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
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
|
// SPDX-License-Identifier: GPL-2.0
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <poll.h>
#include <pthread.h>
#include <unistd.h>
#include <linux/perf_event.h>
#include <sys/mman.h>
#include "trace_helpers.h"
#include <linux/limits.h>
#include <libelf.h>
#include <gelf.h>
#include "bpf/libbpf_internal.h"
#define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe"
#define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe"
struct ksyms {
struct ksym *syms;
size_t sym_cap;
size_t sym_cnt;
};
static struct ksyms *ksyms;
static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
static int ksyms__add_symbol(struct ksyms *ksyms, const char *name,
unsigned long addr)
{
void *tmp;
tmp = strdup(name);
if (!tmp)
return -ENOMEM;
ksyms->syms[ksyms->sym_cnt].addr = addr;
ksyms->syms[ksyms->sym_cnt].name = tmp;
ksyms->sym_cnt++;
return 0;
}
void free_kallsyms_local(struct ksyms *ksyms)
{
unsigned int i;
if (!ksyms)
return;
if (!ksyms->syms) {
free(ksyms);
return;
}
for (i = 0; i < ksyms->sym_cnt; i++)
free(ksyms->syms[i].name);
free(ksyms->syms);
free(ksyms);
}
static int ksym_cmp(const void *p1, const void *p2)
{
return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
}
struct ksyms *load_kallsyms_local(void)
{
FILE *f;
char func[256], buf[256];
char symbol;
void *addr;
int ret;
struct ksyms *ksyms;
f = fopen("/proc/kallsyms", "r");
if (!f)
return NULL;
ksyms = calloc(1, sizeof(struct ksyms));
if (!ksyms) {
fclose(f);
return NULL;
}
while (fgets(buf, sizeof(buf), f)) {
if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
break;
if (!addr)
continue;
ret = libbpf_ensure_mem((void **) &ksyms->syms, &ksyms->sym_cap,
sizeof(struct ksym), ksyms->sym_cnt + 1);
if (ret)
goto error;
ret = ksyms__add_symbol(ksyms, func, (unsigned long)addr);
if (ret)
goto error;
}
fclose(f);
qsort(ksyms->syms, ksyms->sym_cnt, sizeof(struct ksym), ksym_cmp);
return ksyms;
error:
fclose(f);
free_kallsyms_local(ksyms);
return NULL;
}
int load_kallsyms(void)
{
pthread_mutex_lock(&ksyms_mutex);
if (!ksyms)
ksyms = load_kallsyms_local();
pthread_mutex_unlock(&ksyms_mutex);
return ksyms ? 0 : 1;
}
struct ksym *ksym_search_local(struct ksyms *ksyms, long key)
{
int start = 0, end = ksyms->sym_cnt;
int result;
/* kallsyms not loaded. return NULL */
if (ksyms->sym_cnt <= 0)
return NULL;
while (start < end) {
size_t mid = start + (end - start) / 2;
result = key - ksyms->syms[mid].addr;
if (result < 0)
end = mid;
else if (result > 0)
start = mid + 1;
else
return &ksyms->syms[mid];
}
if (start >= 1 && ksyms->syms[start - 1].addr < key &&
key < ksyms->syms[start].addr)
/* valid ksym */
return &ksyms->syms[start - 1];
/* out of range. return _stext */
return &ksyms->syms[0];
}
struct ksym *ksym_search(long key)
{
if (!ksyms)
return NULL;
return ksym_search_local(ksyms, key);
}
long ksym_get_addr_local(struct ksyms *ksyms, const char *name)
{
int i;
for (i = 0; i < ksyms->sym_cnt; i++) {
if (strcmp(ksyms->syms[i].name, name) == 0)
return ksyms->syms[i].addr;
}
return 0;
}
long ksym_get_addr(const char *name)
{
if (!ksyms)
return 0;
return ksym_get_addr_local(ksyms, name);
}
/* open kallsyms and read symbol addresses on the fly. Without caching all symbols,
* this is faster than load + find.
*/
int kallsyms_find(const char *sym, unsigned long long *addr)
{
char type, name[500];
unsigned long long value;
int err = 0;
FILE *f;
f = fopen("/proc/kallsyms", "r");
if (!f)
return -EINVAL;
while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
if (strcmp(name, sym) == 0) {
*addr = value;
goto out;
}
}
err = -ENOENT;
out:
fclose(f);
return err;
}
void read_trace_pipe(void)
{
int trace_fd;
if (access(TRACEFS_PIPE, F_OK) == 0)
trace_fd = open(TRACEFS_PIPE, O_RDONLY, 0);
else
trace_fd = open(DEBUGFS_PIPE, O_RDONLY, 0);
if (trace_fd < 0)
return;
while (1) {
static char buf[4096];
ssize_t sz;
sz = read(trace_fd, buf, sizeof(buf) - 1);
if (sz > 0) {
buf[sz] = 0;
puts(buf);
}
}
}
ssize_t get_uprobe_offset(const void *addr)
{
size_t start, end, base;
char buf[256];
bool found = false;
FILE *f;
f = fopen("/proc/self/maps", "r");
if (!f)
return -errno;
while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
found = true;
break;
}
}
fclose(f);
if (!found)
return -ESRCH;
#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
#define OP_RT_RA_MASK 0xffff0000UL
#define LIS_R2 0x3c400000UL
#define ADDIS_R2_R12 0x3c4c0000UL
#define ADDI_R2_R2 0x38420000UL
/*
* A PPC64 ABIv2 function may have a local and a global entry
* point. We need to use the local entry point when patching
* functions, so identify and step over the global entry point
* sequence.
*
* The global entry point sequence is always of the form:
*
* addis r2,r12,XXXX
* addi r2,r2,XXXX
*
* A linker optimisation may convert the addis to lis:
*
* lis r2,XXXX
* addi r2,r2,XXXX
*/
{
const __u32 *insn = (const __u32 *)(uintptr_t)addr;
if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2))
return (uintptr_t)(insn + 2) - start + base;
}
#endif
return (uintptr_t)addr - start + base;
}
ssize_t get_rel_offset(uintptr_t addr)
{
size_t start, end, offset;
char buf[256];
FILE *f;
f = fopen("/proc/self/maps", "r");
if (!f)
return -errno;
while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
if (addr >= start && addr < end) {
fclose(f);
return (size_t)addr - start + offset;
}
}
fclose(f);
return -EINVAL;
}
static int
parse_build_id_buf(const void *note_start, Elf32_Word note_size, char *build_id)
{
Elf32_Word note_offs = 0;
while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
if (nhdr->n_type == 3 && nhdr->n_namesz == sizeof("GNU") &&
!strcmp((char *)(nhdr + 1), "GNU") && nhdr->n_descsz > 0 &&
nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
memcpy(build_id, note_start + note_offs +
ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr), nhdr->n_descsz);
memset(build_id + nhdr->n_descsz, 0, BPF_BUILD_ID_SIZE - nhdr->n_descsz);
return (int) nhdr->n_descsz;
}
note_offs = note_offs + sizeof(Elf32_Nhdr) +
ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
}
return -ENOENT;
}
/* Reads binary from *path* file and returns it in the *build_id* buffer
* with *size* which is expected to be at least BPF_BUILD_ID_SIZE bytes.
* Returns size of build id on success. On error the error value is
* returned.
*/
int read_build_id(const char *path, char *build_id, size_t size)
{
int fd, err = -EINVAL;
Elf *elf = NULL;
GElf_Ehdr ehdr;
size_t max, i;
if (size < BPF_BUILD_ID_SIZE)
return -EINVAL;
fd = open(path, O_RDONLY | O_CLOEXEC);
if (fd < 0)
return -errno;
(void)elf_version(EV_CURRENT);
elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
if (!elf)
goto out;
if (elf_kind(elf) != ELF_K_ELF)
goto out;
if (!gelf_getehdr(elf, &ehdr))
goto out;
for (i = 0; i < ehdr.e_phnum; i++) {
GElf_Phdr mem, *phdr;
char *data;
phdr = gelf_getphdr(elf, i, &mem);
if (!phdr)
goto out;
if (phdr->p_type != PT_NOTE)
continue;
data = elf_rawfile(elf, &max);
if (!data)
goto out;
if (phdr->p_offset + phdr->p_memsz > max)
goto out;
err = parse_build_id_buf(data + phdr->p_offset, phdr->p_memsz, build_id);
if (err > 0)
break;
}
out:
if (elf)
elf_end(elf);
close(fd);
return err;
}
|