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
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
|
/* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/vmalloc.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include "percpu_freelist.h"
struct stack_map_bucket {
struct pcpu_freelist_node fnode;
u32 hash;
u32 nr;
u64 ip[];
};
struct bpf_stack_map {
struct bpf_map map;
void *elems;
struct pcpu_freelist freelist;
u32 n_buckets;
struct stack_map_bucket *buckets[];
};
static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
int err;
smap->elems = vzalloc(elem_size * smap->map.max_entries);
if (!smap->elems)
return -ENOMEM;
err = pcpu_freelist_init(&smap->freelist);
if (err)
goto free_elems;
pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
smap->map.max_entries);
return 0;
free_elems:
vfree(smap->elems);
return err;
}
/* Called from syscall */
static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
{
u32 value_size = attr->value_size;
struct bpf_stack_map *smap;
u64 cost, n_buckets;
int err;
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
if (attr->map_flags)
return ERR_PTR(-EINVAL);
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
value_size < 8 || value_size % 8 ||
value_size / 8 > sysctl_perf_event_max_stack)
return ERR_PTR(-EINVAL);
/* hash table size must be power of 2 */
n_buckets = roundup_pow_of_two(attr->max_entries);
cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
if (!smap) {
smap = vzalloc(cost);
if (!smap)
return ERR_PTR(-ENOMEM);
}
err = -E2BIG;
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
if (cost >= U32_MAX - PAGE_SIZE)
goto free_smap;
smap->map.map_type = attr->map_type;
smap->map.key_size = attr->key_size;
smap->map.value_size = value_size;
smap->map.max_entries = attr->max_entries;
smap->n_buckets = n_buckets;
smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
err = bpf_map_precharge_memlock(smap->map.pages);
if (err)
goto free_smap;
err = get_callchain_buffers(sysctl_perf_event_max_stack);
if (err)
goto free_smap;
err = prealloc_elems_and_freelist(smap);
if (err)
goto put_buffers;
return &smap->map;
put_buffers:
put_callchain_buffers();
free_smap:
kvfree(smap);
return ERR_PTR(err);
}
static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
{
struct pt_regs *regs = (struct pt_regs *) (long) r1;
struct bpf_map *map = (struct bpf_map *) (long) r2;
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
struct perf_callchain_entry *trace;
struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
u32 max_depth = map->value_size / 8;
/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
u32 init_nr = sysctl_perf_event_max_stack - max_depth;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
u32 hash, id, trace_nr, trace_len;
bool user = flags & BPF_F_USER_STACK;
bool kernel = !user;
u64 *ips;
if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
trace = get_perf_callchain(regs, init_nr, kernel, user,
sysctl_perf_event_max_stack, false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
return -EFAULT;
/* get_perf_callchain() guarantees that trace->nr >= init_nr
* and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
*/
trace_nr = trace->nr - init_nr;
if (trace_nr <= skip)
/* skipping more than usable stack trace */
return -EFAULT;
trace_nr -= skip;
trace_len = trace_nr * sizeof(u64);
ips = trace->ip + skip + init_nr;
hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
id = hash & (smap->n_buckets - 1);
bucket = READ_ONCE(smap->buckets[id]);
if (bucket && bucket->hash == hash) {
if (flags & BPF_F_FAST_STACK_CMP)
return id;
if (bucket->nr == trace_nr &&
memcmp(bucket->ip, ips, trace_len) == 0)
return id;
}
/* this call stack is not in the map, try to add it */
if (bucket && !(flags & BPF_F_REUSE_STACKID))
return -EEXIST;
new_bucket = (struct stack_map_bucket *)
pcpu_freelist_pop(&smap->freelist);
if (unlikely(!new_bucket))
return -ENOMEM;
memcpy(new_bucket->ip, ips, trace_len);
new_bucket->hash = hash;
new_bucket->nr = trace_nr;
old_bucket = xchg(&smap->buckets[id], new_bucket);
if (old_bucket)
pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
return id;
}
const struct bpf_func_proto bpf_get_stackid_proto = {
.func = bpf_get_stackid,
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
};
/* Called from eBPF program */
static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}
/* Called from syscall */
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
struct stack_map_bucket *bucket, *old_bucket;
u32 id = *(u32 *)key, trace_len;
if (unlikely(id >= smap->n_buckets))
return -ENOENT;
bucket = xchg(&smap->buckets[id], NULL);
if (!bucket)
return -ENOENT;
trace_len = bucket->nr * sizeof(u64);
memcpy(value, bucket->ip, trace_len);
memset(value + trace_len, 0, map->value_size - trace_len);
old_bucket = xchg(&smap->buckets[id], bucket);
if (old_bucket)
pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
return 0;
}
static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
return -EINVAL;
}
static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
return -EINVAL;
}
/* Called from syscall or from eBPF program */
static int stack_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
struct stack_map_bucket *old_bucket;
|