mm: soft-offline: fix num_poisoned_pages counting on concurrent events

[ Upstream commit 602498f9aa43d4951eece3fd6ad95a6d0a78d537 ]

If multiple soft offline events hit one free page/hugepage concurrently,
soft_offline_page() can handle the free page/hugepage multiple times,
which makes num_poisoned_pages counter increased more than once.  This
patch fixes this wrong counting by checking TestSetPageHWPoison for normal
papes and by checking the return value of dequeue_hwpoisoned_huge_page()
for hugepages.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Dean Nelson <dnelson@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: <stable@vger.kernel.org>	[3.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f098ae8a519aa6c2620964c1415ebdf89ebc3bbc..22f047fbaa336685123a33f5c220544a1b945552 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1733,12 +1733,12 @@ int soft_offline_page(struct page *page, int flags)
        } else if (ret == 0) { /* for free pages */
                if (PageHuge(page)) {
                        set_page_hwpoison_huge_page(hpage);
-                       dequeue_hwpoisoned_huge_page(hpage);
-                       atomic_long_add(1 << compound_order(hpage),
+                       if (!dequeue_hwpoisoned_huge_page(hpage))
+                               atomic_long_add(1 << compound_order(hpage),
                                        &num_poisoned_pages);
                } else {
-                       SetPageHWPoison(page);
-                       atomic_long_inc(&num_poisoned_pages);
+                       if (!TestSetPageHWPoison(page))
+                               atomic_long_inc(&num_poisoned_pages);
                }
        }
        unset_migratetype_isolate(page, MIGRATE_MOVABLE);