kvm_host.h 20.6 KB
Newer Older
1
/*
2 3 4 5 6 7 8 9 10
 * Kernel-based Virtual Machine driver for Linux
 *
 * This header defines architecture specific interfaces, x86 version
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

H
H. Peter Anvin 已提交
11 12
#ifndef _ASM_X86_KVM_HOST_H
#define _ASM_X86_KVM_HOST_H
13

14 15
#include <linux/types.h>
#include <linux/mm.h>
16
#include <linux/mmu_notifier.h>
17 18 19

#include <linux/kvm.h>
#include <linux/kvm_para.h>
20
#include <linux/kvm_types.h>
21

22
#include <asm/pvclock-abi.h>
23 24
#include <asm/desc.h>

25 26 27 28 29 30
#define KVM_MAX_VCPUS 16
#define KVM_MEMORY_SLOTS 32
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4

#define KVM_PIO_PAGE_OFFSET 1
31
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
32

33 34
#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
35 36
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
				  0xFFFFFF0000000000ULL)
37

38
#define KVM_GUEST_CR0_MASK				   \
39 40
	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
	 | X86_CR0_NW | X86_CR0_CD)
41
#define KVM_VM_CR0_ALWAYS_ON						\
42 43
	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
	 | X86_CR0_MP)
44
#define KVM_GUEST_CR4_MASK						\
45 46 47 48 49 50 51
	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)

#define INVALID_PAGE (~(hpa_t)0)
#define UNMAPPED_GVA (~(gpa_t)0)

M
Marcelo Tosatti 已提交
52 53 54 55 56 57 58
/* shadow tables are PAE even on non-PAE hosts */
#define KVM_HPAGE_SHIFT 21
#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))

#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)

59
#define DE_VECTOR 0
J
Jan Kiszka 已提交
60
#define DB_VECTOR 1
61 62 63
#define BP_VECTOR 3
#define OF_VECTOR 4
#define BR_VECTOR 5
64 65 66 67 68 69 70 71
#define UD_VECTOR 6
#define NM_VECTOR 7
#define DF_VECTOR 8
#define TS_VECTOR 10
#define NP_VECTOR 11
#define SS_VECTOR 12
#define GP_VECTOR 13
#define PF_VECTOR 14
72
#define MF_VECTOR 16
73
#define MC_VECTOR 18
74 75 76 77 78 79

#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03

#define IOPL_SHIFT 12

80 81
#define KVM_ALIAS_SLOTS 4

82 83
#define KVM_PERMILLE_MMU_PAGES 20
#define KVM_MIN_ALLOC_MMU_PAGES 64
84 85
#define KVM_MMU_HASH_SHIFT 10
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
86 87 88
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40
A
Avi Kivity 已提交
89
#define KVM_NR_VAR_MTRR 8
90

91 92 93
extern spinlock_t kvm_lock;
extern struct list_head vm_list;

94 95 96
struct kvm_vcpu;
struct kvm;

97
enum kvm_reg {
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
	VCPU_REGS_RAX = 0,
	VCPU_REGS_RCX = 1,
	VCPU_REGS_RDX = 2,
	VCPU_REGS_RBX = 3,
	VCPU_REGS_RSP = 4,
	VCPU_REGS_RBP = 5,
	VCPU_REGS_RSI = 6,
	VCPU_REGS_RDI = 7,
#ifdef CONFIG_X86_64
	VCPU_REGS_R8 = 8,
	VCPU_REGS_R9 = 9,
	VCPU_REGS_R10 = 10,
	VCPU_REGS_R11 = 11,
	VCPU_REGS_R12 = 12,
	VCPU_REGS_R13 = 13,
	VCPU_REGS_R14 = 14,
	VCPU_REGS_R15 = 15,
#endif
116
	VCPU_REGS_RIP,
117 118 119 120
	NR_VCPU_REGS
};

enum {
121
	VCPU_SREG_ES,
122
	VCPU_SREG_CS,
123
	VCPU_SREG_SS,
124 125 126 127 128 129 130
	VCPU_SREG_DS,
	VCPU_SREG_FS,
	VCPU_SREG_GS,
	VCPU_SREG_TR,
	VCPU_SREG_LDTR,
};

131
#include <asm/kvm_x86_emulate.h>
132

133 134
#define KVM_NR_MEM_OBJS 40

135 136 137 138 139 140
struct kvm_guest_debug {
	int enabled;
	unsigned long bp[4];
	int singlestep;
};

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
/*
 * We don't want allocation failures within the mmu code, so we preallocate
 * enough memory for a single page fault in a cache.
 */
struct kvm_mmu_memory_cache {
	int nobjs;
	void *objects[KVM_NR_MEM_OBJS];
};

#define NR_PTE_CHAIN_ENTRIES 5

struct kvm_pte_chain {
	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
	struct hlist_node link;
};

/*
 * kvm_mmu_page_role, below, is defined as:
 *
 *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
 *   bits 4:7 - page table level for this shadow (1-4)
 *   bits 8:9 - page table quadrant for 2-level guests
 *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
 *   bits 17:19 - common access permissions for all ptes in this shadow page
 */
union kvm_mmu_page_role {
	unsigned word;
	struct {
169 170 171 172 173 174
		unsigned glevels:4;
		unsigned level:4;
		unsigned quadrant:2;
		unsigned pad_for_nice_hex_output:6;
		unsigned metaphysical:1;
		unsigned access:3;
175
		unsigned invalid:1;
176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
	};
};

struct kvm_mmu_page {
	struct list_head link;
	struct hlist_node hash_link;

	/*
	 * The following two entries are used to key the shadow page in the
	 * hash table.
	 */
	gfn_t gfn;
	union kvm_mmu_page_role role;

	u64 *spt;
	/* hold the gfn of each spte inside spt */
	gfn_t *gfns;
	unsigned long slot_bitmap; /* One bit set per slot which has memory
				    * in this shadow page.
				    */
	int multimapped;         /* More than one parent_pte? */
	int root_count;          /* Currently serving as active root */
198 199
	bool unsync;
	bool unsync_children;
200 201 202 203
	union {
		u64 *parent_pte;               /* !multimapped */
		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
	};
204
	DECLARE_BITMAP(unsync_child_bitmap, 512);
205 206
};

207 208 209 210 211 212 213
struct kvm_pv_mmu_op_buffer {
	void *ptr;
	unsigned len;
	unsigned processed;
	char buf[512] __aligned(sizeof(long));
};

214 215 216 217 218 219 220 221 222 223 224 225
/*
 * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
 * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
 * mode.
 */
struct kvm_mmu {
	void (*new_cr3)(struct kvm_vcpu *vcpu);
	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
	void (*free)(struct kvm_vcpu *vcpu);
	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
	void (*prefetch_page)(struct kvm_vcpu *vcpu,
			      struct kvm_mmu_page *page);
226 227
	int (*sync_page)(struct kvm_vcpu *vcpu,
			 struct kvm_mmu_page *sp);
M
Marcelo Tosatti 已提交
228
	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
229 230 231 232 233 234 235
	hpa_t root_hpa;
	int root_level;
	int shadow_root_level;

	u64 *pae_root;
};

236
struct kvm_vcpu_arch {
237 238 239 240
	u64 host_tsc;
	int interrupt_window_open;
	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
241 242 243 244 245 246 247
	/*
	 * rip and regs accesses must go through
	 * kvm_{register,rip}_{read,write} functions.
	 */
	unsigned long regs[NR_VCPU_REGS];
	u32 regs_avail;
	u32 regs_dirty;
248 249 250 251 252 253 254 255 256 257 258 259 260

	unsigned long cr0;
	unsigned long cr2;
	unsigned long cr3;
	unsigned long cr4;
	unsigned long cr8;
	u64 pdptrs[4]; /* pae */
	u64 shadow_efer;
	u64 apic_base;
	struct kvm_lapic *apic;    /* kernel irqchip context */
	int mp_state;
	int sipi_vector;
	u64 ia32_misc_enable_msr;
261
	bool tpr_access_reporting;
262 263

	struct kvm_mmu mmu;
264 265 266
	/* only needed in kvm_pv_mmu_op() path, but it's hot so
	 * put it here to avoid allocation */
	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
267 268 269 270 271 272 273 274 275

	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
	struct kvm_mmu_memory_cache mmu_page_cache;
	struct kvm_mmu_memory_cache mmu_page_header_cache;

	gfn_t last_pt_write_gfn;
	int   last_pt_write_count;
	u64  *last_pte_updated;
276
	gfn_t last_pte_gfn;
277

278
	struct {
279 280
		gfn_t gfn;	/* presumed gfn during guest pte update */
		pfn_t pfn;	/* pfn corresponding to that gfn */
M
Marcelo Tosatti 已提交
281
		int largepage;
282
		unsigned long mmu_seq;
283 284
	} update_pte;

285 286 287 288 289 290 291
	struct i387_fxsave_struct host_fx_image;
	struct i387_fxsave_struct guest_fx_image;

	gva_t mmio_fault_cr2;
	struct kvm_pio_request pio;
	void *pio_data;

292 293 294 295 296 297 298
	struct kvm_queued_exception {
		bool pending;
		bool has_error_code;
		u8 nr;
		u32 error_code;
	} exception;

A
Avi Kivity 已提交
299 300 301 302 303
	struct kvm_queued_interrupt {
		bool pending;
		u8 nr;
	} interrupt;

304 305 306 307 308 309 310 311 312 313 314 315 316
	struct {
		int active;
		u8 save_iopl;
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
		} tr, es, ds, fs, gs;
	} rmode;
	int halt_request; /* real mode on Intel only */

	int cpuid_nent;
317
	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
318 319 320
	/* emulate context */

	struct x86_emulate_ctxt emulate_ctxt;
321 322

	gpa_t time;
323 324
	struct pvclock_vcpu_time_info hv_clock;
	unsigned int hv_clock_tsc_khz;
325 326
	unsigned int time_offset;
	struct page *time_page;
327 328

	bool nmi_pending;
329
	bool nmi_injected;
330
	bool nmi_window_open;
A
Avi Kivity 已提交
331 332

	u64 mtrr[0x100];
333 334
};

335 336 337 338 339 340 341 342 343
struct kvm_mem_alias {
	gfn_t base_gfn;
	unsigned long npages;
	gfn_t target_gfn;
};

struct kvm_arch{
	int naliases;
	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
344 345 346 347 348 349 350 351 352

	unsigned int n_free_mmu_pages;
	unsigned int n_requested_mmu_pages;
	unsigned int n_alloc_mmu_pages;
	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
	/*
	 * Hash table of struct kvm_mmu_page.
	 */
	struct list_head active_mmu_pages;
B
Ben-Ami Yassour 已提交
353
	struct list_head assigned_dev_head;
B
Ben-Ami Yassour 已提交
354
	struct dmar_domain *intel_iommu_domain;
355 356
	struct kvm_pic *vpic;
	struct kvm_ioapic *vioapic;
S
Sheng Yang 已提交
357
	struct kvm_pit *vpit;
A
Avi Kivity 已提交
358
	struct hlist_head irq_ack_notifier_list;
359 360 361 362

	int round_robin_prev_vcpu;
	unsigned int tss_addr;
	struct page *apic_access_page;
363 364

	gpa_t wall_clock;
365 366 367

	struct page *ept_identity_pagetable;
	bool ept_identity_pagetable_done;
368 369 370

	unsigned long irq_sources_bitmap;
	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
371 372
};

373 374 375 376 377 378 379
struct kvm_vm_stat {
	u32 mmu_shadow_zapped;
	u32 mmu_pte_write;
	u32 mmu_pte_updated;
	u32 mmu_pde_zapped;
	u32 mmu_flooded;
	u32 mmu_recycled;
A
Avi Kivity 已提交
380
	u32 mmu_cache_miss;
381
	u32 mmu_unsync;
382
	u32 remote_tlb_flush;
M
Marcelo Tosatti 已提交
383
	u32 lpages;
384 385
};

386 387 388 389 390 391 392 393 394 395 396
struct kvm_vcpu_stat {
	u32 pf_fixed;
	u32 pf_guest;
	u32 tlb_flush;
	u32 invlpg;

	u32 exits;
	u32 io_exits;
	u32 mmio_exits;
	u32 signal_exits;
	u32 irq_window_exits;
397
	u32 nmi_window_exits;
398 399 400
	u32 halt_exits;
	u32 halt_wakeup;
	u32 request_irq_exits;
401
	u32 request_nmi_exits;
402 403 404 405 406 407
	u32 irq_exits;
	u32 host_state_reload;
	u32 efer_reload;
	u32 fpu_reload;
	u32 insn_emulation;
	u32 insn_emulation_fail;
A
Amit Shah 已提交
408
	u32 hypercalls;
409
	u32 irq_injections;
410
	u32 nmi_injections;
411
};
412

413 414 415 416 417
struct descriptor_table {
	u16 limit;
	unsigned long base;
} __attribute__((packed));

418 419 420 421 422 423 424 425
struct kvm_x86_ops {
	int (*cpu_has_kvm_support)(void);          /* __init */
	int (*disabled_by_bios)(void);             /* __init */
	void (*hardware_enable)(void *dummy);      /* __init */
	void (*hardware_disable)(void *dummy);
	void (*check_processor_compatibility)(void *rtn);
	int (*hardware_setup)(void);               /* __init */
	void (*hardware_unsetup)(void);            /* __exit */
426
	bool (*cpu_has_accelerated_tpr)(void);
427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444

	/* Create, but do not attach this VCPU */
	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
	void (*vcpu_free)(struct kvm_vcpu *vcpu);
	int (*vcpu_reset)(struct kvm_vcpu *vcpu);

	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
	void (*vcpu_put)(struct kvm_vcpu *vcpu);

	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
			       struct kvm_debug_guest *dbg);
	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
	void (*get_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
445
	int (*get_cpl)(struct kvm_vcpu *vcpu);
446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
	void (*set_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
	void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
		       int *exception);
461
	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
462 463 464 465 466 467 468 469 470 471 472 473
	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);

	void (*tlb_flush)(struct kvm_vcpu *vcpu);

	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
				unsigned char *hypercall_addr);
	int (*get_irq)(struct kvm_vcpu *vcpu);
	void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
474 475 476
	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
				bool has_error_code, u32 error_code);
	bool (*exception_injected)(struct kvm_vcpu *vcpu);
477 478 479 480 481
	void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
	void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
				       struct kvm_run *run);

	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
482
	int (*get_tdp_level)(void);
483 484
};

485 486
extern struct kvm_x86_ops *kvm_x86_ops;

487 488 489 490 491 492 493
int kvm_mmu_module_init(void);
void kvm_mmu_module_exit(void);

void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
int kvm_mmu_setup(struct kvm_vcpu *vcpu);
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
S
Sheng Yang 已提交
494 495 496
void kvm_mmu_set_base_ptes(u64 base_pte);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
		u64 dirty_mask, u64 nx_mask, u64 x_mask);
497 498 499 500

int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
void kvm_mmu_zap_all(struct kvm *kvm);
501
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
502 503
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);

504 505
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);

506
int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
507
			  const void *val, int bytes);
508 509 510 511
int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
		  gpa_t addr, unsigned long *ret);

extern bool tdp_enabled;
512

513 514 515 516 517 518
enum emulation_result {
	EMULATE_DONE,       /* no further processing */
	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
	EMULATE_FAIL,         /* can't emulate this instruction */
};

519 520
#define EMULTYPE_NO_DECODE	    (1 << 0)
#define EMULTYPE_TRAP_UD	    (1 << 1)
521
int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
522
			unsigned long cr2, u16 error_code, int emulation_type);
523 524 525 526 527 528 529 530 531
void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
		   unsigned long *rflags);

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
		     unsigned long *rflags);
532
void kvm_enable_efer_bits(u64);
533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);

struct x86_emulate_ctxt;

int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
		     int size, unsigned port);
int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
			   int size, unsigned long count, int down,
			    gva_t address, int rep, unsigned port);
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
int emulate_clts(struct kvm_vcpu *vcpu);
int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
		    unsigned long *dest);
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
		    unsigned long value);

552 553 554 555
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
				int type_bits, int seg);

556 557
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);

558
void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
559 560 561
void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
562 563
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
564 565 566 567 568
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);

569 570
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
571 572
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
			   u32 error_code);
573

574 575
void kvm_pic_set_irq(void *opaque, int irq, int level);

576 577
void kvm_inject_nmi(struct kvm_vcpu *vcpu);

578 579 580 581 582 583 584 585 586 587 588 589 590
void fx_init(struct kvm_vcpu *vcpu);

int emulator_read_std(unsigned long addr,
		      void *val,
		      unsigned int bytes,
		      struct kvm_vcpu *vcpu);
int emulator_write_emulated(unsigned long addr,
			    const void *val,
			    unsigned int bytes,
			    struct kvm_vcpu *vcpu);

unsigned long segment_base(u16 selector);

591
void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
592 593 594 595 596 597
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
		       const u8 *new, int bytes);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
598
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
599 600 601 602 603

int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);

int kvm_fix_hypercall(struct kvm_vcpu *vcpu);

604
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
M
Marcelo Tosatti 已提交
605
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
606

607
void kvm_enable_tdp(void);
608
void kvm_disable_tdp(void);
609

610
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
611
int complete_pio(struct kvm_vcpu *vcpu);
612 613 614 615 616 617 618 619

static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
{
	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);

	return (struct kvm_mmu_page *)page_private(page);
}

620
static inline u16 kvm_read_fs(void)
621 622 623 624 625 626
{
	u16 seg;
	asm("mov %%fs, %0" : "=g"(seg));
	return seg;
}

627
static inline u16 kvm_read_gs(void)
628 629 630 631 632 633
{
	u16 seg;
	asm("mov %%gs, %0" : "=g"(seg));
	return seg;
}

634
static inline u16 kvm_read_ldt(void)
635 636 637 638 639 640
{
	u16 ldt;
	asm("sldt %0" : "=g"(ldt));
	return ldt;
}

641
static inline void kvm_load_fs(u16 sel)
642 643 644 645
{
	asm("mov %0, %%fs" : : "rm"(sel));
}

646
static inline void kvm_load_gs(u16 sel)
647 648 649 650
{
	asm("mov %0, %%gs" : : "rm"(sel));
}

651
static inline void kvm_load_ldt(u16 sel)
652 653 654 655
{
	asm("lldt %0" : : "rm"(sel));
}

656
static inline void kvm_get_idt(struct descriptor_table *table)
657 658 659 660
{
	asm("sidt %0" : "=m"(*table));
}

661
static inline void kvm_get_gdt(struct descriptor_table *table)
662 663 664 665
{
	asm("sgdt %0" : "=m"(*table));
}

666
static inline unsigned long kvm_read_tr_base(void)
667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682
{
	u16 tr;
	asm("str %0" : "=g"(tr));
	return segment_base(tr);
}

#ifdef CONFIG_X86_64
static inline unsigned long read_msr(unsigned long msr)
{
	u64 value;

	rdmsrl(msr, value);
	return value;
}
#endif

683
static inline void kvm_fx_save(struct i387_fxsave_struct *image)
684 685 686 687
{
	asm("fxsave (%0)":: "r" (image));
}

688
static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
689 690 691 692
{
	asm("fxrstor (%0)":: "r" (image));
}

693
static inline void kvm_fx_finit(void)
694 695 696 697 698 699 700 701 702
{
	asm("finit");
}

static inline u32 get_rdx_init_val(void)
{
	return 0x600; /* P6 family */
}

703 704 705 706 707
static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
{
	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}

708 709 710 711 712 713 714 715 716
#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
717
#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
718
#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
719 720 721 722 723 724 725

#define MSR_IA32_TIME_STAMP_COUNTER		0x010

#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
#define TSS_REDIRECTION_SIZE (256 / 8)
726 727
#define RMODE_TSS_SIZE							\
	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
728

729 730 731 732 733 734 735
enum {
	TASK_SWITCH_CALL = 0,
	TASK_SWITCH_IRET = 1,
	TASK_SWITCH_JMP = 2,
	TASK_SWITCH_GATE = 3,
};

736 737 738 739 740 741 742 743 744
/*
 * Hardware virtualization extension instructions may fault if a
 * reboot turns off virtualization while processes are running.
 * Trap the fault and ignore the instruction if that happens.
 */
asmlinkage void kvm_handle_fault_on_reboot(void);

#define __kvm_handle_fault_on_reboot(insn) \
	"666: " insn "\n\t" \
745
	".pushsection .fixup, \"ax\" \n" \
746
	"667: \n\t" \
747
	__ASM_SIZE(push) " $666b \n\t"	      \
748 749 750
	"jmp kvm_handle_fault_on_reboot \n\t" \
	".popsection \n\t" \
	".pushsection __ex_table, \"a\" \n\t" \
751
	_ASM_PTR " 666b, 667b \n\t" \
752 753
	".popsection"

754 755 756 757
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);

H
H. Peter Anvin 已提交
758
#endif /* _ASM_X86_KVM_HOST_H */