summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/x86.h
blob: a8b71803777baa13060b8051cc2b9aa3ce7287fd (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH_X86_KVM_X86_H
#define ARCH_X86_KVM_X86_H

#include <linux/kvm_host.h>
#include <asm/fpu/xstate.h>
#include <asm/mce.h>
#include <asm/pvclock.h>
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"

struct kvm_caps {
	/* control of guest tsc rate supported? */
	bool has_tsc_control;
	/* maximum supported tsc_khz for guests */
	u32  max_guest_tsc_khz;
	/* number of bits of the fractional part of the TSC scaling ratio */
	u8   tsc_scaling_ratio_frac_bits;
	/* maximum allowed value of TSC scaling ratio */
	u64  max_tsc_scaling_ratio;
	/* 1ull << kvm_caps.tsc_scaling_ratio_frac_bits */
	u64  default_tsc_scaling_ratio;
	/* bus lock detection supported? */
	bool has_bus_lock_exit;
	/* notify VM exit supported? */
	bool has_notify_vmexit;

	u64 supported_mce_cap;
	u64 supported_xcr0;
	u64 supported_xss;
	u64 supported_perf_cap;
};

void kvm_spurious_fault(void);

#define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check)		\
({									\
	bool failed = (consistency_check);				\
	if (failed)							\
		trace_kvm_nested_vmenter_failed(#consistency_check, 0);	\
	failed;								\
})

/*
 * The first...last VMX feature MSRs that are emulated by KVM.  This may or may
 * not cover all known VMX MSRs, as KVM doesn't emulate an MSR until there's an
 * associated feature that KVM supports for nested virtualization.
 */
#define KVM_FIRST_EMULATED_VMX_MSR	MSR_IA32_VMX_BASIC
#define KVM_LAST_EMULATED_VMX_MSR	MSR_IA32_VMX_VMFUNC

#define KVM_DEFAULT_PLE_GAP		128
#define KVM_VMX_DEFAULT_PLE_WINDOW	4096
#define KVM_DEFAULT_PLE_WINDOW_GROW	2
#define KVM_DEFAULT_PLE_WINDOW_SHRINK	0
#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX	UINT_MAX
#define KVM_SVM_DEFAULT_PLE_WINDOW_MAX	USHRT_MAX
#define KVM_SVM_DEFAULT_PLE_WINDOW	3000

static inline unsigned int __grow_ple_window(unsigned int val,
		unsigned int base, unsigned int modifier, unsigned int max)
{
	u64 ret = val;

	if (modifier < 1)
		return base;

	if (modifier < base)
		ret *= modifier;
	else
		ret += modifier;

	return min(ret, (u64)max);
}

static inline unsigned int __shrink_ple_window(unsigned int val,
		unsigned int base, unsigned int modifier, unsigned int min)
{
	if (modifier < 1)
		return base;

	if (modifier < base)
		val /= modifier;
	else
		val -= modifier;

	return max(val, min);
}

#define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL

void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
int kvm_check_nested_events(struct kvm_vcpu *vcpu);

static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.last_vmentry_cpu != -1;
}

static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.exception.pending ||
	       vcpu->arch.exception_vmexit.pending ||
	       kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
}

static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
	vcpu->arch.exception.pending = false;
	vcpu->arch.exception.injected = false;
	vcpu->arch.exception_vmexit.pending = false;
}

static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
	bool soft)
{
	vcpu->arch.interrupt.injected = true;
	vcpu->arch.interrupt.soft = soft;
	vcpu->arch.interrupt.nr = vector;
}

static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
{
	vcpu->arch.interrupt.injected = false;
}

static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.exception.injected || vcpu->arch.interrupt.injected ||
		vcpu->arch.nmi_injected;
}

static inline bool kvm_exception_is_soft(unsigned int nr)
{
	return (nr == BP_VECTOR) || (nr == OF_VECTOR);
}

static inline bool is_protmode(struct kvm_vcpu *vcpu)
{
	return kvm_is_cr0_bit_set(vcpu, X86_CR0_PE);
}

static inline bool is_long_mode(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
	return !!(vcpu->arch.efer & EFER_LMA);
#else
	return false;
#endif
}

static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
{
	int cs_db, cs_l;

	WARN_ON_ONCE(vcpu->arch.guest_state_protected);

	if (!is_long_mode(vcpu))
		return false;
	static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
	return cs_l;
}

static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu)
{
	/*
	 * If running with protected guest state, the CS register is not
	 * accessible. The hypercall register values will have had to been
	 * provided in 64-bit mode, so assume the guest is in 64-bit.
	 */
	return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu);
}

static inline bool x86_exception_has_error_code(unsigned int vector)
{
	static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
			BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
			BIT(PF_VECTOR) | BIT(AC_VECTOR);

	return (1U << vector) & exception_has_error_code;
}

static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
}

static inline bool is_pae(struct kvm_vcpu *vcpu)
{
	return kvm_is_cr4_bit_set(vcpu, X86_CR4_PAE);
}

static inline bool is_pse(struct kvm_vcpu *vcpu)
{
	return kvm_is_cr4_bit_set(vcpu, X86_CR4_PSE);
}

static inline bool is_paging(struct kvm_vcpu *vcpu)
{
	return likely(kvm_is_cr0_bit_set(vcpu, X86_CR0_PG));
}

static inline bool is_pae_paging(struct kvm_vcpu *vcpu)
{
	return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu);
}

static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
{
	return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48;
}

static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
{
	return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
}

static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
					gva_t gva, gfn_t gfn, unsigned access)
{
	u64 gen = kvm_memslots(vcpu->kvm)->generation;

	if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
		return;

	/*
	 * If this is a shadow nested page table, the "GVA" is
	 * actually a nGPA.
	 */
	vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK;
	vcpu->arch.mmio_access = access;
	vcpu->arch.mmio_gfn = gfn;
	vcpu->arch.mmio_gen = gen;
}

static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
}

/*
 * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
 * clear all mmio cache info.
 */
#define MMIO_GVA_ANY (~(gva_t)0)

static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
{
	if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
		return;

	vcpu->arch.mmio_gva = 0;
}

static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
{
	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
	      vcpu->arch.mmio_gva == (gva & PAGE_MASK))
		return true;

	return false;
}

static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
	      vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
		return true;

	return false;
}

static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
{
	unsigned long val = kvm_register_read_raw(vcpu, reg);

	return is_64_bit_mode(vcpu) ? val : (u32)val;
}

static inline void kvm_register_write(struct kvm_vcpu *vcpu,
				       int reg, unsigned long val)
{
	if (!is_64_bit_mode(vcpu))
		val = (u32)val;
	return kvm_register_write_raw(vcpu, reg, val);
}

static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
{
	return !(kvm->arch.disabled_quirks & quirk);
}

void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);

u64 get_kvmclock_ns(struct kvm *kvm);
uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm);
bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp);

int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
	gva_t addr, void *val, unsigned int bytes,
	struct x86_exception *exception);

int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
	gva_t addr, void *val, unsigned int bytes,
	struct x86_exception *exception);

int handle_ud(struct kvm_vcpu *vcpu);

void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu,
				   struct kvm_queued_exception *ex);

void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
					  int page_num);
bool kvm_vector_hashing_enabled(void);
void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code);
int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
				    void *insn, int insn_len);
int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
			    int emulation_type, void *insn, int insn_len);
fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);

extern u64 host_xcr0;
extern u64 host_xss;
extern u64 host_arch_capabilities;

extern struct kvm_caps kvm_caps;

extern bool enable_pmu;

/*
 * Get a filtered version of KVM's supported XCR0 that strips out dynamic
 * features for which the current process doesn't (yet) have permission to use.
 * This is intended to be used only when enumerating support to userspace,
 * e.g. in KVM_GET_SUPPORTED_CPUID and KVM_CAP_XSAVE2, it does NOT need to be
 * used to check/restrict guest behavior as KVM rejects KVM_SET_CPUID{2} if
 * userspace attempts to enable unpermitted features.
 */
static inline u64 kvm_get_filtered_xcr0(void)
{
	u64 permitted_xcr0 = kvm_caps.supported_xcr0;

	BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA);

	if (permitted_xcr0 & XFEATURE_MASK_USER_DYNAMIC) {
		permitted_xcr0 &= xstate_get_guest_group_perm();

		/*
		 * Treat XTILE_CFG as unsupported if the current process isn't
		 * allowed to use XTILE_DATA, as attempting to set XTILE_CFG in
		 * XCR0 without setting XTILE_DATA is architecturally illegal.
		 */
		if (!(permitted_xcr0 & XFEATURE_MASK_XTILE_DATA))
			permitted_xcr0 &= ~XFEATURE_MASK_XTILE_CFG;
	}
	return permitted_xcr0;
}

static inline bool kvm_mpx_supported(void)
{
	return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
		== (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
}

extern unsigned int min_timer_period_us;

extern bool enable_vmware_backdoor;

extern int pi_inject_timer;

extern bool report_ignored_msrs;

extern bool eager_page_split;

static inline void kvm_pr_unimpl_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	if (report_ignored_msrs)
		vcpu_unimpl(vcpu, "Unhandled WRMSR(0x%x) = 0x%llx\n", msr, data);
}

static inline void kvm_pr_unimpl_rdmsr(struct kvm_vcpu *vcpu, u32 msr)
{
	if (report_ignored_msrs)
		vcpu_unimpl(vcpu, "Unhandled RDMSR(0x%x)\n", msr);
}

static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
{
	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
				   vcpu->arch.virtual_tsc_shift);
}

/* Same "calling convention" as do_div:
 * - divide (n << 32) by base
 * - put result in n
 * - return remainder
 */
#define do_shl32_div32(n, base)					\
	({							\
	    u32 __quot, __rem;					\
	    asm("divl %2" : "=a" (__quot), "=d" (__rem)		\
			: "rm" (base), "0" (0), "1" ((u32) n));	\
	    n = __quot;						\
	    __rem;						\
	 })

static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
	return kvm->arch.mwait_in_guest;
}

static inline bool kvm_hlt_in_guest(struct kvm *kvm)
{
	return kvm->arch.hlt_in_guest;
}

static inline bool kvm_pause_in_guest(struct kvm *kvm)
{
	return kvm->arch.pause_in_guest;
}

static inline bool kvm_cstate_in_guest(struct kvm *kvm)
{
	return kvm->arch.cstate_in_guest;
}

static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm)
{
	return kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_ENABLED;
}

static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu,
						 enum kvm_intr_type intr)
{
	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr);
}

static __always_inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
{
	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0);
}

static inline bool kvm_handling_nmi_from_guest(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.handling_intr_from_guest == KVM_HANDLING_NMI;
}

static inline bool kvm_pat_valid(u64 data)
{
	if (data & 0xF8F8F8F8F8F8F8F8ull)
		return false;
	/* 0, 1, 4, 5, 6, 7 are valid values.  */
	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
}

static inline bool kvm_dr7_valid(u64 data)
{
	/* Bits [63:32] are reserved */
	return !(data >> 32);
}
static inline bool kvm_dr6_valid(u64 data)
{
	/* Bits [63:32] are reserved */
	return !(data >> 32);
}

/*
 * Trigger machine check on the host. We assume all the MSRs are already set up
 * by the CPU and that we still run on the same CPU as the MCE occurred on.
 * We pass a fake environment to the machine check handler because we want
 * the guest to be always treated like user space, no matter what context
 * it used internally.
 */
static inline void kvm_machine_check(void)
{
#if defined(CONFIG_X86_MCE)
	struct pt_regs regs = {
		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
		.flags = X86_EFLAGS_IF,
	};

	do_machine_check(&regs);
#endif
}

void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
int kvm_spec_ctrl_test_value(u64 value);
bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
			      struct x86_exception *e);
int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);

/*
 * Internal error codes that are used to indicate that MSR emulation encountered
 * an error that should result in #GP in the guest, unless userspace
 * handles it.
 */
#define  KVM_MSR_RET_INVALID	2	/* in-kernel MSR emulation #GP condition */
#define  KVM_MSR_RET_FILTERED	3	/* #GP due to userspace MSR filter */

#define __cr4_reserved_bits(__cpu_has, __c)             \
({                                                      \
	u64 __reserved_bits = CR4_RESERVED_BITS;        \
                                                        \
	if (!__cpu_has(__c, X86_FEATURE_XSAVE))         \
		__reserved_bits |= X86_CR4_OSXSAVE;     \
	if (!__cpu_has(__c, X86_FEATURE_SMEP))          \
		__reserved_bits |= X86_CR4_SMEP;        \
	if (!__cpu_has(__c, X86_FEATURE_SMAP))          \
		__reserved_bits |= X86_CR4_SMAP;        \
	if (!__cpu_has(__c, X86_FEATURE_FSGSBASE))      \
		__reserved_bits |= X86_CR4_FSGSBASE;    \
	if (!__cpu_has(__c, X86_FEATURE_PKU))           \
		__reserved_bits |= X86_CR4_PKE;         \
	if (!__cpu_has(__c, X86_FEATURE_LA57))          \
		__reserved_bits |= X86_CR4_LA57;        \
	if (!__cpu_has(__c, X86_FEATURE_UMIP))          \
		__reserved_bits |= X86_CR4_UMIP;        \
	if (!__cpu_has(__c, X86_FEATURE_VMX))           \
		__reserved_bits |= X86_CR4_VMXE;        \
	if (!__cpu_has(__c, X86_FEATURE_PCID))          \
		__reserved_bits |= X86_CR4_PCIDE;       \
	if (!__cpu_has(__c, X86_FEATURE_LAM))           \
		__reserved_bits |= X86_CR4_LAM_SUP;     \
	__reserved_bits;                                \
})

int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
			  void *dst);
int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
			 void *dst);
int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
			 unsigned int port, void *data,  unsigned int count,
			 int in);

#endif