注:此文章主要基于展锐Android R代码加上学习总结自IngresGe大佬的分析
简要流程图:
kernel启动init
从源码解析
bsp/kernel/kernel4.14/init/main.c
head.S–>汇编指令跳转到此函数start_kernel(),调用rest_init()开启init和kthreadd进程
asmlinkage __visible void __init start_kernel(void)
{
//各种初始化
...
/* Do the rest non-__init'ed, we're now alive */
>>==rest_init()==<<;
prevent_tail_call_optimization();
}
rest_init()具体实现如下:
static noinline void __ref rest_init(void)
{
struct task_struct *tsk;
int pid;
//启动RCU机制,这个与后面的rcu_read_lock和rcu_read_unlock是配套的,用于多核同步
rcu_scheduler_starting();
/* 函数名既可以表示函数,也可以表示函数指针;kernel_init却作为参数传递了过去,其实传递过去的是一个函数指针
* 用kernel_thread方式创建init进程
* CLONE_FS 子进程与父进程共享相同的文件系统,包括root、当前目录、umask,CLONE_SIGHAND 子进程与父进程共享相同的信号处理(signal handler)表
*/
>>==pid = kernel_thread(kernel_init, NULL, CLONE_FS);==<<
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();
// 设定NUMA系统的默认内存访问策略
numa_default_policy();
//用kernel_thread方式创建kthreadd进程,CLONE_FILES 子进程与父进程共享相同的文件描述符(file descriptor)表
>>==pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);==<<
//打开RCU读取锁,在此期间无法进行进程切换
rcu_read_lock();
// 获取kthreadd的进程描述符,期间需要检索进程pid的使用链表,所以要加锁
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
//关闭RCU读取锁
rcu_read_unlock();
system_state = SYSTEM_SCHEDULING;
//complete和wait_for_completion是配套的同步机制,跟java的notify和wait差不多,
//之前kernel_init函数调用了wait_for_completion(&kthreadd_done),这里调用complete就是通知kernel_init进程kthreadd进程已创建完成,可以继续执行
complete(&kthreadd_done);
//0号进程主动请求调度,让出cpu,1号进程kernel_init将会运行,并且禁止抢占
schedule_preempt_disabled();
/* Call into cpu_idle with preempt disabled */
// 这个函数会调用cpu_idle_loop()使得idle进程进入自己的事件处理循环
cpu_startup_entry(CPUHP_ONLINE);
}
下面解析rest_init()中的各个函数:
bsp/kernel/kernel4.14/kernel/rcu/tree.c
void rcu_scheduler_starting(void)
{
//WARN_ON相当于警告,会打印出当前栈信息,不会重启,num_online_cpus表示当前启动的cpu数
WARN_ON(num_online_cpus() != 1);
//nr_context_switches 进行进程切换的次数
WARN_ON(nr_context_switches() > 0);
rcu_test_sync_prims();
//启用rcu机制
rcu_scheduler_active = RCU_SCHEDULER_INIT;
rcu_test_sync_prims();
}
/bsp/kernel/kernel4.14/kernel/fork.c
/*
* Create a kernel thread.
* C语言中 int (*fn)(void *)表示函数指针的定义,int是返回值,void是函数的参数,fn是名字
*/
pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
return _do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
(unsigned long)arg, NULL, NULL, 0);
}
do_fork函数用于创建进程,它首先调用copy_process()创建新进程,然后调用wake_up_new_task()将进程放入运行队列中并启动新进程。kernel_thread的第一个参数是一个函数指针,会在创建进程后执行,第三个参数是创建进程的方式,具体如下:
参数名 | 作用 |
---|---|
CLONE_PARENT | 创建的子进程的父进程是调用者的父进程,新进程与创建它的进程成了“兄弟”而不是“父子” |
CLONE_FS | 子进程与父进程共享相同的文件系统,包括root、当前目录、umask |
CLONE_FILES | 子进程与父进程共享相同的文件描述符(file descriptor)表 |
CLONE_NEWNS | 在新的namespace启动子进程,namespace描述了进程的文件hierarchy |
CLONE_SIGHAND | 子进程与父进程共享相同的信号处理(signal handler)表 |
CLONE_PTRACE | 若父进程被trace,子进程也被trace |
CLONE_UNTRACED | 若父进程被trace,子进程不被trace |
CLONE_VFORK | 父进程被挂起,直至子进程释放虚拟内存资源 |
CLONE_VM | 子进程与父进程运行于相同的内存空间 |
CLONE_PID | 子进程在创建时PID与父进程一致 |
CLONE_THREAD | Linux 2.4中增加以支持POSIX线程标准,子进程与父进程共享相同的线程群 |
_do_fork()函数如下:
long _do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr,
unsigned long tls)
{
struct task_struct *p;
int trace = 0;
long nr;
if (!(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
>>==p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);==<<
add_latent_entropy();
if (!IS_ERR(p)) {
struct completion vfork;
struct pid *pid;
cpufreq_task_times_alloc(p);
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
>>==wake_up_new_task(p);==<<
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
put_pid(pid);
} else {
nr = PTR_ERR(p);
}
return nr;
}
bsp/kernel/kernel4.14/mm/mempolicy.c
numa_default_policy():
/* Reset policy of current process to default */
void numa_default_policy(void)
{
//设定NUMA系统的内存访问策略为MPOL_DEFAULT
do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}
/* Set the process memory policy */
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
struct mempolicy *new, *old;
NODEMASK_SCRATCH(scratch);
int ret;
if (!scratch)
return -ENOMEM;
new = mpol_new(mode, flags, nodes);
if (IS_ERR(new)) {
ret = PTR_ERR(new);
goto out;
}
task_lock(current);
ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
task_unlock(current);
mpol_put(new);
goto out;
}
old = current->mempolicy;
current->mempolicy = new;
if (new && new->mode == MPOL_INTERLEAVE)
current->il_prev = MAX_NUMNODES-1;
task_unlock(current);
mpol_put(old);
ret = 0;
out:
NODEMASK_SCRATCH_FREE(scratch);
return ret;
}
bsp/kernel/kernel4.14/include/linux/rcupdate.h
RCU(Read-Copy Update)是数据同步的一种方式,在当前的Linux内核中发挥着重要的作用。RCU主要针对的数据对象是链表,目的是提高遍历读取数据的效率,为了达到目的使用RCU机制读取数据的时候不对链表进行耗时的加锁操作。这样在同一时间可以有多个线程同时读取该链表,并且允许一个线程对链表进行修改(修改的时候,需要加锁)
static __always_inline void rcu_read_lock(void)
{
__rcu_read_lock();
__acquire(RCU);
rcu_lock_acquire(&rcu_lock_map);
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_lock() used illegally while idle");
}
static inline void rcu_read_unlock(void)
{
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_unlock() used illegally while idle");
__release(RCU);
__rcu_read_unlock();
rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
}
bsp/kernel/kernel4.14/kernel/pid.c
task_struct叫进程描述符,这个结构体包含了一个进程所需的所有信息
find_task_by_pid_ns的作用就是根据pid,在hash表中获得对应pid的task_struct
/*
* Must be called under rcu_read_lock().
*/
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"find_task_by_pid_ns() needs rcu_read_lock() protection");
return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
struct upid *pnr;
hlist_for_each_entry_rcu(pnr,
&pid_hash[pid_hashfn(nr, ns)], pid_chain)
if (pnr->nr == nr && pnr->ns == ns)
return container_of(pnr, struct pid,
numbers[ns->level]);
return NULL;
}
struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result = NULL;
if (pid) {
struct hlist_node *first;
first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
lockdep_tasklist_lock_is_held());
if (first)
result = hlist_entry(first, struct task_struct, pids[(type)].node);
}
return result;
}
bsp/kernel/kernel4.14/kernel/sched/core.c
/**
* schedule_preempt_disabled - called with preemption disabled
*
* Returns with preemption disabled. Note: preempt_count must be 1
*/
void __sched schedule_preempt_disabled(void)
{
//开启内核抢占
sched_preempt_enable_no_resched();
//并主动请求调度,让出cpu
schedule();
//关闭内核抢占
preempt_disable();
}
bsp/kernel/kernel4.14/kernel/sched/idle.c
void cpu_startup_entry(enum cpuhp_state state)
{
/*
* This #ifdef needs to die, but it's too late in the cycle to
* make this generic (arm and sh have never invoked the canary
* init for the non boot cpus!). Will be fixed in 3.11
*/
#ifdef CONFIG_X86
/*
* If we're the non-boot CPU, nothing set the stack canary up
* for us. The boot CPU already has it initialized but no harm
* in doing it again. This is a good place for updating it, as
* we wont ever return from this function (so the invalid
* canaries already on the stack wont ever trigger).
*/
//只有在x86这种non-boot CPU机器上执行,该函数主要用于初始化stack_canary的值,用于防止栈溢出
boot_init_stack_canary();
#endif
//进行idle前的准备工作
arch_cpu_idle_prepare();
cpuhp_online_idle(state);
while (1)
do_idle();
}
idle进程是Linux系统的第一个进程,进程号是0,在完成系统环境初始化工作之后,开启了两个重要的进程,init进程和kthreadd进程,执行完创建工作之后,开启一个无限循环,负责进程的调度。
接下来分析kthreadd与init进程