diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9a910612336d..bf9d8d04bf4f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5535,6 +5535,23 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, return handle_userfault(&vmf, reason); } +/* + * Recheck pte with pgtable lock. Returns true if pte didn't change, or + * false if pte changed or is changing. + */ +static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, + pte_t *ptep, pte_t old_pte) +{ + spinlock_t *ptl; + bool same; + + ptl = huge_pte_lock(h, mm, ptep); + same = pte_same(huge_ptep_get(ptep), old_pte); + spin_unlock(ptl); + + return same; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -5575,10 +5592,33 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (idx >= size) goto out; /* Check for page in userfault range */ - if (userfaultfd_missing(vma)) - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MISSING); + if (userfaultfd_missing(vma)) { + /* + * Since hugetlb_no_page() was examining pte + * without pgtable lock, we need to re-test under + * lock because the pte may not be stable and could + * have changed from under us. Try to detect + * either changed or during-changing ptes and retry + * properly when needed. + * + * Note that userfaultfd is actually fine with + * false positives (e.g. caused by pte changed), + * but not wrong logical events (e.g. caused by + * reading a pte during changing). The latter can + * confuse the userspace, so the strictness is very + * much preferred. E.g., MISSING event should + * never happen on the page after UFFDIO_COPY has + * correctly installed the page and returned. + */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MISSING); + } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { @@ -5644,9 +5684,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (userfaultfd_minor(vma)) { unlock_page(page); put_page(page); - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MINOR); + /* See comment in userfaultfd_missing() block above */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MINOR); } }