[PATCH] drm/radeon: Override fpfn for all VRAM placements in radeon_evict_flags

[Julien Isorce]

Hi Michel,

Great ! Would you mind to just add a note to mention that the infinite loop
actually happens in ttm_bo_mem_force_space ? Thx!

Cheers
Julien

On 27 March 2017 at 07:36, Christian König <deathsimple at vodafone.de> wrote:

> Am 27.03.2017 um 02:58 schrieb Michel Dänzer:
>
>> From: Michel Dänzer <michel.daenzer at amd.com>
>>
>> We were accidentally only overriding the first VRAM placement. For BOs
>> with the RADEON_GEM_NO_CPU_ACCESS flag set,
>> radeon_ttm_placement_from_domain creates a second VRAM placment with
>> fpfn == 0. If VRAM is almost full, the first VRAM placement with
>> fpfn > 0 may not work, but the second one with fpfn == 0 always will
>> (the BO's current location trivially satisfies it). Because "moving"
>> the BO to its current location puts it back on the LRU list, this
>> results in an infinite loop.
>>
>> Fixes: 2a85aedd117c ("drm/radeon: Try evicting from CPU accessible to
>>                        inaccessible VRAM first")
>> Reported-by: Zachary Michaels <zmichaels at oblong.com>
>> Reported-and-Tested-by: Julien Isorce <jisorce at oblong.com>
>> Signed-off-by: Michel Dänzer <michel.daenzer at amd.com>
>>
>
> Reviewed-by: Christian König <christian.koenig at amd.com>
>
> ---
>>   drivers/gpu/drm/radeon/radeon_ttm.c | 4 ++--
>>   1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c
>> b/drivers/gpu/drm/radeon/radeon_ttm.c
>> index 5c7cf644ba1d..37d68cd1f272 100644
>> --- a/drivers/gpu/drm/radeon/radeon_ttm.c
>> +++ b/drivers/gpu/drm/radeon/radeon_ttm.c
>> @@ -213,8 +213,8 @@ static void radeon_evict_flags(struct
>> ttm_buffer_object *bo,
>>                         rbo->placement.num_busy_placement = 0;
>>                         for (i = 0; i < rbo->placement.num_placement;
>> i++) {
>>                                 if (rbo->placements[i].flags &
>> TTM_PL_FLAG_VRAM) {
>> -                                       if (rbo->placements[0].fpfn <
>> fpfn)
>> -                                               rbo->placements[0].fpfn =
>> fpfn;
>> +                                       if (rbo->placements[i].fpfn <
>> fpfn)
>> +                                               rbo->placements[i].fpfn =
>> fpfn;
>>                                 } else {
>>                                         rbo->placement.busy_placement =
>>                                                 &rbo->placements[i];
>>
>
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20170327/b08295af/attachment.html>