Linux内核分析之（二）操作系统是如何工作的？

     肖勇 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 

 

一、实验步骤：

 （1）使用实验楼的虚拟机打开shell

cd LinuxKernel/linux-3.9.4qemu -kernel arch/x86/boot/bzImage

实验截图如下：

 

 

然后cd mykernel 您可以看到qemu窗口输出的内容的代码mymain.c和myinterrupt.c

如下图：

 mymain.c

 

 

 

myinterrupt.c

 

 

(2)在实验楼中的虚拟机中，用浏览器打开https://github.com/mengning/mykernel ，把代码打包下载下来，然后解压复制到实验（1）中的mykernel文件夹中。

   在shell中进入linux-3.9.4文件夹中，执行make，再执行qemu -kernel arch/x86/boot/bzImage。

实验截图如下：

 

 

 

 

二、代码分析：

 

在实验（2）中，最主要的三个文件是mymain.c，myinterrupt.c，mypcb.h。下面分别分析它们的源代码。

 

（1）mypcb.h

 

/* *  linux/mykernel/mypcb.h * *  Kernel internal PCB types * *  Copyright (C) 2013  Mengning * */#define MAX_TASK_NUM        4#define KERNEL_STACK_SIZE   1024*8/* CPU-specific state of this task */struct Thread {    unsigned longip;    unsigned longsp;};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 longtask_entry;    struct PCB *next;}tPCB;void my_schedule(void);

#define MAX_TASK_NUM        4#define KERNEL_STACK_SIZE   1024*8

宏定义进程的最大数目和堆栈的大小。 

struct Thread {    unsigned longip;    unsigned longsp;};

这里定义了一个结构体，用来存储eip和esp。

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 longtask_entry;    struct PCB *next;}tPCB;

定义了一个PCB的结构体，pid为进程的pid，state表示进程状态，-1表示未执行，0表示正在执行，>0表示执行结束。task_entry为进程的入口地址。同时，这个结构体里，还用struct PCB *next定义了指向下一个PCB结构体的指针。

 

void my_schedule(void);

my_schedule为进程调度函数，是在myinterrupt.c中的函数。

 

 

（2）mymain.c

 

/* *  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;    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];        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)            {                my_need_sched = 0;            my_schedule();        }        printk(KERN_NOTICE "this is process %d +\n",my_current_task->pid);        }         }}

#include "mypcb.h"tPCB task[MAX_TASK_NUM];tPCB * my_current_task = NULL;volatile int my_need_sched = 0;void my_process(void);

在头文件中加入mypcb.h，定义一个名为task的tPCB数组，my_current_task表示当前进程，my_need_sched表示当前进程是否需要调度。

 

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;    task[pid].thread.sp = (unsigned long)&task[pid].stack[KERNEL_STACK_SIZE-1];    task[pid].next = &task[pid];

初始化0进程，0号进程中的各种信息（如pid,进程状态state，task_entry等）都在task[pid]所表示的那个tPCB结构体里。

 

/*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];        task[i].next = task[i-1].next;        task[i-1].next = &task[i];    }

创建更多的进程。因为MAX_TASK_NUM为4（在mypcb.h中已定义），所以，这里实际上是创建了1，2，3这三个进程。

/* 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*/);}  

启动0进程。其中有内嵌汇编代码。这里实际上是把task[pid]所表示的那个tPCB结构体中与堆栈有关的信息（thread.sp，thread.ip）赋值给esp，ebp。

 

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)            {                my_need_sched = 0;            my_schedule();        }        printk(KERN_NOTICE "this is process %d +\n",my_current_task->pid);        }         }}

my_process函数每当i能整除10000000时，就输出当前进程的pid，同时判断是否需要调度，如果需要调度，就调用my_schedule函数。

 

 

（3）myinterrupt.c

 

/* *  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)    {        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 */    {    /* switch to next process */    asm volatile(        "pushl %%ebp\n\t"     /* save ebp */        "movl %%esp,%0\n\t" /* save esp */        "movl %2,%%esp\n\t"     /* restore  esp */        "movl $1f,%1\n\t"       /* save eip */        "pushl %3\n\t"         "ret\n\t"             /* restore  eip */        "1:\t"                  /* next process start here */        "popl %%ebp\n\t"        : "=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    {        next->state = 0;        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;}

#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;

在头文件中引入mypcb.h，同时定义tPCB数组task、my_current_task（当前进程）、my_need_sched（是否需要调度）、time_count（表示时间计数）这几个全局变量。

void my_timer_handler(void){#if 1    if(time_count%1000 == 0 && my_need_sched != 1)    {        printk(KERN_NOTICE ">>>my_timer_handler here<<<\n");        my_need_sched = 1;    }     time_count ++ ;  #endif    return;  }

my_timer_handler是一个时间处理的函数，每当time_count能被1000整除且my_need_sched不为1时，就把my_need_sched赋值为1（1即表示需要调度）。 

 

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 */    {    /* switch to next process */    asm volatile(        "pushl %%ebp\n\t"     /* save ebp */        "movl %%esp,%0\n\t" /* save esp */        "movl %2,%%esp\n\t"     /* restore  esp */        "movl $1f,%1\n\t"       /* save eip */        "pushl %3\n\t"         "ret\n\t"             /* restore  eip */        "1:\t"                  /* next process start here */        "popl %%ebp\n\t"        : "=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    {        next->state = 0;        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;}

my_schedule是进程调度的函数，也是这次实验的代码中最关键、最难理解的部分。当下一进程的状态为正在执行（即next->state == 0）时，就执行“/* switch to next process */”部分的代码，否则就执行else部分的代码。

这部分进程调度的代码，具有保存现场和恢复现场的功能。

"pushl %%ebp\n\t"、     "movl %%esp,%0\n\t" 、  "movl $1f,%1\n\t"   

这几句代码保存了当前进程的ebp、esp、eip信息。

"movl %2,%%esp\n\t"、  "movl %2,%%ebp\n\t" 、  "ret\n\t"    

这几句代码用来恢复下一进程的ebp、esp、eip信息。

 

通过my_schedule函数，就成功地实现了从一个进程到另一个进程的切换，它的切换机理分为两个过程：1）把esp、$1f赋值给prev->thread.sp、prev->thread.ip，以及其他一些代码，成功地保存了当前进程的堆栈信息，实现了现场保护；2）把next->thread.sp赋值给esp，以及"pushl %3\n\t" 、"ret\n\t" 等代码，恢复了下一进程的堆栈信息，实现了现场恢复。

 

三、实验总结

理解Linux操作系统的工作原理的难点在于理解它的进程调度的机制，而进程调度又分为保护现场和恢复现场两个过程。因此，只要理解了保护现场和恢复现场这两个部分的代码，也就不难理解它的进程调度机制了。