path: root/kernel/sched_fair.c

/*
 * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
 *
 *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *
 *  Interactivity improvements by Mike Galbraith
 *  (C) 2007 Mike Galbraith <efault@gmx.de>
 *
 *  Various enhancements by Dmitry Adamushko.
 *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
 *
 *  Group scheduling enhancements by Srivatsa Vaddagiri
 *  Copyright IBM Corporation, 2007
 *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
 *
 *  Scaled math optimizations by Thomas Gleixner
 *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
 *
 *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
 *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 */

/*
 * Targeted preemption latency for CPU-bound tasks:
 * (default: 20ms, units: nanoseconds)
 *
 * NOTE: this latency value is not the same as the concept of
 * 'timeslice length' - timeslices in CFS are of variable length.
 * (to see the precise effective timeslice length of your workload,
 *  run vmstat and monitor the context-switches field)
 *
 * On SMP systems the value of this is multiplied by the log2 of the
 * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
 * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
 * Targeted preemption latency for CPU-bound tasks:
 */
const_debug unsigned int sysctl_sched_latency = 20000000ULL;

/*
 * After fork, child runs first. (default) If set to 0 then
 * parent will (try to) run first.
 */
const_debug unsigned int sysctl_sched_child_runs_first = 1;

/*
 * Minimal preemption granularity for CPU-bound tasks:
 * (default: 2 msec, units: nanoseconds)
 */
unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;

/*
 * sys_sched_yield() compat mode
 *
 * This option switches the agressive yield implementation of the
 * old scheduler back on.
 */
unsigned int __read_mostly sysctl_sched_compat_yield;

/*
 * SCHED_BATCH wake-up granularity.
 * (default: 25 msec, units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 25000000UL;

/*
 * SCHED_OTHER wake-up granularity.
 * (default: 1 msec, units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
const_debug unsigned int sysctl_sched_wakeup_granularity = 2000000UL;

unsigned int sysctl_sched_runtime_limit __read_mostly;

extern struct sched_class fair_sched_class;

/**************************************************************
 * CFS operations on generic schedulable entities:
 */

#ifdef CONFIG_FAIR_GROUP_SCHED

/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return cfs_rq->rq;
}

/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se)	(!se->my_q)

#else	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return container_of(cfs_rq, struct rq, cfs);
}

#define entity_is_task(se)	1

#endif	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct task_struct *task_of(struct sched_entity *se)
{
	return container_of(se, struct task_struct, se);
}


/**************************************************************
 * Scheduling class tree data structure manipulation methods:
 */

static inline void
set_leftmost(struct cfs_rq *cfs_rq, struct rb_node *leftmost)
{
	struct sched_entity *se;

	cfs_rq->rb_leftmost = leftmost;
	if (leftmost) {
		se = rb_entry(leftmost, struct sched_entity, run_node);
		if ((se->vruntime > cfs_rq->min_vruntime) ||
		    (cfs_rq->min_vruntime > (1ULL << 61) &&
		     se->vruntime < (1ULL << 50)))
			cfs_rq->min_vruntime = se->vruntime;
	}
}

s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	return se->fair_key - cfs_rq->min_vruntime;
}

/*
 * Enqueue an entity into the rb-tree:
 */
static void
__enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
	struct rb_node *parent = NULL;
	struct sched_entity *entry;
	s64 key = entity_key(cfs_rq, se);
	int leftmost = 1;

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct sched_entity, run_node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same key stay together.
		 */
		if (key < entity_key(cfs_rq, entry)) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = 0;
		}
	}

	/*
	 * Maintain a cache of leftmost tree entries (it is frequently
	 * used):
	 */
	if (leftmost)
		set_leftmost(cfs_rq, &se->run_node);

	rb_link_node(&se->run_node, parent, link);
	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
	update_load_add(&cfs_rq->load, se->load.weight);
	cfs_rq->nr_running++;
	se->on_rq = 1;

	schedstat_add(