1 files changed, 148 insertions, 31 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9a7a228ad04a..14439806b5ef 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,7 +74,13 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
 static bool hw_memory_failure __read_mostly = false;
 
-static bool __page_handle_poison(struct page *page)
+/*
+ * Return values:
+ *   1:   the page is dissolved (if needed) and taken off from buddy,
+ *   0:   the page is dissolved (if needed) and not taken off from buddy,
+ *   < 0: failed to dissolve.
+ */
+static int __page_handle_poison(struct page *page)
 {
 	int ret;
 
@@ -84,7 +90,7 @@ static bool __page_handle_poison(struct page *page)
 		ret = take_page_off_buddy(page);
 	zone_pcp_enable(page_zone(page));
 
-	return ret > 0;
+	return ret;
 }
 
 static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
@@ -94,7 +100,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo
 		 * Doing this check for free pages is also fine since dissolve_free_huge_page
 		 * returns 0 for non-hugetlb pages as well.
 		 */
-		if (!__page_handle_poison(page))
+		if (__page_handle_poison(page) <= 0)
 			/*
 			 * We could fail to take off the target page from buddy
 			 * for example due to racy page allocation, but that's
@@ -762,7 +768,6 @@ static const char * const action_page_types[] = {
 	[MF_MSG_DIFFERENT_COMPOUND]	= "different compound page after locking",
 	[MF_MSG_HUGE]			= "huge page",
 	[MF_MSG_FREE_HUGE]		= "free huge page",
-	[MF_MSG_NON_PMD_HUGE]		= "non-pmd-sized huge page",
 	[MF_MSG_UNMAP_FAILED]		= "unmapping failed page",
 	[MF_MSG_DIRTY_SWAPCACHE]	= "dirty swapcache page",
 	[MF_MSG_CLEAN_SWAPCACHE]	= "clean swapcache page",
@@ -1078,7 +1083,6 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		res = truncate_error_page(hpage, page_to_pfn(p), mapping);
 		unlock_page(hpage);
 	} else {
-		res = MF_FAILED;
 		unlock_page(hpage);
 		/*
 		 * migration entry prevents later access on error hugepage,
@@ -1086,9 +1090,11 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		 * subpages.
 		 */
 		put_page(hpage);
-		if (__page_handle_poison(p)) {
+		if (__page_handle_poison(p) >= 0) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
+		} else {
+			res = MF_FAILED;
 		}
 	}
 
@@ -1662,6 +1668,113 @@ 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 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);
+
+		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)
+{
+	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, 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, true);
+}
+
 /*
  * Called from hugetlb code with hugetlb_lock held.
  *
@@ -1693,10 +1806,11 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
 			count_increased = true;
 	} else {
 		ret = -EBUSY;
-		goto out;
+		if (!(flags & MF_NO_RETRY))
+			goto out;
 	}
 
-	if (TestSetPageHWPoison(head)) {
+	if (hugetlb_set_page_hwpoison(head, page)) {
 		ret = -EHWPOISON;
 		goto out;
 	}
@@ -1708,7 +1822,6 @@ 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.
@@ -1721,7 +1834,6 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
 	struct page *p = pfn_to_page(pfn);
 	struct page *head;
 	unsigned long page_flags;
-	bool retry = true;
 
 	*hugetlb = 1;
 retry:
@@ -1737,8 +1849,8 @@ retry:
 		}
 		return res;
 	} else if (res == -EBUSY) {
-		if (retry) {
-			retry = false;
+		if (!(flags & MF_NO_RETRY)) {
+			flags |= MF_NO_RETRY;
 			goto retry;
 		}
 		action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
@@ -1749,7 +1861,7 @@ retry:
 	lock_page(head);
 
 	if (hwpoison_filter(p)) {
-		ClearPageHWPoison(head);
+		hugetlb_clear_page_hwpoison(head);
 		res = -EOPNOTSUPP;
 		goto out;
 	}
@@ -1760,10 +1872,11 @@ retry:
 	 */
 	if (res == 0) {
 		unlock_page(head);
-		res = MF_FAILED;
-		if (__page_handle_poison(p)) {
+		if (__page_handle_poison(p) >= 0) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
+		} else {
+			res = MF_FAILED;
 		}
 		action_result(pfn, MF_MSG_FREE_HUGE, res);
 		return res == MF_RECOVERED ? 0 : -EBUSY;
@@ -1771,21 +1884,6 @@ retry:
 
 	page_flags = head->flags;
 
-	/*
-	 * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so
-	 * simply disable it. In order to make it work properly, we need
-	 * make sure that:
-	 *  - conversion of a pud that maps an error hugetlb into hwpoison
-	 *    entry properly works, and
-	 *  - other mm code walking over page table is aware of pud-aligned
-	 *    hwpoison entries.
-	 */
-	if (huge_page_size(page_hstate(head)) > PMD_SIZE) {
-		action_result(pfn, MF_MSG_NON_PMD_HUGE, MF_IGNORED);
-		res = -EBUSY;
-		goto out;
-	}
-
 	if (!hwpoison_user_mappings(p, pfn, flags, head)) {
 		action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
 		res = -EBUSY;
@@ -1804,6 +1902,10 @@ static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *
 	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,
@@ -2209,6 +2311,7 @@ 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);
 
@@ -2256,6 +2359,13 @@ 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) {
@@ -2264,6 +2374,13 @@ 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);
@@ -2276,7 +2393,7 @@ 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);
 	}