summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/mmu.h
blob: 60f21bb4c27b196d7da820a304771b31b700899f (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_MMU_H
#define __KVM_X86_MMU_H

#include <linux/kvm_host.h>
#include "kvm_cache_regs.h"
#include "cpuid.h"

extern bool __read_mostly enable_mmio_caching;

#define PT_WRITABLE_SHIFT 1
#define PT_USER_SHIFT 2

#define PT_PRESENT_MASK (1ULL << 0)
#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
#define PT_USER_MASK (1ULL << PT_USER_SHIFT)
#define PT_PWT_MASK (1ULL << 3)
#define PT_PCD_MASK (1ULL << 4)
#define PT_ACCESSED_SHIFT 5
#define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
#define PT_DIRTY_SHIFT 6
#define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
#define PT_PAGE_SIZE_SHIFT 7
#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
#define PT_PAT_MASK (1ULL << 7)
#define PT_GLOBAL_MASK (1ULL << 8)
#define PT64_NX_SHIFT 63
#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)

#define PT_PAT_SHIFT 7
#define PT_DIR_PAT_SHIFT 12
#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)

#define PT64_ROOT_5LEVEL 5
#define PT64_ROOT_4LEVEL 4
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3

#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PSE | X86_CR4_PAE | X86_CR4_LA57 | \
			       X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE)

#define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP)
#define KVM_MMU_EFER_ROLE_BITS (EFER_LME | EFER_NX)

static __always_inline u64 rsvd_bits(int s, int e)
{
	BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s);

	if (__builtin_constant_p(e))
		BUILD_BUG_ON(e > 63);
	else
		e &= 63;

	if (e < s)
		return 0;

	return ((2ULL << (e - s)) - 1) << s;
}

/*
 * The number of non-reserved physical address bits irrespective of features
 * that repurpose legal bits, e.g. MKTME.
 */
extern u8 __read_mostly shadow_phys_bits;

static inline gfn_t kvm_mmu_max_gfn(void)
{
	/*
	 * Note that this uses the host MAXPHYADDR, not the guest's.
	 * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR;
	 * assuming KVM is running on bare metal, guest accesses beyond
	 * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit
	 * (either EPT Violation/Misconfig or #NPF), and so KVM will never
	 * install a SPTE for such addresses.  If KVM is running as a VM
	 * itself, on the other hand, it might see a MAXPHYADDR that is less
	 * than hardware's real MAXPHYADDR.  Using the host MAXPHYADDR
	 * disallows such SPTEs entirely and simplifies the TDP MMU.
	 */
	int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52;

	return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1;
}

static inline 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;
}

void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);

void kvm_init_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
			     unsigned long cr4, u64 efer, gpa_t nested_cr3);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
			     int huge_page_level, bool accessed_dirty,
			     gpa_t new_eptp);
bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
				u64 fault_address, char *insn, int insn_len);
void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
					struct kvm_mmu *mmu);

int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu);
void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
			 int bytes);

static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
	if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE))
		return 0;

	return kvm_mmu_load(vcpu);
}

static inline unsigned long kvm_get_pcid(struct kvm_vcpu *vcpu, gpa_t cr3)
{
	BUILD_BUG_ON((X86_CR3_PCID_MASK & PAGE_MASK) != 0);

	return kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)
	       ? cr3 & X86_CR3_PCID_MASK
	       : 0;
}

static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
{
	return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu));
}

static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu)
{
	if (!guest_can_use(vcpu, X86_FEATURE_LAM))
		return 0;

	return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
}

static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
{
	u64 root_hpa = vcpu->arch.mmu->root.hpa;

	if (!VALID_PAGE(root_hpa))
		return;

	static_call(kvm_x86_load_mmu_pgd)(vcpu, root_hpa,
					  vcpu->arch.mmu->root_role.level);
}

static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
						    struct kvm_mmu *mmu)
{
	/*
	 * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e.
	 * @mmu's snapshot of CR0.WP and thus all related paging metadata may
	 * be stale.  Refresh CR0.WP and the metadata on-demand when checking
	 * for permission faults.  Exempt nested MMUs, i.e. MMUs for shadowing
	 * nEPT and nNPT, as CR0.WP is ignored in both cases.  Note, KVM does
	 * need to refresh nested_mmu, a.k.a. the walker used to translate L2
	 * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP.
	 */
	if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu)
		return;

	__kvm_mmu_refresh_passthrough_bits(vcpu, mmu);
}

/*
 * Check if a given access (described through the I/D, W/R and U/S bits of a
 * page fault error code pfec) causes a permission fault with the given PTE
 * access rights (in ACC_* format).
 *
 * Return zero if the access does not fault; return the page fault error code
 * if the access faults.
 */
static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
				  unsigned pte_access, unsigned pte_pkey,
				  u64 access)
{
	/* strip nested paging fault error codes */
	unsigned int pfec = access;
	unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);

	/*
	 * For explicit supervisor accesses, SMAP is disabled if EFLAGS.AC = 1.
	 * For implicit supervisor accesses, SMAP cannot be overridden.
	 *
	 * SMAP works on supervisor accesses only, and not_smap can
	 * be set or not set when user access with neither has any bearing
	 * on the result.
	 *
	 * We put the SMAP checking bit in place of the PFERR_RSVD_MASK bit;
	 * this bit will always be zero in pfec, but it will be one in index
	 * if SMAP checks are being disabled.
	 */
	u64 implicit_access = access & PFERR_IMPLICIT_ACCESS;
	bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC;
	int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1;
	u32 errcode = PFERR_PRESENT_MASK;
	bool fault;

	kvm_mmu_refresh_passthrough_bits(vcpu, mmu);

	fault = (mmu->permissions[index] >> pte_access) & 1;

	WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK));
	if (unlikely(mmu->pkru_mask)) {
		u32 pkru_bits, offset;

		/*
		* PKRU defines 32 bits, there are 16 domains and 2
		* attribute bits per domain in pkru.  pte_pkey is the
		* index of the protection domain, so pte_pkey * 2 is
		* is the index of the first bit for the domain.
		*/
		pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;

		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
		offset = (pfec & ~1) +
			((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));

		pkru_bits &= mmu->pkru_mask >> offset;
		errcode |= -pkru_bits & PFERR_PK_MASK;
		fault |= (pkru_bits != 0);
	}

	return -(u32)fault & errcode;
}

bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma);

static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm)
{
	return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm));
}

void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);

int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);

int kvm_mmu_post_init_vm(struct kvm *kvm);
void kvm_mmu_pre_destroy_vm(struct kvm *kvm);

static inline bool kvm_shadow_root_allocated(struct kvm *kvm)
{
	/*
	 * Read shadow_root_allocated before related pointers. Hence, threads
	 * reading shadow_root_allocated in any lock context are guaranteed to
	 * see the pointers. Pairs with smp_store_release in
	 * mmu_first_shadow_root_alloc.
	 */
	return smp_load_acquire(&kvm->arch.shadow_root_allocated);
}

#ifdef CONFIG_X86_64
extern bool tdp_mmu_enabled;
#else
#define tdp_mmu_enabled false
#endif

static inline bool kvm_memslots_have_rmaps(struct kvm *kvm)
{
	return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm);
}

static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
{
	/* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */
	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
}

static inline unsigned long
__kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, unsigned long npages,
		      int level)
{
	return gfn_to_index(slot->base_gfn + npages - 1,
			    slot->base_gfn, level) + 1;
}

static inline unsigned long
kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, int level)
{
	return __kvm_mmu_slot_lpages(slot, slot->npages, level);
}

static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count)
{
	atomic64_add(count, &kvm->stat.pages[level - 1]);
}

gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access,
			   struct x86_exception *exception);

static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu,
				      struct kvm_mmu *mmu,
				      gpa_t gpa, u64 access,
				      struct x86_exception *exception)
{
	if (mmu != &vcpu->arch.nested_mmu)
		return gpa;
	return translate_nested_gpa(vcpu, gpa, access, exception);
}
#endif