resize.c

linux 内核源代码

	if (err) {
		ext4_warning(sb, __FUNCTION__,
			     "can't update backup for group %d (err %d), "
			     "forcing fsck on next reboot", group, err);
		sbi->s_mount_state &= ~EXT4_VALID_FS;
		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
		mark_buffer_dirty(sbi->s_sbh);
	}
}

/* Add group descriptor data to an existing or new group descriptor block.
 * Ensure we handle all possible error conditions _before_ we start modifying
 * the filesystem, because we cannot abort the transaction and not have it
 * write the data to disk.
 *
 * If we are on a GDT block boundary, we need to get the reserved GDT block.
 * Otherwise, we may need to add backup GDT blocks for a sparse group.
 *
 * We only need to hold the superblock lock while we are actually adding
 * in the new group's counts to the superblock.  Prior to that we have
 * not really "added" the group at all.  We re-check that we are still
 * adding in the last group in case things have changed since verifying.
 */
int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
	struct buffer_head *primary = NULL;
	struct ext4_group_desc *gdp;
	struct inode *inode = NULL;
	handle_t *handle;
	int gdb_off, gdb_num;
	int err, err2;

	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);

	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
		ext4_warning(sb, __FUNCTION__,
			     "Can't resize non-sparse filesystem further");
		return -EPERM;
	}

	if (ext4_blocks_count(es) + input->blocks_count <
	    ext4_blocks_count(es)) {
		ext4_warning(sb, __FUNCTION__, "blocks_count overflow\n");
		return -EINVAL;
	}

	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
	    le32_to_cpu(es->s_inodes_count)) {
		ext4_warning(sb, __FUNCTION__, "inodes_count overflow\n");
		return -EINVAL;
	}

	if (reserved_gdb || gdb_off == 0) {
		if (!EXT4_HAS_COMPAT_FEATURE(sb,
					     EXT4_FEATURE_COMPAT_RESIZE_INODE)){
			ext4_warning(sb, __FUNCTION__,
				     "No reserved GDT blocks, can't resize");
			return -EPERM;
		}
		inode = iget(sb, EXT4_RESIZE_INO);
		if (!inode || is_bad_inode(inode)) {
			ext4_warning(sb, __FUNCTION__,
				     "Error opening resize inode");
			iput(inode);
			return -ENOENT;
		}
	}

	if ((err = verify_group_input(sb, input)))
		goto exit_put;

	if ((err = setup_new_group_blocks(sb, input)))
		goto exit_put;

	/*
	 * We will always be modifying at least the superblock and a GDT
	 * block.  If we are adding a group past the last current GDT block,
	 * we will also modify the inode and the dindirect block.  If we
	 * are adding a group with superblock/GDT backups  we will also
	 * modify each of the reserved GDT dindirect blocks.
	 */
	handle = ext4_journal_start_sb(sb,
				       ext4_bg_has_super(sb, input->group) ?
				       3 + reserved_gdb : 4);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		goto exit_put;
	}

	lock_super(sb);
	if (input->group != sbi->s_groups_count) {
		ext4_warning(sb, __FUNCTION__,
			     "multiple resizers run on filesystem!");
		err = -EBUSY;
		goto exit_journal;
	}

	if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
		goto exit_journal;

	/*
	 * We will only either add reserved group blocks to a backup group
	 * or remove reserved blocks for the first group in a new group block.
	 * Doing both would be mean more complex code, and sane people don't
	 * use non-sparse filesystems anymore.  This is already checked above.
	 */
	if (gdb_off) {
		primary = sbi->s_group_desc[gdb_num];
		if ((err = ext4_journal_get_write_access(handle, primary)))
			goto exit_journal;

		if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) &&
		    (err = reserve_backup_gdb(handle, inode, input)))
			goto exit_journal;
	} else if ((err = add_new_gdb(handle, inode, input, &primary)))
		goto exit_journal;

	/*
	 * OK, now we've set up the new group.  Time to make it active.
	 *
	 * Current kernels don't lock all allocations via lock_super(),
	 * so we have to be safe wrt. concurrent accesses the group
	 * data.  So we need to be careful to set all of the relevant
	 * group descriptor data etc. *before* we enable the group.
	 *
	 * The key field here is sbi->s_groups_count: as long as
	 * that retains its old value, nobody is going to access the new
	 * group.
	 *
	 * So first we update all the descriptor metadata for the new
	 * group; then we update the total disk blocks count; then we
	 * update the groups count to enable the group; then finally we
	 * update the free space counts so that the system can start
	 * using the new disk blocks.
	 */

	/* Update group descriptor block for new group */
	gdp = (struct ext4_group_desc *)primary->b_data + gdb_off;

	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
	ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
	gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
	gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);

	/*
	 * Make the new blocks and inodes valid next.  We do this before
	 * increasing the group count so that once the group is enabled,
	 * all of its blocks and inodes are already valid.
	 *
	 * We always allocate group-by-group, then block-by-block or
	 * inode-by-inode within a group, so enabling these
	 * blocks/inodes before the group is live won't actually let us
	 * allocate the new space yet.
	 */
	ext4_blocks_count_set(es, ext4_blocks_count(es) +
		input->blocks_count);
	es->s_inodes_count = cpu_to_le32(le32_to_cpu(es->s_inodes_count) +
		EXT4_INODES_PER_GROUP(sb));

	/*
	 * We need to protect s_groups_count against other CPUs seeing
	 * inconsistent state in the superblock.
	 *
	 * The precise rules we use are:
	 *
	 * * Writers of s_groups_count *must* hold lock_super
	 * AND
	 * * Writers must perform a smp_wmb() after updating all dependent
	 *   data and before modifying the groups count
	 *
	 * * Readers must hold lock_super() over the access
	 * OR
	 * * Readers must perform an smp_rmb() after reading the groups count
	 *   and before reading any dependent data.
	 *
	 * NB. These rules can be relaxed when checking the group count
	 * while freeing data, as we can only allocate from a block
	 * group after serialising against the group count, and we can
	 * only then free after serialising in turn against that
	 * allocation.
	 */
	smp_wmb();

	/* Update the global fs size fields */
	sbi->s_groups_count++;

	ext4_journal_dirty_metadata(handle, primary);

	/* Update the reserved block counts only once the new group is
	 * active. */
	ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
		input->reserved_blocks);

	/* Update the free space counts */
	percpu_counter_add(&sbi->s_freeblocks_counter,
			   input->free_blocks_count);
	percpu_counter_add(&sbi->s_freeinodes_counter,
			   EXT4_INODES_PER_GROUP(sb));

	ext4_journal_dirty_metadata(handle, sbi->s_sbh);
	sb->s_dirt = 1;

exit_journal:
	unlock_super(sb);
	if ((err2 = ext4_journal_stop(handle)) && !err)
		err = err2;
	if (!err) {
		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
			       sizeof(struct ext4_super_block));
		update_backups(sb, primary->b_blocknr, primary->b_data,
			       primary->b_size);
	}
exit_put:
	iput(inode);
	return err;
} /* ext4_group_add */

/* Extend the filesystem to the new number of blocks specified.  This entry
 * point is only used to extend the current filesystem to the end of the last
 * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
 * for emergencies (because it has no dependencies on reserved blocks).
 *
 * If we _really_ wanted, we could use default values to call ext4_group_add()
 * allow the "remount" trick to work for arbitrary resizing, assuming enough
 * GDT blocks are reserved to grow to the desired size.
 */
int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
		      ext4_fsblk_t n_blocks_count)
{
	ext4_fsblk_t o_blocks_count;
	unsigned long o_groups_count;
	ext4_grpblk_t last;
	ext4_grpblk_t add;
	struct buffer_head * bh;
	handle_t *handle;
	int err;
	unsigned long freed_blocks;

	/* We don't need to worry about locking wrt other resizers just
	 * yet: we're going to revalidate es->s_blocks_count after
	 * taking lock_super() below. */
	o_blocks_count = ext4_blocks_count(es);
	o_groups_count = EXT4_SB(sb)->s_groups_count;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n",
		       o_blocks_count, n_blocks_count);

	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
		return 0;

	if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
			" too large to resize to %llu blocks safely\n",
			sb->s_id, n_blocks_count);
		if (sizeof(sector_t) < 8)
			ext4_warning(sb, __FUNCTION__,
			"CONFIG_LBD not enabled\n");
		return -EINVAL;
	}

	if (n_blocks_count < o_blocks_count) {
		ext4_warning(sb, __FUNCTION__,
			     "can't shrink FS - resize aborted");
		return -EBUSY;
	}

	/* Handle the remaining blocks in the last group only. */
	ext4_get_group_no_and_offset(sb, o_blocks_count, NULL, &last);

	if (last == 0) {
		ext4_warning(sb, __FUNCTION__,
			     "need to use ext2online to resize further");
		return -EPERM;
	}

	add = EXT4_BLOCKS_PER_GROUP(sb) - last;

	if (o_blocks_count + add < o_blocks_count) {
		ext4_warning(sb, __FUNCTION__, "blocks_count overflow");
		return -EINVAL;
	}

	if (o_blocks_count + add > n_blocks_count)
		add = n_blocks_count - o_blocks_count;

	if (o_blocks_count + add < n_blocks_count)
		ext4_warning(sb, __FUNCTION__,
			     "will only finish group (%llu"
			     " blocks, %u new)",
			     o_blocks_count + add, add);

	/* See if the device is actually as big as what was requested */
	bh = sb_bread(sb, o_blocks_count + add -1);
	if (!bh) {
		ext4_warning(sb, __FUNCTION__,
			     "can't read last block, resize aborted");
		return -ENOSPC;
	}
	brelse(bh);

	/* We will update the superblock, one block bitmap, and
	 * one group descriptor via ext4_free_blocks().
	 */
	handle = ext4_journal_start_sb(sb, 3);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		ext4_warning(sb, __FUNCTION__, "error %d on journal start",err);
		goto exit_put;
	}

	lock_super(sb);
	if (o_blocks_count != ext4_blocks_count(es)) {
		ext4_warning(sb, __FUNCTION__,
			     "multiple resizers run on filesystem!");
		unlock_super(sb);
		err = -EBUSY;
		goto exit_put;
	}

	if ((err = ext4_journal_get_write_access(handle,
						 EXT4_SB(sb)->s_sbh))) {
		ext4_warning(sb, __FUNCTION__,
			     "error %d on journal write access", err);
		unlock_super(sb);
		ext4_journal_stop(handle);
		goto exit_put;
	}
	ext4_blocks_count_set(es, o_blocks_count + add);
	ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
	sb->s_dirt = 1;
	unlock_super(sb);
	ext4_debug("freeing blocks %lu through %llu\n", o_blocks_count,
		   o_blocks_count + add);
	ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
		   o_blocks_count + add);
	if ((err = ext4_journal_stop(handle)))
		goto exit_put;
	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
		       ext4_blocks_count(es));
	update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
		       sizeof(struct ext4_super_block));
exit_put:
	return err;
} /* ext4_group_extend */