Re: [patch 3/5] KVM: add kvm_follow_page()

[Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>]

On Sun, 23 Dec 2007 12:35:30 +0200 Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> wrote:

> Andrew Morton wrote:
> > On Sun, 23 Dec 2007 10:59:22 +0200 Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> wrote:
> >
> >   
> >> Avi Kivity wrote:
> >>     
> >>> Avi Kivity wrote:
> >>>   
> >>>       
> >>>> Exactly.  But it is better to be explicit about it and pass the page
> >>>> directly like you did before.  I hate to make you go back-and-fourth,
> >>>> but I did not understand the issue completely before.
> >>>>
> >>>>     
> >>>>         
> >>> btw, the call to gfn_to_page() can happen in page_fault() instead of
> >>> walk_addr(); that will reduce the amount of error handling, and will
> >>> simplify the callers to walk_addr() that don't need the page.
> >>>
> >>>   
> >>>       
> >> Note further that all this doesn't obviate the need for follow_page()
> >> (or get_user_pages_inatomic()); we still need something in update_pte()
> >> for the demand paging case.
> >>     
> >
> > Please review -mm's mm/pagewalk.c for suitability.
> >
> > If is is unsuitable but repairable then please cc Matt Mackall
> > <mpm-VDJrAJ4Gl5ZBDgjK7y7TUQ@public.gmane.org> on the review.
> >
> >   
> 
> The "no locks are taken" comment is very worrying.  We need accurate 
> results.

take down_read(mm->mmap_sem) before calling it..

You have to do that anyway for its results to be meaningful in the caller. 
Ditto get_user_pages().

> Getting pte_t's in the callbacks is a little too low level for kvm's use 
> (which wants struct page pointers) but of course that easily handled in 
> a kvm wrapper.
> 
> I'd prefer an atomic version of get_user_pages(), but if pagewalk is 
> fixed to take the necessary locks, it will do.

It isn't exported to modules at present, although I see no problem in
changing that.


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2005.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/