From: Peter Xu Subject: mm/hugetlb: handle pte markers in page faults Allow hugetlb code to handle pte markers just like none ptes. It's mostly there, we just need to make sure we don't assume hugetlb_no_page() only handles none pte, so when detecting pte change we should use pte_same() rather than pte_none(). We need to pass in the old_pte to do the comparison. Check the original pte to see whether it's a pte marker, if it is, we should recover uffd-wp bit on the new pte to be installed, so that the next write will be trapped by uffd. Link: https://lkml.kernel.org/r/20220405014909.14761-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- mm/hugetlb.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) --- a/mm/hugetlb.c~mm-hugetlb-handle-pte-markers-in-page-faults +++ a/mm/hugetlb.c @@ -5425,7 +5425,8 @@ static inline vm_fault_t hugetlb_handle_ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, - unsigned long address, pte_t *ptep, unsigned int flags) + unsigned long address, pte_t *ptep, + pte_t old_pte, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; @@ -5552,7 +5553,8 @@ retry: ptl = huge_pte_lock(h, mm, ptep); ret = 0; - if (!huge_pte_none(huge_ptep_get(ptep))) + /* If pte changed from under us, retry */ + if (!pte_same(huge_ptep_get(ptep), old_pte)) goto backout; if (anon_rmap) { @@ -5562,6 +5564,12 @@ retry: page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); + /* + * If this pte was previously wr-protected, keep it wr-protected even + * if populated. + */ + if (unlikely(pte_marker_uffd_wp(old_pte))) + new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte)); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); @@ -5679,8 +5687,10 @@ vm_fault_t hugetlb_fault(struct mm_struc mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); - if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); + /* PTE markers should be handled the same way as none pte */ + if (huge_pte_none_mostly(entry)) { + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, + entry, flags); goto out_mutex; } _