summaryrefslogtreecommitdiff
path: root/tools/lib/bpf/libbpf.c
blob: ac69ae3bd628c9a1ca11585ffacab793c3d84c83 (plain)
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
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
/*
 * Common eBPF ELF object loading operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
 */

#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <libelf.h>
#include <gelf.h>

#include "libbpf.h"

#define __printf(a, b)	__attribute__((format(printf, a, b)))

__printf(1, 2)
static int __base_pr(const char *format, ...)
{
	va_list args;
	int err;

	va_start(args, format);
	err = vfprintf(stderr, format, args);
	va_end(args);
	return err;
}

static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_debug;

#define __pr(func, fmt, ...)	\
do {				\
	if ((func))		\
		(func)("libbpf: " fmt, ##__VA_ARGS__); \
} while (0)

#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)

void libbpf_set_print(libbpf_print_fn_t warn,
		      libbpf_print_fn_t info,
		      libbpf_print_fn_t debug)
{
	__pr_warning = warn;
	__pr_info = info;
	__pr_debug = debug;
}

/* Copied from tools/perf/util/util.h */
#ifndef zfree
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
#endif

#ifndef zclose
# define zclose(fd) ({			\
	int ___err = 0;			\
	if ((fd) >= 0)			\
		___err = close((fd));	\
	fd = -1;			\
	___err; })
#endif

#ifdef HAVE_LIBELF_MMAP_SUPPORT
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
#endif

/*
 * bpf_prog should be a better name but it has been used in
 * linux/filter.h.
 */
struct bpf_program {
	/* Index in elf obj file, for relocation use. */
	int idx;
	char *section_name;
	struct bpf_insn *insns;
	size_t insns_cnt;

	struct {
		int insn_idx;
		int map_idx;
	} *reloc_desc;
	int nr_reloc;
};

struct bpf_object {
	char license[64];
	u32 kern_version;
	void *maps_buf;
	size_t maps_buf_sz;

	struct bpf_program *programs;
	size_t nr_programs;

	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
		void *obj_buf;
		size_t obj_buf_sz;
		Elf *elf;
		GElf_Ehdr ehdr;
		Elf_Data *symbols;
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
	} efile;
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

	zfree(&prog->section_name);
	zfree(&prog->insns);
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
	prog->insns_cnt = 0;
	prog->idx = -1;
}

static int
bpf_program__init(void *data, size_t size, char *name, int idx,
		    struct bpf_program *prog)
{
	if (size < sizeof(struct bpf_insn)) {
		pr_warning("corrupted section '%s'\n", name);
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

	prog->section_name = strdup(name);
	if (!prog->section_name) {
		pr_warning("failed to alloc name for prog %s\n",
			   name);
		goto errout;
	}

	prog->insns = malloc(size);
	if (!prog->insns) {
		pr_warning("failed to alloc insns for %s\n", name);
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;

	return 0;
errout:
	bpf_program__exit(prog);
	return -ENOMEM;
}

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
			char *name, int idx)
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

	err = bpf_program__init(data, size, name, idx, &prog);
	if (err)
		return err;

	progs = obj->programs;
	nr_progs = obj->nr_programs;

	progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
		pr_warning("failed to alloc a new program '%s'\n",
			   name);
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
	progs[nr_progs] = prog;
	return 0;
}

static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
{
	struct bpf_object *obj;

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
		return NULL;
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;

	/*
	 * Caller of this function should also calls
	 * bpf_object__elf_finish() after data collection to return
	 * obj_buf to user. If not, we should duplicate the buffer to
	 * avoid user freeing them before elf finish.
	 */
	obj->efile.obj_buf = obj_buf;
	obj->efile.obj_buf_sz = obj_buf_sz;

	return obj;
}

static void bpf_object__elf_finish(struct bpf_object *obj)
{
	if (!obj_elf_valid(obj))
		return;

	if (obj->efile.elf) {
		elf_end(obj->efile.elf);
		obj->efile.elf = NULL;
	}
	obj->efile.symbols = NULL;

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
	zclose(obj->efile.fd);
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
}

static int bpf_object__elf_init(struct bpf_object *obj)
{
	int err = 0;
	GElf_Ehdr *ep;

	if (obj_elf_valid(obj)) {
		pr_warning("elf init: internal error\n");
		return -EEXIST;
	}

	if (obj->efile.obj_buf_sz > 0) {
		/*
		 * obj_buf should have been validated by
		 * bpf_object__open_buffer().
		 */
		obj->efile.elf = elf_memory(obj->efile.obj_buf,
					    obj->efile.obj_buf_sz);
	} else {
		obj->efile.fd = open(obj->path, O_RDONLY);
		if (obj->efile.fd < 0) {
			pr_warning("failed to open %s: %s\n", obj->path,
					strerror(errno));
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
		err = -EINVAL;
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
		err = -EINVAL;
		goto errout;
	}
	ep = &obj->efile.ehdr;

	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
		err = -EINVAL;
		goto errout;
	}

	return 0;
errout:
	bpf_object__elf_finish(obj);
	return err;
}

static int
bpf_object__check_endianness(struct bpf_object *obj)
{
	static unsigned int const endian = 1;

	switch (obj->efile.ehdr.e_ident[EI_DATA]) {
	case ELFDATA2LSB:
		/* We are big endian, BPF obj is little endian. */
		if (*(unsigned char const *)&endian != 1)
			goto mismatch;
		break;

	case ELFDATA2MSB:
		/* We are little endian, BPF obj is big endian. */
		if (*(unsigned char const *)&endian != 0)
			goto mismatch;
		break;
	default:
		return -EINVAL;
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
	return -EINVAL;
}

static int
bpf_object__init_license(struct bpf_object *obj,
			 void *data, size_t size)
{
	memcpy(obj->license, data,
	       min(size, sizeof(obj->license) - 1));
	pr_debug("license of %s is %s\n", obj->path, obj->license);
	return 0;
}

static int
bpf_object__init_kversion(struct bpf_object *obj,
			  void *data, size_t size)
{
	u32 kver;

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
		return -EINVAL;
	}
	memcpy(&kver, data, sizeof(kver));
	obj->kern_version = kver;
	pr_debug("kernel version of %s is %x\n", obj->path,
		 obj->kern_version);
	return 0;
}

static int
bpf_object__init_maps(struct bpf_object *obj, void *data,
		      size_t size)
{
	if (size == 0) {
		pr_debug("%s doesn't need map definition\n",
			 obj->path);
		return 0;
	}

	obj->maps_buf = malloc(size);
	if (!obj->maps_buf) {
		pr_warning("malloc maps failed: %s\n", obj->path);
		return -ENOMEM;
	}

	obj->maps_buf_sz = size;
	memcpy(obj->maps_buf, data, size);
	pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
	return 0;
}

static int bpf_object__elf_collect(struct bpf_object *obj)
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
	int idx = 0, err = 0;

	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
		pr_warning("failed to get e_shstrndx from %s\n",
			   obj->path);
		return -EINVAL;
	}

	while ((scn = elf_nextscn(elf, scn)) != NULL) {
		char *name;
		GElf_Shdr sh;
		Elf_Data *data;

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
			pr_warning("failed to get section header from %s\n",
				   obj->path);
			err = -EINVAL;
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
			pr_warning("failed to get section name from %s\n",
				   obj->path);
			err = -EINVAL;
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section data from %s(%s)\n",
				   name, obj->path);
			err = -EINVAL;
			goto out;
		}
		pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
			 name, (unsigned long)data->d_size,
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);

		if (strcmp(name, "license") == 0)
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
		else if (strcmp(name, "version") == 0)
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
		else if (strcmp(name, "maps") == 0)
			err = bpf_object__init_maps(obj, data->d_buf,
						    data->d_size);
		else if (sh.sh_type == SHT_SYMTAB) {
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
				err = -EEXIST;
			} else
				obj->efile.symbols = data;
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
				char errmsg[128];
				strerror_r(-err, errmsg, sizeof(errmsg));
				pr_warning("failed to alloc program %s (%s): %s",
					   name, obj->path, errmsg);
			}
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;

			reloc = realloc(reloc,
					sizeof(*obj->efile.reloc) * nr_reloc);
			if (!reloc) {
				pr_warning("realloc failed\n");
				err = -ENOMEM;
			} else {
				int n = nr_reloc - 1;

				obj->efile.reloc = reloc;
				obj->efile.nr_reloc = nr_reloc;

				obj->efile.reloc[n].shdr = sh;
				obj->efile.reloc[n].data = data;
			}
		}
		if (err)
			goto out;
	}
out:
	return err;
}

static struct bpf_program *
bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
{
	struct bpf_program *prog;
	size_t i;

	for (i = 0; i < obj->nr_programs; i++) {
		prog = &obj->programs[i];
		if (prog->idx == idx)
			return prog;
	}
	return NULL;
}

static int
bpf_program__collect_reloc(struct bpf_program *prog,
			   size_t nr_maps, GElf_Shdr *shdr,
			   Elf_Data *data, Elf_Data *symbols)
{
	int i, nrels;

	pr_debug("collecting relocating info for: '%s'\n",
		 prog->section_name);
	nrels = shdr->sh_size / shdr->sh_entsize;

	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
	if (!prog->reloc_desc) {
		pr_warning("failed to alloc memory in relocation\n");
		return -ENOMEM;
	}
	prog->nr_reloc = nrels;

	for (i = 0; i < nrels; i++) {
		GElf_Sym sym;
		GElf_Rel rel;
		unsigned int insn_idx;
		struct bpf_insn *insns = prog->insns;
		size_t map_idx;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
			return -EINVAL;
		}

		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
		pr_debug("relocation: insn_idx=%u\n", insn_idx);

		if (!gelf_getsym(symbols,
				 GELF_R_SYM(rel.r_info),
				 &sym)) {
			pr_warning("relocation: symbol %"PRIx64" not found\n",
				   GELF_R_SYM(rel.r_info));
			return -EINVAL;
		}

		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
				   insn_idx, insns[insn_idx].code);
			return -EINVAL;
		}

		map_idx = sym.st_value / sizeof(struct bpf_map_def);
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
			return -EINVAL;
		}

		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

static int bpf_object__collect_reloc(struct bpf_object *obj)
{
	int i, err;

	if (!obj_elf_valid(obj)) {
		pr_warning("Internal error: elf object is closed\n");
		return -EINVAL;
	}

	for (i = 0; i < obj->efile.nr_reloc; i++) {
		GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
		Elf_Data *data = obj->efile.reloc[i].data;
		int idx = shdr->sh_info;
		struct bpf_program *prog;
		size_t nr_maps = obj->maps_buf_sz /
				 sizeof(struct bpf_map_def);

		if (shdr->sh_type != SHT_REL) {
			pr_warning("internal error at %d\n", __LINE__);
			return -EINVAL;
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
			pr_warning("relocation failed: no %d section\n",
				   idx);
			return -ENOENT;
		}

		err = bpf_program__collect_reloc(prog, nr_maps,
						 shdr, data,
						 obj->efile.symbols);
		if (err)
			return -EINVAL;
	}
	return 0;
}

static int bpf_object__validate(struct bpf_object *obj)
{
	if (obj->kern_version == 0) {
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
		return -EINVAL;
	}
	return 0;
}

static struct bpf_object *
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
{
	struct bpf_object *obj;

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
		return NULL;
	}

	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
	if (!obj)
		return NULL;

	if (bpf_object__elf_init(obj))
		goto out;
	if (bpf_object__check_endianness(obj))
		goto out;
	if (bpf_object__elf_collect(obj))
		goto out;
	if (bpf_object__collect_reloc(obj))
		goto out;
	if (bpf_object__validate(obj))
		goto out;

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
	return NULL;
}

struct bpf_object *bpf_object__open(const char *path)
{
	/* param validation */
	if (!path)
		return NULL;

	pr_debug("loading %s\n", path);

	return __bpf_object__open(path, NULL, 0);
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
					   size_t obj_buf_sz)
{
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

	pr_debug("loading object from buffer\n");

	return __bpf_object__open("[buffer]", obj_buf, obj_buf_sz);
}

void bpf_object__close(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return;

	bpf_object__elf_finish(obj);

	zfree(&obj->maps_buf);

	if (obj->programs && obj->nr_programs) {
		for (i = 0; i < obj->nr_programs; i++)
			bpf_program__exit(&obj->programs[i]);
	}
	zfree(&obj->programs);

	free(obj);
}