c++应用网络编程之十三Linux下的epoll模式应用

一、epoll的应用

epoll在实际场景的应用是非常多的，特别是开源的框架中，基本都支持这种用法。大家可以在网上轻松的得到各种形式的epoll的封装代码，但是一定要明白的是，这些代码哪些是利用了epoll的机制，哪些是上层多线程的封装，哪些又是数据处理的封装。甚至有些可能做了一些其它的辅助动作如修改了一些内核的参数等等。
学习epoll，除了理解前面分析的各种内部原理和机制，更要根据实际情况进行应用。学不能致用，学和不学没有意义；用而不思考其中的技术，则遇到问题无从下手。

二、数据结构和API

1、epoll主要的数据结构如下：

struct epoll_event {
   
	__poll_t events;
	__u64 data;
} EPOLL_PACKED;
struct epitem {
   
	union {
   
		/* RB tree node links this structure to the eventpoll RB tree */
		struct rb_node rbn;
		/* Used to free the struct epitem */
		struct rcu_head rcu;
	};

	/* List header used to link this structure to the eventpoll ready list */
	struct list_head rdllink;

	/*
	 * Works together "struct eventpoll"->ovflist in keeping the
	 * single linked chain of items.
	 */
	struct epitem *next;

	/* The file descriptor information this item refers to */
	struct epoll_filefd ffd;

	/* List containing poll wait queues */
	struct eppoll_entry *pwqlist;

	/* The "container" of this item */
	struct eventpoll *ep;

	/* List header used to link this item to the "struct file" items list */
	struct hlist_node fllink;

	/* wakeup_source used when EPOLLWAKEUP is set */
	struct wakeup_source __rcu *ws;

	/* The structure that describe the interested events and the source fd */
	struct epoll_event event;
};

struct eventpoll {
   
	/*
	 * 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;

	/* Lock which protects rdllist and ovflist */
	rwlock_t lock;

	/* RB tree root used to store monitored fd structs */
	struct rb_root_cached 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 */
	u64 gen;
	struct hlist_head refs;

#ifdef CONFIG_NET_RX_BUSY_POLL
	/* used to track busy poll napi_id */
	unsigned int napi_id;
#endif

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	/* tracks wakeup nests for lockdep validation */
	u8 nests;
#endif
};

/* Wrapper struct used by poll queueing */
struct ep_pqueue {
   
	poll_table pt;
	struct epitem *epi;
};

2、其API主要有三个

int epoll_create(int size);
int epoll_ctl(int epfd, int op, int fd, struct epoll_event *event);
int epoll_wait(int epfd, struct epoll_event *events,int maxevents, int timeout);

其调用的是内核中的代码：

//fs/eventpoll.c
/*
 * Open an eventpoll file descriptor.
 */
static int do_epoll_create(int flags)
{
   
	int error, fd;
	struct eventpoll *ep = NULL;
	struct file *file;

	/* Check the EPOLL_* constant for consistency.  */
	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);

	if (flags & ~EPOLL_CLOEXEC)
		return -EINVAL;
	/*
	 * Create the internal data structure ("struct eventpoll").
	 */
	error = ep_alloc(&ep);
	if (error < 0)
		return error;
	/*
	 * 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));
	if (fd < 0) {
   
		error = fd;
		goto out_free_ep;
	}
	file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
				 O_RDWR | (flags & O_CLOEXEC));
	if (IS_ERR(file)) {
   
		error = PTR_ERR(file);
		goto out_free_fd;
	}
	ep->file = file;
	fd_install(fd, file);
	return fd;

out_free_fd:
	put_unused_fd(fd);
out_free_ep:
	ep_free(ep);
	return error;
}

SYSCALL_DEFINE1(epoll_create1, int, flags)
{
   
	return do_epoll_create(flags);
}

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

	return do_epoll_create(0);
}

static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
				   bool nonblock)
{
   
	if (!nonblock) {
   
		mutex_lock_nested(mutex, depth);
		return 0;
	}
	if (mutex_trylock(mutex))
		return 0;
	return -EAGAIN;
}

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;

	/* Check if EPOLLWAKEUP is allowed */
	if (ep_op_has_event(op))
		ep_take_care_of_epollwakeup(epds);

	/*
	 * We have to check that the file structure underneath the file descriptor
	 * the user passed to us _is_ an eventpoll file. And also we do not permit
	 * adding an epoll file descriptor inside itself.
	 */
	error = -EINVAL;
	if (f.file == tf.file || !is_file_epoll(f.file))
		goto error_tgt_fput;

	/*
	 * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
	 * Also, we do not currently supported nested exclusive wakeups.
	 */
	if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
   
		if (op == EPOLL_CTL_MOD)
			goto error_tgt_fput;
		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
				(epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
			goto error_tgt_fput;
	}

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = f.file->private_data;

	/*
	 * When we insert an epoll file descriptor inside another epoll file
	 * descriptor, there is the chance of creating closed loops, which are
	 * better be handled here, than in more critical paths. While we are
	 * checking for loops we also determine the list of files reachable
	 * and hang them on the tfile_check_list, so we can check that we
	 * haven't created too many possible wakeup paths.
	 *
	 * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when
	 * the epoll file descriptor is attaching directly to a wakeup source,
	 * unless the epoll file descriptor is nested. The purpose of taking the
	 * 'epmutex' on add is to prevent complex toplogies such as loops and
	 * deep wakeup paths from forming in parallel through multiple
	 * EPOLL_CTL_ADD operations.
	 */
	error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
	if (error)
		goto error_tgt_fput;
	if (op == EPOLL_CTL_ADD) {
   
		if (READ_ONCE(f.file->f_ep) || ep->gen == loop_check_gen ||
		    is_file_epoll(tf.file)) {
   
			mutex_unlock(&ep->mtx);
			error = epoll_mutex_lock(&epmutex, 0, nonblock);
			if (error)
				goto error_tgt_fput;
			loop_check_gen++;
			full_check = 1;
			if (is_file_epoll(tf.file)) {
   
				tep = tf.file->private_data;
				error = -ELOOP;
				if (ep_loop_check(ep, tep) != 0)
					goto error_tgt_fput;
			}
			error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
			if (error)
				goto error_tgt_fput;
		}
	}

	/*
	 * Try to lookup the file inside our RB tree. Since we grabbed "mtx"
	 * above, we can be sure to be able to use the item looked up by
	 * ep_find() till we release the mutex.
	 */
	epi = ep_find(ep, tf.file, fd);

	error = -EINVAL;
	switch (op) {
   
	case EPOLL_CTL_ADD:
		if (!epi) {
   
			epds->events |= EPOLLERR | EPOLLHUP;
			error = ep_insert(ep, epds, tf.file, fd, full_check);
		} else
			error = -EEXIST;
		break;
	case EPOLL_CTL_DEL:
		if (epi)
			error = ep_remove(ep, epi);
		else
			error = -ENOENT;
		break;
	case EPOLL_CTL_MOD:
		if (epi) {
   
			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
   
				epds->events |= EPOLLERR | EPOLLHUP;
				error = ep_modify(ep, epi, epds);
			}
		} else
			error = -ENOENT;
		break;
	}
	mutex_unlock(&ep->mtx);

error_tgt_fput:
	if (full_check) {
   
		clear_tfile_check_list();
		loop_check_gen++;
		mutex_unlock(&epmutex);
	}

	fdput(tf);
error_fput:
	fdput(f);
error_return:

	return error;
}

/*
 * 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)
{
   
	struct epoll_event epds;

	if (ep_op_has_event(op) &&
	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
		return -EFAULT;

	return do_epoll_ctl(epfd, op, fd, &epds, false);
}

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_wait(2).
 */
static int do_epoll_wait(int epfd, struct epoll_event __user *events,
			 int maxevents, struct timespec64 *to)
{
   
	int error;
	struct fd f;
	struct eventpoll *ep;

	/* The maximum number of event must be greater than zero */
	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
		return -EINVAL;

	/* Verify that the area passed by the user is writeable */
	if (!access_ok(events, maxevents * sizeof(struct epoll_event)))
		return -EFAULT;

	/* Get the "struct file *" for the eventpoll file */
	f = fdget(epfd);
	if (!f.file)
		return -EBADF;

	/*
	 * We have to check that the file structure underneath the fd
	 * the user passed to us _is_ an eventpoll file.
	 */
	error = -EINVAL;
	if (!is_file_epoll(f.file))
		goto error_fput;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = f.file->private_data;

	/* Time to fish for events ... */
	error = ep_poll(ep, events, maxevents, to);

error_fput:
	fdput(f);
	return error;
}

SYSCALL_DEFINE4(epoll_wait, int