Hello, On Thu, Jun 15, 2017 at 05:52:24PM +0300, Kirill A. Shutemov wrote: > 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 > @@ -906,13 +906,13 @@ static inline void clear_soft_dirty(struct > vm_area_struct *vma, > static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, > unsigned long addr, pmd_t *pmdp) > { > - pmd_t pmd = *pmdp; > + pmd_t old, pmd = *pmdp; > > /* See comment in change_huge_pmd() */ > - pmdp_invalidate(vma, addr, pmdp); > - if (pmd_dirty(*pmdp)) > + old = pmdp_invalidate(vma, addr, pmdp); > + if (pmd_dirty(old)) > pmd = pmd_mkdirty(pmd); > - if (pmd_young(*pmdp)) > + if (pmd_young(old)) > pmd = pmd_mkyoung(pmd); > > pmd = pmd_wrprotect(pmd); > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > index a84909cf20d3..0433e73531bf 100644 > --- a/mm/huge_memory.c > +++ b/mm/huge_memory.c > @@ -1777,17 +1777,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t > *pmd, > * pmdp_invalidate() is required to make sure we don't miss > * dirty/young flags set by hardware. > */ > - entry = *pmd; > - pmdp_invalidate(vma, addr, pmd); > - > - /* > - * Recover dirty/young flags. It relies on pmdp_invalidate to not > - * corrupt them. > - */ > - if (pmd_dirty(*pmd)) > - entry = pmd_mkdirty(entry); > - if (pmd_young(*pmd)) > - entry = pmd_mkyoung(entry); > + entry = pmdp_invalidate(vma, addr, pmd); > > entry = pmd_modify(entry, newprot); > if (preserve_write) > @@ -1927,8 +1917,8 @@ static void __split_huge_pmd_locked(struct > vm_area_struct *vma, pmd_t *pmd, > struct mm_struct *mm = vma->vm_mm; > struct page *page; > pgtable_t pgtable; > - pmd_t _pmd; > - bool young, write, dirty, soft_dirty; > + pmd_t old, _pmd; > + bool young, write, soft_dirty; > unsigned long addr; > int i; > > @@ -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); > +
When I see this, without this patch, MADV_FREE has been broken because it can lose dirty bit by early checking. Right? If so, isn't it a candidate for -stable?
