LDD3源码分析之poll分析

转载自http://blog.csdn.net/liuhaoyutz/article/details/7400037

作者：刘昊昱

博客：http://blog.csdn.net/liuhaoyutz

编译环境：Ubuntu 10.10

内核版本：2.6.32-38-generic-pae

LDD3源码路径：examples/scull/pipe.c examples/scull/main.c

本文分析LDD3第6章的poll(轮询)操作。要理解驱动程序中poll函数的作用和实现，必须先理解用户空间中poll和select函数的用法。本文与前面的文章介绍的顺序有所不同，首先分析测试程序，以此理解用户空间中的poll和select函数的用法。然后再分析驱动程序怎样对用户空间的poll和select函数提供支持。

一、poll函数的使用

用户态的poll函数用以监测一组文件描述符是否可以执行指定的I/O操作，如果被监测的文件描述符都不能执行指定的I/O操作，则poll函数会阻塞，直到有文件描述符的状态发生变化，可以执行指定的I/O操作才解除阻塞。poll函数还可以指定一个最长阻塞时间，如果时间超时，将直接返回。poll函数的函数原型如下：

int poll(struct pollfd *fds, nfds_t nfds,int timeout);

int poll(struct pollfd *fds, nfds_t nfds, int timeout);

要监测的文件描述符由第一个参数fds指定，它是一个struct pollfd数组，pollfd结构体定义如下：

struct pollfd {
int fd; /* file descriptor */
short events; /* requested events */
short revents; /* returned events */
};

struct pollfd {
    int   fd;         /* file descriptor */
    short events;     /* requested events */
    short revents;    /* returned events */
};

pollfd结构体的第一个成员fd是文件描述符，代表一个打开的文件。第二个成员events是一个输入参数，用于指定poll监测哪些事件(如可读、可写等等)。第三个成员revents是一个输出参数，由内核填充，指示对于文件描述符fd，发生了哪些事件(如可读、可写等等)。

poll函数的第二个参数nfds代表监测的文件描述符的个数，即fds数组的成员个数。

poll函数的第三个参数timeout代表阻塞时间(以毫秒为单位)，如果poll要求监测的事件没有发生，则poll会阻塞最多timeout毫秒。如果timeout设置为负数，则poll会一直阻塞，直到监测的事件发生。

poll函数如果返回一个正数，代表内核返回了状态(保存在pollfd.revents中)的文件描述符的个数。如果poll返回0，表明是因为超时而返回的。如果poll返回-1，表明poll调用出错。

poll函数可以监测哪些状态(由pollfd.events指定)，以及内核可以返回哪些状态(保存在pollfd.revents中)，由下面的宏设定：

POLLIN：There is data to read.

POLLOUT：Writing now will not block.

POLLPRI：There is urgent data to read (e.g., out-of-band data on TCP socket; pseudo-terminal master in packet mode has seen state change in slave).

POLLRDHUP： (since Linux 2.6.17) Stream socket peer closed connection, or shut down writing half of connection. The _GNU_SOURCE feature test macro must be defined in order to obtain this definition.

POLLERR：Error condition (output only).

POLLHUP：Hang up (output only).

POLLNVAL：Invalid request: fd not open (output only).

When compiling with _XOPEN_SOURCE defined, one also has the following, which convey no further information beyond the bits listed above:

POLLRDNORM：Equivalent to POLLIN.

POLLRDBAND：Priority band data can be read (generally unused on Linux).

POLLWRNORM：Equivalent to POLLOUT.

POLLWRBAND：Priority data may be written.

下面我们看一个测试scullpipe设备的poll操作(内核态poll)的测试程序，该程序使用了我们前面介绍的poll函数(用户态poll)。其代码如下：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <linux/poll.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>

int main(int argc,char *argv[])
{
int fd0, fd1, fd2, fd3;
struct pollfd poll_fd[4];
char buf[100];
int retval;

if(argc != 2 || ((strcmp(argv[1],  "read") != 0) && (strcmp(argv[1], "write") != 0)))
{
printf("usage: ./poll_test read|write\n");
return -1;
}

fd0 = open("/dev/scullpipe0", O_RDWR);
if ( fd0 < 0)
{
printf("open scullpipe0 error\n");
return -1;
}

fd1 = open("/dev/scullpipe1", O_RDWR);
if ( fd1 < 0)
{
printf("open scullpipe1 error\n");
return -1;
}

fd2 = open("/dev/scullpipe2", O_RDWR);
if ( fd2 < 0)
{
printf("open scullpipe2 error\n");
return -1;
}

fd3 = open("/dev/scullpipe3", O_RDWR);
if ( fd3 < 0)
{
printf("open scullpipe3 error\n");
return -1;
}

if(strcmp(argv[1], "read") == 0)
{
poll_fd[0].fd = fd0;
poll_fd[1].fd = fd1;
poll_fd[2].fd = fd2;
poll_fd[3].fd = fd3;

poll_fd[0].events = POLLIN | POLLRDNORM;
poll_fd[1].events = POLLIN | POLLRDNORM;
poll_fd[2].events = POLLIN | POLLRDNORM;
poll_fd[3].events = POLLIN | POLLRDNORM;

retval = poll(poll_fd, 4, 10000);
}
else
{
poll_fd[0].fd = fd0;
poll_fd[1].fd = fd1;
poll_fd[2].fd = fd2;
poll_fd[3].fd = fd3;

poll_fd[0].events = POLLOUT | POLLWRNORM;
poll_fd[1].events = POLLOUT | POLLWRNORM;
poll_fd[2].events = POLLOUT | POLLWRNORM;
poll_fd[3].events = POLLOUT | POLLWRNORM;

retval = poll(poll_fd, 4, 10000);
}

if (retval == -1)
{
printf("poll error!\n");
return -1;
}
else if (retval)
{
if(strcmp(argv[1], "read") == 0)
{
if(poll_fd[0].revents & (POLLIN | POLLRDNORM))
{
printf("/dev/scullpipe0 is readable!\n");
memset(buf, 0, 100);
read(fd0, buf, 100);
printf("%s\n", buf);
}

if(poll_fd[1].revents & (POLLIN | POLLRDNORM))
{
printf("/dev/scullpipe1 is readable!\n");
memset(buf, 0, 100);
read(fd1, buf, 100);
printf("%s\n", buf);
}

if(poll_fd[2].revents & (POLLIN | POLLRDNORM))
{
printf("/dev/scullpipe2 is readable!\n");
memset(buf, 0, 100);
read(fd2, buf, 100);
printf("%s\n", buf);
}

if(poll_fd[3].revents & (POLLIN | POLLRDNORM))
{
printf("/dev/scullpipe3 is readable!\n");
memset(buf, 0, 100);
read(fd3, buf, 100);
printf("%s\n", buf);
}
}
else
{
if(poll_fd[0].revents & (POLLOUT | POLLWRNORM))
{
printf("/dev/scullpipe0 is writable!\n");
}

if(poll_fd[1].revents & (POLLOUT | POLLWRNORM))
{
printf("/dev/scullpipe1 is writable!\n");
}

if(poll_fd[2].revents & (POLLOUT | POLLWRNORM))
{
printf("/dev/scullpipe2 is writable!\n");
}

if(poll_fd[3].revents & (POLLOUT | POLLWRNORM))
{
printf("/dev/scullpipe3 is writable!\n");
}
}
}
else
{
if(strcmp(argv[1],  "read") == 0)
{
printf("No data within ten seconds.\n");
}
else
{
printf("Can not write within ten seconds.\n");
}
}

return 0;
}

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <linux/poll.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>

int main(int argc, char *argv[])
{
    int fd0, fd1, fd2, fd3;
    struct pollfd poll_fd[4];
    char buf[100];
    int retval;

    if(argc != 2 || ((strcmp(argv[1], "read") != 0) && (strcmp(argv[1], "write") != 0)))
    {
        printf("usage: ./poll_test read|write\n");
        return -1;
    }

    fd0 = open("/dev/scullpipe0", O_RDWR);
    if ( fd0 < 0)
    {
        printf("open scullpipe0 error\n");
        return -1;
    }
    
    fd1 = open("/dev/scullpipe1", O_RDWR);
    if ( fd1 < 0)
    {
        printf("open scullpipe1 error\n");
        return -1;
    }
    
    fd2 = open("/dev/scullpipe2", O_RDWR);
    if ( fd2 < 0)
    {
        printf("open scullpipe2 error\n");
        return -1;
    }
    
    fd3 = open("/dev/scullpipe3", O_RDWR);
    if ( fd3 < 0)
    {
        printf("open scullpipe3 error\n");
        return -1;
    }

    if(strcmp(argv[1], "read") == 0)
    {
        poll_fd[0].fd = fd0;
        poll_fd[1].fd = fd1;
        poll_fd[2].fd = fd2;
        poll_fd[3].fd = fd3;

        poll_fd[0].events = POLLIN | POLLRDNORM;
        poll_fd[1].events = POLLIN | POLLRDNORM;
        poll_fd[2].events = POLLIN | POLLRDNORM;
        poll_fd[3].events = POLLIN | POLLRDNORM;

        retval = poll(poll_fd, 4, 10000);
    }
    else
    {
        poll_fd[0].fd = fd0;
        poll_fd[1].fd = fd1;
        poll_fd[2].fd = fd2;
        poll_fd[3].fd = fd3;

        poll_fd[0].events = POLLOUT | POLLWRNORM;
        poll_fd[1].events = POLLOUT | POLLWRNORM;
        poll_fd[2].events = POLLOUT | POLLWRNORM;
        poll_fd[3].events = POLLOUT | POLLWRNORM;
        
        retval = poll(poll_fd, 4, 10000);
    }

    if (retval == -1)
    {
        printf("poll error!\n");
        return -1;
    }
    else if (retval)
    {
        if(strcmp(argv[1], "read") == 0)
        {
            if(poll_fd[0].revents & (POLLIN | POLLRDNORM))
            {
                printf("/dev/scullpipe0 is readable!\n");
                memset(buf, 0, 100);
                read(fd0, buf, 100);
                printf("%s\n", buf);
            }

            if(poll_fd[1].revents & (POLLIN | POLLRDNORM))
            {
                printf("/dev/scullpipe1 is readable!\n");
                memset(buf, 0, 100);
                read(fd1, buf, 100);
                printf("%s\n", buf);
            }

            if(poll_fd[2].revents & (POLLIN | POLLRDNORM))
            {
                printf("/dev/scullpipe2 is readable!\n");
                memset(buf, 0, 100);
                read(fd2, buf, 100);
                printf("%s\n", buf);
            }

            if(poll_fd[3].revents & (POLLIN | POLLRDNORM))
            {
                printf("/dev/scullpipe3 is readable!\n");
                memset(buf, 0, 100);
                read(fd3, buf, 100);
                printf("%s\n", buf);
            }
        }
        else
        {
            if(poll_fd[0].revents & (POLLOUT | POLLWRNORM))
            {
                printf("/dev/scullpipe0 is writable!\n");
            }

            if(poll_fd[1].revents & (POLLOUT | POLLWRNORM))
            {
                printf("/dev/scullpipe1 is writable!\n");
            }

            if(poll_fd[2].revents & (POLLOUT | POLLWRNORM))
            {
                printf("/dev/scullpipe2 is writable!\n");
            }

            if(poll_fd[3].revents & (POLLOUT | POLLWRNORM))
            {
                printf("/dev/scullpipe3 is writable!\n");
            }
        }
    }
    else
    {
        if(strcmp(argv[1], "read") == 0)
        {
            printf("No data within ten seconds.\n");
        }
        else
        {
            printf("Can not write within ten seconds.\n");
        }
    }

    return 0;
}

测试过程如下图所示：

从上图可以看出，scullpipe0 - scullpipe3都是可写的。但是因为没有向其中写入任何内容，所以读的时候会阻塞住，因为测试程序设置最长阻塞时间为10秒，所以10秒后解除阻塞退出，并打印”No data within ten seconds.”。

下面再次测试读操作，因为设备中没有内容，还是阻塞住，但是在10秒钟内，从另外一个终端向/dev/scullpipe2写入数据，这里是写入字符串”hello”，可以看到，写入数据后，测试程序解除阻塞，并打印”/dev/scullpipe2 is readable!”和”hello”字符串，这个过程如下图所示：

二、select函数的使用

select函数的作用与poll函数类似，也是监测一组文件描述符是否准备好执行指定的I/O操作。如果没有任何一个文件描述符可以完成指定的操作，select函数会阻塞住。select函数可以指定一个最长阻塞时间，如果超时，则直接返回。

select函数的函数原型如下：

int select(int nfds, fd_set *readfds, fd_set *writefds,
fd_set *exceptfds, struct timeval *timeout);

int select(int nfds, fd_set *readfds, fd_set *writefds,
                  fd_set *exceptfds, struct timeval *timeout);

select通过三个独立的文件描述符集(fd_set)readfds，writefds，exceptfds指示监测哪些文件描述符，其中readfds中的文件描述符监测是否可进行非阻塞的读操作。writefds数组中的文件描述符监测是否可进行非阻塞的写操作。exceptfds数组中的文件描述符监测是否有异常(exceptions)。

select的第一个参数nfds是三个文件描述符集readfds、writefds、exceptfds中最大文件描述符值加1。

select的最后一个参数timeout代表最长阻塞时间。

select函数返回满足指定I/O要求的文件描述符的个数，如果是超时退出的，select函数返回0。如果出错，select函数返回-1。

有四个宏用来操作文件描述符集：

void FD_ZERO(fd_set *set); 清空一个文件描述符集。

void FD_SET(int fd, fd_set *set);将一个文件描述符fd加入到指定的文件描述符集set中。

void FD_CLR(int fd, fd_set *set);将一个文件描述符fd从指定的文件描述符集set中删除。

int FD_ISSET(int fd, fd_set *set);测试文件描述符fd是否在指定的文件描述符集set中。

下面我们看使用select函数实现的测试驱动中poll操作的测试程序，其代码如下：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>

int main(int argc,char *argv[])
{
fd_set rfds, wfds;
int fd0, fd1, fd2, fd3;
char buf[100];
int retval;

/* Wait up to ten seconds. */
struct timeval tv;
tv.tv_sec = 10;
tv.tv_usec = 0;

if(argc != 2 || ((strcmp(argv[1],  "read") != 0) && (strcmp(argv[1], "write") != 0)))
{
printf("usage: ./select_test read|write\n");
return -1;
}

fd0 = open("/dev/scullpipe0", O_RDWR);
if ( fd0 < 0)
{
printf("open scullpipe0 error\n");
return -1;
}

fd1 = open("/dev/scullpipe1", O_RDWR);
if ( fd1 < 0)
{
printf("open scullpipe1 error\n");
return -1;
}

fd2 = open("/dev/scullpipe2", O_RDWR);
if ( fd2 < 0)
{
printf("open scullpipe2 error\n");
return -1;
}

fd3 = open("/dev/scullpipe3", O_RDWR);
if ( fd3 < 0)
{
printf("open scullpipe3 error\n");
return -1;
}

if(strcmp(argv[1], "read") == 0)
{
FD_ZERO(&rfds);
FD_SET(fd0, &rfds);
FD_SET(fd1, &rfds);
FD_SET(fd2, &rfds);
FD_SET(fd3, &rfds);
retval = select(fd3 + 1, &rfds, NULL, NULL, &tv);
}
else
{
FD_ZERO(&wfds);
FD_SET(fd0, &wfds);
FD_SET(fd1, &wfds);
FD_SET(fd2, &wfds);
FD_SET(fd3, &wfds);
retval = select(fd3 + 1, NULL, &wfds, NULL, &tv);
}

if (retval == -1)
{
printf("select error!\n");
return -1;
}
else if (retval)
{
if(strcmp(argv[1], "read") == 0)
{
if(FD_ISSET(fd0, &rfds))
{
printf("/dev/scullpipe0 is readable!\n");
memset(buf, 0, 100);
read(fd0, buf, 100);
printf("%s\n", buf);
}

if(FD_ISSET(fd1, &rfds))
{
printf("/dev/scullpipe1 is readable!\n");
memset(buf, 0, 100);
read(fd1, buf, 100);
printf("%s\n", buf);
}

if(FD_ISSET(fd2, &rfds))
{
printf("/dev/scullpipe2 is readable!\n");
memset(buf, 0, 100);
read(fd2, buf, 100);
printf("%s\n", buf);
}

if(FD_ISSET(fd3, &rfds))
{
printf("/dev/scullpipe3 is readable!\n");
memset(buf, 0, 100);
read(fd3, buf, 100);
printf("%s\n", buf);
}
}
else
{
if(FD_ISSET(fd0, &wfds))
{
printf("/dev/scullpipe0 is writable!\n");
}

if(FD_ISSET(fd1, &wfds))
{
printf("/dev/scullpipe1 is writable!\n");
}

if(FD_ISSET(fd2, &wfds))
{
printf("/dev/scullpipe2 is writable!\n");
}

if(FD_ISSET(fd3, &wfds))
{
printf("/dev/scullpipe3 is writable!\n");
}
}
}
else
{
if(strcmp(argv[1],  "read") == 0)
{
printf("No data within ten seconds.\n");
}
else
{
printf("Can not write within ten seconds.\n");
}
}

return 0;
}

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>

int main(int argc, char *argv[])
{
    fd_set rfds, wfds;
    int fd0, fd1, fd2, fd3;
    char buf[100];
    int retval;    

    /* Wait up to ten seconds. */
    struct timeval tv;
    tv.tv_sec = 10;
    tv.tv_usec = 0;

    if(argc != 2 || ((strcmp(argv[1], "read") != 0) && (strcmp(argv[1], "write") != 0)))
    {
        printf("usage: ./select_test read|write\n");
        return -1;
    }

    fd0 = open("/dev/scullpipe0", O_RDWR);
    if ( fd0 < 0)
    {
        printf("open scullpipe0 error\n");
        return -1;
    }
    
    fd1 = open("/dev/scullpipe1", O_RDWR);
    if ( fd1 < 0)
    {
        printf("open scullpipe1 error\n");
        return -1;
    }
    
    fd2 = open("/dev/scullpipe2", O_RDWR);
    if ( fd2 < 0)
    {
        printf("open scullpipe2 error\n");
        return -1;
    }
    
    fd3 = open("/dev/scullpipe3", O_RDWR);
    if ( fd3 < 0)
    {
        printf("open scullpipe3 error\n");
        return -1;
    }

    if(strcmp(argv[1], "read") == 0)
    {
        FD_ZERO(&rfds);
        FD_SET(fd0, &rfds);
        FD_SET(fd1, &rfds);
        FD_SET(fd2, &rfds);
        FD_SET(fd3, &rfds);
        retval = select(fd3 + 1, &rfds, NULL, NULL, &tv);
    }
    else
    {
        FD_ZERO(&wfds);
        FD_SET(fd0, &wfds);
        FD_SET(fd1, &wfds);
        FD_SET(fd2, &wfds);
        FD_SET(fd3, &wfds);
        retval = select(fd3 + 1, NULL, &wfds, NULL, &tv);
    }

    if (retval == -1)
    {
        printf("select error!\n");
        return -1;
    }
    else if (retval)
    {
        if(strcmp(argv[1], "read") == 0)
        {
            if(FD_ISSET(fd0, &rfds))
            {
                printf("/dev/scullpipe0 is readable!\n");
                memset(buf, 0, 100);
                read(fd0, buf, 100);
                printf("%s\n", buf);
            }

            if(FD_ISSET(fd1, &rfds))
            {
                printf("/dev/scullpipe1 is readable!\n");
                memset(buf, 0, 100);
                read(fd1, buf, 100);
                printf("%s\n", buf);
            }

            if(FD_ISSET(fd2, &rfds))
            {
                printf("/dev/scullpipe2 is readable!\n");
                memset(buf, 0, 100);
                read(fd2, buf, 100);
                printf("%s\n", buf);
            }

            if(FD_ISSET(fd3, &rfds))
            {
                printf("/dev/scullpipe3 is readable!\n");
                memset(buf, 0, 100);
                read(fd3, buf, 100);
                printf("%s\n", buf);
            }
        }
        else
        {
            if(FD_ISSET(fd0, &wfds))
            {
                printf("/dev/scullpipe0 is writable!\n");
            }

            if(FD_ISSET(fd1, &wfds))
            {
                printf("/dev/scullpipe1 is writable!\n");
            }

            if(FD_ISSET(fd2, &wfds))
            {
                printf("/dev/scullpipe2 is writable!\n");
            }

            if(FD_ISSET(fd3, &wfds))
            {
                printf("/dev/scullpipe3 is writable!\n");
            }
        }
    }
    else
    {
        if(strcmp(argv[1], "read") == 0)
        {
            printf("No data within ten seconds.\n");
        }
        else
        {
            printf("Can not write within ten seconds.\n");
        }
    }

    return 0;
}

测试过程如下图所示：

从上图可以看出，scullpipe0 - scullpipe3都是可写的。但是因为没有向其中写入任何内容，所以读的时候会阻塞住，因为测试程序设置最长阻塞时间为10秒，所以10秒后解除阻塞退出，并打印”No data within ten seconds.”。

下面再次测试读操作，因为设备中没有内容，还是阻塞住，但是在10秒钟内，从另外一个终端向/dev/scullpipe2写入数据，这里是写入字符串”hello”，可以看到，写入数据后，测试程序解除阻塞，并打印”/dev/scullpipe2 is readable!”和”hello”字符串，这个过程如下图所示：

三、驱动程序中poll操作的实现

用户空间的poll和select函数，最终都会调用驱动程序中的poll函数，其函数原型如下：

unsigned int (*poll) (struct file *filp, poll_table *wait);

unsigned int (*poll) (struct file *filp, poll_table *wait);

poll函数应该实现两个功能：

一是把能标志轮询状态变化的等待队列加入到poll_table中，这通过调用poll_wait函数实现。

二是返回指示能进行的I/O操作的标志位。

poll函数的第二个参数poll_table，是内核中用来实现poll，select系统调用的结构体，对于驱动开发者来说，不必关心其具体内容，可以把poll_table看成是不透明的结构体，只要拿过来使用就可以了。驱动程序通过poll_wait函数，把能够唤醒进程，改变轮询状态的等待队列加入到poll_table中。该函数定义如下：

void poll_wait (struct file *, wait_queue_head_t *, poll_table *);

void poll_wait (struct file *, wait_queue_head_t *, poll_table *);

对于poll函数的第二个功能，返回的标志位与用户空间相对应，最常用的标志位是POLLIN | POLLRDNORM和POLLOUT | POLLWRNORM，分别标志可进行非阻塞的读和写操作。

下面看scullpipe设备对poll操作的实现，其内容其实非常简单：

228static unsigned int scull_p_poll(struct file *filp, poll_table *wait)
229{
230 struct scull_pipe *dev = filp->private_data;
231 unsigned int mask = 0;
232
233 /*
234 * The buffer is circular; it is considered full
235 * if "wp" is right behind "rp" and empty if the
236 * two are equal.
237 */
238 down(&dev->sem);
239 poll_wait(filp, &dev->inq, wait);
240 poll_wait(filp, &dev->outq, wait);
241 if (dev->rp != dev->wp)
242 mask |= POLLIN | POLLRDNORM; /* readable */
243 if (spacefree(dev))
244 mask |= POLLOUT | POLLWRNORM; /* writable */
245 up(&dev->sem);
246 return mask;
247}

228static unsigned int scull_p_poll(struct file *filp, poll_table *wait)
229{
230    struct scull_pipe *dev = filp->private_data;
231    unsigned int mask = 0;
232
233    /*
234     * The buffer is circular; it is considered full
235     * if "wp" is right behind "rp" and empty if the
236     * two are equal.
237     */
238    down(&dev->sem);
239    poll_wait(filp, &dev->inq,  wait);
240    poll_wait(filp, &dev->outq, wait);
241    if (dev->rp != dev->wp)
242        mask |= POLLIN | POLLRDNORM;    /* readable */
243    if (spacefree(dev))
244        mask |= POLLOUT | POLLWRNORM;   /* writable */
245    up(&dev->sem);
246    return mask;
247}

第239行，调用poll_wait函数将读等待队列加入到poll_table中。

第240行，调用poll_wait函数将写等待队列加入到poll_table中。

241 - 242行，如果有内容可读，设置可读标志位。

243 - 244行，如果有空间可写，设置可写标志位。

246行，将标志位返回。

驱动程序中的poll函数很简单，那么内核是怎么实现poll和select系统调用的呢？当用户空间程序调用poll和select函数时，内核会调用由用户程序指定的全部文件的poll方法，并向它们传递同一个poll_table结构。poll_table结构其实是一个生成”实际数据结构”的函数(名为poll_queue_proc)的封装，这个函数poll_queue_proc，不同的应用场景，内核有不同的实现，这里我们不仔细研究对应的函数。对于poll和select系统调用来说，这个”实际数据结构”是一个包含poll_table_entry结构的内存页链表。这里提到的相关数据结构在linux-2.6.32-38源码中，定义在include/linux/poll.h文件中，代码如下所示：

30/*
31 * structures and helpers for f_op->poll implementations
32 */
33typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *,struct poll_table_struct *);
34
35typedef struct poll_table_struct {
36 poll_queue_proc qproc;
37 unsigned long key;
38} poll_table;
39
40static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
41{
42 if (p && wait_address)
43 p->qproc(filp, wait_address, p);
44}
45
46static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
47{
48 pt->qproc = qproc;
49 pt->key = ~0UL; /* all events enabled */
50}
51
52struct poll_table_entry {
53 struct file *filp;
54 unsigned long key;
55 wait_queue_t wait;
56 wait_queue_head_t *wait_address;
57};

 30/*
 31 * structures and helpers for f_op->poll implementations
 32 */
 33typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);
 34
 35typedef struct poll_table_struct {
 36    poll_queue_proc qproc;
 37    unsigned long key;
 38} poll_table;
 39
 40static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
 41{
 42    if (p && wait_address)
 43        p->qproc(filp, wait_address, p);
 44}
 45
 46static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 47{
 48    pt->qproc = qproc;
 49    pt->key   = ~0UL; /* all events enabled */
 50}
 51
 52struct poll_table_entry {
 53    struct file *filp;
 54    unsigned long key;
 55    wait_queue_t wait;
 56    wait_queue_head_t *wait_address;
 57};

poll操作我们就分析完了，内核要求驱动程序做的事并不多，但是我们在学习时，要把poll操作和前面介绍的阻塞型read/write函数以及scullpipe设备的等待队列等结合起来考虑，因为scullpipe设备是一个完整的程序模块。