基于mykernel 2.0编写一个操作系统内核

1. 搭建虚拟的x86-64 CPU实验平台mykernel 2.0

1.1 实验环境

Ubuntu 18.04 LTS

1.2 依次执行下列命令，配置环境

mykernel-2.0_for_linux-5.4.34.patch在本地下载完成后上传到ubuntu上。

 

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   #切换到linux-5.4.34目录下执行
make -j$(nproc)
sudo apt install qemu
qemu-system-x86_64 -kernel arch/x86/boot/bzImage

 执行make defconfig前要切换到linux-5.4.34目录下

执行make -j$(nproc)时花费的时间比较长，执行完的结果如下图所示。

可以看到kernel:arch/x86/boot/bzImage is ready

执行qemu-system-x86_64 -kernel arch/x86/boot/bzImage结果如下图所示。

上图输出部分内容是mymain.c和myinterrupt.c的结果，分别查看两份代码

#mymain.c的代码
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);
    }
}

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

mymain.c文件中，通过计数每隔计100000数之后循环输出my_start_kernel here；myinterrupt.c文件中一直输出>>>>>>>>>>>>>>my_timer_handler here<<<<<<<<<<<。通过上述流程，相信对linux内核的编译有了一定的熟悉，下面开始基于mykernel2.0编写一个操作系统内核。

2.基于mykernel2.0编写一个操作系统内核

 本部分参照https://github.com/mengning/kernel

2.1 修改相关文件

mymain.c文件是内核运行的程序，当前mymain.c的代码一直在执行，同时还有一个中断处理程序的上下文环境，周期性的产生时段中断信号，可以触发myinterrupt.c。

修改mymain.c、myinterrupt.c，添加mypcb.h头文件，过程及代码参考https://github.com/mengning/kernel里的范例。

其中mymain.c在原来的基础上增加了进程管理的代码，mypcb.h文件里定义了PCB的结构，myinterrupt.c文件中定义了进程如何切换，下面看一下mymain.c、myinterrupt.c、mypcb.h三个文件里的代码。

/*
 *  linux/mykernel/mymain.c
 *
 *  Kernel internal my_start_kernel
 *  Change IA32 to x86-64 arch, 2020/4/26
 *
 *  Copyright (C) 2013, 2020  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].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);
        }     
    }
}

/*
 *  linux/mykernel/myinterrupt.c
 *
 *  Kernel internal my_timer_handler
 *  Change IA32 to x86-64 arch, 2020/4/26
 *
 *  Copyright (C) 2013, 2020  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(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;    
}

/*
 *  linux/mykernel/mypcb.h
 *
 *  定义了PCB的结构
 */

#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);

mymain.c文件中定义了全局变量my_need_sched，myinterrupt.c文件中定义了全局变量time_count，两个变量都是volatile变量，保证了编译器不会对代码进行优化，每次直接读取值。myinterrupt.c文件中定义了一个时间片大小为1000，如果时间片轮转完成并且my_need_sched不等于1，则将my_need_sched设为1，触发mymain.c文件中my_process函数工作，又将my_need_sched设为0，触发myinterrupt.c文件中的my_schedule函数，完成进程切换，循环往复。

重新编译后再次运行，结果如下图所示。

 

可以清楚看到进程的切换。

3.简要分析操作系统内核核心功能及运行工作机制

核心功能是my_schedule函数的实现，即进程的切换。

asm volatile(    
            "pushq %%rbp\n\t"       /*   1  save rbp of prev */
            "movq %%rsp,%0\n\t"     /*   2  save rsp of prev */
            "movq %2,%%rsp\n\t"     /*   3  restore  rsp of next */
            "movq $1f,%1\n\t"       /*   4  save rip of prev */    
            "pushq %3\n\t"          /*   5                   */
            "ret\n\t"               /*   6  restore  rip of next */
            "1:\t"                  /*   7  next process start here */
            "popq %%rbp\n\t"        /*   8                   */
            : "=m" (prev->thread.sp),"=m" (prev->thread.ip)
            : "m" (next->thread.sp),"m" (next->thread.ip)
); 

步骤1把当前RBP寄存器的值推入到栈中

步骤2将前一个进程的sp保存到RSP寄存器中，即保存前一个进程的栈顶地址

步骤3将RSP指向下一个进程的sp

步骤4将当前进程的ip放到RIP中

步骤5将下个进程的ip推入栈中

步骤6将下个进程的ip放到RIP中

步骤7下个进程开始执行的位置

步骤8将next进程堆栈基地址从堆栈中恢复到RBP寄存器中

运行工作机制：myinterrupt.c文件中定义了一个时间片大小为1000，如果时间片轮转完成并且my_need_sched不等于1，则将my_need_sched设为1，触发mymain.c文件中my_process函数工作，又将my_need_sched设为0，触发myinterrupt.c文件中的my_schedule函数，完成进程切换，循环往复。