[PATCH 6.18 086/122] mm/memory-failure: fix missing ->mf_stats count in hugetlb poison

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jane Chu <jane.chu@oracle.com>

commit a148a2040191b12b45b82cb29c281cb3036baf90 upstream.

When a newly poisoned subpage ends up in an already poisoned hugetlb
folio, 'num_poisoned_pages' is incremented, but the per node ->mf_stats is
not.  Fix the inconsistency by designating action_result() to update them
both.

While at it, define __get_huge_page_for_hwpoison() return values in terms
of symbol names for better readibility.  Also rename
folio_set_hugetlb_hwpoison() to hugetlb_update_hwpoison() since the
function does more than the conventional bit setting and the fact three
possible return values are expected.

Link: https://lkml.kernel.org/r/20260120232234.3462258-1-jane.chu@oracle.com
Fixes: 18f41fa616ee ("mm: memory-failure: bump memory failure stats to pglist_data")
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Chris Mason <clm@meta.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: William Roche <william.roche@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 mm/memory-failure.c |   93 +++++++++++++++++++++++++++++++---------------------
 1 file changed, 56 insertions(+), 37 deletions(-)

--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1873,12 +1873,22 @@ static unsigned long __folio_free_raw_hw
 	return count;
 }
 
-static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page)
+#define	MF_HUGETLB_FREED		0	/* freed hugepage */
+#define	MF_HUGETLB_IN_USED		1	/* in-use hugepage */
+#define	MF_HUGETLB_NON_HUGEPAGE		2	/* not a hugepage */
+#define	MF_HUGETLB_FOLIO_PRE_POISONED	3	/* folio already poisoned */
+#define	MF_HUGETLB_PAGE_PRE_POISONED	4	/* exact page already poisoned */
+#define	MF_HUGETLB_RETRY		5	/* hugepage is busy, retry */
+/*
+ * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list
+ * to keep track of the poisoned pages.
+ */
+static int hugetlb_update_hwpoison(struct folio *folio, struct page *page)
 {
 	struct llist_head *head;
 	struct raw_hwp_page *raw_hwp;
 	struct raw_hwp_page *p;
-	int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0;
+	int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_FOLIO_PRE_POISONED : 0;
 
 	/*
 	 * Once the hwpoison hugepage has lost reliable raw error info,
@@ -1886,20 +1896,17 @@ static int folio_set_hugetlb_hwpoison(st
 	 * so skip to add additional raw error info.
 	 */
 	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
-		return -EHWPOISON;
+		return MF_HUGETLB_FOLIO_PRE_POISONED;
 	head = raw_hwp_list_head(folio);
 	llist_for_each_entry(p, head->first, node) {
 		if (p->page == page)
-			return -EHWPOISON;
+			return MF_HUGETLB_PAGE_PRE_POISONED;
 	}
 
 	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(page_to_pfn(page));
 	} else {
 		/*
 		 * Failed to save raw error info.  We no longer trace all
@@ -1947,42 +1954,39 @@ void folio_clear_hugetlb_hwpoison(struct
 
 /*
  * Called from hugetlb code with hugetlb_lock held.
- *
- * Return values:
- *   0             - free hugepage
- *   1             - in-use hugepage
- *   2             - not a hugepage
- *   -EBUSY        - the hugepage is busy (try to retry)
- *   -EHWPOISON    - the hugepage is already hwpoisoned
  */
 int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 				 bool *migratable_cleared)
 {
 	struct page *page = pfn_to_page(pfn);
 	struct folio *folio = page_folio(page);
-	int ret = 2;	/* fallback to normal page handling */
 	bool count_increased = false;
+	int ret, rc;
 
-	if (!folio_test_hugetlb(folio))
+	if (!folio_test_hugetlb(folio)) {
+		ret = MF_HUGETLB_NON_HUGEPAGE;
 		goto out;
-
-	if (flags & MF_COUNT_INCREASED) {
-		ret = 1;
+	} else if (flags & MF_COUNT_INCREASED) {
+		ret = MF_HUGETLB_IN_USED;
 		count_increased = true;
 	} else if (folio_test_hugetlb_freed(folio)) {
-		ret = 0;
+		ret = MF_HUGETLB_FREED;
 	} else if (folio_test_hugetlb_migratable(folio)) {
-		ret = folio_try_get(folio);
-		if (ret)
+		if (folio_try_get(folio)) {
+			ret = MF_HUGETLB_IN_USED;
 			count_increased = true;
+		} else {
+			ret = MF_HUGETLB_FREED;
+		}
 	} else {
-		ret = -EBUSY;
+		ret = MF_HUGETLB_RETRY;
 		if (!(flags & MF_NO_RETRY))
 			goto out;
 	}
 
-	if (folio_set_hugetlb_hwpoison(folio, page)) {
-		ret = -EHWPOISON;
+	rc = hugetlb_update_hwpoison(folio, page);
+	if (rc >= MF_HUGETLB_FOLIO_PRE_POISONED) {
+		ret = rc;
 		goto out;
 	}
 
@@ -2007,10 +2011,16 @@ out:
  * with basic operations like hugepage allocation/free/demotion.
  * So some of prechecks for hwpoison (pinning, and testing/setting
  * PageHWPoison) should be done in single hugetlb_lock range.
+ * Returns:
+ *	0		- not hugetlb, or recovered
+ *	-EBUSY		- not recovered
+ *	-EOPNOTSUPP	- hwpoison_filter'ed
+ *	-EHWPOISON	- folio or exact page already poisoned
+ *	-EFAULT		- kill_accessing_process finds current->mm null
  */
 static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
 {
-	int res;
+	int res, rv;
 	struct page *p = pfn_to_page(pfn);
 	struct folio *folio;
 	unsigned long page_flags;
@@ -2019,22 +2029,31 @@ static int try_memory_failure_hugetlb(un
 	*hugetlb = 1;
 retry:
 	res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared);
-	if (res == 2) { /* fallback to normal page handling */
+	switch (res) {
+	case MF_HUGETLB_NON_HUGEPAGE:	/* fallback to normal page handling */
 		*hugetlb = 0;
 		return 0;
-	} else if (res == -EHWPOISON) {
-		if (flags & MF_ACTION_REQUIRED) {
-			folio = page_folio(p);
-			res = kill_accessing_process(current, folio_pfn(folio), flags);
-		}
-		action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
-		return res;
-	} else if (res == -EBUSY) {
+	case MF_HUGETLB_RETRY:
 		if (!(flags & MF_NO_RETRY)) {
 			flags |= MF_NO_RETRY;
 			goto retry;
 		}
 		return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED);
+	case MF_HUGETLB_FOLIO_PRE_POISONED:
+	case MF_HUGETLB_PAGE_PRE_POISONED:
+		rv = -EHWPOISON;
+		if (flags & MF_ACTION_REQUIRED) {
+			folio = page_folio(p);
+			rv = kill_accessing_process(current, folio_pfn(folio), flags);
+		}
+		if (res == MF_HUGETLB_PAGE_PRE_POISONED)
+			action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
+		else
+			action_result(pfn, MF_MSG_HUGE, MF_FAILED);
+		return rv;
+	default:
+		WARN_ON((res != MF_HUGETLB_FREED) && (res != MF_HUGETLB_IN_USED));
+		break;
 	}
 
 	folio = page_folio(p);
@@ -2045,7 +2064,7 @@ retry:
 		if (migratable_cleared)
 			folio_set_hugetlb_migratable(folio);
 		folio_unlock(folio);
-		if (res == 1)
+		if (res == MF_HUGETLB_IN_USED)
 			folio_put(folio);
 		return -EOPNOTSUPP;
 	}
@@ -2054,7 +2073,7 @@ retry:
 	 * Handling free hugepage.  The possible race with hugepage allocation
 	 * or demotion can be prevented by PageHWPoison flag.
 	 */
-	if (res == 0) {
+	if (res == MF_HUGETLB_FREED) {
 		folio_unlock(folio);
 		if (__page_handle_poison(p) > 0) {
 			page_ref_inc(p);