ext4: add DAX functionality

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

[[email protected]: heavily tweaked]
[[email protected]: remap_pages went away]
Signed-off-by: Ross Zwisler <[email protected]>
Reviewed-by: Andreas Dilger <[email protected]>
Signed-off-by: Matthew Wilcox <[email protected]>
Cc: Boaz Harrosh <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Theodore Ts'o <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/filesystems/dax.txt

@@ -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

@@ -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

@@ -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

@@ -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);
-	vma->vm_ops = &ext4_file_vm_ops;
+	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

@@ -689,14 +689,22 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 			inode_dio_done(inode);
 			goto locked;
 		}
-		ret = __blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iter, offset,
-				 ext4_get_block, NULL, NULL, 0);
+		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:
-		ret = blockdev_direct_IO(rw, iocb, inode, iter,
-				 offset, ext4_get_block);
+		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);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);

fs/ext4/inode.c

@@ -657,6 +657,18 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	return retval;
 }
 
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+	struct inode *inode = bh->b_assoc_map->host;
+	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+	int err;
+	if (!uptodate)
+		return;
+	WARN_ON(!buffer_unwritten(bh));
+	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -694,6 +706,11 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+			bh->b_assoc_map = inode->i_mapping;
+			bh->b_private = (void *)(unsigned long)iblock;
+			bh->b_end_io = ext4_end_io_unwritten;
+		}
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -3010,13 +3027,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
-	ret = __blockdev_direct_IO(rw, iocb, inode,
-				   inode->i_sb->s_bdev, iter,
-				   offset,
-				   get_block_func,
-				   ext4_end_io_dio,
-				   NULL,
-				   dio_flags);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+				ext4_end_io_dio, dio_flags);
+	else
+		ret = __blockdev_direct_IO(rw, iocb, inode,
+					   inode->i_sb->s_bdev, iter, offset,
+					   get_block_func,
+					   ext4_end_io_dio, NULL, dio_flags);
 
 	/*
 	 * Put our reference to io_end. This can free the io_end structure e.g.
@@ -3180,19 +3198,12 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_aops;
 }
 
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-static int ext4_block_zero_page_range(handle_t *handle,
+static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
+	unsigned blocksize, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3205,14 +3216,6 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
 
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
@@ -3277,6 +3280,33 @@ static int ext4_block_zero_page_range(handle_t *handle,
 	return err;
 }
 
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+static int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
+	struct inode *inode = mapping->host;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize = inode->i_sb->s_blocksize;
+	unsigned max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	if (IS_DAX(inode))
+		return dax_zero_page_range(inode, from, length, ext4_get_block);
+	return __ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
 /*
  * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
@@ -3798,8 +3828,10 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4052,7 +4084,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &ext4_dir_inode_operations;
@@ -4534,7 +4569,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
 		 */
-			truncate_pagecache(inode, inode->i_size);
+		truncate_pagecache(inode, inode->i_size);
 	}
 	/*
 	 * We want to call ext4_truncate() even if attr->ia_size ==

fs/ext4/namei.c

@@ -2235,7 +2235,10 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))
@@ -2299,7 +2302,10 @@ static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		d_tmpfile(dentry, inode);
 		err = ext4_orphan_add(handle, inode);