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.

4 files changed, 19 insertions, 7 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index c5c9d89c73ed..610ef62b6a32 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -63,6 +63,8 @@ enum wb_reason {
 struct wb_completion {
 	atomic_t		cnt;
 	wait_queue_head_t	*waitq;
+	unsigned long progress_stamp;	/* The jiffies when slow progress is detected */
+	unsigned long wait_start;	/* The jiffies when waiting for the writeback work to finish */
 };
 
 #define __WB_COMPLETION_INIT(_waitq)	\
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc70673b55bb..1011b82977fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1642,6 +1642,7 @@ struct super_block {
 
 	spinlock_t		s_inode_wblist_lock;
 	struct list_head	s_inodes_wb;	/* writeback inodes */
+	long			s_min_writeback_pages;
 } __randomize_layout;
 
 static inline struct user_namespace *i_user_ns(const struct inode *inode)
@@ -3075,7 +3076,7 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
 extern int __must_check file_check_and_advance_wb_err(struct file *file);
 extern int __must_check file_write_and_wait_range(struct file *file,
 						loff_t start, loff_t end);
-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);
 
 static inline int file_write_and_wait(struct file *file)
@@ -3112,8 +3113,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
 		struct address_space *mapping = iocb->ki_filp->f_mapping;
 
-		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
-					      iocb->ki_pos - 1);
+		filemap_flush_range(mapping, iocb->ki_pos - count,
+				iocb->ki_pos - 1);
 	}
 
 	return count;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7274a86b4871..378eedadc3ee 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -38,6 +38,7 @@ int filemap_invalidate_pages(struct address_space *mapping,
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);
 int filemap_flush(struct address_space *);
+int filemap_flush_nr(struct address_space *mapping, long *nr_to_write);
 int filemap_fdatawait_keep_errors(struct address_space *mapping);
 int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend);
 int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
@@ -53,14 +54,10 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend);
 int filemap_write_and_wait_range(struct address_space *mapping,
 		loff_t lstart, loff_t lend);
-int __filemap_fdatawrite_range(struct address_space *mapping,
-		loff_t start, loff_t end, int sync_mode);
 int filemap_fdatawrite_range(struct address_space *mapping,
 		loff_t start, loff_t end);
 int filemap_check_errors(struct address_space *mapping);
 void __filemap_set_wb_err(struct address_space *mapping, int err);
-int filemap_fdatawrite_wbc(struct address_space *mapping,
-			   struct writeback_control *wbc);
 int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
 
 static inline int filemap_write_and_wait(struct address_space *mapping)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 102071ffedcb..f48e8ccffe81 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -189,6 +189,13 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
 void inode_wait_for_writeback(struct inode *inode);
 void inode_io_list_del(struct inode *inode);
 
+static inline xa_mark_t wbc_to_tag(struct writeback_control *wbc)
+{
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		return PAGECACHE_TAG_TOWRITE;
+	return PAGECACHE_TAG_DIRTY;
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 #include <linux/cgroup.h>
@@ -367,4 +374,9 @@ bool redirty_page_for_writepage(struct writeback_control *, struct page *);
 void sb_mark_inode_writeback(struct inode *inode);
 void sb_clear_inode_writeback(struct inode *inode);
 
+/*
+ * 4MB minimal write chunk size
+ */
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_SHIFT - 10))
+
 #endif		/* WRITEBACK_H */