From: Yu Zhao <yuzhao@xxxxxxxxxx> Subject: mm/gup: fix gup_pmd_range() for dax For dax pmd, pmd_trans_huge() returns false but pmd_huge() returns true on x86. So the function works as long as hugetlb is configured. However, dax doesn't depend on hugetlb. Link: http://lkml.kernel.org/r/20190111034033.601-1-yuzhao@xxxxxxxxxx Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx> Reviewed-by: Jan Kara <jack@xxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Huang Ying <ying.huang@xxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Keith Busch <keith.busch@xxxxxxxxx> Cc: "Michael S . Tsirkin" <mst@xxxxxxxxxx> Cc: John Hubbard <jhubbard@xxxxxxxxxx> Cc: Wei Yang <richard.weiyang@xxxxxxxxx> Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: "Kirill A . Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/gup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/mm/gup.c~mm-gup-fix-gup_pmd_range-for-dax +++ a/mm/gup.c @@ -1674,7 +1674,8 @@ static int gup_pmd_range(pud_t pud, unsi if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they _