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()
  ...

2 files changed, 39 insertions, 58 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 0edab9deae2a..a4fa81af60d9 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -864,16 +864,19 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 		.len		= iov_iter_count(i),
 		.flags		= IOMAP_WRITE,
 	};
-	int ret;
+	ssize_t ret;
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iter.flags |= IOMAP_NOWAIT;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = iomap_write_iter(&iter, i);
-	if (iter.pos == iocb->ki_pos)
+
+	if (unlikely(ret < 0))
 		return ret;
-	return iter.pos - iocb->ki_pos;
+	ret = iter.pos - iocb->ki_pos;
+	iocb->ki_pos += ret;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
 
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 08873f0627dd..ea3b868c8355 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -81,7 +81,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
-	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret = dio->error;
 
@@ -94,7 +93,6 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 		if (offset + ret > dio->i_size &&
 		    !(dio->flags & IOMAP_DIO_WRITE))
 			ret = dio->i_size - offset;
-		iocb->ki_pos += ret;
 	}
 
 	/*
@@ -109,30 +107,25 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error && dio->size &&
-	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
-		int err;
-		err = invalidate_inode_pages2_range(inode->i_mapping,
-				offset >> PAGE_SHIFT,
-				(offset + dio->size - 1) >> PAGE_SHIFT);
-		if (err)
-			dio_warn_stale_pagecache(iocb->ki_filp);
-	}
+	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE))
+		kiocb_invalidate_post_direct_write(iocb, dio->size);
 
 	inode_dio_end(file_inode(iocb->ki_filp));
-	/*
-	 * If this is a DSYNC write, make sure we push it to stable storage now
-	 * that we've written data.
-	 */
-	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
-		ret = generic_write_sync(iocb, ret);
 
-	if (ret > 0)
-		ret += dio->done_before;
+	if (ret > 0) {
+		iocb->ki_pos += ret;
 
+		/*
+		 * If this is a DSYNC write, make sure we push it to stable
+		 * storage now that we've written data.
+		 */
+		if (dio->flags & IOMAP_DIO_NEED_SYNC)
+			ret = generic_write_sync(iocb, ret);
+		if (ret > 0)
+			ret += dio->done_before;
+	}
 	trace_iomap_dio_complete(iocb, dio->error, ret);
 	kfree(dio);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_dio_complete);
@@ -478,7 +471,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before)
 {
-	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct iomap_iter iomi = {
 		.inode		= inode,
@@ -487,11 +479,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		.flags		= IOMAP_DIRECT,
 		.private	= private,
 	};
-	loff_t end = iomi.pos + iomi.len - 1, ret = 0;
 	bool wait_for_completion =
 		is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
+	loff_t ret = 0;
 
 	trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before);
 
@@ -515,31 +507,29 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->submit.waiter = current;
 	dio->submit.poll_bio = NULL;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iomi.flags |= IOMAP_NOWAIT;
+
 	if (iov_iter_rw(iter) == READ) {
 		if (iomi.pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_needs_writeback(mapping, iomi.pos,
-					end)) {
-				ret = -EAGAIN;
-				goto out_free_dio;
-			}
-			iomi.flags |= IOMAP_NOWAIT;
-		}
-
 		if (user_backed_iter(iter))
 			dio->flags |= IOMAP_DIO_DIRTY;
+
+		ret = kiocb_write_and_wait(iocb, iomi.len);
+		if (ret)
+			goto out_free_dio;
 	} else {
 		iomi.flags |= IOMAP_WRITE;
 		dio->flags |= IOMAP_DIO_WRITE;
 
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (filemap_range_has_page(mapping, iomi.pos, end)) {
-				ret = -EAGAIN;
+		if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
+			ret = -EAGAIN;
+			if (iomi.pos >= dio->i_size ||
+			    iomi.pos + iomi.len > dio->i_size)
 				goto out_free_dio;
-			}
-			iomi.flags |= IOMAP_NOWAIT;
+			iomi.flags |= IOMAP_OVERWRITE_ONLY;
 		}
 
 		/* for data sync or sync, we need sync completion processing */
@@ -555,31 +545,19 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!(iocb->ki_flags & IOCB_SYNC))
 				dio->flags |= IOMAP_DIO_WRITE_FUA;
 		}
-	}
 
-	if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
-		ret = -EAGAIN;
-		if (iomi.pos >= dio->i_size ||
-		    iomi.pos + iomi.len > dio->i_size)
-			goto out_free_dio;
-		iomi.flags |= IOMAP_OVERWRITE_ONLY;
-	}
-
-	ret = filemap_write_and_wait_range(mapping, iomi.pos, end);
-	if (ret)
-		goto out_free_dio;
-
-	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * Try to invalidate cache pages for the range we are writing.
 		 * If this invalidation fails, let the caller fall back to
 		 * buffered I/O.
 		 */
-		if (invalidate_inode_pages2_range(mapping,
-				iomi.pos >> PAGE_SHIFT, end >> PAGE_SHIFT)) {
-			trace_iomap_dio_invalidate_fail(inode, iomi.pos,
-							iomi.len);
-			ret = -ENOTBLK;
+		ret = kiocb_invalidate_pages(iocb, iomi.len);
+		if (ret) {
+			if (ret != -EAGAIN) {
+				trace_iomap_dio_invalidate_fail(inode, iomi.pos,
+								iomi.len);
+				ret = -ENOTBLK;
+			}
 			goto out_free_dio;
 		}