Fixing zero timeout handling for fence functions

Sumit Semwal sumit.semwal at linaro.org
Wed Oct 26 02:39:45 UTC 2016


Hi Christian,


On 25 October 2016 at 17:55, Christian König <deathsimple at vodafone.de> wrote:
> Hi Sumit,
>
> sending this once more with all the patches in once set, cause the last one
> turned out to be a bit chaotic because I send from the wrong branch.
>
> The following patch set fixes the handling in the fence and reservation object
> wait function when the timeout is zero.
>

Thanks for your patches!

Adding a few more reviewers.

Also, usually, I find it easier if the intro patch comes as (patch
0/X), since that lists all the patches of the patch series as well. If
you could do that from next time onwards, that'd be great!

> An AMD developer introduced this a while ago to work around some issues in TTM
> and our amdgpu driver, but essentially this effort was a bit flawed because
> even with a zero timeout enable_signalling() should be called.
>
> Otherwise someone busy waiting for the fence might never be signaled when you
> have hardware with faulty interrupts for example.
>
> Please review and/or comment,
> Christian.
>

Best regards,
Sumit.


More information about the dri-devel mailing list