1 files changed, 114 insertions, 356 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a314fc7b56fa..65d27a502909 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -48,40 +48,6 @@
 static const struct vm_operations_struct xfs_file_vm_ops;
 
 /*
- * Locking primitives for read and write IO paths to ensure we consistently use
- * and order the inode->i_mutex, ip->i_lock and ip->i_iolock.
- */
-static inline void
-xfs_rw_ilock(
-	struct xfs_inode	*ip,
-	int			type)
-{
-	if (type & XFS_IOLOCK_EXCL)
-		inode_lock(VFS_I(ip));
-	xfs_ilock(ip, type);
-}
-
-static inline void
-xfs_rw_iunlock(
-	struct xfs_inode	*ip,
-	int			type)
-{
-	xfs_iunlock(ip, type);
-	if (type & XFS_IOLOCK_EXCL)
-		inode_unlock(VFS_I(ip));
-}
-
-static inline void
-xfs_rw_ilock_demote(
-	struct xfs_inode	*ip,
-	int			type)
-{
-	xfs_ilock_demote(ip, type);
-	if (type & XFS_IOLOCK_EXCL)
-		inode_unlock(VFS_I(ip));
-}
-
-/*
  * Clear the specified ranges to zero through either the pagecache or DAX.
  * Holes and unwritten extents will be left as-is as they already are zeroed.
  */
@@ -183,19 +149,16 @@ xfs_file_fsync(
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
-	if (mp->m_flags & XFS_MOUNT_BARRIER) {
-		/*
-		 * If we have an RT and/or log subvolume we need to make sure
-		 * to flush the write cache the device used for file data
-		 * first.  This is to ensure newly written file data make
-		 * it to disk before logging the new inode size in case of
-		 * an extending write.
-		 */
-		if (XFS_IS_REALTIME_INODE(ip))
-			xfs_blkdev_issue_flush(mp->m_rtdev_targp);
-		else if (mp->m_logdev_targp != mp->m_ddev_targp)
-			xfs_blkdev_issue_flush(mp->m_ddev_targp);
-	}
+	/*
+	 * If we have an RT and/or log subvolume we need to make sure to flush
+	 * the write cache the device used for file data first.  This is to
+	 * ensure newly written file data make it to disk before logging the new
+	 * inode size in case of an extending write.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip))
+		xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+	else if (mp->m_logdev_targp != mp->m_ddev_targp)
+		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	/*
 	 * All metadata updates are logged, which means that we just have to
@@ -230,10 +193,8 @@ xfs_file_fsync(
 	 * an already allocated file and thus do not have any metadata to
 	 * commit.
 	 */
-	if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
-	    mp->m_logdev_targp == mp->m_ddev_targp &&
-	    !XFS_IS_REALTIME_INODE(ip) &&
-	    !log_flushed)
+	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
+	    mp->m_logdev_targp == mp->m_ddev_targp)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	return error;
@@ -244,87 +205,20 @@ xfs_file_dio_aio_read(
 	struct kiocb		*iocb,
 	struct iov_iter		*to)
 {
-	struct address_space	*mapping = iocb->ki_filp->f_mapping;
-	struct inode		*inode = mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	loff_t			isize = i_size_read(inode);
+	struct xfs_inode	*ip = XFS_I(file_inode(iocb->ki_filp));
 	size_t			count = iov_iter_count(to);
-	struct iov_iter		data;
-	struct xfs_buftarg	*target;
-	ssize_t			ret = 0;
+	ssize_t			ret;
 
 	trace_xfs_file_direct_read(ip, count, iocb->ki_pos);
 
 	if (!count)
 		return 0; /* skip atime */
 
-	if (XFS_IS_REALTIME_INODE(ip))
-		target = ip->i_mount->m_rtdev_targp;
-	else
-		target = ip->i_mount->m_ddev_targp;
-
-	/* DIO must be aligned to device logical sector size */
-	if ((iocb->ki_pos | count) & target->bt_logical_sectormask) {
-		if (iocb->ki_pos == isize)
-			return 0;
-		return -EINVAL;
-	}
-
 	file_accessed(iocb->ki_filp);
 
-	/*
-	 * Locking is a bit tricky here. If we take an exclusive lock for direct
-	 * IO, we effectively serialise all new concurrent read IO to this file
-	 * and block it behind IO that is currently in progress because IO in
-	 * progress holds the IO lock shared. We only need to hold the lock
-	 * exclusive to blow away the page cache, so only take lock exclusively
-	 * if the page cache needs invalidation. This allows the normal direct
-	 * IO case of no page cache pages to proceeed concurrently without
-	 * serialisation.
-	 */
-	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	if (mapping->nrpages) {
-		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
-
-		/*
-		 * The generic dio code only flushes the range of the particular
-		 * I/O. Because we take an exclusive lock here, this whole
-		 * sequence is considerably more expensive for us. This has a
-		 * noticeable performance impact for any file with cached pages,
-		 * even when outside of the range of the particular I/O.
-		 *
-		 * Hence, amortize the cost of the lock against a full file
-		 * flush and reduce the chances of repeated iolock cycles going
-		 * forward.
-		 */
-		if (mapping->nrpages) {
-			ret = filemap_write_and_wait(mapping);
-			if (ret) {
-				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
-				return ret;
-			}
-
-			/*
-			 * Invalidate whole pages. This can return an error if
-			 * we fail to invalidate a page, but this should never
-			 * happen on XFS. Warn if it does fail.
-			 */
-			ret = invalidate_inode_pages2(mapping);
-			WARN_ON_ONCE(ret);
-			ret = 0;
-		}
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
-	}
-
-	data = *to;
-	ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data,
-			xfs_get_blocks_direct, NULL, NULL, 0);
-	if (ret >= 0) {
-		iocb->ki_pos += ret;
-		iov_iter_advance(to, ret);
-	}
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
 }
@@ -343,9 +237,9 @@ xfs_file_dax_read(
 	if (!count)
 		return 0; /* skip atime */
 
-	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	file_accessed(iocb->ki_filp);
 	return ret;
@@ -361,9 +255,9 @@ xfs_file_buffered_aio_read(
 
 	trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);
 
-	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	ret = generic_file_read_iter(iocb, to);
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
 }
@@ -444,15 +338,18 @@ restart:
 	if (error <= 0)
 		return error;
 
-	error = xfs_break_layouts(inode, iolock, true);
+	error = xfs_break_layouts(inode, iolock);
 	if (error)
 		return error;
 
-	/* For changing security info in file_remove_privs() we need i_mutex */
+	/*
+	 * For changing security info in file_remove_privs() we need i_rwsem
+	 * exclusively.
+	 */
 	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
-		xfs_rw_iunlock(ip, *iolock);
+		xfs_iunlock(ip, *iolock);
 		*iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, *iolock);
+		xfs_ilock(ip, *iolock);
 		goto restart;
 	}
 	/*
@@ -477,9 +374,9 @@ restart:
 		spin_unlock(&ip->i_flags_lock);
 		if (!drained_dio) {
 			if (*iolock == XFS_IOLOCK_SHARED) {
-				xfs_rw_iunlock(ip, *iolock);
+				xfs_iunlock(ip, *iolock);
 				*iolock = XFS_IOLOCK_EXCL;
-				xfs_rw_ilock(ip, *iolock);
+				xfs_ilock(ip, *iolock);
 				iov_iter_reexpand(from, count);
 			}
 			/*
@@ -522,6 +419,58 @@ restart:
 	return 0;
 }
 
+static int
+xfs_dio_write_end_io(
+	struct kiocb		*iocb,
+	ssize_t			size,
+	unsigned		flags)
+{
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	loff_t			offset = iocb->ki_pos;
+	bool			update_size = false;
+	int			error = 0;
+
+	trace_xfs_end_io_direct_write(ip, offset, size);
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	if (size <= 0)
+		return size;
+
+	/*
+	 * We need to update the in-core inode size here so that we don't end up
+	 * with the on-disk inode size being outside the in-core inode size. We
+	 * have no other method of updating EOF for AIO, so always do it here
+	 * if necessary.
+	 *
+	 * We need to lock the test/set EOF update as we can be racing with
+	 * other IO completions here to update the EOF. Failing to serialise
+	 * here can result in EOF moving backwards and Bad Things Happen when
+	 * that occurs.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	if (offset + size > i_size_read(inode)) {
+		i_size_write(inode, offset + size);
+		update_size = true;
+	}
+	spin_unlock(&ip->i_flags_lock);
+
+	if (flags & IOMAP_DIO_COW) {
+		error = xfs_reflink_end_cow(ip, offset, size);
+		if (error)
+			return error;
+	}
+
+	if (flags & IOMAP_DIO_UNWRITTEN)
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+	else if (update_size)
+		error = xfs_setfilesize(ip, offset, size);
+
+	return error;
+}
+
 /*
  * xfs_file_dio_aio_write - handle direct IO writes
  *
@@ -561,75 +510,44 @@ xfs_file_dio_aio_write(
 	int			unaligned_io = 0;
 	int			iolock;
 	size_t			count = iov_iter_count(from);
-	loff_t			end;
-	struct iov_iter		data;
-	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
+	struct xfs_buftarg      *target = XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp;
 
 	/* DIO must be aligned to device logical sector size */
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
 
-	/* "unaligned" here means not aligned to a filesystem block */
-	if ((iocb->ki_pos & mp->m_blockmask) ||
-	    ((iocb->ki_pos + count) & mp->m_blockmask))
-		unaligned_io = 1;
-
 	/*
-	 * We don't need to take an exclusive lock unless there page cache needs
-	 * to be invalidated or unaligned IO is being executed. We don't need to
-	 * consider the EOF extension case here because
-	 * xfs_file_aio_write_checks() will relock the inode as necessary for
-	 * EOF zeroing cases and fill out the new inode size as appropriate.
+	 * Don't take the exclusive iolock here unless the I/O is unaligned to
+	 * the file system block size.  We don't need to consider the EOF
+	 * extension case here because xfs_file_aio_write_checks() will relock
+	 * the inode as necessary for EOF zeroing cases and fill out the new
+	 * inode size as appropriate.
 	 */
-	if (unaligned_io || mapping->nrpages)
+	if ((iocb->ki_pos & mp->m_blockmask) ||
+	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
+		unaligned_io = 1;
 		iolock = XFS_IOLOCK_EXCL;
-	else
+	} else {
 		iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, iolock);
-
-	/*
-	 * Recheck if there are cached pages that need invalidate after we got
-	 * the iolock to protect against other threads adding new pages while
-	 * we were waiting for the iolock.
-	 */
-	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, iolock);
-		iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, iolock);
 	}
 
+	xfs_ilock(ip, iolock);
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
 	count = iov_iter_count(from);
-	end = iocb->ki_pos + count - 1;
-
-	/*
-	 * See xfs_file_dio_aio_read() for why we do a full-file flush here.
-	 */
-	if (mapping->nrpages) {
-		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
-		if (ret)
-			goto out;
-		/*
-		 * Invalidate whole pages. This can return an error if we fail
-		 * to invalidate a page, but this should never happen on XFS.
-		 * Warn if it does fail.
-		 */
-		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
-		WARN_ON_ONCE(ret);
-		ret = 0;
-	}
 
 	/*
 	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to flush cached pages
+	 * otherwise demote the lock if we had to take the exclusive lock
+	 * for other reasons in xfs_file_aio_write_checks.
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
 	else if (iolock == XFS_IOLOCK_EXCL) {
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
@@ -642,24 +560,9 @@ xfs_file_dio_aio_write(
 			goto out;
 	}
 
-	data = *from;
-	ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data,
-			xfs_get_blocks_direct, xfs_end_io_direct_write,
-			NULL, DIO_ASYNC_EXTEND);
-
-	/* see generic_file_direct_write() for why this is necessary */
-	if (mapping->nrpages) {
-		invalidate_inode_pages2_range(mapping,
-					      iocb->ki_pos >> PAGE_SHIFT,
-					      end >> PAGE_SHIFT);
-	}
-
-	if (ret > 0) {
-		iocb->ki_pos += ret;
-		iov_iter_advance(from, ret);
-	}
+	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
 out:
-	xfs_rw_iunlock(ip, iolock);
+	xfs_iunlock(ip, iolock);
 
 	/*
 	 * No fallback to buffered IO on errors for XFS, direct IO will either
@@ -681,7 +584,7 @@ xfs_file_dax_write(
 	size_t			count;
 	loff_t			pos;
 
-	xfs_rw_ilock(ip, iolock);
+	xfs_ilock(ip, iolock);
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
@@ -690,15 +593,13 @@ xfs_file_dax_write(
 	count = iov_iter_count(from);
 
 	trace_xfs_file_dax_write(ip, count, pos);
-
-	ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
 	}
-
 out:
-	xfs_rw_iunlock(ip, iolock);
+	xfs_iunlock(ip, iolock);
 	return error ? error : ret;
 }
 
@@ -715,7 +616,7 @@ xfs_file_buffered_aio_write(
 	int			enospc = 0;
 	int			iolock = XFS_IOLOCK_EXCL;
 
-	xfs_rw_ilock(ip, iolock);
+	xfs_ilock(ip, iolock);
 
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
@@ -759,7 +660,7 @@ write_retry:
 
 	current->backing_dev_info = NULL;
 out:
-	xfs_rw_iunlock(ip, iolock);
+	xfs_iunlock(ip, iolock);
 	return ret;
 }
 
@@ -835,7 +736,7 @@ xfs_file_fallocate(
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock, false);
+	error = xfs_break_layouts(inode, &iolock);
 	if (error)
 		goto out_unlock;
 
@@ -947,134 +848,6 @@ out_unlock:
 	return error;
 }
 
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
-	struct inode	*inode,
-	loff_t		offset,
-	size_t		len)
-{
-	loff_t		rounding;
-	loff_t		ioffset;
-	loff_t		iendoffset;
-	loff_t		bs;
-	int		ret;
-
-	bs = inode->i_sb->s_blocksize;
-	inode_dio_wait(inode);
-
-	rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   iendoffset);
-	return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len,
-	bool		is_dedupe)
-{
-	struct inode	*inode_in;
-	struct inode	*inode_out;
-	ssize_t		ret;
-	loff_t		bs;
-	loff_t		isize;
-	int		same_inode;
-	loff_t		blen;
-	unsigned int	flags = 0;
-
-	inode_in = file_inode(file_in);
-	inode_out = file_inode(file_out);
-	bs = inode_out->i_sb->s_blocksize;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-	if (IS_SWAPFILE(inode_in) ||
-	    IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Reflink only works within this filesystem. */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-	same_inode = (inode_in->i_ino == inode_out->i_ino);
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
-		return -EINVAL;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
-		return -EINVAL;
-
-	/* Are we going all the way to the end? */
-	isize = i_size_read(inode_in);
-	if (isize == 0)
-		return 0;
-	if (len == 0)
-		len = isize - pos_in;
-
-	/* Ensure offsets don't wrap and the input is inside i_size */
-	if (pos_in + len < pos_in || pos_out + len < pos_out ||
-	    pos_in + len > isize)
-		return -EINVAL;
-
-	/* Don't allow dedupe past EOF in the dest file */
-	if (is_dedupe) {
-		loff_t	disize;
-
-		disize = i_size_read(inode_out);
-		if (pos_out >= disize || pos_out + len > disize)
-			return -EINVAL;
-	}
-
-	/* If we're linking to EOF, continue to the block boundary. */
-	if (pos_in + len == isize)
-		blen = ALIGN(isize, bs) - pos_in;
-	else
-		blen = len;
-
-	/* Only reflink if we're aligned to block boundaries */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
-	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
-		return -EINVAL;
-
-	/* Don't allow overlapped reflink within the same file */
-	if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
-		return -EINVAL;
-
-	/* Wait for the completion of any pending IOs on srcfile */
-	ret = xfs_file_wait_for_io(inode_in, pos_in, len);
-	if (ret)
-		goto out;
-	ret = xfs_file_wait_for_io(inode_out, pos_out, len);
-	if (ret)
-		goto out;
-
-	if (is_dedupe)
-		flags |= XFS_REFLINK_DEDUPE;
-	ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
-			pos_out, len, flags);
-	if (ret < 0)
-		goto out;
-
-out:
-	return ret;
-}
-
 STATIC ssize_t
 xfs_file_copy_range(
 	struct file	*file_in,
@@ -1086,7 +859,7 @@ xfs_file_copy_range(
 {
 	int		error;
 
-	error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 	if (error)
 		return error;
@@ -1101,11 +874,10 @@ xfs_file_clone_range(
 	loff_t		pos_out,
 	u64		len)
 {
-	return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 }
 
-#define XFS_MAX_DEDUPE_LEN	(16 * 1024 * 1024)
 STATIC ssize_t
 xfs_file_dedupe_range(
 	struct file	*src_file,
@@ -1116,15 +888,7 @@ xfs_file_dedupe_range(
 {
 	int		error;
 
-	/*
-	 * Limit the total length we will dedupe for each operation.
-	 * This is intended to bound the total time spent in this
-	 * ioctl to something sane.
-	 */
-	if (len > XFS_MAX_DEDUPE_LEN)
-		len = XFS_MAX_DEDUPE_LEN;
-
-	error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
 		return error;
@@ -1640,7 +1404,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else {
 		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
@@ -1667,15 +1431,9 @@ xfs_filemap_fault(
 		return xfs_filemap_page_mkwrite(vma, vmf);
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	if (IS_DAX(inode)) {
-		/*
-		 * we do not want to trigger unwritten extent conversion on read
-		 * faults - that is unnecessary overhead and would also require
-		 * changes to xfs_get_blocks_direct() to map unwritten extent
-		 * ioend for conversion on read-only mappings.
-		 */
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
-	} else
+	if (IS_DAX(inode))
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+	else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
@@ -1711,7 +1469,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)