Merge branch 'pm-cpufreq-governor' into pm-cpufreq

drivers/cpufreq/Kconfig

@@ -19,6 +19,7 @@ config CPU_FREQ
 if CPU_FREQ
 
 config CPU_FREQ_GOV_COMMON
+	select IRQ_WORK
 	bool
 
 config CPU_FREQ_BOOST_SW

drivers/cpufreq/amd_freq_sensitivity.c

@@ -21,7 +21,7 @@
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 
-#include "cpufreq_governor.h"
+#include "cpufreq_ondemand.h"
 
 #define MSR_AMD64_FREQ_SENSITIVITY_ACTUAL	0xc0010080
 #define MSR_AMD64_FREQ_SENSITIVITY_REFERENCE	0xc0010081
@@ -45,10 +45,10 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 	long d_actual, d_reference;
 	struct msr actual, reference;
 	struct cpu_data_t *data = &per_cpu(cpu_data, policy->cpu);
-	struct dbs_data *od_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *od_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = od_data->tuners;
-	struct od_cpu_dbs_info_s *od_info =
-		od_data->cdata->get_cpu_dbs_info_s(policy->cpu);
+	struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs);
 
 	if (!od_info->freq_table)
 		return freq_next;

drivers/cpufreq/cpufreq.c

@@ -64,7 +64,6 @@ static LIST_HEAD(cpufreq_governor_list);
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
-DEFINE_MUTEX(cpufreq_governor_lock);
 
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
@@ -75,10 +74,8 @@ static inline bool has_target(void)
 }
 
 /* internal prototypes */
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-		unsigned int event);
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
-static void handle_update(struct work_struct *work);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -955,30 +952,38 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 	if (cpumask_test_cpu(cpu, policy->cpus))
 		return 0;
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
+			goto unlock;
 		}
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_set_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
 
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to start governor\n", __func__);
-			return ret;
-		}
 	}
 
-	return 0;
+unlock:
+	up_write(&policy->rwsem);
+	return ret;
+}
+
+static void handle_update(struct work_struct *work)
+{
+	struct cpufreq_policy *policy =
+		container_of(work, struct cpufreq_policy, update);
+	unsigned int cpu = policy->cpu;
+	pr_debug("handle_update for cpu %u called\n", cpu);
+	cpufreq_update_policy(cpu);
 }
 
 static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
@@ -1267,9 +1272,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	return ret;
 }
 
-static void cpufreq_offline_prepare(unsigned int cpu)
+static void cpufreq_offline(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
@@ -1279,13 +1285,13 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		return;
 	}
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_clear_cpu(cpu, policy->cpus);
 
 	if (policy_is_inactive(policy)) {
@@ -1298,39 +1304,27 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
 	}
-	up_write(&policy->rwsem);
 
 	/* Start governor again for active policy */
 	if (!policy_is_inactive(policy)) {
 		if (has_target()) {
-			int ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 			if (!ret)
-				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+				ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
 			if (ret)
 				pr_err("%s: Failed to start governor\n", __func__);
 		}
-	} else if (cpufreq_driver->stop_cpu) {
-		cpufreq_driver->stop_cpu(policy);
-	}
-}
-
-static void cpufreq_offline_finish(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-	if (!policy) {
-		pr_debug("%s: No cpu_data found\n", __func__);
-		return;
+		goto unlock;
 	}
 
-	/* Only proceed for inactive policies */
-	if (!policy_is_inactive(policy))
-		return;
+	if (cpufreq_driver->stop_cpu)
+		cpufreq_driver->stop_cpu(policy);
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
 	}
@@ -1344,6 +1338,9 @@ static void cpufreq_offline_finish(unsigned int cpu)
 		cpufreq_driver->exit(policy);
 		policy->freq_table = NULL;
 	}
+
+unlock:
+	up_write(&policy->rwsem);
 }
 
 /**
@@ -1359,10 +1356,8 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (!policy)
 		return;
 
-	if (cpu_online(cpu)) {
-		cpufreq_offline_prepare(cpu);
-		cpufreq_offline_finish(cpu);
-	}
+	if (cpu_online(cpu))
+		cpufreq_offline(cpu);
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
 	remove_cpu_dev_symlink(policy, cpu);
@@ -1371,15 +1366,6 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 		cpufreq_policy_free(policy, true);
 }
 
-static void handle_update(struct work_struct *work)
-{
-	struct cpufreq_policy *policy =
-		container_of(work, struct cpufreq_policy, update);
-	unsigned int cpu = policy->cpu;
-	pr_debug("handle_update for cpu %u called\n", cpu);
-	cpufreq_update_policy(cpu);
-}
-
 /**
  *	cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're
  *	in deep trouble.
@@ -1542,6 +1528,7 @@ EXPORT_SYMBOL(cpufreq_generic_suspend);
 void cpufreq_suspend(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1552,7 +1539,11 @@ void cpufreq_suspend(void)
 	pr_debug("%s: Suspending Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+		down_write(&policy->rwsem);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		up_write(&policy->rwsem);
+
+		if (ret)
 			pr_err("%s: Failed to stop governor for policy: %p\n",
 				__func__, policy);
 		else if (cpufreq_driver->suspend
@@ -1574,6 +1565,7 @@ void cpufreq_suspend(void)
 void cpufreq_resume(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1586,14 +1578,21 @@ void cpufreq_resume(void)
 	pr_debug("%s: Resuming Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
+		if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) {
 			pr_err("%s: Failed to resume driver: %p\n", __func__,
 				policy);
-		else if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
-		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
+		} else {
+			down_write(&policy->rwsem);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
+
+			if (ret)
 				pr_err("%s: Failed to start governor for policy: %p\n",
 				       __func__, policy);
 		}
+	}
 
 	/*
 	 * schedule call cpufreq_update_policy() for first-online CPU, as that
@@ -1878,8 +1877,7 @@ __weak struct cpufreq_governor *cpufreq_fallback_governor(void)
 	return NULL;
 }
 
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-					unsigned int event)
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
 {
 	int ret;
 
@@ -1913,21 +1911,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 
 	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
 
-	mutex_lock(&cpufreq_governor_lock);
-	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
-	    || (!policy->governor_enabled
-	    && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
-		mutex_unlock(&cpufreq_governor_lock);
-		return -EBUSY;
-	}
-
-	if (event == CPUFREQ_GOV_STOP)
-		policy->governor_enabled = false;
-	else if (event == CPUFREQ_GOV_START)
-		policy->governor_enabled = true;
-
-	mutex_unlock(&cpufreq_governor_lock);
-
 	ret = policy->governor->governor(policy, event);
 
 	if (!ret) {
@@ -1935,14 +1918,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 			policy->governor->initialized++;
 		else if (event == CPUFREQ_GOV_POLICY_EXIT)
 			policy->governor->initialized--;
-	} else {
-		/* Restore original values */
-		mutex_lock(&cpufreq_governor_lock);
-		if (event == CPUFREQ_GOV_STOP)
-			policy->governor_enabled = true;
-		else if (event == CPUFREQ_GOV_START)
-			policy->governor_enabled = false;
-		mutex_unlock(&cpufreq_governor_lock);
 	}
 
 	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
@@ -2097,7 +2072,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	old_gov = policy->governor;
 	/* end old governor */
 	if (old_gov) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			/* This can happen due to race with other operations */
 			pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
@@ -2105,10 +2080,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			return ret;
 		}
 
-		up_write(&policy->rwsem);
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
-
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret) {
 			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
 			       __func__, old_gov->name, ret);
@@ -2118,32 +2090,30 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
 	if (!ret) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
 			goto out;
 
-		up_write(&policy->rwsem);
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
+		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 	}
 
 	/* new governor failed, so re-start old one */
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
 			policy->governor = NULL;
 		else
-			__cpufreq_governor(policy, CPUFREQ_GOV_START);
+			cpufreq_governor(policy, CPUFREQ_GOV_START);
 	}
 
 	return ret;
 
  out:
 	pr_debug("governor: change or update limits\n");
-	return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 }
 
 /**
@@ -2210,11 +2180,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 		break;
 
 	case CPU_DOWN_PREPARE:
-		cpufreq_offline_prepare(cpu);
-		break;
-
-	case CPU_POST_DEAD:
-		cpufreq_offline_finish(cpu);
+		cpufreq_offline(cpu);
 		break;
 
 	case CPU_DOWN_FAILED:
@@ -2247,8 +2213,11 @@ static int cpufreq_boost_set_sw(int state)
 				       __func__);
 				break;
 			}
+
+			down_write(&policy->rwsem);
 			policy->user_policy.max = policy->max;
-			__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
 		}
 	}
 

drivers/cpufreq/cpufreq_conservative.c

@@ -14,6 +14,22 @@
 #include <linux/slab.h>
 #include "cpufreq_governor.h"
 
+struct cs_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+};
+
+static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct cs_policy_dbs_info, policy_dbs);
+}
+
+struct cs_dbs_tuners {
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
 /* Conservative governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
@@ -21,18 +37,6 @@
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
 
-static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
-
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event);
-
-static struct cpufreq_governor cpufreq_gov_conservative = {
-	.name			= "conservative",
-	.governor		= cs_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
 static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 					   struct cpufreq_policy *policy)
 {
@@ -54,27 +58,28 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
  * Any frequency increase takes it to the maximum frequency. Frequency reduction
  * happens at minimum steps of 5% (default) of maximum frequency
  */
-static void cs_check_cpu(int cpu, unsigned int load)
+static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 {
-	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	unsigned int load = dbs_update(policy);
 
 	/*
 	 * break out if we 'cannot' reduce the speed as the user might
 	 * want freq_step to be zero
 	 */
 	if (cs_tuners->freq_step == 0)
-		return;
+		goto out;
 
 	/* Check for frequency increase */
-	if (load > cs_tuners->up_threshold) {
+	if (load > dbs_data->up_threshold) {
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
 		if (dbs_info->requested_freq == policy->max)
-			return;
+			goto out;
 
 		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
 
@@ -83,12 +88,12 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 			CPUFREQ_RELATION_H);
-		return;
+		goto out;
 	}
 
 	/* if sampling_down_factor is active break out early */
-	if (++dbs_info->down_skip < cs_tuners->sampling_down_factor)
-		return;
+	if (++dbs_info->down_skip < dbs_data->sampling_down_factor)
+		goto out;
 	dbs_info->down_skip = 0;
 
 	/* Check for frequency decrease */
@@ -98,7 +103,7 @@ static void cs_check_cpu(int cpu, unsigned int load)
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
 		if (policy->cur == policy->min)
-			return;
+			goto out;
 
 		freq_target = get_freq_target(cs_tuners, policy);
 		if (dbs_info->requested_freq > freq_target)
@@ -108,58 +113,25 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 				CPUFREQ_RELATION_L);
-		return;
 	}
-}
-
-static unsigned int cs_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
-{
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-	if (modify_all)
-		dbs_check_cpu(dbs_data, policy->cpu);
 
-	return delay_for_sampling_rate(cs_tuners->sampling_rate);
+ out:
+	return dbs_data->sampling_rate;
 }
 
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-		void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cs_cpu_dbs_info_s *dbs_info =
-					&per_cpu(cs_cpu_dbs_info, freq->cpu);
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
-
-	if (!policy)
-		return 0;
-
-	/* policy isn't governed by conservative governor */
-	if (policy->governor != &cpufreq_gov_conservative)
-		return 0;
-
-	/*
-	 * we only care if our internally tracked freq moves outside the 'valid'
-	 * ranges of frequency available to us otherwise we do not change it
-	*/
-	if (dbs_info->requested_freq > policy->max
-			|| dbs_info->requested_freq < policy->min)
-		dbs_info->requested_freq = freq->new;
-
-	return 0;
-}
+				void *data);
 
 static struct notifier_block cs_cpufreq_notifier_block = {
 	.notifier_call = dbs_cpufreq_notifier,
 };
 
 /************************** sysfs interface ************************/
-static struct common_dbs_data cs_dbs_cdata;
+static struct dbs_governor cs_dbs_gov;
 
 static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -167,22 +139,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
 
-	cs_tuners->sampling_down_factor = input;
-	return count;
-}
-
-static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
-{
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input;
-	int ret;
-	ret = sscanf(buf, "%u", &input);
-
-	if (ret != 1)
-		return -EINVAL;
-
-	cs_tuners->sampling_rate = max(input, dbs_data->min_sampling_rate);
+	dbs_data->sampling_down_factor = input;
 	return count;
 }
 
@@ -197,7 +154,7 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	if (ret != 1 || input > 100 || input <= cs_tuners->down_threshold)
 		return -EINVAL;
 
-	cs_tuners->up_threshold = input;
+	dbs_data->up_threshold = input;
 	return count;
 }
 
@@ -211,7 +168,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 
 	/* cannot be lower than 11 otherwise freq will not fall */
 	if (ret != 1 || input < 11 || input > 100 ||
-			input >= cs_tuners->up_threshold)
+			input >= dbs_data->up_threshold)
 		return -EINVAL;
 
 	cs_tuners->down_threshold = input;
@@ -221,8 +178,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	unsigned int input;
 	int ret;
 
 	ret = sscanf(buf, "%u", &input);
@@ -232,21 +188,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	if (input > 1)
 		input = 1;
 
-	if (input == cs_tuners->ignore_nice_load) /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) /* nothing to do */
 		return count;
 
-	cs_tuners->ignore_nice_load = input;
+	dbs_data->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct cs_cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-					&dbs_info->cdbs.prev_cpu_wall, 0);
-		if (cs_tuners->ignore_nice_load)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-	}
+	gov_update_cpu_data(dbs_data);
+
 	return count;
 }
 
@@ -272,55 +221,47 @@ static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-show_store_one(cs, sampling_rate);
-show_store_one(cs, sampling_down_factor);
-show_store_one(cs, up_threshold);
-show_store_one(cs, down_threshold);
-show_store_one(cs, ignore_nice_load);
-show_store_one(cs, freq_step);
-declare_show_sampling_rate_min(cs);
-
-gov_sys_pol_attr_rw(sampling_rate);
-gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(up_threshold);
-gov_sys_pol_attr_rw(down_threshold);
-gov_sys_pol_attr_rw(ignore_nice_load);
-gov_sys_pol_attr_rw(freq_step);
-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,
-	&sampling_down_factor_gov_sys.attr,
-	&up_threshold_gov_sys.attr,
-	&down_threshold_gov_sys.attr,
-	&ignore_nice_load_gov_sys.attr,
-	&freq_step_gov_sys.attr,
+gov_show_one_common(sampling_rate);
+gov_show_one_common(sampling_down_factor);
+gov_show_one_common(up_threshold);
+gov_show_one_common(ignore_nice_load);
+gov_show_one_common(min_sampling_rate);
+gov_show_one(cs, down_threshold);
+gov_show_one(cs, freq_step);
+
+gov_attr_rw(sampling_rate);
+gov_attr_rw(sampling_down_factor);
+gov_attr_rw(up_threshold);
+gov_attr_rw(ignore_nice_load);
+gov_attr_ro(min_sampling_rate);
+gov_attr_rw(down_threshold);
+gov_attr_rw(freq_step);
+
+static struct attribute *cs_attributes[] = {
+	&min_sampling_rate.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 cs_attr_group_gov_sys = {
-	.attrs = dbs_attributes_gov_sys,
-	.name = "conservative",
-};
+/************************** sysfs end ************************/
 
-static struct attribute *dbs_attributes_gov_pol[] = {
-	&sampling_rate_min_gov_pol.attr,
-	&sampling_rate_gov_pol.attr,
-	&sampling_down_factor_gov_pol.attr,
-	&up_threshold_gov_pol.attr,
-	&down_threshold_gov_pol.attr,
-	&ignore_nice_load_gov_pol.attr,
-	&freq_step_gov_pol.attr,
-	NULL
-};
+static struct policy_dbs_info *cs_alloc(void)
+{
+	struct cs_policy_dbs_info *dbs_info;
 
-static struct attribute_group cs_attr_group_gov_pol = {
-	.attrs = dbs_attributes_gov_pol,
-	.name = "conservative",
-};
+	dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL);
+	return dbs_info ? &dbs_info->policy_dbs : NULL;
+}
 
-/************************** sysfs end ************************/
+static void cs_free(struct policy_dbs_info *policy_dbs)
+{
+	kfree(to_dbs_info(policy_dbs));
+}
 
 static int cs_init(struct dbs_data *dbs_data, bool notify)
 {
@@ -332,11 +273,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify)
 		return -ENOMEM;
 	}
 
-	tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice_load = 0;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
+	dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
+	dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
+	dbs_data->ignore_nice_load = 0;
 
 	dbs_data->tuners = tuners;
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
@@ -358,35 +299,66 @@ static void cs_exit(struct dbs_data *dbs_data, bool notify)
 	kfree(dbs_data->tuners);
 }
 
-define_get_cpu_dbs_routines(cs_cpu_dbs_info);
+static void cs_start(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->down_skip = 0;
+	dbs_info->requested_freq = policy->cur;
+}
 
-static struct common_dbs_data cs_dbs_cdata = {
-	.governor = GOV_CONSERVATIVE,
-	.attr_group_gov_sys = &cs_attr_group_gov_sys,
-	.attr_group_gov_pol = &cs_attr_group_gov_pol,
-	.get_cpu_cdbs = get_cpu_cdbs,
-	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+static struct dbs_governor cs_dbs_gov = {
+	.gov = {
+		.name = "conservative",
+		.governor = cpufreq_governor_dbs,
+		.max_transition_latency = TRANSITION_LATENCY_LIMIT,
+		.owner = THIS_MODULE,
+	},
+	.kobj_type = { .default_attrs = cs_attributes },
 	.gov_dbs_timer = cs_dbs_timer,
-	.gov_check_cpu = cs_check_cpu,
+	.alloc = cs_alloc,
+	.free = cs_free,
 	.init = cs_init,
 	.exit = cs_exit,
-	.mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex),
+	.start = cs_start,
 };
 
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event)
+#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_dbs_gov.gov)
+
+static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
 {
-	return cpufreq_governor_dbs(policy, &cs_dbs_cdata, event);
+	struct cpufreq_freqs *freq = data;
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
+	struct cs_policy_dbs_info *dbs_info;
+
+	if (!policy)
+		return 0;
+
+	/* policy isn't governed by conservative governor */
+	if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE)
+		return 0;
+
+	dbs_info = to_dbs_info(policy->governor_data);
+	/*
+	 * we only care if our internally tracked freq moves outside the 'valid'
+	 * ranges of frequency available to us otherwise we do not change it
+	*/
+	if (dbs_info->requested_freq > policy->max
+			|| dbs_info->requested_freq < policy->min)
+		dbs_info->requested_freq = freq->new;
+
+	return 0;
 }
 
 static int __init cpufreq_gov_dbs_init(void)
 {
-	return cpufreq_register_governor(&cpufreq_gov_conservative);
+	return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-	cpufreq_unregister_governor(&cpufreq_gov_conservative);
+	cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
@@ -398,7 +370,7 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return &cpufreq_gov_conservative;
+	return CPU_FREQ_GOV_CONSERVATIVE;
 }
 
 fs_initcall(cpufreq_gov_dbs_init);

drivers/cpufreq/cpufreq_governor.c

@@ -18,95 +18,193 @@
 
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 
 #include "cpufreq_governor.h"
 
-static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
+static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);
+
+static DEFINE_MUTEX(gov_dbs_data_mutex);
+
+/* Common sysfs tunables */
+/**
+ * store_sampling_rate - update sampling rate effective immediately if needed.
+ *
+ * If new rate is smaller than the old, simply updating
+ * dbs.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.
+ *
+ * This must be called with dbs_data->mutex held, otherwise traversing
+ * policy_dbs_list isn't safe.
+ */
+ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+			    size_t count)
 {
-	if (have_governor_per_policy())
-		return dbs_data->cdata->attr_group_gov_pol;
-	else
-		return dbs_data->cdata->attr_group_gov_sys;
+	struct policy_dbs_info *policy_dbs;
+	unsigned int rate;
+	int ret;
+	ret = sscanf(buf, "%u", &rate);
+	if (ret != 1)
+		return -EINVAL;
+
+	dbs_data->sampling_rate = max(rate, dbs_data->min_sampling_rate);
+
+	/*
+	 * We are operating under dbs_data->mutex and so the list and its
+	 * entries can't be freed concurrently.
+	 */
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+		mutex_lock(&policy_dbs->timer_mutex);
+		/*
+		 * On 32-bit architectures this may race with the
+		 * sample_delay_ns read in dbs_update_util_handler(), but that
+		 * really doesn't matter.  If the read returns a value that's
+		 * too big, the sample will be skipped, but the next invocation
+		 * of dbs_update_util_handler() (when the update has been
+		 * completed) will take a sample.
+		 *
+		 * If this runs in parallel with dbs_work_handler(), we may end
+		 * up overwriting the sample_delay_ns value that it has just
+		 * written, but it will be corrected next time a sample is
+		 * taken, so it shouldn't be significant.
+		 */
+		gov_update_sample_delay(policy_dbs, 0);
+		mutex_unlock(&policy_dbs->timer_mutex);
+	}
+
+	return count;
 }
+EXPORT_SYMBOL_GPL(store_sampling_rate);
 
-void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
+/**
+ * gov_update_cpu_data - Update CPU load data.
+ * @dbs_data: Top-level governor data pointer.
+ *
+ * Update CPU load data for all CPUs in the domain governed by @dbs_data
+ * (that may be a single policy or a bunch of them if governor tunables are
+ * system-wide).
+ *
+ * Call under the @dbs_data mutex.
+ */
+void gov_update_cpu_data(struct dbs_data *dbs_data)
 {
-	struct cpu_dbs_info *cdbs = dbs_data->cdata->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 = cdbs->shared->policy;
-	unsigned int sampling_rate;
-	unsigned int max_load = 0;
-	unsigned int ignore_nice;
+	struct policy_dbs_info *policy_dbs;
+
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
 		unsigned int j;
 
-	if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-		struct od_cpu_dbs_info_s *od_dbs_info =
-				dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+		for_each_cpu(j, policy_dbs->policy->cpus) {
+			struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
-		/*
-		 * Sometimes, the ondemand governor uses an additional
-		 * multiplier to give long delays. So apply this multiplier to
-		 * the 'sampling_rate', so as to keep the wake-up-from-idle
-		 * detection logic a bit conservative.
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall,
+								  dbs_data->io_is_busy);
+			if (dbs_data->ignore_nice_load)
+				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(gov_update_cpu_data);
+
+static inline struct dbs_data *to_dbs_data(struct kobject *kobj)
+{
+	return container_of(kobj, struct dbs_data, kobj);
+}
+
+static inline struct governor_attr *to_gov_attr(struct attribute *attr)
+{
+	return container_of(attr, struct governor_attr, attr);
+}
+
+static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct dbs_data *dbs_data = to_dbs_data(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+
+	return gattr->show(dbs_data, buf);
+}
+
+static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct dbs_data *dbs_data = to_dbs_data(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+	int ret = -EBUSY;
+
+	mutex_lock(&dbs_data->mutex);
+
+	if (dbs_data->usage_count)
+		ret = gattr->store(dbs_data, buf, count);
+
+	mutex_unlock(&dbs_data->mutex);
+
+	return ret;
+}
+
+/*
+ * Sysfs Ops for accessing governor attributes.
+ *
+ * All show/store invocations for governor specific sysfs attributes, will first
+ * call the below show/store callbacks and the attribute specific callback will
+ * be called from within it.
  */
-		sampling_rate = od_tuners->sampling_rate;
-		sampling_rate *= od_dbs_info->rate_mult;
+static const struct sysfs_ops governor_sysfs_ops = {
+	.show	= governor_show,
+	.store	= governor_store,
+};
 
-		ignore_nice = od_tuners->ignore_nice_load;
-	} else {
-		sampling_rate = cs_tuners->sampling_rate;
-		ignore_nice = cs_tuners->ignore_nice_load;
-	}
+unsigned int dbs_update(struct cpufreq_policy *policy)
+{
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	unsigned int ignore_nice = dbs_data->ignore_nice_load;
+	unsigned int max_load = 0;
+	unsigned int sampling_rate, io_busy, j;
+
+	/*
+	 * Sometimes governors may use an additional multiplier to increase
+	 * sample delays temporarily.  Apply that multiplier to sampling_rate
+	 * so as to keep the wake-up-from-idle detection logic a bit
+	 * conservative.
+	 */
+	sampling_rate = dbs_data->sampling_rate * policy_dbs->rate_mult;
+	/*
+	 * 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 do not add the iowait time to the CPU idle time then.
+	 */
+	io_busy = dbs_data->io_is_busy;
 
 	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info *j_cdbs;
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 		u64 cur_wall_time, cur_idle_time;
 		unsigned int idle_time, wall_time;
 		unsigned int load;
-		int io_busy = 0;
-
-		j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);
 
-		/*
-		 * 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 do not add
-		 * the iowait time to the cpu idle time.
-		 */
-		if (dbs_data->cdata->governor == GOV_ONDEMAND)
-			io_busy = od_tuners->io_is_busy;
 		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
 
-		wall_time = (unsigned int)
-			(cur_wall_time - j_cdbs->prev_cpu_wall);
+		wall_time = cur_wall_time - j_cdbs->prev_cpu_wall;
 		j_cdbs->prev_cpu_wall = cur_wall_time;
 
-		if (cur_idle_time < j_cdbs->prev_cpu_idle)
-			cur_idle_time = j_cdbs->prev_cpu_idle;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_cdbs->prev_cpu_idle);
+		if (cur_idle_time <= j_cdbs->prev_cpu_idle) {
+			idle_time = 0;
+		} else {
+			idle_time = 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;
+			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			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);
+			idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice);
+			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 
 		if (unlikely(!wall_time || wall_time < idle_time))
@@ -128,10 +226,10 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		 * dropped down. So we perform the copy only once, upon the
 		 * first wake-up from idle.)
 		 *
-		 * Detecting this situation is easy: the governor's deferrable
-		 * timer would not have fired during CPU-idle periods. Hence
-		 * an unusually large 'wall_time' (as compared to the sampling
-		 * rate) indicates this scenario.
+		 * Detecting this situation is easy: the governor's utilization
+		 * update handler would not have run during CPU-idle periods.
+		 * Hence, an unusually large 'wall_time' (as compared to the
+		 * sampling rate) indicates this scenario.
 		 *
 		 * prev_load can be zero in two cases and we must recalculate it
 		 * for both cases:
@@ -156,222 +254,224 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		if (load > max_load)
 			max_load = load;
 	}
-
-	dbs_data->cdata->gov_check_cpu(cpu, max_load);
+	return max_load;
 }
-EXPORT_SYMBOL_GPL(dbs_check_cpu);
+EXPORT_SYMBOL_GPL(dbs_update);
 
-void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay)
+static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
+				unsigned int delay_us)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cpu_dbs_info *cdbs;
+	struct cpufreq_policy *policy = policy_dbs->policy;
 	int cpu;
 
+	gov_update_sample_delay(policy_dbs, delay_us);
+	policy_dbs->last_sample_time = 0;
+
 	for_each_cpu(cpu, policy->cpus) {
-		cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
-		cdbs->timer.expires = jiffies + delay;
-		add_timer_on(&cdbs->timer, cpu);
+		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
+
+		cpufreq_set_update_util_data(cpu, &cdbs->update_util);
 	}
 }
-EXPORT_SYMBOL_GPL(gov_add_timers);
 
-static inline void gov_cancel_timers(struct cpufreq_policy *policy)
+static inline void gov_clear_update_util(struct cpufreq_policy *policy)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cpu_dbs_info *cdbs;
 	int i;
 
-	for_each_cpu(i, policy->cpus) {
-		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
-		del_timer_sync(&cdbs->timer);
-	}
-}
+	for_each_cpu(i, policy->cpus)
+		cpufreq_set_update_util_data(i, NULL);
 
-void gov_cancel_work(struct cpu_common_dbs_info *shared)
-{
-	/* Tell dbs_timer_handler() to skip queuing up work items. */
-	atomic_inc(&shared->skip_work);
-	/*
-	 * If dbs_timer_handler() is already running, it may not notice the
-	 * incremented skip_work, so wait for it to complete to prevent its work
-	 * item from being queued up after the cancel_work_sync() below.
-	 */
-	gov_cancel_timers(shared->policy);
-	/*
-	 * In case dbs_timer_handler() managed to run and spawn a work item
-	 * before the timers have been canceled, wait for that work item to
-	 * complete and then cancel all of the timers set up by it.  If
-	 * dbs_timer_handler() runs again at that point, it will see the
-	 * positive value of skip_work and won't spawn any more work items.
-	 */
-	cancel_work_sync(&shared->work);
-	gov_cancel_timers(shared->policy);
-	atomic_set(&shared->skip_work, 0);
+	synchronize_sched();
 }
-EXPORT_SYMBOL_GPL(gov_cancel_work);
 
-/* Will return if we need to evaluate cpu load again or not */
-static bool need_load_eval(struct cpu_common_dbs_info *shared,
-			   unsigned int sampling_rate)
+static void gov_cancel_work(struct cpufreq_policy *policy)
 {
-	if (policy_is_shared(shared->policy)) {
-		ktime_t time_now = ktime_get();
-		s64 delta_us = ktime_us_delta(time_now, shared->time_stamp);
-
-		/* Do nothing if we recently have sampled */
-		if (delta_us < (s64)(sampling_rate / 2))
-			return false;
-		else
-			shared->time_stamp = time_now;
-	}
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
-	return true;
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
 }
 
 static void dbs_work_handler(struct work_struct *work)
 {
-	struct cpu_common_dbs_info *shared = container_of(work, struct
-					cpu_common_dbs_info, work);
+	struct policy_dbs_info *policy_dbs;
 	struct cpufreq_policy *policy;
-	struct dbs_data *dbs_data;
-	unsigned int sampling_rate, delay;
-	bool eval_load;
+	struct dbs_governor *gov;
 
-	policy = shared->policy;
-	dbs_data = policy->governor_data;
+	policy_dbs = container_of(work, struct policy_dbs_info, work);
+	policy = policy_dbs->policy;
+	gov = dbs_governor_of(policy);
 
-	/* Kill all timers */
-	gov_cancel_timers(policy);
-
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-		sampling_rate = cs_tuners->sampling_rate;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-
-		sampling_rate = od_tuners->sampling_rate;
-	}
-
-	eval_load = need_load_eval(shared, sampling_rate);
+	/*
+	 * Make sure cpufreq_governor_limits() isn't evaluating load or the
+	 * ondemand governor isn't updating the sampling rate in parallel.
+	 */
+	mutex_lock(&policy_dbs->timer_mutex);
+	gov_update_sample_delay(policy_dbs, gov->gov_dbs_timer(policy));
+	mutex_unlock(&policy_dbs->timer_mutex);
 
+	/* Allow the utilization update handler to queue up more work. */
+	atomic_set(&policy_dbs->work_count, 0);
 	/*
-	 * Make sure cpufreq_governor_limits() isn't evaluating load in
-	 * parallel.
+	 * If the update below is reordered with respect to the sample delay
+	 * modification, the utilization update handler may end up using a stale
+	 * sample delay value.
 	 */
-	mutex_lock(&shared->timer_mutex);
-	delay = dbs_data->cdata->gov_dbs_timer(policy, eval_load);
-	mutex_unlock(&shared->timer_mutex);
+	smp_wmb();
+	policy_dbs->work_in_progress = false;
+}
 
-	atomic_dec(&shared->skip_work);
+static void dbs_irq_work(struct irq_work *irq_work)
+{
+	struct policy_dbs_info *policy_dbs;
 
-	gov_add_timers(policy, delay);
+	policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work);
+	schedule_work(&policy_dbs->work);
 }
 
-static void dbs_timer_handler(unsigned long data)
+static void dbs_update_util_handler(struct update_util_data *data, u64 time,
+				    unsigned long util, unsigned long max)
 {
-	struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data;
-	struct cpu_common_dbs_info *shared = cdbs->shared;
+	struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util);
+	struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
+	u64 delta_ns, lst;
 
 	/*
-	 * Timer handler may not be allowed to queue the work at the moment,
-	 * because:
-	 * - Another timer handler has done that
-	 * - We are stopping the governor
-	 * - Or we are updating the sampling rate of the ondemand governor
+	 * The work may not be allowed to be queued up right now.
+	 * Possible reasons:
+	 * - Work has already been queued up or is in progress.
+	 * - It is too early (too little time from the previous sample).
 	 */
-	if (atomic_inc_return(&shared->skip_work) > 1)
-		atomic_dec(&shared->skip_work);
-	else
-		queue_work(system_wq, &shared->work);
-}
+	if (policy_dbs->work_in_progress)
+		return;
 
-static void set_sampling_rate(struct dbs_data *dbs_data,
-		unsigned int sampling_rate)
-{
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-		cs_tuners->sampling_rate = sampling_rate;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-		od_tuners->sampling_rate = sampling_rate;
+	/*
+	 * If the reads below are reordered before the check above, the value
+	 * of sample_delay_ns used in the computation may be stale.
+	 */
+	smp_rmb();
+	lst = READ_ONCE(policy_dbs->last_sample_time);
+	delta_ns = time - lst;
+	if ((s64)delta_ns < policy_dbs->sample_delay_ns)
+		return;
+
+	/*
+	 * If the policy is not shared, the irq_work may be queued up right away
+	 * at this point.  Otherwise, we need to ensure that only one of the
+	 * CPUs sharing the policy will do that.
+	 */
+	if (policy_dbs->is_shared) {
+		if (!atomic_add_unless(&policy_dbs->work_count, 1, 1))
+			return;
+
+		/*
+		 * If another CPU updated last_sample_time in the meantime, we
+		 * shouldn't be here, so clear the work counter and bail out.
+		 */
+		if (unlikely(lst != READ_ONCE(policy_dbs->last_sample_time))) {
+			atomic_set(&policy_dbs->work_count, 0);
+			return;
 		}
+	}
+
+	policy_dbs->last_sample_time = time;
+	policy_dbs->work_in_progress = true;
+	irq_work_queue(&policy_dbs->irq_work);
 }
 
-static int alloc_common_dbs_info(struct cpufreq_policy *policy,
-				 struct common_dbs_data *cdata)
+static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
+						     struct dbs_governor *gov)
 {
-	struct cpu_common_dbs_info *shared;
+	struct policy_dbs_info *policy_dbs;
 	int j;
 
-	/* Allocate memory for the common information for policy->cpus */
-	shared = kzalloc(sizeof(*shared), GFP_KERNEL);
-	if (!shared)
-		return -ENOMEM;
+	/* Allocate memory for per-policy governor data. */
+	policy_dbs = gov->alloc();
+	if (!policy_dbs)
+		return NULL;
 
-	/* Set shared for all CPUs, online+offline */
-	for_each_cpu(j, policy->related_cpus)
-		cdata->get_cpu_cdbs(j)->shared = shared;
+	policy_dbs->policy = policy;
+	mutex_init(&policy_dbs->timer_mutex);
+	atomic_set(&policy_dbs->work_count, 0);
+	init_irq_work(&policy_dbs->irq_work, dbs_irq_work);
+	INIT_WORK(&policy_dbs->work, dbs_work_handler);
 
-	mutex_init(&shared->timer_mutex);
-	atomic_set(&shared->skip_work, 0);
-	INIT_WORK(&shared->work, dbs_work_handler);
-	return 0;
+	/* Set policy_dbs for all CPUs, online+offline */
+	for_each_cpu(j, policy->related_cpus) {
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
+
+		j_cdbs->policy_dbs = policy_dbs;
+		j_cdbs->update_util.func = dbs_update_util_handler;
+	}
+	return policy_dbs;
 }
 
-static void free_common_dbs_info(struct cpufreq_policy *policy,
-				 struct common_dbs_data *cdata)
+static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs,
+				 struct dbs_governor *gov)
 {
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
 	int j;
 
-	mutex_destroy(&shared->timer_mutex);
+	mutex_destroy(&policy_dbs->timer_mutex);
 
-	for_each_cpu(j, policy->cpus)
-		cdata->get_cpu_cdbs(j)->shared = NULL;
+	for_each_cpu(j, policy_dbs->policy->related_cpus) {
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
-	kfree(shared);
+		j_cdbs->policy_dbs = NULL;
+		j_cdbs->update_util.func = NULL;
+	}
+	gov->free(policy_dbs);
 }
 
-static int cpufreq_governor_init(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data,
-				 struct common_dbs_data *cdata)
+static int cpufreq_governor_init(struct cpufreq_policy *policy)
 {
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct dbs_data *dbs_data;
+	struct policy_dbs_info *policy_dbs;
 	unsigned int latency;
-	int ret;
+	int ret = 0;
 
 	/* State should be equivalent to EXIT */
 	if (policy->governor_data)
 		return -EBUSY;
 
-	if (dbs_data) {
-		if (WARN_ON(have_governor_per_policy()))
-			return -EINVAL;
+	policy_dbs = alloc_policy_dbs_info(policy, gov);
+	if (!policy_dbs)
+		return -ENOMEM;
 
-		ret = alloc_common_dbs_info(policy, cdata);
-		if (ret)
-			return ret;
+	/* Protect gov->gdbs_data against concurrent updates. */
+	mutex_lock(&gov_dbs_data_mutex);
+
+	dbs_data = gov->gdbs_data;
+	if (dbs_data) {
+		if (WARN_ON(have_governor_per_policy())) {
+			ret = -EINVAL;
+			goto free_policy_dbs_info;
+		}
+		policy_dbs->dbs_data = dbs_data;
+		policy->governor_data = policy_dbs;
 
+		mutex_lock(&dbs_data->mutex);
 		dbs_data->usage_count++;
-		policy->governor_data = dbs_data;
-		return 0;
+		list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
+		mutex_unlock(&dbs_data->mutex);
+		goto out;
 	}
 
 	dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
-	if (!dbs_data)
-		return -ENOMEM;
+	if (!dbs_data) {
+		ret = -ENOMEM;
+		goto free_policy_dbs_info;
+	}
 
-	ret = alloc_common_dbs_info(policy, cdata);
-	if (ret)
-		goto free_dbs_data;
+	INIT_LIST_HEAD(&dbs_data->policy_dbs_list);
+	mutex_init(&dbs_data->mutex);
 
-	dbs_data->cdata = cdata;
-	dbs_data->usage_count = 1;
-
-	ret = cdata->init(dbs_data, !policy->governor->initialized);
+	ret = gov->init(dbs_data, !policy->governor->initialized);
 	if (ret)
-		goto free_common_dbs_info;
+		goto free_policy_dbs_info;
 
 	/* policy latency is in ns. Convert it to us first */
 	latency = policy->cpuinfo.transition_latency / 1000;
@@ -381,216 +481,156 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy,
 	/* Bring kernel and HW constraints together */
 	dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
 					  MIN_LATENCY_MULTIPLIER * latency);
-	set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
-					latency * LATENCY_MULTIPLIER));
+	dbs_data->sampling_rate = max(dbs_data->min_sampling_rate,
+				      LATENCY_MULTIPLIER * latency);
 
 	if (!have_governor_per_policy())
-		cdata->gdbs_data = dbs_data;
+		gov->gdbs_data = dbs_data;
 
-	policy->governor_data = dbs_data;
+	policy->governor_data = policy_dbs;
 
-	ret = sysfs_create_group(get_governor_parent_kobj(policy),
-				 get_sysfs_attr(dbs_data));
-	if (ret)
-		goto reset_gdbs_data;
+	policy_dbs->dbs_data = dbs_data;
+	dbs_data->usage_count = 1;
+	list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
 
-	return 0;
+	gov->kobj_type.sysfs_ops = &governor_sysfs_ops;
+	ret = kobject_init_and_add(&dbs_data->kobj, &gov->kobj_type,
+				   get_governor_parent_kobj(policy),
+				   "%s", gov->gov.name);
+	if (!ret)
+		goto out;
+
+	/* Failure, so roll back. */
+	pr_err("cpufreq: Governor initialization failed (dbs_data kobject init error %d)\n", ret);
 
-reset_gdbs_data:
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
-		cdata->gdbs_data = NULL;
-	cdata->exit(dbs_data, !policy->governor->initialized);
-free_common_dbs_info:
-	free_common_dbs_info(policy, cdata);
-free_dbs_data:
+		gov->gdbs_data = NULL;
+	gov->exit(dbs_data, !policy->governor->initialized);
 	kfree(dbs_data);
+
+free_policy_dbs_info:
+	free_policy_dbs_info(policy_dbs, gov);
+
+out:
+	mutex_unlock(&gov_dbs_data_mutex);
 	return ret;
 }
 
-static int cpufreq_governor_exit(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data)
+static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	int count;
 
-	/* State should be equivalent to INIT */
-	if (!cdbs->shared || cdbs->shared->policy)
-		return -EBUSY;
+	/* Protect gov->gdbs_data against concurrent updates. */
+	mutex_lock(&gov_dbs_data_mutex);
+
+	mutex_lock(&dbs_data->mutex);
+	list_del(&policy_dbs->list);
+	count = --dbs_data->usage_count;
+	mutex_unlock(&dbs_data->mutex);
 
-	if (!--dbs_data->usage_count) {
-		sysfs_remove_group(get_governor_parent_kobj(policy),
-				   get_sysfs_attr(dbs_data));
+	if (!count) {
+		kobject_put(&dbs_data->kobj);
 
 		policy->governor_data = NULL;
 
 		if (!have_governor_per_policy())
-			cdata->gdbs_data = NULL;
+			gov->gdbs_data = NULL;
 
-		cdata->exit(dbs_data, policy->governor->initialized == 1);
+		gov->exit(dbs_data, policy->governor->initialized == 1);
+		mutex_destroy(&dbs_data->mutex);
 		kfree(dbs_data);
 	} else {
 		policy->governor_data = NULL;
 	}
 
-	free_common_dbs_info(policy, cdata);
+	free_policy_dbs_info(policy_dbs, gov);
+
+	mutex_unlock(&gov_dbs_data_mutex);
 	return 0;
 }
 
-static int cpufreq_governor_start(struct cpufreq_policy *policy,
-				  struct dbs_data *dbs_data)
+static int cpufreq_governor_start(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
-	int io_busy = 0;
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	unsigned int sampling_rate, ignore_nice, j;
+	unsigned int io_busy;
 
 	if (!policy->cur)
 		return -EINVAL;
 
-	/* State should be equivalent to INIT */
-	if (!shared || shared->policy)
-		return -EBUSY;
-
-	if (cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	policy_dbs->is_shared = policy_is_shared(policy);
+	policy_dbs->rate_mult = 1;
 
-		sampling_rate = cs_tuners->sampling_rate;
-		ignore_nice = cs_tuners->ignore_nice_load;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-
-		sampling_rate = od_tuners->sampling_rate;
-		ignore_nice = od_tuners->ignore_nice_load;
-		io_busy = od_tuners->io_is_busy;
-	}
-
-	shared->policy = policy;
-	shared->time_stamp = ktime_get();
+	sampling_rate = dbs_data->sampling_rate;
+	ignore_nice = dbs_data->ignore_nice_load;
+	io_busy = dbs_data->io_is_busy;
 
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j);
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 		unsigned int prev_load;
 
-		j_cdbs->prev_cpu_idle =
-			get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
+		j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
 
-		prev_load = (unsigned int)(j_cdbs->prev_cpu_wall -
-					    j_cdbs->prev_cpu_idle);
-		j_cdbs->prev_load = 100 * prev_load /
-				    (unsigned int)j_cdbs->prev_cpu_wall;
+		prev_load = j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle;
+		j_cdbs->prev_load = 100 * prev_load / (unsigned int)j_cdbs->prev_cpu_wall;
 
 		if (ignore_nice)
 			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-
-		__setup_timer(&j_cdbs->timer, dbs_timer_handler,
-			      (unsigned long)j_cdbs,
-			      TIMER_DEFERRABLE | TIMER_IRQSAFE);
 	}
 
-	if (cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_cpu_dbs_info_s *cs_dbs_info =
-			cdata->get_cpu_dbs_info_s(cpu);
+	gov->start(policy);
 
-		cs_dbs_info->down_skip = 0;
-		cs_dbs_info->requested_freq = policy->cur;
-	} else {
-		struct od_ops *od_ops = cdata->gov_ops;
-		struct od_cpu_dbs_info_s *od_dbs_info = cdata->get_cpu_dbs_info_s(cpu);
-
-		od_dbs_info->rate_mult = 1;
-		od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
-		od_ops->powersave_bias_init_cpu(cpu);
-	}
-
-	gov_add_timers(policy, delay_for_sampling_rate(sampling_rate));
+	gov_set_update_util(policy_dbs, sampling_rate);
 	return 0;
 }
 
-static int cpufreq_governor_stop(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data)
+static int cpufreq_governor_stop(struct cpufreq_policy *policy)
 {
-	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(policy->cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
-
-	/* State should be equivalent to START */
-	if (!shared || !shared->policy)
-		return -EBUSY;
-
-	gov_cancel_work(shared);
-	shared->policy = NULL;
-
+	gov_cancel_work(policy);
 	return 0;
 }
 
-static int cpufreq_governor_limits(struct cpufreq_policy *policy,
-				   struct dbs_data *dbs_data)
+static int cpufreq_governor_limits(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
-	/* State should be equivalent to START */
-	if (!cdbs->shared || !cdbs->shared->policy)
-		return -EBUSY;
+	mutex_lock(&policy_dbs->timer_mutex);
+
+	if (policy->max < policy->cur)
+		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
+	else if (policy->min > policy->cur)
+		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
 
-	mutex_lock(&cdbs->shared->timer_mutex);
-	if (policy->max < cdbs->shared->policy->cur)
-		__cpufreq_driver_target(cdbs->shared->policy, policy->max,
-					CPUFREQ_RELATION_H);
-	else if (policy->min > cdbs->shared->policy->cur)
-		__cpufreq_driver_target(cdbs->shared->policy, policy->min,
-					CPUFREQ_RELATION_L);
-	dbs_check_cpu(dbs_data, cpu);
-	mutex_unlock(&cdbs->shared->timer_mutex);
+	gov_update_sample_delay(policy_dbs, 0);
+
+	mutex_unlock(&policy_dbs->timer_mutex);
 
 	return 0;
 }
 
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-			 struct common_dbs_data *cdata, unsigned int event)
+int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event)
 {
-	struct dbs_data *dbs_data;
-	int ret;
-
-	/* Lock governor to block concurrent initialization of governor */
-	mutex_lock(&cdata->mutex);
-
-	if (have_governor_per_policy())
-		dbs_data = policy->governor_data;
-	else
-		dbs_data = cdata->gdbs_data;
-
-	if (!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT)) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
+	if (event == CPUFREQ_GOV_POLICY_INIT) {
+		return cpufreq_governor_init(policy);
+	} else if (policy->governor_data) {
 		switch (event) {
-	case CPUFREQ_GOV_POLICY_INIT:
-		ret = cpufreq_governor_init(policy, dbs_data, cdata);
-		break;
 		case CPUFREQ_GOV_POLICY_EXIT:
-		ret = cpufreq_governor_exit(policy, dbs_data);
-		break;
+			return cpufreq_governor_exit(policy);
 		case CPUFREQ_GOV_START:
-		ret = cpufreq_governor_start(policy, dbs_data);
-		break;
+			return cpufreq_governor_start(policy);
 		case CPUFREQ_GOV_STOP:
-		ret = cpufreq_governor_stop(policy, dbs_data);
-		break;
+			return cpufreq_governor_stop(policy);
 		case CPUFREQ_GOV_LIMITS:
-		ret = cpufreq_governor_limits(policy, dbs_data);
-		break;
-	default:
-		ret = -EINVAL;
+			return cpufreq_governor_limits(policy);
 		}
-
-unlock:
-	mutex_unlock(&cdata->mutex);
-
-	return ret;
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);

drivers/cpufreq/cpufreq_governor.h

@@ -18,6 +18,7 @@
 #define _CPUFREQ_GOVERNOR_H
 
 #include <linux/atomic.h>
+#include <linux/irq_work.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -41,96 +42,68 @@
 enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
 /*
- * Macro for creating governors sysfs routines
- *
- * - gov_sys: One governor instance per whole system
- * - gov_pol: One governor instance per policy
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * od_*: On-demand governor
+ * cs_*: Conservative governor
  */
 
-/* Create attributes */
-#define gov_sys_attr_ro(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0444, show_##_name##_gov_sys, NULL)
-
-#define gov_sys_attr_rw(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
-
-#define gov_pol_attr_ro(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0444, show_##_name##_gov_pol, NULL)
-
-#define gov_pol_attr_rw(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
+/* Governor demand based switching data (per-policy or global). */
+struct dbs_data {
+	int usage_count;
+	void *tuners;
+	unsigned int min_sampling_rate;
+	unsigned int ignore_nice_load;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int io_is_busy;
 
-#define gov_sys_pol_attr_rw(_name)					\
-	gov_sys_attr_rw(_name);						\
-	gov_pol_attr_rw(_name)
+	struct kobject kobj;
+	struct list_head policy_dbs_list;
+	/*
+	 * Protect concurrent updates to governor tunables from sysfs,
+	 * policy_dbs_list and usage_count.
+	 */
+	struct mutex mutex;
+};
 
-#define gov_sys_pol_attr_ro(_name)					\
-	gov_sys_attr_ro(_name);						\
-	gov_pol_attr_ro(_name)
+/* Governor's specific attributes */
+struct dbs_data;
+struct governor_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
+	ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
+			 size_t count);
+};
 
-/* Create show/store routines */
-#define show_one(_gov, file_name)					\
-static ssize_t show_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
+#define gov_show_one(_gov, file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct _gov##_dbs_tuners *tuners = _gov##_dbs_cdata.gdbs_data->tuners; \
-	return sprintf(buf, "%u\n", tuners->file_name);			\
-}									\
-									\
-static ssize_t show_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
 	struct _gov##_dbs_tuners *tuners = dbs_data->tuners;		\
 	return sprintf(buf, "%u\n", tuners->file_name);			\
 }
 
-#define store_one(_gov, file_name)					\
-static ssize_t store_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) \
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
-}									\
-									\
-static ssize_t store_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, const char *buf, size_t count)		\
+#define gov_show_one_common(file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
+	return sprintf(buf, "%u\n", dbs_data->file_name);		\
 }
 
-#define show_store_one(_gov, file_name)					\
-show_one(_gov, file_name);						\
-store_one(_gov, file_name)
+#define gov_attr_ro(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0444, show_##_name, NULL)
 
-/* create helper routines */
-#define define_get_cpu_dbs_routines(_dbs_info)				\
-static struct cpu_dbs_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
- * od_*: On-demand governor
- * cs_*: Conservative governor
- */
+#define gov_attr_rw(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0644, show_##_name, store_##_name)
 
 /* Common to all CPUs of a policy */
-struct cpu_common_dbs_info {
+struct policy_dbs_info {
 	struct cpufreq_policy *policy;
 	/*
 	 * Per policy mutex that serializes load evaluation from limit-change
@@ -138,11 +111,27 @@ struct cpu_common_dbs_info {
 	 */
 	struct mutex timer_mutex;
 
-	ktime_t time_stamp;
-	atomic_t skip_work;
+	u64 last_sample_time;
+	s64 sample_delay_ns;
+	atomic_t work_count;
+	struct irq_work irq_work;
 	struct work_struct work;
+	/* dbs_data may be shared between multiple policy objects */
+	struct dbs_data *dbs_data;
+	struct list_head list;
+	/* Multiplier for increasing sample delay temporarily. */
+	unsigned int rate_mult;
+	/* Status indicators */
+	bool is_shared;		/* This object is used by multiple CPUs */
+	bool work_in_progress;	/* Work is being queued up or in progress */
 };
 
+static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs,
+					   unsigned int delay_us)
+{
+	policy_dbs->sample_delay_ns = delay_us * NSEC_PER_USEC;
+}
+
 /* Per cpu structures */
 struct cpu_dbs_info {
 	u64 prev_cpu_idle;
@@ -155,54 +144,14 @@ struct cpu_dbs_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	struct timer_list timer;
-	struct cpu_common_dbs_info *shared;
-};
-
-struct od_cpu_dbs_info_s {
-	struct cpu_dbs_info cdbs;
-	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_info cdbs;
-	unsigned int down_skip;
-	unsigned int requested_freq;
-};
-
-/* Per policy Governors sysfs tunables */
-struct od_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int powersave_bias;
-	unsigned int io_is_busy;
-};
-
-struct cs_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int down_threshold;
-	unsigned int freq_step;
+	struct update_util_data update_util;
+	struct policy_dbs_info *policy_dbs;
 };
 
 /* Common Governor data across policies */
-struct dbs_data;
-struct common_dbs_data {
-	/* Common across governors */
-	#define GOV_ONDEMAND		0
-	#define GOV_CONSERVATIVE	1
-	int governor;
-	struct attribute_group *attr_group_gov_sys; /* one governor - system */
-	struct attribute_group *attr_group_gov_pol; /* one governor - policy */
+struct dbs_governor {
+	struct cpufreq_governor gov;
+	struct kobj_type kobj_type;
 
 	/*
 	 * Common data for platforms that don't set
@@ -210,74 +159,32 @@ struct common_dbs_data {
 	 */
 	struct dbs_data *gdbs_data;
 
-	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
-	void *(*get_cpu_dbs_info_s)(int cpu);
-	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy,
-				      bool modify_all);
-	void (*gov_check_cpu)(int cpu, unsigned int load);
+	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
+	struct policy_dbs_info *(*alloc)(void);
+	void (*free)(struct policy_dbs_info *policy_dbs);
 	int (*init)(struct dbs_data *dbs_data, bool notify);
 	void (*exit)(struct dbs_data *dbs_data, bool notify);
-
-	/* Governor specific ops, see below */
-	void *gov_ops;
-
-	/*
-	 * Protects governor's data (struct dbs_data and struct common_dbs_data)
-	 */
-	struct mutex mutex;
+	void (*start)(struct cpufreq_policy *policy);
 };
 
-/* Governor Per policy data */
-struct dbs_data {
-	struct common_dbs_data *cdata;
-	unsigned int min_sampling_rate;
-	int usage_count;
-	void *tuners;
-};
+static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
+{
+	return container_of(policy->governor, struct dbs_governor, gov);
+}
 
-/* Governor specific ops, will be passed to dbs_data->gov_ops */
+/* Governor specific operations */
 struct od_ops {
-	void (*powersave_bias_init_cpu)(int cpu);
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
 			unsigned int freq_next, unsigned int relation);
-	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
-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;
-}
-
-#define declare_show_sampling_rate_min(_gov)				\
-static ssize_t show_sampling_rate_min_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}									\
-									\
-static ssize_t show_sampling_rate_min_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}
-
-extern struct mutex cpufreq_governor_lock;
-
-void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay);
-void gov_cancel_work(struct cpu_common_dbs_info *shared);
-void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		struct common_dbs_data *cdata, unsigned int event);
+unsigned int dbs_update(struct cpufreq_policy *policy);
+int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
 void od_unregister_powersave_bias_handler(void);
+ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+			    size_t count);
+void gov_update_cpu_data(struct dbs_data *dbs_data);
 #endif /* _CPUFREQ_GOVERNOR_H */

drivers/cpufreq/cpufreq_ondemand.c

@@ -16,7 +16,8 @@
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
 #include <linux/tick.h>
-#include "cpufreq_governor.h"
+
+#include "cpufreq_ondemand.h"
 
 /* On-demand governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
@@ -27,22 +28,10 @@
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
 #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;
 
-static struct cpufreq_governor cpufreq_gov_ondemand;
-
 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.
@@ -68,8 +57,8 @@ static int should_io_be_busy(void)
 
 /*
  * 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)
@@ -77,15 +66,15 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 	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 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;
 
 	if (!dbs_info->freq_table) {
 		dbs_info->freq_lo = 0;
-		dbs_info->freq_lo_jiffies = 0;
+		dbs_info->freq_lo_delay_us = 0;
 		return freq_next;
 	}
 
@@ -108,31 +97,30 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 	/* 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_table = cpufreq_frequency_get_table(policy->cpu);
+	dbs_info->freq_lo = 0;
 }
 
 static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 {
-	struct dbs_data *dbs_data = policy->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)
@@ -150,21 +138,21 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
  * (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)
+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.shared->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 > od_tuners->up_threshold) {
+	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);
 	} else {
 		/* Calculate the next frequency proportional to load */
@@ -175,177 +163,70 @@ static void od_check_cpu(int cpu, unsigned int load)
 		freq_next = min_f + load * (max_f - min_f) / 100;
 
 		/* No longer fully busy, reset rate_mult */
-		dbs_info->rate_mult = 1;
-
-		if (!od_tuners->powersave_bias) {
-			__cpufreq_driver_target(policy, freq_next,
-					CPUFREQ_RELATION_C);
-			return;
-		}
+		policy_dbs->rate_mult = 1;
 
-		freq_next = od_ops.powersave_bias_target(policy, freq_next,
+		if (od_tuners->powersave_bias)
+			freq_next = od_ops.powersave_bias_target(policy,
+								 freq_next,
 								 CPUFREQ_RELATION_L);
+
 		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_C);
 	}
 }
 
-static unsigned int od_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
+static unsigned int od_dbs_timer(struct cpufreq_policy *policy)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	unsigned int cpu = policy->cpu;
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-			cpu);
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int delay = 0, sample_type = dbs_info->sample_type;
-
-	if (!modify_all)
-		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 */
 	dbs_info->sample_type = OD_NORMAL_SAMPLE;
-	if (sample_type == OD_SUB_SAMPLE) {
-		delay = dbs_info->freq_lo_jiffies;
+	/*
+	 * 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_H);
-	} else {
-		dbs_check_cpu(dbs_data, cpu);
+		return dbs_info->freq_lo_delay_us;
+	}
+
+	od_update(policy);
+
 	if (dbs_info->freq_lo) {
 		/* Setup timer for SUB_SAMPLE */
 		dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = dbs_info->freq_hi_jiffies;
+		return dbs_info->freq_hi_delay_us;
 	}
-	}
-
-max_delay:
-	if (!delay)
-		delay = delay_for_sampling_rate(od_tuners->sampling_rate
-				* dbs_info->rate_mult);
 
-	return delay;
+	return dbs_data->sampling_rate * policy_dbs->rate_mult;
 }
 
 /************************** 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;
-	struct cpumask cpumask;
-	int cpu;
-
-	od_tuners->sampling_rate = new_rate = max(new_rate,
-			dbs_data->min_sampling_rate);
-
-	/*
-	 * Lock governor so that governor start/stop can't execute in parallel.
-	 */
-	mutex_lock(&od_dbs_cdata.mutex);
-
-	cpumask_copy(&cpumask, cpu_online_mask);
-
-	for_each_cpu(cpu, &cpumask) {
-		struct cpufreq_policy *policy;
-		struct od_cpu_dbs_info_s *dbs_info;
-		struct cpu_dbs_info *cdbs;
-		struct cpu_common_dbs_info *shared;
-		unsigned long next_sampling, appointed_at;
-
-		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-		cdbs = &dbs_info->cdbs;
-		shared = cdbs->shared;
-
-		/*
-		 * A valid shared and shared->policy means governor hasn't
-		 * stopped or exited yet.
-		 */
-		if (!shared || !shared->policy)
-			continue;
-
-		policy = shared->policy;
-
-		/* clear all CPUs of this policy */
-		cpumask_andnot(&cpumask, &cpumask, policy->cpus);
-
-		/*
-		 * Update sampling rate for CPUs whose policy is governed by
-		 * dbs_data. In case of governor_per_policy, only a single
-		 * policy will be governed by dbs_data, otherwise there can be
-		 * multiple policies that are governed by the same dbs_data.
-		 */
-		if (dbs_data != policy->governor_data)
-			continue;
-
-		/*
-		 * Checking this for any CPU should be fine, timers for all of
-		 * them are scheduled together.
-		 */
-		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.timer.expires;
-
-		if (time_before(next_sampling, appointed_at)) {
-			gov_cancel_work(shared);
-			gov_add_timers(policy, usecs_to_jiffies(new_rate));
-
-		}
-	}
-
-	mutex_unlock(&od_dbs_cdata.mutex);
-}
-
-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;
-}
+static struct dbs_governor od_dbs_gov;
 
 static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
 		size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	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)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -355,40 +236,43 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 		return -EINVAL;
 	}
 
-	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)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	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, &dbs_data->policy_dbs_list, list) {
+		/*
+		 * Doing this without locking might lead to using different
+		 * rate_mult values in od_update() and od_dbs_timer().
+		 */
+		mutex_lock(&policy_dbs->timer_mutex);
+		policy_dbs->rate_mult = 1;
+		mutex_unlock(&policy_dbs->timer_mutex);
 	}
+
 	return count;
 }
 
 static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 
-	unsigned int j;
-
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
@@ -396,22 +280,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	if (input > 1)
 		input = 1;
 
-	if (input == od_tuners->ignore_nice_load) { /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) { /* nothing to do */
 		return count;
 	}
-	od_tuners->ignore_nice_load = 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_load)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+	gov_update_cpu_data(dbs_data);
 
-	}
 	return count;
 }
 
@@ -419,6 +295,7 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 		size_t count)
 {
 	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);
@@ -430,59 +307,54 @@ 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, &dbs_data->policy_dbs_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_load);
-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_load);
-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_load_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(min_sampling_rate);
+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);
+gov_attr_ro(min_sampling_rate);
+
+static struct attribute *od_attributes[] = {
+	&min_sampling_rate.attr,
+	&sampling_rate.attr,
+	&up_threshold.attr,
+	&sampling_down_factor.attr,
+	&ignore_nice_load.attr,
+	&powersave_bias.attr,
+	&io_is_busy.attr,
 	NULL
 };
 
-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_load_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, bool notify)
 {
@@ -501,7 +373,7 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 	put_cpu();
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
-		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
+		dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -509,17 +381,17 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 		*/
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
-		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
+		dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 			jiffies_to_usecs(10);
 	}
 
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice_load = 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 = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
 	return 0;
@@ -530,46 +402,38 @@ static void od_exit(struct dbs_data *dbs_data, bool notify)
 	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,
+static struct dbs_governor od_dbs_gov = {
+	.gov = {
+		.name = "ondemand",
+		.governor = cpufreq_governor_dbs,
+		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
+		.owner = THIS_MODULE,
+	},
+	.kobj_type = { .default_attrs = od_attributes },
 	.gov_dbs_timer = od_dbs_timer,
-	.gov_check_cpu = od_check_cpu,
-	.gov_ops = &od_ops,
+	.alloc = od_alloc,
+	.free = od_free,
 	.init = od_init,
 	.exit = od_exit,
-	.mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex),
+	.start = od_start,
 };
 
-static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		unsigned int event)
-{
-	return cpufreq_governor_dbs(policy, &od_dbs_cdata, event);
-}
-
-static struct cpufreq_governor cpufreq_gov_ondemand = {
-	.name			= "ondemand",
-	.governor		= od_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
+#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;
 
@@ -578,22 +442,25 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
-		struct cpu_common_dbs_info *shared;
+		struct cpufreq_policy *policy;
+		struct policy_dbs_info *policy_dbs;
+		struct dbs_data *dbs_data;
+		struct od_dbs_tuners *od_tuners;
 
 		if (cpumask_test_cpu(cpu, &done))
 			continue;
 
-		shared = per_cpu(od_cpu_dbs_info, cpu).cdbs.shared;
-		if (!shared)
+		policy = cpufreq_cpu_get_raw(cpu);
+		if (!policy || policy->governor != CPU_FREQ_GOV_ONDEMAND)
 			continue;
 
-		policy = shared->policy;
-		cpumask_or(&done, &done, policy->cpus);
-
-		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;
 	}
@@ -618,12 +485,12 @@ EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
 
 static int __init cpufreq_gov_dbs_init(void)
 {
-	return cpufreq_register_governor(&cpufreq_gov_ondemand);
+	return cpufreq_register_governor(CPU_FREQ_GOV_ONDEMAND);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
+	cpufreq_unregister_governor(CPU_FREQ_GOV_ONDEMAND);
 }
 
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
@@ -635,7 +502,7 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return &cpufreq_gov_ondemand;
+	return CPU_FREQ_GOV_ONDEMAND;
 }
 
 fs_initcall(cpufreq_gov_dbs_init);

drivers/cpufreq/cpufreq_ondemand.h

+/*
+ * Header file for CPUFreq ondemand governor and related code.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "cpufreq_governor.h"
+
+struct od_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_delay_us;
+	unsigned int freq_hi_delay_us;
+	unsigned int sample_type:1;
+};
+
+static inline struct od_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct od_policy_dbs_info, policy_dbs);
+}
+
+struct od_dbs_tuners {
+	unsigned int powersave_bias;
+};

drivers/cpufreq/intel_pstate.c

@@ -71,7 +71,7 @@ struct sample {
 	u64 mperf;
 	u64 tsc;
 	int freq;
-	ktime_t time;
+	u64 time;
 };
 
 struct pstate_data {
@@ -103,13 +103,13 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
-	struct timer_list timer;
+	struct update_util_data update_util;
 
 	struct pstate_data pstate;
 	struct vid_data vid;
 	struct _pid pid;
 
-	ktime_t last_sample_time;
+	u64	last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
@@ -120,6 +120,7 @@ struct cpudata {
 static struct cpudata **all_cpu_data;
 struct pstate_adjust_policy {
 	int sample_rate_ms;
+	s64 sample_rate_ns;
 	int deadband;
 	int setpoint;
 	int p_gain_pct;
@@ -718,7 +719,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
-	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
+	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
 static int knl_get_turbo_pstate(void)
@@ -889,7 +890,7 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	sample->core_pct_busy = (int32_t)core_pct;
 }
 
-static inline void intel_pstate_sample(struct cpudata *cpu)
+static inline void intel_pstate_sample(struct cpudata *cpu, u64 time)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
@@ -906,7 +907,7 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
-	cpu->sample.time = ktime_get();
+	cpu->sample.time = time;
 	cpu->sample.aperf = aperf;
 	cpu->sample.mperf = mperf;
 	cpu->sample.tsc =  tsc;
@@ -921,22 +922,6 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	cpu->prev_tsc = tsc;
 }
 
-static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
-{
-	int delay;
-
-	delay = msecs_to_jiffies(50);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
-static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
-{
-	int delay;
-
-	delay = msecs_to_jiffies(pid_params.sample_rate_ms);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
@@ -976,8 +961,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 {
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
-	s64 duration_us;
-	u32 sample_time;
+	u64 duration_ns;
 
 	/*
 	 * core_busy is the ratio of actual performance to max
@@ -996,18 +980,16 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
 	/*
-	 * Since we have a deferred timer, it will not fire unless
-	 * we are in C0.  So, determine if the actual elapsed time
-	 * is significantly greater (3x) than our sample interval.  If it
-	 * is, then we were idle for a long enough period of time
-	 * to adjust our busyness.
+	 * Since our utilization update callback will not run unless we are
+	 * in C0, check if the actual elapsed time is significantly greater (3x)
+	 * than our sample interval.  If it is, then we were idle for a long
+	 * enough period of time to adjust our busyness.
 	 */
-	sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-	duration_us = ktime_us_delta(cpu->sample.time,
-				     cpu->last_sample_time);
-	if (duration_us > sample_time * 3) {
-		sample_ratio = div_fp(int_tofp(sample_time),
-				      int_tofp(duration_us));
+	duration_ns = cpu->sample.time - cpu->last_sample_time;
+	if ((s64)duration_ns > pid_params.sample_rate_ns * 3
+	    && cpu->last_sample_time > 0) {
+		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
+				      int_tofp(duration_ns));
 		core_busy = mul_fp(core_busy, sample_ratio);
 	}
 
@@ -1037,23 +1019,17 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 		sample->freq);
 }
 
-static void intel_hwp_timer_func(unsigned long __data)
-{
-	struct cpudata *cpu = (struct cpudata *) __data;
-
-	intel_pstate_sample(cpu);
-	intel_hwp_set_sample_time(cpu);
-}
-
-static void intel_pstate_timer_func(unsigned long __data)
+static void intel_pstate_update_util(struct update_util_data *data, u64 time,
+				     unsigned long util, unsigned long max)
 {
-	struct cpudata *cpu = (struct cpudata *) __data;
-
-	intel_pstate_sample(cpu);
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+	u64 delta_ns = time - cpu->sample.time;
 
+	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
+		intel_pstate_sample(cpu, time);
+		if (!hwp_active)
 			intel_pstate_adjust_busy_pstate(cpu);
-
-	intel_pstate_set_sample_time(cpu);
+	}
 }
 
 #define ICPU(model, policy) \
@@ -1101,24 +1077,19 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	cpu->cpu = cpunum;
 
-	if (hwp_active)
+	if (hwp_active) {
 		intel_pstate_hwp_enable(cpu);
+		pid_params.sample_rate_ms = 50;
+		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+	}
 
 	intel_pstate_get_cpu_pstates(cpu);
 
-	init_timer_deferrable(&cpu->timer);
-	cpu->timer.data = (unsigned long)cpu;
-	cpu->timer.expires = jiffies + HZ/100;
-
-	if (!hwp_active)
-		cpu->timer.function = intel_pstate_timer_func;
-	else
-		cpu->timer.function = intel_hwp_timer_func;
-
 	intel_pstate_busy_pid_reset(cpu);
-	intel_pstate_sample(cpu);
+	intel_pstate_sample(cpu, 0);
 
-	add_timer_on(&cpu->timer, cpunum);
+	cpu->update_util.func = intel_pstate_update_util;
+	cpufreq_set_update_util_data(cpunum, &cpu->update_util);
 
 	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
@@ -1202,7 +1173,9 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 
 	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
-	del_timer_sync(&all_cpu_data[cpu_num]->timer);
+	cpufreq_set_update_util_data(cpu_num, NULL);
+	synchronize_sched();
+
 	if (hwp_active)
 		return;
 
@@ -1266,6 +1239,7 @@ static int intel_pstate_msrs_not_valid(void)
 static void copy_pid_params(struct pstate_adjust_policy *policy)
 {
 	pid_params.sample_rate_ms = policy->sample_rate_ms;
+	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
 	pid_params.p_gain_pct = policy->p_gain_pct;
 	pid_params.i_gain_pct = policy->i_gain_pct;
 	pid_params.d_gain_pct = policy->d_gain_pct;
@@ -1467,7 +1441,8 @@ static int __init intel_pstate_init(void)
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if (all_cpu_data[cpu]) {
-			del_timer_sync(&all_cpu_data[cpu]->timer);
+			cpufreq_set_update_util_data(cpu, NULL);
+			synchronize_sched();
 			kfree(all_cpu_data[cpu]);
 		}
 	}

include/linux/cpufreq.h

@@ -80,7 +80,6 @@ struct cpufreq_policy {
 	unsigned int		last_policy; /* policy before unplug */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
-	bool			governor_enabled; /* governor start/stop flag */
 	char			last_governor[CPUFREQ_NAME_LEN]; /* last governor used */
 
 	struct work_struct	update; /* if update_policy() needs to be
@@ -100,10 +99,6 @@ struct cpufreq_policy {
 	 * - Any routine that will write to the policy structure and/or may take away
 	 *   the policy altogether (eg. CPU hotplug), will hold this lock in write
 	 *   mode before doing so.
-	 *
-	 * Additional rules:
-	 * - Lock should not be held across
-	 *     __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
 	 */
 	struct rw_semaphore	rwsem;
 

include/linux/sched.h

@@ -3207,4 +3207,13 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CPU_FREQ
+struct update_util_data {
+	void (*func)(struct update_util_data *data,
+		     u64 time, unsigned long util, unsigned long max);
+};
+
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data);
+#endif /* CONFIG_CPU_FREQ */
+
 #endif

kernel/sched/Makefile

@@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o

kernel/sched/cpufreq.c

+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.  That pointer
+ * points to a struct update_util_data object containing a callback function
+ * to call from cpufreq_update_util().  That function will be called from an RCU
+ * read-side critical section, so it must not sleep.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data)
+{
+	if (WARN_ON(data && !data->func))
+		return;
+
+	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data);

kernel/sched/deadline.c

@@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq)
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	/*
 	 * Consumed budget is computed considering the time as
 	 * observed by schedulable tasks (excluding time spent

kernel/sched/fair.c

@@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int cpu = cpu_of(rq_of(cfs_rq));
+	struct rq *rq = rq_of(cfs_rq);
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
@@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
+
+	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+		unsigned long max = rq->cpu_capacity_orig;
+
+		/*
+		 * There are a few boundary cases this might miss but it should
+		 * get called often enough that that should (hopefully) not be
+		 * a real problem -- added to that it only calls on the local
+		 * CPU, so if we enqueue remotely we'll miss an update, but
+		 * the next tick/schedule should update.
+		 *
+		 * It will not get called when we go idle, because the idle
+		 * thread is a different class (!fair), nor will the utilization
+		 * number include things like RT tasks.
+		 *
+		 * As is, the util number is not freq-invariant (we'd have to
+		 * implement arch_scale_freq_capacity() for that).
+		 *
+		 * See cpu_util().
+		 */
+		cpufreq_update_util(rq_clock(rq),
+				    min(cfs_rq->avg.util_avg, max), max);
+	}
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)

kernel/sched/rt.c

@@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq)
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;

kernel/sched/sched.h

@@ -1738,3 +1738,51 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @time: Current time.
+ * @util: Current utilization.
+ * @max: Utilization ceiling.
+ *
+ * This function is called by the scheduler on every invocation of
+ * update_load_avg() on the CPU whose utilization is being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ */
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
+{
+       struct update_util_data *data;
+
+       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+       if (data)
+               data->func(data, time, util, max);
+}
+
+/**
+ * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
+ * @time: Current time.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid.  Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_trigger_update(u64 time)
+{
+	cpufreq_update_util(time, ULONG_MAX, 0);
+}
+#else
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
+static inline void cpufreq_trigger_update(u64 time) {}
+#endif /* CONFIG_CPU_FREQ */