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

Peter Zijlstra peterz at infradead.org
Wed Apr 12 12:31:34 UTC 2017


On Wed, Apr 12, 2017 at 12:04:00PM +0000, Lofstedt, Marta wrote:
> Hi,
> 
> We have this "old" Lenovo Cantiga laptop(Intel Core 2 Duo L9400), hocked up to our i915 pre-merge CI system, that has started to give unstable results after commit:
> 
> commit 7b09cc5a9debc86c903c2eff8f8a1fdef773c649
> Author: Pavel Tatashin <pasha.tatashin at oracle.com>
> Date:   Wed Mar 22 16:24:17 2017 -0400
> 
>     sched/clock: Fix broken stable to unstable transfer
> 
> The issue is describe more in detail here:
> https://bugs.freedesktop.org/show_bug.cgi?id=100548

I don't click links.

> We have reverted above patch and then issue is no longer reproducible.
> Also, note that this issue has not been reproduced on any of our other machines,
> https://intel-gfx-ci.01.org/CI/
> 
> So, why is this only affecting the Core 2 Duo?

Core2 doesn't have a usable TSC and would revert to the slow path. I'll
have another look at that patch.



More information about the Intel-gfx mailing list