Beispiel #1
0
/*
 * Initialize realtime fields in the mount structure.
 */
static int
rtmount_init(
	xfs_mount_t	*mp,	/* file system mount structure */
	int		flags)
{
	xfs_buf_t	*bp;	/* buffer for last block of subvolume */
	xfs_daddr_t	d;	/* address of last block of subvolume */
	xfs_sb_t	*sbp;	/* filesystem superblock copy in mount */

	sbp = &mp->m_sb;
	if (sbp->sb_rblocks == 0)
		return 0;
	if (mp->m_rtdev_targp->dev == 0 && !(flags & LIBXFS_MOUNT_DEBUGGER)) {
		fprintf(stderr, _("%s: filesystem has a realtime subvolume\n"),
			progname);
		return -1;
	}
	mp->m_rsumlevels = sbp->sb_rextslog + 1;
	mp->m_rsumsize =
		(uint)sizeof(xfs_suminfo_t) * mp->m_rsumlevels *
		sbp->sb_rbmblocks;
	mp->m_rsumsize = roundup(mp->m_rsumsize, sbp->sb_blocksize);
	mp->m_rbmip = mp->m_rsumip = NULL;

	/*
	 * Allow debugger to be run without the realtime device present.
	 */
	if (flags & LIBXFS_MOUNT_DEBUGGER)
		return 0;

	/*
	 * Check that the realtime section is an ok size.
	 */
	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_rblocks) {
		fprintf(stderr, _("%s: realtime init - %llu != %llu\n"),
			progname, (unsigned long long) XFS_BB_TO_FSB(mp, d),
			(unsigned long long) mp->m_sb.sb_rblocks);
		return -1;
	}
	bp = libxfs_readbuf(mp->m_rtdev,
			d - XFS_FSB_TO_BB(mp, 1), XFS_FSB_TO_BB(mp, 1), 0, NULL);
	if (bp == NULL) {
		fprintf(stderr, _("%s: realtime size check failed\n"),
			progname);
		return -1;
	}
	libxfs_putbuf(bp);
	return 0;
}
STATIC bool
xfs_dquot_buf_verify_crc(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp)
{
	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
	int			ndquots;
	int			i;

	if (!xfs_sb_version_hascrc(&mp->m_sb))
		return true;

	/*
	 * if we are in log recovery, the quota subsystem has not been
	 * initialised so we have no quotainfo structure. In that case, we need
	 * to manually calculate the number of dquots in the buffer.
	 */
	if (mp->m_quotainfo)
		ndquots = mp->m_quotainfo->qi_dqperchunk;
	else
		ndquots = xfs_calc_dquots_per_chunk(mp,
					XFS_BB_TO_FSB(mp, bp->b_length));

	for (i = 0; i < ndquots; i++, d++) {
		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
				 XFS_DQUOT_CRC_OFF))
			return false;
		if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_uuid))
			return false;
	}
	return true;
}
Beispiel #3
0
/*
 * Calculate the minimum valid log size for the given superblock configuration.
 * Used to calculate the minimum log size at mkfs time, and to determine if
 * the log is large enough or not at mount time. Returns the minimum size in
 * filesystem block size units.
 */
int
xfs_log_calc_minimum_size(
	struct xfs_mount	*mp)
{
	struct xfs_trans_res	tres = {0};
	int			max_logres;
	int			min_logblks = 0;
	int			lsunit = 0;

	xfs_log_get_max_trans_res(mp, &tres);

	max_logres = xfs_log_calc_unit_res(mp, tres.tr_logres);
	if (tres.tr_logcount > 1)
		max_logres *= tres.tr_logcount;

	if (xfs_sb_version_haslogv2(&mp->m_sb) && mp->m_sb.sb_logsunit > 1)
		lsunit = BTOBB(mp->m_sb.sb_logsunit);

	/*
	 * Two factors should be taken into account for calculating the minimum
	 * log space.
	 * 1) The fundamental limitation is that no single transaction can be
	 *    larger than half size of the log.
	 *
	 *    From mkfs.xfs, this is considered by the XFS_MIN_LOG_FACTOR
	 *    define, which is set to 3. That means we can definitely fit
	 *    maximally sized 2 transactions in the log. We'll use this same
	 *    value here.
	 *
	 * 2) If the lsunit option is specified, a transaction requires 2 LSU
	 *    for the reservation because there are two log writes that can
	 *    require padding - the transaction data and the commit record which
	 *    are written separately and both can require padding to the LSU.
	 *    Consider that we can have an active CIL reservation holding 2*LSU,
	 *    but the CIL is not over a push threshold, in this case, if we
	 *    don't have enough log space for at one new transaction, which
	 *    includes another 2*LSU in the reservation, we will run into dead
	 *    loop situation in log space grant procedure. i.e.
	 *    xlog_grant_head_wait().
	 *
	 *    Hence the log size needs to be able to contain two maximally sized
	 *    and padded transactions, which is (2 * (2 * LSU + maxlres)).
	 *
	 * Also, the log size should be a multiple of the log stripe unit, round
	 * it up to lsunit boundary if lsunit is specified.
	 */
	if (lsunit) {
		min_logblks = roundup_64(BTOBB(max_logres), lsunit) +
			      2 * lsunit;
	} else
		min_logblks = BTOBB(max_logres) + 2 * BBSIZE;
	min_logblks *= XFS_MIN_LOG_FACTOR;

	return XFS_BB_TO_FSB(mp, min_logblks);
}
/*
 * trim a range of the filesystem.
 *
 * Note: the parameters passed from userspace are byte ranges into the
 * filesystem which does not match to the format we use for filesystem block
 * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
 * is a linear address range. Hence we need to use DADDR based conversions and
 * comparisons for determining the correct offset and regions to trim.
 */
int
xfs_ioc_trim(
	struct xfs_mount		*mp,
	struct fstrim_range __user	*urange)
{
	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
	unsigned int		granularity = q->limits.discard_granularity;
	struct fstrim_range	range;
	xfs_daddr_t		start, end, minlen;
	xfs_agnumber_t		start_agno, end_agno, agno;
	__uint64_t		blocks_trimmed = 0;
	int			error, last_error = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -XFS_ERROR(EPERM);
	if (!blk_queue_discard(q))
		return -XFS_ERROR(EOPNOTSUPP);
	if (copy_from_user(&range, urange, sizeof(range)))
		return -XFS_ERROR(EFAULT);

	/*
	 * Truncating down the len isn't actually quite correct, but using
	 * BBTOB would mean we trivially get overflows for values
	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
	 * used by the fstrim application.  In the end it really doesn't
	 * matter as trimming blocks is an advisory interface.
	 */
	start = BTOBB(range.start);
	end = start + BTOBBT(range.len) - 1;
	minlen = BTOBB(max_t(u64, granularity, range.minlen));

	if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks)
		return -XFS_ERROR(EINVAL);
	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;

	start_agno = xfs_daddr_to_agno(mp, start);
	end_agno = xfs_daddr_to_agno(mp, end);

	for (agno = start_agno; agno <= end_agno; agno++) {
		error = -xfs_trim_extents(mp, agno, start, end, minlen,
					  &blocks_trimmed);
		if (error)
			last_error = error;
	}

	if (last_error)
		return last_error;

	range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
	if (copy_to_user(urange, &range, sizeof(range)))
		return -XFS_ERROR(EFAULT);
	return 0;
}
Beispiel #5
0
/*
 * If we are doing readahead on an inode buffer, we might be in log recovery
 * reading an inode allocation buffer that hasn't yet been replayed, and hence
 * has not had the inode cores stamped into it. Hence for readahead, the buffer
 * may be potentially invalid.
 *
 * If the readahead buffer is invalid, we need to mark it with an error and
 * clear the DONE status of the buffer so that a followup read will re-read it
 * from disk. We don't report the error otherwise to avoid warnings during log
 * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
 * because all we want to do is say readahead failed; there is no-one to report
 * the error to, so this will distinguish it from a non-ra verifier failure.
 * Changes to this readahead error behavour also need to be reflected in
 * xfs_dquot_buf_readahead_verify().
 */
static void
xfs_inode_buf_verify(
	struct xfs_buf	*bp,
	bool		readahead)
{
	struct xfs_mount *mp = bp->b_target->bt_mount;
	xfs_agnumber_t	agno;
	int		i;
	int		ni;

	/*
	 * Validate the magic number and version of every inode in the buffer
	 */
	agno = xfs_daddr_to_agno(mp, XFS_BUF_ADDR(bp));
	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;
		xfs_agino_t	unlinked_ino;

		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
		unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
			xfs_dinode_good_version(mp, dip->di_version) &&
			(unlinked_ino == NULLAGINO ||
			 xfs_verify_agino(mp, agno, unlinked_ino));
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP))) {
			if (readahead) {
				bp->b_flags &= ~XBF_DONE;
				xfs_buf_ioerror(bp, -EIO);
				return;
			}

#ifdef DEBUG
			xfs_alert(mp,
				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
				(unsigned long long)bp->b_bn, i,
				be16_to_cpu(dip->di_magic));
#endif
			xfs_buf_verifier_error(bp, -EFSCORRUPTED,
					__func__, dip, sizeof(*dip),
					NULL);
			return;
		}
	}
}
Beispiel #6
0
/* Execute a getfsmap query against the realtime device. */
STATIC int
__xfs_getfsmap_rtdev(
	struct xfs_trans		*tp,
	struct xfs_fsmap		*keys,
	int				(*query_fn)(struct xfs_trans *,
						    struct xfs_getfsmap_info *),
	struct xfs_getfsmap_info	*info)
{
	struct xfs_mount		*mp = tp->t_mountp;
	xfs_fsblock_t			start_fsb;
	xfs_fsblock_t			end_fsb;
	xfs_daddr_t			eofs;
	int				error = 0;

	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
	if (keys[0].fmr_physical >= eofs)
		return 0;
	if (keys[1].fmr_physical >= eofs)
		keys[1].fmr_physical = eofs - 1;
	start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
	end_fsb = XFS_BB_TO_FSB(mp, keys[1].fmr_physical);

	/* Set up search keys */
	info->low.rm_startblock = start_fsb;
	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
	if (error)
		return error;
	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
	info->low.rm_blockcount = 0;
	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);

	info->high.rm_startblock = end_fsb;
	error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
	if (error)
		return error;
	info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset);
	info->high.rm_blockcount = 0;
	xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);

	trace_xfs_fsmap_low_key(mp, info->dev, info->agno, &info->low);
	trace_xfs_fsmap_high_key(mp, info->dev, info->agno, &info->high);

	return query_fn(tp, info);
}
Beispiel #7
0
/*
 * If we are doing readahead on an inode buffer, we might be in log recovery
 * reading an inode allocation buffer that hasn't yet been replayed, and hence
 * has not had the inode cores stamped into it. Hence for readahead, the buffer
 * may be potentially invalid.
 *
 * If the readahead buffer is invalid, we don't want to mark it with an error,
 * but we do want to clear the DONE status of the buffer so that a followup read
 * will re-read it from disk. This will ensure that we don't get an unnecessary
 * warnings during log recovery and we don't get unnecssary panics on debug
 * kernels.
 */
static void
xfs_inode_buf_verify(
	struct xfs_buf	*bp,
	bool		readahead)
{
	struct xfs_mount *mp = bp->b_target->bt_mount;
	int		i;
	int		ni;

	/*
	 * Validate the magic number and version of every inode in the buffer
	 */
	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;

		dip = (struct xfs_dinode *)xfs_buf_offset(bp,
					(i << mp->m_sb.sb_inodelog));
		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
			    XFS_DINODE_GOOD_VERSION(dip->di_version);
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP,
						XFS_RANDOM_ITOBP_INOTOBP))) {
			if (readahead) {
				bp->b_flags &= ~XBF_DONE;
				return;
			}

			xfs_buf_ioerror(bp, -EFSCORRUPTED);
			xfs_verifier_error(bp);
#ifdef DEBUG
			xfs_alert(mp,
				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
				(unsigned long long)bp->b_bn, i,
				be16_to_cpu(dip->di_magic));
#endif
		}
	}
	xfs_inobp_check(mp, bp);
}
/*
 * returns 1 for success, 0 if we failed to map the extent.
 */
STATIC int
xfs_getbmapx_fix_eof_hole(
	xfs_inode_t		*ip,		/* xfs incore inode pointer */
	struct getbmapx		*out,		/* output structure */
	int			prealloced,	/* this is a file with
						 * preallocated data space */
	__int64_t		end,		/* last block requested */
	xfs_fsblock_t		startblock)
{
	__int64_t		fixlen;
	xfs_mount_t		*mp;		/* file system mount point */
	xfs_ifork_t		*ifp;		/* inode fork pointer */
	xfs_extnum_t		lastx;		/* last extent pointer */
	xfs_fileoff_t		fileblock;

	if (startblock == HOLESTARTBLOCK) {
		mp = ip->i_mount;
		out->bmv_block = -1;
		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
		fixlen -= out->bmv_offset;
		if (prealloced && out->bmv_offset + out->bmv_length == end) {
			/* Came to hole at EOF. Trim it. */
			if (fixlen <= 0)
				return 0;
			out->bmv_length = fixlen;
		}
	} else {
		if (startblock == DELAYSTARTBLOCK)
			out->bmv_block = -2;
		else
			out->bmv_block = xfs_fsb_to_db(ip, startblock);
		fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
		ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
		if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
		   (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
			out->bmv_oflags |= BMV_OF_LAST;
	}

	return 1;
}
/*
 * Adjust quota limits, and start/stop timers accordingly.
 */
STATIC int
xfs_qm_scall_setqlim(
	xfs_mount_t		*mp,
	xfs_dqid_t		id,
	uint			type,
	fs_disk_quota_t		*newlim)
{
	xfs_disk_dquot_t	*ddq;
	xfs_dquot_t		*dqp;
	xfs_trans_t		*tp;
	int			error;
	xfs_qcnt_t		hard, soft;

	if (!capable(CAP_SYS_ADMIN))
		return XFS_ERROR(EPERM);

	if ((newlim->d_fieldmask &
	    (FS_DQ_LIMIT_MASK|FS_DQ_TIMER_MASK|FS_DQ_WARNS_MASK)) == 0)
		return (0);

	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
	if ((error = xfs_trans_reserve(tp, 0, sizeof(xfs_disk_dquot_t) + 128,
				      0, 0, XFS_DEFAULT_LOG_COUNT))) {
		xfs_trans_cancel(tp, 0);
		return (error);
	}

	/*
	 * We don't want to race with a quotaoff so take the quotaoff lock.
	 * (We don't hold an inode lock, so there's nothing else to stop
	 * a quotaoff from happening). (XXXThis doesn't currently happen
	 * because we take the vfslock before calling xfs_qm_sysent).
	 */
	mutex_lock(&(XFS_QI_QOFFLOCK(mp)));

	/*
	 * Get the dquot (locked), and join it to the transaction.
	 * Allocate the dquot if this doesn't exist.
	 */
	if ((error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp))) {
		xfs_trans_cancel(tp, XFS_TRANS_ABORT);
		mutex_unlock(&(XFS_QI_QOFFLOCK(mp)));
		ASSERT(error != ENOENT);
		return (error);
	}
	xfs_dqtrace_entry(dqp, "Q_SETQLIM: AFT DQGET");
	xfs_trans_dqjoin(tp, dqp);
	ddq = &dqp->q_core;

	/*
	 * Make sure that hardlimits are >= soft limits before changing.
	 */
	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
			be64_to_cpu(ddq->d_blk_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
			be64_to_cpu(ddq->d_blk_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_blk_hardlimit = cpu_to_be64(hard);
		ddq->d_blk_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			mp->m_quotainfo->qi_bhardlimit = hard;
			mp->m_quotainfo->qi_bsoftlimit = soft;
		}
	} else {
		qdprintk("blkhard %Ld < blksoft %Ld\n", hard, soft);
	}
	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
			be64_to_cpu(ddq->d_rtb_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
			be64_to_cpu(ddq->d_rtb_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
		ddq->d_rtb_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			mp->m_quotainfo->qi_rtbhardlimit = hard;
			mp->m_quotainfo->qi_rtbsoftlimit = soft;
		}
	} else {
		qdprintk("rtbhard %Ld < rtbsoft %Ld\n", hard, soft);
	}

	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
		(xfs_qcnt_t) newlim->d_ino_hardlimit :
			be64_to_cpu(ddq->d_ino_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
		(xfs_qcnt_t) newlim->d_ino_softlimit :
			be64_to_cpu(ddq->d_ino_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_ino_hardlimit = cpu_to_be64(hard);
		ddq->d_ino_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			mp->m_quotainfo->qi_ihardlimit = hard;
			mp->m_quotainfo->qi_isoftlimit = soft;
		}
	} else {
		qdprintk("ihard %Ld < isoft %Ld\n", hard, soft);
	}

	/*
	 * Update warnings counter(s) if requested
	 */
	if (newlim->d_fieldmask & FS_DQ_BWARNS)
		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
	if (newlim->d_fieldmask & FS_DQ_IWARNS)
		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);

	if (id == 0) {
		/*
		 * Timelimits for the super user set the relative time
		 * the other users can be over quota for this file system.
		 * If it is zero a default is used.  Ditto for the default
		 * soft and hard limit values (already done, above), and
		 * for warnings.
		 */
		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
			mp->m_quotainfo->qi_btimelimit = newlim->d_btimer;
			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
		}
		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
			mp->m_quotainfo->qi_itimelimit = newlim->d_itimer;
			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
		}
		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
			mp->m_quotainfo->qi_rtbtimelimit = newlim->d_rtbtimer;
			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
		}
		if (newlim->d_fieldmask & FS_DQ_BWARNS)
			mp->m_quotainfo->qi_bwarnlimit = newlim->d_bwarns;
		if (newlim->d_fieldmask & FS_DQ_IWARNS)
			mp->m_quotainfo->qi_iwarnlimit = newlim->d_iwarns;
		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
			mp->m_quotainfo->qi_rtbwarnlimit = newlim->d_rtbwarns;
	} else {
		/*
		 * If the user is now over quota, start the timelimit.
		 * The user will not be 'warned'.
		 * Note that we keep the timers ticking, whether enforcement
		 * is on or off. We don't really want to bother with iterating
		 * over all ondisk dquots and turning the timers on/off.
		 */
		xfs_qm_adjust_dqtimers(mp, ddq);
	}
	dqp->dq_flags |= XFS_DQ_DIRTY;
	xfs_trans_log_dquot(tp, dqp);

	xfs_dqtrace_entry(dqp, "Q_SETQLIM: COMMIT");
	xfs_trans_commit(tp, 0, NULL);
	xfs_qm_dqprint(dqp);
	xfs_qm_dqrele(dqp);
	mutex_unlock(&(XFS_QI_QOFFLOCK(mp)));

	return (0);
}
Beispiel #10
0
/*
 * Get inode's extents as described in bmv, and format for output.
 * Calls formatter to fill the user's buffer until all extents
 * are mapped, until the passed-in bmv->bmv_count slots have
 * been filled, or until the formatter short-circuits the loop,
 * if it is tracking filled-in extents on its own.
 */
int						/* error code */
xfs_getbmap(
	xfs_inode_t		*ip,
	struct getbmapx		*bmv,		/* user bmap structure */
	xfs_bmap_format_t	formatter,	/* format to user */
	void			*arg)		/* formatter arg */
{
	__int64_t		bmvend;		/* last block requested */
	int			error = 0;	/* return value */
	__int64_t		fixlen;		/* length for -1 case */
	int			i;		/* extent number */
	int			lock;		/* lock state */
	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
	xfs_mount_t		*mp;		/* file system mount point */
	int			nex;		/* # of user extents can do */
	int			nexleft;	/* # of user extents left */
	int			subnex;		/* # of bmapi's can do */
	int			nmap;		/* number of map entries */
	struct getbmapx		*out;		/* output structure */
	int			whichfork;	/* data or attr fork */
	int			prealloced;	/* this is a file with
						 * preallocated data space */
	int			iflags;		/* interface flags */
	int			bmapi_flags;	/* flags for xfs_bmapi */
	int			cur_ext = 0;

	mp = ip->i_mount;
	iflags = bmv->bmv_iflags;
	whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;

	if (whichfork == XFS_ATTR_FORK) {
		if (XFS_IFORK_Q(ip)) {
			if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
			    ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
			    ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
				return XFS_ERROR(EINVAL);
		} else if (unlikely(
			   ip->i_d.di_aformat != 0 &&
			   ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
			XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
					 ip->i_mount);
			return XFS_ERROR(EFSCORRUPTED);
		}

		prealloced = 0;
		fixlen = 1LL << 32;
	} else {
		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
			return XFS_ERROR(EINVAL);

		if (xfs_get_extsz_hint(ip) ||
		    ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
			prealloced = 1;
			fixlen = mp->m_super->s_maxbytes;
		} else {
			prealloced = 0;
			fixlen = XFS_ISIZE(ip);
		}
	}

	if (bmv->bmv_length == -1) {
		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
		bmv->bmv_length =
			max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
	} else if (bmv->bmv_length == 0) {
		bmv->bmv_entries = 0;
		return 0;
	} else if (bmv->bmv_length < 0) {
		return XFS_ERROR(EINVAL);
	}

	nex = bmv->bmv_count - 1;
	if (nex <= 0)
		return XFS_ERROR(EINVAL);
	bmvend = bmv->bmv_offset + bmv->bmv_length;


	if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
		return XFS_ERROR(ENOMEM);
	out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
	if (!out)
		return XFS_ERROR(ENOMEM);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	if (whichfork == XFS_DATA_FORK) {
		if (!(iflags & BMV_IF_DELALLOC) &&
		    (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
			error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
			if (error)
				goto out_unlock_iolock;

			/*
			 * Even after flushing the inode, there can still be
			 * delalloc blocks on the inode beyond EOF due to
			 * speculative preallocation.  These are not removed
			 * until the release function is called or the inode
			 * is inactivated.  Hence we cannot assert here that
			 * ip->i_delayed_blks == 0.
			 */
		}

		lock = xfs_ilock_data_map_shared(ip);
	} else {
		lock = xfs_ilock_attr_map_shared(ip);
	}

	/*
	 * Don't let nex be bigger than the number of extents
	 * we can have assuming alternating holes and real extents.
	 */
	if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
		nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;

	bmapi_flags = xfs_bmapi_aflag(whichfork);
	if (!(iflags & BMV_IF_PREALLOC))
		bmapi_flags |= XFS_BMAPI_IGSTATE;

	/*
	 * Allocate enough space to handle "subnex" maps at a time.
	 */
	error = ENOMEM;
	subnex = 16;
	map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
	if (!map)
		goto out_unlock_ilock;

	bmv->bmv_entries = 0;

	if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
	    (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
		error = 0;
		goto out_free_map;
	}

	nexleft = nex;

	do {
		nmap = (nexleft > subnex) ? subnex : nexleft;
		error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
				       XFS_BB_TO_FSB(mp, bmv->bmv_length),
				       map, &nmap, bmapi_flags);
		if (error)
			goto out_free_map;
		ASSERT(nmap <= subnex);

		for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
			out[cur_ext].bmv_oflags = 0;
			if (map[i].br_state == XFS_EXT_UNWRITTEN)
				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
			else if (map[i].br_startblock == DELAYSTARTBLOCK)
				out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
			out[cur_ext].bmv_offset =
				XFS_FSB_TO_BB(mp, map[i].br_startoff);
			out[cur_ext].bmv_length =
				XFS_FSB_TO_BB(mp, map[i].br_blockcount);
			out[cur_ext].bmv_unused1 = 0;
			out[cur_ext].bmv_unused2 = 0;

			/*
			 * delayed allocation extents that start beyond EOF can
			 * occur due to speculative EOF allocation when the
			 * delalloc extent is larger than the largest freespace
			 * extent at conversion time. These extents cannot be
			 * converted by data writeback, so can exist here even
			 * if we are not supposed to be finding delalloc
			 * extents.
			 */
			if (map[i].br_startblock == DELAYSTARTBLOCK &&
			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
				ASSERT((iflags & BMV_IF_DELALLOC) != 0);

                        if (map[i].br_startblock == HOLESTARTBLOCK &&
			    whichfork == XFS_ATTR_FORK) {
				/* came to the end of attribute fork */
				out[cur_ext].bmv_oflags |= BMV_OF_LAST;
				goto out_free_map;
			}

			if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
					prealloced, bmvend,
					map[i].br_startblock))
				goto out_free_map;

			bmv->bmv_offset =
				out[cur_ext].bmv_offset +
				out[cur_ext].bmv_length;
			bmv->bmv_length =
				max_t(__int64_t, 0, bmvend - bmv->bmv_offset);

			/*
			 * In case we don't want to return the hole,
			 * don't increase cur_ext so that we can reuse
			 * it in the next loop.
			 */
			if ((iflags & BMV_IF_NO_HOLES) &&
			    map[i].br_startblock == HOLESTARTBLOCK) {
				memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
				continue;
			}

			nexleft--;
			bmv->bmv_entries++;
			cur_ext++;
		}
	} while (nmap && nexleft && bmv->bmv_length);

 out_free_map:
	kmem_free(map);
 out_unlock_ilock:
	xfs_iunlock(ip, lock);
 out_unlock_iolock:
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	for (i = 0; i < cur_ext; i++) {
		int full = 0;	/* user array is full */

		/* format results & advance arg */
		error = formatter(&arg, &out[i], &full);
		if (error || full)
			break;
	}

	kmem_free(out);
	return error;
}
Beispiel #11
0
/*
 * Process a bmap update intent item that was recovered from the log.
 * We need to update some inode's bmbt.
 */
int
xfs_bui_recover(
	struct xfs_mount		*mp,
	struct xfs_bui_log_item		*buip,
	struct xfs_defer_ops		*dfops)
{
	int				error = 0;
	unsigned int			bui_type;
	struct xfs_map_extent		*bmap;
	xfs_fsblock_t			startblock_fsb;
	xfs_fsblock_t			inode_fsb;
	xfs_filblks_t			count;
	bool				op_ok;
	struct xfs_bud_log_item		*budp;
	enum xfs_bmap_intent_type	type;
	int				whichfork;
	xfs_exntst_t			state;
	struct xfs_trans		*tp;
	struct xfs_inode		*ip = NULL;
	struct xfs_bmbt_irec		irec;

	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));

	/* Only one mapping operation per BUI... */
	if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
		set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
		xfs_bui_release(buip);
		return -EIO;
	}

	/*
	 * First check the validity of the extent described by the
	 * BUI.  If anything is bad, then toss the BUI.
	 */
	bmap = &buip->bui_format.bui_extents[0];
	startblock_fsb = XFS_BB_TO_FSB(mp,
			   XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
	inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
			XFS_INO_TO_FSB(mp, bmap->me_owner)));
	switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
	case XFS_BMAP_MAP:
	case XFS_BMAP_UNMAP:
		op_ok = true;
		break;
	default:
		op_ok = false;
		break;
	}
	if (!op_ok || startblock_fsb == 0 ||
	    bmap->me_len == 0 ||
	    inode_fsb == 0 ||
	    startblock_fsb >= mp->m_sb.sb_dblocks ||
	    bmap->me_len >= mp->m_sb.sb_agblocks ||
	    inode_fsb >= mp->m_sb.sb_dblocks ||
	    (bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
		/*
		 * This will pull the BUI from the AIL and
		 * free the memory associated with it.
		 */
		set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
		xfs_bui_release(buip);
		return -EIO;
	}

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
	if (error)
		return error;
	budp = xfs_trans_get_bud(tp, buip);

	/* Grab the inode. */
	error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
	if (error)
		goto err_inode;

	if (VFS_I(ip)->i_nlink == 0)
		xfs_iflags_set(ip, XFS_IRECOVERY);

	/* Process deferred bmap item. */
	state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
	whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
			XFS_ATTR_FORK : XFS_DATA_FORK;
	bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
	switch (bui_type) {
	case XFS_BMAP_MAP:
	case XFS_BMAP_UNMAP:
		type = bui_type;
		break;
	default:
		error = -EFSCORRUPTED;
		goto err_inode;
	}
	xfs_trans_ijoin(tp, ip, 0);

	count = bmap->me_len;
	error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
			ip, whichfork, bmap->me_startoff,
			bmap->me_startblock, &count, state);
	if (error)
		goto err_inode;

	if (count > 0) {
		ASSERT(type == XFS_BMAP_UNMAP);
		irec.br_startblock = bmap->me_startblock;
		irec.br_blockcount = count;
		irec.br_startoff = bmap->me_startoff;
		irec.br_state = state;
		error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
		if (error)
			goto err_inode;
	}

	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
	error = xfs_trans_commit(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	IRELE(ip);

	return error;

err_inode:
	xfs_trans_cancel(tp);
	if (ip) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		IRELE(ip);
	}
	return error;
}
Beispiel #12
0
/*
 * Process a refcount update intent item that was recovered from the log.
 * We need to update the refcountbt.
 */
int
xfs_cui_recover(
	struct xfs_mount		*mp,
	struct xfs_cui_log_item		*cuip)
{
	int				i;
	int				error = 0;
	unsigned int			refc_type;
	struct xfs_phys_extent		*refc;
	xfs_fsblock_t			startblock_fsb;
	bool				op_ok;
	struct xfs_cud_log_item		*cudp;
	struct xfs_trans		*tp;
	struct xfs_btree_cur		*rcur = NULL;
	enum xfs_refcount_intent_type	type;
	xfs_fsblock_t			firstfsb;
	xfs_fsblock_t			new_fsb;
	xfs_extlen_t			new_len;
	struct xfs_bmbt_irec		irec;
	struct xfs_defer_ops		dfops;
	bool				requeue_only = false;

	ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));

	/*
	 * First check the validity of the extents described by the
	 * CUI.  If any are bad, then assume that all are bad and
	 * just toss the CUI.
	 */
	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
		refc = &cuip->cui_format.cui_extents[i];
		startblock_fsb = XFS_BB_TO_FSB(mp,
				   XFS_FSB_TO_DADDR(mp, refc->pe_startblock));
		switch (refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK) {
		case XFS_REFCOUNT_INCREASE:
		case XFS_REFCOUNT_DECREASE:
		case XFS_REFCOUNT_ALLOC_COW:
		case XFS_REFCOUNT_FREE_COW:
			op_ok = true;
			break;
		default:
			op_ok = false;
			break;
		}
		if (!op_ok || startblock_fsb == 0 ||
		    refc->pe_len == 0 ||
		    startblock_fsb >= mp->m_sb.sb_dblocks ||
		    refc->pe_len >= mp->m_sb.sb_agblocks ||
		    (refc->pe_flags & ~XFS_REFCOUNT_EXTENT_FLAGS)) {
			/*
			 * This will pull the CUI from the AIL and
			 * free the memory associated with it.
			 */
			set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
			xfs_cui_release(cuip);
			return -EIO;
		}
	}

	/*
	 * Under normal operation, refcount updates are deferred, so we
	 * wouldn't be adding them directly to a transaction.  All
	 * refcount updates manage reservation usage internally and
	 * dynamically by deferring work that won't fit in the
	 * transaction.  Normally, any work that needs to be deferred
	 * gets attached to the same defer_ops that scheduled the
	 * refcount update.  However, we're in log recovery here, so we
	 * we create our own defer_ops and use that to finish up any
	 * work that doesn't fit.
	 */
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
	if (error)
		return error;
	cudp = xfs_trans_get_cud(tp, cuip);

	xfs_defer_init(&dfops, &firstfsb);
	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
		refc = &cuip->cui_format.cui_extents[i];
		refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
		switch (refc_type) {
		case XFS_REFCOUNT_INCREASE:
		case XFS_REFCOUNT_DECREASE:
		case XFS_REFCOUNT_ALLOC_COW:
		case XFS_REFCOUNT_FREE_COW:
			type = refc_type;
			break;
		default:
			error = -EFSCORRUPTED;
			goto abort_error;
		}
		if (requeue_only) {
			new_fsb = refc->pe_startblock;
			new_len = refc->pe_len;
		} else
			error = xfs_trans_log_finish_refcount_update(tp, cudp,
				&dfops, type, refc->pe_startblock, refc->pe_len,
				&new_fsb, &new_len, &rcur);
		if (error)
			goto abort_error;

		/* Requeue what we didn't finish. */
		if (new_len > 0) {
			irec.br_startblock = new_fsb;
			irec.br_blockcount = new_len;
			switch (type) {
			case XFS_REFCOUNT_INCREASE:
				error = xfs_refcount_increase_extent(
						tp->t_mountp, &dfops, &irec);
				break;
			case XFS_REFCOUNT_DECREASE:
				error = xfs_refcount_decrease_extent(
						tp->t_mountp, &dfops, &irec);
				break;
			case XFS_REFCOUNT_ALLOC_COW:
				error = xfs_refcount_alloc_cow_extent(
						tp->t_mountp, &dfops,
						irec.br_startblock,
						irec.br_blockcount);
				break;
			case XFS_REFCOUNT_FREE_COW:
				error = xfs_refcount_free_cow_extent(
						tp->t_mountp, &dfops,
						irec.br_startblock,
						irec.br_blockcount);
				break;
			default:
				ASSERT(0);
			}
			if (error)
				goto abort_error;
			requeue_only = true;
		}
	}

	xfs_refcount_finish_one_cleanup(tp, rcur, error);
	error = xfs_defer_finish(&tp, &dfops, NULL);
	if (error)
		goto abort_defer;
	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
	error = xfs_trans_commit(tp);
	return error;

abort_error:
	xfs_refcount_finish_one_cleanup(tp, rcur, error);
abort_defer:
	xfs_defer_cancel(&dfops);
	xfs_trans_cancel(tp);
	return error;
}
/*
 * Adjust quota limits, and start/stop timers accordingly.
 */
int
xfs_qm_scall_setqlim(
	struct xfs_mount	*mp,
	xfs_dqid_t		id,
	uint			type,
	fs_disk_quota_t		*newlim)
{
	struct xfs_quotainfo	*q = mp->m_quotainfo;
	struct xfs_disk_dquot	*ddq;
	struct xfs_dquot	*dqp;
	struct xfs_trans	*tp;
	int			error;
	xfs_qcnt_t		hard, soft;

	if (newlim->d_fieldmask & ~XFS_DQ_MASK)
		return -EINVAL;
	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
		return 0;

	/*
	 * We don't want to race with a quotaoff so take the quotaoff lock.
	 * We don't hold an inode lock, so there's nothing else to stop
	 * a quotaoff from happening.
	 */
	mutex_lock(&q->qi_quotaofflock);

	/*
	 * Get the dquot (locked) before we start, as we need to do a
	 * transaction to allocate it if it doesn't exist. Once we have the
	 * dquot, unlock it so we can start the next transaction safely. We hold
	 * a reference to the dquot, so it's safe to do this unlock/lock without
	 * it being reclaimed in the mean time.
	 */
	error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp);
	if (error) {
		ASSERT(error != -ENOENT);
		goto out_unlock;
	}
	xfs_dqunlock(dqp);

	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_setqlim, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		goto out_rele;
	}

	xfs_dqlock(dqp);
	xfs_trans_dqjoin(tp, dqp);
	ddq = &dqp->q_core;

	/*
	 * Make sure that hardlimits are >= soft limits before changing.
	 */
	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
			be64_to_cpu(ddq->d_blk_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
			be64_to_cpu(ddq->d_blk_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_blk_hardlimit = cpu_to_be64(hard);
		ddq->d_blk_softlimit = cpu_to_be64(soft);
		xfs_dquot_set_prealloc_limits(dqp);
		if (id == 0) {
			q->qi_bhardlimit = hard;
			q->qi_bsoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
	}
	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
			be64_to_cpu(ddq->d_rtb_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
			be64_to_cpu(ddq->d_rtb_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
		ddq->d_rtb_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			q->qi_rtbhardlimit = hard;
			q->qi_rtbsoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
	}

	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
		(xfs_qcnt_t) newlim->d_ino_hardlimit :
			be64_to_cpu(ddq->d_ino_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
		(xfs_qcnt_t) newlim->d_ino_softlimit :
			be64_to_cpu(ddq->d_ino_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_ino_hardlimit = cpu_to_be64(hard);
		ddq->d_ino_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			q->qi_ihardlimit = hard;
			q->qi_isoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft);
	}

	/*
	 * Update warnings counter(s) if requested
	 */
	if (newlim->d_fieldmask & FS_DQ_BWARNS)
		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
	if (newlim->d_fieldmask & FS_DQ_IWARNS)
		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);

	if (id == 0) {
		/*
		 * Timelimits for the super user set the relative time
		 * the other users can be over quota for this file system.
		 * If it is zero a default is used.  Ditto for the default
		 * soft and hard limit values (already done, above), and
		 * for warnings.
		 */
		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
			q->qi_btimelimit = newlim->d_btimer;
			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
		}
		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
			q->qi_itimelimit = newlim->d_itimer;
			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
		}
		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
			q->qi_rtbtimelimit = newlim->d_rtbtimer;
			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
		}
		if (newlim->d_fieldmask & FS_DQ_BWARNS)
			q->qi_bwarnlimit = newlim->d_bwarns;
		if (newlim->d_fieldmask & FS_DQ_IWARNS)
			q->qi_iwarnlimit = newlim->d_iwarns;
		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
			q->qi_rtbwarnlimit = newlim->d_rtbwarns;
	} else {
		/*
		 * If the user is now over quota, start the timelimit.
		 * The user will not be 'warned'.
		 * Note that we keep the timers ticking, whether enforcement
		 * is on or off. We don't really want to bother with iterating
		 * over all ondisk dquots and turning the timers on/off.
		 */
		xfs_qm_adjust_dqtimers(mp, ddq);
	}
	dqp->dq_flags |= XFS_DQ_DIRTY;
	xfs_trans_log_dquot(tp, dqp);

	error = xfs_trans_commit(tp, 0);

out_rele:
	xfs_qm_dqrele(dqp);
out_unlock:
	mutex_unlock(&q->qi_quotaofflock);
	return error;
}
Beispiel #14
0
/*
 * Mount structure initialization, provides a filled-in xfs_mount_t
 * such that the numerous XFS_* macros can be used.  If dev is zero,
 * no IO will be performed (no size checks, read root inodes).
 */
xfs_mount_t *
libxfs_mount(
	xfs_mount_t	*mp,
	xfs_sb_t	*sb,
	dev_t		dev,
	dev_t		logdev,
	dev_t		rtdev,
	int		flags)
{
	xfs_daddr_t	d;
	xfs_buf_t	*bp;
	xfs_sb_t	*sbp;
	int		error;

	libxfs_buftarg_init(mp, dev, logdev, rtdev);

	mp->m_flags = (LIBXFS_MOUNT_32BITINODES|LIBXFS_MOUNT_32BITINOOPT);
	mp->m_sb = *sb;
	INIT_RADIX_TREE(&mp->m_perag_tree, GFP_KERNEL);
	sbp = &(mp->m_sb);

	xfs_sb_mount_common(mp, sb);

	xfs_alloc_compute_maxlevels(mp);
	xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
	xfs_ialloc_compute_maxlevels(mp);

	if (sbp->sb_imax_pct) {
		/* Make sure the maximum inode count is a multiple of the
		 * units we allocate inodes in.
		 */
		mp->m_maxicount = (sbp->sb_dblocks * sbp->sb_imax_pct) / 100;
		mp->m_maxicount = ((mp->m_maxicount / mp->m_ialloc_blks) *
				  mp->m_ialloc_blks)  << sbp->sb_inopblog;
	} else
		mp->m_maxicount = 0;

	mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;

	/*
	 * Set whether we're using stripe alignment.
	 */
	if (xfs_sb_version_hasdalign(&mp->m_sb)) {
		mp->m_dalign = sbp->sb_unit;
		mp->m_swidth = sbp->sb_width;
	}

	/*
	 * Set whether we're using inode alignment.
	 */
	if (xfs_sb_version_hasalign(&mp->m_sb) &&
	    mp->m_sb.sb_inoalignmt >=
	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
	else
		mp->m_inoalign_mask = 0;
	/*
	 * If we are using stripe alignment, check whether
	 * the stripe unit is a multiple of the inode alignment
	 */
	if (mp->m_dalign && mp->m_inoalign_mask &&
					!(mp->m_dalign & mp->m_inoalign_mask))
		mp->m_sinoalign = mp->m_dalign;
	else
		mp->m_sinoalign = 0;

	/*
	 * Check that the data (and log if separate) are an ok size.
	 */
	d = (xfs_daddr_t) XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
		fprintf(stderr, _("%s: size check failed\n"), progname);
		if (!(flags & LIBXFS_MOUNT_DEBUGGER))
			return NULL;
	}

	/*
	 * We automatically convert v1 inodes to v2 inodes now, so if
	 * the NLINK bit is not set we can't operate on the filesystem.
	 */
	if (!(sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {

		fprintf(stderr, _(
	"%s: V1 inodes unsupported. Please try an older xfsprogs.\n"),
				 progname);
		exit(1);
	}

	/* Check for supported directory formats */
	if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) {

		fprintf(stderr, _(
	"%s: V1 directories unsupported. Please try an older xfsprogs.\n"),
				 progname);
		exit(1);
	}

	/* check for unsupported other features */
	if (!xfs_sb_good_version(sbp)) {
		fprintf(stderr, _(
	"%s: Unsupported features detected. Please try a newer xfsprogs.\n"),
				 progname);
		exit(1);
	}

	xfs_da_mount(mp);

	if (xfs_sb_version_hasattr2(&mp->m_sb))
		mp->m_flags |= LIBXFS_MOUNT_ATTR2;

	/* Initialize the precomputed transaction reservations values */
	xfs_trans_init(mp);

	if (dev == 0)	/* maxtrres, we have no device so leave now */
		return mp;

	bp = libxfs_readbuf(mp->m_dev,
			d - XFS_FSS_TO_BB(mp, 1), XFS_FSS_TO_BB(mp, 1),
			!(flags & LIBXFS_MOUNT_DEBUGGER), NULL);
	if (!bp) {
		fprintf(stderr, _("%s: data size check failed\n"), progname);
		if (!(flags & LIBXFS_MOUNT_DEBUGGER))
			return NULL;
	} else
		libxfs_putbuf(bp);

	if (mp->m_logdev_targp->dev &&
	    mp->m_logdev_targp->dev != mp->m_ddev_targp->dev) {
		d = (xfs_daddr_t) XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
		if ( (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) ||
		     (!(bp = libxfs_readbuf(mp->m_logdev_targp,
					d - XFS_FSB_TO_BB(mp, 1),
					XFS_FSB_TO_BB(mp, 1),
					!(flags & LIBXFS_MOUNT_DEBUGGER), NULL))) ) {
			fprintf(stderr, _("%s: log size checks failed\n"),
					progname);
			if (!(flags & LIBXFS_MOUNT_DEBUGGER))
				return NULL;
		}
		if (bp)
			libxfs_putbuf(bp);
	}

	/* Initialize realtime fields in the mount structure */
	if (rtmount_init(mp, flags)) {
		fprintf(stderr, _("%s: realtime device init failed\n"),
			progname);
			return NULL;
	}

	error = libxfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
	if (error) {
		fprintf(stderr, _("%s: perag init failed\n"),
			progname);
		exit(1);
	}

	return mp;
}
int
xfs_qm_scall_setqlim(
	xfs_mount_t		*mp,
	xfs_dqid_t		id,
	uint			type,
	fs_disk_quota_t		*newlim)
{
	struct xfs_quotainfo	*q = mp->m_quotainfo;
	xfs_disk_dquot_t	*ddq;
	xfs_dquot_t		*dqp;
	xfs_trans_t		*tp;
	int			error;
	xfs_qcnt_t		hard, soft;

	if (newlim->d_fieldmask & ~XFS_DQ_MASK)
		return EINVAL;
	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
		return 0;

	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
	if ((error = xfs_trans_reserve(tp, 0, sizeof(xfs_disk_dquot_t) + 128,
				      0, 0, XFS_DEFAULT_LOG_COUNT))) {
		xfs_trans_cancel(tp, 0);
		return (error);
	}

	mutex_lock(&q->qi_quotaofflock);

	if ((error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp))) {
		xfs_trans_cancel(tp, XFS_TRANS_ABORT);
		ASSERT(error != ENOENT);
		goto out_unlock;
	}
	xfs_trans_dqjoin(tp, dqp);
	ddq = &dqp->q_core;

	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
			be64_to_cpu(ddq->d_blk_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
			be64_to_cpu(ddq->d_blk_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_blk_hardlimit = cpu_to_be64(hard);
		ddq->d_blk_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			q->qi_bhardlimit = hard;
			q->qi_bsoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "blkhard %Ld < blksoft %Ld\n", hard, soft);
	}
	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
			be64_to_cpu(ddq->d_rtb_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
			be64_to_cpu(ddq->d_rtb_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
		ddq->d_rtb_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			q->qi_rtbhardlimit = hard;
			q->qi_rtbsoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld\n", hard, soft);
	}

	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
		(xfs_qcnt_t) newlim->d_ino_hardlimit :
			be64_to_cpu(ddq->d_ino_hardlimit);
	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
		(xfs_qcnt_t) newlim->d_ino_softlimit :
			be64_to_cpu(ddq->d_ino_softlimit);
	if (hard == 0 || hard >= soft) {
		ddq->d_ino_hardlimit = cpu_to_be64(hard);
		ddq->d_ino_softlimit = cpu_to_be64(soft);
		if (id == 0) {
			q->qi_ihardlimit = hard;
			q->qi_isoftlimit = soft;
		}
	} else {
		xfs_debug(mp, "ihard %Ld < isoft %Ld\n", hard, soft);
	}

	if (newlim->d_fieldmask & FS_DQ_BWARNS)
		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
	if (newlim->d_fieldmask & FS_DQ_IWARNS)
		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);

	if (id == 0) {
		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
			q->qi_btimelimit = newlim->d_btimer;
			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
		}
		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
			q->qi_itimelimit = newlim->d_itimer;
			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
		}
		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
			q->qi_rtbtimelimit = newlim->d_rtbtimer;
			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
		}
		if (newlim->d_fieldmask & FS_DQ_BWARNS)
			q->qi_bwarnlimit = newlim->d_bwarns;
		if (newlim->d_fieldmask & FS_DQ_IWARNS)
			q->qi_iwarnlimit = newlim->d_iwarns;
		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
			q->qi_rtbwarnlimit = newlim->d_rtbwarns;
	} else {
		xfs_qm_adjust_dqtimers(mp, ddq);
	}
	dqp->dq_flags |= XFS_DQ_DIRTY;
	xfs_trans_log_dquot(tp, dqp);

	error = xfs_trans_commit(tp, 0);
	xfs_qm_dqrele(dqp);

 out_unlock:
	mutex_unlock(&q->qi_quotaofflock);
	return error;
}