init 进程号称天字一号进程,做系统的小伙伴应该都有了解。那么,这个一号进程是如何被启动的呢? 今天就来一起简单看看这个进程的前世今生。
因为目前运行Linux最多的就是ARM设备了,我们就基于Linux的master分支简单分析下ARM 32架构下的启动过程。
kernel的执行起点是stext函数,定义于arch/arm/kernel/head.S。我们就从这个函数开始看看init如何被启动的。
ENTRY(stext)
......
/*这里将__mmap_switched 函数的地址赋给了r13寄存器,
这个函数会在MMU被使能之后执行。
MMU是Memory Management Unit的缩写,中文名是内存管理单元,
同时也负责虚拟地址映射为物理地址,以及提供硬件机制的内存访问授权*/
ldr r13, =__mmap_switched @ address to jump to after
@ mmu has been enabled
badr lr, 1f @ return (PIC) address
......
/*接下来执行__enable_mmu 函数*/
1: b __enable_mmu
ENDPROC(stext)
下面来看__enable_mmu 函数做了什么
__enable_mmu:
......
/*主要调用了__turn_mmu_on 来打开MMU ,让CPU进入虚拟内存的运行阶段。*/
b __turn_mmu_on
ENDPROC(__enable_mmu)
ENTRY(__turn_mmu_on)
......
/*这里将r13保存的函数地址赋给PC指针,即IP寄存器。 RET指令的内部操作是:栈顶字单元出栈,其值赋给IP寄存器*/
mov r3, r13
ret r3
__turn_mmu_on_end:
ENDPROC(__turn_mmu_on)
接下来就是运行__mmap_switched 方法的事情了。那我们就来看看__mmap_switched 是怎样的。这个方法位于arch/arm/kernel/head-common.S
__INIT
__mmap_switched:
......
/*这么愉快地就要跳转到start_kernel 了,马上就进入了C的世界*/
b start_kernel
ENDPROC(__mmap_switched)
start_kernel 位于init/main.c
asmlinkage __visible void __init start_kernel(void)
{
......
/*start_kernel会进行一堆初始化的工作。最后通过rest_init来启动init进程*/
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
static noinline void __ref rest_init(void)
{
struct task_struct *tsk;
int pid;
rcu_scheduler_starting();
//这里会先创建init进程,保证它的PID为1,不过会停下等待kthreadd的创建。
//kernel_init-》kernel_init_freeable-》wait_for_completion(&kthreadd_done)
//kthreadd进程由idle通过kernel_thread创建,并始终运行在内核空间, 负责所有内核线程的调度和管理
/*
* 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();
//创建kthreadd,获取kthreadd线程信息,获取完成,说明创建成功
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_PRREMPT=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;
//通知kernel_init kthreadd创建完成
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);
}
接下来看kernel_init如何启动init
static int __ref kernel_init(void *unused)
{
int ret;
kernel_init_freeable();
/* 在释放内存前,必须完成所有的异步 __init 代码
need to finish all async __init code before freeing the memory */
async_synchronize_full();
//释放init内存
free_initmem();
mark_readonly();
system_state = SYSTEM_RUNNING;
//设置numa内存访问策略为默认, NUMA技术主要用于服务器
numa_default_policy();
rcu_end_inkernel_boot();
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);
}
//下面就是运行init程序了,会尝试所有可能的情况,包括init启动时候的参数,和各个目录下的init文件/sbin/init /etc/init等, 最终调用do_execve去执行init文件。
/*
* 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/admin-guide/init.rst for guidance.");
}
就这样, init进程就被执行起来了。 不过到目前为止,init进程依然是一个内核进程,怎么变成用户空间进程的事情是在init程序里面实现的,这个每个不同的Linux发行版有不同的操作。不在本文讨论范围内。
完。