq_policy *policy,
-				   unsigned int target_freq,
-				   unsigned int relation);
+#define cpufreq_freq_attr_ro(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0444, show_##_name, NULL)
 
-extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy,
-				   unsigned int cpu);
+#define cpufreq_freq_attr_ro_perm(_name, _perm)	\
+static struct freq_attr _name =			\
+__ATTR(_name, _perm, show_##_name, NULL)
 
-int cpufreq_register_governor(struct cpufreq_governor *governor);
-void cpufreq_unregister_governor(struct cpufreq_governor *governor);
+#define cpufreq_freq_attr_rw(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0644, show_##_name, store_##_name)
 
-/*********************************************************************
- *                      CPUFREQ DRIVER INTERFACE                     *
- *********************************************************************/
+struct global_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct kobject *kobj,
+			struct attribute *attr, char *buf);
+	ssize_t (*store)(struct kobject *a, struct attribute *b,
+			 const char *c, size_t count);
+};
 
-#define CPUFREQ_RELATION_L 0  /* lowest frequency at or above target */
-#define CPUFREQ_RELATION_H 1  /* highest frequency below or at target */
+#define define_one_global_ro(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define define_one_global_rw(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0644, show_##_name, store_##_name)
 
-struct freq_attr;
 
 struct cpufreq_driver {
-	struct module		*owner;
 	char			name[CPUFREQ_NAME_LEN];
 	u8			flags;
 	/*
@@ -258,8 +203,6 @@ struct cpufreq_driver {
 	unsigned int	(*get)	(unsigned int cpu);
 
 	/* optional */
-	unsigned int (*getavg)	(struct cpufreq_policy *policy,
-				 unsigned int cpu);
 	int	(*bios_limit)	(int cpu, unsigned int *limit);
 
 	int	(*exit)		(struct cpufreq_policy *policy);
@@ -269,7 +212,6 @@ struct cpufreq_driver {
 };
 
 /* flags */
-
 #define CPUFREQ_STICKY		0x01	/* the driver isn't removed even if
 					 * all ->init() calls failed */
 #define CPUFREQ_CONST_LOOPS	0x02	/* loops_per_jiffy or other kernel
@@ -281,8 +223,7 @@ struct cpufreq_driver {
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
-void cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state);
+const char *cpufreq_get_current_driver(void);
 
 static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
 		unsigned int min, unsigned int max)
@@ -300,86 +241,117 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
 	return;
 }
 
-struct freq_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct cpufreq_policy *, char *);
-	ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count);
-};
-
-#define cpufreq_freq_attr_ro(_name)		\
-static struct freq_attr _name =			\
-__ATTR(_name, 0444, show_##_name, NULL)
-
-#define cpufreq_freq_attr_ro_perm(_name, _perm)	\
-static struct freq_attr _name =			\
-__ATTR(_name, _perm, show_##_name, NULL)
-
-#define cpufreq_freq_attr_rw(_name)		\
-static struct freq_attr _name =			\
-__ATTR(_name, 0644, show_##_name, store_##_name)
+/*********************************************************************
+ *                     CPUFREQ NOTIFIER INTERFACE                    *
+ *********************************************************************/
 
-struct global_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct kobject *kobj,
-			struct attribute *attr, char *buf);
-	ssize_t (*store)(struct kobject *a, struct attribute *b,
-			 const char *c, size_t count);
-};
+#define CPUFREQ_TRANSITION_NOTIFIER	(0)
+#define CPUFREQ_POLICY_NOTIFIER		(1)
 
-#define define_one_global_ro(_name)		\
-static struct global_attr _name =		\
-__ATTR(_name, 0444, show_##_name, NULL)
+/* Transition notifiers */
+#define CPUFREQ_PRECHANGE		(0)
+#define CPUFREQ_POSTCHANGE		(1)
+#define CPUFREQ_RESUMECHANGE		(8)
+#define CPUFREQ_SUSPENDCHANGE		(9)
 
-#define define_one_global_rw(_name)		\
-static struct global_attr _name =		\
-__ATTR(_name, 0644, show_##_name, store_##_name)
+/* Policy Notifiers  */
+#define CPUFREQ_ADJUST			(0)
+#define CPUFREQ_INCOMPATIBLE		(1)
+#define CPUFREQ_NOTIFY			(2)
+#define CPUFREQ_START			(3)
+#define CPUFREQ_UPDATE_POLICY_CPU	(4)
 
-struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
-void cpufreq_cpu_put(struct cpufreq_policy *data);
-const char *cpufreq_get_current_driver(void);
+#ifdef CONFIG_CPU_FREQ
+int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
+int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
 
-/*********************************************************************
- *                        CPUFREQ 2.6. INTERFACE                     *
- *********************************************************************/
-u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
-int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
-int cpufreq_update_policy(unsigned int cpu);
-bool have_governor_per_policy(void);
-struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
+void cpufreq_notify_transition(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs, unsigned int state);
 
-#ifdef CONFIG_CPU_FREQ
-/*
- * query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it
- */
-unsigned int cpufreq_get(unsigned int cpu);
-#else
-static inline unsigned int cpufreq_get(unsigned int cpu)
+#else /* CONFIG_CPU_FREQ */
+static inline int cpufreq_register_notifier(struct notifier_block *nb,
+						unsigned int list)
 {
 	return 0;
 }
-#endif
-
-/*
- * query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it
- */
-#ifdef CONFIG_CPU_FREQ
-unsigned int cpufreq_quick_get(unsigned int cpu);
-unsigned int cpufreq_quick_get_max(unsigned int cpu);
-#else
-static inline unsigned int cpufreq_quick_get(unsigned int cpu)
+static inline int cpufreq_unregister_notifier(struct notifier_block *nb,
+						unsigned int list)
 {
 	return 0;
 }
-static inline unsigned int cpufreq_quick_get_max(unsigned int cpu)
+#endif /* !CONFIG_CPU_FREQ */
+
+/**
+ * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch
+ * safe)
+ * @old:   old value
+ * @div:   divisor
+ * @mult:  multiplier
+ *
+ *
+ * new = old * mult / div
+ */
+static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
+		u_int mult)
 {
-	return 0;
-}
+#if BITS_PER_LONG == 32
+	u64 result = ((u64) old) * ((u64) mult);
+	do_div(result, div);
+	return (unsigned long) result;
+
+#elif BITS_PER_LONG == 64
+	unsigned long result = old * ((u64) mult);
+	result /= div;
+	return result;
 #endif
+}
 
 /*********************************************************************
- *                       CPUFREQ DEFAULT GOVERNOR                    *
+ *                          CPUFREQ GOVERNORS                        *
  *********************************************************************/
 
+/*
+ * If (cpufreq_driver->target) exists, the ->governor decides what frequency
+ * within the limits is used. If (cpufreq_driver->setpolicy> exists, these
+ * two generic policies are available:
+ */
+#define CPUFREQ_POLICY_POWERSAVE	(1)
+#define CPUFREQ_POLICY_PERFORMANCE	(2)
+
+/* Governor Events */
+#define CPUFREQ_GOV_START	1
+#define CPUFREQ_GOV_STOP	2
+#define CPUFREQ_GOV_LIMITS	3
+#define CPUFREQ_GOV_POLICY_INIT	4
+#define CPUFREQ_GOV_POLICY_EXIT	5
+
+struct cpufreq_governor {
+	char	name[CPUFREQ_NAME_LEN];
+	int	initialized;
+	int	(*governor)	(struct cpufreq_policy *policy,
+				 unsigned int event);
+	ssize_t	(*show_setspeed)	(struct cpufreq_policy *policy,
+					 char *buf);
+	int	(*store_setspeed)	(struct cpufreq_policy *policy,
+					 unsigned int freq);
+	unsigned int max_transition_latency; /* HW must be able to switch to
+			next freq faster than this value in nano secs or we
+			will fallback to performance governor */
+	struct list_head	governor_list;
+	struct module		*owner;
+};
+
+/* Pass a target to the cpufreq driver */
+int cpufreq_driver_target(struct cpufreq_policy *policy,
+				 unsigned int target_freq,
+				 unsigned int relation);
+int __cpufreq_driver_target(struct cpufreq_policy *policy,
+				   unsigned int target_freq,
+				   unsigned int relation);
+int cpufreq_register_governor(struct cpufreq_governor *governor);
+void cpufreq_unregister_governor(struct cpufreq_governor *governor);
+
+/* CPUFREQ DEFAULT GOVERNOR */
 /*
  * Performance governor is fallback governor if any other gov failed to auto
  * load due latency restrictions
@@ -428,18 +400,16 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 				   unsigned int relation,
 				   unsigned int *index);
 
-/* the following 3 funtions are for cpufreq core use only */
+void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy);
+ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
+
+/* the following funtion is for cpufreq core use only */
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
-
 void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
-void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy);
-
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
 
-ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
-
 #endif /* _LINUX_CPUFREQ_H */