Merge tag 'vfs-7.3-rc1.sync' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs writeback updates from Christian Brauner:
 "This makes sync_inode_metadata() and writeback_single_inode() persist
  not only the inode but all metadata associated with it.

  A new .sync_inode_metadata superblock operation is called from
  __writeback_single_inode(). Alongside it a new I_METADATA_WRITEBACK
  state flag is added.

  Filesystems no longer need their own mmb_fsync() implementations and
  can just use simple_fsync(). All metadata is now written for IS_SYNC
  and IS_DIRSYNC inodes. Races where several fsyncs raced and mmb_sync()
  could return before all buffers were really persisted are fixed since
  I_SYNC now serializes properly.

  The I_METADATA_WRITEBACK scheme also fixes the case where a
  WB_SYNC_NONE writeback landing between write(2) and fsync(2) left
  fsync(2) failing to persist the inode. That problem is not specific to
  filesystems using the generic metadata bh tracking, and the ones that
  do not are left alone.

  ext2, udf, bfs, minix, fat and ext4 in nojournal mode have their data
  integrity writeout fixed and are converted. affs drops metadata bh
  tracking and mmb_fsync() is removed.

  A few other fixes came out of this:

   - a UAF in mark_buffer_write_io_error()

   - missed inode writeback when racing with __writeback_single_inode()

   - ext4 allocating the mapping_metadata_bhs struct on demand

   - three fat fixes: a lost inode update in do_msdos_rename() with
     DIRSYNC, inode buffer write errors not propagating out of
     fat_sync_inode_metadata() and directory entries not being
     persisted on fsync(2) of the root directory"

* tag 'vfs-7.3-rc1.sync' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  writeback: Export __inode_attach_wb()
  fat: Fix persisting directory entries on fsync(2) of the root directory
  fat: Propagate inode buffer write errors from fat_sync_inode_metadata()
  fat: Fix lost inode update in do_msdos_rename() with DIRSYNC
  vfs: Remove mmb_fsync()
  fat: Replace fat_sync_inode() with sync_inode_metadata()
  fat: Fix missed inode writeback during fsync(2)
  ext4: Fix data integrity writeout issues in nojournal mode
  minix: Fix data integrity writeout issues
  bfs: Fix data integrity writeout issues
  udf: Fold udf_update_inode() into udf_write_inode()
  udf: Use sync_inode_metadata() in udf_evict_inode()
  udf: Drop udf_sync_inode()
  udf: Use sync_inode_metadata() to writeout IS_SYNC inode
  udf: Fix data integrity writeout issues
  ext2: Fix data integrity writeout issues
  ext2: Avoid unnecessary inode buffer writeback for sync(2)
  ext2: Drop __ext2_write_inode()
  ext2: Fix lost inode updates for IS_SYNC inodes
  fs: Provide way for filesystem to wait for metadata writeback
  ...

3 files changed, 11 insertions, 5 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 8b23bc9a244c..fd2c7115c054 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -210,10 +210,6 @@ void bh_end_async_write(struct bio *bio);
 
 /* Things to do with metadata buffers list */
 void mmb_mark_buffer_dirty(struct buffer_head *bh, struct mapping_metadata_bhs *mmb);
-int mmb_fsync_noflush(struct file *file, struct mapping_metadata_bhs *mmb,
-		      loff_t start, loff_t end, bool datasync);
-int mmb_fsync(struct file *file, struct mapping_metadata_bhs *mmb,
-	      loff_t start, loff_t end, bool datasync);
 void clean_bdev_aliases(struct block_device *bdev, sector_t block,
 			sector_t len);
 static inline void clean_bdev_bh_alias(struct buffer_head *bh)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 04b00f53adc4..8e9bc9dda0cb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -740,7 +740,8 @@ enum inode_state_flags_enum {
 	I_CREATING		= (1U << 15),
 	I_DONTCACHE		= (1U << 16),
 	I_SYNC_QUEUED		= (1U << 17),
-	I_PINNING_NETFS_WB	= (1U << 18)
+	I_PINNING_NETFS_WB	= (1U << 18),
+	I_METADATA_WRITEBACK	= (1U << 19),
 };
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
@@ -2211,6 +2212,13 @@ static inline void mark_inode_dirty_sync(struct inode *inode)
 	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 }
 
+static inline void set_inode_metadata_writeback(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	inode_state_set(inode, I_METADATA_WRITEBACK);
+	spin_unlock(&inode->i_lock);
+}
+
 /*
  * returns the refcount on the inode. it can change arbitrarily.
  */
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index c8172558750f..a8da89a51401 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -87,6 +87,8 @@ struct super_operations {
 	void (*free_inode)(struct inode *inode);
 	void (*dirty_inode)(struct inode *inode, int flags);
 	int (*write_inode)(struct inode *inode, struct writeback_control *wbc);
+	int (*sync_inode_metadata)(struct inode *inode,
+				   struct writeback_control *wbc);
 	int (*drop_inode)(struct inode *inode);
 	void (*evict_inode)(struct inode *inode);
 	void (*put_super)(struct super_block *sb);