Kernel boot sequence Kernel boot sequence 0

Kernel 4.4
第一步、函数start_kernel(): (init/main.c)

asmlinkage __visible void __init start_kernel(void)
{
	set_task_stack_end_magic(&init_task);//STACK_END_MAGIC=0x57AC6E90
	smp_setup_processor_id();//printf("Booting Linux on physical CPU 0x%")
 
	local_irq_disable(); //屏蔽CPU0上的中断 (include/linux/irqflags.h)；
	early_boot_irqs_disabled = true;
 
	boot_cpu_init();// (init/main.c)激活current thread CPU which is CPU0；
	page_address_init(); // (mm/highmem.c)初始化内存子系统；
	pr_notice("%s", linux_banner);// (init/version.c)打印内核版本信息到终端；
	setup_arch(&command_line);//设置架构特有的子系统如内存、I/O、处理器、等等，其中command_line 是从U-Boot传来的参数列表
	mm_init_cpumask(&init_mm);
	setup_command_line(command_line);
	setup_nr_cpu_ids();
	setup_per_cpu_areas();//设置多处理器环境，这个函数确定单个CPU所需要的内存大小，并分配和初始化4个核分别所需要的内存，这样一来，每一个CPU有自己的区域放置数据；(init/main.c)
	smp_prepare_boot_cpu();	//允许current processor(CPU0）访问自己的初始化过的数据；(arch/arm/kernel/smp.c)
	build_all_zonelists(NULL, NULL);
	page_alloc_init();
 
	pr_notice("Kernel command line: %s\n", boot_command_line);
	parse_early_param();
	after_dashes = parse_args("Booting kernel",
				  static_command_line, __start___param,
				  __stop___param - __start___param,
				  -1, -1, NULL, &unknown_bootoption);
	if (!IS_ERR_OR_NULL(after_dashes))
		parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
			   NULL, set_init_arg);
 
	jump_label_init();
 
	/*
	 * These use large bootmem allocations and must precede
	 * kmem_cache_init()
	 */
	setup_log_buf(0);
	pidhash_init();
	vfs_caches_init_early();
	sort_main_extable();
	trap_init();
	mm_init();
 
 	sched_init();//(kernel/sched.c)设置Linux调度器；
          // 1）为每一个cpu相应的数据初始化一个运行队列；
          // 2）用函数init_idle(current, smp_processor_id())为cpu0 fork一个idle线程；
 
	/*
	 * Disable preemption - early bootup scheduling is extremely
	 * fragile until we cpu_idle() for the first time.
	 */
	preempt_disable();
	if (WARN(!irqs_disabled(),
		 "Interrupts were enabled *very* early, fixing it\n"))
		local_irq_disable();
	idr_init_cache();
	rcu_init();
 
	/* trace_printk() and trace points may be used after this */
	trace_init();
 
	context_tracking_init();
	radix_tree_init();
	/* init some links before init_ISA_irqs() */
	early_irq_init();
	init_IRQ();
	tick_init();
	rcu_init_nohz();
	init_timers();
	hrtimers_init();
	softirq_init();
	timekeeping_init();
	time_init();
	sched_clock_postinit();
	perf_event_init();
	profile_init();
	call_function_init();
	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
	early_boot_irqs_disabled = false;
	local_irq_enable();
 
	kmem_cache_init_late();
 
	/*
	 * HACK ALERT! This is early. We're enabling the console before
	 * we've done PCI setups etc, and console_init() must be aware of
	 * this. But we do want output early, in case something goes wrong.
	 */
	console_init();
	if (panic_later)
		panic("Too many boot %s vars at `%s'", panic_later,
		      panic_param);
 
	lockdep_info();
 
	/*
	 * Need to run this when irqs are enabled, because it wants
	 * to self-test [hard/soft]-irqs on/off lock inversion bugs
	 * too:
	 */
	locking_selftest();
 
#ifdef CONFIG_BLK_DEV_INITRD
	if (initrd_start && !initrd_below_start_ok &&
	    page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
		pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
		    page_to_pfn(virt_to_page((void *)initrd_start)),
		    min_low_pfn);
		initrd_start = 0;
	}
#endif
	page_ext_init();
	debug_objects_mem_init();
	kmemleak_init();
	setup_per_cpu_pageset();
	numa_policy_init();
	if (late_time_init)
		late_time_init();
	sched_clock_init();
	calibrate_delay();
	pidmap_init();
	anon_vma_init();
	acpi_early_init();
#ifdef CONFIG_X86
	if (efi_enabled(EFI_RUNTIME_SERVICES))
		efi_enter_virtual_mode();
#endif
#ifdef CONFIG_X86_ESPFIX64
	/* Should be run before the first non-init thread is created */
	init_espfix_bsp();
#endif
	thread_info_cache_init();
	cred_init();
	fork_init();
	proc_caches_init();
	buffer_init();
	key_init();
	security_init();
	dbg_late_init();
	vfs_caches_init();
	signals_init();
	/* rootfs populating might need page-writeback */
	page_writeback_init();
	proc_root_init();
	nsfs_init();
	cpuset_init();
	cgroup_init();
	taskstats_init_early();
	delayacct_init();
 
	check_bugs();
 
	acpi_subsystem_init();
	sfi_init_late();
 
	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
		efi_late_init();
		efi_free_boot_services();
	}
 
	ftrace_init();
 
	/* Do the rest non-__init'ed, we're now alive */
	rest_init();//建立进程1；

第二步、函数rest_init(): (init/main.c)

static noinline void __init_refok rest_init(void)
{
	int pid;
 
	rcu_scheduler_starting(); //rcu_schedulr_active = 1
	smpboot_thread_init();//if config SMP, register_cpu_notifier
	/*
	 * We need to spawn init first so that it obtains pid 1, however
	 * the init task will end up wanting to create kthreads, which, if
	 * we schedule it before we create kthreadd, will OOPS.
	 */
	kernel_thread(kernel_init, NULL, CLONE_FS); //第三步
	numa_default_policy();
	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);//kthreadd (kernel/kthread.c) 
	rcu_read_lock();
	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
	rcu_read_unlock();
	complete(&kthreadd_done);
 
	/*
	 * The boot idle thread must execute schedule()
	 * at least once to get things moving:
	 */
	init_idle_bootup_task(current);
	schedule_preempt_disabled();
	/* Call into cpu_idle with preempt disabled */
	cpu_startup_entry(CPUHP_ONLINE);
}

第三步、函数kernel_init(): (init/main.c) <进程1>

static int __ref kernel_init(void *unused)
{
	int ret;
 
	kernel_init_freeable();
	/* need to finish all async __init code before freeing the memory */
	async_synchronize_full();
	free_initmem();
	mark_readonly();
	system_state = SYSTEM_RUNNING;
	numa_default_policy();
 
	flush_delayed_fput();
 
	if (ramdisk_execute_command) {
		ret = run_init_process(ramdisk_execute_command);
		if (!ret)
			return 0;
		pr_err("Failed to execute %s (error %d)\n",
		       ramdisk_execute_command, ret);
	}
 
	/*
	 * 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) {
		ret = run_init_process(execute_command);
		if (!ret)
			return 0;
		panic("Requested init %s failed (error %d).",
		      execute_command, ret);
	}
	if (!try_to_run_init_process("/sbin/init") ||
	    !try_to_run_init_process("/etc/init") ||
	    !try_to_run_init_process("/bin/init") ||
	    !try_to_run_init_process("/bin/sh"))
		return 0;
 
	panic("No working init found.  Try passing init= option to kernel. "
	      "See Linux Documentation/init.txt for guidance.");
}

第四步、函数init_post() (init/main.c):

     这里是我们切换到用户模式的地方，调用下面的序列, 优先择一调用：
     run_init_process("/sbin/init");
     run_init_process("/etc/init");
     run_init_process("/bin/init");
     run_init_process("/bin/sh");

第五步、/sbin/init 进程执行，并在终端上显示很多信息,并且最后它把控制权交给终端，停留在激活状态。

Reference: https://blog.csdn.net/cs0301lm/article/details/41078599