@@ -85,6 +85,8 @@ void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
dl_rq->running_bw += dl_bw;
SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+ /* kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq_of_dl_rq(dl_rq), SCHED_CPUFREQ_DL);
}
static inline
@@ -97,6 +99,8 @@ void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
if (dl_rq->running_bw > old)
dl_rq->running_bw = 0;
+ /* kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq_of_dl_rq(dl_rq), SCHED_CPUFREQ_DL);
}
static inline
@@ -1135,9 +1139,6 @@ static void update_curr_dl(struct rq *rq)
return;
}
- /* kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
-
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -2057,14 +2057,14 @@ DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
* The way cpufreq is currently arranged requires it to evaluate the CPU
* performance state (frequency/voltage) on a regular basis to prevent it from
* being stuck in a completely inadequate performance level for too long.
- * That is not guaranteed to happen if the updates are only triggered from CFS,
- * though, because they may not be coming in if RT or deadline tasks are active
- * all the time (or there are RT and DL tasks only).
+ * That is not guaranteed to happen if the updates are only triggered from CFS
+ * and DL, though, because they may not be coming in if only RT tasks are
+ * active all the time (or there are RT tasks only).
*
- * As a workaround for that issue, this function is called by the RT and DL
- * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * As a workaround for that issue, this function is called periodically by the
+ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
* but that really is a band-aid. Going forward it should be replaced with
- * solutions targeted more specifically at RT and DL tasks.
+ * solutions targeted more specifically at RT tasks.
*/
static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
{
Since SCHED_DEADLINE doesn't track utilization signal (but reserves a fraction of CPU bandwidth to tasks admitted to the system), there is no point in evaluating frequency changes during each tick event. Move frequency selection triggering points to where running_bw changes. Co-authored-by: Claudio Scordino <claudio@evidence.eu.com> Signed-off-by: Juri Lelli <juri.lelli@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Luca Abeni <luca.abeni@santannapisa.it> --- Changes from RFCv0: - modify comment regarding periodic RT updates (Claudio) --- kernel/sched/deadline.c | 7 ++++--- kernel/sched/sched.h | 12 ++++++------ 2 files changed, 10 insertions(+), 9 deletions(-)