epoll 的大概实现基于回调. 当文件被写入时, 回调指定函数, 将其加入到 wait_queue 中.

当 epoll_wait 调用时, 无需遍历已监听节点, 可直接使用 wait_queue 中的节点. 这样通过一种 "顺势而为" 的操作, 提高了效率.

(以上是我观察源码时所看到的总结. 其实现有差异, 但可以这么简单理解)

然后, 现在像分析一些不太明白/有意思的点.

1. 文件自身必须直接 poll

   之前也说到了, epoll 通过回调函数来实现. 我本来以为这些回调是通过 epoll_ctl 增加对应的函数指针来实现的. 但好像不对. 源码中明确了, 文件自身必须支持 poll 回调.

   以下是 epoll_ctl 的部分代码:

   int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
   		 bool nonblock)
   {
   	int error;
   	int full_check = 0;
   	struct fd f, tf;
   	struct eventpoll *ep;
   	struct epitem *epi;
   	struct eventpoll *tep = NULL;
   
   	error = -EBADF;
   	f = fdget(epfd);
   	if (!f.file)
   		goto error_return;
   
   	/* Get the "struct file *" for the target file */
   	tf = fdget(fd);
   	if (!tf.file)
   		goto error_fput;
   
   	/* The target file descriptor must support poll */
   	error = -EPERM;
   	if (!file_can_poll(tf.file))
   		goto error_tgt_fput;
   

   其中 file_can_poll 的代码如下:

   static inline bool file_can_poll(struct file *file)
   {
   	return file->f_op->poll;
   }
   

   完整的 file_operation 为:

   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 (*read_iter) (struct kiocb *, struct iov_iter *);
   	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
   	int (*iopoll)(struct kiocb *kiocb, bool spin);
   	int (*iterate) (struct file *, struct dir_context *);
   	int (*iterate_shared) (struct file *, struct dir_context *);
   	__poll_t (*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 *);
   	unsigned long mmap_supported_flags;
   	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 (*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);
   	void (*show_fdinfo)(struct seq_file *m, struct file *f);
   #ifndef CONFIG_MMU
   	unsigned (*mmap_capabilities)(struct file *);
   #endif
   	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
   			loff_t, size_t, unsigned int);
   	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
   				   struct file *file_out, loff_t pos_out,
   				   loff_t len, unsigned int remap_flags);
   	int (*fadvise)(struct file *, loff_t, loff_t, int);
   } __randomize_layout;
   

   emm. 但是很奇怪的是, 我之前看的时候, 发现, 基础文件函数是没有这个函数指针的. 所以, 来找一下, 分别以 socket 和 open 及 fopen 创建的文件描述符为例.

   PS: 有一处有趣的地方:

   int sock_create(int family, int type, int protocol, struct socket **res)
   {
   	return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
   }
   EXPORT_SYMBOL(sock_create);
   

   这里 __sock_create 的首个参数表明, 资源被创建再对应的 namespace 中.

   emm. 为什么? namespace 是系统级别的隔离. 也就是说, sock 也是系统级别的资源?