基于mykernel 2.0编写一个操作系统内核

1.实验要求

• 按照https://github.com/mengning/mykernel 的说明配置mykernel 2.0，熟悉Linux内核的编译；
• 基于mykernel 2.0编写一个操作系统内核，参照https://github.com/mengning/mykernel提供的范例代码；
• 简要分析操作系统内核核心功能及运行工作机制。

2.实验步骤

（本次实验在Ubuntu 16.0.4环境下进行）

2.1 安装和编译

首先根据 https://github.com/mengning/mykernel 中所说，输入以下命令下载 linux-5.4.34 和 mykernel-2.0_for_linux-5.4.34.patch，打上补丁并编译内核

注意路径可能有所不同

 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
 sudo apt install qemu
 make defconfig
 make -j$(nproc)

之后输入

qemu-system-x86_64 -kernel arch/x86/boot/bzImage

即可运行起内核，运行结果是一个不断循环的打印

 

进入mykernel文件夹下，能看到的C文件就是这两个：mymain.c 和 myinterrupt.c，打开mymain.c，可以看到如下一段代码

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);
            
    }
}

显然，在循环打印中，my_start_kernel here... ...这条消息是由进程运行mymain.c时进行打印的。再打开myinterrupt.c，能够看到如下代码

void my_timer_handler(void)
{
    pr_notice("\n>>>>>>>>>>>>>>>>>my_timer_handler here<<<<<<<<<<<<<<<<<<\n\n");
}

循环打印里的另一段就是由进程执行到此处打印的

mykernel能够周期性的产生时钟中断，中断处理程序就会调用my_timer_handler函数，调用完成后再返回到原来的上下文中（mymain.c的循环处），就会产生交替打印的效果。

 

2.2 完善内核的进程切换部分

 在 https://github.com/mengning/mykernel 中，可以看到 mypcb.h 这一文件，即进程控制块相关。想要完善内核的进程切换，首先需要实现我们自己的进程控制块（此处直接copy的孟宁老师的代码）

#define MAX_TASK_NUM        4
#define KERNEL_STACK_SIZE   1024*2
/* 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 */
    unsigned long 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);

可以看到进程拥有三种状态：unrunnable、runnable和stopped，每个进程都拥有自己的堆栈，并由ip、sp（对应eip寄存器和esp寄存器）进行控制。pcb块间以链表的形式串联起来

 

接下来修改mymain.c

#include 
#include string.h>
#include 
#include 
#include 


#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)
    {
        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;
    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);
        }     
    }
}

新添加的my_start_kernel函数用来执行初始化工作。它初始化了MAX_TASK_NUM个进程控制块，然后内嵌了汇编代码，这段代码会把pid为0的进程的sp和ip写入寄存器

 

完善了mymain.c后，继续完善myinterrupt.c

#include 
#include string.h>
#include 
#include 
#include 

#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(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;
    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;    
}

新增的my_schedule函数是处理进程调度的关键。上文已经说过，pcb块以链表的形式串联起来，my_schedule函数选择进程链表中的下一个就绪进程进行切换。它也内嵌了汇编代码，实现的功能如下：

1. 保存进程rbp寄存器内的值

2. 保存进程rsp寄存器内的值

3. 更新寄存器rsp为next指向的新进程内的sp变量值，此时进行了进程间栈帧的转换

4. 保存原进程rip寄存器内的值

5. 更新寄存器rip为新进程的ip变量值，至此进程调度完毕，切换到了新进程运行

make clean，再make一遍，再次运行时能够看到完善后的效果