Re: kicking everybody out of the softc

[David Young <dyoung%pobox.com@localhost>]

On Sun, Aug 15, 2010 at 04:08:29PM -0400, der Mouse wrote:
> > I've been working in spare moments on lockless code to prevent
> > storage for a softc from going away while a driver uses it.  [...]
> 
> This looks superficially good, but isn't the cost of the necessary
> memory barries and cache flushes comparable with the cost of a more
> traditional scheme?

On the fast path, a processor does not modify any shared cachelines, so
we avoid many of the memory barriers and cache flushes of a traditional
scheme, unless there's something I've missed.

Dave

-- 
David Young             OJC Technologies
dyoung%ojctech.com@localhost      Urbana, IL * (217) 278-3933