[PATCH 3/3] minix: convert file operations to iomap and add direct I/O

[Jeremy Bingham]

Replace the generic file read/write iterators with iomap-aware
versions.  Buffered reads go through iomap_bio_read_folio (via the
aops read_folio), and buffered writes now use iomap_file_buffered_write
instead of the generic_file_write_iter path.

Add direct I/O support: minix_dio_read_iter and minix_dio_write_iter
implement DIO read and write paths using iomap_dio_rw, with a
write_end_io callback that updates i_size and marks the inode dirty.
Unaligned or extending DIO writes fall back to buffered I/O via
iomap_file_buffered_write after the DIO portion completes.

The minix_file_open hook sets FMODE_CAN_ODIRECT so that the VFS allows
O_DIRECT opens.  splice_write is added via iter_file_splice_write.

Signed-off-by: Jeremy Bingham <jbingham@xxxxxxxxx>
---
 fs/minix/file.c | 153 ++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 149 insertions(+), 4 deletions(-)

diff --git a/fs/minix/file.c b/fs/minix/file.c
index 86e5943cd2ff..1f4217115401 100644
--- a/fs/minix/file.c
+++ b/fs/minix/file.c
@@ -17,17 +17,162 @@ int minix_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			start, end, datasync);
 }
 
+static ssize_t minix_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	ssize_t ret;
+
+	inode_lock_shared(inode);
+
+	const struct iomap_ops *ops = minix_iomap_ops_ver(inode);
+
+	ret = iomap_dio_rw(iocb, to, ops, NULL, 0, NULL, 0);
+	inode_unlock_shared(inode);
+	return ret;
+}
+
+static int minix_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error,
+		unsigned int flags)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t pos = iocb->ki_pos;
+
+	if (error)
+		return error;
+
+	pos += size;
+	if (size && pos > i_size_read(inode)) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+	return 0;
+}
+
+static const struct iomap_dio_ops minix_dio_write_ops = {
+	.end_io = minix_dio_write_end_io,
+};
+
+static ssize_t minix_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	ssize_t ret;
+	unsigned int flags = 0;
+	unsigned long blocksize = inode->i_sb->s_blocksize;
+
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out_unlock;
+
+	ret = kiocb_modified(iocb);
+	if (ret)
+		goto out_unlock;
+
+	if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+		!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize))
+		flags |= IOMAP_DIO_FORCE_WAIT;
+
+	const struct iomap_ops *ops = minix_iomap_ops_ver(inode);
+
+	ret = iomap_dio_rw(iocb, from, ops,
+		&minix_dio_write_ops, flags, NULL, 0);
+	if (ret == -ENOTBLK)
+		ret = 0; /* fallback to buffered */
+
+	if (ret >= 0 && iov_iter_count(from)) {
+		loff_t pos;
+		loff_t endbyte;
+		ssize_t status;
+
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		pos = iocb->ki_pos;
+		status = iomap_file_buffered_write(iocb, from, ops,
+			NULL, NULL);
+		if (unlikely(status < 0)) {
+			ret = status;
+			goto out_unlock;
+		}
+
+		ret += status;
+		endbyte = pos + status - 1;
+		status = filemap_write_and_wait_range(inode->i_mapping, pos, endbyte);
+		if (!status) {
+			invalidate_mapping_pages(inode->i_mapping,
+				pos >> PAGE_SHIFT,
+				endbyte >> PAGE_SHIFT);
+			if (ret > 0)
+				ret = generic_write_sync(iocb, ret);
+		} else {
+			ret = status;
+		}
+	}
+
+out_unlock:
+	inode_unlock(inode);
+	return ret;
+}
+
+static ssize_t minix_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return minix_dio_read_iter(iocb, to);
+
+	return generic_file_read_iter(iocb, to);
+}
+
+static ssize_t minix_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	ssize_t ret;
+
+	/* minix_dio_write_iter also locks the inode and appears to do the same
+	 * general sorts of checks as this, so just return directly from there.
+	 */
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return minix_dio_write_iter(iocb, from);
+
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto unlock;
+
+	ret = file_modified(iocb->ki_filp);
+	if (ret)
+		goto unlock;
+
+	const struct iomap_ops *ops = minix_iomap_ops_ver(inode);
+
+	ret = iomap_file_buffered_write(iocb, from, ops,
+			NULL, NULL);
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+
+unlock:
+	inode_unlock(inode);
+	return ret;
+}
+
+static int minix_file_open(struct inode *inode, struct file *filp)
+{
+	filp->f_mode |= FMODE_CAN_ODIRECT;
+	return generic_file_open(inode, filp);
+}
+
 /*
- * We have mostly NULLs here: the current defaults are OK for
- * the minix filesystem.
+ * We still have some NULLs here, but not as many of the current defaults are
+ * still OK for the minix filesystem.
  */
+
 const struct file_operations minix_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read_iter	= generic_file_read_iter,
-	.write_iter	= generic_file_write_iter,
+	.read_iter	= minix_file_read_iter,
+	.write_iter	= minix_file_write_iter,
 	.mmap_prepare	= generic_file_mmap_prepare,
+	.open		= minix_file_open,
 	.fsync		= minix_fsync,
 	.splice_read	= filemap_splice_read,
+	.splice_write	= iter_file_splice_write,
 };
 
 static int minix_setattr(struct mnt_idmap *idmap,
-- 
2.47.3