summaryrefslogtreecommitdiffstats
path: root/kernel/delayacct.c
blob: 3f086903b2954f9319f5163326517ecb27a08cd6 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* delayacct.c - per-task delay accounting
 *
 * Copyright (C) Shailabh Nagar, IBM Corp. 2006
 */

#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
#include <linux/sched/clock.h>
#include <linux/slab.h>
#include <linux/taskstats.h>
#include <linux/sysctl.h>
#include <linux/delayacct.h>
#include <linux/module.h>

DEFINE_STATIC_KEY_FALSE(delayacct_key);
int delayacct_on __read_mostly;	/* Delay accounting turned on/off */
struct kmem_cache *delayacct_cache;

static int __init delayacct_setup_enable(char *str)
{
	delayacct_on = 1;
	return 1;
}
__setup("delayacct", delayacct_setup_enable);

void delayacct_init(void)
{
	delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT);
	delayacct_tsk_init(&init_task);
	if (delayacct_on)
		static_branch_enable(&delayacct_key);
}

void __delayacct_tsk_init(struct task_struct *tsk)
{
	tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
	if (tsk->delays)
		raw_spin_lock_init(&tsk->delays->lock);
}

/*
 * Finish delay accounting for a statistic using its timestamps (@start),
 * accumalator (@total) and @count
 */
static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count)
{
	s64 ns = local_clock() - *start;
	unsigned long flags;

	if (ns > 0) {
		raw_spin_lock_irqsave(lock, flags);
		*total += ns;
		(*count)++;
		raw_spin_unlock_irqrestore(lock, flags);
	}
}

void __delayacct_blkio_start(void)
{
	current->delays->blkio_start = local_clock();
}

/*
 * We cannot rely on the `current` macro, as we haven't yet switched back to
 * the process being woken.
 */
void __delayacct_blkio_end(struct task_struct *p)
{
	struct task_delay_info *delays = p->delays;
	u64 *total;
	u32 *count;

	if (p->delays->flags & DELAYACCT_PF_SWAPIN) {
		total = &delays->swapin_delay;
		count = &delays->swapin_count;
	} else {
		total = &delays->blkio_delay;
		count = &delays->blkio_count;
	}

	delayacct_end(&delays->lock, &delays->blkio_start, total, count);
}

int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
{
	u64 utime, stime, stimescaled, utimescaled;
	unsigned long long t2, t3;
	unsigned long flags, t1;
	s64 tmp;

	task_cputime(tsk, &utime, &stime);
	tmp = (s64)d->cpu_run_real_total;
	tmp += utime + stime;
	d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;

	task_cputime_scaled(tsk, &utimescaled, &stimescaled);
	tmp = (s64)d->cpu_scaled_run_real_total;
	tmp += utimescaled + stimescaled;
	d->cpu_scaled_run_real_total =
		(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;

	/*
	 * No locking available for sched_info (and too expensive to add one)
	 * Mitigate by taking snapshot of values
	 */
	t1 = tsk->sched_info.pcount;
	t2 = tsk->sched_info.run_delay;
	t3 = tsk->se.sum_exec_runtime;

	d->cpu_count += t1;

	tmp = (s64)d->cpu_delay_total + t2;
	d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp;

	tmp = (s64)d->cpu_run_virtual_total + t3;
	d->cpu_run_virtual_total =
		(tmp < (s64)d->cpu_run_virtual_total) ?	0 : tmp;

	if (!tsk->delays)
		return 0;

	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */

	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
	tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
	d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
	tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
	d->blkio_count += tsk->delays->blkio_count;
	d->swapin_count += tsk->delays->swapin_count;
	d->freepages_count += tsk->delays->freepages_count;
	d->thrashing_count += tsk->delays->thrashing_count;
	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);

	return 0;
}

__u64 __delayacct_blkio_ticks(struct task_struct *tsk)
{
	__u64 ret;
	unsigned long flags;

	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
	ret = nsec_to_clock_t(tsk->delays->blkio_delay +
				tsk->delays->swapin_delay);
	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
	return ret;
}

void __delayacct_freepages_start(void)
{
	current->delays->freepages_start = local_clock();
}

void __delayacct_freepages_end(void)
{
	delayacct_end(&current->delays->lock,
		      &current->delays->freepages_start,
		      &current->delays->freepages_delay,
		      &current->delays->freepages_count);
}

void __delayacct_thrashing_start(void)
{
	current->delays->thrashing_start = local_clock();
}

void __delayacct_thrashing_end(void)
{
	delayacct_end(&current->delays->lock,
		      &current->delays->thrashing_start,
		      &current->delays->thrashing_delay,
		      &current->delays->thrashing_count);
}