The quilt patch titled Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage has been removed from the -mm tree. Its filename was mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Naoya Horiguchi <naoya.horiguchi@xxxxxxx> Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage Date: Fri, 8 Jul 2022 14:36:49 +0900 Raw error info list needs to be removed when hwpoisoned hugetlb is unpoisoned. And unpoison handler needs to know how many errors there are in the target hugepage. So add them. HPageVmemmapOptimized(hpage) and HPageRawHwpUnreliable(hpage)) can't be unpoisoned, so let's skip them. Link: https://lkml.kernel.org/r/20220708053653.964464-5-naoya.horiguchi@xxxxxxxxx Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx> Reported-by: kernel test robot <lkp@xxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Liu Shixin <liushixin2@xxxxxxxxxx> Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx> Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Cc: Yang Shi <shy828301@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/swapops.h | 9 ++++++ mm/memory-failure.c | 50 +++++++++++++++++++++++++++++++++----- 2 files changed, 53 insertions(+), 6 deletions(-) --- a/include/linux/swapops.h~mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage +++ a/include/linux/swapops.h @@ -490,6 +490,11 @@ static inline void num_poisoned_pages_de atomic_long_dec(&num_poisoned_pages); } +static inline void num_poisoned_pages_sub(long i) +{ + atomic_long_sub(i, &num_poisoned_pages); +} + #else static inline swp_entry_t make_hwpoison_entry(struct page *page) @@ -505,6 +510,10 @@ static inline int is_hwpoison_entry(swp_ static inline void num_poisoned_pages_inc(void) { } + +static inline void num_poisoned_pages_sub(long i) +{ +} #endif static inline int non_swap_entry(swp_entry_t entry) --- a/mm/memory-failure.c~mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage +++ a/mm/memory-failure.c @@ -1720,22 +1720,41 @@ static int hugetlb_set_page_hwpoison(str return ret; } -int hugetlb_clear_page_hwpoison(struct page *hpage) +static long free_raw_hwp_pages(struct page *hpage, bool move_flag) { struct llist_head *head; struct llist_node *t, *tnode; + long count = 0; - if (!HPageRawHwpUnreliable(hpage)) - ClearPageHWPoison(hpage); + /* + * HPageVmemmapOptimized hugepages can't be unpoisoned because + * struct pages for tail pages are required to free hwpoisoned + * hugepages. HPageRawHwpUnreliable hugepages shouldn't be + * unpoisoned by definition. + */ + if (HPageVmemmapOptimized(hpage) || HPageRawHwpUnreliable(hpage)) + return 0; head = raw_hwp_list_head(hpage); llist_for_each_safe(tnode, t, head->first) { struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node); - SetPageHWPoison(p->page); + if (move_flag) + SetPageHWPoison(p->page); kfree(p); + count++; } llist_del_all(head); - return 0; + return count; +} + +int hugetlb_clear_page_hwpoison(struct page *hpage) +{ + int ret = -EBUSY; + + if (!HPageRawHwpUnreliable(hpage)) + ret = !TestClearPageHWPoison(hpage); + free_raw_hwp_pages(hpage, true); + return ret; } /* @@ -1879,6 +1898,10 @@ static inline int try_memory_failure_hug return 0; } +static inline long free_raw_hwp_pages(struct page *hpage, bool move_flag) +{ + return 0; +} #endif /* CONFIG_HUGETLB_PAGE */ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, @@ -2284,6 +2307,7 @@ int unpoison_memory(unsigned long pfn) struct page *p; int ret = -EBUSY; int freeit = 0; + long count = 1; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -2331,6 +2355,13 @@ int unpoison_memory(unsigned long pfn) ret = get_hwpoison_page(p, MF_UNPOISON); if (!ret) { + if (PageHuge(p)) { + count = free_raw_hwp_pages(page, false); + if (count == 0) { + ret = -EBUSY; + goto unlock_mutex; + } + } ret = TestClearPageHWPoison(page) ? 0 : -EBUSY; } else if (ret < 0) { if (ret == -EHWPOISON) { @@ -2339,6 +2370,13 @@ int unpoison_memory(unsigned long pfn) unpoison_pr_info("Unpoison: failed to grab page %#lx\n", pfn, &unpoison_rs); } else { + if (PageHuge(p)) { + count = free_raw_hwp_pages(page, false); + if (count == 0) { + ret = -EBUSY; + goto unlock_mutex; + } + } freeit = !!TestClearPageHWPoison(p); put_page(page); @@ -2351,7 +2389,7 @@ int unpoison_memory(unsigned long pfn) unlock_mutex: mutex_unlock(&mf_mutex); if (!ret || freeit) { - num_poisoned_pages_dec(); + num_poisoned_pages_sub(count); unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", page_to_pfn(p), &unpoison_rs); } _ Patches currently in -mm which might be from naoya.horiguchi@xxxxxxx are mm-hugetlb-separate-path-for-hwpoison-entry-in-copy_hugetlb_page_range.patch mm-hwpoison-set-pg_hwpoison-for-busy-hugetlb-pages.patch mm-hwpoison-make-__page_handle_poison-returns-int.patch mm-hwpoison-skip-raw-hwpoison-page-in-freeing-1gb-hugepage.patch mm-hwpoison-enable-memory-error-handling-on-1gb-hugepage.patch