cpufreq/schedutil: Use RT utilization tracking

Add both CFS and RT utilization when selecting an OPP for CFS tasks as RT
can preempt and steal CFS's running time.

RT util_avg is used to take into account the utilization of RT tasks
on the CPU when selecting OPP. If a RT task migrate, the RT utilization
will not migrate but will decay over time. On an overloaded CPU, CFS
utilization reflects the remaining utilization avialable on CPU. When RT
task migrates, the CFS utilization will increase when tasks will start to
use the newly available capacity. At the same pace, RT utilization will
decay and both variations will compensate each other to keep unchanged
overall utilization and will prevent any OPP drop.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-4-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c907fde01eaa65fcf784074466a17f8a64ab0203..da29b5a33adbd702ef5ec243c24bccd6e42349c1 100644 (file)
--- 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           util_rt;
        unsigned long           max;
 
        /* The field below is for single-CPU policies only: */
@@ -186,15 +187,21 @@ 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->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;
 
        if (rt_rq_is_runnable(&rq->rt))
                return sg_cpu->max;
 
+       util = sg_cpu->util_dl;
+       util += sg_cpu->util_cfs;
+       util += sg_cpu->util_rt;
+
        /*
         * Utilization required by DEADLINE must always be granted while, for
         * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
@@ -205,7 +212,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
         * 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->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+       return min(sg_cpu->max, util);
 }
 
 /**