Linux 用户线程切换分析

Linux内核利用esp ebp实现用户栈的切换,并通过eip的跳转来实现用户级线程的切换,简单分析如下
首先定义mypcb.h

#define MAX_TASK_NUM        4
#define KERNEL_STACK_SIZE   1024*8

/* CPU-specific state of this task */
struct Thread {
    unsigned long		ip;
    unsigned long		sp;
};

typedef struct PCB{
    int pid;
    volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
    char stack[KERNEL_STACK_SIZE];
    /* CPU-specific state of this task */
    struct Thread thread;
    unsigned long	task_entry;
    struct PCB *next;
}tPCB;

void my_schedule(void);



 

mymain.c中 __init my_start_kernel函数用来初始化我们的第0号线程,并fork了1 2 3号线程,void my_process(void)函数用来实现线程的调度工作

/*
 *  linux/mykernel/mymain.c
 *
 *  Kernel internal my_start_kernel
 *
 *  Copyright (C) 2013  Mengning
 *
 */
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/tty.h>
#include <linux/vmalloc.h>


#include "mypcb.h"

tPCB task[MAX_TASK_NUM];
tPCB * my_current_task = NULL;
volatile int my_need_sched = 0;

void my_process(void);


void __init my_start_kernel(void)
{
    int pid = 0;
    int i;
    /* Initialize process 0*/
    task[pid].pid = pid;
    task[pid].state = 0;/* -1 unrunnable, 0 runnable, >0 stopped */
    task[pid].task_entry = task[pid].thread.ip = (unsigned long)my_process;/* set entry */
    task[pid].thread.sp = (unsigned long)&task[pid].stack[KERNEL_STACK_SIZE-1];
    task[pid].next = &task[pid];
    /*fork more process */
    for(i=1;i<MAX_TASK_NUM;i++)
    {
        memcpy(&task[i],&task[0],sizeof(tPCB));
        task[i].pid = i;
        task[i].state = -1;
        task[i].thread.sp = (unsigned long)&task[i].stack[KERNEL_STACK_SIZE-1];
        /* 循环链表,将0 1 2 3线程连接起来 */
        task[i].next = task[i-1].next;
        task[i-1].next = &task[i];
    }
    /* start process 0 by task[0] */
    pid = 0;
    my_current_task = &task[pid];
	asm volatile(
    	"movl %1,%%esp\n\t" 	/* set task[pid].thread.sp to esp */
    	"pushl %1\n\t" 	        /* push ebp */
    	"pushl %0\n\t" 	        /* push task[pid].thread.ip */
    	"ret\n\t" 	            /* pop task[pid].thread.ip to eip */
    	"popl %%ebp\n\t"
    	: 
    	: "c" (task[pid].thread.ip),"d" (task[pid].thread.sp)	/* input c or d mean %ecx/%edx*/
	);                                                                                                                                                void my_process(void)
{
    int i = 0;
    while(1)
    {
        i++;
        if(i%10000000 == 0)
        {
            printk(KERN_NOTICE "this is process %d -\n",my_current_task->pid);
            if(my_need_sched == 1) /* need schedule */
            {
                my_need_sched = 0;
        <span style="white-space:pre">	</span>    my_schedule();
        <span style="white-space:pre">	</span>}
        <span style="white-space:pre">	</span>printk(KERN_NOTICE "this is process %d +\n",my_current_task->pid);
        }     
    }
}
关键的myinterrupt.c文件,我们定义了一个时钟中段,每1000毫秒发出一个时钟中段并根据my_need_sched来决定是否需要进行线程的切换,关键函数在于void my_schedule(void),esp ebp的切换详见注释部分</span>
/*
 *  linux/mykernel/myinterrupt.c
 *
 *  Kernel internal my_timer_handler
 *
 *  Copyright (C) 2013  Mengning
 *
 */
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/tty.h>
#include <linux/vmalloc.h>

#include "mypcb.h"

extern tPCB task[MAX_TASK_NUM];
extern tPCB * my_current_task;
extern volatile int my_need_sched;
volatile int time_count = 0;

/*
 * Called by timer interrupt.
 * it runs in the name of current running process,
 * so it use kernel stack of current running process
 */
void my_timer_handler(void)
{
#if 1
    if(time_count%1000 == 0 && my_need_sched != 1)/* 每1000毫秒发出一个时钟中段并根据my_need_sched来决定是否需要进行线程的切换 */
    {
        printk(KERN_NOTICE ">>>my_timer_handler here<<<\n");
        my_need_sched = 1;
    } 
    time_count ++ ;  
#endif
    return;  	
}

void my_schedule(void)
{
    tPCB * next;
    tPCB * prev;

    if(my_current_task == NULL 
        || my_current_task->next == NULL)
    {
    	return;
    }
    printk(KERN_NOTICE ">>>my_schedule<<<\n");
    /* schedule */
    next = my_current_task->next;
    prev = my_current_task;
    if(next->state == 0)/* -1 unrunnable, 0 runnable, >0 stopped */
    {
    	/*下个线程的状态为runable,当前线程让出cpu,进行线程的切换 */
    	asm volatile(	
        	"pushl %%ebp\n\t" 	    /* save current thread ebp */
        	"movl %%esp,%0\n\t" 	/* save current thread esp */
        	"movl %2,%%esp\n\t"     /* restore next thread esp ,恢复下个线程的栈状态*/
        	"movl $1f,%1\n\t"       /* $1f就是指线程标号1:的代码在内存中存储的地址 */	
        	"pushl %3\n\t"          /* save next eip */ 
        	"ret\n\t" 	            /* restore  eip,<span style="font-family: Arial, Helvetica, sans-serif;">配合上条指令,</span>模拟了1个函数的返回动作,把eip弹出,实现线程的切换 */
        	"1:\t"                  /* next process start here */
        	"popl %%ebp\n\t"        /*next线程时间片轮转完毕,现在轮到我执行了,恢复我的栈*/
        	: "=m" (prev->thread.sp),"=m" (prev->thread.ip)
        	: "m" (next->thread.sp),"m" (next->thread.ip)
    	); 
    	my_current_task = next; 
    	printk(KERN_NOTICE ">>>switch %d to %d<<<\n",prev->pid,next->pid);   	
    }
    else
    {
        /*设置下个线程状态为runable*/
        next->state = 0;
        /*当前task指向下个线程*/
        my_current_task = next;
        printk(KERN_NOTICE ">>>switch %d to %d<<<\n",prev->pid,next->pid);
    	/* switch to new process */
    	asm volatile(	
        	"pushl %%ebp\n\t" 	    /* save ebp */
        	"movl %%esp,%0\n\t" 	/* save esp */
        	"movl %2,%%esp\n\t"     /* restore  esp */
        	"movl %2,%%ebp\n\t"     /* restore  ebp */
        	"movl $1f,%1\n\t"       /* save eip */	
        	"pushl %3\n\t" 
        	"ret\n\t" 	            /* restore  eip */
        	: "=m" (prev->thread.sp),"=m" (prev->thread.ip)
        	: "m" (next->thread.sp),"m" (next->thread.ip)
    	);          
    }   
    return;	
}


codeyangjun 原创作品转载请注明出处 《Linux内核分析》MOOC课程http://mooc.study.163.com/course/USTC-1000029000
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值