There're a bunch of things that were wrong: - Reading uffd-wp bit from a swap entry should use pte_swp_uffd_wp() rather than huge_pte_uffd_wp(). - When copying over a pte, we should drop uffd-wp bit when !EVENT_FORK (aka, when !userfaultfd_wp(dst_vma)). - When doing early CoW for private hugetlb (e.g. when the parent page was pinned), uffd-wp bit should be properly carried over if necessary. No bug reported probably because most people do not even care about these corner cases, but they are still bugs and can be exposed by the recent unit tests introduced, so fix all of them in one shot. Cc: linux-stable <stable@xxxxxxxxxxxxxxx> Fixes: bc70fbf269fd ("mm/hugetlb: handle uffd-wp during fork()") Reviewed-by: David Hildenbrand <david@xxxxxxxxxx> Signed-off-by: Peter Xu <peterx@xxxxxxxxxx> --- mm/hugetlb.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f16b25b1a6b9..0213efaf31be 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4953,11 +4953,15 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte) static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, - struct folio *new_folio) + struct folio *new_folio, pte_t old) { + pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); + __folio_mark_uptodate(new_folio); hugepage_add_new_anon_rmap(new_folio, vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, &new_folio->page, 1)); + if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) + newpte = huge_pte_mkuffd_wp(newpte); + set_huge_pte_at(vma->vm_mm, addr, ptep, newpte); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } @@ -5032,14 +5036,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { - bool uffd_wp = huge_pte_uffd_wp(entry); - - if (!userfaultfd_wp(dst_vma) && uffd_wp) + if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); - bool uffd_wp = huge_pte_uffd_wp(entry); + bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* @@ -5050,10 +5052,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) - entry = huge_pte_mkuffd_wp(entry); + entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry); } - if (!userfaultfd_wp(dst_vma) && uffd_wp) + if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { @@ -5114,7 +5116,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, /* huge_ptep of dst_pte won't change as in child */ goto again; } - hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio); + hugetlb_install_folio(dst_vma, dst_pte, addr, + new_folio, src_pte_old); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -5132,6 +5135,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = huge_pte_wrprotect(entry); } + if (!userfaultfd_wp(dst_vma)) + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(npages, dst); } -- 2.39.1