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
|
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
// Copyright (c) 2022 Google
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <bpf/bpf_core_read.h>
#include "lock_data.h"
/* default buffer size */
#define MAX_ENTRIES 10240
struct tstamp_data {
__u64 timestamp;
__u64 lock;
__u32 flags;
__s32 stack_id;
};
/* callstack storage */
struct {
__uint(type, BPF_MAP_TYPE_STACK_TRACE);
__uint(key_size, sizeof(__u32));
__uint(value_size, sizeof(__u64));
__uint(max_entries, MAX_ENTRIES);
} stacks SEC(".maps");
/* maintain timestamp at the beginning of contention */
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, int);
__type(value, struct tstamp_data);
__uint(max_entries, MAX_ENTRIES);
} tstamp SEC(".maps");
/* actual lock contention statistics */
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(key_size, sizeof(struct contention_key));
__uint(value_size, sizeof(struct contention_data));
__uint(max_entries, MAX_ENTRIES);
} lock_stat SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(key_size, sizeof(__u32));
__uint(value_size, sizeof(struct contention_task_data));
__uint(max_entries, MAX_ENTRIES);
} task_data SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(key_size, sizeof(__u32));
__uint(value_size, sizeof(__u8));
__uint(max_entries, 1);
} cpu_filter SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(key_size, sizeof(__u32));
__uint(value_size, sizeof(__u8));
__uint(max_entries, 1);
} task_filter SEC(".maps");
/* control flags */
int enabled;
int has_cpu;
int has_task;
int stack_skip;
/* determine the key of lock stat */
int aggr_mode;
/* error stat */
int lost;
static inline int can_record(void)
{
if (has_cpu) {
__u32 cpu = bpf_get_smp_processor_id();
__u8 *ok;
ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
if (!ok)
return 0;
}
if (has_task) {
__u8 *ok;
__u32 pid = bpf_get_current_pid_tgid();
ok = bpf_map_lookup_elem(&task_filter, &pid);
if (!ok)
return 0;
}
return 1;
}
static inline void update_task_data(__u32 pid)
{
struct contention_task_data *p;
p = bpf_map_lookup_elem(&task_data, &pid);
if (p == NULL) {
struct contention_task_data data;
bpf_get_current_comm(data.comm, sizeof(data.comm));
bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST);
}
}
SEC("tp_btf/contention_begin")
int contention_begin(u64 *ctx)
{
__u32 pid;
struct tstamp_data *pelem;
if (!enabled || !can_record())
return 0;
pid = bpf_get_current_pid_tgid();
pelem = bpf_map_lookup_elem(&tstamp, &pid);
if (pelem && pelem->lock)
return 0;
if (pelem == NULL) {
struct tstamp_data zero = {};
bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY);
pelem = bpf_map_lookup_elem(&tstamp, &pid);
if (pelem == NULL) {
lost++;
return 0;
}
}
pelem->timestamp = bpf_ktime_get_ns();
pelem->lock = (__u64)ctx[0];
pelem->flags = (__u32)ctx[1];
if (aggr_mode == LOCK_AGGR_CALLER) {
pelem->stack_id = bpf_get_stackid(ctx, &stacks,
BPF_F_FAST_STACK_CMP | stack_skip);
if (pelem->stack_id < 0)
lost++;
}
return 0;
}
SEC("tp_btf/contention_end")
int contention_end(u64 *ctx)
{
__u32 pid;
struct tstamp_data *pelem;
struct contention_key key;
struct contention_data *data;
__u64 duration;
if (!enabled)
return 0;
pid = bpf_get_current_pid_tgid();
pelem = bpf_map_lookup_elem(&tstamp, &pid);
if (!pelem || pelem->lock != ctx[0])
return 0;
duration = bpf_ktime_get_ns() - pelem->timestamp;
switch (aggr_mode) {
case LOCK_AGGR_CALLER:
key.aggr_key = pelem->stack_id;
break;
case LOCK_AGGR_TASK:
key.aggr_key = pid;
update_task_data(pid);
break;
case LOCK_AGGR_ADDR:
key.aggr_key = pelem->lock;
break;
default:
/* should not happen */
return 0;
}
data = bpf_map_lookup_elem(&lock_stat, &key);
if (!data) {
struct contention_data first = {
.total_time = duration,
.max_time = duration,
.min_time = duration,
.count = 1,
.flags = pelem->flags,
};
bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
bpf_map_delete_elem(&tstamp, &pid);
return 0;
}
__sync_fetch_and_add(&data->total_time, duration);
__sync_fetch_and_add(&data->count, 1);
/* FIXME: need atomic operations */
if (data->max_time < duration)
data->max_time = duration;
if (data->min_time > duration)
data->min_time = duration;
bpf_map_delete_elem(&tstamp, &pid);
return 0;
}
char LICENSE[] SEC("license") = "Dual BSD/GPL";
|
