summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/machine_kexec_64.c
blob: 0611fd83858e6404da8c9124d15a09a72016b97e (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * handle transition of Linux booting another kernel
 * Copyright (C) 2002-2005 Eric Biederman  <ebiederm@xmission.com>
 */

#define pr_fmt(fmt)	"kexec: " fmt

#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/string.h>
#include <linux/gfp.h>
#include <linux/reboot.h>
#include <linux/numa.h>
#include <linux/ftrace.h>
#include <linux/io.h>
#include <linux/suspend.h>
#include <linux/vmalloc.h>
#include <linux/efi.h>
#include <linux/cc_platform.h>

#include <asm/init.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/io_apic.h>
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/cpu.h>

#ifdef CONFIG_ACPI
/*
 * Used while adding mapping for ACPI tables.
 * Can be reused when other iomem regions need be mapped
 */
struct init_pgtable_data {
	struct x86_mapping_info *info;
	pgd_t *level4p;
};

static int mem_region_callback(struct resource *res, void *arg)
{
	struct init_pgtable_data *data = arg;
	unsigned long mstart, mend;

	mstart = res->start;
	mend = mstart + resource_size(res) - 1;

	return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
}

static int
map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
{
	struct init_pgtable_data data;
	unsigned long flags;
	int ret;

	data.info = info;
	data.level4p = level4p;
	flags = IORESOURCE_MEM | IORESOURCE_BUSY;

	ret = walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1,
				  &data, mem_region_callback);
	if (ret && ret != -EINVAL)
		return ret;

	/* ACPI tables could be located in ACPI Non-volatile Storage region */
	ret = walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1,
				  &data, mem_region_callback);
	if (ret && ret != -EINVAL)
		return ret;

	return 0;
}
#else
static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
#endif

#ifdef CONFIG_KEXEC_FILE
const struct kexec_file_ops * const kexec_file_loaders[] = {
		&kexec_bzImage64_ops,
		NULL
};
#endif

static int
map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
{
#ifdef CONFIG_EFI
	unsigned long mstart, mend;

	if (!efi_enabled(EFI_BOOT))
		return 0;

	mstart = (boot_params.efi_info.efi_systab |
			((u64)boot_params.efi_info.efi_systab_hi<<32));

	if (efi_enabled(EFI_64BIT))
		mend = mstart + sizeof(efi_system_table_64_t);
	else
		mend = mstart + sizeof(efi_system_table_32_t);

	if (!mstart)
		return 0;

	return kernel_ident_mapping_init(info, level4p, mstart, mend);
#endif
	return 0;
}

static void free_transition_pgtable(struct kimage *image)
{
	free_page((unsigned long)image->arch.p4d);
	image->arch.p4d = NULL;
	free_page((unsigned long)image->arch.pud);
	image->arch.pud = NULL;
	free_page((unsigned long)image->arch.pmd);
	image->arch.pmd = NULL;
	free_page((unsigned long)image->arch.pte);
	image->arch.pte = NULL;
}

static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
{
	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
	unsigned long vaddr, paddr;
	int result = -ENOMEM;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	vaddr = (unsigned long)relocate_kernel;
	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
	pgd += pgd_index(vaddr);
	if (!pgd_present(*pgd)) {
		p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
		if (!p4d)
			goto err;
		image->arch.p4d = p4d;
		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
	}
	p4d = p4d_offset(pgd, vaddr);
	if (!p4d_present(*p4d)) {
		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
		if (!pud)
			goto err;
		image->arch.pud = pud;
		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
	}
	pud = pud_offset(p4d, vaddr);
	if (!pud_present(*pud)) {
		pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
		if (!pmd)
			goto err;
		image->arch.pmd = pmd;
		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
	}
	pmd = pmd_offset(pud, vaddr);
	if (!pmd_present(*pmd)) {
		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
		if (!pte)
			goto err;
		image->arch.pte = pte;
		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
	}
	pte = pte_offset_kernel(pmd, vaddr);

	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
		prot = PAGE_KERNEL_EXEC;

	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
	return 0;
err:
	return result;
}

static void *alloc_pgt_page(void *data)
{
	struct kimage *image = (struct kimage *)data;
	struct page *page;
	void *p = NULL;

	page = kimage_alloc_control_pages(image, 0);
	if (page) {
		p = page_address(page);
		clear_page(p);
	}

	return p;
}

static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
	struct x86_mapping_info info = {
		.alloc_pgt_page	= alloc_pgt_page,
		.context	= image,
		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
		.kernpg_flag	= _KERNPG_TABLE_NOENC,
	};
	unsigned long mstart, mend;
	pgd_t *level4p;
	int result;
	int i;

	level4p = (pgd_t *)__va(start_pgtable);
	clear_page(level4p);

	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
		info.page_flag   |= _PAGE_ENC;
		info.kernpg_flag |= _PAGE_ENC;
	}

	if (direct_gbpages)
		info.direct_gbpages = true;

	for (i = 0; i < nr_pfn_mapped; i++) {
		mstart = pfn_mapped[i].start << PAGE_SHIFT;
		mend   = pfn_mapped[i].end << PAGE_SHIFT;

		result = kernel_ident_mapping_init(&info,
						 level4p, mstart, mend);
		if (result)
			return result;
	}

	/*
	 * segments's mem ranges could be outside 0 ~ max_pfn,
	 * for example when jump back to original kernel from kexeced kernel.
	 * or first kernel is booted with user mem map, and second kernel
	 * could be loaded out of that range.
	 */
	for (i = 0; i < image->nr_segments; i++) {
		mstart = image->segment[i].mem;
		mend   = mstart + image->segment[i].memsz;

		result = kernel_ident_mapping_init(&info,
						 level4p, mstart, mend);

		if (result)
			return result;
	}

	/*
	 * Prepare EFI systab and ACPI tables for kexec kernel since they are
	 * not covered by pfn_mapped.
	 */
	result = map_efi_systab(&info, level4p);
	if (result)
		return result;

	result = map_acpi_tables(&info, level4p);
	if (result)
		return result;

	return init_transition_pgtable(image, level4p);
}

static void load_segments(void)
{
	__asm__ __volatile__ (
		"\tmovl %0,%%ds\n"
		"\tmovl %0,%%es\n"
		"\tmovl %0,%%ss\n"
		"\tmovl %0,%%fs\n"
		"\tmovl %0,%%gs\n"
		: : "a" (__KERNEL_DS) : "memory"
		);
}

int machine_kexec_prepare(struct kimage *image)
{
	unsigned long start_pgtable;
	int result;

	/* Calculate the offsets */
	start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;

	/* Setup the identity mapped 64bit page table */
	result = init_pgtable(image, start_pgtable);
	if (result)
		return result;

	return 0;
}

void machine_kexec_cleanup(struct kimage *image)
{
	free_transition_pgtable(image);
}

/*
 * Do not allocate memory (or fail in any way) in machine_kexec().
 * We are past the point of no return, committed to rebooting now.
 */
void machine_kexec(struct kimage *image)
{
	unsigned long page_list[PAGES_NR];
	void *control_page;
	int save_ftrace_enabled;

#ifdef CONFIG_KEXEC_JUMP
	if (image->preserve_context)
		save_processor_state();
#endif

	save_ftrace_enabled = __ftrace_enabled_save();

	/* Interrupts aren't acceptable while we reboot */
	local_irq_disable();
	hw_breakpoint_disable();
	cet_disable();

	if (image->preserve_context) {
#ifdef CONFIG_X86_IO_APIC
		/*
		 * We need to put APICs in legacy mode so that we can
		 * get timer interrupts in second kernel. kexec/kdump
		 * paths already have calls to restore_boot_irq_mode()
		 * in one form or other. kexec jump path also need one.
		 */
		clear_IO_APIC();
		restore_boot_irq_mode();
#endif
	}

	control_page = page_address(image->control_code_page) + PAGE_SIZE;
	__memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);

	page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
	page_list[PA_TABLE_PAGE] =
	  (unsigned long)__pa(page_address(image->control_code_page));

	if (image->type == KEXEC_TYPE_DEFAULT)
		page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
						<< PAGE_SHIFT);

	/*
	 * The segment registers are funny things, they have both a
	 * visible and an invisible part.  Whenever the visible part is
	 * set to a specific selector, the invisible part is loaded
	 * with from a table in memory.  At no other time is the
	 * descriptor table in memory accessed.
	 *
	 * I take advantage of this here by force loading the
	 * segments, before I zap the gdt with an invalid value.
	 */
	load_segments();
	/*
	 * The gdt & idt are now invalid.
	 * If you want to load them you must set up your own idt & gdt.
	 */
	native_idt_invalidate();
	native_gdt_invalidate();

	/* now call it */
	image->start = relocate_kernel((unsigned long)image->head,
				       (unsigned long)page_list,
				       image->start,
				       image->preserve_context,
				       cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT));

#ifdef CONFIG_KEXEC_JUMP
	if (image->preserve_context)
		restore_processor_state();
#endif

	__ftrace_enabled_restore(save_ftrace_enabled);
}

/* arch-dependent functionality related to kexec file-based syscall */

#ifdef CONFIG_KEXEC_FILE
void *arch_kexec_kernel_image_load(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);
}

/*
 * Apply purgatory relocations.
 *
 * @pi:		Purgatory to be relocated.
 * @section:	Section relocations applying to.
 * @relsec:	Section containing RELAs.
 * @symtabsec:	Corresponding symtab.
 *
 * TODO: Some of the code belongs to generic code. Move that in kexec.c.
 */
int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
				     Elf_Shdr *section, const Elf_Shdr *relsec,
				     const Elf_Shdr *symtabsec)
{
	unsigned int i;
	Elf64_Rela *rel;
	Elf64_Sym *sym;
	void *location;
	unsigned long address, sec_base, value;
	const char *strtab, *name, *shstrtab;
	const Elf_Shdr *sechdrs;

	/* String & section header string table */
	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
	strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset;
	shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;

	rel = (void *)pi->ehdr + relsec->sh_offset;

	pr_debug("Applying relocate section %s to %u\n",
		 shstrtab + relsec->sh_name, relsec->sh_info);

	for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) {

		/*
		 * rel[i].r_offset contains byte offset from beginning
		 * of section to the storage unit affected.
		 *
		 * This is location to update. This is temporary buffer
		 * where section is currently loaded. This will finally be
		 * loaded to a different address later, pointed to by
		 * ->sh_addr. kexec takes care of moving it
		 *  (kexec_load_segment()).
		 */
		location = pi->purgatory_buf;
		location += section->sh_offset;
		location += rel[i].r_offset;

		/* Final address of the location */
		address = section->sh_addr + rel[i].r_offset;

		/*
		 * rel[i].r_info contains information about symbol table index
		 * w.r.t which relocation must be made and type of relocation
		 * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get
		 * these respectively.
		 */
		sym = (void *)pi->ehdr + symtabsec->sh_offset;
		sym += ELF64_R_SYM(rel[i].r_info);

		if (sym->st_name)
			name = strtab + sym->st_name;
		else
			name = shstrtab + sechdrs[sym->st_shndx].sh_name;

		pr_debug("Symbol: %s info: %02x shndx: %02x value=%llx size: %llx\n",
			 name, sym->st_info, sym->st_shndx, sym->st_value,
			 sym->st_size);

		if (sym->st_shndx == SHN_UNDEF) {
			pr_err("Undefined symbol: %s\n", name);
			return -ENOEXEC;
		}

		if (sym->st_shndx == SHN_COMMON) {
			pr_err("symbol '%s' in common section\n", name);
			return -ENOEXEC;
		}

		if (sym->st_shndx == SHN_ABS)
			sec_base = 0;
		else if (sym->st_shndx >= pi->ehdr->e_shnum) {
			pr_err("Invalid section %d for symbol %s\n",
			       sym->st_shndx, name);
			return -ENOEXEC;
		} else
			sec_base = pi->sechdrs[sym->st_shndx].sh_addr;

		value = sym->st_value;
		value += sec_base;
		value += rel[i].r_addend;

		switch (ELF64_R_TYPE(rel[i].r_info)) {
		case R_X86_64_NONE:
			break;
		case R_X86_64_64:
			*(u64 *)location = value;
			break;
		case R_X86_64_32:
			*(u32 *)location = value;
			if (value != *(u32 *)location)
				goto overflow;
			break;
		case R_X86_64_32S:
			*(s32 *)location = value;
			if ((s64)value != *(s32 *)location)
				goto overflow;
			break;
		case R_X86_64_PC32:
		case R_X86_64_PLT32:
			value -= (u64)address;
			*(u32 *)location = value;
			break;
		default:
			pr_err("Unknown rela relocation: %llu\n",
			       ELF64_R_TYPE(rel[i].r_info));
			return -ENOEXEC;
		}
	}
	return 0;

overflow:
	pr_err("Overflow in relocation type %d value 0x%lx\n",
	       (int)ELF64_R_TYPE(rel[i].r_info), value);
	return -ENOEXEC;
}

int arch_kimage_file_post_load_cleanup(struct kimage *image)
{
	vfree(image->elf_headers);
	image->elf_headers = NULL;
	image->elf_headers_sz = 0;

	return kexec_image_post_load_cleanup_default(image);
}
#endif /* CONFIG_KEXEC_FILE */

static int
kexec_mark_range(unsigned long start, unsigned long end, bool protect)
{
	struct page *page;
	unsigned int nr_pages;

	/*
	 * For physical range: [start, end]. We must skip the unassigned
	 * crashk resource with zero-valued "end" member.
	 */
	if (!end || start > end)
		return 0;

	page = pfn_to_page(start >> PAGE_SHIFT);
	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
	if (protect)
		return set_pages_ro(page, nr_pages);
	else
		return set_pages_rw(page, nr_pages);
}

static void kexec_mark_crashkres(bool protect)
{
	unsigned long control;

	kexec_mark_range(crashk_low_res.start, crashk_low_res.end, protect);

	/* Don't touch the control code page used in crash_kexec().*/
	control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page));
	/* Control code page is located in the 2nd page. */
	kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect);
	control += KEXEC_CONTROL_PAGE_SIZE;
	kexec_mark_range(control, crashk_res.end, protect);
}

void arch_kexec_protect_crashkres(void)
{
	kexec_mark_crashkres(true);
}

void arch_kexec_unprotect_crashkres(void)
{
	kexec_mark_crashkres(false);
}

/*
 * During a traditional boot under SME, SME will encrypt the kernel,
 * so the SME kexec kernel also needs to be un-encrypted in order to
 * replicate a normal SME boot.
 *
 * During a traditional boot under SEV, the kernel has already been
 * loaded encrypted, so the SEV kexec kernel needs to be encrypted in
 * order to replicate a normal SEV boot.
 */
int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
{
	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
		return 0;

	/*
	 * If host memory encryption is active we need to be sure that kexec
	 * pages are not encrypted because when we boot to the new kernel the
	 * pages won't be accessed encrypted (initially).
	 */
	return set_memory_decrypted((unsigned long)vaddr, pages);
}

void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
{
	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
		return;

	/*
	 * If host memory encryption is active we need to reset the pages back
	 * to being an encrypted mapping before freeing them.
	 */
	set_memory_encrypted((unsigned long)vaddr, pages);
}