From: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx> commit 7c8d42fdf1a84b1a0dd60d6528309c8ec127e87c upstream. The alignment check in prepare_hugepage_range() is wrong for 2 GB hugepages, it only checks for 1 MB hugepage alignment. This can result in kernel crash in __unmap_hugepage_range() at the BUG_ON(start & ~huge_page_mask(h)) alignment check, for mappings created with MAP_FIXED at unaligned address. Fix this by correctly handling multiple hugepage sizes, similar to the generic version of prepare_hugepage_range(). Fixes: d08de8e2d867 ("s390/mm: add support for 2GB hugepages") Cc: <stable@xxxxxxxxxxxxxxx> # 4.8+ Acked-by: Alexander Gordeev <agordeev@xxxxxxxxxxxxx> Signed-off-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx> Signed-off-by: Vasily Gorbik <gor@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/s390/include/asm/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -28,9 +28,11 @@ pte_t huge_ptep_get_and_clear(struct mm_ static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; }