resize.c

linux 内核源代码

/*
 *  linux/fs/ext3/resize.c
 *
 * Support for resizing an ext3 filesystem while it is mounted.
 *
 * Copyright (C) 2001, 2002 Andreas Dilger <[e-mail]>
 *
 * This could probably be made into a module, because it is not often in use.
 */


#define EXT3FS_DEBUG

#include <linux/ext3_jbd.h>

#include <linux/errno.h>
#include <linux/slab.h>


#define outside(b, first, last)	((b) < (first) || (b) >= (last))
#define inside(b, first, last)	((b) >= (first) && (b) < (last))

static int verify_group_input(struct super_block *sb,
			      struct ext3_new_group_data *input)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
	ext3_fsblk_t start = le32_to_cpu(es->s_blocks_count);
	ext3_fsblk_t end = start + input->blocks_count;
	unsigned group = input->group;
	ext3_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
	unsigned overhead = ext3_bg_has_super(sb, group) ?
		(1 + ext3_bg_num_gdb(sb, group) +
		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
	ext3_fsblk_t metaend = start + overhead;
	struct buffer_head *bh = NULL;
	ext3_grpblk_t free_blocks_count;
	int err = -EINVAL;

	input->free_blocks_count = free_blocks_count =
		input->blocks_count - 2 - overhead - sbi->s_itb_per_group;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT3-fs: adding %s group %u: %u blocks "
		       "(%d free, %u reserved)\n",
		       ext3_bg_has_super(sb, input->group) ? "normal" :
		       "no-super", input->group, input->blocks_count,
		       free_blocks_count, input->reserved_blocks);

	if (group != sbi->s_groups_count)
		ext3_warning(sb, __FUNCTION__,
			     "Cannot add at group %u (only %lu groups)",
			     input->group, sbi->s_groups_count);
	else if ((start - le32_to_cpu(es->s_first_data_block)) %
		 EXT3_BLOCKS_PER_GROUP(sb))
		ext3_warning(sb, __FUNCTION__, "Last group not full");
	else if (input->reserved_blocks > input->blocks_count / 5)
		ext3_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)",
			     input->reserved_blocks);
	else if (free_blocks_count < 0)
		ext3_warning(sb, __FUNCTION__, "Bad blocks count %u",
			     input->blocks_count);
	else if (!(bh = sb_bread(sb, end - 1)))
		ext3_warning(sb, __FUNCTION__,
			     "Cannot read last block ("E3FSBLK")",
			     end - 1);
	else if (outside(input->block_bitmap, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap not in group (block %u)",
			     input->block_bitmap);
	else if (outside(input->inode_bitmap, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap not in group (block %u)",
			     input->inode_bitmap);
	else if (outside(input->inode_table, start, end) ||
	         outside(itend - 1, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Inode table not in group (blocks %u-"E3FSBLK")",
			     input->inode_table, itend - 1);
	else if (input->inode_bitmap == input->block_bitmap)
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap same as inode bitmap (%u)",
			     input->block_bitmap);
	else if (inside(input->block_bitmap, input->inode_table, itend))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap (%u) in inode table (%u-"E3FSBLK")",
			     input->block_bitmap, input->inode_table, itend-1);
	else if (inside(input->inode_bitmap, input->inode_table, itend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap (%u) in inode table (%u-"E3FSBLK")",
			     input->inode_bitmap, input->inode_table, itend-1);
	else if (inside(input->block_bitmap, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap (%u) in GDT table"
			     " ("E3FSBLK"-"E3FSBLK")",
			     input->block_bitmap, start, metaend - 1);
	else if (inside(input->inode_bitmap, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap (%u) in GDT table"
			     " ("E3FSBLK"-"E3FSBLK")",
			     input->inode_bitmap, start, metaend - 1);
	else if (inside(input->inode_table, start, metaend) ||
	         inside(itend - 1, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode table (%u-"E3FSBLK") overlaps"
			     "GDT table ("E3FSBLK"-"E3FSBLK")",
			     input->inode_table, itend - 1, start, metaend - 1);
	else
		err = 0;
	brelse(bh);

	return err;
}

static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
				  ext3_fsblk_t blk)
{
	struct buffer_head *bh;
	int err;

	bh = sb_getblk(sb, blk);
	if (!bh)
		return ERR_PTR(-EIO);
	if ((err = ext3_journal_get_write_access(handle, bh))) {
		brelse(bh);
		bh = ERR_PTR(err);
	} else {
		lock_buffer(bh);
		memset(bh->b_data, 0, sb->s_blocksize);
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
	}

	return bh;
}

/*
 * To avoid calling the atomic setbit hundreds or thousands of times, we only
 * need to use it within a single byte (to ensure we get endianness right).
 * We can use memset for the rest of the bitmap as there are no other users.
 */
static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
	int i;

	if (start_bit >= end_bit)
		return;

	ext3_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
		ext3_set_bit(i, bitmap);
	if (i < end_bit)
		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
}

/*
 * If we have fewer than thresh credits, extend by EXT3_MAX_TRANS_DATA.
 * If that fails, restart the transaction & regain write access for the
 * buffer head which is used for block_bitmap modifications.
 */
static int extend_or_restart_transaction(handle_t *handle, int thresh,
					 struct buffer_head *bh)
{
	int err;

	if (handle->h_buffer_credits >= thresh)
		return 0;

	err = ext3_journal_extend(handle, EXT3_MAX_TRANS_DATA);
	if (err < 0)
		return err;
	if (err) {
		err = ext3_journal_restart(handle, EXT3_MAX_TRANS_DATA);
		if (err)
			return err;
		err = ext3_journal_get_write_access(handle, bh);
		if (err)
			return err;
	}

	return 0;
}

/*
 * Set up the block and inode bitmaps, and the inode table for the new group.
 * This doesn't need to be part of the main transaction, since we are only
 * changing blocks outside the actual filesystem.  We still do journaling to
 * ensure the recovery is correct in case of a failure just after resize.
 * If any part of this fails, we simply abort the resize.
 */
static int setup_new_group_blocks(struct super_block *sb,
				  struct ext3_new_group_data *input)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	ext3_fsblk_t start = ext3_group_first_block_no(sb, input->group);
	int reserved_gdb = ext3_bg_has_super(sb, input->group) ?
		le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
	unsigned long gdblocks = ext3_bg_num_gdb(sb, input->group);
	struct buffer_head *bh;
	handle_t *handle;
	ext3_fsblk_t block;
	ext3_grpblk_t bit;
	int i;
	int err = 0, err2;

	/* This transaction may be extended/restarted along the way */
	handle = ext3_journal_start_sb(sb, EXT3_MAX_TRANS_DATA);

	if (IS_ERR(handle))
		return PTR_ERR(handle);

	lock_super(sb);
	if (input->group != sbi->s_groups_count) {
		err = -EBUSY;
		goto exit_journal;
	}

	if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
		err = PTR_ERR(bh);
		goto exit_journal;
	}

	if (ext3_bg_has_super(sb, input->group)) {
		ext3_debug("mark backup superblock %#04lx (+0)\n", start);
		ext3_set_bit(0, bh->b_data);
	}

	/* Copy all of the GDT blocks into the backup in this group */
	for (i = 0, bit = 1, block = start + 1;
	     i < gdblocks; i++, block++, bit++) {
		struct buffer_head *gdb;

		ext3_debug("update backup group %#04lx (+%d)\n", block, bit);

		err = extend_or_restart_transaction(handle, 1, bh);
		if (err)
			goto exit_bh;

		gdb = sb_getblk(sb, block);
		if (!gdb) {
			err = -EIO;
			goto exit_bh;
		}
		if ((err = ext3_journal_get_write_access(handle, gdb))) {
			brelse(gdb);
			goto exit_bh;
		}
		lock_buffer(gdb);
		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
		set_buffer_uptodate(gdb);
		unlock_buffer(gdb);
		ext3_journal_dirty_metadata(handle, gdb);
		ext3_set_bit(bit, bh->b_data);
		brelse(gdb);
	}

	/* Zero out all of the reserved backup group descriptor table blocks */
	for (i = 0, bit = gdblocks + 1, block = start + bit;
	     i < reserved_gdb; i++, block++, bit++) {
		struct buffer_head *gdb;

		ext3_debug("clear reserved block %#04lx (+%d)\n", block, bit);

		err = extend_or_restart_transaction(handle, 1, bh);
		if (err)
			goto exit_bh;

		if (IS_ERR(gdb = bclean(handle, sb, block))) {
			err = PTR_ERR(bh);
			goto exit_bh;
		}
		ext3_journal_dirty_metadata(handle, gdb);
		ext3_set_bit(bit, bh->b_data);
		brelse(gdb);
	}
	ext3_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
		   input->block_bitmap - start);
	ext3_set_bit(input->block_bitmap - start, bh->b_data);
	ext3_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
		   input->inode_bitmap - start);
	ext3_set_bit(input->inode_bitmap - start, bh->b_data);

	/* Zero out all of the inode table blocks */
	for (i = 0, block = input->inode_table, bit = block - start;
	     i < sbi->s_itb_per_group; i++, bit++, block++) {
		struct buffer_head *it;

		ext3_debug("clear inode block %#04lx (+%d)\n", block, bit);

		err = extend_or_restart_transaction(handle, 1, bh);
		if (err)
			goto exit_bh;

		if (IS_ERR(it = bclean(handle, sb, block))) {
			err = PTR_ERR(it);
			goto exit_bh;
		}
		ext3_journal_dirty_metadata(handle, it);
		brelse(it);
		ext3_set_bit(bit, bh->b_data);
	}

	err = extend_or_restart_transaction(handle, 2, bh);
	if (err)
		goto exit_bh;

	mark_bitmap_end(input->blocks_count, EXT3_BLOCKS_PER_GROUP(sb),
			bh->b_data);
	ext3_journal_dirty_metadata(handle, bh);
	brelse(bh);

	/* Mark unused entries in inode bitmap used */
	ext3_debug("clear inode bitmap %#04x (+%ld)\n",
		   input->inode_bitmap, input->inode_bitmap - start);
	if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
		err = PTR_ERR(bh);
		goto exit_journal;
	}

	mark_bitmap_end(EXT3_INODES_PER_GROUP(sb), EXT3_BLOCKS_PER_GROUP(sb),
			bh->b_data);
	ext3_journal_dirty_metadata(handle, bh);
exit_bh:
	brelse(bh);

exit_journal:
	unlock_super(sb);
	if ((err2 = ext3_journal_stop(handle)) && !err)
		err = err2;

	return err;
}

/*
 * Iterate through the groups which hold BACKUP superblock/GDT copies in an
 * ext3 filesystem.  The counters should be initialized to 1, 5, and 7 before
 * calling this for the first time.  In a sparse filesystem it will be the
 * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
 * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
 */
static unsigned ext3_list_backups(struct super_block *sb, unsigned *three,
				  unsigned *five, unsigned *seven)
{
	unsigned *min = three;
	int mult = 3;
	unsigned ret;

	if (!EXT3_HAS_RO_COMPAT_FEATURE(sb,
					EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
		ret = *min;
		*min += 1;
		return ret;
	}

	if (*five < *min) {
		min = five;
		mult = 5;
	}
	if (*seven < *min) {
		min = seven;
		mult = 7;
	}