1 files changed, 211 insertions, 415 deletions

diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 93eb5cbcc1f6..a6ecc203f7b7 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -1,371 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  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.
  */
 
 #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 <linux/sched/cpufreq.h>
 
-#include "cpufreq_governor.h"
+#include "cpufreq_ondemand.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)
+#define MIN_FREQUENCY_UP_THRESHOLD		(1)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
-static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info);
-
 static struct od_ops od_ops;
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static struct cpufreq_governor cpufreq_gov_ondemand;
-#endif
-
 static unsigned int default_powersave_bias;
 
-static void ondemand_powersave_bias_init_cpu(int cpu)
-{
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-
-	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
-	dbs_info->freq_lo = 0;
-}
-
-/*
- * Not all CPUs want IO time to be accounted as busy; this depends on how
- * efficient idling at a higher frequency/voltage is.
- * Pavel Machek says this is not so for various generations of AMD and old
- * Intel systems.
- * Mike Chan (android.com) claims this is also not true for ARM.
- * Because of this, whitelist specific known (series) of CPUs by default, and
- * leave all others up to the user.
- */
-static int should_io_be_busy(void)
-{
-#if defined(CONFIG_X86)
-	/*
-	 * For Intel, Core 2 (model 15) and later have an efficient idle.
-	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-			boot_cpu_data.x86 == 6 &&
-			boot_cpu_data.x86_model >= 15)
-		return 1;
-#endif
-	return 0;
-}
-
 /*
  * 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.
+ * Returns the freq_hi to be used right now and will set freq_hi_delay_us,
+ * freq_lo, and freq_lo_delay_us in percpu area for averaging freqs.
  */
 static unsigned int generic_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 od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-						   policy->cpu);
-	struct dbs_data *dbs_data = policy->governor_data;
+	unsigned int index;
+	unsigned int delay_hi_us;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
 
-	if (!dbs_info->freq_table) {
+	if (!freq_table) {
 		dbs_info->freq_lo = 0;
-		dbs_info->freq_lo_jiffies = 0;
+		dbs_info->freq_lo_delay_us = 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;
+	index = cpufreq_frequency_table_target(policy, freq_next, policy->min,
+					       policy->max, relation);
+	freq_req = freq_table[index].frequency;
 	freq_reduc = freq_req * od_tuners->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;
+	index = cpufreq_table_find_index_h(policy, freq_avg,
+					   relation & CPUFREQ_RELATION_E);
+	freq_lo = freq_table[index].frequency;
+	index = cpufreq_table_find_index_l(policy, freq_avg,
+					   relation & CPUFREQ_RELATION_E);
+	freq_hi = 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;
+		dbs_info->freq_lo_delay_us = 0;
 		return freq_lo;
 	}
-	jiffies_total = usecs_to_jiffies(od_tuners->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;
+	delay_hi_us = (freq_avg - freq_lo) * dbs_data->sampling_rate;
+	delay_hi_us += (freq_hi - freq_lo) / 2;
+	delay_hi_us /= freq_hi - freq_lo;
+	dbs_info->freq_hi_delay_us = delay_hi_us;
 	dbs_info->freq_lo = freq_lo;
-	dbs_info->freq_lo_jiffies = jiffies_lo;
-	dbs_info->freq_hi_jiffies = jiffies_hi;
+	dbs_info->freq_lo_delay_us = dbs_data->sampling_rate - delay_hi_us;
 	return freq_hi;
 }
 
-static void ondemand_powersave_bias_init(void)
+static void ondemand_powersave_bias_init(struct cpufreq_policy *policy)
 {
-	int i;
-	for_each_online_cpu(i) {
-		ondemand_powersave_bias_init_cpu(i);
-	}
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->freq_lo = 0;
 }
 
-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 policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
 	if (od_tuners->powersave_bias)
-		freq = od_ops.powersave_bias_target(p, freq,
-				CPUFREQ_RELATION_H);
-	else if (p->cur == p->max)
+		freq = od_ops.powersave_bias_target(policy, freq,
+						    CPUFREQ_RELATION_HE);
+	else if (policy->cur == policy->max)
 		return;
 
-	__cpufreq_driver_target(p, freq, od_tuners->powersave_bias ?
-			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
+	__cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ?
+			CPUFREQ_RELATION_LE : CPUFREQ_RELATION_HE);
 }
 
 /*
  * 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_update(struct cpufreq_policy *policy)
 {
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	unsigned int load = dbs_update(policy);
 
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load_freq > od_tuners->up_threshold * policy->cur) {
+	if (load > dbs_data->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;
+			policy_dbs->rate_mult = dbs_data->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;
+	} else {
+		/* Calculate the next frequency proportional to load */
+		unsigned int freq_next, min_f, max_f;
 
-	/*
-	 * 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) {
-		unsigned int freq_next;
-		freq_next = load_freq / od_tuners->adj_up_threshold;
+		min_f = policy->cpuinfo.min_freq;
+		max_f = policy->cpuinfo.max_freq;
+		freq_next = min_f + load * (max_f - min_f) / 100;
 
 		/* No longer fully busy, reset rate_mult */
-		dbs_info->rate_mult = 1;
-
-		if (freq_next < policy->min)
-			freq_next = policy->min;
+		policy_dbs->rate_mult = 1;
 
-		if (!od_tuners->powersave_bias) {
-			__cpufreq_driver_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-			return;
-		}
+		if (od_tuners->powersave_bias)
+			freq_next = od_ops.powersave_bias_target(policy,
+								 freq_next,
+								 CPUFREQ_RELATION_LE);
 
-		freq_next = od_ops.powersave_bias_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L);
+		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_CE);
 	}
 }
 
-static void od_dbs_timer(struct work_struct *work)
+static unsigned int od_dbs_update(struct cpufreq_policy *policy)
 {
-	struct od_cpu_dbs_info_s *dbs_info =
-		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
-	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
-	struct od_cpu_dbs_info_s *core_dbs_info = &per_cpu(od_cpu_dbs_info,
-			cpu);
-	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int delay = 0, sample_type = core_dbs_info->sample_type;
-	bool modify_all = true;
-
-	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
-	if (!need_load_eval(&core_dbs_info->cdbs, od_tuners->sampling_rate)) {
-		modify_all = false;
-		goto max_delay;
-	}
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	int sample_type = dbs_info->sample_type;
 
 	/* Common NORMAL_SAMPLE setup */
-	core_dbs_info->sample_type = OD_NORMAL_SAMPLE;
-	if (sample_type == OD_SUB_SAMPLE) {
-		delay = core_dbs_info->freq_lo_jiffies;
-		__cpufreq_driver_target(core_dbs_info->cdbs.cur_policy,
-				core_dbs_info->freq_lo, CPUFREQ_RELATION_H);
-	} else {
-		dbs_check_cpu(dbs_data, cpu);
-		if (core_dbs_info->freq_lo) {
-			/* Setup timer for SUB_SAMPLE */
-			core_dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = core_dbs_info->freq_hi_jiffies;
-		}
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	/*
+	 * OD_SUB_SAMPLE doesn't make sense if sample_delay_ns is 0, so ignore
+	 * it then.
+	 */
+	if (sample_type == OD_SUB_SAMPLE && policy_dbs->sample_delay_ns > 0) {
+		__cpufreq_driver_target(policy, dbs_info->freq_lo,
+					CPUFREQ_RELATION_HE);
+		return dbs_info->freq_lo_delay_us;
 	}
 
-max_delay:
-	if (!delay)
-		delay = delay_for_sampling_rate(od_tuners->sampling_rate
-				* core_dbs_info->rate_mult);
-
-	gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy, delay, modify_all);
-	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
-}
-
-/************************** sysfs interface ************************/
-static struct common_dbs_data od_dbs_cdata;
-
-/**
- * update_sampling_rate - update sampling rate effective immediately if needed.
- * @new_rate: new sampling rate
- *
- * If new rate is smaller than the old, simply updating
- * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the
- * original sampling_rate was 1 second and the requested new sampling rate is 10
- * ms because the user needs immediate reaction from ondemand governor, but not
- * sure if higher frequency will be required or not, then, the governor may
- * change the sampling rate too late; up to 1 second later. Thus, if we are
- * reducing the sampling rate, we need to make the new value effective
- * immediately.
- */
-static void update_sampling_rate(struct dbs_data *dbs_data,
-		unsigned int new_rate)
-{
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int cpu;
+	od_update(policy);
 
-	od_tuners->sampling_rate = new_rate = max(new_rate,
-			dbs_data->min_sampling_rate);
-
-	for_each_online_cpu(cpu) {
-		struct cpufreq_policy *policy;
-		struct od_cpu_dbs_info_s *dbs_info;
-		unsigned long next_sampling, appointed_at;
-
-		policy = cpufreq_cpu_get(cpu);
-		if (!policy)
-			continue;
-		if (policy->governor != &cpufreq_gov_ondemand) {
-			cpufreq_cpu_put(policy);
-			continue;
-		}
-		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-		cpufreq_cpu_put(policy);
-
-		mutex_lock(&dbs_info->cdbs.timer_mutex);
-
-		if (!delayed_work_pending(&dbs_info->cdbs.work)) {
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
-			continue;
-		}
-
-		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.work.timer.expires;
-
-		if (time_before(next_sampling, appointed_at)) {
-
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
-			cancel_delayed_work_sync(&dbs_info->cdbs.work);
-			mutex_lock(&dbs_info->cdbs.timer_mutex);
-
-			gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy,
-					usecs_to_jiffies(new_rate), true);
-
-		}
-		mutex_unlock(&dbs_info->cdbs.timer_mutex);
+	if (dbs_info->freq_lo) {
+		/* Setup SUB_SAMPLE */
+		dbs_info->sample_type = OD_SUB_SAMPLE;
+		return dbs_info->freq_hi_delay_us;
 	}
-}
 
-static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
-{
-	unsigned int input;
-	int ret;
-	ret = sscanf(buf, "%u", &input);
-	if (ret != 1)
-		return -EINVAL;
-
-	update_sampling_rate(dbs_data, input);
-	return count;
+	return dbs_data->sampling_rate * policy_dbs->rate_mult;
 }
 
-static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+/************************** sysfs interface ************************/
+static struct dbs_governor od_dbs_gov;
+
+static ssize_t io_is_busy_store(struct gov_attr_set *attr_set, const char *buf,
+				size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
-	unsigned int j;
 
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	od_tuners->io_is_busy = !!input;
+	dbs_data->io_is_busy = !!input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-									j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
-	}
+	gov_update_cpu_data(dbs_data);
+
 	return count;
 }
 
-static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t up_threshold_store(struct gov_attr_set *attr_set,
+				  const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -374,44 +209,46 @@ 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;
+	dbs_data->up_threshold = input;
 	return count;
 }
 
-static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t sampling_down_factor_store(struct gov_attr_set *attr_set,
+					  const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
+	struct policy_dbs_info *policy_dbs;
+	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
 
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
-	od_tuners->sampling_down_factor = input;
+
+	dbs_data->sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-				j);
-		dbs_info->rate_mult = 1;
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
+		/*
+		 * Doing this without locking might lead to using different
+		 * rate_mult values in od_update() and od_dbs_update().
+		 */
+		mutex_lock(&policy_dbs->update_mutex);
+		policy_dbs->rate_mult = 1;
+		mutex_unlock(&policy_dbs->update_mutex);
 	}
+
 	return count;
 }
 
-static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t ignore_nice_load_store(struct gov_attr_set *attr_set,
+				      const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
-	unsigned int j;
-
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
@@ -419,29 +256,23 @@ static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 	if (input > 1)
 		input = 1;
 
-	if (input == od_tuners->ignore_nice) { /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) { /* nothing to do */
 		return count;
 	}
-	od_tuners->ignore_nice = input;
+	dbs_data->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(od_cpu_dbs_info, j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
-		if (od_tuners->ignore_nice)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+	gov_update_cpu_data(dbs_data);
 
-	}
 	return count;
 }
 
-static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t powersave_bias_store(struct gov_attr_set *attr_set,
+				    const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -453,59 +284,52 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 		input = 1000;
 
 	od_tuners->powersave_bias = input;
-	ondemand_powersave_bias_init();
+
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list)
+		ondemand_powersave_bias_init(policy_dbs->policy);
+
 	return count;
 }
 
-show_store_one(od, sampling_rate);
-show_store_one(od, io_is_busy);
-show_store_one(od, up_threshold);
-show_store_one(od, sampling_down_factor);
-show_store_one(od, ignore_nice);
-show_store_one(od, powersave_bias);
-declare_show_sampling_rate_min(od);
-
-gov_sys_pol_attr_rw(sampling_rate);
-gov_sys_pol_attr_rw(io_is_busy);
-gov_sys_pol_attr_rw(up_threshold);
-gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(ignore_nice);
-gov_sys_pol_attr_rw(powersave_bias);
-gov_sys_pol_attr_ro(sampling_rate_min);
-
-static struct attribute *dbs_attributes_gov_sys[] = {
-	&sampling_rate_min_gov_sys.attr,
-	&sampling_rate_gov_sys.attr,
-	&up_threshold_gov_sys.attr,
-	&sampling_down_factor_gov_sys.attr,
-	&ignore_nice_gov_sys.attr,
-	&powersave_bias_gov_sys.attr,
-	&io_is_busy_gov_sys.attr,
+gov_show_one_common(sampling_rate);
+gov_show_one_common(up_threshold);
+gov_show_one_common(sampling_down_factor);
+gov_show_one_common(ignore_nice_load);
+gov_show_one_common(io_is_busy);
+gov_show_one(od, powersave_bias);
+
+gov_attr_rw(sampling_rate);
+gov_attr_rw(io_is_busy);
+gov_attr_rw(up_threshold);
+gov_attr_rw(sampling_down_factor);
+gov_attr_rw(ignore_nice_load);
+gov_attr_rw(powersave_bias);
+
+static struct attribute *od_attrs[] = {
+	&sampling_rate.attr,
+	&up_threshold.attr,
+	&sampling_down_factor.attr,
+	&ignore_nice_load.attr,
+	&powersave_bias.attr,
+	&io_is_busy.attr,
 	NULL
 };
+ATTRIBUTE_GROUPS(od);
 
-static struct attribute_group od_attr_group_gov_sys = {
-	.attrs = dbs_attributes_gov_sys,
-	.name = "ondemand",
-};
+/************************** sysfs end ************************/
 
-static struct attribute *dbs_attributes_gov_pol[] = {
-	&sampling_rate_min_gov_pol.attr,
-	&sampling_rate_gov_pol.attr,
-	&up_threshold_gov_pol.attr,
-	&sampling_down_factor_gov_pol.attr,
-	&ignore_nice_gov_pol.attr,
-	&powersave_bias_gov_pol.attr,
-	&io_is_busy_gov_pol.attr,
-	NULL
-};
+static struct policy_dbs_info *od_alloc(void)
+{
+	struct od_policy_dbs_info *dbs_info;
 
-static struct attribute_group od_attr_group_gov_pol = {
-	.attrs = dbs_attributes_gov_pol,
-	.name = "ondemand",
-};
+	dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL);
+	return dbs_info ? &dbs_info->policy_dbs : NULL;
+}
 
-/************************** sysfs end ************************/
+static void od_free(struct policy_dbs_info *policy_dbs)
+{
+	kfree(to_dbs_info(policy_dbs));
+}
 
 static int od_init(struct dbs_data *dbs_data)
 {
@@ -513,43 +337,26 @@ static int od_init(struct dbs_data *dbs_data)
 	u64 idle_time;
 	int cpu;
 
-	tuners = kzalloc(sizeof(struct od_dbs_tuners), GFP_KERNEL);
-	if (!tuners) {
-		pr_err("%s: kzalloc failed\n", __func__);
+	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
+	if (!tuners)
 		return -ENOMEM;
-	}
 
 	cpu = get_cpu();
 	idle_time = get_cpu_idle_time_us(cpu, NULL);
 	put_cpu();
 	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
-		 * timer might skip some samples if idle/sleeping as needed.
-		*/
-		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
+		dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
 	} 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 *
-			jiffies_to_usecs(10);
+		dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 	}
 
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice = 0;
+	dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
+	dbs_data->ignore_nice_load = 0;
 	tuners->powersave_bias = default_powersave_bias;
-	tuners->io_is_busy = should_io_be_busy();
+	dbs_data->io_is_busy = od_should_io_be_busy();
 
 	dbs_data->tuners = tuners;
-	mutex_init(&dbs_data->mutex);
 	return 0;
 }
 
@@ -558,57 +365,69 @@ static void od_exit(struct dbs_data *dbs_data)
 	kfree(dbs_data->tuners);
 }
 
-define_get_cpu_dbs_routines(od_cpu_dbs_info);
+static void od_start(struct cpufreq_policy *policy)
+{
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	ondemand_powersave_bias_init(policy);
+}
 
 static struct od_ops od_ops = {
-	.powersave_bias_init_cpu = ondemand_powersave_bias_init_cpu,
 	.powersave_bias_target = generic_powersave_bias_target,
-	.freq_increase = dbs_freq_increase,
 };
 
-static struct common_dbs_data od_dbs_cdata = {
-	.governor = GOV_ONDEMAND,
-	.attr_group_gov_sys = &od_attr_group_gov_sys,
-	.attr_group_gov_pol = &od_attr_group_gov_pol,
-	.get_cpu_cdbs = get_cpu_cdbs,
-	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
-	.gov_dbs_timer = od_dbs_timer,
-	.gov_check_cpu = od_check_cpu,
-	.gov_ops = &od_ops,
+static struct dbs_governor od_dbs_gov = {
+	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"),
+	.kobj_type = { .default_groups = od_groups },
+	.gov_dbs_update = od_dbs_update,
+	.alloc = od_alloc,
+	.free = od_free,
 	.init = od_init,
 	.exit = od_exit,
+	.start = od_start,
 };
 
+#define CPU_FREQ_GOV_ONDEMAND	(od_dbs_gov.gov)
+
 static void od_set_powersave_bias(unsigned int powersave_bias)
 {
-	struct cpufreq_policy *policy;
-	struct dbs_data *dbs_data;
-	struct od_dbs_tuners *od_tuners;
 	unsigned int cpu;
-	cpumask_t done;
+	cpumask_var_t done;
+
+	if (!alloc_cpumask_var(&done, GFP_KERNEL))
+		return;
 
 	default_powersave_bias = powersave_bias;
-	cpumask_clear(&done);
+	cpumask_clear(done);
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
-		if (cpumask_test_cpu(cpu, &done))
-			continue;
+		struct cpufreq_policy *policy;
+		struct policy_dbs_info *policy_dbs;
+		struct dbs_data *dbs_data;
+		struct od_dbs_tuners *od_tuners;
 
-		policy = per_cpu(od_cpu_dbs_info, cpu).cdbs.cur_policy;
-		if (!policy)
+		if (cpumask_test_cpu(cpu, done))
 			continue;
 
-		cpumask_or(&done, &done, policy->cpus);
+		policy = cpufreq_cpu_get_raw(cpu);
+		if (!policy || policy->governor != &CPU_FREQ_GOV_ONDEMAND)
+			continue;
 
-		if (policy->governor != &cpufreq_gov_ondemand)
+		policy_dbs = policy->governor_data;
+		if (!policy_dbs)
 			continue;
 
-		dbs_data = policy->governor_data;
+		cpumask_or(done, done, policy->cpus);
+
+		dbs_data = policy_dbs->dbs_data;
 		od_tuners = dbs_data->tuners;
 		od_tuners->powersave_bias = default_powersave_bias;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
+
+	free_cpumask_var(done);
 }
 
 void od_register_powersave_bias_handler(unsigned int (*f)
@@ -627,32 +446,6 @@ void od_unregister_powersave_bias_handler(void)
 }
 EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
 
-static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		unsigned int event)
-{
-	return cpufreq_governor_dbs(policy, &od_dbs_cdata, event);
-}
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static
-#endif
-struct cpufreq_governor cpufreq_gov_ondemand = {
-	.name			= "ondemand",
-	.governor		= od_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
-static int __init cpufreq_gov_dbs_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_ondemand);
-}
-
-static void __exit cpufreq_gov_dbs_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
-}
-
 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 "
@@ -660,8 +453,11 @@ MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-fs_initcall(cpufreq_gov_dbs_init);
-#else
-module_init(cpufreq_gov_dbs_init);
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &CPU_FREQ_GOV_ONDEMAND;
+}
 #endif
-module_exit(cpufreq_gov_dbs_exit);
+
+cpufreq_governor_init(CPU_FREQ_GOV_ONDEMAND);
+cpufreq_governor_exit(CPU_FREQ_GOV_ONDEMAND);