forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
kexec_file.c
1183 lines (992 loc) · 29.1 KB
/
kexec_file.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
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
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
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
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
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-only
/*
* kexec: kexec_file_load system call
*
* Copyright (C) 2014 Red Hat Inc.
* Authors:
* Vivek Goyal <vgoyal@redhat.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/kexec.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/fs.h>
#include <linux/ima.h>
#include <crypto/hash.h>
#include <crypto/sha2.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/kernel.h>
#include <linux/kernel_read_file.h>
#include <linux/syscalls.h>
#include <linux/vmalloc.h>
#include "kexec_internal.h"
#ifdef CONFIG_KEXEC_SIG
static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE);
void set_kexec_sig_enforced(void)
{
sig_enforce = true;
}
#endif
static int kexec_calculate_store_digests(struct kimage *image);
/* Maximum size in bytes for kernel/initrd files. */
#define KEXEC_FILE_SIZE_MAX min_t(s64, 4LL << 30, SSIZE_MAX)
/*
* 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;
}
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);
}
int kexec_image_post_load_cleanup_default(struct kimage *image)
{
if (!image->fops || !image->fops->cleanup)
return 0;
return image->fops->cleanup(image->image_loader_data);
}
/*
* 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;
#ifdef CONFIG_IMA_KEXEC
vfree(image->ima_buffer);
image->ima_buffer = NULL;
#endif /* CONFIG_IMA_KEXEC */
/* 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;
kexec_file_dbg_print = false;
}
#ifdef CONFIG_KEXEC_SIG
#ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len)
{
int ret;
ret = verify_pefile_signature(kernel, kernel_len,
VERIFY_USE_SECONDARY_KEYRING,
VERIFYING_KEXEC_PE_SIGNATURE);
if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) {
ret = verify_pefile_signature(kernel, kernel_len,
VERIFY_USE_PLATFORM_KEYRING,
VERIFYING_KEXEC_PE_SIGNATURE);
}
return ret;
}
#endif
static int kexec_image_verify_sig(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);
}
static int
kimage_validate_signature(struct kimage *image)
{
int ret;
ret = kexec_image_verify_sig(image, image->kernel_buf,
image->kernel_buf_len);
if (ret) {
if (sig_enforce) {
pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
return ret;
}
/*
* If IMA is guaranteed to appraise a signature on the kexec
* 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;
pr_debug("kernel signature verification failed (%d).\n", ret);
}
return 0;
}
#endif
/*
* 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)
{
ssize_t ret;
void *ldata;
ret = kernel_read_file_from_fd(kernel_fd, 0, &image->kernel_buf,
KEXEC_FILE_SIZE_MAX, NULL,
READING_KEXEC_IMAGE);
if (ret < 0)
return ret;
image->kernel_buf_len = ret;
kexec_dprintk("kernel: %p kernel_size: %#lx\n",
image->kernel_buf, image->kernel_buf_len);
/* Call arch image probe handlers */
ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
image->kernel_buf_len);
if (ret)
goto out;
#ifdef CONFIG_KEXEC_SIG
ret = kimage_validate_signature(image);
if (ret)
goto out;
#endif
/* It is possible that there no initramfs is being loaded */
if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
ret = kernel_read_file_from_fd(initrd_fd, 0, &image->initrd_buf,
KEXEC_FILE_SIZE_MAX, NULL,
READING_KEXEC_INITRAMFS);
if (ret < 0)
goto out;
image->initrd_buf_len = ret;
ret = 0;
}
if (cmdline_len) {
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;
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;
}
ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
image->cmdline_buf_len - 1);
}
/* IMA needs to pass the measurement list to the next kernel. */
ima_add_kexec_buffer(image);
/* Call image load handler */
ldata = kexec_image_load_default(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;
kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG);
image->file_mode = 1;
#ifdef CONFIG_CRASH_DUMP
if (kexec_on_panic) {
/* Enable special crash kernel control page alloc policy. */
image->control_page = crashk_res.start;
image->type = KEXEC_TYPE_CRASH;
}
#endif
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 image_type = (flags & KEXEC_FILE_ON_CRASH) ?
KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT;
struct kimage **dest_image, *image;
int ret = 0, i;
/* We only trust the superuser with rebooting the system. */
if (!kexec_load_permitted(image_type))
return -EPERM;
/* Make sure we have a legal set of flags */
if (flags != (flags & KEXEC_FILE_FLAGS))
return -EINVAL;
image = NULL;
if (!kexec_trylock())
return -EBUSY;
#ifdef CONFIG_CRASH_DUMP
if (image_type == KEXEC_TYPE_CRASH) {
dest_image = &kexec_crash_image;
if (kexec_crash_image)
arch_kexec_unprotect_crashkres();
} else
#endif
dest_image = &kexec_image;
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;
#ifdef CONFIG_CRASH_HOTPLUG
if ((flags & KEXEC_FILE_ON_CRASH) && arch_crash_hotplug_support(image, flags))
image->hotplug_support = 1;
#endif
ret = machine_kexec_prepare(image);
if (ret)
goto out;
/*
* 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;
ret = kexec_calculate_store_digests(image);
if (ret)
goto out;
kexec_dprintk("nr_segments = %lu\n", image->nr_segments);
for (i = 0; i < image->nr_segments; i++) {
struct kexec_segment *ksegment;
ksegment = &image->segment[i];
kexec_dprintk("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);
ret = machine_kexec_post_load(image);
if (ret)
goto out;
kexec_dprintk("kexec_file_load: type:%u, start:0x%lx head:0x%lx flags:0x%lx\n",
image->type, image->start, image->head, flags);
/*
* 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:
#ifdef CONFIG_CRASH_DUMP
if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
arch_kexec_protect_crashkres();
#endif
kexec_unlock();
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 + 1;
do {
/* align down start */
temp_start = ALIGN_DOWN(temp_start, kbuf->buf_align);
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;
}
static int locate_mem_hole_callback(struct resource *res, void *arg)
{
struct kexec_buf *kbuf = (struct kexec_buf *)arg;
u64 start = res->start, end = res->end;
unsigned long sz = end - start + 1;
/* Returning 0 will take to next memory range */
/* Don't use memory that will be detected and handled by a driver. */
if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
return 0;
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);
}
#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
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 = { };
#ifdef CONFIG_CRASH_DUMP
if (kbuf->image->type == KEXEC_TYPE_CRASH)
return func(&crashk_res, kbuf);
#endif
/*
* Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See
* IORESOURCE_SYSRAM_DRIVER_MANAGED handling in
* locate_mem_hole_callback().
*/
if (kbuf->top_down) {
for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&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 {
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&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;
}
}
return ret;
}
#else
static int kexec_walk_memblock(struct kexec_buf *kbuf,
int (*func)(struct resource *, void *))
{
return 0;
}
#endif
/**
* kexec_walk_resources - call func(data) on free memory regions
* @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.
*/
static int kexec_walk_resources(struct kexec_buf *kbuf,
int (*func)(struct resource *, void *))
{
#ifdef CONFIG_CRASH_DUMP
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);
#endif
if (kbuf->top_down)
return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func);
else
return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
}
/**
* 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;
/* Arch knows where to place */
if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
return 0;
if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
else
ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
return ret == 1 ? 0 : -EADDRNOTAVAIL;
}
/**
* kexec_add_buffer - place a buffer in a kexec segment
* @kbuf: Buffer contents and memory parameters.
*
* This function assumes that kexec_lock 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.
*/
int kexec_add_buffer(struct kexec_buf *kbuf)
{
struct kexec_segment *ksegment;
int ret;
/* Currently adding segment this way is allowed only in file mode */
if (!kbuf->image->file_mode)
return -EINVAL;
if (kbuf->image->nr_segments >= KEXEC_SEGMENT_MAX)
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.
*/
if (!list_empty(&kbuf->image->control_pages)) {
WARN_ON(1);
return -EINVAL;
}
/* Ensure minimum alignment needed for segments. */
kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
/* Walk the RAM ranges and allocate a suitable range for the buffer */
ret = arch_kexec_locate_mem_hole(kbuf);
if (ret)
return ret;
/* Found a suitable memory range */
ksegment = &kbuf->image->segment[kbuf->image->nr_segments];
ksegment->kbuf = kbuf->buffer;
ksegment->bufsz = kbuf->bufsz;
ksegment->mem = kbuf->mem;
ksegment->memsz = kbuf->memsz;
kbuf->image->nr_segments++;
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;
if (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY))
return 0;
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) {
ret = -ENOMEM;
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;
#ifdef CONFIG_CRASH_HOTPLUG
/* Exclude elfcorehdr segment to allow future changes via hotplug */
if (i == image->elfcorehdr_index)
continue;
#endif
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;
ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
sha_regions, sha_region_sz, 0);
if (ret)
goto out_free_digest;
ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
digest, SHA256_DIGEST_SIZE, 0);
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;
}
#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY
/*
* 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)
{
const Elf_Shdr *sechdrs;
unsigned long bss_align;
unsigned long bss_sz;
unsigned long align;
int i, ret;
sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
kbuf->buf_align = bss_align = 1;
kbuf->bufsz = bss_sz = 0;
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;
size_t sechdrs_size;
Elf_Shdr *sechdrs;
int i;
/*
* The section headers in kexec_purgatory are read-only. In order to
* have them modifiable make a temporary copy.
*/
sechdrs_size = array_size(sizeof(Elf_Shdr), pi->ehdr->e_shnum);
sechdrs = vzalloc(sechdrs_size);
if (!sechdrs)
return -ENOMEM;
memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff, sechdrs_size);
pi->sechdrs = sechdrs;
offset = 0;
bss_addr = kbuf->mem + kbuf->bufsz;
kbuf->image->start = pi->ehdr->e_entry;
for (i = 0; i < pi->ehdr->e_shnum; i++) {
unsigned long align;
void *src, *dst;
if (!(sechdrs[i].sh_flags & SHF_ALLOC))
continue;
align = sechdrs[i].sh_addralign;
if (sechdrs[i].sh_type == SHT_NOBITS) {
bss_addr = ALIGN(bss_addr, align);
sechdrs[i].sh_addr = bss_addr;
bss_addr += sechdrs[i].sh_size;
continue;
}
offset = ALIGN(offset, align);
/*
* Check if the segment contains the entry point, if so,
* calculate the value of image->start based on it.
* If the compiler has produced more than one .text section
* (Eg: .text.hot), they are generally after the main .text
* section, and they shall not be used to calculate
* image->start. So do not re-calculate image->start if it
* is not set to the initial value, and warn the user so they
* have a chance to fix their purgatory's linker script.
*/
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) &&
!WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
kbuf->image->start -= sechdrs[i].sh_addr;
kbuf->image->start += kbuf->mem + offset;
}
src = (void *)pi->ehdr + sechdrs[i].sh_offset;
dst = pi->purgatory_buf + offset;
memcpy(dst, src, sechdrs[i].sh_size);
sechdrs[i].sh_addr = kbuf->mem + offset;
sechdrs[i].sh_offset = offset;
offset += sechdrs[i].sh_size;
}
return 0;
}
static int kexec_apply_relocations(struct kimage *image)
{
int i, ret;
struct purgatory_info *pi = &image->purgatory_info;
const Elf_Shdr *sechdrs;
sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
for (i = 0; i < pi->ehdr->e_shnum; i++) {
const Elf_Shdr *relsec;
const Elf_Shdr *symtab;
Elf_Shdr *section;
relsec = sechdrs + i;
if (relsec->sh_type != SHT_RELA &&
relsec->sh_type != SHT_REL)
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.
*/
if (relsec->sh_info >= pi->ehdr->e_shnum ||
relsec->sh_link >= pi->ehdr->e_shnum)
return -ENOEXEC;
section = pi->sechdrs + relsec->sh_info;
symtab = sechdrs + relsec->sh_link;
if (!(section->sh_flags & SHF_ALLOC))
continue;