Commit caf2f156 authored by Lucas De Marchi's avatar Lucas De Marchi
Browse files

drm/xe: Move survivability back to xe 



Commit d40f275d ("drm/xe: Move survivability entirely to xe_pci")
moved the survivability handling to be done entirely in the xe_pci
layer. However there are some issues with that approach:

1) Survivability mode needs at least the mmio initialized, otherwise it
   can't really read a register to decide if it should enter that state
2) SR-IOV mode should be initialized, otherwise it's not possible to
   check if it's VF

Besides, as pointed by Riana the check for
xe_survivability_mode_enable() was wrong in xe_pci_probe() since it's
not a bool return.

Fix that by moving the initialization to be entirely in the xe_device
layer, with the correct dependencies handled: only after mmio and sriov
initialization, and not triggering it on error from
wait_for_lmem_ready(). This restores the trigger behavior before that
commit. The xe_pci layer now only checks for "is it enabled?",
like it's doing in xe_pci_suspend()/xe_pci_remove(), etc.

Cc: Riana Tauro <riana.tauro@intel.com>
Fixes: d40f275d ("drm/xe: Move survivability entirely to xe_pci")
Reviewed-by: default avatarRiana Tauro <riana.tauro@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250314-fix-survivability-v5-1-fdb3559ea965@intel.com


Signed-off-by: default avatarLucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 86b5e0db)
Signed-off-by: default avatarLucas De Marchi <lucas.demarchi@intel.com>
parent d2de4410

drivers/gpu/drm/xe/xe_device.c

+15 −2
Original line number Diff line number Diff line
@@ -53,6 +53,7 @@ 
#include "xe_pxp.h"

#include "xe_query.h"

#include "xe_shrinker.h"

#include "xe_survivability_mode.h"

#include "xe_sriov.h"

#include "xe_tile.h"

#include "xe_ttm_stolen_mgr.h"
@@ -705,9 +706,21 @@ int xe_device_probe_early(struct xe_device *xe) 
	sriov_update_device_info(xe);



	err = xe_pcode_probe_early(xe);

	if (err) {

		int save_err = err;



		/*

		 * Try to leave device in survivability mode if device is

		 * possible, but still return the previous error for error

		 * propagation

		 */

		err = xe_survivability_mode_enable(xe);

		if (err)

			return err;



		return save_err;

	}



	err = wait_for_lmem_ready(xe);

	if (err)

		return err;

drivers/gpu/drm/xe/xe_pci.c

+7 −9
Original line number Diff line number Diff line
@@ -803,16 +803,14 @@ 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. If early probe fails, check if survivability mode is flagged by

	 * HW to be enabled. In that case enable it and return success.

		 * 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 early probe failed, but it managed to

		 * enable survivability mode, return success.

		 */

	if (err) {

		if (xe_survivability_mode_required(xe) &&

		    xe_survivability_mode_enable(xe))

		if (xe_survivability_mode_is_enabled(xe))

			return 0;



		return err;

drivers/gpu/drm/xe/xe_survivability_mode.c

+12 −7
Original line number Diff line number Diff line
@@ -178,15 +178,16 @@ bool xe_survivability_mode_is_enabled(struct xe_device *xe) 
	return xe->survivability.mode;

}



/**

 * xe_survivability_mode_required - checks if survivability mode is required

 * @xe: xe device instance

/*

 * survivability_mode_requested - check if it's possible to enable

 * survivability mode and that was requested by firmware

 *

 * This function reads the boot status from Pcode

 * This function reads the boot status from Pcode.

 *

 * Return: true if boot status indicates failure, false otherwise

 * Return: true if platform support is available and boot status indicates

 * failure, false otherwise.

 */

bool xe_survivability_mode_required(struct xe_device *xe)

static bool survivability_mode_requested(struct xe_device *xe)

{

	struct xe_survivability *survivability = &xe->survivability;

	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
@@ -208,7 +209,8 @@ bool xe_survivability_mode_required(struct xe_device *xe) 
 *

 * Initialize survivability information and enable survivability mode

 *

 * Return: 0 for success, negative error code otherwise.

 * Return: 0 if survivability mode is enabled or not requested; negative error

 * code otherwise.

 */

int xe_survivability_mode_enable(struct xe_device *xe)

{
@@ -216,6 +218,9 @@ int xe_survivability_mode_enable(struct xe_device *xe) 
	struct xe_survivability_info *info;

	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);



	if (!survivability_mode_requested(xe))

		return 0;



	survivability->size = MAX_SCRATCH_MMIO;



	info = devm_kcalloc(xe->drm.dev, survivability->size, sizeof(*info),

drivers/gpu/drm/xe/xe_survivability_mode.h

+0 −1
Original line number Diff line number Diff line
@@ -12,6 +12,5 @@ struct xe_device; 


int xe_survivability_mode_enable(struct xe_device *xe);

bool xe_survivability_mode_is_enabled(struct xe_device *xe);

bool xe_survivability_mode_required(struct xe_device *xe);



#endif /* _XE_SURVIVABILITY_MODE_H_ */