Linux启动分析

这几天一直在纠结：

main函数是程序的入口，一个程序启动后，经过bootloader的初始化就该经main函数进入C语言的世界，
但是linux中每个应用程序的开始都是从main函数开始的。
linux下有多个应用程序，岂不是有很多个main。那bootloader会知道跳到哪个main？多个main编译怎么不冲突？

在网上搜索了很久，渐渐的有些明白了：

1、main函数是C语言的入口，这句话没错；但是这句话仅仅是一个约定，而非一个亘古不变的铁律！
从程序的更为本质的汇编代码来看，只是大家约定汇编初始化完了后，跳到一个名字叫”main”的标号处；
言外之意就是这个标号也是可以改名的，比如linux的C语言入口就是start_kernel（）；
从这个标号地址后就是C语言的天下了。用main这个名字仅仅是因为大家的约定而已，不遵守约定能玩的转也行啊，就像苹果充电线啥的都和别人不一样。

2、在编译时是不存多个main函数的！每个应用程序虽说都有一个main函数（从应用程序来看应用程序的入口是main函数哦）；
但是应用程序都是独立编译的，不会一起编译，操作系统内核就更不可能和应用程序一起编译了！
所以根本不存在多个main冲突的！！
可能是统一操作系统与应用程序之间的接口，抑或是侧面影响下main是程序入口的说法，main是应用程序和操作系统之间约定好的一个接口名！
所以linux中每个应用程序的第一个函数必须是main。除非你改掉了内核调度的接口地方。

3、linux的应用程序的安装启动也可以类比下我们每天都在用的Windows。
Windows应用程序的安装其实也是把一些执行文件拷贝到指定的文件夹里（从绿色软件看），点击就可以运行。
linux下也是这样。编译好的bin文件放到指定的文件夹目录下，然后用命令启动执行。

/*

• linux/init/main.c
• Copyright (C) 1991, 1992 Linus Torvalds
• GK 2/5/95 - Changed to support mounting root fs via NFS
• Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb ‘96
• Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May ‘96
• Simplified starting of init: Michael A. Griffith grif@acm.org
• start_kernel->rest_init->kernel_init创建用户init pid=1
  ->kthreadd管理内核线程 pid=x
  ->pid=0，是idle线程
  在rest_init中，会创建kernel_init线程，它负责创建用户init进程,完成工作后，自己
  化身为idle线程
  */

#include <linux/types.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/stackprotector.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/tty.h>
#include <linux/percpu.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
#include <linux/kernel_stat.h>
#include <linux/start_kernel.h>
#include <linux/security.h>
#include <linux/smp.h>
#include <linux/profile.h>
#include <linux/rcupdate.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
#include <linux/writeback.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/cgroup.h>
#include <linux/efi.h>
#include <linux/tick.h>
#include <linux/interrupt.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/unistd.h>
#include <linux/rmap.h>
#include <linux/mempolicy.h>
#include <linux/key.h>
#include <linux/buffer_head.h>
#include <linux/page_cgroup.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
#include <linux/kmemleak.h>
#include <linux/pid_namespace.h>
#include <linux/device.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/signal.h>
#include <linux/idr.h>
#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/async.h>
#include <linux/kmemcheck.h>
#include <linux/sfi.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/perf_event.h>

#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>

#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>
#endif

static int kernel_init(void *);

extern void init_IRQ(void);
extern void fork_init(unsigned long);
extern void mca_init(void);
extern void sbus_init(void);
extern void prio_tree_init(void);
extern void radix_tree_init(void);
#ifndef CONFIG_DEBUG_RODATA
static inline void mark_rodata_ro(void) { }
#endif

#ifdef CONFIG_TC
extern void tc_init(void);
#endif

/*

• Debug helper: via this flag we know that we are in ‘early bootup code’
• where only the boot processor is running with IRQ disabled. This means
• two things - IRQ must not be enabled before the flag is cleared and some
• operations which are not allowed with IRQ disabled are allowed while the
• flag is set.
  */
  bool early_boot_irqs_disabled __read_mostly;

enum system_states system_state __read_mostly;
EXPORT_SYMBOL(system_state);

/*

• Boot command-line arguments
  */

#define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
#define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT

extern void time_init(void);
/* Default late time init is NULL. archs can override this later. /
void (__initdata late_time_init)(void);
extern void softirq_init(void);

/* Untouched command line saved by arch-specific code. /
char __initdata boot_command_line[COMMAND_LINE_SIZE];
/ Untouched saved command line (eg. for /proc) */
char saved_command_line;
/ Command line for parameter parsing */
static char *static_command_line;

static char *execute_command;
static char *ramdisk_execute_command;

/*

• If set, this is an indication to the drivers that reset the underlying
• device before going ahead with the initialization otherwise driver might
• rely on the BIOS and skip the reset operation.
• This is useful if kernel is booting in an unreliable environment.
• For ex. kdump situaiton where previous kernel has crashed, BIOS has been
• skipped and devices will be in unknown state.
  */
  unsigned int reset_devices;
  EXPORT_SYMBOL(reset_devices);

static int __init set_reset_devices(char *str)
{
reset_devices = 1;
return 1;
}

__setup(“reset_devices”, set_reset_devices);

static const char * argv_init[MAX_INIT_ARGS+2] = { “init”, NULL, };
const char * envp_init[MAX_INIT_ENVS+2] = { “HOME=/“, “TERM=linux”, NULL, };
static const char *panic_later, *panic_param;

extern const struct obs_kernel_param __setup_start[], __setup_end[];

static int __init obsolete_checksetup(char *line)
{
const struct obs_kernel_param *p;
int had_early_param = 0;

p = __setup_start;
do {
    int n = strlen(p->str);
    if (parameqn(line, p->str, n)) {
        if (p->early) {
            /* Already done in parse_early_param?
             * (Needs exact match on param part).
             * Keep iterating, as we can have early
             * params and __setups of same names 8( */
            if (line[n] == '\0' || line[n] == '=')
                had_early_param = 1;
        } else if (!p->setup_func) {
            printk(KERN_WARNING "Parameter %s is obsolete,"
                   " ignored\n", p->str);
            return 1;
        } else if (p->setup_func(line + n))
            return 1;
    }
    p++;
} while (p < __setup_end);

return had_early_param;

}

/*

• This should be approx 2 Bo*oMips to start (note initial shift), and will
• still work even if initially too large, it will just take slightly longer
  */
  unsigned long loops_per_jiffy = (1<<12);
  EXPORT_SYMBOL(loops_per_jiffy);
  static int __init debug_kernel(char *str)
  {
  console_loglevel = 10;
  return 0;
  }
  static int __init quiet_kernel(char *str)
  {
  console_loglevel = 4;
  return 0;
  }
  early_param(“debug”, debug_kernel);
  early_param(“quiet”, quiet_kernel);
  static int __init loglevel(char str)
  {
  int newlevel;
  /
  • Only update loglevel value when a correct setting was passed,
  • to prevent blind crashes (when loglevel being set to 0) that
  • are quite hard to debug
    /
    if (get_option(&str, &newlevel)) {
    console_loglevel = newlevel;
    return 0;
    }
    return -EINVAL;
    }
    early_param(“loglevel”, loglevel);
    / Change NUL term back to “=”, to make “param” the whole string. */
    static int __init repair_env_string(char *param, char val)
    {
    if (val) {
    / param=val or param=”val”? */
    if (val == param+strlen(param)+1)
    val[-1] = ‘=’;
    else if (val == param+strlen(param)+2) {
    val[-2] = ‘=’;
    memmove(val-1, val, strlen(val)+1);
    val–;
    } else
    BUG();

  }
  return 0;
  }
  /*

• Unknown boot options get handed to init, unless they look like
• unused parameters (modprobe will find them in /proc/cmdline).
  */
  static int __init unknown_bootoption(char *param, char val)
  {
  repair_env_string(param, val);
  / Handle obsolete-style parameters /
  if (obsolete_checksetup(param))
  return 0;
  / Unused module parameter. /
  if (strchr(param, ‘.’) && (!val || strchr(param, ‘.’) < val))
  return 0;
  if (panic_later)
  return 0;
  if (val) {
  / Environment option */
  unsigned int i;
  for (i = 0; envp_init[i]; i++) {
  if (i == MAX_INIT_ENVS) {
  panic_later = “Too many boot env vars at %s'"; panic_param = param; } if (!strncmp(param, envp_init[i], val - param)) break; } envp_init[i] = param; } else { /* Command line option */ unsigned int i; for (i = 0; argv_init[i]; i++) { if (i == MAX_INIT_ARGS) { panic_later = "Too many boot init vars at %s’”;
  panic_param = param;
  }
  }
  argv_init[i] = param;
  }
  return 0;
  }
  static int __init init_setup(char str)
  {
  unsigned int i;
  execute_command = str;
  /
  • In case LILO is going to boot us with default command line,
  • it prepends “auto” before the whole cmdline which makes
  • the shell think it should execute a script with such name.
  • So we ignore all arguments entered before init=… [MJ]
    */
    for (i = 1; i < MAX_INIT_ARGS; i++)
    argv_init[i] = NULL;
    return 1;
    }
    __setup(“init=”, init_setup);
    static int __init rdinit_setup(char str)
    {
    unsigned int i;
    ramdisk_execute_command = str;
    / See “auto” comment in init_setup */
    for (i = 1; i < MAX_INIT_ARGS; i++)
    argv_init[i] = NULL;
    return 1;
    }
    __setup(“rdinit=”, rdinit_setup);

#ifndef CONFIG_SMP
static const unsigned int setup_max_cpus = NR_CPUS;
#ifdef CONFIG_X86_LOCAL_APIC
static void __init smp_init(void)
{
APIC_init_uniprocessor();
}
#else
#define smp_init() do { } while (0)
#endif
static inline void setup_nr_cpu_ids(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
#endif
/*

• We need to store the untouched command line for future reference.
• We also need to store the touched command line since the parameter
• parsing is performed in place, and we should allow a component to
• store reference of name/value for future reference.
  */
  static void __init setup_command_line(char command_line)
  {
  saved_command_line = alloc_bootmem(strlen (boot_command_line)+1);
  static_command_line = alloc_bootmem(strlen (command_line)+1);
  strcpy (saved_command_line, boot_command_line);
  strcpy (static_command_line, command_line);
  }
  /
• We need to finalize in a non-__init function or else race conditions
• between the root thread and the init thread may cause start_kernel to
• be reaped by free_initmem before the root thread has proceeded to
• cpu_idle.
• gcc-3.4 accidentally inlines this function, so use noinline.
  /
  static __initdata DECLARE_COMPLETION(kthreadd_done);
  static noinline void __init_refok rest_init(void)
  {
  int pid;
  rcu_scheduler_starting();//READ-COPY UPDATE启动
  /
  • 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.
  • 创建一个内核线程，它的线程函数是kernel_init,pid=1,内核进程
    /
    kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
    //numa策略设置
    numa_default_policy();
    //全局链表kthread_create_list中的kthread内核线程都被运行
    //kthreadd线程管理和调度其它内核线程
    pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
    rcu_read_lock();
    //通过pid,ini_pid_ns取得kthreadd地址
    kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
    rcu_read_unlock();
    //通知在kthreadd_done条件的kernel_init线程
    complete(&kthreadd_done);
    /
  • The boot idle thread must execute schedule()
  • at least once to get things moving:
  • idle 线程初始化
    /
    init_idle_bootup_task(current);
    //抢占禁用
    schedule_preempt_disabled();
    / Call into cpu_idle with preempt disabled /
    cpu_idle();
    }
    / Check for early params. */
    static int __init do_early_param(char *param, char *val)
    {
    const struct obs_kernel_param p;
    for (p = __setup_start; p < __setup_end; p++) {
    if ((p->early && parameq(param, p->str)) ||
    (strcmp(param, “console”) == 0 &&
    strcmp(p->str, “earlycon”) == 0)
    ) {
    if (p->setup_func(val) != 0)
    printk(KERN_WARNING
    “Malformed early option ‘%s’\n”, param);
    }
    }
    / We accept everything at this stage. */
    return 0;
    }
    void __init parse_early_options(char cmdline)
    {
    parse_args(“early options”, cmdline, NULL, 0, 0, 0, do_early_param);
    }
    / Arch code calls this early on, or if not, just before other parsing. /
    void __init parse_early_param(void)
    {
    static __initdata int done = 0;
    static __initdata char tmp_cmdline[COMMAND_LINE_SIZE];
    if (done)
    return;
    / All fall through to do_early_param. /
    strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
    parse_early_options(tmp_cmdline);
    done = 1;
    }
    /
• Activate the first processor.
  /
  static void __init boot_cpu_init(void)
  {
  int cpu = smp_processor_id();
  / Mark the boot cpu “present”, “online” etc for SMP and UP case /
  set_cpu_online(cpu, true);
  set_cpu_active(cpu, true);
  set_cpu_present(cpu, true);
  set_cpu_possible(cpu, true);
  }
  void __init __weak smp_setup_processor_id(void)
  {
  }
  void __init __weak thread_info_cache_init(void)
  {
  }
  /
• Set up kernel memory allocators
  /
  static void __init mm_init(void)
  {
  /
  • page_cgroup requires contiguous pages,
  • bigger than MAX_ORDER unless SPARSEMEM.
    /
    page_cgroup_init_flatmem();
    mem_init();
    kmem_cache_init();
    percpu_init_late();
    pgtable_cache_init();
    vmalloc_init();
    }
    asmlinkage void __init start_kernel(void)
    {
    char * command_line;
    extern const struct kernel_param __start___param[], __stop___param[];
    /
  • Need to run as early as possible, to initialize the
  • lockdep hash:
    /
    //初始化2个hash表-Lock Dependency Validator(内核依赖的关系表)
    lockdep_init();
    smp_setup_processor_id(); //空函数
    debug_objects_early_init();//初始化内核调试相关
    /
  • Set up the the initial canary ASAP:
    /
    boot_init_stack_canary();//栈溢出保护初始化
    //控制组初始化-cgroup-资源任务分组管理
    cgroup_init_early();
    local_irq_disable();//关中断
    early_boot_irqs_disabled = true;
    /
• Interrupts are still disabled. Do necessary setups, then
• enable them
  /
  tick_init();//时钟初始化
  boot_cpu_init();//启动cpu初始化
  page_address_init();//页面初始化
  printk(KERN_NOTICE “%s”, linux_banner);
  setup_arch(&command_line);//架构相关初始化
  mm_init_owner(&init_mm, &init_task);//内存管理初始化
  mm_init_cpumask(&init_mm);//内存管理初始化
  setup_command_line(command_line);//处理命令行(保存2份)
  setup_nr_cpu_ids();//cpuid相关
  setup_per_cpu_areas();//每cpu变量申请空间(包括gdt)
  //smp中用来启动的cpu
  smp_prepare_boot_cpu(); / arch-specific boot-cpu hooks /
  //建立系统内存页区链表
  build_all_zonelists(NULL);
  //内存页相关初始化
  page_alloc_init();
  printk(KERN_NOTICE “Kernel command line: %s\n”, boot_command_line);
  //命令行boot_command_line
  parse_early_param();
  //解析参数
  parse_args(“Booting kernel”, static_command_line, __start___param,
  __stop___param - __start___param,
  -1, -1, &unknown_bootoption);
  //
  jump_label_init();
  /
  • These use large bootmem allocations and must precede
  • kmem_cache_init()
  • 内存初始化相关
    /
    setup_log_buf(0);
    pidhash_init();
    vfs_caches_init_early();
    sort_main_extable();
    trap_init();
    mm_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.
  • 调度初始化
    /
    sched_init();
    /
  • Disable preemption - early bootup scheduling is extremely
  • fragile until we cpu_idle() for the first time.
  • 抢占禁用
    /
    preempt_disable();
    if (!irqs_disabled()) {
    printk(KERN_WARNING “start_kernel(): bug: interrupts were “
    “enabled very early, fixing it\n”);
    local_irq_disable();
    }
    idr_init_cache();//idr
    perf_event_init();//performance event
    rcu_init();//read-copy-update 机制
    radix_tree_init();//radix树机制
    / init some links before init_ISA_irqs() */
    early_irq_init();//中断请求
    init_IRQ();//中断请求
    prio_tree_init();//优先查找树
    init_timers();//时钟
    hrtimers_init();//High-resolution kernel timers高精度内核时钟
    softirq_init();//软中断
    timekeeping_init();//时间相关
    time_init();//时间
    profile_init();//分配内核性能统计保存的内存
    call_function_init();//smp中每cpu的call_single_queue初始化
    if (!irqs_disabled())
    printk(KERN_CRIT “start_kernel(): bug: interrupts were “
    “enabled early\n”);

  early_boot_irqs_disabled = false;//中断请求开
  local_irq_enable();//本地中断开
  kmem_cache_init_late();//kmem后期初始化
  /*

  • 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();//初始化系统控制台结构
    if (panic_later)
    panic(panic_later, panic_param);
    //锁依赖信息
    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) {
printk(KERN_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_cgroup_init();//control groups初始化
debug_objects_mem_init();//对象调试
kmemleak_init();//检测内核内存泄漏的功能
setup_per_cpu_pageset();//申请并初始化每cpu页set
numa_policy_init();//numa相关
if (late_time_init)
late_time_init();
//初始化每cpusched_clock_data=ktime_now
sched_clock_init();
calibrate_delay();//计算cpuMIPS百万条指令/s
pidmap_init();//pid进程id表初始化
anon_vma_init();//虚拟地址
#ifdef CONFIG_X86
if (efi_enabled)//efi bois
efi_enter_virtual_mode();
#endif
thread_info_cache_init();//申请thread_info的内存
cred_init();//credential健在分配
//根据物理内存大小，计算可创建进/线程数量
fork_init(totalram_pages);
proc_caches_init();//进程内存初始化
buffer_init();//页高速缓存
key_init();//红黑树内存，存keys
security_init();//安全相关
dbg_late_init();//调试相关
vfs_caches_init(totalram_pages);//虚拟文件系统初始化
signals_init();//sigqueue申请内存，信号系统
/ rootfs populating might need page-writeback /
page_writeback_init();//页回写
#ifdef CONFIG_PROC_FS
proc_root_init();//proc文件系统初始化
#endif
cgroup_init();//cgroup相关
cpuset_init();//cpuset相关
taskstats_init_early();//进程计数器
delayacct_init();//进程延时审计
check_bugs();//系统bug相关测试
//acpi总线
acpi_early_init(); / before LAPIC and SMP init /
sfi_init_late();//Simple Firmware Interface
//功能追踪初始化,一种调试工具
ftrace_init();
/ Do the rest non-__init’ed, we’re now alive /
rest_init();
}
/ Call all constructor functions linked into the kernel. */
static void __init do_ctors(void)
{
#ifdef CONFIG_CONSTRUCTORS
ctor_fn_t *fn = (ctor_fn_t *) __ctors_start;
for (; fn < (ctor_fn_t *) __ctors_end; fn++)
(*fn)();
#endif
}
bool initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
static char msgbuf[64];
static int __init_or_module do_one_initcall_debug(initcall_t fn)
{
ktime_t calltime, delta, rettime;
unsigned long long duration;
int ret;
printk(KERN_DEBUG “calling %pF @ %i\n”, fn, task_pid_nr(current));
calltime = ktime_get();
ret = fn();
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
printk(KERN_DEBUG “initcall %pF returned %d after %lld usecs\n”, fn,
ret, duration);
return ret;
}
int __init_or_module do_one_initcall(initcall_t fn)
{
int count = preempt_count();
int ret;
if (initcall_debug)
ret = do_one_initcall_debug(fn);
else
ret = fn();
msgbuf[0] = 0;
if (ret && ret != -ENODEV && initcall_debug)
sprintf(msgbuf, “error code %d “, ret);
if (preempt_count() != count) {
strlcat(msgbuf, “preemption imbalance “, sizeof(msgbuf));
preempt_count() = count;
}
if (irqs_disabled()) {
strlcat(msgbuf, “disabled interrupts “, sizeof(msgbuf));
local_irq_enable();
}
if (msgbuf[0]) {
printk(“initcall %pF returned with %s\n”, fn, msgbuf);
}
return ret;
}
extern initcall_t __initcall_start[];
extern initcall_t __initcall0_start[];
extern initcall_t __initcall1_start[];
extern initcall_t __initcall2_start[];
extern initcall_t __initcall3_start[];
extern initcall_t __initcall4_start[];
extern initcall_t __initcall5_start[];
extern initcall_t __initcall6_start[];
extern initcall_t __initcall7_start[];
extern initcall_t __initcall_end[];
static initcall_t *initcall_levels[] __initdata = {
__initcall0_start,
__initcall1_start,
__initcall2_start,
__initcall3_start,
__initcall4_start,
__initcall5_start,
__initcall6_start,
__initcall7_start,
__initcall_end,
};
static char *initcall_level_names[] __initdata = {
“early parameters”,
“core parameters”,
“postcore parameters”,
“arch parameters”,
“subsys parameters”,
“fs parameters”,
“device parameters”,
“late parameters”,
};
static void __init do_initcall_level(int level)
{
extern const struct kernel_param __start___param[], __stop___param[];
initcall_t *fn;
strcpy(static_command_line, saved_command_line);
parse_args(initcall_level_names[level],
static_command_line, __start___param,
__stop___param - __start___param,
level, level,
repair_env_string);
for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
do_one_initcall(fn);
}
static void __init do_initcalls(void)
{
int level;
for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
do_initcall_level(level);
}
/

• Ok, the machine is now initialized. None of the devices
• have been touched yet, but the CPU subsystem is up and
• running, and memory and process management works.
• Now we can finally start doing some real work..
  */
  static void __init do_basic_setup(void)
  {
  cpuset_init_smp();//smp cpuset相关
  usermodehelper_init();//khelper单线程工作队列
  shmem_init();//sheme机制
  driver_init();//驱动各子系统
  init_irq_proc();//proc中创建irq目录
  do_ctors();//内核中所有构造函数,介于.ctors段中的函数
  usermodehelper_enable();
  //所有编译进内核的驱动模块初始化函数
  do_initcalls();
  }
  static void __init do_pre_smp_initcalls(void)
  {
  initcall_t *fn;
  for (fn = __initcall_start; fn < __initcall0_start; fn++)
  do_one_initcall(*fn);

}
static void run_init_process(const char init_filename)
{
argv_init[0] = init_filename;
kernel_execve(init_filename, argv_init, envp_init);
}
/ This is a non __init function. Force it to be noinline otherwise gcc

• makes it inline to init() and it becomes part of init.text section
• 这是个非Init函数，防止gcc让它内联到init()，并成为Init.text段的一部分
  /
  static noinline int init_post(void)
  {
  / need to finish all async __init code before freeing the memory
  • 在释放init内存前，必须完成所有__init代码执行
    */
    async_synchronize_full();
    free_initmem();//释放init.*段中的内存
    //修改页表，保证只读数据段为只读属性read only
    mark_rodata_ro();
    //系统运行状态标志
    system_state = SYSTEM_RUNNING;
    //numa默认策略
    numa_default_policy();
    //当前进程不能被杀掉，只为它是init
    current->signal->flags |= SIGNAL_UNKILLABLE;
    //如果ramdisk_execute_command变量指定了init程序，执行它
    if (ramdisk_execute_command) {
    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.
  • 又一个程序，看能不能执行，如果不能，则执行下面4个之一
    */
    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”);
  //两个变量和4个init都不能成功执行，报错
  panic(“No init found. Try passing init= option to kernel. “
  “See Linux Documentation/init.txt for guidance.”);

}
static int __init kernel_init(void * unused)
{
/*
* Wait until kthreadd is all set-up.等待kthreadd的启动完成
/
wait_for_completion(&kthreadd_done);
/ Now the scheduler is fully set up and can do blocking allocations
*
/
gfp_allowed_mask = __GFP_BITS_MASK;
/
* init can allocate pages on any node
/
set_mems_allowed(node_states[N_HIGH_MEMORY]);
/
* init can run on any cpu.
/
set_cpus_allowed_ptr(current, cpu_all_mask);
//cad_pid为接收Ctrl-alt-del操作的INT信号的进程ID,设置成了init的pid
//说明init可接受这3个键
cad_pid = task_pid(current);
//smp系统准备、激活所有cpu
smp_prepare_cpus(setup_max_cpus);
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
//初始化设备驱动、内核模块
do_basic_setup();
/ Open the /dev/console on the rootfs, this should never fail
* 打开/dev/console设备
*/
if (sys_open((const char __user ) “/dev/console”, O_RDWR, 0) < 0)
printk(KERN_WARNING “Warning: unable to open an initial console.\n”);
/
* 复制两次标准输入0，一个是标准输入1，一个是标准错误2
/
(void) sys_dup(0);
(void) sys_dup(0);
/
* check if there is an early userspace init. If yes, let it do all
* the work
* 是否有早期用户空间init进程，有的话，让其执行
*/
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();
}
/
* 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..
*/
//启动用户空间的init进程
init_post();
return 0;
}