Messages in this thread | | | Date | Fri, 15 May 2015 14:36:46 +0300 | From | "Kirill A. Shutemov" <> | Subject | Re: [PATCHv5 05/28] mm: adjust FOLL_SPLIT for new refcounting |
| |
On Fri, May 15, 2015 at 01:05:27PM +0200, Vlastimil Babka wrote: > On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: > >We need to prepare kernel to allow transhuge pages to be mapped with > >ptes too. We need to handle FOLL_SPLIT in follow_page_pte(). > > > >Also we use split_huge_page() directly instead of split_huge_page_pmd(). > >split_huge_page_pmd() will gone. > > You still call split_huge_page_pmd() for the is_huge_zero_page(page) case.
For huge zero page we split PMD into table of zero pages and don't touch compound page under it. That's what split_huge_page_pmd() (renamed into split_huge_pmd()) will do by the end of patchset.
> Also, of the code around split_huge_page() you basically took from > split_huge_page_pmd() and open-coded into follow_page_mask(), you didn't > include the mmu notifier calls. Why are they needed in split_huge_page_pmd() > but not here?
We do need mmu notifier in split_huge_page_pmd() for huge zero page. When we need to split compound page we go into split_huge_page() which takes care about mmut notifiers.
-- Kirill A. Shutemov
| |