Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

3 files changed, 37 insertions, 40 deletions

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index a5f4be6b9213..1c407eba1e30 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -38,13 +38,13 @@
 
 
 void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
-			     unsigned int from, unsigned int len)
+			     size_t from, size_t len)
 {
 	struct buffer_head *head = folio_buffers(folio);
 	unsigned int bsize = head->b_size;
 	struct buffer_head *bh;
-	unsigned int to = from + len;
-	unsigned int start, end;
+	size_t to = from + len;
+	size_t start, end;
 
 	for (bh = head, start = 0; bh != head || !start;
 	     bh = bh->b_this_page, start = end) {
@@ -82,61 +82,61 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 }
 
 /**
- * gfs2_write_jdata_page - gfs2 jdata-specific version of block_write_full_page
- * @page: The page to write
+ * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_page
+ * @folio: The folio to write
  * @wbc: The writeback control
  *
  * This is the same as calling block_write_full_page, but it also
  * writes pages outside of i_size
  */
-static int gfs2_write_jdata_page(struct page *page,
+static int gfs2_write_jdata_folio(struct folio *folio,
 				 struct writeback_control *wbc)
 {
-	struct inode * const inode = page->mapping->host;
+	struct inode * const inode = folio->mapping->host;
 	loff_t i_size = i_size_read(inode);
-	const pgoff_t end_index = i_size >> PAGE_SHIFT;
-	unsigned offset;
 
 	/*
-	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * The folio straddles i_size.  It must be zeroed out on each and every
 	 * writepage invocation because it may be mmapped.  "A file is mapped
 	 * in multiples of the page size.  For a file that is not a multiple of
-	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * the page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	offset = i_size & (PAGE_SIZE - 1);
-	if (page->index == end_index && offset)
-		zero_user_segment(page, offset, PAGE_SIZE);
+	if (folio_pos(folio) < i_size &&
+	    i_size < folio_pos(folio) + folio_size(folio))
+		folio_zero_segment(folio, offset_in_folio(folio, i_size),
+				folio_size(folio));
 
-	return __block_write_full_page(inode, page, gfs2_get_block_noalloc, wbc,
-				       end_buffer_async_write);
+	return __block_write_full_folio(inode, folio, gfs2_get_block_noalloc,
+			wbc, end_buffer_async_write);
 }
 
 /**
- * __gfs2_jdata_writepage - The core of jdata writepage
- * @page: The page to write
+ * __gfs2_jdata_write_folio - The core of jdata writepage
+ * @folio: The folio to write
  * @wbc: The writeback control
  *
  * This is shared between writepage and writepages and implements the
  * core of the writepage operation. If a transaction is required then
- * PageChecked will have been set and the transaction will have
+ * the checked flag will have been set and the transaction will have
  * already been started before this is called.
  */
-
-static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+static int __gfs2_jdata_write_folio(struct folio *folio,
+		struct writeback_control *wbc)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	if (PageChecked(page)) {
-		ClearPageChecked(page);
-		if (!page_has_buffers(page)) {
-			create_empty_buffers(page, inode->i_sb->s_blocksize,
-					     BIT(BH_Dirty)|BIT(BH_Uptodate));
+	if (folio_test_checked(folio)) {
+		folio_clear_checked(folio);
+		if (!folio_buffers(folio)) {
+			folio_create_empty_buffers(folio,
+					inode->i_sb->s_blocksize,
+					BIT(BH_Dirty)|BIT(BH_Uptodate));
 		}
-		gfs2_trans_add_databufs(ip, page_folio(page), 0, PAGE_SIZE);
+		gfs2_trans_add_databufs(ip, folio, 0, folio_size(folio));
 	}
-	return gfs2_write_jdata_page(page, wbc);
+	return gfs2_write_jdata_folio(folio, wbc);
 }
 
 /**
@@ -150,20 +150,21 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w
 
 static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(page);
 	struct inode *inode = page->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
 	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
 		goto out;
-	if (PageChecked(page) || current->journal_info)
+	if (folio_test_checked(folio) || current->journal_info)
 		goto out_ignore;
-	return __gfs2_jdata_writepage(page, wbc);
+	return __gfs2_jdata_write_folio(folio, wbc);
 
 out_ignore:
-	redirty_page_for_writepage(wbc, page);
+	folio_redirty_for_writepage(wbc, folio);
 out:
-	unlock_page(page);
+	folio_unlock(folio);
 	return 0;
 }
 
@@ -255,7 +256,7 @@ continue_unlock:
 
 		trace_wbc_writepage(wbc, inode_to_bdi(inode));
 
-		ret = __gfs2_jdata_writepage(&folio->page, wbc);
+		ret = __gfs2_jdata_write_folio(folio, wbc);
 		if (unlikely(ret)) {
 			if (ret == AOP_WRITEPAGE_ACTIVATE) {
 				folio_unlock(folio);
diff --git a/fs/gfs2/aops.h b/fs/gfs2/aops.h
index 09db1914425e..f08322ef41cf 100644
--- a/fs/gfs2/aops.h
+++ b/fs/gfs2/aops.h
@@ -10,6 +10,6 @@
 
 extern void adjust_fs_space(struct inode *inode);
 extern void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
-				    unsigned int from, unsigned int len);
+				    size_t from, size_t len);
 
 #endif /* __AOPS_DOT_H__ */
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 1d679a3178ff..f146447eac63 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1052,15 +1052,11 @@ retry:
 			goto out_unlock;
 	}
 
-	current->backing_dev_info = inode_to_bdi(inode);
 	pagefault_disable();
 	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
 	pagefault_enable();
-	current->backing_dev_info = NULL;
-	if (ret > 0) {
-		iocb->ki_pos += ret;
+	if (ret > 0)
 		written += ret;
-	}
 
 	if (inode == sdp->sd_rindex)
 		gfs2_glock_dq_uninit(statfs_gh);