drm/xe/pxp: add PXP PM support

The HW suspend flow kills all PXP HWDRM sessions, so we need to mark all
the queues and BOs as invalid and do a full termination when PXP is next
used.

v2: rebase
v3: rebase on new status flow, defer termination to next PXP use as it
makes things much easier and allows us to use the same function for all
types of suspend.
v4: fix the documentation of the suspend function (John)

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250129174140.948829-12-daniele.ceraolospurio@intel.com

1 files changed, 30 insertions, 9 deletions

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index c9cc0c091dfd..35dd1757b40b 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -22,6 +22,7 @@
 #include "xe_guc.h"
 #include "xe_irq.h"
 #include "xe_pcode.h"
+#include "xe_pxp.h"
 #include "xe_trace.h"
 #include "xe_wa.h"
 
@@ -122,6 +123,10 @@ int xe_pm_suspend(struct xe_device *xe)
 	drm_dbg(&xe->drm, "Suspending device\n");
 	trace_xe_pm_suspend(xe, __builtin_return_address(0));
 
+	err = xe_pxp_pm_suspend(xe->pxp);
+	if (err)
+		goto err;
+
 	for_each_gt(gt, xe, id)
 		xe_gt_suspend_prepare(gt);
 
@@ -130,14 +135,12 @@ int xe_pm_suspend(struct xe_device *xe)
 	/* FIXME: Super racey... */
 	err = xe_bo_evict_all(xe);
 	if (err)
-		goto err;
+		goto err_pxp;
 
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
-		if (err) {
-			xe_display_pm_resume(xe);
-			goto err;
-		}
+		if (err)
+			goto err_display;
 	}
 
 	xe_irq_suspend(xe);
@@ -146,6 +149,11 @@ int xe_pm_suspend(struct xe_device *xe)
 
 	drm_dbg(&xe->drm, "Device suspended\n");
 	return 0;
+
+err_display:
+	xe_display_pm_resume(xe);
+err_pxp:
+	xe_pxp_pm_resume(xe->pxp);
 err:
 	drm_dbg(&xe->drm, "Device suspend failed %d\n", err);
 	return err;
@@ -195,6 +203,8 @@ int xe_pm_resume(struct xe_device *xe)
 	if (err)
 		goto err;
 
+	xe_pxp_pm_resume(xe->pxp);
+
 	drm_dbg(&xe->drm, "Device resumed\n");
 	return 0;
 err:
@@ -389,6 +399,10 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 	 */
 	xe_rpm_lockmap_acquire(xe);
 
+	err = xe_pxp_pm_suspend(xe->pxp);
+	if (err)
+		goto out;
+
 	/*
 	 * Applying lock for entire list op as xe_ttm_bo_destroy and xe_bo_move_notify
 	 * also checks and deletes bo entry from user fault list.
@@ -404,22 +418,27 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 	if (xe->d3cold.allowed) {
 		err = xe_bo_evict_all(xe);
 		if (err)
-			goto out;
+			goto out_resume;
 	}
 
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
 		if (err)
-			goto out;
+			goto out_resume;
 	}
 
 	xe_irq_suspend(xe);
 
 	xe_display_pm_runtime_suspend_late(xe);
 
+	xe_rpm_lockmap_release(xe);
+	xe_pm_write_callback_task(xe, NULL);
+	return 0;
+
+out_resume:
+	xe_display_pm_runtime_resume(xe);
+	xe_pxp_pm_resume(xe->pxp);
 out:
-	if (err)
-		xe_display_pm_runtime_resume(xe);
 	xe_rpm_lockmap_release(xe);
 	xe_pm_write_callback_task(xe, NULL);
 	return err;
@@ -472,6 +491,8 @@ int xe_pm_runtime_resume(struct xe_device *xe)
 			goto out;
 	}
 
+	xe_pxp_pm_resume(xe->pxp);
+
 out:
 	xe_rpm_lockmap_release(xe);
 	xe_pm_write_callback_task(xe, NULL);