fork之后发生了什么（基于3.16-rc4）

在linux c编程中，我们可以使用fork，vfork，clone三个系统调用来创建子进程。下面我们先分析下fork系统调用的实现原理。代码如下（kernel/fork.c）：

 #ifdef __ARCH_WANT_SYS_FORK
 SYSCALL_DEFINE0(fork)
 {
 #ifdef CONFIG_MMU
     return do_fork(SIGCHLD, , , NULL, NULL);
 #else
     /* can not support in nommu mode */
     return -EINVAL;
 #endif
 }
 #endif

看见了么，linux中系统调用就是这样定义的。可以看见fork系统调用是do_fork函数的一个封装，它会通过软中断（系统门）的形式跳到内核函数do_fork中。下面我们来分析下do_fork函数（kernel/fork.c）：

 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;
     int trace = ;
     long nr;
 
     /*
      * 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 = ;
     }
 
     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);
 
         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;
 }

第17-27行对函数接收到的标志进行判断，如果设置了追踪标志，则依据创建进程所使用的系统调用，在trace变量中放入不同的类型值。第29行创建子进程的描述符以及其他的数据结构，返回值为子进程的描述符指针，保存在变量p中，该函数可以说最核心的函数，待会来分析它。第35行，如果p指针没有出错，则进入if体。第41行获取子进程的pid号。第42行更新子进程的pid命名空间，并获得进程的pid号，存放在nr变量中。第44-45行，如果设置了CLONE_PARENT_SETTID标志，则将子进程的命名空间保存到父进程的一个用户态变量中，该变量的指针就是传进来的参数parent_tidptr。该函数中大部分是跟子进程追踪有关，我们暂且不分析这部分，主要分析下copy_process函数，代码如下（kernel/fork.c）：

 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;
 
     if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
         return ERR_PTR(-EINVAL);
 
     if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
         return ERR_PTR(-EINVAL);
 
     /*
      * Thread groups must share signals as well, and detached threads
      * can only be started up within the thread group.
      */
     if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
         return ERR_PTR(-EINVAL);
 
     /*
      * Shared signal handlers imply shared VM. By way of the above,
      * thread groups also imply shared VM. Blocking this case allows
      * for various simplifications in other code.
      */
     if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
         return ERR_PTR(-EINVAL);
 
     /*
      * Siblings of global init remain as zombies on exit since they are
      * not reaped by their parent (swapper). To solve this and to avoid
      * multi-rooted process trees, prevent global and container-inits
      * from creating siblings.
      */
     if ((clone_flags & CLONE_PARENT) &&
                 current->signal->flags & SIGNAL_UNKILLABLE)
         return ERR_PTR(-EINVAL);
 
     /*
      * If the new process will be in a different pid or user namespace
      * do not allow it to share a thread group or signal handlers or
      * parent with the forking task.
      */
     if (clone_flags & CLONE_SIGHAND) {
         if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
             (task_active_pid_ns(current) !=
                 current->nsproxy->pid_ns_for_children))
             return ERR_PTR(-EINVAL);
     }
 
     retval = security_task_create(clone_flags);
     if (retval)
         goto fork_out;
 
     retval = -ENOMEM;
     p = dup_task_struct(current);
     if (!p)
         goto fork_out;
 
     ftrace_graph_init_task(p);
     get_seccomp_filter(p);
 
     rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
     DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
     DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
     retval = -EAGAIN;
     if (atomic_read(&p->real_cred->user->processes) >=
             task_rlimit(p, RLIMIT_NPROC)) {
         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 < )
         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;
     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);
     p->flags |= PF_FORKNOEXEC;
     INIT_LIST_HEAD(&p->children);
     INIT_LIST_HEAD(&p->sibling);
     rcu_copy_process(p);
     p->vfork_done = NULL;
     spin_lock_init(&p->alloc_lock);
 
     init_sigpending(&p->pending);
 
     p->utime = p->stime = p->gtime = ;
     p->utimescaled = p->stimescaled = ;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
     p->prev_cputime.utime = p->prev_cputime.stime = ;
 #endif
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
     seqlock_init(&p->vtime_seqlock);
     p->vtime_snap = ;
     p->vtime_snap_whence = VTIME_SLEEPING;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)
     memset(&p->rss_stat, , sizeof(p->rss_stat));
 #endif
 
     p->default_timer_slack_ns = current->timer_slack_ns;
 
     task_io_accounting_init(&p->ioac);
     acct_clear_integrals(p);
 
     posix_cpu_timers_init(p);
 
     do_posix_clock_monotonic_gettime(&p->start_time);
     p->real_start_time = p->start_time;
     monotonic_to_bootbased(&p->real_start_time);
     p->io_context = NULL;
     p->audit_context = NULL;
     if (clone_flags & CLONE_THREAD)
         threadgroup_change_begin(current);
     cgroup_fork(p);
 #ifdef CONFIG_NUMA
     p->mempolicy = mpol_dup(p->mempolicy);
     if (IS_ERR(p->mempolicy)) {
         retval = PTR_ERR(p->mempolicy);
         p->mempolicy = NULL;
         goto bad_fork_cleanup_threadgroup_lock;
     }
 #endif
 #ifdef CONFIG_CPUSETS
     p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
     p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
     seqcount_init(&p->mems_allowed_seq);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
     p->irq_events = ;
     p->hardirqs_enabled = ;
     p->hardirq_enable_ip = ;
     p->hardirq_enable_event = ;
     p->hardirq_disable_ip = _THIS_IP_;
     p->hardirq_disable_event = ;
     p->softirqs_enabled = ;
     p->softirq_enable_ip = _THIS_IP_;
     p->softirq_enable_event = ;
     p->softirq_disable_ip = ;
     p->softirq_disable_event = ;
     p->hardirq_context = ;
     p->softirq_context = ;
 #endif
 #ifdef CONFIG_LOCKDEP
     p->lockdep_depth = ; /* no locks held yet */
     p->curr_chain_key = ;
     p->lockdep_recursion = ;
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
     p->blocked_on = NULL; /* not blocked yet */
 #endif
 #ifdef CONFIG_MEMCG
     p->memcg_batch.do_batch = ;
     p->memcg_batch.memcg = NULL;
 #endif
 #ifdef CONFIG_BCACHE
     p->sequential_io    = ;
     p->sequential_io_avg    = ;
 #endif
 
     /* Perform scheduler related setup. Assign this task to a CPU. */
     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_policy;
     /* copy all the process information */
     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;
     retval = copy_fs(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_files;
     retval = copy_sighand(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_fs;
     retval = copy_signal(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_sighand;
     retval = copy_mm(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_signal;
     retval = copy_namespaces(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_mm;
     retval = copy_io(clone_flags, p);
     if (retval)
         goto bad_fork_cleanup_namespaces;
     retval = copy_thread(clone_flags, stack_start, stack_size, p);
     if (retval)
         goto bad_fork_cleanup_io;
 
     if (pid != &init_struct_pid) {
         retval = -ENOMEM;
         pid = alloc_pid(p->nsproxy->pid_ns_for_children);
         if (!pid)
             goto bad_fork_cleanup_io;
     }
 
     p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
     /*
      * Clear TID on mm_release()?
      */
     p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
 #ifdef CONFIG_BLOCK
     p->plug = NULL;
 #endif
 #ifdef CONFIG_FUTEX
     p->robust_list = NULL;
 #ifdef CONFIG_COMPAT
     p->compat_robust_list = NULL;
 #endif
     INIT_LIST_HEAD(&p->pi_state_list);
     p->pi_state_cache = NULL;
 #endif
     /*
      * sigaltstack should be cleared when sharing the same VM
      */
     if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
         p->sas_ss_sp = p->sas_ss_size = ;
 
     /*
      * Syscall tracing and stepping should be turned off in the
      * child regardless of CLONE_PTRACE.
      */
     user_disable_single_step(p);
     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.. */
     p->pid = pid_nr(pid);
     if (clone_flags & CLONE_THREAD) {
         p->exit_signal = -;
         p->group_leader = current->group_leader;
         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);
         p->group_leader = p;
         p->tgid = p->pid;
     }
 
     p->nr_dirtied = ;
     p->nr_dirtied_pause =  >> (PAGE_SHIFT - );
     p->dirty_paused_when = ;
 
     p->pdeath_signal = ;
     INIT_LIST_HEAD(&p->thread_group);
     p->task_works = NULL;
 
     /*
      * Make it visible to the rest of the system, but dont wake it up yet.
      * Need tasklist lock for parent etc handling!
      */
     write_lock_irq(&tasklist_lock);
 
     /* CLONE_PARENT re-uses the old parent */
     if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
         p->real_parent = current->real_parent;
         p->parent_exec_id = current->parent_exec_id;
     } else {
         p->real_parent = current;
         p->parent_exec_id = current->self_exec_id;
     }
 
     spin_lock(&current->sighand->siglock);
 
     /*
      * Process group and session signals need to be delivered to just the
      * parent before the fork or both the parent and the child after the
      * fork. Restart if a signal comes in before we add the new process to
      * it's process group.
      * A fatal signal pending means that current will exit, so the new
      * thread can't slip out of an OOM kill (or normal SIGKILL).
     */
     recalc_sigpending();
     if (signal_pending(current)) {
         spin_unlock(&current->sighand->siglock);
         write_unlock_irq(&tasklist_lock);
         retval = -ERESTARTNOINTR;
         goto bad_fork_free_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)) {
             init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
             init_task_pid(p, PIDTYPE_SID, task_session(current));
 
             if (is_child_reaper(pid)) {
                 ns_of_pid(pid)->child_reaper = p;
                 p->signal->flags |= SIGNAL_UNKILLABLE;
             }
 
             p->signal->leader_pid = pid;
             p->signal->tty = tty_kref_get(current->signal->tty);
             list_add_tail(&p->sibling, &p->real_parent->children);
             list_add_tail_rcu(&p->tasks, &init_task.tasks);
             attach_pid(p, PIDTYPE_PGID);
             attach_pid(p, PIDTYPE_SID);
             __this_cpu_inc(process_counts);
         } else {
             current->signal->nr_threads++;
             atomic_inc(&current->signal->live);
             atomic_inc(&current->signal->sigcnt);
             list_add_tail_rcu(&p->thread_group,
                       &p->group_leader->thread_group);
             list_add_tail_rcu(&p->thread_node,
                       &p->signal->thread_head);
         }
         attach_pid(p, PIDTYPE_PID);
         nr_threads++;
     }
 
     total_forks++;
     spin_unlock(&current->sighand->siglock);
     syscall_tracepoint_update(p);
     write_unlock_irq(&tasklist_lock);
 
     proc_fork_connector(p);
     cgroup_post_fork(p);
     if (clone_flags & CLONE_THREAD)
         threadgroup_change_end(current);
     perf_event_fork(p);
 
     trace_task_newtask(p, clone_flags);
     uprobe_copy_process(p, clone_flags);
 
     return p;
 
 bad_fork_free_pid:
     if (pid != &init_struct_pid)
         free_pid(pid);
 bad_fork_cleanup_io:
     if (p->io_context)
         exit_io_context(p);
 bad_fork_cleanup_namespaces:
     exit_task_namespaces(p);
 bad_fork_cleanup_mm:
     if (p->mm)
         mmput(p->mm);
 bad_fork_cleanup_signal:
     if (!(clone_flags & CLONE_THREAD))
         free_signal_struct(p->signal);
 bad_fork_cleanup_sighand:
     __cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
     exit_fs(p); /* blocking */
 bad_fork_cleanup_files:
     exit_files(p); /* blocking */
 bad_fork_cleanup_semundo:
     exit_sem(p);
 bad_fork_cleanup_audit:
     audit_free(p);
 bad_fork_cleanup_policy:
     perf_event_free_task(p);
 #ifdef CONFIG_NUMA
     mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
     if (clone_flags & CLONE_THREAD)
         threadgroup_change_end(current);
     delayacct_tsk_free(p);
     module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
     atomic_dec(&p->cred->user->processes);
     exit_creds(p);
 bad_fork_free:
     free_task(p);
 fork_out:
     return ERR_PTR(retval);
 }

copy_process

第11-52行对传递进来的clone_flags标志进行一致性检查，如果有错误，返回错误代码。第54行对clone_flags进行附加性安全检查。第59行为子进程创建进程描述符。第63行，这个版本的linux内核源码中该函数为空函数，不研究它。第64行增加子进程p的seccomp.filter结构体成员的引用数量。第66行初始化子进程中的互斥锁。第73-77行比较子进程的拥有者所拥有的进程数量是否超过限制，如果超过了限制并且该拥有者不是root用户，就会跳到错误处理代码。第81行将父进程的拥有者信息拷贝给子进程。第91行检查系统中的进程数量是否超过了限制，nr_threads是内核中的全局变量，存放着进程的总数。第94行检查子进程的执行域（要执行的代码）所在的模块是否已经加载进了内核，如果没有的话就进行出错处理。第98-99行对子进程flags进程初始化。第100-101对子进程的孩子链表和兄弟链表进行初始化。第102行初始化子进程的rcu（一种锁机制）。第104行初始化子进程的alloc_lock自旋锁。第106行初始化进程的挂起信号集。第108-116对进行的各种时间进程初始化。第125行初始化子进程的io计数。第126行对子进程的多个计数域进行清零。第128行初始化子进程的定时器。第185-222行，使用了多个copy_***函数创建了子进程要用的各种数据结构，并将父进程的相应结构体中的内容拷贝进来，或者根据flags指定的内容来初始化子进程的这些数据结构。第224-228行，如果传进来的pid指针和全局结构体变量init_struct_pid的地址不相同的话，就要为子进程分配pid结构体。第265行从pid结构体中获取到子进程的pid号，保存到子进程描述符的pid域。第266-269行，如果设置了CLONE_THREAD标志，说明子进程和父进程在同一个线程组，那么子进程将继承父进程的tgid，否则第275-276行，子进程的组领导者就是它自己，组号tgpid是它自己的pid号。第279-281行设置一些和进程脏页限制有关的成员。下面291-356行的代码需要关掉中断并且获取写锁。第294-296行对进程亲子关系初始化，如果设置了CLONE_PARENT和CLONE_THREAD标志，子进程的真实父进程设置为它的父进程的真实父进程（它的爷爷进程）,否则第298-299行，子进程的真实父进程设置为它的父进程。第302行-354行需要获取自旋锁。第321行初始化子进程的ptraced字段（和进程追踪有关）。第323行，对子进程的pid结构体进行初始化。第324-340行，如果子进程是线程组的组长，则对子进程进行相应处理，其中，第325-326行将子进程的进程组和会话组的组长分别设置为父进程的组领导的进程组和会话组组长，第337-338行，将子进程加入它所在组的哈希链表中。否则，子进程不是线程组组长的话，第341-347行不对子进程做pid相关的操作。第349行，同样要将子进程加入到pid哈希表中。第350行全局变量nr_threads自加1，说明系统中的进程又多了一个。如果整个函数内部没有出错的话，第367行返回创建好的子进程描述符指针p。第369行到结束，均为错误处理的代码，如果函数中有出错的地方，就会跳到这些代码中。
下面我们接着分析第59行的dup_task_struct函数，代码如下（kernel/fork.c）：

 static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
     struct task_struct *tsk;
     struct thread_info *ti;
     unsigned long *stackend;
     int node = tsk_fork_get_node(orig);
     int err;
 
     tsk = alloc_task_struct_node(node);
     if (!tsk)
         return NULL;
 
     ti = alloc_thread_info_node(tsk, node);
     if (!ti)
         goto free_tsk;
 
     err = arch_dup_task_struct(tsk, orig);
     if (err)
         goto free_ti;
 
     tsk->stack = ti;
 
     setup_thread_stack(tsk, orig);
     clear_user_return_notifier(tsk);
     clear_tsk_need_resched(tsk);
     stackend = end_of_stack(tsk);
     *stackend = STACK_END_MAGIC;    /* for overflow detection */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
     tsk->stack_canary = get_random_int();
 #endif
 
     /*
      * One for us, one for whoever does the "release_task()" (usually
      * parent)
      */
     atomic_set(&tsk->usage, );
 #ifdef CONFIG_BLK_DEV_IO_TRACE
     tsk->btrace_seq = ;
 #endif
     tsk->splice_pipe = NULL;
     tsk->task_frag.page = NULL;
 
     account_kernel_stack(ti, );
 
     return tsk;
 
 free_ti:
     free_thread_info(ti);
 free_tsk:
     free_task_struct(tsk);
     return NULL;
 }

在该函数中创建了子进程的进程描述符，并将描述符指针返回。第6行，如果使用到了NUMA技术的话，函数返回父进程描述符的pref_node_fork字段值，否则，返回-1。第9行为子进程创建进程描述符，将描述符指针保存在tsk变量中。第13行为子进程创建thread_info结构体（也就是创建内核栈），并返回结构体指针（该指针实际上也是子进程堆栈的内核栈指针）。第17行将父进程描述符的各个成员值全部复制给子进程描述符的成员。第21行将子进程内核栈地址ti赋给stack成员。第23行对子进程的thread_info结构体进行初始化，将父进程的该结构体成员值复制给子进程，然后将子进程的描述符指针存入thread_info结构体的task域（从thread_info就可找到进程描述符了）。第25行清除子进程thread_info结构体中的flag标志（具体而言，就是need_resched标志，取消内核抢占）。第26行将自进程内核栈顶指针保存到stackend变量中。第27行向子进程内核堆栈中存入STACK_END_MAGIC，来进行堆栈溢出检测。第23行将子进程描述符使用计数置为2（一个表示父进程的引用，一个表示自己）。第44行将子进程的内核栈所在的zone结构体使用计数置为1。第46行返回子进程描述符指针。接下来，我们回到do_fork函数中，第53行wake_up_new_task函数会将刚创建好的子进程加入到运行队列中并且唤醒它，下面看看该函数（kernel/sched/core.c）。

 void wake_up_new_task(struct task_struct *p)
 {
     unsigned long flags;
     struct rq *rq;
 
     raw_spin_lock_irqsave(&p->pi_lock, flags);
 #ifdef CONFIG_SMP
     /*
      * Fork balancing, do it here and not earlier because:
      *  - cpus_allowed can change in the fork path
      *  - any previously selected cpu might disappear through hotplug
      */
     set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, ));
 #endif
 
     /* Initialize new task's runnable average */
     init_task_runnable_average(p);
     rq = __task_rq_lock(p);
     activate_task(rq, p, );
     p->on_rq = ;
     trace_sched_wakeup_new(p, true);
     check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
     if (p->sched_class->task_woken)
         p->sched_class->task_woken(rq, p);
 #endif
     task_rq_unlock(rq, p, &flags);
 }

该函数暂且放到这里，带我把进程调度这块的博文完成之后，再完善这里。该函数执行完后，第68行父进程返回子进程的pid号，回到do_fork中，子进程创建的工作就完成了。此后父子进程公平的参与进程调度。