sched/core: Use PELT for scale_rt_capacity()

The utilization of the CPU by RT, DL and IRQs are now tracked with
PELT so we can use these metrics instead of rt_avg to evaluate the remaining
capacity available for CFS class.

scale_rt_capacity() behavior has been changed and now returns the remaining
capacity available for CFS instead of a scaling factor because RT, DL and
IRQ provide now absolute utilization value.

The same formula as schedutil is used:

  IRQ util_avg + (1 - IRQ util_avg / max capacity ) * /Sum rq util_avg

but the implementation is different because it doesn't return the same value
and doesn't benefit of the same optimization.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.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
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-10-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f4de26982d80a00d1f40a08bff326d2b6b91c3c7..68b8a9f1c9ca0075b2088df9b9a44240a5325d2b 100644 (file)
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1180,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
        curr->se.exec_start = now;
        cgroup_account_cputime(curr, delta_exec);
 
-       sched_rt_avg_update(rq, delta_exec);
-
        if (dl_entity_is_special(dl_se))
                return;
 

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c2782b29c79f5298e15290bfd5431329208bb000..d265fa9756a2f5c39ad62001e99ba3fdd309aba9 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7551,39 +7551,39 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
-       u64 total, used, age_stamp, avg;
-       s64 delta;
-
-       /*
-        * Since we're reading these variables without serialization make sure
-        * we read them once before doing sanity checks on them.
-        */
-       age_stamp = READ_ONCE(rq->age_stamp);
-       avg = READ_ONCE(rq->rt_avg);
-       delta = __rq_clock_broken(rq) - age_stamp;
+       unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+       unsigned long used, free;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+       unsigned long irq;
+#endif
 
-       if (unlikely(delta < 0))
-               delta = 0;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+       irq = READ_ONCE(rq->avg_irq.util_avg);
 
-       total = sched_avg_period() + delta;
+       if (unlikely(irq >= max))
+               return 1;
+#endif
 
-       used = div_u64(avg, total);
+       used = READ_ONCE(rq->avg_rt.util_avg);
+       used += READ_ONCE(rq->avg_dl.util_avg);
 
-       if (likely(used < SCHED_CAPACITY_SCALE))
-               return SCHED_CAPACITY_SCALE - used;
+       if (unlikely(used >= max))
+               return 1;
 
-       return 1;
+       free = max - used;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+       free *= (max - irq);
+       free /= max;
+#endif
+       return free;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-       unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+       unsigned long capacity = scale_rt_capacity(cpu);
        struct sched_group *sdg = sd->groups;
 
-       cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-       capacity *= scale_rt_capacity(cpu);
-       capacity >>= SCHED_CAPACITY_SHIFT;
+       cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
        if (!capacity)
                capacity = 1;

diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index ead6d8b4a8b84fead75424af56597a67d03cceb5..35475c0c5419c4c16f98948a0d17dd6d8b100132 100644 (file)
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -237,7 +237,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
         */
        sa->load_avg = div_u64(load * sa->load_sum, divider);
        sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider);
-       sa->util_avg = sa->util_sum / divider;
+       WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
 /*

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0dc8ad1915e6927a1d5b18bb53a4a190ff7bc0fb..2df72abfa24a0c6225b60b4a6d1161f660e6d20d 100644 (file)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -973,8 +973,6 @@ static void update_curr_rt(struct rq *rq)
        curr->se.exec_start = now;
        cgroup_account_cputime(curr, delta_exec);
 
-       sched_rt_avg_update(rq, delta_exec);
-
        if (!rt_bandwidth_enabled())
                return;