From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 1 Aug 2025 14:28:22 +0000 (+0200)
Subject: drm/xe/pf: Don't resume device from restart worker
X-Git-Tag: v6.18-rc1~134^2~18^2~119
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=9fd9f221440024b7451678898facfb34af054310;p=thirdparty%2Flinux.git

drm/xe/pf: Don't resume device from restart worker

The PF's restart worker shouldn't attempt to resume the device on
its own, since its goal is to finish PF and VFs reprovisioning on
the recently reset GuC. Take extra RPM reference while scheduling
a work and release it from the worker or when we cancel a work.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801142822.180530-4-michal.wajdeczko@intel.com
---

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index bdbd15f3afe38..c4dda87b47cc8 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -55,7 +55,12 @@ static void pf_init_workers(struct xe_gt *gt)
 static void pf_fini_workers(struct xe_gt *gt)
 {
 	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
-	disable_work_sync(&gt->sriov.pf.workers.restart);
+
+	if (disable_work_sync(&gt->sriov.pf.workers.restart)) {
+		xe_gt_sriov_dbg_verbose(gt, "pending restart disabled!\n");
+		/* release an rpm reference taken on the worker's behalf */
+		xe_pm_runtime_put(gt_to_xe(gt));
+	}
 }
 
 /**
@@ -207,8 +212,11 @@ static void pf_cancel_restart(struct xe_gt *gt)
 {
 	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
 
-	if (cancel_work_sync(&gt->sriov.pf.workers.restart))
+	if (cancel_work_sync(&gt->sriov.pf.workers.restart)) {
 		xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n");
+		/* release an rpm reference taken on the worker's behalf */
+		xe_pm_runtime_put(gt_to_xe(gt));
+	}
 }
 
 /**
@@ -226,9 +234,12 @@ static void pf_restart(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 
-	xe_pm_runtime_get(xe);
+	xe_gt_assert(gt, !xe_pm_runtime_suspended(xe));
+
 	xe_gt_sriov_pf_config_restart(gt);
 	xe_gt_sriov_pf_control_restart(gt);
+
+	/* release an rpm reference taken on our behalf */
 	xe_pm_runtime_put(xe);
 
 	xe_gt_sriov_dbg(gt, "restart completed\n");
@@ -247,8 +258,13 @@ static void pf_queue_restart(struct xe_gt *gt)
 
 	xe_gt_assert(gt, IS_SRIOV_PF(xe));
 
-	if (!queue_work(xe->sriov.wq, &gt->sriov.pf.workers.restart))
+	/* take an rpm reference on behalf of the worker */
+	xe_pm_runtime_get_noresume(xe);
+
+	if (!queue_work(xe->sriov.wq, &gt->sriov.pf.workers.restart)) {
 		xe_gt_sriov_dbg(gt, "restart already in queue!\n");
+		xe_pm_runtime_put(xe);
+	}
 }
 
 /**