Commit ff26b00b authored Oct 23, 2018 by Chris Redpath

ANDROID: sched/fair: initialise util_est values to 0 on fork



Since "sched/fair: Align PELT windows between cfs_rq and its se" the
upstream kernel has initialised the whole content of sched_avg to zero
on fork. When util_est was backported, we missed this and so ended up
with util_est values copied from the parent task.

Add the zero initialisation which is present upstream and ensure that
util_est values always start from a known point.

Fixes: 700f1172 ("BACKPORT: sched/fair: Add util_est on top of PELT")
Reported-by: Puja Gupta <pujag@quicinc.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Abhijeet Dharmapurikar <adharmap@codeaurora.org>
Cc: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Todd Kjos <tkjos@google.com>
Cc: Saravana Kannan <skannan@codeaurora.org>
Change-Id: I06995e4320d606a52761d0e773baf28fcd1e2680
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

parent a3ac63b1

kernel/sched/fair.c

+3 −6

Original line number	Diff line number	Diff line
		@@ -736,8 +736,10 @@ void init_entity_runnable_average(struct sched_entity *se)
		{
		struct sched_avg *sa = &se->avg;

		sa->last_update_time = 0;
		memset(sa, 0, sizeof(*sa));
		/*
		* util_avg is initialized in post_init_entity_util_avg.
		* util_est should start from zero.
		* sched_avg's period_contrib should be strictly less then 1024, so
		* we give it 1023 to make sure it is almost a period (1024us), and
		* will definitely be update (after enqueue).
		@@ -752,11 +754,6 @@ void init_entity_runnable_average(struct sched_entity *se)
		if (entity_is_task(se))
		sa->load_avg = scale_load_down(se->load.weight);
		sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
		/*
		* At this point, util_avg won't be used in select_task_rq_fair anyway
		*/
		sa->util_avg = 0;
		sa->util_sum = 0;
		/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
		}