Re: [Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-30 Thread Marek Olšák
I'm dropping the patch. It makes UE4 Elemental hang. We have a bigger CE issue than I thought. It could be a Mesa issue too. Marek On Fri, May 27, 2016 at 12:12 PM, Marek Olšák wrote: > On Fri, May 27, 2016 at 11:12 AM, Christian König > wrote: >> Am

Re: [Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-27 Thread Marek Olšák
On Fri, May 27, 2016 at 11:12 AM, Christian König wrote: > Am 27.05.2016 um 00:19 schrieb Marek Olšák: >> >> On Fri, May 27, 2016 at 12:13 AM, Alex Deucher >> wrote: >>> >>> On Thu, May 26, 2016 at 5:51 PM, Marek Olšák wrote:

Re: [Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-27 Thread Christian König
Am 27.05.2016 um 00:19 schrieb Marek Olšák: On Fri, May 27, 2016 at 12:13 AM, Alex Deucher wrote: On Thu, May 26, 2016 at 5:51 PM, Marek Olšák wrote: From: Marek Olšák SDMA submission somehow interacts with the skipping CE

Re: [Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-26 Thread Marek Olšák
On Fri, May 27, 2016 at 12:13 AM, Alex Deucher wrote: > On Thu, May 26, 2016 at 5:51 PM, Marek Olšák wrote: >> From: Marek Olšák >> >> SDMA submission somehow interacts with the skipping CE preamble logic. >> This is a workaround for

Re: [Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-26 Thread Alex Deucher
On Thu, May 26, 2016 at 5:51 PM, Marek Olšák wrote: > From: Marek Olšák > > SDMA submission somehow interacts with the skipping CE preamble logic. > This is a workaround for current kernels which have the bug. > > Sadly, I can't see what's wrong with the

[Mesa-dev] [PATCH 2/2] winsys/amdgpu: disable CE preamble until the kernel is fixed

2016-05-26 Thread Marek Olšák
From: Marek Olšák SDMA submission somehow interacts with the skipping CE preamble logic. This is a workaround for current kernels which have the bug. Sadly, I can't see what's wrong with the kernel driver. The CE preamble handling there looks good to me. Bugzilla: