[PATCH 05/10] drm/amdgpu: Add helper to initialize badpage info

[Alex Deucher]

On Mon, Sep 2, 2024 at 3:53 AM Lijo Lazar <lijo.lazar at amd.com> wrote:
>
> Add a separate function to read badpage data during initialization.
> Reading bad pages will need hardware access and cannot be done during
> reset. Hence in cases where device needs a full reset during
> init itself, attempting to read will cause a deadlock.
>
> Signed-off-by: Lijo Lazar <lijo.lazar at amd.com>

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

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    | 56 +++++++++++++++-------
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h    |  4 +-
>  3 files changed, 41 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index e28227869307..468c4f590183 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -2945,7 +2945,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
>          * Note: theoretically, this should be called before all vram allocations
>          * to protect retired page from abusing
>          */
> -       r = amdgpu_ras_recovery_init(adev);
> +       r = amdgpu_ras_recovery_init(adev, true);
>         if (r)
>                 goto init_failed;
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 2076f157cb6a..65c891b6b999 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -3146,7 +3146,42 @@ static int amdgpu_ras_page_retirement_thread(void *param)
>         return 0;
>  }
>
> -int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
> +int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
> +{
> +       struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
> +       int ret;
> +
> +       if (!con || amdgpu_sriov_vf(adev))
> +               return 0;
> +
> +       ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
> +
> +       if (ret)
> +               return ret;
> +
> +       /* HW not usable */
> +       if (amdgpu_ras_is_rma(adev))
> +               return -EHWPOISON;
> +
> +       if (con->eeprom_control.ras_num_recs) {
> +               ret = amdgpu_ras_load_bad_pages(adev);
> +               if (ret)
> +                       return ret;
> +
> +               amdgpu_dpm_send_hbm_bad_pages_num(
> +                       adev, con->eeprom_control.ras_num_recs);
> +
> +               if (con->update_channel_flag == true) {
> +                       amdgpu_dpm_send_hbm_bad_channel_flag(
> +                               adev, con->eeprom_control.bad_channel_bitmap);
> +                       con->update_channel_flag = false;
> +               }
> +       }
> +
> +       return ret;
> +}
> +
> +int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
>  {
>         struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
>         struct ras_err_handler_data **data;
> @@ -3187,25 +3222,10 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
>          */
>         if (adev->init_lvl->level == AMDGPU_INIT_LEVEL_MINIMAL)
>                 return 0;
> -       ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
> -       /*
> -        * This calling fails when is_rma is true or
> -        * ret != 0.
> -        */
> -       if (amdgpu_ras_is_rma(adev) || ret)
> -               goto free;
> -
> -       if (con->eeprom_control.ras_num_recs) {
> -               ret = amdgpu_ras_load_bad_pages(adev);
> +       if (init_bp_info) {
> +               ret = amdgpu_ras_init_badpage_info(adev);
>                 if (ret)
>                         goto free;
> -
> -               amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs);
> -
> -               if (con->update_channel_flag == true) {
> -                       amdgpu_dpm_send_hbm_bad_channel_flag(adev, con->eeprom_control.bad_channel_bitmap);
> -                       con->update_channel_flag = false;
> -               }
>         }
>
>         mutex_init(&con->page_rsv_lock);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> index 669720a9c60a..871b2d6278e0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> @@ -736,8 +736,8 @@ struct amdgpu_ras_block_hw_ops {
>   * 8: feature disable
>   */
>
> -
> -int amdgpu_ras_recovery_init(struct amdgpu_device *adev);
> +int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev);
> +int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info);
>
>  void amdgpu_ras_resume(struct amdgpu_device *adev);
>  void amdgpu_ras_suspend(struct amdgpu_device *adev);
> --
> 2.25.1
>