When the loose edge and vertex status are cached in the source mesh and
the combination of selection domain and mode don't add loose elements,
copy the cache status to avoid recomputation. In a test with a 1 million
face grid:
- All: 23 -> 30 FPS
- Only faces: 22 -> 23.5 FPS
- Only edges and faces: 24 -> 27 FPS
Also remove unnecessary includes and fix a build error introduced in
the last commit to this area from an inconsistent forward declaration.