Linux 文件系统内核代码学习

(先占个坑，后面边学边完善)

1. 结构体

对于每一个文件（包括目录、字符设备、块设备、socket 文件、FIFO文件、软连接）均有一个与之对应的 inode 和 dentry ，每个打开的文件都一个与之关联的 file 。

1.1 inode

/* kernel 4.19.55 */
struct inode {
    /* 参考 Documentation/filesystems/ext4/ondisk/inodes.rst */
	umode_t			i_mode; /* 文件类型和访问权限 */
	unsigned short		i_opflags;
	kuid_t			i_uid; /* 用户id */
	kgid_t			i_gid; /* 组id*/
	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; /* 关联文件系统超级块 */
	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; /* 关联的设备 */
	loff_t			i_size;
	struct timespec64	i_atime; /* 最近访问时间 */
	struct timespec64	i_mtime; /* 最近修改时间 */
	struct timespec64	i_ctime; /* 创建时间 */
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
	u8			i_blkbits;
	u8			i_write_hint;
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct rw_semaphore	i_rwsem;

	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;
	struct list_head	i_wb_list;	/* backing dev writeback list */
	union {
		struct hlist_head	i_dentry;
		struct rcu_head		i_rcu;
	};
	atomic64_t		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;
		unsigned		i_dir_seq;
	};

	__u32			i_generation;

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

#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
	struct fscrypt_info	*i_crypt_info;
#endif

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

1.2 dentry

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; /* 文件名称字符串 */
	struct inode *d_inode;		/* Where the name belongs to - NULL is
					 * negative 关联的 inode */
	unsigned char d_iname[DNAME_INLINE_LEN]; 	/* small names 
			* 名称字符串，长度超过 DNAME_INLINE_LEN 时，则保存在 d_name 中 */

	/* 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 关联文件系统超级块 */ 
	unsigned long d_time;		/* used by d_revalidate */
	void *d_fsdata;			/* fs-specific data */

	union {
		struct list_head d_lru;		/* LRU list */
		wait_queue_head_t *d_wait;	/* in-lookup ones only */
	};
	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 hlist_bl_node d_in_lookup_hash;	/* only for in-lookup ones */
	 	struct rcu_head d_rcu;
	} d_u;
} __randomize_layout;

1.3 file

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

	/*
	 * Protects f_ep_links, f_flags.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
	enum rw_hint		f_write_hint;
	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;
	errseq_t		f_wb_err;
} __randomize_layout
  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */

1.4 files_struct

struct files_struct {
  /*
   * read mostly part
   */
	atomic_t count;
	bool resize_in_progress;
	wait_queue_head_t resize_wait;

	struct fdtable __rcu *fdt; /* 打开文件列表 */
	struct fdtable fdtab;
  /*
   * written part on a separate cache line in SMP
   */
	spinlock_t file_lock ____cacheline_aligned_in_smp;
	unsigned int next_fd; /* 最小可分配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];
}

1.5 fdtable

struct fdtable {
	unsigned int max_fds; /* fd 数组最大个数 */
	struct file __rcu **fd;      /* current fd array, fd[i] 对应打开文件 file */
	unsigned long *close_on_exec;
	unsigned long *open_fds; /* 已使用fd 位图 */
	unsigned long *full_fds_bits;
	struct rcu_head rcu;
};

1.6 path

struct path {
	struct vfsmount *mnt;
	struct dentry *dentry;
} __randomize_layout;

1.7 vfsmount

struct vfsmount {
	struct dentry *mnt_root;	/* root of the mounted tree */
	struct super_block *mnt_sb;	/* pointer to superblock */
	int mnt_flags;
} __randomize_layout;

1.8 super_block

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;
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
	const struct fscrypt_operations	*s_cop;
#endif
	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
	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 */
	uuid_t			s_uuid;		/* 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;

	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;

	/* Pending fsnotify inode refs */
	atomic_long_t s_fsnotify_inode_refs;

	/* 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;

	/*
	 * Owning user namespace and default context in which to
	 * interpret filesystem uids, gids, quotas, device nodes,
	 * xattrs and security labels.
	 */
	struct user_namespace *s_user_ns;

	/*
	 * 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 */

	spinlock_t		s_inode_wblist_lock;
	struct list_head	s_inodes_wb;	/* writeback inodes */
} __randomize_layout;

2. 函数

2.1 filename_lookup

static int filename_lookup(int dfd, struct filename *name, unsigned flags,
			   struct path *path, struct path *root)
{
	int retval;
	struct nameidata nd;
	if (IS_ERR(name))
		return PTR_ERR(name);
	if (unlikely(root)) {
		nd.root = *root;
		flags |= LOOKUP_ROOT;
	}
	set_nameidata(&nd, dfd, name);
	retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
	if (unlikely(retval == -ECHILD))
		retval = path_lookupat(&nd, flags, path);
	if (unlikely(retval == -ESTALE))
		retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);

	if (likely(!retval))
		audit_inode(name, path->dentry, flags & LOOKUP_PARENT);
	restore_nameidata();
	putname(name);
	return retval;
}

2.2 path_lookupat

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
	const char *s = path_init(nd, flags);
	int err;

	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
		err = handle_lookup_down(nd);
		if (unlikely(err < 0))
			s = ERR_PTR(err);
	}

	while (!(err = link_path_walk(s, nd))
		&& ((err = lookup_last(nd)) > 0)) {
		s = trailing_symlink(nd);
	}
	if (!err)
		err = complete_walk(nd);

	if (!err && nd->flags & LOOKUP_DIRECTORY)
		if (!d_can_lookup(nd->path.dentry))
			err = -ENOTDIR;
	if (!err) {
		*path = nd->path;
		nd->path.mnt = NULL;
		nd->path.dentry = NULL;
	}
	terminate_walk(nd);
	return err;
}

2.3 path_init

/* must be paired with terminate_walk() */
static const char *path_init(struct nameidata *nd, unsigned flags)
{
	const char *s = nd->name->name;

	if (!*s)
		flags &= ~LOOKUP_RCU;
	if (flags & LOOKUP_RCU)
		rcu_read_lock();

	nd->last_type = LAST_ROOT; /* if there are only slashes... */
	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
	nd->depth = 0;
	if (flags & LOOKUP_ROOT) {
		struct dentry *root = nd->root.dentry;
		struct inode *inode = root->d_inode;
		if (*s && unlikely(!d_can_lookup(root)))
			return ERR_PTR(-ENOTDIR);
		nd->path = nd->root;
		nd->inode = inode;
		if (flags & LOOKUP_RCU) {
			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			nd->root_seq = nd->seq;
			nd->m_seq = read_seqbegin(&mount_lock);
		} else {
			path_get(&nd->path);
		}
		return s;
	}

	nd->root.mnt = NULL;
	nd->path.mnt = NULL;
	nd->path.dentry = NULL;

	nd->m_seq = read_seqbegin(&mount_lock);
	if (*s == '/') {
		set_root(nd);
		if (likely(!nd_jump_root(nd)))
			return s;
		return ERR_PTR(-ECHILD);
	} else if (nd->dfd == AT_FDCWD) {
		if (flags & LOOKUP_RCU) {
			struct fs_struct *fs = current->fs;
			unsigned seq;

			do {
				seq = read_seqcount_begin(&fs->seq);
				nd->path = fs->pwd;
				nd->inode = nd->path.dentry->d_inode;
				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			} while (read_seqcount_retry(&fs->seq, seq));
		} else {
			get_fs_pwd(current->fs, &nd->path);
			nd->inode = nd->path.dentry->d_inode;
		}
		return s;
	} else {
		/* Caller must check execute permissions on the starting path component */
		struct fd f = fdget_raw(nd->dfd);
		struct dentry *dentry;

		if (!f.file)
			return ERR_PTR(-EBADF);

		dentry = f.file->f_path.dentry;

		if (*s && unlikely(!d_can_lookup(dentry))) {
			fdput(f);
			return ERR_PTR(-ENOTDIR);
		}

		nd->path = f.file->f_path;
		if (flags & LOOKUP_RCU) {
			nd->inode = nd->path.dentry->d_inode;
			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
		} else {
			path_get(&nd->path);
			nd->inode = nd->path.dentry->d_inode;
		}
		fdput(f);
		return s;
	}
}

2.4 link_path_walk

/*
 * Name resolution.
 * This is the basic name resolution function, turning a pathname into
 * the final dentry. We expect 'base' to be positive and a directory.
 *
 * Returns 0 and nd will have valid dentry and mnt on success.
 * Returns error and drops reference to input namei data on failure.
 */
static int link_path_walk(const char *name, struct nameidata *nd)
{
	int err;

	if (IS_ERR(name))
		return PTR_ERR(name);
	while (*name=='/')   /* 跳过字符串开头的 '/' 字符 */
		name++;
	if (!*name)
		return 0;

	/* At this point we know we have a real path component. */
	for(;;) {
		u64 hash_len;
		int type;

		err = may_lookup(nd); /* 主要根据 super_block 的 s_flags 和 inode 的 i_mode，判断当前目录权限 */
		if (err)
			return err;
        /* 
         * hash_name: 计算 hash 值，根据父目录 dentry 地址和目录名字符串计算
         *            低 32 位表示 hash 值，高 32 位表示，返回当前字符到下一个 '/' 间的长度
         * hashlen_len: 返回长度，如："/home": 0, "./home": 1, "../home": 2, "..tmp/home": 5
         * hashlen_hash: 返回 hash 值
         */
		hash_len = hash_name(nd->path.dentry, name);

		type = LAST_NORM;
		if (name[0] == '.') switch (hashlen_len(hash_len)) {
			case 2:
				if (name[1] == '.') {
					type = LAST_DOTDOT;
					nd->flags |= LOOKUP_JUMPED;
				}
				break;
			case 1:
				type = LAST_DOT;
		}
		if (likely(type == LAST_NORM)) {
			struct dentry *parent = nd->path.dentry;
			nd->flags &= ~LOOKUP_JUMPED;
			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
				struct qstr this = { { .hash_len = hash_len }, .name = name };
				err = parent->d_op->d_hash(parent, &this);
				if (err < 0)
					return err;
				hash_len = this.hash_len;
				name = this.name;
			}
		}

		nd->last.hash_len = hash_len;
		nd->last.name = name;
		nd->last_type = type;

		name += hashlen_len(hash_len);
		if (!*name)
			goto OK;
		/*
		 * If it wasn't NUL, we know it was '/'. Skip that
		 * slash, and continue until no more slashes.
		 */
		do {
			name++;
		} while (unlikely(*name == '/'));
		if (unlikely(!*name)) {
OK:
			/* pathname body, done */
			if (!nd->depth)
				return 0;
			name = nd->stack[nd->depth - 1].name;
			/* trailing symlink, done */
			if (!name)
				return 0;
			/* last component of nested symlink */
			err = walk_component(nd, WALK_FOLLOW);
		} else {
			/* not the last component */
			err = walk_component(nd, WALK_FOLLOW | WALK_MORE);
		}
		if (err < 0)
			return err;

		if (err) {
			const char *s = get_link(nd);

			if (IS_ERR(s))
				return PTR_ERR(s);
			err = 0;
			if (unlikely(!s)) {
				/* jumped */
				put_link(nd);
			} else {
				nd->stack[nd->depth - 1].name = name;
				name = s;
				continue;
			}
		}
		if (unlikely(!d_can_lookup(nd->path.dentry))) {
			if (nd->flags & LOOKUP_RCU) {
				if (unlazy_walk(nd))
					return -ECHILD;
			}
			return -ENOTDIR;
		}
	}
}