drm/xe: Prepare display for D3Cold

Prepare power-well and DC handling for a full power
lost during D3Cold, then sanitize it upon D3->D0.
Otherwise we get a bunch of state mismatch.

Ideally we could leave DC9 enabled and wouldn't need
to move DC9->DC0 on every runtime resume, however,
the disable_DC is part of the power-well checks and
intrinsic to the dc_off power well. In the future that
can be detangled so we can have even bigger power savings.
But for now, let's focus on getting a D3Cold, which saves
much more power by itself.

v2: create new functions to avoid full-suspend-resume path,
which would result in a deadlock between xe_gem_fault and the
modeset-ioctl.

v3: Only avoid the full modeset to avoid the race, for a more
robust suspend-resume.

Cc: Anshuman Gupta <anshuman.gupta@intel.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Tested-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240522170105.327472-5-rodrigo.vivi@intel.comSigned-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/display/xe_display.c

@@ -308,7 +308,7 @@ static bool suspend_to_idle(void)
 	return false;
 }
 
-void xe_display_pm_suspend(struct xe_device *xe)
+void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 {
 	bool s2idle = suspend_to_idle();
 	if (!xe->info.enable_display)
@@ -322,6 +322,7 @@ void xe_display_pm_suspend(struct xe_device *xe)
 	if (has_display(xe))
 		drm_kms_helper_poll_disable(&xe->drm);
 
+	if (!runtime)
 		intel_display_driver_suspend(xe);
 
 	intel_dp_mst_suspend(xe);
@@ -358,7 +359,7 @@ void xe_display_pm_resume_early(struct xe_device *xe)
 	intel_power_domains_resume(xe);
 }
 
-void xe_display_pm_resume(struct xe_device *xe)
+void xe_display_pm_resume(struct xe_device *xe, bool runtime)
 {
 	if (!xe->info.enable_display)
 		return;
@@ -373,6 +374,7 @@ void xe_display_pm_resume(struct xe_device *xe)
 
 	/* MST sideband requires HPD interrupts enabled */
 	intel_dp_mst_resume(xe);
+	if (!runtime)
 		intel_display_driver_resume(xe);
 
 	intel_hpd_poll_disable(xe);

drivers/gpu/drm/xe/display/xe_display.h

@@ -34,10 +34,10 @@ void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir);
 void xe_display_irq_reset(struct xe_device *xe);
 void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt);
 
-void xe_display_pm_suspend(struct xe_device *xe);
+void xe_display_pm_suspend(struct xe_device *xe, bool runtime);
 void xe_display_pm_suspend_late(struct xe_device *xe);
 void xe_display_pm_resume_early(struct xe_device *xe);
-void xe_display_pm_resume(struct xe_device *xe);
+void xe_display_pm_resume(struct xe_device *xe, bool runtime);
 
 #else
 
@@ -63,10 +63,10 @@ static inline void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir)
 static inline void xe_display_irq_reset(struct xe_device *xe) {}
 static inline void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) {}
 
-static inline void xe_display_pm_suspend(struct xe_device *xe) {}
+static inline void xe_display_pm_suspend(struct xe_device *xe, bool runtime) {}
 static inline void xe_display_pm_suspend_late(struct xe_device *xe) {}
 static inline void xe_display_pm_resume_early(struct xe_device *xe) {}
-static inline void xe_display_pm_resume(struct xe_device *xe) {}
+static inline void xe_display_pm_resume(struct xe_device *xe, bool runtime) {}
 
 #endif /* CONFIG_DRM_XE_DISPLAY */
 #endif /* _XE_DISPLAY_H_ */

drivers/gpu/drm/xe/xe_pm.c

@@ -96,12 +96,12 @@ int xe_pm_suspend(struct xe_device *xe)
 	if (err)
 		goto err;
 
-	xe_display_pm_suspend(xe);
+	xe_display_pm_suspend(xe, false);
 
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
 		if (err) {
-			xe_display_pm_resume(xe);
+			xe_display_pm_resume(xe, false);
 			goto err;
 		}
 	}
@@ -151,7 +151,7 @@ int xe_pm_resume(struct xe_device *xe)
 
 	xe_irq_resume(xe);
 
-	xe_display_pm_resume(xe);
+	xe_display_pm_resume(xe, false);
 
 	for_each_gt(gt, xe, id)
 		xe_gt_resume(gt);
@@ -366,6 +366,7 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 		err = xe_bo_evict_all(xe);
 		if (err)
 			goto out;
+		xe_display_pm_suspend(xe, true);
 	}
 
 	for_each_gt(gt, xe, id) {
@@ -375,7 +376,12 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 	}
 
 	xe_irq_suspend(xe);
+
+	if (xe->d3cold.allowed)
+		xe_display_pm_suspend_late(xe);
 out:
+	if (err)
+		xe_display_pm_resume(xe, true);
 	lock_map_release(&xe_pm_runtime_lockdep_map);
 	xe_pm_write_callback_task(xe, NULL);
 	return err;
@@ -411,6 +417,8 @@ int xe_pm_runtime_resume(struct xe_device *xe)
 		if (err)
 			goto out;
 
+		xe_display_pm_resume_early(xe);
+
 		/*
 		 * This only restores pinned memory which is the memory
 		 * required for the GT(s) to resume.
@@ -426,6 +434,7 @@ int xe_pm_runtime_resume(struct xe_device *xe)
 		xe_gt_resume(gt);
 
 	if (xe->d3cold.allowed && xe->d3cold.power_lost) {
+		xe_display_pm_resume(xe, true);
 		err = xe_bo_restore_user(xe);
 		if (err)
 			goto out;