@@ -958,9 +958,6 @@ 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_this_cpu(rq, SCHED_CPUFREQ_RT);
-
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -1326,6 +1323,9 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
enqueue_pushable_task(rq, p);
+
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1563,6 +1563,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
p = _pick_next_task_rt(rq);
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
@@ -2272,6 +2275,9 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
struct sched_rt_entity *rt_se = &p->rt;
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+
update_curr_rt(rq);
watchdog(rq, p);
@@ -2307,6 +2313,9 @@ static void set_curr_task_rt(struct rq *rq)
p->se.exec_start = rq_clock_task(rq);
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
}
Currently schedutil updates are triggered for the RT class using a single call place, which is part of the rt::update_curr_rt() used in: - dequeue_task_rt: but it does not make sense to set the schedutil's SCHED_CPUFREQ_RT in case the next task should not be an RT one - put_prev_task_rt: likewise, we set the SCHED_CPUFREQ_RT flag without knowing if required by the next task - pick_next_task_rt: likewise, the schedutil's SCHED_CPUFREQ_RT is set in case the prev task was RT, while we don't yet know if the next will be RT - task_tick_rt: that's the only really useful call, which can ramp up the frequency in case a RT task started its execution without a chance to order a frequency switch (e.g. because of the schedutil ratelimit) Apart from the last call in task_tick_rt, the others are at least useless. Thus, although being a simple solution, not all the call sites of that update_curr_rt() are interesting to trigger a frequency switch as well as some of the most interesting points are not covered by that call. For example, a task set to RT has to wait the next tick to get the frequency boost. This patch fixes these issue by placing explicitly the schedutils update calls in the only sensible places, which are: - when an RT task wakeups and it's enqueued in a CPU - when we actually pick a RT task for execution - at each tick time - when a task is set to be RT Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org --- kernel/sched/rt.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) -- 2.7.4