[PATCH 05/11] cpufreq/schedutil: use dl utilization tracking

[Vincent Guittot]

Now that we have both the dl class bandwidth requirement and the dl class
utilization, we can detect when CPU is fully used so we should run at max.
Otherwise, we keep using the dl bandwidth requirement to define the
utilization of the CPU

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/cpufreq_schedutil.c | 23 +++++++++++++++++------
 kernel/sched/sched.h             |  7 ++++++-
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 9c5e92e..edfbfc1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -56,6 +56,7 @@ struct sugov_cpu {
 	/* 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;
 
@@ -187,6 +188,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	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);
 }
 
@@ -198,20 +200,29 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	if (rq->rt.rt_nr_running)
 		return sg_cpu->max;
 
-	util = sg_cpu->util_dl;
-	util += sg_cpu->util_cfs;
+	util = sg_cpu->util_cfs;
 	util += sg_cpu->util_rt;
 
+	if ((util + sg_cpu->util_dl) >= sg_cpu->max)
+		return sg_cpu->max;
+
 	/*
-	 * Utilization required by DEADLINE must always be granted while, for
-	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
-	 * gracefully reduce the frequency when no tasks show up for longer
+	 * 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 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.
 	 */
+
+	/* Add DL bandwidth requirement */
+	util += sg_cpu->bw_dl;
+
 	return min(sg_cpu->max, util);
 }
 
@@ -367,7 +378,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
-	if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_policy->need_freq_update = true;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7d7d4f4..ef5d6aa 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2192,11 +2192,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
 }
 
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_dl.util_avg);
+}
+
 static inline unsigned long cpu_util_cfs(struct rq *rq)
 {
 	unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
-- 
2.7.4