summaryrefslogtreecommitdiff
path: root/fs/proc/kcore.c
blob: 25b44b303b355606ee417521deb4c63878dd0cfb (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
// SPDX-License-Identifier: GPL-2.0
/*
 *	fs/proc/kcore.c kernel ELF core dumper
 *
 *	Modelled on fs/exec.c:aout_core_dump()
 *	Jeremy Fitzhardinge <jeremy@sw.oz.au>
 *	ELF version written by David Howells <David.Howells@nexor.co.uk>
 *	Modified and incorporated into 2.3.x by Tigran Aivazian <tigran@veritas.com>
 *	Support to dump vmalloc'd areas (ELF only), Tigran Aivazian <tigran@veritas.com>
 *	Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com>
 */

#include <linux/crash_core.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/kcore.h>
#include <linux/user.h>
#include <linux/capability.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/printk.h>
#include <linux/memblock.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <asm/io.h>
#include <linux/list.h>
#include <linux/ioport.h>
#include <linux/memory.h>
#include <linux/sched/task.h>
#include <linux/security.h>
#include <asm/sections.h>
#include "internal.h"

#define CORE_STR "CORE"

#ifndef ELF_CORE_EFLAGS
#define ELF_CORE_EFLAGS	0
#endif

static struct proc_dir_entry *proc_root_kcore;


#ifndef kc_vaddr_to_offset
#define	kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET)
#endif
#ifndef	kc_offset_to_vaddr
#define	kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
#endif

static LIST_HEAD(kclist_head);
static DECLARE_RWSEM(kclist_lock);
static int kcore_need_update = 1;

/*
 * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
 * Same as oldmem_pfn_is_ram in vmcore
 */
static int (*mem_pfn_is_ram)(unsigned long pfn);

int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn))
{
	if (mem_pfn_is_ram)
		return -EBUSY;
	mem_pfn_is_ram = fn;
	return 0;
}

static int pfn_is_ram(unsigned long pfn)
{
	if (mem_pfn_is_ram)
		return mem_pfn_is_ram(pfn);
	else
		return 1;
}

/* This doesn't grab kclist_lock, so it should only be used at init time. */
void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
		       int type)
{
	new->addr = (unsigned long)addr;
	new->size = size;
	new->type = type;

	list_add_tail(&new->list, &kclist_head);
}

static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len,
			     size_t *data_offset)
{
	size_t try, size;
	struct kcore_list *m;

	*nphdr = 1; /* PT_NOTE */
	size = 0;

	list_for_each_entry(m, &kclist_head, list) {
		try = kc_vaddr_to_offset((size_t)m->addr + m->size);
		if (try > size)
			size = try;
		*nphdr = *nphdr + 1;
	}

	*phdrs_len = *nphdr * sizeof(struct elf_phdr);
	*notes_len = (4 * sizeof(struct elf_note) +
		      3 * ALIGN(sizeof(CORE_STR), 4) +
		      VMCOREINFO_NOTE_NAME_BYTES +
		      ALIGN(sizeof(struct elf_prstatus), 4) +
		      ALIGN(sizeof(struct elf_prpsinfo), 4) +
		      ALIGN(arch_task_struct_size, 4) +
		      ALIGN(vmcoreinfo_size, 4));
	*data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len +
				  *notes_len);
	return *data_offset + size;
}

#ifdef CONFIG_HIGHMEM
/*
 * If no highmem, we can assume [0...max_low_pfn) continuous range of memory
 * because memory hole is not as big as !HIGHMEM case.
 * (HIGHMEM is special because part of memory is _invisible_ from the kernel.)
 */
static int kcore_ram_list(struct list_head *head)
{
	struct kcore_list *ent;

	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
	if (!ent)
		return -ENOMEM;
	ent->addr = (unsigned long)__va(0);
	ent->size = max_low_pfn << PAGE_SHIFT;
	ent->type = KCORE_RAM;
	list_add(&ent->list, head);
	return 0;
}

#else /* !CONFIG_HIGHMEM */

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/* calculate vmemmap's address from given system ram pfn and register it */
static int
get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
{
	unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
	unsigned long nr_pages = ent->size >> PAGE_SHIFT;
	unsigned long start, end;
	struct kcore_list *vmm, *tmp;


	start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
	end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
	end = PAGE_ALIGN(end);
	/* overlap check (because we have to align page */
	list_for_each_entry(tmp, head, list) {
		if (tmp->type != KCORE_VMEMMAP)
			continue;
		if (start < tmp->addr + tmp->size)
			if (end > tmp->addr)
				end = tmp->addr;
	}
	if (start < end) {
		vmm = kmalloc(sizeof(*vmm), GFP_KERNEL);
		if (!vmm)
			return 0;
		vmm->addr = start;
		vmm->size = end - start;
		vmm->type = KCORE_VMEMMAP;
		list_add_tail(&vmm->list, head);
	}
	return 1;

}
#else
static int
get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
{
	return 1;
}

#endif

static int
kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
{
	struct list_head *head = (struct list_head *)arg;
	struct kcore_list *ent;
	struct page *p;

	if (!pfn_valid(pfn))
		return 1;

	p = pfn_to_page(pfn);

	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
	if (!ent)
		return -ENOMEM;
	ent->addr = (unsigned long)page_to_virt(p);
	ent->size = nr_pages << PAGE_SHIFT;

	if (!virt_addr_valid(ent->addr))
		goto free_out;

	/* cut not-mapped area. ....from ppc-32 code. */
	if (ULONG_MAX - ent->addr < ent->size)
		ent->size = ULONG_MAX - ent->addr;

	/*
	 * We've already checked virt_addr_valid so we know this address
	 * is a valid pointer, therefore we can check against it to determine
	 * if we need to trim
	 */
	if (VMALLOC_START > ent->addr) {
		if (VMALLOC_START - ent->addr < ent->size)
			ent->size = VMALLOC_START - ent->addr;
	}

	ent->type = KCORE_RAM;
	list_add_tail(&ent->list, head);

	if (!get_sparsemem_vmemmap_info(ent, head)) {
		list_del(&ent->list);
		goto free_out;
	}

	return 0;
free_out:
	kfree(ent);
	return 1;
}

static int kcore_ram_list(struct list_head *list)
{
	int nid, ret;
	unsigned long end_pfn;

	/* Not inialized....update now */
	/* find out "max pfn" */
	end_pfn = 0;
	for_each_node_state(nid, N_MEMORY) {
		unsigned long node_end;
		node_end = node_end_pfn(nid);
		if (end_pfn < node_end)
			end_pfn = node_end;
	}
	/* scan 0 to max_pfn */
	ret = walk_system_ram_range(0, end_pfn, list, kclist_add_private);
	if (ret)
		return -ENOMEM;
	return 0;
}
#endif /* CONFIG_HIGHMEM */

static int kcore_update_ram(void)
{
	LIST_HEAD(list);
	LIST_HEAD(garbage);
	int nphdr;
	size_t phdrs_len, notes_len, data_offset;
	struct kcore_list *tmp, *pos;
	int ret = 0;

	down_write(&kclist_lock);
	if (!xchg(&kcore_need_update, 0))
		goto out;

	ret = kcore_ram_list(&list);
	if (ret) {
		/* Couldn't get the RAM list, try again next time. */
		WRITE_ONCE(kcore_need_update, 1);
		list_splice_tail(&list, &garbage);
		goto out;
	}

	list_for_each_entry_safe(pos, tmp, &kclist_head, list) {
		if (pos->type == KCORE_RAM || pos->type == KCORE_VMEMMAP)
			list_move(&pos->list, &garbage);
	}
	list_splice_tail(&list, &kclist_head);

	proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, &notes_len,
					       &data_offset);

out:
	up_write(&kclist_lock);
	list_for_each_entry_safe(pos, tmp, &garbage, list) {
		list_del(&pos->list);
		kfree(pos);
	}
	return ret;
}

static void append_kcore_note(char *notes, size_t *i, const char *name,
			      unsigned int type, const void *desc,
			      size_t descsz)
{
	struct elf_note *note = (struct elf_note *)&notes[*i];

	note->n_namesz = strlen(name) + 1;
	note->n_descsz = descsz;
	note->n_type = type;
	*i += sizeof(*note);
	memcpy(&notes[*i], name, note->n_namesz);
	*i = ALIGN(*i + note->n_namesz, 4);
	memcpy(&notes[*i], desc, descsz);
	*i = ALIGN(*i + descsz, 4);
}

static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
{
	loff_t *fpos = &iocb->ki_pos;
	size_t phdrs_offset, notes_offset, data_offset;
	size_t page_offline_frozen = 1;
	size_t phdrs_len, notes_len;
	struct kcore_list *m;
	size_t tsz;
	int nphdr;
	unsigned long start;
	size_t buflen = iov_iter_count(iter);
	size_t orig_buflen = buflen;
	int ret = 0;

	down_read(&kclist_lock);
	/*
	 * Don't race against drivers that set PageOffline() and expect no
	 * further page access.
	 */
	page_offline_freeze();

	get_kcore_size(&nphdr, &phdrs_len, &notes_len, &data_offset);
	phdrs_offset = sizeof(struct elfhdr);
	notes_offset = phdrs_offset + phdrs_len;

	/* ELF file header. */
	if (buflen && *fpos < sizeof(struct elfhdr)) {
		struct elfhdr ehdr = {
			.e_ident = {
				[EI_MAG0] = ELFMAG0,
				[EI_MAG1] = ELFMAG1,
				[EI_MAG2] = ELFMAG2,
				[EI_MAG3] = ELFMAG3,
				[EI_CLASS] = ELF_CLASS,
				[EI_DATA] = ELF_DATA,
				[EI_VERSION] = EV_CURRENT,
				[EI_OSABI] = ELF_OSABI,
			},
			.e_type = ET_CORE,
			.e_machine = ELF_ARCH,
			.e_version = EV_CURRENT,
			.e_phoff = sizeof(struct elfhdr),
			.e_flags = ELF_CORE_EFLAGS,
			.e_ehsize = sizeof(struct elfhdr),
			.e_phentsize = sizeof(struct elf_phdr),
			.e_phnum = nphdr,
		};

		tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
		if (copy_to_iter((char *)&ehdr + *fpos, tsz, iter) != tsz) {
			ret = -EFAULT;
			goto out;
		}

		buflen -= tsz;
		*fpos += tsz;
	}

	/* ELF program headers. */
	if (buflen && *fpos < phdrs_offset + phdrs_len) {
		struct elf_phdr *phdrs, *phdr;

		phdrs = kzalloc(phdrs_len, GFP_KERNEL);
		if (!phdrs) {
			ret = -ENOMEM;
			goto out;
		}

		phdrs[0].p_type = PT_NOTE;
		phdrs[0].p_offset = notes_offset;
		phdrs[0].p_filesz = notes_len;

		phdr = &phdrs[1];
		list_for_each_entry(m, &kclist_head, list) {
			phdr->p_type = PT_LOAD;
			phdr->p_flags = PF_R | PF_W | PF_X;
			phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
			phdr->p_vaddr = (size_t)m->addr;
			if (m->type == KCORE_RAM)
				phdr->p_paddr = __pa(m->addr);
			else if (m->type == KCORE_TEXT)
				phdr->p_paddr = __pa_symbol(m->addr);
			else
				phdr->p_paddr = (elf_addr_t)-1;
			phdr->p_filesz = phdr->p_memsz = m->size;
			phdr->p_align = PAGE_SIZE;
			phdr++;
		}

		tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
		if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz,
				 iter) != tsz) {
			kfree(phdrs);
			ret = -EFAULT;
			goto out;
		}
		kfree(phdrs);

		buflen -= tsz;
		*fpos += tsz;
	}

	/* ELF note segment. */
	if (buflen && *fpos < notes_offset + notes_len) {
		struct elf_prstatus prstatus = {};
		struct elf_prpsinfo prpsinfo = {
			.pr_sname = 'R',
			.pr_fname = "vmlinux",
		};
		char *notes;
		size_t i = 0;

		strlcpy(prpsinfo.pr_psargs, saved_command_line,
			sizeof(prpsinfo.pr_psargs));

		notes = kzalloc(notes_len, GFP_KERNEL);
		if (!notes) {
			ret = -ENOMEM;
			goto out;
		}

		append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
				  sizeof(prstatus));
		append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
				  sizeof(prpsinfo));
		append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
				  arch_task_struct_size);
		/*
		 * vmcoreinfo_size is mostly constant after init time, but it
		 * can be changed by crash_save_vmcoreinfo(). Racing here with a
		 * panic on another CPU before the machine goes down is insanely
		 * unlikely, but it's better to not leave potential buffer
		 * overflows lying around, regardless.
		 */
		append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
				  vmcoreinfo_data,
				  min(vmcoreinfo_size, notes_len - i));

		tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
		if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) {
			kfree(notes);
			ret = -EFAULT;
			goto out;
		}
		kfree(notes);

		buflen -= tsz;
		*fpos += tsz;
	}

	/*
	 * Check to see if our file offset matches with any of
	 * the addresses in the elf_phdr on our list.
	 */
	start = kc_offset_to_vaddr(*fpos - data_offset);
	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
		tsz = buflen;

	m = NULL;
	while (buflen) {
		struct page *page;
		unsigned long pfn;

		/*
		 * If this is the first iteration or the address is not within
		 * the previous entry, search for a matching entry.
		 */
		if (!m || start < m->addr || start >= m->addr + m->size) {
			struct kcore_list *iter;

			m = NULL;
			list_for_each_entry(iter, &kclist_head, list) {
				if (start >= iter->addr &&
				    start < iter->addr + iter->size) {
					m = iter;
					break;
				}
			}
		}

		if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) {
			page_offline_thaw();
			cond_resched();
			page_offline_freeze();
		}

		if (!m) {
			if (iov_iter_zero(tsz, iter) != tsz) {
				ret = -EFAULT;
				goto out;
			}
			goto skip;
		}

		switch (m->type) {
		case KCORE_VMALLOC:
		{
			const char *src = (char *)start;
			size_t read = 0, left = tsz;

			/*
			 * vmalloc uses spinlocks, so we optimistically try to
			 * read memory. If this fails, fault pages in and try
			 * again until we are done.
			 */
			while (true) {
				read += vread_iter(iter, src, left);
				if (read == tsz)
					break;

				src += read;
				left -= read;

				if (fault_in_iov_iter_writeable(iter, left)) {
					ret = -EFAULT;
					goto out;
				}
			}
			break;
		}
		case KCORE_USER:
			/* User page is handled prior to normal kernel page: */
			if (copy_to_iter((char *)start, tsz, iter) != tsz) {
				ret = -EFAULT;
				goto out;
			}
			break;
		case KCORE_RAM:
			pfn = __pa(start) >> PAGE_SHIFT;
			page = pfn_to_online_page(pfn);

			/*
			 * Don't read offline sections, logically offline pages
			 * (e.g., inflated in a balloon), hwpoisoned pages,
			 * and explicitly excluded physical ranges.
			 */
			if (!page || PageOffline(page) ||
			    is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
				if (iov_iter_zero(tsz, iter) != tsz) {
					ret = -EFAULT;
					goto out;
				}
				break;
			}
			fallthrough;
		case KCORE_VMEMMAP:
		case KCORE_TEXT:
			/*
			 * We use _copy_to_iter() to bypass usermode hardening
			 * which would otherwise prevent this operation.
			 */
			if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
				ret = -EFAULT;
				goto out;
			}
			break;
		default:
			pr_warn_once("Unhandled KCORE type: %d\n", m->type);
			if (iov_iter_zero(tsz, iter) != tsz) {
				ret = -EFAULT;
				goto out;
			}
		}
skip:
		buflen -= tsz;
		*fpos += tsz;
		start += tsz;
		tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
	}

out:
	page_offline_thaw();
	up_read(&kclist_lock);
	if (ret)
		return ret;
	return orig_buflen - buflen;
}

static int open_kcore(struct inode *inode, struct file *filp)
{
	int ret = security_locked_down(LOCKDOWN_KCORE);

	if (!capable(CAP_SYS_RAWIO))
		return -EPERM;

	if (ret)
		return ret;

	if (kcore_need_update)
		kcore_update_ram();
	if (i_size_read(inode) != proc_root_kcore->size) {
		inode_lock(inode);
		i_size_write(inode, proc_root_kcore->size);
		inode_unlock(inode);
	}
	return 0;
}

static const struct proc_ops kcore_proc_ops = {
	.proc_read_iter	= read_kcore_iter,
	.proc_open	= open_kcore,
	.proc_lseek	= default_llseek,
};

/* just remember that we have to update kcore */
static int __meminit kcore_callback(struct notifier_block *self,
				    unsigned long action, void *arg)
{
	switch (action) {
	case MEM_ONLINE:
	case MEM_OFFLINE:
		kcore_need_update = 1;
		break;
	}
	return NOTIFY_OK;
}


static struct kcore_list kcore_vmalloc;

#ifdef CONFIG_ARCH_PROC_KCORE_TEXT
static struct kcore_list kcore_text;
/*
 * If defined, special segment is used for mapping kernel text instead of
 * direct-map area. We need to create special TEXT section.
 */
static void __init proc_kcore_text_init(void)
{
	kclist_add(&kcore_text, _text, _end - _text, KCORE_TEXT);
}
#else
static void __init proc_kcore_text_init(void)
{
}
#endif

#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
/*
 * MODULES_VADDR has no intersection with VMALLOC_ADDR.
 */
static struct kcore_list kcore_modules;
static void __init add_modules_range(void)
{
	if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
		kclist_add(&kcore_modules, (void *)MODULES_VADDR,
			MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
	}
}
#else
static void __init add_modules_range(void)
{
}
#endif

static int __init proc_kcore_init(void)
{
	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops);
	if (!proc_root_kcore) {
		pr_err("couldn't create /proc/kcore\n");
		return 0; /* Always returns 0. */
	}
	/* Store text area if it's special */
	proc_kcore_text_init();
	/* Store vmalloc area */
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
		VMALLOC_END - VMALLOC_START, KCORE_VMALLOC);
	add_modules_range();
	/* Store direct-map area from physical memory map */
	kcore_update_ram();
	hotplug_memory_notifier(kcore_callback, DEFAULT_CALLBACK_PRI);

	return 0;
}
fs_initcall(proc_kcore_init);