drm/xe: add missing bulk_move reset

It looks like bulk_move is set during object construction, but is only
removed on object close, however in various places we might not yet have
an actual fd to close, like on the error paths for the gem_create ioctl,
and also one internal user for the evict_test_run_gt() selftest. Try to
handle those cases by manually resetting the bulk_move. This should
prevent triggering:

WARNING: CPU: 7 PID: 8252 at drivers/gpu/drm/ttm/ttm_bo.c:327
ttm_bo_release+0x25e/0x2a0 [ttm]

v2 (Nirmoy):
  - It should be safe to just unconditionally call
    __xe_bo_unset_bulk_move() in most places.

Signed-off-by: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Nirmoy Das <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>

3 files changed, 30 insertions, 9 deletions

diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
index 5d60dc6bfe71..b32a9068d76c 100644
--- a/drivers/gpu/drm/xe/tests/xe_bo.c
+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
@@ -283,6 +283,10 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni
 		xe_bo_unlock(external, &ww);
 
 		xe_bo_put(external);
+
+		xe_bo_lock(bo, &ww, 0, false);
+		__xe_bo_unset_bulk_move(bo);
+		xe_bo_unlock(bo, &ww);
 		xe_bo_put(bo);
 		continue;
 
@@ -293,6 +297,9 @@ cleanup_all:
 cleanup_external:
 		xe_bo_put(external);
 cleanup_bo:
+		xe_bo_lock(bo, &ww, 0, false);
+		__xe_bo_unset_bulk_move(bo);
+		xe_bo_unlock(bo, &ww);
 		xe_bo_put(bo);
 		break;
 	}
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 9ad5cf3e2463..a3bb14aa2234 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1327,6 +1327,7 @@ xe_bo_create_locked_range(struct xe_device *xe,
 	return bo;
 
 err_unlock_put_bo:
+	__xe_bo_unset_bulk_move(bo);
 	xe_bo_unlock_vm_held(bo);
 	xe_bo_put(bo);
 	return ERR_PTR(err);
@@ -1770,22 +1771,29 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 	bo_flags |= args->flags << (ffs(XE_BO_CREATE_SYSTEM_BIT) - 1);
 	bo = xe_bo_create(xe, NULL, vm, args->size, ttm_bo_type_device,
 			  bo_flags);
-	if (vm) {
-		xe_vm_unlock(vm, &ww);
-		xe_vm_put(vm);
+	if (IS_ERR(bo)) {
+		err = PTR_ERR(bo);
+		goto out_vm;
 	}
 
-	if (IS_ERR(bo))
-		return PTR_ERR(bo);
-
 	err = drm_gem_handle_create(file, &bo->ttm.base, &handle);
-	xe_bo_put(bo);
 	if (err)
-		return err;
+		goto out_bulk;
 
 	args->handle = handle;
+	goto out_put;
 
-	return 0;
+out_bulk:
+	if (vm && !xe_vm_in_fault_mode(vm))
+		__xe_bo_unset_bulk_move(bo);
+out_put:
+	xe_bo_put(bo);
+out_vm:
+	if (vm) {
+		xe_vm_unlock(vm, &ww);
+		xe_vm_put(vm);
+	}
+	return err;
 }
 
 int xe_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 53a82ff7bce2..3e98f3c0b85e 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -144,6 +144,12 @@ static inline void xe_bo_put(struct xe_bo *bo)
 		drm_gem_object_put(&bo->ttm.base);
 }
 
+static inline void __xe_bo_unset_bulk_move(struct xe_bo *bo)
+{
+	if (bo)
+		ttm_bo_set_bulk_move(&bo->ttm, NULL);
+}
+
 static inline void xe_bo_assert_held(struct xe_bo *bo)
 {
 	if (bo)