[Intel-xe] [PATCH v2 09/27] drm/xe: Move drm exec loop to vm_bind_ioctl_ops_execute

[Dafna Hirschfeld]

On 06.11.2023 21:25, Matthew Brost wrote:
>The execution of the ops list can allocate memory in TTM which can
>trigger an eviction. Lockdep is not happy if the drm exec is closed when
>this happens.
>
>Signed-off-by: Matthew Brost <matthew.brost at intel.com>
>---
> drivers/gpu/drm/xe/xe_vm.c | 46 ++++++++++++++++++--------------------
> 1 file changed, 22 insertions(+), 24 deletions(-)
>
>diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>index 8dc448bf6222..485252f69ed7 100644
>--- a/drivers/gpu/drm/xe/xe_vm.c
>+++ b/drivers/gpu/drm/xe/xe_vm.c
>@@ -2851,23 +2851,17 @@ static int vm_bind_ioctl_ops_lock(struct drm_exec *exec,
> 	struct xe_vma_op *op;
> 	int err;
>
>-	drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
>-	drm_exec_until_all_locked(exec) {
>-		err = drm_exec_prepare_obj(exec, &xe_vm_ttm_bo(vm)->base, 1);
>-		drm_exec_retry_on_contention(exec);
>-		if (err)
>-			goto out;
>+	err = drm_exec_prepare_obj(exec, &xe_vm_ttm_bo(vm)->base, 1);
>+	if (err)
>+		return err;
>
>-		list_for_each_entry(op, &vops->list, link) {
>-			err = op_lock(exec, vm, op);
>-			drm_exec_retry_on_contention(exec);
>-			if (err)
>-				goto out;
>-		}
>+	list_for_each_entry(op, &vops->list, link) {
>+		err = op_lock(exec, vm, op);
>+		if (err)
>+			return err;
> 	}
>
>-out:
>-	return err;
>+	return 0;
> }
>
> static struct dma_fence *ops_execute(struct xe_vm *vm,
>@@ -2900,17 +2894,21 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
>
> 	lockdep_assert_held_write(&vm->lock);
>
>-	err = vm_bind_ioctl_ops_lock(&exec, vm, vops);
>-	if (err)
>-		return err;
>+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
>+	drm_exec_until_all_locked(&exec) {
>+		err = vm_bind_ioctl_ops_lock(&exec, vm, vops);
>+		drm_exec_retry_on_contention(&exec);
>+		if (err)
>+			return err;

I think here you miss drm_exec_fini
thanks,
Dafna

>
>-	fence = ops_execute(vm, vops, true);
>-	if (IS_ERR(fence)) {
>-		err = PTR_ERR(fence);
>-		/* FIXME: Killing VM rather than proper error handling */
>-		xe_vm_kill(vm, false);
>-	} else {
>-		dma_fence_put(fence);
>+		fence = ops_execute(vm, vops, true);
>+		if (IS_ERR(fence)) {
>+			err = PTR_ERR(fence);
>+			/* FIXME: Killing VM rather than proper error handling */
>+			xe_vm_kill(vm, false);
>+		} else {
>+			dma_fence_put(fence);
>+		}
> 	}
>
> 	drm_exec_fini(&exec);
>-- 
>2.34.1
>