On Fri, Jun 16, 2017 at 05:01:30PM +0530, Aneesh Kumar K.V wrote: > "Kirill A. Shutemov" <[email protected]> writes: > > > This patch uses modifed pmdp_invalidate(), that return previous value of > > pmd, > > to transfer dirty and accessed bits. > > > > Signed-off-by: Kirill A. Shutemov <[email protected]> > > --- > > fs/proc/task_mmu.c | 8 ++++---- > > mm/huge_memory.c | 29 ++++++++++++----------------- > > 2 files changed, 16 insertions(+), 21 deletions(-) > > > > diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c > > index f0c8b33d99b1..f2fc1ef5bba2 100644 > > --- a/fs/proc/task_mmu.c > > +++ b/fs/proc/task_mmu.c > > ..... > > > @@ -1965,7 +1955,6 @@ static void __split_huge_pmd_locked(struct > > vm_area_struct *vma, pmd_t *pmd, > > page_ref_add(page, HPAGE_PMD_NR - 1); > > write = pmd_write(*pmd); > > young = pmd_young(*pmd); > > - dirty = pmd_dirty(*pmd); > > soft_dirty = pmd_soft_dirty(*pmd); > > > > pmdp_huge_split_prepare(vma, haddr, pmd); > > @@ -1995,8 +1984,6 @@ static void __split_huge_pmd_locked(struct > > vm_area_struct *vma, pmd_t *pmd, > > if (soft_dirty) > > entry = pte_mksoft_dirty(entry); > > } > > - if (dirty) > > - SetPageDirty(page + i); > > pte = pte_offset_map(&_pmd, addr); > > BUG_ON(!pte_none(*pte)); > > set_pte_at(mm, addr, pte, entry); > > @@ -2045,7 +2032,15 @@ static void __split_huge_pmd_locked(struct > > vm_area_struct *vma, pmd_t *pmd, > > * and finally we write the non-huge version of the pmd entry with > > * pmd_populate. > > */ > > - pmdp_invalidate(vma, haddr, pmd); > > + old = pmdp_invalidate(vma, haddr, pmd); > > + > > + /* > > + * Transfer dirty bit using value returned by pmd_invalidate() to be > > + * sure we don't race with CPU that can set the bit under us. > > + */ > > + if (pmd_dirty(old)) > > + SetPageDirty(page); > > + > > pmd_populate(mm, pmd, pgtable); > > > > if (freeze) { > > > Can we invalidate the pmd early here ? ie, do pmdp_invalidate instead of > pmdp_huge_split_prepare() ?
I think we can. But it means we would block access to the page for longer than it's necessary on most architectures. I guess it's not a bit deal. Maybe as separate patch on top of this patchet? Aneesh, would you take care of this? -- Kirill A. Shutemov
