The conversion to move pfn_to_online_page() internal to
soft_offline_page() missed that the get_user_pages() reference taken by
the madvise() path needs to be dropped when pfn_to_online_page() fails.
Note the direct sysfs-path to soft_offline_page() does not perform a
get_user_pages() lookup.
When soft_offline_page() is handed a pfn_valid() &&
!pfn_to_online_page() pfn the kernel hangs at dax-device shutdown due to
a leaked reference.
Fixes: feec24a6139d ("mm, soft-offline: convert parameter to pfn")
Cc: Andrew Morton <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Michal Hocko <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Cc: <[email protected]>
Signed-off-by: Dan Williams <[email protected]>
---
mm/memory-failure.c | 20 ++++++++++++++++----
1 file changed, 16 insertions(+), 4 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5a38e9eade94..78b173c7190c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1885,6 +1885,12 @@ static int soft_offline_free_page(struct page *page)
return rc;
}
+static void put_ref_page(struct page *page)
+{
+ if (page)
+ put_page(page);
+}
+
/**
* soft_offline_page - Soft offline a page.
* @pfn: pfn to soft-offline
@@ -1910,20 +1916,26 @@ static int soft_offline_free_page(struct page *page)
int soft_offline_page(unsigned long pfn, int flags)
{
int ret;
- struct page *page;
bool try_again = true;
+ struct page *page, *ref_page = NULL;
+
+ WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED));
if (!pfn_valid(pfn))
return -ENXIO;
+ if (flags & MF_COUNT_INCREASED)
+ ref_page = pfn_to_page(pfn);
+
/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
page = pfn_to_online_page(pfn);
- if (!page)
+ if (!page) {
+ put_ref_page(ref_page);
return -EIO;
+ }
if (PageHWPoison(page)) {
pr_info("%s: %#lx page already poisoned\n", __func__, pfn);
- if (flags & MF_COUNT_INCREASED)
- put_page(page);
+ put_ref_page(ref_page);
return 0;
}