Linux那些事儿之我是Sysfs(6)文件系统

接下来，我们进入sysfs部分。看看
kobject_add()->kobject_add_varg->kobject_add_internal->create_dir()->sysfs_create_dir_ns()
bus_create_file()->sysfs_create_file()

. . .
这些sysfs函数的内幕。
说白了，sysfs就是利用VFS的接口去读写kobject的层次结构，建立起来的文件系统。关于sysfs的内容就在fs/sysfs/下。 kobject的层次结构的更新与删除就是那些乱七八糟的XX_register()们干的事情。

在kobject_add()里面，调用了sysfs_create_dir_ns()。让我们看看它究竟是如何create的。

int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
{
	struct kernfs_node *parent, *kn;

	BUG_ON(!kobj);

	if (kobj->parent)
		parent = kobj->parent->sd;
	else
		parent = sysfs_root_kn;

	if (!parent)
		return -ENOENT;

	kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
				  S_IRWXU | S_IRUGO | S_IXUGO, kobj, ns);
	if (IS_ERR(kn)) {
		if (PTR_ERR(kn) == -EEXIST)
			sysfs_warn_dup(parent, kobject_name(kobj));
		return PTR_ERR(kn);
	}

	kobj->sd = kn;
	return 0;
}

 

当你看见这么些新东西，如kernfs_node出现的时候，你一定感到很困惑。诚然，我一度为代码中突然出现的事物感到恐慌，人类对未知的恐惧是与生俱来的，面对死亡，面对怪力乱神，我们抱着一颗敬畏的心灵就可以了。而面对linux，我们始终坚信，未知肯定是可以被探索出来的。妖是妖他妈生的，代码是人他妈写出来的，既然写得出来，那就肯定看得懂。对不起，扯远了....我还是介绍介绍文件系统的基本知识先。

文件系统

文件系统是个很模糊广泛的概念，"文件"狭义地说，是指磁盘文件，广义理解，可以是有组织有次序地存储与任何介质(包括内存)的一组信息。linux把所有的资源都看成是文件，让用户通过一个统一的文件系统操作界面，也就是同一组系统调用，对属于不同文件系统的文件进行操作。这样，就可以对用户程序隐藏各种不同文件系统的实现细节，为用户程序提供了一个统一的，抽象的，虚拟的文件系统界面，这就是所谓"VFS(Virtual Filesystem Switch)"。这个抽象出来的接口就是一组函数操作。

我们要实现一种文件系统就是要实现VFS所定义的一系列接口，file_operations, dentry_operations, inode_operations等，供上层调用。file_operations是对每个具体文件的读写操作，dentry_operations, inode_operations则是对文件的属性，如改名字，建立或删除的操作。

include/linux/fs.h

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);
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
	int (*iterate) (struct file *, struct dir_context *);
	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 *, loff_t, loff_t, 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 **, void **);
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
	int (*show_fdinfo)(struct seq_file *m, struct file *f);
};

include/linux/dcache.h

struct dentry_operations {
	int (*d_revalidate)(struct dentry *, unsigned int);
	int (*d_weak_revalidate)(struct dentry *, unsigned int);
	int (*d_hash)(const struct dentry *, struct qstr *);
	int (*d_compare)(const struct dentry *, const struct dentry *,
			unsigned int, const char *, const struct qstr *);
	int (*d_delete)(const struct dentry *);
	void (*d_release)(struct dentry *);
	void (*d_prune)(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);
}

include/linux/fs.h

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

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

	/* WARNING: probably going away soon, do not use! */
	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
} 

举个例子，我们写C程序，open(“hello.c”, O_RDONLY)，它通过系统调用的流程是这样的

open() ->       /*用户空间*/
-> 系统调用->
sys_open() -> file_operations->open()           /*内核空间*/

不同的文件系统，调用不同的file_operations->open()，在sysfs下就是sysfs_open_file()。