long do_fork(unsigned long clone_flags,
          unsigned long stack_start,
          unsigned long stack_size,
          int __user *parent_tidptr,
          int __user *child_tidptr)
{
    struct task_struct *p; //进程描述符结构体指针
    int trace = 0;
    long nr; //总的pid数量

    /*
     * Determine whether and which event to report to ptracer.  When
     * called from kernel_thread or CLONE_UNTRACED is explicitly
     * requested, no event is reported; otherwise, report if the event
     * for the type of forking is enabled.
     */
    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;
    }

    // 复制进程描述符，返回创建的task_struct的指针
    p = copy_process(clone_flags, stack_start, stack_size,
             child_tidptr, NULL, trace);
    /*
     * Do this prior waking up the new thread - the thread pointer
     * might get invalid after that point, if the thread exits quickly.
     */
    if (!IS_ERR(p)) {
        struct completion vfork;
        struct pid *pid;

        trace_sched_process_fork(current, p);

        // 取出task结构体内的pid
        pid = get_task_pid(p, PIDTYPE_PID);
        nr = pid_vnr(pid);

        if (clone_flags & CLONE_PARENT_SETTID)
            put_user(nr, parent_tidptr);

        // 如果使用的是vfork，那么必须采用某种完成机制，确保父进程后运行
        if (clone_flags & CLONE_VFORK) {
            p->vfork_done = &vfork;
            init_completion(&vfork);
            get_task_struct(p);
        }

        // 将子进程添加到调度器的队列，使得子进程有机会获得CPU
        wake_up_new_task(p);

        /* forking complete and child started to run, tell ptracer */
        if (unlikely(trace))
            ptrace_event_pid(trace, pid);

        // 如果设置了 CLONE_VFORK 则将父进程插入等待队列，并挂起父进程直到子进程释放自己的内存空间
        // 保证子进程优先于父进程运行
        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;
}

/*
    创建进程描述符以及子进程所需要的其他所有数据结构
    为子进程准备运行环境
*/
static struct task_struct *copy_process(unsigned long clone_flags,
                    unsigned long stack_start,
                    unsigned long stack_size,
                    int __user *child_tidptr,
                    struct pid *pid,
                    int trace)
{
    ...
    int retval;
    struct task_struct *p;

    ...
    // 分配一个新的task_struct，此时的p与当前进程的task，仅仅是stack地址不同
    p = dup_task_struct(current);
    if (!p)
        goto fork_out;

    ···
    
    retval = -EAGAIN;
    // 检查该用户的进程数是否超过限制
    if (atomic_read(&p->real_cred->user->processes) >=
            task_rlimit(p, RLIMIT_NPROC)) {
        // 检查该用户是否具有相关权限，不一定是root
        if (p->real_cred->user != INIT_USER &&
            !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
            goto bad_fork_free;
    }
    current->flags &= ~PF_NPROC_EXCEEDED;

    retval = copy_creds(p, clone_flags);
    if (retval < 0)
        goto bad_fork_free;

    /*
     * If multiple threads are within copy_process(), then this check
     * triggers too late. This doesn't hurt, the check is only there
     * to stop root fork bombs.
     */
    retval = -EAGAIN;
    // 检查进程数量是否超过 max_threads，后者取决于内存的大小
    if (nr_threads >= max_threads)
        goto bad_fork_cleanup_count;

    if (!try_module_get(task_thread_info(p)->exec_domain->module))
        goto bad_fork_cleanup_count;

    delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
    p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
    // 表明子进程还没有调用exec系统调用
    p->flags |= PF_FORKNOEXEC;
    INIT_LIST_HEAD(&p->children);
    INIT_LIST_HEAD(&p->sibling);
    rcu_copy_process(p);
    p->vfork_done = NULL;

    // 初始化自旋锁
    spin_lock_init(&p->alloc_lock);

    // 初始化挂起信号
    init_sigpending(&p->pending);

    // 初始化定时器
    p->utime = p->stime = p->gtime = 0;
    p->utimescaled = p->stimescaled = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
    p->prev_cputime.utime = p->prev_cputime.stime = 0;
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
    seqlock_init(&p->vtime_seqlock);
    p->vtime_snap = 0;
    p->vtime_snap_whence = VTIME_SLEEPING;
#endif

    ...

#ifdef CONFIG_DEBUG_MUTEXES
    p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
    p->sequential_io    = 0;
    p->sequential_io_avg    = 0;
#endif

    /* Perform scheduler related setup. Assign this task to a CPU. */
    
    // 完成对新进程调度程序数据结构的初始化，并把新进程的状态设置为TASK_RUNNING
    // 同时将thread_info中得preempt_count置为1，禁止内核抢占
    retval = sched_fork(clone_flags, p);
    if (retval)
        goto bad_fork_cleanup_policy;

    retval = perf_event_init_task(p);
    if (retval)
        goto bad_fork_cleanup_policy;
    retval = audit_alloc(p);
    if (retval)
        goto bad_fork_cleanup_perf;
    /* copy all the process information */

    // 复制所有的进程信息
    shm_init_task(p);
    retval = copy_semundo(clone_flags, p);
    if (retval)
        goto bad_fork_cleanup_audit;
    retval = copy_files(clone_flags, p);
    if (retval)
        goto bad_fork_cleanup_semundo;
        
    ...

    // 初始化子进程的内核栈
    retval = copy_thread(clone_flags, stack_start, stack_size, p);
    if (retval)
        goto bad_fork_cleanup_io;

    if (pid != &init_struct_pid) {
        retval = -ENOMEM;
        // 这里为子进程分配了新的pid号
        pid = alloc_pid(p->nsproxy->pid_ns_for_children);
        if (!pid)
            goto bad_fork_cleanup_io;
    }

    ...
    
    // 清除子进程thread_info结构的 TIF_SYSCALL_TRACE，防止 ret_from_fork将系统调用消息通知给调试进程
    clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
    clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
    clear_all_latency_tracing(p);

    /* ok, now we should be set up.. */
    
    // 设置子进程的pid
    p->pid = pid_nr(pid);
    
    // 如果是创建线程
    if (clone_flags & CLONE_THREAD) {
        p->exit_signal = -1;
        
        // 线程组的leader设置为当前线程的leader
        p->group_leader = current->group_leader;
        
        // tgid是当前线程组的id，也就是main进程的pid
        p->tgid = current->tgid;
    } else {
        if (clone_flags & CLONE_PARENT)
            p->exit_signal = current->group_leader->exit_signal;
        else
            p->exit_signal = (clone_flags & CSIGNAL);
            
        // 创建的是进程，自己是一个单独的线程组
        p->group_leader = p;
        
        // tgid和pid相同
        p->tgid = p->pid;
    }

    ...
    
    if (likely(p->pid)) {
        ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);

        init_task_pid(p, PIDTYPE_PID, pid);
        if (thread_group_leader(p)) {

            ...
            
            // 将pid加入散列表
            attach_pid(p, PIDTYPE_PGID);
            attach_pid(p, PIDTYPE_SID);
            __this_cpu_inc(process_counts);
        } else {

            ...

        }
        // 将pid加入PIDTYPE_PID这个散列表
        attach_pid(p, PIDTYPE_PID);