mm, hugetlb: close race when setting PageTail for gigantic pages

Now that gigantic pages are dynamically allocatable, care must be taken to
ensure that p->first_page is valid before setting PageTail.

If this isn't done, then it is possible to race and have compound_head()
return NULL.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a9ac6c268325a6ca9096bfc784cfbf68ac6a65e..c41b2a0ee2736e4f7df74c440ceb90bd5fcceecb 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -917,7 +917,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
        __SetPageHead(page);
        __ClearPageReserved(page);
        for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-               __SetPageTail(p);
                /*
                 * For gigantic hugepages allocated through bootmem at
                 * boot, it's safer to be consistent with the not-gigantic
@@ -933,6 +932,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
                __ClearPageReserved(p);
                set_page_count(p, 0);
                p->first_page = page;
+               /* Make sure p->first_page is always valid for PageTail() */
+               smp_wmb();
+               __SetPageTail(p);
        }
 }