[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3344ad77-62db-830f-94db-f4bdd7257478@linaro.org>
Date: Wed, 11 Jan 2017 22:33:56 +0800
From: Alex Shi <alex.shi@...aro.org>
To: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Cc: Daniel Lezcano <daniel.lezcano@...aro.org>,
"Rafael J . Wysocki" <rafael.j.wysocki@...el.com>,
vincent.guittot@...aro.org,
open list <linux-kernel@...r.kernel.org>,
linux-pm@...r.kernel.org, Ulf Hansson <ulf.hansson@...aro.org>
Subject: Re: [PATCH 2/3] cpu: expose pm_qos_resume_latency for each cpu
>> > #include "base.h"
>> >
>> > @@ -376,6 +377,9 @@ int register_cpu(struct cpu *cpu, int num)
>> >
>> > per_cpu(cpu_sys_devices, num) = &cpu->dev;
>> > register_cpu_under_node(num, cpu_to_node(num));
>> > +#ifdef CONFIG_CPU_IDLE_GOV_MENU
>> > + dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
>> > +#endif
> No way to do this without the #ifdef? That's really not recommended for
> .c code :(
>
Hi Greg,
Thanks for comments!
The function dev_pm_qos_expose_latency_limit() is null if no CONFIG_PM.
So when CONFIG_PM enabled, may we could consider the cpu idle is also
wanted. In this assumption the #ifdef could be removed. If user want to
use this feature, she/he should understand the feature only work on menu
gov only currently. So consider this, I guess we could remove this
#ifdef. :)
Any different concerns on this?
Regards
Alex
BTW,
Although I did try this patch on other platform, but it clearly other
multi core system, like x86 could also get the same benefit.
Powered by blists - more mailing lists