xfs_mount.c

linux 内核源代码

		if (size == 1 || xfs_sb_info[f].type == 1) {
			memcpy(to_ptr + first, from_ptr + first, size);
		} else {
			switch (size) {
			case 2:
				*(__be16 *)(to_ptr + first) =
					cpu_to_be16(*(__u16 *)(from_ptr + first));
				break;
			case 4:
				*(__be32 *)(to_ptr + first) =
					cpu_to_be32(*(__u32 *)(from_ptr + first));
				break;
			case 8:
				*(__be64 *)(to_ptr + first) =
					cpu_to_be64(*(__u64 *)(from_ptr + first));
				break;
			default:
				ASSERT(0);
			}
		}

		fields &= ~(1LL << f);
	}
}

/*
 * xfs_readsb
 *
 * Does the initial read of the superblock.
 */
int
xfs_readsb(xfs_mount_t *mp, int flags)
{
	unsigned int	sector_size;
	unsigned int	extra_flags;
	xfs_buf_t	*bp;
	int		error;

	ASSERT(mp->m_sb_bp == NULL);
	ASSERT(mp->m_ddev_targp != NULL);

	/*
	 * Allocate a (locked) buffer to hold the superblock.
	 * This will be kept around at all times to optimize
	 * access to the superblock.
	 */
	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
	extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;

	bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
				BTOBB(sector_size), extra_flags);
	if (!bp || XFS_BUF_ISERROR(bp)) {
		xfs_fs_mount_cmn_err(flags, "SB read failed");
		error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
		goto fail;
	}
	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);

	/*
	 * Initialize the mount structure from the superblock.
	 * But first do some basic consistency checking.
	 */
	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));

	error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags);
	if (error) {
		xfs_fs_mount_cmn_err(flags, "SB validate failed");
		goto fail;
	}

	/*
	 * We must be able to do sector-sized and sector-aligned IO.
	 */
	if (sector_size > mp->m_sb.sb_sectsize) {
		xfs_fs_mount_cmn_err(flags,
			"device supports only %u byte sectors (not %u)",
			sector_size, mp->m_sb.sb_sectsize);
		error = ENOSYS;
		goto fail;
	}

	/*
	 * If device sector size is smaller than the superblock size,
	 * re-read the superblock so the buffer is correctly sized.
	 */
	if (sector_size < mp->m_sb.sb_sectsize) {
		XFS_BUF_UNMANAGE(bp);
		xfs_buf_relse(bp);
		sector_size = mp->m_sb.sb_sectsize;
		bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
					BTOBB(sector_size), extra_flags);
		if (!bp || XFS_BUF_ISERROR(bp)) {
			xfs_fs_mount_cmn_err(flags, "SB re-read failed");
			error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
			goto fail;
		}
		ASSERT(XFS_BUF_ISBUSY(bp));
		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
	}

	/* Initialize per-cpu counters */
	xfs_icsb_reinit_counters(mp);

	mp->m_sb_bp = bp;
	xfs_buf_relse(bp);
	ASSERT(XFS_BUF_VALUSEMA(bp) > 0);
	return 0;

 fail:
	if (bp) {
		XFS_BUF_UNMANAGE(bp);
		xfs_buf_relse(bp);
	}
	return error;
}


/*
 * xfs_mount_common
 *
 * Mount initialization code establishing various mount
 * fields from the superblock associated with the given
 * mount structure
 */
STATIC void
xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
{
	int	i;

	mp->m_agfrotor = mp->m_agirotor = 0;
	spinlock_init(&mp->m_agirotor_lock, "m_agirotor_lock");
	mp->m_maxagi = mp->m_sb.sb_agcount;
	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
	mp->m_litino = sbp->sb_inodesize -
		((uint)sizeof(xfs_dinode_core_t) + (uint)sizeof(xfs_agino_t));
	mp->m_blockmask = sbp->sb_blocksize - 1;
	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
	mp->m_blockwmask = mp->m_blockwsize - 1;
	INIT_LIST_HEAD(&mp->m_del_inodes);

	/*
	 * Setup for attributes, in case they get created.
	 * This value is for inodes getting attributes for the first time,
	 * the per-inode value is for old attribute values.
	 */
	ASSERT(sbp->sb_inodesize >= 256 && sbp->sb_inodesize <= 2048);
	switch (sbp->sb_inodesize) {
	case 256:
		mp->m_attroffset = XFS_LITINO(mp) -
				   XFS_BMDR_SPACE_CALC(MINABTPTRS);
		break;
	case 512:
	case 1024:
	case 2048:
		mp->m_attroffset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
		break;
	default:
		ASSERT(0);
	}
	ASSERT(mp->m_attroffset < XFS_LITINO(mp));

	for (i = 0; i < 2; i++) {
		mp->m_alloc_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_alloc, i == 0);
		mp->m_alloc_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_alloc, i == 0);
	}
	for (i = 0; i < 2; i++) {
		mp->m_bmap_dmxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_bmbt, i == 0);
		mp->m_bmap_dmnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_bmbt, i == 0);
	}
	for (i = 0; i < 2; i++) {
		mp->m_inobt_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_inobt, i == 0);
		mp->m_inobt_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_inobt, i == 0);
	}

	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
					sbp->sb_inopblock);
	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
}

/*
 * xfs_initialize_perag_data
 *
 * Read in each per-ag structure so we can count up the number of
 * allocated inodes, free inodes and used filesystem blocks as this
 * information is no longer persistent in the superblock. Once we have
 * this information, write it into the in-core superblock structure.
 */
STATIC int
xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
{
	xfs_agnumber_t	index;
	xfs_perag_t	*pag;
	xfs_sb_t	*sbp = &mp->m_sb;
	uint64_t	ifree = 0;
	uint64_t	ialloc = 0;
	uint64_t	bfree = 0;
	uint64_t	bfreelst = 0;
	uint64_t	btree = 0;
	int		error;
	int		s;

	for (index = 0; index < agcount; index++) {
		/*
		 * read the agf, then the agi. This gets us
		 * all the inforamtion we need and populates the
		 * per-ag structures for us.
		 */
		error = xfs_alloc_pagf_init(mp, NULL, index, 0);
		if (error)
			return error;

		error = xfs_ialloc_pagi_init(mp, NULL, index);
		if (error)
			return error;
		pag = &mp->m_perag[index];
		ifree += pag->pagi_freecount;
		ialloc += pag->pagi_count;
		bfree += pag->pagf_freeblks;
		bfreelst += pag->pagf_flcount;
		btree += pag->pagf_btreeblks;
	}
	/*
	 * Overwrite incore superblock counters with just-read data
	 */
	s = XFS_SB_LOCK(mp);
	sbp->sb_ifree = ifree;
	sbp->sb_icount = ialloc;
	sbp->sb_fdblocks = bfree + bfreelst + btree;
	XFS_SB_UNLOCK(mp, s);

	/* Fixup the per-cpu counters as well. */
	xfs_icsb_reinit_counters(mp);

	return 0;
}

/*
 * xfs_mountfs
 *
 * This function does the following on an initial mount of a file system:
 *	- reads the superblock from disk and init the mount struct
 *	- if we're a 32-bit kernel, do a size check on the superblock
 *		so we don't mount terabyte filesystems
 *	- init mount struct realtime fields
 *	- allocate inode hash table for fs
 *	- init directory manager
 *	- perform recovery and init the log manager
 */
int
xfs_mountfs(
	xfs_mount_t	*mp,
	int		mfsi_flags)
{
	xfs_buf_t	*bp;
	xfs_sb_t	*sbp = &(mp->m_sb);
	xfs_inode_t	*rip;
	bhv_vnode_t	*rvp = NULL;
	int		readio_log, writeio_log;
	xfs_daddr_t	d;
	__uint64_t	resblks;
	__int64_t	update_flags;
	uint		quotamount, quotaflags;
	int		agno;
	int		uuid_mounted = 0;
	int		error = 0;

	if (mp->m_sb_bp == NULL) {
		if ((error = xfs_readsb(mp, mfsi_flags))) {
			return error;
		}
	}
	xfs_mount_common(mp, sbp);

	/*
	 * Check if sb_agblocks is aligned at stripe boundary
	 * If sb_agblocks is NOT aligned turn off m_dalign since
	 * allocator alignment is within an ag, therefore ag has
	 * to be aligned at stripe boundary.
	 */
	update_flags = 0LL;
	if (mp->m_dalign && !(mfsi_flags & XFS_MFSI_SECOND)) {
		/*
		 * If stripe unit and stripe width are not multiples
		 * of the fs blocksize turn off alignment.
		 */
		if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
		    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
			if (mp->m_flags & XFS_MOUNT_RETERR) {
				cmn_err(CE_WARN,
					"XFS: alignment check 1 failed");
				error = XFS_ERROR(EINVAL);
				goto error1;
			}
			mp->m_dalign = mp->m_swidth = 0;
		} else {
			/*
			 * Convert the stripe unit and width to FSBs.
			 */
			mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
			if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
				if (mp->m_flags & XFS_MOUNT_RETERR) {
					error = XFS_ERROR(EINVAL);
					goto error1;
				}
				xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d)/swidth(%d) incompatible with agsize(%d)",
					mp->m_dalign, mp->m_swidth,
					sbp->sb_agblocks);

				mp->m_dalign = 0;
				mp->m_swidth = 0;
			} else if (mp->m_dalign) {
				mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
			} else {
				if (mp->m_flags & XFS_MOUNT_RETERR) {
					xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d) less than bsize(%d)",
                                        	mp->m_dalign,
						mp->m_blockmask +1);
					error = XFS_ERROR(EINVAL);
					goto error1;
				}
				mp->m_swidth = 0;
			}
		}

		/*
		 * Update superblock with new values
		 * and log changes
		 */
		if (XFS_SB_VERSION_HASDALIGN(sbp)) {
			if (sbp->sb_unit != mp->m_dalign) {
				sbp->sb_unit = mp->m_dalign;
				update_flags |= XFS_SB_UNIT;
			}
			if (sbp->sb_width != mp->m_swidth) {
				sbp->sb_width = mp->m_swidth;
				update_flags |= XFS_SB_WIDTH;
			}
		}
	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
		    XFS_SB_VERSION_HASDALIGN(&mp->m_sb)) {
			mp->m_dalign = sbp->sb_unit;
			mp->m_swidth = sbp->sb_width;
	}

	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) {
		__uint64_t	icount;

		/* Make sure the maximum inode count is a multiple of the
		 * units we allocate inodes in.
		 */

		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
		do_div(icount, 100);
		do_div(icount, mp->m_ialloc_blks);
		mp->m_maxicount = (icount * mp->m_ialloc_blks)  <<
				   sbp->sb_inopblog;
	} else
		mp->m_maxicount = 0;

	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);

	/*
	 * XFS uses the uuid from the superblock as the unique
	 * identifier for fsid.  We can not use the uuid from the volume
	 * since a single partition filesystem is identical to a single
	 * partition volume/filesystem.
	 */
	if ((mfsi_flags & XFS_MFSI_SECOND) == 0 &&
	    (mp->m_flags & XFS_MOUNT_NOUUID) == 0) {
		if (xfs_uuid_mount(mp)) {
			error = XFS_ERROR(EINVAL);
			goto error1;
		}
		uuid_mounted=1;
	}

	/*
	 * Set the default minimum read and write sizes unless
	 * already specified in a mount option.
	 * We use smaller I/O sizes when the file system
	 * is being used for NFS service (wsync mount option).
	 */
	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
		if (mp->m_flags & XFS_MOUNT_WSYNC) {
			readio_log = XFS_WSYNC_READIO_LOG;
			writeio_log = XFS_WSYNC_WRITEIO_LOG;
		} else {
			readio_log = XFS_READIO_LOG_LARGE;
			writeio_log = XFS_WRITEIO_LOG_LARGE;
		}
	} else {
		readio_log = mp->m_readio_log;
		writeio_log = mp->m_writeio_log;
	}

	if (sbp->sb_blocklog > readio_log) {
		mp->m_readio_log = sbp->sb_blocklog;
	} else {
		mp->m_readio_log = readio_log;
	}
	mp->m_readio_blocks = 1 << (mp->m_readio_log - sbp->sb_blocklog);
	if (sbp->sb_blocklog > writeio_log) {
		mp->m_writeio_log = sbp->sb_blocklog;
	} else {
		mp->m_writeio_log = writeio_log;
	}
	mp->m_writeio_blocks = 1 << (mp->m_writeio_log - sbp->sb_blocklog);

	/*
	 * Set the inode cluster size.
	 * This may still be overridden by the file system
	 * block size if it is larger than the chosen cluster size.
	 */
	mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;

	/*
	 * 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) {
		cmn_err(CE_WARN, "XFS: size check 1 failed");
		error = XFS_ERROR(E2BIG);
		goto error1;
	}
	error = xfs_read_buf(mp, mp->m_ddev_targp,
			     d - XFS_FSS_TO_BB(mp, 1),
			     XFS_FSS_TO_BB(mp, 1), 0, &bp);
	if (!error) {
		xfs_buf_relse(bp);
	} else {
		cmn_err(CE_WARN, "XFS: size check 2 failed");
		if (error == ENOSPC) {
			error = XFS_ERROR(E2BIG);
		}
		goto error1;
	}

	if (((mfsi_flags & XFS_MFSI_CLIENT) == 0) &&
	    mp->m_logdev_targp != mp->m_ddev_targp) {
		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) {
			cmn_err(CE_WARN, "XFS: size check 3 failed");
			error = XFS_ERROR(E2BIG);
			goto error1;
		}
		error = xfs_read_buf(mp, mp->m_logdev_targp,
				     d - XFS_FSB_TO_BB(mp, 1),
				     XFS_FSB_TO_BB(mp, 1), 0, &bp);