xfs_mount.c

linux 内核源代码

		if (!error) {
			xfs_buf_relse(bp);
		} else {
			cmn_err(CE_WARN, "XFS: size check 3 failed");
			if (error == ENOSPC) {
				error = XFS_ERROR(E2BIG);
			}
			goto error1;
		}
	}

	/*
	 * Initialize realtime fields in the mount structure
	 */
	if ((error = xfs_rtmount_init(mp))) {
		cmn_err(CE_WARN, "XFS: RT mount failed");
		goto error1;
	}

	/*
	 * For client case we are done now
	 */
	if (mfsi_flags & XFS_MFSI_CLIENT) {
		return 0;
	}

	/*
	 *  Copies the low order bits of the timestamp and the randomly
	 *  set "sequence" number out of a UUID.
	 */
	uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid);

	mp->m_dmevmask = 0;	/* not persistent; set after each mount */

	xfs_dir_mount(mp);

	/*
	 * Initialize the attribute manager's entries.
	 */
	mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;

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

	/*
	 * Allocate and initialize the per-ag data.
	 */
	init_rwsem(&mp->m_peraglock);
	mp->m_perag =
		kmem_zalloc(sbp->sb_agcount * sizeof(xfs_perag_t), KM_SLEEP);

	mp->m_maxagi = xfs_initialize_perag(mp, sbp->sb_agcount);

	/*
	 * log's mount-time initialization. Perform 1st part recovery if needed
	 */
	if (likely(sbp->sb_logblocks > 0)) {	/* check for volume case */
		error = xfs_log_mount(mp, mp->m_logdev_targp,
				      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
				      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
		if (error) {
			cmn_err(CE_WARN, "XFS: log mount failed");
			goto error2;
		}
	} else {	/* No log has been defined */
		cmn_err(CE_WARN, "XFS: no log defined");
		XFS_ERROR_REPORT("xfs_mountfs_int(1)", XFS_ERRLEVEL_LOW, mp);
		error = XFS_ERROR(EFSCORRUPTED);
		goto error2;
	}

	/*
	 * Now the log is mounted, we know if it was an unclean shutdown or
	 * not. If it was, with the first phase of recovery has completed, we
	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
	 * but they are recovered transactionally in the second recovery phase
	 * later.
	 *
	 * Hence we can safely re-initialise incore superblock counters from
	 * the per-ag data. These may not be correct if the filesystem was not
	 * cleanly unmounted, so we need to wait for recovery to finish before
	 * doing this.
	 *
	 * If the filesystem was cleanly unmounted, then we can trust the
	 * values in the superblock to be correct and we don't need to do
	 * anything here.
	 *
	 * If we are currently making the filesystem, the initialisation will
	 * fail as the perag data is in an undefined state.
	 */

	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
	     !mp->m_sb.sb_inprogress) {
		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
		if (error) {
			goto error2;
		}
	}
	/*
	 * Get and sanity-check the root inode.
	 * Save the pointer to it in the mount structure.
	 */
	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0);
	if (error) {
		cmn_err(CE_WARN, "XFS: failed to read root inode");
		goto error3;
	}

	ASSERT(rip != NULL);
	rvp = XFS_ITOV(rip);

	if (unlikely((rip->i_d.di_mode & S_IFMT) != S_IFDIR)) {
		cmn_err(CE_WARN, "XFS: corrupted root inode");
		cmn_err(CE_WARN, "Device %s - root %llu is not a directory",
			XFS_BUFTARG_NAME(mp->m_ddev_targp),
			(unsigned long long)rip->i_ino);
		xfs_iunlock(rip, XFS_ILOCK_EXCL);
		XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
				 mp);
		error = XFS_ERROR(EFSCORRUPTED);
		goto error4;
	}
	mp->m_rootip = rip;	/* save it */

	xfs_iunlock(rip, XFS_ILOCK_EXCL);

	/*
	 * Initialize realtime inode pointers in the mount structure
	 */
	if ((error = xfs_rtmount_inodes(mp))) {
		/*
		 * Free up the root inode.
		 */
		cmn_err(CE_WARN, "XFS: failed to read RT inodes");
		goto error4;
	}

	/*
	 * If fs is not mounted readonly, then update the superblock
	 * unit and width changes.
	 */
	if (update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY))
		xfs_mount_log_sbunit(mp, update_flags);

	/*
	 * Initialise the XFS quota management subsystem for this mount
	 */
	if ((error = XFS_QM_INIT(mp, &quotamount, &quotaflags)))
		goto error4;

	/*
	 * Finish recovering the file system.  This part needed to be
	 * delayed until after the root and real-time bitmap inodes
	 * were consistently read in.
	 */
	error = xfs_log_mount_finish(mp, mfsi_flags);
	if (error) {
		cmn_err(CE_WARN, "XFS: log mount finish failed");
		goto error4;
	}

	/*
	 * Complete the quota initialisation, post-log-replay component.
	 */
	if ((error = XFS_QM_MOUNT(mp, quotamount, quotaflags, mfsi_flags)))
		goto error4;

	/*
	 * Now we are mounted, reserve a small amount of unused space for
	 * privileged transactions. This is needed so that transaction
	 * space required for critical operations can dip into this pool
	 * when at ENOSPC. This is needed for operations like create with
	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
	 * are not allowed to use this reserved space.
	 *
	 * We default to 5% or 1024 fsbs of space reserved, whichever is smaller.
	 * This may drive us straight to ENOSPC on mount, but that implies
	 * we were already there on the last unmount.
	 */
	resblks = mp->m_sb.sb_dblocks;
	do_div(resblks, 20);
	resblks = min_t(__uint64_t, resblks, 1024);
	xfs_reserve_blocks(mp, &resblks, NULL);

	return 0;

 error4:
	/*
	 * Free up the root inode.
	 */
	VN_RELE(rvp);
 error3:
	xfs_log_unmount_dealloc(mp);
 error2:
	for (agno = 0; agno < sbp->sb_agcount; agno++)
		if (mp->m_perag[agno].pagb_list)
			kmem_free(mp->m_perag[agno].pagb_list,
			  sizeof(xfs_perag_busy_t) * XFS_PAGB_NUM_SLOTS);
	kmem_free(mp->m_perag, sbp->sb_agcount * sizeof(xfs_perag_t));
	mp->m_perag = NULL;
	/* FALLTHROUGH */
 error1:
	if (uuid_mounted)
		xfs_uuid_unmount(mp);
	xfs_freesb(mp);
	return error;
}

/*
 * xfs_unmountfs
 *
 * This flushes out the inodes,dquots and the superblock, unmounts the
 * log and makes sure that incore structures are freed.
 */
int
xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
{
	__uint64_t	resblks;

	/*
	 * We can potentially deadlock here if we have an inode cluster
	 * that has been freed has it's buffer still pinned in memory because
	 * the transaction is still sitting in a iclog. The stale inodes
	 * on that buffer will have their flush locks held until the
	 * transaction hits the disk and the callbacks run. the inode
	 * flush takes the flush lock unconditionally and with nothing to
	 * push out the iclog we will never get that unlocked. hence we
	 * need to force the log first.
	 */
	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
	xfs_iflush_all(mp);

	XFS_QM_DQPURGEALL(mp, XFS_QMOPT_QUOTALL | XFS_QMOPT_UMOUNTING);

	/*
	 * Flush out the log synchronously so that we know for sure
	 * that nothing is pinned.  This is important because bflush()
	 * will skip pinned buffers.
	 */
	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);

	xfs_binval(mp->m_ddev_targp);
	if (mp->m_rtdev_targp) {
		xfs_binval(mp->m_rtdev_targp);
	}

	/*
	 * Unreserve any blocks we have so that when we unmount we don't account
	 * the reserved free space as used. This is really only necessary for
	 * lazy superblock counting because it trusts the incore superblock
	 * counters to be aboslutely correct on clean unmount.
	 *
	 * We don't bother correcting this elsewhere for lazy superblock
	 * counting because on mount of an unclean filesystem we reconstruct the
	 * correct counter value and this is irrelevant.
	 *
	 * For non-lazy counter filesystems, this doesn't matter at all because
	 * we only every apply deltas to the superblock and hence the incore
	 * value does not matter....
	 */
	resblks = 0;
	xfs_reserve_blocks(mp, &resblks, NULL);

	xfs_log_sbcount(mp, 1);
	xfs_unmountfs_writesb(mp);
	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
	xfs_log_unmount(mp);			/* Done! No more fs ops. */

	xfs_freesb(mp);

	/*
	 * All inodes from this mount point should be freed.
	 */
	ASSERT(mp->m_inodes == NULL);

	xfs_unmountfs_close(mp, cr);
	if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0)
		xfs_uuid_unmount(mp);

#if defined(DEBUG) || defined(INDUCE_IO_ERROR)
	xfs_errortag_clearall(mp, 0);
#endif
	XFS_IODONE(mp);
	xfs_mount_free(mp);
	return 0;
}

void
xfs_unmountfs_close(xfs_mount_t *mp, struct cred *cr)
{
	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
		xfs_free_buftarg(mp->m_logdev_targp, 1);
	if (mp->m_rtdev_targp)
		xfs_free_buftarg(mp->m_rtdev_targp, 1);
	xfs_free_buftarg(mp->m_ddev_targp, 0);
}

STATIC void
xfs_unmountfs_wait(xfs_mount_t *mp)
{
	if (mp->m_logdev_targp != mp->m_ddev_targp)
		xfs_wait_buftarg(mp->m_logdev_targp);
	if (mp->m_rtdev_targp)
		xfs_wait_buftarg(mp->m_rtdev_targp);
	xfs_wait_buftarg(mp->m_ddev_targp);
}

int
xfs_fs_writable(xfs_mount_t *mp)
{
	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
		(mp->m_flags & XFS_MOUNT_RDONLY));
}

/*
 * xfs_log_sbcount
 *
 * Called either periodically to keep the on disk superblock values
 * roughly up to date or from unmount to make sure the values are
 * correct on a clean unmount.
 *
 * Note this code can be called during the process of freezing, so
 * we may need to use the transaction allocator which does not not
 * block when the transaction subsystem is in its frozen state.
 */
int
xfs_log_sbcount(
	xfs_mount_t	*mp,
	uint		sync)
{
	xfs_trans_t	*tp;
	int		error;

	if (!xfs_fs_writable(mp))
		return 0;

	xfs_icsb_sync_counters(mp);

	/*
	 * we don't need to do this if we are updating the superblock
	 * counters on every modification.
	 */
	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
		return 0;

	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
					XFS_DEFAULT_LOG_COUNT);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}

	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
	if (sync)
		xfs_trans_set_sync(tp);
	xfs_trans_commit(tp, 0);

	return 0;
}

STATIC void
xfs_mark_shared_ro(
	xfs_mount_t	*mp,
	xfs_buf_t	*bp)
{
	xfs_dsb_t	*sb = XFS_BUF_TO_SBP(bp);
	__uint16_t	version;

	if (!(sb->sb_flags & XFS_SBF_READONLY))
		sb->sb_flags |= XFS_SBF_READONLY;

	version = be16_to_cpu(sb->sb_versionnum);
	if ((version & XFS_SB_VERSION_NUMBITS) != XFS_SB_VERSION_4 ||
	    !(version & XFS_SB_VERSION_SHAREDBIT))
		version |= XFS_SB_VERSION_SHAREDBIT;
	sb->sb_versionnum = cpu_to_be16(version);
}

int
xfs_unmountfs_writesb(xfs_mount_t *mp)
{
	xfs_buf_t	*sbp;
	int		error = 0;

	/*
	 * skip superblock write if fs is read-only, or
	 * if we are doing a forced umount.
	 */
	if (!((mp->m_flags & XFS_MOUNT_RDONLY) ||
		XFS_FORCED_SHUTDOWN(mp))) {

		sbp = xfs_getsb(mp, 0);

		/*
		 * mark shared-readonly if desired
		 */
		if (mp->m_mk_sharedro)
			xfs_mark_shared_ro(mp, sbp);

		XFS_BUF_UNDONE(sbp);
		XFS_BUF_UNREAD(sbp);
		XFS_BUF_UNDELAYWRITE(sbp);
		XFS_BUF_WRITE(sbp);
		XFS_BUF_UNASYNC(sbp);
		ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp);
		xfsbdstrat(mp, sbp);
		/* Nevermind errors we might get here. */
		error = xfs_iowait(sbp);
		if (error)
			xfs_ioerror_alert("xfs_unmountfs_writesb",
					  mp, sbp, XFS_BUF_ADDR(sbp));
		if (error && mp->m_mk_sharedro)
			xfs_fs_cmn_err(CE_ALERT, mp, "Superblock write error detected while unmounting.  Filesystem may not be marked shared readonly");
		xfs_buf_relse(sbp);
	}
	return error;
}

/*
 * xfs_mod_sb() can be used to copy arbitrary changes to the
 * in-core superblock into the superblock buffer to be logged.
 * It does not provide the higher level of locking that is
 * needed to protect the in-core superblock from concurrent
 * access.
 */
void
xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
{
	xfs_buf_t	*bp;
	int		first;
	int		last;
	xfs_mount_t	*mp;
	xfs_sb_field_t	f;

	ASSERT(fields);
	if (!fields)
		return;
	mp = tp->t_mountp;
	bp = xfs_trans_getsb(tp, mp, 0);
	first = sizeof(xfs_sb_t);
	last = 0;

	/* translate/copy */

	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields);

	/* find modified range */

	f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
	first = xfs_sb_info[f].offset;

	f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
	last = xfs_sb_info[f + 1].offset - 1;

	xfs_trans_log_buf(tp, bp, first, last);
}


/*
 * xfs_mod_incore_sb_unlocked() is a utility routine common used to apply
 * a delta to a specified field in the in-core superblock.  Simply
 * switch on the field indicated and apply the delta to that field.
 * Fields are not allowed to dip below zero, so if the delta would
 * do this do not apply it and return EINVAL.
 *
 * The SB_LOCK must be held when this routine is called.
 */
int
xfs_mod_incore_sb_unlocked(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field,
	int64_t		delta,
	int		rsvd)
{
	int		scounter;	/* short counter for 32 bit fields */
	long long	lcounter;	/* long counter for 64 bit fields */
	long long	res_used, rem;

	/*
	 * With the in-core superblock spin lock held, switch