summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu/spte.c
blob: 66d43cec0c31aa51d18cdf5c32c0cad9590daa35 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * Macros and functions to access KVM PTEs (also known as SPTEs)
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2020 Red Hat, Inc. and/or its affiliates.
 */


#include <linux/kvm_host.h>
#include "mmu.h"
#include "mmu_internal.h"
#include "x86.h"
#include "spte.h"

#include <asm/e820/api.h>
#include <asm/vmx.h>

static bool __read_mostly enable_mmio_caching = true;
module_param_named(mmio_caching, enable_mmio_caching, bool, 0444);

u64 __read_mostly shadow_host_writable_mask;
u64 __read_mostly shadow_mmu_writable_mask;
u64 __read_mostly shadow_nx_mask;
u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
u64 __read_mostly shadow_user_mask;
u64 __read_mostly shadow_accessed_mask;
u64 __read_mostly shadow_dirty_mask;
u64 __read_mostly shadow_mmio_value;
u64 __read_mostly shadow_mmio_mask;
u64 __read_mostly shadow_mmio_access_mask;
u64 __read_mostly shadow_present_mask;
u64 __read_mostly shadow_me_mask;
u64 __read_mostly shadow_acc_track_mask;

u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;

u8 __read_mostly shadow_phys_bits;

static u64 generation_mmio_spte_mask(u64 gen)
{
	u64 mask;

	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);

	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
	return mask;
}

u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
{
	u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK;
	u64 spte = generation_mmio_spte_mask(gen);
	u64 gpa = gfn << PAGE_SHIFT;

	WARN_ON_ONCE(!shadow_mmio_value);

	access &= shadow_mmio_access_mask;
	spte |= shadow_mmio_value | access;
	spte |= gpa | shadow_nonpresent_or_rsvd_mask;
	spte |= (gpa & shadow_nonpresent_or_rsvd_mask)
		<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;

	return spte;
}

static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
	if (pfn_valid(pfn))
		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
			/*
			 * Some reserved pages, such as those from NVDIMM
			 * DAX devices, are not for MMIO, and can be mapped
			 * with cached memory type for better performance.
			 * However, the above check misconceives those pages
			 * as MMIO, and results in KVM mapping them with UC
			 * memory type, which would hurt the performance.
			 * Therefore, we check the host memory type in addition
			 * and only treat UC/UC-/WC pages as MMIO.
			 */
			(!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));

	return !e820__mapped_raw_any(pfn_to_hpa(pfn),
				     pfn_to_hpa(pfn + 1) - 1,
				     E820_TYPE_RAM);
}

int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level,
		     gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool speculative,
		     bool can_unsync, bool host_writable, bool ad_disabled,
		     u64 *new_spte)
{
	u64 spte = SPTE_MMU_PRESENT_MASK;
	int ret = 0;

	if (ad_disabled)
		spte |= SPTE_TDP_AD_DISABLED_MASK;
	else if (kvm_vcpu_ad_need_write_protect(vcpu))
		spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK;

	/*
	 * Bits 62:52 of PAE SPTEs are reserved.  WARN if said bits are set
	 * if PAE paging may be employed (shadow paging or any 32-bit KVM).
	 */
	WARN_ON_ONCE((!tdp_enabled || !IS_ENABLED(CONFIG_X86_64)) &&
		     (spte & SPTE_TDP_AD_MASK));

	/*
	 * For the EPT case, shadow_present_mask is 0 if hardware
	 * supports exec-only page table entries.  In that case,
	 * ACC_USER_MASK and shadow_user_mask are used to represent
	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
	 */
	spte |= shadow_present_mask;
	if (!speculative)
		spte |= spte_shadow_accessed_mask(spte);

	if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
	    is_nx_huge_page_enabled()) {
		pte_access &= ~ACC_EXEC_MASK;
	}

	if (pte_access & ACC_EXEC_MASK)
		spte |= shadow_x_mask;
	else
		spte |= shadow_nx_mask;

	if (pte_access & ACC_USER_MASK)
		spte |= shadow_user_mask;

	if (level > PG_LEVEL_4K)
		spte |= PT_PAGE_SIZE_MASK;
	if (tdp_enabled)
		spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn,
			kvm_is_mmio_pfn(pfn));

	if (host_writable)
		spte |= shadow_host_writable_mask;
	else
		pte_access &= ~ACC_WRITE_MASK;

	if (!kvm_is_mmio_pfn(pfn))
		spte |= shadow_me_mask;

	spte |= (u64)pfn << PAGE_SHIFT;

	if (pte_access & ACC_WRITE_MASK) {
		spte |= PT_WRITABLE_MASK | shadow_mmu_writable_mask;

		/*
		 * Optimization: for pte sync, if spte was writable the hash
		 * lookup is unnecessary (and expensive). Write protection
		 * is responsibility of mmu_get_page / kvm_sync_page.
		 * Same reasoning can be applied to dirty page accounting.
		 */
		if (!can_unsync && is_writable_pte(old_spte))
			goto out;

		if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
			pgprintk("%s: found shadow page for %llx, marking ro\n",
				 __func__, gfn);
			ret |= SET_SPTE_WRITE_PROTECTED_PT;
			pte_access &= ~ACC_WRITE_MASK;
			spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
		}
	}

	if (pte_access & ACC_WRITE_MASK)
		spte |= spte_shadow_dirty_mask(spte);

	if (speculative)
		spte = mark_spte_for_access_track(spte);

out:
	WARN_ON(is_mmio_spte(spte));
	*new_spte = spte;
	return ret;
}

u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
{
	u64 spte = SPTE_MMU_PRESENT_MASK;

	spte |= __pa(child_pt) | shadow_present_mask | PT_WRITABLE_MASK |
		shadow_user_mask | shadow_x_mask | shadow_me_mask;

	if (ad_disabled)
		spte |= SPTE_TDP_AD_DISABLED_MASK;
	else
		spte |= shadow_accessed_mask;

	return spte;
}

u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
{
	u64 new_spte;

	new_spte = old_spte & ~PT64_BASE_ADDR_MASK;
	new_spte |= (u64)new_pfn << PAGE_SHIFT;

	new_spte &= ~PT_WRITABLE_MASK;
	new_spte &= ~shadow_host_writable_mask;

	new_spte = mark_spte_for_access_track(new_spte);

	return new_spte;
}

static u8 kvm_get_shadow_phys_bits(void)
{
	/*
	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
	 * in CPU detection code, but the processor treats those reduced bits as
	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
	 * the physical address bits reported by CPUID.
	 */
	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
		return cpuid_eax(0x80000008) & 0xff;

	/*
	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
	 * custom CPUID.  Proceed with whatever the kernel found since these features
	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
	 */
	return boot_cpu_data.x86_phys_bits;
}

u64 mark_spte_for_access_track(u64 spte)
{
	if (spte_ad_enabled(spte))
		return spte & ~shadow_accessed_mask;

	if (is_access_track_spte(spte))
		return spte;

	/*
	 * Making an Access Tracking PTE will result in removal of write access
	 * from the PTE. So, verify that we will be able to restore the write
	 * access in the fast page fault path later on.
	 */
	WARN_ONCE((spte & PT_WRITABLE_MASK) &&
		  !spte_can_locklessly_be_made_writable(spte),
		  "kvm: Writable SPTE is not locklessly dirty-trackable\n");

	WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
			  SHADOW_ACC_TRACK_SAVED_BITS_SHIFT),
		  "kvm: Access Tracking saved bit locations are not zero\n");

	spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
		SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
	spte &= ~shadow_acc_track_mask;

	return spte;
}

void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
{
	BUG_ON((u64)(unsigned)access_mask != access_mask);
	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);

	if (!enable_mmio_caching)
		mmio_value = 0;

	/*
	 * Disable MMIO caching if the MMIO value collides with the bits that
	 * are used to hold the relocated GFN when the L1TF mitigation is
	 * enabled.  This should never fire as there is no known hardware that
	 * can trigger this condition, e.g. SME/SEV CPUs that require a custom
	 * MMIO value are not susceptible to L1TF.
	 */
	if (WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask <<
				  SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)))
		mmio_value = 0;

	/*
	 * The masked MMIO value must obviously match itself and a removed SPTE
	 * must not get a false positive.  Removed SPTEs and MMIO SPTEs should
	 * never collide as MMIO must set some RWX bits, and removed SPTEs must
	 * not set any RWX bits.
	 */
	if (WARN_ON((mmio_value & mmio_mask) != mmio_value) ||
	    WARN_ON(mmio_value && (REMOVED_SPTE & mmio_mask) == mmio_value))
		mmio_value = 0;

	shadow_mmio_value = mmio_value;
	shadow_mmio_mask  = mmio_mask;
	shadow_mmio_access_mask = access_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);

void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
{
	shadow_user_mask	= VMX_EPT_READABLE_MASK;
	shadow_accessed_mask	= has_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull;
	shadow_dirty_mask	= has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
	shadow_nx_mask		= 0ull;
	shadow_x_mask		= VMX_EPT_EXECUTABLE_MASK;
	shadow_present_mask	= has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
	shadow_acc_track_mask	= VMX_EPT_RWX_MASK;
	shadow_me_mask		= 0ull;

	shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
	shadow_mmu_writable_mask  = EPT_SPTE_MMU_WRITABLE;

	/*
	 * EPT Misconfigurations are generated if the value of bits 2:0
	 * of an EPT paging-structure entry is 110b (write/execute).
	 */
	kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE,
				   VMX_EPT_RWX_MASK, 0);
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks);

void kvm_mmu_reset_all_pte_masks(void)
{
	u8 low_phys_bits;
	u64 mask;

	shadow_phys_bits = kvm_get_shadow_phys_bits();

	/*
	 * If the CPU has 46 or less physical address bits, then set an
	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
	 * assumed that the CPU is not vulnerable to L1TF.
	 *
	 * Some Intel CPUs address the L1 cache using more PA bits than are
	 * reported by CPUID. Use the PA width of the L1 cache when possible
	 * to achieve more effective mitigation, e.g. if system RAM overlaps
	 * the most significant bits of legal physical address space.
	 */
	shadow_nonpresent_or_rsvd_mask = 0;
	low_phys_bits = boot_cpu_data.x86_phys_bits;
	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
			  52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) {
		low_phys_bits = boot_cpu_data.x86_cache_bits
			- SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
		shadow_nonpresent_or_rsvd_mask =
			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
	}

	shadow_nonpresent_or_rsvd_lower_gfn_mask =
		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);

	shadow_user_mask	= PT_USER_MASK;
	shadow_accessed_mask	= PT_ACCESSED_MASK;
	shadow_dirty_mask	= PT_DIRTY_MASK;
	shadow_nx_mask		= PT64_NX_MASK;
	shadow_x_mask		= 0;
	shadow_present_mask	= PT_PRESENT_MASK;
	shadow_acc_track_mask	= 0;
	shadow_me_mask		= sme_me_mask;

	shadow_host_writable_mask = DEFAULT_SPTE_HOST_WRITEABLE;
	shadow_mmu_writable_mask  = DEFAULT_SPTE_MMU_WRITEABLE;

	/*
	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
	 * 52-bit physical addresses then there are no reserved PA bits in the
	 * PTEs and so the reserved PA approach must be disabled.
	 */
	if (shadow_phys_bits < 52)
		mask = BIT_ULL(51) | PT_PRESENT_MASK;
	else
		mask = 0;

	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
}