예제 #1
0
/*
 * Ensure the reflink bit is set in both inodes.
 */
STATIC int
xfs_reflink_set_inode_flag(
	struct xfs_inode	*src,
	struct xfs_inode	*dest)
{
	struct xfs_mount	*mp = src->i_mount;
	int			error;
	struct xfs_trans	*tp;

	if (xfs_is_reflink_inode(src) && xfs_is_reflink_inode(dest))
		return 0;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		goto out_error;

	/* Lock both files against IO */
	if (src->i_ino == dest->i_ino)
		xfs_ilock(src, XFS_ILOCK_EXCL);
	else
		xfs_lock_two_inodes(src, dest, XFS_ILOCK_EXCL);

	if (!xfs_is_reflink_inode(src)) {
		trace_xfs_reflink_set_inode_flag(src);
		xfs_trans_ijoin(tp, src, XFS_ILOCK_EXCL);
		src->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
		xfs_trans_log_inode(tp, src, XFS_ILOG_CORE);
		xfs_ifork_init_cow(src);
	} else
		xfs_iunlock(src, XFS_ILOCK_EXCL);

	if (src->i_ino == dest->i_ino)
		goto commit_flags;

	if (!xfs_is_reflink_inode(dest)) {
		trace_xfs_reflink_set_inode_flag(dest);
		xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
		dest->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
		xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
		xfs_ifork_init_cow(dest);
	} else
		xfs_iunlock(dest, XFS_ILOCK_EXCL);

commit_flags:
	error = xfs_trans_commit(tp);
	if (error)
		goto out_error;
	return error;

out_error:
	trace_xfs_reflink_set_inode_flag_error(dest, error, _RET_IP_);
	return error;
}
예제 #2
0
int
xfs_swap_extents(
	xfs_inode_t	*ip,	/* target inode */
	xfs_inode_t	*tip,	/* tmp inode */
	xfs_swapext_t	*sxp)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_trans_t	*tp;
	xfs_bstat_t	*sbp = &sxp->sx_stat;
	xfs_ifork_t	*tempifp, *ifp, *tifp;
	int		src_log_flags, target_log_flags;
	int		error = 0;
	int		aforkblks = 0;
	int		taforkblks = 0;
	__uint64_t	tmp;

	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
	if (!tempifp) {
		error = XFS_ERROR(ENOMEM);
		goto out;
	}

	/*
	 * we have to do two separate lock calls here to keep lockdep
	 * happy. If we try to get all the locks in one call, lock will
	 * report false positives when we drop the ILOCK and regain them
	 * below.
	 */
	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);

	/* Verify that both files have the same format */
	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
		error = XFS_ERROR(EINVAL);
		goto out_unlock;
	}

	/* Verify both files are either real-time or non-realtime */
	if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
		error = XFS_ERROR(EINVAL);
		goto out_unlock;
	}

	error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
	if (error)
		goto out_unlock;
	truncate_pagecache_range(VFS_I(tip), 0, -1);

	/* Verify O_DIRECT for ftmp */
	if (VN_CACHED(VFS_I(tip)) != 0) {
		error = XFS_ERROR(EINVAL);
		goto out_unlock;
	}

	/* Verify all data are being swapped */
	if (sxp->sx_offset != 0 ||
	    sxp->sx_length != ip->i_d.di_size ||
	    sxp->sx_length != tip->i_d.di_size) {
		error = XFS_ERROR(EFAULT);
		goto out_unlock;
	}

	trace_xfs_swap_extent_before(ip, 0);
	trace_xfs_swap_extent_before(tip, 1);

	/* check inode formats now that data is flushed */
	error = xfs_swap_extents_check_format(ip, tip);
	if (error) {
		xfs_notice(mp,
		    "%s: inode 0x%llx format is incompatible for exchanging.",
				__func__, ip->i_ino);
		goto out_unlock;
	}

	/*
	 * Compare the current change & modify times with that
	 * passed in.  If they differ, we abort this swap.
	 * This is the mechanism used to ensure the calling
	 * process that the file was not changed out from
	 * under it.
	 */
	if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
	    (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
	    (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
	    (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
		error = XFS_ERROR(EBUSY);
		goto out_unlock;
	}

	/* We need to fail if the file is memory mapped.  Once we have tossed
	 * all existing pages, the page fault will have no option
	 * but to go to the filesystem for pages. By making the page fault call
	 * vop_read (or write in the case of autogrow) they block on the iolock
	 * until we have switched the extents.
	 */
	if (VN_MAPPED(VFS_I(ip))) {
		error = XFS_ERROR(EBUSY);
		goto out_unlock;
	}

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	xfs_iunlock(tip, XFS_ILOCK_EXCL);

	/*
	 * There is a race condition here since we gave up the
	 * ilock.  However, the data fork will not change since
	 * we have the iolock (locked for truncation too) so we
	 * are safe.  We don't really care if non-io related
	 * fields change.
	 */
	truncate_pagecache_range(VFS_I(ip), 0, -1);

	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
	if (error) {
		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
		xfs_trans_cancel(tp, 0);
		goto out;
	}
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);

	/*
	 * Count the number of extended attribute blocks
	 */
	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
		if (error)
			goto out_trans_cancel;
	}
	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
			&taforkblks);
		if (error)
			goto out_trans_cancel;
	}

	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);

	/*
	 * Before we've swapped the forks, lets set the owners of the forks
	 * appropriately. We have to do this as we are demand paging the btree
	 * buffers, and so the validation done on read will expect the owner
	 * field to be correctly set. Once we change the owners, we can swap the
	 * inode forks.
	 *
	 * Note the trickiness in setting the log flags - we set the owner log
	 * flag on the opposite inode (i.e. the inode we are setting the new
	 * owner to be) because once we swap the forks and log that, log
	 * recovery is going to see the fork as owned by the swapped inode,
	 * not the pre-swapped inodes.
	 */
	src_log_flags = XFS_ILOG_CORE;
	target_log_flags = XFS_ILOG_CORE;
	if (ip->i_d.di_version == 3 &&
	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		target_log_flags |= XFS_ILOG_DOWNER;
		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
					      tip->i_ino, NULL);
		if (error)
			goto out_trans_cancel;
	}

	if (tip->i_d.di_version == 3 &&
	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		src_log_flags |= XFS_ILOG_DOWNER;
		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
					      ip->i_ino, NULL);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * Swap the data forks of the inodes
	 */
	ifp = &ip->i_df;
	tifp = &tip->i_df;
	*tempifp = *ifp;	/* struct copy */
	*ifp = *tifp;		/* struct copy */
	*tifp = *tempifp;	/* struct copy */

	/*
	 * Fix the on-disk inode values
	 */
	tmp = (__uint64_t)ip->i_d.di_nblocks;
	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;

	tmp = (__uint64_t) ip->i_d.di_nextents;
	ip->i_d.di_nextents = tip->i_d.di_nextents;
	tip->i_d.di_nextents = tmp;

	tmp = (__uint64_t) ip->i_d.di_format;
	ip->i_d.di_format = tip->i_d.di_format;
	tip->i_d.di_format = tmp;

	/*
	 * The extents in the source inode could still contain speculative
	 * preallocation beyond EOF (e.g. the file is open but not modified
	 * while defrag is in progress). In that case, we need to copy over the
	 * number of delalloc blocks the data fork in the source inode is
	 * tracking beyond EOF so that when the fork is truncated away when the
	 * temporary inode is unlinked we don't underrun the i_delayed_blks
	 * counter on that inode.
	 */
	ASSERT(tip->i_delayed_blks == 0);
	tip->i_delayed_blks = ip->i_delayed_blks;
	ip->i_delayed_blks = 0;

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			ifp->if_u1.if_extents =
				ifp->if_u2.if_inline_ext;
		}
		src_log_flags |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		ASSERT(ip->i_d.di_version < 3 ||
		       (src_log_flags & XFS_ILOG_DOWNER));
		src_log_flags |= XFS_ILOG_DBROOT;
		break;
	}

	switch (tip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			tifp->if_u1.if_extents =
				tifp->if_u2.if_inline_ext;
		}
		target_log_flags |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		target_log_flags |= XFS_ILOG_DBROOT;
		ASSERT(tip->i_d.di_version < 3 ||
		       (target_log_flags & XFS_ILOG_DOWNER));
		break;
	}

	xfs_trans_log_inode(tp, ip,  src_log_flags);
	xfs_trans_log_inode(tp, tip, target_log_flags);

	/*
	 * If this is a synchronous mount, make sure that the
	 * transaction goes to disk before returning to the user.
	 */
	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp, 0);

	trace_xfs_swap_extent_after(ip, 0);
	trace_xfs_swap_extent_after(tip, 1);
out:
	kmem_free(tempifp);
	return error;

out_unlock:
	xfs_iunlock(ip,  XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	goto out;

out_trans_cancel:
	xfs_trans_cancel(tp, 0);
	goto out_unlock;
}
예제 #3
0
/*
 * Prepare two files for range cloning.  Upon a successful return both inodes
 * will have the iolock and mmaplock held, the page cache of the out file will
 * be truncated, and any leases on the out file will have been broken.  This
 * function borrows heavily from xfs_file_aio_write_checks.
 *
 * The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
 * checked that the bytes beyond EOF physically match. Hence we cannot use the
 * EOF block in the source dedupe range because it's not a complete block match,
 * hence can introduce a corruption into the file that has it's block replaced.
 *
 * In similar fashion, the VFS file cloning also allows partial EOF blocks to be
 * "block aligned" for the purposes of cloning entire files.  However, if the
 * source file range includes the EOF block and it lands within the existing EOF
 * of the destination file, then we can expose stale data from beyond the source
 * file EOF in the destination file.
 *
 * XFS doesn't support partial block sharing, so in both cases we have check
 * these cases ourselves. For dedupe, we can simply round the length to dedupe
 * down to the previous whole block and ignore the partial EOF block. While this
 * means we can't dedupe the last block of a file, this is an acceptible
 * tradeoff for simplicity on implementation.
 *
 * For cloning, we want to share the partial EOF block if it is also the new EOF
 * block of the destination file. If the partial EOF block lies inside the
 * existing destination EOF, then we have to abort the clone to avoid exposing
 * stale data in the destination file. Hence we reject these clone attempts with
 * -EINVAL in this case.
 */
int
xfs_reflink_remap_prep(
	struct file		*file_in,
	loff_t			pos_in,
	struct file		*file_out,
	loff_t			pos_out,
	loff_t			*len,
	unsigned int		remap_flags)
{
	struct inode		*inode_in = file_inode(file_in);
	struct xfs_inode	*src = XFS_I(inode_in);
	struct inode		*inode_out = file_inode(file_out);
	struct xfs_inode	*dest = XFS_I(inode_out);
	bool			same_inode = (inode_in == inode_out);
	ssize_t			ret;

	/* Lock both files against IO */
	ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
	if (ret)
		return ret;
	if (same_inode)
		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
	else
		xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
				XFS_MMAPLOCK_EXCL);

	/* Check file eligibility and prepare for block sharing. */
	ret = -EINVAL;
	/* Don't reflink realtime inodes */
	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
		goto out_unlock;

	/* Don't share DAX file data for now. */
	if (IS_DAX(inode_in) || IS_DAX(inode_out))
		goto out_unlock;

	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
			len, remap_flags);
	if (ret < 0 || *len == 0)
		goto out_unlock;

	/* Attach dquots to dest inode before changing block map */
	ret = xfs_qm_dqattach(dest);
	if (ret)
		goto out_unlock;

	/*
	 * Zero existing post-eof speculative preallocations in the destination
	 * file.
	 */
	ret = xfs_reflink_zero_posteof(dest, pos_out);
	if (ret)
		goto out_unlock;

	/* Set flags and remap blocks. */
	ret = xfs_reflink_set_inode_flag(src, dest);
	if (ret)
		goto out_unlock;

	/*
	 * If pos_out > EOF, we may have dirtied blocks between EOF and
	 * pos_out. In that case, we need to extend the flush and unmap to cover
	 * from EOF to the end of the copy length.
	 */
	if (pos_out > XFS_ISIZE(dest)) {
		loff_t	flen = *len + (pos_out - XFS_ISIZE(dest));
		ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
	} else {
		ret = xfs_flush_unmap_range(dest, pos_out, *len);
	}
	if (ret)
		goto out_unlock;

	return 1;
out_unlock:
	xfs_reflink_remap_unlock(file_in, file_out);
	return ret;
}
예제 #4
0
/*
 * Link a range of blocks from one file to another.
 */
int
xfs_reflink_remap_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 = file_inode(file_in);
	struct xfs_inode	*src = XFS_I(inode_in);
	struct inode		*inode_out = file_inode(file_out);
	struct xfs_inode	*dest = XFS_I(inode_out);
	struct xfs_mount	*mp = src->i_mount;
	bool			same_inode = (inode_in == inode_out);
	xfs_fileoff_t		sfsbno, dfsbno;
	xfs_filblks_t		fsblen;
	xfs_extlen_t		cowextsize;
	ssize_t			ret;

	if (!xfs_sb_version_hasreflink(&mp->m_sb))
		return -EOPNOTSUPP;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	/* Lock both files against IO */
	lock_two_nondirectories(inode_in, inode_out);
	if (same_inode)
		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
	else
		xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);

	/* Check file eligibility and prepare for block sharing. */
	ret = -EINVAL;
	/* Don't reflink realtime inodes */
	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
		goto out_unlock;

	/* Don't share DAX file data for now. */
	if (IS_DAX(inode_in) || IS_DAX(inode_out))
		goto out_unlock;

	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
			&len, is_dedupe);
	if (ret <= 0)
		goto out_unlock;

	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);

	/* Set flags and remap blocks. */
	ret = xfs_reflink_set_inode_flag(src, dest);
	if (ret)
		goto out_unlock;

	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
	fsblen = XFS_B_TO_FSB(mp, len);
	ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
			pos_out + len);
	if (ret)
		goto out_unlock;

	/* Zap any page cache for the destination file's range. */
	truncate_inode_pages_range(&inode_out->i_data, pos_out,
				   PAGE_ALIGN(pos_out + len) - 1);

	/*
	 * Carry the cowextsize hint from src to dest if we're sharing the
	 * entire source file to the entire destination file, the source file
	 * has a cowextsize hint, and the destination file does not.
	 */
	cowextsize = 0;
	if (pos_in == 0 && len == i_size_read(inode_in) &&
	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
	    pos_out == 0 && len >= i_size_read(inode_out) &&
	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
		cowextsize = src->i_d.di_cowextsize;

	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
			is_dedupe);

out_unlock:
	xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
	if (!same_inode)
		xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
	unlock_two_nondirectories(inode_in, inode_out);
	if (ret)
		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
	return ret;
}
예제 #5
0
int
xfs_swap_extents(
	xfs_inode_t	*ip,	/* target inode */
	xfs_inode_t	*tip,	/* tmp inode */
	xfs_swapext_t	*sxp)
{
	xfs_mount_t	*mp;
	xfs_trans_t	*tp;
	xfs_bstat_t	*sbp = &sxp->sx_stat;
	xfs_ifork_t	*tempifp, *ifp, *tifp;
	int		ilf_fields, tilf_fields;
	static uint	lock_flags = XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL;
	int		error = 0;
	int		aforkblks = 0;
	int		taforkblks = 0;
	__uint64_t	tmp;
	char		locked = 0;

	mp = ip->i_mount;

	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
	if (!tempifp) {
		error = XFS_ERROR(ENOMEM);
		goto error0;
	}

	sbp = &sxp->sx_stat;

	/*
	 * we have to do two separate lock calls here to keep lockdep
	 * happy. If we try to get all the locks in one call, lock will
	 * report false positives when we drop the ILOCK and regain them
	 * below.
	 */
	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
	locked = 1;

	/* Verify that both files have the same format */
	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	/* Verify both files are either real-time or non-realtime */
	if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	if (VN_CACHED(VFS_I(tip)) != 0) {
		xfs_inval_cached_trace(tip, 0, -1, 0, -1);
		error = xfs_flushinval_pages(tip, 0, -1,
				FI_REMAPF_LOCKED);
		if (error)
			goto error0;
	}

	/* Verify O_DIRECT for ftmp */
	if (VN_CACHED(VFS_I(tip)) != 0) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	/* Verify all data are being swapped */
	if (sxp->sx_offset != 0 ||
	    sxp->sx_length != ip->i_d.di_size ||
	    sxp->sx_length != tip->i_d.di_size) {
		error = XFS_ERROR(EFAULT);
		goto error0;
	}

	/* check inode formats now that data is flushed */
	error = xfs_swap_extents_check_format(ip, tip);
	if (error) {
		xfs_fs_cmn_err(CE_NOTE, mp,
		    "%s: inode 0x%llx format is incompatible for exchanging.",
				__FILE__, ip->i_ino);
		goto error0;
	}

	/*
	 * Compare the current change & modify times with that
	 * passed in.  If they differ, we abort this swap.
	 * This is the mechanism used to ensure the calling
	 * process that the file was not changed out from
	 * under it.
	 */
	if ((sbp->bs_ctime.tv_sec != ip->i_d.di_ctime.t_sec) ||
	    (sbp->bs_ctime.tv_nsec != ip->i_d.di_ctime.t_nsec) ||
	    (sbp->bs_mtime.tv_sec != ip->i_d.di_mtime.t_sec) ||
	    (sbp->bs_mtime.tv_nsec != ip->i_d.di_mtime.t_nsec)) {
		error = XFS_ERROR(EBUSY);
		goto error0;
	}

	/* We need to fail if the file is memory mapped.  Once we have tossed
	 * all existing pages, the page fault will have no option
	 * but to go to the filesystem for pages. By making the page fault call
	 * vop_read (or write in the case of autogrow) they block on the iolock
	 * until we have switched the extents.
	 */
	if (VN_MAPPED(VFS_I(ip))) {
		error = XFS_ERROR(EBUSY);
		goto error0;
	}

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	xfs_iunlock(tip, XFS_ILOCK_EXCL);

	/*
	 * There is a race condition here since we gave up the
	 * ilock.  However, the data fork will not change since
	 * we have the iolock (locked for truncation too) so we
	 * are safe.  We don't really care if non-io related
	 * fields change.
	 */

	xfs_tosspages(ip, 0, -1, FI_REMAPF);

	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
	if ((error = xfs_trans_reserve(tp, 0,
				     XFS_ICHANGE_LOG_RES(mp), 0,
				     0, 0))) {
		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
		xfs_trans_cancel(tp, 0);
		locked = 0;
		goto error0;
	}
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);

	/*
	 * Count the number of extended attribute blocks
	 */
	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
		if (error) {
			xfs_trans_cancel(tp, 0);
			goto error0;
		}
	}
	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
			&taforkblks);
		if (error) {
			xfs_trans_cancel(tp, 0);
			goto error0;
		}
	}

	/*
	 * Swap the data forks of the inodes
	 */
	ifp = &ip->i_df;
	tifp = &tip->i_df;
	*tempifp = *ifp;	/* struct copy */
	*ifp = *tifp;		/* struct copy */
	*tifp = *tempifp;	/* struct copy */

	/*
	 * Fix the in-memory data fork values that are dependent on the fork
	 * offset in the inode. We can't assume they remain the same as attr2
	 * has dynamic fork offsets.
	 */
	ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
					(uint)sizeof(xfs_bmbt_rec_t);
	tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
					(uint)sizeof(xfs_bmbt_rec_t);

	/*
	 * Fix the on-disk inode values
	 */
	tmp = (__uint64_t)ip->i_d.di_nblocks;
	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;

	tmp = (__uint64_t) ip->i_d.di_nextents;
	ip->i_d.di_nextents = tip->i_d.di_nextents;
	tip->i_d.di_nextents = tmp;

	tmp = (__uint64_t) ip->i_d.di_format;
	ip->i_d.di_format = tip->i_d.di_format;
	tip->i_d.di_format = tmp;

	ilf_fields = XFS_ILOG_CORE;

	switch(ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			ifp->if_u1.if_extents =
				ifp->if_u2.if_inline_ext;
		}
		ilf_fields |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		ilf_fields |= XFS_ILOG_DBROOT;
		break;
	}

	tilf_fields = XFS_ILOG_CORE;

	switch(tip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			tifp->if_u1.if_extents =
				tifp->if_u2.if_inline_ext;
		}
		tilf_fields |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		tilf_fields |= XFS_ILOG_DBROOT;
		break;
	}


	IHOLD(ip);
	xfs_trans_ijoin(tp, ip, lock_flags);

	IHOLD(tip);
	xfs_trans_ijoin(tp, tip, lock_flags);

	xfs_trans_log_inode(tp, ip,  ilf_fields);
	xfs_trans_log_inode(tp, tip, tilf_fields);

	/*
	 * If this is a synchronous mount, make sure that the
	 * transaction goes to disk before returning to the user.
	 */
	if (mp->m_flags & XFS_MOUNT_WSYNC) {
		xfs_trans_set_sync(tp);
	}

	error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT);
	locked = 0;

 error0:
	if (locked) {
		xfs_iunlock(ip,  lock_flags);
		xfs_iunlock(tip, lock_flags);
	}
	if (tempifp != NULL)
		kmem_free(tempifp);
	return error;
}