[PATCH 2/3] drm/amdgpu: Make noretry the default on Aldebaran

[Felix Kuehling]

This depends on two previous patches:

2e464a7fb883 drm/amdgpu: Enable retry faults unconditionally on Aldebaran
628c8d3a1602 drm/amdgpu: Retry fault handling based on per-process XNACK
mode

Regards,
  Felix

Am 2021-02-25 um 1:56 p.m. schrieb Alex Deucher:
> From: Felix Kuehling <Felix.Kuehling at amd.com>
>
> This is needed for best machine learning performance. XNACK can still
> be enabled per-process if needed.
>
> Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
> Reviewed-by: Philip Yang <Philip.Yang at amd.com>
> Tested-by: Alex Sierra <alex.sierra at amd.com>
> Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 1 +
>  1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 6d9c660da27a..8a64f5e49cb2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -508,6 +508,7 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
>  	switch (adev->asic_type) {
>  	case CHIP_VEGA10:
>  	case CHIP_VEGA20:
> +	case CHIP_ALDEBARAN:
>  		/*
>  		 * noretry = 0 will cause kfd page fault tests fail
>  		 * for some ASICs, so set default to 1 for these ASICs.