[PATCH] drm/amdgpu: fix when the cleaner shader is emitted

[Alex Deucher]

On Fri, Dec 6, 2024 at 9:35 AM Christian König
<ckoenig.leichtzumerken at gmail.com> wrote:
>
> Emitting the cleaner shader must come after the check if a VM switch is
> necessary or not.
>
> Otherwise we will emit the cleaner shader every time and not just when it is
> necessary because we switched between applications.
>
> This can otherwise crash on gang submit and probably decreases performance
> quite a bit.
>
> Signed-off-by: Christian König <christian.koenig at amd.com>

Acked-by: Alex Deucher <alexander.deucher at amd.com>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +++++-----
>  1 file changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 68dd4130b5ad..db913d533898 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -674,11 +674,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
>         pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping &&
>                 ring->funcs->emit_wreg;
>
> -       if (adev->gfx.enable_cleaner_shader &&
> -           ring->funcs->emit_cleaner_shader &&
> -           job->enforce_isolation)
> -               ring->funcs->emit_cleaner_shader(ring);
> -
>         if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync)
>                 return 0;
>
> @@ -690,6 +685,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
>         if (need_pipe_sync)
>                 amdgpu_ring_emit_pipeline_sync(ring);
>
> +       if (adev->gfx.enable_cleaner_shader &&
> +           ring->funcs->emit_cleaner_shader &&
> +           job->enforce_isolation)
> +               ring->funcs->emit_cleaner_shader(ring);
> +
>         if (vm_flush_needed) {
>                 trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr);
>                 amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
> --
> 2.34.1
>