套接字之select系统调用

select是IO多路复用的一种方式，用来等待一个列表中的多个描述符的可读可写状态；

 SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
         fd_set __user *, exp, struct timeval __user *, tvp)
 {
     struct timespec64 end_time, *to = NULL;
     struct timeval tv;
     int ret;

     if (tvp) {
         if (copy_from_user(&tv, tvp, sizeof(tv)))
             return -EFAULT;

         to = &end_time;
         if (poll_select_set_timeout(to,
                 tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
                 (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
             return -EINVAL;
     }

     ret = core_sys_select(n, inp, outp, exp, to);
     ret = poll_select_copy_remaining(&end_time, tvp, , ret);

     return ret;
 }

本文主要分析socket的select操作，所以对于select系统调用前面通用的部分，我们只分析其调用关系，如下，可见在do_select函数中，会调用文件操作的poll函数；

  /**
   * select系统调用函数调用关系
   * sys_select
   *   |-->core_sys_select
   *       |-->do_select
   *           |-->f_op->poll 调用文件的poll操作
   */

socket文件操作结构实现如下，我们本文重点分析poll操作，即sock_poll函数；

 /*
  *    Socket files have a set of 'special' operations as well as the generic file ones. These don't appear
  *    in the operation structures but are done directly via the socketcall() multiplexor.
  */
 /* socket文件操作函数 */
 static const struct file_operations socket_file_ops = {
     .owner =    THIS_MODULE,
     .llseek =    no_llseek,
     .read_iter =    sock_read_iter,
     .write_iter =    sock_write_iter,
     .poll =        sock_poll,
     .unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
     .compat_ioctl = compat_sock_ioctl,
 #endif
     .mmap =        sock_mmap,
     .release =    sock_close,
     .fasync =    sock_fasync,
     .sendpage =    sock_sendpage,
     .splice_write = generic_splice_sendpage,
     .splice_read =    sock_splice_read,
 };

sock_poll函数在获取到socket之后，会调用其操作中的poll函数，其中tcp为tcp_poll，udp为udp_poll;

 /* No kernel lock held - perfect */
 static unsigned int sock_poll(struct file *file, poll_table *wait)
 {
     unsigned int busy_flag = ;
     struct socket *sock;

     /*
      *      We can't return errors to poll, so it's either yes or no.
      */
     /* 获取到socket */
     sock = file->private_data;

     if (sk_can_busy_loop(sock->sk)) {
         /* this socket can poll_ll so tell the system call */
         busy_flag = POLL_BUSY_LOOP;

         /* once, only if requested by syscall */
         if (wait && (wait->_key & POLL_BUSY_LOOP))
             sk_busy_loop(sock->sk, );
     }

     /* 执行socket操作中的poll，tcp为tcp_poll，udp为udp_poll */
     return busy_flag | sock->ops->poll(file, sock, wait);
 }

tcp_poll的代码分析会在阅读tcp源码时补充；