Commit b1b4705d authored by Matthew Bobrowski's avatar Matthew Bobrowski Committed by Theodore Ts'o
Browse files

ext4: introduce direct I/O read using iomap infrastructure 



This patch introduces a new direct I/O read path which makes use of
the iomap infrastructure.

The new function ext4_do_read_iter() is responsible for calling into
the iomap infrastructure via iomap_dio_rw(). If the read operation
performed on the inode is not supported, which is checked via
ext4_dio_supported(), then we simply fallback and complete the I/O
using buffered I/O.

Existing direct I/O read code path has been removed, as it is now
redundant.

Signed-off-by: default avatarMatthew Bobrowski <mbobrowski@mbobrowski.org>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Reviewed-by: default avatarRitesh Harjani <riteshh@linux.ibm.com>
Link: https://lore.kernel.org/r/f98a6f73fadddbfbad0fc5ed04f712ca0b799f37.1572949325.git.mbobrowski@mbobrowski.org


Signed-off-by: default avatarTheodore Ts'o <tytso@mit.edu>
parent 09edf4d3

fs/ext4/file.c

+53 −2
Original line number Diff line number Diff line
@@ -34,6 +34,52 @@ 
#include "xattr.h"

#include "acl.h"



static bool ext4_dio_supported(struct inode *inode)

{

	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))

		return false;

	if (fsverity_active(inode))

		return false;

	if (ext4_should_journal_data(inode))

		return false;

	if (ext4_has_inline_data(inode))

		return false;

	return true;

}



static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)

{

	ssize_t ret;

	struct inode *inode = file_inode(iocb->ki_filp);



	if (iocb->ki_flags & IOCB_NOWAIT) {

		if (!inode_trylock_shared(inode))

			return -EAGAIN;

	} else {

		inode_lock_shared(inode);

	}



	if (!ext4_dio_supported(inode)) {

		inode_unlock_shared(inode);

		/*

		 * Fallback to buffered I/O if the operation being performed on

		 * the inode is not supported by direct I/O. The IOCB_DIRECT

		 * flag needs to be cleared here in order to ensure that the

		 * direct I/O path within generic_file_read_iter() is not

		 * taken.

		 */

		iocb->ki_flags &= ~IOCB_DIRECT;

		return generic_file_read_iter(iocb, to);

	}



	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,

			   is_sync_kiocb(iocb));

	inode_unlock_shared(inode);



	file_accessed(iocb->ki_filp);

	return ret;

}



#ifdef CONFIG_FS_DAX

static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)

{
@@ -64,16 +110,21 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) 


static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)

{

	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))

	struct inode *inode = file_inode(iocb->ki_filp);



	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))

		return -EIO;



	if (!iov_iter_count(to))

		return 0; /* skip atime */



#ifdef CONFIG_FS_DAX

	if (IS_DAX(file_inode(iocb->ki_filp)))

	if (IS_DAX(inode))

		return ext4_dax_read_iter(iocb, to);

#endif

	if (iocb->ki_flags & IOCB_DIRECT)

		return ext4_dio_read_iter(iocb, to);



	return generic_file_read_iter(iocb, to);

}

fs/ext4/inode.c

+1 −37
Original line number Diff line number Diff line
@@ -863,9 +863,6 @@ int ext4_dio_get_block(struct inode *inode, sector_t iblock, 
{

	/* We don't expect handle for direct IO */

	WARN_ON_ONCE(ext4_journal_current_handle());



	if (!create)

		return _ext4_get_block(inode, iblock, bh, 0);

	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);

}
@@ -3916,36 +3913,6 @@ out: 
	return ret;

}



static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)

{

	struct address_space *mapping = iocb->ki_filp->f_mapping;

	struct inode *inode = mapping->host;

	size_t count = iov_iter_count(iter);

	ssize_t ret;



	/*

	 * Shared inode_lock is enough for us - it protects against concurrent

	 * writes & truncates and since we take care of writing back page cache,

	 * we are protected against page writeback as well.

	 */

	if (iocb->ki_flags & IOCB_NOWAIT) {

		if (!inode_trylock_shared(inode))

			return -EAGAIN;

	} else {

		inode_lock_shared(inode);

	}



	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,

					   iocb->ki_pos + count - 1);

	if (ret)

		goto out_unlock;

	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,

				   iter, ext4_dio_get_block, NULL, NULL, 0);

out_unlock:

	inode_unlock_shared(inode);

	return ret;

}



static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)

{

	struct file *file = iocb->ki_filp;
@@ -3972,9 +3939,6 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) 
		return 0;



	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));

	if (iov_iter_rw(iter) == READ)

		ret = ext4_direct_IO_read(iocb, iter);

	else

	ret = ext4_direct_IO_write(iocb, iter);

	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);

	return ret;

CRA Git | Maintained and supported by SUSTech CRA and CCSE