[Intel-gfx] freedesktop bug id: 100548, bisected to sched/clock commit

[Peter Zijlstra]

On Tue, Apr 18, 2017 at 05:53:56PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 18, 2017 at 02:10:07PM +0000, Lofstedt, Marta wrote:
> > Sorry Peter, I still see regression on the Core2 machine, with your patch.
> > 
> 
> Blergh, ok. I'll see if I can dig out an actual Core2 machine somewhere.
> I should have enough parts about.

Argh!

My Core2 seems to work as expected _without_ this patch (time is
continuous at the stable->unstable switch), but is broken (time jumps
backwards by almost .2s) with this patch -- because by the time ACPI
Processor marks TSC as busted, we haven't ran the clocksource watchdog
yet.


Just for my sanity, could you confirm "tsc=unstable" (which requires the
patch) actually works for you?

I'll go prod at things now that I have an actual Core2 running; although
sadly I don't see an obvious problem without this patch.