resize.c

linux 内核源代码

	ret = *min;
	*min *= mult;

	return ret;
}

/*
 * Check that all of the backup GDT blocks are held in the primary GDT block.
 * It is assumed that they are stored in group order.  Returns the number of
 * groups in current filesystem that have BACKUPS, or -ve error code.
 */
static int verify_reserved_gdb(struct super_block *sb,
			       struct buffer_head *primary)
{
	const ext3_fsblk_t blk = primary->b_blocknr;
	const unsigned long end = EXT3_SB(sb)->s_groups_count;
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned grp;
	__le32 *p = (__le32 *)primary->b_data;
	int gdbackups = 0;

	while ((grp = ext3_list_backups(sb, &three, &five, &seven)) < end) {
		if (le32_to_cpu(*p++) != grp * EXT3_BLOCKS_PER_GROUP(sb) + blk){
			ext3_warning(sb, __FUNCTION__,
				     "reserved GDT "E3FSBLK
				     " missing grp %d ("E3FSBLK")",
				     blk, grp,
				     grp * EXT3_BLOCKS_PER_GROUP(sb) + blk);
			return -EINVAL;
		}
		if (++gdbackups > EXT3_ADDR_PER_BLOCK(sb))
			return -EFBIG;
	}

	return gdbackups;
}

/*
 * Called when we need to bring a reserved group descriptor table block into
 * use from the resize inode.  The primary copy of the new GDT block currently
 * is an indirect block (under the double indirect block in the resize inode).
 * The new backup GDT blocks will be stored as leaf blocks in this indirect
 * block, in group order.  Even though we know all the block numbers we need,
 * we check to ensure that the resize inode has actually reserved these blocks.
 *
 * Don't need to update the block bitmaps because the blocks are still in use.
 *
 * We get all of the error cases out of the way, so that we are sure to not
 * fail once we start modifying the data on disk, because JBD has no rollback.
 */
static int add_new_gdb(handle_t *handle, struct inode *inode,
		       struct ext3_new_group_data *input,
		       struct buffer_head **primary)
{
	struct super_block *sb = inode->i_sb;
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
	unsigned long gdb_num = input->group / EXT3_DESC_PER_BLOCK(sb);
	ext3_fsblk_t gdblock = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
	struct buffer_head **o_group_desc, **n_group_desc;
	struct buffer_head *dind;
	int gdbackups;
	struct ext3_iloc iloc;
	__le32 *data;
	int err;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG
		       "EXT3-fs: ext3_add_new_gdb: adding group block %lu\n",
		       gdb_num);

	/*
	 * If we are not using the primary superblock/GDT copy don't resize,
	 * because the user tools have no way of handling this.  Probably a
	 * bad time to do it anyways.
	 */
	if (EXT3_SB(sb)->s_sbh->b_blocknr !=
	    le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block)) {
		ext3_warning(sb, __FUNCTION__,
			"won't resize using backup superblock at %llu",
			(unsigned long long)EXT3_SB(sb)->s_sbh->b_blocknr);
		return -EPERM;
	}

	*primary = sb_bread(sb, gdblock);
	if (!*primary)
		return -EIO;

	if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
		err = gdbackups;
		goto exit_bh;
	}

	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_bh;
	}

	data = (__le32 *)dind->b_data;
	if (le32_to_cpu(data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)]) != gdblock) {
		ext3_warning(sb, __FUNCTION__,
			     "new group %u GDT block "E3FSBLK" not reserved",
			     input->group, gdblock);
		err = -EINVAL;
		goto exit_dind;
	}

	if ((err = ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh)))
		goto exit_dind;

	if ((err = ext3_journal_get_write_access(handle, *primary)))
		goto exit_sbh;

	if ((err = ext3_journal_get_write_access(handle, dind)))
		goto exit_primary;

	/* ext3_reserve_inode_write() gets a reference on the iloc */
	if ((err = ext3_reserve_inode_write(handle, inode, &iloc)))
		goto exit_dindj;

	n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
			GFP_KERNEL);
	if (!n_group_desc) {
		err = -ENOMEM;
		ext3_warning (sb, __FUNCTION__,
			      "not enough memory for %lu groups", gdb_num + 1);
		goto exit_inode;
	}

	/*
	 * Finally, we have all of the possible failures behind us...
	 *
	 * Remove new GDT block from inode double-indirect block and clear out
	 * the new GDT block for use (which also "frees" the backup GDT blocks
	 * from the reserved inode).  We don't need to change the bitmaps for
	 * these blocks, because they are marked as in-use from being in the
	 * reserved inode, and will become GDT blocks (primary and backup).
	 */
	data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)] = 0;
	ext3_journal_dirty_metadata(handle, dind);
	brelse(dind);
	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
	ext3_mark_iloc_dirty(handle, inode, &iloc);
	memset((*primary)->b_data, 0, sb->s_blocksize);
	ext3_journal_dirty_metadata(handle, *primary);

	o_group_desc = EXT3_SB(sb)->s_group_desc;
	memcpy(n_group_desc, o_group_desc,
	       EXT3_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
	n_group_desc[gdb_num] = *primary;
	EXT3_SB(sb)->s_group_desc = n_group_desc;
	EXT3_SB(sb)->s_gdb_count++;
	kfree(o_group_desc);

	es->s_reserved_gdt_blocks =
		cpu_to_le16(le16_to_cpu(es->s_reserved_gdt_blocks) - 1);
	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);

	return 0;

exit_inode:
	//ext3_journal_release_buffer(handle, iloc.bh);
	brelse(iloc.bh);
exit_dindj:
	//ext3_journal_release_buffer(handle, dind);
exit_primary:
	//ext3_journal_release_buffer(handle, *primary);
exit_sbh:
	//ext3_journal_release_buffer(handle, *primary);
exit_dind:
	brelse(dind);
exit_bh:
	brelse(*primary);

	ext3_debug("leaving with error %d\n", err);
	return err;
}

/*
 * Called when we are adding a new group which has a backup copy of each of
 * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
 * We need to add these reserved backup GDT blocks to the resize inode, so
 * that they are kept for future resizing and not allocated to files.
 *
 * Each reserved backup GDT block will go into a different indirect block.
 * The indirect blocks are actually the primary reserved GDT blocks,
 * so we know in advance what their block numbers are.  We only get the
 * double-indirect block to verify it is pointing to the primary reserved
 * GDT blocks so we don't overwrite a data block by accident.  The reserved
 * backup GDT blocks are stored in their reserved primary GDT block.
 */
static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
			      struct ext3_new_group_data *input)
{
	struct super_block *sb = inode->i_sb;
	int reserved_gdb =le16_to_cpu(EXT3_SB(sb)->s_es->s_reserved_gdt_blocks);
	struct buffer_head **primary;
	struct buffer_head *dind;
	struct ext3_iloc iloc;
	ext3_fsblk_t blk;
	__le32 *data, *end;
	int gdbackups = 0;
	int res, i;
	int err;

	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL);
	if (!primary)
		return -ENOMEM;

	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_free;
	}

	blk = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + EXT3_SB(sb)->s_gdb_count;
	data = (__le32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count;
	end = (__le32 *)dind->b_data + EXT3_ADDR_PER_BLOCK(sb);

	/* Get each reserved primary GDT block and verify it holds backups */
	for (res = 0; res < reserved_gdb; res++, blk++) {
		if (le32_to_cpu(*data) != blk) {
			ext3_warning(sb, __FUNCTION__,
				     "reserved block "E3FSBLK
				     " not at offset %ld",
				     blk,
				     (long)(data - (__le32 *)dind->b_data));
			err = -EINVAL;
			goto exit_bh;
		}
		primary[res] = sb_bread(sb, blk);
		if (!primary[res]) {
			err = -EIO;
			goto exit_bh;
		}
		if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
			brelse(primary[res]);
			err = gdbackups;
			goto exit_bh;
		}
		if (++data >= end)
			data = (__le32 *)dind->b_data;
	}

	for (i = 0; i < reserved_gdb; i++) {
		if ((err = ext3_journal_get_write_access(handle, primary[i]))) {
			/*
			int j;
			for (j = 0; j < i; j++)
				ext3_journal_release_buffer(handle, primary[j]);
			 */
			goto exit_bh;
		}
	}

	if ((err = ext3_reserve_inode_write(handle, inode, &iloc)))
		goto exit_bh;

	/*
	 * Finally we can add each of the reserved backup GDT blocks from
	 * the new group to its reserved primary GDT block.
	 */
	blk = input->group * EXT3_BLOCKS_PER_GROUP(sb);
	for (i = 0; i < reserved_gdb; i++) {
		int err2;
		data = (__le32 *)primary[i]->b_data;
		/* printk("reserving backup %lu[%u] = %lu\n",
		       primary[i]->b_blocknr, gdbackups,
		       blk + primary[i]->b_blocknr); */
		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
		err2 = ext3_journal_dirty_metadata(handle, primary[i]);
		if (!err)
			err = err2;
	}
	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
	ext3_mark_iloc_dirty(handle, inode, &iloc);

exit_bh:
	while (--res >= 0)
		brelse(primary[res]);
	brelse(dind);

exit_free:
	kfree(primary);

	return err;
}

/*
 * Update the backup copies of the ext3 metadata.  These don't need to be part
 * of the main resize transaction, because e2fsck will re-write them if there
 * is a problem (basically only OOM will cause a problem).  However, we
 * _should_ update the backups if possible, in case the primary gets trashed
 * for some reason and we need to run e2fsck from a backup superblock.  The
 * important part is that the new block and inode counts are in the backup
 * superblocks, and the location of the new group metadata in the GDT backups.
 *
 * We do not need lock_super() for this, because these blocks are not
 * otherwise touched by the filesystem code when it is mounted.  We don't
 * need to worry about last changing from sbi->s_groups_count, because the
 * worst that can happen is that we do not copy the full number of backups
 * at this time.  The resize which changed s_groups_count will backup again.
 */
static void update_backups(struct super_block *sb,
			   int blk_off, char *data, int size)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	const unsigned long last = sbi->s_groups_count;
	const int bpg = EXT3_BLOCKS_PER_GROUP(sb);
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned group;
	int rest = sb->s_blocksize - size;
	handle_t *handle;
	int err = 0, err2;

	handle = ext3_journal_start_sb(sb, EXT3_MAX_TRANS_DATA);
	if (IS_ERR(handle)) {
		group = 1;
		err = PTR_ERR(handle);
		goto exit_err;
	}

	while ((group = ext3_list_backups(sb, &three, &five, &seven)) < last) {
		struct buffer_head *bh;

		/* Out of journal space, and can't get more - abort - so sad */
		if (handle->h_buffer_credits == 0 &&
		    ext3_journal_extend(handle, EXT3_MAX_TRANS_DATA) &&
		    (err = ext3_journal_restart(handle, EXT3_MAX_TRANS_DATA)))
			break;

		bh = sb_getblk(sb, group * bpg + blk_off);
		if (!bh) {
			err = -EIO;
			break;
		}
		ext3_debug("update metadata backup %#04lx\n",
			  (unsigned long)bh->b_blocknr);
		if ((err = ext3_journal_get_write_access(handle, bh)))
			break;
		lock_buffer(bh);
		memcpy(bh->b_data, data, size);
		if (rest)
			memset(bh->b_data + size, 0, rest);
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
		ext3_journal_dirty_metadata(handle, bh);
		brelse(bh);
	}
	if ((err2 = ext3_journal_stop(handle)) && !err)
		err = err2;

	/*
	 * Ugh! Need to have e2fsck write the backup copies.  It is too
	 * late to revert the resize, we shouldn't fail just because of
	 * the backup copies (they are only needed in case of corruption).
	 *