[PATCH 2/2] RFC drm/xe: Enable Boot Survivability mode

[Rodrigo Vivi]

On Thu, Dec 12, 2024 at 11:19:45AM +0530, Riana Tauro wrote:
> Enable boot survivability mode if pcode initialization fails and
> if boot status indicates a failure. In this mode, drm card is not
> exposed and driver probe returns success after loading the bare minimum
> to allow firmware to be flashed via mei.
> 
> Signed-off-by: Riana Tauro <riana.tauro at intel.com>

Reviewed-by: Rodrigo Vivi <rodrigo.vivi at intel.com>

> ---
>  drivers/gpu/drm/xe/xe_device.c             |  9 +++++++--
>  drivers/gpu/drm/xe/xe_pci.c                | 13 +++++++++++++
>  drivers/gpu/drm/xe/xe_survivability_mode.c |  3 +++
>  3 files changed, 23 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index 56d4ffb650da..50ed980e1db9 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -51,6 +51,7 @@
>  #include "xe_pm.h"
>  #include "xe_query.h"
>  #include "xe_sriov.h"
> +#include "xe_survivability_mode.h"
>  #include "xe_tile.h"
>  #include "xe_ttm_stolen_mgr.h"
>  #include "xe_ttm_sys_mgr.h"
> @@ -585,8 +586,12 @@ int xe_device_probe_early(struct xe_device *xe)
>  	update_device_info(xe);
>  
>  	err = xe_pcode_probe_early(xe);
> -	if (err)
> -		return err;
> +	if (err) {
> +		if (xe->info.platform == XE_BATTLEMAGE && xe_survivability_mode_required(xe))
> +			xe_survivability_mode_init(xe);
> +
> +		return xe->survivability.mode ? 0 : err;
> +	}
>  
>  	err = wait_for_lmem_ready(xe);
>  	if (err)
> diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
> index 7d146e3e8e21..b9dcd36de06d 100644
> --- a/drivers/gpu/drm/xe/xe_pci.c
> +++ b/drivers/gpu/drm/xe/xe_pci.c
> @@ -30,6 +30,7 @@
>  #include "xe_pm.h"
>  #include "xe_sriov.h"
>  #include "xe_step.h"
> +#include "xe_survivability_mode.h"
>  #include "xe_tile.h"
>  
>  enum toggle_d3cold {
> @@ -768,6 +769,9 @@ static void xe_pci_remove(struct pci_dev *pdev)
>  	if (IS_SRIOV_PF(xe))
>  		xe_pci_sriov_configure(pdev, 0);
>  
> +	if (xe->survivability.mode)
> +		return xe_survivability_mode_remove(xe);
> +
>  	xe_device_remove(xe);
>  	xe_pm_runtime_fini(xe);
>  	pci_set_drvdata(pdev, NULL);
> @@ -840,6 +844,15 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
>  		return err;
>  
>  	err = xe_device_probe_early(xe);
> +
> +	/*
> +	 * In Boot Survivability mode, no drm card is exposed
> +	 * and driver is loaded with bare minimum to allow
> +	 * for firmware to be flashed through mei
> +	 */
> +	if (!err && xe->survivability.mode)
> +		return 0;
> +
>  	if (err)
>  		return err;
>  
> diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
> index 7e36989efd68..6c1e79b5c15f 100644
> --- a/drivers/gpu/drm/xe/xe_survivability_mode.c
> +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
> @@ -176,7 +176,10 @@ bool xe_survivability_mode_required(struct xe_device *xe)
>   */
>  void xe_survivability_mode_remove(struct xe_device *xe)
>  {
> +	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> +
>  	sysfs_remove_files(&xe->drm.dev->kobj, survivability_attrs);
> +	pci_set_drvdata(pdev, NULL);
>  }
>  
>  /**
> -- 
> 2.47.1
>