commit
9638556a276125553549fdfe349c464481ec2f39 upstream.
The following check in rbd_img_obj_request_submit()
rbd_dev->parent_overlap <= obj_request->img_offset
allows the fall through to the non-layered write case even if both
parent_overlap and obj_request->img_offset belong to the same RADOS
object. This leads to data corruption, because the area to the left of
parent_overlap ends up unconditionally zero-filled instead of being
populated with parent data. Suppose we want to write 1M to offset 6M
of image bar, which is a clone of foo@snap; object_size is 4M,
parent_overlap is 5M:
rbd_data.<id>.
0000000000000001
---------------------|----------------------|------------
| should be copyup'ed | should be zeroed out | write ...
---------------------|----------------------|------------
4M 5M 6M
parent_overlap obj_request->img_offset
4..5M should be copyup'ed from foo, yet it is zero-filled, just like
5..6M is.
Given that the only striping mode kernel client currently supports is
chunking (i.e. stripe_unit == object_size, stripe_count == 1), round
parent_overlap up to the next object boundary for the purposes of the
overlap check.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
}
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+ struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+ return obj_request->img_offset <
+ round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
{
dout("%s: obj %p (was %d)\n", __func__, obj_request,
*/
if (!img_request_write_test(img_request) ||
!img_request_layered_test(img_request) ||
- rbd_dev->parent_overlap <= obj_request->img_offset ||
+ !obj_request_overlaps_parent(obj_request) ||
((known = obj_request_known_test(obj_request)) &&
obj_request_exists_test(obj_request))) {