From 1a3798dececa8cb26b9eee26840195ccc1a4d6c1 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 24 May 2024 15:53:06 -0600 Subject: mm/memory-failure: send SIGBUS in the event of thp split fail While handling hwpoison in a THP page, it is possible that try_to_split_thp_page() fails. For example, when the THP page has been RDMA pinned. At this point, the kernel cannot isolate the poisoned THP page, all it could do is to send a SIGBUS to the user process with meaningful payload to give user-level recovery a chance. Link: https://lkml.kernel.org/r/20240524215306.2705454-6-jane.chu@oracle.com Signed-off-by: Jane Chu Reviewed-by: Oscar Salvador Acked-by: Miaohe Lin Cc: Naoya Horiguchi Cc: Oscar Salvador Signed-off-by: Andrew Morton --- mm/memory-failure.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7e568838fb32..fc9ce331eb16 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1706,7 +1706,12 @@ static int identify_page_state(unsigned long pfn, struct page *p, return page_action(ps, p, pfn); } -static int try_to_split_thp_page(struct page *page) +/* + * When 'release' is 'false', it means that if thp split has failed, + * there is still more to do, hence the page refcount we took earlier + * is still needed. + */ +static int try_to_split_thp_page(struct page *page, bool release) { int ret; @@ -1714,7 +1719,7 @@ static int try_to_split_thp_page(struct page *page) ret = split_huge_page(page); unlock_page(page); - if (unlikely(ret)) + if (ret && release) put_page(page); return ret; @@ -2186,6 +2191,22 @@ out: return rc; } +/* + * The calling condition is as such: thp split failed, page might have + * been RDMA pinned, not much can be done for recovery. + * But a SIGBUS should be delivered with vaddr provided so that the user + * application has a chance to recover. Also, application processes' + * election for MCE early killed will be honored. + */ +static void kill_procs_now(struct page *p, unsigned long pfn, int flags, + struct folio *folio) +{ + LIST_HEAD(tokill); + + collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); + kill_procs(&tokill, true, pfn, flags); +} + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -2327,8 +2348,11 @@ try_again: * page is a valid handlable page. */ folio_set_has_hwpoisoned(folio); - if (try_to_split_thp_page(p) < 0) { - res = action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); + if (try_to_split_thp_page(p, false) < 0) { + res = -EHWPOISON; + kill_procs_now(p, pfn, flags, folio); + put_page(p); + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_FAILED); goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); @@ -2709,7 +2733,7 @@ static int soft_offline_in_use_page(struct page *page) }; if (!huge && folio_test_large(folio)) { - if (try_to_split_thp_page(page)) { + if (try_to_split_thp_page(page, true)) { pr_info("soft offline: %#lx: thp split failed\n", pfn); return -EBUSY; } -- cgit v1.2.3