linux0.12--14.可执行文件的加载过程

1. 开始
init/main.c中 L195

void init(void)
{
    int pid,i;
    printf("next setup\n");
    setup((void *) &drive_info);
    (void) open("/dev/tty1",O_RDWR,0);
    (void) dup(0);
    (void) dup(0);
    printf("%d buffers = %d bytes buffer space\n\r",NR_BUFFERS,
        NR_BUFFERS*BLOCK_SIZE);
    printf("Free mem: %d bytes\n\r",memory_end-main_memory_start);
    if (!(pid=fork())) {
        close(0);
        if (open("/etc/rc",O_RDONLY,0))
            _exit(1);
        execve("/bin/sh",argv_rc,envp_rc);
        _exit(2);
    }
}

a. 其中 execve("/bin/sh",argv_rc,envp_rc)的execve是一个宏定义的:

lib/execve.c
_syscall3(int,execve,const char *,file,char **,argv,char **,envp)

b. include/unistd.h中的宏
lib/execve.c:_syscall3(int,execve,const char *,file,char **,argv,char **,envp)

include/unistd.h --> L189定义了syscall3 #define _syscall3(type,name,atype,a,btype,b,ctype,c) \ type name(atype a,btype b,ctype c) \ { \ long __res; \ __asm__ volatile ("int $0x80" \ : "=a" (__res) \ : "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b)),"d" ((long)(c))); \ if (__res>=0) \ return (type) __res; \ errno=-__res; \ return -1; \ }

展开后: int execve(const char * file,char ** argv,char ** envp) { long __res; __asm__ volatile ("int $0x80" : "=a" (__res) : "0" (11),"b" ((long)(file)),"c" ((long)(argv)),"d"((long)(envp)) ); if (__res>=0) return (int) __res; errno=-__res; return -1; }

c. int 0x80系统调用
sys_call --> sys_call_table[11] --> sys_execve

在kernel/sys_call.s中 L214

.align 4
sys_execve:
    lea EIP(%esp),%eax
    pushl %eax
    call do_execve
    addl $4,%esp
    ret

即系统调用到了do_execve

2. do_execve

#0  do_execve (eip=0xffbfec, tmp=30935, filename=0x22660 "/bin/sh", argv=0x29820 , envp=0x29828 ) at exec.c:220

在fs/exec.c中L207

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 (in_group_p(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)) {
          //这儿先不关心shell脚本的执行过程
    }
    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 */
/* note that current->library stays unchanged by an exec */
    if (current->executable)
        iput(current->executable);
    current->executable = inode;
    current->signal = 0;
    for (i=0 ; i<32 ; i++) {
        current->sigaction[i].sa_mask = 0;
        current->sigaction[i].sa_flags = 0;
        if (current->sigaction[i].sa_handler != SIG_IGN)
            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);
    p -= LIBRARY_SIZE + 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->suid = current->euid = e_uid;
    current->sgid = current->egid = e_gid;
    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);
}