[Mesa-dev] [PATCH] r600g: Include SH and SMX when invalidating read caches

[Marek Olšák]

FYI, I have applied the patch to my local branch and added a few more
fixes. I'll send it once I finish some other things I'm working on right
now.

Marek

On Sun, Jun 23, 2013 at 11:56 PM, Alex Deucher <alexdeucher at gmail.com> wrote:
> On Sun, Jun 23, 2013 at 2:24 PM, Marek Olšák <maraeo at gmail.com> wrote:
>> Hi Alex,
>>
>> rctx->framebuffer.state.nr_cbufs might not contain what you think it
>> does, because the framebuffer that needs flushing may have been
>> replaced by a new framebuffer and the cache flushing of the old
>> framebuffer usually takes place before the first draw to the new
>> framebuffer. To solve this, we can either set all CB bits, or move
>> setting CP_COHER_CNTL outside of r600_flush_emit.
>
> I think it should be ok to just set all the CB bits.  My only concern
> was whether there would be a problems with flushing unbound CBs.  I
> think it should be ok.  Martin, can you try the attached patch?
>
> Alex
>
>>
>> Marek
>>
>> On Sun, Jun 23, 2013 at 7:41 PM, Alex Deucher <alexdeucher at gmail.com> wrote:
>>> On Sat, Jun 22, 2013 at 11:53 AM, Martin Andersson <g02maran at gmail.com> wrote:
>>>> On Sat, Jun 22, 2013 at 12:22 PM, Marek Olšák <maraeo at gmail.com> wrote:
>>>>> Reviewed-by: Marek Olšák <maraeo at gmail.com>
>>>>>
>>>>> BTW, SMX is a write cache, to maybe it shouldn't be part of this patch.
>>>>
>>>> I made a little experiment where i ran
>>>> "ext_framebuffer_multisample-unaligned-blit 4 color downsample -auto"
>>>> 10000 times and found that without SMX the test failed 177 times and
>>>> with SMX it didn't fail at all. So I do think the SMX cache should be
>>>> invalidated somewhere.
>>>>
>>>> Before http://cgit.freedesktop.org/mesa/mesa/commit/?id=4539f8e20af286d1f521eb016c89c6d9af0b801c
>>>> it was under R600_CONTEXT_FLUSH_AND_INV, is that a better place?
>>>>
>>>> If that is the proper place for SMX should SH also be there, since it
>>>> was also there before the patch, or do you have any other suggestions?
>>>
>>> Does something like this help?  You might play with some variants of
>>> this patch.  This might break compute however as Tom had some problems
>>> with CB flushes on cayman class hw in the past.
>>>
>>> Alex
>>>
>>>
>>>>
>>>>> Marek
>>>>>
>>>>> On Sun, Jun 16, 2013 at 1:27 PM, Martin Andersson <g02maran at gmail.com> wrote:
>>>>>> Not including the SH and SMX caches when invalidating read caches causes
>>>>>> random failures on some piglit tests when VA is enabled.
>>>>>>
>>>>>> Since the failures are random, and there other problems also causing random
>>>>>> failures, it's hard to know exactly what tests were effected, but these
>>>>>> tests now consistently pass:
>>>>>>
>>>>>> fast_color_clear/all-colors
>>>>>> fast_color_clear/redundant-clear
>>>>>> spec/!OpenGL 1.1/draw-pixels samples={2,4,6,8}
>>>>>> spec/!OpenGL 1.1/drawbuffer-modes
>>>>>> ---
>>>>>>  src/gallium/drivers/r600/r600_hw_context.c | 2 ++
>>>>>>  1 file changed, 2 insertions(+)
>>>>>>
>>>>>> diff --git a/src/gallium/drivers/r600/r600_hw_context.c b/src/gallium/drivers/r600/r600_hw_context.c
>>>>>> index 944b666..df20e56 100644
>>>>>> --- a/src/gallium/drivers/r600/r600_hw_context.c
>>>>>> +++ b/src/gallium/drivers/r600/r600_hw_context.c
>>>>>> @@ -231,6 +231,8 @@ void r600_flush_emit(struct r600_context *rctx)
>>>>>>         if (rctx->flags & R600_CONTEXT_INVAL_READ_CACHES) {
>>>>>>                 cp_coher_cntl |= S_0085F0_VC_ACTION_ENA(1) |
>>>>>>                                 S_0085F0_TC_ACTION_ENA(1) |
>>>>>> +                               S_0085F0_SH_ACTION_ENA(1) |
>>>>>> +                               S_0085F0_SMX_ACTION_ENA(1) |
>>>>>>                                 S_0085F0_FULL_CACHE_ENA(1);
>>>>>>                 emit_flush = 1;
>>>>>>         }
>>>>>> --
>>>>>> 1.8.3
>>>>>>
>>>>>> _______________________________________________
>>>>>> mesa-dev mailing list
>>>>>> mesa-dev at lists.freedesktop.org
>>>>>> http://lists.freedesktop.org/mailman/listinfo/mesa-dev
>>>> _______________________________________________
>>>> mesa-dev mailing list
>>>> mesa-dev at lists.freedesktop.org
>>>> http://lists.freedesktop.org/mailman/listinfo/mesa-dev