Re: [PATCHv2 2/3] mm: Do not loose dirty and access bits in pmdp_invalidate()

From: Andrea Arcangeli
Date: Fri Jun 16 2017 - 09:40:48 EST

On Thu, Jun 15, 2017 at 05:52:23PM +0300, Kirill A. Shutemov wrote:
> -void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
> +pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
> pmd_t *pmdp)
> {
> - pmd_t entry = *pmdp;
> - set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
> - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
> + pmd_t old = pmdp_establish(pmdp, pmd_mknotpresent(*pmdp));
> + if (pmd_present(old))
> + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
> + return old;
> }
> #endif

The pmd_present() check added above is superflous because there's no
point to call pmdp_invalidate if the pmd is not present (present as in
pmd_present) already. pmd_present returns true if _PAGE_PSE is set
and it was always set before calling pmdp_invalidate.

It looks like we could skip the flush if _PAGE_PRESENT is not set
(i.e. for example if the pmd is PROTNONE) but that's not what the above
pmd_present will do.