Ignore madvise(MADV_WILLNEED) for hugetlbfs-backed regions

madvise(MADV_WILLNEED) forces page cache readahead on a range of memory
backed by a file.  The assumption is made that the page required is
order-0 and "normal" page cache.

On hugetlbfs, this assumption is not true and order-0 pages are
allocated and inserted into the hugetlbfs page cache.  This leaks
hugetlbfs page reservations and can cause BUGs to trigger related to
corrupted page tables.

This patch causes MADV_WILLNEED to be ignored for hugetlbfs-backed
regions.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/madvise.c b/mm/madvise.c
index b9ce574..36d6ea2 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -112,6 +112,14 @@ static long madvise_willneed(struct vm_area_struct * vma,
        if (!file)
                return -EBADF;
 
+       /*
+        * Page cache readahead assumes page cache pages are order-0 which
+        * is not the case for hugetlbfs. Do not give a bad return value
+        * but ignore the advice.
+        */
+       if (vma->vm_flags & VM_HUGETLB)
+               return 0;
+
        if (file->f_mapping->a_ops->get_xip_mem) {
                /* no bad return value, but ignore advice */
                return 0;