基于mykernel 2.0编写一个操作系统内核

一、实验环境配置

1.操作系统环境

阿里云Ubuntu 16.04

2.内核环境配置

按照https://github.com/mengning/mykernel上的内容输入如下命令：

wget https://raw.github.com/mengning/mykernel/master/mykernel-2.0_for_linux-5.4.34.patch
sudo apt install axel
axel -n 20 https://mirrors.edge.kernel.org/pub/linux/kernel/v5.x/linux-5.4.34.tar.xz
xz -d linux-5.4.34.tar.xz
tar -xvf linux-5.4.34.tar
cd linux-5.4.34
patch -p1 < ../mykernel-2.0_for_linux-5.4.34.patch
sudo apt install build-essential libncurses-dev bison flex libssl-dev libelf-dev
make defconfig # Default configuration is based on 'x86_64_defconfig'
make -j$(nproc)
sudo apt install qemu # install QEMU
qemu-system-x86_64 -kernel arch/x86/boot/bzImage

运行结果如下：

 

二、编写操作系统内核

1.内核编写先验知识

首先，进入mykernel目录可以看到qemu窗口输出的内容的代码mymain.c和myinterrupt.c

查看mymain.c和myinterrcupt.c的代码内容：

# mymain.c
void __init my_start_kernel(void)
{
    int i = 0;
    while(1)
    {
        i++;
        if(i%100000 == 0)
            pr_notice("my_start_kernel here  %d \n",i);
            
    }
}

# myinterrupt.c
void my_timer_handler(void)
{
     pr_notice("\n>>>>>>>>>>>>>>>>>my_timer_handler 
     here<<<<<<<<<<<<<<<<<<\n\n");
}

可知mymain.c中为一个while一个死循环，每当计数器i为10000的倍数时打印相应内容，而myinterrupt.c则是由时钟中断触发，触发时会打印相应内容提示时钟中断触发。

我们的任务即为在mymain.c基础上继续写进程描述PCB和进程链表管理等代码，在myinterrupt.c的基础上完成进程切换代码，这样即可完成一个可运行的小OS kernel。

2.编写内核代码

首先，要进行进程切换，需要有一个描述进程的对象，linux中采用进程控制块pcb作为进程实体对象，下面为定义PCB的头文件代码：

/*
 *  linux/mykernel/mypcb.h
 *  Kernel internal PCB types
 */

#define MAX_TASK_NUM        4                //最大task数
#define KERNEL_STACK_SIZE   1024*2    //进程堆栈容量 

/* CPU-specific state of this task */
struct Thread {
    unsigned long        ip;    //进程代码段指针
    unsigned long        sp;   //进程栈顶指针
};

typedef struct PCB{
    int pid;    //进程的id
    volatile long state;    /* 进程状态 -1 unrunnable, 0 runnable, >0 stopped */
    unsigned long stack[KERNEL_STACK_SIZE];  //进程堆栈
    /* CPU-specific state of this task */
    struct Thread thread;
    unsigned long    task_entry;      //进程入口，
    struct PCB *next;    //指向下一个PCB的指针，PCB间用链表连接
}tPCB;

//调度函数
void my_schedule(void);

其次，修改mymain.c

/*
 *  linux/mykernel/mymain.c
 *  Kernel internal my_start_kernel
 */
#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;    //进程是否需要切换的标志

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 */
    //模拟fork新建一个进程并将进程0的PCB内容赋给进程i
    for(i=1;i<MAX_TASK_NUM;i++)
    {
        memcpy(&task[i],&task[0],sizeof(tPCB));
        task[i].pid = i;
        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;
    //进程切换
    my_current_task = &task[pid];
    asm volatile(
        "movq %1,%%rsp\n\t"     /* set task[pid].thread.sp to rsp */
        "pushq %1\n\t"             /* push rbp */
        "pushq %0\n\t"             /* push task[pid].thread.ip */
        "ret\n\t"                 /* pop task[pid].thread.ip to rip */
        : 
        : "c" (task[pid].thread.ip),"d" (task[pid].thread.sp)    /* input c or d mean %ecx/%edx*/
    );
} 

int i = 0;

void my_process(void)
{    
    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);
        }     
    }
}

最后修改myinterrupt.c

/*
 *  linux/mykernel/myinterrupt.c
 *  Kernel internal my_timer_handler
 */

#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)
{
    //计数，每当计数值为1000倍数时将允许进程切换
    if(time_count%1000 == 0 && my_need_sched != 1)
    {
        printk(KERN_NOTICE ">>>my_timer_handler here<<<\n");
        my_need_sched = 1;
    } 
    time_count ++ ;  
    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;

    //若下一个进程state为0则说明下一进程可运行，执行切换操作
    if(next->state == 0)/* -1 unrunnable, 0 runnable, >0 stopped */
    {        
        my_current_task = next; 
        printk(KERN_NOTICE ">>>switch %d to %d<<<\n",prev->pid,next->pid);  
        /* switch to next process */
        asm volatile(    
            "pushq %%rbp\n\t"         /* save rbp of prev */
            "movq %%rsp,%0\n\t"     /* save rsp of prev */
            "movq %2,%%rsp\n\t"     /* restore  rsp of next */
            "movq $1f,%1\n\t"       /* save rip of prev */    
            "pushq %3\n\t" 
            "ret\n\t"                 /* restore  rip of next */
            "1:\t"                  /* next process start here */
            "popq %%rbp\n\t"
            : "=m" (prev->thread.sp),"=m" (prev->thread.ip)
            : "m" (next->thread.sp),"m" (next->thread.ip)
        ); 
    }  
    return;    
}

修改完代码后执行make命令重新编译一次，再次执行qemu-system-x86_64 -kernel arch/x86/boot/bzImage命令可得到如下结果：


三、简要分析操作系统内核核心功能及运行工作机制

首先需要明白的是，操作系统内核先将进程0的PCB块初始化并让其他的进程fork进程0，之后操作系统内核会不断地执行mymain.c中的while(1)死循环,而由while(1)中的代码可知当进程调度标志my_nedd_sched为1后便执行进程调度的相应代码(my_schedule)：

if(my_need_sched == 1)
{
        my_need_sched = 0;
        my_schedule();
 }

而my_need_sched则是在myinterrupt.c中根据时钟中断来置位的:

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

之后再来了解进程调度的相应代码：

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;

    //若下一个进程state为0则说明下一进程可运行，执行切换操作
    if(next->state == 0)/* -1 unrunnable, 0 runnable, >0 stopped */
    {        
        my_current_task = next; 
        printk(KERN_NOTICE ">>>switch %d to %d<<<\n",prev->pid,next->pid);  
        /* switch to next process */
        asm volatile(    
            "pushq %%rbp\n\t"         /* save rbp of prev */
            "movq %%rsp,%0\n\t"     /* save rsp of prev */
            "movq %2,%%rsp\n\t"     /* restore  rsp of next */
            "movq $1f,%1\n\t"       /* save rip of prev */    
            "pushq %3\n\t" 
            "ret\n\t"                 /* restore  rip of next */
            "1:\t"                  /* next process start here */
            "popq %%rbp\n\t"
            : "=m" (prev->thread.sp),"=m" (prev->thread.ip)
            : "m" (next->thread.sp),"m" (next->thread.ip)
        ); 
    }  
    return;    
}

可见此处进程调度是按照进程在链表中的顺序依次进入cpu执行，大致步骤就是先保存前一进程的rbp和rsp，之后将rsp指向新进程的堆栈的sp指针，保存prev进程当前RIP寄存器值到prev->thread.ip(即前一进程的代码段)，这里的$1f解释为24行1：的地址，实际上这是at&t一种语法，然后将新进程的代码指针ip入栈并随后将压⼊栈中的代码指针ip放⼊RIP寄存器，最后将新进程堆栈基地址从堆栈中恢复到RBP寄存器中。以上便是操作系统内核的简单的运行机制。