mm/hwpoison: fix traversal of hugetlbfs pages to avoid printk flood

madvise_hwpoison won't check if the page is small page or huge page and
traverses in small page granularity against the range unconditionally,
which result in a printk flood "MCE xxx: already hardware poisoned" if
the page is a huge page.

This patch fixes it by using compound_order(compound_head(page)) for
huge page iterator.

Testcase:

#define _GNU_SOURCE
#include <stdlib.h>
#include <stdio.h>
#include <sys/mman.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <errno.h>

#define PAGES_TO_TEST 3
#define PAGE_SIZE	4096 * 512

int main(void)
{
	char *mem;
	int i;

	mem = mmap(NULL, PAGES_TO_TEST * PAGE_SIZE,
			PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, 0, 0);

	if (madvise(mem, PAGES_TO_TEST * PAGE_SIZE, MADV_HWPOISON) == -1)
		return -1;

	munmap(mem, PAGES_TO_TEST * PAGE_SIZE);

	return 0;
}

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/madvise.c b/mm/madvise.c
index 6975bc812542d2c13642363d928005f355199c54..539eeb96b323bf649f83783e0dddcb4f907e1d6e 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -343,10 +343,11 @@ static long madvise_remove(struct vm_area_struct *vma,
  */
 static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 {
+       struct page *p;
        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;
-       for (; start < end; start += PAGE_SIZE) {
-               struct page *p;
+       for (; start < end; start += PAGE_SIZE <<
+                               compound_order(compound_head(p))) {
                int ret;
 
                ret = get_user_pages_fast(start, 1, 0, &p);