cpufreq/schedutil: Rewrite CPUFREQ_RT support

Instead of trying to duplicate scheduler state to track if an RT task
is running, directly use the scheduler runqueue state for it.

This vastly simplifies things and fixes a number of bugs related to
sugov and the scheduler getting out of sync wrt this state.

As a consequence we not also update the remove cfs/dl state when
iterating the shared mask.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched/cpufreq.h

@@ -8,8 +8,7 @@
  * Interface between cpufreq drivers and the scheduler:
  */
 
-#define SCHED_CPUFREQ_RT	(1U << 0)
-#define SCHED_CPUFREQ_IOWAIT	(1U << 1)
+#define SCHED_CPUFREQ_IOWAIT	(1U << 0)
 
 #ifdef CONFIG_CPU_FREQ
 struct update_util_data {

kernel/sched/cpufreq_schedutil.c

@@ -57,7 +57,6 @@ struct sugov_cpu {
 	unsigned long		util_cfs;
 	unsigned long		util_dl;
 	unsigned long		max;
-	unsigned int		flags;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -183,17 +182,28 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
+	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util;
+
+	if (rq->rt.rt_nr_running) {
+		util = sg_cpu->max;
+	} else {
+		util = sg_cpu->util_dl;
+		if (rq->cfs.h_nr_running)
+			util += sg_cpu->util_cfs;
+	}
+
 	/*
 	 * Ideally we would like to set util_dl as min/guaranteed freq and
 	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
-	return min(sg_cpu->util_cfs + sg_cpu->util_dl, sg_cpu->max);
+	return min(util, sg_cpu->max);
 }
 
-static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time)
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, unsigned int flags)
 {
-	if (sg_cpu->flags & SCHED_CPUFREQ_IOWAIT) {
+	if (flags & SCHED_CPUFREQ_IOWAIT) {
 		if (sg_cpu->iowait_boost_pending)
 			return;
 
@@ -262,12 +272,11 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
-	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned long util, max;
 	unsigned int next_f;
 	bool busy;
 
-	sugov_set_iowait_boost(sg_cpu, time);
+	sugov_set_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	if (!sugov_should_update_freq(sg_policy, time))
@@ -275,25 +284,22 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	if (flags & SCHED_CPUFREQ_RT) {
-		next_f = policy->cpuinfo.max_freq;
-	} else {
-		sugov_get_util(sg_cpu);
-		max = sg_cpu->max;
-		util = sugov_aggregate_util(sg_cpu);
-		sugov_iowait_boost(sg_cpu, &util, &max);
-		next_f = get_next_freq(sg_policy, util, max);
-		/*
-		 * Do not reduce the frequency if the CPU has not been idle
-		 * recently, as the reduction is likely to be premature then.
-		 */
-		if (busy && next_f < sg_policy->next_freq) {
-			next_f = sg_policy->next_freq;
+	sugov_get_util(sg_cpu);
+	max = sg_cpu->max;
+	util = sugov_aggregate_util(sg_cpu);
+	sugov_iowait_boost(sg_cpu, &util, &max);
+	next_f = get_next_freq(sg_policy, util, max);
+	/*
+	 * Do not reduce the frequency if the CPU has not been idle
+	 * recently, as the reduction is likely to be premature then.
+	 */
+	if (busy && 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;
-		}
+		/* Reset cached freq as next_freq has changed */
+		sg_policy->cached_raw_freq = 0;
 	}
+
 	sugov_update_commit(sg_policy, time, next_f);
 }
 
@@ -309,6 +315,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		unsigned long j_util, j_max;
 		s64 delta_ns;
 
+		sugov_get_util(j_sg_cpu);
+
 		/*
 		 * If the CFS CPU utilization was last updated before the
 		 * previous frequency update and the time elapsed between the
@@ -322,21 +330,15 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		if (delta_ns > TICK_NSEC) {
 			j_sg_cpu->iowait_boost = 0;
 			j_sg_cpu->iowait_boost_pending = false;
-			j_sg_cpu->util_cfs = 0;
-			if (j_sg_cpu->util_dl == 0)
-				continue;
 		}
-		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT)
-			return policy->cpuinfo.max_freq;
 
 		j_max = j_sg_cpu->max;
 		j_util = sugov_aggregate_util(j_sg_cpu);
+		sugov_iowait_boost(j_sg_cpu, &j_util, &j_max);
 		if (j_util * max > j_max * util) {
 			util = j_util;
 			max = j_max;
 		}
-
-		sugov_iowait_boost(j_sg_cpu, &util, &max);
 	}
 
 	return get_next_freq(sg_policy, util, max);
@@ -351,18 +353,11 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 
 	raw_spin_lock(&sg_policy->update_lock);
 
-	sugov_get_util(sg_cpu);
-	sg_cpu->flags = flags;
-
-	sugov_set_iowait_boost(sg_cpu, time);
+	sugov_set_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		if (flags & SCHED_CPUFREQ_RT)
-			next_f = sg_policy->policy->cpuinfo.max_freq;
-		else
-			next_f = sugov_next_freq_shared(sg_cpu, time);
-
+		next_f = sugov_next_freq_shared(sg_cpu, time);
 		sugov_update_commit(sg_policy, time, next_f);
 	}
 
@@ -673,7 +668,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->flags			= 0;
 		sg_cpu->iowait_boost_max	= policy->cpuinfo.max_freq;
 	}
 

kernel/sched/rt.c

@@ -957,9 +957,6 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
-	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
-	cpufreq_update_util(rq, SCHED_CPUFREQ_RT);
-
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
 
@@ -1001,6 +998,9 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
 
 	sub_nr_running(rq, rt_rq->rt_nr_running);
 	rt_rq->rt_queued = 0;
+
+	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_util(rq, 0);
 }
 
 static void
@@ -1017,6 +1017,9 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq)
 
 	add_nr_running(rq, rt_rq->rt_nr_running);
 	rt_rq->rt_queued = 1;
+
+	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_util(rq, 0);
 }
 
 #if defined CONFIG_SMP