vfs 文件系统

vfs是在应用程序和真实文件系统之间插了一层

应用  
  ↓
vfs    
  ↓
ext2
怎么体现的？

比如应用执行read时，首先会调用到vfs的sys_read系统调用，然后再由sys_read转至真实文件系统的read函数中。
也就是vfs向上提供统一的系统调用接口，向下提供一个callbak函数指针，由真实文件系统实现vfs的这些系统调用的callbak函数。
类比于tcpip的协议无关接口，vfs好像充当了“文件系统无关接口”
真实文件系统除了需要实现vfs的系统调用callbak函数，还需要实现vfs通用文件模型的一些数据结构，才能正常工作。

vfs 通用文件模型

四大对象及其对应的操作函数集(refer ulk3)

1.超级块对象 super_block 和 super_operations
2.索引节点对象 inode (index node) 和 inode_operations
3.目录项对象 dentry 和 dentry_operations
4.文件对象 file 和 file_operations

1.超级块对象 super_block 和 super_operations

VFS中保存了系统中挂接的文件系统的链表以及这些文件系统对应的VFS超级块。系统启动后所有被初始化的文件系统都要向VFS登记。每个已安装的文件系统由一个VFS 超块表示
include/linux/fs.h

struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned char		s_dirt;
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
	loff_t			s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type;
	const struct super_operations	*s_op;
	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;
	struct rw_semaphore	s_umount;
	struct mutex		s_lock;
	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 */
#ifdef CONFIG_SMP
	struct list_head __percpu *s_files;
#else
	struct list_head	s_files;
#endif
	/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
	struct list_head	s_dentry_lru;	/* unused dentry lru */
	int			s_nr_dentry_unused;	/* # of dentry on lru */

	struct block_device	*s_bdev;
	struct backing_dev_info *s_bdi;
	struct mtd_info		*s_mtd;
	struct list_head	s_instances;
	struct quota_info	s_dquot;	/* Diskquota specific options */

	int			s_frozen;
	wait_queue_head_t	s_wait_unfrozen;

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

	void 			*s_fs_info;	/* Filesystem private info */
	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 super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);

   	void (*dirty_inode) (struct inode *, int flags);
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
	int (*drop_inode) (struct inode *);
	void (*evict_inode) (struct inode *);
	void (*put_super) (struct super_block *);
	void (*write_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
	int (*freeze_fs) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
	int (*statfs) (struct dentry *, struct kstatfs *);
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*umount_begin) (struct super_block *);

	int (*show_options)(struct seq_file *, struct vfsmount *);
	int (*show_devname)(struct seq_file *, struct vfsmount *);
	int (*show_path)(struct seq_file *, struct vfsmount *);
	int (*show_stats)(struct seq_file *, struct vfsmount *);
#ifdef CONFIG_QUOTA
	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
};

2.索引节点对象 inode (index node) 和 inode_operations

唯一的标识磁盘上的一个文件(目录也是文件)，描述文件的物理属性。


include/linux/fs.h

struct inode {
	/* RCU path lookup touches following: */
	umode_t			i_mode;
	uid_t			i_uid;
	gid_t			i_gid;
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;

	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned int		i_flags;
	unsigned long		i_state;
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
	struct mutex		i_mutex;


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

	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 list_head	i_dentry;
		struct rcu_head		i_rcu;
	};
	unsigned long		i_ino;
	atomic_t		i_count;
	unsigned int		i_nlink;
	dev_t			i_rdev;
	unsigned int		i_blkbits;
	u64			i_version;
	loff_t			i_size;
#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
	blkcnt_t		i_blocks;
	unsigned short          i_bytes;
	struct rw_semaphore	i_alloc_sem;
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
	struct file_lock	*i_flock;
	struct address_space	*i_mapping;
	struct address_space	i_data;
#ifdef CONFIG_QUOTA
	struct dquot		*i_dquot[MAXQUOTAS];
#endif
	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

#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
	atomic_t		i_writecount;
#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
#endif
	void			*i_private; /* fs or device private pointer */
};

struct inode_operations {
	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
	void * (*follow_link) (struct dentry *, struct nameidata *);
	int (*permission) (struct inode *, int, unsigned int);
	int (*check_acl)(struct inode *, int, unsigned int);

	int (*readlink) (struct dentry *, char __user *,int);
	void (*put_link) (struct dentry *, struct nameidata *, void *);

	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
	int (*mkdir) (struct inode *,struct dentry *,int);
	int (*rmdir) (struct inode *,struct dentry *);
	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
	void (*truncate) (struct inode *);
	int (*setattr) (struct dentry *, struct iattr *);
	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*removexattr) (struct dentry *, const char *);
	void (*truncate_range)(struct inode *, loff_t, loff_t);
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
} ____cacheline_aligned;

3.目录项对象 dentry 和 dentry_operations

表示逻辑意义上的文件(目录也是文件)，描述文件的逻辑属性。
路径查找时用到
include/linux/dcache.h

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 */
	unsigned int d_count;		/* protected by d_lock */
	spinlock_t d_lock;		/* per dentry lock */
	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 */
	/*
	 * d_child and d_rcu can share memory
	 */
	union {
		struct list_head d_child;	/* child of parent list */
	 	struct rcu_head d_rcu;
	} d_u;
	struct list_head d_subdirs;	/* our children */
	struct list_head d_alias;	/* inode alias list */
};

struct dentry_operations {
	int (*d_revalidate)(struct dentry *, struct nameidata *);
	int (*d_hash)(const struct dentry *, const struct inode *,
			struct qstr *);
	int (*d_compare)(const struct dentry *, const struct inode *,
			const struct dentry *, const struct inode *,
			unsigned int, const char *, const struct qstr *);
	int (*d_delete)(const struct dentry *);
	void (*d_release)(struct dentry *);
	void (*d_iput)(struct dentry *, struct inode *);
	char *(*d_dname)(struct dentry *, char *, int);
	struct vfsmount *(*d_automount)(struct path *);
	int (*d_manage)(struct dentry *, bool);
} ____cacheline_aligned;

4. 文件对象 file 和 file_operations

描述进程打开的某个文件
include/linux/fs.h

struct file {
	/*
	 * fu_list becomes invalid after file_free is called and queued via
	 * fu_rcuhead for RCU freeing
	 */
	union {
		struct list_head	fu_list;
		struct rcu_head 	fu_rcuhead;
	} f_u;
	struct path		f_path;
#define f_dentry	f_path.dentry
#define f_vfsmnt	f_path.mnt
	const struct file_operations	*f_op;
	spinlock_t		f_lock;  /* f_ep_links, f_flags, no IRQ */
#ifdef CONFIG_SMP
	int			f_sb_list_cpu;
#endif
	atomic_long_t		f_count;
	unsigned int 		f_flags;
	fmode_t			f_mode;
	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;
#ifdef CONFIG_DEBUG_WRITECOUNT
	unsigned long f_mnt_write_state;
#endif
};

struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
	int (*flush) (struct file *, fl_owner_t id);
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, int datasync);
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*flock) (struct file *, int, struct file_lock *);
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
	int (*setlease)(struct file *, long, struct file_lock **);
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
};

文件的打开读写流程：

首先在当前进程的文件描述表fdtale中分配一个空的文件描述符fd , 然后在filp_cachep中创建一个file struct , 调用do_path_lookup()找的文件的inode ,取出inode的文件操作方法file_operations赋给file struct ,并调用f->f_op->open()执行打开的操作. 最后根据根据文件描述符fd将file安装在当前进程文件描述表fdtable对应的位置.
这样在以后读写文件操作时, 只需要根据文件描述符fd,就可以在当前进程的描述表中找到该文件的file对象,然后调用f->f_op操作方法对文件进行操作.

最重要的是要明白file结构体的file_operations来自inode结构体的file_operations。而inode结构体的file_operations一般定义在各个文件系统目录下的file.c中，比如fs/ext2/file.c

根文件系统的注册和挂载：refer to ulk3

分两阶段
1.特殊rootfs的注册和挂载

start_kernel	init/main.c
vfs_caches_init	fs/dcatch.c
mnt_init	fs/namespace.c
init_rootfs	fs/ramfs/inode.c
register_filesystem(&rootfs_fs_type);
init_mount_tree	fs/namespace.c
do_kern_mount("rootfs", 0, "rootfs", NULL);	fs/namespace.c
vfs_kern_mount	fs/namespace.c
mount_fs	fs/super.c
调用rootfs file_system_type 的mount函数 rootfs_mount

2.实际根文件系统的注册和挂载(即uboot通过root=传递进来的设备)

start_kernel	init/main.c
rest_init	init/main.c
kernel_init	init/main.c
prepare_namespace	init/do_mounts.c
create_dev("/dev/root", ROOT_DEV);//uboot传来ROOT_DEV(root=)	init/do_mounts.c
mount_root	init/do_mounts.c
mount_block_root("/dev/root", root_mountflags);	init/do_mounts.c
do_mount_root	init/do_mounts.c
sys_mount	fs/namespace.c
接下来跟普通文件系统的挂载流程类似，见下面

普通文件系统的注册和挂载：

sys_mount	fs/namespace.c
do_mount	fs/namespace.c
do_kern_mount	fs/namespace.c
vfs_kern_mount	fs/namespace.c
mount_fs	fs/super.c
调用真实文件系统 file_system_type 的mount函数 rootfs_mount