[PATCH v2] drm/amd: Don't reset dGPUs if the system is going to s2idle

[Alex Deucher]

On Tue, May 17, 2022 at 1:00 PM Mario Limonciello
<mario.limonciello at amd.com> wrote:
>
> An A+A configuration on ASUS ROG Strix G513QY proves that the ASIC
> reset for handling aborted suspend can't work with s2idle.
>
> This functionality was introduced in commit daf8de0874ab5b ("drm/amdgpu:
> always reset the asic in suspend (v2)").  A few other commits have
> gone on top of the ASIC reset, but this still doesn't work on the A+A
> configuration in s2idle.
>
> Avoid doing the reset on dGPUs specifically when using s2idle.
>
> Fixes: daf8de0874ab5b ("drm/amdgpu: always reset the asic in suspend (v2)")
> Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2008
> Signed-off-by: Mario Limonciello <mario.limonciello at amd.com>

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

> ---
> v1->v2:
>  * Add missing stub function for non CONFIG_ACPI case
>
>  drivers/gpu/drm/amd/amdgpu/amdgpu.h      |  2 ++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 14 ++++++++++++++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c  |  2 +-
>  3 files changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 3c20c2eadf4e..76df583663c7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1378,9 +1378,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
>
>  #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
>  bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
> +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev);
>  bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
>  #else
>  static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
> +static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; }
>  static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
>  #endif
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
> index 0e12315fa0cb..98ac53ee6bb5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
> @@ -1045,6 +1045,20 @@ bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev)
>                 (pm_suspend_target_state == PM_SUSPEND_MEM);
>  }
>
> +/**
> + * amdgpu_acpi_should_gpu_reset
> + *
> + * @adev: amdgpu_device_pointer
> + *
> + * returns true if should reset GPU, false if not
> + */
> +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
> +{
> +       if (adev->flags & AMD_IS_APU)
> +               return false;
> +       return pm_suspend_target_state != PM_SUSPEND_TO_IDLE;
> +}
> +
>  /**
>   * amdgpu_acpi_is_s0ix_active
>   *
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 16871baee784..a84766c13ac5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2315,7 +2315,7 @@ 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);
>
> -       if (!adev->in_s0ix)
> +       if (amdgpu_acpi_should_gpu_reset(adev))
>                 return amdgpu_asic_reset(adev);
>
>         return 0;
> --
> 2.25.1
>