1 // SPDX-License-Identifier: GPL-2.0
2 /*
3 * fs/proc/kcore.c kernel ELF core dumper
4 *
5 * Modelled on fs/exec.c:aout_core_dump()
6 * Jeremy Fitzhardinge <jeremy@sw.oz.au>
7 * ELF version written by David Howells <David.Howells@nexor.co.uk>
8 * Modified and incorporated into 2.3.x by Tigran Aivazian <tigran@veritas.com>
9 * Support to dump vmalloc'd areas (ELF only), Tigran Aivazian <tigran@veritas.com>
10 * Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com>
11 */
12
13 #include <linux/crash_core.h>
14 #include <linux/mm.h>
15 #include <linux/proc_fs.h>
16 #include <linux/kcore.h>
17 #include <linux/user.h>
18 #include <linux/capability.h>
19 #include <linux/elf.h>
20 #include <linux/elfcore.h>
21 #include <linux/vmalloc.h>
22 #include <linux/highmem.h>
23 #include <linux/printk.h>
24 #include <linux/memblock.h>
25 #include <linux/init.h>
26 #include <linux/slab.h>
27 #include <linux/uaccess.h>
28 #include <asm/io.h>
29 #include <linux/list.h>
30 #include <linux/ioport.h>
31 #include <linux/memory.h>
32 #include <linux/sched/task.h>
33 #include <linux/security.h>
34 #include <asm/sections.h>
35 #include "internal.h"
36
37 #define CORE_STR "CORE"
38
39 #ifndef ELF_CORE_EFLAGS
40 #define ELF_CORE_EFLAGS 0
41 #endif
42
43 static struct proc_dir_entry *proc_root_kcore;
44
45
46 #ifndef kc_vaddr_to_offset
47 #define kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET)
48 #endif
49 #ifndef kc_offset_to_vaddr
50 #define kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
51 #endif
52
53 static LIST_HEAD(kclist_head);
54 static DECLARE_RWSEM(kclist_lock);
55 static int kcore_need_update = 1;
56
57 /*
58 * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
59 * Same as oldmem_pfn_is_ram in vmcore
60 */
61 static int (*mem_pfn_is_ram)(unsigned long pfn);
62
register_mem_pfn_is_ram(int (* fn)(unsigned long pfn))63 int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn))
64 {
65 if (mem_pfn_is_ram)
66 return -EBUSY;
67 mem_pfn_is_ram = fn;
68 return 0;
69 }
70
pfn_is_ram(unsigned long pfn)71 static int pfn_is_ram(unsigned long pfn)
72 {
73 if (mem_pfn_is_ram)
74 return mem_pfn_is_ram(pfn);
75 else
76 return 1;
77 }
78
79 /* This doesn't grab kclist_lock, so it should only be used at init time. */
kclist_add(struct kcore_list * new,void * addr,size_t size,int type)80 void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
81 int type)
82 {
83 new->addr = (unsigned long)addr;
84 new->size = size;
85 new->type = type;
86
87 list_add_tail(&new->list, &kclist_head);
88 }
89
get_kcore_size(int * nphdr,size_t * phdrs_len,size_t * notes_len,size_t * data_offset)90 static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len,
91 size_t *data_offset)
92 {
93 size_t try, size;
94 struct kcore_list *m;
95
96 *nphdr = 1; /* PT_NOTE */
97 size = 0;
98
99 list_for_each_entry(m, &kclist_head, list) {
100 try = kc_vaddr_to_offset((size_t)m->addr + m->size);
101 if (try > size)
102 size = try;
103 *nphdr = *nphdr + 1;
104 }
105
106 *phdrs_len = *nphdr * sizeof(struct elf_phdr);
107 *notes_len = (4 * sizeof(struct elf_note) +
108 3 * ALIGN(sizeof(CORE_STR), 4) +
109 VMCOREINFO_NOTE_NAME_BYTES +
110 ALIGN(sizeof(struct elf_prstatus), 4) +
111 ALIGN(sizeof(struct elf_prpsinfo), 4) +
112 ALIGN(arch_task_struct_size, 4) +
113 ALIGN(vmcoreinfo_size, 4));
114 *data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len +
115 *notes_len);
116 return *data_offset + size;
117 }
118
119 #ifdef CONFIG_HIGHMEM
120 /*
121 * If no highmem, we can assume [0...max_low_pfn) continuous range of memory
122 * because memory hole is not as big as !HIGHMEM case.
123 * (HIGHMEM is special because part of memory is _invisible_ from the kernel.)
124 */
kcore_ram_list(struct list_head * head)125 static int kcore_ram_list(struct list_head *head)
126 {
127 struct kcore_list *ent;
128
129 ent = kmalloc(sizeof(*ent), GFP_KERNEL);
130 if (!ent)
131 return -ENOMEM;
132 ent->addr = (unsigned long)__va(0);
133 ent->size = max_low_pfn << PAGE_SHIFT;
134 ent->type = KCORE_RAM;
135 list_add(&ent->list, head);
136 return 0;
137 }
138
139 #else /* !CONFIG_HIGHMEM */
140
141 #ifdef CONFIG_SPARSEMEM_VMEMMAP
142 /* calculate vmemmap's address from given system ram pfn and register it */
143 static int
get_sparsemem_vmemmap_info(struct kcore_list * ent,struct list_head * head)144 get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
145 {
146 unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
147 unsigned long nr_pages = ent->size >> PAGE_SHIFT;
148 unsigned long start, end;
149 struct kcore_list *vmm, *tmp;
150
151
152 start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
153 end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
154 end = PAGE_ALIGN(end);
155 /* overlap check (because we have to align page */
156 list_for_each_entry(tmp, head, list) {
157 if (tmp->type != KCORE_VMEMMAP)
158 continue;
159 if (start < tmp->addr + tmp->size)
160 if (end > tmp->addr)
161 end = tmp->addr;
162 }
163 if (start < end) {
164 vmm = kmalloc(sizeof(*vmm), GFP_KERNEL);
165 if (!vmm)
166 return 0;
167 vmm->addr = start;
168 vmm->size = end - start;
169 vmm->type = KCORE_VMEMMAP;
170 list_add_tail(&vmm->list, head);
171 }
172 return 1;
173
174 }
175 #else
176 static int
get_sparsemem_vmemmap_info(struct kcore_list * ent,struct list_head * head)177 get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
178 {
179 return 1;
180 }
181
182 #endif
183
184 static int
kclist_add_private(unsigned long pfn,unsigned long nr_pages,void * arg)185 kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
186 {
187 struct list_head *head = (struct list_head *)arg;
188 struct kcore_list *ent;
189 struct page *p;
190
191 if (!pfn_valid(pfn))
192 return 1;
193
194 p = pfn_to_page(pfn);
195
196 ent = kmalloc(sizeof(*ent), GFP_KERNEL);
197 if (!ent)
198 return -ENOMEM;
199 ent->addr = (unsigned long)page_to_virt(p);
200 ent->size = nr_pages << PAGE_SHIFT;
201
202 if (!virt_addr_valid(ent->addr))
203 goto free_out;
204
205 /* cut not-mapped area. ....from ppc-32 code. */
206 if (ULONG_MAX - ent->addr < ent->size)
207 ent->size = ULONG_MAX - ent->addr;
208
209 /*
210 * We've already checked virt_addr_valid so we know this address
211 * is a valid pointer, therefore we can check against it to determine
212 * if we need to trim
213 */
214 if (VMALLOC_START > ent->addr) {
215 if (VMALLOC_START - ent->addr < ent->size)
216 ent->size = VMALLOC_START - ent->addr;
217 }
218
219 ent->type = KCORE_RAM;
220 list_add_tail(&ent->list, head);
221
222 if (!get_sparsemem_vmemmap_info(ent, head)) {
223 list_del(&ent->list);
224 goto free_out;
225 }
226
227 return 0;
228 free_out:
229 kfree(ent);
230 return 1;
231 }
232
kcore_ram_list(struct list_head * list)233 static int kcore_ram_list(struct list_head *list)
234 {
235 int nid, ret;
236 unsigned long end_pfn;
237
238 /* Not inialized....update now */
239 /* find out "max pfn" */
240 end_pfn = 0;
241 for_each_node_state(nid, N_MEMORY) {
242 unsigned long node_end;
243 node_end = node_end_pfn(nid);
244 if (end_pfn < node_end)
245 end_pfn = node_end;
246 }
247 /* scan 0 to max_pfn */
248 ret = walk_system_ram_range(0, end_pfn, list, kclist_add_private);
249 if (ret)
250 return -ENOMEM;
251 return 0;
252 }
253 #endif /* CONFIG_HIGHMEM */
254
kcore_update_ram(void)255 static int kcore_update_ram(void)
256 {
257 LIST_HEAD(list);
258 LIST_HEAD(garbage);
259 int nphdr;
260 size_t phdrs_len, notes_len, data_offset;
261 struct kcore_list *tmp, *pos;
262 int ret = 0;
263
264 down_write(&kclist_lock);
265 if (!xchg(&kcore_need_update, 0))
266 goto out;
267
268 ret = kcore_ram_list(&list);
269 if (ret) {
270 /* Couldn't get the RAM list, try again next time. */
271 WRITE_ONCE(kcore_need_update, 1);
272 list_splice_tail(&list, &garbage);
273 goto out;
274 }
275
276 list_for_each_entry_safe(pos, tmp, &kclist_head, list) {
277 if (pos->type == KCORE_RAM || pos->type == KCORE_VMEMMAP)
278 list_move(&pos->list, &garbage);
279 }
280 list_splice_tail(&list, &kclist_head);
281
282 proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, ¬es_len,
283 &data_offset);
284
285 out:
286 up_write(&kclist_lock);
287 list_for_each_entry_safe(pos, tmp, &garbage, list) {
288 list_del(&pos->list);
289 kfree(pos);
290 }
291 return ret;
292 }
293
append_kcore_note(char * notes,size_t * i,const char * name,unsigned int type,const void * desc,size_t descsz)294 static void append_kcore_note(char *notes, size_t *i, const char *name,
295 unsigned int type, const void *desc,
296 size_t descsz)
297 {
298 struct elf_note *note = (struct elf_note *)¬es[*i];
299
300 note->n_namesz = strlen(name) + 1;
301 note->n_descsz = descsz;
302 note->n_type = type;
303 *i += sizeof(*note);
304 memcpy(¬es[*i], name, note->n_namesz);
305 *i = ALIGN(*i + note->n_namesz, 4);
306 memcpy(¬es[*i], desc, descsz);
307 *i = ALIGN(*i + descsz, 4);
308 }
309
310 static ssize_t
read_kcore(struct file * file,char __user * buffer,size_t buflen,loff_t * fpos)311 read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
312 {
313 char *buf = file->private_data;
314 size_t phdrs_offset, notes_offset, data_offset;
315 size_t page_offline_frozen = 1;
316 size_t phdrs_len, notes_len;
317 struct kcore_list *m;
318 size_t tsz;
319 int nphdr;
320 unsigned long start;
321 size_t orig_buflen = buflen;
322 int ret = 0;
323
324 down_read(&kclist_lock);
325 /*
326 * Don't race against drivers that set PageOffline() and expect no
327 * further page access.
328 */
329 page_offline_freeze();
330
331 get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset);
332 phdrs_offset = sizeof(struct elfhdr);
333 notes_offset = phdrs_offset + phdrs_len;
334
335 /* ELF file header. */
336 if (buflen && *fpos < sizeof(struct elfhdr)) {
337 struct elfhdr ehdr = {
338 .e_ident = {
339 [EI_MAG0] = ELFMAG0,
340 [EI_MAG1] = ELFMAG1,
341 [EI_MAG2] = ELFMAG2,
342 [EI_MAG3] = ELFMAG3,
343 [EI_CLASS] = ELF_CLASS,
344 [EI_DATA] = ELF_DATA,
345 [EI_VERSION] = EV_CURRENT,
346 [EI_OSABI] = ELF_OSABI,
347 },
348 .e_type = ET_CORE,
349 .e_machine = ELF_ARCH,
350 .e_version = EV_CURRENT,
351 .e_phoff = sizeof(struct elfhdr),
352 .e_flags = ELF_CORE_EFLAGS,
353 .e_ehsize = sizeof(struct elfhdr),
354 .e_phentsize = sizeof(struct elf_phdr),
355 .e_phnum = nphdr,
356 };
357
358 tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
359 if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) {
360 ret = -EFAULT;
361 goto out;
362 }
363
364 buffer += tsz;
365 buflen -= tsz;
366 *fpos += tsz;
367 }
368
369 /* ELF program headers. */
370 if (buflen && *fpos < phdrs_offset + phdrs_len) {
371 struct elf_phdr *phdrs, *phdr;
372
373 phdrs = kzalloc(phdrs_len, GFP_KERNEL);
374 if (!phdrs) {
375 ret = -ENOMEM;
376 goto out;
377 }
378
379 phdrs[0].p_type = PT_NOTE;
380 phdrs[0].p_offset = notes_offset;
381 phdrs[0].p_filesz = notes_len;
382
383 phdr = &phdrs[1];
384 list_for_each_entry(m, &kclist_head, list) {
385 phdr->p_type = PT_LOAD;
386 phdr->p_flags = PF_R | PF_W | PF_X;
387 phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
388 phdr->p_vaddr = (size_t)m->addr;
389 if (m->type == KCORE_RAM)
390 phdr->p_paddr = __pa(m->addr);
391 else if (m->type == KCORE_TEXT)
392 phdr->p_paddr = __pa_symbol(m->addr);
393 else
394 phdr->p_paddr = (elf_addr_t)-1;
395 phdr->p_filesz = phdr->p_memsz = m->size;
396 phdr->p_align = PAGE_SIZE;
397 phdr++;
398 }
399
400 tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
401 if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset,
402 tsz)) {
403 kfree(phdrs);
404 ret = -EFAULT;
405 goto out;
406 }
407 kfree(phdrs);
408
409 buffer += tsz;
410 buflen -= tsz;
411 *fpos += tsz;
412 }
413
414 /* ELF note segment. */
415 if (buflen && *fpos < notes_offset + notes_len) {
416 struct elf_prstatus prstatus = {};
417 struct elf_prpsinfo prpsinfo = {
418 .pr_sname = 'R',
419 .pr_fname = "vmlinux",
420 };
421 char *notes;
422 size_t i = 0;
423
424 strlcpy(prpsinfo.pr_psargs, saved_command_line,
425 sizeof(prpsinfo.pr_psargs));
426
427 notes = kzalloc(notes_len, GFP_KERNEL);
428 if (!notes) {
429 ret = -ENOMEM;
430 goto out;
431 }
432
433 append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
434 sizeof(prstatus));
435 append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
436 sizeof(prpsinfo));
437 append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
438 arch_task_struct_size);
439 /*
440 * vmcoreinfo_size is mostly constant after init time, but it
441 * can be changed by crash_save_vmcoreinfo(). Racing here with a
442 * panic on another CPU before the machine goes down is insanely
443 * unlikely, but it's better to not leave potential buffer
444 * overflows lying around, regardless.
445 */
446 append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
447 vmcoreinfo_data,
448 min(vmcoreinfo_size, notes_len - i));
449
450 tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
451 if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) {
452 kfree(notes);
453 ret = -EFAULT;
454 goto out;
455 }
456 kfree(notes);
457
458 buffer += tsz;
459 buflen -= tsz;
460 *fpos += tsz;
461 }
462
463 /*
464 * Check to see if our file offset matches with any of
465 * the addresses in the elf_phdr on our list.
466 */
467 start = kc_offset_to_vaddr(*fpos - data_offset);
468 if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
469 tsz = buflen;
470
471 m = NULL;
472 while (buflen) {
473 struct page *page;
474 unsigned long pfn;
475
476 /*
477 * If this is the first iteration or the address is not within
478 * the previous entry, search for a matching entry.
479 */
480 if (!m || start < m->addr || start >= m->addr + m->size) {
481 struct kcore_list *iter;
482
483 m = NULL;
484 list_for_each_entry(iter, &kclist_head, list) {
485 if (start >= iter->addr &&
486 start < iter->addr + iter->size) {
487 m = iter;
488 break;
489 }
490 }
491 }
492
493 if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) {
494 page_offline_thaw();
495 cond_resched();
496 page_offline_freeze();
497 }
498
499 if (!m) {
500 if (clear_user(buffer, tsz)) {
501 ret = -EFAULT;
502 goto out;
503 }
504 goto skip;
505 }
506
507 switch (m->type) {
508 case KCORE_VMALLOC:
509 vread(buf, (char *)start, tsz);
510 /* we have to zero-fill user buffer even if no read */
511 if (copy_to_user(buffer, buf, tsz)) {
512 ret = -EFAULT;
513 goto out;
514 }
515 break;
516 case KCORE_USER:
517 /* User page is handled prior to normal kernel page: */
518 if (copy_to_user(buffer, (char *)start, tsz)) {
519 ret = -EFAULT;
520 goto out;
521 }
522 break;
523 case KCORE_RAM:
524 pfn = __pa(start) >> PAGE_SHIFT;
525 page = pfn_to_online_page(pfn);
526
527 /*
528 * Don't read offline sections, logically offline pages
529 * (e.g., inflated in a balloon), hwpoisoned pages,
530 * and explicitly excluded physical ranges.
531 */
532 if (!page || PageOffline(page) ||
533 is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
534 if (clear_user(buffer, tsz)) {
535 ret = -EFAULT;
536 goto out;
537 }
538 break;
539 }
540 fallthrough;
541 case KCORE_VMEMMAP:
542 case KCORE_TEXT:
543 /*
544 * Using bounce buffer to bypass the
545 * hardened user copy kernel text checks.
546 */
547 if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
548 if (clear_user(buffer, tsz)) {
549 ret = -EFAULT;
550 goto out;
551 }
552 } else {
553 if (copy_to_user(buffer, buf, tsz)) {
554 ret = -EFAULT;
555 goto out;
556 }
557 }
558 break;
559 default:
560 pr_warn_once("Unhandled KCORE type: %d\n", m->type);
561 if (clear_user(buffer, tsz)) {
562 ret = -EFAULT;
563 goto out;
564 }
565 }
566 skip:
567 buflen -= tsz;
568 *fpos += tsz;
569 buffer += tsz;
570 start += tsz;
571 tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
572 }
573
574 out:
575 page_offline_thaw();
576 up_read(&kclist_lock);
577 if (ret)
578 return ret;
579 return orig_buflen - buflen;
580 }
581
open_kcore(struct inode * inode,struct file * filp)582 static int open_kcore(struct inode *inode, struct file *filp)
583 {
584 int ret = security_locked_down(LOCKDOWN_KCORE);
585
586 if (!capable(CAP_SYS_RAWIO))
587 return -EPERM;
588
589 if (ret)
590 return ret;
591
592 filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
593 if (!filp->private_data)
594 return -ENOMEM;
595
596 if (kcore_need_update)
597 kcore_update_ram();
598 if (i_size_read(inode) != proc_root_kcore->size) {
599 inode_lock(inode);
600 i_size_write(inode, proc_root_kcore->size);
601 inode_unlock(inode);
602 }
603 return 0;
604 }
605
release_kcore(struct inode * inode,struct file * file)606 static int release_kcore(struct inode *inode, struct file *file)
607 {
608 kfree(file->private_data);
609 return 0;
610 }
611
612 static const struct proc_ops kcore_proc_ops = {
613 .proc_read = read_kcore,
614 .proc_open = open_kcore,
615 .proc_release = release_kcore,
616 .proc_lseek = default_llseek,
617 };
618
619 /* just remember that we have to update kcore */
kcore_callback(struct notifier_block * self,unsigned long action,void * arg)620 static int __meminit kcore_callback(struct notifier_block *self,
621 unsigned long action, void *arg)
622 {
623 switch (action) {
624 case MEM_ONLINE:
625 case MEM_OFFLINE:
626 kcore_need_update = 1;
627 break;
628 }
629 return NOTIFY_OK;
630 }
631
632
633 static struct kcore_list kcore_vmalloc;
634
635 #ifdef CONFIG_ARCH_PROC_KCORE_TEXT
636 static struct kcore_list kcore_text;
637 /*
638 * If defined, special segment is used for mapping kernel text instead of
639 * direct-map area. We need to create special TEXT section.
640 */
proc_kcore_text_init(void)641 static void __init proc_kcore_text_init(void)
642 {
643 kclist_add(&kcore_text, _text, _end - _text, KCORE_TEXT);
644 }
645 #else
proc_kcore_text_init(void)646 static void __init proc_kcore_text_init(void)
647 {
648 }
649 #endif
650
651 #if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
652 /*
653 * MODULES_VADDR has no intersection with VMALLOC_ADDR.
654 */
655 static struct kcore_list kcore_modules;
add_modules_range(void)656 static void __init add_modules_range(void)
657 {
658 if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
659 kclist_add(&kcore_modules, (void *)MODULES_VADDR,
660 MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
661 }
662 }
663 #else
add_modules_range(void)664 static void __init add_modules_range(void)
665 {
666 }
667 #endif
668
proc_kcore_init(void)669 static int __init proc_kcore_init(void)
670 {
671 proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops);
672 if (!proc_root_kcore) {
673 pr_err("couldn't create /proc/kcore\n");
674 return 0; /* Always returns 0. */
675 }
676 /* Store text area if it's special */
677 proc_kcore_text_init();
678 /* Store vmalloc area */
679 kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
680 VMALLOC_END - VMALLOC_START, KCORE_VMALLOC);
681 add_modules_range();
682 /* Store direct-map area from physical memory map */
683 kcore_update_ram();
684 hotplug_memory_notifier(kcore_callback, DEFAULT_CALLBACK_PRI);
685
686 return 0;
687 }
688 fs_initcall(proc_kcore_init);
689