fs: add CONFIG_BUFFER_HEAD

Add a new config option that controls building the buffer_head code, and
select it from all file systems and stacking drivers that need it.

For the block device nodes and alternative iomap based buffered I/O path
is provided when buffer_head support is not enabled, and iomap needs a
a small tweak to define the IOMAP_F_BUFFER_HEAD flag to 0 to not call
into the buffer_head code when it doesn't exist.

Otherwise this is just Kconfig and ifdef changes.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20230801172201.1923299-7-hch@lst.deSigned-off-by: Jens Axboe <axboe@kernel.dk>

block/fops.c

@@ -24,15 +24,6 @@ static inline struct inode *bdev_file_inode(struct file *file)
 	return file->f_mapping->host;
 }
 
-static int blkdev_get_block(struct inode *inode, sector_t iblock,
-		struct buffer_head *bh, int create)
-{
-	bh->b_bdev = I_BDEV(inode);
-	bh->b_blocknr = iblock;
-	set_buffer_mapped(bh);
-	return 0;
-}
-
 static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
 {
 	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
@@ -400,7 +391,7 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	iomap->type = IOMAP_MAPPED;
 	iomap->addr = iomap->offset;
 	iomap->length = isize - iomap->offset;
-	iomap->flags |= IOMAP_F_BUFFER_HEAD;
+	iomap->flags |= IOMAP_F_BUFFER_HEAD; /* noop for !CONFIG_BUFFER_HEAD */
 	return 0;
 }
 
@@ -408,6 +399,16 @@ static const struct iomap_ops blkdev_iomap_ops = {
 	.iomap_begin		= blkdev_iomap_begin,
 };
 
+#ifdef CONFIG_BUFFER_HEAD
+static int blkdev_get_block(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh, int create)
+{
+	bh->b_bdev = I_BDEV(inode);
+	bh->b_blocknr = iblock;
+	set_buffer_mapped(bh);
+	return 0;
+}
+
 static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, blkdev_get_block, wbc);
@@ -453,6 +454,55 @@ const struct address_space_operations def_blk_aops = {
 	.migrate_folio	= buffer_migrate_folio_norefs,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
+#else /* CONFIG_BUFFER_HEAD */
+static int blkdev_read_folio(struct file *file, struct folio *folio)
+{
+	return iomap_read_folio(folio, &blkdev_iomap_ops);
+}
+
+static void blkdev_readahead(struct readahead_control *rac)
+{
+	iomap_readahead(rac, &blkdev_iomap_ops);
+}
+
+static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
+		struct inode *inode, loff_t offset)
+{
+	loff_t isize = i_size_read(inode);
+
+	if (WARN_ON_ONCE(offset >= isize))
+		return -EIO;
+	if (offset >= wpc->iomap.offset &&
+	    offset < wpc->iomap.offset + wpc->iomap.length)
+		return 0;
+	return blkdev_iomap_begin(inode, offset, isize - offset,
+				  IOMAP_WRITE, &wpc->iomap, NULL);
+}
+
+static const struct iomap_writeback_ops blkdev_writeback_ops = {
+	.map_blocks		= blkdev_map_blocks,
+};
+
+static int blkdev_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct iomap_writepage_ctx wpc = { };
+
+	return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
+}
+
+const struct address_space_operations def_blk_aops = {
+	.dirty_folio	= filemap_dirty_folio,
+	.release_folio		= iomap_release_folio,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.read_folio		= blkdev_read_folio,
+	.readahead		= blkdev_readahead,
+	.writepages		= blkdev_writepages,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
+	.migrate_folio		= filemap_migrate_folio,
+};
+#endif /* CONFIG_BUFFER_HEAD */
 
 /*
  * for a block special file file_inode(file)->i_size is zero

drivers/md/Kconfig

@@ -15,6 +15,7 @@ if MD
 config BLK_DEV_MD
 	tristate "RAID support"
 	select BLOCK_HOLDER_DEPRECATED if SYSFS
+	select BUFFER_HEAD
 	# BLOCK_LEGACY_AUTOLOAD requirement should be removed
 	# after relevant mdadm enhancements - to make "names=yes"
 	# the default - are widely available.

fs/Kconfig

@@ -18,8 +18,12 @@ config VALIDATE_FS_PARSER
 config FS_IOMAP
 	bool
 
+config BUFFER_HEAD
+	bool
+
 # old blockdev_direct_IO implementation.  Use iomap for new code instead
 config LEGACY_DIRECT_IO
+	depends on BUFFER_HEAD
 	bool
 
 if BLOCK

fs/Makefile

@@ -17,7 +17,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
 		kernel_read_file.o mnt_idmapping.o remap_range.o
 
-obj-$(CONFIG_BLOCK)		+= buffer.o mpage.o
+obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o
 obj-$(CONFIG_LEGACY_DIRECT_IO)	+= direct-io.o
 obj-y				+= notify/

fs/adfs/Kconfig

@@ -2,6 +2,7 @@
 config ADFS_FS
 	tristate "ADFS file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  The Acorn Disc Filing System is the standard file system of the
 	  RiscOS operating system which runs on Acorn's ARM-based Risc PC

fs/affs/Kconfig

@@ -2,6 +2,7 @@
 config AFFS_FS
 	tristate "Amiga FFS file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select LEGACY_DIRECT_IO
 	help
 	  The Fast File System (FFS) is the common file system used on hard

fs/befs/Kconfig

@@ -2,6 +2,7 @@
 config BEFS_FS
 	tristate "BeOS file system (BeFS) support (read only)"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select NLS
 	help
 	  The BeOS File System (BeFS) is the native file system of Be, Inc's

fs/bfs/Kconfig

@@ -2,6 +2,7 @@
 config BFS_FS
 	tristate "BFS file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  Boot File System (BFS) is a file system used under SCO UnixWare to
 	  allow the bootloader access to the kernel image and other important

fs/efs/Kconfig

@@ -2,6 +2,7 @@
 config EFS_FS
 	tristate "EFS file system support (read only)"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  EFS is an older file system used for non-ISO9660 CD-ROMs and hard
 	  disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer

fs/exfat/Kconfig

@@ -2,6 +2,7 @@
 
 config EXFAT_FS
 	tristate "exFAT filesystem support"
+	select BUFFER_HEAD
 	select NLS
 	select LEGACY_DIRECT_IO
 	help

fs/ext2/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config EXT2_FS
 	tristate "Second extended fs support"
+	select BUFFER_HEAD
 	select FS_IOMAP
 	select LEGACY_DIRECT_IO
 	help

fs/ext4/Kconfig

@@ -28,6 +28,7 @@ config EXT3_FS_SECURITY
 
 config EXT4_FS
 	tristate "The Extended 4 (ext4) filesystem"
+	select BUFFER_HEAD
 	select JBD2
 	select CRC16
 	select CRYPTO

fs/f2fs/Kconfig

@@ -2,6 +2,7 @@
 config F2FS_FS
 	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select NLS
 	select CRYPTO
 	select CRYPTO_CRC32

fs/fat/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config FAT_FS
 	tristate
+	select BUFFER_HEAD
 	select NLS
 	select LEGACY_DIRECT_IO
 	help

fs/freevxfs/Kconfig

@@ -2,6 +2,7 @@
 config VXFS_FS
 	tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  FreeVxFS is a file system driver that support the VERITAS VxFS(TM)
 	  file system format.  VERITAS VxFS(TM) is the standard file system

fs/gfs2/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config GFS2_FS
 	tristate "GFS2 file system support"
+	select BUFFER_HEAD
 	select FS_POSIX_ACL
 	select CRC32
 	select LIBCRC32C

fs/hfs/Kconfig

@@ -2,6 +2,7 @@
 config HFS_FS
 	tristate "Apple Macintosh file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select NLS
 	select LEGACY_DIRECT_IO
 	help

fs/hfsplus/Kconfig

@@ -2,6 +2,7 @@
 config HFSPLUS_FS
 	tristate "Apple Extended HFS file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select NLS
 	select NLS_UTF8
 	select LEGACY_DIRECT_IO

fs/hpfs/Kconfig

@@ -2,6 +2,7 @@
 config HPFS_FS
 	tristate "OS/2 HPFS file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select FS_IOMAP
 	help
 	  OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS

fs/isofs/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config ISO9660_FS
 	tristate "ISO 9660 CDROM file system support"
+	select BUFFER_HEAD
 	help
 	  This is the standard file system used on CD-ROMs.  It was previously
 	  known as "High Sierra File System" and is called "hsfs" on other

fs/jfs/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config JFS_FS
 	tristate "JFS filesystem support"
+	select BUFFER_HEAD
 	select NLS
 	select CRC32
 	select LEGACY_DIRECT_IO

fs/minix/Kconfig

@@ -2,6 +2,7 @@
 config MINIX_FS
 	tristate "Minix file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  Minix is a simple operating system used in many classes about OS's.
 	  The minix file system (method to organize files on a hard disk

fs/nilfs2/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config NILFS2_FS
 	tristate "NILFS2 file system support"
+	select BUFFER_HEAD
 	select CRC32
 	select LEGACY_DIRECT_IO
 	help

fs/ntfs/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config NTFS_FS
 	tristate "NTFS file system support"
+	select BUFFER_HEAD
 	select NLS
 	help
 	  NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003.

fs/ntfs3/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config NTFS3_FS
 	tristate "NTFS Read-Write file system support"
+	select BUFFER_HEAD
 	select NLS
 	select LEGACY_DIRECT_IO
 	help

fs/ocfs2/Kconfig

@@ -2,6 +2,7 @@
 config OCFS2_FS
 	tristate "OCFS2 file system support"
 	depends on INET && SYSFS && CONFIGFS_FS
+	select BUFFER_HEAD
 	select JBD2
 	select CRC32
 	select QUOTA

fs/omfs/Kconfig

@@ -2,6 +2,7 @@
 config OMFS_FS
 	tristate "SonicBlue Optimized MPEG File System support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	select CRC_ITU_T
 	help
 	  This is the proprietary file system used by the Rio Karma music

fs/qnx4/Kconfig

@@ -2,6 +2,7 @@
 config QNX4FS_FS
 	tristate "QNX4 file system support (read only)"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  This is the file system used by the real-time operating systems
 	  QNX 4 and QNX 6 (the latter is also called QNX RTP).

fs/qnx6/Kconfig

@@ -2,6 +2,7 @@
 config QNX6FS_FS
 	tristate "QNX6 file system support (read only)"
 	depends on BLOCK && CRC32
+	select BUFFER_HEAD
 	help
 	  This is the file system used by the real-time operating systems
 	  QNX 6 (also called QNX RTP).

fs/reiserfs/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config REISERFS_FS
 	tristate "Reiserfs support (deprecated)"
+	select BUFFER_HEAD
 	select CRC32
 	select LEGACY_DIRECT_IO
 	help

fs/sysv/Kconfig

@@ -2,6 +2,7 @@
 config SYSV_FS
 	tristate "System V/Xenix/V7/Coherent file system support"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  SCO, Xenix and Coherent are commercial Unix systems for Intel
 	  machines, and Version 7 was used on the DEC PDP-11. Saying Y

fs/udf/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config UDF_FS
 	tristate "UDF file system support"
+	select BUFFER_HEAD
 	select CRC_ITU_T
 	select NLS
 	select LEGACY_DIRECT_IO

fs/ufs/Kconfig

@@ -2,6 +2,7 @@
 config UFS_FS
 	tristate "UFS file system support (read only)"
 	depends on BLOCK
+	select BUFFER_HEAD
 	help
 	  BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD,
 	  OpenBSD and NeXTstep) use a file system called UFS. Some System V

include/linux/buffer_head.h

@@ -16,8 +16,6 @@
 #include <linux/wait.h>
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BLOCK
-
 enum bh_state_bits {
 	BH_Uptodate,	/* Contains valid data */
 	BH_Dirty,	/* Is dirty */
@@ -198,7 +196,6 @@ void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset);
 void folio_set_bh(struct buffer_head *bh, struct folio *folio,
 		  unsigned long offset);
-bool try_to_free_buffers(struct folio *);
 struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
 					bool retry);
 struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
@@ -213,10 +210,6 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
-int inode_has_buffers(struct inode *);
-void invalidate_inode_buffers(struct inode *);
-int remove_inode_buffers(struct inode *inode);
-int sync_mapping_buffers(struct address_space *mapping);
 int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
 				  bool datasync);
 int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
@@ -240,9 +233,6 @@ void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
-void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(void);
-bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
@@ -258,8 +248,6 @@ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
 void __bh_read_batch(int nr, struct buffer_head *bhs[],
 		     blk_opf_t op_flags, bool force_lock);
 
-extern int buffer_heads_over_limit;
-
 /*
  * Generic address_space_operations implementations for buffer_head-backed
  * address_spaces.
@@ -304,8 +292,6 @@ extern int buffer_migrate_folio_norefs(struct address_space *,
 #define buffer_migrate_folio_norefs NULL
 #endif
 
-void buffer_init(void);
-
 /*
  * inline definitions
  */
@@ -465,7 +451,20 @@ __bread(struct block_device *bdev, sector_t block, unsigned size)
 
 bool block_dirty_folio(struct address_space *mapping, struct folio *folio);
 
-#else /* CONFIG_BLOCK */
+#ifdef CONFIG_BUFFER_HEAD
+
+void buffer_init(void);
+bool try_to_free_buffers(struct folio *folio);
+int inode_has_buffers(struct inode *inode);
+void invalidate_inode_buffers(struct inode *inode);
+int remove_inode_buffers(struct inode *inode);
+int sync_mapping_buffers(struct address_space *mapping);
+void invalidate_bh_lrus(void);
+void invalidate_bh_lrus_cpu(void);
+bool has_bh_in_lru(int cpu, void *dummy);
+extern int buffer_heads_over_limit;
+
+#else /* CONFIG_BUFFER_HEAD */
 
 static inline void buffer_init(void) {}
 static inline bool try_to_free_buffers(struct folio *folio) { return true; }
@@ -473,9 +472,10 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bh_lrus(void) {}
 static inline void invalidate_bh_lrus_cpu(void) {}
 static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
-#endif /* CONFIG_BLOCK */
+#endif /* CONFIG_BUFFER_HEAD */
 #endif /* _LINUX_BUFFER_HEAD_H */

include/linux/iomap.h

@@ -58,7 +58,11 @@ struct vm_fault;
 #define IOMAP_F_DIRTY		(1U << 1)
 #define IOMAP_F_SHARED		(1U << 2)
 #define IOMAP_F_MERGED		(1U << 3)
+#ifdef CONFIG_BUFFER_HEAD
 #define IOMAP_F_BUFFER_HEAD	(1U << 4)
+#else
+#define IOMAP_F_BUFFER_HEAD	0
+#endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
 
 /*

include/trace/events/block.h

@@ -12,6 +12,7 @@
 
 #define RWBS_LEN	8
 
+#ifdef CONFIG_BUFFER_HEAD
 DECLARE_EVENT_CLASS(block_buffer,
 
 	TP_PROTO(struct buffer_head *bh),
@@ -61,6 +62,7 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer,
 
 	TP_ARGS(bh)
 );
+#endif /* CONFIG_BUFFER_HEAD */
 
 /**
  * block_rq_requeue - place block IO request back on a queue

mm/migrate.c

@@ -684,7 +684,7 @@ int migrate_folio(struct address_space *mapping, struct folio *dst,
 }
 EXPORT_SYMBOL(migrate_folio);
 
-#ifdef CONFIG_BLOCK
+#ifdef CONFIG_BUFFER_HEAD
 /* Returns true if all buffers are successfully locked */
 static bool buffer_migrate_lock_buffers(struct buffer_head *head,
 							enum migrate_mode mode)
@@ -837,7 +837,7 @@ int buffer_migrate_folio_norefs(struct address_space *mapping,
 	return __buffer_migrate_folio(mapping, dst, src, mode, true);
 }
 EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs);
-#endif
+#endif /* CONFIG_BUFFER_HEAD */
 
 int filemap_migrate_folio(struct address_space *mapping,
 		struct folio *dst, struct folio *src, enum migrate_mode mode)