[PATCH v4 2/3] drm/xe: Enable Boot Survivability mode

[Gupta, Anshuman]

> -----Original Message-----
> From: Tauro, Riana <riana.tauro at intel.com>
> Sent: Thursday, January 23, 2025 12:54 PM
> To: intel-xe at lists.freedesktop.org
> Cc: Tauro, Riana <riana.tauro at intel.com>; Gupta, Anshuman
> <anshuman.gupta at intel.com>; Vivi, Rodrigo <rodrigo.vivi at intel.com>;
> Iddamsetty, Aravind <aravind.iddamsetty at intel.com>
> Subject: [PATCH v4 2/3] drm/xe: Enable Boot Survivability mode
> 
> 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.
> 
> v2: abstract survivability mode variable
>     add BMG check inside function (Jani, Rodrigo)
> 
> v3: return -EBUSY during system suspend (Anshuman)
>     check survivability mode in pci probe only
>     on error
> 
> 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             |  7 ++++++-
>  drivers/gpu/drm/xe/xe_pci.c                | 23 ++++++++++++++++++++--
>  drivers/gpu/drm/xe/xe_survivability_mode.c | 16 +++++++++++++++
> drivers/gpu/drm/xe/xe_survivability_mode.h |  1 +
>  4 files changed, 44 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index bd6191e1ed3e..0a938bd0e34d 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"
> @@ -692,8 +693,12 @@ int xe_device_probe_early(struct xe_device *xe)
>  	update_device_info(xe);
> 
>  	err = xe_pcode_probe_early(xe);
> -	if (err)
> +	if (err) {
> +		if (xe_survivability_mode_required(xe))
> +			xe_survivability_mode_init(xe);
> +
>  		return 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
> e6ad189294c1..b483c5c90132 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 {
> @@ -766,6 +767,9 @@ static void xe_pci_remove(struct pci_dev *pdev)
>  	if (IS_SRIOV_PF(xe))
>  		xe_pci_sriov_configure(pdev, 0);
> 
> +	if (xe_survivability_mode_enabled(xe))
> +		return xe_survivability_mode_remove(xe);
> +
>  	xe_device_remove(xe);
>  	xe_pm_runtime_fini(xe);
>  	pci_set_drvdata(pdev, NULL);
> @@ -838,8 +842,19 @@ static int xe_pci_probe(struct pci_dev *pdev, const
> struct pci_device_id *ent)
>  		return err;
> 
>  	err = xe_device_probe_early(xe);
> -	if (err)
> +
> +	/*
> +	 * 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. Return
> +	 * success if survivability mode is enabled.
> +	 */
> +	if (err) {
> +		if (xe_survivability_mode_enabled(xe))
> +			return 0;
> +
>  		return err;
> +	}
> 
>  	err = xe_info_init(xe, desc->graphics, desc->media);
>  	if (err)
> @@ -926,9 +941,13 @@ static void d3cold_toggle(struct pci_dev *pdev,
> enum toggle_d3cold toggle)  static int xe_pci_suspend(struct device *dev)  {
>  	struct pci_dev *pdev = to_pci_dev(dev);
> +	struct xe_device *xe = pdev_to_xe_device(pdev);
>  	int err;
> 
> -	err = xe_pm_suspend(pdev_to_xe_device(pdev));
> +	if (xe_survivability_mode_enabled(xe))
> +		return -EBUSY;
@Vivi, Rodrigo how about using pm_stay_awake() to avoid the suspend instead of returning -EBUSY from driver, Let PM Core abort the suspend ?
and pm_relax() in module unload path.
CC: Rafael to provide if above can be used here.
Thanks,
Anshuman
> +
> +	err = xe_pm_suspend(xe);
>  	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 8b7bd6e79eca..14d0ab7b75e5 100644
> --- a/drivers/gpu/drm/xe/xe_survivability_mode.c
> +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
> @@ -144,6 +144,19 @@ static void enable_survivability_mode(struct pci_dev
> *pdev)
>  	}
>  }
> 
> +/**
> + * xe_survivability_mode_enabled - check if survivability mode is
> +enabled
> + * @xe: xe device instance
> + *
> + * Returns true if in survivability mode, false otherwise  */ bool
> +xe_survivability_mode_enabled(struct xe_device *xe) {
> +	struct xe_survivability *survivability = &xe->survivability;
> +
> +	return survivability->mode;
> +}
> +
>  /**
>   * xe_survivability_mode_required - checks if survivability mode is required
>   * @xe: xe device instance
> @@ -158,6 +171,9 @@ bool xe_survivability_mode_required(struct
> xe_device *xe)
>  	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
>  	u32 data;
> 
> +	if (!IS_DGFX(xe) || xe->info.platform < XE_BATTLEMAGE)
> +		return false;
> +
>  	data = xe_mmio_read32(mmio, PCODE_SCRATCH(0));
>  	survivability->boot_status = REG_FIELD_GET(BOOT_STATUS, data);
> 
> diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h
> b/drivers/gpu/drm/xe/xe_survivability_mode.h
> index 410e3ee5f5d1..f530507a22c6 100644
> --- a/drivers/gpu/drm/xe/xe_survivability_mode.h
> +++ b/drivers/gpu/drm/xe/xe_survivability_mode.h
> @@ -12,6 +12,7 @@ struct xe_device;
> 
>  void xe_survivability_mode_init(struct xe_device *xe);  void
> xe_survivability_mode_remove(struct xe_device *xe);
> +bool xe_survivability_mode_enabled(struct xe_device *xe);
>  bool xe_survivability_mode_required(struct xe_device *xe);
> 
>  #endif /* _XE_SURVIVABILITY_MODE_H_ */
> --
> 2.47.1