xfs_mount.c

linux 内核源代码

	 * on the indicated field.  Apply the delta to the
	 * proper field.  If the fields value would dip below
	 * 0, then do not apply the delta and return EINVAL.
	 */
	switch (field) {
	case XFS_SBS_ICOUNT:
		lcounter = (long long)mp->m_sb.sb_icount;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_icount = lcounter;
		return 0;
	case XFS_SBS_IFREE:
		lcounter = (long long)mp->m_sb.sb_ifree;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_ifree = lcounter;
		return 0;
	case XFS_SBS_FDBLOCKS:
		lcounter = (long long)
			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);

		if (delta > 0) {		/* Putting blocks back */
			if (res_used > delta) {
				mp->m_resblks_avail += delta;
			} else {
				rem = delta - res_used;
				mp->m_resblks_avail = mp->m_resblks;
				lcounter += rem;
			}
		} else {				/* Taking blocks away */

			lcounter += delta;

		/*
		 * If were out of blocks, use any available reserved blocks if
		 * were allowed to.
		 */

			if (lcounter < 0) {
				if (rsvd) {
					lcounter = (long long)mp->m_resblks_avail + delta;
					if (lcounter < 0) {
						return XFS_ERROR(ENOSPC);
					}
					mp->m_resblks_avail = lcounter;
					return 0;
				} else {	/* not reserved */
					return XFS_ERROR(ENOSPC);
				}
			}
		}

		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
		return 0;
	case XFS_SBS_FREXTENTS:
		lcounter = (long long)mp->m_sb.sb_frextents;
		lcounter += delta;
		if (lcounter < 0) {
			return XFS_ERROR(ENOSPC);
		}
		mp->m_sb.sb_frextents = lcounter;
		return 0;
	case XFS_SBS_DBLOCKS:
		lcounter = (long long)mp->m_sb.sb_dblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_dblocks = lcounter;
		return 0;
	case XFS_SBS_AGCOUNT:
		scounter = mp->m_sb.sb_agcount;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_agcount = scounter;
		return 0;
	case XFS_SBS_IMAX_PCT:
		scounter = mp->m_sb.sb_imax_pct;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_imax_pct = scounter;
		return 0;
	case XFS_SBS_REXTSIZE:
		scounter = mp->m_sb.sb_rextsize;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_rextsize = scounter;
		return 0;
	case XFS_SBS_RBMBLOCKS:
		scounter = mp->m_sb.sb_rbmblocks;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_rbmblocks = scounter;
		return 0;
	case XFS_SBS_RBLOCKS:
		lcounter = (long long)mp->m_sb.sb_rblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_rblocks = lcounter;
		return 0;
	case XFS_SBS_REXTENTS:
		lcounter = (long long)mp->m_sb.sb_rextents;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_rextents = lcounter;
		return 0;
	case XFS_SBS_REXTSLOG:
		scounter = mp->m_sb.sb_rextslog;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return XFS_ERROR(EINVAL);
		}
		mp->m_sb.sb_rextslog = scounter;
		return 0;
	default:
		ASSERT(0);
		return XFS_ERROR(EINVAL);
	}
}

/*
 * xfs_mod_incore_sb() is used to change a field in the in-core
 * superblock structure by the specified delta.  This modification
 * is protected by the SB_LOCK.  Just use the xfs_mod_incore_sb_unlocked()
 * routine to do the work.
 */
int
xfs_mod_incore_sb(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field,
	int64_t		delta,
	int		rsvd)
{
	unsigned long	s;
	int	status;

	/* check for per-cpu counters */
	switch (field) {
#ifdef HAVE_PERCPU_SB
	case XFS_SBS_ICOUNT:
	case XFS_SBS_IFREE:
	case XFS_SBS_FDBLOCKS:
		if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
			status = xfs_icsb_modify_counters(mp, field,
							delta, rsvd);
			break;
		}
		/* FALLTHROUGH */
#endif
	default:
		s = XFS_SB_LOCK(mp);
		status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
		XFS_SB_UNLOCK(mp, s);
		break;
	}

	return status;
}

/*
 * xfs_mod_incore_sb_batch() is used to change more than one field
 * in the in-core superblock structure at a time.  This modification
 * is protected by a lock internal to this module.  The fields and
 * changes to those fields are specified in the array of xfs_mod_sb
 * structures passed in.
 *
 * Either all of the specified deltas will be applied or none of
 * them will.  If any modified field dips below 0, then all modifications
 * will be backed out and EINVAL will be returned.
 */
int
xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd)
{
	unsigned long	s;
	int		status=0;
	xfs_mod_sb_t	*msbp;

	/*
	 * Loop through the array of mod structures and apply each
	 * individually.  If any fail, then back out all those
	 * which have already been applied.  Do all of this within
	 * the scope of the SB_LOCK so that all of the changes will
	 * be atomic.
	 */
	s = XFS_SB_LOCK(mp);
	msbp = &msb[0];
	for (msbp = &msbp[0]; msbp < (msb + nmsb); msbp++) {
		/*
		 * Apply the delta at index n.  If it fails, break
		 * from the loop so we'll fall into the undo loop
		 * below.
		 */
		switch (msbp->msb_field) {
#ifdef HAVE_PERCPU_SB
		case XFS_SBS_ICOUNT:
		case XFS_SBS_IFREE:
		case XFS_SBS_FDBLOCKS:
			if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
				XFS_SB_UNLOCK(mp, s);
				status = xfs_icsb_modify_counters(mp,
							msbp->msb_field,
							msbp->msb_delta, rsvd);
				s = XFS_SB_LOCK(mp);
				break;
			}
			/* FALLTHROUGH */
#endif
		default:
			status = xfs_mod_incore_sb_unlocked(mp,
						msbp->msb_field,
						msbp->msb_delta, rsvd);
			break;
		}

		if (status != 0) {
			break;
		}
	}

	/*
	 * If we didn't complete the loop above, then back out
	 * any changes made to the superblock.  If you add code
	 * between the loop above and here, make sure that you
	 * preserve the value of status. Loop back until
	 * we step below the beginning of the array.  Make sure
	 * we don't touch anything back there.
	 */
	if (status != 0) {
		msbp--;
		while (msbp >= msb) {
			switch (msbp->msb_field) {
#ifdef HAVE_PERCPU_SB
			case XFS_SBS_ICOUNT:
			case XFS_SBS_IFREE:
			case XFS_SBS_FDBLOCKS:
				if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
					XFS_SB_UNLOCK(mp, s);
					status = xfs_icsb_modify_counters(mp,
							msbp->msb_field,
							-(msbp->msb_delta),
							rsvd);
					s = XFS_SB_LOCK(mp);
					break;
				}
				/* FALLTHROUGH */
#endif
			default:
				status = xfs_mod_incore_sb_unlocked(mp,
							msbp->msb_field,
							-(msbp->msb_delta),
							rsvd);
				break;
			}
			ASSERT(status == 0);
			msbp--;
		}
	}
	XFS_SB_UNLOCK(mp, s);
	return status;
}

/*
 * xfs_getsb() is called to obtain the buffer for the superblock.
 * The buffer is returned locked and read in from disk.
 * The buffer should be released with a call to xfs_brelse().
 *
 * If the flags parameter is BUF_TRYLOCK, then we'll only return
 * the superblock buffer if it can be locked without sleeping.
 * If it can't then we'll return NULL.
 */
xfs_buf_t *
xfs_getsb(
	xfs_mount_t	*mp,
	int		flags)
{
	xfs_buf_t	*bp;

	ASSERT(mp->m_sb_bp != NULL);
	bp = mp->m_sb_bp;
	if (flags & XFS_BUF_TRYLOCK) {
		if (!XFS_BUF_CPSEMA(bp)) {
			return NULL;
		}
	} else {
		XFS_BUF_PSEMA(bp, PRIBIO);
	}
	XFS_BUF_HOLD(bp);
	ASSERT(XFS_BUF_ISDONE(bp));
	return bp;
}

/*
 * Used to free the superblock along various error paths.
 */
void
xfs_freesb(
	xfs_mount_t	*mp)
{
	xfs_buf_t	*bp;

	/*
	 * Use xfs_getsb() so that the buffer will be locked
	 * when we call xfs_buf_relse().
	 */
	bp = xfs_getsb(mp, 0);
	XFS_BUF_UNMANAGE(bp);
	xfs_buf_relse(bp);
	mp->m_sb_bp = NULL;
}

/*
 * See if the UUID is unique among mounted XFS filesystems.
 * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
 */
STATIC int
xfs_uuid_mount(
	xfs_mount_t	*mp)
{
	if (uuid_is_nil(&mp->m_sb.sb_uuid)) {
		cmn_err(CE_WARN,
			"XFS: Filesystem %s has nil UUID - can't mount",
			mp->m_fsname);
		return -1;
	}
	if (!uuid_table_insert(&mp->m_sb.sb_uuid)) {
		cmn_err(CE_WARN,
			"XFS: Filesystem %s has duplicate UUID - can't mount",
			mp->m_fsname);
		return -1;
	}
	return 0;
}

/*
 * Remove filesystem from the UUID table.
 */
STATIC void
xfs_uuid_unmount(
	xfs_mount_t	*mp)
{
	uuid_table_remove(&mp->m_sb.sb_uuid);
}

/*
 * Used to log changes to the superblock unit and width fields which could
 * be altered by the mount options. Only the first superblock is updated.
 */
STATIC void
xfs_mount_log_sbunit(
	xfs_mount_t	*mp,
	__int64_t	fields)
{
	xfs_trans_t	*tp;

	ASSERT(fields & (XFS_SB_UNIT|XFS_SB_WIDTH|XFS_SB_UUID));

	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
	if (xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
				XFS_DEFAULT_LOG_COUNT)) {
		xfs_trans_cancel(tp, 0);
		return;
	}
	xfs_mod_sb(tp, fields);
	xfs_trans_commit(tp, 0);
}


#ifdef HAVE_PERCPU_SB
/*
 * Per-cpu incore superblock counters
 *
 * Simple concept, difficult implementation
 *
 * Basically, replace the incore superblock counters with a distributed per cpu
 * counter for contended fields (e.g.  free block count).
 *
 * Difficulties arise in that the incore sb is used for ENOSPC checking, and
 * hence needs to be accurately read when we are running low on space. Hence
 * there is a method to enable and disable the per-cpu counters based on how
 * much "stuff" is available in them.
 *
 * Basically, a counter is enabled if there is enough free resource to justify
 * running a per-cpu fast-path. If the per-cpu counter runs out (i.e. a local
 * ENOSPC), then we disable the counters to synchronise all callers and
 * re-distribute the available resources.
 *
 * If, once we redistributed the available resources, we still get a failure,
 * we disable the per-cpu counter and go through the slow path.
 *
 * The slow path is the current xfs_mod_incore_sb() function.  This means that
 * when we disable a per-cpu counter, we need to drain it's resources back to
 * the global superblock. We do this after disabling the counter to prevent
 * more threads from queueing up on the counter.
 *
 * Essentially, this means that we still need a lock in the fast path to enable
 * synchronisation between the global counters and the per-cpu counters. This
 * is not a problem because the lock will be local to a CPU almost all the time
 * and have little contention except when we get to ENOSPC conditions.
 *
 * Basically, this lock becomes a barrier that enables us to lock out the fast
 * path while we do things like enabling and disabling counters and
 * synchronising the counters.
 *
 * Locking rules:
 *
 * 	1. XFS_SB_LOCK() before picking up per-cpu locks
 * 	2. per-cpu locks always picked up via for_each_online_cpu() order
 * 	3. accurate counter sync requires XFS_SB_LOCK + per cpu locks
 * 	4. modifying per-cpu counters requires holding per-cpu lock
 * 	5. modifying global counters requires holding XFS_SB_LOCK
 *	6. enabling or disabling a counter requires holding the XFS_SB_LOCK
 *	   and _none_ of the per-cpu locks.
 *
 * Disabled counters are only ever re-enabled by a balance operation
 * that results in more free resources per CPU than a given threshold.
 * To ensure counters don't remain disabled, they are rebalanced when
 * the global resource goes above a higher threshold (i.e. some hysteresis
 * is present to prevent thrashing).
 */

#ifdef CONFIG_HOTPLUG_CPU
/*
 * hot-plug CPU notifier support.
 *
 * We need a notifier per filesystem as we need to be able to identify
 * the filesystem to balance the counters out. This is achieved by
 * having a notifier block embedded in the xfs_mount_t and doing pointer
 * magic to get the mount pointer from the notifier block address.
 */
STATIC int
xfs_icsb_cpu_notify(
	struct notifier_block *nfb,
	unsigned long action,
	void *hcpu)
{
	xfs_icsb_cnts_t *cntp;
	xfs_mount_t	*mp;
	int		s;

	mp = (xfs_mount_t *)container_of(nfb, xfs_mount_t, m_icsb_notifier);
	cntp = (xfs_icsb_cnts_t *)
			per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		/* Easy Case - initialize the area and locks, and
		 * then rebalance when online does everything else for us. */
		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		xfs_icsb_lock(mp);
		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0, 0);
		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0, 0);
		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0, 0);
		xfs_icsb_unlock(mp);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN: