1 files changed, 49 insertions, 5 deletions

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ec04bef8ae40..5146999d27fa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -240,8 +240,8 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 
 	pfence = xe_preempt_fence_create(q, q->lr.context,
 					 ++q->lr.seqno);
-	if (!pfence) {
-		err = -ENOMEM;
+	if (IS_ERR(pfence)) {
+		err = PTR_ERR(pfence);
 		goto out_fini;
 	}
 
@@ -393,6 +393,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 		list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind,
 			       &vm->rebind_list);
 
+	if (!try_wait_for_completion(&vm->xe->pm_block))
+		return -EAGAIN;
+
 	ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false);
 	if (ret)
 		return ret;
@@ -479,6 +482,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 	return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues);
 }
 
+static bool vm_suspend_rebind_worker(struct xe_vm *vm)
+{
+	struct xe_device *xe = vm->xe;
+	bool ret = false;
+
+	mutex_lock(&xe->rebind_resume_lock);
+	if (!try_wait_for_completion(&vm->xe->pm_block)) {
+		ret = true;
+		list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list);
+	}
+	mutex_unlock(&xe->rebind_resume_lock);
+
+	return ret;
+}
+
+/**
+ * xe_vm_resume_rebind_worker() - Resume the rebind worker.
+ * @vm: The vm whose preempt worker to resume.
+ *
+ * Resume a preempt worker that was previously suspended by
+ * vm_suspend_rebind_worker().
+ */
+void xe_vm_resume_rebind_worker(struct xe_vm *vm)
+{
+	queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work);
+}
+
 static void preempt_rebind_work_func(struct work_struct *w)
 {
 	struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work);
@@ -502,6 +532,11 @@ static void preempt_rebind_work_func(struct work_struct *w)
 	}
 
 retry:
+	if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) {
+		up_write(&vm->lock);
+		return;
+	}
+
 	if (xe_vm_userptr_check_repin(vm)) {
 		err = xe_vm_userptr_pin(vm);
 		if (err)
@@ -1610,8 +1645,12 @@ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile,
 
 	for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) {
 		vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i);
-		if (IS_ERR(vm->scratch_pt[id][i]))
-			return PTR_ERR(vm->scratch_pt[id][i]);
+		if (IS_ERR(vm->scratch_pt[id][i])) {
+			int err = PTR_ERR(vm->scratch_pt[id][i]);
+
+			vm->scratch_pt[id][i] = NULL;
+			return err;
+		}
 
 		xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]);
 	}
@@ -1710,6 +1749,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 	if (flags & XE_VM_FLAG_LR_MODE) {
 		INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func);
 		xe_pm_runtime_get_noresume(xe);
+		INIT_LIST_HEAD(&vm->preempt.pm_activate_link);
 	}
 
 	if (flags & XE_VM_FLAG_FAULT_MODE) {
@@ -1891,8 +1931,12 @@ void xe_vm_close_and_put(struct xe_vm *vm)
 	xe_assert(xe, !vm->preempt.num_exec_queues);
 
 	xe_vm_close(vm);
-	if (xe_vm_in_preempt_fence_mode(vm))
+	if (xe_vm_in_preempt_fence_mode(vm)) {
+		mutex_lock(&xe->rebind_resume_lock);
+		list_del_init(&vm->preempt.pm_activate_link);
+		mutex_unlock(&xe->rebind_resume_lock);
 		flush_work(&vm->preempt.rebind_work);
+	}
 	if (xe_vm_in_fault_mode(vm))
 		xe_svm_close(vm);