[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9832f588-7d1b-edc2-2f20-da1990a8ab03@oracle.com>
Date: Thu, 12 May 2022 22:31:42 +0000
From: Jane Chu <jane.chu@...cle.com>
To: Naoya Horiguchi <naoya.horiguchi@...ux.dev>,
"linux-mm@...ck.org" <linux-mm@...ck.org>
CC: Andrew Morton <akpm@...ux-foundation.org>,
Miaohe Lin <linmiaohe@...wei.com>,
David Hildenbrand <david@...hat.com>,
Mike Kravetz <mike.kravetz@...cle.com>,
Yang Shi <shy828301@...il.com>,
Oscar Salvador <osalvador@...e.de>,
Muchun Song <songmuchun@...edance.com>,
Naoya Horiguchi <naoya.horiguchi@....com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH v1 1/4] mm, hwpoison, hugetlb: introduce
SUBPAGE_INDEX_HWPOISON to save raw error page
On 4/26/2022 9:28 PM, Naoya Horiguchi wrote:
> From: Naoya Horiguchi <naoya.horiguchi@....com>
>
> When handling memory error on a hugetlb page, the error handler tries to
> dissolve and turn it into 4kB pages. If it's successfully dissolved,
> PageHWPoison flag is moved to the raw error page, so but that's all
> right. However, dissolve sometimes fails, then the error page is left
> as hwpoisoned hugepage. It's useful if we can retry to dissolve it to
> save healthy pages, but that's not possible now because the information
> about where the raw error page is lost.
>
> Use the private field of a tail page to keep that information. The code
> path of shrinking hugepage pool used this info to try delayed dissolve.
>
> Signed-off-by: Naoya Horiguchi <naoya.horiguchi@....com>
> ---
> include/linux/hugetlb.h | 24 ++++++++++++++++++++++++
> mm/hugetlb.c | 9 +++++++++
> mm/memory-failure.c | 2 ++
> 3 files changed, 35 insertions(+)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index ac2a1d758a80..689e69cb556b 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -42,6 +42,9 @@ enum {
> SUBPAGE_INDEX_CGROUP, /* reuse page->private */
> SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */
> __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
> +#endif
> +#ifdef CONFIG_CGROUP_HUGETLB
> + SUBPAGE_INDEX_HWPOISON,
> #endif
> __NR_USED_SUBPAGE,
> };
> @@ -784,6 +787,27 @@ extern int dissolve_free_huge_page(struct page *page);
> extern int dissolve_free_huge_pages(unsigned long start_pfn,
> unsigned long end_pfn);
>
> +#ifdef CONFIG_MEMORY_FAILURE
> +/*
> + * pointer to raw error page is located in hpage[SUBPAGE_INDEX_HWPOISON].private
> + */
> +static inline struct page *hugetlb_page_hwpoison(struct page *hpage)
> +{
> + return (void *)page_private(hpage + SUBPAGE_INDEX_HWPOISON);
> +}
> +
> +static inline void hugetlb_set_page_hwpoison(struct page *hpage,
> + struct page *page)
> +{
> + set_page_private(hpage + SUBPAGE_INDEX_HWPOISON, (unsigned long)page);
> +}
What happens if the ->private field is already holding a poisoned page
pointer? that is, in a scenario of multiple poisoned pages within a
hugepage, what to do? mark the entire hpage poisoned?
thanks,
-jane
> +#else
> +static inline struct page *hugetlb_page_hwpoison(struct page *hpage)
> +{
> + return NULL;
> +}
> +#endif
> +
> #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
> #ifndef arch_hugetlb_migration_supported
> static inline bool arch_hugetlb_migration_supported(struct hstate *h)
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index f8e048b939c7..6867ea8345d1 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1547,6 +1547,15 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
> return;
> }
>
> + if (unlikely(PageHWPoison(page))) {
> + struct page *raw_error = hugetlb_page_hwpoison(page);
> +
> + if (raw_error && raw_error != page) {
> + SetPageHWPoison(raw_error);
> + ClearPageHWPoison(page);
> + }
> + }
> +
> for (i = 0; i < pages_per_huge_page(h);
> i++, subpage = mem_map_next(subpage, page, i)) {
> subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 3e36fc19c4d1..73948a00ad4a 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1535,6 +1535,8 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
> goto out;
> }
>
> + hugetlb_set_page_hwpoison(head, page);
> +
> return ret;
> out:
> if (count_increased)
Powered by blists - more mailing lists