follow_pud_mask() reads the PUD without a lock. If it is a leaf, it takes the lock and calls follow_huge_pud(), which reads the entry again, but only tests whether it is present. A leaf can be zapped concurrently and a page fault can fill the empty entry with a page table. This currently only applies when device-dax makes use of PUD entries, and the fault after e.g., MADV_DONTNEED would find THPs to be disabled. That requires a sequence like 1) Fault in the PUD 2) Disable THP 3) Have GUP race against concurrent MADV_DONTNEED + refault Which is rather unlikely to happen in practice, which is why we never received a report about such a problem. Before commit 1b1676180246 ("mm/gup: handle huge pud for follow_pud_mask()"), we performed that check in follow_devmap_pud() by testing for pud_devmap(). Let's fix it by just structuring follow_pud_mask() similar to follow_pmd_mask(), minus protnone stuff that does not apply and minus FOLL_SPLIT_PMD handling. That makes it much easier to spot any such inconsistencies. Perform the pud_bad() check early in follow_pmd_mask() and just forward the PUD value. We can drop the pud_present() check in follow_huge_pud(), just like we have in follow_huge_pmd(). Even though we are performing more changes than strictly necessary, the fix should be easy to backport. Fixes: 1b1676180246 ("mm/gup: handle huge pud for follow_pud_mask()") Cc: stable@vger.kernel.org Reported-by: Josef Bacik Tested-by: Muhammad Usama Anjum Signed-off-by: David Hildenbrand (Arm) --- mm/gup.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 7d43ce717b246..f809361227e7e 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -658,9 +658,6 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, assert_spin_locked(pud_lockptr(mm, pudp)); - if (!pud_present(pud)) - return NULL; - if ((flags & FOLL_WRITE) && !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags)) return NULL; @@ -896,15 +893,17 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, } static struct page *follow_pmd_mask(struct vm_area_struct *vma, - unsigned long address, pud_t *pudp, - unsigned int flags, - unsigned long *page_mask) + unsigned long address, pud_t *pudp, pud_t pud, + unsigned int flags, unsigned long *page_mask) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; + if (unlikely(pud_bad(pud))) + return no_page_table(vma, flags, address); + pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) @@ -953,18 +952,23 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, pud = pudp_get(pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); - if (pud_leaf(pud)) { - ptl = pud_lock(mm, pudp); - page = follow_huge_pud(vma, address, pudp, flags, page_mask); + if (!pud_leaf(pud)) + return follow_pmd_mask(vma, address, pudp, pud, flags, page_mask); + + ptl = pud_lock(mm, pudp); + pud = *pudp; + if (unlikely(!pud_present(pud))) { spin_unlock(ptl); - if (page) - return page; return no_page_table(vma, flags, address); } - if (unlikely(pud_bad(pud))) - return no_page_table(vma, flags, address); + if (unlikely(!pud_leaf(pud))) { + spin_unlock(ptl); + return follow_pmd_mask(vma, address, pudp, pud, flags, page_mask); + } - return follow_pmd_mask(vma, address, pudp, flags, page_mask); + page = follow_huge_pud(vma, address, pudp, flags, page_mask); + spin_unlock(ptl); + return page; } static struct page *follow_p4d_mask(struct vm_area_struct *vma, -- 2.43.0