CFS Infrastructures: rq, task_struct, cfs_rq, sched_entity etc. 筆記 (3)

cfs_rq

/* CFS-related fields in a runqueue */
struct cfs_rq {
	struct load_weight	load;
	unsigned int		nr_running;
	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
	unsigned int		idle_nr_running;   /* SCHED_IDLE */
	unsigned int		idle_h_nr_running; /* SCHED_IDLE */

	s64			avg_vruntime;
	u64			avg_load;

	u64			exec_clock;
	u64			min_vruntime;
#ifdef CONFIG_SCHED_CORE
	unsigned int		forceidle_seq;
	u64			min_vruntime_fi;
#endif

#ifndef CONFIG_64BIT
	u64			min_vruntime_copy;
#endif

	struct rb_root_cached	tasks_timeline;

	/*
	 * 'curr' points to currently running entity on this cfs_rq.
	 * It is set to NULL otherwise (i.e when none are currently running).
	 */
	struct sched_entity	*curr;
	struct sched_entity	*next;

#ifdef	CONFIG_SCHED_DEBUG
	unsigned int		nr_spread_over;
#endif

#ifdef CONFIG_SMP
	/*
	 * CFS load tracking
	 */
	struct sched_avg	avg;
#ifndef CONFIG_64BIT
	u64			last_update_time_copy;
#endif
	struct {
		raw_spinlock_t	lock ____cacheline_aligned;
		int		nr;
		unsigned long	load_avg;
		unsigned long	util_avg;
		unsigned long	runnable_avg;
	} removed;

#ifdef CONFIG_FAIR_GROUP_SCHED
	u64			last_update_tg_load_avg;
	unsigned long		tg_load_avg_contrib;
	long			propagate;
	long			prop_runnable_sum;

	/*
	 *   h_load = weight * f(tg)
	 *
	 * Where f(tg) is the recursive weight fraction assigned to
	 * this group.
	 */
	unsigned long		h_load;
	u64			last_h_load_update;
	struct sched_entity	*h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#endif /* CONFIG_SMP */

#ifdef CONFIG_FAIR_GROUP_SCHED
	struct rq		*rq;	/* CPU runqueue to which this cfs_rq is attached */

	/*
	 * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
	 * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
	 * (like users, containers etc.)
	 *
	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a CPU.
	 * This list is used during load balance.
	 */
	int			on_list;
	struct list_head	leaf_cfs_rq_list;
	struct task_group	*tg;	/* group that "owns" this runqueue */

	/* Locally cached copy of our task_group's idle value */
	int			idle;

#ifdef CONFIG_CFS_BANDWIDTH
	int			runtime_enabled;
	s64			runtime_remaining;

	u64			throttled_pelt_idle;
#ifndef CONFIG_64BIT
	u64                     throttled_pelt_idle_copy;
#endif
	u64			throttled_clock;
	u64			throttled_clock_pelt;
	u64			throttled_clock_pelt_time;
	u64			throttled_clock_self;
	u64			throttled_clock_self_time;
	int			throttled;
	int			throttle_count;
	struct list_head	throttled_list;
	struct list_head	throttled_csd_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};

RBtree in cfs_rq

void init_cfs_rq(struct cfs_rq *cfs_rq)
{
	cfs_rq->tasks_timeline = RB_ROOT_CACHED;
	u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
	raw_spin_lock_init(&cfs_rq->removed.lock);
#endif
}

struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
	struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);

	if (!left)
		return NULL;

	return __node_2_se(left);
}

sched_entity

struct sched_entity {
	/* For load-balancing: */
	struct load_weight		load;
	struct rb_node			run_node;
	u64				deadline;
	u64				min_vruntime;

	struct list_head		group_node;
	unsigned int			on_rq;

	u64				exec_start;
	u64				sum_exec_runtime;
	u64				prev_sum_exec_runtime;
	u64				vruntime;
	s64				vlag;
	u64				slice;

	u64				nr_migrations;

#ifdef CONFIG_FAIR_GROUP_SCHED
	int				depth;
	struct sched_entity		*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq			*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq			*my_q;
	/* cached value of my_q->h_nr_running */
	unsigned long			runnable_weight;
#endif

#ifdef CONFIG_SMP
	/*
	 * Per entity load average tracking.
	 *
	 * Put into separate cache line so it does not
	 * collide with read-mostly values above.
	 */
	struct sched_avg		avg;
#endif
};

task_group

The scheduling entities se(1) and se(3) represents some individual tasks, whereas se(2) represents a group of tasks with child scheduling entities se(A) and se(B). Since se(2) corresponds to a group, it owns a CFS runqueue that can be accessed through its my_q field. Entities that belongs to a group, like se(A) and se(B), have a non-NULL member called parent that enables them to access their parent task_group. Note that the entirety of Figure 4.1 only represents one per-CPU runqueue rq of struct rq, in which the cfs_rq for the root taskgroup is a reference of rq->cfs_rq.