Re: [RFC][PATCH v3 1/6] mm: Don't unmap gup()ed page

[Andrea Arcangeli <aarcange@redhat.com>]

On Wed, Apr 15, 2009 at 08:39:04PM +0900, KOSAKI Motohiro wrote:
> >> +     if (!migration) {
> >> +             /* re-check */
> >> +             if (PageSwapCache(page) &&
> >> +                 page_count(page) != page_mapcount(page) + 2) {
> >> +                     /* We lose race against get_user_pages_fast() */
> >> +                     set_pte_at(mm, address, pte, pteval);
> >> +                     ret = SWAP_FAIL;
> >> +                     goto out_unmap;
> >> +             }
> >> +     }
> >> +     mmu_notifier_invalidate_page(vma->vm_mm, address);
> >
> > With regard to mmu notifier, this is the opposite of the right
> > ordering. One mmu_notifier_invalidate_page must run _before_ the first
> > check. The ptep_clear_flush_notify will then stay and there's no need
> > of a further mmu_notifier_invalidate_page after the second check.
> 
> OK. but I have one question.
> 
> Can we assume mmu_notifier is only used by kvm now?
> if not, we need to make new notifier.

KVM is no fundamentally different from other users in this respect, so
I don't see why need a new notifier. If it works for others it'll work
for KVM and the other way around is true too.

mmu notifier users can or cannot take a page pin. KVM does. GRU
doesn't. XPMEM does. All of them releases any pin after
mmu_notifier_invalidate_page. All that is important is to run
mmu_notifier_invalidate_page _after_ the ptep_clear_young_notify, so
that we don't nuke secondary mappings on the pages unless we really go
to nuke the pte.