ialloc.c

linux 内核源代码

	 */
	for (i = 1; i < ngroups; i <<= 1) {
		group += i;
		if (group >= ngroups)
			group -= ngroups;
		desc = ext4_get_group_desc (sb, group, NULL);
		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
				le16_to_cpu(desc->bg_free_blocks_count))
			return group;
	}

	/*
	 * That failed: try linear search for a free inode, even if that group
	 * has no free blocks.
	 */
	group = parent_group;
	for (i = 0; i < ngroups; i++) {
		if (++group >= ngroups)
			group = 0;
		desc = ext4_get_group_desc (sb, group, NULL);
		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
			return group;
	}

	return -1;
}

/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
{
	struct super_block *sb;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	int group;
	unsigned long ino = 0;
	struct inode * inode;
	struct ext4_group_desc * gdp = NULL;
	struct ext4_super_block * es;
	struct ext4_inode_info *ei;
	struct ext4_sb_info *sbi;
	int err = 0;
	struct inode *ret;
	int i, free = 0;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	ei = EXT4_I(inode);

	sbi = EXT4_SB(sb);
	es = sbi->s_es;
	if (S_ISDIR(mode)) {
		if (test_opt (sb, OLDALLOC))
			group = find_group_dir(sb, dir);
		else
			group = find_group_orlov(sb, dir);
	} else
		group = find_group_other(sb, dir);

	err = -ENOSPC;
	if (group == -1)
		goto out;

	for (i = 0; i < sbi->s_groups_count; i++) {
		err = -EIO;

		gdp = ext4_get_group_desc(sb, group, &bh2);
		if (!gdp)
			goto fail;

		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, group);
		if (!bitmap_bh)
			goto fail;

		ino = 0;

repeat_in_this_group:
		ino = ext4_find_next_zero_bit((unsigned long *)
				bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
		if (ino < EXT4_INODES_PER_GROUP(sb)) {

			BUFFER_TRACE(bitmap_bh, "get_write_access");
			err = ext4_journal_get_write_access(handle, bitmap_bh);
			if (err)
				goto fail;

			if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
						ino, bitmap_bh->b_data)) {
				/* we won it */
				BUFFER_TRACE(bitmap_bh,
					"call ext4_journal_dirty_metadata");
				err = ext4_journal_dirty_metadata(handle,
								bitmap_bh);
				if (err)
					goto fail;
				goto got;
			}
			/* we lost it */
			jbd2_journal_release_buffer(handle, bitmap_bh);

			if (++ino < EXT4_INODES_PER_GROUP(sb))
				goto repeat_in_this_group;
		}

		/*
		 * This case is possible in concurrent environment.  It is very
		 * rare.  We cannot repeat the find_group_xxx() call because
		 * that will simply return the same blockgroup, because the
		 * group descriptor metadata has not yet been updated.
		 * So we just go onto the next blockgroup.
		 */
		if (++group == sbi->s_groups_count)
			group = 0;
	}
	err = -ENOSPC;
	goto out;

got:
	ino++;
	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
	    ino > EXT4_INODES_PER_GROUP(sb)) {
		ext4_error(sb, __FUNCTION__,
			   "reserved inode or inode > inodes count - "
			   "block_group = %d, inode=%lu", group,
			   ino + group * EXT4_INODES_PER_GROUP(sb));
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
	err = ext4_journal_get_write_access(handle, bh2);
	if (err) goto fail;

	/* We may have to initialize the block bitmap if it isn't already */
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
		struct buffer_head *block_bh = read_block_bitmap(sb, group);

		BUFFER_TRACE(block_bh, "get block bitmap access");
		err = ext4_journal_get_write_access(handle, block_bh);
		if (err) {
			brelse(block_bh);
			goto fail;
		}

		free = 0;
		spin_lock(sb_bgl_lock(sbi, group));
		/* recheck and clear flag under lock if we still need to */
		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
			free = ext4_free_blocks_after_init(sb, group, gdp);
			gdp->bg_free_blocks_count = cpu_to_le16(free);
		}
		spin_unlock(sb_bgl_lock(sbi, group));

		/* Don't need to dirty bitmap block if we didn't change it */
		if (free) {
			BUFFER_TRACE(block_bh, "dirty block bitmap");
			err = ext4_journal_dirty_metadata(handle, block_bh);
		}

		brelse(block_bh);
		if (err)
			goto fail;
	}

	spin_lock(sb_bgl_lock(sbi, group));
	/* If we didn't allocate from within the initialized part of the inode
	 * table then we need to initialize up to this inode. */
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);

			/* When marking the block group with
			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
			 * on the value of bg_itable_unsed even though
			 * mke2fs could have initialized the same for us.
			 * Instead we calculated the value below
			 */

			free = 0;
		} else {
			free = EXT4_INODES_PER_GROUP(sb) -
				le16_to_cpu(gdp->bg_itable_unused);
		}

		/*
		 * Check the relative inode number against the last used
		 * relative inode number in this group. if it is greater
		 * we need to  update the bg_itable_unused count
		 *
		 */
		if (ino > free)
			gdp->bg_itable_unused =
				cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
	}

	gdp->bg_free_inodes_count =
		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
	if (S_ISDIR(mode)) {
		gdp->bg_used_dirs_count =
			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
	}
	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
	spin_unlock(sb_bgl_lock(sbi, group));
	BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bh2);
	if (err) goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);
	sb->s_dirt = 1;

	inode->i_uid = current->fsuid;
	if (test_opt (sb, GRPID))
		inode->i_gid = dir->i_gid;
	else if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current->fsgid;
	inode->i_mode = mode;

	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
						       ext4_current_time(inode);

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

	ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
	if (S_ISLNK(mode))
		ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
	/* dirsync only applies to directories */
	if (!S_ISDIR(mode))
		ei->i_flags &= ~EXT4_DIRSYNC_FL;
	ei->i_file_acl = 0;
	ei->i_dir_acl = 0;
	ei->i_dtime = 0;
	ei->i_block_alloc_info = NULL;
	ei->i_block_group = group;

	ext4_set_inode_flags(inode);
	if (IS_DIRSYNC(inode))
		handle->h_sync = 1;
	insert_inode_hash(inode);
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

	ei->i_state = EXT4_STATE_NEW;

	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;

	ret = inode;
	if(DQUOT_ALLOC_INODE(inode)) {
		err = -EDQUOT;
		goto fail_drop;
	}

	err = ext4_init_acl(handle, inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext4_init_security(handle,inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_std_error(sb, err);
		goto fail_free_drop;
	}
	if (test_opt(sb, EXTENTS)) {
		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
		ext4_ext_tree_init(handle, inode);
		if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
			err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
			if (err) goto fail;
			EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
			BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
			err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
		}
	}

	ext4_debug("allocating inode %lu\n", inode->i_ino);
	goto really_out;
fail:
	ext4_std_error(sb, err);
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(bitmap_bh);
	return ret;

fail_free_drop:
	DQUOT_FREE_INODE(inode);

fail_drop:
	DQUOT_DROP(inode);
	inode->i_flags |= S_NOQUOTA;
	inode->i_nlink = 0;
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}

/* Verify that we are loading a valid orphan from disk */
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
{
	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
	unsigned long block_group;
	int bit;
	struct buffer_head *bitmap_bh = NULL;
	struct inode *inode = NULL;

	/* Error cases - e2fsck has already cleaned up for us */
	if (ino > max_ino) {
		ext4_warning(sb, __FUNCTION__,
			     "bad orphan ino %lu!  e2fsck was run?", ino);
		goto out;
	}

	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh) {
		ext4_warning(sb, __FUNCTION__,
			     "inode bitmap error for orphan %lu", ino);
		goto out;
	}

	/* Having the inode bit set should be a 100% indicator that this
	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
	 * inodes that were being truncated, so we can't check i_nlink==0.
	 */
	if (!ext4_test_bit(bit, bitmap_bh->b_data) ||
			!(inode = iget(sb, ino)) || is_bad_inode(inode) ||
			NEXT_ORPHAN(inode) > max_ino) {
		ext4_warning(sb, __FUNCTION__,
			     "bad orphan inode %lu!  e2fsck was run?", ino);
		printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
		       bit, (unsigned long long)bitmap_bh->b_blocknr,
		       ext4_test_bit(bit, bitmap_bh->b_data));
		printk(KERN_NOTICE "inode=%p\n", inode);
		if (inode) {
			printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
			       is_bad_inode(inode));
			printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
			       NEXT_ORPHAN(inode));
			printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
		}
		/* Avoid freeing blocks if we got a bad deleted inode */
		if (inode && inode->i_nlink == 0)
			inode->i_blocks = 0;
		iput(inode);
		inode = NULL;
	}
out:
	brelse(bitmap_bh);
	return inode;
}

unsigned long ext4_count_free_inodes (struct super_block * sb)
{
	unsigned long desc_count;
	struct ext4_group_desc *gdp;
	int i;
#ifdef EXT4FS_DEBUG
	struct ext4_super_block *es;
	unsigned long bitmap_count, x;
	struct buffer_head *bitmap_bh = NULL;

	es = EXT4_SB(sb)->s_es;
	desc_count = 0;
	bitmap_count = 0;
	gdp = NULL;
	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		gdp = ext4_get_group_desc (sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, i);
		if (!bitmap_bh)
			continue;

		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
		printk("group %d: stored = %d, counted = %lu\n",
			i, le16_to_cpu(gdp->bg_free_inodes_count), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
	printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
		le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
	return desc_count;
#else
	desc_count = 0;
	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		gdp = ext4_get_group_desc (sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
		cond_resched();
	}
	return desc_count;
#endif
}

/* Called at mount-time, super-block is locked */
unsigned long ext4_count_dirs (struct super_block * sb)
{
	unsigned long count = 0;
	int i;

	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
		if (!gdp)
			continue;
		count += le16_to_cpu(gdp->bg_used_dirs_count);
	}
	return count;
}