summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/svm/svm.h
blob: df3474f4fb022578a29c0d5954048f5f66d0950e (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * AMD SVM support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 */

#ifndef __SVM_SVM_H
#define __SVM_SVM_H

#include <linux/kvm_types.h>
#include <linux/kvm_host.h>

#include <asm/svm.h>

static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
	MSR_FS_BASE,
#endif
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_TSC_AUX,
};

#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)

#define MSRPM_OFFSETS	16
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;

enum {
	VMCB_INTERCEPTS, /* Intercept vectors, TSC offset,
			    pause filter count */
	VMCB_PERM_MAP,   /* IOPM Base and MSRPM Base */
	VMCB_ASID,	 /* ASID */
	VMCB_INTR,	 /* int_ctl, int_vector */
	VMCB_NPT,        /* npt_en, nCR3, gPAT */
	VMCB_CR,	 /* CR0, CR3, CR4, EFER */
	VMCB_DR,         /* DR6, DR7 */
	VMCB_DT,         /* GDT, IDT */
	VMCB_SEG,        /* CS, DS, SS, ES, CPL */
	VMCB_CR2,        /* CR2 only */
	VMCB_LBR,        /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */
	VMCB_AVIC,       /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE,
			  * AVIC PHYSICAL_TABLE pointer,
			  * AVIC LOGICAL_TABLE pointer
			  */
	VMCB_DIRTY_MAX,
};

/* TPR and CR2 are always written before VMRUN */
#define VMCB_ALWAYS_DIRTY_MASK	((1U << VMCB_INTR) | (1U << VMCB_CR2))

struct kvm_sev_info {
	bool active;		/* SEV enabled guest */
	unsigned int asid;	/* ASID used for this guest */
	unsigned int handle;	/* SEV firmware handle */
	int fd;			/* SEV device fd */
	unsigned long pages_locked; /* Number of pages locked */
	struct list_head regions_list;  /* List of registered regions */
};

struct kvm_svm {
	struct kvm kvm;

	/* Struct members for AVIC */
	u32 avic_vm_id;
	struct page *avic_logical_id_table_page;
	struct page *avic_physical_id_table_page;
	struct hlist_node hnode;

	struct kvm_sev_info sev_info;
};

struct kvm_vcpu;

struct nested_state {
	struct vmcb *hsave;
	u64 hsave_msr;
	u64 vm_cr_msr;
	u64 vmcb;

	/* These are the merged vectors */
	u32 *msrpm;

	/* gpa pointers to the real vectors */
	u64 vmcb_msrpm;
	u64 vmcb_iopm;

	/* A VMEXIT is required but not yet emulated */
	bool exit_required;

	/* cache for intercepts of the guest */
	u32 intercept_cr;
	u32 intercept_dr;
	u32 intercept_exceptions;
	u64 intercept;

	/* Nested Paging related state */
	u64 nested_cr3;
};

struct vcpu_svm {
	struct kvm_vcpu vcpu;
	struct vmcb *vmcb;
	unsigned long vmcb_pa;
	struct svm_cpu_data *svm_data;
	uint64_t asid_generation;
	uint64_t sysenter_esp;
	uint64_t sysenter_eip;
	uint64_t tsc_aux;

	u64 msr_decfg;

	u64 next_rip;

	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
	struct {
		u16 fs;
		u16 gs;
		u16 ldt;
		u64 gs_base;
	} host;

	u64 spec_ctrl;
	/*
	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
	 * translated into the appropriate L2_CFG bits on the host to
	 * perform speculative control.
	 */
	u64 virt_spec_ctrl;

	u32 *msrpm;

	ulong nmi_iret_rip;

	struct nested_state nested;

	bool nmi_singlestep;
	u64 nmi_singlestep_guest_rflags;

	unsigned int3_injected;
	unsigned long int3_rip;

	/* cached guest cpuid flags for faster access */
	bool nrips_enabled	: 1;

	u32 ldr_reg;
	u32 dfr_reg;
	struct page *avic_backing_page;
	u64 *avic_physical_id_cache;
	bool avic_is_running;

	/*
	 * Per-vcpu list of struct amd_svm_iommu_ir:
	 * This is used mainly to store interrupt remapping information used
	 * when update the vcpu affinity. This avoids the need to scan for
	 * IRTE and try to match ga_tag in the IOMMU driver.
	 */
	struct list_head ir_list;
	spinlock_t ir_list_lock;

	/* which host CPU was used for running this vcpu */
	unsigned int last_cpu;
};

struct svm_cpu_data {
	int cpu;

	u64 asid_generation;
	u32 max_asid;
	u32 next_asid;
	u32 min_asid;
	struct kvm_ldttss_desc *tss_desc;

	struct page *save_area;
	struct vmcb *current_vmcb;

	/* index = sev_asid, value = vmcb pointer */
	struct vmcb **sev_vmcbs;
};

DECLARE_PER_CPU(struct svm_cpu_data *, svm_data);

void recalc_intercepts(struct vcpu_svm *svm);

static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
{
	return container_of(kvm, struct kvm_svm, kvm);
}

static inline void mark_all_dirty(struct vmcb *vmcb)
{
	vmcb->control.clean = 0;
}

static inline void mark_all_clean(struct vmcb *vmcb)
{
	vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1)
			       & ~VMCB_ALWAYS_DIRTY_MASK;
}

static inline void mark_dirty(struct vmcb *vmcb, int bit)
{
	vmcb->control.clean &= ~(1 << bit);
}

static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
{
	return container_of(vcpu, struct vcpu_svm, vcpu);
}

static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm)
{
	if (is_guest_mode(&svm->vcpu))
		return svm->nested.hsave;
	else
		return svm->vmcb;
}

static inline void set_cr_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_cr |= (1U << bit);

	recalc_intercepts(svm);
}

static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_cr &= ~(1U << bit);

	recalc_intercepts(svm);
}

static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	return vmcb->control.intercept_cr & (1U << bit);
}

static inline void set_dr_intercepts(struct vcpu_svm *svm)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ)
		| (1 << INTERCEPT_DR1_READ)
		| (1 << INTERCEPT_DR2_READ)
		| (1 << INTERCEPT_DR3_READ)
		| (1 << INTERCEPT_DR4_READ)
		| (1 << INTERCEPT_DR5_READ)
		| (1 << INTERCEPT_DR6_READ)
		| (1 << INTERCEPT_DR7_READ)
		| (1 << INTERCEPT_DR0_WRITE)
		| (1 << INTERCEPT_DR1_WRITE)
		| (1 << INTERCEPT_DR2_WRITE)
		| (1 << INTERCEPT_DR3_WRITE)
		| (1 << INTERCEPT_DR4_WRITE)
		| (1 << INTERCEPT_DR5_WRITE)
		| (1 << INTERCEPT_DR6_WRITE)
		| (1 << INTERCEPT_DR7_WRITE);

	recalc_intercepts(svm);
}

static inline void clr_dr_intercepts(struct vcpu_svm *svm)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_dr = 0;

	recalc_intercepts(svm);
}

static inline void set_exception_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_exceptions |= (1U << bit);

	recalc_intercepts(svm);
}

static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept_exceptions &= ~(1U << bit);

	recalc_intercepts(svm);
}

static inline void set_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept |= (1ULL << bit);

	recalc_intercepts(svm);
}

static inline void clr_intercept(struct vcpu_svm *svm, int bit)
{
	struct vmcb *vmcb = get_host_vmcb(svm);

	vmcb->control.intercept &= ~(1ULL << bit);

	recalc_intercepts(svm);
}

static inline bool is_intercept(struct vcpu_svm *svm, int bit)
{
	return (svm->vmcb->control.intercept & (1ULL << bit)) != 0;
}

static inline bool vgif_enabled(struct vcpu_svm *svm)
{
	return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK);
}

static inline void enable_gif(struct vcpu_svm *svm)
{
	if (vgif_enabled(svm))
		svm->vmcb->control.int_ctl |= V_GIF_MASK;
	else
		svm->vcpu.arch.hflags |= HF_GIF_MASK;
}

static inline void disable_gif(struct vcpu_svm *svm)
{
	if (vgif_enabled(svm))
		svm->vmcb->control.int_ctl &= ~V_GIF_MASK;
	else
		svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
}

static inline bool gif_set(struct vcpu_svm *svm)
{
	if (vgif_enabled(svm))
		return !!(svm->vmcb->control.int_ctl & V_GIF_MASK);
	else
		return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
}

/* svm.c */
#define MSR_INVALID			0xffffffffU

u32 svm_msrpm_offset(u32 msr);
void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
void disable_nmi_singlestep(struct vcpu_svm *svm);

/* nested.c */

#define NESTED_EXIT_HOST	0	/* Exit handled on host level */
#define NESTED_EXIT_DONE	1	/* Exit caused nested vmexit  */
#define NESTED_EXIT_CONTINUE	2	/* Further checks needed      */

/* This function returns true if it is save to enable the nmi window */
static inline bool nested_svm_nmi(struct vcpu_svm *svm)
{
	if (!is_guest_mode(&svm->vcpu))
		return true;

	if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI)))
		return true;

	svm->vmcb->control.exit_code = SVM_EXIT_NMI;
	svm->nested.exit_required = true;

	return false;
}

static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu)
{
	return is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK);
}

void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
			  struct vmcb *nested_vmcb, struct kvm_host_map *map);
int nested_svm_vmrun(struct vcpu_svm *svm);
void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
int nested_svm_vmexit(struct vcpu_svm *svm);
int nested_svm_exit_handled(struct vcpu_svm *svm);
int nested_svm_check_permissions(struct vcpu_svm *svm);
int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
			       bool has_error_code, u32 error_code);
int svm_check_nested_events(struct kvm_vcpu *vcpu);
int nested_svm_exit_special(struct vcpu_svm *svm);

/* avic.c */

#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT			31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)

#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK	(0xFFFFFFFFFFULL << 12)
#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK		(1ULL << 62)
#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK		(1ULL << 63)

#define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL

extern int avic;

static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data)
{
	svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK;
	mark_dirty(svm->vmcb, VMCB_AVIC);
}

static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	u64 *entry = svm->avic_physical_id_cache;

	if (!entry)
		return false;

	return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
}

int avic_ga_log_notifier(u32 ga_tag);
void avic_vm_destroy(struct kvm *kvm);
int avic_vm_init(struct kvm *kvm);
void avic_init_vmcb(struct vcpu_svm *svm);
void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate);
int avic_incomplete_ipi_interception(struct vcpu_svm *svm);
int avic_unaccelerated_access_interception(struct vcpu_svm *svm);
int avic_init_vcpu(struct vcpu_svm *svm);
void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void avic_vcpu_put(struct kvm_vcpu *vcpu);
void avic_post_state_restore(struct kvm_vcpu *vcpu);
void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
bool svm_check_apicv_inhibit_reasons(ulong bit);
void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate);
void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr);
int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec);
bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu);
int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
		       uint32_t guest_irq, bool set);
void svm_vcpu_blocking(struct kvm_vcpu *vcpu);
void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);

/* sev.c */

extern unsigned int max_sev_asid;

static inline bool sev_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;

	return sev->active;
#else
	return false;
#endif
}

static inline bool svm_sev_enabled(void)
{
	return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
}

void sev_vm_destroy(struct kvm *kvm);
int svm_mem_enc_op(struct kvm *kvm, void __user *argp);
int svm_register_enc_region(struct kvm *kvm,
			    struct kvm_enc_region *range);
int svm_unregister_enc_region(struct kvm *kvm,
			      struct kvm_enc_region *range);
void pre_sev_run(struct vcpu_svm *svm, int cpu);
int __init sev_hardware_setup(void);
void sev_hardware_teardown(void);

#endif