drm/xe/vf: Teardown VF post migration worker on driver unload

Be cautious and ensure the VF post-migration worker is not running
during driver unload.

v3:
 - More teardown later in driver init, use devm (Tomasz)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-16-matthew.brost@intel.com

drivers/gpu/drm/xe/xe_gt.c

@@ -651,6 +651,12 @@ int xe_gt_init(struct xe_gt *gt)
 	if (err)
 		return err;
 
+	if (IS_SRIOV_VF(gt_to_xe(gt))) {
+		err = xe_gt_sriov_vf_init(gt);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/xe/xe_gt_sriov_vf.c

@@ -725,7 +725,8 @@ static void vf_start_migration_recovery(struct xe_gt *gt)
 
 	spin_lock(&gt->sriov.vf.migration.lock);
 
-	if (!gt->sriov.vf.migration.recovery_queued) {
+	if (!gt->sriov.vf.migration.recovery_queued ||
+	    !gt->sriov.vf.migration.recovery_teardown) {
 		gt->sriov.vf.migration.recovery_queued = true;
 		WRITE_ONCE(gt->sriov.vf.migration.recovery_inprogress, true);
 
@@ -1206,6 +1207,17 @@ static void migration_worker_func(struct work_struct *w)
 	vf_post_migration_recovery(gt);
 }
 
+static void vf_migration_fini(void *arg)
+{
+	struct xe_gt *gt = arg;
+
+	spin_lock_irq(&gt->sriov.vf.migration.lock);
+	gt->sriov.vf.migration.recovery_teardown = true;
+	spin_unlock_irq(&gt->sriov.vf.migration.lock);
+
+	cancel_work_sync(&gt->sriov.vf.migration.worker);
+}
+
 /**
  * xe_gt_sriov_vf_init_early() - GT VF init early
  * @gt: the &xe_gt
@@ -1232,6 +1244,26 @@ int xe_gt_sriov_vf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+/**
+ * xe_gt_sriov_vf_init() - GT VF init
+ * @gt: the &xe_gt
+ *
+ * Return 0 on success, errno on failure
+ */
+int xe_gt_sriov_vf_init(struct xe_gt *gt)
+{
+	if (!xe_sriov_vf_migration_supported(gt_to_xe(gt)))
+		return 0;
+
+	/*
+	 * We want to tear down the VF post-migration early during driver
+	 * unload; therefore, we add this finalization action later during
+	 * driver load.
+	 */
+	return devm_add_action_or_reset(gt_to_xe(gt)->drm.dev,
+					vf_migration_fini, gt);
+}
+
 /**
  * xe_gt_sriov_vf_recovery_pending() - VF post migration recovery pending
  * @gt: the &xe_gt

drivers/gpu/drm/xe/xe_gt_sriov_vf.h

@@ -24,6 +24,7 @@ int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt);
 void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
 
 int xe_gt_sriov_vf_init_early(struct xe_gt *gt);
+int xe_gt_sriov_vf_init(struct xe_gt *gt);
 bool xe_gt_sriov_vf_recovery_pending(struct xe_gt *gt);
 
 u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt);

drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h

@@ -45,10 +45,12 @@ struct xe_gt_sriov_vf_runtime {
 struct xe_gt_sriov_vf_migration {
 	/** @migration: VF migration recovery worker */
 	struct work_struct worker;
-	/** @lock: Protects recovery_queued */
+	/** @lock: Protects recovery_queued, teardown */
 	spinlock_t lock;
 	/** @scratch: Scratch memory for VF recovery */
 	void *scratch;
+	/** @recovery_teardown: VF post migration recovery is being torn down */
+	bool recovery_teardown;
 	/** @recovery_queued: VF post migration recovery in queued */
 	bool recovery_queued;
 	/** @recovery_inprogress: VF post migration recovery in progress */