Creation of Cybook 2416 (actually Gen4) repository

drivers/cpufreq/Kconfig

@@ -0,0 +1,143 @@
+config CPU_FREQ
+	bool "CPU Frequency scaling"
+	help
+	  CPU Frequency scaling allows you to change the clock speed of 
+	  CPUs on the fly. This is a nice method to save power, because 
+	  the lower the CPU clock speed, the less power the CPU consumes.
+
+	  Note that this driver doesn't automatically change the CPU
+	  clock speed, you need to either enable a dynamic cpufreq governor
+	  (see below) after boot, or use a userspace tool.
+
+	  For details, take a look at <file:Documentation/cpu-freq>.
+
+	  If in doubt, say N.
+
+if CPU_FREQ
+
+config CPU_FREQ_TABLE
+       tristate
+
+config CPU_FREQ_DEBUG
+	bool "Enable CPUfreq debugging"
+	help
+	  Say Y here to enable CPUfreq subsystem (including drivers)
+	  debugging. You will need to activate it via the kernel
+	  command line by passing
+	     cpufreq.debug=<value>
+
+	  To get <value>, add 
+	       1 to activate CPUfreq core debugging,
+	       2 to activate CPUfreq drivers debugging, and
+	       4 to activate CPUfreq governor debugging
+
+config CPU_FREQ_STAT
+       tristate "CPU frequency translation statistics"
+       select CPU_FREQ_TABLE
+       default y
+       help
+         This driver exports CPU frequency statistics information through sysfs
+         file system
+
+config CPU_FREQ_STAT_DETAILS
+       bool "CPU frequency translation statistics details"
+       depends on CPU_FREQ_STAT
+       help
+         This will show detail CPU frequency translation table in sysfs file
+         system
+
+# Note that it is not currently possible to set the other governors (such as ondemand)
+# as the default, since if they fail to initialise, cpufreq will be
+# left in an undefined state.
+
+choice
+	prompt "Default CPUFreq governor"
+	default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110
+	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+	help
+	  This option sets which CPUFreq governor shall be loaded at
+	  startup. If in doubt, select 'performance'.
+
+config CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+	bool "performance"
+	select CPU_FREQ_GOV_PERFORMANCE
+	help
+	  Use the CPUFreq governor 'performance' as default. This sets
+	  the frequency statically to the highest frequency supported by
+	  the CPU.
+
+config CPU_FREQ_DEFAULT_GOV_USERSPACE
+	bool "userspace"
+	select CPU_FREQ_GOV_USERSPACE
+	help
+	  Use the CPUFreq governor 'userspace' as default. This allows
+	  you to set the CPU frequency manually or when an userspace 
+	  program shall be able to set the CPU dynamically without having
+	  to enable the userspace governor manually.
+
+endchoice
+
+config CPU_FREQ_GOV_PERFORMANCE
+       tristate "'performance' governor"
+       help
+	  This cpufreq governor sets the frequency statically to the
+	  highest available CPU frequency.
+
+	  If in doubt, say Y.
+
+config CPU_FREQ_GOV_POWERSAVE
+       tristate "'powersave' governor"
+       help
+	  This cpufreq governor sets the frequency statically to the
+	  lowest available CPU frequency.
+
+	  If in doubt, say Y.
+
+config CPU_FREQ_GOV_USERSPACE
+       tristate "'userspace' governor for userspace frequency scaling"
+       help
+	  Enable this cpufreq governor when you either want to set the
+	  CPU frequency manually or when an userspace program shall
+	  be able to set the CPU dynamically, like on LART 
+	  <http://www.lartmaker.nl/>.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say Y.
+
+config CPU_FREQ_GOV_ONDEMAND
+	tristate "'ondemand' cpufreq policy governor"
+	select CPU_FREQ_TABLE
+	help
+	  'ondemand' - This driver adds a dynamic cpufreq policy governor.
+	  The governor does a periodic polling and 
+	  changes frequency based on the CPU utilization.
+	  The support for this governor depends on CPU capability to
+	  do fast frequency switching (i.e, very low latency frequency
+	  transitions). 
+
+	  For details, take a look at linux/Documentation/cpu-freq.
+
+	  If in doubt, say N.
+
+config CPU_FREQ_GOV_CONSERVATIVE
+	tristate "'conservative' cpufreq governor"
+	depends on CPU_FREQ
+	help
+	  'conservative' - this driver is rather similar to the 'ondemand'
+	  governor both in its source code and its purpose, the difference is
+	  its optimisation for better suitability in a battery powered
+	  environment.  The frequency is gracefully increased and decreased
+	  rather than jumping to 100% when speed is required.
+
+	  If you have a desktop machine then you should really be considering
+	  the 'ondemand' governor instead, however if you are using a laptop,
+	  PDA or even an AMD64 based computer (due to the unacceptable
+	  step-by-step latency issues between the minimum and maximum frequency
+	  transitions in the CPU) you will probably want to use this governor.
+
+	  For details, take a look at linux/Documentation/cpu-freq.
+
+	  If in doubt, say N.
+
+endif	# CPU_FREQ

drivers/cpufreq/Makefile

@@ -0,0 +1,15 @@
+# CPUfreq core
+obj-$(CONFIG_CPU_FREQ)			+= cpufreq.o
+# CPUfreq stats
+obj-$(CONFIG_CPU_FREQ_STAT)             += cpufreq_stats.o
+
+# CPUfreq governors 
+obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE)	+= cpufreq_performance.o
+obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE)	+= cpufreq_powersave.o
+obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
+obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
+obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
+
+# CPUfreq cross-arch helpers
+obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o
+

drivers/cpufreq/cpufreq_conservative.c

@@ -0,0 +1,581 @@
+/*
+ *  drivers/cpufreq/cpufreq_conservative.c
+ *
+ *  Copyright (C)  2001 Russell King
+ *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *                      Jun Nakajima <jun.nakajima@intel.com>
+ *            (C)  2004 Alexander Clouter <alex-kernel@digriz.org.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ctype.h>
+#include <linux/cpufreq.h>
+#include <linux/sysctl.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/cpu.h>
+#include <linux/kmod.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+/*
+ * dbs is used in this file as a shortform for demandbased switching
+ * It helps to keep variable names smaller, simpler
+ */
+
+#define DEF_FREQUENCY_UP_THRESHOLD		(80)
+#define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
+
+/* 
+ * The polling frequency of this governor 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.
+ */
+static unsigned int 				def_sampling_rate;
+#define MIN_SAMPLING_RATE_RATIO			(2)
+/* for correct statistics, we need at least 10 ticks between each measure */
+#define MIN_STAT_SAMPLING_RATE			\
+			(MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
+#define MIN_SAMPLING_RATE			\
+			(def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
+#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
+#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
+#define DEF_SAMPLING_DOWN_FACTOR		(1)
+#define MAX_SAMPLING_DOWN_FACTOR		(10)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000)
+
+static void do_dbs_timer(struct work_struct *work);
+
+struct cpu_dbs_info_s {
+	struct cpufreq_policy 	*cur_policy;
+	unsigned int 		prev_cpu_idle_up;
+	unsigned int 		prev_cpu_idle_down;
+	unsigned int 		enable;
+	unsigned int		down_skip;
+	unsigned int		requested_freq;
+};
+static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
+
+static unsigned int dbs_enable;	/* number of CPUs using this policy */
+
+/*
+ * DEADLOCK ALERT! There is a ordering requirement between cpu_hotplug
+ * lock and dbs_mutex. cpu_hotplug lock should always be held before
+ * dbs_mutex. If any function that can potentially take cpu_hotplug lock
+ * (like __cpufreq_driver_target()) is being called with dbs_mutex taken, then
+ * cpu_hotplug lock should be taken before that. Note that cpu_hotplug lock
+ * is recursive for the same process. -Venki
+ */
+static DEFINE_MUTEX 	(dbs_mutex);
+static DECLARE_DELAYED_WORK(dbs_work, do_dbs_timer);
+
+struct dbs_tuners {
+	unsigned int 		sampling_rate;
+	unsigned int		sampling_down_factor;
+	unsigned int		up_threshold;
+	unsigned int		down_threshold;
+	unsigned int		ignore_nice;
+	unsigned int		freq_step;
+};
+
+static struct dbs_tuners dbs_tuners_ins = {
+	.up_threshold 		= DEF_FREQUENCY_UP_THRESHOLD,
+	.down_threshold 	= DEF_FREQUENCY_DOWN_THRESHOLD,
+	.sampling_down_factor 	= DEF_SAMPLING_DOWN_FACTOR,
+	.ignore_nice		= 0,
+	.freq_step		= 5,
+};
+
+static inline unsigned int get_cpu_idle_time(unsigned int cpu)
+{
+	unsigned int add_nice = 0, ret;
+
+	if (dbs_tuners_ins.ignore_nice)
+		add_nice = kstat_cpu(cpu).cpustat.nice;
+
+	ret = 	kstat_cpu(cpu).cpustat.idle +
+		kstat_cpu(cpu).cpustat.iowait +
+		add_nice;
+
+	return ret;
+}
+
+/************************** sysfs interface ************************/
+static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
+}
+
+static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MIN_SAMPLING_RATE);
+}
+
+#define define_one_ro(_name) 					\
+static struct freq_attr _name =  				\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+define_one_ro(sampling_rate_max);
+define_one_ro(sampling_rate_min);
+
+/* cpufreq_conservative Governor Tunables */
+#define show_one(file_name, object)					\
+static ssize_t show_##file_name						\
+(struct cpufreq_policy *unused, char *buf)				\
+{									\
+	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
+}
+show_one(sampling_rate, sampling_rate);
+show_one(sampling_down_factor, sampling_down_factor);
+show_one(up_threshold, up_threshold);
+show_one(down_threshold, down_threshold);
+show_one(ignore_nice_load, ignore_nice);
+show_one(freq_step, freq_step);
+
+static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
+		return -EINVAL;
+
+	mutex_lock(&dbs_mutex);
+	dbs_tuners_ins.sampling_down_factor = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_sampling_rate(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	mutex_lock(&dbs_mutex);
+	if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) {
+		mutex_unlock(&dbs_mutex);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.sampling_rate = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_up_threshold(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	mutex_lock(&dbs_mutex);
+	if (ret != 1 || input > 100 || input <= dbs_tuners_ins.down_threshold) {
+		mutex_unlock(&dbs_mutex);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.up_threshold = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_down_threshold(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	mutex_lock(&dbs_mutex);
+	if (ret != 1 || input > 100 || input >= dbs_tuners_ins.up_threshold) {
+		mutex_unlock(&dbs_mutex);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.down_threshold = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	unsigned int j;
+	
+	ret = sscanf (buf, "%u", &input);
+	if ( ret != 1 )
+		return -EINVAL;
+
+	if ( input > 1 )
+		input = 1;
+	
+	mutex_lock(&dbs_mutex);
+	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
+		mutex_unlock(&dbs_mutex);
+		return count;
+	}
+	dbs_tuners_ins.ignore_nice = input;
+
+	/* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */
+	for_each_online_cpu(j) {
+		struct cpu_dbs_info_s *j_dbs_info;
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
+	}
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_freq_step(struct cpufreq_policy *policy,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	ret = sscanf (buf, "%u", &input);
+
+	if ( ret != 1 )
+		return -EINVAL;
+
+	if ( input > 100 )
+		input = 100;
+	
+	/* no need to test here if freq_step is zero as the user might actually
+	 * want this, they would be crazy though :) */
+	mutex_lock(&dbs_mutex);
+	dbs_tuners_ins.freq_step = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+#define define_one_rw(_name) \
+static struct freq_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+define_one_rw(sampling_rate);
+define_one_rw(sampling_down_factor);
+define_one_rw(up_threshold);
+define_one_rw(down_threshold);
+define_one_rw(ignore_nice_load);
+define_one_rw(freq_step);
+
+static struct attribute * dbs_attributes[] = {
+	&sampling_rate_max.attr,
+	&sampling_rate_min.attr,
+	&sampling_rate.attr,
+	&sampling_down_factor.attr,
+	&up_threshold.attr,
+	&down_threshold.attr,
+	&ignore_nice_load.attr,
+	&freq_step.attr,
+	NULL
+};
+
+static struct attribute_group dbs_attr_group = {
+	.attrs = dbs_attributes,
+	.name = "conservative",
+};
+
+/************************** sysfs end ************************/
+
+static void dbs_check_cpu(int cpu)
+{
+	unsigned int idle_ticks, up_idle_ticks, down_idle_ticks;
+	unsigned int tmp_idle_ticks, total_idle_ticks;
+	unsigned int freq_step;
+	unsigned int freq_down_sampling_rate;
+	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+	struct cpufreq_policy *policy;
+
+	if (!this_dbs_info->enable)
+		return;
+
+	policy = this_dbs_info->cur_policy;
+
+	/* 
+	 * The default safe range is 20% to 80% 
+	 * Every sampling_rate, we check
+	 * 	- If current idle time is less than 20%, then we try to 
+	 * 	  increase frequency
+	 * Every sampling_rate*sampling_down_factor, we check
+	 * 	- If current idle time is more than 80%, then we try to
+	 * 	  decrease frequency
+	 *
+	 * Any frequency increase takes it to the maximum frequency. 
+	 * Frequency reduction happens at minimum steps of 
+	 * 5% (default) of max_frequency 
+	 */
+
+	/* Check for frequency increase */
+	idle_ticks = UINT_MAX;
+
+	/* Check for frequency increase */
+	total_idle_ticks = get_cpu_idle_time(cpu);
+	tmp_idle_ticks = total_idle_ticks -
+		this_dbs_info->prev_cpu_idle_up;
+	this_dbs_info->prev_cpu_idle_up = total_idle_ticks;
+
+	if (tmp_idle_ticks < idle_ticks)
+		idle_ticks = tmp_idle_ticks;
+
+	/* Scale idle ticks by 100 and compare with up and down ticks */
+	idle_ticks *= 100;
+	up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+
+	if (idle_ticks < up_idle_ticks) {
+		this_dbs_info->down_skip = 0;
+		this_dbs_info->prev_cpu_idle_down =
+			this_dbs_info->prev_cpu_idle_up;
+
+		/* if we are already at full speed then break out early */
+		if (this_dbs_info->requested_freq == policy->max)
+			return;
+		
+		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;
+
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_step == 0))
+			freq_step = 5;
+		
+		this_dbs_info->requested_freq += freq_step;
+		if (this_dbs_info->requested_freq > policy->max)
+			this_dbs_info->requested_freq = policy->max;
+
+		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
+			CPUFREQ_RELATION_H);
+		return;
+	}
+
+	/* Check for frequency decrease */
+	this_dbs_info->down_skip++;
+	if (this_dbs_info->down_skip < dbs_tuners_ins.sampling_down_factor)
+		return;
+
+	/* Check for frequency decrease */
+	total_idle_ticks = this_dbs_info->prev_cpu_idle_up;
+	tmp_idle_ticks = total_idle_ticks -
+		this_dbs_info->prev_cpu_idle_down;
+	this_dbs_info->prev_cpu_idle_down = total_idle_ticks;
+
+	if (tmp_idle_ticks < idle_ticks)
+		idle_ticks = tmp_idle_ticks;
+
+	/* Scale idle ticks by 100 and compare with up and down ticks */
+	idle_ticks *= 100;
+	this_dbs_info->down_skip = 0;
+
+	freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
+		dbs_tuners_ins.sampling_down_factor;
+	down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) *
+		usecs_to_jiffies(freq_down_sampling_rate);
+
+	if (idle_ticks > down_idle_ticks) {
+		/*
+		 * if we are already at the lowest speed then break out early
+		 * or if we 'cannot' reduce the speed as the user might want
+		 * freq_step to be zero
+		 */
+		if (this_dbs_info->requested_freq == policy->min
+				|| dbs_tuners_ins.freq_step == 0)
+			return;
+
+		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;
+
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_step == 0))
+			freq_step = 5;
+
+		this_dbs_info->requested_freq -= freq_step;
+		if (this_dbs_info->requested_freq < policy->min)
+			this_dbs_info->requested_freq = policy->min;
+
+		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
+				CPUFREQ_RELATION_H);
+		return;
+	}
+}
+
+static void do_dbs_timer(struct work_struct *work)
+{ 
+	int i;
+	mutex_lock(&dbs_mutex);
+	for_each_online_cpu(i)
+		dbs_check_cpu(i);
+	schedule_delayed_work(&dbs_work, 
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
+	mutex_unlock(&dbs_mutex);
+} 
+
+static inline void dbs_timer_init(void)
+{
+	schedule_delayed_work(&dbs_work,
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
+	return;
+}
+
+static inline void dbs_timer_exit(void)
+{
+	cancel_delayed_work(&dbs_work);
+	return;
+}
+
+static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+				   unsigned int event)
+{
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_info_s *this_dbs_info;
+	unsigned int j;
+	int rc;
+
+	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if ((!cpu_online(cpu)) || 
+		    (!policy->cur))
+			return -EINVAL;
+
+		if (policy->cpuinfo.transition_latency >
+				(TRANSITION_LATENCY_LIMIT * 1000))
+			return -EINVAL;
+		if (this_dbs_info->enable) /* Already enabled */
+			break;
+		 
+		mutex_lock(&dbs_mutex);
+
+		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group);
+		if (rc) {
+			mutex_unlock(&dbs_mutex);
+			return rc;
+		}
+
+		for_each_cpu_mask(j, policy->cpus) {
+			struct cpu_dbs_info_s *j_dbs_info;
+			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info->cur_policy = policy;
+		
+			j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(cpu);
+			j_dbs_info->prev_cpu_idle_down
+				= j_dbs_info->prev_cpu_idle_up;
+		}
+		this_dbs_info->enable = 1;
+		this_dbs_info->down_skip = 0;
+		this_dbs_info->requested_freq = policy->cur;
+
+		dbs_enable++;
+		/*
+		 * Start the timerschedule work, when this governor
+		 * is used for first time
+		 */
+		if (dbs_enable == 1) {
+			unsigned int latency;
+			/* policy latency is in nS. Convert it to uS first */
+			latency = policy->cpuinfo.transition_latency / 1000;
+			if (latency == 0)
+				latency = 1;
+
+			def_sampling_rate = 10 * latency *
+					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
+
+			if (def_sampling_rate < MIN_STAT_SAMPLING_RATE)
+				def_sampling_rate = MIN_STAT_SAMPLING_RATE;
+
+			dbs_tuners_ins.sampling_rate = def_sampling_rate;
+
+			dbs_timer_init();
+		}
+		
+		mutex_unlock(&dbs_mutex);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		mutex_lock(&dbs_mutex);
+		this_dbs_info->enable = 0;
+		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
+		dbs_enable--;
+		/*
+		 * Stop the timerschedule work, when this governor
+		 * is used for first time
+		 */
+		if (dbs_enable == 0) 
+			dbs_timer_exit();
+		
+		mutex_unlock(&dbs_mutex);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&dbs_mutex);
+		if (policy->max < this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(
+					this_dbs_info->cur_policy,
+				       	policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(
+					this_dbs_info->cur_policy,
+				       	policy->min, CPUFREQ_RELATION_L);
+		mutex_unlock(&dbs_mutex);
+		break;
+	}
+	return 0;
+}
+
+static struct cpufreq_governor cpufreq_gov_dbs = {
+	.name		= "conservative",
+	.governor	= cpufreq_governor_dbs,
+	.owner		= THIS_MODULE,
+};
+
+static int __init cpufreq_gov_dbs_init(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_dbs);
+}
+
+static void __exit cpufreq_gov_dbs_exit(void)
+{
+	/* Make sure that the scheduled work is indeed not running */
+	flush_scheduled_work();
+
+	cpufreq_unregister_governor(&cpufreq_gov_dbs);
+}
+
+
+MODULE_AUTHOR ("Alexander Clouter <alex-kernel@digriz.org.uk>");
+MODULE_DESCRIPTION ("'cpufreq_conservative' - A dynamic cpufreq governor for "
+		"Low Latency Frequency Transition capable processors "
+		"optimised for use in a battery environment");
+MODULE_LICENSE ("GPL");
+
+module_init(cpufreq_gov_dbs_init);
+module_exit(cpufreq_gov_dbs_exit);

drivers/cpufreq/cpufreq_ondemand.c

@@ -0,0 +1,607 @@
+/*
+ *  drivers/cpufreq/cpufreq_ondemand.c
+ *
+ *  Copyright (C)  2001 Russell King
+ *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *                      Jun Nakajima <jun.nakajima@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 <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+#include <linux/cpu.h>
+#include <linux/jiffies.h>
+#include <linux/kernel_stat.h>
+#include <linux/mutex.h>
+
+/*
+ * dbs is used in this file as a shortform for demandbased switching
+ * It helps to keep variable names smaller, simpler
+ */
+
+#define DEF_FREQUENCY_UP_THRESHOLD		(80)
+#define MIN_FREQUENCY_UP_THRESHOLD		(11)
+#define MAX_FREQUENCY_UP_THRESHOLD		(100)
+
+/*
+ * The polling frequency of this governor 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.
+ */
+static unsigned int def_sampling_rate;
+#define MIN_SAMPLING_RATE_RATIO			(2)
+/* for correct statistics, we need at least 10 ticks between each measure */
+#define MIN_STAT_SAMPLING_RATE 			\
+			(MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
+#define MIN_SAMPLING_RATE			\
+			(def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
+#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
+#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000)
+
+static void do_dbs_timer(struct work_struct *work);
+
+/* Sampling types */
+enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
+
+struct cpu_dbs_info_s {
+	cputime64_t prev_cpu_idle;
+	cputime64_t prev_cpu_wall;
+	struct cpufreq_policy *cur_policy;
+ 	struct delayed_work work;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_jiffies;
+	unsigned int freq_hi_jiffies;
+	int cpu;
+	unsigned int enable:1,
+	             sample_type:1;
+};
+static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
+
+static unsigned int dbs_enable;	/* number of CPUs using this policy */
+
+/*
+ * DEADLOCK ALERT! There is a ordering requirement between cpu_hotplug
+ * lock and dbs_mutex. cpu_hotplug lock should always be held before
+ * dbs_mutex. If any function that can potentially take cpu_hotplug lock
+ * (like __cpufreq_driver_target()) is being called with dbs_mutex taken, then
+ * cpu_hotplug lock should be taken before that. Note that cpu_hotplug lock
+ * is recursive for the same process. -Venki
+ */
+static DEFINE_MUTEX(dbs_mutex);
+
+static struct workqueue_struct	*kondemand_wq;
+
+static struct dbs_tuners {
+	unsigned int sampling_rate;
+	unsigned int up_threshold;
+	unsigned int ignore_nice;
+	unsigned int powersave_bias;
+} dbs_tuners_ins = {
+	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
+	.ignore_nice = 0,
+	.powersave_bias = 0,
+};
+
+static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
+{
+	cputime64_t retval;
+
+	retval = cputime64_add(kstat_cpu(cpu).cpustat.idle,
+			kstat_cpu(cpu).cpustat.iowait);
+
+	if (dbs_tuners_ins.ignore_nice)
+		retval = cputime64_add(retval, kstat_cpu(cpu).cpustat.nice);
+
+	return retval;
+}
+
+/*
+ * Find right freq to be set now with powersave_bias on.
+ * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
+ * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
+ */
+static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
+					  unsigned int freq_next,
+					  unsigned int relation)
+{
+	unsigned int freq_req, freq_reduc, freq_avg;
+	unsigned int freq_hi, freq_lo;
+	unsigned int index = 0;
+	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
+	struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, policy->cpu);
+
+	if (!dbs_info->freq_table) {
+		dbs_info->freq_lo = 0;
+		dbs_info->freq_lo_jiffies = 0;
+		return freq_next;
+	}
+
+	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
+			relation, &index);
+	freq_req = dbs_info->freq_table[index].frequency;
+	freq_reduc = freq_req * dbs_tuners_ins.powersave_bias / 1000;
+	freq_avg = freq_req - freq_reduc;
+
+	/* Find freq bounds for freq_avg in freq_table */
+	index = 0;
+	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
+			CPUFREQ_RELATION_H, &index);
+	freq_lo = dbs_info->freq_table[index].frequency;
+	index = 0;
+	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
+			CPUFREQ_RELATION_L, &index);
+	freq_hi = dbs_info->freq_table[index].frequency;
+
+	/* Find out how long we have to be in hi and lo freqs */
+	if (freq_hi == freq_lo) {
+		dbs_info->freq_lo = 0;
+		dbs_info->freq_lo_jiffies = 0;
+		return freq_lo;
+	}
+	jiffies_total = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
+	jiffies_hi += ((freq_hi - freq_lo) / 2);
+	jiffies_hi /= (freq_hi - freq_lo);
+	jiffies_lo = jiffies_total - jiffies_hi;
+	dbs_info->freq_lo = freq_lo;
+	dbs_info->freq_lo_jiffies = jiffies_lo;
+	dbs_info->freq_hi_jiffies = jiffies_hi;
+	return freq_hi;
+}
+
+static void ondemand_powersave_bias_init(void)
+{
+	int i;
+	for_each_online_cpu(i) {
+		struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, i);
+		dbs_info->freq_table = cpufreq_frequency_get_table(i);
+		dbs_info->freq_lo = 0;
+	}
+}
+
+/************************** sysfs interface ************************/
+static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
+}
+
+static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MIN_SAMPLING_RATE);
+}
+
+#define define_one_ro(_name)		\
+static struct freq_attr _name =		\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+define_one_ro(sampling_rate_max);
+define_one_ro(sampling_rate_min);
+
+/* cpufreq_ondemand Governor Tunables */
+#define show_one(file_name, object)					\
+static ssize_t show_##file_name						\
+(struct cpufreq_policy *unused, char *buf)				\
+{									\
+	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
+}
+show_one(sampling_rate, sampling_rate);
+show_one(up_threshold, up_threshold);
+show_one(ignore_nice_load, ignore_nice);
+show_one(powersave_bias, powersave_bias);
+
+static ssize_t store_sampling_rate(struct cpufreq_policy *unused,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+
+	mutex_lock(&dbs_mutex);
+	if (ret != 1 || input > MAX_SAMPLING_RATE
+		     || input < MIN_SAMPLING_RATE) {
+		mutex_unlock(&dbs_mutex);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.sampling_rate = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_up_threshold(struct cpufreq_policy *unused,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+
+	mutex_lock(&dbs_mutex);
+	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD ||
+			input < MIN_FREQUENCY_UP_THRESHOLD) {
+		mutex_unlock(&dbs_mutex);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.up_threshold = input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	unsigned int j;
+
+	ret = sscanf(buf, "%u", &input);
+	if ( ret != 1 )
+		return -EINVAL;
+
+	if ( input > 1 )
+		input = 1;
+
+	mutex_lock(&dbs_mutex);
+	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
+		mutex_unlock(&dbs_mutex);
+		return count;
+	}
+	dbs_tuners_ins.ignore_nice = input;
+
+	/* we need to re-evaluate prev_cpu_idle */
+	for_each_online_cpu(j) {
+		struct cpu_dbs_info_s *dbs_info;
+		dbs_info = &per_cpu(cpu_dbs_info, j);
+		dbs_info->prev_cpu_idle = get_cpu_idle_time(j);
+		dbs_info->prev_cpu_wall = get_jiffies_64();
+	}
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+static ssize_t store_powersave_bias(struct cpufreq_policy *unused,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+
+	if (ret != 1)
+		return -EINVAL;
+
+	if (input > 1000)
+		input = 1000;
+
+	mutex_lock(&dbs_mutex);
+	dbs_tuners_ins.powersave_bias = input;
+	ondemand_powersave_bias_init();
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
+#define define_one_rw(_name) \
+static struct freq_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+define_one_rw(sampling_rate);
+define_one_rw(up_threshold);
+define_one_rw(ignore_nice_load);
+define_one_rw(powersave_bias);
+
+static struct attribute * dbs_attributes[] = {
+	&sampling_rate_max.attr,
+	&sampling_rate_min.attr,
+	&sampling_rate.attr,
+	&up_threshold.attr,
+	&ignore_nice_load.attr,
+	&powersave_bias.attr,
+	NULL
+};
+
+static struct attribute_group dbs_attr_group = {
+	.attrs = dbs_attributes,
+	.name = "ondemand",
+};
+
+/************************** sysfs end ************************/
+
+static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
+{
+	unsigned int idle_ticks, total_ticks;
+	unsigned int load;
+	cputime64_t cur_jiffies;
+
+	struct cpufreq_policy *policy;
+	unsigned int j;
+
+	if (!this_dbs_info->enable)
+		return;
+
+	this_dbs_info->freq_lo = 0;
+	policy = this_dbs_info->cur_policy;
+	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
+	total_ticks = (unsigned int) cputime64_sub(cur_jiffies,
+			this_dbs_info->prev_cpu_wall);
+	this_dbs_info->prev_cpu_wall = cur_jiffies;
+	if (!total_ticks)
+		return;
+	/*
+	 * 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 a 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
+	 */
+
+	/* Get Idle Time */
+	idle_ticks = UINT_MAX;
+	for_each_cpu_mask(j, policy->cpus) {
+		cputime64_t total_idle_ticks;
+		unsigned int tmp_idle_ticks;
+		struct cpu_dbs_info_s *j_dbs_info;
+
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		total_idle_ticks = get_cpu_idle_time(j);
+		tmp_idle_ticks = (unsigned int) cputime64_sub(total_idle_ticks,
+				j_dbs_info->prev_cpu_idle);
+		j_dbs_info->prev_cpu_idle = total_idle_ticks;
+
+		if (tmp_idle_ticks < idle_ticks)
+			idle_ticks = tmp_idle_ticks;
+	}
+	load = (100 * (total_ticks - idle_ticks)) / total_ticks;
+
+	/* Check for frequency increase */
+	if (load > dbs_tuners_ins.up_threshold) {
+		/* if we are already at full speed then break out early */
+		if (!dbs_tuners_ins.powersave_bias) {
+			if (policy->cur == policy->max)
+				return;
+
+			__cpufreq_driver_target(policy, policy->max,
+				CPUFREQ_RELATION_H);
+		} else {
+			int freq = powersave_bias_target(policy, policy->max,
+					CPUFREQ_RELATION_H);
+			__cpufreq_driver_target(policy, freq,
+				CPUFREQ_RELATION_L);
+		}
+		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 < (dbs_tuners_ins.up_threshold - 10)) {
+		unsigned int freq_next, freq_cur;
+
+		freq_cur = __cpufreq_driver_getavg(policy);
+		if (!freq_cur)
+			freq_cur = policy->cur;
+
+		freq_next = (freq_cur * load) /
+			(dbs_tuners_ins.up_threshold - 10);
+
+		if (!dbs_tuners_ins.powersave_bias) {
+			__cpufreq_driver_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+		} else {
+			int freq = powersave_bias_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+			__cpufreq_driver_target(policy, freq,
+				CPUFREQ_RELATION_L);
+		}
+	}
+}
+
+static void do_dbs_timer(struct work_struct *work)
+{
+	struct cpu_dbs_info_s *dbs_info =
+		container_of(work, struct cpu_dbs_info_s, work.work);
+	unsigned int cpu = dbs_info->cpu;
+	int sample_type = dbs_info->sample_type;
+
+	/* We want all CPUs to do sampling nearly on same jiffy */
+	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+
+	delay -= jiffies % delay;
+
+	if (lock_policy_rwsem_write(cpu) < 0)
+		return;
+
+	if (!dbs_info->enable) {
+		unlock_policy_rwsem_write(cpu);
+		return;
+	}
+
+	/* Common NORMAL_SAMPLE setup */
+	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
+	if (!dbs_tuners_ins.powersave_bias ||
+	    sample_type == DBS_NORMAL_SAMPLE) {
+		dbs_check_cpu(dbs_info);
+		if (dbs_info->freq_lo) {
+			/* Setup timer for SUB_SAMPLE */
+			dbs_info->sample_type = DBS_SUB_SAMPLE;
+			delay = dbs_info->freq_hi_jiffies;
+		}
+	} else {
+		__cpufreq_driver_target(dbs_info->cur_policy,
+	                        	dbs_info->freq_lo,
+	                        	CPUFREQ_RELATION_H);
+	}
+	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
+	unlock_policy_rwsem_write(cpu);
+}
+
+static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
+{
+	/* We want all CPUs to do sampling nearly on same jiffy */
+	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+	delay -= jiffies % delay;
+
+	dbs_info->enable = 1;
+	ondemand_powersave_bias_init();
+	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
+	INIT_DELAYED_WORK(&dbs_info->work, do_dbs_timer);
+	queue_delayed_work_on(dbs_info->cpu, kondemand_wq, &dbs_info->work,
+	                      delay);
+}
+
+static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
+{
+	dbs_info->enable = 0;
+	cancel_delayed_work(&dbs_info->work);
+}
+
+static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+				   unsigned int event)
+{
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_info_s *this_dbs_info;
+	unsigned int j;
+	int rc;
+
+	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if ((!cpu_online(cpu)) || (!policy->cur))
+			return -EINVAL;
+
+		if (policy->cpuinfo.transition_latency >
+				(TRANSITION_LATENCY_LIMIT * 1000)) {
+			printk(KERN_WARNING "ondemand governor failed to load "
+			       "due to too long transition latency\n");
+			return -EINVAL;
+		}
+		if (this_dbs_info->enable) /* Already enabled */
+			break;
+
+		mutex_lock(&dbs_mutex);
+		dbs_enable++;
+
+		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group);
+		if (rc) {
+			dbs_enable--;
+			mutex_unlock(&dbs_mutex);
+			return rc;
+		}
+
+		for_each_cpu_mask(j, policy->cpus) {
+			struct cpu_dbs_info_s *j_dbs_info;
+			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info->cur_policy = policy;
+
+			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j);
+			j_dbs_info->prev_cpu_wall = get_jiffies_64();
+		}
+		this_dbs_info->cpu = cpu;
+		/*
+		 * Start the timerschedule work, when this governor
+		 * is used for first time
+		 */
+		if (dbs_enable == 1) {
+			unsigned int latency;
+			/* policy latency is in nS. Convert it to uS first */
+			latency = policy->cpuinfo.transition_latency / 1000;
+			if (latency == 0)
+				latency = 1;
+
+			def_sampling_rate = latency *
+					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
+
+			if (def_sampling_rate < MIN_STAT_SAMPLING_RATE)
+				def_sampling_rate = MIN_STAT_SAMPLING_RATE;
+
+			dbs_tuners_ins.sampling_rate = def_sampling_rate;
+		}
+		dbs_timer_init(this_dbs_info);
+
+		mutex_unlock(&dbs_mutex);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		mutex_lock(&dbs_mutex);
+		dbs_timer_exit(this_dbs_info);
+		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
+		dbs_enable--;
+		mutex_unlock(&dbs_mutex);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&dbs_mutex);
+		if (policy->max < this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(this_dbs_info->cur_policy,
+			                        policy->max,
+			                        CPUFREQ_RELATION_H);
+		else if (policy->min > this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(this_dbs_info->cur_policy,
+			                        policy->min,
+			                        CPUFREQ_RELATION_L);
+		mutex_unlock(&dbs_mutex);
+		break;
+	}
+	return 0;
+}
+
+static struct cpufreq_governor cpufreq_gov_dbs = {
+	.name = "ondemand",
+	.governor = cpufreq_governor_dbs,
+	.owner = THIS_MODULE,
+};
+
+static int __init cpufreq_gov_dbs_init(void)
+{
+	kondemand_wq = create_workqueue("kondemand");
+	if (!kondemand_wq) {
+		printk(KERN_ERR "Creation of kondemand failed\n");
+		return -EFAULT;
+	}
+	return cpufreq_register_governor(&cpufreq_gov_dbs);
+}
+
+static void __exit cpufreq_gov_dbs_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_dbs);
+	destroy_workqueue(kondemand_wq);
+}
+
+
+MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
+MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
+MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
+                   "Low Latency Frequency Transition capable processors");
+MODULE_LICENSE("GPL");
+
+module_init(cpufreq_gov_dbs_init);
+module_exit(cpufreq_gov_dbs_exit);
+

drivers/cpufreq/cpufreq_performance.c

@@ -0,0 +1,64 @@
+/*
+ *  linux/drivers/cpufreq/cpufreq_performance.c
+ *
+ *  Copyright (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufreq.h>
+#include <linux/init.h>
+
+#define dprintk(msg...) \
+	cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg)
+
+
+static int cpufreq_governor_performance(struct cpufreq_policy *policy,
+					unsigned int event)
+{
+	switch (event) {
+	case CPUFREQ_GOV_START:
+	case CPUFREQ_GOV_LIMITS:
+		dprintk("setting to %u kHz because of event %u\n",
+						policy->max, event);
+		__cpufreq_driver_target(policy, policy->max,
+						CPUFREQ_RELATION_H);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+struct cpufreq_governor cpufreq_gov_performance = {
+	.name		= "performance",
+	.governor	= cpufreq_governor_performance,
+	.owner		= THIS_MODULE,
+};
+EXPORT_SYMBOL(cpufreq_gov_performance);
+
+
+static int __init cpufreq_gov_performance_init(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_performance);
+}
+
+
+static void __exit cpufreq_gov_performance_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_performance);
+}
+
+
+MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
+MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
+MODULE_LICENSE("GPL");
+
+fs_initcall(cpufreq_gov_performance_init);
+module_exit(cpufreq_gov_performance_exit);

drivers/cpufreq/cpufreq_powersave.c

@@ -0,0 +1,62 @@
+/*
+ *  linux/drivers/cpufreq/cpufreq_powersave.c
+ *
+ *  Copyright (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufreq.h>
+#include <linux/init.h>
+
+#define dprintk(msg...) \
+	cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg)
+
+static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
+					unsigned int event)
+{
+	switch (event) {
+	case CPUFREQ_GOV_START:
+	case CPUFREQ_GOV_LIMITS:
+		dprintk("setting to %u kHz because of event %u\n",
+							policy->min, event);
+		__cpufreq_driver_target(policy, policy->min,
+						CPUFREQ_RELATION_L);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static struct cpufreq_governor cpufreq_gov_powersave = {
+	.name		= "powersave",
+	.governor	= cpufreq_governor_powersave,
+	.owner		= THIS_MODULE,
+};
+
+
+static int __init cpufreq_gov_powersave_init(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_powersave);
+}
+
+
+static void __exit cpufreq_gov_powersave_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_powersave);
+}
+
+
+MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
+MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
+MODULE_LICENSE("GPL");
+
+module_init(cpufreq_gov_powersave_init);
+module_exit(cpufreq_gov_powersave_exit);

drivers/cpufreq/cpufreq_stats.c

@@ -0,0 +1,385 @@
+/*
+ *  drivers/cpufreq/cpufreq_stats.c
+ *
+ *  Copyright (C) 2003-2004 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *	      (C) 2004 Zou Nan hai <nanhai.zou@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 <linux/kernel.h>
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/sysfs.h>
+#include <linux/cpufreq.h>
+#include <linux/jiffies.h>
+#include <linux/percpu.h>
+#include <linux/kobject.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <asm/cputime.h>
+
+static spinlock_t cpufreq_stats_lock;
+
+#define CPUFREQ_STATDEVICE_ATTR(_name,_mode,_show) \
+static struct freq_attr _attr_##_name = {\
+	.attr = {.name = __stringify(_name), .owner = THIS_MODULE, \
+		.mode = _mode, }, \
+	.show = _show,\
+};
+
+struct cpufreq_stats {
+	unsigned int cpu;
+	unsigned int total_trans;
+	unsigned long long  last_time;
+	unsigned int max_state;
+	unsigned int state_num;
+	unsigned int last_index;
+	cputime64_t *time_in_state;
+	unsigned int *freq_table;
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	unsigned int *trans_table;
+#endif
+};
+
+static struct cpufreq_stats *cpufreq_stats_table[NR_CPUS];
+
+struct cpufreq_stats_attribute {
+	struct attribute attr;
+	ssize_t(*show) (struct cpufreq_stats *, char *);
+};
+
+static int
+cpufreq_stats_update (unsigned int cpu)
+{
+	struct cpufreq_stats *stat;
+	unsigned long long cur_time;
+
+	cur_time = get_jiffies_64();
+	spin_lock(&cpufreq_stats_lock);
+	stat = cpufreq_stats_table[cpu];
+	if (stat->time_in_state)
+		stat->time_in_state[stat->last_index] =
+			cputime64_add(stat->time_in_state[stat->last_index],
+				      cputime_sub(cur_time, stat->last_time));
+	stat->last_time = cur_time;
+	spin_unlock(&cpufreq_stats_lock);
+	return 0;
+}
+
+static ssize_t
+show_total_trans(struct cpufreq_policy *policy, char *buf)
+{
+	struct cpufreq_stats *stat = cpufreq_stats_table[policy->cpu];
+	if (!stat)
+		return 0;
+	return sprintf(buf, "%d\n",
+			cpufreq_stats_table[stat->cpu]->total_trans);
+}
+
+static ssize_t
+show_time_in_state(struct cpufreq_policy *policy, char *buf)
+{
+	ssize_t len = 0;
+	int i;
+	struct cpufreq_stats *stat = cpufreq_stats_table[policy->cpu];
+	if (!stat)
+		return 0;
+	cpufreq_stats_update(stat->cpu);
+	for (i = 0; i < stat->state_num; i++) {
+		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
+			(unsigned long long)cputime64_to_clock_t(stat->time_in_state[i]));
+	}
+	return len;
+}
+
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+static ssize_t
+show_trans_table(struct cpufreq_policy *policy, char *buf)
+{
+	ssize_t len = 0;
+	int i, j;
+
+	struct cpufreq_stats *stat = cpufreq_stats_table[policy->cpu];
+	if (!stat)
+		return 0;
+	cpufreq_stats_update(stat->cpu);
+	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
+	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
+	for (i = 0; i < stat->state_num; i++) {
+		if (len >= PAGE_SIZE)
+			break;
+		len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
+				stat->freq_table[i]);
+	}
+	if (len >= PAGE_SIZE)
+		return len;
+
+	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+
+	for (i = 0; i < stat->state_num; i++) {
+		if (len >= PAGE_SIZE)
+			break;
+
+		len += snprintf(buf + len, PAGE_SIZE - len, "%9u: ",
+				stat->freq_table[i]);
+
+		for (j = 0; j < stat->state_num; j++)   {
+			if (len >= PAGE_SIZE)
+				break;
+			len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
+					stat->trans_table[i*stat->max_state+j]);
+		}
+		len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+	}
+	return len;
+}
+CPUFREQ_STATDEVICE_ATTR(trans_table,0444,show_trans_table);
+#endif
+
+CPUFREQ_STATDEVICE_ATTR(total_trans,0444,show_total_trans);
+CPUFREQ_STATDEVICE_ATTR(time_in_state,0444,show_time_in_state);
+
+static struct attribute *default_attrs[] = {
+	&_attr_total_trans.attr,
+	&_attr_time_in_state.attr,
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	&_attr_trans_table.attr,
+#endif
+	NULL
+};
+static struct attribute_group stats_attr_group = {
+	.attrs = default_attrs,
+	.name = "stats"
+};
+
+static int
+freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
+{
+	int index;
+	for (index = 0; index < stat->max_state; index++)
+		if (stat->freq_table[index] == freq)
+			return index;
+	return -1;
+}
+
+static void
+cpufreq_stats_free_table (unsigned int cpu)
+{
+	struct cpufreq_stats *stat = cpufreq_stats_table[cpu];
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	if (policy && policy->cpu == cpu)
+		sysfs_remove_group(&policy->kobj, &stats_attr_group);
+	if (stat) {
+		kfree(stat->time_in_state);
+		kfree(stat);
+	}
+	cpufreq_stats_table[cpu] = NULL;
+	if (policy)
+		cpufreq_cpu_put(policy);
+}
+
+static int
+cpufreq_stats_create_table (struct cpufreq_policy *policy,
+		struct cpufreq_frequency_table *table)
+{
+	unsigned int i, j, count = 0, ret = 0;
+	struct cpufreq_stats *stat;
+	struct cpufreq_policy *data;
+	unsigned int alloc_size;
+	unsigned int cpu = policy->cpu;
+	if (cpufreq_stats_table[cpu])
+		return -EBUSY;
+	if ((stat = kzalloc(sizeof(struct cpufreq_stats), GFP_KERNEL)) == NULL)
+		return -ENOMEM;
+
+	data = cpufreq_cpu_get(cpu);
+	if (data == NULL) {
+		ret = -EINVAL;
+		goto error_get_fail;
+	}
+
+	if ((ret = sysfs_create_group(&data->kobj, &stats_attr_group)))
+		goto error_out;
+
+	stat->cpu = cpu;
+	cpufreq_stats_table[cpu] = stat;
+
+	for (i=0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+		count++;
+	}
+
+	alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);
+
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	alloc_size += count * count * sizeof(int);
+#endif
+	stat->max_state = count;
+	stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
+	if (!stat->time_in_state) {
+		ret = -ENOMEM;
+		goto error_out;
+	}
+	stat->freq_table = (unsigned int *)(stat->time_in_state + count);
+
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	stat->trans_table = stat->freq_table + count;
+#endif
+	j = 0;
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+		if (freq_table_get_index(stat, freq) == -1)
+			stat->freq_table[j++] = freq;
+	}
+	stat->state_num = j;
+	spin_lock(&cpufreq_stats_lock);
+	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);
+	return 0;
+error_out:
+	cpufreq_cpu_put(data);
+error_get_fail:
+	kfree(stat);
+	cpufreq_stats_table[cpu] = NULL;
+	return ret;
+}
+
+static int
+cpufreq_stat_notifier_policy (struct notifier_block *nb, unsigned long val,
+		void *data)
+{
+	int ret;
+	struct cpufreq_policy *policy = data;
+	struct cpufreq_frequency_table *table;
+	unsigned int cpu = policy->cpu;
+	if (val != CPUFREQ_NOTIFY)
+		return 0;
+	table = cpufreq_frequency_get_table(cpu);
+	if (!table)
+		return 0;
+	if ((ret = cpufreq_stats_create_table(policy, table)))
+		return ret;
+	return 0;
+}
+
+static int
+cpufreq_stat_notifier_trans (struct notifier_block *nb, unsigned long val,
+		void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct cpufreq_stats *stat;
+	int old_index, new_index;
+
+	if (val != CPUFREQ_POSTCHANGE)
+		return 0;
+
+	stat = cpufreq_stats_table[freq->cpu];
+	if (!stat)
+		return 0;
+
+	old_index = freq_table_get_index(stat, freq->old);
+	new_index = freq_table_get_index(stat, freq->new);
+
+	cpufreq_stats_update(freq->cpu);
+	if (old_index == new_index)
+		return 0;
+
+	if (old_index == -1 || new_index == -1)
+		return 0;
+
+	spin_lock(&cpufreq_stats_lock);
+	stat->last_index = new_index;
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	stat->trans_table[old_index * stat->max_state + new_index]++;
+#endif
+	stat->total_trans++;
+	spin_unlock(&cpufreq_stats_lock);
+	return 0;
+}
+
+static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+		cpufreq_update_policy(cpu);
+		break;
+	case CPU_DEAD:
+		cpufreq_stats_free_table(cpu);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_stat_cpu_notifier =
+{
+	.notifier_call = cpufreq_stat_cpu_callback,
+};
+
+static struct notifier_block notifier_policy_block = {
+	.notifier_call = cpufreq_stat_notifier_policy
+};
+
+static struct notifier_block notifier_trans_block = {
+	.notifier_call = cpufreq_stat_notifier_trans
+};
+
+static int
+__init cpufreq_stats_init(void)
+{
+	int ret;
+	unsigned int cpu;
+
+	spin_lock_init(&cpufreq_stats_lock);
+	if ((ret = cpufreq_register_notifier(&notifier_policy_block,
+				CPUFREQ_POLICY_NOTIFIER)))
+		return ret;
+
+	if ((ret = cpufreq_register_notifier(&notifier_trans_block,
+				CPUFREQ_TRANSITION_NOTIFIER))) {
+		cpufreq_unregister_notifier(&notifier_policy_block,
+				CPUFREQ_POLICY_NOTIFIER);
+		return ret;
+	}
+
+	register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
+	for_each_online_cpu(cpu) {
+		cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier,
+				CPU_ONLINE, (void *)(long)cpu);
+	}
+	return 0;
+}
+static void
+__exit cpufreq_stats_exit(void)
+{
+	unsigned int cpu;
+
+	cpufreq_unregister_notifier(&notifier_policy_block,
+			CPUFREQ_POLICY_NOTIFIER);
+	cpufreq_unregister_notifier(&notifier_trans_block,
+			CPUFREQ_TRANSITION_NOTIFIER);
+	unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
+	for_each_online_cpu(cpu) {
+		cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier,
+						CPU_DEAD, (void *)(long)cpu);
+	}
+}
+
+MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>");
+MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats"
+				"through sysfs filesystem");
+MODULE_LICENSE ("GPL");
+
+module_init(cpufreq_stats_init);
+module_exit(cpufreq_stats_exit);

drivers/cpufreq/cpufreq_userspace.c

@@ -0,0 +1,218 @@
+
+/*
+ *  linux/drivers/cpufreq/cpufreq_userspace.c
+ *
+ *  Copyright (C)  2001 Russell King
+ *            (C)  2002 - 2004 Dominik Brodowski <linux@brodo.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/cpufreq.h>
+#include <linux/cpu.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/mutex.h>
+
+#include <asm/uaccess.h>
+
+
+/**
+ * A few values needed by the userspace governor
+ */
+static unsigned int	cpu_max_freq[NR_CPUS];
+static unsigned int	cpu_min_freq[NR_CPUS];
+static unsigned int	cpu_cur_freq[NR_CPUS]; /* current CPU freq */
+static unsigned int	cpu_set_freq[NR_CPUS]; /* CPU freq desired by userspace */
+static unsigned int	cpu_is_managed[NR_CPUS];
+
+static DEFINE_MUTEX	(userspace_mutex);
+
+#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "userspace", msg)
+
+/* keep track of frequency transitions */
+static int
+userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+                       void *data)
+{
+        struct cpufreq_freqs *freq = data;
+
+	dprintk("saving cpu_cur_freq of cpu %u to be %u kHz\n", freq->cpu, freq->new);
+	cpu_cur_freq[freq->cpu] = freq->new;
+
+        return 0;
+}
+
+static struct notifier_block userspace_cpufreq_notifier_block = {
+        .notifier_call  = userspace_cpufreq_notifier
+};
+
+
+/**
+ * cpufreq_set - set the CPU frequency
+ * @freq: target frequency in kHz
+ * @cpu: CPU for which the frequency is to be set
+ *
+ * Sets the CPU frequency to freq.
+ */
+static int cpufreq_set(unsigned int freq, struct cpufreq_policy *policy)
+{
+	int ret = -EINVAL;
+
+	dprintk("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
+
+	mutex_lock(&userspace_mutex);
+	if (!cpu_is_managed[policy->cpu])
+		goto err;
+
+	cpu_set_freq[policy->cpu] = freq;
+
+	if (freq < cpu_min_freq[policy->cpu])
+		freq = cpu_min_freq[policy->cpu];
+	if (freq > cpu_max_freq[policy->cpu])
+		freq = cpu_max_freq[policy->cpu];
+
+	/*
+	 * We're safe from concurrent calls to ->target() here
+	 * as we hold the userspace_mutex lock. If we were calling
+	 * cpufreq_driver_target, a deadlock situation might occur:
+	 * A: cpufreq_set (lock userspace_mutex) -> cpufreq_driver_target(lock policy->lock)
+	 * B: cpufreq_set_policy(lock policy->lock) -> __cpufreq_governor -> cpufreq_governor_userspace (lock userspace_mutex)
+	 */
+	ret = __cpufreq_driver_target(policy, freq, CPUFREQ_RELATION_L);
+
+ err:
+	mutex_unlock(&userspace_mutex);
+	return ret;
+}
+
+
+/************************** sysfs interface ************************/
+static ssize_t show_speed (struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", cpu_cur_freq[policy->cpu]);
+}
+
+static ssize_t
+store_speed (struct cpufreq_policy *policy, const char *buf, size_t count)
+{
+	unsigned int freq = 0;
+	unsigned int ret;
+
+	ret = sscanf (buf, "%u", &freq);
+	if (ret != 1)
+		return -EINVAL;
+
+	cpufreq_set(freq, policy);
+
+	return count;
+}
+
+static struct freq_attr freq_attr_scaling_setspeed =
+{
+	.attr = { .name = "scaling_setspeed", .mode = 0644, .owner = THIS_MODULE },
+	.show = show_speed,
+	.store = store_speed,
+};
+
+static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
+				   unsigned int event)
+{
+	unsigned int cpu = policy->cpu;
+	int rc = 0;
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if (!cpu_online(cpu))
+			return -EINVAL;
+		BUG_ON(!policy->cur);
+		mutex_lock(&userspace_mutex);
+		rc = sysfs_create_file (&policy->kobj,
+					&freq_attr_scaling_setspeed.attr);
+		if (rc)
+			goto start_out;
+
+		cpu_is_managed[cpu] = 1;
+		cpu_min_freq[cpu] = policy->min;
+		cpu_max_freq[cpu] = policy->max;
+		cpu_cur_freq[cpu] = policy->cur;
+		cpu_set_freq[cpu] = policy->cur;
+		dprintk("managing cpu %u started (%u - %u kHz, currently %u kHz)\n", cpu, cpu_min_freq[cpu], cpu_max_freq[cpu], cpu_cur_freq[cpu]);
+start_out:
+		mutex_unlock(&userspace_mutex);
+		break;
+	case CPUFREQ_GOV_STOP:
+		mutex_lock(&userspace_mutex);
+		cpu_is_managed[cpu] = 0;
+		cpu_min_freq[cpu] = 0;
+		cpu_max_freq[cpu] = 0;
+		cpu_set_freq[cpu] = 0;
+		sysfs_remove_file (&policy->kobj, &freq_attr_scaling_setspeed.attr);
+		dprintk("managing cpu %u stopped\n", cpu);
+		mutex_unlock(&userspace_mutex);
+		break;
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&userspace_mutex);
+		dprintk("limit event for cpu %u: %u - %u kHz,"
+			"currently %u kHz, last set to %u kHz\n",
+			cpu, policy->min, policy->max,
+			cpu_cur_freq[cpu], cpu_set_freq[cpu]);
+		if (policy->max < cpu_set_freq[cpu]) {
+			__cpufreq_driver_target(policy, policy->max,
+						CPUFREQ_RELATION_H);
+		}
+		else if (policy->min > cpu_set_freq[cpu]) {
+			__cpufreq_driver_target(policy, policy->min,
+						CPUFREQ_RELATION_L);
+		}
+		else {
+			__cpufreq_driver_target(policy, cpu_set_freq[cpu],
+						CPUFREQ_RELATION_L);
+		}
+		cpu_min_freq[cpu] = policy->min;
+		cpu_max_freq[cpu] = policy->max;
+		cpu_cur_freq[cpu] = policy->cur;
+		mutex_unlock(&userspace_mutex);
+		break;
+	}
+	return rc;
+}
+
+
+struct cpufreq_governor cpufreq_gov_userspace = {
+	.name		= "userspace",
+	.governor	= cpufreq_governor_userspace,
+	.owner		= THIS_MODULE,
+};
+EXPORT_SYMBOL(cpufreq_gov_userspace);
+
+static int __init cpufreq_gov_userspace_init(void)
+{
+	cpufreq_register_notifier(&userspace_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER);
+	return cpufreq_register_governor(&cpufreq_gov_userspace);
+}
+
+
+static void __exit cpufreq_gov_userspace_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_userspace);
+        cpufreq_unregister_notifier(&userspace_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER);
+}
+
+
+MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>, Russell King <rmk@arm.linux.org.uk>");
+MODULE_DESCRIPTION ("CPUfreq policy governor 'userspace'");
+MODULE_LICENSE ("GPL");
+
+fs_initcall(cpufreq_gov_userspace_init);
+module_exit(cpufreq_gov_userspace_exit);

drivers/cpufreq/freq_table.c

@@ -0,0 +1,235 @@
+/*
+ * linux/drivers/cpufreq/freq_table.c
+ *
+ * Copyright (C) 2002 - 2003 Dominik Brodowski
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+
+#define dprintk(msg...) \
+	cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg)
+
+/*********************************************************************
+ *                     FREQUENCY TABLE HELPERS                       *
+ *********************************************************************/
+
+int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
+				    struct cpufreq_frequency_table *table)
+{
+	unsigned int min_freq = ~0;
+	unsigned int max_freq = 0;
+	unsigned int i;
+
+	for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID) {
+			dprintk("table entry %u is invalid, skipping\n", i);
+
+			continue;
+		}
+		dprintk("table entry %u: %u kHz, %u index\n",
+					i, freq, table[i].index);
+		if (freq < min_freq)
+			min_freq = freq;
+		if (freq > max_freq)
+			max_freq = freq;
+	}
+
+	policy->min = policy->cpuinfo.min_freq = min_freq;
+	policy->max = policy->cpuinfo.max_freq = max_freq;
+
+	if (policy->min == ~0)
+		return -EINVAL;
+	else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_table_cpuinfo);
+
+
+int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
+				   struct cpufreq_frequency_table *table)
+{
+	unsigned int next_larger = ~0;
+	unsigned int i;
+	unsigned int count = 0;
+
+	dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n",
+					policy->min, policy->max, policy->cpu);
+
+	if (!cpu_online(policy->cpu))
+		return -EINVAL;
+
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
+
+	for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+		if ((freq >= policy->min) && (freq <= policy->max))
+			count++;
+		else if ((next_larger > freq) && (freq > policy->max))
+			next_larger = freq;
+	}
+
+	if (!count)
+		policy->max = next_larger;
+
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
+
+	dprintk("verification lead to (%u - %u kHz) for cpu %u\n",
+				policy->min, policy->max, policy->cpu);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
+
+
+int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
+				   struct cpufreq_frequency_table *table,
+				   unsigned int target_freq,
+				   unsigned int relation,
+				   unsigned int *index)
+{
+	struct cpufreq_frequency_table optimal = {
+		.index = ~0,
+		.frequency = 0,
+	};
+	struct cpufreq_frequency_table suboptimal = {
+		.index = ~0,
+		.frequency = 0,
+	};
+	unsigned int i;
+
+	dprintk("request for target %u kHz (relation: %u) for cpu %u\n",
+					target_freq, relation, policy->cpu);
+
+	switch (relation) {
+	case CPUFREQ_RELATION_H:
+		suboptimal.frequency = ~0;
+		break;
+	case CPUFREQ_RELATION_L:
+		optimal.frequency = ~0;
+		break;
+	}
+
+	if (!cpu_online(policy->cpu))
+		return -EINVAL;
+
+	for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+		if ((freq < policy->min) || (freq > policy->max))
+			continue;
+		switch(relation) {
+		case CPUFREQ_RELATION_H:
+			if (freq <= target_freq) {
+				if (freq >= optimal.frequency) {
+					optimal.frequency = freq;
+					optimal.index = i;
+				}
+			} else {
+				if (freq <= suboptimal.frequency) {
+					suboptimal.frequency = freq;
+					suboptimal.index = i;
+				}
+			}
+			break;
+		case CPUFREQ_RELATION_L:
+			if (freq >= target_freq) {
+				if (freq <= optimal.frequency) {
+					optimal.frequency = freq;
+					optimal.index = i;
+				}
+			} else {
+				if (freq >= suboptimal.frequency) {
+					suboptimal.frequency = freq;
+					suboptimal.index = i;
+				}
+			}
+			break;
+		}
+	}
+	if (optimal.index > i) {
+		if (suboptimal.index > i)
+			return -EINVAL;
+		*index = suboptimal.index;
+	} else
+		*index = optimal.index;
+
+	dprintk("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
+		table[*index].index);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
+
+static struct cpufreq_frequency_table *show_table[NR_CPUS];
+/**
+ * show_scaling_governor - show the current policy for the specified CPU
+ */
+static ssize_t show_available_freqs (struct cpufreq_policy *policy, char *buf)
+{
+	unsigned int i = 0;
+	unsigned int cpu = policy->cpu;
+	ssize_t count = 0;
+	struct cpufreq_frequency_table *table;
+
+	if (!show_table[cpu])
+		return -ENODEV;
+
+	table = show_table[cpu];
+
+	for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
+		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
+			continue;
+		count += sprintf(&buf[count], "%d ", table[i].frequency);
+	}
+	count += sprintf(&buf[count], "\n");
+
+	return count;
+
+}
+
+struct freq_attr cpufreq_freq_attr_scaling_available_freqs = {
+	.attr = { .name = "scaling_available_frequencies",
+		  .mode = 0444,
+		  .owner=THIS_MODULE
+		},
+	.show = show_available_freqs,
+};
+EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
+
+/*
+ * if you use these, you must assure that the frequency table is valid
+ * all the time between get_attr and put_attr!
+ */
+void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
+				      unsigned int cpu)
+{
+	dprintk("setting show_table for cpu %u to %p\n", cpu, table);
+	show_table[cpu] = table;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_attr);
+
+void cpufreq_frequency_table_put_attr(unsigned int cpu)
+{
+	dprintk("clearing show_table for cpu %u\n", cpu);
+	show_table[cpu] = NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
+
+struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
+{
+	return show_table[cpu];
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
+
+MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>");
+MODULE_DESCRIPTION ("CPUfreq frequency table helpers");
+MODULE_LICENSE ("GPL");