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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Energy Model of CPUs
*
* Copyright (c) 2018, Arm ltd.
* Written by: Quentin Perret, Arm ltd.
*/
#define pr_fmt(fmt) "energy_model: " fmt
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/energy_model.h>
#include <linux/sched/topology.h>
#include <linux/slab.h>
/* Mapping of each CPU to the performance domain to which it belongs. */
static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
/*
* Mutex serializing the registrations of performance domains and letting
* callbacks defined by drivers sleep.
*/
static DEFINE_MUTEX(em_pd_mutex);
static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
struct em_data_callback *cb)
{
unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
unsigned long power, freq, prev_freq = 0;
int i, ret, cpu = cpumask_first(span);
struct em_cap_state *table;
struct em_perf_domain *pd;
u64 fmax;
if (!cb->active_power)
return NULL;
pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
if (!pd)
return NULL;
table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
if (!table)
goto free_pd;
/* Build the list of capacity states for this performance domain */
for (i = 0, freq = 0; i < nr_states; i++, freq++) {
/*
* active_power() is a driver callback which ceils 'freq' to
* lowest capacity state of 'cpu' above 'freq' and updates
* 'power' and 'freq' accordingly.
*/
ret = cb->active_power(&power, &freq, cpu);
if (ret) {
pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
goto free_cs_table;
}
/*
* We expect the driver callback to increase the frequency for
* higher capacity states.
*/
if (freq <= prev_freq) {
pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
goto free_cs_table;
}
/*
* The power returned by active_state() is expected to be
* positive, in milli-watts and to fit into 16 bits.
*/
if (!power || power > EM_CPU_MAX_POWER) {
pr_err("pd%d: invalid power: %lu\n", cpu, power);
goto free_cs_table;
}
table[i].power = power;
table[i].frequency = prev_freq = freq;
/*
* The hertz/watts efficiency ratio should decrease as the
* frequency grows on sane platforms. But this isn't always
* true in practice so warn the user if a higher OPP is more
* power efficient than a lower one.
*/
opp_eff = freq / power;
if (opp_eff >= prev_opp_eff)
pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
cpu, i, i - 1);
prev_opp_eff = opp_eff;
}
/* Compute the cost of each capacity_state. */
fmax = (u64) table[nr_states - 1].frequency;
for (i = 0; i < nr_states; i++) {
table[i].cost = div64_u64(fmax * table[i].power,
table[i].frequency);
}
pd->table = table;
pd->nr_cap_states = nr_states;
cpumask_copy(to_cpumask(pd->cpus), span);
return pd;
free_cs_table:
kfree(table);
free_pd:
kfree(pd);
return NULL;
}
/**
* em_cpu_get() - Return the performance domain for a CPU
* @cpu : CPU to find the performance domain for
*
* Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
* exist.
*/
struct em_perf_domain *em_cpu_get(int cpu)
{
return READ_ONCE(per_cpu(em_data, cpu));
}
EXPORT_SYMBOL_GPL(em_cpu_get);
/**
* em_register_perf_domain() - Register the Energy Model of a performance domain
* @span : Mask of CPUs in the performance domain
* @nr_states : Number of capacity states to register
* @cb : Callback functions providing the data of the Energy Model
*
* Create Energy Model tables for a performance domain using the callbacks
* defined in cb.
*
* If multiple clients register the same performance domain, all but the first
* registration will be ignored.
*
* Return 0 on success
*/
int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
struct em_data_callback *cb)
{
unsigned long cap, prev_cap = 0;
struct em_perf_domain *pd;
int cpu, ret = 0;
if (!span || !nr_states || !cb)
return -EINVAL;
/*
* Use a mutex to serialize the registration of performance domains and
* let the driver-defined callback functions sleep.
*/
mutex_lock(&em_pd_mutex);
for_each_cpu(cpu, span) {
/* Make sure we don't register again an existing domain. */
if (READ_ONCE(per_cpu(em_data, cpu))) {
ret = -EEXIST;
goto unlock;
}
/*
* All CPUs of a domain must have the same micro-architecture
* since they all share the same table.
*/
cap = arch_scale_cpu_capacity(NULL, cpu);
if (prev_cap && prev_cap != cap) {
pr_err("CPUs of %*pbl must have the same capacity\n",
cpumask_pr_args(span));
ret = -EINVAL;
goto unlock;
}
prev_cap = cap;
}
/* Create the performance domain and add it to the Energy Model. */
pd = em_create_pd(span, nr_states, cb);
if (!pd) {
ret = -EINVAL;
goto unlock;
}
for_each_cpu(cpu, span) {
/*
* The per-cpu array can be read concurrently from em_cpu_get().
* The barrier enforces the ordering needed to make sure readers
* can only access well formed em_perf_domain structs.
*/
smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
}
pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
unlock:
mutex_unlock(&em_pd_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(em_register_perf_domain);
|
