From d6614c4e2c49df3cc32a77c3b3a90fff1b4df597 Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Wed, 25 Jan 2017 17:07:19 -0800 Subject: [PATCH] cpufreq: sched: WALT: don't apply capacity margin twice With WALT all the scheduler classes' load are accounted in scr->cfs and update_cpu_capacity_request() adds capacity margin. At present, at tick path, scheduler also adds capacity margin. Therefore the margin applied twice. Fix such error by using margin applied cpu utilization only for checking whether frequency increase is needed. Change-Id: Id7d8cc73b2e4eec70b274ca66e09bb0b16bf6f09 Signed-off-by: Joonwoo Park (trivial rebase conflict) Signed-off-by: Chris Redpath --- kernel/sched/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4f97de8e0b18..0b14b4634b8c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2999,13 +2999,13 @@ static void sched_freq_tick_walt(int cpu) return sched_freq_tick_pelt(cpu); /* - * Add a margin to the WALT utilization. + * Add a margin to the WALT utilization to check if we will need to + * increase frequency. * NOTE: WALT tracks a single CPU signal for all the scheduling * classes, thus this margin is going to be added to the DL class as * well, which is something we do not do in sched_freq_tick_pelt case. */ - cpu_utilization = add_capacity_margin(cpu_utilization); - if (cpu_utilization <= capacity_curr) + if (add_capacity_margin(cpu_utilization) <= capacity_curr) return; /*