f2fs mkfs格式化系列3

前面讲了f2fs格式化主要进行了哪些操作，本篇看一下，mount过程中是如何读取格式化写到磁盘的那些内容的。

主要说一下如果读取f2fs meta data这些信息，mount过程还有一些比较重要的步骤，像build node management, build sit management后面会分开仔细再说。

static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct f2fs_sb_info *sbi;
	struct f2fs_super_block *raw_super;
	struct buffer_head *raw_super_buf;
	struct inode *root;
	long err;
	bool retry = true, need_fsck = false;
	char *options = NULL;
	int recovery, i;

try_onemore:
	err = -EINVAL;
	raw_super = NULL;
	raw_super_buf = NULL;
	recovery = 0;

	/* allocate memory for f2fs-specific super block info */
	sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	/* set a block size */
	if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
		goto free_sbi;
	}
	//读取磁盘中的super block,其中raw_super是f2fs superblock
	//f2fs super block有效数据并不是在一个物理block 0地址开始的，所以有一个head偏移，
	//raw_super_buff是包含head偏移的物理block
	err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery);
	if (err)
		goto free_sbi;
	//将vfs super block private info设置成f2fs super block
	sb->s_fs_info = sbi;
	default_options(sbi);
	/* parse mount options */
	options = kstrdup((const char *)data, GFP_KERNEL);
	if (data && !options) {
		err = -ENOMEM;
		goto free_sb_buf;
	}

	err = parse_options(sb, options);
	if (err)
		goto free_options;
	//下面设置filesystem物理属性
	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
	sb->s_max_links = F2FS_LINK_MAX;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));

	sb->s_op = &f2fs_sops;//super block相关的一些操作
	sb->s_xattr = f2fs_xattr_handlers;
	sb->s_export_op = &f2fs_export_ops;
	sb->s_magic = F2FS_SUPER_MAGIC;
	sb->s_time_gran = 1;
	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));

	/* init f2fs-specific super block info */
	sbi->sb = sb;//f2fs super block指向vfs super block
	sbi->raw_super = raw_super;
	sbi->raw_super_buf = raw_super_buf;
	mutex_init(&sbi->gc_mutex);
	mutex_init(&sbi->writepages);
	mutex_init(&sbi->cp_mutex);
	init_rwsem(&sbi->node_write);

	/* disallow all the data/node/meta page writes */
	set_sbi_flag(sbi, SBI_POR_DOING);
	spin_lock_init(&sbi->stat_lock);

	init_rwsem(&sbi->read_io.io_rwsem);
	sbi->read_io.sbi = sbi;
	sbi->read_io.bio = NULL;
	for (i = 0; i < NR_PAGE_TYPE; i++) {
		init_rwsem(&sbi->write_io[i].io_rwsem);
		sbi->write_io[i].sbi = sbi;
		sbi->write_io[i].bio = NULL;
	}

	init_rwsem(&sbi->cp_rwsem);
	init_waitqueue_head(&sbi->cp_wait);
	//设置super block物理特性，如块大小，segment, section大小，ino,meta ino等
	init_sb_info(sbi);

	/* get an inode for meta space */
	//初始化meta inode
	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
	if (IS_ERR(sbi->meta_inode)) {
		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
		err = PTR_ERR(sbi->meta_inode);
		goto free_options;
	}
	//读取check point
	err = get_valid_checkpoint(sbi);
	if (err) {
		f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
		goto free_meta_inode;
	}

	/* sanity checking of checkpoint */
	err = -EINVAL;
	if (sanity_check_ckpt(sbi)) {
		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
		goto free_cp;
	}
	//设置f2fs super block相关信息
	sbi->total_valid_node_count =
				le32_to_cpu(sbi->ckpt->valid_node_count);
	sbi->total_valid_inode_count =
				le32_to_cpu(sbi->ckpt->valid_inode_count);
	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
	sbi->total_valid_block_count =
				le64_to_cpu(sbi->ckpt->valid_block_count);
	sbi->last_valid_block_count = sbi->total_valid_block_count;
	sbi->alloc_valid_block_count = 0;
	INIT_LIST_HEAD(&sbi->dir_inode_list);
	spin_lock_init(&sbi->dir_inode_lock);

	init_extent_cache_info(sbi);

	init_ino_entry_info(sbi);

	/* setup f2fs internal modules */
	err = build_segment_manager(sbi);//初始化segmen info
	if (err) {
		f2fs_msg(sb, KERN_ERR,
			"Failed to initialize F2FS segment manager");
		goto free_sm;
	}
	err = build_node_manager(sbi);//初始化node info
	if (err) {
		f2fs_msg(sb, KERN_ERR,
			"Failed to initialize F2FS node manager");
		goto free_nm;
	}

	build_gc_manager(sbi);//初始化gc操作

	/* get an inode for node space */
	//初始化node inode,分配一个新的inode,并cache
	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
	if (IS_ERR(sbi->node_inode)) {
		f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
		err = PTR_ERR(sbi->node_inode);
		goto free_nm;
	}

	f2fs_join_shrinker(sbi);

	/* if there are nt orphan nodes free them */
	err = recover_orphan_inodes(sbi);
	if (err)
		goto free_node_inode;

	/* read root inode and dentry */
	//从磁盘读取root inode
	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
	if (IS_ERR(root)) {
		f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
		err = PTR_ERR(root);
		goto free_node_inode;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		iput(root);
		err = -EINVAL;
		goto free_node_inode;
	}
	//申请root dentry
	sb->s_root = d_make_root(root); /* allocate root dentry */
	if (!sb->s_root) {
		err = -ENOMEM;
		goto free_root_inode;
	}

	err = f2fs_build_stats(sbi);
	if (err)
		goto free_root_inode;

	if (f2fs_proc_root)
		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);

	if (sbi->s_proc)
		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
				 &f2fs_seq_segment_info_fops, sb);

	sbi->s_kobj.kset = f2fs_kset;
	init_completion(&sbi->s_kobj_unregister);
	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
							"%s", sb->s_id);
	if (err)
		goto free_proc;

	/* recover fsynced data */
	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
		/*
		 * mount should be failed, when device has readonly mode, and
		 * previous checkpoint was not done by clean system shutdown.
		 */
		if (bdev_read_only(sb->s_bdev) &&
				!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
			err = -EROFS;
			goto free_kobj;
		}

		if (need_fsck)
			set_sbi_flag(sbi, SBI_NEED_FSCK);

		err = recover_fsync_data(sbi);
		if (err) {
			need_fsck = true;
			f2fs_msg(sb, KERN_ERR,
				"Cannot recover all fsync data errno=%ld", err);
			goto free_kobj;
		}
	}
	/* recover_fsync_data() cleared this already */
	clear_sbi_flag(sbi, SBI_POR_DOING);

	/*
	 * If filesystem is not mounted as read-only then
	 * do start the gc_thread.
	 */
	if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
		/* After POR, we can run background GC thread.*/
		err = start_gc_thread(sbi);
		if (err)
			goto free_kobj;
	}
	kfree(options);

	/* recover broken superblock */
	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
		f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
		f2fs_commit_super(sbi, true);
	}

	sbi->cp_expires = round_jiffies_up(jiffies);

	return 0;

free_kobj:
	kobject_del(&sbi->s_kobj);
free_proc:
	if (sbi->s_proc) {
		remove_proc_entry("segment_info", sbi->s_proc);
		remove_proc_entry(sb->s_id, f2fs_proc_root);
	}
	f2fs_destroy_stats(sbi);
free_root_inode:
	dput(sb->s_root);
	sb->s_root = NULL;
free_node_inode:
	mutex_lock(&sbi->umount_mutex);
	f2fs_leave_shrinker(sbi);
	iput(sbi->node_inode);
	mutex_unlock(&sbi->umount_mutex);
free_nm:
	destroy_node_manager(sbi);
free_sm:
	destroy_segment_manager(sbi);
free_cp:
	kfree(sbi->ckpt);
free_meta_inode:
	make_bad_inode(sbi->meta_inode);
	iput(sbi->meta_inode);
free_options:
	kfree(options);
free_sb_buf:
	brelse(raw_super_buf);
free_sbi:
	kfree(sbi);

	/* give only one another chance */
	if (retry) {
		retry = false;
		shrink_dcache_sb(sb);
		goto try_onemore;
	}
	return err;
}