summaryrefslogtreecommitdiff
path: root/arch/x86/boot/compressed/ident_map_64.c
blob: d4a314cc50d6ee6ecaa7268f59bbb946c71fb916 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * This code is used on x86_64 to create page table identity mappings on
 * demand by building up a new set of page tables (or appending to the
 * existing ones), and then switching over to them when ready.
 *
 * Copyright (C) 2015-2016  Yinghai Lu
 * Copyright (C)      2016  Kees Cook
 */

/*
 * Since we're dealing with identity mappings, physical and virtual
 * addresses are the same, so override these defines which are ultimately
 * used by the headers in misc.h.
 */
#define __pa(x)  ((unsigned long)(x))
#define __va(x)  ((void *)((unsigned long)(x)))

/* No PAGE_TABLE_ISOLATION support needed either: */
#undef CONFIG_PAGE_TABLE_ISOLATION

#include "error.h"
#include "misc.h"

/* These actually do the work of building the kernel identity maps. */
#include <linux/pgtable.h>
#include <asm/cmpxchg.h>
#include <asm/trap_pf.h>
#include <asm/trapnr.h>
#include <asm/init.h>
/* Use the static base for this part of the boot process */
#undef __PAGE_OFFSET
#define __PAGE_OFFSET __PAGE_OFFSET_BASE
#include "../../mm/ident_map.c"

#define _SETUP
#include <asm/setup.h>	/* For COMMAND_LINE_SIZE */
#undef _SETUP

extern unsigned long get_cmd_line_ptr(void);

/* Used by PAGE_KERN* macros: */
pteval_t __default_kernel_pte_mask __read_mostly = ~0;

/* Used to track our page table allocation area. */
struct alloc_pgt_data {
	unsigned char *pgt_buf;
	unsigned long pgt_buf_size;
	unsigned long pgt_buf_offset;
};

/*
 * Allocates space for a page table entry, using struct alloc_pgt_data
 * above. Besides the local callers, this is used as the allocation
 * callback in mapping_info below.
 */
static void *alloc_pgt_page(void *context)
{
	struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
	unsigned char *entry;

	/* Validate there is space available for a new page. */
	if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
		debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
		debug_putaddr(pages->pgt_buf_offset);
		debug_putaddr(pages->pgt_buf_size);
		return NULL;
	}

	entry = pages->pgt_buf + pages->pgt_buf_offset;
	pages->pgt_buf_offset += PAGE_SIZE;

	return entry;
}

/* Used to track our allocated page tables. */
static struct alloc_pgt_data pgt_data;

/* The top level page table entry pointer. */
static unsigned long top_level_pgt;

phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;

/*
 * Mapping information structure passed to kernel_ident_mapping_init().
 * Due to relocation, pointers must be assigned at run time not build time.
 */
static struct x86_mapping_info mapping_info;

/*
 * Adds the specified range to the identity mappings.
 */
void kernel_add_identity_map(unsigned long start, unsigned long end)
{
	int ret;

	/* Align boundary to 2M. */
	start = round_down(start, PMD_SIZE);
	end = round_up(end, PMD_SIZE);
	if (start >= end)
		return;

	/* Build the mapping. */
	ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end);
	if (ret)
		error("Error: kernel_ident_mapping_init() failed\n");
}

/* Locates and clears a region for a new top level page table. */
void initialize_identity_maps(void *rmode)
{
	unsigned long cmdline;
	struct setup_data *sd;

	/* Exclude the encryption mask from __PHYSICAL_MASK */
	physical_mask &= ~sme_me_mask;

	/* Init mapping_info with run-time function/buffer pointers. */
	mapping_info.alloc_pgt_page = alloc_pgt_page;
	mapping_info.context = &pgt_data;
	mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
	mapping_info.kernpg_flag = _KERNPG_TABLE;

	/*
	 * It should be impossible for this not to already be true,
	 * but since calling this a second time would rewind the other
	 * counters, let's just make sure this is reset too.
	 */
	pgt_data.pgt_buf_offset = 0;

	/*
	 * If we came here via startup_32(), cr3 will be _pgtable already
	 * and we must append to the existing area instead of entirely
	 * overwriting it.
	 *
	 * With 5-level paging, we use '_pgtable' to allocate the p4d page table,
	 * the top-level page table is allocated separately.
	 *
	 * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level
	 * cases. On 4-level paging it's equal to 'top_level_pgt'.
	 */
	top_level_pgt = read_cr3_pa();
	if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) {
		pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
		pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
	} else {
		pgt_data.pgt_buf = _pgtable;
		pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
		top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data);
	}

	/*
	 * New page-table is set up - map the kernel image, boot_params and the
	 * command line. The uncompressed kernel requires boot_params and the
	 * command line to be mapped in the identity mapping. Map them
	 * explicitly here in case the compressed kernel does not touch them,
	 * or does not touch all the pages covering them.
	 */
	kernel_add_identity_map((unsigned long)_head, (unsigned long)_end);
	boot_params = rmode;
	kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1));
	cmdline = get_cmd_line_ptr();
	kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);

	/*
	 * Also map the setup_data entries passed via boot_params in case they
	 * need to be accessed by uncompressed kernel via the identity mapping.
	 */
	sd = (struct setup_data *)boot_params->hdr.setup_data;
	while (sd) {
		unsigned long sd_addr = (unsigned long)sd;

		kernel_add_identity_map(sd_addr, sd_addr + sizeof(*sd) + sd->len);
		sd = (struct setup_data *)sd->next;
	}

	sev_prep_identity_maps(top_level_pgt);

	/* Load the new page-table. */
	write_cr3(top_level_pgt);
}

static pte_t *split_large_pmd(struct x86_mapping_info *info,
			      pmd_t *pmdp, unsigned long __address)
{
	unsigned long page_flags;
	unsigned long address;
	pte_t *pte;
	pmd_t pmd;
	int i;

	pte = (pte_t *)info->alloc_pgt_page(info->context);
	if (!pte)
		return NULL;

	address     = __address & PMD_MASK;
	/* No large page - clear PSE flag */
	page_flags  = info->page_flag & ~_PAGE_PSE;

	/* Populate the PTEs */
	for (i = 0; i < PTRS_PER_PMD; i++) {
		set_pte(&pte[i], __pte(address | page_flags));
		address += PAGE_SIZE;
	}

	/*
	 * Ideally we need to clear the large PMD first and do a TLB
	 * flush before we write the new PMD. But the 2M range of the
	 * PMD might contain the code we execute and/or the stack
	 * we are on, so we can't do that. But that should be safe here
	 * because we are going from large to small mappings and we are
	 * also the only user of the page-table, so there is no chance
	 * of a TLB multihit.
	 */
	pmd = __pmd((unsigned long)pte | info->kernpg_flag);
	set_pmd(pmdp, pmd);
	/* Flush TLB to establish the new PMD */
	write_cr3(top_level_pgt);

	return pte + pte_index(__address);
}

static void clflush_page(unsigned long address)
{
	unsigned int flush_size;
	char *cl, *start, *end;

	/*
	 * Hardcode cl-size to 64 - CPUID can't be used here because that might
	 * cause another #VC exception and the GHCB is not ready to use yet.
	 */
	flush_size = 64;
	start      = (char *)(address & PAGE_MASK);
	end        = start + PAGE_SIZE;

	/*
	 * First make sure there are no pending writes on the cache-lines to
	 * flush.
	 */
	asm volatile("mfence" : : : "memory");

	for (cl = start; cl != end; cl += flush_size)
		clflush(cl);
}

static int set_clr_page_flags(struct x86_mapping_info *info,
			      unsigned long address,
			      pteval_t set, pteval_t clr)
{
	pgd_t *pgdp = (pgd_t *)top_level_pgt;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep, pte;

	/*
	 * First make sure there is a PMD mapping for 'address'.
	 * It should already exist, but keep things generic.
	 *
	 * To map the page just read from it and fault it in if there is no
	 * mapping yet. kernel_add_identity_map() can't be called here because
	 * that would unconditionally map the address on PMD level, destroying
	 * any PTE-level mappings that might already exist. Use assembly here
	 * so the access won't be optimized away.
	 */
	asm volatile("mov %[address], %%r9"
		     :: [address] "g" (*(unsigned long *)address)
		     : "r9", "memory");

	/*
	 * The page is mapped at least with PMD size - so skip checks and walk
	 * directly to the PMD.
	 */
	p4dp = p4d_offset(pgdp, address);
	pudp = pud_offset(p4dp, address);
	pmdp = pmd_offset(pudp, address);

	if (pmd_large(*pmdp))
		ptep = split_large_pmd(info, pmdp, address);
	else
		ptep = pte_offset_kernel(pmdp, address);

	if (!ptep)
		return -ENOMEM;

	/*
	 * Changing encryption attributes of a page requires to flush it from
	 * the caches.
	 */
	if ((set | clr) & _PAGE_ENC) {
		clflush_page(address);

		/*
		 * If the encryption attribute is being cleared, change the page state
		 * to shared in the RMP table.
		 */
		if (clr)
			snp_set_page_shared(__pa(address & PAGE_MASK));
	}

	/* Update PTE */
	pte = *ptep;
	pte = pte_set_flags(pte, set);
	pte = pte_clear_flags(pte, clr);
	set_pte(ptep, pte);

	/*
	 * If the encryption attribute is being set, then change the page state to
	 * private in the RMP entry. The page state change must be done after the PTE
	 * is updated.
	 */
	if (set & _PAGE_ENC)
		snp_set_page_private(__pa(address & PAGE_MASK));

	/* Flush TLB after changing encryption attribute */
	write_cr3(top_level_pgt);

	return 0;
}

int set_page_decrypted(unsigned long address)
{
	return set_clr_page_flags(&mapping_info, address, 0, _PAGE_ENC);
}

int set_page_encrypted(unsigned long address)
{
	return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0);
}

int set_page_non_present(unsigned long address)
{
	return set_clr_page_flags(&mapping_info, address, 0, _PAGE_PRESENT);
}

static void do_pf_error(const char *msg, unsigned long error_code,
			unsigned long address, unsigned long ip)
{
	error_putstr(msg);

	error_putstr("\nError Code: ");
	error_puthex(error_code);
	error_putstr("\nCR2: 0x");
	error_puthex(address);
	error_putstr("\nRIP relative to _head: 0x");
	error_puthex(ip - (unsigned long)_head);
	error_putstr("\n");

	error("Stopping.\n");
}

void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
{
	unsigned long address = native_read_cr2();
	unsigned long end;
	bool ghcb_fault;

	ghcb_fault = sev_es_check_ghcb_fault(address);

	address   &= PMD_MASK;
	end        = address + PMD_SIZE;

	/*
	 * Check for unexpected error codes. Unexpected are:
	 *	- Faults on present pages
	 *	- User faults
	 *	- Reserved bits set
	 */
	if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD))
		do_pf_error("Unexpected page-fault:", error_code, address, regs->ip);
	else if (ghcb_fault)
		do_pf_error("Page-fault on GHCB page:", error_code, address, regs->ip);

	/*
	 * Error code is sane - now identity map the 2M region around
	 * the faulting address.
	 */
	kernel_add_identity_map(address, end);
}