All of lore.kernel.org
 help / color / mirror / Atom feed
* + mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch added to mm-unstable branch
@ 2022-07-02  4:06 Andrew Morton
  0 siblings, 0 replies; 4+ messages in thread
From: Andrew Morton @ 2022-07-02  4:06 UTC (permalink / raw)
  To: mm-commits, songmuchun, shy828301, osalvador, mike.kravetz,
	liushixin2, linmiaohe, david, naoya.horiguchi, akpm


The patch titled
     Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
has been added to the -mm mm-unstable branch.  Its filename is
     mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
Date: Thu, 30 Jun 2022 11:27:51 +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.

Link: https://lkml.kernel.org/r/20220630022755.3362349-6-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/swapops.h |    9 +++++++++
 mm/memory-failure.c     |   31 +++++++++++++++++++++++++------
 2 files changed, 34 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
@@ -1769,22 +1769,33 @@ static inline int hugetlb_set_page_hwpoi
 	return ret;
 }
 
-inline int hugetlb_clear_page_hwpoison(struct page *hpage)
+static inline 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);
 	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;
+}
+
+inline 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;
 }
 
 /*
@@ -1882,6 +1893,9 @@ static inline int try_memory_failure_hug
 	return 0;
 }
 
+static inline void free_raw_hwp_pages(struct page *hpage, bool move_flag)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
@@ -2287,6 +2301,7 @@ 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);
 
@@ -2334,6 +2349,8 @@ 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);
 		ret = TestClearPageHWPoison(page) ? 0 : -EBUSY;
 	} else if (ret < 0) {
 		if (ret == -EHWPOISON) {
@@ -2342,6 +2359,8 @@ 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);
 		freeit = !!TestClearPageHWPoison(p);
 
 		put_page(page);
@@ -2354,7 +2373,7 @@ 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@nec.com are

mm-hugetlb-check-gigantic_page_runtime_supported-in-return_unused_surplus_pages.patch
mm-hugetlb-separate-path-for-hwpoison-entry-in-copy_hugetlb_page_range.patch
mm-hugetlb-make-pud_huge-and-follow_huge_pud-aware-of-non-present-pud-entry.patch
mm-hwpoison-hugetlb-support-saving-mechanism-of-raw-error-pages.patch
mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.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


^ permalink raw reply	[flat|nested] 4+ messages in thread

* + mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch added to mm-unstable branch
@ 2022-07-17  0:53 Andrew Morton
  0 siblings, 0 replies; 4+ messages in thread
From: Andrew Morton @ 2022-07-17  0:53 UTC (permalink / raw)
  To: mm-commits, songmuchun, shy828301, osalvador, mike.kravetz, lkp,
	liushixin2, linmiaohe, david, naoya.horiguchi, akpm


The patch titled
     Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
has been added to the -mm mm-unstable branch.  Its filename is
     mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
Date: Thu, 14 Jul 2022 13:24:16 +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)) sometimes
can't be unpoisoned, so skip them.

Link: https://lkml.kernel.org/r/20220714042420.1847125-5-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/swapops.h |    9 ++++++
 mm/memory-failure.c     |   52 ++++++++++++++++++++++++++++++++++----
 2 files changed, 56 insertions(+), 5 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
@@ -1680,19 +1680,23 @@ static inline struct llist_head *raw_hwp
 	return (struct llist_head *)&page_private(hpage + SUBPAGE_INDEX_HWPOISON);
 }
 
-static void __free_raw_hwp_pages(struct page *hpage)
+static unsigned long __free_raw_hwp_pages(struct page *hpage, bool move_flag)
 {
 	struct llist_head *head;
 	struct llist_node *t, *tnode;
+	unsigned long count = 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 count;
 }
 
 static int hugetlb_set_page_hwpoison(struct page *hpage, struct page *page)
@@ -1735,17 +1739,36 @@ static int hugetlb_set_page_hwpoison(str
 		 * Once HPageRawHwpUnreliable is set, raw_hwp_page is not
 		 * used any more, so free it.
 		 */
-		__free_raw_hwp_pages(hpage);
+		__free_raw_hwp_pages(hpage, false);
 	}
 	return ret;
 }
 
+static unsigned long free_raw_hwp_pages(struct page *hpage, bool move_flag)
+{
+	/*
+	 * HPageVmemmapOptimized hugepages can't be freed because struct
+	 * pages for tail pages are required but they don't exist.
+	 */
+	if (move_flag && HPageVmemmapOptimized(hpage))
+		return 0;
+
+	/*
+	 * HPageRawHwpUnreliable hugepages shouldn't be unpoisoned by
+	 * definition.
+	 */
+	if (HPageRawHwpUnreliable(hpage))
+		return 0;
+
+	return __free_raw_hwp_pages(hpage, move_flag);
+}
+
 void hugetlb_clear_page_hwpoison(struct page *hpage)
 {
 	if (HPageRawHwpUnreliable(hpage))
 		return;
 	ClearPageHWPoison(hpage);
-	__free_raw_hwp_pages(hpage);
+	free_raw_hwp_pages(hpage, true);
 }
 
 /*
@@ -1889,6 +1912,10 @@ static inline int try_memory_failure_hug
 	return 0;
 }
 
+static inline unsigned long free_raw_hwp_pages(struct page *hpage, bool flag)
+{
+	return 0;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
@@ -2294,6 +2321,7 @@ int unpoison_memory(unsigned long pfn)
 	struct page *p;
 	int ret = -EBUSY;
 	int freeit = 0;
+	unsigned long count = 1;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
@@ -2341,6 +2369,13 @@ 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) {
@@ -2349,6 +2384,13 @@ 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);
@@ -2361,7 +2403,7 @@ 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@nec.com are

mm-hugetlb-separate-path-for-hwpoison-entry-in-copy_hugetlb_page_range.patch
mm-hugetlb-check-gigantic_page_runtime_supported-in-return_unused_surplus_pages.patch
mm-hugetlb-make-pud_huge-and-follow_huge_pud-aware-of-non-present-pud-entry.patch
mm-hwpoison-hugetlb-support-saving-mechanism-of-raw-error-pages.patch
mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.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


^ permalink raw reply	[flat|nested] 4+ messages in thread

* + mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch added to mm-unstable branch
@ 2022-07-08 20:27 Andrew Morton
  0 siblings, 0 replies; 4+ messages in thread
From: Andrew Morton @ 2022-07-08 20:27 UTC (permalink / raw)
  To: mm-commits, songmuchun, shy828301, osalvador, mike.kravetz, lkp,
	liushixin2, linmiaohe, david, naoya.horiguchi, akpm


The patch titled
     Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
has been added to the -mm mm-unstable branch.  Its filename is
     mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
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@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 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@nec.com are

mm-hugetlb-separate-path-for-hwpoison-entry-in-copy_hugetlb_page_range.patch
mm-hugetlb-check-gigantic_page_runtime_supported-in-return_unused_surplus_pages.patch
mm-hugetlb-make-pud_huge-and-follow_huge_pud-aware-of-non-present-pud-entry.patch
mm-hwpoison-hugetlb-support-saving-mechanism-of-raw-error-pages.patch
mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.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


^ permalink raw reply	[flat|nested] 4+ messages in thread

* + mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch added to mm-unstable branch
@ 2022-07-04  1:40 Andrew Morton
  0 siblings, 0 replies; 4+ messages in thread
From: Andrew Morton @ 2022-07-04  1:40 UTC (permalink / raw)
  To: mm-commits, songmuchun, shy828301, osalvador, mike.kravetz,
	liushixin2, linmiaohe, david, naoya.horiguchi, akpm


The patch titled
     Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
has been added to the -mm mm-unstable branch.  Its filename is
     mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
Date: Mon, 4 Jul 2022 10:33:08 +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.

Link: https://lkml.kernel.org/r/20220704013312.2415700-6-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/swapops.h |    9 +++++++++
 mm/memory-failure.c     |   31 +++++++++++++++++++++++++------
 2 files changed, 34 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
@@ -1722,22 +1722,33 @@ static inline int hugetlb_set_page_hwpoi
 	return ret;
 }
 
-inline int hugetlb_clear_page_hwpoison(struct page *hpage)
+static inline 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);
 	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;
+}
+
+inline 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;
 }
 
 /*
@@ -1882,6 +1893,9 @@ static inline int try_memory_failure_hug
 	return 0;
 }
 
+static inline void free_raw_hwp_pages(struct page *hpage, bool move_flag)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
@@ -2287,6 +2301,7 @@ 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);
 
@@ -2334,6 +2349,8 @@ 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);
 		ret = TestClearPageHWPoison(page) ? 0 : -EBUSY;
 	} else if (ret < 0) {
 		if (ret == -EHWPOISON) {
@@ -2342,6 +2359,8 @@ 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);
 		freeit = !!TestClearPageHWPoison(p);
 
 		put_page(page);
@@ -2354,7 +2373,7 @@ 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@nec.com are

mm-hugetlb-check-gigantic_page_runtime_supported-in-return_unused_surplus_pages.patch
mm-hugetlb-separate-path-for-hwpoison-entry-in-copy_hugetlb_page_range.patch
mm-hugetlb-make-pud_huge-and-follow_huge_pud-aware-of-non-present-pud-entry.patch
mm-hwpoison-hugetlb-support-saving-mechanism-of-raw-error-pages.patch
mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.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


^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2022-07-17  0:53 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-07-02  4:06 + mm-hwpoison-make-unpoison-aware-of-raw-error-info-in-hwpoisoned-hugepage.patch added to mm-unstable branch Andrew Morton
2022-07-04  1:40 Andrew Morton
2022-07-08 20:27 Andrew Morton
2022-07-17  0:53 Andrew Morton

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.