Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 923ae0ff authored by Ross Zwisler's avatar Ross Zwisler Committed by Linus Torvalds
Browse files

ext4: add DAX functionality 



This is a port of the DAX functionality found in the current version of
ext2.

[matthew.r.wilcox@intel.com: heavily tweaked]
[akpm@linux-foundation.org: remap_pages went away]
Signed-off-by: default avatarRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: default avatarAndreas Dilger <andreas.dilger@intel.com>
Signed-off-by: default avatarMatthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 25726bc1

Documentation/filesystems/dax.txt

+1 −0
Original line number Diff line number Diff line
@@ -73,6 +73,7 @@ or a write()) work correctly. 


These filesystems may be used for inspiration:

- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt

- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt





Shortcomings

Documentation/filesystems/ext4.txt

+4 −0
Original line number Diff line number Diff line
@@ -386,6 +386,10 @@ max_dir_size_kb=n This limits the size of directories so that any 
i_version		Enable 64-bit inode version support. This option is

			off by default.



dax			Use direct access (no page cache).  See

			Documentation/filesystems/dax.txt.  Note that

			this option is incompatible with data=journal.



Data Mode

=========

There are 3 different data modes:

fs/ext4/ext4.h

+6 −0
Original line number Diff line number Diff line
@@ -965,6 +965,11 @@ struct ext4_inode_info { 
#define EXT4_MOUNT_ERRORS_MASK		0x00070

#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */

#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/

#ifdef CONFIG_FS_DAX

#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */

#else

#define EXT4_MOUNT_DAX			0

#endif

#define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */

#define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */

#define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
@@ -2578,6 +2583,7 @@ extern const struct file_operations ext4_dir_operations; 
/* file.c */

extern const struct inode_operations ext4_file_inode_operations;

extern const struct file_operations ext4_file_operations;

extern const struct file_operations ext4_dax_file_operations;

extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);



/* inline.c */

fs/ext4/file.c

+47 −2
Original line number Diff line number Diff line
@@ -95,7 +95,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) 
	struct inode *inode = file_inode(iocb->ki_filp);

	struct mutex *aio_mutex = NULL;

	struct blk_plug plug;

	int o_direct = file->f_flags & O_DIRECT;

	int o_direct = io_is_direct(file);

	int overwrite = 0;

	size_t length = iov_iter_count(from);

	ssize_t ret;
@@ -191,6 +191,26 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) 
	return ret;

}



#ifdef CONFIG_FS_DAX

static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)

{

	return dax_fault(vma, vmf, ext4_get_block);

					/* Is this the right get_block? */

}



static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)

{

	return dax_mkwrite(vma, vmf, ext4_get_block);

}



static const struct vm_operations_struct ext4_dax_vm_ops = {

	.fault		= ext4_dax_fault,

	.page_mkwrite	= ext4_dax_mkwrite,

};

#else

#define ext4_dax_vm_ops	ext4_file_vm_ops

#endif



static const struct vm_operations_struct ext4_file_vm_ops = {

	.fault		= filemap_fault,

	.map_pages	= filemap_map_pages,
@@ -200,7 +220,12 @@ static const struct vm_operations_struct ext4_file_vm_ops = { 
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)

{

	file_accessed(file);

	if (IS_DAX(file_inode(file))) {

		vma->vm_ops = &ext4_dax_vm_ops;

		vma->vm_flags |= VM_MIXEDMAP;

	} else {

		vma->vm_ops = &ext4_file_vm_ops;

	}

	return 0;

}
@@ -599,6 +624,26 @@ const struct file_operations ext4_file_operations = { 
	.fallocate	= ext4_fallocate,

};



#ifdef CONFIG_FS_DAX

const struct file_operations ext4_dax_file_operations = {

	.llseek		= ext4_llseek,

	.read		= new_sync_read,

	.write		= new_sync_write,

	.read_iter	= generic_file_read_iter,

	.write_iter	= ext4_file_write_iter,

	.unlocked_ioctl = ext4_ioctl,

#ifdef CONFIG_COMPAT

	.compat_ioctl	= ext4_compat_ioctl,

#endif

	.mmap		= ext4_file_mmap,

	.open		= ext4_file_open,

	.release	= ext4_release_file,

	.fsync		= ext4_sync_file,

	/* Splice not yet supported with DAX */

	.fallocate	= ext4_fallocate,

};

#endif



const struct inode_operations ext4_file_inode_operations = {

	.setattr	= ext4_setattr,

	.getattr	= ext4_getattr,

fs/ext4/indirect.c

+13 −5
Original line number Diff line number Diff line
@@ -689,12 +689,20 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, 
			inode_dio_done(inode);

			goto locked;

		}

		if (IS_DAX(inode))

			ret = dax_do_io(rw, iocb, inode, iter, offset,

					ext4_get_block, NULL, 0);

		else

			ret = __blockdev_direct_IO(rw, iocb, inode,

					inode->i_sb->s_bdev, iter, offset,

					ext4_get_block, NULL, NULL, 0);

		inode_dio_done(inode);

	} else {

locked:

		if (IS_DAX(inode))

			ret = dax_do_io(rw, iocb, inode, iter, offset,

					ext4_get_block, NULL, DIO_LOCKING);

		else

			ret = blockdev_direct_IO(rw, iocb, inode, iter,

					offset, ext4_get_block);