Status of the following patch (clocksource sched_clock) ?
Russell King - ARM Linux
linux at arm.linux.org.uk
Mon Dec 19 16:04:38 EST 2011
On Mon, Dec 19, 2011 at 05:29:49PM +0000, Karicheri, Muralidharan wrote:
> Russell,
>
> Thanks for responding.
>
> >>
> >> > Could someone tell me what is the status of this patch? I want to try
> >> > it on my target platform which is a davinci variant.
> >>
> >> Dead.
> >>
> >> Just make sure you use the sched_clock infrastructure already provided
> >> on ARM and provided you give it the correct information - and set it up
> >> early enough (in init_early) you will not have any sched_clock() wraps.
> >> This is because a timer will be set to automatically update things
> >> before any wrap occurs.
>
> Good to know that there is already support available to avoid
> clocksource wraparound. Could you point me to the code in kernel
> tree where this infrastructure is located and some sample code
> that implements it?
Let's get one thing straight - are you talking about clocksource
wrap-around or sched_clock wrap-around?
I interpreted you as referring to sched_clock wrap-around.
More information about the linux-arm-kernel
mailing list