mm, hwpoison, hugetlb: support saving mechanism of raw error pages

When handling memory error on a hugetlb page, the error handler tries to
dissolve and turn it into 4kB pages.  If it's successfully dissolved,
PageHWPoison flag is moved to the raw error page, so that's all right. 
However, dissolve sometimes fails, then the error page is left as
hwpoisoned hugepage.  It's useful if we can retry to dissolve it to save
healthy pages, but that's not possible now because the information about
where the raw error pages is lost.

Use the private field of a few tail pages to keep that information.  The
code path of shrinking hugepage pool uses this info to try delayed
dissolve.  In order to remember multiple errors in a hugepage, a
singly-linked list originated from SUBPAGE_INDEX_HWPOISON-th tail page is
constructed.  Only simple operations (adding an entry or clearing all) are
required and the list is assumed not to be very long, so this simple data
structure should be enough.

If we failed to save raw error info, the hwpoison hugepage has errors on
unknown subpage, then this new saving mechanism does not work any more, so
disable saving new raw error info and freeing hwpoison hugepages.

Link: https://lkml.kernel.org/r/20220714042420.1847125-4-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>

2 files changed, 100 insertions, 12 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9b79806be17b..0aee2f3ae15c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1535,6 +1535,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
+	/*
+	 * If we don't know which subpages are hwpoisoned, we can't free
+	 * the hugepage, so it's leaked intentionally.
+	 */
+	if (HPageRawHwpUnreliable(page))
+		return;
+
 	if (hugetlb_vmemmap_restore(h, page)) {
 		spin_lock_irq(&hugetlb_lock);
 		/*
@@ -1547,6 +1554,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 		return;
 	}
 
+	/*
+	 * Move PageHWPoison flag from head page to the raw error pages,
+	 * which makes any healthy subpages reusable.
+	 */
+	if (unlikely(PageHWPoison(page)))
+		hugetlb_clear_page_hwpoison(page);
+
 	for (i = 0; i < pages_per_huge_page(h);
 	     i++, subpage = mem_map_next(subpage, page, i)) {
 		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
@@ -2109,15 +2123,6 @@ retry:
 		 */
 		rc = hugetlb_vmemmap_restore(h, head);
 		if (!rc) {
-			/*
-			 * Move PageHWPoison flag from head page to the raw
-			 * error page, which makes any subpages rather than
-			 * the error page reusable.
-			 */
-			if (PageHWPoison(head) && page != head) {
-				SetPageHWPoison(page);
-				ClearPageHWPoison(head);
-			}
 			update_and_free_page(h, head, false);
 		} else {
 			spin_lock_irq(&hugetlb_lock);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9a7a228ad04a..61668ce20836 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1662,6 +1662,90 @@ unlock:
 EXPORT_SYMBOL_GPL(mf_dax_kill_procs);
 #endif /* CONFIG_FS_DAX */
 
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * Struct raw_hwp_page represents information about "raw error page",
+ * constructing singly linked list originated from ->private field of
+ * SUBPAGE_INDEX_HWPOISON-th tail page.
+ */
+struct raw_hwp_page {
+	struct llist_node node;
+	struct page *page;
+};
+
+static inline struct llist_head *raw_hwp_list_head(struct page *hpage)
+{
+	return (struct llist_head *)&page_private(hpage + SUBPAGE_INDEX_HWPOISON);
+}
+
+static void __free_raw_hwp_pages(struct page *hpage)
+{
+	struct llist_head *head;
+	struct llist_node *t, *tnode;
+
+	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);
+		kfree(p);
+	}
+	llist_del_all(head);
+}
+
+static int hugetlb_set_page_hwpoison(struct page *hpage, struct page *page)
+{
+	struct llist_head *head;
+	struct raw_hwp_page *raw_hwp;
+	struct llist_node *t, *tnode;
+	int ret = TestSetPageHWPoison(hpage) ? -EHWPOISON : 0;
+
+	/*
+	 * Once the hwpoison hugepage has lost reliable raw error info,
+	 * there is little meaning to keep additional error info precisely,
+	 * so skip to add additional raw error info.
+	 */
+	if (HPageRawHwpUnreliable(hpage))
+		return -EHWPOISON;
+	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);
+
+		if (p->page == page)
+			return -EHWPOISON;
+	}
+
+	raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC);
+	if (raw_hwp) {
+		raw_hwp->page = page;
+		llist_add(&raw_hwp->node, head);
+		/* the first error event will be counted in action_result(). */
+		if (ret)
+			num_poisoned_pages_inc();
+	} else {
+		/*
+		 * Failed to save raw error info.  We no longer trace all
+		 * hwpoisoned subpages, and we need refuse to free/dissolve
+		 * this hwpoisoned hugepage.
+		 */
+		SetHPageRawHwpUnreliable(hpage);
+		/*
+		 * Once HPageRawHwpUnreliable is set, raw_hwp_page is not
+		 * used any more, so free it.
+		 */
+		__free_raw_hwp_pages(hpage);
+	}
+	return ret;
+}
+
+void hugetlb_clear_page_hwpoison(struct page *hpage)
+{
+	if (HPageRawHwpUnreliable(hpage))
+		return;
+	ClearPageHWPoison(hpage);
+	__free_raw_hwp_pages(hpage);
+}
+
 /*
  * Called from hugetlb code with hugetlb_lock held.
  *
@@ -1696,7 +1780,7 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
 		goto out;
 	}
 
-	if (TestSetPageHWPoison(head)) {
+	if (hugetlb_set_page_hwpoison(head, page)) {
 		ret = -EHWPOISON;
 		goto out;
 	}
@@ -1708,7 +1792,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_HUGETLB_PAGE
 /*
  * Taking refcount of hugetlb pages needs extra care about race conditions
  * with basic operations like hugepage allocation/free/demotion.
@@ -1749,7 +1832,7 @@ retry:
 	lock_page(head);
 
 	if (hwpoison_filter(p)) {
-		ClearPageHWPoison(head);
+		hugetlb_clear_page_hwpoison(head);
 		res = -EOPNOTSUPP;
 		goto out;
 	}