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 <[email protected]> Cc: [email protected] Signed-off-by: Linus Torvalds <[email protected]>
akeromi · May 5, 2009 · a425a63 · a425a63
1 parent 99ee129
commit a425a63
Showing 1 changed file with 8 additions and 0 deletions.
diff --git 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;