s390/hugetlb: fix prepare_hugepage_range() check for 2 GB hugepages
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: d08de8e2d8
("s390/mm: add support for 2GB hugepages")
Cc: <stable@vger.kernel.org> # 4.8+
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
This commit is contained in:
parent
bdbf57bca6
commit
7c8d42fdf1
|
@ -28,9 +28,11 @@ pte_t huge_ptep_get_and_clear(struct mm_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;
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue