balloc.c

linux 内核源代码

{
	struct ext2_reserve_window_node *next_rsv;
	struct rb_node *next;
	spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;

	if (!spin_trylock(rsv_lock))
		return;

	next = rb_next(&my_rsv->rsv_node);

	if (!next)
		my_rsv->rsv_end += size;
	else {
		next_rsv = rb_entry(next, struct ext2_reserve_window_node, rsv_node);

		if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
			my_rsv->rsv_end += size;
		else
			my_rsv->rsv_end = next_rsv->rsv_start - 1;
	}
	spin_unlock(rsv_lock);
}

/**
 * ext2_try_to_allocate_with_rsv()
 * @sb:			superblock
 * @group:		given allocation block group
 * @bitmap_bh:		bufferhead holds the block bitmap
 * @grp_goal:		given target block within the group
 * @count:		target number of blocks to allocate
 * @my_rsv:		reservation window
 *
 * This is the main function used to allocate a new block and its reservation
 * window.
 *
 * Each time when a new block allocation is need, first try to allocate from
 * its own reservation.  If it does not have a reservation window, instead of
 * looking for a free bit on bitmap first, then look up the reservation list to
 * see if it is inside somebody else's reservation window, we try to allocate a
 * reservation window for it starting from the goal first. Then do the block
 * allocation within the reservation window.
 *
 * This will avoid keeping on searching the reservation list again and
 * again when somebody is looking for a free block (without
 * reservation), and there are lots of free blocks, but they are all
 * being reserved.
 *
 * We use a red-black tree for the per-filesystem reservation list.
 */
static ext2_grpblk_t
ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group,
			struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal,
			struct ext2_reserve_window_node * my_rsv,
			unsigned long *count)
{
	ext2_fsblk_t group_first_block, group_last_block;
	ext2_grpblk_t ret = 0;
	unsigned long num = *count;

	/*
	 * we don't deal with reservation when
	 * filesystem is mounted without reservation
	 * or the file is not a regular file
	 * or last attempt to allocate a block with reservation turned on failed
	 */
	if (my_rsv == NULL) {
		return ext2_try_to_allocate(sb, group, bitmap_bh,
						grp_goal, count, NULL);
	}
	/*
	 * grp_goal is a group relative block number (if there is a goal)
	 * 0 <= grp_goal < EXT2_BLOCKS_PER_GROUP(sb)
	 * first block is a filesystem wide block number
	 * first block is the block number of the first block in this group
	 */
	group_first_block = ext2_group_first_block_no(sb, group);
	group_last_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);

	/*
	 * Basically we will allocate a new block from inode's reservation
	 * window.
	 *
	 * We need to allocate a new reservation window, if:
	 * a) inode does not have a reservation window; or
	 * b) last attempt to allocate a block from existing reservation
	 *    failed; or
	 * c) we come here with a goal and with a reservation window
	 *
	 * We do not need to allocate a new reservation window if we come here
	 * at the beginning with a goal and the goal is inside the window, or
	 * we don't have a goal but already have a reservation window.
	 * then we could go to allocate from the reservation window directly.
	 */
	while (1) {
		if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
			!goal_in_my_reservation(&my_rsv->rsv_window,
						grp_goal, group, sb)) {
			if (my_rsv->rsv_goal_size < *count)
				my_rsv->rsv_goal_size = *count;
			ret = alloc_new_reservation(my_rsv, grp_goal, sb,
							group, bitmap_bh);
			if (ret < 0)
				break;			/* failed */

			if (!goal_in_my_reservation(&my_rsv->rsv_window,
							grp_goal, group, sb))
				grp_goal = -1;
		} else if (grp_goal >= 0) {
			int curr = my_rsv->rsv_end -
					(grp_goal + group_first_block) + 1;

			if (curr < *count)
				try_to_extend_reservation(my_rsv, sb,
							*count - curr);
		}

		if ((my_rsv->rsv_start > group_last_block) ||
				(my_rsv->rsv_end < group_first_block)) {
			rsv_window_dump(&EXT2_SB(sb)->s_rsv_window_root, 1);
			BUG();
		}
		ret = ext2_try_to_allocate(sb, group, bitmap_bh, grp_goal,
					   &num, &my_rsv->rsv_window);
		if (ret >= 0) {
			my_rsv->rsv_alloc_hit += num;
			*count = num;
			break;				/* succeed */
		}
		num = *count;
	}
	return ret;
}

/**
 * ext2_has_free_blocks()
 * @sbi:		in-core super block structure.
 *
 * Check if filesystem has at least 1 free block available for allocation.
 */
static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
{
	ext2_fsblk_t free_blocks, root_blocks;

	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
	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;
}

/*
 * ext2_new_blocks() -- core block(s) allocation function
 * @inode:		file inode
 * @goal:		given target block(filesystem wide)
 * @count:		target number of blocks to allocate
 * @errp:		error code
 *
 * ext2_new_blocks uses a goal block to assist allocation.  If the goal is
 * free, or there is a free block within 32 blocks of the goal, that block
 * is allocated.  Otherwise a forward search is made for a free block; within 
 * each block group the search first looks for an entire free byte in the block
 * bitmap, and then for any free bit if that fails.
 * This function also updates quota and i_blocks field.
 */
ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
		    unsigned long *count, int *errp)
{
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *gdp_bh;
	int group_no;
	int goal_group;
	ext2_grpblk_t grp_target_blk;	/* blockgroup relative goal block */
	ext2_grpblk_t grp_alloc_blk;	/* blockgroup-relative allocated block*/
	ext2_fsblk_t ret_block;		/* filesyetem-wide allocated block */
	int bgi;			/* blockgroup iteration index */
	int performed_allocation = 0;
	ext2_grpblk_t free_blocks;	/* number of free blocks in a group */
	struct super_block *sb;
	struct ext2_group_desc *gdp;
	struct ext2_super_block *es;
	struct ext2_sb_info *sbi;
	struct ext2_reserve_window_node *my_rsv = NULL;
	struct ext2_block_alloc_info *block_i;
	unsigned short windowsz = 0;
	unsigned long ngroups;
	unsigned long num = *count;

	*errp = -ENOSPC;
	sb = inode->i_sb;
	if (!sb) {
		printk("ext2_new_blocks: nonexistent device");
		return 0;
	}

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

	sbi = EXT2_SB(sb);
	es = EXT2_SB(sb)->s_es;
	ext2_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 EXT2_IOC_SETRSVSZ to set the window size to 0 to turn off
	 * reservation on that particular file)
	 */
	block_i = EXT2_I(inode)->i_block_alloc_info;
	if (block_i) {
		windowsz = block_i->rsv_window_node.rsv_goal_size;
		if (windowsz > 0)
			my_rsv = &block_i->rsv_window_node;
	}

	if (!ext2_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 >= le32_to_cpu(es->s_blocks_count))
		goal = le32_to_cpu(es->s_first_data_block);
	group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
			EXT2_BLOCKS_PER_GROUP(sb);
	goal_group = group_no;
retry_alloc:
	gdp = ext2_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) {
		grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) %
				EXT2_BLOCKS_PER_GROUP(sb));
		bitmap_bh = read_block_bitmap(sb, group_no);
		if (!bitmap_bh)
			goto io_error;
		grp_alloc_blk = ext2_try_to_allocate_with_rsv(sb, group_no,
					bitmap_bh, grp_target_blk,
					my_rsv, &num);
		if (grp_alloc_blk >= 0)
			goto allocated;
	}

	ngroups = EXT2_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 = ext2_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 = ext2_try_to_allocate_with_rsv(sb, group_no,
					bitmap_bh, -1, my_rsv, &num);
		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:

	ext2_debug("using block group %d(%d)\n",
			group_no, gdp->bg_free_blocks_count);

	ret_block = grp_alloc_blk + ext2_group_first_block_no(sb, group_no);

	if (in_range(le32_to_cpu(gdp->bg_block_bitmap), ret_block, num) ||
	    in_range(le32_to_cpu(gdp->bg_inode_bitmap), ret_block, num) ||
	    in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
		      EXT2_SB(sb)->s_itb_per_group) ||
	    in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table),
		      EXT2_SB(sb)->s_itb_per_group))
		ext2_error(sb, "ext2_new_blocks",
			    "Allocating block in system zone - "
			    "blocks from "E2FSBLK", length %lu",
			    ret_block, num);

	performed_allocation = 1;

	if (ret_block + num - 1 >= le32_to_cpu(es->s_blocks_count)) {
		ext2_error(sb, "ext2_new_blocks",
			    "block("E2FSBLK") >= blocks count(%d) - "
			    "block_group = %d, es == %p ", ret_block,
			le32_to_cpu(es->s_blocks_count), group_no, es);
		goto out;
	}

	group_adjust_blocks(sb, group_no, gdp, gdp_bh, -num);
	percpu_counter_sub(&sbi->s_freeblocks_counter, num);

	mark_buffer_dirty(bitmap_bh);
	if (sb->s_flags & MS_SYNCHRONOUS)
		sync_dirty_buffer(bitmap_bh);

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

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

ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp)
{
	unsigned long count = 1;

	return ext2_new_blocks(inode, goal, &count, errp);
}

#ifdef EXT2FS_DEBUG

static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};

unsigned long ext2_count_free (struct buffer_head * map, unsigned int numchars)
{
	unsigned int i;
	unsigned long sum = 0;

	if (!map)
		return (0);
	for (i = 0; i < numchars; i++)
		sum += nibblemap[map->b_data[i] & 0xf] +
			nibblemap[(map->b_data[i] >> 4) & 0xf];
	return (sum);
}

#endif  /*  EXT2FS_DEBUG  */

unsigned long ext2_count_free_blocks (struct super_block * sb)
{
	struct ext2_group_desc * desc;
	unsigned long desc_count = 0;
	int i;
#ifdef EXT2FS_DEBUG
	unsigned long bitmap_count, x;
	struct ext2_super_block *es;

	es = EXT2_SB(sb)->s_es;
	desc_count = 0;
	bitmap_count = 0;
	desc = NULL;
	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
		struct buffer_head *bitmap_bh;
		desc = ext2_get_group_desc (sb, i, NULL);
		if (!desc)
			continue;
		desc_count += le16_to_cpu(desc->bg_free_blocks_count);
		bitmap_bh = read_block_bitmap(sb, i);
		if (!bitmap_bh)
			continue;
		
		x = ext2_count_free(bitmap_bh, sb->s_blocksize);
		printk ("group %d: stored = %d, counted = %lu\n",
			i, le16_to_cpu(desc->bg_free_blocks_count), x);
		bitmap_count += x;
		brelse(bitmap_bh);
	}
	printk("ext2_count_free_blocks: stored = %lu, computed = %lu, %lu\n",
		(long)le32_to_cpu(es->s_free_blocks_count),
		desc_count, bitmap_count);
	return bitmap_count;
#else
        for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
                desc = ext2_get_group_desc (sb, i, NULL);
                if (!desc)
                        continue;
                desc_count += le16_to_cpu(desc->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 ext2_group_sparse(int group)
{
	if (group <= 1)
		return 1;
	return (test_root(group, 3) || test_root(group, 5) ||
		test_root(group, 7));
}

/**
 *	ext2_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 ext2_bg_has_super(struct super_block *sb, int group)
{
	if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&&
	    !ext2_group_sparse(group))
		return 0;
	return 1;
}

/**
 *	ext2_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 ext2_bg_num_gdb(struct super_block *sb, int group)
{
	if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&&
	    !ext2_group_sparse(group))
		return 0;
	return EXT2_SB(sb)->s_gdb_count;
}