VFS - Jokacer/Learn GitHub Wiki
作为内核子系统，为用户空间程序提供了文件和文件系统相关的接口，系统中的文件系统依赖VFS协同工作。VFS作为一个抽象层定义了所有文件系统都支持的、基本的、概念上的接口和数据结构，用户不需要了解文件系统的内部细节。进程与VFS对象之间的交互如图
存放已安装文件系统的有关信息。对基于磁盘的文件系统，这类对象通常对应与存放在磁盘上的文件系统控制块(filesystem control block)。
超级块对象由super_block结构组成,结构如下：
struct super_block {
struct list_head s_list; /* Keep this first */
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;
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_iflags; /* internal SB_I_* flags */
unsigned long s_magic;
struct dentry *s_root;
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 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;
struct work_struct destroy_work;
struct mutex s_sync_lock; /* sync serialisation lock */
/*
* Indicates how deep in a filesystem stack this SB is
*/
int s_stack_depth;
/* s_inode_list_lock protects s_inodes */
spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
struct list_head s_inodes; /* all inodes */
};其中s_op字段指向超级块的操作函数表，用super_operation结构表示：
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 *);
int (*sync_fs)(struct super_block *sb, int wait);
int (*freeze_super) (struct super_block *);
int (*freeze_fs) (struct super_block *);
int (*thaw_super) (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 dentry *);
int (*show_devname)(struct seq_file *, struct dentry *);
int (*show_path)(struct seq_file *, struct dentry *);
int (*show_stats)(struct seq_file *, struct dentry *);
#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);
struct dquot **(*get_dquots)(struct inode *);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
long (*nr_cached_objects)(struct super_block *,
struct shrink_control *);
long (*free_cached_objects)(struct super_block *,
struct shrink_control *);
};所有的超级块对象都以双向循环链表的新式链接在一起，链表第一个元素用super_block变量表示：
/------------\
/--------->|super_blocks|<--- .......... ---------------------\
| \------------/ |
| |
| super_block super_block super_block |
| +-----------+ +-----------+ +-----------+ |
\----->| s_list |<--------->| s_list |<--------->| s_list |<---/
+-----------+ +-----------+ +-----------+
| s_inodes | | s_inodes | | s_inodes |
+-----------+ +-----------+ +-----------+
| s_files | | s_files | | s_files |
+-----------+ +-----------+ +-----------+
| s_dirty | | s_dirty | | s_dirty |
+-----------+ +-----------+ +-----------+
| s_op | | s_op | | s_op |
+-----------+ +-----------+ +-----------+
| s_fs_info| | s_fs_info| | s_fs_info|
+-----------+ +-----------+ +-----------+
| | | | | |
其中s_fs_info指向属于具体文件系统的超级块信息，其数据会被复制到内存，由于VFS运行文件系统直接对内存超级块的s_fs_info字段进行操作，而无需访问磁盘，因此使用一个s_dirty字段标志该超级块是否式“脏”的。
存放关于具体文件的一般信息。对基于磁盘的文件系统，这类对象通常对应于存放在磁盘上的文件控制块(file control block)。每个索引节点对象都有一个索引节点号，这个节点号唯一的标志文件系统中的文件。
每个索引节点会复制磁盘索引节点的一些数据，如分配给文件的磁盘块数等，内存中的索引节点对象由inode结构表示：
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_io_list; /* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *i_wb; /* the associated cgroup wb */
/* foreign inode detection, see wbc_detach_inode() */
int i_wb_frn_winner;
u16 i_wb_frn_avg_time;
u16 i_wb_frn_history;
#endif
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;
char *i_link;
};
__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 */
};其中i_state字段可表示节点是否“脏”、是否处于I/O传送中等状态。i_op字段指向操作函数表，由inode_operations结构表示。
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
const char * (*follow_link) (struct dentry *, void **);
int (*permission) (struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
void (*put_link) (struct inode *, void *);
int (*create) (struct inode *,struct dentry *, umode_t, bool);
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 *,umode_t);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *);
int (*rename2) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
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 *);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
umode_t create_mode, int *opened);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
int (*set_acl)(struct inode *, struct posix_acl *, int);
} ____cacheline_aligned;文件对象存放打开文件与进程之间进行交互的有关信息，这类信息仅当进程访问文件期间存在于内核内存中。文件对象是在文件被打开时创建的，由于文件对象在磁盘上没有对应的映像，所以没有设置脏字段，存在file结构中：
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 */存放文件对象中的主要信息是文件指针，即当前文件的位置。文件对象通过一个名为filp的slab高速缓存分配，filp描述符存放在fila_cachep变量中。
存放目录项（文件的特定名称）与对应文件进行链接的有关信息，每个磁盘文件系统都以自己特有的方式将该类信息存在磁盘上。VFS把每个目录看作由若干子目录和文件组成的一个普通文件，如:/bin/vi路径中bin是特殊目录文件而vi是一个普通文件，一旦目录项被读入内存，VFS就把它转换成基于dentry结构的一个目录项对象，每个dentry代表路径中的一个特定部分，如：/、bin、vi都属于目录项对象，前两个是目录，最后一个是普通文件，在路径中每个部分都是目录项对象（包括普通文件）。目录项对象在磁盘上并没有对应的映像，因此在dentry结构中不包含脏字段。
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;
};目录项对象存在名为dentry_cache的slab分配器高速缓存中。每个目录项对象可以处于四种状态之一：
- 空闲状态(free)
不包括有效信息，未被VFS使用，等待slab分配器进行处理 - 未使用状态(unused)
该目录项对象还没有被内核使用，对象的引用计数器d_count值为0，该对象包含有效信息，可在必要时被回收丢弃。 - 正在使用状态(in use)
处于该状态的目录项对象正在被内核使用，该对象包含有效信息并且不能被丢弃。 - 负状态(negative)
与目录项关联的索引节点不复存在，即相应磁盘的索引节点已被删除，或者因为目录项对象是通过解析一个不存在文件的路径名创建的，该对象仍被保存在目录项高速缓存中以便后续对同一文件目录名的查找操作能快速完成。
每个进程都有当前工作的目录和自己的根目录，进程描述符中fs字段指向进程的fs_struct结构，包含文件系统和进程相关的信息：
struct fs_struct {
int users;//用户数目
spinlock_t lock;//保护该结构体的锁
seqcount_t seq;//顺序锁
int umask;//掩码
int in_exec;//当前正在执行的文件
struct path root, pwd;//根目录路径和当前工作目录路径
};表示进程当前打开的文件的表地址存放在进程描述符的files字段中，包含在files_struct结构体中：
struct files_struct {
/*
* read mostly part
*/
atomic_t count;
bool resize_in_progress;
wait_queue_head_t resize_wait;
struct fdtable __rcu *fdt;
struct fdtable fdtab;
/*
* written part on a separate cache line in SMP
*/
spinlock_t file_lock ____cacheline_aligned_in_smp;
int next_fd;
unsigned long close_on_exec_init[1];
unsigned long open_fds_init[1];
unsigned long full_fds_bits_init[1];
struct file __rcu * fd_array[NR_OPEN_DEFAULT];
};fd字段指向文件对象的指针数组。