summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/pti.c
blob: bce8aea656062197ac0649e7a204d0c5cd0a5e29 (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
/*
 * Copyright(c) 2017 Intel Corporation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * This code is based in part on work published here:
 *
 *	https://github.com/IAIK/KAISER
 *
 * The original work was written by and and signed off by for the Linux
 * kernel by:
 *
 *   Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
 *   Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at>
 *   Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
 *   Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
 *
 * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com>
 * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and
 *		       Andy Lutomirsky <luto@amacapital.net>
 */
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/uaccess.h>

#include <asm/cpufeature.h>
#include <asm/hypervisor.h>
#include <asm/vsyscall.h>
#include <asm/cmdline.h>
#include <asm/pti.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/desc.h>

#undef pr_fmt
#define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt

/* Backporting helper */
#ifndef __GFP_NOTRACK
#define __GFP_NOTRACK	0
#endif

static void __init pti_print_if_insecure(const char *reason)
{
	if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
		pr_info("%s\n", reason);
}

static void __init pti_print_if_secure(const char *reason)
{
	if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
		pr_info("%s\n", reason);
}

void __init pti_check_boottime_disable(void)
{
	char arg[5];
	int ret;

	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
		pti_print_if_insecure("disabled on XEN PV.");
		return;
	}

	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
	if (ret > 0)  {
		if (ret == 3 && !strncmp(arg, "off", 3)) {
			pti_print_if_insecure("disabled on command line.");
			return;
		}
		if (ret == 2 && !strncmp(arg, "on", 2)) {
			pti_print_if_secure("force enabled on command line.");
			goto enable;
		}
		if (ret == 4 && !strncmp(arg, "auto", 4))
			goto autosel;
	}

	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
		pti_print_if_insecure("disabled on command line.");
		return;
	}

autosel:
	if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
		return;
enable:
	setup_force_cpu_cap(X86_FEATURE_PTI);
}

pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
{
	/*
	 * Changes to the high (kernel) portion of the kernelmode page
	 * tables are not automatically propagated to the usermode tables.
	 *
	 * Users should keep in mind that, unlike the kernelmode tables,
	 * there is no vmalloc_fault equivalent for the usermode tables.
	 * Top-level entries added to init_mm's usermode pgd after boot
	 * will not be automatically propagated to other mms.
	 */
	if (!pgdp_maps_userspace(pgdp))
		return pgd;

	/*
	 * The user page tables get the full PGD, accessible from
	 * userspace:
	 */
	kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;

	/*
	 * If this is normal user memory, make it NX in the kernel
	 * pagetables so that, if we somehow screw up and return to
	 * usermode with the kernel CR3 loaded, we'll get a page fault
	 * instead of allowing user code to execute with the wrong CR3.
	 *
	 * As exceptions, we don't set NX if:
	 *  - _PAGE_USER is not set.  This could be an executable
	 *     EFI runtime mapping or something similar, and the kernel
	 *     may execute from it
	 *  - we don't have NX support
	 *  - we're clearing the PGD (i.e. the new pgd is not present).
	 */
	if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
	    (__supported_pte_mask & _PAGE_NX))
		pgd.pgd |= _PAGE_NX;

	/* return the copy of the PGD we want the kernel to use: */
	return pgd;
}

/*
 * Walk the user copy of the page tables (optionally) trying to allocate
 * page table pages on the way down.
 *
 * Returns a pointer to a P4D on success, or NULL on failure.
 */
static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
{
	pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);

	if (address < PAGE_OFFSET) {
		WARN_ONCE(1, "attempt to walk user address\n");
		return NULL;
	}

	if (pgd_none(*pgd)) {
		unsigned long new_p4d_page = __get_free_page(gfp);
		if (!new_p4d_page)
			return NULL;

		if (pgd_none(*pgd)) {
			set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
			new_p4d_page = 0;
		}
		if (new_p4d_page)
			free_page(new_p4d_page);
	}
	BUILD_BUG_ON(pgd_large(*pgd) != 0);

	return p4d_offset(pgd, address);
}

/*
 * Walk the user copy of the page tables (optionally) trying to allocate
 * page table pages on the way down.
 *
 * Returns a pointer to a PMD on success, or NULL on failure.
 */
static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
{
	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
	pud_t *pud;

	BUILD_BUG_ON(p4d_large(*p4d) != 0);
	if (p4d_none(*p4d)) {
		unsigned long new_pud_page = __get_free_page(gfp);
		if (!new_pud_page)
			return NULL;

		if (p4d_none(*p4d)) {
			set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
			new_pud_page = 0;
		}
		if (new_pud_page)
			free_page(new_pud_page);
	}

	pud = pud_offset(p4d, address);
	/* The user page tables do not use large mappings: */
	if (pud_large(*pud)) {
		WARN_ON(1);
		return NULL;
	}
	if (pud_none(*pud)) {
		unsigned long new_pmd_page = __get_free_page(gfp);
		if (!new_pmd_page)
			return NULL;

		if (pud_none(*pud)) {
			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
			new_pmd_page = 0;
		}
		if (new_pmd_page)
			free_page(new_pmd_page);
	}

	return pmd_offset(pud, address);
}

#ifdef CONFIG_X86_VSYSCALL_EMULATION
/*
 * Walk the shadow copy of the page tables (optionally) trying to allocate
 * page table pages on the way down.  Does not support large pages.
 *
 * Note: this is only used when mapping *new* kernel data into the
 * user/shadow page tables.  It is never used for userspace data.
 *
 * Returns a pointer to a PTE on success, or NULL on failure.
 */
static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
{
	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
	pte_t *pte;

	/* We can't do anything sensible if we hit a large mapping. */
	if (pmd_large(*pmd)) {
		WARN_ON(1);
		return NULL;
	}

	if (pmd_none(*pmd)) {
		unsigned long new_pte_page = __get_free_page(gfp);
		if (!new_pte_page)
			return NULL;

		if (pmd_none(*pmd)) {
			set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
			new_pte_page = 0;
		}
		if (new_pte_page)
			free_page(new_pte_page);
	}

	pte = pte_offset_kernel(pmd, address);
	if (pte_flags(*pte) & _PAGE_USER) {
		WARN_ONCE(1, "attempt to walk to user pte\n");
		return NULL;
	}
	return pte;
}

static void __init pti_setup_vsyscall(void)
{
	pte_t *pte, *target_pte;
	unsigned int level;

	pte = lookup_address(VSYSCALL_ADDR, &level);
	if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
		return;

	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
	if (WARN_ON(!target_pte))
		return;

	*target_pte = *pte;
	set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
}
#else
static void __init pti_setup_vsyscall(void) { }
#endif

static void __init
pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
{
	unsigned long addr;

	/*
	 * Clone the populated PMDs which cover start to end. These PMD areas
	 * can have holes.
	 */
	for (addr = start; addr < end; addr += PMD_SIZE) {
		pmd_t *pmd, *target_pmd;
		pgd_t *pgd;
		p4d_t *p4d;
		pud_t *pud;

		pgd = pgd_offset_k(addr);
		if (WARN_ON(pgd_none(*pgd)))
			return;
		p4d = p4d_offset(pgd, addr);
		if (WARN_ON(p4d_none(*p4d)))
			return;
		pud = pud_offset(p4d, addr);
		if (pud_none(*pud))
			continue;
		pmd = pmd_offset(pud, addr);
		if (pmd_none(*pmd))
			continue;

		target_pmd = pti_user_pagetable_walk_pmd(addr);
		if (WARN_ON(!target_pmd))
			return;

		/*
		 * Copy the PMD.  That is, the kernelmode and usermode
		 * tables will share the last-level page tables of this
		 * address range
		 */
		*target_pmd = pmd_clear_flags(*pmd, clear);
	}
}

/*
 * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
 * next-level entry on 5-level systems.
 */
static void __init pti_clone_p4d(unsigned long addr)
{
	p4d_t *kernel_p4d, *user_p4d;
	pgd_t *kernel_pgd;

	user_p4d = pti_user_pagetable_walk_p4d(addr);
	kernel_pgd = pgd_offset_k(addr);
	kernel_p4d = p4d_offset(kernel_pgd, addr);
	*user_p4d = *kernel_p4d;
}

/*
 * Clone the CPU_ENTRY_AREA into the user space visible page table.
 */
static void __init pti_clone_user_shared(void)
{
	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
}

/*
 * Clone the ESPFIX P4D into the user space visinble page table
 */
static void __init pti_setup_espfix64(void)
{
#ifdef CONFIG_X86_ESPFIX64
	pti_clone_p4d(ESPFIX_BASE_ADDR);
#endif
}

/*
 * Clone the populated PMDs of the entry and irqentry text and force it RO.
 */
static void __init pti_clone_entry_text(void)
{
	pti_clone_pmds((unsigned long) __entry_text_start,
			(unsigned long) __irqentry_text_end, _PAGE_RW);
}

/*
 * Initialize kernel page table isolation
 */
void __init pti_init(void)
{
	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	pr_info("enabled\n");

	pti_clone_user_shared();
	pti_clone_entry_text();
	pti_setup_espfix64();
	pti_setup_vsyscall();
}