mm, hwpoison: set PG_hwpoison for busy hugetlb pages

If memory_failure() fails to grab page refcount on a hugetlb page because
it's busy, it returns without setting PG_hwpoison on it.  This not only
loses a chance of error containment, but breaks the rule that
action_result() should be called only when memory_failure() do any of
handling work (even if that's just setting PG_hwpoison).  This
inconsistency could harm code maintainability.

So set PG_hwpoison and call hugetlb_set_page_hwpoison() for such a case.

Link: https://lkml.kernel.org/r/20220714042420.1847125-6-naoya.horiguchi@linux.dev
Fixes: 405ce051236c ("mm/hwpoison: fix race between hugetlb free/demotion and memory_failure_hugetlb()")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index e6e201a..0345b8c 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3176,6 +3176,7 @@ enum mf_flags {
        MF_SOFT_OFFLINE = 1 << 3,
        MF_UNPOISON = 1 << 4,
        MF_SW_SIMULATED = 1 << 5,
+       MF_NO_RETRY = 1 << 6,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
                      unsigned long count, int mf_flags);

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e30dbec..a748f5d 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1800,7 +1800,8 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
                        count_increased = true;
        } else {
                ret = -EBUSY;
-               goto out;
+               if (!(flags & MF_NO_RETRY))
+                       goto out;
        }
 
        if (hugetlb_set_page_hwpoison(head, page)) {
@@ -1827,7 +1828,6 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
        struct page *p = pfn_to_page(pfn);
        struct page *head;
        unsigned long page_flags;
-       bool retry = true;
 
        *hugetlb = 1;
 retry:
@@ -1843,8 +1843,8 @@ retry:
                }
                return res;
        } else if (res == -EBUSY) {
-               if (retry) {
-                       retry = false;
+               if (!(flags & MF_NO_RETRY)) {
+                       flags |= MF_NO_RETRY;
                        goto retry;
                }
                action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);