[Funkunux] Linux_2.6.22.6 内核 start_kernel 函数分析之 rest_init

前面我们已经对parse_args函数进行了分析，得到三个参数：

saved_root_name="/dev/mtdblock3";
                                    
console_cmdline[0].name= "ttySAC";
console_cmdline[0].options= 0;
console_cmdline[0].idx= 0;
                                    
execute_command = "/linuxrc"
           

start_kernel函数中调用的console_init函数会对console_cmdline[i]进行处理并初始化串口，这些我在上一篇文章中已经讲解过了。

接下来我们要对rest_init()函数进行分析：

static void noinline __init_refok rest_init(void)
	__releases(kernel_lock)
{
	int pid;

	kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);//创建进程，调用kernel_init函数
	numa_default_policy();
	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
	kthreadd_task = find_task_by_pid(pid);
	unlock_kernel();

	/*
	 * The boot idle thread must execute schedule()
	 * at least one to get things moving:
	 */
	preempt_enable_no_resched();
	schedule();
	preempt_disable();

	/* Call into cpu_idle with preempt disabled */
	cpu_idle();
} 
           

显然，rest_init()中调用了kernel_init函数：

static int __init kernel_init(void * unused)
{
	lock_kernel();
	/*
	 * init can run on any cpu.
	 */
	set_cpus_allowed(current, CPU_MASK_ALL);
	/*
	 * Tell the world that we're going to be the grim
	 * reaper of innocent orphaned children.
	 *
	 * We don't want people to have to make incorrect
	 * assumptions about where in the task array this
	 * can be found.
	 */
	init_pid_ns.child_reaper = current;

	__set_special_pids(1, 1);
	cad_pid = task_pid(current);

	smp_prepare_cpus(max_cpus);

	do_pre_smp_initcalls();

	smp_init();
	sched_init_smp();

	cpuset_init_smp();

	do_basic_setup();

	/*
	 * check if there is an early userspace init.  If yes, let it do all
	 * the work
	 */

	if (!ramdisk_execute_command)
		ramdisk_execute_command = "/init";

	if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) {
		ramdisk_execute_command = NULL;
		prepare_namespace();<span style="white-space:pre">	</span>//调用prepare_namespace();
	}

	/*
	 * Ok, we have completed the initial bootup, and
	 * we're essentially up and running. Get rid of the
	 * initmem segments and start the user-mode stuff..
	 */
	init_post();<span style="white-space:pre">	</span><span style="font-family: Arial, Helvetica, sans-serif;">	</span><span style="font-family: Arial, Helvetica, sans-serif;">//调用init_post();</span>

	return 0;
}
           

可以看到，kernel_init函数中调用了prepare_namespace()函数和init_post()函数，我们先看prepare_namespace函数：

void __init prepare_namespace(void)
{
	int is_floppy;

	if (root_delay) {
		printk(KERN_INFO "Waiting %dsec before mounting root device...\n",
		       root_delay);
		ssleep(root_delay);
	}

	/* wait for the known devices to complete their probing */
	while (driver_probe_done() != 0)
		msleep(100);

	md_run_setup();

	if (saved_root_name[0]) {
		root_device_name = saved_root_name;
		if (!strncmp(root_device_name, "mtd", 3)) {
			mount_block_root(root_device_name, root_mountflags);
			goto out;
		}
		ROOT_DEV = name_to_dev_t(root_device_name);
		if (strncmp(root_device_name, "/dev/", 5) == 0)
			root_device_name += 5;
	}

	is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;

	if (initrd_load())
		goto out;

	if (is_floppy && rd_doload && rd_load_disk(0))
		ROOT_DEV = Root_RAM0;

	mount_root();
out:
	sys_mount(".", "/", NULL, MS_MOVE, NULL);
	sys_chroot(".");
	security_sb_post_mountroot();
}
           

我们可以看到，prepare_namespace中令root_device_name = saved_root_name = "/dev/mtdblock3" ，ROOT_DEV = name_to_dev_t(root_device_name)， 然后令root_device_name += 5 = "mtdblock3" ，最后调用mount_root()函数，对根文件系统进行挂载。

接下来我们看init_post函数：

static int noinline init_post(void)
{
	free_initmem();
	unlock_kernel();
	mark_rodata_ro();
	system_state = SYSTEM_RUNNING;
	numa_default_policy();

	if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
		printk(KERN_WARNING "Warning: unable to open an initial console.\n");

	(void) sys_dup(0);
	(void) sys_dup(0);

	if (ramdisk_execute_command) {<span style="white-space:pre">			</span>//在parse_args()函数分析中我们知道，ramdisk_execute_command = NULL
		run_init_process(ramdisk_execute_command);
		printk(KERN_WARNING "Failed to execute %s\n",
				ramdisk_execute_command);
	}

	/*
	 * We try each of these until one succeeds.
	 *
	 * The Bourne shell can be used instead of init if we are
	 * trying to recover a really broken machine.
	 */
	if (execute_command) {
		run_init_process(execute_command);
		printk(KERN_WARNING "Failed to execute %s.  Attempting "
					"defaults...\n", execute_command);
	}
	run_init_process("/sbin/init");
	run_init_process("/etc/init");
	run_init_process("/bin/init");
	run_init_process("/bin/sh");

	panic("No init found.  Try passing init= option to kernel.");
}
           

显然，init_post()调用了run_init_process(execute_command)，进入根文件系统对应的目录调用第一个程序init，如果失败，则继续执行：

<span style="white-space:pre">	</span>run_init_process("/sbin/init");
	run_init_process("/etc/init");
	run_init_process("/bin/init");
	run_init_process("/bin/sh");
           

若全部失败，则发出 panic 信息。

如果没有烧写根文件系统，内核找不到对应的init程序，则会出现上述panic信息：

Warning: unable to open an initial console.
Failed to execute /linuxrc.  Attempting defaults...
Kernel panic - not syncing: No init found.  Try passing init= option to kernel.
           

我们来实验一下，我将自己开发板上root分区的根文件系统擦除：

然后boot：

最后出现如下三行信息：

和我们分析的一模一样，证明我们的分析是对的。

以上就是我对start_kernel中rest_init函数的分析。