Linux-Select上层调用到内核实现流程

曾经终败给现在 2023-01-15 08:03 68阅读 0赞

### Linux-Select上层调用到底层实现过程 ###

*  1、select简介
 *  2、调用逻辑
 *   *  2.1、应用层调用select函数
     *  2.2、调用系统的sys\_select函数
     *  2.3、系统的sys\_select调用do\_select

# 1、select简介 #

文章中的内核文件基于2.6.2版本内核。

头文件：

#include <sys/select.h>

select应用层的使用：[select简单使用及其Demo][select_Demo]

# 2、调用逻辑 #

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NTMwOTkxNg_size_16_color_FFFFFF_t_70]

## 2.1、应用层调用select函数 ##

int select (int maxfd + 1,fd_set *readset,fd_set *writeset,
                fd_set *exceptset,const struct timeval * timeout);

## 2.2、调用系统的sys\_select函数 ##

以下代码为内核2.6.2内核源码

asmlinkage long
    sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp)
    { 
    	fd_set_bits fds;
    	char *bits;
    	long timeout;
    	int ret, size, max_fdset;
    
    	timeout = MAX_SCHEDULE_TIMEOUT;
    	if (tvp) { 
    		time_t sec, usec;
    
    		if ((ret = verify_area(VERIFY_READ, tvp, sizeof(*tvp)))
    		    || (ret = __get_user(sec, &tvp->tv_sec))
    		    || (ret = __get_user(usec, &tvp->tv_usec)))
    			goto out_nofds;
    
    		ret = -EINVAL;
    		if (sec < 0 || usec < 0)
    			goto out_nofds;
    
    		if ((unsigned long) sec < MAX_SELECT_SECONDS) { 
    			timeout = ROUND_UP(usec, 1000000/HZ);
    			timeout += sec * (unsigned long) HZ;
    		}
    	}
    
    	ret = -EINVAL;
    	if (n < 0)
    		goto out_nofds;
    
    	/* max_fdset can increase, so grab it once to avoid race */
    	max_fdset = current->files->max_fdset;
    	if (n > max_fdset)
    		n = max_fdset;
    
    	/* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */
    	ret = -ENOMEM;
    	size = FDS_BYTES(n);
    	bits = select_bits_alloc(size);
    	if (!bits)
    		goto out_nofds;
    	fds.in      = (unsigned long *)  bits;
    	fds.out     = (unsigned long *) (bits +   size);
    	fds.ex      = (unsigned long *) (bits + 2*size);
    	fds.res_in  = (unsigned long *) (bits + 3*size);
    	fds.res_out = (unsigned long *) (bits + 4*size);
    	fds.res_ex  = (unsigned long *) (bits + 5*size);
    
    	if ((ret = get_fd_set(n, inp, fds.in)) ||
    	    (ret = get_fd_set(n, outp, fds.out)) ||
    	    (ret = get_fd_set(n, exp, fds.ex)))
    		goto out;
    	zero_fd_set(n, fds.res_in);
    	zero_fd_set(n, fds.res_out);
    	zero_fd_set(n, fds.res_ex);
    
    	ret = do_select(n, &fds, &timeout);
    
    	if (tvp && !(current->personality & STICKY_TIMEOUTS)) { 
    		time_t sec = 0, usec = 0;
    		if (timeout) { 
    			sec = timeout / HZ;
    			usec = timeout % HZ;
    			usec *= (1000000/HZ);
    		}
    		put_user(sec, &tvp->tv_sec);
    		put_user(usec, &tvp->tv_usec);
    	}
    
    	if (ret < 0)
    		goto out;
    	if (!ret) { 
    		ret = -ERESTARTNOHAND;
    		if (signal_pending(current))
    			goto out;
    		ret = 0;
    	}
    
    	set_fd_set(n, inp, fds.res_in);
    	set_fd_set(n, outp, fds.res_out);
    	set_fd_set(n, exp, fds.res_ex);
    
    out:
    	select_bits_free(bits, size);
    out_nofds:
    	return ret;
    }

在以上代码中最主要的功能是调用do\_select(n, &fds, &timeout)

## 2.3、系统的sys\_select调用do\_select ##

int do_select(int n, fd_set_bits *fds, long *timeout)
    { 
    	struct poll_wqueues table;
    	poll_table *wait;
    	int retval, i;
    	long __timeout = *timeout;
    
     	spin_lock(&current->files->file_lock);
    	retval = max_select_fd(n, fds);
    	spin_unlock(&current->files->file_lock);
    
    	if (retval < 0)
    		return retval;
    	n = retval;
    
    	poll_initwait(&table);
    	wait = &table.pt;
    	if (!__timeout)
    		wait = NULL;
    	retval = 0;
    	for (;;) { 
    		unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
    
    		set_current_state(TASK_INTERRUPTIBLE);
    
    		inp = fds->in; outp = fds->out; exp = fds->ex;
    		rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
    
    		for (i = 0; i < n; ++rinp, ++routp, ++rexp) { 
    			unsigned long in, out, ex, all_bits, bit = 1, mask, j;
    			unsigned long res_in = 0, res_out = 0, res_ex = 0;
    			struct file_operations *f_op = NULL;
    			struct file *file = NULL;
    
    			in = *inp++; out = *outp++; ex = *exp++;
    			all_bits = in | out | ex;
    			if (all_bits == 0) { 
    				i += __NFDBITS;
    				continue;
    			}
    
    			for (j = 0; j < __NFDBITS; ++j, ++i, bit <<= 1) { 
    				if (i >= n)
    					break;
    				if (!(bit & all_bits))
    					continue;
    				file = fget(i);
    				if (file) { 
    					f_op = file->f_op;
    					mask = DEFAULT_POLLMASK;
    					if (f_op && f_op->poll)
    						mask = (*f_op->poll)(file, retval ? NULL : wait);
    					fput(file);
    					if ((mask & POLLIN_SET) && (in & bit)) { 
    						res_in |= bit;
    						retval++;
    					}
    					if ((mask & POLLOUT_SET) && (out & bit)) { 
    						res_out |= bit;
    						retval++;
    					}
    					if ((mask & POLLEX_SET) && (ex & bit)) { 
    						res_ex |= bit;
    						retval++;
    					}
    				}
    			}
    			if (res_in)
    				*rinp = res_in;
    			if (res_out)
    				*routp = res_out;
    			if (res_ex)
    				*rexp = res_ex;
    		}
    		wait = NULL;
    		if (retval || !__timeout || signal_pending(current))
    			break;
    		if(table.error) { 
    			retval = table.error;
    			break;
    		}
    		__timeout = schedule_timeout(__timeout);
    	}
    	__set_current_state(TASK_RUNNING);
    
    	poll_freewait(&table);
    
    	/* * Up-to-date the caller timeout. */
    	*timeout = __timeout;
    	return retval;
    }

从这开始才是真的的select函数的实现。

在do\_select函数中，从第二个参数**fd\_set\_bits \*fds**我们可以发现，我们app层传入的fd\_set \*readset,fd\_set \*writeset,fd\_set \*exceptset这三个参数都整合到了fd\_set\_bits的指针中去了，所以我们在进行监听的时候这三个参数随便填一个就OK了。

之后进入这个函数，首先进行了监听个数（n）和超时时间（timeout）的判断，之后便进入了死循环中。

在这个死循环中我们还有还有一个for循环，在这个for循环中我们发现了我们select传入的第一个参数（监听的最大的FD加一），这也就解释我们为什么要给最大的fd加一的原因了（for循环中给轮询到上限所使用的）。

接着在这死循环中能引起返回的有两种情况：  
①、发生错误时：

if(table.error) { 
    			retval = table.error;
    			break;

这里也就是我们调用select时错误返回的地方。

②、正确返回时：

if (retval || !__timeout || signal_pending(current))
    			break;

在这个if判断中三种情况都能实现do\_select的返回，第一：监听到有句柄有输入输出时的正确返回retval 。第二：超时返回\_\_timeout ，第三：被信号打断导致返回signal\_pending。

[select_Demo]: https://blog.csdn.net/weixin_45309916/article/details/107405356?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522161900807116780262522729%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fblog.%2522%257D&request_id=161900807116780262522729&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_v2~rank_v29-1-107405356.nonecase&utm_term=select
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NTMwOTkxNg_size_16_color_FFFFFF_t_70]: /images/20221022/52e8fc3563f048e0b12961cae18ea3bb.png