Linux内核笔记十 程序的启动

exec.c do_execve (执行一个可执行程序 执行shell脚本)
1、程序运行前是如何做的
2、进程 线程？
3、进程的具体内存格式？

1、程序在运行前都在磁盘
2、在运行程序中，首先把程序的头读出（高速 内存）
3、运行程序的函数
程序的头被载入高速缓冲区之后----fork----copy_process----ldt tss
ldt 代码段 数据段
tss 程序运行时的状态
4、程序运行前要进行的几个事情
首先在程序运行的时候要创建参数和环境变量的存储页面
要设置新的函数的sp
重新调整代码段

static unsigned long copy_strings(int argc,char ** argv,unsigned long *page,
		unsigned long p, int from_kmem)
{
	char *tmp, *pag;
	int len, offset = 0;
	unsigned long old_fs, new_fs;

	if (!p)
		return 0;	/* bullet-proofing */
	new_fs = get_ds();
	old_fs = get_fs();
	if (from_kmem==2)
		set_fs(new_fs);
	while (argc-- > 0) {
		if (from_kmem == 1)
			set_fs(new_fs);
		if (!(tmp = (char *)get_fs_long(((unsigned long *)argv)+argc)))
			panic("argc is wrong");
		if (from_kmem == 1)
			set_fs(old_fs);
		len=0;		/* remember zero-padding */
		do {
			len++;
		} while (get_fs_byte(tmp++));
		if (p-len < 0) {	/* this shouldn't happen - 128kB */
			set_fs(old_fs);
			return 0;
		}
		while (len) {
			--p; --tmp; --len;
			if (--offset < 0) {
				offset = p % PAGE_SIZE;
				if (from_kmem==2)
					set_fs(old_fs);
				if (!(pag = (char *) page[p/PAGE_SIZE]) &&
				    !(pag = (char *) page[p/PAGE_SIZE] =
				      (unsigned long *) get_free_page())) 
					return 0;
				if (from_kmem==2)
					set_fs(new_fs);

			}
			*(pag + offset) = get_fs_byte(tmp);
		}
	}
	if (from_kmem==2)
		set_fs(old_fs);
	return p;
}

这个函数主要做的一件事情就是说把当前的一些乱七八糟参数放到page里面去，就是放到程序存储的空间

page 参数页表首指针

cs 代码段
ds 数据段
es 额外段
ss 栈
fs 用户数据段

用户态 相等
内核态 ds内核程序数据段 fs用户数据段

argv argc

shell脚本的执行流程

int do_execve(unsigned long * eip,long tmp,char * filename,
	char ** argv, char ** envp)
{
	struct m_inode * inode;
	struct buffer_head * bh;
	struct exec ex;
	unsigned long page[MAX_ARG_PAGES];
	int i,argc,envc;
	int e_uid, e_gid;
	int retval;
	int sh_bang = 0;
	unsigned long p=PAGE_SIZE*MAX_ARG_PAGES-4;

	if ((0xffff & eip[1]) != 0x000f)
		panic("execve called from supervisor mode");
	for (i=0 ; i<MAX_ARG_PAGES ; i++)	/* clear page-table */
		page[i]=0;
	if (!(inode=namei(filename)))		/* get executables inode */
		return -ENOENT;
	argc = count(argv);
	envc = count(envp);
	
restart_interp:
	if (!S_ISREG(inode->i_mode)) {	/* must be regular file */
		retval = -EACCES;
		goto exec_error2;
	}
	i = inode->i_mode;
	e_uid = (i & S_ISUID) ? inode->i_uid : current->euid;
	e_gid = (i & S_ISGID) ? inode->i_gid : current->egid;
	if (current->euid == inode->i_uid)
		i >>= 6;
	else if (current->egid == inode->i_gid)
		i >>= 3;
	if (!(i & 1) &&
	    !((inode->i_mode & 0111) && suser())) {
		retval = -ENOEXEC;
		goto exec_error2;
	}
	if (!(bh = bread(inode->i_dev,inode->i_zone[0]))) {
		retval = -EACCES;
		goto exec_error2;
	}
	ex = *((struct exec *) bh->b_data);	/* read exec-header */
	if ((bh->b_data[0] == '#') && (bh->b_data[1] == '!') && (!sh_bang)) {
		/*
		 * This section does the #! interpretation.
		 * Sorta complicated, but hopefully it will work.  -TYT
		 */

		char buf[1023], *cp, *interp, *i_name, *i_arg;
		unsigned long old_fs;

		strncpy(buf, bh->b_data+2, 1022);
		brelse(bh);
		iput(inode);
		buf[1022] = '\0';
		if (cp = strchr(buf, '\n')) {
			*cp = '\0';
			for (cp = buf; (*cp == ' ') || (*cp == '\t'); cp++);
		}
		if (!cp || *cp == '\0') {
			retval = -ENOEXEC; /* No interpreter name found */
			goto exec_error1;
		}
		interp = i_name = cp;
		i_arg = 0;
		for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++) {
 			if (*cp == '/')
				i_name = cp+1;
		}
		if (*cp) {
			*cp++ = '\0';
			i_arg = cp;
		}
		/*
		 * OK, we've parsed out the interpreter name and
		 * (optional) argument.
		 */
		if (sh_bang++ == 0) {
			p = copy_strings(envc, envp, page, p, 0);
			p = copy_strings(--argc, argv+1, page, p, 0);
		}
		/*
		 * Splice in (1) the interpreter's name for argv[0]
		 *           (2) (optional) argument to interpreter
		 *           (3) filename of shell script
		 *
		 * This is done in reverse order, because of how the
		 * user environment and arguments are stored.
		 */
		p = copy_strings(1, &filename, page, p, 1);
		argc++;
		if (i_arg) {
			p = copy_strings(1, &i_arg, page, p, 2);
			argc++;
		}
		p = copy_strings(1, &i_name, page, p, 2);
		argc++;
		if (!p) {
			retval = -ENOMEM;
			goto exec_error1;
		}
		/*
		 * OK, now restart the process with the interpreter's inode.
		 */
		old_fs = get_fs();
		set_fs(get_ds());
		if (!(inode=namei(interp))) { /* get executables inode */
			set_fs(old_fs);
			retval = -ENOENT;
			goto exec_error1;
		}
		set_fs(old_fs);
		goto restart_interp;
	}
	brelse(bh);
	if (N_MAGIC(ex) != ZMAGIC || ex.a_trsize || ex.a_drsize ||
		ex.a_text+ex.a_data+ex.a_bss>0x3000000 ||
		inode->i_size < ex.a_text+ex.a_data+ex.a_syms+N_TXTOFF(ex)) {
		retval = -ENOEXEC;
		goto exec_error2;
	}
	if (N_TXTOFF(ex) != BLOCK_SIZE) {
		printk("%s: N_TXTOFF != BLOCK_SIZE. See a.out.h.", filename);
		retval = -ENOEXEC;
		goto exec_error2;
	}
	if (!sh_bang) {
		p = copy_strings(envc,envp,page,p,0);
		p = copy_strings(argc,argv,page,p,0);
		if (!p) {
			retval = -ENOMEM;
			goto exec_error2;
		}
	}
/* OK, This is the point of no return */
	if (current->executable)
		iput(current->executable);
	current->executable = inode;
	for (i=0 ; i<32 ; i++)
		current->sigaction[i].sa_handler = NULL;
	for (i=0 ; i<NR_OPEN ; i++)
		if ((current->close_on_exec>>i)&1)
			sys_close(i);
	current->close_on_exec = 0;
	free_page_tables(get_base(current->ldt[1]),get_limit(0x0f));
	free_page_tables(get_base(current->ldt[2]),get_limit(0x17));
	if (last_task_used_math == current)
		last_task_used_math = NULL;
	current->used_math = 0;
	p += change_ldt(ex.a_text,page)-MAX_ARG_PAGES*PAGE_SIZE;
	p = (unsigned long) create_tables((char *)p,argc,envc);
	current->brk = ex.a_bss +
		(current->end_data = ex.a_data +
		(current->end_code = ex.a_text));
	current->start_stack = p & 0xfffff000;
	current->euid = e_uid;
	current->egid = e_gid;
	i = ex.a_text+ex.a_data;
	while (i&0xfff)
		put_fs_byte(0,(char *) (i++));
	eip[0] = ex.a_entry;		/* eip, magic happens :-) */
	eip[3] = p;			/* stack pointer */
	return 0;
exec_error2:
	iput(inode);
exec_error1:
	for (i=0 ; i<MAX_ARG_PAGES ; i++)
		free_page(page[i]);
	return(retval);
}

先清空了参数列表，或者说参数数组
然后打开了文件的inode节点
判断当前指向文件属性和执行权限
读取当前执行程序或shell脚本的文件头结构
解析出shell的脚本解析程序名
让iname指向执行文件名
根据头文件信息进行当前程序的判定
拷贝执行文件的环境变量和参数
执行线程时 进程要做的切换和更新