cputime.c 16.6 KB
Newer Older
1
2
3
4
5
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/tsacct_kern.h>
#include <linux/kernel_stat.h>
#include <linux/static_key.h>
6
#include <linux/context_tracking.h>
7
8
9
10
11
12
13
#include "sched.h"


#ifdef CONFIG_IRQ_TIME_ACCOUNTING

/*
 * There are no locks covering percpu hardirq/softirq time.
14
 * They are only modified in vtime_account, on corresponding CPU
15
16
17
 * with interrupts disabled. So, writes are safe.
 * They are read and saved off onto struct rq in update_rq_clock().
 * This may result in other CPU reading this CPU's irq time and can
18
 * race with irq/vtime_account on this CPU. We would either get old
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
 * or new value with a side effect of accounting a slice of irq time to wrong
 * task when irq is in progress while we read rq->clock. That is a worthy
 * compromise in place of having locks on each irq in account_system_time.
 */
DEFINE_PER_CPU(u64, cpu_hardirq_time);
DEFINE_PER_CPU(u64, cpu_softirq_time);

static DEFINE_PER_CPU(u64, irq_start_time);
static int sched_clock_irqtime;

void enable_sched_clock_irqtime(void)
{
	sched_clock_irqtime = 1;
}

void disable_sched_clock_irqtime(void)
{
	sched_clock_irqtime = 0;
}

#ifndef CONFIG_64BIT
DEFINE_PER_CPU(seqcount_t, irq_time_seq);
#endif /* CONFIG_64BIT */

/*
 * Called before incrementing preempt_count on {soft,}irq_enter
 * and before decrementing preempt_count on {soft,}irq_exit.
 */
47
void irqtime_account_irq(struct task_struct *curr)
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
{
	unsigned long flags;
	s64 delta;
	int cpu;

	if (!sched_clock_irqtime)
		return;

	local_irq_save(flags);

	cpu = smp_processor_id();
	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
	__this_cpu_add(irq_start_time, delta);

	irq_time_write_begin();
	/*
	 * We do not account for softirq time from ksoftirqd here.
	 * We want to continue accounting softirq time to ksoftirqd thread
	 * in that case, so as not to confuse scheduler with a special task
	 * that do not consume any time, but still wants to run.
	 */
	if (hardirq_count())
		__this_cpu_add(cpu_hardirq_time, delta);
	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
		__this_cpu_add(cpu_softirq_time, delta);

	irq_time_write_end();
	local_irq_restore(flags);
}
77
EXPORT_SYMBOL_GPL(irqtime_account_irq);
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

static int irqtime_account_hi_update(void)
{
	u64 *cpustat = kcpustat_this_cpu->cpustat;
	unsigned long flags;
	u64 latest_ns;
	int ret = 0;

	local_irq_save(flags);
	latest_ns = this_cpu_read(cpu_hardirq_time);
	if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
		ret = 1;
	local_irq_restore(flags);
	return ret;
}

static int irqtime_account_si_update(void)
{
	u64 *cpustat = kcpustat_this_cpu->cpustat;
	unsigned long flags;
	u64 latest_ns;
	int ret = 0;

	local_irq_save(flags);
	latest_ns = this_cpu_read(cpu_softirq_time);
	if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
		ret = 1;
	local_irq_restore(flags);
	return ret;
}

#else /* CONFIG_IRQ_TIME_ACCOUNTING */

#define sched_clock_irqtime	(0)

#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */

static inline void task_group_account_field(struct task_struct *p, int index,
					    u64 tmp)
{
#ifdef CONFIG_CGROUP_CPUACCT
	struct kernel_cpustat *kcpustat;
	struct cpuacct *ca;
#endif
	/*
	 * Since all updates are sure to touch the root cgroup, we
	 * get ourselves ahead and touch it first. If the root cgroup
	 * is the only cgroup, then nothing else should be necessary.
	 *
	 */
	__get_cpu_var(kernel_cpustat).cpustat[index] += tmp;

#ifdef CONFIG_CGROUP_CPUACCT
	if (unlikely(!cpuacct_subsys.active))
		return;

	rcu_read_lock();
	ca = task_ca(p);
	while (ca && (ca != &root_cpuacct)) {
		kcpustat = this_cpu_ptr(ca->cpustat);
		kcpustat->cpustat[index] += tmp;
		ca = parent_ca(ca);
	}
	rcu_read_unlock();
#endif
}

/*
 * Account user cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in user space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_user_time(struct task_struct *p, cputime_t cputime,
		       cputime_t cputime_scaled)
{
	int index;

	/* Add user time to process. */
	p->utime += cputime;
	p->utimescaled += cputime_scaled;
	account_group_user_time(p, cputime);

	index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;

	/* Add user time to cpustat. */
	task_group_account_field(p, index, (__force u64) cputime);

	/* Account for user time used */
167
	acct_account_cputime(p);
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
}

/*
 * Account guest cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in virtual machine since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
static void account_guest_time(struct task_struct *p, cputime_t cputime,
			       cputime_t cputime_scaled)
{
	u64 *cpustat = kcpustat_this_cpu->cpustat;

	/* Add guest time to process. */
	p->utime += cputime;
	p->utimescaled += cputime_scaled;
	account_group_user_time(p, cputime);
	p->gtime += cputime;

	/* Add guest time to cpustat. */
	if (TASK_NICE(p) > 0) {
		cpustat[CPUTIME_NICE] += (__force u64) cputime;
		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
	} else {
		cpustat[CPUTIME_USER] += (__force u64) cputime;
		cpustat[CPUTIME_GUEST] += (__force u64) cputime;
	}
}

/*
 * Account system cpu time to a process and desired cpustat field
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in kernel space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 * @target_cputime64: pointer to cpustat field that has to be updated
 */
static inline
void __account_system_time(struct task_struct *p, cputime_t cputime,
			cputime_t cputime_scaled, int index)
{
	/* Add system time to process. */
	p->stime += cputime;
	p->stimescaled += cputime_scaled;
	account_group_system_time(p, cputime);

	/* Add system time to cpustat. */
	task_group_account_field(p, index, (__force u64) cputime);

	/* Account for system time used */
217
	acct_account_cputime(p);
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
}

/*
 * Account system cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @hardirq_offset: the offset to subtract from hardirq_count()
 * @cputime: the cpu time spent in kernel space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_system_time(struct task_struct *p, int hardirq_offset,
			 cputime_t cputime, cputime_t cputime_scaled)
{
	int index;

	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
		account_guest_time(p, cputime, cputime_scaled);
		return;
	}

	if (hardirq_count() - hardirq_offset)
		index = CPUTIME_IRQ;
	else if (in_serving_softirq())
		index = CPUTIME_SOFTIRQ;
	else
		index = CPUTIME_SYSTEM;

	__account_system_time(p, cputime, cputime_scaled, index);
}

/*
 * Account for involuntary wait time.
 * @cputime: the cpu time spent in involuntary wait
 */
void account_steal_time(cputime_t cputime)
{
	u64 *cpustat = kcpustat_this_cpu->cpustat;

	cpustat[CPUTIME_STEAL] += (__force u64) cputime;
}

/*
 * Account for idle time.
 * @cputime: the cpu time spent in idle wait
 */
void account_idle_time(cputime_t cputime)
{
	u64 *cpustat = kcpustat_this_cpu->cpustat;
	struct rq *rq = this_rq();

	if (atomic_read(&rq->nr_iowait) > 0)
		cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
	else
		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}

static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
	if (static_key_false(&paravirt_steal_enabled)) {
		u64 steal, st = 0;

		steal = paravirt_steal_clock(smp_processor_id());
		steal -= this_rq()->prev_steal_time;

		st = steal_ticks(steal);
		this_rq()->prev_steal_time += st * TICK_NSEC;

		account_steal_time(st);
		return st;
	}
#endif
	return false;
}

292
293
294
295
296
297
298
/*
 * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
 * tasks (sum on group iteration) belonging to @tsk's group.
 */
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
{
	struct signal_struct *sig = tsk->signal;
299
	cputime_t utime, stime;
300
301
302
303
304
305
306
307
308
309
310
311
312
	struct task_struct *t;

	times->utime = sig->utime;
	times->stime = sig->stime;
	times->sum_exec_runtime = sig->sum_sched_runtime;

	rcu_read_lock();
	/* make sure we can trust tsk->thread_group list */
	if (!likely(pid_alive(tsk)))
		goto out;

	t = tsk;
	do {
313
314
315
		task_cputime(tsk, &utime, &stime);
		times->utime += utime;
		times->stime += stime;
316
317
318
319
320
321
		times->sum_exec_runtime += task_sched_runtime(t);
	} while_each_thread(tsk, t);
out:
	rcu_read_unlock();
}

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
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
 * Account a tick to a process and cpustat
 * @p: the process that the cpu time gets accounted to
 * @user_tick: is the tick from userspace
 * @rq: the pointer to rq
 *
 * Tick demultiplexing follows the order
 * - pending hardirq update
 * - pending softirq update
 * - user_time
 * - idle_time
 * - system time
 *   - check for guest_time
 *   - else account as system_time
 *
 * Check for hardirq is done both for system and user time as there is
 * no timer going off while we are on hardirq and hence we may never get an
 * opportunity to update it solely in system time.
 * p->stime and friends are only updated on system time and not on irq
 * softirq as those do not count in task exec_runtime any more.
 */
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
						struct rq *rq)
{
	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
	u64 *cpustat = kcpustat_this_cpu->cpustat;

	if (steal_account_process_tick())
		return;

	if (irqtime_account_hi_update()) {
		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
	} else if (irqtime_account_si_update()) {
		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
	} else if (this_cpu_ksoftirqd() == p) {
		/*
		 * ksoftirqd time do not get accounted in cpu_softirq_time.
		 * So, we have to handle it separately here.
		 * Also, p->stime needs to be updated for ksoftirqd.
		 */
		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
					CPUTIME_SOFTIRQ);
	} else if (user_tick) {
		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
	} else if (p == rq->idle) {
		account_idle_time(cputime_one_jiffy);
	} else if (p->flags & PF_VCPU) { /* System time or guest time */
		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
	} else {
		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
					CPUTIME_SYSTEM);
	}
}

static void irqtime_account_idle_ticks(int ticks)
{
	int i;
	struct rq *rq = this_rq();

	for (i = 0; i < ticks; i++)
		irqtime_account_process_tick(current, 0, rq);
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
386
387
static inline void irqtime_account_idle_ticks(int ticks) {}
static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
388
389
390
						struct rq *rq) {}
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */

391
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
392
393
394
395
396
397
398
399
400
401
/*
 * Account a single tick of cpu time.
 * @p: the process that the cpu time gets accounted to
 * @user_tick: indicates if the tick is a user or a system tick
 */
void account_process_tick(struct task_struct *p, int user_tick)
{
	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
	struct rq *rq = this_rq();

402
403
404
	if (vtime_accounting_enabled())
		return;

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
	if (sched_clock_irqtime) {
		irqtime_account_process_tick(p, user_tick, rq);
		return;
	}

	if (steal_account_process_tick())
		return;

	if (user_tick)
		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
				    one_jiffy_scaled);
	else
		account_idle_time(cputime_one_jiffy);
}

/*
 * Account multiple ticks of steal time.
 * @p: the process from which the cpu time has been stolen
 * @ticks: number of stolen ticks
 */
void account_steal_ticks(unsigned long ticks)
{
	account_steal_time(jiffies_to_cputime(ticks));
}

/*
 * Account multiple ticks of idle time.
 * @ticks: number of stolen ticks
 */
void account_idle_ticks(unsigned long ticks)
{

	if (sched_clock_irqtime) {
		irqtime_account_idle_ticks(ticks);
		return;
	}

	account_idle_time(jiffies_to_cputime(ticks));
}
446
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
447
448
449
450
451

/*
 * Use precise platform statistics if available:
 */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
452
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
453
454
455
456
457
{
	*ut = p->utime;
	*st = p->stime;
}

458
void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
459
460
461
462
463
464
465
466
{
	struct task_cputime cputime;

	thread_group_cputime(p, &cputime);

	*ut = cputime.utime;
	*st = cputime.stime;
}
467

468
469
470
#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
void vtime_task_switch(struct task_struct *prev)
{
471
472
473
	if (!vtime_accounting_enabled())
		return;

474
475
476
477
478
	if (is_idle_task(prev))
		vtime_account_idle(prev);
	else
		vtime_account_system(prev);

479
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
480
	vtime_account_user(prev);
481
#endif
482
483
484
	arch_vtime_task_switch(prev);
}
#endif
485

486
487
488
/*
 * Archs that account the whole time spent in the idle task
 * (outside irq) as idle time can rely on this and just implement
489
 * vtime_account_system() and vtime_account_idle(). Archs that
490
491
492
493
494
495
496
 * have other meaning of the idle time (s390 only includes the
 * time spent by the CPU when it's in low power mode) must override
 * vtime_account().
 */
#ifndef __ARCH_HAS_VTIME_ACCOUNT
void vtime_account(struct task_struct *tsk)
{
497
498
499
	if (!vtime_accounting_enabled())
		return;

500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
	if (!in_interrupt()) {
		/*
		 * If we interrupted user, context_tracking_in_user()
		 * is 1 because the context tracking don't hook
		 * on irq entry/exit. This way we know if
		 * we need to flush user time on kernel entry.
		 */
		if (context_tracking_in_user()) {
			vtime_account_user(tsk);
			return;
		}

		if (is_idle_task(tsk)) {
			vtime_account_idle(tsk);
			return;
		}
	}
	vtime_account_system(tsk);
518
519
520
521
}
EXPORT_SYMBOL_GPL(vtime_account);
#endif /* __ARCH_HAS_VTIME_ACCOUNT */

522
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537

static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
{
	u64 temp = (__force u64) rtime;

	temp *= (__force u64) utime;

	if (sizeof(cputime_t) == 4)
		temp = div_u64(temp, (__force u32) total);
	else
		temp = div64_u64(temp, (__force u64) total);

	return (__force cputime_t) temp;
}

538
539
540
541
/*
 * Adjust tick based cputime random precision against scheduler
 * runtime accounting.
 */
542
543
544
static void cputime_adjust(struct task_cputime *curr,
			   struct cputime *prev,
			   cputime_t *ut, cputime_t *st)
545
{
546
	cputime_t rtime, utime, total;
547

548
549
	utime = curr->utime;
	total = utime + curr->stime;
550

551
	/*
552
553
554
555
556
557
558
559
	 * Tick based cputime accounting depend on random scheduling
	 * timeslices of a task to be interrupted or not by the timer.
	 * Depending on these circumstances, the number of these interrupts
	 * may be over or under-optimistic, matching the real user and system
	 * cputime with a variable precision.
	 *
	 * Fix this by scaling these tick based values against the total
	 * runtime accounted by the CFS scheduler.
560
	 */
561
	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
562
563
564
565
566
567
568

	if (total)
		utime = scale_utime(utime, rtime, total);
	else
		utime = rtime;

	/*
569
570
571
	 * If the tick based count grows faster than the scheduler one,
	 * the result of the scaling may go backward.
	 * Let's enforce monotonicity.
572
	 */
573
574
575
576
577
578
	prev->utime = max(prev->utime, utime);
	prev->stime = max(prev->stime, rtime - prev->utime);

	*ut = prev->utime;
	*st = prev->stime;
}
579

580
581
582
583
584
585
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
	struct task_cputime cputime = {
		.sum_exec_runtime = p->se.sum_exec_runtime,
	};

586
	task_cputime(p, &cputime.utime, &cputime.stime);
587
	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
588
589
590
591
592
}

/*
 * Must be called with siglock held.
 */
593
void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
594
595
596
597
{
	struct task_cputime cputime;

	thread_group_cputime(p, &cputime);
598
	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
599
}
600
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
static DEFINE_PER_CPU(unsigned long long, cputime_snap);

static cputime_t get_vtime_delta(void)
{
	unsigned long long delta;

	delta = sched_clock() - __this_cpu_read(cputime_snap);
	__this_cpu_add(cputime_snap, delta);

	/* CHECKME: always safe to convert nsecs to cputime? */
	return nsecs_to_cputime(delta);
}

void vtime_account_system(struct task_struct *tsk)
{
618
619
620
621
	cputime_t delta_cpu;

	if (!vtime_accounting_enabled())
		return;
622

623
	delta_cpu = get_vtime_delta();
624
625
626
627
628
	account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu));
}

void vtime_account_user(struct task_struct *tsk)
{
629
630
631
632
633
634
	cputime_t delta_cpu;

	if (!vtime_accounting_enabled())
		return;

	delta_cpu = get_vtime_delta();
635
636
637
638
639
640
641
642
643
644

	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
}

void vtime_account_idle(struct task_struct *tsk)
{
	cputime_t delta_cpu = get_vtime_delta();

	account_idle_time(delta_cpu);
}
645
646
647
648
649

bool vtime_accounting_enabled(void)
{
	return context_tracking_active();
}
650
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */