万字解析如何调试内核启动流程！

内核生命周期

uboot 打印完 Starting kernel . . .，就完成了自己的使命，控制权便交给了 kernel 的第一条指令，也就是下面这个函数
init/main.c

    asmlinkage __visible void __init start_kernel(void)
    {
     ...
     rest_init();
    }

start_kernel 相当于内核的 main 函数，内核的生命周期就是从执行这个函数的第一条语句开始的，直到最后一个函数 reset_init()，内核将不再从这个函数中返回，而是陷入这个函数里面的一个 while(1) 死循环，这个死循环被作为 idle 进程，也就是 0 号进程。

所以，内核的生命周期，就是一个完整的 start_kernel 函数。始于 start_kernel 函数的第一条语句，停留在最后的死循环。

init 进程

kernel 会创建众多内核线程，来持续致力于内存、磁盘、CPU 的管理，其中有两个内核线程比较重要，需要我们重点讲解，那就是 1 号内核线程 kernel_init 和 2 号内核线程 kthreadd。1 号内核线程最终会被用户的第一个进程 init 代替，也就成了 1 号进程。如下：

# ps
    PID   USER     COMMAND
        1 root     init
        2 root     [kthreadd]
        3 root     [rcu_gp]
        4 root     [rcu_par_gp]
        7 root     [kworker/u4:0-ev]
        8 root     [mm_percpu_wq]
        9 root     [ksoftirqd/0]
    ...

COMMAND 这一列，带中括号的是内核线程，不带中括号的是用户进程。从 PID 统一编址就可以看出，它俩地位是一样的。
下面我们深入分析一下从 start_kernel 到最终运行 init 进程，kernel 都经历了什么

打印

添加打印，是分析流程的好方法。

    asmlinkage __visible void __init start_kernel(void)
    {
     char *command_line;
     char *after_dashes;
    
        set_task_stack_end_magic(&init_task);
        smp_setup_processor_id();
        debug_objects_early_init();
    
        cgroup_init_early();
    
        local_irq_disable();
        early_boot_irqs_disabled = true;
    
        /*
         * Interrupts are still disabled. Do necessary setups, then
         * enable them.
         */
        boot_cpu_init();
        page_address_init();
        pr_notice("%s", linux_banner);
        setup_arch(&command_line);
        /*
         * Set up the the initial canary and entropy after arch
         * and after adding latent and command line entropy.
         */
        add_latent_entropy();
        add_device_randomness(command_line, strlen(command_line));
        boot_init_stack_canary();
        mm_init_cpumask(&init_mm);
        setup_command_line(command_line);
        setup_nr_cpu_ids();
        setup_per_cpu_areas();
        smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
        boot_cpu_hotplug_init();
    
        build_all_zonelists(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);
        vfs_caches_init_early();
        sort_main_extable();
        trap_init();
        mm_init();
    
        ftrace_init();
    
        /* trace_printk can be enabled here */
        early_trace_init();
    
        /*
         * Set up the scheduler prior starting any interrupts (such as the
         * timer interrupt). Full topology setup happens at smp_init()
         * time - but meanwhile we still have a functioning scheduler.
         */
        sched_init();
        /*
         * 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();
        radix_tree_init();
    
        /*
         * Set up housekeeping before setting up workqueues to allow the unbound
         * workqueue to take non-housekeeping into account.
         */
        housekeeping_init();
    
        /*
         * Allow workqueue creation and work item queueing/cancelling
         * early.  Work item execution depends on kthreads and starts after
         * workqueue_init().
         */
        workqueue_init_early();
    
        rcu_init();
    
        /* Trace events are available after this */
        trace_init();
    
        if (initcall_debug)
         initcall_debug_enable();
    
        context_tracking_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();
        printk_safe_init();
        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();
    
    printk("## start_kernel() --> console_init()\n");
    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();
    
        /*
         * This needs to be called before any devices perform DMA
         * operations that might use the SWIOTLB bounce buffers. It will
         * mark the bounce buffers as decrypted so that their usage will
         * not cause "plain-text" data to be decrypted when accessed.
         */
        mem_encrypt_init();
    
    #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();
    kmemleak_init();
    debug_objects_mem_init();
    setup_per_cpu_pageset();
    numa_policy_init();
    acpi_early_init();
    if (late_time_init)
    late_time_init();
    calibrate_delay();
    pid_idr_init();
    anon_vma_init();
    #ifdef CONFIG_X86
    if (efi_enabled(EFI_RUNTIME_SERVICES))
    efi_enter_virtual_mode();
    #endif
    thread_stac