On Fri, Mar 11, 2022 at 11:47 PM Miaohe Lin <linmiaohe@xxxxxxxxxx> wrote:
>
> We can not really handle non-LRU movable pages in memory failure. Typically
> they are balloon, zsmalloc, etc. Assuming we run into a base (4K) non-LRU
> movable page, we could reach as far as identify_page_state(), it should not
> fall into any category except me_unknown. For the non-LRU compound movable
> pages, they could be taken for transhuge pages but it's unexpected to split
> non-LRU movable pages using split_huge_page_to_list in memory_failure. So
> we could just simply make non-LRU movable pages unhandlable to avoid these
> possible nasty cases.
>
> Suggested-by: Yang Shi <shy828301@xxxxxxxxx>
> Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
> ---
> mm/memory-failure.c | 20 +++++++++++++-------
> 1 file changed, 13 insertions(+), 7 deletions(-)
>
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 2ff7dd2078c4..ba621c6823ed 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1177,12 +1177,18 @@ void ClearPageHWPoisonTakenOff(struct page *page)
> * does not return true for hugetlb or device memory pages, so it's assumed
> * to be called only in the context where we never have such pages.
> */
> -static inline bool HWPoisonHandlable(struct page *page)
> +static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
> {
> - return PageLRU(page) || __PageMovable(page) || is_free_buddy_page(page);
> + bool movable = false;
> +
> + /* Soft offline could mirgate non-LRU movable pages */
> + if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
> + movable = true;
> +
> + return movable || PageLRU(page) || is_free_buddy_page(page);
> }
>
> -static int __get_hwpoison_page(struct page *page)
> +static int __get_hwpoison_page(struct page *page, unsigned long flags)
> {
> struct page *head = compound_head(page);
> int ret = 0;
> @@ -1197,7 +1203,7 @@ static int __get_hwpoison_page(struct page *page)
> * for any unsupported type of page in order to reduce the risk of
> * unexpected races caused by taking a page refcount.
> */
> - if (!HWPoisonHandlable(head))
> + if (!HWPoisonHandlable(head, flags))
> return -EBUSY;
>
> if (get_page_unless_zero(head)) {
> @@ -1222,7 +1228,7 @@ static int get_any_page(struct page *p, unsigned long flags)
>
> try_again:
> if (!count_increased) {
> - ret = __get_hwpoison_page(p);
> + ret = __get_hwpoison_page(p, flags);
> if (!ret) {
> if (page_count(p)) {
> /* We raced with an allocation, retry. */
> @@ -1250,7 +1256,7 @@ static int get_any_page(struct page *p, unsigned long flags)
> }
> }
>
> - if (PageHuge(p) || HWPoisonHandlable(p)) {
> + if (PageHuge(p) || HWPoisonHandlable(p, flags)) {
> ret = 1;
> } else {
> /*
> @@ -2308,7 +2314,7 @@ int soft_offline_page(unsigned long pfn, int flags)
>
> retry:
> get_online_mems();
> - ret = get_hwpoison_page(page, flags);
> + ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE);
> put_online_mems();
>
> if (ret > 0) {
> --
> 2.23.0
>
