On Mon, May 29, 2017 at 12:22:52PM -0700, Nick Desaulniers wrote:
On Fri, May 26, 2017 at 10:07:46AM -0700, Dmitry Torokhov wrote:
quoted
If you look at the code of this fucntion we really use ps2_data as
signed in calculations, and this change would break that. While making
ps2_data u8 might be beneficial we'd need to rework mousedev_packet() to
use signed temporaries for dx, dy and dz before stufifng them into
ps2_data.
Is your recommendation then to stick with the simple cast as in V1 of
this patch, or stick with u8 and rework mousedev_packet()?
I think casts are often mysterious, so, unless we'll end up with worse
object code, I'd switch to u8 and temps.
--
Dmitry