3 files changed, 209 insertions, 86 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d18804491d9f..966556ebdbb3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5280,6 +5280,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
+	idle->flags |= PF_IDLE;
 
 	kasan_unpoison_task_stack(idle);
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 69e06898997d..fd4659313640 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,11 +12,14 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/cpufreq.h>
+#include <linux/kthread.h>
 #include <linux/slab.h>
 #include <trace/events/power.h>
 
 #include "sched.h"
 
+#define SUGOV_KTHREAD_PRIORITY	50
+
 struct sugov_tunables {
 	struct gov_attr_set attr_set;
 	unsigned int rate_limit_us;
@@ -35,8 +38,10 @@ struct sugov_policy {
 
 	/* The next fields are only needed if fast switch cannot be used. */
 	struct irq_work irq_work;
-	struct work_struct work;
+	struct kthread_work work;
 	struct mutex work_lock;
+	struct kthread_worker worker;
+	struct task_struct *thread;
 	bool work_in_progress;
 
 	bool need_freq_update;
@@ -291,7 +296,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
 	raw_spin_unlock(&sg_policy->update_lock);
 }
 
-static void sugov_work(struct work_struct *work)
+static void sugov_work(struct kthread_work *work)
 {
 	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
 
@@ -308,7 +313,21 @@ static void sugov_irq_work(struct irq_work *irq_work)
 	struct sugov_policy *sg_policy;
 
 	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
-	schedule_work_on(smp_processor_id(), &sg_policy->work);
+
+	/*
+	 * For RT and deadline tasks, the schedutil governor shoots the
+	 * frequency to maximum. Special care must be taken to ensure that this
+	 * kthread doesn't result in the same behavior.
+	 *
+	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
+	 * updated only at the end of the sugov_work() function and before that
+	 * the schedutil governor rejects all other frequency scaling requests.
+	 *
+	 * There is a very rare case though, where the RT thread yields right
+	 * after the work_in_progress flag is cleared. The effects of that are
+	 * neglected for now.
+	 */
+	kthread_queue_work(&sg_policy->worker, &sg_policy->work);
 }
 
 /************************** sysfs interface ************************/
@@ -371,19 +390,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
 		return NULL;
 
 	sg_policy->policy = policy;
-	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
-	INIT_WORK(&sg_policy->work, sugov_work);
-	mutex_init(&sg_policy->work_lock);
 	raw_spin_lock_init(&sg_policy->update_lock);
 	return sg_policy;
 }
 
 static void sugov_policy_free(struct sugov_policy *sg_policy)
 {
-	mutex_destroy(&sg_policy->work_lock);
 	kfree(sg_policy);
 }
 
+static int sugov_kthread_create(struct sugov_policy *sg_policy)
+{
+	struct task_struct *thread;
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+	struct cpufreq_policy *policy = sg_policy->policy;
+	int ret;
+
+	/* kthread only required for slow path */
+	if (policy->fast_switch_enabled)
+		return 0;
+
+	kthread_init_work(&sg_policy->work, sugov_work);
+	kthread_init_worker(&sg_policy->worker);
+	thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
+				"sugov:%d",
+				cpumask_first(policy->related_cpus));
+	if (IS_ERR(thread)) {
+		pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
+		return PTR_ERR(thread);
+	}
+
+	ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, &param);
+	if (ret) {
+		kthread_stop(thread);
+		pr_warn("%s: failed to set SCHED_FIFO\n", __func__);
+		return ret;
+	}
+
+	sg_policy->thread = thread;
+	kthread_bind_mask(thread, policy->related_cpus);
+	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
+	mutex_init(&sg_policy->work_lock);
+
+	wake_up_process(thread);
+
+	return 0;
+}
+
+static void sugov_kthread_stop(struct sugov_policy *sg_policy)
+{
+	/* kthread only required for slow path */
+	if (sg_policy->policy->fast_switch_enabled)
+		return;
+
+	kthread_flush_worker(&sg_policy->worker);
+	kthread_stop(sg_policy->thread);
+	mutex_destroy(&sg_policy->work_lock);
+}
+
 static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
 {
 	struct sugov_tunables *tunables;
@@ -416,16 +480,24 @@ static int sugov_init(struct cpufreq_policy *policy)
 	if (policy->governor_data)
 		return -EBUSY;
 
+	cpufreq_enable_fast_switch(policy);
+
 	sg_policy = sugov_policy_alloc(policy);
-	if (!sg_policy)
-		return -ENOMEM;
+	if (!sg_policy) {
+		ret = -ENOMEM;
+		goto disable_fast_switch;
+	}
+
+	ret = sugov_kthread_create(sg_policy);
+	if (ret)
+		goto free_sg_policy;
 
 	mutex_lock(&global_tunables_lock);
 
 	if (global_tunables) {
 		if (WARN_ON(have_governor_per_policy())) {
 			ret = -EINVAL;
-			goto free_sg_policy;
+			goto stop_kthread;
 		}
 		policy->governor_data = sg_policy;
 		sg_policy->tunables = global_tunables;
@@ -437,7 +509,7 @@ static int sugov_init(struct cpufreq_policy *policy)
 	tunables = sugov_tunables_alloc(sg_policy);
 	if (!tunables) {
 		ret = -ENOMEM;
-		goto free_sg_policy;
+		goto stop_kthread;
 	}
 
 	tunables->rate_limit_us = LATENCY_MULTIPLIER;
@@ -454,20 +526,25 @@ static int sugov_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto fail;
 
- out:
+out:
 	mutex_unlock(&global_tunables_lock);
-
-	cpufreq_enable_fast_switch(policy);
 	return 0;
 
- fail:
+fail:
 	policy->governor_data = NULL;
 	sugov_tunables_free(tunables);
 
- free_sg_policy:
+stop_kthread:
+	sugov_kthread_stop(sg_policy);
+
+free_sg_policy:
 	mutex_unlock(&global_tunables_lock);
 
 	sugov_policy_free(sg_policy);
+
+disable_fast_switch:
+	cpufreq_disable_fast_switch(policy);
+
 	pr_err("initialization failed (error %d)\n", ret);
 	return ret;
 }
@@ -478,8 +555,6 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	struct sugov_tunables *tunables = sg_policy->tunables;
 	unsigned int count;
 
-	cpufreq_disable_fast_switch(policy);
-
 	mutex_lock(&global_tunables_lock);
 
 	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
@@ -489,7 +564,9 @@ static void sugov_exit(struct cpufreq_policy *policy)
 
 	mutex_unlock(&global_tunables_lock);
 
+	sugov_kthread_stop(sg_policy);
 	sugov_policy_free(sg_policy);
+	cpufreq_disable_fast_switch(policy);
 }
 
 static int sugov_start(struct cpufreq_policy *policy)
@@ -535,8 +612,10 @@ static void sugov_stop(struct cpufreq_policy *policy)
 
 	synchronize_sched();
 
-	irq_work_sync(&sg_policy->irq_work);
-	cancel_work_sync(&sg_policy->work);
+	if (!policy->fast_switch_enabled) {
+		irq_work_sync(&sg_policy->irq_work);
+		kthread_cancel_work_sync(&sg_policy->work);
+	}
 }
 
 static void sugov_limits(struct cpufreq_policy *policy)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 1d8718d5300d..6a4bae0a649d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -164,11 +164,14 @@ static void cpuidle_idle_call(void)
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
 	 */
-	if (idle_should_freeze()) {
-		entered_state = cpuidle_enter_freeze(drv, dev);
-		if (entered_state > 0) {
-			local_irq_enable();
-			goto exit_idle;
+
+	if (idle_should_freeze() || dev->use_deepest_state) {
+		if (idle_should_freeze()) {
+			entered_state = cpuidle_enter_freeze(drv, dev);
+			if (entered_state > 0) {
+				local_irq_enable();
+				goto exit_idle;
+			}
 		}
 
 		next_state = cpuidle_find_deepest_state(drv, dev);
@@ -202,76 +205,65 @@ exit_idle:
  *
  * Called with polling cleared.
  */
-static void cpu_idle_loop(void)
+static void do_idle(void)
 {
-	int cpu = smp_processor_id();
-
-	while (1) {
-		/*
-		 * If the arch has a polling bit, we maintain an invariant:
-		 *
-		 * Our polling bit is clear if we're not scheduled (i.e. if
-		 * rq->curr != rq->idle).  This means that, if rq->idle has
-		 * the polling bit set, then setting need_resched is
-		 * guaranteed to cause the cpu to reschedule.
-		 */
-
-		__current_set_polling();
-		quiet_vmstat();
-		tick_nohz_idle_enter();
+	/*
+	 * If the arch has a polling bit, we maintain an invariant:
+	 *
+	 * Our polling bit is clear if we're not scheduled (i.e. if rq->curr !=
+	 * rq->idle). This means that, if rq->idle has the polling bit set,
+	 * then setting need_resched is guaranteed to cause the CPU to
+	 * reschedule.
+	 */
 
-		while (!need_resched()) {
-			check_pgt_cache();
-			rmb();
+	__current_set_polling();
+	tick_nohz_idle_enter();
 
-			if (cpu_is_offline(cpu)) {
-				cpuhp_report_idle_dead();
-				arch_cpu_idle_dead();
-			}
+	while (!need_resched()) {
+		check_pgt_cache();
+		rmb();
 
-			local_irq_disable();
-			arch_cpu_idle_enter();
-
-			/*
-			 * In poll mode we reenable interrupts and spin.
-			 *
-			 * Also if we detected in the wakeup from idle
-			 * path that the tick broadcast device expired
-			 * for us, we don't want to go deep idle as we
-			 * know that the IPI is going to arrive right
-			 * away
-			 */
-			if (cpu_idle_force_poll || tick_check_broadcast_expired())
-				cpu_idle_poll();
-			else
-				cpuidle_idle_call();
-
-			arch_cpu_idle_exit();
+		if (cpu_is_offline(smp_processor_id())) {
+			cpuhp_report_idle_dead();
+			arch_cpu_idle_dead();
 		}
 
-		/*
-		 * Since we fell out of the loop above, we know
-		 * TIF_NEED_RESCHED must be set, propagate it into
-		 * PREEMPT_NEED_RESCHED.
-		 *
-		 * This is required because for polling idle loops we will
-		 * not have had an IPI to fold the state for us.
-		 */
-		preempt_set_need_resched();
-		tick_nohz_idle_exit();
-		__current_clr_polling();
+		local_irq_disable();
+		arch_cpu_idle_enter();
 
 		/*
-		 * We promise to call sched_ttwu_pending and reschedule
-		 * if need_resched is set while polling is set.  That
-		 * means that clearing polling needs to be visible
-		 * before doing these things.
+		 * In poll mode we reenable interrupts and spin. Also if we
+		 * detected in the wakeup from idle path that the tick
+		 * broadcast device expired for us, we don't want to go deep
+		 * idle as we know that the IPI is going to arrive right away.
 		 */
-		smp_mb__after_atomic();
-
-		sched_ttwu_pending();
-		schedule_preempt_disabled();
+		if (cpu_idle_force_poll || tick_check_broadcast_expired())
+			cpu_idle_poll();
+		else
+			cpuidle_idle_call();
+		arch_cpu_idle_exit();
 	}
+
+	/*
+	 * Since we fell out of the loop above, we know TIF_NEED_RESCHED must
+	 * be set, propagate it into PREEMPT_NEED_RESCHED.
+	 *
+	 * This is required because for polling idle loops we will not have had
+	 * an IPI to fold the state for us.
+	 */
+	preempt_set_need_resched();
+	tick_nohz_idle_exit();
+	__current_clr_polling();
+
+	/*
+	 * We promise to call sched_ttwu_pending() and reschedule if
+	 * need_resched() is set while polling is set. That means that clearing
+	 * polling needs to be visible before doing these things.
+	 */
+	smp_mb__after_atomic();
+
+	sched_ttwu_pending();
+	schedule_preempt_disabled();
 }
 
 bool cpu_in_idle(unsigned long pc)
@@ -280,6 +272,56 @@ bool cpu_in_idle(unsigned long pc)
 		pc < (unsigned long)__cpuidle_text_end;
 }
 
+struct idle_timer {
+	struct hrtimer timer;
+	int done;
+};
+
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	struct idle_timer *it = container_of(timer, struct idle_timer, timer);
+
+	WRITE_ONCE(it->done, 1);
+	set_tsk_need_resched(current);
+
+	return HRTIMER_NORESTART;
+}
+
+void play_idle(unsigned long duration_ms)
+{
+	struct idle_timer it;
+
+	/*
+	 * Only FIFO tasks can disable the tick since they don't need the forced
+	 * preemption.
+	 */
+	WARN_ON_ONCE(current->policy != SCHED_FIFO);
+	WARN_ON_ONCE(current->nr_cpus_allowed != 1);
+	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
+	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
+	WARN_ON_ONCE(!duration_ms);
+
+	rcu_sleep_check();
+	preempt_disable();
+	current->flags |= PF_IDLE;
+	cpuidle_use_deepest_state(true);
+
+	it.done = 0;
+	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	it.timer.function = idle_inject_timer_fn;
+	hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED);
+
+	while (!READ_ONCE(it.done))
+		do_idle();
+
+	cpuidle_use_deepest_state(false);
+	current->flags &= ~PF_IDLE;
+
+	preempt_fold_need_resched();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(play_idle);
+
 void cpu_startup_entry(enum cpuhp_state state)
 {
 	/*
@@ -299,5 +341,6 @@ void cpu_startup_entry(enum cpuhp_state state)
 #endif
 	arch_cpu_idle_prepare();
 	cpuhp_online_idle(state);
-	cpu_idle_loop();
+	while (1)
+		do_idle();
 }