Epoll

graph LR
epoll_create-->|1创建|fileNode("创建并初始化eventpoll结构体ep,将ep放入file->private,并返回fd")
epoll_create-->|1创建|RBTree("红黑树用于存储以后epoll_ctl传来的fd")
epoll_create-->|1创建|epitems("链表,用于存储准备就绪的事件")

epoll_ctl-->|2 fd对应到|RBTree
epoll_ctl-->|2 注册回调ep_poll_callback,回调时将fd对应的epitem实例放入就绪链表并唤醒进程|RBTree

epoll_wait-->|3 ep_poll观察是否有数据|epitems-->|3|isEvent{是否有数据?}-->|3有|返回数据
isEvent-->|3否|sleepTimeoutThenReturn-->被唤醒后从队列中移除wait,再传输就绪事件到用户空间

// /usr/include/x86_64-linux-gnu/sys/epoll.h

/* Creates an epoll instance.  Returns an fd for the new instance.
   The "size" parameter is a hint specifying the number of file
   descriptors to be associated with the new instance.  The fd
   returned by epoll_create() should be closed with close().  */
extern int epoll_create (int __size) __THROW;

SYSCALL_DEFINE1(epoll_create, int, size)
{
	if (size <= 0)
		return -EINVAL;

	return sys_epoll_create1(0);
}

/*
 * Open an eventpoll file descriptor.
 */
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
    int error, fd;
	struct eventpoll *ep = NULL;
	struct file *file;
 
     /*
	 * Create the internal data structure ("struct eventpoll").
	 */
	error = ep_alloc(&ep);
    
    /*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure and a free file descriptor.
	 */
	fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
    
	file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
				 O_RDWR | (flags & O_CLOEXEC));
    
	ep->file = file;
	fd_install(fd, file);
	return fd;
}

// /usr/include/x86_64-linux-gnu/sys/epoll.h
/* Valid opcodes ( "op" parameter ) to issue to epoll_ctl().  */
#define EPOLL_CTL_ADD 1	/* Add a file descriptor to the interface.  */
#define EPOLL_CTL_DEL 2	/* Remove a file descriptor from the interface.  */
#define EPOLL_CTL_MOD 3	/* Change file descriptor epoll_event structure.  */

/* Manipulate an epoll instance "epfd". Returns 0 in case of success,
   -1 in case of error ( the "errno" variable will contain the
   specific error code ) The "op" parameter is one of the EPOLL_CTL_*
   constants defined above. The "fd" parameter is the target of the
   operation. The "event" parameter describes which events the caller
   is interested in and any associated user data.  */
extern int epoll_ctl (int __epfd, int __op, int __fd,
		      struct epoll_event *__event) __THROW;

/*
 * The following function implements the controller interface for
 * the eventpoll file that enables the insertion/removal/change of
 * file descriptors inside the interest set.
 */
SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
		struct epoll_event __user *, event)
{
    int error;
	int full_check = 0;
	struct fd f, tf;
	struct eventpoll *ep;
	struct epitem *epi;
	struct epoll_event epds;
	struct eventpoll *tep = NULL;
    
    ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event)
                                          
    f = fdget(epfd);
  	/* Get the "struct file *" for the target file */
	tf = fdget(fd);
    /*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = f.file->private_data;                                      
}

/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
static inline int ep_op_has_event(int op)
{
	return op != EPOLL_CTL_DEL;
}

// /usr/include/x86_64-linux-gnu/sys/epoll.h
/* Wait for events on an epoll instance "epfd". Returns the number of
   triggered events returned in "events" buffer. Or -1 in case of
   error with the "errno" variable set to the specific error code. The
   "events" parameter is a buffer that will contain triggered
   events. The "maxevents" is the maximum number of events to be
   returned ( usually size of "events" ). The "timeout" parameter
   specifies the maximum wait time in milliseconds (-1 == infinite).

   This function is a cancellation point and therefore not marked with
   __THROW.  */
extern int epoll_wait (int __epfd, struct epoll_event *__events,
		       int __maxevents, int __timeout);

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_wait(2).
 */
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
		int, maxevents, int, timeout)
{
}

/*
 * This structure is stored inside the "private_data" member of the file
 * structure and represents the main data structure for the eventpoll
 * interface.
 */
struct eventpoll {
	/* Protect the access to this structure */
	spinlock_t lock;

	/*
	 * This mutex is used to ensure that files are not removed
	 * while epoll is using them. This is held during the event
	 * collection loop, the file cleanup path, the epoll file exit
	 * code and the ctl operations.
	 */
	struct mutex mtx;

	/* Wait queue used by sys_epoll_wait() */
	wait_queue_head_t wq;

	/* Wait queue used by file->poll() */
	wait_queue_head_t poll_wait;

	/* List of ready file descriptors */
	struct list_head rdllist;

	/* RB tree root used to store monitored fd structs */
	struct rb_root rbr;

	/*
	 * This is a single linked list that chains all the "struct epitem" that
	 * happened while transferring ready events to userspace w/out
	 * holding ->lock.
	 */
	struct epitem *ovflist;

	/* wakeup_source used when ep_scan_ready_list is running */
	struct wakeup_source *ws;

	/* The user that created the eventpoll descriptor */
	struct user_struct *user;

	struct file *file;

	/* used to optimize loop detection check */
	int visited;
	struct list_head visited_list_link;
};

struct epoll_event
{
  uint32_t events;	/* Epoll events */
  epoll_data_t data;	/* User data variable */
} __EPOLL_PACKED;

typedef union epoll_data
{
  void *ptr;
  int fd;
  uint32_t u32;
  uint64_t u64;
} epoll_data_t;

/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= ep_show_fdinfo,
#endif
	.release	= ep_eventpoll_release,
	.poll		= ep_eventpoll_poll,
	.llseek		= noop_llseek,
};