mm/huge_memory: do not change split_huge_page*() target order silently

commit 77008e1b2ef73249bceb078a321a3ff6bc087afb upstream.

Page cache folios from a file system that support large block size (LBS)
can have minimal folio order greater than 0, thus a high order folio might
not be able to be split down to order-0.  Commit e220917 ("mm: split
a folio in minimum folio order chunks") bumps the target order of
split_huge_page*() to the minimum allowed order when splitting a LBS
folio.  This causes confusion for some split_huge_page*() callers like
memory failure handling code, since they expect after-split folios all
have order-0 when split succeeds but in reality get min_order_for_split()
order folios and give warnings.

Fix it by failing a split if the folio cannot be split to the target
order.  Rename try_folio_split() to try_folio_split_to_order() to reflect
the added new_order parameter.  Remove its unused list parameter.

[The test poisons LBS folios, which cannot be split to order-0 folios, and
also tries to poison all memory.  The non split LBS folios take more
memory than the test anticipated, leading to OOM.  The patch fixed the
kernel warning and the test needs some change to avoid OOM.]

Link: https://lkml.kernel.org/r/[email protected]
Fixes: e220917 ("mm: split a folio in minimum folio order chunks")
Signed-off-by: Zi Yan <[email protected]>
Reported-by: [email protected]
Closes: https://lore.kernel.org/all/[email protected]/
Reviewed-by: Luis Chamberlain <[email protected]>
Reviewed-by: Pankaj Raghav <[email protected]>
Reviewed-by: Wei Yang <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Reviewed-by: Lorenzo Stoakes <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
Cc: Baolin Wang <[email protected]>
Cc: Barry Song <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Dev Jain <[email protected]>
Cc: Jane Chu <[email protected]>
Cc: Lance Yang <[email protected]>
Cc: Liam Howlett <[email protected]>
Cc: Mariano Pache <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Ryan Roberts <[email protected]>
Cc: Christian Brauner <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: x-y-z

include/linux/huge_mm.h

@@ -354,45 +354,30 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
 int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
 		struct list_head *list);
 /*
- * try_folio_split - try to split a @folio at @page using non uniform split.
+ * try_folio_split_to_order - try to split a @folio at @page to @new_order using
+ * non uniform split.
  * @folio: folio to be split
- * @page: split to order-0 at the given page
- * @list: store the after-split folios
+ * @page: split to @new_order at the given page
+ * @new_order: the target split order
  *
- * Try to split a @folio at @page using non uniform split to order-0, if
- * non uniform split is not supported, fall back to uniform split.
+ * Try to split a @folio at @page using non uniform split to @new_order, if
+ * non uniform split is not supported, fall back to uniform split. After-split
+ * folios are put back to LRU list. Use min_order_for_split() to get the lower
+ * bound of @new_order.
  *
  * Return: 0: split is successful, otherwise split failed.
  */
-static inline int try_folio_split(struct folio *folio, struct page *page,
-		struct list_head *list)
+static inline int try_folio_split_to_order(struct folio *folio,
+		struct page *page, unsigned int new_order)
 {
-	int ret = min_order_for_split(folio);
-
-	if (ret < 0)
-		return ret;
-
-	if (!non_uniform_split_supported(folio, 0, false))
-		return split_huge_page_to_list_to_order(&folio->page, list,
-				ret);
-	return folio_split(folio, ret, page, list);
+	if (!non_uniform_split_supported(folio, new_order, /* warns= */ false))
+		return split_huge_page_to_list_to_order(&folio->page, NULL,
+				new_order);
+	return folio_split(folio, new_order, page, NULL);
 }
 static inline int split_huge_page(struct page *page)
 {
-	struct folio *folio = page_folio(page);
-	int ret = min_order_for_split(folio);
-
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * split_huge_page() locks the page before splitting and
-	 * expects the same page that has been split to be locked when
-	 * returned. split_folio(page_folio(page)) cannot be used here
-	 * because it converts the page to folio and passes the head
-	 * page to be split.
-	 */
-	return split_huge_page_to_list_to_order(page, NULL, ret);
+	return split_huge_page_to_list_to_order(page, NULL, 0);
 }
 void deferred_split_folio(struct folio *folio, bool partially_mapped);
 
@@ -560,13 +545,19 @@ static inline int split_huge_page(struct page *page)
 	return 0;
 }
 
+static inline int min_order_for_split(struct folio *folio)
+{
+	VM_WARN_ON_ONCE_FOLIO(1, folio);
+	return -EINVAL;
+}
+
 static inline int split_folio_to_list(struct folio *folio, struct list_head *list)
 {
 	return 0;
 }
 
-static inline int try_folio_split(struct folio *folio, struct page *page,
-		struct list_head *list)
+static inline int try_folio_split_to_order(struct folio *folio,
+		struct page *page, unsigned int new_order)
 {
 	return 0;
 }

mm/huge_memory.c

@@ -3680,8 +3680,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 		min_order = mapping_min_folio_order(folio->mapping);
 		if (new_order < min_order) {
-			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
-				     min_order);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -4016,12 +4014,7 @@ int min_order_for_split(struct folio *folio)
 
 int split_folio_to_list(struct folio *folio, struct list_head *list)
 {
-	int ret = min_order_for_split(folio);
-
-	if (ret < 0)
-		return ret;
-
-	return split_huge_page_to_list_to_order(&folio->page, list, ret);
+	return split_huge_page_to_list_to_order(&folio->page, list, 0);
 }
 
 /*

mm/truncate.c

@@ -194,6 +194,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	size_t size = folio_size(folio);
 	unsigned int offset, length;
 	struct page *split_at, *split_at2;
+	unsigned int min_order;
 
 	if (pos < start)
 		offset = start - pos;
@@ -223,8 +224,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	if (!folio_test_large(folio))
 		return true;
 
+	min_order = mapping_min_folio_order(folio->mapping);
 	split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE);
-	if (!try_folio_split(folio, split_at, NULL)) {
+	if (!try_folio_split_to_order(folio, split_at, min_order)) {
 		/*
 		 * try to split at offset + length to make sure folios within
 		 * the range can be dropped, especially to avoid memory waste
@@ -254,7 +256,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 		 */
 		if (folio_test_large(folio2) &&
 		    folio2->mapping == folio->mapping)
-			try_folio_split(folio2, split_at2, NULL);
+			try_folio_split_to_order(folio2, split_at2, min_order);
 
 		folio_unlock(folio2);
 out: