aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched/pelt.h
blob: 3a0e0dc28721960276b97a67eba0bc3ea7343ff5 (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
#ifdef CONFIG_SMP
#include "sched-pelt.h"

int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);

#ifdef CONFIG_SCHED_THERMAL_PRESSURE
int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);

static inline u64 thermal_load_avg(struct rq *rq)
{
	return READ_ONCE(rq->avg_thermal.load_avg);
}
#else
static inline int
update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
{
	return 0;
}

static inline u64 thermal_load_avg(struct rq *rq)
{
	return 0;
}
#endif

#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
int update_irq_load_avg(struct rq *rq, u64 running);
#else
static inline int
update_irq_load_avg(struct rq *rq, u64 running)
{
	return 0;
}
#endif

#define PELT_MIN_DIVIDER	(LOAD_AVG_MAX - 1024)

static inline u32 get_pelt_divider(struct sched_avg *avg)
{
	return PELT_MIN_DIVIDER + avg->period_contrib;
}

static inline void cfs_se_util_change(struct sched_avg *avg)
{
	unsigned int enqueued;

	if (!sched_feat(UTIL_EST))
		return;

	/* Avoid store if the flag has been already reset */
	enqueued = avg->util_est.enqueued;
	if (!(enqueued & UTIL_AVG_UNCHANGED))
		return;

	/* Reset flag to report util_avg has been updated */
	enqueued &= ~UTIL_AVG_UNCHANGED;
	WRITE_ONCE(avg->util_est.enqueued, enqueued);
}

static inline u64 rq_clock_pelt(struct rq *rq)
{
	lockdep_assert_rq_held(rq);
	assert_clock_updated(rq);

	return rq->clock_pelt - rq->lost_idle_time;
}

/* The rq is idle, we can sync to clock_task */
static inline void _update_idle_rq_clock_pelt(struct rq *rq)
{
	rq->clock_pelt  = rq_clock_task(rq);

	u64_u32_store(rq->clock_idle, rq_clock(rq));
	/* Paired with smp_rmb in migrate_se_pelt_lag() */
	smp_wmb();
	u64_u32_store(rq->clock_pelt_idle, rq_clock_pelt(rq));
}

/*
 * The clock_pelt scales the time to reflect the effective amount of
 * computation done during the running delta time but then sync back to
 * clock_task when rq is idle.
 *
 *
 * absolute time   | 1| 2| 3| 4| 5| 6| 7| 8| 9|10|11|12|13|14|15|16
 * @ max capacity  ------******---------------******---------------
 * @ half capacity ------************---------************---------
 * clock pelt      | 1| 2|    3|    4| 7| 8| 9|   10|   11|14|15|16
 *
 */
static inline void update_rq_clock_pelt(struct rq *rq, s64 delta)
{
	if (unlikely(is_idle_task(rq->curr))) {
		_update_idle_rq_clock_pelt(rq);
		return;
	}

	/*
	 * When a rq runs at a lower compute capacity, it will need
	 * more time to do the same amount of work than at max
	 * capacity. In order to be invariant, we scale the delta to
	 * reflect how much work has been really done.
	 * Running longer results in stealing idle time that will
	 * disturb the load signal compared to max capacity. This
	 * stolen idle time will be automatically reflected when the
	 * rq will be idle and the clock will be synced with
	 * rq_clock_task.
	 */

	/*
	 * Scale the elapsed time to reflect the real amount of
	 * computation
	 */
	delta = cap_scale(delta, arch_scale_cpu_capacity(cpu_of(rq)));
	delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq)));

	rq->clock_pelt += delta;
}

/*
 * When rq becomes idle, we have to check if it has lost idle time
 * because it was fully busy. A rq is fully used when the /Sum util_sum
 * is greater or equal to:
 * (LOAD_AVG_MAX - 1024 + rq->cfs.avg.period_contrib) << SCHED_CAPACITY_SHIFT;
 * For optimization and computing rounding purpose, we don't take into account
 * the position in the current window (period_contrib) and we use the higher
 * bound of util_sum to decide.
 */
static inline void update_idle_rq_clock_pelt(struct rq *rq)
{
	u32 divider = ((LOAD_AVG_MAX - 1024) << SCHED_CAPACITY_SHIFT) - LOAD_AVG_MAX;
	u32 util_sum = rq->cfs.avg.util_sum;
	util_sum += rq->avg_rt.util_sum;
	util_sum += rq->avg_dl.util_sum;

	/*
	 * Reflecting stolen time makes sense only if the idle
	 * phase would be present at max capacity. As soon as the
	 * utilization of a rq has reached the maximum value, it is
	 * considered as an always running rq without idle time to
	 * steal. This potential idle time is considered as lost in
	 * this case. We keep track of this lost idle time compare to
	 * rq's clock_task.
	 */
	if (util_sum >= divider)
		rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt;

	_update_idle_rq_clock_pelt(rq);
}

#ifdef CONFIG_CFS_BANDWIDTH
static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
{
	u64 throttled;

	if (unlikely(cfs_rq->throttle_count))
		throttled = U64_MAX;
	else
		throttled = cfs_rq->throttled_clock_pelt_time;

	u64_u32_store(cfs_rq->throttled_pelt_idle, throttled);
}

/* rq->task_clock normalized against any time this cfs_rq has spent throttled */
static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
{
	if (unlikely(cfs_rq->throttle_count))
		return cfs_rq->throttled_clock_pelt - cfs_rq->throttled_clock_pelt_time;

	return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_pelt_time;
}
#else
static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { }
static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
{
	return rq_clock_pelt(rq_of(cfs_rq));
}
#endif

#else

static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
	return 0;
}

static inline int
update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
{
	return 0;
}

static inline int
update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
{
	return 0;
}

static inline int
update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
{
	return 0;
}

static inline u64 thermal_load_avg(struct rq *rq)
{
	return 0;
}

static inline int
update_irq_load_avg(struct rq *rq, u64 running)
{
	return 0;
}

static inline u64 rq_clock_pelt(struct rq *rq)
{
	return rq_clock_task(rq);
}

static inline void
update_rq_clock_pelt(struct rq *rq, s64 delta) { }

static inline void
update_idle_rq_clock_pelt(struct rq *rq) { }

static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { }
#endif