Unverified Commit 8d490e01 authored by Rodrigo Vivi's avatar Rodrigo Vivi
Browse files

drm/xe: Stop checking for power_lost on D3Cold 



GuC reset status is not reliable for this purpose and it is
once in a while ending up in a situation of D3Cold, where
power_reset is false and without the proper memory restoration
the GuC reload and Display will fail to come back from D3Cold.

So, let's do a full restoration of everything if we have a risk
of losing power, without further optimizations.

v2: also remove the gut_in_reset function (Anshuman)

Cc: Anshuman Gupta <anshuman.gupta@intel.com>
Reviewed-by: default avatarAnshuman Gupta <anshuman.gupta@intel.com>
Reviewed-by: default avatarBadal Nilawar <badal.nilawar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240522170105.327472-6-rodrigo.vivi@intel.com


Signed-off-by: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
parent e7b180b2

drivers/gpu/drm/xe/xe_device_types.h

+0 −3
Original line number Diff line number Diff line
@@ -431,9 +431,6 @@ struct xe_device { 
		/** @d3cold.allowed: Indicates if d3cold is a valid device state */

		bool allowed;



		/** @d3cold.power_lost: Indicates if card has really lost power. */

		bool power_lost;



		/**

		 * @d3cold.vram_threshold:

		 *

drivers/gpu/drm/xe/xe_guc.c

+0 −27
Original line number Diff line number Diff line
@@ -1023,30 +1023,3 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p) 
	xe_guc_ct_print(&guc->ct, p, false);

	xe_guc_submit_print(guc, p);

}
 


/**

 * xe_guc_in_reset() - Detect if GuC MIA is in reset.

 * @guc: The GuC object

 *

 * This function detects runtime resume from d3cold by leveraging

 * GUC_STATUS, GUC doesn't get reset during d3hot,

 * it strictly to be called from RPM resume handler.

 *

 * Return: true if failed to get forcewake or GuC MIA is in Reset,

 * otherwise false.

 */

bool xe_guc_in_reset(struct xe_guc *guc)

{

	struct xe_gt *gt = guc_to_gt(guc);

	u32 status;

	int err;



	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);

	if (err)

		return true;



	status = xe_mmio_read32(gt, GUC_STATUS);

	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);



	return  status & GS_MIA_IN_RESET;

}

drivers/gpu/drm/xe/xe_guc.h

+0 −1
Original line number Diff line number Diff line
@@ -37,7 +37,6 @@ void xe_guc_reset_wait(struct xe_guc *guc); 
void xe_guc_stop_prepare(struct xe_guc *guc);

void xe_guc_stop(struct xe_guc *guc);

int xe_guc_start(struct xe_guc *guc);

bool xe_guc_in_reset(struct xe_guc *guc);



static inline u16 xe_engine_class_to_guc_class(enum xe_engine_class class)

{

drivers/gpu/drm/xe/xe_pm.c

+2 −10
Original line number Diff line number Diff line
@@ -404,15 +404,7 @@ int xe_pm_runtime_resume(struct xe_device *xe) 


	lock_map_acquire(&xe_pm_runtime_lockdep_map);



	/*

	 * It can be possible that xe has allowed d3cold but other pcie devices

	 * in gfx card soc would have blocked d3cold, therefore card has not

	 * really lost power. Detecting primary Gt power is sufficient.

	 */

	gt = xe_device_get_gt(xe, 0);

	xe->d3cold.power_lost = xe_guc_in_reset(&gt->uc.guc);



	if (xe->d3cold.allowed && xe->d3cold.power_lost) {

	if (xe->d3cold.allowed) {

		err = xe_pcode_ready(xe, true);

		if (err)

			goto out;
@@ -433,7 +425,7 @@ int xe_pm_runtime_resume(struct xe_device *xe) 
	for_each_gt(gt, xe, id)

		xe_gt_resume(gt);



	if (xe->d3cold.allowed && xe->d3cold.power_lost) {

	if (xe->d3cold.allowed) {

		xe_display_pm_resume(xe, true);

		err = xe_bo_restore_user(xe);

		if (err)