aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched_stats.h
blob: 25c2f962f6fcb3b545719e4a8871c991bdbeb37f (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

#ifdef CONFIG_SCHEDSTATS
/*
 * bump this up when changing the output format or the meaning of an existing
 * format, so that tools can adapt (or abort)
 */
#define SCHEDSTAT_VERSION 15

static int show_schedstat(struct seq_file *seq, void *v)
{
	int cpu;
	int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
	char *mask_str = kmalloc(mask_len, GFP_KERNEL);

	if (mask_str == NULL)
		return -ENOMEM;

	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
	seq_printf(seq, "timestamp %lu\n", jiffies);
	for_each_online_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
		struct sched_domain *sd;
		int dcount = 0;
#endif

		/* runqueue-specific stats */
		seq_printf(seq,
		    "cpu%d %u %u %u %u %u %u %llu %llu %lu",
		    cpu, rq->yld_count,
		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
		    rq->ttwu_count, rq->ttwu_local,
		    rq->rq_cpu_time,
		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);

		seq_printf(seq, "\n");

#ifdef CONFIG_SMP
		/* domain-specific stats */
		preempt_disable();
		for_each_domain(cpu, sd) {
			enum cpu_idle_type itype;

			cpumask_scnprintf(mask_str, mask_len,
					  sched_domain_span(sd));
			seq_printf(seq, "domain%d %s", dcount++, mask_str);
			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
					itype++) {
				seq_printf(seq, " %u %u %u %u %u %u %u %u",
				    sd->lb_count[itype],
				    sd->lb_balanced[itype],
				    sd->lb_failed[itype],
				    sd->lb_imbalance[itype],
				    sd->lb_gained[itype],
				    sd->lb_hot_gained[itype],
				    sd->lb_nobusyq[itype],
				    sd->lb_nobusyg[itype]);
			}
			seq_printf(seq,
				   " %u %u %u %u %u %u %u %u %u %u %u %u\n",
			    sd->alb_count, sd->alb_failed, sd->alb_pushed,
			    sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed,
			    sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
			    sd->ttwu_wake_remote, sd->ttwu_move_affine,
			    sd->ttwu_move_balance);
		}
		preempt_enable();
#endif
	}
	kfree(mask_str);
	return 0;
}

static int schedstat_open(struct inode *inode, struct file *file)
{
	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
	char *buf = kmalloc(size, GFP_KERNEL);
	struct seq_file *m;
	int res;

	if (!buf)
		return -ENOMEM;
	res = single_open(file, show_schedstat, NULL);
	if (!res) {
		m = file->private_data;
		m->buf = buf;
		m->size = size;
	} else
		kfree(buf);
	return res;
}

static const struct file_operations proc_schedstat_operations = {
	.open    = schedstat_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = single_release,
};

static int __init proc_schedstat_init(void)
{
	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
	return 0;
}
module_init(proc_schedstat_init);

/*
 * Expects runqueue lock to be held for atomicity of update
 */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
{
	if (rq) {
		rq->rq_sched_info.run_delay += delta;
		rq->rq_sched_info.pcount++;
	}
}

/*
 * Expects runqueue lock to be held for atomicity of update
 */
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{
	if (rq)
		rq->rq_cpu_time += delta;
}

static inline void
rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
{
	if (rq)
		rq->rq_sched_info.run_delay += delta;
}
# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
# define schedstat_set(var, val)	do { var = (val); } while (0)
#else /* !CONFIG_SCHEDSTATS */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
{}
static inline void
rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
{}
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{}
# define schedstat_inc(rq, field)	do { } while (0)
# define schedstat_add(rq, field, amt)	do { } while (0)
# define schedstat_set(var, val)	do { } while (0)
#endif

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
	t->sched_info.last_queued = 0;
}

/*
 * Called when a process is dequeued from the active array and given
 * the cpu.  We should note that with the exception of interactive
 * tasks, the expired queue will become the active queue after the active
 * queue is empty, without explicitly dequeuing and requeuing tasks in the
 * expired queue.  (Interactive tasks may be requeued directly to the
 * active queue, thus delaying tasks in the expired queue from running;
 * see scheduler_tick()).
 *
 * Though we are interested in knowing how long it was from the *first* time a
 * task was queued to the time that it finally hit a cpu, we call this routine
 * from dequeue_task() to account for possible rq->clock skew across cpus. The
 * delta taken on each cpu would annul the skew.
 */
static inline void sched_info_dequeued(struct task_struct *t)
{
	unsigned long long now = task_rq(t)->clock, delta = 0;

	if (unlikely(sched_info_on()))
		if (t->sched_info.last_queued)
			delta = now - t->sched_info.last_queued;
	sched_info_reset_dequeued(t);
	t->sched_info.run_delay += delta;

	rq_sched_info_dequeued(task_rq(t), delta);
}

/*
 * Called when a task finally hits the cpu.  We can now calculate how
 * long it was waiting to run.  We also note when it began so that we
 * can keep stats on how long its timeslice is.
 */
static void sched_info_arrive(struct task_struct *t)
{
	unsigned long long now = task_rq(t)->clock, delta = 0;

	if (t->sched_info.last_queued)
		delta = now - t->sched_info.last_queued;
	sched_info_reset_dequeued(t);
	t->sched_info.run_delay += delta;
	t->sched_info.last_arrival = now;
	t->sched_info.pcount++;

	rq_sched_info_arrive(task_rq(t), delta);
}

/*
 * Called when a process is queued into either the active or expired
 * array.  The time is noted and later used to determine how long we
 * had to wait for us to reach the cpu.  Since the expired queue will
 * become the active queue after active queue is empty, without dequeuing
 * and requeuing any tasks, we are interested in queuing to either. It
 * is unusual but not impossible for tasks to be dequeued and immediately
 * requeued in the same or another array: this can happen in sched_yield(),
 * set_user_nice(), and even load_balance() as it moves tasks from runqueue
 * to runqueue.
 *
 * This function is only called from enqueue_task(), but also only updates
 * the timestamp if it is already not set.  It's assumed that
 * sched_info_dequeued() will clear that stamp when appropriate.
 */
static inline void sched_info_queued(struct task_struct *t)
{
	if (unlikely(sched_info_on()))
		if (!t->sched_info.last_queued)
			t->sched_info.last_queued = task_rq(t)->clock;
}

/*
 * Called when a process ceases being the active-running process, either
 * voluntarily or involuntarily.  Now we can calculate how long we ran.
 * Also, if the process is still in the TASK_RUNNING state, call
 * sched_info_queued() to mark that it has now again started waiting on
 * the runqueue.
 */
static inline void sched_info_depart(struct task_struct *t)
{
	unsigned long long delta = task_rq(t)->clock -
					t->sched_info.last_arrival;

	rq_sched_info_depart(task_rq(t), delta);

	if (t->state == TASK_RUNNING)
		sched_info_queued(t);
}

/*
 * Called when tasks are switched involuntarily due, typically, to expiring
 * their time slice.  (This may also be called when switching to or from
 * the idle task.)  We are only called when prev != next.
 */
static inline void
__sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
	struct rq *rq = task_rq(prev);

	/*
	 * prev now departs the cpu.  It's not interesting to record
	 * stats about how efficient we were at scheduling the idle
	 * process, however.
	 */
	if (prev != rq->idle)
		sched_info_depart(prev);

	if (next != rq->idle)
		sched_info_arrive(next);
}
static inline void
sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
	if (unlikely(sched_info_on()))
		__sched_info_switch(prev, next);
}
#else
#define sched_info_queued(t)			do { } while (0)
#define sched_info_reset_dequeued(t)	do { } while (0)
#define sched_info_dequeued(t)			do { } while (0)
#define sched_info_switch(t, next)		do { } while (0)
#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */

/*
 * The following are functions that support scheduler-internal time accounting.
 * These functions are generally called at the timer tick.  None of this depends
 * on CONFIG_SCHEDSTATS.
 */

/**
 * account_group_user_time - Maintain utime for a thread group.
 *
 * @tsk:	Pointer to task structure.
 * @cputime:	Time value by which to increment the utime field of the
 *		thread_group_cputime structure.
 *
 * If thread group time is being maintained, get the structure for the
 * running CPU and update the utime field there.
 */
static inline void account_group_user_time(struct task_struct *tsk,
					   cputime_t cputime)
{
	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;

	if (!cputimer->running)
		return;

	spin_lock(&cputimer->lock);
	cputimer->cputime.utime =
		cputime_add(cputimer->cputime.utime, cputime);
	spin_unlock(&cputimer->lock);
}

/**
 * account_group_system_time - Maintain stime for a thread group.
 *
 * @tsk:	Pointer to task structure.
 * @cputime:	Time value by which to increment the stime field of the
 *		thread_group_cputime structure.
 *
 * If thread group time is being maintained, get the structure for the
 * running CPU and update the stime field there.
 */
static inline void account_group_system_time(struct task_struct *tsk,
					     cputime_t cputime)
{
	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;

	if (!cputimer->running)
		return;

	spin_lock(&cputimer->lock);
	cputimer->cputime.stime =
		cputime_add(cputimer->cputime.stime, cputime);
	spin_unlock(&cputimer->lock);
}

/**
 * account_group_exec_runtime - Maintain exec runtime for a thread group.
 *
 * @tsk:	Pointer to task structure.
 * @ns:		Time value by which to increment the sum_exec_runtime field
 *		of the thread_group_cputime structure.
 *
 * If thread group time is being maintained, get the structure for the
 * running CPU and update the sum_exec_runtime field there.
 */
static inline void account_group_exec_runtime(struct task_struct *tsk,
					      unsigned long long ns)
{
	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;

	if (!cputimer->running)
		return;

	spin_lock(&cputimer->lock);
	cputimer->cputime.sum_exec_runtime += ns;
	spin_unlock(&cputimer->lock);
}