【Linux】初见Linux内核以及进程上下文切换

1、下载Linux内核并进行配置、运行

#github下载补丁
wget https://raw.github.com/mengning/mykernel/master/mykernel-2.0_for_linux-5.4.34.patch 
#安装下载工具
sudo apt install axel
#下载linux内核
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
#打补丁并编译内核
patch -p1 < ../mykernel-2.0_for_linux-5.4.34.patch
sudo apt install build-essential gcc-multilib  libncurses5-dev bison flex libssl-dev libelf-dev
sudo apt install qemu # install QEMU
sudo apt install make   
make defconfig #应用配置
make -j$(nproc)

　　配置成功便能输入以下命令运行内核

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

　　

可以发现有两条输出语句交替打印

这是mymain.c和myinterrupt.c两份代码所的执行结果

//linux-5.4.34/mykernel/mymain.c
void __init my_start_kernel(void)
{
    int i = 0;
    while(1)
    {
        i++;
        if(i%100000 == 0)
            printk(KERN_NOTICE "my_start_kernel here  %d \n",i);

    }
}

//linux-5.4.34/mykernel/myinterrupt.c
void my_timer_handler(void)
{
    printk(KERN_NOTICE "\n>>>>>>>>>>>>>>>>>my_timer_handler here<<<<<<<<<<<<<<<<<<\n\n");
}

这些代码是用来周期性地产⽣的时钟中断信号，之后将在这里尝试填写处理中断时的工作代码。

2、完成内核进程切换功能

编写上文中提到的处理中断时的工作代码

mypcb.h：

#define MAX_TASK_NUM        4
#define KERNEL_STACK_SIZE   1024*2 # unsigned long
/* 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：

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].stack[KERNEL_STACK_SIZE-1] - 1) = (unsigned long)&task[i].stack[KERNEL_STACK_SIZE-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 */
        : 
        : "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);
        }     
    }
}

 

myinterrupt.c：

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;    
}

　　

重新编译、运行内核，便可以看到进程的切换过程

make defconfig # Default configuration is based on 'x86_64_defconfig'
make -j$(nproc)
qemu-system-x86_64 -kernel arch/x86/boot/bzImage

 

 

 

 

　　3.原理介绍

　　上文中的代码运行过程如下：

　　1.保存原进程的栈底

　　2.保存原进程的栈顶

　　3.读取后续进程的栈顶

　　4.将1f(标签，指向第7步)保存在原进程的ip中

　　5.出栈（此时的栈已经是切换后的了）给后续进程的ip

　　6.利用ret指令修改eip

　　7.将rbp指向next进程的栈底

 

参考：https://github.com/mengning/mykernel