kexec_file.c 33.3 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2
3
4
5
6
7
8
9
/*
 * kexec: kexec_file_load system call
 *
 * Copyright (C) 2014 Red Hat Inc.
 * Authors:
 *      Vivek Goyal <vgoyal@redhat.com>
 */

10
11
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

12
13
14
15
16
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/kexec.h>
17
#include <linux/memblock.h>
18
19
#include <linux/mutex.h>
#include <linux/list.h>
20
#include <linux/fs.h>
21
#include <linux/ima.h>
22
23
#include <crypto/hash.h>
#include <crypto/sha.h>
24
25
26
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/kernel.h>
27
28
29
30
31
32
#include <linux/syscalls.h>
#include <linux/vmalloc.h>
#include "kexec_internal.h"

static int kexec_calculate_store_digests(struct kimage *image);

33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
/*
 * Currently this is the only default function that is exported as some
 * architectures need it to do additional handlings.
 * In the future, other default functions may be exported too if required.
 */
int kexec_image_probe_default(struct kimage *image, void *buf,
			      unsigned long buf_len)
{
	const struct kexec_file_ops * const *fops;
	int ret = -ENOEXEC;

	for (fops = &kexec_file_loaders[0]; *fops && (*fops)->probe; ++fops) {
		ret = (*fops)->probe(buf, buf_len);
		if (!ret) {
			image->fops = *fops;
			return ret;
		}
	}

	return ret;
}

55
56
57
58
/* Architectures can provide this probe function */
int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
					 unsigned long buf_len)
{
59
60
61
62
63
64
65
66
67
68
69
70
	return kexec_image_probe_default(image, buf, buf_len);
}

static void *kexec_image_load_default(struct kimage *image)
{
	if (!image->fops || !image->fops->load)
		return ERR_PTR(-ENOEXEC);

	return image->fops->load(image, image->kernel_buf,
				 image->kernel_buf_len, image->initrd_buf,
				 image->initrd_buf_len, image->cmdline_buf,
				 image->cmdline_buf_len);
71
72
73
74
}

void * __weak arch_kexec_kernel_image_load(struct kimage *image)
{
75
76
77
	return kexec_image_load_default(image);
}

78
int kexec_image_post_load_cleanup_default(struct kimage *image)
79
80
81
82
83
{
	if (!image->fops || !image->fops->cleanup)
		return 0;

	return image->fops->cleanup(image->image_loader_data);
84
85
86
87
}

int __weak arch_kimage_file_post_load_cleanup(struct kimage *image)
{
88
	return kexec_image_post_load_cleanup_default(image);
89
90
}

91
#ifdef CONFIG_KEXEC_SIG
92
93
94
95
96
97
98
99
100
101
102
static int kexec_image_verify_sig_default(struct kimage *image, void *buf,
					  unsigned long buf_len)
{
	if (!image->fops || !image->fops->verify_sig) {
		pr_debug("kernel loader does not support signature verification.\n");
		return -EKEYREJECTED;
	}

	return image->fops->verify_sig(buf, buf_len);
}

103
104
105
int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
					unsigned long buf_len)
{
106
	return kexec_image_verify_sig_default(image, buf, buf_len);
107
}
108
#endif
109

110
111
112
113
114
115
116
117
118
/*
 * arch_kexec_apply_relocations_add - apply relocations of type RELA
 * @pi:		Purgatory to be relocated.
 * @section:	Section relocations applying to.
 * @relsec:	Section containing RELAs.
 * @symtab:	Corresponding symtab.
 *
 * Return: 0 on success, negative errno on error.
 */
119
int __weak
120
121
arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section,
				 const Elf_Shdr *relsec, const Elf_Shdr *symtab)
122
123
124
125
126
{
	pr_err("RELA relocation unsupported.\n");
	return -ENOEXEC;
}

127
128
129
130
131
132
133
134
135
/*
 * arch_kexec_apply_relocations - apply relocations of type REL
 * @pi:		Purgatory to be relocated.
 * @section:	Section relocations applying to.
 * @relsec:	Section containing RELs.
 * @symtab:	Corresponding symtab.
 *
 * Return: 0 on success, negative errno on error.
 */
136
int __weak
137
138
arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section,
			     const Elf_Shdr *relsec, const Elf_Shdr *symtab)
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
{
	pr_err("REL relocation unsupported.\n");
	return -ENOEXEC;
}

/*
 * Free up memory used by kernel, initrd, and command line. This is temporary
 * memory allocation which is not needed any more after these buffers have
 * been loaded into separate segments and have been copied elsewhere.
 */
void kimage_file_post_load_cleanup(struct kimage *image)
{
	struct purgatory_info *pi = &image->purgatory_info;

	vfree(image->kernel_buf);
	image->kernel_buf = NULL;

	vfree(image->initrd_buf);
	image->initrd_buf = NULL;

	kfree(image->cmdline_buf);
	image->cmdline_buf = NULL;

	vfree(pi->purgatory_buf);
	pi->purgatory_buf = NULL;

	vfree(pi->sechdrs);
	pi->sechdrs = NULL;

	/* See if architecture has anything to cleanup post load */
	arch_kimage_file_post_load_cleanup(image);

	/*
	 * Above call should have called into bootloader to free up
	 * any data stored in kimage->image_loader_data. It should
	 * be ok now to free it up.
	 */
	kfree(image->image_loader_data);
	image->image_loader_data = NULL;
}

180
181
182
183
184
185
186
187
#ifdef CONFIG_KEXEC_SIG
static int
kimage_validate_signature(struct kimage *image)
{
	int ret;

	ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
					   image->kernel_buf_len);
188
	if (ret) {
189
190

		if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
191
			pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
192
193
194
			return ret;
		}

195
196
		/*
		 * If IMA is guaranteed to appraise a signature on the kexec
197
198
199
200
201
202
203
		 * image, permit it even if the kernel is otherwise locked
		 * down.
		 */
		if (!ima_appraise_signature(READING_KEXEC_IMAGE) &&
		    security_locked_down(LOCKDOWN_KEXEC))
			return -EPERM;

204
		pr_debug("kernel signature verification failed (%d).\n", ret);
205
206
	}

207
	return 0;
208
209
210
}
#endif

211
212
213
214
215
216
217
218
219
/*
 * In file mode list of segments is prepared by kernel. Copy relevant
 * data from user space, do error checking, prepare segment list
 */
static int
kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
			     const char __user *cmdline_ptr,
			     unsigned long cmdline_len, unsigned flags)
{
220
	int ret;
221
	void *ldata;
222
	loff_t size;
223

224
225
	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
				       &size, INT_MAX, READING_KEXEC_IMAGE);
226
227
	if (ret)
		return ret;
228
	image->kernel_buf_len = size;
229
230
231
232
233
234
235

	/* Call arch image probe handlers */
	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
					    image->kernel_buf_len);
	if (ret)
		goto out;

236
237
238
239
#ifdef CONFIG_KEXEC_SIG
	ret = kimage_validate_signature(image);

	if (ret)
240
241
242
243
		goto out;
#endif
	/* It is possible that there no initramfs is being loaded */
	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
244
245
246
		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
					       &size, INT_MAX,
					       READING_KEXEC_INITRAMFS);
247
248
		if (ret)
			goto out;
249
		image->initrd_buf_len = size;
250
251
252
	}

	if (cmdline_len) {
253
254
255
256
		image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len);
		if (IS_ERR(image->cmdline_buf)) {
			ret = PTR_ERR(image->cmdline_buf);
			image->cmdline_buf = NULL;
257
258
259
260
261
262
263
264
265
266
			goto out;
		}

		image->cmdline_buf_len = cmdline_len;

		/* command line should be a string with last byte null */
		if (image->cmdline_buf[cmdline_len - 1] != '\0') {
			ret = -EINVAL;
			goto out;
		}
267

268
		ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
269
				  image->cmdline_buf_len - 1);
270
271
	}

272
273
274
	/* IMA needs to pass the measurement list to the next kernel. */
	ima_add_kexec_buffer(image);

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
	/* Call arch image load handlers */
	ldata = arch_kexec_kernel_image_load(image);

	if (IS_ERR(ldata)) {
		ret = PTR_ERR(ldata);
		goto out;
	}

	image->image_loader_data = ldata;
out:
	/* In case of error, free up all allocated memory in this function */
	if (ret)
		kimage_file_post_load_cleanup(image);
	return ret;
}

static int
kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
		       int initrd_fd, const char __user *cmdline_ptr,
		       unsigned long cmdline_len, unsigned long flags)
{
	int ret;
	struct kimage *image;
	bool kexec_on_panic = flags & KEXEC_FILE_ON_CRASH;

	image = do_kimage_alloc_init();
	if (!image)
		return -ENOMEM;

	image->file_mode = 1;

	if (kexec_on_panic) {
		/* Enable special crash kernel control page alloc policy. */
		image->control_page = crashk_res.start;
		image->type = KEXEC_TYPE_CRASH;
	}

	ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd,
					   cmdline_ptr, cmdline_len, flags);
	if (ret)
		goto out_free_image;

	ret = sanity_check_segment_list(image);
	if (ret)
		goto out_free_post_load_bufs;

	ret = -ENOMEM;
	image->control_code_page = kimage_alloc_control_pages(image,
					   get_order(KEXEC_CONTROL_PAGE_SIZE));
	if (!image->control_code_page) {
		pr_err("Could not allocate control_code_buffer\n");
		goto out_free_post_load_bufs;
	}

	if (!kexec_on_panic) {
		image->swap_page = kimage_alloc_control_pages(image, 0);
		if (!image->swap_page) {
			pr_err("Could not allocate swap buffer\n");
			goto out_free_control_pages;
		}
	}

	*rimage = image;
	return 0;
out_free_control_pages:
	kimage_free_page_list(&image->control_pages);
out_free_post_load_bufs:
	kimage_file_post_load_cleanup(image);
out_free_image:
	kfree(image);
	return ret;
}

SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
		unsigned long, cmdline_len, const char __user *, cmdline_ptr,
		unsigned long, flags)
{
	int ret = 0, i;
	struct kimage **dest_image, *image;

	/* We only trust the superuser with rebooting the system. */
	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
		return -EPERM;

	/* Make sure we have a legal set of flags */
	if (flags != (flags & KEXEC_FILE_FLAGS))
		return -EINVAL;

	image = NULL;

	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;

	dest_image = &kexec_image;
369
	if (flags & KEXEC_FILE_ON_CRASH) {
370
		dest_image = &kexec_crash_image;
371
372
373
		if (kexec_crash_image)
			arch_kexec_unprotect_crashkres();
	}
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394

	if (flags & KEXEC_FILE_UNLOAD)
		goto exchange;

	/*
	 * In case of crash, new kernel gets loaded in reserved region. It is
	 * same memory where old crash kernel might be loaded. Free any
	 * current crash dump kernel before we corrupt it.
	 */
	if (flags & KEXEC_FILE_ON_CRASH)
		kimage_free(xchg(&kexec_crash_image, NULL));

	ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr,
				     cmdline_len, flags);
	if (ret)
		goto out;

	ret = machine_kexec_prepare(image);
	if (ret)
		goto out;

395
396
397
398
399
400
401
402
	/*
	 * Some architecture(like S390) may touch the crash memory before
	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
	 */
	ret = kimage_crash_copy_vmcoreinfo(image);
	if (ret)
		goto out;

403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
	ret = kexec_calculate_store_digests(image);
	if (ret)
		goto out;

	for (i = 0; i < image->nr_segments; i++) {
		struct kexec_segment *ksegment;

		ksegment = &image->segment[i];
		pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
			 i, ksegment->buf, ksegment->bufsz, ksegment->mem,
			 ksegment->memsz);

		ret = kimage_load_segment(image, &image->segment[i]);
		if (ret)
			goto out;
	}

	kimage_terminate(image);

422
423
424
425
	ret = machine_kexec_post_load(image);
	if (ret)
		goto out;

426
427
428
429
430
431
432
433
	/*
	 * Free up any temporary buffers allocated which are not needed
	 * after image has been loaded
	 */
	kimage_file_post_load_cleanup(image);
exchange:
	image = xchg(dest_image, image);
out:
434
435
436
	if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
		arch_kexec_protect_crashkres();

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
	mutex_unlock(&kexec_mutex);
	kimage_free(image);
	return ret;
}

static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
				    struct kexec_buf *kbuf)
{
	struct kimage *image = kbuf->image;
	unsigned long temp_start, temp_end;

	temp_end = min(end, kbuf->buf_max);
	temp_start = temp_end - kbuf->memsz;

	do {
		/* align down start */
		temp_start = temp_start & (~(kbuf->buf_align - 1));

		if (temp_start < start || temp_start < kbuf->buf_min)
			return 0;

		temp_end = temp_start + kbuf->memsz - 1;

		/*
		 * Make sure this does not conflict with any of existing
		 * segments
		 */
		if (kimage_is_destination_range(image, temp_start, temp_end)) {
			temp_start = temp_start - PAGE_SIZE;
			continue;
		}

		/* We found a suitable memory range */
		break;
	} while (1);

	/* If we are here, we found a suitable memory range */
	kbuf->mem = temp_start;

	/* Success, stop navigating through remaining System RAM ranges */
	return 1;
}

static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
				     struct kexec_buf *kbuf)
{
	struct kimage *image = kbuf->image;
	unsigned long temp_start, temp_end;

	temp_start = max(start, kbuf->buf_min);

	do {
		temp_start = ALIGN(temp_start, kbuf->buf_align);
		temp_end = temp_start + kbuf->memsz - 1;

		if (temp_end > end || temp_end > kbuf->buf_max)
			return 0;
		/*
		 * Make sure this does not conflict with any of existing
		 * segments
		 */
		if (kimage_is_destination_range(image, temp_start, temp_end)) {
			temp_start = temp_start + PAGE_SIZE;
			continue;
		}

		/* We found a suitable memory range */
		break;
	} while (1);

	/* If we are here, we found a suitable memory range */
	kbuf->mem = temp_start;

	/* Success, stop navigating through remaining System RAM ranges */
	return 1;
}

514
static int locate_mem_hole_callback(struct resource *res, void *arg)
515
516
{
	struct kexec_buf *kbuf = (struct kexec_buf *)arg;
517
	u64 start = res->start, end = res->end;
518
519
520
	unsigned long sz = end - start + 1;

	/* Returning 0 will take to next memory range */
521
522
523
524
525

	/* Don't use memory that will be detected and handled by a driver. */
	if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
		return 0;

526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
	if (sz < kbuf->memsz)
		return 0;

	if (end < kbuf->buf_min || start > kbuf->buf_max)
		return 0;

	/*
	 * Allocate memory top down with-in ram range. Otherwise bottom up
	 * allocation.
	 */
	if (kbuf->top_down)
		return locate_mem_hole_top_down(start, end, kbuf);
	return locate_mem_hole_bottom_up(start, end, kbuf);
}

541
#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
542
543
544
545
546
547
548
549
static int kexec_walk_memblock(struct kexec_buf *kbuf,
			       int (*func)(struct resource *, void *))
{
	int ret = 0;
	u64 i;
	phys_addr_t mstart, mend;
	struct resource res = { };

550
551
552
	if (kbuf->image->type == KEXEC_TYPE_CRASH)
		return func(&crashk_res, kbuf);

553
	if (kbuf->top_down) {
554
		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
555
556
557
558
559
560
561
562
563
564
565
566
567
						&mstart, &mend, NULL) {
			/*
			 * In memblock, end points to the first byte after the
			 * range while in kexec, end points to the last byte
			 * in the range.
			 */
			res.start = mstart;
			res.end = mend - 1;
			ret = func(&res, kbuf);
			if (ret)
				break;
		}
	} else {
568
569
		for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
					&mstart, &mend, NULL) {
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
			/*
			 * In memblock, end points to the first byte after the
			 * range while in kexec, end points to the last byte
			 * in the range.
			 */
			res.start = mstart;
			res.end = mend - 1;
			ret = func(&res, kbuf);
			if (ret)
				break;
		}
	}

	return ret;
}
585
586
587
588
589
590
#else
static int kexec_walk_memblock(struct kexec_buf *kbuf,
			       int (*func)(struct resource *, void *))
{
	return 0;
}
591
592
#endif

593
/**
594
 * kexec_walk_resources - call func(data) on free memory regions
595
596
597
598
599
600
601
 * @kbuf:	Context info for the search. Also passed to @func.
 * @func:	Function to call for each memory region.
 *
 * Return: The memory walk will stop when func returns a non-zero value
 * and that value will be returned. If all free regions are visited without
 * func returning non-zero, then zero will be returned.
 */
602
603
static int kexec_walk_resources(struct kexec_buf *kbuf,
				int (*func)(struct resource *, void *))
604
605
606
607
608
609
610
611
612
613
{
	if (kbuf->image->type == KEXEC_TYPE_CRASH)
		return walk_iomem_res_desc(crashk_res.desc,
					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
					   crashk_res.start, crashk_res.end,
					   kbuf, func);
	else
		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
}

614
615
616
617
618
619
620
621
622
623
624
625
/**
 * kexec_locate_mem_hole - find free memory for the purgatory or the next kernel
 * @kbuf:	Parameters for the memory search.
 *
 * On success, kbuf->mem will have the start address of the memory region found.
 *
 * Return: 0 on success, negative errno on error.
 */
int kexec_locate_mem_hole(struct kexec_buf *kbuf)
{
	int ret;

626
627
628
629
	/* Arch knows where to place */
	if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
		return 0;

630
	if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
631
632
633
		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
	else
		ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
634
635
636
637

	return ret == 1 ? 0 : -EADDRNOTAVAIL;
}

638
639
640
641
642
643
644
645
646
647
648
649
650
/**
 * arch_kexec_locate_mem_hole - Find free memory to place the segments.
 * @kbuf:                       Parameters for the memory search.
 *
 * On success, kbuf->mem will have the start address of the memory region found.
 *
 * Return: 0 on success, negative errno on error.
 */
int __weak arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
{
	return kexec_locate_mem_hole(kbuf);
}

651
652
653
654
655
656
657
658
659
/**
 * kexec_add_buffer - place a buffer in a kexec segment
 * @kbuf:	Buffer contents and memory parameters.
 *
 * This function assumes that kexec_mutex is held.
 * On successful return, @kbuf->mem will have the physical address of
 * the buffer in memory.
 *
 * Return: 0 on success, negative errno on error.
660
 */
661
int kexec_add_buffer(struct kexec_buf *kbuf)
662
663
664
665
666
{
	struct kexec_segment *ksegment;
	int ret;

	/* Currently adding segment this way is allowed only in file mode */
667
	if (!kbuf->image->file_mode)
668
669
		return -EINVAL;

670
	if (kbuf->image->nr_segments >= KEXEC_SEGMENT_MAX)
671
672
673
674
675
676
677
678
679
		return -EINVAL;

	/*
	 * Make sure we are not trying to add buffer after allocating
	 * control pages. All segments need to be placed first before
	 * any control pages are allocated. As control page allocation
	 * logic goes through list of segments to make sure there are
	 * no destination overlaps.
	 */
680
	if (!list_empty(&kbuf->image->control_pages)) {
681
682
683
684
		WARN_ON(1);
		return -EINVAL;
	}

685
686
687
	/* Ensure minimum alignment needed for segments. */
	kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
688
689

	/* Walk the RAM ranges and allocate a suitable range for the buffer */
690
	ret = arch_kexec_locate_mem_hole(kbuf);
691
692
	if (ret)
		return ret;
693
694

	/* Found a suitable memory range */
695
	ksegment = &kbuf->image->segment[kbuf->image->nr_segments];
696
697
698
699
	ksegment->kbuf = kbuf->buffer;
	ksegment->bufsz = kbuf->bufsz;
	ksegment->mem = kbuf->mem;
	ksegment->memsz = kbuf->memsz;
700
	kbuf->image->nr_segments++;
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
	return 0;
}

/* Calculate and store the digest of segments */
static int kexec_calculate_store_digests(struct kimage *image)
{
	struct crypto_shash *tfm;
	struct shash_desc *desc;
	int ret = 0, i, j, zero_buf_sz, sha_region_sz;
	size_t desc_size, nullsz;
	char *digest;
	void *zero_buf;
	struct kexec_sha_region *sha_regions;
	struct purgatory_info *pi = &image->purgatory_info;

716
717
718
	if (!IS_ENABLED(CONFIG_ARCH_HAS_KEXEC_PURGATORY))
		return 0;

719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
	zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT);
	zero_buf_sz = PAGE_SIZE;

	tfm = crypto_alloc_shash("sha256", 0, 0);
	if (IS_ERR(tfm)) {
		ret = PTR_ERR(tfm);
		goto out;
	}

	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
	desc = kzalloc(desc_size, GFP_KERNEL);
	if (!desc) {
		ret = -ENOMEM;
		goto out_free_tfm;
	}

	sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region);
	sha_regions = vzalloc(sha_region_sz);
	if (!sha_regions)
		goto out_free_desc;

	desc->tfm   = tfm;

	ret = crypto_shash_init(desc);
	if (ret < 0)
		goto out_free_sha_regions;

	digest = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
	if (!digest) {
		ret = -ENOMEM;
		goto out_free_sha_regions;
	}

	for (j = i = 0; i < image->nr_segments; i++) {
		struct kexec_segment *ksegment;

		ksegment = &image->segment[i];
		/*
		 * Skip purgatory as it will be modified once we put digest
		 * info in purgatory.
		 */
		if (ksegment->kbuf == pi->purgatory_buf)
			continue;

		ret = crypto_shash_update(desc, ksegment->kbuf,
					  ksegment->bufsz);
		if (ret)
			break;

		/*
		 * Assume rest of the buffer is filled with zero and
		 * update digest accordingly.
		 */
		nullsz = ksegment->memsz - ksegment->bufsz;
		while (nullsz) {
			unsigned long bytes = nullsz;

			if (bytes > zero_buf_sz)
				bytes = zero_buf_sz;
			ret = crypto_shash_update(desc, zero_buf, bytes);
			if (ret)
				break;
			nullsz -= bytes;
		}

		if (ret)
			break;

		sha_regions[j].start = ksegment->mem;
		sha_regions[j].len = ksegment->memsz;
		j++;
	}

	if (!ret) {
		ret = crypto_shash_final(desc, digest);
		if (ret)
			goto out_free_digest;
796
797
		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
						     sha_regions, sha_region_sz, 0);
798
799
800
		if (ret)
			goto out_free_digest;

801
802
		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
						     digest, SHA256_DIGEST_SIZE, 0);
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
		if (ret)
			goto out_free_digest;
	}

out_free_digest:
	kfree(digest);
out_free_sha_regions:
	vfree(sha_regions);
out_free_desc:
	kfree(desc);
out_free_tfm:
	kfree(tfm);
out:
	return ret;
}

819
#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY
820
821
822
823
824
825
826
827
828
829
830
831
/*
 * kexec_purgatory_setup_kbuf - prepare buffer to load purgatory.
 * @pi:		Purgatory to be loaded.
 * @kbuf:	Buffer to setup.
 *
 * Allocates the memory needed for the buffer. Caller is responsible to free
 * the memory after use.
 *
 * Return: 0 on success, negative errno on error.
 */
static int kexec_purgatory_setup_kbuf(struct purgatory_info *pi,
				      struct kexec_buf *kbuf)
832
{
833
834
835
836
837
	const Elf_Shdr *sechdrs;
	unsigned long bss_align;
	unsigned long bss_sz;
	unsigned long align;
	int i, ret;
838

839
	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
840
841
	kbuf->buf_align = bss_align = 1;
	kbuf->bufsz = bss_sz = 0;
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897

	for (i = 0; i < pi->ehdr->e_shnum; i++) {
		if (!(sechdrs[i].sh_flags & SHF_ALLOC))
			continue;

		align = sechdrs[i].sh_addralign;
		if (sechdrs[i].sh_type != SHT_NOBITS) {
			if (kbuf->buf_align < align)
				kbuf->buf_align = align;
			kbuf->bufsz = ALIGN(kbuf->bufsz, align);
			kbuf->bufsz += sechdrs[i].sh_size;
		} else {
			if (bss_align < align)
				bss_align = align;
			bss_sz = ALIGN(bss_sz, align);
			bss_sz += sechdrs[i].sh_size;
		}
	}
	kbuf->bufsz = ALIGN(kbuf->bufsz, bss_align);
	kbuf->memsz = kbuf->bufsz + bss_sz;
	if (kbuf->buf_align < bss_align)
		kbuf->buf_align = bss_align;

	kbuf->buffer = vzalloc(kbuf->bufsz);
	if (!kbuf->buffer)
		return -ENOMEM;
	pi->purgatory_buf = kbuf->buffer;

	ret = kexec_add_buffer(kbuf);
	if (ret)
		goto out;

	return 0;
out:
	vfree(pi->purgatory_buf);
	pi->purgatory_buf = NULL;
	return ret;
}

/*
 * kexec_purgatory_setup_sechdrs - prepares the pi->sechdrs buffer.
 * @pi:		Purgatory to be loaded.
 * @kbuf:	Buffer prepared to store purgatory.
 *
 * Allocates the memory needed for the buffer. Caller is responsible to free
 * the memory after use.
 *
 * Return: 0 on success, negative errno on error.
 */
static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
					 struct kexec_buf *kbuf)
{
	unsigned long bss_addr;
	unsigned long offset;
	Elf_Shdr *sechdrs;
	int i;
898

899
900
901
902
	/*
	 * The section headers in kexec_purgatory are read-only. In order to
	 * have them modifiable make a temporary copy.
	 */
903
	sechdrs = vzalloc(array_size(sizeof(Elf_Shdr), pi->ehdr->e_shnum));
904
905
	if (!sechdrs)
		return -ENOMEM;
906
907
908
	memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff,
	       pi->ehdr->e_shnum * sizeof(Elf_Shdr));
	pi->sechdrs = sechdrs;
909

910
911
	offset = 0;
	bss_addr = kbuf->mem + kbuf->bufsz;
912
	kbuf->image->start = pi->ehdr->e_entry;
913
914

	for (i = 0; i < pi->ehdr->e_shnum; i++) {
915
		unsigned long align;
916
		void *src, *dst;
917

918
919
920
921
		if (!(sechdrs[i].sh_flags & SHF_ALLOC))
			continue;

		align = sechdrs[i].sh_addralign;
922
		if (sechdrs[i].sh_type == SHT_NOBITS) {
923
924
925
			bss_addr = ALIGN(bss_addr, align);
			sechdrs[i].sh_addr = bss_addr;
			bss_addr += sechdrs[i].sh_size;
926
927
928
			continue;
		}

929
		offset = ALIGN(offset, align);
930
931
932
933
934
		if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
		    pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
		    pi->ehdr->e_entry < (sechdrs[i].sh_addr
					 + sechdrs[i].sh_size)) {
			kbuf->image->start -= sechdrs[i].sh_addr;
935
			kbuf->image->start += kbuf->mem + offset;
936
937
		}

938
		src = (void *)pi->ehdr + sechdrs[i].sh_offset;
939
940
941
942
		dst = pi->purgatory_buf + offset;
		memcpy(dst, src, sechdrs[i].sh_size);

		sechdrs[i].sh_addr = kbuf->mem + offset;
943
		sechdrs[i].sh_offset = offset;
944
		offset += sechdrs[i].sh_size;
945
	}
946

947
	return 0;
948
949
950
951
952
953
}

static int kexec_apply_relocations(struct kimage *image)
{
	int i, ret;
	struct purgatory_info *pi = &image->purgatory_info;
954
955
956
	const Elf_Shdr *sechdrs;

	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
957
958

	for (i = 0; i < pi->ehdr->e_shnum; i++) {
959
960
961
962
963
		const Elf_Shdr *relsec;
		const Elf_Shdr *symtab;
		Elf_Shdr *section;

		relsec = sechdrs + i;
964

965
966
		if (relsec->sh_type != SHT_RELA &&
		    relsec->sh_type != SHT_REL)
967
968
969
970
971
972
973
974
			continue;

		/*
		 * For section of type SHT_RELA/SHT_REL,
		 * ->sh_link contains section header index of associated
		 * symbol table. And ->sh_info contains section header
		 * index of section to which relocations apply.
		 */
975
976
		if (relsec->sh_info >= pi->ehdr->e_shnum ||
		    relsec->sh_link >= pi->ehdr->e_shnum)
977
978
			return -ENOEXEC;

979
980
		section = pi->sechdrs + relsec->sh_info;
		symtab = sechdrs + relsec->sh_link;
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996

		if (!(section->sh_flags & SHF_ALLOC))
			continue;

		/*
		 * symtab->sh_link contain section header index of associated
		 * string table.
		 */
		if (symtab->sh_link >= pi->ehdr->e_shnum)
			/* Invalid section number? */
			continue;

		/*
		 * Respective architecture needs to provide support for applying
		 * relocations of type SHT_RELA/SHT_REL.
		 */
997
998
999
1000
1001
1002
		if (relsec->sh_type == SHT_RELA)
			ret = arch_kexec_apply_relocations_add(pi, section,
							       relsec, symtab);
		else if (relsec->sh_type == SHT_REL)
			ret = arch_kexec_apply_relocations(pi, section,
							   relsec, symtab);
1003
1004
1005
1006
1007
1008
1009
		if (ret)
			return ret;
	}

	return 0;
}

1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
/*
 * kexec_load_purgatory - Load and relocate the purgatory object.
 * @image:	Image to add the purgatory to.
 * @kbuf:	Memory parameters to use.
 *
 * Allocates the memory needed for image->purgatory_info.sechdrs and
 * image->purgatory_info.purgatory_buf/kbuf->buffer. Caller is responsible
 * to free the memory after use.
 *
 * Return: 0 on success, negative errno on error.
 */
int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf)
1022
1023
1024
1025
1026
1027
1028
{
	struct purgatory_info *pi = &image->purgatory_info;
	int ret;

	if (kexec_purgatory_size <= 0)
		return -EINVAL;

1029
	pi->ehdr = (const Elf_Ehdr *)kexec_purgatory;
1030

1031
	ret = kexec_purgatory_setup_kbuf(pi, kbuf);
1032
1033
1034
	if (ret)
		return ret;

1035
	ret = kexec_purgatory_setup_sechdrs(pi, kbuf);
1036
1037
1038
	if (ret)
		goto out_free_kbuf;

1039
1040
1041
1042
1043
1044
1045
	ret = kexec_apply_relocations(image);
	if (ret)
		goto out;

	return 0;
out:
	vfree(pi->sechdrs);
1046
	pi->sechdrs = NULL;
1047
out_free_kbuf:
1048
	vfree(pi->purgatory_buf);
1049
	pi->purgatory_buf = NULL;
1050
1051
1052
	return ret;
}

1053
1054
1055
1056
1057
1058
1059
1060
1061
/*
 * kexec_purgatory_find_symbol - find a symbol in the purgatory
 * @pi:		Purgatory to search in.
 * @name:	Name of the symbol.
 *
 * Return: pointer to symbol in read-only symtab on success, NULL on error.
 */
static const Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi,
						  const char *name)
1062
{
1063
	const Elf_Shdr *sechdrs;
1064
	const Elf_Ehdr *ehdr;
1065
	const Elf_Sym *syms;
1066
	const char *strtab;
1067
	int i, k;
1068

1069
	if (!pi->ehdr)
1070
1071
1072
		return NULL;

	ehdr = pi->ehdr;
1073
	sechdrs = (void *)ehdr + ehdr->e_shoff;
1074
1075
1076
1077
1078
1079
1080
1081

	for (i = 0; i < ehdr->e_shnum; i++) {
		if (sechdrs[i].sh_type != SHT_SYMTAB)
			continue;

		if (sechdrs[i].sh_link >= ehdr->e_shnum)
			/* Invalid strtab section number */
			continue;
1082
1083
		strtab = (void *)ehdr + sechdrs[sechdrs[i].sh_link].sh_offset;
		syms = (void *)ehdr + sechdrs[i].sh_offset;
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110

		/* Go through symbols for a match */
		for (k = 0; k < sechdrs[i].sh_size/sizeof(Elf_Sym); k++) {
			if (ELF_ST_BIND(syms[k].st_info) != STB_GLOBAL)
				continue;

			if (strcmp(strtab + syms[k].st_name, name) != 0)
				continue;

			if (syms[k].st_shndx == SHN_UNDEF ||
			    syms[k].st_shndx >= ehdr->e_shnum) {
				pr_debug("Symbol: %s has bad section index %d.\n",
						name, syms[k].st_shndx);
				return NULL;
			}

			/* Found the symbol we are looking for */
			return &syms[k];
		}
	}

	return NULL;
}

void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name)
{
	struct purgatory_info *pi = &image->purgatory_info;
1111
	const Elf_Sym *sym;
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
	Elf_Shdr *sechdr;

	sym = kexec_purgatory_find_symbol(pi, name);
	if (!sym)
		return ERR_PTR(-EINVAL);

	sechdr = &pi->sechdrs[sym->st_shndx];

	/*
	 * Returns the address where symbol will finally be loaded after
	 * kexec_load_segment()
	 */
	return (void *)(sechdr->sh_addr + sym->st_value);
}

/*
 * Get or set value of a symbol. If "get_value" is true, symbol value is
 * returned in buf otherwise symbol value is set based on value in buf.
 */
int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
				   void *buf, unsigned int size, bool get_value)
{
	struct purgatory_info *pi = &image->purgatory_info;
1135
1136
	const Elf_Sym *sym;
	Elf_Shdr *sec;
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
	char *sym_buf;

	sym = kexec_purgatory_find_symbol(pi, name);
	if (!sym)
		return -EINVAL;

	if (sym->st_size != size) {
		pr_err("symbol %s size mismatch: expected %lu actual %u\n",
		       name, (unsigned long)sym->st_size, size);
		return -EINVAL;
	}

1149
	sec = pi->sechdrs + sym->st_shndx;
1150

1151
	if (sec->sh_type == SHT_NOBITS) {
1152
1153
1154
1155
1156
		pr_err("symbol %s is in a bss section. Cannot %s\n", name,
		       get_value ? "get" : "set");
		return -EINVAL;
	}

1157
	sym_buf = (char *)pi->purgatory_buf + sec->sh_offset + sym->st_value;
1158
1159
1160
1161
1162
1163
1164
1165

	if (get_value)
		memcpy((void *)buf, sym_buf, size);
	else
		memcpy((void *)sym_buf, buf, size);

	return 0;
}
1166
#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */
1167
1168
1169
1170
1171

int crash_exclude_mem_range(struct crash_mem *mem,
			    unsigned long long mstart, unsigned long long mend)
{
	int i, j;
1172
	unsigned long long start, end, p_start, p_end;
1173
1174
1175
1176
1177
	struct crash_mem_range temp_range = {0, 0};

	for (i = 0; i < mem->nr_ranges; i++) {
		start = mem->ranges[i].start;
		end = mem->ranges[i].end;
1178
1179
		p_start = mstart;
		p_end = mend;
1180
1181
1182
1183
1184
1185

		if (mstart > end || mend < start)
			continue;

		/* Truncate any area outside of range */
		if (mstart < start)
1186
			p_start = start;
1187
		if (mend > end)
1188
			p_end = end;
1189
1190

		/* Found completely overlapping range */
1191
		if (p_start == start && p_end == end) {
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
			mem->ranges[i].start = 0;
			mem->ranges[i].end = 0;
			if (i < mem->nr_ranges - 1) {
				/* Shift rest of the ranges to left */
				for (j = i; j < mem->nr_ranges - 1; j++) {
					mem->ranges[j].start =
						mem->ranges[j+1].start;
					mem->ranges[j].end =
							mem->ranges[j+1].end;
				}
1202
1203
1204
1205
1206
1207
1208
1209
1210

				/*
				 * Continue to check if there are another overlapping ranges
				 * from the current position because of shifting the above
				 * mem ranges.
				 */
				i--;
				mem->nr_ranges--;
				continue;
1211
1212
1213
1214
1215
			}
			mem->nr_ranges--;
			return 0;
		}

1216
		if (p_start > start && p_end < end) {
1217
			/* Split original range */
1218
1219
			mem->ranges[i].end = p_start - 1;
			temp_range.start = p_end + 1;
1220
			temp_range.end = end;
1221
1222
		} else if (p_start != start)
			mem->ranges[i].end = p_start - 1;
1223
		else
1224
			mem->ranges[i].start = p_end + 1;
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
		break;
	}

	/* If a split happened, add the split to array */
	if (!temp_range.end)
		return 0;

	/* Split happened */
	if (i == mem->max_nr_ranges - 1)
		return -ENOMEM;

	/* Location where new range should go */
	j = i + 1;
	if (j < mem->nr_ranges) {
		/* Move over all ranges one slot towards the end */
		for (i = mem->nr_ranges - 1; i >= j; i--)
			mem->ranges[i + 1] = mem->ranges[i];
	}

	mem->ranges[j].start = temp_range.start;
	mem->ranges[j].end = temp_range.end;
	mem->nr_ranges++;
	return 0;
}

int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
			  void **addr, unsigned long *sz)
{
	Elf64_Ehdr *ehdr;
	Elf64_Phdr *phdr;
	unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
	unsigned char *buf;
	unsigned int cpu, i;
	unsigned long long notes_addr;
	unsigned long mstart, mend;

1261
	/* extra phdr for vmcoreinfo ELF note */
1262
1263
1264
1265
1266
1267
1268
	nr_phdr = nr_cpus + 1;
	nr_phdr += mem->nr_ranges;

	/*
	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
	 * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
	 * I think this is required by tools like gdb. So same physical
1269
	 * memory will be mapped in two ELF headers. One will contain kernel
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
	 * text virtual addresses and other will have __va(physical) addresses.
	 */

	nr_phdr++;
	elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
	elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);

	buf = vzalloc(elf_sz);
	if (!buf)
		return -ENOMEM;

	ehdr = (Elf64_Ehdr *)buf;
	phdr = (Elf64_Phdr *)(ehdr + 1);
	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
	ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
	ehdr->e_ident[EI_OSABI] = ELF_OSABI;
	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
	ehdr->e_type = ET_CORE;
	ehdr->e_machine = ELF_ARCH;
	ehdr->e_version = EV_CURRENT;
	ehdr->e_phoff = sizeof(Elf64_Ehdr);
	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
	ehdr->e_phentsize = sizeof(Elf64_Phdr);

1296
	/* Prepare one phdr of type PT_NOTE for each present CPU */
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
	for_each_present_cpu(cpu) {
		phdr->p_type = PT_NOTE;
		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
		phdr->p_offset = phdr->p_paddr = notes_addr;
		phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
		(ehdr->e_phnum)++;
		phdr++;
	}

	/* Prepare one PT_NOTE header for vmcoreinfo */
	phdr->p_type = PT_NOTE;
	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
	(ehdr->e_phnum)++;
	phdr++;

	/* Prepare PT_LOAD type program header for kernel text region */
	if (kernel_map) {
		phdr->p_type = PT_LOAD;
		phdr->p_flags = PF_R|PF_W|PF_X;
1317
		phdr->p_vaddr = (unsigned long) _text;
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
		phdr->p_filesz = phdr->p_memsz = _end - _text;
		phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
		ehdr->e_phnum++;
		phdr++;
	}

	/* Go through all the ranges in mem->ranges[] and prepare phdr */
	for (i = 0; i < mem->nr_ranges; i++) {
		mstart = mem->ranges[i].start;
		mend = mem->ranges[i].end;

		phdr->p_type = PT_LOAD;
		phdr->p_flags = PF_R|PF_W|PF_X;
		phdr->p_offset  = mstart;

		phdr->p_paddr = mstart;
1334
		phdr->p_vaddr = (unsigned long) __va(mstart);
1335
1336
1337
		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
		phdr->p_align = 0;
		ehdr->e_phnum++;
1338
		pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
1339
1340
			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
			ehdr->e_phnum, phdr->p_offset);
1341
		phdr++;
1342
1343
1344
1345
1346
1347
	}

	*addr = buf;
	*sz = elf_sz;
	return 0;
}