Merge tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:

 - Two follow-on fixes for the post-5.19 series "Use pageblock_order for
   cma and alloc_contig_range alignment", from Zi Yan.

 - A series of z3fold cleanups and fixes from Miaohe Lin.

 - Some memcg selftests work from Michal Koutný <mkoutny@suse.com>

 - Some swap fixes and cleanups from Miaohe Lin

 - Several individual minor fixups

* tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (25 commits)
  mm/shmem.c: suppress shift warning
  mm: Kconfig: reorganize misplaced mm options
  mm: kasan: fix input of vmalloc_to_page()
  mm: fix is_pinnable_page against a cma page
  mm: filter out swapin error entry in shmem mapping
  mm/shmem: fix infinite loop when swap in shmem error at swapoff time
  mm/madvise: free hwpoison and swapin error entry in madvise_free_pte_range
  mm/swapfile: fix lost swap bits in unuse_pte()
  mm/swapfile: unuse_pte can map random data if swap read fails
  selftests: memcg: factor out common parts of memory.{low,min} tests
  selftests: memcg: remove protection from top level memcg
  selftests: memcg: adjust expected reclaim values of protected cgroups
  selftests: memcg: expect no low events in unprotected sibling
  selftests: memcg: fix compilation
  mm/z3fold: fix z3fold_page_migrate races with z3fold_map
  mm/z3fold: fix z3fold_reclaim_page races with z3fold_free
  mm/z3fold: always clear PAGE_CLAIMED under z3fold page lock
  mm/z3fold: put z3fold page back into unbuddied list when reclaim or migration fails
  revert "mm/z3fold.c: allow __GFP_HIGHMEM in z3fold_alloc"
  mm/z3fold: throw warning on failure of trylock_page in z3fold_alloc
  ...

1 files changed, 26 insertions, 6 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 149f2ab5063b..e008a3df0485 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -482,8 +482,12 @@ unsigned long __get_pfnblock_flags_mask(const struct page *page,
 	bitidx = pfn_to_bitidx(page, pfn);
 	word_bitidx = bitidx / BITS_PER_LONG;
 	bitidx &= (BITS_PER_LONG-1);
-
-	word = bitmap[word_bitidx];
+	/*
+	 * This races, without locks, with set_pfnblock_flags_mask(). Ensure
+	 * a consistent read of the memory array, so that results, even though
+	 * racy, are not corrupted.
+	 */
+	word = READ_ONCE(bitmap[word_bitidx]);
 	return (word >> bitidx) & mask;
 }
 
@@ -1100,30 +1104,44 @@ done_merging:
  * @order:		the order of the page
  * @split_pfn_offset:	split offset within the page
  *
+ * Return -ENOENT if the free page is changed, otherwise 0
+ *
  * It is used when the free page crosses two pageblocks with different migratetypes
  * at split_pfn_offset within the page. The split free page will be put into
  * separate migratetype lists afterwards. Otherwise, the function achieves
  * nothing.
  */
-void split_free_page(struct page *free_page,
-				int order, unsigned long split_pfn_offset)
+int split_free_page(struct page *free_page,
+			unsigned int order, unsigned long split_pfn_offset)
 {
 	struct zone *zone = page_zone(free_page);
 	unsigned long free_page_pfn = page_to_pfn(free_page);
 	unsigned long pfn;
 	unsigned long flags;
 	int free_page_order;
+	int mt;
+	int ret = 0;
 
 	if (split_pfn_offset == 0)
-		return;
+		return ret;
 
 	spin_lock_irqsave(&zone->lock, flags);
+
+	if (!PageBuddy(free_page) || buddy_order(free_page) != order) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	mt = get_pageblock_migratetype(free_page);
+	if (likely(!is_migrate_isolate(mt)))
+		__mod_zone_freepage_state(zone, -(1UL << order), mt);
+
 	del_page_from_free_list(free_page, zone, order);
 	for (pfn = free_page_pfn;
 	     pfn < free_page_pfn + (1UL << order);) {
 		int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn);
 
-		free_page_order = min_t(int,
+		free_page_order = min_t(unsigned int,
 					pfn ? __ffs(pfn) : order,
 					__fls(split_pfn_offset));
 		__free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order,
@@ -1134,7 +1152,9 @@ void split_free_page(struct page *free_page,
 		if (split_pfn_offset == 0)
 			split_pfn_offset = (1UL << order) - (pfn - free_page_pfn);
 	}
+out:
 	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret;
 }
 /*
  * A bad page could be due to a number of fields. Instead of multiple branches,