网络篇之poll

网络篇之select

struct pollfd {

    int fd; // socket句柄

    short events; // 需要读取的可读，可写状态

    short revents; // 函数返回后，查询到的可读，可写状态

};

// 使用示例

struct pollfd pfd;

pfd.fd = 3;

pfd.events = POLLIN; // 检查socket是否可读

pfd.events = POLLIN|POLLOUT; // 检查socket是否可读或可写

poll(&pfd,1,-1);

与select不同的是，每个socket对应一个pollfd，需要读取的信号放到events中，系统返回的信号放到revents中。这样用户空间调用poll的时候，只需设置一次fd和events，在poll函数返回后，检查revents即可。

如果看了select内核的实现，再看这篇，会觉得简单了好多。

SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
		int, timeout_msecs)
{
	struct timespec64 end_time, *to = NULL;
	int ret;

	if (timeout_msecs >= 0) {
		to = &end_time;
		poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC,
			NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC));
	}

	ret = do_sys_poll(ufds, nfds, to);

	... ...

	return ret;
}

系统调用poll中，将用户空间传入的超时时间转成timespec64格式，调用do_sys_poll。

static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
		struct timespec64 *end_time)
{
	struct poll_wqueues table;
 	int err = -EFAULT, fdcount, len, size;
	/* Allocate small arguments on the stack to save memory and be
	   faster - use long to make sure the buffer is aligned properly
	   on 64 bit archs to avoid unaligned access */
	long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
	struct poll_list *const head = (struct poll_list *)stack_pps;
 	struct poll_list *walk = head;
 	unsigned long todo = nfds;

	if (nfds > rlimit(RLIMIT_NOFILE))
		return -EINVAL;

	// 一次可复制的pollfd的最大数量
	len = min_t(unsigned int, nfds, N_STACK_PPS);
	for (;;) {
		walk->next = NULL;
		walk->len = len;
		if (!len)
			break;

		if (copy_from_user(walk->entries, ufds + nfds-todo,
					sizeof(struct pollfd) * walk->len))
			goto out_fds;

		todo -= walk->len;
		if (!todo)
			break;

		len = min(todo, POLLFD_PER_PAGE); // POLLFD_PER_PAGE表示一个页框，可以保存多少个pollfd
		size = sizeof(struct poll_list) + sizeof(struct pollfd) * len; // 需新申请的内存空间
		walk = walk->next = kmalloc(size, GFP_KERNEL);
		if (!walk) {
			err = -ENOMEM;
			goto out_fds;
		}
	}

	poll_initwait(&table);
	fdcount = do_poll(head, &table, end_time);
	poll_freewait(&table);

	for (walk = head; walk; walk = walk->next) {
		struct pollfd *fds = walk->entries;
		int j;

		for (j = 0; j < walk->len; j++, ufds++)
			if (__put_user(fds[j].revents, &ufds->revents))
				goto out_fds;
  	}

	err = fdcount;
out_fds:
	walk = head->next;
	while (walk) {
		struct poll_list *pos = walk;
		walk = walk->next;
		kfree(pos);
	}

	return err;
}

struct poll_list {

    struct poll_list *next;

    int len;

    struct pollfd entries[0];

};

 poll_list的定义如上所示，在do_sys_poll中，将用户空间的数据，拷贝到以head为链表头的poll_list结构中，然后调用do_poll。

static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
		   struct timespec64 *end_time)
{
	poll_table* pt = &wait->pt;
	ktime_t expire, *to = NULL;
	int timed_out = 0, count = 0;
	u64 slack = 0;
	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
	unsigned long busy_start = 0;

	/* Optimise the no-wait case */
	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
		pt->_qproc = NULL;
		timed_out = 1;
	}

	if (end_time && !timed_out)
		slack = select_estimate_accuracy(end_time);

	for (;;) {
		struct poll_list *walk;
		bool can_busy_loop = false;

		// 遍历每一个poll_list
		for (walk = list; walk != NULL; walk = walk->next) {
			struct pollfd * pfd, * pfd_end;

			pfd = walk->entries;
			pfd_end = pfd + walk->len;

			// 遍历poll_list中的每个pollfd
			for (; pfd != pfd_end; pfd++) {
				/*
				 * Fish for events. If we found one, record it
				 * and kill poll_table->_qproc, so we don't
				 * needlessly register any other waiters after
				 * this. They'll get immediately deregistered
				 * when we break out and return.
				 */
				if (do_pollfd(pfd, pt, &can_busy_loop,
					      busy_flag)) {
					count++;
					pt->_qproc = NULL;
					/* found something, stop busy polling */
					busy_flag = 0;
					can_busy_loop = false;
				}
			}
		}
		/*
		 * All waiters have already been registered, so don't provide
		 * a poll_table->_qproc to them on the next loop iteration.
		 */
		pt->_qproc = NULL;
		if (!count) {
			count = wait->error;
			if (signal_pending(current))
				count = -EINTR;
		}
		if (count || timed_out)
			break;

		/* only if found POLL_BUSY_LOOP sockets && not out of time */
		if (can_busy_loop && !need_resched()) {
			if (!busy_start) {
				busy_start = busy_loop_current_time();
				continue;
			}
			if (!busy_loop_timeout(busy_start))
				continue;
		}
		busy_flag = 0;

		/*
		 * If this is the first loop and we have a timeout
		 * given, then we convert to ktime_t and set the to
		 * pointer to the expiry value.
		 */
		if (end_time && !to) {
			expire = timespec64_to_ktime(*end_time);
			to = &expire;
		}

		if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))
			timed_out = 1;
	}
	return count;
}

内部两层for循环，遍历传入的所有pollfd，调用do_pollfd检查当前的socket是否有用户空间查询的数据，如果有count的值加1。

if (count || timed_out)

    break;

最外层的循环中， 判断读取到数据，或超时时间已到，退出循环，函数返回。

if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))

    timed_out = 1;

 当前没有用户空间查询的数据，则执行进程调度，等待数据的到来。

下面看下do_pollfd：

static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
				     bool *can_busy_poll,
				     unsigned int busy_flag)
{
	unsigned int mask;
	int fd;

	mask = 0;
	fd = pollfd->fd;
	if (fd >= 0) {
		struct fd f = fdget(fd);
		mask = POLLNVAL;
		if (f.file) {
			mask = DEFAULT_POLLMASK;
			if (f.file->f_op->poll) { // sock_poll
				pwait->_key = pollfd->events|POLLERR|POLLHUP;
				pwait->_key |= busy_flag;
				mask = f.file->f_op->poll(f.file, pwait);
				if (mask & busy_flag)
					*can_busy_poll = true;
			}
			/* Mask out unneeded events. */
			mask &= pollfd->events | POLLERR | POLLHUP;
			fdput(f);
		}
	}
	pollfd->revents = mask;

	return mask;
}

sock_poll在介绍select时已经说过了，该函数返回socket所有的可读，可写及其他状态。

mask &= pollfd->events | POLLERR | POLLHUP;

 socket当前状态与用户空间请求的状态(events)做位与操作，获取到的就是用户空间请求的数据，放到了revents，最终返回给用户空间。