[PATCH 1/2] drm/amdgpu: skip to program GFXDEC registers for suspend abort

[Deucher, Alexander]

[AMD Official Use Only - General]

> -----Original Message-----
> From: Liang, Prike <Prike.Liang at amd.com>
> Sent: Thursday, February 1, 2024 3:58 AM
> To: amd-gfx at lists.freedesktop.org
> Cc: Deucher, Alexander <Alexander.Deucher at amd.com>; Sharma, Deepak
> <Deepak.Sharma at amd.com>; Liang, Prike <Prike.Liang at amd.com>
> Subject: [PATCH 1/2] drm/amdgpu: skip to program GFXDEC registers for
> suspend abort
>
> In the suspend abort cases, the gfx power rail doesn't turn off so some
> GFXDEC registers/CSB can't reset to default value and at this moment
> reinitialize GFXDEC/CSB will result in an unexpected error.
> So let skip those program sequence for the suspend abort case.
>
> Signed-off-by: Prike Liang <Prike.Liang at amd.com>

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


> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 2 ++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 ++
>  drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c   | 8 ++++++++
>  3 files changed, 12 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index c5f3859fd682..312dfaec7b4a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1079,6 +1079,8 @@ struct amdgpu_device {
>       bool                            in_s3;
>       bool                            in_s4;
>       bool                            in_s0ix;
> +     /* indicate amdgpu suspension status */
> +     bool                            suspend_complete;
>
>       enum pp_mp1_state               mp1_state;
>       struct amdgpu_doorbell_index doorbell_index; diff --git
> a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 475bd59c9ac2..59254144916c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2472,6 +2472,7 @@ static int amdgpu_pmops_suspend(struct device
> *dev)
>       struct drm_device *drm_dev = dev_get_drvdata(dev);
>       struct amdgpu_device *adev = drm_to_adev(drm_dev);
>
> +     adev->suspend_complete = false;
>       if (amdgpu_acpi_is_s0ix_active(adev))
>               adev->in_s0ix = true;
>       else if (amdgpu_acpi_is_s3_active(adev)) @@ -2486,6 +2487,7 @@
> static int amdgpu_pmops_suspend_noirq(struct device *dev)
>       struct drm_device *drm_dev = dev_get_drvdata(dev);
>       struct amdgpu_device *adev = drm_to_adev(drm_dev);
>
> +     adev->suspend_complete = true;
>       if (amdgpu_acpi_should_gpu_reset(adev))
>               return amdgpu_asic_reset(adev);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index 57808be6e3ec..169d45268ef6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct
> amdgpu_device *adev)
>
>       gfx_v9_0_cp_gfx_enable(adev, true);
>
> +     /* Now only limit the quirk on the APU gfx9 series and already
> +      * confirmed that the APU gfx10/gfx11 needn't such update.
> +      */
> +     if (adev->flags & AMD_IS_APU &&
> +                     adev->in_s3 && !adev->suspend_complete) {
> +             DRM_INFO(" Will skip the CSB packet resubmit\n");
> +             return 0;
> +     }
>       r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
>       if (r) {
>               DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
> --
> 2.34.1