sched_fork过程分析

sched_fork包含的主要过程

设置子进程类型为TASK_NEW

设置子进程的优先级为父进程的优先级

设置子进程的调度类为CFS

更新新进程的虚拟实际vruntime

根据实际情况，对新进程vruntime进行一些惩罚

最后唤醒进程

源码分析

sched_fork() -> __sched_fork()

< kernel/sched/core.c >

/*
 * fork()/clone()-time setup:
 */
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
	__sched_fork(clone_flags, p);
	/*
	 * We mark the process as NEW here. This guarantees that
	 * nobody will actually run it, and a signal or other external
	 * event cannot wake it up and insert it on the runqueue either.
	 */
	p->__state = TASK_NEW;                 /*  TASK_NEW表示新进程 */

	/*
	 * Make sure we do not leak PI boosting priority to the child.
	 */
	p->prio = current->normal_prio;     /* 设置子进程的优先级为父进程的优先级 */

	uclamp_fork(p);

	/*
	 * Revert to default priority/policy on fork if requested.
	 */
	if (unlikely(p->sched_reset_on_fork)) {
		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
			p->policy = SCHED_NORMAL;
			p->static_prio = NICE_TO_PRIO(0);
			p->rt_priority = 0;
		} else if (PRIO_TO_NICE(p->static_prio) < 0)
			p->static_prio = NICE_TO_PRIO(0);

		p->prio = p->normal_prio = p->static_prio;
		set_load_weight(p, false);

		/*
		 * We don't need the reset flag anymore after the fork. It has
		 * fulfilled its duty:
		 */
		p->sched_reset_on_fork = 0;
	}

	if (dl_prio(p->prio))
		return -EAGAIN;
	else if (rt_prio(p->prio))
		p->sched_class = &rt_sched_class;
	else
		p->sched_class = &fair_sched_class;                              /* 设置子进程的调度类为CFS */

	init_entity_runnable_average(&p->se);                                /* 初始化与子进程调度实体se相关的成员 */


#ifdef CONFIG_SCHED_INFO
	if (likely(sched_info_on()))
		memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
	p->on_cpu = 0;
#endif
	init_task_preempt_count(p);
#ifdef CONFIG_SMP
	plist_node_init(&p->pushable_tasks, MAX_PRIO);
	RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
	return 0;
}

__sched_fork()代码如下，可见，基本就是把所有值赋值默认值

< kernel/sched/core.c >

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
{
	p->on_rq			= 0;

	p->se.on_rq			= 0;
	p->se.exec_start		= 0;
	p->se.sum_exec_runtime		= 0;
	p->se.prev_sum_exec_runtime	= 0;
	p->se.nr_migrations		= 0;
	p->se.vruntime			= 0;
	INIT_LIST_HEAD(&p->se.group_node);

#ifdef CONFIG_FAIR_GROUP_SCHED
	p->se.cfs_rq			= NULL;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* Even if schedstat is disabled, there should not be garbage */
	memset(&p->stats, 0, sizeof(p->stats));
#endif

	RB_CLEAR_NODE(&p->dl.rb_node);
	init_dl_task_timer(&p->dl);
	init_dl_inactive_task_timer(&p->dl);
	__dl_clear_params(p);

	INIT_LIST_HEAD(&p->rt.run_list);
	p->rt.timeout		= 0;
	p->rt.time_slice	= sched_rr_timeslice;
	p->rt.on_rq		= 0;
	p->rt.on_list		= 0;

#ifdef CONFIG_PREEMPT_NOTIFIERS
	INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif

#ifdef CONFIG_COMPACTION
	p->capture_control = NULL;
#endif
	init_numa_balancing(clone_flags, p);
#ifdef CONFIG_SMP
	p->wake_entry.u_flags = CSD_TYPE_TTWU;
	p->migration_pending = NULL;
#endif
}

task_fork_fair的定义在DEFINE_SCHED_CLASS(fair)

< kernel/sched/fair.c >

/*
 * All the scheduling class methods:
 */
DEFINE_SCHED_CLASS(fair) = {

	.enqueue_task		= enqueue_task_fair,
	.dequeue_task		= dequeue_task_fair,
	.yield_task		= yield_task_fair,
	.yield_to_task		= yield_to_task_fair,

	.check_preempt_curr	= check_preempt_wakeup,

	.pick_next_task		= __pick_next_task_fair,
	.put_prev_task		= put_prev_task_fair,
	.set_next_task          = set_next_task_fair,

#ifdef CONFIG_SMP
	.balance		= balance_fair,
	.pick_task		= pick_task_fair,
	.select_task_rq		= select_task_rq_fair,
	.migrate_task_rq	= migrate_task_rq_fair,

	.rq_online		= rq_online_fair,
	.rq_offline		= rq_offline_fair,

	.task_dead		= task_dead_fair,
	.set_cpus_allowed	= set_cpus_allowed_common,
#endif

	.task_tick		= task_tick_fair,
	.task_fork		= task_fork_fair,                 /* CFS 对应的task_fork回调 */

	.prio_changed		= prio_changed_fair,
	.switched_from		= switched_from_fair,
	.switched_to		= switched_to_fair,

	.get_rr_interval	= get_rr_interval_fair,

	.update_curr		= update_curr_fair,

#ifdef CONFIG_FAIR_GROUP_SCHED
	.task_change_group	= task_change_group_fair,
#endif

#ifdef CONFIG_UCLAMP_TASK
	.uclamp_enabled		= 1,
#endif
};

所以，在cfs对应的函数就是task_fork_fair()

task_fork_fair() ->

< kernel/sched/fair.c >

/*
 * called on fork with the child task as argument from the parent's context
 *  - child not yet on the tasklist
 *  - preemption disabled
 */
static void task_fork_fair(struct task_struct *p)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se, *curr;
	struct rq *rq = this_rq();
	struct rq_flags rf;

	rq_lock(rq, &rf);
	update_rq_clock(rq);

	cfs_rq = task_cfs_rq(current);              /* cfs_rq表示CFS调度器就绪队列 */
	curr = cfs_rq->curr;
	if (curr) {
		update_curr(cfs_rq);                    /* 更新当前正在运行的调度实体的运行时间，比如sum_exec_runtime，vruntime 都在这里更新 */
		se->vruntime = curr->vruntime;          /* 初始化当新进程的虚拟时间,这里直接使用了当前进程vruntime，后面会修改这个值 */
	}
	place_entity(cfs_rq, se, 1);                /* 对新进程的虚拟时间进行一定的惩罚 */

	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
		/*
		 * Upon rescheduling, sched_class::put_prev_task() will place
		 * 'current' within the tree based on its new key value.
		 */
		swap(curr->vruntime, se->vruntime);
		resched_curr(rq);
	}

	se->vruntime -= cfs_rq->min_vruntime;
	rq_unlock(rq, &rf);
}

place_entity()的行为不是很好理解，为什么要惩罚新进程vruntime

创建进程的时候传递参数initial=1,惩罚的原因是为了防止新进程恶意占用CPU时间

代码如下

< kernel/sched/fair.c >

static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
	u64 vruntime = cfs_rq->min_vruntime;
	u64 sleep_time;

	/*
	 * The 'current' period is already promised to the current tasks,
	 * however the extra weight of the new task will slow them down a
	 * little, place the new task so that it fits in the slot that
	 * stays open at the end.
	 */
	if (initial && sched_feat(START_DEBIT))
		vruntime += sched_vslice(cfs_rq, se);

	/* sleeps up to a single latency don't count. */
	if (!initial) {
		unsigned long thresh;

		if (se_is_idle(se))
			thresh = sysctl_sched_min_granularity;
		else
			thresh = sysctl_sched_latency;

		/*
		 * Halve their sleep time's effect, to allow
		 * for a gentler effect of sleepers:
		 */
		if (sched_feat(GENTLE_FAIR_SLEEPERS))
			thresh >>= 1;

		vruntime -= thresh;
	}

	/*
	 * Pull vruntime of the entity being placed to the base level of
	 * cfs_rq, to prevent boosting it if placed backwards.  If the entity
	 * slept for a long time, don't even try to compare its vruntime with
	 * the base as it may be too far off and the comparison may get
	 * inversed due to s64 overflow.
	 */
	sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
	if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
		se->vruntime = vruntime;
	else
		se->vruntime = max_vruntime(se->vruntime, vruntime);
}

init_entity_runnable_average() 函数初始化与子进程调度实体se相关的成员

< kernel/sched/fair.c >

/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
{
	struct sched_avg *sa = &se->avg;

	memset(sa, 0, sizeof(*sa));

	/*
	 * Tasks are initialized with full load to be seen as heavy tasks until
	 * they get a chance to stabilize to their real load level.
	 * Group entities are initialized with zero load to reflect the fact that
	 * nothing has been attached to the task group yet.
	 */
	if (entity_is_task(se))
		sa->load_avg = scale_load_down(se->load.weight);

	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}

最后是唤醒新进程,将新进程加入运行队列，唤醒进程会单独拿出一个章节进行讲解，所以这里只是贴出wake_up_new_task()代码

< kernel/sched/core.c >

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */
void wake_up_new_task(struct task_struct *p)
{
	struct rq_flags rf;
	struct rq *rq;

	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
	WRITE_ONCE(p->__state, TASK_RUNNING);
#ifdef CONFIG_SMP
	/*
	 * Fork balancing, do it here and not earlier because:
	 *  - cpus_ptr can change in the fork path
	 *  - any previously selected CPU might disappear through hotplug
	 *
	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
	 * as we're not fully set-up yet.
	 */
	p->recent_used_cpu = task_cpu(p);
	rseq_migrate(p);
	__set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK));
#endif
	rq = __task_rq_lock(p, &rf);
	update_rq_clock(rq);
	post_init_entity_util_avg(p);

	activate_task(rq, p, ENQUEUE_NOCLOCK);
	trace_sched_wakeup_new(p);
	check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
	if (p->sched_class->task_woken) {
		/*
		 * Nothing relies on rq->lock after this, so it's fine to
		 * drop it.
		 */
		rq_unpin_lock(rq, &rf);
		p->sched_class->task_woken(rq, p);
		rq_repin_lock(rq, &rf);
	}
#endif
	task_rq_unlock(rq, p, &rf);
}