Linux内核分析（二）之“复杂的操作系统”

一、内容简介
在有万经之源之称的《易》中有”太极生两仪，两仪生四象，四象生八卦”这一说法，再复杂的东西其核必简。毫无疑问，计算机的设计亦遵循这一规律。计算机的核心由“0”和“1”组成，但是构建于计算机之上的操作系统确十分复杂。
二、两把宝剑
计算机有三个法宝：存储程序计算机、函数调用堆栈、中断机制。操作系统有两把宝剑：中断与恢复现场，或许将其称作剑与鞘更为贴切。因为中断与恢复都依赖一个数据结构—-堆栈。拔出宝剑，则为出栈。宝剑入鞘，则为进栈。
堆栈可以提供：
- 函数调用框架
- 传递参数
- 保存返回地址
- 提供局部变量空间
- …..
在一个进程中断之后，必须保存该进程的信息，才可以切换到下个进程。而当下面的进程运行结束或同样处于中断状态时，切换到原先的进程则可以继续运行原先的进程。
三、实验与分析
纸上得来终觉浅，绝知此事要躬行。接下来我们运行分析一个精简的操作系统内核。
打开shell运行以下命令

cd LinuxKernel/linux-3.9.4
rm -rf mykernel
patch -p1 < ../mykernel_for_linux3.9.4sc.patch
make allnoconfig
make 
qemu -kernel arch/x86/boot/bzImage

全部代码如下

#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);

定义进程相关的数据结构

主程序 在init_my_start_kernel中初始化0号线程，并创建MAX_TASK_NUM数量的线程。process启动运行线程，并且在每运行10000000次之后，进行一次时钟调度。

#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].thread.sp - 1) = task[i].thread.sp;
    task[i].thread.sp -= 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);
        }     
    }
}

处理中断

#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 */
    {        
        my_current_task = next; 
        printk(KERN_NOTICE ">>>switch %d to %d<<<\n",prev->pid,next->pid);  
        /* 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)
        ); 
    }  
    return; 
}

在处理中断的代码中插入了以下汇编指令。该指令保存了将当前进程的esp,ebp,eip信息。并切换至下一个进程。

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)
        ); 

在C语言中内嵌汇编的语法如下


四、总结
操作系统构建于计算机三层“堡垒”之上，具有了更为复杂的特性，其中包含了多个线程的运行。进程的中断与恢复，便是操作系统的两个“翅膀”，使得进程之间可以切换。所谓“道生一，一生二，二生三，三生万物”，各个不同进程构建了如今多如繁星的应用程序的蓝图。
Linux内核分析
writen by 江明星