Re: [PATCH v18 5/9] mm: hugetlb: set the PageHWPoison to the raw error page

[Michal Hocko <mhocko@suse.com>]

On Mon 08-03-21 18:28:03, Muchun Song wrote:
> Because we reuse the first tail vmemmap page frame and remap it
> with read-only, we cannot set the PageHWPosion on some tail pages.
> So we can use the head[4].private (There are at least 128 struct
> page structures associated with the optimized HugeTLB page, so
> using head[4].private is safe) to record the real error page index
> and set the raw error page PageHWPoison later.

Can we have more poisoned tail pages? Also who does consume that index
and set the HWPoison on the proper tail page?
 
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> Reviewed-by: Oscar Salvador <osalvador@suse.de>
> Acked-by: David Rientjes <rientjes@google.com>
> Tested-by: Chen Huang <chenhuang5@huawei.com>
> Tested-by: Bodeddula Balasubramaniam <bodeddub@amazon.com>
> ---
>  mm/hugetlb.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++++------
>  1 file changed, 72 insertions(+), 8 deletions(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 377e0c1b283f..c0c1b7635ca9 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1304,6 +1304,74 @@ static inline void destroy_compound_gigantic_page(struct page *page,
>  						unsigned int order) { }
>  #endif
>  
> +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
> +static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
> +{
> +	struct page *page;
> +
> +	if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
> +		return;
> +
> +	page = head + page_private(head + 4);
> +
> +	/*
> +	 * Move PageHWPoison flag from head page to the raw error page,
> +	 * which makes any subpages rather than the error page reusable.
> +	 */
> +	if (page != head) {
> +		SetPageHWPoison(page);
> +		ClearPageHWPoison(head);
> +	}
> +}
> +
> +static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
> +					struct page *page)
> +{
> +	if (!PageHWPoison(head))
> +		return;
> +
> +	if (free_vmemmap_pages_per_hpage(h)) {
> +		set_page_private(head + 4, page - head);
> +	} else if (page != head) {
> +		/*
> +		 * Move PageHWPoison flag from head page to the raw error page,
> +		 * which makes any subpages rather than the error page reusable.
> +		 */
> +		SetPageHWPoison(page);
> +		ClearPageHWPoison(head);
> +	}
> +}
> +
> +static inline void hwpoison_subpage_clear(struct hstate *h, struct page *head)
> +{
> +	if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
> +		return;
> +
> +	set_page_private(head + 4, 0);
> +}
> +#else
> +static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
> +{
> +}
> +
> +static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
> +					struct page *page)
> +{
> +	if (PageHWPoison(head) && page != head) {
> +		/*
> +		 * Move PageHWPoison flag from head page to the raw error page,
> +		 * which makes any subpages rather than the error page reusable.
> +		 */
> +		SetPageHWPoison(page);
> +		ClearPageHWPoison(head);
> +	}
> +}
> +
> +static inline void hwpoison_subpage_clear(struct hstate *h, struct page *head)
> +{
> +}
> +#endif
> +
>  static int update_and_free_page(struct hstate *h, struct page *page)
>  	__releases(&hugetlb_lock) __acquires(&hugetlb_lock)
>  {
> @@ -1357,6 +1425,8 @@ static int update_and_free_page(struct hstate *h, struct page *page)
>  		return -ENOMEM;
>  	}
>  
> +	hwpoison_subpage_deliver(h, 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 |
> @@ -1801,14 +1871,7 @@ int dissolve_free_huge_page(struct page *page)
>  			goto retry;
>  		}
>  
> -		/*
> -		 * Move PageHWPoison flag from head page to the raw error page,
> -		 * which makes any subpages rather than the error page reusable.
> -		 */
> -		if (PageHWPoison(head) && page != head) {
> -			SetPageHWPoison(page);
> -			ClearPageHWPoison(head);
> -		}
> +		hwpoison_subpage_set(h, head, page);
>  		list_del(&head->lru);
>  		h->free_huge_pages--;
>  		h->free_huge_pages_node[nid]--;
> @@ -1818,6 +1881,7 @@ int dissolve_free_huge_page(struct page *page)
>  			h->surplus_huge_pages--;
>  			h->surplus_huge_pages_node[nid]--;
>  			h->max_huge_pages++;
> +			hwpoison_subpage_clear(h, head);
>  		}
>  	}
>  out:
> -- 
> 2.11.0
> 

-- 
Michal Hocko
SUSE Labs