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.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.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 */