1 files changed, 136 insertions, 223 deletions

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7fbaee24c824..9161d1136d01 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -6,13 +6,6 @@
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "sched.h"
-
-#include <linux/sched/cpufreq.h>
-#include <trace/events/power.h>
-
 #define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
 
 struct sugov_tunables {
@@ -26,12 +19,15 @@ struct sugov_policy {
 	struct sugov_tunables	*tunables;
 	struct list_head	tunables_hook;
 
-	raw_spinlock_t		update_lock;	/* For shared policies */
+	raw_spinlock_t		update_lock;
 	u64			last_freq_update_time;
 	s64			freq_update_delay_ns;
 	unsigned int		next_freq;
 	unsigned int		cached_raw_freq;
 
+	/* max CPU capacity, which is equal for all CPUs in freq. domain */
+	unsigned long		max;
+
 	/* The next fields are only needed if fast switch cannot be used: */
 	struct			irq_work irq_work;
 	struct			kthread_work work;
@@ -53,8 +49,8 @@ struct sugov_cpu {
 	unsigned int		iowait_boost;
 	u64			last_update;
 
+	unsigned long		util;
 	unsigned long		bw_dl;
-	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -102,7 +98,9 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->next_freq == next_freq)
+	if (sg_policy->need_freq_update)
+		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	else if (sg_policy->next_freq == next_freq)
 		return false;
 
 	sg_policy->next_freq = next_freq;
@@ -111,33 +109,8 @@ static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 	return true;
 }
 
-static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
-			      unsigned int next_freq)
-{
-	struct cpufreq_policy *policy = sg_policy->policy;
-	int cpu;
-
-	if (!sugov_update_next_freq(sg_policy, time, next_freq))
-		return;
-
-	next_freq = cpufreq_driver_fast_switch(policy, next_freq);
-	if (!next_freq)
-		return;
-
-	policy->cur = next_freq;
-
-	if (trace_cpu_frequency_enabled()) {
-		for_each_cpu(cpu, policy->cpus)
-			trace_cpu_frequency(next_freq, cpu);
-	}
-}
-
-static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
-				  unsigned int next_freq)
+static void sugov_deferred_update(struct sugov_policy *sg_policy)
 {
-	if (!sugov_update_next_freq(sg_policy, time, next_freq))
-		return;
-
 	if (!sg_policy->work_in_progress) {
 		sg_policy->work_in_progress = true;
 		irq_work_queue(&sg_policy->irq_work);
@@ -173,132 +146,23 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
 
+	util = map_util_perf(util);
 	freq = map_util_freq(util, freq, max);
 
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
 
-	sg_policy->need_freq_update = false;
 	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-/*
- * This function computes an effective utilization for the given CPU, to be
- * used for frequency selection given the linear relation: f = u * f_max.
- *
- * The scheduler tracks the following metrics:
- *
- *   cpu_util_{cfs,rt,dl,irq}()
- *   cpu_bw_dl()
- *
- * Where the cfs,rt and dl util numbers are tracked with the same metric and
- * synchronized windows and are thus directly comparable.
- *
- * The cfs,rt,dl utilization are the running times measured with rq->clock_task
- * which excludes things like IRQ and steal-time. These latter are then accrued
- * in the irq utilization.
- *
- * The DL bandwidth number otoh is not a measured metric but a value computed
- * based on the task model parameters and gives the minimal utilization
- * required to meet deadlines.
- */
-unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum schedutil_type type,
-				 struct task_struct *p)
-{
-	unsigned long dl_util, util, irq;
-	struct rq *rq = cpu_rq(cpu);
-
-	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
-	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
-		return max;
-	}
-
-	/*
-	 * Early check to see if IRQ/steal time saturates the CPU, can be
-	 * because of inaccuracies in how we track these -- see
-	 * update_irq_load_avg().
-	 */
-	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= max))
-		return max;
-
-	/*
-	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
-	 * CFS tasks and we use the same metric to track the effective
-	 * utilization (PELT windows are synchronized) we can directly add them
-	 * to obtain the CPU's actual utilization.
-	 *
-	 * CFS and RT utilization can be boosted or capped, depending on
-	 * utilization clamp constraints requested by currently RUNNABLE
-	 * tasks.
-	 * When there are no CFS RUNNABLE tasks, clamps are released and
-	 * frequency will be gracefully reduced with the utilization decay.
-	 */
-	util = util_cfs + cpu_util_rt(rq);
-	if (type == FREQUENCY_UTIL)
-		util = uclamp_rq_util_with(rq, util, p);
-
-	dl_util = cpu_util_dl(rq);
-
-	/*
-	 * For frequency selection we do not make cpu_util_dl() a permanent part
-	 * of this sum because we want to use cpu_bw_dl() later on, but we need
-	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
-	 * that we select f_max when there is no idle time.
-	 *
-	 * NOTE: numerical errors or stop class might cause us to not quite hit
-	 * saturation when we should -- something for later.
-	 */
-	if (util + dl_util >= max)
-		return max;
-
-	/*
-	 * OTOH, for energy computation we need the estimated running time, so
-	 * include util_dl and ignore dl_bw.
-	 */
-	if (type == ENERGY_UTIL)
-		util += dl_util;
-
-	/*
-	 * There is still idle time; further improve the number by using the
-	 * irq metric. Because IRQ/steal time is hidden from the task clock we
-	 * need to scale the task numbers:
-	 *
-	 *              max - irq
-	 *   U' = irq + --------- * U
-	 *                 max
-	 */
-	util = scale_irq_capacity(util, irq, max);
-	util += irq;
-
-	/*
-	 * Bandwidth required by DEADLINE must always be granted while, for
-	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
-	 * to gracefully reduce the frequency when no tasks show up for longer
-	 * periods of time.
-	 *
-	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
-	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
-	 * an interface. So, we only do the latter for now.
-	 */
-	if (type == FREQUENCY_UTIL)
-		util += cpu_bw_dl(rq);
-
-	return min(max, util);
-}
-
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util = cpu_util_cfs(rq);
-	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
 
-	sg_cpu->max = max;
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
-
-	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
+	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
+					  FREQUENCY_UTIL, NULL);
 }
 
 /**
@@ -375,8 +239,6 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * sugov_iowait_apply() - Apply the IO boost to a CPU.
  * @sg_cpu: the sugov data for the cpu to boost
  * @time: the update time from the caller
- * @util: the utilization to (eventually) boost
- * @max: the maximum value the utilization can be boosted to
  *
  * A CPU running a task which woken up after an IO operation can have its
  * utilization boosted to speed up the completion of those IO operations.
@@ -390,18 +252,18 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
-					unsigned long util, unsigned long max)
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 {
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long boost;
 
 	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
-		return util;
+		return;
 
 	/* Reset boost if the CPU appears to have been idle enough */
 	if (sugov_iowait_reset(sg_cpu, time, false))
-		return util;
+		return;
 
 	if (!sg_cpu->iowait_boost_pending) {
 		/*
@@ -410,18 +272,21 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		sg_cpu->iowait_boost >>= 1;
 		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
-			return util;
+			return;
 		}
 	}
 
 	sg_cpu->iowait_boost_pending = false;
 
 	/*
-	 * @util is already in capacity scale; convert iowait_boost
+	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
-	return max(boost, util);
+	boost = sg_cpu->iowait_boost * sg_policy->max;
+	boost >>= SCHED_CAPACITY_SHIFT;
+	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
+	if (sg_cpu->util < boost)
+		sg_cpu->util = boost;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -441,83 +306,126 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  * Make sugov_should_update_freq() ignore the rate limit when DL
  * has increased the utilization.
  */
-static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
+static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
-		sg_policy->limits_changed = true;
+		sg_cpu->sg_policy->limits_changed = true;
 }
 
-static void sugov_update_single(struct update_util_data *hook, u64 time,
-				unsigned int flags)
+static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+					      u64 time, unsigned int flags)
 {
-	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
-	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
-	unsigned long util, max;
-	unsigned int next_f;
-	bool busy;
-
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
-	ignore_dl_rate_limit(sg_cpu, sg_policy);
+	ignore_dl_rate_limit(sg_cpu);
 
-	if (!sugov_should_update_freq(sg_policy, time))
-		return;
+	if (!sugov_should_update_freq(sg_cpu->sg_policy, time))
+		return false;
+
+	sugov_get_util(sg_cpu);
+	sugov_iowait_apply(sg_cpu, time);
+
+	return true;
+}
 
-	/* Limits may have changed, don't skip frequency update */
-	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
+static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
+				     unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned int cached_freq = sg_policy->cached_raw_freq;
+	unsigned int next_f;
 
-	util = sugov_get_util(sg_cpu);
-	max = sg_cpu->max;
-	util = sugov_iowait_apply(sg_cpu, time, util, max);
-	next_f = get_next_freq(sg_policy, util, max);
+	if (!sugov_update_single_common(sg_cpu, time, flags))
+		return;
+
+	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
 	 */
-	if (busy && next_f < sg_policy->next_freq) {
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
-		/* Reset cached freq as next_freq has changed */
-		sg_policy->cached_raw_freq = 0;
+		/* Restore cached freq as next_freq has changed */
+		sg_policy->cached_raw_freq = cached_freq;
 	}
 
+	if (!sugov_update_next_freq(sg_policy, time, next_f))
+		return;
+
 	/*
 	 * This code runs under rq->lock for the target CPU, so it won't run
 	 * concurrently on two different CPUs for the same target and it is not
 	 * necessary to acquire the lock in the fast switch case.
 	 */
 	if (sg_policy->policy->fast_switch_enabled) {
-		sugov_fast_switch(sg_policy, time, next_f);
+		cpufreq_driver_fast_switch(sg_policy->policy, next_f);
 	} else {
 		raw_spin_lock(&sg_policy->update_lock);
-		sugov_deferred_update(sg_policy, time, next_f);
+		sugov_deferred_update(sg_policy);
 		raw_spin_unlock(&sg_policy->update_lock);
 	}
 }
 
+static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
+				     unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned long prev_util = sg_cpu->util;
+
+	/*
+	 * Fall back to the "frequency" path if frequency invariance is not
+	 * supported, because the direct mapping between the utilization and
+	 * the performance levels depends on the frequency invariance.
+	 */
+	if (!arch_scale_freq_invariant()) {
+		sugov_update_single_freq(hook, time, flags);
+		return;
+	}
+
+	if (!sugov_update_single_common(sg_cpu, time, flags))
+		return;
+
+	/*
+	 * Do not reduce the target performance level if the CPU has not been
+	 * idle recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
+	 */
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+		sg_cpu->util = prev_util;
+
+	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
+				   map_util_perf(sg_cpu->util),
+				   sg_policy->max);
+
+	sg_cpu->sg_policy->last_freq_update_time = time;
+}
+
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned long util = 0, max = 1;
+	unsigned long util = 0;
 	unsigned int j;
 
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
-		unsigned long j_util, j_max;
 
-		j_util = sugov_get_util(j_sg_cpu);
-		j_max = j_sg_cpu->max;
-		j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
+		sugov_get_util(j_sg_cpu);
+		sugov_iowait_apply(j_sg_cpu, time);
 
-		if (j_util * max > j_max * util) {
-			util = j_util;
-			max = j_max;
-		}
+		util = max(j_sg_cpu->util, util);
 	}
 
-	return get_next_freq(sg_policy, util, max);
+	return get_next_freq(sg_policy, util, sg_policy->max);
 }
 
 static void
@@ -532,17 +440,20 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
-	ignore_dl_rate_limit(sg_cpu, sg_policy);
+	ignore_dl_rate_limit(sg_cpu);
 
 	if (sugov_should_update_freq(sg_policy, time)) {
 		next_f = sugov_next_freq_shared(sg_cpu, time);
 
+		if (!sugov_update_next_freq(sg_policy, time, next_f))
+			goto unlock;
+
 		if (sg_policy->policy->fast_switch_enabled)
-			sugov_fast_switch(sg_policy, time, next_f);
+			cpufreq_driver_fast_switch(sg_policy->policy, next_f);
 		else
-			sugov_deferred_update(sg_policy, time, next_f);
+			sugov_deferred_update(sg_policy);
 	}
-
+unlock:
 	raw_spin_unlock(&sg_policy->update_lock);
 }
 
@@ -554,7 +465,7 @@ static void sugov_work(struct kthread_work *work)
 
 	/*
 	 * Hold sg_policy->update_lock shortly to handle the case where:
-	 * incase sg_policy->next_freq is read here, and then updated by
+	 * in case sg_policy->next_freq is read here, and then updated by
 	 * sugov_deferred_update() just before work_in_progress is set to false
 	 * here, we may miss queueing the new update.
 	 *
@@ -624,9 +535,17 @@ static struct attribute *sugov_attrs[] = {
 };
 ATTRIBUTE_GROUPS(sugov);
 
+static void sugov_tunables_free(struct kobject *kobj)
+{
+	struct gov_attr_set *attr_set = to_gov_attr_set(kobj);
+
+	kfree(to_sugov_tunables(attr_set));
+}
+
 static struct kobj_type sugov_tunables_ktype = {
 	.default_groups = sugov_groups,
 	.sysfs_ops = &governor_sysfs_ops,
+	.release = &sugov_tunables_free,
 };
 
 /********************** cpufreq governor interface *********************/
@@ -726,12 +645,10 @@ static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_polic
 	return tunables;
 }
 
-static void sugov_tunables_free(struct sugov_tunables *tunables)
+static void sugov_clear_global_tunables(void)
 {
 	if (!have_governor_per_policy())
 		global_tunables = NULL;
-
-	kfree(tunables);
 }
 
 static int sugov_init(struct cpufreq_policy *policy)
@@ -794,7 +711,7 @@ out:
 fail:
 	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
-	sugov_tunables_free(tunables);
+	sugov_clear_global_tunables();
 
 stop_kthread:
 	sugov_kthread_stop(sg_policy);
@@ -821,7 +738,7 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
 	policy->governor_data = NULL;
 	if (!count)
-		sugov_tunables_free(tunables);
+		sugov_clear_global_tunables();
 
 	mutex_unlock(&global_tunables_lock);
 
@@ -833,15 +750,18 @@ static void sugov_exit(struct cpufreq_policy *policy)
 static int sugov_start(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
-	unsigned int cpu;
+	void (*uu)(struct update_util_data *data, u64 time, unsigned int flags);
+	unsigned int cpu = cpumask_first(policy->cpus);
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
 	sg_policy->last_freq_update_time	= 0;
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
-	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
+	sg_policy->max				= arch_scale_cpu_capacity(cpu);
+
+	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
 
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
@@ -851,13 +771,17 @@ static int sugov_start(struct cpufreq_policy *policy)
 		sg_cpu->sg_policy		= sg_policy;
 	}
 
+	if (policy_is_shared(policy))
+		uu = sugov_update_shared;
+	else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
+		uu = sugov_update_single_perf;
+	else
+		uu = sugov_update_single_freq;
+
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
-		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-					     policy_is_shared(policy) ?
-							sugov_update_shared :
-							sugov_update_single);
+		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu);
 	}
 	return 0;
 }
@@ -894,7 +818,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
-	.dynamic_switching	= true,
+	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
 	.init			= sugov_init,
 	.exit			= sugov_exit,
 	.start			= sugov_start,
@@ -909,23 +833,12 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
-static int __init sugov_register(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-core_initcall(sugov_register);
+cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
-extern bool sched_energy_update;
-extern struct mutex sched_energy_mutex;
-
 static void rebuild_sd_workfn(struct work_struct *work)
 {
-	mutex_lock(&sched_energy_mutex);
-	sched_energy_update = true;
-	rebuild_sched_domains();
-	sched_energy_update = false;
-	mutex_unlock(&sched_energy_mutex);
+	rebuild_sched_domains_energy();
 }
 static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);