Re: RFC: COW for hugepages

[David Gibson <david@gibson.dropbear.id.au>]

On Wed, Apr 07, 2004 at 08:24:43PM -0700, Andrew Morton wrote:
> David Gibson <david@gibson.dropbear.id.au> wrote:
> >
> > > I don't see much in the COW code which is ppc64-specific.  All the hardware
> >  > needs to do is to provide a way to make the big pages readonly.  With a bit
> >  > of an abstraction for the TLB manipulation in there it should be pretty
> >  > straightforward.
> >  > 
> >  > Certainly worth the attempt, no?
> > 
> >  Yes, you have a point.  However doing it in a cross-arch way will
> >  require building more of a shared abstraction about hugepage pte
> >  entries that exists currently.  And that will mean making significant
> >  changes to all the archs to create that abstraction.  I don't know
> >  enough about the other archs to be confident of debugging such
> >  changes, but I'll see what I can do.
> 
> Well the first step is to consolidate the existing duplication in 2.6.5
> before thinking about new features.  That's largely a cut-n-paste job which
> I've been meaning to get onto but alas have not.  I don't want to dump it
> on you just because you want to tend to your COWs so if you have other
> things to do, please let me know.

Well, I do have other things to do, so I'll try to look at the
consolidation when I get a chance.

> We could use the `weak' attribute in mm/hugetlbpage.c for those cases where
> one arch really needs to do something different.

Yes, that's an idea.

-- 
David Gibson			| For every complex problem there is a
david AT gibson.dropbear.id.au	| solution which is simple, neat and
				| wrong.
http://www.ozlabs.org/people/dgibson