cpufreq: governors: remove redundant code

Initially ondemand governor was written and then using its code conservative
governor is written. It used a lot of code from ondemand governor, but copy of
code was created instead of using the same routines from both governors. Which
increased code redundancy, which is difficult to manage.

This patch is an attempt to move common part of both the governors to
cpufreq_governor.c file to come over above mentioned issues.

This shouldn't change anything from functionality point of view.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/cpufreq/cpufreq_governor.c

@@ -3,19 +3,31 @@
  *
  * CPUFREQ governors common code
  *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
  * 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 <asm/cputime.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 #include <linux/tick.h>
 #include <linux/types.h>
-/*
- * Code picked from earlier governer implementations
- */
+#include <linux/workqueue.h>
+
+#include "cpufreq_governor.h"
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -33,9 +45,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = cputime_to_usecs(cur_wall_time);
+		*wall = jiffies_to_usecs(cur_wall_time);
 
-	return cputime_to_usecs(idle_time);
+	return jiffies_to_usecs(idle_time);
 }
 
 cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
@@ -50,3 +62,257 @@ cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
 	return idle_time;
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
+
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
+{
+	struct cpu_dbs_common_info *cdbs = dbs_data->get_cpu_cdbs(cpu);
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpufreq_policy *policy;
+	unsigned int max_load = 0;
+	unsigned int ignore_nice;
+	unsigned int j;
+
+	if (dbs_data->governor == GOV_ONDEMAND)
+		ignore_nice = od_tuners->ignore_nice;
+	else
+		ignore_nice = cs_tuners->ignore_nice;
+
+	policy = cdbs->cur_policy;
+
+	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	for_each_cpu(j, policy->cpus) {
+		struct cpu_dbs_common_info *j_cdbs;
+		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
+		unsigned int idle_time, wall_time, iowait_time;
+		unsigned int load;
+
+		j_cdbs = dbs_data->get_cpu_cdbs(j);
+
+		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+
+		wall_time = (unsigned int)
+			(cur_wall_time - j_cdbs->prev_cpu_wall);
+		j_cdbs->prev_cpu_wall = cur_wall_time;
+
+		idle_time = (unsigned int)
+			(cur_idle_time - j_cdbs->prev_cpu_idle);
+		j_cdbs->prev_cpu_idle = cur_idle_time;
+
+		if (ignore_nice) {
+			u64 cur_nice;
+			unsigned long cur_nice_jiffies;
+
+			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
+					 cdbs->prev_cpu_nice;
+			/*
+			 * Assumption: nice time between sampling periods will
+			 * be less than 2^32 jiffies for 32 bit sys
+			 */
+			cur_nice_jiffies = (unsigned long)
+					cputime64_to_jiffies64(cur_nice);
+
+			cdbs->prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			idle_time += jiffies_to_usecs(cur_nice_jiffies);
+		}
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			struct od_cpu_dbs_info_s *od_j_dbs_info =
+				dbs_data->get_cpu_dbs_info_s(cpu);
+
+			cur_iowait_time = get_cpu_iowait_time_us(j,
+					&cur_wall_time);
+			if (cur_iowait_time == -1ULL)
+				cur_iowait_time = 0;
+
+			iowait_time = (unsigned int) (cur_iowait_time -
+					od_j_dbs_info->prev_cpu_iowait);
+			od_j_dbs_info->prev_cpu_iowait = cur_iowait_time;
+
+			/*
+			 * For the purpose of ondemand, waiting for disk IO is
+			 * an indication that you're performance critical, and
+			 * not that the system is actually idle. So subtract the
+			 * iowait time from the cpu idle time.
+			 */
+			if (od_tuners->io_is_busy && idle_time >= iowait_time)
+				idle_time -= iowait_time;
+		}
+
+		if (unlikely(!wall_time || wall_time < idle_time))
+			continue;
+
+		load = 100 * (wall_time - idle_time) / wall_time;
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			int freq_avg = __cpufreq_driver_getavg(policy, j);
+			if (freq_avg <= 0)
+				freq_avg = policy->cur;
+
+			load *= freq_avg;
+		}
+
+		if (load > max_load)
+			max_load = load;
+	}
+
+	dbs_data->gov_check_cpu(cpu, max_load);
+}
+EXPORT_SYMBOL_GPL(dbs_check_cpu);
+
+static inline void dbs_timer_init(struct dbs_data *dbs_data,
+		struct cpu_dbs_common_info *cdbs, unsigned int sampling_rate)
+{
+	int delay = delay_for_sampling_rate(sampling_rate);
+
+	INIT_DEFERRABLE_WORK(&cdbs->work, dbs_data->gov_dbs_timer);
+	schedule_delayed_work_on(cdbs->cpu, &cdbs->work, delay);
+}
+
+static inline void dbs_timer_exit(struct cpu_dbs_common_info *cdbs)
+{
+	cancel_delayed_work_sync(&cdbs->work);
+}
+
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event)
+{
+	struct od_cpu_dbs_info_s *od_dbs_info = NULL;
+	struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpu_dbs_common_info *cpu_cdbs;
+	unsigned int *sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
+	int rc;
+
+	cpu_cdbs = dbs_data->get_cpu_cdbs(cpu);
+
+	if (dbs_data->governor == GOV_CONSERVATIVE) {
+		cs_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &cs_tuners->sampling_rate;
+		ignore_nice = cs_tuners->ignore_nice;
+	} else {
+		od_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &od_tuners->sampling_rate;
+		ignore_nice = od_tuners->ignore_nice;
+	}
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if ((!cpu_online(cpu)) || (!policy->cur))
+			return -EINVAL;
+
+		mutex_lock(&dbs_data->mutex);
+
+		dbs_data->enable++;
+		cpu_cdbs->cpu = cpu;
+		for_each_cpu(j, policy->cpus) {
+			struct cpu_dbs_common_info *j_cdbs;
+			j_cdbs = dbs_data->get_cpu_cdbs(j);
+
+			j_cdbs->cur_policy = policy;
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
+					&j_cdbs->prev_cpu_wall);
+			if (ignore_nice)
+				j_cdbs->prev_cpu_nice =
+					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		}
+
+		/*
+		 * Start the timerschedule work, when this governor is used for
+		 * first time
+		 */
+		if (dbs_data->enable != 1)
+			goto second_time;
+
+		rc = sysfs_create_group(cpufreq_global_kobject,
+				dbs_data->attr_group);
+		if (rc) {
+			mutex_unlock(&dbs_data->mutex);
+			return rc;
+		}
+
+		/* policy latency is in nS. Convert it to uS first */
+		latency = policy->cpuinfo.transition_latency / 1000;
+		if (latency == 0)
+			latency = 1;
+
+		/*
+		 * conservative does not implement micro like ondemand
+		 * governor, thus we are bound to jiffes/HZ
+		 */
+		if (dbs_data->governor == GOV_CONSERVATIVE) {
+			struct cs_ops *ops = dbs_data->gov_ops;
+
+			cpufreq_register_notifier(ops->notifier_block,
+					CPUFREQ_TRANSITION_NOTIFIER);
+
+			dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
+				jiffies_to_usecs(10);
+		} else {
+			struct od_ops *ops = dbs_data->gov_ops;
+
+			od_tuners->io_is_busy = ops->io_busy();
+		}
+
+		/* Bring kernel and HW constraints together */
+		dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
+				MIN_LATENCY_MULTIPLIER * latency);
+		*sampling_rate = max(dbs_data->min_sampling_rate, latency *
+				LATENCY_MULTIPLIER);
+
+second_time:
+		if (dbs_data->governor == GOV_CONSERVATIVE) {
+			cs_dbs_info->down_skip = 0;
+			cs_dbs_info->enable = 1;
+			cs_dbs_info->requested_freq = policy->cur;
+		} else {
+			struct od_ops *ops = dbs_data->gov_ops;
+			od_dbs_info->rate_mult = 1;
+			od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+			ops->powersave_bias_init_cpu(cpu);
+		}
+		mutex_unlock(&dbs_data->mutex);
+
+		mutex_init(&cpu_cdbs->timer_mutex);
+		dbs_timer_init(dbs_data, cpu_cdbs, *sampling_rate);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		if (dbs_data->governor == GOV_CONSERVATIVE)
+			cs_dbs_info->enable = 0;
+
+		dbs_timer_exit(cpu_cdbs);
+
+		mutex_lock(&dbs_data->mutex);
+		mutex_destroy(&cpu_cdbs->timer_mutex);
+		dbs_data->enable--;
+		if (!dbs_data->enable) {
+			struct cs_ops *ops = dbs_data->gov_ops;
+
+			sysfs_remove_group(cpufreq_global_kobject,
+					dbs_data->attr_group);
+			if (dbs_data->governor == GOV_CONSERVATIVE)
+				cpufreq_unregister_notifier(ops->notifier_block,
+						CPUFREQ_TRANSITION_NOTIFIER);
+		}
+		mutex_unlock(&dbs_data->mutex);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&cpu_cdbs->timer_mutex);
+		if (policy->max < cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->min, CPUFREQ_RELATION_L);
+		dbs_check_cpu(dbs_data, cpu);
+		mutex_unlock(&cpu_cdbs->timer_mutex);
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);

drivers/cpufreq/cpufreq_governor.h

+/*
+ * drivers/cpufreq/cpufreq_governor.h
+ *
+ * Header file for CPUFreq governors common code
+ *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * 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.
+ */
+
+#ifndef _CPUFREQ_GOVERNER_H
+#define _CPUFREQ_GOVERNER_H
+
+#include <asm/cputime.h>
+#include <linux/cpufreq.h>
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+
+/*
+ * The polling frequency depends on the capability of the processor. Default
+ * polling frequency is 1000 times the transition latency of the processor. The
+ * governor will work on any processor with transition latency <= 10mS, using
+ * appropriate sampling rate.
+ *
+ * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
+ * this governor will not work. All times here are in uS.
+ */
+#define MIN_SAMPLING_RATE_RATIO			(2)
+#define LATENCY_MULTIPLIER			(1000)
+#define MIN_LATENCY_MULTIPLIER			(100)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
+
+/* Ondemand Sampling types */
+enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
+
+/* Macro creating sysfs show routines */
+#define show_one(_gov, file_name, object)				\
+static ssize_t show_##file_name						\
+(struct kobject *kobj, struct attribute *attr, char *buf)		\
+{									\
+	return sprintf(buf, "%u\n", _gov##_tuners.object);		\
+}
+
+#define define_get_cpu_dbs_routines(_dbs_info)				\
+static struct cpu_dbs_common_info *get_cpu_cdbs(int cpu)		\
+{									\
+	return &per_cpu(_dbs_info, cpu).cdbs;				\
+}									\
+									\
+static void *get_cpu_dbs_info_s(int cpu)				\
+{									\
+	return &per_cpu(_dbs_info, cpu);				\
+}
+
+/*
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * on_*: On-demand governor
+ * cs_*: Conservative governor
+ */
+
+/* Per cpu structures */
+struct cpu_dbs_common_info {
+	int cpu;
+	cputime64_t prev_cpu_idle;
+	cputime64_t prev_cpu_wall;
+	cputime64_t prev_cpu_nice;
+	struct cpufreq_policy *cur_policy;
+	struct delayed_work work;
+	/*
+	 * percpu mutex that serializes governor limit change with gov_dbs_timer
+	 * invocation. We do not want gov_dbs_timer to run when user is changing
+	 * the governor or limits.
+	 */
+	struct mutex timer_mutex;
+};
+
+struct od_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	cputime64_t prev_cpu_iowait;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_jiffies;
+	unsigned int freq_hi_jiffies;
+	unsigned int rate_mult;
+	unsigned int sample_type:1;
+};
+
+struct cs_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+	unsigned int enable:1;
+};
+
+/* Governers sysfs tunables */
+struct od_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int down_differential;
+	unsigned int powersave_bias;
+	unsigned int io_is_busy;
+};
+
+struct cs_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
+/* Per Governer data */
+struct dbs_data {
+	/* Common across governors */
+	#define GOV_ONDEMAND		0
+	#define GOV_CONSERVATIVE	1
+	int governor;
+	unsigned int min_sampling_rate;
+	unsigned int enable; /* number of CPUs using this policy */
+	struct attribute_group *attr_group;
+	void *tuners;
+
+	/* dbs_mutex protects dbs_enable in governor start/stop */
+	struct mutex mutex;
+
+	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
+	void *(*get_cpu_dbs_info_s)(int cpu);
+	void (*gov_dbs_timer)(struct work_struct *work);
+	void (*gov_check_cpu)(int cpu, unsigned int load);
+
+	/* Governor specific ops, see below */
+	void *gov_ops;
+};
+
+/* Governor specific ops, will be passed to dbs_data->gov_ops */
+struct od_ops {
+	int (*io_busy)(void);
+	void (*powersave_bias_init_cpu)(int cpu);
+	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
+			unsigned int freq_next, unsigned int relation);
+	void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq);
+};
+
+struct cs_ops {
+	struct notifier_block *notifier_block;
+};
+
+static inline int delay_for_sampling_rate(unsigned int sampling_rate)
+{
+	int delay = usecs_to_jiffies(sampling_rate);
+
+	/* We want all CPUs to do sampling nearly on same jiffy */
+	if (num_online_cpus() > 1)
+		delay -= jiffies % delay;
+
+	return delay;
+}
+
+cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall);
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event);
+#endif /* _CPUFREQ_GOVERNER_H */

include/linux/cpufreq.h

@@ -407,10 +407,4 @@ void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
-
-/*********************************************************************
- *                     Governor Helpers				     *
- *********************************************************************/
-cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall);
-
 #endif /* _LINUX_CPUFREQ_H */