balloc.c

linux 内核源代码

out:
	if (ret >= 0) {
		BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
					"bitmap block");
		fatal = ext4_journal_dirty_metadata(handle, bitmap_bh);
		if (fatal) {
			*errp = fatal;
			return -1;
		}
		return ret;
	}

	BUFFER_TRACE(bitmap_bh, "journal_release_buffer");
	ext4_journal_release_buffer(handle, bitmap_bh);
	return ret;
}

/**
 * ext4_has_free_blocks()
 * @sbi:		in-core super block structure.
 *
 * Check if filesystem has at least 1 free block available for allocation.
 */
static int ext4_has_free_blocks(struct ext4_sb_info *sbi)
{
	ext4_fsblk_t free_blocks, root_blocks;

	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
	root_blocks = ext4_r_blocks_count(sbi->s_es);
	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
		sbi->s_resuid != current->fsuid &&
		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
		return 0;
	}
	return 1;
}

/**
 * ext4_should_retry_alloc()
 * @sb:			super block
 * @retries		number of attemps has been made
 *
 * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
 * it is profitable to retry the operation, this function will wait
 * for the current or commiting transaction to complete, and then
 * return TRUE.
 *
 * if the total number of retries exceed three times, return FALSE.
 */
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
	if (!ext4_has_free_blocks(EXT4_SB(sb)) || (*retries)++ > 3)
		return 0;

	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);

	return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
}

/**
 * ext4_new_blocks() -- core block(s) allocation function
 * @handle:		handle to this transaction
 * @inode:		file inode
 * @goal:		given target block(filesystem wide)
 * @count:		target number of blocks to allocate
 * @errp:		error code
 *
 * ext4_new_blocks uses a goal block to assist allocation.  It tries to
 * allocate block(s) from the block group contains the goal block first. If that
 * fails, it will try to allocate block(s) from other block groups without
 * any specific goal block.
 *
 */
ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
			ext4_fsblk_t goal, unsigned long *count, int *errp)
{
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *gdp_bh;
	unsigned long group_no;
	int goal_group;
	ext4_grpblk_t grp_target_blk;	/* blockgroup relative goal block */
	ext4_grpblk_t grp_alloc_blk;	/* blockgroup-relative allocated block*/
	ext4_fsblk_t ret_block;		/* filesyetem-wide allocated block */
	int bgi;			/* blockgroup iteration index */
	int fatal = 0, err;
	int performed_allocation = 0;
	ext4_grpblk_t free_blocks;	/* number of free blocks in a group */
	struct super_block *sb;
	struct ext4_group_desc *gdp;
	struct ext4_super_block *es;
	struct ext4_sb_info *sbi;
	struct ext4_reserve_window_node *my_rsv = NULL;
	struct ext4_block_alloc_info *block_i;
	unsigned short windowsz = 0;
#ifdef EXT4FS_DEBUG
	static int goal_hits, goal_attempts;
#endif
	unsigned long ngroups;
	unsigned long num = *count;

	*errp = -ENOSPC;
	sb = inode->i_sb;
	if (!sb) {
		printk("ext4_new_block: nonexistent device");
		return 0;
	}

	/*
	 * Check quota for allocation of this block.
	 */
	if (DQUOT_ALLOC_BLOCK(inode, num)) {
		*errp = -EDQUOT;
		return 0;
	}

	sbi = EXT4_SB(sb);
	es = EXT4_SB(sb)->s_es;
	ext4_debug("goal=%lu.\n", goal);
	/*
	 * Allocate a block from reservation only when
	 * filesystem is mounted with reservation(default,-o reservation), and
	 * it's a regular file, and
	 * the desired window size is greater than 0 (One could use ioctl
	 * command EXT4_IOC_SETRSVSZ to set the window size to 0 to turn off
	 * reservation on that particular file)
	 */
	block_i = EXT4_I(inode)->i_block_alloc_info;
	if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
		my_rsv = &block_i->rsv_window_node;

	if (!ext4_has_free_blocks(sbi)) {
		*errp = -ENOSPC;
		goto out;
	}

	/*
	 * First, test whether the goal block is free.
	 */
	if (goal < le32_to_cpu(es->s_first_data_block) ||
	    goal >= ext4_blocks_count(es))
		goal = le32_to_cpu(es->s_first_data_block);
	ext4_get_group_no_and_offset(sb, goal, &group_no, &grp_target_blk);
	goal_group = group_no;
retry_alloc:
	gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
	if (!gdp)
		goto io_error;

	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
	/*
	 * if there is not enough free blocks to make a new resevation
	 * turn off reservation for this allocation
	 */
	if (my_rsv && (free_blocks < windowsz)
		&& (rsv_is_empty(&my_rsv->rsv_window)))
		my_rsv = NULL;

	if (free_blocks > 0) {
		bitmap_bh = read_block_bitmap(sb, group_no);
		if (!bitmap_bh)
			goto io_error;
		grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
					group_no, bitmap_bh, grp_target_blk,
					my_rsv,	&num, &fatal);
		if (fatal)
			goto out;
		if (grp_alloc_blk >= 0)
			goto allocated;
	}

	ngroups = EXT4_SB(sb)->s_groups_count;
	smp_rmb();

	/*
	 * Now search the rest of the groups.  We assume that
	 * i and gdp correctly point to the last group visited.
	 */
	for (bgi = 0; bgi < ngroups; bgi++) {
		group_no++;
		if (group_no >= ngroups)
			group_no = 0;
		gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
		if (!gdp)
			goto io_error;
		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
		/*
		 * skip this group if the number of
		 * free blocks is less than half of the reservation
		 * window size.
		 */
		if (free_blocks <= (windowsz/2))
			continue;

		brelse(bitmap_bh);
		bitmap_bh = read_block_bitmap(sb, group_no);
		if (!bitmap_bh)
			goto io_error;
		/*
		 * try to allocate block(s) from this group, without a goal(-1).
		 */
		grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
					group_no, bitmap_bh, -1, my_rsv,
					&num, &fatal);
		if (fatal)
			goto out;
		if (grp_alloc_blk >= 0)
			goto allocated;
	}
	/*
	 * We may end up a bogus ealier ENOSPC error due to
	 * filesystem is "full" of reservations, but
	 * there maybe indeed free blocks avaliable on disk
	 * In this case, we just forget about the reservations
	 * just do block allocation as without reservations.
	 */
	if (my_rsv) {
		my_rsv = NULL;
		windowsz = 0;
		group_no = goal_group;
		goto retry_alloc;
	}
	/* No space left on the device */
	*errp = -ENOSPC;
	goto out;

allocated:

	ext4_debug("using block group %d(%d)\n",
			group_no, gdp->bg_free_blocks_count);

	BUFFER_TRACE(gdp_bh, "get_write_access");
	fatal = ext4_journal_get_write_access(handle, gdp_bh);
	if (fatal)
		goto out;

	ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no);

	if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
	    in_range(ext4_inode_bitmap(sb, gdp), ret_block, num) ||
	    in_range(ret_block, ext4_inode_table(sb, gdp),
		     EXT4_SB(sb)->s_itb_per_group) ||
	    in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
		     EXT4_SB(sb)->s_itb_per_group))
		ext4_error(sb, "ext4_new_block",
			    "Allocating block in system zone - "
			    "blocks from %llu, length %lu",
			     ret_block, num);

	performed_allocation = 1;

#ifdef CONFIG_JBD2_DEBUG
	{
		struct buffer_head *debug_bh;

		/* Record bitmap buffer state in the newly allocated block */
		debug_bh = sb_find_get_block(sb, ret_block);
		if (debug_bh) {
			BUFFER_TRACE(debug_bh, "state when allocated");
			BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state");
			brelse(debug_bh);
		}
	}
	jbd_lock_bh_state(bitmap_bh);
	spin_lock(sb_bgl_lock(sbi, group_no));
	if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
		int i;

		for (i = 0; i < num; i++) {
			if (ext4_test_bit(grp_alloc_blk+i,
					bh2jh(bitmap_bh)->b_committed_data)) {
				printk("%s: block was unexpectedly set in "
					"b_committed_data\n", __FUNCTION__);
			}
		}
	}
	ext4_debug("found bit %d\n", grp_alloc_blk);
	spin_unlock(sb_bgl_lock(sbi, group_no));
	jbd_unlock_bh_state(bitmap_bh);
#endif

	if (ret_block + num - 1 >= ext4_blocks_count(es)) {
		ext4_error(sb, "ext4_new_block",
			    "block(%llu) >= blocks count(%llu) - "
			    "block_group = %lu, es == %p ", ret_block,
			ext4_blocks_count(es), group_no, es);
		goto out;
	}

	/*
	 * It is up to the caller to add the new buffer to a journal
	 * list of some description.  We don't know in advance whether
	 * the caller wants to use it as metadata or data.
	 */
	ext4_debug("allocating block %lu. Goal hits %d of %d.\n",
			ret_block, goal_hits, goal_attempts);

	spin_lock(sb_bgl_lock(sbi, group_no));
	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
	gdp->bg_free_blocks_count =
			cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num);
	gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
	spin_unlock(sb_bgl_lock(sbi, group_no));
	percpu_counter_sub(&sbi->s_freeblocks_counter, num);

	BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
	err = ext4_journal_dirty_metadata(handle, gdp_bh);
	if (!fatal)
		fatal = err;

	sb->s_dirt = 1;
	if (fatal)
		goto out;

	*errp = 0;
	brelse(bitmap_bh);
	DQUOT_FREE_BLOCK(inode, *count-num);
	*count = num;
	return ret_block;

io_error:
	*errp = -EIO;
out:
	if (fatal) {
		*errp = fatal;
		ext4_std_error(sb, fatal);
	}
	/*
	 * Undo the block allocation
	 */
	if (!performed_allocation)
		DQUOT_FREE_BLOCK(inode, *count);
	brelse(bitmap_bh);
	return 0;
}

ext4_fsblk_t ext4_new_block(handle_t *handle, struct inode *inode,
			ext4_fsblk_t goal, int *errp)
{
	unsigned long count = 1;

	return ext4_new_blocks(handle, inode, goal, &count, errp);
}

/**
 * ext4_count_free_blocks() -- count filesystem free blocks
 * @sb:		superblock
 *
 * Adds up the number of free blocks from each block group.
 */
ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
{
	ext4_fsblk_t desc_count;
	struct ext4_group_desc *gdp;
	int i;
	unsigned long ngroups = EXT4_SB(sb)->s_groups_count;
#ifdef EXT4FS_DEBUG
	struct ext4_super_block *es;
	ext4_fsblk_t bitmap_count;
	unsigned long x;
	struct buffer_head *bitmap_bh = NULL;

	es = EXT4_SB(sb)->s_es;
	desc_count = 0;
	bitmap_count = 0;
	gdp = NULL;

	smp_rmb();
	for (i = 0; i < ngroups; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
		brelse(bitmap_bh);
		bitmap_bh = read_block_bitmap(sb, i);
		if (bitmap_bh == NULL)
			continue;

		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
		printk("group %d: stored = %d, counted = %lu\n",
			i, le16_to_cpu(gdp->bg_free_blocks_count), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
	printk("ext4_count_free_blocks: stored = %llu"
		", computed = %llu, %llu\n",
	       EXT4_FREE_BLOCKS_COUNT(es),
		desc_count, bitmap_count);
	return bitmap_count;
#else
	desc_count = 0;
	smp_rmb();
	for (i = 0; i < ngroups; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
	}

	return desc_count;
#endif
}

static inline int test_root(int a, int b)
{
	int num = b;

	while (a > num)
		num *= b;
	return num == a;
}

static int ext4_group_sparse(int group)
{
	if (group <= 1)
		return 1;
	if (!(group & 1))
		return 0;
	return (test_root(group, 7) || test_root(group, 5) ||
		test_root(group, 3));
}

/**
 *	ext4_bg_has_super - number of blocks used by the superblock in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the superblock (primary or backup)
 *	in this group.  Currently this will be only 0 or 1.
 */
int ext4_bg_has_super(struct super_block *sb, int group)
{
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
			!ext4_group_sparse(group))
		return 0;
	return 1;
}

static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group)
{
	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
	unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb);
	unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1;

	if (group == first || group == first + 1 || group == last)
		return 1;
	return 0;
}

static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
{
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
			!ext4_group_sparse(group))
		return 0;
	return EXT4_SB(sb)->s_gdb_count;
}

/**
 *	ext4_bg_num_gdb - number of blocks used by the group table in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the group descriptor table
 *	(primary or backup) in this group.  In the future there may be a
 *	different number of descriptor blocks in each group.
 */
unsigned long ext4_bg_num_gdb(struct super_block *sb, int group)
{
	unsigned long first_meta_bg =
			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);

	if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
			metagroup < first_meta_bg)
		return ext4_bg_num_gdb_nometa(sb,group);

	return ext4_bg_num_gdb_meta(sb,group);

}