[PATCH 1/2] drm/amdgpu: refine eeprom data check

[Xie, Patrick]

[AMD Official Use Only - AMD Internal Distribution Only]

Thanks, will add this NULL check

-----Original Message-----
From: Lazar, Lijo <Lijo.Lazar at amd.com>
Sent: Friday, July 11, 2025 3:17 PM
To: Xie, Patrick <Gangliang.Xie at amd.com>; amd-gfx at lists.freedesktop.org
Cc: Zhou1, Tao <Tao.Zhou1 at amd.com>
Subject: Re: [PATCH 1/2] drm/amdgpu: refine eeprom data check



On 7/11/2025 8:10 AM, ganglxie wrote:
> add eeprom data checksum check before driver unload. reset eeprom and
> save correct data to eeprom when check failed
>
> Signed-off-by: ganglxie <ganglxie at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c       |  1 +
>  .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c    | 25 +++++++++++++++++++
>  .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h    |  2 ++
>  3 files changed, 28 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 571b70da4562..1009b60f6ae4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2560,6 +2560,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
>       struct drm_device *dev = pci_get_drvdata(pdev);
>       struct amdgpu_device *adev = drm_to_adev(dev);
>
> +     amdgpu_ras_eeprom_check_and_recover(adev);
>       amdgpu_xcp_dev_unplug(adev);
>       amdgpu_gmc_prepare_nps_mode_change(adev);
>       drm_dev_unplug(dev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
> index 2af14c369bb9..2458c67526c9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
> @@ -1522,3 +1522,28 @@ int amdgpu_ras_eeprom_check(struct
> amdgpu_ras_eeprom_control *control)
>
>       return res < 0 ? res : 0;
>  }
> +
> +void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev)
> +{
> +     struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);

Doesn't this require a NULL check?

Thanks,
Lijo

> +     struct amdgpu_ras_eeprom_control *control = &ras->eeprom_control;
> +     int res = 0;
> +
> +     if (!control->is_eeprom_valid)
> +             return;
> +     res = __verify_ras_table_checksum(control);
> +     if (res) {
> +             dev_warn(adev->dev,
> +                     "RAS table incorrect checksum or error:%d, try to recover\n",
> +                     res);
> +             if (!amdgpu_ras_eeprom_reset_table(control))
> +                     if (!amdgpu_ras_save_bad_pages(adev, NULL))
> +                             if (!__verify_ras_table_checksum(control)) {
> +                                     dev_info(adev->dev, "RAS table recovery succeed\n");
> +                                     return;
> +                             }
> +             dev_err(adev->dev, "RAS table recovery failed\n");
> +             control->is_eeprom_valid = false;
> +     }
> +     return;
> +}
> \ No newline at end of file
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
> index 35c69ac3dbeb..ebfca4cb5688 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
> @@ -161,6 +161,8 @@ void amdgpu_ras_debugfs_set_ret_size(struct
> amdgpu_ras_eeprom_control *control);
>
>  int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control
> *control);
>
> +void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev);
> +
>  extern const struct file_operations
> amdgpu_ras_debugfs_eeprom_size_ops;
>  extern const struct file_operations
> amdgpu_ras_debugfs_eeprom_table_ops;
>