Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

1 files changed, 54 insertions, 35 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 08341616ae7a..c4d4ace9cc70 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -506,9 +506,6 @@ static void __filemap_fdatawait_range(struct address_space *mapping,
 	struct pagevec pvec;
 	int nr_pages;
 
-	if (end_byte < start_byte)
-		return;
-
 	pagevec_init(&pvec);
 	while (index <= end) {
 		unsigned i;
@@ -670,6 +667,9 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0, err2;
 
+	if (lend < lstart)
+		return 0;
+
 	if (mapping_needs_writeback(mapping)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
@@ -770,6 +770,9 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
 	int err = 0, err2;
 	struct address_space *mapping = file->f_mapping;
 
+	if (lend < lstart)
+		return 0;
+
 	if (mapping_needs_writeback(mapping)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
@@ -785,56 +788,54 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
 EXPORT_SYMBOL(file_write_and_wait_range);
 
 /**
- * replace_page_cache_page - replace a pagecache page with a new one
- * @old:	page to be replaced
- * @new:	page to replace with
- *
- * This function replaces a page in the pagecache with a new one.  On
- * success it acquires the pagecache reference for the new page and
- * drops it for the old page.  Both the old and new pages must be
- * locked.  This function does not add the new page to the LRU, the
+ * replace_page_cache_folio - replace a pagecache folio with a new one
+ * @old:	folio to be replaced
+ * @new:	folio to replace with
+ *
+ * This function replaces a folio in the pagecache with a new one.  On
+ * success it acquires the pagecache reference for the new folio and
+ * drops it for the old folio.  Both the old and new folios must be
+ * locked.  This function does not add the new folio to the LRU, the
  * caller must do that.
  *
  * The remove + add is atomic.  This function cannot fail.
  */
-void replace_page_cache_page(struct page *old, struct page *new)
+void replace_page_cache_folio(struct folio *old, struct folio *new)
 {
-	struct folio *fold = page_folio(old);
-	struct folio *fnew = page_folio(new);
 	struct address_space *mapping = old->mapping;
 	void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
 	pgoff_t offset = old->index;
 	XA_STATE(xas, &mapping->i_pages, offset);
 
-	VM_BUG_ON_PAGE(!PageLocked(old), old);
-	VM_BUG_ON_PAGE(!PageLocked(new), new);
-	VM_BUG_ON_PAGE(new->mapping, new);
+	VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
+	VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
+	VM_BUG_ON_FOLIO(new->mapping, new);
 
-	get_page(new);
+	folio_get(new);
 	new->mapping = mapping;
 	new->index = offset;
 
-	mem_cgroup_migrate(fold, fnew);
+	mem_cgroup_migrate(old, new);
 
 	xas_lock_irq(&xas);
 	xas_store(&xas, new);
 
 	old->mapping = NULL;
 	/* hugetlb pages do not participate in page cache accounting. */
-	if (!PageHuge(old))
-		__dec_lruvec_page_state(old, NR_FILE_PAGES);
-	if (!PageHuge(new))
-		__inc_lruvec_page_state(new, NR_FILE_PAGES);
-	if (PageSwapBacked(old))
-		__dec_lruvec_page_state(old, NR_SHMEM);
-	if (PageSwapBacked(new))
-		__inc_lruvec_page_state(new, NR_SHMEM);
+	if (!folio_test_hugetlb(old))
+		__lruvec_stat_sub_folio(old, NR_FILE_PAGES);
+	if (!folio_test_hugetlb(new))
+		__lruvec_stat_add_folio(new, NR_FILE_PAGES);
+	if (folio_test_swapbacked(old))
+		__lruvec_stat_sub_folio(old, NR_SHMEM);
+	if (folio_test_swapbacked(new))
+		__lruvec_stat_add_folio(new, NR_SHMEM);
 	xas_unlock_irq(&xas);
 	if (free_folio)
-		free_folio(fold);
-	folio_put(fold);
+		free_folio(old);
+	folio_put(old);
 }
-EXPORT_SYMBOL_GPL(replace_page_cache_page);
+EXPORT_SYMBOL_GPL(replace_page_cache_folio);
 
 noinline int __filemap_add_folio(struct address_space *mapping,
 		struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
@@ -2048,10 +2049,10 @@ reset:
  *
  * Return: The number of entries which were found.
  */
-unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
 {
-	XA_STATE(xas, &mapping->i_pages, start);
+	XA_STATE(xas, &mapping->i_pages, *start);
 	struct folio *folio;
 
 	rcu_read_lock();
@@ -2062,6 +2063,15 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 	}
 	rcu_read_unlock();
 
+	if (folio_batch_count(fbatch)) {
+		unsigned long nr = 1;
+		int idx = folio_batch_count(fbatch) - 1;
+
+		folio = fbatch->folios[idx];
+		if (!xa_is_value(folio) && !folio_test_hugetlb(folio))
+			nr = folio_nr_pages(folio);
+		*start = indices[idx] + nr;
+	}
 	return folio_batch_count(fbatch);
 }
 
@@ -2085,16 +2095,16 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
  *
  * Return: The number of entries which were found.
  */
-unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
+unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
 {
-	XA_STATE(xas, &mapping->i_pages, start);
+	XA_STATE(xas, &mapping->i_pages, *start);
 	struct folio *folio;
 
 	rcu_read_lock();
 	while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
 		if (!xa_is_value(folio)) {
-			if (folio->index < start)
+			if (folio->index < *start)
 				goto put;
 			if (folio->index + folio_nr_pages(folio) - 1 > end)
 				goto put;
@@ -2117,6 +2127,15 @@ put:
 	}
 	rcu_read_unlock();
 
+	if (folio_batch_count(fbatch)) {
+		unsigned long nr = 1;
+		int idx = folio_batch_count(fbatch) - 1;
+
+		folio = fbatch->folios[idx];
+		if (!xa_is_value(folio) && !folio_test_hugetlb(folio))
+			nr = folio_nr_pages(folio);
+		*start = indices[idx] + nr;
+	}
 	return folio_batch_count(fbatch);
 }