aboutsummaryrefslogtreecommitdiffstats
path: root/fs/proc/vmcore.c
blob: aaa7486b6f0d9e42a850c9f154d3dcfdceb34e95 (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
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
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
/*
 *	fs/proc/vmcore.c Interface for accessing the crash
 * 				 dump from the system's previous life.
 * 	Heavily borrowed from fs/proc/kcore.c
 *	Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
 *	Copyright (C) IBM Corporation, 2004. All rights reserved
 *
 */

#include <linux/mm.h>
#include <linux/kcore.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/printk.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/list.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
#include <asm/io.h>
#include "internal.h"

/* List representing chunks of contiguous memory areas and their offsets in
 * vmcore file.
 */
static LIST_HEAD(vmcore_list);

/* Stores the pointer to the buffer containing kernel elf core headers. */
static char *elfcorebuf;
static size_t elfcorebuf_sz;
static size_t elfcorebuf_sz_orig;

static char *elfnotes_buf;
static size_t elfnotes_sz;

/* Total size of vmcore file. */
static u64 vmcore_size;

static struct proc_dir_entry *proc_vmcore;

/*
 * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
 * The called function has to take care of module refcounting.
 */
static int (*oldmem_pfn_is_ram)(unsigned long pfn);

int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
{
	if (oldmem_pfn_is_ram)
		return -EBUSY;
	oldmem_pfn_is_ram = fn;
	return 0;
}
EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);

void unregister_oldmem_pfn_is_ram(void)
{
	oldmem_pfn_is_ram = NULL;
	wmb();
}
EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);

static int pfn_is_ram(unsigned long pfn)
{
	int (*fn)(unsigned long pfn);
	/* pfn is ram unless fn() checks pagetype */
	int ret = 1;

	/*
	 * Ask hypervisor if the pfn is really ram.
	 * A ballooned page contains no data and reading from such a page
	 * will cause high load in the hypervisor.
	 */
	fn = oldmem_pfn_is_ram;
	if (fn)
		ret = fn(pfn);

	return ret;
}

/* Reads a page from the oldmem device from given offset. */
static ssize_t read_from_oldmem(char *buf, size_t count,
				u64 *ppos, int userbuf)
{
	unsigned long pfn, offset;
	size_t nr_bytes;
	ssize_t read = 0, tmp;

	if (!count)
		return 0;

	offset = (unsigned long)(*ppos % PAGE_SIZE);
	pfn = (unsigned long)(*ppos / PAGE_SIZE);

	do {
		if (count > (PAGE_SIZE - offset))
			nr_bytes = PAGE_SIZE - offset;
		else
			nr_bytes = count;

		/* If pfn is not ram, return zeros for sparse dump files */
		if (pfn_is_ram(pfn) == 0)
			memset(buf, 0, nr_bytes);
		else {
			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
						offset, userbuf);
			if (tmp < 0)
				return tmp;
		}
		*ppos += nr_bytes;
		count -= nr_bytes;
		buf += nr_bytes;
		read += nr_bytes;
		++pfn;
		offset = 0;
	} while (count);

	return read;
}

/*
 * Architectures may override this function to allocate ELF header in 2nd kernel
 */
int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
{
	return 0;
}

/*
 * Architectures may override this function to free header
 */
void __weak elfcorehdr_free(unsigned long long addr)
{}

/*
 * Architectures may override this function to read from ELF header
 */
ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
{
	return read_from_oldmem(buf, count, ppos, 0);
}

/*
 * Architectures may override this function to read from notes sections
 */
ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
{
	return read_from_oldmem(buf, count, ppos, 0);
}

/*
 * Architectures may override this function to map oldmem
 */
int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
				  unsigned long from, unsigned long pfn,
				  unsigned long size, pgprot_t prot)
{
	return remap_pfn_range(vma, from, pfn, size, prot);
}

/*
 * Architectures which support memory encryption override this.
 */
ssize_t __weak
copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize,
			   unsigned long offset, int userbuf)
{
	return copy_oldmem_page(pfn, buf, csize, offset, userbuf);
}

/*
 * Copy to either kernel or user space
 */
static int copy_to(void *target, void *src, size_t size, int userbuf)
{
	if (userbuf) {
		if (copy_to_user((char __user *) target, src, size))
			return -EFAULT;
	} else {
		memcpy(target, src, size);
	}
	return 0;
}

/* Read from the ELF header and then the crash dump. On error, negative value is
 * returned otherwise number of bytes read are returned.
 */
static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
			     int userbuf)
{
	ssize_t acc = 0, tmp;
	size_t tsz;
	u64 start;
	struct vmcore *m = NULL;

	if (buflen == 0 || *fpos >= vmcore_size)
		return 0;

	/* trim buflen to not go beyond EOF */
	if (buflen > vmcore_size - *fpos)
		buflen = vmcore_size - *fpos;

	/* Read ELF core header */
	if (*fpos < elfcorebuf_sz) {
		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
		if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
			return -EFAULT;
		buflen -= tsz;
		*fpos += tsz;
		buffer += tsz;
		acc += tsz;

		/* leave now if filled buffer already */
		if (buflen == 0)
			return acc;
	}

	/* Read Elf note segment */
	if (*fpos < elfcorebuf_sz + elfnotes_sz) {
		void *kaddr;

		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
		if (copy_to(buffer, kaddr, tsz, userbuf))
			return -EFAULT;
		buflen -= tsz;
		*fpos += tsz;
		buffer += tsz;
		acc += tsz;

		/* leave now if filled buffer already */
		if (buflen == 0)
			return acc;
	}

	list_for_each_entry(m, &vmcore_list, list) {
		if (*fpos < m->offset + m->size) {
			tsz = (size_t)min_t(unsigned long long,
					    m->offset + m->size - *fpos,
					    buflen);
			start = m->paddr + *fpos - m->offset;
			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
			if (tmp < 0)
				return tmp;
			buflen -= tsz;
			*fpos += tsz;
			buffer += tsz;
			acc += tsz;

			/* leave now if filled buffer already */
			if (buflen == 0)
				return acc;
		}
	}

	return acc;
}

static ssize_t read_vmcore(struct file *file, char __user *buffer,
			   size_t buflen, loff_t *fpos)
{
	return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
}

/*
 * The vmcore fault handler uses the page cache and fills data using the
 * standard __vmcore_read() function.
 *
 * On s390 the fault handler is used for memory regions that can't be mapped
 * directly with remap_pfn_range().
 */
static int mmap_vmcore_fault(struct vm_fault *vmf)
{
#ifdef CONFIG_S390
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	pgoff_t index = vmf->pgoff;
	struct page *page;
	loff_t offset;
	char *buf;
	int rc;

	page = find_or_create_page(mapping, index, GFP_KERNEL);
	if (!page)
		return VM_FAULT_OOM;
	if (!PageUptodate(page)) {
		offset = (loff_t) index << PAGE_SHIFT;
		buf = __va((page_to_pfn(page) << PAGE_SHIFT));
		rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
		if (rc < 0) {
			unlock_page(page);
			put_page(page);
			return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
		}
		SetPageUptodate(page);
	}
	unlock_page(page);
	vmf->page = page;
	return 0;
#else
	return VM_FAULT_SIGBUS;
#endif
}

static const struct vm_operations_struct vmcore_mmap_ops = {
	.fault = mmap_vmcore_fault,
};

/**
 * alloc_elfnotes_buf - allocate buffer for ELF note segment in
 *                      vmalloc memory
 *
 * @notes_sz: size of buffer
 *
 * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
 * the buffer to user-space by means of remap_vmalloc_range().
 *
 * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
 * disabled and there's no need to allow users to mmap the buffer.
 */
static inline char *alloc_elfnotes_buf(size_t notes_sz)
{
#ifdef CONFIG_MMU
	return vmalloc_user(notes_sz);
#else
	return vzalloc(notes_sz);
#endif
}

/*
 * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is
 * essential for mmap_vmcore() in order to map physically
 * non-contiguous objects (ELF header, ELF note segment and memory
 * regions in the 1st kernel pointed to by PT_LOAD entries) into
 * virtually contiguous user-space in ELF layout.
 */
#ifdef CONFIG_MMU
/*
 * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
 * reported as not being ram with the zero page.
 *
 * @vma: vm_area_struct describing requested mapping
 * @from: start remapping from
 * @pfn: page frame number to start remapping to
 * @size: remapping size
 * @prot: protection bits
 *
 * Returns zero on success, -EAGAIN on failure.
 */
static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
				    unsigned long from, unsigned long pfn,
				    unsigned long size, pgprot_t prot)
{
	unsigned long map_size;
	unsigned long pos_start, pos_end, pos;
	unsigned long zeropage_pfn = my_zero_pfn(0);
	size_t len = 0;

	pos_start = pfn;
	pos_end = pfn + (size >> PAGE_SHIFT);

	for (pos = pos_start; pos < pos_end; ++pos) {
		if (!pfn_is_ram(pos)) {
			/*
			 * We hit a page which is not ram. Remap the continuous
			 * region between pos_start and pos-1 and replace
			 * the non-ram page at pos with the zero page.
			 */
			if (pos > pos_start) {
				/* Remap continuous region */
				map_size = (pos - pos_start) << PAGE_SHIFT;
				if (remap_oldmem_pfn_range(vma, from + len,
							   pos_start, map_size,
							   prot))
					goto fail;
				len += map_size;
			}
			/* Remap the zero page */
			if (remap_oldmem_pfn_range(vma, from + len,
						   zeropage_pfn,
						   PAGE_SIZE, prot))
				goto fail;
			len += PAGE_SIZE;
			pos_start = pos + 1;
		}
	}
	if (pos > pos_start) {
		/* Remap the rest */
		map_size = (pos - pos_start) << PAGE_SHIFT;
		if (remap_oldmem_pfn_range(vma, from + len, pos_start,
					   map_size, prot))
			goto fail;
	}
	return 0;
fail:
	do_munmap(vma->vm_mm, from, len, NULL);
	return -EAGAIN;
}

static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
			    unsigned long from, unsigned long pfn,
			    unsigned long size, pgprot_t prot)
{
	/*
	 * Check if oldmem_pfn_is_ram was registered to avoid
	 * looping over all pages without a reason.
	 */
	if (oldmem_pfn_is_ram)
		return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
	else
		return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
}

static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
	size_t size = vma->vm_end - vma->vm_start;
	u64 start, end, len, tsz;
	struct vmcore *m;

	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
	end = start + size;

	if (size > vmcore_size || end > vmcore_size)
		return -EINVAL;

	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
		return -EPERM;

	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
	vma->vm_flags |= VM_MIXEDMAP;
	vma->vm_ops = &vmcore_mmap_ops;

	len = 0;

	if (start < elfcorebuf_sz) {
		u64 pfn;

		tsz = min(elfcorebuf_sz - (size_t)start, size);
		pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
		if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
				    vma->vm_page_prot))
			return -EAGAIN;
		size -= tsz;
		start += tsz;
		len += tsz;

		if (size == 0)
			return 0;
	}

	if (start < elfcorebuf_sz + elfnotes_sz) {
		void *kaddr;

		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
		kaddr = elfnotes_buf + start - elfcorebuf_sz;
		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
						kaddr, 0, tsz))
			goto fail;
		size -= tsz;
		start += tsz;
		len += tsz;

		if (size == 0)
			return 0;
	}

	list_for_each_entry(m, &vmcore_list, list) {
		if (start < m->offset + m->size) {
			u64 paddr = 0;

			tsz = (size_t)min_t(unsigned long long,
					    m->offset + m->size - start, size);
			paddr = m->paddr + start - m->offset;
			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
						    paddr >> PAGE_SHIFT, tsz,
						    vma->vm_page_prot))
				goto fail;
			size -= tsz;
			start += tsz;
			len += tsz;

			if (size == 0)
				return 0;
		}
	}

	return 0;
fail:
	do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
	return -EAGAIN;
}
#else
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
	return -ENOSYS;
}
#endif

static const struct file_operations proc_vmcore_operations = {
	.read		= read_vmcore,
	.llseek		= default_llseek,
	.mmap		= mmap_vmcore,
};

static struct vmcore* __init get_new_element(void)
{
	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
}

static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
				  struct list_head *vc_list)
{
	u64 size;
	struct vmcore *m;

	size = elfsz + elfnotesegsz;
	list_for_each_entry(m, vc_list, list) {
		size += m->size;
	}
	return size;
}

/**
 * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry
 *
 * @ehdr_ptr: ELF header
 *
 * This function updates p_memsz member of each PT_NOTE entry in the
 * program header table pointed to by @ehdr_ptr to real size of ELF
 * note segment.
 */
static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
{
	int i, rc=0;
	Elf64_Phdr *phdr_ptr;
	Elf64_Nhdr *nhdr_ptr;

	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		void *notes_section;
		u64 offset, max_sz, sz, real_sz = 0;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		max_sz = phdr_ptr->p_memsz;
		offset = phdr_ptr->p_offset;
		notes_section = kmalloc(max_sz, GFP_KERNEL);
		if (!notes_section)
			return -ENOMEM;
		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
		if (rc < 0) {
			kfree(notes_section);
			return rc;
		}
		nhdr_ptr = notes_section;
		while (nhdr_ptr->n_namesz != 0) {
			sz = sizeof(Elf64_Nhdr) +
				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
			if ((real_sz + sz) > max_sz) {
				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
				break;
			}
			real_sz += sz;
			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
		}
		kfree(notes_section);
		phdr_ptr->p_memsz = real_sz;
		if (real_sz == 0) {
			pr_warn("Warning: Zero PT_NOTE entries found\n");
		}
	}

	return 0;
}

/**
 * get_note_number_and_size_elf64 - get the number of PT_NOTE program
 * headers and sum of real size of their ELF note segment headers and
 * data.
 *
 * @ehdr_ptr: ELF header
 * @nr_ptnote: buffer for the number of PT_NOTE program headers
 * @sz_ptnote: buffer for size of unique PT_NOTE program header
 *
 * This function is used to merge multiple PT_NOTE program headers
 * into a unique single one. The resulting unique entry will have
 * @sz_ptnote in its phdr->p_mem.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf64
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr,
						 int *nr_ptnote, u64 *sz_ptnote)
{
	int i;
	Elf64_Phdr *phdr_ptr;

	*nr_ptnote = *sz_ptnote = 0;

	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		*nr_ptnote += 1;
		*sz_ptnote += phdr_ptr->p_memsz;
	}

	return 0;
}

/**
 * copy_notes_elf64 - copy ELF note segments in a given buffer
 *
 * @ehdr_ptr: ELF header
 * @notes_buf: buffer into which ELF note segments are copied
 *
 * This function is used to copy ELF note segment in the 1st kernel
 * into the buffer @notes_buf in the 2nd kernel. It is assumed that
 * size of the buffer @notes_buf is equal to or larger than sum of the
 * real ELF note segment headers and data.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf64
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
{
	int i, rc=0;
	Elf64_Phdr *phdr_ptr;

	phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1);

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 offset;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		offset = phdr_ptr->p_offset;
		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
					   &offset);
		if (rc < 0)
			return rc;
		notes_buf += phdr_ptr->p_memsz;
	}

	return 0;
}

/* Merges all the PT_NOTE headers into one. */
static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
					   char **notes_buf, size_t *notes_sz)
{
	int i, nr_ptnote=0, rc=0;
	char *tmp;
	Elf64_Ehdr *ehdr_ptr;
	Elf64_Phdr phdr;
	u64 phdr_sz = 0, note_off;

	ehdr_ptr = (Elf64_Ehdr *)elfptr;

	rc = update_note_header_size_elf64(ehdr_ptr);
	if (rc < 0)
		return rc;

	rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz);
	if (rc < 0)
		return rc;

	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
	*notes_buf = alloc_elfnotes_buf(*notes_sz);
	if (!*notes_buf)
		return -ENOMEM;

	rc = copy_notes_elf64(ehdr_ptr, *notes_buf);
	if (rc < 0)
		return rc;

	/* Prepare merged PT_NOTE program header. */
	phdr.p_type    = PT_NOTE;
	phdr.p_flags   = 0;
	note_off = sizeof(Elf64_Ehdr) +
			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr);
	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
	phdr.p_vaddr   = phdr.p_paddr = 0;
	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
	phdr.p_align   = 0;

	/* Add merged PT_NOTE program header*/
	tmp = elfptr + sizeof(Elf64_Ehdr);
	memcpy(tmp, &phdr, sizeof(phdr));
	tmp += sizeof(phdr);

	/* Remove unwanted PT_NOTE program headers. */
	i = (nr_ptnote - 1) * sizeof(Elf64_Phdr);
	*elfsz = *elfsz - i;
	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr)));
	memset(elfptr + *elfsz, 0, i);
	*elfsz = roundup(*elfsz, PAGE_SIZE);

	/* Modify e_phnum to reflect merged headers. */
	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;

	return 0;
}

/**
 * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry
 *
 * @ehdr_ptr: ELF header
 *
 * This function updates p_memsz member of each PT_NOTE entry in the
 * program header table pointed to by @ehdr_ptr to real size of ELF
 * note segment.
 */
static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
{
	int i, rc=0;
	Elf32_Phdr *phdr_ptr;
	Elf32_Nhdr *nhdr_ptr;

	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		void *notes_section;
		u64 offset, max_sz, sz, real_sz = 0;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		max_sz = phdr_ptr->p_memsz;
		offset = phdr_ptr->p_offset;
		notes_section = kmalloc(max_sz, GFP_KERNEL);
		if (!notes_section)
			return -ENOMEM;
		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
		if (rc < 0) {
			kfree(notes_section);
			return rc;
		}
		nhdr_ptr = notes_section;
		while (nhdr_ptr->n_namesz != 0) {
			sz = sizeof(Elf32_Nhdr) +
				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
			if ((real_sz + sz) > max_sz) {
				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
				break;
			}
			real_sz += sz;
			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
		}
		kfree(notes_section);
		phdr_ptr->p_memsz = real_sz;
		if (real_sz == 0) {
			pr_warn("Warning: Zero PT_NOTE entries found\n");
		}
	}

	return 0;
}

/**
 * get_note_number_and_size_elf32 - get the number of PT_NOTE program
 * headers and sum of real size of their ELF note segment headers and
 * data.
 *
 * @ehdr_ptr: ELF header
 * @nr_ptnote: buffer for the number of PT_NOTE program headers
 * @sz_ptnote: buffer for size of unique PT_NOTE program header
 *
 * This function is used to merge multiple PT_NOTE program headers
 * into a unique single one. The resulting unique entry will have
 * @sz_ptnote in its phdr->p_mem.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf32
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr,
						 int *nr_ptnote, u64 *sz_ptnote)
{
	int i;
	Elf32_Phdr *phdr_ptr;

	*nr_ptnote = *sz_ptnote = 0;

	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		*nr_ptnote += 1;
		*sz_ptnote += phdr_ptr->p_memsz;
	}

	return 0;
}

/**
 * copy_notes_elf32 - copy ELF note segments in a given buffer
 *
 * @ehdr_ptr: ELF header
 * @notes_buf: buffer into which ELF note segments are copied
 *
 * This function is used to copy ELF note segment in the 1st kernel
 * into the buffer @notes_buf in the 2nd kernel. It is assumed that
 * size of the buffer @notes_buf is equal to or larger than sum of the
 * real ELF note segment headers and data.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf32
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
{
	int i, rc=0;
	Elf32_Phdr *phdr_ptr;

	phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1);

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 offset;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		offset = phdr_ptr->p_offset;
		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
					   &offset);
		if (rc < 0)
			return rc;
		notes_buf += phdr_ptr->p_memsz;
	}

	return 0;
}

/* Merges all the PT_NOTE headers into one. */
static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
					   char **notes_buf, size_t *notes_sz)
{
	int i, nr_ptnote=0, rc=0;
	char *tmp;
	Elf32_Ehdr *ehdr_ptr;
	Elf32_Phdr phdr;
	u64 phdr_sz = 0, note_off;

	ehdr_ptr = (Elf32_Ehdr *)elfptr;

	rc = update_note_header_size_elf32(ehdr_ptr);
	if (rc < 0)
		return rc;

	rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz);
	if (rc < 0)
		return rc;

	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
	*notes_buf = alloc_elfnotes_buf(*notes_sz);
	if (!*notes_buf)
		return -ENOMEM;

	rc = copy_notes_elf32(ehdr_ptr, *notes_buf);
	if (rc < 0)
		return rc;

	/* Prepare merged PT_NOTE program header. */
	phdr.p_type    = PT_NOTE;
	phdr.p_flags   = 0;
	note_off = sizeof(Elf32_Ehdr) +
			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr);
	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
	phdr.p_vaddr   = phdr.p_paddr = 0;
	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
	phdr.p_align   = 0;

	/* Add merged PT_NOTE program header*/
	tmp = elfptr + sizeof(Elf32_Ehdr);
	memcpy(tmp, &phdr, sizeof(phdr));
	tmp += sizeof(phdr);

	/* Remove unwanted PT_NOTE program headers. */
	i = (nr_ptnote - 1) * sizeof(Elf32_Phdr);
	*elfsz = *elfsz - i;
	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr)));
	memset(elfptr + *elfsz, 0, i);
	*elfsz = roundup(*elfsz, PAGE_SIZE);

	/* Modify e_phnum to reflect merged headers. */
	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;

	return 0;
}

/* Add memory chunks represented by program headers to vmcore list. Also update
 * the new offset fields of exported program headers. */
static int __init process_ptload_program_headers_elf64(char *elfptr,
						size_t elfsz,
						size_t elfnotes_sz,
						struct list_head *vc_list)
{
	int i;
	Elf64_Ehdr *ehdr_ptr;
	Elf64_Phdr *phdr_ptr;
	loff_t vmcore_off;
	struct vmcore *new;

	ehdr_ptr = (Elf64_Ehdr *)elfptr;
	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */

	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 paddr, start, end, size;

		if (phdr_ptr->p_type != PT_LOAD)
			continue;

		paddr = phdr_ptr->p_offset;
		start = rounddown(paddr, PAGE_SIZE);
		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
		size = end - start;

		/* Add this contiguous chunk of memory to vmcore list.*/
		new = get_new_element();
		if (!new)
			return -ENOMEM;
		new->paddr = start;
		new->size = size;
		list_add_tail(&new->list, vc_list);

		/* Update the program header offset. */
		phdr_ptr->p_offset = vmcore_off + (paddr - start);
		vmcore_off = vmcore_off + size;
	}
	return 0;
}

static int __init process_ptload_program_headers_elf32(char *elfptr,
						size_t elfsz,
						size_t elfnotes_sz,
						struct list_head *vc_list)
{
	int i;
	Elf32_Ehdr *ehdr_ptr;
	Elf32_Phdr *phdr_ptr;
	loff_t vmcore_off;
	struct vmcore *new;

	ehdr_ptr = (Elf32_Ehdr *)elfptr;
	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */

	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 paddr, start, end, size;

		if (phdr_ptr->p_type != PT_LOAD)
			continue;

		paddr = phdr_ptr->p_offset;
		start = rounddown(paddr, PAGE_SIZE);
		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
		size = end - start;

		/* Add this contiguous chunk of memory to vmcore list.*/
		new = get_new_element();
		if (!new)
			return -ENOMEM;
		new->paddr = start;
		new->size = size;
		list_add_tail(&new->list, vc_list);

		/* Update the program header offset */
		phdr_ptr->p_offset = vmcore_off + (paddr - start);
		vmcore_off = vmcore_off + size;
	}
	return 0;
}

/* Sets offset fields of vmcore elements. */
static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
					   struct list_head *vc_list)
{
	loff_t vmcore_off;
	struct vmcore *m;

	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;

	list_for_each_entry(m, vc_list, list) {
		m->offset = vmcore_off;
		vmcore_off += m->size;
	}
}

static void free_elfcorebuf(void)
{
	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
	elfcorebuf = NULL;
	vfree(elfnotes_buf);
	elfnotes_buf = NULL;
}

static int __init parse_crash_elf64_headers(void)
{
	int rc=0;
	Elf64_Ehdr ehdr;
	u64 addr;

	addr = elfcorehdr_addr;

	/* Read Elf header */
	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
	if (rc < 0)
		return rc;

	/* Do some basic Verification. */
	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
		(ehdr.e_type != ET_CORE) ||
		!vmcore_elf64_check_arch(&ehdr) ||
		ehdr.e_ident[EI_CLASS] != ELFCLASS64 ||
		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
		ehdr.e_version != EV_CURRENT ||
		ehdr.e_ehsize != sizeof(Elf64_Ehdr) ||
		ehdr.e_phentsize != sizeof(Elf64_Phdr) ||
		ehdr.e_phnum == 0) {
		pr_warn("Warning: Core image elf header is not sane\n");
		return -EINVAL;
	}

	/* Read in all elf headers. */
	elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) +
				ehdr.e_phnum * sizeof(Elf64_Phdr);
	elfcorebuf_sz = elfcorebuf_sz_orig;
	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					      get_order(elfcorebuf_sz_orig));
	if (!elfcorebuf)
		return -ENOMEM;
	addr = elfcorehdr_addr;
	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
	if (rc < 0)
		goto fail;

	/* Merge all PT_NOTE headers into one. */
	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz,
				      &elfnotes_buf, &elfnotes_sz);
	if (rc)
		goto fail;
	rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz,
						  elfnotes_sz, &vmcore_list);
	if (rc)
		goto fail;
	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
	return 0;
fail:
	free_elfcorebuf();
	return rc;
}

static int __init parse_crash_elf32_headers(void)
{
	int rc=0;
	Elf32_Ehdr ehdr;
	u64 addr;

	addr = elfcorehdr_addr;

	/* Read Elf header */
	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
	if (rc < 0)
		return rc;

	/* Do some basic Verification. */
	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
		(ehdr.e_type != ET_CORE) ||
		!vmcore_elf32_check_arch(&ehdr) ||
		ehdr.e_ident[EI_CLASS] != ELFCLASS32||
		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
		ehdr.e_version != EV_CURRENT ||
		ehdr.e_ehsize != sizeof(Elf32_Ehdr) ||
		ehdr.e_phentsize != sizeof(Elf32_Phdr) ||
		ehdr.e_phnum == 0) {
		pr_warn("Warning: Core image elf header is not sane\n");
		return -EINVAL;
	}

	/* Read in all elf headers. */
	elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
	elfcorebuf_sz = elfcorebuf_sz_orig;
	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					      get_order(elfcorebuf_sz_orig));
	if (!elfcorebuf)
		return -ENOMEM;
	addr = elfcorehdr_addr;
	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
	if (rc < 0)
		goto fail;

	/* Merge all PT_NOTE headers into one. */
	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz,
				      &elfnotes_buf, &elfnotes_sz);
	if (rc)
		goto fail;
	rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz,
						  elfnotes_sz, &vmcore_list);
	if (rc)
		goto fail;
	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
	return 0;
fail:
	free_elfcorebuf();
	return rc;
}

static int __init parse_crash_elf_headers(void)
{
	unsigned char e_ident[EI_NIDENT];
	u64 addr;
	int rc=0;

	addr = elfcorehdr_addr;
	rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
	if (rc < 0)
		return rc;
	if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
		pr_warn("Warning: Core image elf header not found\n");
		return -EINVAL;
	}

	if (e_ident[EI_CLASS] == ELFCLASS64) {
		rc = parse_crash_elf64_headers();
		if (rc)
			return rc;
	} else if (e_ident[EI_CLASS] == ELFCLASS32) {
		rc = parse_crash_elf32_headers();
		if (rc)
			return rc;
	} else {
		pr_warn("Warning: Core image elf header is not sane\n");
		return -EINVAL;
	}

	/* Determine vmcore size. */
	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
				      &vmcore_list);

	return 0;
}

/* Init function for vmcore module. */
static int __init vmcore_init(void)
{
	int rc = 0;

	/* Allow architectures to allocate ELF header in 2nd kernel */
	rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
	if (rc)
		return rc;
	/*
	 * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
	 * then capture the dump.
	 */
	if (!(is_vmcore_usable()))
		return rc;
	rc = parse_crash_elf_headers();
	if (rc) {
		pr_warn("Kdump: vmcore not initialized\n");
		return rc;
	}
	elfcorehdr_free(elfcorehdr_addr);
	elfcorehdr_addr = ELFCORE_ADDR_ERR;

	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
	if (proc_vmcore)
		proc_vmcore->size = vmcore_size;
	return 0;
}
fs_initcall(vmcore_init);

/* Cleanup function for vmcore module. */
void vmcore_cleanup(void)
{
	struct list_head *pos, *next;

	if (proc_vmcore) {
		proc_remove(proc_vmcore);
		proc_vmcore = NULL;
	}

	/* clear the vmcore list. */
	list_for_each_safe(pos, next, &vmcore_list) {
		struct vmcore *m;

		m = list_entry(pos, struct vmcore, list);
		list_del(&m->list);
		kfree(m);
	}
	free_elfcorebuf();
}