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
  ...

block/bdev.c

@@ -417,19 +417,11 @@ static void init_once(void *data)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static void bdev_evict_inode(struct inode *inode)
-{
-	truncate_inode_pages_final(&inode->i_data);
-	invalidate_inode_buffers(inode); /* is it needed here? */
-	clear_inode(inode);
-}
-
 static const struct super_operations bdev_sops = {
 	.statfs = simple_statfs,
 	.alloc_inode = bdev_alloc_inode,
 	.free_inode = bdev_free_inode,
 	.drop_inode = inode_just_drop,
-	.evict_inode = bdev_evict_inode,
 };
 
 static int bd_init_fs_context(struct fs_context *fc)

fs/adfs/dir.c

@@ -389,7 +389,7 @@ const struct file_operations adfs_dir_operations = {
 	.read		= generic_read_dir,
 	.llseek		= generic_file_llseek,
 	.iterate_shared	= adfs_iterate,
-	.fsync		= generic_file_fsync,
+	.fsync		= simple_fsync,
 };
 
 static int

fs/adfs/file.c

@@ -26,7 +26,7 @@ const struct file_operations adfs_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
 	.mmap_prepare	= generic_file_mmap_prepare,
-	.fsync		= generic_file_fsync,
+	.fsync		= simple_fsync,
 	.write_iter	= generic_file_write_iter,
 	.splice_read	= filemap_splice_read,
 };

fs/affs/affs.h

@@ -44,6 +44,7 @@ struct affs_inode_info {
 	struct mutex i_link_lock;		/* Protects internal inode access. */
 	struct mutex i_ext_lock;		/* Protects internal inode access. */
 #define i_hash_lock i_ext_lock
+	struct mapping_metadata_bhs i_metadata_bhs;
 	u32	 i_blkcnt;			/* block count */
 	u32	 i_extcnt;			/* extended block count */
 	u32	*i_lc;				/* linear cache of extended blocks */
@@ -151,6 +152,7 @@ extern bool	affs_nofilenametruncate(const struct dentry *dentry);
 extern int	affs_check_name(const unsigned char *name, int len,
 				bool notruncate);
 extern int	affs_copy_name(unsigned char *bstr, struct dentry *dentry);
+struct mapping_metadata_bhs *affs_get_metadata_bhs(struct inode *inode);
 
 /* bitmap. c */
 

fs/affs/amigaffs.c

@@ -57,7 +57,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh)
 		AFFS_TAIL(sb, dir_bh)->hash_chain = cpu_to_be32(ino);
 
 	affs_adjust_checksum(dir_bh, ino);
-	mark_buffer_dirty_inode(dir_bh, dir);
+	mmb_mark_buffer_dirty(dir_bh, &AFFS_I(dir)->i_metadata_bhs);
 	affs_brelse(dir_bh);
 
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -100,7 +100,7 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
 			else
 				AFFS_TAIL(sb, bh)->hash_chain = ino;
 			affs_adjust_checksum(bh, be32_to_cpu(ino) - hash_ino);
-			mark_buffer_dirty_inode(bh, dir);
+			mmb_mark_buffer_dirty(bh, &AFFS_I(dir)->i_metadata_bhs);
 			AFFS_TAIL(sb, rem_bh)->parent = 0;
 			retval = 0;
 			break;
@@ -180,7 +180,7 @@ affs_remove_link(struct dentry *dentry)
 			affs_unlock_dir(dir);
 			goto done;
 		}
-		mark_buffer_dirty_inode(link_bh, inode);
+		mmb_mark_buffer_dirty(link_bh, &AFFS_I(inode)->i_metadata_bhs);
 
 		memcpy(AFFS_TAIL(sb, bh)->name, AFFS_TAIL(sb, link_bh)->name, 32);
 		retval = affs_insert_hash(dir, bh);
@@ -188,7 +188,7 @@ affs_remove_link(struct dentry *dentry)
 			affs_unlock_dir(dir);
 			goto done;
 		}
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 
 		affs_unlock_dir(dir);
 		iput(dir);
@@ -203,7 +203,7 @@ affs_remove_link(struct dentry *dentry)
 			__be32 ino2 = AFFS_TAIL(sb, link_bh)->link_chain;
 			AFFS_TAIL(sb, bh)->link_chain = ino2;
 			affs_adjust_checksum(bh, be32_to_cpu(ino2) - link_ino);
-			mark_buffer_dirty_inode(bh, inode);
+			mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 			retval = 0;
 			/* Fix the link count, if bh is a normal header block without links */
 			switch (be32_to_cpu(AFFS_TAIL(sb, bh)->stype)) {
@@ -306,7 +306,7 @@ affs_remove_header(struct dentry *dentry)
 	retval = affs_remove_hash(dir, bh);
 	if (retval)
 		goto done_unlock;
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 
 	affs_unlock_dir(dir);
 

fs/affs/file.c

@@ -140,14 +140,14 @@ affs_alloc_extblock(struct inode *inode, struct buffer_head *bh, u32 ext)
 	AFFS_TAIL(sb, new_bh)->parent = cpu_to_be32(inode->i_ino);
 	affs_fix_checksum(sb, new_bh);
 
-	mark_buffer_dirty_inode(new_bh, inode);
+	mmb_mark_buffer_dirty(new_bh, &AFFS_I(inode)->i_metadata_bhs);
 
 	tmp = be32_to_cpu(AFFS_TAIL(sb, bh)->extension);
 	if (tmp)
 		affs_warning(sb, "alloc_ext", "previous extension set (%x)", tmp);
 	AFFS_TAIL(sb, bh)->extension = cpu_to_be32(blocknr);
 	affs_adjust_checksum(bh, blocknr - tmp);
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 
 	AFFS_I(inode)->i_extcnt++;
 	mark_inode_dirty(inode);
@@ -581,7 +581,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		memset(AFFS_DATA(bh) + boff, 0, tmp);
 		be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
 		affs_fix_checksum(sb, bh);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 		size += tmp;
 		bidx++;
 	} else if (bidx) {
@@ -603,7 +603,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 		affs_fix_checksum(sb, bh);
 		bh->b_state &= ~(1UL << BH_New);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 		if (prev_bh) {
 			u32 tmp_next = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
 
@@ -613,7 +613,8 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 					     bidx, tmp_next);
 			AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
 			affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
-			mark_buffer_dirty_inode(prev_bh, inode);
+			mmb_mark_buffer_dirty(prev_bh,
+					      &AFFS_I(inode)->i_metadata_bhs);
 			affs_brelse(prev_bh);
 		}
 		size += bsize;
@@ -732,7 +733,7 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
 			max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
 		affs_fix_checksum(sb, bh);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 		written += tmp;
 		from += tmp;
 		bidx++;
@@ -765,12 +766,13 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
 						     bidx, tmp_next);
 				AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
 				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
-				mark_buffer_dirty_inode(prev_bh, inode);
+				mmb_mark_buffer_dirty(prev_bh,
+					&AFFS_I(inode)->i_metadata_bhs);
 			}
 		}
 		affs_brelse(prev_bh);
 		affs_fix_checksum(sb, bh);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 		written += bsize;
 		from += bsize;
 		bidx++;
@@ -799,13 +801,14 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
 						     bidx, tmp_next);
 				AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
 				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
-				mark_buffer_dirty_inode(prev_bh, inode);
+				mmb_mark_buffer_dirty(prev_bh,
+						&AFFS_I(inode)->i_metadata_bhs);
 			}
 		} else if (be32_to_cpu(AFFS_DATA_HEAD(bh)->size) < tmp)
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 		affs_brelse(prev_bh);
 		affs_fix_checksum(sb, bh);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 		written += tmp;
 		from += tmp;
 		bidx++;
@@ -942,7 +945,7 @@ affs_truncate(struct inode *inode)
 	}
 	AFFS_TAIL(sb, ext_bh)->extension = 0;
 	affs_fix_checksum(sb, ext_bh);
-	mark_buffer_dirty_inode(ext_bh, inode);
+	mmb_mark_buffer_dirty(ext_bh, &AFFS_I(inode)->i_metadata_bhs);
 	affs_brelse(ext_bh);
 
 	if (inode->i_size) {

fs/affs/inode.c

@@ -206,7 +206,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		}
 	}
 	affs_fix_checksum(sb, bh);
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 	affs_brelse(bh);
 	affs_free_prealloc(inode);
 	return 0;
@@ -267,9 +267,11 @@ affs_evict_inode(struct inode *inode)
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		affs_truncate(inode);
+	} else {
+		mmb_sync(&AFFS_I(inode)->i_metadata_bhs);
 	}
 
-	invalidate_inode_buffers(inode);
+	mmb_invalidate(&AFFS_I(inode)->i_metadata_bhs);
 	clear_inode(inode);
 	affs_free_prealloc(inode);
 	cache_page = (unsigned long)AFFS_I(inode)->i_lc;
@@ -304,7 +306,7 @@ affs_new_inode(struct inode *dir)
 	bh = affs_getzeroblk(sb, block);
 	if (!bh)
 		goto err_bh;
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 	affs_brelse(bh);
 
 	inode->i_uid     = current_fsuid();
@@ -392,17 +394,17 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
 		AFFS_TAIL(sb, bh)->link_chain = chain;
 		AFFS_TAIL(sb, inode_bh)->link_chain = cpu_to_be32(block);
 		affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain));
-		mark_buffer_dirty_inode(inode_bh, inode);
+		mmb_mark_buffer_dirty(inode_bh, &AFFS_I(inode)->i_metadata_bhs);
 		set_nlink(inode, 2);
 		ihold(inode);
 	}
 	affs_fix_checksum(sb, bh);
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 	dentry->d_fsdata = (void *)(long)bh->b_blocknr;
 
 	affs_lock_dir(dir);
 	retval = affs_insert_hash(dir, bh);
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 	affs_unlock_dir(dir);
 	affs_unlock_link(inode);
 

fs/affs/namei.c

@@ -373,7 +373,7 @@ affs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	}
 	*p = 0;
 	inode->i_size = i + 1;
-	mark_buffer_dirty_inode(bh, inode);
+	mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
 	affs_brelse(bh);
 	mark_inode_dirty(inode);
 
@@ -443,7 +443,8 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	/* TODO: move it back to old_dir, if error? */
 
 done:
-	mark_buffer_dirty_inode(bh, retval ? old_dir : new_dir);
+	mmb_mark_buffer_dirty(bh,
+			&AFFS_I(retval ? old_dir : new_dir)->i_metadata_bhs);
 	affs_brelse(bh);
 	return retval;
 }
@@ -496,8 +497,8 @@ affs_xrename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = affs_insert_hash(old_dir, bh_new);
 	affs_unlock_dir(old_dir);
 done:
-	mark_buffer_dirty_inode(bh_old, new_dir);
-	mark_buffer_dirty_inode(bh_new, old_dir);
+	mmb_mark_buffer_dirty(bh_old, &AFFS_I(new_dir)->i_metadata_bhs);
+	mmb_mark_buffer_dirty(bh_new, &AFFS_I(old_dir)->i_metadata_bhs);
 	affs_brelse(bh_old);
 	affs_brelse(bh_new);
 	return retval;

fs/affs/super.c

@@ -108,6 +108,7 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
 	i->i_lc = NULL;
 	i->i_ext_bh = NULL;
 	i->i_pa_cnt = 0;
+	mmb_init(&i->i_metadata_bhs, &i->vfs_inode.i_data);
 
 	return &i->vfs_inode;
 }

fs/aio.c

@@ -218,6 +218,17 @@ struct aio_kiocb {
 	struct eventfd_ctx	*ki_eventfd;
 };
 
+struct aio_inode_info {
+	struct inode vfs_inode;
+	spinlock_t migrate_lock;
+	struct kioctx *ctx;
+};
+
+static inline struct aio_inode_info *AIO_I(struct inode *inode)
+{
+	return container_of(inode, struct aio_inode_info, vfs_inode);
+}
+
 /*------ sysctl variables----*/
 static DEFINE_SPINLOCK(aio_nr_lock);
 static unsigned long aio_nr;		/* current system wide number of aio requests */
@@ -251,6 +262,7 @@ static void __init aio_sysctl_init(void)
 
 static struct kmem_cache	*kiocb_cachep;
 static struct kmem_cache	*kioctx_cachep;
+static struct kmem_cache	*aio_inode_cachep;
 
 static struct vfsmount *aio_mnt;
 
@@ -261,11 +273,12 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
 	struct file *file;
 	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
+
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
-	inode->i_mapping->i_private_data = ctx;
+	AIO_I(inode)->ctx = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
@@ -275,14 +288,49 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	return file;
 }
 
+static struct inode *aio_alloc_inode(struct super_block *sb)
+{
+	struct aio_inode_info *ai;
+
+	ai = alloc_inode_sb(sb, aio_inode_cachep, GFP_KERNEL);
+	if (!ai)
+		return NULL;
+	ai->ctx = NULL;
+
+	return &ai->vfs_inode;
+}
+
+static void aio_free_inode(struct inode *inode)
+{
+	kmem_cache_free(aio_inode_cachep, AIO_I(inode));
+}
+
+static const struct super_operations aio_super_operations = {
+	.alloc_inode	= aio_alloc_inode,
+	.free_inode	= aio_free_inode,
+	.statfs		= simple_statfs,
+};
+
 static int aio_init_fs_context(struct fs_context *fc)
 {
-	if (!init_pseudo(fc, AIO_RING_MAGIC))
+	struct pseudo_fs_context *pfc;
+
+	pfc = init_pseudo(fc, AIO_RING_MAGIC);
+	if (!pfc)
 		return -ENOMEM;
 	fc->s_iflags |= SB_I_NOEXEC;
+	pfc->ops = &aio_super_operations;
 	return 0;
 }
 
+static void init_once(void *obj)
+{
+	struct aio_inode_info *ai = obj;
+
+	inode_init_once(&ai->vfs_inode);
+	spin_lock_init(&ai->migrate_lock);
+}
+
 /* aio_setup
  *	Creates the slab caches used by the aio routines, panic on
  *	failure as this is done early during the boot sequence.
@@ -294,6 +342,11 @@ static int __init aio_setup(void)
 		.init_fs_context = aio_init_fs_context,
 		.kill_sb	= kill_anon_super,
 	};
+
+	aio_inode_cachep = kmem_cache_create("aio_inode_cache",
+				sizeof(struct aio_inode_info), 0,
+				(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT),
+				init_once);
 	aio_mnt = kern_mount(&aio_fs);
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
@@ -308,17 +361,17 @@ __initcall(aio_setup);
 static void put_aio_ring_file(struct kioctx *ctx)
 {
 	struct file *aio_ring_file = ctx->aio_ring_file;
-	struct address_space *i_mapping;
 
 	if (aio_ring_file) {
-		truncate_setsize(file_inode(aio_ring_file), 0);
+		struct inode *inode = file_inode(aio_ring_file);
+
+		truncate_setsize(inode, 0);
 
 		/* Prevent further access to the kioctx from migratepages */
-		i_mapping = aio_ring_file->f_mapping;
-		spin_lock(&i_mapping->i_private_lock);
-		i_mapping->i_private_data = NULL;
+		spin_lock(&AIO_I(inode)->migrate_lock);
+		AIO_I(inode)->ctx = NULL;
 		ctx->aio_ring_file = NULL;
-		spin_unlock(&i_mapping->i_private_lock);
+		spin_unlock(&AIO_I(inode)->migrate_lock);
 
 		fput(aio_ring_file);
 	}
@@ -408,13 +461,14 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 			struct folio *src, enum migrate_mode mode)
 {
 	struct kioctx *ctx;
+	struct aio_inode_info *ai = AIO_I(mapping->host);
 	unsigned long flags;
 	pgoff_t idx;
 	int rc = 0;
 
-	/* mapping->i_private_lock here protects against the kioctx teardown.  */
-	spin_lock(&mapping->i_private_lock);
-	ctx = mapping->i_private_data;
+	/* ai->migrate_lock here protects against the kioctx teardown.  */
+	spin_lock(&ai->migrate_lock);
+	ctx = ai->ctx;
 	if (!ctx) {
 		rc = -EINVAL;
 		goto out;
@@ -467,7 +521,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 out_unlock:
 	mutex_unlock(&ctx->ring_lock);
 out:
-	spin_unlock(&mapping->i_private_lock);
+	spin_unlock(&ai->migrate_lock);
 	return rc;
 }
 #else

fs/bfs/bfs.h

@@ -35,6 +35,7 @@ struct bfs_inode_info {
 	unsigned long i_dsk_ino; /* inode number from the disk, can be 0 */
 	unsigned long i_sblock;
 	unsigned long i_eblock;
+	struct mapping_metadata_bhs i_metadata_bhs;
 	struct inode vfs_inode;
 };
 

fs/bfs/dir.c

@@ -68,10 +68,17 @@ static int bfs_readdir(struct file *f, struct dir_context *ctx)
 	return 0;
 }
 
+static int bfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	return mmb_fsync(file,
+			&BFS_I(file->f_mapping->host)->i_metadata_bhs,
+			start, end, datasync);
+}
+
 const struct file_operations bfs_dir_operations = {
 	.read		= generic_read_dir,
 	.iterate_shared	= bfs_readdir,
-	.fsync		= generic_file_fsync,
+	.fsync		= bfs_fsync,
 	.llseek		= generic_file_llseek,
 };
 
@@ -186,7 +193,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
 		set_nlink(inode, 1);
 	}
 	de->ino = 0;
-	mark_buffer_dirty_inode(bh, dir);
+	mmb_mark_buffer_dirty(bh, &BFS_I(dir)->i_metadata_bhs);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 	mark_inode_dirty(dir);
 	inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
@@ -246,7 +253,7 @@ static int bfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		inode_set_ctime_current(new_inode);
 		inode_dec_link_count(new_inode);
 	}
-	mark_buffer_dirty_inode(old_bh, old_dir);
+	mmb_mark_buffer_dirty(old_bh, &BFS_I(old_dir)->i_metadata_bhs);
 	error = 0;
 
 end_rename:
@@ -296,7 +303,8 @@ static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino)
 				for (i = 0; i < BFS_NAMELEN; i++)
 					de->name[i] =
 						(i < namelen) ? name[i] : 0;
-				mark_buffer_dirty_inode(bh, dir);
+				mmb_mark_buffer_dirty(bh,
+						&BFS_I(dir)->i_metadata_bhs);
 				brelse(bh);
 				return 0;
 			}

fs/bfs/inode.c

@@ -187,7 +187,9 @@ static void bfs_evict_inode(struct inode *inode)
 	dprintf("ino=%08lx\n", ino);
 
 	truncate_inode_pages_final(&inode->i_data);
-	invalidate_inode_buffers(inode);
+	if (inode->i_nlink)
+		mmb_sync(&BFS_I(inode)->i_metadata_bhs);
+	mmb_invalidate(&BFS_I(inode)->i_metadata_bhs);
 	clear_inode(inode);
 
 	if (inode->i_nlink)
@@ -257,6 +259,8 @@ static struct inode *bfs_alloc_inode(struct super_block *sb)
 	bi = alloc_inode_sb(sb, bfs_inode_cachep, GFP_KERNEL);
 	if (!bi)
 		return NULL;
+	mmb_init(&bi->i_metadata_bhs, &bi->vfs_inode.i_data);
+
 	return &bi->vfs_inode;
 }
 

fs/exfat/file.c

@@ -577,7 +577,7 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
 		return -EIO;
 
-	err = __generic_file_fsync(filp, start, end, datasync);
+	err = simple_fsync_noflush(filp, start, end, datasync);
 	if (err)
 		return err;
 

fs/exfat/inode.c

@@ -695,7 +695,6 @@ void exfat_evict_inode(struct inode *inode)
 		mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock);
 	}
 
-	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	exfat_cache_inval_inode(inode);
 	exfat_unhash_inode(inode);

fs/ext2/ext2.h

@@ -676,6 +676,7 @@ struct ext2_inode_info {
 #ifdef CONFIG_QUOTA
 	struct dquot __rcu *i_dquot[MAXQUOTAS];
 #endif
+	struct mapping_metadata_bhs i_metadata_bhs;
 };
 
 /*

fs/ext2/file.c

@@ -156,9 +156,11 @@ static int ext2_release_file (struct inode * inode, struct file * filp)
 int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	int ret;
-	struct super_block *sb = file->f_mapping->host->i_sb;
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
 
-	ret = generic_buffers_fsync(file, start, end, datasync);
+	ret = mmb_fsync(file, &EXT2_I(inode)->i_metadata_bhs,
+			start, end, datasync);
 	if (ret == -EIO)
 		/* We don't really know where the IO error happened... */
 		ext2_error(sb, __func__,

fs/ext2/inode.c

@@ -94,9 +94,10 @@ void ext2_evict_inode(struct inode * inode)
 		if (inode->i_blocks)
 			ext2_truncate_blocks(inode, 0);
 		ext2_xattr_delete_inode(inode);
+	} else {
+		mmb_sync(&EXT2_I(inode)->i_metadata_bhs);
 	}
-
-	invalidate_inode_buffers(inode);
+	mmb_invalidate(&EXT2_I(inode)->i_metadata_bhs);
 	clear_inode(inode);
 
 	ext2_discard_reservation(inode);
@@ -526,7 +527,7 @@ static int ext2_alloc_branch(struct inode *inode,
 		}
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
-		mark_buffer_dirty_inode(bh, inode);
+		mmb_mark_buffer_dirty(bh, &EXT2_I(inode)->i_metadata_bhs);
 		/* We used to sync bh here if IS_SYNC(inode).
 		 * But we now rely upon generic_write_sync()
 		 * and b_inode_buffers.  But not for directories.
@@ -597,7 +598,7 @@ static void ext2_splice_branch(struct inode *inode,
 
 	/* had we spliced it onto indirect block? */
 	if (where->bh)
-		mark_buffer_dirty_inode(where->bh, inode);
+		mmb_mark_buffer_dirty(where->bh, &EXT2_I(inode)->i_metadata_bhs);
 
 	inode_set_ctime_current(inode);
 	mark_inode_dirty(inode);
@@ -1210,7 +1211,8 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 		if (partial == chain)
 			mark_inode_dirty(inode);
 		else
-			mark_buffer_dirty_inode(partial->bh, inode);
+			mmb_mark_buffer_dirty(partial->bh,
+					      &EXT2_I(inode)->i_metadata_bhs);
 		ext2_free_branches(inode, &nr, &nr+1, (chain+n-1) - partial);
 	}
 	/* Clear the ends of indirect blocks on the shared branch */
@@ -1219,7 +1221,8 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 				   partial->p + 1,
 				   (__le32*)partial->bh->b_data+addr_per_block,
 				   (chain+n-1) - partial);
-		mark_buffer_dirty_inode(partial->bh, inode);
+		mmb_mark_buffer_dirty(partial->bh,
+				      &EXT2_I(inode)->i_metadata_bhs);
 		brelse (partial->bh);
 		partial--;
 	}
@@ -1302,7 +1305,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	if (inode_needs_sync(inode)) {
-		sync_mapping_buffers(inode->i_mapping);
+		mmb_sync(&EXT2_I(inode)->i_metadata_bhs);
 		sync_inode_metadata(inode, 1);
 	} else {
 		mark_inode_dirty(inode);

fs/ext2/super.c

@@ -215,6 +215,7 @@ static struct inode *ext2_alloc_inode(struct super_block *sb)
 #ifdef CONFIG_QUOTA
 	memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
 #endif
+	mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data);
 
 	return &ei->vfs_inode;
 }