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
|
/*
* arch/arm/kernel/topology.c
*
* Copyright (C) 2011 Linaro Limited.
* Written by: Vincent Guittot
*
* based on arch/sh/kernel/topology.c
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*/
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/node.h>
#include <linux/nodemask.h>
#include <linux/sched.h>
#include <asm/cputype.h>
#include <asm/topology.h>
/*
* cpu power scale management
*/
/*
* cpu power table
* This per cpu data structure describes the relative capacity of each core.
* On a heteregenous system, cores don't have the same computation capacity
* and we reflect that difference in the cpu_power field so the scheduler can
* take this difference into account during load balance. A per cpu structure
* is preferred because each CPU updates its own cpu_power field during the
* load balance except for idle cores. One idle core is selected to run the
* rebalance_domains for all idle cores and the cpu_power can be updated
* during this sequence.
*/
static DEFINE_PER_CPU(unsigned long, cpu_scale);
unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
{
return per_cpu(cpu_scale, cpu);
}
static void set_power_scale(unsigned int cpu, unsigned long power)
{
per_cpu(cpu_scale, cpu) = power;
}
/*
* cpu topology management
*/
#define MPIDR_SMP_BITMASK (0x3 << 30)
#define MPIDR_SMP_VALUE (0x2 << 30)
#define MPIDR_MT_BITMASK (0x1 << 24)
/*
* These masks reflect the current use of the affinity levels.
* The affinity level can be up to 16 bits according to ARM ARM
*/
#define MPIDR_LEVEL0_MASK 0x3
#define MPIDR_LEVEL0_SHIFT 0
#define MPIDR_LEVEL1_MASK 0xF
#define MPIDR_LEVEL1_SHIFT 8
#define MPIDR_LEVEL2_MASK 0xFF
#define MPIDR_LEVEL2_SHIFT 16
/*
* cpu topology table
*/
struct cputopo_arm cpu_topology[NR_CPUS];
const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_topology[cpu].core_sibling;
}
void update_siblings_masks(unsigned int cpuid)
{
struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
int cpu;
/* update core and thread sibling masks */
for_each_possible_cpu(cpu) {
cpu_topo = &cpu_topology[cpu];
if (cpuid_topo->socket_id != cpu_topo->socket_id)
continue;
cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
if (cpu != cpuid)
cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
if (cpuid_topo->core_id != cpu_topo->core_id)
continue;
cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
if (cpu != cpuid)
cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
}
smp_wmb();
}
/*
* store_cpu_topology is called at boot when only one cpu is running
* and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
* which prevents simultaneous write access to cpu_topology array
*/
void store_cpu_topology(unsigned int cpuid)
{
struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
unsigned int mpidr;
/* If the cpu topology has been already set, just return */
if (cpuid_topo->core_id != -1)
return;
mpidr = read_cpuid_mpidr();
/* create cpu topology mapping */
if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
/*
* This is a multiprocessor system
* multiprocessor format & multiprocessor mode field are set
*/
if (mpidr & MPIDR_MT_BITMASK) {
/* core performance interdependency */
cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
& MPIDR_LEVEL0_MASK;
cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
& MPIDR_LEVEL1_MASK;
cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
& MPIDR_LEVEL2_MASK;
} else {
/* largely independent cores */
cpuid_topo->thread_id = -1;
cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
& MPIDR_LEVEL0_MASK;
cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
& MPIDR_LEVEL1_MASK;
}
} else {
/*
* This is an uniprocessor system
* we are in multiprocessor format but uniprocessor system
* or in the old uniprocessor format
*/
cpuid_topo->thread_id = -1;
cpuid_topo->core_id = 0;
cpuid_topo->socket_id = -1;
}
update_siblings_masks(cpuid);
printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
cpuid, cpu_topology[cpuid].thread_id,
cpu_topology[cpuid].core_id,
cpu_topology[cpuid].socket_id, mpidr);
}
/*
* init_cpu_topology is called at boot when only one cpu is running
* which prevent simultaneous write access to cpu_topology array
*/
void init_cpu_topology(void)
{
unsigned int cpu;
/* init core mask and power*/
for_each_possible_cpu(cpu) {
struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
cpu_topo->thread_id = -1;
cpu_topo->core_id = -1;
cpu_topo->socket_id = -1;
cpumask_clear(&cpu_topo->core_sibling);
cpumask_clear(&cpu_topo->thread_sibling);
set_power_scale(cpu, SCHED_POWER_SCALE);
}
smp_wmb();
}
|
