From 1439f94c548919ab6b7720b70b951461f1fcb16d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 29 May 2019 07:12:37 -0700 Subject: treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 263 Based on 1 normalized pattern(s): this software may be redistributed and or modified under the terms of the gnu general public license gpl version 2 only as published by the free software foundation extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 1 file(s). Signed-off-by: Thomas Gleixner Reviewed-by: Richard Fontana Reviewed-by: Alexios Zavras Reviewed-by: Allison Randal Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190529141333.676969322@linutronix.de Signed-off-by: Greg Kroah-Hartman --- mm/memory-failure.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fc8b51744579..8da0334b9ca0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008, 2009 Intel Corporation * Authors: Andi Kleen, Fengguang Wu * - * This software may be redistributed and/or modified under the terms of - * the GNU General Public License ("GPL") version 2 only as published by the - * Free Software Foundation. - * * High level machine check handler. Handles pages reported by the * hardware as being corrupted usually due to a multi-bit ECC memory or cache * failure. -- cgit From b38e5962f8ed0d2a2b28a887fc2221f7f41db119 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 Jun 2019 12:06:53 -0700 Subject: mm: soft-offline: return -EBUSY if set_hwpoison_free_buddy_page() fails The pass/fail of soft offline should be judged by checking whether the raw error page was finally contained or not (i.e. the result of set_hwpoison_free_buddy_page()), but current code do not work like that. It might lead us to misjudge the test result when set_hwpoison_free_buddy_page() fails. Without this fix, there are cases where madvise(MADV_SOFT_OFFLINE) may not offline the original page and will not return an error. Link: http://lkml.kernel.org/r/1560154686-18497-2-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining") Reviewed-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Xishi Qiu Cc: "Chen, Jerry T" Cc: "Zhuo, Qiuxu" Cc: [4.19+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8da0334b9ca0..8ee7b16235ac 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1730,6 +1730,8 @@ static int soft_offline_huge_page(struct page *page, int flags) if (!ret) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); + else + ret = -EBUSY; } } return ret; -- cgit From faf53def3b143df11062d87c12afe6afeb6f8cc7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 Jun 2019 12:06:56 -0700 Subject: mm: hugetlb: soft-offline: dissolve_free_huge_page() return zero on !PageHuge madvise(MADV_SOFT_OFFLINE) often returns -EBUSY when calling soft offline for hugepages with overcommitting enabled. That was caused by the suboptimal code in current soft-offline code. See the following part: ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { ... } else { /* * We set PG_hwpoison only when the migration source hugepage * was successfully dissolved, because otherwise hwpoisoned * hugepage remains on free hugepage list, then userspace will * find it as SIGBUS by allocation failure. That's not expected * in soft-offlining. */ ret = dissolve_free_huge_page(page); if (!ret) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); } } return ret; Here dissolve_free_huge_page() returns -EBUSY if the migration source page was freed into buddy in migrate_pages(), but even in that case we actually has a chance that set_hwpoison_free_buddy_page() succeeds. So that means current code gives up offlining too early now. dissolve_free_huge_page() checks that a given hugepage is suitable for dissolving, where we should return success for !PageHuge() case because the given hugepage is considered as already dissolved. This change also affects other callers of dissolve_free_huge_page(), which are cleaned up together. [n-horiguchi@ah.jp.nec.com: v3] Link: http://lkml.kernel.org/r/1560761476-4651-3-git-send-email-n-horiguchi@ah.jp.nec.comLink: http://lkml.kernel.org/r/1560154686-18497-3-git-send-email-n-horiguchi@ah.jp.nec.com Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining") Signed-off-by: Naoya Horiguchi Reported-by: Chen, Jerry T Tested-by: Chen, Jerry T Reviewed-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Xishi Qiu Cc: "Chen, Jerry T" Cc: "Zhuo, Qiuxu" Cc: [4.19+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 29 ++++++++++++++++++++--------- mm/memory-failure.c | 5 +---- 2 files changed, 21 insertions(+), 13 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ac843d32b019..ede7e7f5d1ab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1510,16 +1510,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, /* * Dissolve a given free hugepage into free buddy pages. This function does - * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the - * dissolution fails because a give page is not a free hugepage, or because - * free hugepages are fully reserved. + * nothing for in-use hugepages and non-hugepages. + * This function returns values like below: + * + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!PageHuge(page)) + return 0; + spin_lock(&hugetlb_lock); - if (PageHuge(page) && !page_count(page)) { + if (!PageHuge(page)) { + rc = 0; + goto out; + } + + if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); @@ -1564,11 +1577,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { page = pfn_to_page(pfn); - if (PageHuge(page) && !page_count(page)) { - rc = dissolve_free_huge_page(page); - if (rc) - break; - } + rc = dissolve_free_huge_page(page); + if (rc) + break; } return rc; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8ee7b16235ac..d9cc6606f409 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1856,11 +1856,8 @@ static int soft_offline_in_use_page(struct page *page, int flags) static int soft_offline_free_page(struct page *page) { - int rc = 0; - struct page *head = compound_head(page); + int rc = dissolve_free_huge_page(page); - if (PageHuge(head)) - rc = dissolve_free_huge_page(page); if (!rc) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); -- cgit