From 510d25c92ec4ace4199a94f2f0cc9b8208c0de57 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 30 Jun 2021 18:48:38 -0700 Subject: mm/hwpoison: disable pcp for page_handle_poison() Recent changes by patch "mm/page_alloc: allow high-order pages to be stored on the per-cpu lists" makes kernels determine whether to use pcp by pcp_allowed_order(), which breaks soft-offline for hugetlb pages. Soft-offline dissolves a migration source page, then removes it from buddy free list, so it's assumed that any subpage of the soft-offlined hugepage are recognized as a buddy page just after returning from dissolve_free_huge_page(). pcp_allowed_order() returns true for hugetlb, so this assumption is no longer true. So disable pcp during dissolve_free_huge_page() and take_page_off_buddy() to prevent soft-offlined hugepages from linking to pcp lists. Soft-offline should not be common events so the impact on performance should be minimal. And I think that the optimization of Mel's patch could benefit to hugetlb so zone_pcp_disable() is called only in hwpoison context. Link: https://lkml.kernel.org/r/20210617092626.291006-1-nao.horiguchi@gmail.com Signed-off-by: Naoya Horiguchi Acked-by: Mel Gorman Cc: Mike Kravetz Cc: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e5a1531f7f4e..9d2d31ffe8a4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -66,6 +66,19 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +static bool __page_handle_poison(struct page *page) +{ + bool ret; + + zone_pcp_disable(page_zone(page)); + ret = dissolve_free_huge_page(page); + if (!ret) + ret = take_page_off_buddy(page); + zone_pcp_enable(page_zone(page)); + + return ret; +} + static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) { if (hugepage_or_freepage) { @@ -73,7 +86,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo * 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)) + if (!__page_handle_poison(page)) /* * We could fail to take off the target page from buddy * for example due to racy page allocation, but that's @@ -985,7 +998,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) */ if (PageAnon(hpage)) put_page(hpage); - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; } @@ -1446,7 +1459,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) } unlock_page(head); res = MF_FAILED; - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; } -- cgit