summaryrefslogtreecommitdiff
path: root/kernel/sched_rt.c
blob: e3d2ca8832af85e9cb008dedf852a1511f7a6fab (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
/*
 * 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++;
}

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--;
}

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
/*
 * 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);
}
#endif

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,
};