linux启动内核源码分析

内核的启动时从main.c这个文件里面的start_kernel函数开始的,这个文件在linux源码里面的init文件夹下面

下面我们来看看这个函数 这个函数很长,可以看个大概过去

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();
    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();
    if (panic_later)
        panic("Too many boot %s vars at `%s'", panic_later,
              panic_param);

    lockdep_init();

    /*
     * 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
    kmemleak_init();
    setup_per_cpu_pageset();
    numa_policy_init();
    acpi_early_init();
    if (late_time_init)
        late_time_init();
    sched_clock_init();
    calibrate_delay();
    pid_idr_init();
    anon_vma_init();
#ifdef CONFIG_X86
    if (efi_enabled(EFI_RUNTIME_SERVICES))
        efi_enter_virtual_mode();
#endif
    thread_stack_cache_init();
    cred_init();
    fork_init();
    proc_caches_init();
    uts_ns_init();
    buffer_init();
    key_init();
    security_init();
    dbg_late_init();
    vfs_caches_init();
    pagecache_init();
    signals_init();
    seq_file_init();
    proc_root_init();
    nsfs_init();
    cpuset_init();
    cgroup_init();
    taskstats_init_early();
    delayacct_init();

    check_bugs();

    acpi_subsystem_init();
    arch_post_acpi_subsys_init();
    sfi_init_late();

    /* Do the rest non-__init'ed, we're now alive */
    arch_call_rest_init();
}

这个函数里面我们会看到有很多的各种init,也就是初始化,我们只说几个重点操作

 

 

首先来看下这个函数set_task_stack_end_magic(&init_task);

在linux里面所有的进程都是由父进程创建而来,所以说在启动内核的时候需要有个祖先进程,这个进程是系统创建的

第一个进程,我们称为0号进程,它是唯一一个没有通过fork或者kernel_thread的进程

 

然后就是初始化系统调用,对应的函数就是trap_init();这里面设置了很多中断门,用于处理各种中断

系统调用也是通过发送中断的方式进行的。

接下来就是内存管理模块的初始化,对应的函数是mm_init();

 

 

然后就是初始化任务调度,对应的函数就是sched_init();

这个任务调度是干嘛用的呢?就是操作系统协调进程和cpu,比如说分配哪个进程在cpu上运行呀,

在比如说你这个进程在cpu上运行时间过长了,然后操作系统就会把你踢下去,换另一个进程在cpu上运行。

 

到了这个preempt_disable();函数,这个函数的意思就是在这个函数运行以后就禁止被中断

也就是说在这个函数运行后面,如果没有主动让出cpu,那么其他进程是无法抢占他的。

 

然后看下这个tick_init();这个函数是时钟初始化,这个时钟的概念是什么意思呢?

计算机会每隔一段时间周期通知操作系统,就像时钟一样,滴答滴答,每滴答一下就是一个时间周期过去了,

通知操作系统后,操作系统会看下当前在cpu上运行的进程运行时间是否过长,如果过长就标识该进程为可抢占

然后在某些时机下会切掉该进程,换下一个进程。

 

最后start_kernel()调用的是rest_init()用来初始化其他方面,这里面做了好多事情

noinline void __ref rest_init(void)
{
    struct task_struct *tsk;
    int pid;

    rcu_scheduler_starting();
    /*
     * 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.
     */
    pid = kernel_thread(kernel_init, NULL, CLONE_FS);
    /*
     * Pin init on the boot CPU. Task migration is not properly working
     * until sched_init_smp() has been run. It will set the allowed
     * CPUs for init to the non isolated CPUs.
     */
    rcu_read_lock();
    tsk = find_task_by_pid_ns(pid, &init_pid_ns);
    set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
    rcu_read_unlock();

    numa_default_policy();
    pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
    rcu_read_lock();
    kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
    rcu_read_unlock();

    /*
     * Enable might_sleep() and smp_processor_id() checks.
     * They cannot be enabled earlier because with CONFIG_PREEMPT=y
     * kernel_thread() would trigger might_sleep() splats. With
     * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
     * already, but it's stuck on the kthreadd_done completion.
     */
    system_state = SYSTEM_SCHEDULING;

    complete(&kthreadd_done);

    /*
     * The boot idle thread must execute schedule()
     * at least once to get things moving:
     */
    schedule_preempt_disabled();
    /* Call into cpu_idle with preempt disabled */
    cpu_startup_entry(CPUHP_ONLINE);
}

 

首先调用kernel_thread()函数,用来创建用户态的第一个进程,这个进程是所有用户态进程的祖先进程,我们称为1号进程

这个一号进程进入用户态以后,开枝散叶,创建了很多子进程,子进程又创建子进程,就形成了一颗进程树。

一旦有了用户进程,就需要划分资源了,比如说用户态的进程要想使用网卡发送数据,这个时候不能直接让用户态进程调用网卡

而是通过操作系统提供的系统调用函数,给进程发送数据,发送成功以后在返回到用户态进程,通知进程处理结果,也就是封装了

底层实现,用户态进程想要实现什么功能,直接调用系统调用就可以了,在用户态进程进行系统调用时,操作系统会把当前该进程的

参数都保存到寄存器里面,如果有对寄存器不懂的,就把寄存器想象成变量,变量是编程语言存放数据的,那么寄存器就是cpu用来存放数据的东西,

等到系统调用从内核态返回到用户态的时候,会恢复当时保存的寄存器里面的数据,继续运行。

这个过程就是这样的,用户态-》系统调用-》保存寄存器-》内核态执行系统调用-》恢复寄存器-》返回用户态 接着运行

 

 

 

 然后接着说这个一号进程启动过程,现在这个进程还是在内核态的,那么要怎么把它搞到用户态里面的,

一般都是从用户态到内核态在返回到用户态,很少见过直接从内核态开始然后到用户态的

看下下面这个代码

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
set_user_gs(regs, 0);
regs->fs    = 0;
regs->ds    = __USER_DS;
regs->es    = __USER_DS;
regs->ss    = __USER_DS;
regs->cs    = __USER_CS;
regs->ip    = new_ip;
regs->sp    = new_sp;
regs->flags    = X86_EFLAGS_IF;
force_iret();
}
EXPORT_SYMBOL_GPL(start_thread);

 

 创建进程的这函数最后会有这么一个函数也就是start_thread(),这里面把各个寄存器都设置为了_USER,啥意思呢,里面将用户态的代码段CS设置为_USER_CS,将用户态的数据段DS设置为_USER_DS,

以及指令指针寄存器IP,栈顶指针SP,最后的force_iret();是用来恢复寄存器的,按理来说应该恢复在系统调用的时候保存的寄存器,这里面恢复的其实就是上面设置的寄存器。CS和指令指针寄存器IP恢复了,

指向用户态下一个要执行的语句,DS和函数栈指针SP也被恢复了,指向用户态函数栈的栈顶,所以,下一条指令就从用户态开始了。

 

用户态的祖先进程创建完了,那么内核态有没有一个祖先进程呢?

有的,rest_init第二大事情就是第三个进程,也就是2号进程。

 了解更多:https://www.toutiao.com/c/user/83293539887/#mid=1633933053814798

posted @ 2019-05-20 12:01  小二郎**  阅读(2737)  评论(0编辑  收藏  举报