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
|
#include <linux/perf_event.h>
#include <linux/types.h>
#include <asm/perf_event.h>
#include <asm/msr.h>
#include "perf_event.h"
enum {
LBR_FORMAT_32 = 0x00,
LBR_FORMAT_LIP = 0x01,
LBR_FORMAT_EIP = 0x02,
LBR_FORMAT_EIP_FLAGS = 0x03,
};
/*
* We only support LBR implementations that have FREEZE_LBRS_ON_PMI
* otherwise it becomes near impossible to get a reliable stack.
*/
static void __intel_pmu_lbr_enable(void)
{
u64 debugctl;
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
}
static void __intel_pmu_lbr_disable(void)
{
u64 debugctl;
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
}
static void intel_pmu_lbr_reset_32(void)
{
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++)
wrmsrl(x86_pmu.lbr_from + i, 0);
}
static void intel_pmu_lbr_reset_64(void)
{
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
wrmsrl(x86_pmu.lbr_from + i, 0);
wrmsrl(x86_pmu.lbr_to + i, 0);
}
}
void intel_pmu_lbr_reset(void)
{
if (!x86_pmu.lbr_nr)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
intel_pmu_lbr_reset_32();
else
intel_pmu_lbr_reset_64();
}
void intel_pmu_lbr_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (!x86_pmu.lbr_nr)
return;
/*
* Reset the LBR stack if we changed task context to
* avoid data leaks.
*/
if (event->ctx->task && cpuc->lbr_context != event->ctx) {
intel_pmu_lbr_reset();
cpuc->lbr_context = event->ctx;
}
cpuc->lbr_users++;
}
void intel_pmu_lbr_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (!x86_pmu.lbr_nr)
return;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
if (cpuc->enabled && !cpuc->lbr_users)
__intel_pmu_lbr_disable();
}
void intel_pmu_lbr_enable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (cpuc->lbr_users)
__intel_pmu_lbr_enable();
}
void intel_pmu_lbr_disable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (cpuc->lbr_users)
__intel_pmu_lbr_disable();
}
static inline u64 intel_pmu_lbr_tos(void)
{
u64 tos;
rdmsrl(x86_pmu.lbr_tos, tos);
return tos;
}
static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
{
unsigned long mask = x86_pmu.lbr_nr - 1;
u64 tos = intel_pmu_lbr_tos();
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
union {
struct {
u32 from;
u32 to;
};
u64 lbr;
} msr_lastbranch;
rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
cpuc->lbr_entries[i].from = msr_lastbranch.from;
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].flags = 0;
}
cpuc->lbr_stack.nr = i;
}
#define LBR_FROM_FLAG_MISPRED (1ULL << 63)
/*
* Due to lack of segmentation in Linux the effective address (offset)
* is the same as the linear address, allowing us to merge the LIP and EIP
* LBR formats.
*/
static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
{
unsigned long mask = x86_pmu.lbr_nr - 1;
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
u64 from, to, flags = 0;
rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
rdmsrl(x86_pmu.lbr_to + lbr_idx, to);
if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
flags = !!(from & LBR_FROM_FLAG_MISPRED);
from = (u64)((((s64)from) << 1) >> 1);
}
cpuc->lbr_entries[i].from = from;
cpuc->lbr_entries[i].to = to;
cpuc->lbr_entries[i].flags = flags;
}
cpuc->lbr_stack.nr = i;
}
void intel_pmu_lbr_read(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (!cpuc->lbr_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
intel_pmu_lbr_read_32(cpuc);
else
intel_pmu_lbr_read_64(cpuc);
}
void intel_pmu_lbr_init_core(void)
{
x86_pmu.lbr_nr = 4;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x40;
x86_pmu.lbr_to = 0x60;
}
void intel_pmu_lbr_init_nhm(void)
{
x86_pmu.lbr_nr = 16;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x680;
x86_pmu.lbr_to = 0x6c0;
}
void intel_pmu_lbr_init_atom(void)
{
x86_pmu.lbr_nr = 8;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x40;
x86_pmu.lbr_to = 0x60;
}
|
