>> - if (mgr == NULL || mgr->drv == NULL) >> - return ret; >> - > > Can either of these conditions be true here? If so, we should leave > the check here (possibly add an error message), because GetNested > will dereference them. > > If not, they should be cleaned up in a separate patch. > > Jan > Well, the thing is, this was the first function in qemuProcessStart that touched the seclabel structures as well as the security manager and no other function called after this one didn't really need a check like this, because GenLabel would have returned -1 in case of NULL pointer, thus jumping to cleanup. Now, as I introduced a new function that is called before GenLabel, I think it might be correct to move this check up to this CheckAllLabel function and the original meaning remains, i.e. in case of NULL pointer CheckAllLabel returns -1 (I'll fix the return code from 0 to -1 which is clearly wrong and this must be just a typo, but you get the point...) followed by qemuProcessStart jumping to cleanup. Erik -- libvir-list mailing list libvir-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/libvir-list