Linux VFS文件系统及其对象

引入:VFS

VFS（Virtual Filesystem Switch）称为虚拟文件系统或虚拟文件系统转换，是一个内核软件层，在具体的文件系统之上抽象的一层，用来处理与Posix文件系统相关的所有调用，给各种文件系统提供一个通用的接口，使上层的应用程序能够使用通用的接口访问不同文件系统，同时也为不同文件系统的通信提供了媒介。

VFS提供了一个抽象层，将POSIX API接口与不同存储设备的具体接口实现进行了分离，使得底层的文件系统类型、设备类型对上层应用程序透明。

linux下“一切皆文件”是Unix/Linux的基本哲学之一。unix标准文件:普通文件，目录文件，符号链接文件，设备文件，管道文件。

–  普通文件、d  目录文件、b  块设备、c  字符设备、l   符号链接文件、p  管道文件pipe、s  套接字文件socket

通用文件模型

数据类型	Superblock	inode	dentry	file
功能	存储文件系统元数据	文件相关的元数据	文件（目录）名称和具体的inode的对应关系，缓存最近最常访问的文件或目录，提示系统性能	进程与打开文件的交互
存储内容	文件系统类型、大小、状态（存放于磁盘文件系统控制块）	文件的所有者（用户、组）、访问时间、文件类型等（存放于磁盘文件控制块）		文件指针（文件当前位置）
是否存储在介质中	是	是	否	否
何时创建	mount时从介质中读取，并常驻内存			文件打开时创建
内存中如何分配		名为filp的slab分配器高速缓存	名为dentry_cache的slab分配器高速缓存
重要成员	s_list、
涉及操作函数	*s_op
维护	所有SB对象以双向循环链表链接在一起
是否缓存			是

Superblock

其成员相关信息在介质中存储，mount时读取介质信息并在内存中创建。

结构体定义

struct super_block {
	struct list_head	s_list;		/* 支持挂载多个文件系统，并将super_block链起来 */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
	loff_t			s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type; /* 文件系统类型 */
	const struct super_operations	*s_op; /* 文件系统相关操作函数 */
	const struct dquot_operations	*dq_op;
	const struct quotactl_ops	*s_qcop;
	const struct export_operations *s_export_op;
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;/* 该文件系统的根目录 */
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
#ifdef CONFIG_SECURITY
	void                    *s_security;
#endif
	const struct xattr_handler **s_xattr;

	struct list_head	s_inodes;	/* all inodes */
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
	struct block_device	*s_bdev;
	struct backing_dev_info *s_bdi;
	struct mtd_info		*s_mtd;
	struct hlist_node	s_instances;
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
	struct quota_info	s_dquot;	/* Diskquota specific options */

	struct sb_writers	s_writers;

	char s_id[32];				/* Informational name */
	u8 s_uuid[16];				/* UUID */

	void 			*s_fs_info;	/* Filesystem private info */
	unsigned int		s_max_links;
	fmode_t			s_mode;

	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
	struct mutex s_vfs_rename_mutex;	/* Kludge */

	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
	char __rcu *s_options;
	const struct dentry_operations *s_d_op; /* default d_op for dentries */

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;

	struct shrinker s_shrink;	/* per-sb shrinker handle */

	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

	/* Being remounted read-only */
	int s_readonly_remount;

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
	struct hlist_head s_pins;

	/*
	 * Keep the lru lists last in the structure so they always sit on their
	 * own individual cachelines.
	 */
	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
	struct rcu_head		rcu;

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;
};

重要成员

类型	类型名	成员名	作用
struct	list_head	s_list	支持挂载多个文件系统，并将super_block链起来
struct	dentry	s_root	该文件系统的根目录
struct	super_operations	*s_op	文件系统相关操作函数
		*s_d_op
struct	file_system_type	*s_type	文件系统类型名称，mount时指定类型名
void		*s_fs_info	指向具体文件系统的超级块信息

Index node(inode)

静态：创建文件系统时生成inode，保存在具体存储设备上，记录了文件系统的元信息；

动态：VFS在内存中使用inode数据结构，来管理文件系统的文件对象，记录了文件对象的详细信息，部分字段与关联的文件对象有关，会动态创建。

结构体定义

/*
 * Keep mostly read-only and often accessed (especially for
 * the RCU path lookup and 'stat' data) fields at the beginning
 * of the 'struct inode'
 */
struct inode {
	umode_t			i_mode;
	unsigned short		i_opflags;
	kuid_t			i_uid;
	kgid_t			i_gid;
	unsigned int		i_flags;

#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
#endif

	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
	struct address_space	*i_mapping;

#ifdef CONFIG_SECURITY
	void			*i_security;
#endif

	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
	/*
	 * Filesystems may only read i_nlink directly.  They shall use the
	 * following functions for modification:
	 *
	 *    (set|clear|inc|drop)_nlink
	 *    inode_(inc|dec)_link_count
	 */
	union {
		const unsigned int i_nlink;
		unsigned int __i_nlink;
	};
	dev_t			i_rdev;
	loff_t			i_size;
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
	unsigned int		i_blkbits;
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;

	unsigned long		dirtied_when;	/* jiffies of first dirtying */
	unsigned long		dirtied_time_when;

	struct hlist_node	i_hash;
	struct list_head	i_wb_list;	/* backing dev IO list */
	struct list_head	i_lru;		/* inode LRU list */
	struct list_head	i_sb_list;
	union {
		struct hlist_head	i_dentry;
		struct rcu_head		i_rcu;
	};
	u64			i_version;
	atomic_t		i_count;
	atomic_t		i_dio_count;
	atomic_t		i_writecount;
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
	struct file_lock_context	*i_flctx;
	struct address_space	i_data;
	struct list_head	i_devices;
	union {
		struct pipe_inode_info	*i_pipe;
		struct block_device	*i_bdev;
		struct cdev		*i_cdev;
	};

	__u32			i_generation;

#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
	struct hlist_head	i_fsnotify_marks;
#endif

	void			*i_private; /* fs or device private pointer */
};

重要成员

类型	类型名	成员名	作用
struct	inode_operations	*i_op	索引节点操作函数列表
struct	super_block	*i_sb	指向所属的超级块对象
long	\	i_ino	索引节点编号
short	\	i_bytes	最后一个块的有效字节数
int		i_blkbits	每个块所占位数
blkcnt_t		i_blocks	文件所占块数

Directory entry(dentry)

目录项=子目录项+文件

结构体定义

struct dentry {
	/* RCU lookup touched fields */
	unsigned int d_flags;		/* protected by d_lock */
	seqcount_t d_seq;		/* per dentry seqlock */
	struct hlist_bl_node d_hash;	/* lookup hash list */
	struct dentry *d_parent;	/* parent directory */
	struct qstr d_name;
	struct inode *d_inode;		/* Where the name belongs to - NULL is
					 * negative */
	unsigned char d_iname[DNAME_INLINE_LEN];	/* small names */

	/* Ref lookup also touches following */
	struct lockref d_lockref;	/* per-dentry lock and refcount */
	const struct dentry_operations *d_op;
	struct super_block *d_sb;	/* The root of the dentry tree */
	unsigned long d_time;		/* used by d_revalidate */
	void *d_fsdata;			/* fs-specific data */

	struct list_head d_lru;		/* LRU list */
	struct list_head d_child;	/* child of parent list */
	struct list_head d_subdirs;	/* our children */
	/*
	 * d_alias and d_rcu can share memory
	 */
	union {
		struct hlist_node d_alias;	/* inode alias list */
	 	struct rcu_head d_rcu;
	} d_u;
};

重要成员

类型	类型名	成员名	作用
int	\	d_flags	标记，如是否为挂载点
		d_hash	hash链表
struct	dentry	d_parent	当前目录项的父目录项
unsigned char		d_iname	文件名
struct	qstr	d_name	长文件名
		d_inode	与此dentry关联的文件inode
struct	list_head	d_subdirs	子目录项链表
struct	super_block	*d_sb	所属文件系统超级块

File
 

结构体定义（include/linux/fs.h）

struct file {
	union {
		struct llist_node	fu_llist;
		struct rcu_head 	fu_rcuhead;
	} f_u;
	struct path		f_path;
	struct inode		*f_inode;	/* cached value */
	const struct file_operations	*f_op;

	/*
	 * Protects f_ep_links, f_flags.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
	atomic_long_t		f_count;
	unsigned int 		f_flags;
	fmode_t			f_mode;
	struct mutex		f_pos_lock;
	loff_t			f_pos;
	struct fown_struct	f_owner;
	const struct cred	*f_cred;
	struct file_ra_state	f_ra;

	u64			f_version;
#ifdef CONFIG_SECURITY
	void			*f_security;
#endif
	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct list_head	f_ep_links;
	struct list_head	f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */

重要成员

类型	类型名	成员名	作用

文件系统类型

所有文件系统注册到file_systems单项链表中（register_filesystem()函数注册）。get_fs_type(name)获取file_system_type对象。

结构体定义

struct file_system_type {
	const char *name;
	int fs_flags;
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
#define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
#define FS_USERNS_VISIBLE	32	/* FS must already be visible */
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct hlist_head fs_supers;

	struct lock_class_key s_lock_key;
	struct lock_class_key s_umount_key;
	struct lock_class_key s_vfs_rename_key;
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
	struct lock_class_key i_mutex_dir_key;
};

重要成员

类型	类型名	成员名	作用
char*		*name;	文件系统名
int		fs_flags	文件系统类型标志
dentry		mount	文件系统挂在触发的操作
		kill_sb	删除超级块

Linux 虚拟文件系统（VFS）介绍_落尘纷扰的博客-CSDN博客_虚拟文件系统

linux的VFS详解_土豆西瓜大芝麻的博客-CSDN博客_linux vfs

Linux文件系统详解_圣诞的博客-CSDN博客_linux 文件系统

Linux文件系统详解 - 赛艇队长 - 博客园

Linux文件系统的实现 - Vamei - 博客园

IBM Developer