Пример #1
0
STATIC int
xfs_commit_dummy_trans(
	struct xfs_mount	*mp,
	uint			log_flags)
{
	struct xfs_inode	*ip = mp->m_rootip;
	struct xfs_trans	*tp;
	int			error;

	/*
	 * Put a dummy transaction in the log to tell recovery
	 * that all others are OK.
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_ihold(tp, ip);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	/* XXX(hch): ignoring the error here.. */
	error = xfs_trans_commit(tp, 0);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	xfs_log_force(mp, 0, log_flags);
	return 0;
}
Пример #2
0
STATIC int
xfs_commit_dummy_trans(
	struct xfs_mount	*mp,
	uint			flags)
{
	struct xfs_inode	*ip = mp->m_rootip;
	struct xfs_trans	*tp;
	int			error;

	/*
	 * Put a dummy transaction in the log to tell recovery
	 * that all others are OK.
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_ihold(tp, ip);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	error = xfs_trans_commit(tp, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	/* the log force ensures this transaction is pushed to disk */
	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
	return error;
}
Пример #3
0
STATIC int
xfs_ioctl_setattr(
	xfs_inode_t		*ip,
	struct fsxattr		*fa,
	int			mask)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	unsigned int		lock_flags = 0;
	struct xfs_dquot	*udqp = NULL;
	struct xfs_dquot	*gdqp = NULL;
	struct xfs_dquot	*olddquot = NULL;
	int			code;

	trace_xfs_ioctl_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);
	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	/*
	 * Disallow 32bit project ids when projid32bit feature is not enabled.
	 */
	if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
			!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
		return XFS_ERROR(EINVAL);

	/*
	 * If disk quotas is on, we make sure that the dquots do exist on disk,
	 * before we start any other transactions. Trying to do this later
	 * is messy. We don't care to take a readlock to look at the ids
	 * in inode here, because we can't hold it across the trans_reserve.
	 * If the IDs do change before we take the ilock, we're covered
	 * because the i_*dquot fields will get updated anyway.
	 */
	if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
		code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
					 ip->i_d.di_gid, fa->fsx_projid,
					 XFS_QMOPT_PQUOTA, &udqp, &gdqp);
		if (code)
			return code;
	}

	/*
	 * For the other attributes, we acquire the inode lock and
	 * first do an error checking pass.
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (code)
		goto error_return;

	lock_flags = XFS_ILOCK_EXCL;
	xfs_ilock(ip, lock_flags);

	/*
	 * CAP_FOWNER overrides the following restrictions:
	 *
	 * The user ID of the calling process must be equal
	 * to the file owner ID, except in cases where the
	 * CAP_FSETID capability is applicable.
	 */
	if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
		code = XFS_ERROR(EPERM);
		goto error_return;
	}

	/*
	 * Do a quota reservation only if projid is actually going to change.
	 */
	if (mask & FSX_PROJID) {
		if (XFS_IS_QUOTA_RUNNING(mp) &&
		    XFS_IS_PQUOTA_ON(mp) &&
		    xfs_get_projid(ip) != fa->fsx_projid) {
			ASSERT(tp);
			code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
			if (code)	/* out of quota */
				goto error_return;
		}
	}

	if (mask & FSX_EXTSIZE) {
		/*
		 * Can't change extent size if any extents are allocated.
		 */
		if (ip->i_d.di_nextents &&
		    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
		     fa->fsx_extsize)) {
			code = XFS_ERROR(EINVAL);	/* EFBIG? */
			goto error_return;
		}

		/*
		 * Extent size must be a multiple of the appropriate block
		 * size, if set at all. It must also be smaller than the
		 * maximum extent size supported by the filesystem.
		 *
		 * Also, for non-realtime files, limit the extent size hint to
		 * half the size of the AGs in the filesystem so alignment
		 * doesn't result in extents larger than an AG.
		 */
		if (fa->fsx_extsize != 0) {
			xfs_extlen_t    size;
			xfs_fsblock_t   extsize_fsb;

			extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
			if (extsize_fsb > MAXEXTLEN) {
				code = XFS_ERROR(EINVAL);
				goto error_return;
			}

			if (XFS_IS_REALTIME_INODE(ip) ||
			    ((mask & FSX_XFLAGS) &&
			    (fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
				size = mp->m_sb.sb_rextsize <<
				       mp->m_sb.sb_blocklog;
			} else {
				size = mp->m_sb.sb_blocksize;
				if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
					code = XFS_ERROR(EINVAL);
					goto error_return;
				}
			}

			if (fa->fsx_extsize % size) {
				code = XFS_ERROR(EINVAL);
				goto error_return;
			}
		}
	}


	if (mask & FSX_XFLAGS) {
		/*
		 * Can't change realtime flag if any extents are allocated.
		 */
		if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
		    (XFS_IS_REALTIME_INODE(ip)) !=
		    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
			code = XFS_ERROR(EINVAL);	/* EFBIG? */
			goto error_return;
		}

		/*
		 * If realtime flag is set then must have realtime data.
		 */
		if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
			if ((mp->m_sb.sb_rblocks == 0) ||
			    (mp->m_sb.sb_rextsize == 0) ||
			    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
				code = XFS_ERROR(EINVAL);
				goto error_return;
			}
		}

		/*
		 * Can't modify an immutable/append-only file unless
		 * we have appropriate permission.
		 */
		if ((ip->i_d.di_flags &
				(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
		     (fa->fsx_xflags &
				(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
		    !capable(CAP_LINUX_IMMUTABLE)) {
			code = XFS_ERROR(EPERM);
			goto error_return;
		}
	}

	xfs_trans_ijoin(tp, ip, 0);

	/*
	 * Change file ownership.  Must be the owner or privileged.
	 */
	if (mask & FSX_PROJID) {
		/*
		 * CAP_FSETID overrides the following restrictions:
		 *
		 * The set-user-ID and set-group-ID bits of a file will be
		 * cleared upon successful return from chown()
		 */
		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
		    !capable(CAP_FSETID))
			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);

		/*
		 * Change the ownerships and register quota modifications
		 * in the transaction.
		 */
		if (xfs_get_projid(ip) != fa->fsx_projid) {
			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
				olddquot = xfs_qm_vop_chown(tp, ip,
							&ip->i_gdquot, gdqp);
			}
			xfs_set_projid(ip, fa->fsx_projid);

			/*
			 * We may have to rev the inode as well as
			 * the superblock version number since projids didn't
			 * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
			 */
			if (ip->i_d.di_version == 1)
				xfs_bump_ino_vers2(tp, ip);
		}

	}

	if (mask & FSX_EXTSIZE)
		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
	if (mask & FSX_XFLAGS) {
		xfs_set_diflags(ip, fa->fsx_xflags);
		xfs_diflags_to_linux(ip);
	}

	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	/*
	 * If this is a synchronous mount, make sure that the
	 * transaction goes to disk before returning to the user.
	 * This is slightly sub-optimal in that truncates require
	 * two sync transactions instead of one for wsync filesystems.
	 * One for the truncate and one for the timestamps since we
	 * don't want to change the timestamps unless we're sure the
	 * truncate worked.  Truncates are less than 1% of the laddis
	 * mix so this probably isn't worth the trouble to optimize.
	 */
	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);
	code = xfs_trans_commit(tp, 0);
	xfs_iunlock(ip, lock_flags);

	/*
	 * Release any dquot(s) the inode had kept before chown.
	 */
	xfs_qm_dqrele(olddquot);
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);

	return code;

 error_return:
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_trans_cancel(tp, 0);
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return code;
}
Пример #4
0
STATIC int
xfs_ioctl_setattr(
	xfs_inode_t		*ip,
	struct fsxattr		*fa,
	int			mask)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	unsigned int		lock_flags = 0;
	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
	struct xfs_dquot	*olddquot = NULL;
	int			code;

	xfs_itrace_entry(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);
	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	/*
	 * If disk quotas is on, we make sure that the dquots do exist on disk,
	 * before we start any other transactions. Trying to do this later
	 * is messy. We don't care to take a readlock to look at the ids
	 * in inode here, because we can't hold it across the trans_reserve.
	 * If the IDs do change before we take the ilock, we're covered
	 * because the i_*dquot fields will get updated anyway.
	 */
	if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
		code = XFS_QM_DQVOPALLOC(mp, ip, ip->i_d.di_uid,
					 ip->i_d.di_gid, fa->fsx_projid,
					 XFS_QMOPT_PQUOTA, &udqp, &gdqp);
		if (code)
			return code;
	}

	/*
	 * For the other attributes, we acquire the inode lock and
	 * first do an error checking pass.
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (code)
		goto error_return;

	lock_flags = XFS_ILOCK_EXCL;
	xfs_ilock(ip, lock_flags);

	/*
	 * CAP_FOWNER overrides the following restrictions:
	 *
	 * The user ID of the calling process must be equal
	 * to the file owner ID, except in cases where the
	 * CAP_FSETID capability is applicable.
	 */
	if (current->fsuid != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
		code = XFS_ERROR(EPERM);
		goto error_return;
	}

	/*
	 * Do a quota reservation only if projid is actually going to change.
	 */
	if (mask & FSX_PROJID) {
		if (XFS_IS_PQUOTA_ON(mp) &&
		    ip->i_d.di_projid != fa->fsx_projid) {
			ASSERT(tp);
			code = XFS_QM_DQVOPCHOWNRESV(mp, tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
			if (code)	/* out of quota */
				goto error_return;
		}
	}

	if (mask & FSX_EXTSIZE) {
		/*
		 * Can't change extent size if any extents are allocated.
		 */
		if (ip->i_d.di_nextents &&
		    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
		     fa->fsx_extsize)) {
			code = XFS_ERROR(EINVAL);	/* EFBIG? */
			goto error_return;
		}

		/*
		 * Extent size must be a multiple of the appropriate block
		 * size, if set at all.
		 */
		if (fa->fsx_extsize != 0) {
			xfs_extlen_t	size;

			if (XFS_IS_REALTIME_INODE(ip) ||
			    ((mask & FSX_XFLAGS) &&
			    (fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
				size = mp->m_sb.sb_rextsize <<
				       mp->m_sb.sb_blocklog;
			} else {
				size = mp->m_sb.sb_blocksize;
			}

			if (fa->fsx_extsize % size) {
				code = XFS_ERROR(EINVAL);
				goto error_return;
			}
		}
	}


	if (mask & FSX_XFLAGS) {
		/*
		 * Can't change realtime flag if any extents are allocated.
		 */
		if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
		    (XFS_IS_REALTIME_INODE(ip)) !=
		    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
			code = XFS_ERROR(EINVAL);	/* EFBIG? */
			goto error_return;
		}

		/*
		 * If realtime flag is set then must have realtime data.
		 */
		if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
			if ((mp->m_sb.sb_rblocks == 0) ||
			    (mp->m_sb.sb_rextsize == 0) ||
			    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
				code = XFS_ERROR(EINVAL);
				goto error_return;
			}
		}

		/*
		 * Can't modify an immutable/append-only file unless
		 * we have appropriate permission.
		 */
		if ((ip->i_d.di_flags &
				(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
		     (fa->fsx_xflags &
				(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
		    !capable(CAP_LINUX_IMMUTABLE)) {
			code = XFS_ERROR(EPERM);
			goto error_return;
		}
	}

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

	/*
	 * Change file ownership.  Must be the owner or privileged.
	 * If the system was configured with the "restricted_chown"
	 * option, the owner is not permitted to give away the file,
	 * and can change the group id only to a group of which he
	 * or she is a member.
	 */
	if (mask & FSX_PROJID) {
		/*
		 * CAP_FSETID overrides the following restrictions:
		 *
		 * The set-user-ID and set-group-ID bits of a file will be
		 * cleared upon successful return from chown()
		 */
		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
		    !capable(CAP_FSETID))
			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);

		/*
		 * Change the ownerships and register quota modifications
		 * in the transaction.
		 */
		if (ip->i_d.di_projid != fa->fsx_projid) {
			if (XFS_IS_PQUOTA_ON(mp)) {
				olddquot = XFS_QM_DQVOPCHOWN(mp, tp, ip,
							&ip->i_gdquot, gdqp);
			}
			ip->i_d.di_projid = fa->fsx_projid;

			/*
			 * We may have to rev the inode as well as
			 * the superblock version number since projids didn't
			 * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
			 */
			if (ip->i_d.di_version == XFS_DINODE_VERSION_1)
				xfs_bump_ino_vers2(tp, ip);
		}

	}

	if (mask & FSX_EXTSIZE)
		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
	if (mask & FSX_XFLAGS) {
		xfs_set_diflags(ip, fa->fsx_xflags);
		xfs_diflags_to_linux(ip);
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	xfs_ichgtime(ip, XFS_ICHGTIME_CHG);

	XFS_STATS_INC(xs_ig_attrchg);

	/*
	 * If this is a synchronous mount, make sure that the
	 * transaction goes to disk before returning to the user.
	 * This is slightly sub-optimal in that truncates require
	 * two sync transactions instead of one for wsync filesystems.
	 * One for the truncate and one for the timestamps since we
	 * don't want to change the timestamps unless we're sure the
	 * truncate worked.  Truncates are less than 1% of the laddis
	 * mix so this probably isn't worth the trouble to optimize.
	 */
	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);
	code = xfs_trans_commit(tp, 0);
	xfs_iunlock(ip, lock_flags);

	/*
	 * Release any dquot(s) the inode had kept before chown.
	 */
	XFS_QM_DQRELE(mp, olddquot);
	XFS_QM_DQRELE(mp, udqp);
	XFS_QM_DQRELE(mp, gdqp);

	if (code)
		return code;

	if (DM_EVENT_ENABLED(ip, DM_EVENT_ATTRIBUTE)) {
		XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, ip, DM_RIGHT_NULL,
				NULL, DM_RIGHT_NULL, NULL, NULL, 0, 0,
				(mask & FSX_NONBLOCK) ? DM_FLAGS_NDELAY : 0);
	}

	return 0;

 error_return:
	XFS_QM_DQRELE(mp, udqp);
	XFS_QM_DQRELE(mp, gdqp);
	xfs_trans_cancel(tp, 0);
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return code;
}
Пример #5
0
static 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		ilf_fields, tilf_fields;
	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;
	}

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

	/* 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.
	 */

	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);
		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;
	}

	/*
	 * 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;

	/*
	 * 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;

	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;
	}

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

	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);

	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;
}
Пример #6
0
/*
 * Syssgi interface for swapext
 */
int
xfs_swapext(
	xfs_swapext_t	__user *sxp)
{
	xfs_swapext_t	sx;
	xfs_inode_t     *ip=NULL, *tip=NULL, *ips[2];
	xfs_trans_t     *tp;
	xfs_mount_t     *mp;
	xfs_bstat_t	*sbp;
	struct file	*fp = NULL, *tfp = NULL;
	vnode_t		*vp, *tvp;
	bhv_desc_t      *bdp, *tbdp;
	vn_bhv_head_t   *bhp, *tbhp;
	uint		lock_flags=0;
	int		ilf_fields, tilf_fields;
	int		error = 0;
	xfs_ifork_t	tempif, *ifp, *tifp;
	__uint64_t	tmp;
	int		aforkblks = 0;
	int		taforkblks = 0;
	int		locked = 0;

	if (copy_from_user(&sx, sxp, sizeof(sx)))
		return XFS_ERROR(EFAULT);

	/* Pull information for the target fd */
	if (((fp = fget((int)sx.sx_fdtarget)) == NULL) ||
	    ((vp = LINVFS_GET_VP(fp->f_dentry->d_inode)) == NULL))  {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	bhp = VN_BHV_HEAD(vp);
	bdp = vn_bhv_lookup(bhp, &xfs_vnodeops);
	if (bdp == NULL) {
		error = XFS_ERROR(EBADF);
		goto error0;
	} else {
		ip = XFS_BHVTOI(bdp);
	}

	if (((tfp = fget((int)sx.sx_fdtmp)) == NULL) ||
	    ((tvp = LINVFS_GET_VP(tfp->f_dentry->d_inode)) == NULL)) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	tbhp = VN_BHV_HEAD(tvp);
	tbdp = vn_bhv_lookup(tbhp, &xfs_vnodeops);
	if (tbdp == NULL) {
		error = XFS_ERROR(EBADF);
		goto error0;
	} else {
		tip = XFS_BHVTOI(tbdp);
	}

	if (ip->i_mount != tip->i_mount) {
		error =  XFS_ERROR(EINVAL);
		goto error0;
	}

	if (ip->i_ino == tip->i_ino) {
		error =  XFS_ERROR(EINVAL);
		goto error0;
	}

	mp = ip->i_mount;

	sbp = &sx.sx_stat;

	if (XFS_FORCED_SHUTDOWN(mp)) {
		error =  XFS_ERROR(EIO);
		goto error0;
	}

	locked = 1;

	/* Lock in i_ino order */
	if (ip->i_ino < tip->i_ino) {
		ips[0] = ip;
		ips[1] = tip;
	} else {
		ips[0] = tip;
		ips[1] = ip;
	}
	lock_flags = XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL;
	xfs_lock_inodes(ips, 2, 0, lock_flags);

	/* Check permissions */
	error = xfs_iaccess(ip, S_IWUSR, NULL);
	if (error)
		goto error0;

	error = xfs_iaccess(tip, S_IWUSR, NULL);
	if (error)
		goto error0;

	/* 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 ((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) !=
	    (tip->i_d.di_flags & XFS_DIFLAG_REALTIME)) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	/* Should never get a local format */
	if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
	    tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
		error = XFS_ERROR(EINVAL);
		goto error0;
	}

	if (VN_CACHED(tvp) != 0)
		xfs_inval_cached_pages(XFS_ITOV(tip), &(tip->i_iocore),
						(xfs_off_t)0, 0, 0);

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

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

	/*
	 * If the target has extended attributes, the tmp file
	 * must also in order to ensure the correct data fork
	 * format.
	 */
	if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
		error = XFS_ERROR(EINVAL);
		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(vp)) {
		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.
	 */

	VOP_TOSS_PAGES(vp, 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);
		return error;
	}
	xfs_lock_inodes(ips, 2, 0, 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_iunlock(ip,  lock_flags);
			xfs_iunlock(tip, lock_flags);
			xfs_trans_cancel(tp, 0);
			return error;
		}
	}
	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_iunlock(ip,  lock_flags);
			xfs_iunlock(tip, lock_flags);
			xfs_trans_cancel(tp, 0);
			return error;
		}
	}

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

	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;
	}

	/*
	 * Increment vnode ref counts since xfs_trans_commit &
	 * xfs_trans_cancel will both unlock the inodes and
	 * decrement the associated ref counts.
	 */
	VN_HOLD(vp);
	VN_HOLD(tvp);

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

	fput(fp);
	fput(tfp);

	return error;

 error0:
	if (locked) {
		xfs_iunlock(ip,  lock_flags);
		xfs_iunlock(tip, lock_flags);
	}

	if (fp != NULL) fput(fp);
	if (tfp != NULL) fput(tfp);

	return error;
}
int
xfs_setattr_nonsize(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	xfs_mount_t		*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	xfs_trans_t		*tp;
	int			error;
	uid_t			uid = 0, iuid = 0;
	gid_t			gid = 0, igid = 0;
	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT((mask & ATTR_SIZE) == 0);

	/*
	 * If disk quotas is on, we make sure that the dquots do exist on disk,
	 * before we start any other transactions. Trying to do this later
	 * is messy. We don't care to take a readlock to look at the ids
	 * in inode here, because we can't hold it across the trans_reserve.
	 * If the IDs do change before we take the ilock, we're covered
	 * because the i_*dquot fields will get updated anyway.
	 */
	if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
		uint	qflags = 0;

		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
			uid = iattr->ia_uid;
			qflags |= XFS_QMOPT_UQUOTA;
		} else {
			uid = ip->i_d.di_uid;
		}
		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
			gid = iattr->ia_gid;
			qflags |= XFS_QMOPT_GQUOTA;
		}  else {
			gid = ip->i_d.di_gid;
		}

		/*
		 * We take a reference when we initialize udqp and gdqp,
		 * so it is important that we never blindly double trip on
		 * the same variable. See xfs_create() for an example.
		 */
		ASSERT(udqp == NULL);
		ASSERT(gdqp == NULL);
		error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
					 qflags, &udqp, &gdqp);
		if (error)
			return error;
	}

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error)
		goto out_dqrele;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	/*
	 * Change file ownership.  Must be the owner or privileged.
	 */
	if (mask & (ATTR_UID|ATTR_GID)) {
		/*
		 * These IDs could have changed since we last looked at them.
		 * But, we're assured that if the ownership did change
		 * while we didn't have the inode locked, inode's dquot(s)
		 * would have changed also.
		 */
		iuid = ip->i_d.di_uid;
		igid = ip->i_d.di_gid;
		gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
		uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;

		/*
		 * Do a quota reservation only if uid/gid is actually
		 * going to change.
		 */
		if (XFS_IS_QUOTA_RUNNING(mp) &&
		    ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
		     (XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
			ASSERT(tp);
			error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
			if (error)	/* out of quota */
				goto out_trans_cancel;
		}
	}

	xfs_trans_ijoin(tp, ip);

	/*
	 * Change file ownership.  Must be the owner or privileged.
	 */
	if (mask & (ATTR_UID|ATTR_GID)) {
		/*
		 * CAP_FSETID overrides the following restrictions:
		 *
		 * The set-user-ID and set-group-ID bits of a file will be
		 * cleared upon successful return from chown()
		 */
		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
		    !capable(CAP_FSETID))
			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);

		/*
		 * Change the ownerships and register quota modifications
		 * in the transaction.
		 */
		if (iuid != uid) {
			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
				ASSERT(mask & ATTR_UID);
				ASSERT(udqp);
				olddquot1 = xfs_qm_vop_chown(tp, ip,
							&ip->i_udquot, udqp);
			}
			ip->i_d.di_uid = uid;
			inode->i_uid = uid;
		}
		if (igid != gid) {
			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
				ASSERT(!XFS_IS_PQUOTA_ON(mp));
				ASSERT(mask & ATTR_GID);
				ASSERT(gdqp);
				olddquot2 = xfs_qm_vop_chown(tp, ip,
							&ip->i_gdquot, gdqp);
			}
			ip->i_d.di_gid = gid;
			inode->i_gid = gid;
		}
	}

	/*
	 * Change file access modes.
	 */
	if (mask & ATTR_MODE) {
		umode_t mode = iattr->ia_mode;

		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
			mode &= ~S_ISGID;

		ip->i_d.di_mode &= S_IFMT;
		ip->i_d.di_mode |= mode & ~S_IFMT;

		inode->i_mode &= S_IFMT;
		inode->i_mode |= mode & ~S_IFMT;
	}

	/*
	 * Change file access or modified times.
	 */
	if (mask & ATTR_ATIME) {
		inode->i_atime = iattr->ia_atime;
		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
		ip->i_update_core = 1;
	}
	if (mask & ATTR_CTIME) {
		inode->i_ctime = iattr->ia_ctime;
		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
		ip->i_update_core = 1;
	}
	if (mask & ATTR_MTIME) {
		inode->i_mtime = iattr->ia_mtime;
		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
		ip->i_update_core = 1;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp, 0);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	/*
	 * Release any dquot(s) the inode had kept before chown.
	 */
	xfs_qm_dqrele(olddquot1);
	xfs_qm_dqrele(olddquot2);
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);

	if (error)
		return XFS_ERROR(error);

	/*
	 * XXX(hch): Updating the ACL entries is not atomic vs the i_mode
	 * 	     update.  We could avoid this with linked transactions
	 * 	     and passing down the transaction pointer all the way
	 *	     to attr_set.  No previous user of the generic
	 * 	     Posix ACL code seems to care about this issue either.
	 */
	if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
		error = -xfs_acl_chmod(inode);
		if (error)
			return XFS_ERROR(error);
	}

	return 0;

out_trans_cancel:
	xfs_trans_cancel(tp, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	return error;
}
int
xfs_setattr_nonsize(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	xfs_mount_t		*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	xfs_trans_t		*tp;
	int			error;
	uid_t			uid = 0, iuid = 0;
	gid_t			gid = 0, igid = 0;
	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT((mask & ATTR_SIZE) == 0);

	if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
		uint	qflags = 0;

		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
			uid = iattr->ia_uid;
			qflags |= XFS_QMOPT_UQUOTA;
		} else {
			uid = ip->i_d.di_uid;
		}
		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
			gid = iattr->ia_gid;
			qflags |= XFS_QMOPT_GQUOTA;
		}  else {
			gid = ip->i_d.di_gid;
		}

		ASSERT(udqp == NULL);
		ASSERT(gdqp == NULL);
		error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
					 qflags, &udqp, &gdqp);
		if (error)
			return error;
	}

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error)
		goto out_dqrele;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	if (mask & (ATTR_UID|ATTR_GID)) {
		iuid = ip->i_d.di_uid;
		igid = ip->i_d.di_gid;
		gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
		uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;

		if (XFS_IS_QUOTA_RUNNING(mp) &&
		    ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
		     (XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
			ASSERT(tp);
			error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
			if (error)	
				goto out_trans_cancel;
		}
	}

	xfs_trans_ijoin(tp, ip, 0);

	if (mask & (ATTR_UID|ATTR_GID)) {
		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
		    !capable(CAP_FSETID))
			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);

		if (iuid != uid) {
			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
				ASSERT(mask & ATTR_UID);
				ASSERT(udqp);
				olddquot1 = xfs_qm_vop_chown(tp, ip,
							&ip->i_udquot, udqp);
			}
			ip->i_d.di_uid = uid;
			inode->i_uid = uid;
		}
		if (igid != gid) {
			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
				ASSERT(!XFS_IS_PQUOTA_ON(mp));
				ASSERT(mask & ATTR_GID);
				ASSERT(gdqp);
				olddquot2 = xfs_qm_vop_chown(tp, ip,
							&ip->i_gdquot, gdqp);
			}
			ip->i_d.di_gid = gid;
			inode->i_gid = gid;
		}
	}

	if (mask & ATTR_MODE) {
		umode_t mode = iattr->ia_mode;

		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
			mode &= ~S_ISGID;

		ip->i_d.di_mode &= S_IFMT;
		ip->i_d.di_mode |= mode & ~S_IFMT;

		inode->i_mode &= S_IFMT;
		inode->i_mode |= mode & ~S_IFMT;
	}

	if (mask & ATTR_ATIME) {
		inode->i_atime = iattr->ia_atime;
		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
	}
	if (mask & ATTR_CTIME) {
		inode->i_ctime = iattr->ia_ctime;
		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
	}
	if (mask & ATTR_MTIME) {
		inode->i_mtime = iattr->ia_mtime;
		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp, 0);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	xfs_qm_dqrele(olddquot1);
	xfs_qm_dqrele(olddquot2);
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);

	if (error)
		return XFS_ERROR(error);

	if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
		error = -xfs_acl_chmod(inode);
		if (error)
			return XFS_ERROR(error);
	}

	return 0;

out_trans_cancel:
	xfs_trans_cancel(tp, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	return error;
}