summaryrefslogtreecommitdiff
path: root/kernel/sched_rt.c
blob: 7815e90b1147dddfec0fcc5ba8cb2e4655a8918c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
/*
 * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
 * policies)
 */

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static void update_curr_rt(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	u64 delta_exec;

	if (!task_has_rt_policy(curr))
		return;

	delta_exec = rq->clock - curr->se.exec_start;
	if (unlikely((s64)delta_exec < 0))
		delta_exec = 0;

	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));

	curr->se.sum_exec_runtime += delta_exec;
	curr->se.exec_start = rq->clock;
	cpuacct_charge(curr, delta_exec);
}

static inline void inc_rt_tasks(struct task_struct *p, struct rq *rq)
{
	WARN_ON(!rt_task(p));
	rq->rt.rt_nr_running++;
#ifdef CONFIG_SMP
	if (p->prio < rq->rt.highest_prio)
		rq->rt.highest_prio = p->prio;
#endif /* CONFIG_SMP */
}

static inline void dec_rt_tasks(struct task_struct *p, struct rq *rq)
{
	WARN_ON(!rt_task(p));
	WARN_ON(!rq->rt.rt_nr_running);
	rq->rt.rt_nr_running--;
#ifdef CONFIG_SMP
	if (rq->rt.rt_nr_running) {
		struct rt_prio_array *array;

		WARN_ON(p->prio < rq->rt.highest_prio);
		if (p->prio == rq->rt.highest_prio) {
			/* recalculate */
			array = &rq->rt.active;
			rq->rt.highest_prio =
				sched_find_first_bit(array->bitmap);
		} /* otherwise leave rq->highest prio alone */
	} else
		rq->rt.highest_prio = MAX_RT_PRIO;
#endif /* CONFIG_SMP */
}

static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
{
	struct rt_prio_array *array = &rq->rt.active;

	list_add_tail(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	inc_cpu_load(rq, p->se.load.weight);

	inc_rt_tasks(p, rq);
}

/*
 * Adding/removing a task to/from a priority array:
 */
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
{
	struct rt_prio_array *array = &rq->rt.active;

	update_curr_rt(rq);

	list_del(&p->run_list);
	if (list_empty(array->queue + p->prio))
		__clear_bit(p->prio, array->bitmap);
	dec_cpu_load(rq, p->se.load.weight);

	dec_rt_tasks(p, rq);
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void requeue_task_rt(struct rq *rq, struct task_struct *p)
{
	struct rt_prio_array *array = &rq->rt.active;

	list_move_tail(&p->run_list, array->queue + p->prio);
}

static void
yield_task_rt(struct rq *rq)
{
	requeue_task_rt(rq, rq->curr);
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
{
	if (p->prio < rq->curr->prio)
		resched_task(rq->curr);
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
{
	struct rt_prio_array *array = &rq->rt.active;
	struct task_struct *next;
	struct list_head *queue;
	int idx;

	idx = sched_find_first_bit(array->bitmap);
	if (idx >= MAX_RT_PRIO)
		return NULL;

	queue = array->queue + idx;
	next = list_entry(queue->next, struct task_struct, run_list);

	next->se.exec_start = rq->clock;

	return next;
}

static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
	update_curr_rt(rq);
	p->se.exec_start = 0;
}

#ifdef CONFIG_SMP
/* Only try algorithms three times */
#define RT_MAX_TRIES 3

static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);

/* Return the second highest RT task, NULL otherwise */
static struct task_struct *pick_next_highest_task_rt(struct rq *rq)
{
	struct rt_prio_array *array = &rq->rt.active;
	struct task_struct *next;
	struct list_head *queue;
	int idx;

	assert_spin_locked(&rq->lock);

	if (likely(rq->rt.rt_nr_running < 2))
		return NULL;

	idx = sched_find_first_bit(array->bitmap);
	if (unlikely(idx >= MAX_RT_PRIO)) {
		WARN_ON(1); /* rt_nr_running is bad */
		return NULL;
	}

	queue = array->queue + idx;
	next = list_entry(queue->next, struct task_struct, run_list);
	if (unlikely(next != rq->curr))
		return next;

	if (queue->next->next != queue) {
		/* same prio task */
		next = list_entry(queue->next->next, struct task_struct, run_list);
		return next;
	}

	/* slower, but more flexible */
	idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1);
	if (unlikely(idx >= MAX_RT_PRIO)) {
		WARN_ON(1); /* rt_nr_running was 2 and above! */
		return NULL;
	}

	queue = array->queue + idx;
	next = list_entry(queue->next, struct task_struct, run_list);

	return next;
}

static DEFINE_PER_CPU(cpumask_t, local_cpu_mask);

/* Will lock the rq it finds */
static struct rq *find_lock_lowest_rq(struct task_struct *task,
				      struct rq *this_rq)
{
	struct rq *lowest_rq = NULL;
	int cpu;
	int tries;
	cpumask_t *cpu_mask = &__get_cpu_var(local_cpu_mask);

	cpus_and(*cpu_mask, cpu_online_map, task->cpus_allowed);

	for (tries = 0; tries < RT_MAX_TRIES; tries++) {
		/*
		 * Scan each rq for the lowest prio.
		 */
		for_each_cpu_mask(cpu, *cpu_mask) {
			struct rq *rq = &per_cpu(runqueues, cpu);

			if (cpu == this_rq->cpu)
				continue;

			/* We look for lowest RT prio or non-rt CPU */
			if (rq->rt.highest_prio >= MAX_RT_PRIO) {
				lowest_rq = rq;
				break;
			}

			/* no locking for now */
			if (rq->rt.highest_prio > task->prio &&
			    (!lowest_rq || rq->rt.highest_prio > lowest_rq->rt.highest_prio)) {
				lowest_rq = rq;
			}
		}

		if (!lowest_rq)
			break;

		/* if the prio of this runqueue changed, try again */
		if (double_lock_balance(this_rq, lowest_rq)) {
			/*
			 * We had to unlock the run queue. In
			 * the mean time, task could have
			 * migrated already or had its affinity changed.
			 * Also make sure that it wasn't scheduled on its rq.
			 */
			if (unlikely(task_rq(task) != this_rq ||
				     !cpu_isset(lowest_rq->cpu, task->cpus_allowed) ||
				     task_running(this_rq, task) ||
				     !task->se.on_rq)) {
				spin_unlock(&lowest_rq->lock);
				lowest_rq = NULL;
				break;
			}
		}

		/* If this rq is still suitable use it. */
		if (lowest_rq->rt.highest_prio > task->prio)
			break;

		/* try again */
		spin_unlock(&lowest_rq->lock);
		lowest_rq = NULL;
	}

	return lowest_rq;
}

/*
 * If the current CPU has more than one RT task, see if the non
 * running task can migrate over to a CPU that is running a task
 * of lesser priority.
 */
static int push_rt_task(struct rq *this_rq)
{
	struct task_struct *next_task;
	struct rq *lowest_rq;
	int ret = 0;
	int paranoid = RT_MAX_TRIES;

	assert_spin_locked(&this_rq->lock);

	next_task = pick_next_highest_task_rt(this_rq);
	if (!next_task)
		return 0;

 retry:
	if (unlikely(next_task == this_rq->curr))
		return 0;

	/*
	 * It's possible that the next_task slipped in of
	 * higher priority than current. If that's the case
	 * just reschedule current.
	 */
	if (unlikely(next_task->prio < this_rq->curr->prio)) {
		resched_task(this_rq->curr);
		return 0;
	}

	/* We might release this_rq lock */
	get_task_struct(next_task);

	/* find_lock_lowest_rq locks the rq if found */
	lowest_rq = find_lock_lowest_rq(next_task, this_rq);
	if (!lowest_rq) {
		struct task_struct *task;
		/*
		 * find lock_lowest_rq releases this_rq->lock
		 * so it is possible that next_task has changed.
		 * If it has, then try again.
		 */
		task = pick_next_highest_task_rt(this_rq);
		if (unlikely(task != next_task) && task && paranoid--) {
			put_task_struct(next_task);
			next_task = task;
			goto retry;
		}
		goto out;
	}

	assert_spin_locked(&lowest_rq->lock);

	deactivate_task(this_rq, next_task, 0);
	set_task_cpu(next_task, lowest_rq->cpu);
	activate_task(lowest_rq, next_task, 0);

	resched_task(lowest_rq->curr);

	spin_unlock(&lowest_rq->lock);

	ret = 1;
out:
	put_task_struct(next_task);

	return ret;
}

/*
 * TODO: Currently we just use the second highest prio task on
 *       the queue, and stop when it can't migrate (or there's
 *       no more RT tasks).  There may be a case where a lower
 *       priority RT task has a different affinity than the
 *       higher RT task. In this case the lower RT task could
 *       possibly be able to migrate where as the higher priority
 *       RT task could not.  We currently ignore this issue.
 *       Enhancements are welcome!
 */
static void push_rt_tasks(struct rq *rq)
{
	/* push_rt_task will return true if it moved an RT */
	while (push_rt_task(rq))
		;
}

static void schedule_tail_balance_rt(struct rq *rq)
{
	/*
	 * If we have more than one rt_task queued, then
	 * see if we can push the other rt_tasks off to other CPUS.
	 * Note we may release the rq lock, and since
	 * the lock was owned by prev, we need to release it
	 * first via finish_lock_switch and then reaquire it here.
	 */
	if (unlikely(rq->rt.rt_nr_running > 1)) {
		spin_lock_irq(&rq->lock);
		push_rt_tasks(rq);
		spin_unlock_irq(&rq->lock);
	}
}

/*
 * Load-balancing iterator. Note: while the runqueue stays locked
 * during the whole iteration, the current task might be
 * dequeued so the iterator has to be dequeue-safe. Here we
 * achieve that by always pre-iterating before returning
 * the current task:
 */
static struct task_struct *load_balance_start_rt(void *arg)
{
	struct rq *rq = arg;
	struct rt_prio_array *array = &rq->rt.active;
	struct list_head *head, *curr;
	struct task_struct *p;
	int idx;

	idx = sched_find_first_bit(array->bitmap);
	if (idx >= MAX_RT_PRIO)
		return NULL;

	head = array->queue + idx;
	curr = head->prev;

	p = list_entry(curr, struct task_struct, run_list);

	curr = curr->prev;

	rq->rt.rt_load_balance_idx = idx;
	rq->rt.rt_load_balance_head = head;
	rq->rt.rt_load_balance_curr = curr;

	return p;
}

static struct task_struct *load_balance_next_rt(void *arg)
{
	struct rq *rq = arg;
	struct rt_prio_array *array = &rq->rt.active;
	struct list_head *head, *curr;
	struct task_struct *p;
	int idx;

	idx = rq->rt.rt_load_balance_idx;
	head = rq->rt.rt_load_balance_head;
	curr = rq->rt.rt_load_balance_curr;

	/*
	 * If we arrived back to the head again then
	 * iterate to the next queue (if any):
	 */
	if (unlikely(head == curr)) {
		int next_idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1);

		if (next_idx >= MAX_RT_PRIO)
			return NULL;

		idx = next_idx;
		head = array->queue + idx;
		curr = head->prev;

		rq->rt.rt_load_balance_idx = idx;
		rq->rt.rt_load_balance_head = head;
	}

	p = list_entry(curr, struct task_struct, run_list);

	curr = curr->prev;

	rq->rt.rt_load_balance_curr = curr;

	return p;
}

static unsigned long
load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
		unsigned long max_load_move,
		struct sched_domain *sd, enum cpu_idle_type idle,
		int *all_pinned, int *this_best_prio)
{
	struct rq_iterator rt_rq_iterator;

	rt_rq_iterator.start = load_balance_start_rt;
	rt_rq_iterator.next = load_balance_next_rt;
	/* pass 'busiest' rq argument into
	 * load_balance_[start|next]_rt iterators
	 */
	rt_rq_iterator.arg = busiest;

	return balance_tasks(this_rq, this_cpu, busiest, max_load_move, sd,
			     idle, all_pinned, this_best_prio, &rt_rq_iterator);
}

static int
move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
		 struct sched_domain *sd, enum cpu_idle_type idle)
{
	struct rq_iterator rt_rq_iterator;

	rt_rq_iterator.start = load_balance_start_rt;
	rt_rq_iterator.next = load_balance_next_rt;
	rt_rq_iterator.arg = busiest;

	return iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
				  &rt_rq_iterator);
}
#else /* CONFIG_SMP */
# define schedule_tail_balance_rt(rq)	do { } while (0)
#endif /* CONFIG_SMP */

static void task_tick_rt(struct rq *rq, struct task_struct *p)
{
	update_curr_rt(rq);

	/*
	 * RR tasks need a special form of timeslice management.
	 * FIFO tasks have no timeslices.
	 */
	if (p->policy != SCHED_RR)
		return;

	if (--p->time_slice)
		return;

	p->time_slice = DEF_TIMESLICE;

	/*
	 * Requeue to the end of queue if we are not the only element
	 * on the queue:
	 */
	if (p->run_list.prev != p->run_list.next) {
		requeue_task_rt(rq, p);
		set_tsk_need_resched(p);
	}
}

static void set_curr_task_rt(struct rq *rq)
{
	struct task_struct *p = rq->curr;

	p->se.exec_start = rq->clock;
}

const struct sched_class rt_sched_class = {
	.next			= &fair_sched_class,
	.enqueue_task		= enqueue_task_rt,
	.dequeue_task		= dequeue_task_rt,
	.yield_task		= yield_task_rt,

	.check_preempt_curr	= check_preempt_curr_rt,

	.pick_next_task		= pick_next_task_rt,
	.put_prev_task		= put_prev_task_rt,

#ifdef CONFIG_SMP
	.load_balance		= load_balance_rt,
	.move_one_task		= move_one_task_rt,
#endif

	.set_curr_task          = set_curr_task_rt,
	.task_tick		= task_tick_rt,
};