Re: [PATCH v3 13/15] mm,hwpoison: Refactor soft_offline_huge_page and __soft_offline_page

[Naresh Kamboju]

On Wed, 24 Jun 2020 at 20:32, <nao.horiguchi@xxxxxxxxx> wrote:
>
> From: Oscar Salvador <osalvador@xxxxxxx>
>
> Merging soft_offline_huge_page and __soft_offline_page let us get rid of
> quite some duplicated code, and makes the code much easier to follow.
>
> Now, __soft_offline_page will handle both normal and hugetlb pages.
>
> Note that move put_page() block to the beginning of page_handle_poison()
> with drain_all_pages() in order to make sure that the target page is
> freed and sent into free list to make take_page_off_buddy() work properly.
>
> Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>
> Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
> ---
> ChangeLog v2 -> v3:
> - use page_is_file_lru() instead of page_is_file_cache(),
> - add description about put_page() and drain_all_pages().
> - fix coding style warnings by checkpatch.pl
> ---
>  mm/memory-failure.c | 185 ++++++++++++++++++++------------------------
>  1 file changed, 86 insertions(+), 99 deletions(-)
>
> diff --git v5.8-rc1-mmots-2020-06-20-21-44/mm/memory-failure.c v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/memory-failure.c
> index f744eb90c15c..22c904f6d17a 100644
> --- v5.8-rc1-mmots-2020-06-20-21-44/mm/memory-failure.c
> +++ v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/memory-failure.c
> @@ -78,14 +78,36 @@ EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
>  EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
>  EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);
>
> -static void page_handle_poison(struct page *page, bool release)
> +static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
>  {
> +       if (release) {
> +               put_page(page);
> +               drain_all_pages(page_zone(page));
> +       }
> +
> +       if (hugepage_or_freepage) {
> +               /*
> +                * Doing this check for free pages is also fine since dissolve_free_huge_page
> +                * returns 0 for non-hugetlb pages as well.
> +                */
> +               if (dissolve_free_huge_page(page) || !take_page_off_buddy(page))
> +               /*
> +                * The hugetlb page can end up being enqueued back into
> +                * the freelists by means of:
> +                * unmap_and_move_huge_page
> +                *  putback_active_hugepage
> +                *   put_page->free_huge_page
> +                *    enqueue_huge_page
> +                * If this happens, we might lose the race against an allocation.
> +                */
> +                       return false;
> +       }
>
>         SetPageHWPoison(page);
> -       if (release)
> -               put_page(page);
>         page_ref_inc(page);
>         num_poisoned_pages_inc();
> +
> +       return true;
>  }
>
>  static int hwpoison_filter_dev(struct page *p)
> @@ -1718,63 +1740,52 @@ static int get_any_page(struct page *page, unsigned long pfn)
>         return ret;
>  }
>
> -static int soft_offline_huge_page(struct page *page)
> +static bool isolate_page(struct page *page, struct list_head *pagelist)
>  {
> -       int ret;
> -       unsigned long pfn = page_to_pfn(page);
> -       struct page *hpage = compound_head(page);
> -       LIST_HEAD(pagelist);
> +       bool isolated = false;
> +       bool lru = PageLRU(page);
> +
> +       if (PageHuge(page)) {
> +               isolated = isolate_huge_page(page, pagelist);
> +       } else {
> +               if (lru)
> +                       isolated = !isolate_lru_page(page);
> +               else
> +                       isolated = !isolate_movable_page(page, ISOLATE_UNEVICTABLE);
> +
> +               if (isolated)
> +                       list_add(&page->lru, pagelist);
>
> -       /*
> -        * This double-check of PageHWPoison is to avoid the race with
> -        * memory_failure(). See also comment in __soft_offline_page().
> -        */
> -       lock_page(hpage);
> -       if (PageHWPoison(hpage)) {
> -               unlock_page(hpage);
> -               put_page(hpage);
> -               pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
> -               return -EBUSY;
>         }
> -       unlock_page(hpage);
>
> -       ret = isolate_huge_page(hpage, &pagelist);
> +       if (isolated && lru)
> +               inc_node_page_state(page, NR_ISOLATED_ANON +
> +                                   page_is_file_lru(page));
> +
>         /*
> -        * get_any_page() and isolate_huge_page() takes a refcount each,
> -        * so need to drop one here.
> +        * If we succeed to isolate the page, we grabbed another refcount on
> +        * the page, so we can safely drop the one we got from get_any_pages().
> +        * If we failed to isolate the page, it means that we cannot go further
> +        * and we will return an error, so drop the reference we got from
> +        * get_any_pages() as well.
>          */
> -       put_page(hpage);
> -       if (!ret) {
> -               pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
> -               return -EBUSY;
> -       }
> -
> -       ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
> -                               MIGRATE_SYNC, MR_MEMORY_FAILURE);
> -       if (ret) {
> -               pr_info("soft offline: %#lx: hugepage migration failed %d, type %lx (%pGp)\n",
> -                       pfn, ret, page->flags, &page->flags);
> -               if (!list_empty(&pagelist))
> -                       putback_movable_pages(&pagelist);
> -               if (ret > 0)
> -                       ret = -EIO;
> -       } else {
> -               /*
> -                * We set PG_hwpoison only when we were able to take the page
> -                * off the buddy.
> -                */
> -               if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
> -                       page_handle_poison(page, false);
> -               else
> -                       ret = -EBUSY;
> -       }
> -       return ret;
> +       put_page(page);
> +       return isolated;
>  }
>
> +/*
> + * __soft_offline_page handles hugetlb-pages and non-hugetlb pages.
> + * If the page is a non-dirty unmapped page-cache page, it simply invalidates.
> + * If the page is mapped, it migrates the contents over.
> + */
>  static int __soft_offline_page(struct page *page)
>  {
> -       int ret;
> +       int ret = 0;
>         unsigned long pfn = page_to_pfn(page);
> +       struct page *hpage = compound_head(page);
> +       const char *msg_page[] = {"page", "hugepage"};
> +       bool huge = PageHuge(page);
> +       LIST_HEAD(pagelist);
>
>         /*
>          * Check PageHWPoison again inside page lock because PageHWPoison
> @@ -1783,98 +1794,74 @@ static int __soft_offline_page(struct page *page)
>          * so there's no race between soft_offline_page() and memory_failure().
>          */
>         lock_page(page);
> -       wait_on_page_writeback(page);
> +       if (!PageHuge(page))
> +               wait_on_page_writeback(page);
>         if (PageHWPoison(page)) {
>                 unlock_page(page);
>                 put_page(page);
>                 pr_info("soft offline: %#lx page already poisoned\n", pfn);
>                 return -EBUSY;
>         }
> -       /*
> -        * Try to invalidate first. This should work for
> -        * non dirty unmapped page cache pages.
> -        */
> -       ret = invalidate_inode_page(page);
> +
> +       if (!PageHuge(page))
> +               /*
> +                * Try to invalidate first. This should work for
> +                * non dirty unmapped page cache pages.
> +                */
> +               ret = invalidate_inode_page(page);
>         unlock_page(page);
> +
>         /*
>          * RED-PEN would be better to keep it isolated here, but we
>          * would need to fix isolation locking first.
>          */
> -       if (ret == 1) {
> +       if (ret) {
>                 pr_info("soft_offline: %#lx: invalidated\n", pfn);
> -               page_handle_poison(page, true);
> +               page_handle_poison(page, false, true);

arm64 build failed on linux-next 20200626 tag

make -sk KBUILD_BUILD_USER=TuxBuild -C/linux -j16 ARCH=arm64
CROSS_COMPILE=aarch64-linux-gnu- HOSTCC=gcc CC="sccache
aarch64-linux-gnu-gcc" O=build Image
79 #
80 ../mm/memory-failure.c: In function â__soft_offline_pageâ:
81 ../mm/memory-failure.c:1827:3: error: implicit declaration of
function âpage_handle_poisonâ; did you mean âpage_init_poisonâ?
[-Werror=implicit-function-declaration]
82  1827 | page_handle_poison(page, false, true);
83  | ^~~~~~~~~~~~~~~~~~
84  | page_init_poison


-- 
Linaro LKFT
https://lkft.linaro.org