forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
recordmcount.c
673 lines (600 loc) · 17.2 KB
/
recordmcount.c
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
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
/*
* recordmcount.c: construct a table of the locations of calls to 'mcount'
* so that ftrace can find them quickly.
* Copyright 2009 John F. Reiser <[email protected]>. All rights reserved.
* Licensed under the GNU General Public License, version 2 (GPLv2).
*
* Restructured to fit Linux format, as well as other updates:
* Copyright 2010 Steven Rostedt <[email protected]>, Red Hat Inc.
*/
/*
* Strategy: alter the .o file in-place.
*
* Append a new STRTAB that has the new section names, followed by a new array
* ElfXX_Shdr[] that has the new section headers, followed by the section
* contents for __mcount_loc and its relocations. The old shstrtab strings,
* and the old ElfXX_Shdr[] array, remain as "garbage" (commonly, a couple
* kilobytes.) Subsequent processing by /bin/ld (or the kernel module loader)
* will ignore the garbage regions, because they are not designated by the
* new .e_shoff nor the new ElfXX_Shdr[]. [In order to remove the garbage,
* then use "ld -r" to create a new file that omits the garbage.]
*/
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <getopt.h>
#include <elf.h>
#include <fcntl.h>
#include <setjmp.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
/*
* glibc synced up and added the metag number but didn't add the relocations.
* Work around this in a crude manner for now.
*/
#ifndef EM_METAG
#define EM_METAG 174
#endif
#ifndef R_METAG_ADDR32
#define R_METAG_ADDR32 2
#endif
#ifndef R_METAG_NONE
#define R_METAG_NONE 3
#endif
#ifndef EM_AARCH64
#define EM_AARCH64 183
#define R_AARCH64_NONE 0
#define R_AARCH64_ABS64 257
#endif
static int fd_map; /* File descriptor for file being modified. */
static int mmap_failed; /* Boolean flag. */
static char gpfx; /* prefix for global symbol name (sometimes '_') */
static struct stat sb; /* Remember .st_size, etc. */
static jmp_buf jmpenv; /* setjmp/longjmp per-file error escape */
static const char *altmcount; /* alternate mcount symbol name */
static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
static void *file_map; /* pointer of the mapped file */
static void *file_end; /* pointer to the end of the mapped file */
static int file_updated; /* flag to state file was changed */
static void *file_ptr; /* current file pointer location */
static void *file_append; /* added to the end of the file */
static size_t file_append_size; /* how much is added to end of file */
/* setjmp() return values */
enum {
SJ_SETJMP = 0, /* hardwired first return */
SJ_FAIL,
SJ_SUCCEED
};
/* Per-file resource cleanup when multiple files. */
static void
cleanup(void)
{
if (!mmap_failed)
munmap(file_map, sb.st_size);
else
free(file_map);
file_map = NULL;
free(file_append);
file_append = NULL;
file_append_size = 0;
file_updated = 0;
}
static void __attribute__((noreturn))
fail_file(void)
{
cleanup();
longjmp(jmpenv, SJ_FAIL);
}
static void __attribute__((noreturn))
succeed_file(void)
{
cleanup();
longjmp(jmpenv, SJ_SUCCEED);
}
/* ulseek, uread, ...: Check return value for errors. */
static off_t
ulseek(int const fd, off_t const offset, int const whence)
{
switch (whence) {
case SEEK_SET:
file_ptr = file_map + offset;
break;
case SEEK_CUR:
file_ptr += offset;
break;
case SEEK_END:
file_ptr = file_map + (sb.st_size - offset);
break;
}
if (file_ptr < file_map) {
fprintf(stderr, "lseek: seek before file\n");
fail_file();
}
return file_ptr - file_map;
}
static size_t
uread(int const fd, void *const buf, size_t const count)
{
size_t const n = read(fd, buf, count);
if (n != count) {
perror("read");
fail_file();
}
return n;
}
static size_t
uwrite(int const fd, void const *const buf, size_t const count)
{
size_t cnt = count;
off_t idx = 0;
file_updated = 1;
if (file_ptr + count >= file_end) {
off_t aoffset = (file_ptr + count) - file_end;
if (aoffset > file_append_size) {
file_append = realloc(file_append, aoffset);
file_append_size = aoffset;
}
if (!file_append) {
perror("write");
fail_file();
}
if (file_ptr < file_end) {
cnt = file_end - file_ptr;
} else {
cnt = 0;
idx = aoffset - count;
}
}
if (cnt)
memcpy(file_ptr, buf, cnt);
if (cnt < count)
memcpy(file_append + idx, buf + cnt, count - cnt);
file_ptr += count;
return count;
}
static void *
umalloc(size_t size)
{
void *const addr = malloc(size);
if (addr == 0) {
fprintf(stderr, "malloc failed: %zu bytes\n", size);
fail_file();
}
return addr;
}
static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
static unsigned char *ideal_nop;
static char rel_type_nop;
static int (*make_nop)(void *map, size_t const offset);
static int make_nop_x86(void *map, size_t const offset)
{
uint32_t *ptr;
unsigned char *op;
/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
ptr = map + offset;
if (*ptr != 0)
return -1;
op = map + offset - 1;
if (*op != 0xe8)
return -1;
/* convert to nop */
ulseek(fd_map, offset - 1, SEEK_SET);
uwrite(fd_map, ideal_nop, 5);
return 0;
}
static unsigned char ideal_nop4_arm_le[4] = { 0x00, 0x00, 0xa0, 0xe1 }; /* mov r0, r0 */
static unsigned char ideal_nop4_arm_be[4] = { 0xe1, 0xa0, 0x00, 0x00 }; /* mov r0, r0 */
static unsigned char *ideal_nop4_arm;
static unsigned char bl_mcount_arm_le[4] = { 0xfe, 0xff, 0xff, 0xeb }; /* bl */
static unsigned char bl_mcount_arm_be[4] = { 0xeb, 0xff, 0xff, 0xfe }; /* bl */
static unsigned char *bl_mcount_arm;
static unsigned char push_arm_le[4] = { 0x04, 0xe0, 0x2d, 0xe5 }; /* push {lr} */
static unsigned char push_arm_be[4] = { 0xe5, 0x2d, 0xe0, 0x04 }; /* push {lr} */
static unsigned char *push_arm;
static unsigned char ideal_nop2_thumb_le[2] = { 0x00, 0xbf }; /* nop */
static unsigned char ideal_nop2_thumb_be[2] = { 0xbf, 0x00 }; /* nop */
static unsigned char *ideal_nop2_thumb;
static unsigned char push_bl_mcount_thumb_le[6] = { 0x00, 0xb5, 0xff, 0xf7, 0xfe, 0xff }; /* push {lr}, bl */
static unsigned char push_bl_mcount_thumb_be[6] = { 0xb5, 0x00, 0xf7, 0xff, 0xff, 0xfe }; /* push {lr}, bl */
static unsigned char *push_bl_mcount_thumb;
static int make_nop_arm(void *map, size_t const offset)
{
char *ptr;
int cnt = 1;
int nop_size;
size_t off = offset;
ptr = map + offset;
if (memcmp(ptr, bl_mcount_arm, 4) == 0) {
if (memcmp(ptr - 4, push_arm, 4) == 0) {
off -= 4;
cnt = 2;
}
ideal_nop = ideal_nop4_arm;
nop_size = 4;
} else if (memcmp(ptr - 2, push_bl_mcount_thumb, 6) == 0) {
cnt = 3;
nop_size = 2;
off -= 2;
ideal_nop = ideal_nop2_thumb;
} else
return -1;
/* Convert to nop */
ulseek(fd_map, off, SEEK_SET);
do {
uwrite(fd_map, ideal_nop, nop_size);
} while (--cnt > 0);
return 0;
}
static unsigned char ideal_nop4_arm64[4] = {0x1f, 0x20, 0x03, 0xd5};
static int make_nop_arm64(void *map, size_t const offset)
{
uint32_t *ptr;
ptr = map + offset;
/* bl <_mcount> is 0x94000000 before relocation */
if (*ptr != 0x94000000)
return -1;
/* Convert to nop */
ulseek(fd_map, offset, SEEK_SET);
uwrite(fd_map, ideal_nop, 4);
return 0;
}
/*
* Get the whole file as a programming convenience in order to avoid
* malloc+lseek+read+free of many pieces. If successful, then mmap
* avoids copying unused pieces; else just read the whole file.
* Open for both read and write; new info will be appended to the file.
* Use MAP_PRIVATE so that a few changes to the in-memory ElfXX_Ehdr
* do not propagate to the file until an explicit overwrite at the last.
* This preserves most aspects of consistency (all except .st_size)
* for simultaneous readers of the file while we are appending to it.
* However, multiple writers still are bad. We choose not to use
* locking because it is expensive and the use case of kernel build
* makes multiple writers unlikely.
*/
static void *mmap_file(char const *fname)
{
fd_map = open(fname, O_RDONLY);
if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
perror(fname);
fail_file();
}
if (!S_ISREG(sb.st_mode)) {
fprintf(stderr, "not a regular file: %s\n", fname);
fail_file();
}
file_map = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
fd_map, 0);
mmap_failed = 0;
if (file_map == MAP_FAILED) {
mmap_failed = 1;
file_map = umalloc(sb.st_size);
uread(fd_map, file_map, sb.st_size);
}
close(fd_map);
file_end = file_map + sb.st_size;
return file_map;
}
static void write_file(const char *fname)
{
char tmp_file[strlen(fname) + 4];
size_t n;
if (!file_updated)
return;
sprintf(tmp_file, "%s.rc", fname);
/*
* After reading the entire file into memory, delete it
* and write it back, to prevent weird side effects of modifying
* an object file in place.
*/
fd_map = open(tmp_file, O_WRONLY | O_TRUNC | O_CREAT, sb.st_mode);
if (fd_map < 0) {
perror(fname);
fail_file();
}
n = write(fd_map, file_map, sb.st_size);
if (n != sb.st_size) {
perror("write");
fail_file();
}
if (file_append_size) {
n = write(fd_map, file_append, file_append_size);
if (n != file_append_size) {
perror("write");
fail_file();
}
}
close(fd_map);
if (rename(tmp_file, fname) < 0) {
perror(fname);
fail_file();
}
}
/* w8rev, w8nat, ...: Handle endianness. */
static uint64_t w8rev(uint64_t const x)
{
return ((0xff & (x >> (0 * 8))) << (7 * 8))
| ((0xff & (x >> (1 * 8))) << (6 * 8))
| ((0xff & (x >> (2 * 8))) << (5 * 8))
| ((0xff & (x >> (3 * 8))) << (4 * 8))
| ((0xff & (x >> (4 * 8))) << (3 * 8))
| ((0xff & (x >> (5 * 8))) << (2 * 8))
| ((0xff & (x >> (6 * 8))) << (1 * 8))
| ((0xff & (x >> (7 * 8))) << (0 * 8));
}
static uint32_t w4rev(uint32_t const x)
{
return ((0xff & (x >> (0 * 8))) << (3 * 8))
| ((0xff & (x >> (1 * 8))) << (2 * 8))
| ((0xff & (x >> (2 * 8))) << (1 * 8))
| ((0xff & (x >> (3 * 8))) << (0 * 8));
}
static uint32_t w2rev(uint16_t const x)
{
return ((0xff & (x >> (0 * 8))) << (1 * 8))
| ((0xff & (x >> (1 * 8))) << (0 * 8));
}
static uint64_t w8nat(uint64_t const x)
{
return x;
}
static uint32_t w4nat(uint32_t const x)
{
return x;
}
static uint32_t w2nat(uint16_t const x)
{
return x;
}
static uint64_t (*w8)(uint64_t);
static uint32_t (*w)(uint32_t);
static uint32_t (*w2)(uint16_t);
/* Names of the sections that could contain calls to mcount. */
static int
is_mcounted_section_name(char const *const txtname)
{
return strcmp(".text", txtname) == 0 ||
strcmp(".init.text", txtname) == 0 ||
strcmp(".ref.text", txtname) == 0 ||
strcmp(".sched.text", txtname) == 0 ||
strcmp(".spinlock.text", txtname) == 0 ||
strcmp(".irqentry.text", txtname) == 0 ||
strcmp(".softirqentry.text", txtname) == 0 ||
strcmp(".kprobes.text", txtname) == 0 ||
strcmp(".cpuidle.text", txtname) == 0 ||
strcmp(".text.unlikely", txtname) == 0;
}
/* 32 bit and 64 bit are very similar */
#include "recordmcount.h"
#define RECORD_MCOUNT_64
#include "recordmcount.h"
/* 64-bit EM_MIPS has weird ELF64_Rela.r_info.
* http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf
* We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40]
* to imply the order of the members; the spec does not say so.
* typedef unsigned char Elf64_Byte;
* fails on MIPS64 because their <elf.h> already has it!
*/
typedef uint8_t myElf64_Byte; /* Type for a 8-bit quantity. */
union mips_r_info {
Elf64_Xword r_info;
struct {
Elf64_Word r_sym; /* Symbol index. */
myElf64_Byte r_ssym; /* Special symbol. */
myElf64_Byte r_type3; /* Third relocation. */
myElf64_Byte r_type2; /* Second relocation. */
myElf64_Byte r_type; /* First relocation. */
} r_mips;
};
static uint64_t MIPS64_r_sym(Elf64_Rel const *rp)
{
return w(((union mips_r_info){ .r_info = rp->r_info }).r_mips.r_sym);
}
static void MIPS64_r_info(Elf64_Rel *const rp, unsigned sym, unsigned type)
{
rp->r_info = ((union mips_r_info){
.r_mips = { .r_sym = w(sym), .r_type = type }
}).r_info;
}
static void
do_file(char const *const fname)
{
Elf32_Ehdr *const ehdr = mmap_file(fname);
unsigned int reltype = 0;
w = w4nat;
w2 = w2nat;
w8 = w8nat;
switch (ehdr->e_ident[EI_DATA]) {
static unsigned int const endian = 1;
default:
fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
ehdr->e_ident[EI_DATA], fname);
fail_file();
break;
case ELFDATA2LSB:
if (*(unsigned char const *)&endian != 1) {
/* main() is big endian, file.o is little endian. */
w = w4rev;
w2 = w2rev;
w8 = w8rev;
}
ideal_nop4_arm = ideal_nop4_arm_le;
bl_mcount_arm = bl_mcount_arm_le;
push_arm = push_arm_le;
ideal_nop2_thumb = ideal_nop2_thumb_le;
push_bl_mcount_thumb = push_bl_mcount_thumb_le;
break;
case ELFDATA2MSB:
if (*(unsigned char const *)&endian != 0) {
/* main() is little endian, file.o is big endian. */
w = w4rev;
w2 = w2rev;
w8 = w8rev;
}
ideal_nop4_arm = ideal_nop4_arm_be;
bl_mcount_arm = bl_mcount_arm_be;
push_arm = push_arm_be;
ideal_nop2_thumb = ideal_nop2_thumb_be;
push_bl_mcount_thumb = push_bl_mcount_thumb_be;
break;
} /* end switch */
if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0
|| w2(ehdr->e_type) != ET_REL
|| ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
fail_file();
}
gpfx = 0;
switch (w2(ehdr->e_machine)) {
default:
fprintf(stderr, "unrecognized e_machine %d %s\n",
w2(ehdr->e_machine), fname);
fail_file();
break;
case EM_386:
reltype = R_386_32;
rel_type_nop = R_386_NONE;
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_32;
mcount_adjust_32 = -1;
break;
case EM_ARM: reltype = R_ARM_ABS32;
altmcount = "__gnu_mcount_nc";
make_nop = make_nop_arm;
rel_type_nop = R_ARM_NONE;
break;
case EM_AARCH64:
reltype = R_AARCH64_ABS64;
make_nop = make_nop_arm64;
rel_type_nop = R_AARCH64_NONE;
ideal_nop = ideal_nop4_arm64;
gpfx = '_';
break;
case EM_IA_64: reltype = R_IA64_IMM64; gpfx = '_'; break;
case EM_METAG: reltype = R_METAG_ADDR32;
altmcount = "_mcount_wrapper";
rel_type_nop = R_METAG_NONE;
/* We happen to have the same requirement as MIPS */
is_fake_mcount32 = MIPS32_is_fake_mcount;
break;
case EM_MIPS: /* reltype: e_class */ gpfx = '_'; break;
case EM_PPC: reltype = R_PPC_ADDR32; gpfx = '_'; break;
case EM_PPC64: reltype = R_PPC64_ADDR64; gpfx = '_'; break;
case EM_S390: /* reltype: e_class */ gpfx = '_'; break;
case EM_SH: reltype = R_SH_DIR32; break;
case EM_SPARCV9: reltype = R_SPARC_64; gpfx = '_'; break;
case EM_X86_64:
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_64;
reltype = R_X86_64_64;
rel_type_nop = R_X86_64_NONE;
mcount_adjust_64 = -1;
break;
} /* end switch */
switch (ehdr->e_ident[EI_CLASS]) {
default:
fprintf(stderr, "unrecognized ELF class %d %s\n",
ehdr->e_ident[EI_CLASS], fname);
fail_file();
break;
case ELFCLASS32:
if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
|| w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
fprintf(stderr,
"unrecognized ET_REL file: %s\n", fname);
fail_file();
}
if (w2(ehdr->e_machine) == EM_MIPS) {
reltype = R_MIPS_32;
is_fake_mcount32 = MIPS32_is_fake_mcount;
}
do32(ehdr, fname, reltype);
break;
case ELFCLASS64: {
Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr)
|| w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
fprintf(stderr,
"unrecognized ET_REL file: %s\n", fname);
fail_file();
}
if (w2(ghdr->e_machine) == EM_S390) {
reltype = R_390_64;
mcount_adjust_64 = -14;
}
if (w2(ghdr->e_machine) == EM_MIPS) {
reltype = R_MIPS_64;
Elf64_r_sym = MIPS64_r_sym;
Elf64_r_info = MIPS64_r_info;
is_fake_mcount64 = MIPS64_is_fake_mcount;
}
do64(ghdr, fname, reltype);
break;
}
} /* end switch */
write_file(fname);
cleanup();
}
int
main(int argc, char *argv[])
{
const char ftrace[] = "/ftrace.o";
int ftrace_size = sizeof(ftrace) - 1;
int n_error = 0; /* gcc-4.3.0 false positive complaint */
int c;
int i;
while ((c = getopt(argc, argv, "w")) >= 0) {
switch (c) {
case 'w':
warn_on_notrace_sect = 1;
break;
default:
fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
return 0;
}
}
if ((argc - optind) < 1) {
fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
return 0;
}
/* Process each file in turn, allowing deep failure. */
for (i = optind; i < argc; i++) {
char *file = argv[i];
int const sjval = setjmp(jmpenv);
int len;
/*
* The file kernel/trace/ftrace.o references the mcount
* function but does not call it. Since ftrace.o should
* not be traced anyway, we just skip it.
*/
len = strlen(file);
if (len >= ftrace_size &&
strcmp(file + (len - ftrace_size), ftrace) == 0)
continue;
switch (sjval) {
default:
fprintf(stderr, "internal error: %s\n", file);
exit(1);
break;
case SJ_SETJMP: /* normal sequence */
/* Avoid problems if early cleanup() */
fd_map = -1;
mmap_failed = 1;
file_map = NULL;
file_ptr = NULL;
file_updated = 0;
do_file(file);
break;
case SJ_FAIL: /* error in do_file or below */
fprintf(stderr, "%s: failed\n", file);
++n_error;
break;
case SJ_SUCCEED: /* premature success */
/* do nothing */
break;
} /* end switch */
}
return !!n_error;
}