cpufreq: schedutil: Use idle_calls counter of the remote CPU
authorJoel Fernandes <joelaf@google.com>
Thu, 21 Dec 2017 01:22:45 +0000 (02:22 +0100)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Tue, 2 Jan 2018 19:31:05 +0000 (20:31 +0100)
commit0c688c288f8e82fdb5f3e0d0f3b2b1f3498ad187
treecfb6dda7923c3f7fc61de8cc00f9b7303e66a1d5
parent9c5ee053a67eb374878b20eab7d16feb2a87a851
cpufreq: schedutil: Use idle_calls counter of the remote CPU

commit 466a2b42d67644447a1765276259a3ea5531ddff upstream.

Since the recent remote cpufreq callback work, its possible that a cpufreq
update is triggered from a remote CPU. For single policies however, the current
code uses the local CPU when trying to determine if the remote sg_cpu entered
idle or is busy. This is incorrect. To remedy this, compare with the nohz tick
idle_calls counter of the remote CPU.

Fixes: 674e75411fc2 (sched: cpufreq: Allow remote cpufreq callbacks)
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
include/linux/tick.h
kernel/sched/cpufreq_schedutil.c
kernel/time/tick-sched.c