summaryrefslogtreecommitdiff
path: root/kernel/sched/stats.h
blob: 84a188913cc9d082faee858777ef81d321fbf9a9 (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _KERNEL_STATS_H
#define _KERNEL_STATS_H

#ifdef CONFIG_SCHEDSTATS

extern struct static_key_false sched_schedstats;

/*
 * 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_dequeue(struct rq *rq, unsigned long long delta)
{
	if (rq)
		rq->rq_sched_info.run_delay += delta;
}
#define   schedstat_enabled()		static_branch_unlikely(&sched_schedstats)
#define __schedstat_inc(var)		do { var++; } while (0)
#define   schedstat_inc(var)		do { if (schedstat_enabled()) { var++; } } while (0)
#define __schedstat_add(var, amt)	do { var += (amt); } while (0)
#define   schedstat_add(var, amt)	do { if (schedstat_enabled()) { var += (amt); } } while (0)
#define __schedstat_set(var, val)	do { var = (val); } while (0)
#define   schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
#define   schedstat_val(var)		(var)
#define   schedstat_val_or_zero(var)	((schedstat_enabled()) ? (var) : 0)

void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
			       struct sched_statistics *stats);

void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
			     struct sched_statistics *stats);
void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
				    struct sched_statistics *stats);

static inline void
check_schedstat_required(void)
{
	if (schedstat_enabled())
		return;

	/* Force schedstat enabled if a dependent tracepoint is active */
	if (trace_sched_stat_wait_enabled()    ||
	    trace_sched_stat_sleep_enabled()   ||
	    trace_sched_stat_iowait_enabled()  ||
	    trace_sched_stat_blocked_enabled() ||
	    trace_sched_stat_runtime_enabled())
		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1\n");
}

#else /* !CONFIG_SCHEDSTATS: */

static inline void rq_sched_info_arrive  (struct rq *rq, unsigned long long delta) { }
static inline void rq_sched_info_dequeue(struct rq *rq, unsigned long long delta) { }
static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delta) { }
# define   schedstat_enabled()		0
# define __schedstat_inc(var)		do { } while (0)
# define   schedstat_inc(var)		do { } while (0)
# define __schedstat_add(var, amt)	do { } while (0)
# define   schedstat_add(var, amt)	do { } while (0)
# define __schedstat_set(var, val)	do { } while (0)
# define   schedstat_set(var, val)	do { } while (0)
# define   schedstat_val(var)		0
# define   schedstat_val_or_zero(var)	0

# define __update_stats_wait_start(rq, p, stats)       do { } while (0)
# define __update_stats_wait_end(rq, p, stats)         do { } while (0)
# define __update_stats_enqueue_sleeper(rq, p, stats)  do { } while (0)
# define check_schedstat_required()                    do { } while (0)

#endif /* CONFIG_SCHEDSTATS */

#ifdef CONFIG_FAIR_GROUP_SCHED
struct sched_entity_stats {
	struct sched_entity     se;
	struct sched_statistics stats;
} __no_randomize_layout;
#endif

static inline struct sched_statistics *
__schedstats_from_se(struct sched_entity *se)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	if (!entity_is_task(se))
		return &container_of(se, struct sched_entity_stats, se)->stats;
#endif
	return &task_of(se)->stats;
}

#ifdef CONFIG_PSI
void psi_task_change(struct task_struct *task, int clear, int set);
void psi_task_switch(struct task_struct *prev, struct task_struct *next,
		     bool sleep);
void psi_account_irqtime(struct task_struct *task, u32 delta);

/*
 * PSI tracks state that persists across sleeps, such as iowaits and
 * memory stalls. As a result, it has to distinguish between sleeps,
 * where a task's runnable state changes, and requeues, where a task
 * and its state are being moved between CPUs and runqueues.
 */
static inline void psi_enqueue(struct task_struct *p, bool wakeup)
{
	int clear = 0, set = TSK_RUNNING;

	if (static_branch_likely(&psi_disabled))
		return;

	if (p->in_memstall)
		set |= TSK_MEMSTALL_RUNNING;

	if (!wakeup || p->sched_psi_wake_requeue) {
		if (p->in_memstall)
			set |= TSK_MEMSTALL;
		if (p->sched_psi_wake_requeue)
			p->sched_psi_wake_requeue = 0;
	} else {
		if (p->in_iowait)
			clear |= TSK_IOWAIT;
	}

	psi_task_change(p, clear, set);
}

static inline void psi_dequeue(struct task_struct *p, bool sleep)
{
	int clear = TSK_RUNNING;

	if (static_branch_likely(&psi_disabled))
		return;

	/*
	 * A voluntary sleep is a dequeue followed by a task switch. To
	 * avoid walking all ancestors twice, psi_task_switch() handles
	 * TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
	 * Do nothing here.
	 */
	if (sleep)
		return;

	if (p->in_memstall)
		clear |= (TSK_MEMSTALL | TSK_MEMSTALL_RUNNING);

	psi_task_change(p, clear, 0);
}

static inline void psi_ttwu_dequeue(struct task_struct *p)
{
	if (static_branch_likely(&psi_disabled))
		return;
	/*
	 * Is the task being migrated during a wakeup? Make sure to
	 * deregister its sleep-persistent psi states from the old
	 * queue, and let psi_enqueue() know it has to requeue.
	 */
	if (unlikely(p->in_iowait || p->in_memstall)) {
		struct rq_flags rf;
		struct rq *rq;
		int clear = 0;

		if (p->in_iowait)
			clear |= TSK_IOWAIT;
		if (p->in_memstall)
			clear |= TSK_MEMSTALL;

		rq = __task_rq_lock(p, &rf);
		psi_task_change(p, clear, 0);
		p->sched_psi_wake_requeue = 1;
		__task_rq_unlock(rq, &rf);
	}
}

static inline void psi_sched_switch(struct task_struct *prev,
				    struct task_struct *next,
				    bool sleep)
{
	if (static_branch_likely(&psi_disabled))
		return;

	psi_task_switch(prev, next, sleep);
}

#else /* CONFIG_PSI */
static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
static inline void psi_ttwu_dequeue(struct task_struct *p) {}
static inline void psi_sched_switch(struct task_struct *prev,
				    struct task_struct *next,
				    bool sleep) {}
static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {}
#endif /* CONFIG_PSI */

#ifdef CONFIG_SCHED_INFO
/*
 * 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_dequeue(struct rq *rq, struct task_struct *t)
{
	unsigned long long delta = 0;

	if (!t->sched_info.last_queued)
		return;

	delta = rq_clock(rq) - t->sched_info.last_queued;
	t->sched_info.last_queued = 0;
	t->sched_info.run_delay += delta;

	rq_sched_info_dequeue(rq, 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 rq *rq, struct task_struct *t)
{
	unsigned long long now, delta = 0;

	if (!t->sched_info.last_queued)
		return;

	now = rq_clock(rq);
	delta = now - t->sched_info.last_queued;
	t->sched_info.last_queued = 0;
	t->sched_info.run_delay += delta;
	t->sched_info.last_arrival = now;
	t->sched_info.pcount++;

	rq_sched_info_arrive(rq, delta);
}

/*
 * 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_dequeue() will clear that stamp when appropriate.
 */
static inline void sched_info_enqueue(struct rq *rq, struct task_struct *t)
{
	if (!t->sched_info.last_queued)
		t->sched_info.last_queued = rq_clock(rq);
}

/*
 * Called when a process ceases being the active-running process involuntarily
 * due, typically, to expiring its time slice (this may also be called when
 * switching to the idle task).  Now we can calculate how long we ran.
 * Also, if the process is still in the TASK_RUNNING state, call
 * sched_info_enqueue() to mark that it has now again started waiting on
 * the runqueue.
 */
static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
{
	unsigned long long delta = rq_clock(rq) - t->sched_info.last_arrival;

	rq_sched_info_depart(rq, delta);

	if (task_is_running(t))
		sched_info_enqueue(rq, 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 rq *rq, struct task_struct *prev, struct task_struct *next)
{
	/*
	 * 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(rq, prev);

	if (next != rq->idle)
		sched_info_arrive(rq, next);
}

#else /* !CONFIG_SCHED_INFO: */
# define sched_info_enqueue(rq, t)	do { } while (0)
# define sched_info_dequeue(rq, t)	do { } while (0)
# define sched_info_switch(rq, t, next)	do { } while (0)
#endif /* CONFIG_SCHED_INFO */

#endif /* _KERNEL_STATS_H */