1 files changed, 31 insertions, 23 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c53543d89282..1f4446a90cef 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -909,6 +909,18 @@ int get_hwpoison_page(struct page *page)
 	 * directly for tail pages.
 	 */
 	if (PageTransHuge(head)) {
+		/*
+		 * Non anonymous thp exists only in allocation/free time. We
+		 * can't handle such a case correctly, so let's give it up.
+		 * This should be better than triggering BUG_ON when kernel
+		 * tries to touch the "partially handled" page.
+		 */
+		if (!PageAnon(head)) {
+			pr_err("MCE: %#lx: non anonymous thp\n",
+				page_to_pfn(page));
+			return 0;
+		}
+
 		if (get_page_unless_zero(head)) {
 			if (PageTail(page))
 				get_page(page);
@@ -1134,17 +1146,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 
 	if (!PageHuge(p) && PageTransHuge(hpage)) {
-		if (!PageAnon(hpage)) {
-			pr_err("MCE: %#lx: non anonymous thp\n", pfn);
-			if (TestClearPageHWPoison(p))
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-			put_page(p);
-			if (p != hpage)
-				put_page(hpage);
-			return -EBUSY;
-		}
-		if (unlikely(split_huge_page(hpage))) {
-			pr_err("MCE: %#lx: thp split failed\n", pfn);
+		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+			if (!PageAnon(hpage))
+				pr_err("MCE: %#lx: non anonymous thp\n", pfn);
+			else
+				pr_err("MCE: %#lx: thp split failed\n", pfn);
 			if (TestClearPageHWPoison(p))
 				atomic_long_sub(nr_pages, &num_poisoned_pages);
 			put_page(p);
@@ -1209,9 +1215,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
 		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		unlock_page(hpage);
 		put_page(hpage);
-		res = 0;
-		goto out;
+		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
@@ -1535,6 +1541,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		 */
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
+			/* Drop page reference which is from __get_any_page() */
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
@@ -1564,13 +1572,12 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	unlock_page(hpage);
 
 	ret = isolate_huge_page(hpage, &pagelist);
-	if (ret) {
-		/*
-		 * get_any_page() and isolate_huge_page() takes a refcount each,
-		 * so need to drop one here.
-		 */
-		put_page(hpage);
-	} else {
+	/*
+	 * get_any_page() and isolate_huge_page() takes a refcount each,
+	 * so need to drop one here.
+	 */
+	put_page(hpage);
+	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
 	}
@@ -1656,6 +1663,8 @@ static int __soft_offline_page(struct page *page, int flags)
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
+		if (!TestSetPageHWPoison(page))
+			atomic_long_inc(&num_poisoned_pages);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
@@ -1670,9 +1679,8 @@ static int __soft_offline_page(struct page *page, int flags)
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
-		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (TestClearPageHWPoison(page))
+				atomic_long_dec(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",