Merge tag 'vfs-6.19-rc1.writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull writeback updates from Christian Brauner:
 "Features:

   - Allow file systems to increase the minimum writeback chunk size.

     The relatively low minimal writeback size of 4MiB means that
     written back inodes on rotational media are switched a lot. Besides
     introducing additional seeks, this also can lead to extreme file
     fragmentation on zoned devices when a lot of files are cached
     relative to the available writeback bandwidth.

     This adds a superblock field that allows the file system to
     override the default size, and sets it to the zone size for zoned
     XFS.

   - Add logging for slow writeback when it exceeds
     sysctl_hung_task_timeout_secs. This helps identify tasks waiting
     for a long time and pinpoint potential issues. Recording the
     starting jiffies is also useful when debugging a crashed vmcore.

   - Wake up waiting tasks when finishing the writeback of a chunk

  Cleanups:

   - filemap_* writeback interface cleanups.

     Adding filemap_fdatawrite_wbc ended up being a mistake, as all but
     the original btrfs caller should be using better high level
     interfaces instead.

     This series removes all these low-level interfaces, switches btrfs
     to a more specific interface, and cleans up other too low-level
     interfaces. With this the writeback_control that is passed to the
     writeback code is only initialized in three places.

   - Remove __filemap_fdatawrite, __filemap_fdatawrite_range, and
     filemap_fdatawrite_wbc

   - Add filemap_flush_nr helper for btrfs

   - Push struct writeback_control into start_delalloc_inodes in btrfs

   - Rename filemap_fdatawrite_range_kick to filemap_flush_range

   - Stop opencoding filemap_fdatawrite_range in 9p, ocfs2, and mm

   - Make wbc_to_tag() inline and use it in fs"

* tag 'vfs-6.19-rc1.writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: Make wbc_to_tag() inline and use it in fs.
  xfs: set s_min_writeback_pages for zoned file systems
  writeback: allow the file system to override MIN_WRITEBACK_PAGES
  writeback: cleanup writeback_chunk_size
  mm: rename filemap_fdatawrite_range_kick to filemap_flush_range
  mm: remove __filemap_fdatawrite_range
  mm: remove filemap_fdatawrite_wbc
  mm: remove __filemap_fdatawrite
  mm,btrfs: add a filemap_flush_nr helper
  btrfs: push struct writeback_control into start_delalloc_inodes
  btrfs: use the local tmp_inode variable in start_delalloc_inodes
  ocfs2: don't opencode filemap_fdatawrite_range in ocfs2_journal_submit_inode_data_buffers
  9p: don't opencode filemap_fdatawrite_range in v9fs_mmap_vm_close
  mm: don't opencode filemap_fdatawrite_range in filemap_invalidate_inode
  writeback: Add logging for slow writeback (exceeds sysctl_hung_task_timeout_secs)
  writeback: Wake up waiting tasks when finishing the writeback of a chunk.

1 files changed, 44 insertions, 65 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 41741b9c351a..dfc8a31f1222 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -366,83 +366,60 @@ static int filemap_check_and_keep_errors(struct address_space *mapping)
 	return 0;
 }
 
-/**
- * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range
- * @mapping:	address space structure to write
- * @wbc:	the writeback_control controlling the writeout
- *
- * Call writepages on the mapping using the provided wbc to control the
- * writeout.
- *
- * Return: %0 on success, negative error code otherwise.
- */
-int filemap_fdatawrite_wbc(struct address_space *mapping,
-			   struct writeback_control *wbc)
+static int filemap_writeback(struct address_space *mapping, loff_t start,
+		loff_t end, enum writeback_sync_modes sync_mode,
+		long *nr_to_write)
 {
+	struct writeback_control wbc = {
+		.sync_mode	= sync_mode,
+		.nr_to_write	= nr_to_write ? *nr_to_write : LONG_MAX,
+		.range_start	= start,
+		.range_end	= end,
+	};
 	int ret;
 
 	if (!mapping_can_writeback(mapping) ||
 	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
 
-	wbc_attach_fdatawrite_inode(wbc, mapping->host);
-	ret = do_writepages(mapping, wbc);
-	wbc_detach_inode(wbc);
+	wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+	ret = do_writepages(mapping, &wbc);
+	wbc_detach_inode(&wbc);
+
+	if (!ret && nr_to_write)
+		*nr_to_write = wbc.nr_to_write;
 	return ret;
 }
-EXPORT_SYMBOL(filemap_fdatawrite_wbc);
 
 /**
- * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
+ * filemap_fdatawrite_range - start writeback on mapping dirty pages in range
  * @mapping:	address space structure to write
  * @start:	offset in bytes where the range starts
  * @end:	offset in bytes where the range ends (inclusive)
- * @sync_mode:	enable synchronous operation
  *
  * Start writeback against all of a mapping's dirty pages that lie
  * within the byte offsets <start, end> inclusive.
  *
- * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
- * opposed to a regular memory cleansing writeback.  The difference between
- * these two operations is that if a dirty page/buffer is encountered, it must
- * be waited upon, and not just skipped over.
+ * This is a data integrity operation that waits upon dirty or in writeback
+ * pages.
  *
  * Return: %0 on success, negative error code otherwise.
  */
-int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
-				loff_t end, int sync_mode)
-{
-	struct writeback_control wbc = {
-		.sync_mode = sync_mode,
-		.nr_to_write = LONG_MAX,
-		.range_start = start,
-		.range_end = end,
-	};
-
-	return filemap_fdatawrite_wbc(mapping, &wbc);
-}
-
-static inline int __filemap_fdatawrite(struct address_space *mapping,
-	int sync_mode)
+int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+		loff_t end)
 {
-	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
+	return filemap_writeback(mapping, start, end, WB_SYNC_ALL, NULL);
 }
+EXPORT_SYMBOL(filemap_fdatawrite_range);
 
 int filemap_fdatawrite(struct address_space *mapping)
 {
-	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
+	return filemap_fdatawrite_range(mapping, 0, LLONG_MAX);
 }
 EXPORT_SYMBOL(filemap_fdatawrite);
 
-int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
-				loff_t end)
-{
-	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
-}
-EXPORT_SYMBOL(filemap_fdatawrite_range);
-
 /**
- * filemap_fdatawrite_range_kick - start writeback on a range
+ * filemap_flush_range - start writeback on a range
  * @mapping:	target address_space
  * @start:	index to start writeback on
  * @end:	last (inclusive) index for writeback
@@ -452,12 +429,12 @@ EXPORT_SYMBOL(filemap_fdatawrite_range);
  *
  * Return: %0 on success, negative error code otherwise.
  */
-int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
+int filemap_flush_range(struct address_space *mapping, loff_t start,
 				  loff_t end)
 {
-	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
+	return filemap_writeback(mapping, start, end, WB_SYNC_NONE, NULL);
 }
-EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
+EXPORT_SYMBOL_GPL(filemap_flush_range);
 
 /**
  * filemap_flush - mostly a non-blocking flush
@@ -470,10 +447,22 @@ EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
  */
 int filemap_flush(struct address_space *mapping)
 {
-	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
+	return filemap_flush_range(mapping, 0, LLONG_MAX);
 }
 EXPORT_SYMBOL(filemap_flush);
 
+/*
+ * Start writeback on @nr_to_write pages from @mapping.  No one but the existing
+ * btrfs caller should be using this.  Talk to linux-mm if you think adding a
+ * new caller is a good idea.
+ */
+int filemap_flush_nr(struct address_space *mapping, long *nr_to_write)
+{
+	return filemap_writeback(mapping, 0, LLONG_MAX, WB_SYNC_NONE,
+			nr_to_write);
+}
+EXPORT_SYMBOL_FOR_MODULES(filemap_flush_nr, "btrfs");
+
 /**
  * filemap_range_has_page - check if a page exists in range.
  * @mapping:           address space within which to check
@@ -691,8 +680,7 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 		return 0;
 
 	if (mapping_needs_writeback(mapping)) {
-		err = __filemap_fdatawrite_range(mapping, lstart, lend,
-						 WB_SYNC_ALL);
+		err = filemap_fdatawrite_range(mapping, lstart, lend);
 		/*
 		 * Even if the above returned error, the pages may be
 		 * written partially (e.g. -ENOSPC), so we wait for it.
@@ -794,8 +782,7 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
 		return 0;
 
 	if (mapping_needs_writeback(mapping)) {
-		err = __filemap_fdatawrite_range(mapping, lstart, lend,
-						 WB_SYNC_ALL);
+		err = filemap_fdatawrite_range(mapping, lstart, lend);
 		/* See comment of filemap_write_and_wait() */
 		if (err != -EIO)
 			__filemap_fdatawait_range(mapping, lstart, lend);
@@ -4528,16 +4515,8 @@ int filemap_invalidate_inode(struct inode *inode, bool flush,
 	unmap_mapping_pages(mapping, first, nr, false);
 
 	/* Write back the data if we're asked to. */
-	if (flush) {
-		struct writeback_control wbc = {
-			.sync_mode	= WB_SYNC_ALL,
-			.nr_to_write	= LONG_MAX,
-			.range_start	= start,
-			.range_end	= end,
-		};
-
-		filemap_fdatawrite_wbc(mapping, &wbc);
-	}
+	if (flush)
+		filemap_fdatawrite_range(mapping, start, end);
 
 	/* Wait for writeback to complete on all folios and discard. */
 	invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE);