Re: [V2 PATCH 0/6] x86, NMI: give NMI handler a face-lift

[Cyrill Gorcunov <gorcunov@gmail.com>]

On Thu, Nov 18, 2010 at 04:02:31PM -0500, Don Zickus wrote:
...
> > >  Don, Robert,
> > > 
> > >  I still have suspicious on ours 'pending' nmi handler. Look what I mean --
> > > (keep in mind that p4 has a a way more counters than others).
> > > 
> > 
> >  To be precise -- it seems this scenario may force the back-to-back
> > nmi handler to eat unknown nmi.
> 
> That was the point of the change to do exactly that.

I missed the word, I meant to eat 'real' unknown nmi, not those
generated by counters and stand 'in-fly', so that unknown_nmi_error()
will be eaten. what is worse the NMI generated by kgdb may be eaten as
well and treated as being 'pending' one, though  there is quite a small
probability of such situation I believe.

> 
> The problem is/was when you go to check to see if the period expired in
> x86_perf_event_set_period(), you refresh the perf counter.  The next step
> is to see if the event period has expired, if so disabled the 'active'
> bit.
> 
> However, there is a race between when you refresh the counter to when you
> actually disable it, such that you may cause the counter to overflow again
> and thus generate another NMI.  The whole ->running thing was implemented
> by Robert to try and check for that condition and eat the NMI as we have
> no intention of handling it (because it is bogus).
> 
> The alternative is to use another rdmsrl to actually see if we trigger
> another NMI.  This was deemed a performance hit for such a small case.
> 
> Cheers,
> Don
> 

yeah, I recall now, thanks for refresh Don!

  Cyrill