Re: [PATCH v6 04/11] cpufreq/schedutil: use rt utilization tracking

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Jun 22, 2018 at 01:37:13PM +0200, Peter Zijlstra wrote:
> That is true.. So we could limit the scaling to the case where there is
> no idle time, something like:
> 
> 	util = sg_cpu->util_cfs;
> 
> 	cap_cfs = (1024 - (sg_cpu->util_rt + ...));
> 	if (util == cap_cfs)
> 		util = sg_cpu->max;
> 

OK, it appears this is more or less what the patches do. And I think
there's a small risk/hole with this where util ~= cap_cfs but very close
due to some unaccounted time.

FWIW, when looking, I saw no reason why sugov_get_util() and
sugov_aggregate_util() were in fact separate functions.

--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,11 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost_max;
 	u64			last_update;
 
-	/* The fields below are only needed when sharing a policy: */
-	unsigned long		util_cfs;
 	unsigned long		util_dl;
-	unsigned long		bw_dl;
-	unsigned long		util_rt;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -181,44 +177,38 @@ static unsigned int get_next_freq(struct
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util, max;
 
-	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->util_cfs = cpu_util_cfs(rq);
-	sg_cpu->util_dl  = cpu_util_dl(rq);
-	sg_cpu->bw_dl    = cpu_bw_dl(rq);
-	sg_cpu->util_rt  = cpu_util_rt(rq);
-}
-
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util;
+	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	sg_cpu->util_dl   = cpu_util_dl(rq);
 
 	if (rq->rt.rt_nr_running)
-		return sg_cpu->max;
+		return max;
 
-	util = sg_cpu->util_cfs;
-	util += sg_cpu->util_rt;
+	util  = cpu_util_cfs(rq);
+	util += cpu_util_rt(rq);
 
-	if ((util + sg_cpu->util_dl) >= sg_cpu->max)
-		return sg_cpu->max;
+	/*
+	 * If there is no idle time, we should run at max frequency.
+	 */
+	if ((util + cpu_util_dl(rq)) >= max)
+		return max;
 
 	/*
-	 * As there is still idle time on the CPU, we need to compute the
-	 * utilization level of the CPU.
 	 * 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 bw_dl
+	 * + util as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
 	 */
 
-	/* Add DL bandwidth requirement */
-	util += sg_cpu->bw_dl;
-
-	return min(sg_cpu->max, util);
+	return min(max, cpu_bw_dl(rq) + util);
 }
 
 /**
@@ -396,9 +386,8 @@ static void sugov_update_single(struct u
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	sugov_get_util(sg_cpu);
+	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	util = sugov_aggregate_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
@@ -437,9 +426,8 @@ static unsigned int sugov_next_freq_shar
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		sugov_get_util(j_sg_cpu);
+		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		j_util = sugov_aggregate_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
 
 		if (j_util * max > j_max * util) {