On Wed, 2017-08-09 at 02:57 -0600, Jan Beulich wrote:
> > > > On 09.08.17 at 10:48, <dario.faggioli@citrix.com> wrote:
> > 
> > _I_think_ what the original author meant was something along the
> > line
> > of <<Accessing nohz_cpu_mask before incrementing rcp->cur is
> > unsafe.
> > Therefore, let's access it afterwords, and put a barrier in
> > between.>>
> > 
> > But yeah, as said, I don't like it myself. In fact, it's the same
> > exact
> > wording used in the changelog of the patch (Linux commit
> > c3f5902325d3053986e7359f706581d8f032e72f), but while it is fine
> > there,
> > here is completely misleading, as it does not comment/describe the
> > final look of the code.
> > 
> > I'm going to change it.
> 
> Perhaps worth submitting a Linux patch too then?
> 
That code is long gone.

The file itself doesn't exist any longer, and the mask has been killed,
in favour of other mechanisms (depending of the variant of RCU, of the
degree of tickles-idleness, etc). :-)

Regards,
Dario
-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)