[PATCH 4/6] drm/amdgpu: bypass RAS error reset in some conditions

[Yang, Stanley]

[AMD Official Use Only - General]

> -----Original Message-----
> From: Zhou1, Tao <Tao.Zhou1 at amd.com>
> Sent: Tuesday, October 17, 2023 8:46 PM
> To: amd-gfx at lists.freedesktop.org; Zhang, Hawking
> <Hawking.Zhang at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>; Li,
> Candice <Candice.Li at amd.com>; Chai, Thomas <YiPeng.Chai at amd.com>;
> Lazar, Lijo <Lijo.Lazar at amd.com>; Wang, Yang(Kevin)
> <KevinYang.Wang at amd.com>
> Cc: Zhou1, Tao <Tao.Zhou1 at amd.com>
> Subject: [PATCH 4/6] drm/amdgpu: bypass RAS error reset in some conditions
>
> PMFW is responsible for RAS error reset in some conditions, driver can skip the
> operation.
>
> v2: add check for ras->in_recovery, it's set earlier than amdgpu_in_reset.
>
> Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 20 ++++++++++++++++++--
>  1 file changed, 18 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 95c7ba889e2d..806c6d4deb63 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -1178,11 +1178,19 @@ int amdgpu_ras_reset_error_count(struct
> amdgpu_device *adev,
>               enum amdgpu_ras_block block)
>  {
>       struct amdgpu_ras_block_object *block_obj =
> amdgpu_ras_get_ras_block(adev, block, 0);
> +     struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
> +     const struct amdgpu_mca_smu_funcs *mca_funcs = adev-
> >mca.mca_funcs;
>
>       if (!block_obj || !block_obj->hw_ops)
>               return 0;
>
> -     if (!amdgpu_ras_is_supported(adev, block))
> +     /* skip ras error reset in gpu reset */
> +     if (amdgpu_in_reset(adev) && atomic_read(&ras->in_recovery) &&
> +         mca_funcs && mca_funcs->mca_set_debug_mode)

[Stanley]: The check condition amdgpu_in_reset(adev) && atomic_read(&ras->in_recovery) should be modify to (amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)),
Can we check ras->is_mca_debug_mode directly since patch#2 and patch#3 set it.

Regards,
Stanley
> +             return 0;
> +
> +     if (!amdgpu_ras_is_supported(adev, block) ||
> +         !amdgpu_ras_get_mca_debug_mode(adev))
>               return 0;
>
>       if (block_obj->hw_ops->reset_ras_error_count)
> @@ -1195,6 +1203,8 @@ int amdgpu_ras_reset_error_status(struct
> amdgpu_device *adev,
>               enum amdgpu_ras_block block)
>  {
>       struct amdgpu_ras_block_object *block_obj =
> amdgpu_ras_get_ras_block(adev, block, 0);
> +     struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
> +     const struct amdgpu_mca_smu_funcs *mca_funcs = adev-
> >mca.mca_funcs;
>
>       if (!block_obj || !block_obj->hw_ops) {
>               dev_dbg_once(adev->dev, "%s doesn't config RAS
> function\n", @@ -1202,7 +1212,13 @@ int
> amdgpu_ras_reset_error_status(struct amdgpu_device *adev,
>               return 0;
>       }
>
> -     if (!amdgpu_ras_is_supported(adev, block))
> +     /* skip ras error reset in gpu reset */
> +     if (amdgpu_in_reset(adev) && atomic_read(&ras->in_recovery) &&
> +         mca_funcs && mca_funcs->mca_set_debug_mode)
[Stanley]: Same as above.

> +             return 0;
> +
> +     if (!amdgpu_ras_is_supported(adev, block) ||
> +         !amdgpu_ras_get_mca_debug_mode(adev))
>               return 0;
>
>       if (block_obj->hw_ops->reset_ras_error_count)
> --
> 2.35.1