On Wed 19-03-25 17:16:06, Mateusz Guzik wrote: > On Wed, Mar 19, 2025 at 5:11 PM Jan Kara <jack@xxxxxxx> wrote: > > > > On Wed 19-03-25 01:46:35, Mateusz Guzik wrote: > > > While this may sound like a pedantic clean up, it does in fact impact > > > code generation -- the patched add routine is slightly smaller. > > > > > > Signed-off-by: Mateusz Guzik <mjguzik@xxxxxxxxx> > > > > I'm surprised it matters for the compiler but as Christian wrote, why not. > > Feel free to add: > > > > In stock code the fence in spin_lock forces the compiler to load > ->i_sb again -- as far as it knows it could have changed. > > On the other this patch forces the compiler to remember the value for > the same reason, which turns out to produce less code. I see. Thanks for explanation! Honza -- Jan Kara <jack@xxxxxxxx> SUSE Labs, CR
