On Thu, Jan 20, 2022 at 05:21:31PM +0100, Jan Beulich wrote: > On 20.01.2022 17:00, Roger Pau Monné wrote: > > On Thu, Jan 20, 2022 at 03:05:12PM +0100, Jan Beulich wrote: > >> While we don't want to skip calling update_idle_stats(), arrange for it > >> to not increment the overall time spent in the state we didn't really > >> enter. > >> > >> Signed-off-by: Jan Beulich <jbeul...@suse.com> > >> --- > >> RFC: Arguably more of what follows could be moved into the if() - > >> thoughts? > > > > I would move at least the restoring of the TSC, but I would be fine > > with moving everything up to local_irq_enable unless I'm missing > > something. > > Yes, that's what I was considering. > > > I think you could likely also avoid the call to update_idle_stats so > > there's no need to fetch the new tick count. > > No, this call cannot be bypassed. At least not without further > rearrangements elsewhere.
Ack, I would move everything you can then. Thanks, Roger.
