Merge tag 'vfs-7.1-rc1.bh.metadata' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs buffer_head updates from Christian Brauner:
 "This cleans up the mess that has accumulated over the years in
  metadata buffer_head tracking for inodes.

  It moves the tracking into dedicated structure in filesystem-private
  part of the inode (so that we don't use private_list, private_data,
  and private_lock in struct address_space), and also moves couple other
  users of private_data and private_list so these are removed from
  struct address_space saving 3 longs in struct inode for 99% of inodes"

* tag 'vfs-7.1-rc1.bh.metadata' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (42 commits)
  fs: Drop i_private_list from address_space
  fs: Drop mapping_metadata_bhs from address space
  ext4: Track metadata bhs in fs-private inode part
  minix: Track metadata bhs in fs-private inode part
  udf: Track metadata bhs in fs-private inode part
  fat: Track metadata bhs in fs-private inode part
  bfs: Track metadata bhs in fs-private inode part
  affs: Track metadata bhs in fs-private inode part
  ext2: Track metadata bhs in fs-private inode part
  fs: Provide functions for handling mapping_metadata_bhs directly
  fs: Switch inode_has_buffers() to take mapping_metadata_bhs
  fs: Make bhs point to mapping_metadata_bhs
  fs: Move metadata bhs tracking to a separate struct
  fs: Fold fsync_buffers_list() into sync_mapping_buffers()
  fs: Drop osync_buffers_list()
  kvm: Use private inode list instead of i_private_list
  fs: Remove i_private_data
  aio: Stop using i_private_data and i_private_lock
  hugetlbfs: Stop using i_private_data
  fs: Stop using i_private_data for metadata bh tracking
  ...

5 files changed, 13 insertions, 9 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1aa4622f812b..0cf68f85dfd1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1121,6 +1121,7 @@ struct ext4_inode_info {
 	struct rw_semaphore i_data_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
+	struct mapping_metadata_bhs i_metadata_bhs;
 
 	/*
 	 * File creation time. Its function is same as that of
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 05e5946ed9b3..9a8c225f2753 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -390,7 +390,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		}
 	} else {
 		if (inode)
-			mark_buffer_dirty_inode(bh, inode);
+			mmb_mark_buffer_dirty(bh,
+					      &EXT4_I(inode)->i_metadata_bhs);
 		else
 			mark_buffer_dirty(bh);
 		if (inode && inode_needs_sync(inode)) {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index bd8f230fa507..924726dcc85f 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -68,7 +68,7 @@ static int ext4_sync_parent(struct inode *inode)
 		 * through ext4_evict_inode()) and so we are safe to flush
 		 * metadata blocks and the inode.
 		 */
-		ret = sync_mapping_buffers(inode->i_mapping);
+		ret = mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
 		if (ret)
 			break;
 		ret = sync_inode_metadata(inode, 1);
@@ -89,7 +89,8 @@ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
 	};
 	int ret;
 
-	ret = generic_buffers_fsync_noflush(file, start, end, datasync);
+	ret = mmb_fsync_noflush(file, &EXT4_I(inode)->i_metadata_bhs,
+				start, end, datasync);
 	if (ret)
 		return ret;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 01679d96cd0f..f78cf5f23835 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -195,7 +195,9 @@ void ext4_evict_inode(struct inode *inode)
 			ext4_warning_inode(inode, "data will be lost");
 
 		truncate_inode_pages_final(&inode->i_data);
-
+		/* Avoid mballoc special inode which has no proper iops */
+		if (!EXT4_SB(inode->i_sb)->s_journal)
+			mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
 		goto no_delete;
 	}
 
@@ -1430,9 +1432,6 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 /*
  * We need to pick up the new inode size which generic_commit_write gave us
  * `iocb` can be NULL - eg, when called from page_symlink().
- *
- * ext4 never places buffers on inode->i_mapping->i_private_list.  metadata
- * buffers are managed internally.
  */
 static int ext4_write_end(const struct kiocb *iocb,
 			  struct address_space *mapping,
@@ -3447,7 +3446,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 	}
 
 	/* Any metadata buffers to write? */
-	if (!list_empty(&inode->i_mapping->i_private_list))
+	if (mmb_has_buffers(&EXT4_I(inode)->i_metadata_bhs))
 		return true;
 	return inode_state_read_once(inode) & I_DIRTY_DATASYNC;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8ca399c15970..578508eb4f1a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1424,6 +1424,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
 	ext4_fc_init_inode(&ei->vfs_inode);
 	spin_lock_init(&ei->i_fc_lock);
+	mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data);
 	return &ei->vfs_inode;
 }
 
@@ -1520,7 +1521,8 @@ static void destroy_inodecache(void)
 void ext4_clear_inode(struct inode *inode)
 {
 	ext4_fc_del(inode);
-	invalidate_inode_buffers(inode);
+	if (!EXT4_SB(inode->i_sb)->s_journal)
+		mmb_invalidate(&EXT4_I(inode)->i_metadata_bhs);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
 	/*