vmx.c 226 KB
Newer Older
Avi Kivity's avatar
Avi Kivity committed
1
2
3
4
5
6
7
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
8
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
Avi Kivity's avatar
Avi Kivity committed
9
10
11
12
13
14
15
16
17
18
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

19
#include "irq.h"
20
#include "mmu.h"
Avi Kivity's avatar
Avi Kivity committed
21
#include "cpuid.h"
Avi Kivity's avatar
Avi Kivity committed
22

23
#include <linux/kvm_host.h>
Avi Kivity's avatar
Avi Kivity committed
24
#include <linux/module.h>
25
#include <linux/kernel.h>
Avi Kivity's avatar
Avi Kivity committed
26
27
#include <linux/mm.h>
#include <linux/highmem.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
28
#include <linux/sched.h>
29
#include <linux/moduleparam.h>
30
#include <linux/mod_devicetable.h>
31
#include <linux/ftrace_event.h>
32
#include <linux/slab.h>
33
#include <linux/tboot.h>
34
#include "kvm_cache_regs.h"
35
#include "x86.h"
Avi Kivity's avatar
Avi Kivity committed
36

Avi Kivity's avatar
Avi Kivity committed
37
#include <asm/io.h>
38
#include <asm/desc.h>
39
#include <asm/vmx.h>
40
#include <asm/virtext.h>
41
#include <asm/mce.h>
42
43
#include <asm/i387.h>
#include <asm/xcr.h>
44
#include <asm/perf_event.h>
45
#include <asm/kexec.h>
Avi Kivity's avatar
Avi Kivity committed
46

47
48
#include "trace.h"

49
#define __ex(x) __kvm_handle_fault_on_reboot(x)
50
51
#define __ex_clear(x, reg) \
	____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)
52

Avi Kivity's avatar
Avi Kivity committed
53
54
55
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

56
57
58
59
60
61
static const struct x86_cpu_id vmx_cpu_id[] = {
	X86_FEATURE_MATCH(X86_FEATURE_VMX),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);

62
static bool __read_mostly enable_vpid = 1;
63
module_param_named(vpid, enable_vpid, bool, 0444);
64

65
static bool __read_mostly flexpriority_enabled = 1;
66
module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
67

68
static bool __read_mostly enable_ept = 1;
69
module_param_named(ept, enable_ept, bool, S_IRUGO);
Sheng Yang's avatar
Sheng Yang committed
70

71
static bool __read_mostly enable_unrestricted_guest = 1;
72
73
74
module_param_named(unrestricted_guest,
			enable_unrestricted_guest, bool, S_IRUGO);

75
76
77
static bool __read_mostly enable_ept_ad_bits = 1;
module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO);

78
static bool __read_mostly emulate_invalid_guest_state = true;
79
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
80

81
static bool __read_mostly vmm_exclusive = 1;
82
83
module_param(vmm_exclusive, bool, S_IRUGO);

84
static bool __read_mostly fasteoi = 1;
85
86
module_param(fasteoi, bool, S_IRUGO);

87
static bool __read_mostly enable_apicv = 1;
88
module_param(enable_apicv, bool, S_IRUGO);
89

90
91
92
93
94
/*
 * If nested=1, nested virtualization is supported, i.e., guests may use
 * VMX and be a hypervisor for its own guests. If nested=0, guests may not
 * use VMX instructions.
 */
95
static bool __read_mostly nested = 0;
96
97
module_param(nested, bool, S_IRUGO);

98
99
#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
100
101
#define KVM_VM_CR0_ALWAYS_ON						\
	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
102
103
104
105
#define KVM_CR4_GUEST_OWNED_BITS				      \
	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
	 | X86_CR4_OSXMMEXCPT)

106
107
108
#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)

109
110
#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))

111
112
113
114
/*
 * These 2 parameters are used to config the controls for Pause-Loop Exiting:
 * ple_gap:    upper bound on the amount of time between two successive
 *             executions of PAUSE in a loop. Also indicate if ple enabled.
115
 *             According to test, this time is usually smaller than 128 cycles.
116
117
118
119
120
121
 * ple_window: upper bound on the amount of time a guest is allowed to execute
 *             in a PAUSE loop. Tests indicate that most spinlocks are held for
 *             less than 2^12 cycles
 * Time is measured based on a counter that runs at the same rate as the TSC,
 * refer SDM volume 3b section 21.6.13 & 22.1.3.
 */
122
#define KVM_VMX_DEFAULT_PLE_GAP    128
123
124
125
126
127
128
129
#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
module_param(ple_gap, int, S_IRUGO);

static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);

Avi Kivity's avatar
Avi Kivity committed
130
131
extern const ulong vmx_return;

132
#define NR_AUTOLOAD_MSRS 8
133
#define VMCS02_POOL_SIZE 1
134

135
136
137
138
139
140
struct vmcs {
	u32 revision_id;
	u32 abort;
	char data[0];
};

141
142
143
144
145
146
147
148
149
150
151
152
/*
 * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also
 * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs
 * loaded on this CPU (so we can clear them if the CPU goes down).
 */
struct loaded_vmcs {
	struct vmcs *vmcs;
	int cpu;
	int launched;
	struct list_head loaded_vmcss_on_cpu_link;
};

153
154
155
struct shared_msr_entry {
	unsigned index;
	u64 data;
156
	u64 mask;
157
158
};

159
160
161
162
163
164
165
166
167
168
169
170
171
/*
 * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a
 * single nested guest (L2), hence the name vmcs12. Any VMX implementation has
 * a VMCS structure, and vmcs12 is our emulated VMX's VMCS. This structure is
 * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
 * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
 * More than one of these structures may exist, if L1 runs multiple L2 guests.
 * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
 * underlying hardware which will be used to run L2.
 * This structure is packed to ensure that its layout is identical across
 * machines (necessary for live migration).
 * If there are changes in this struct, VMCS12_REVISION must be changed.
 */
172
typedef u64 natural_width;
173
174
175
176
177
178
struct __packed vmcs12 {
	/* According to the Intel spec, a VMCS region must start with the
	 * following two fields. Then follow implementation-specific data.
	 */
	u32 revision_id;
	u32 abort;
179

Nadav Har'El's avatar
Nadav Har'El committed
180
181
182
	u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
	u32 padding[7]; /* room for future expansion */

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
	u64 io_bitmap_a;
	u64 io_bitmap_b;
	u64 msr_bitmap;
	u64 vm_exit_msr_store_addr;
	u64 vm_exit_msr_load_addr;
	u64 vm_entry_msr_load_addr;
	u64 tsc_offset;
	u64 virtual_apic_page_addr;
	u64 apic_access_addr;
	u64 ept_pointer;
	u64 guest_physical_address;
	u64 vmcs_link_pointer;
	u64 guest_ia32_debugctl;
	u64 guest_ia32_pat;
	u64 guest_ia32_efer;
	u64 guest_ia32_perf_global_ctrl;
	u64 guest_pdptr0;
	u64 guest_pdptr1;
	u64 guest_pdptr2;
	u64 guest_pdptr3;
	u64 host_ia32_pat;
	u64 host_ia32_efer;
	u64 host_ia32_perf_global_ctrl;
	u64 padding64[8]; /* room for future expansion */
	/*
	 * To allow migration of L1 (complete with its L2 guests) between
	 * machines of different natural widths (32 or 64 bit), we cannot have
	 * unsigned long fields with no explict size. We use u64 (aliased
	 * natural_width) instead. Luckily, x86 is little-endian.
	 */
	natural_width cr0_guest_host_mask;
	natural_width cr4_guest_host_mask;
	natural_width cr0_read_shadow;
	natural_width cr4_read_shadow;
	natural_width cr3_target_value0;
	natural_width cr3_target_value1;
	natural_width cr3_target_value2;
	natural_width cr3_target_value3;
	natural_width exit_qualification;
	natural_width guest_linear_address;
	natural_width guest_cr0;
	natural_width guest_cr3;
	natural_width guest_cr4;
	natural_width guest_es_base;
	natural_width guest_cs_base;
	natural_width guest_ss_base;
	natural_width guest_ds_base;
	natural_width guest_fs_base;
	natural_width guest_gs_base;
	natural_width guest_ldtr_base;
	natural_width guest_tr_base;
	natural_width guest_gdtr_base;
	natural_width guest_idtr_base;
	natural_width guest_dr7;
	natural_width guest_rsp;
	natural_width guest_rip;
	natural_width guest_rflags;
	natural_width guest_pending_dbg_exceptions;
	natural_width guest_sysenter_esp;
	natural_width guest_sysenter_eip;
	natural_width host_cr0;
	natural_width host_cr3;
	natural_width host_cr4;
	natural_width host_fs_base;
	natural_width host_gs_base;
	natural_width host_tr_base;
	natural_width host_gdtr_base;
	natural_width host_idtr_base;
	natural_width host_ia32_sysenter_esp;
	natural_width host_ia32_sysenter_eip;
	natural_width host_rsp;
	natural_width host_rip;
	natural_width paddingl[8]; /* room for future expansion */
	u32 pin_based_vm_exec_control;
	u32 cpu_based_vm_exec_control;
	u32 exception_bitmap;
	u32 page_fault_error_code_mask;
	u32 page_fault_error_code_match;
	u32 cr3_target_count;
	u32 vm_exit_controls;
	u32 vm_exit_msr_store_count;
	u32 vm_exit_msr_load_count;
	u32 vm_entry_controls;
	u32 vm_entry_msr_load_count;
	u32 vm_entry_intr_info_field;
	u32 vm_entry_exception_error_code;
	u32 vm_entry_instruction_len;
	u32 tpr_threshold;
	u32 secondary_vm_exec_control;
	u32 vm_instruction_error;
	u32 vm_exit_reason;
	u32 vm_exit_intr_info;
	u32 vm_exit_intr_error_code;
	u32 idt_vectoring_info_field;
	u32 idt_vectoring_error_code;
	u32 vm_exit_instruction_len;
	u32 vmx_instruction_info;
	u32 guest_es_limit;
	u32 guest_cs_limit;
	u32 guest_ss_limit;
	u32 guest_ds_limit;
	u32 guest_fs_limit;
	u32 guest_gs_limit;
	u32 guest_ldtr_limit;
	u32 guest_tr_limit;
	u32 guest_gdtr_limit;
	u32 guest_idtr_limit;
	u32 guest_es_ar_bytes;
	u32 guest_cs_ar_bytes;
	u32 guest_ss_ar_bytes;
	u32 guest_ds_ar_bytes;
	u32 guest_fs_ar_bytes;
	u32 guest_gs_ar_bytes;
	u32 guest_ldtr_ar_bytes;
	u32 guest_tr_ar_bytes;
	u32 guest_interruptibility_info;
	u32 guest_activity_state;
	u32 guest_sysenter_cs;
	u32 host_ia32_sysenter_cs;
302
303
	u32 vmx_preemption_timer_value;
	u32 padding32[7]; /* room for future expansion */
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
	u16 virtual_processor_id;
	u16 guest_es_selector;
	u16 guest_cs_selector;
	u16 guest_ss_selector;
	u16 guest_ds_selector;
	u16 guest_fs_selector;
	u16 guest_gs_selector;
	u16 guest_ldtr_selector;
	u16 guest_tr_selector;
	u16 host_es_selector;
	u16 host_cs_selector;
	u16 host_ss_selector;
	u16 host_ds_selector;
	u16 host_fs_selector;
	u16 host_gs_selector;
	u16 host_tr_selector;
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
};

/*
 * VMCS12_REVISION is an arbitrary id that should be changed if the content or
 * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
 * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
 */
#define VMCS12_REVISION 0x11e57ed0

/*
 * VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region
 * and any VMCS region. Although only sizeof(struct vmcs12) are used by the
 * current implementation, 4K are reserved to avoid future complications.
 */
#define VMCS12_SIZE 0x1000

336
337
338
339
340
341
342
/* Used to remember the last vmcs02 used for some recently used vmcs12s */
struct vmcs02_list {
	struct list_head list;
	gpa_t vmptr;
	struct loaded_vmcs vmcs02;
};

343
344
345
346
347
348
349
/*
 * The nested_vmx structure is part of vcpu_vmx, and holds information we need
 * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
 */
struct nested_vmx {
	/* Has the level1 guest done vmxon? */
	bool vmxon;
350
351
352
353
354
355

	/* The guest-physical address of the current VMCS L1 keeps for L2 */
	gpa_t current_vmptr;
	/* The host-usable pointer to the above */
	struct page *current_vmcs12_page;
	struct vmcs12 *current_vmcs12;
356
357
358
359

	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
	struct list_head vmcs02_pool;
	int vmcs02_num;
360
	u64 vmcs01_tsc_offset;
361
362
	/* L2 must run next, and mustn't decide to exit to L1. */
	bool nested_run_pending;
363
364
365
366
367
	/*
	 * Guest pages referred to in vmcs02 with host-physical pointers, so
	 * we must keep them pinned while L2 runs.
	 */
	struct page *apic_access_page;
368
369
};

370
371
372
373
374
375
376
377
#define POSTED_INTR_ON  0
/* Posted-Interrupt Descriptor */
struct pi_desc {
	u32 pir[8];     /* Posted interrupt requested */
	u32 control;	/* bit 0 of control is outstanding notification bit */
	u32 rsvd[7];
} __aligned(64);

378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
static bool pi_test_and_set_on(struct pi_desc *pi_desc)
{
	return test_and_set_bit(POSTED_INTR_ON,
			(unsigned long *)&pi_desc->control);
}

static bool pi_test_and_clear_on(struct pi_desc *pi_desc)
{
	return test_and_clear_bit(POSTED_INTR_ON,
			(unsigned long *)&pi_desc->control);
}

static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
{
	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
}

395
struct vcpu_vmx {
396
	struct kvm_vcpu       vcpu;
397
	unsigned long         host_rsp;
398
	u8                    fail;
Avi Kivity's avatar
Avi Kivity committed
399
	u8                    cpl;
400
	bool                  nmi_known_unmasked;
401
	u32                   exit_intr_info;
402
	u32                   idt_vectoring_info;
403
	ulong                 rflags;
404
	struct shared_msr_entry *guest_msrs;
405
406
	int                   nmsrs;
	int                   save_nmsrs;
407
	unsigned long	      host_idt_base;
408
#ifdef CONFIG_X86_64
409
410
	u64 		      msr_host_kernel_gs_base;
	u64 		      msr_guest_kernel_gs_base;
411
#endif
412
413
414
415
416
417
418
419
	/*
	 * loaded_vmcs points to the VMCS currently used in this vcpu. For a
	 * non-nested (L1) guest, it always points to vmcs01. For a nested
	 * guest (L2), it points to a different VMCS.
	 */
	struct loaded_vmcs    vmcs01;
	struct loaded_vmcs   *loaded_vmcs;
	bool                  __launched; /* temporary, used in vmx_vcpu_run */
420
421
422
423
424
	struct msr_autoload {
		unsigned nr;
		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
	} msr_autoload;
425
426
427
	struct {
		int           loaded;
		u16           fs_sel, gs_sel, ldt_sel;
428
429
430
#ifdef CONFIG_X86_64
		u16           ds_sel, es_sel;
#endif
431
432
		int           gs_ldt_reload_needed;
		int           fs_reload_needed;
Mike Day's avatar
Mike Day committed
433
	} host_state;
434
	struct {
435
		int vm86_active;
436
		ulong save_rflags;
437
438
439
440
		struct kvm_segment segs[8];
	} rmode;
	struct {
		u32 bitmask; /* 4 bits per segment (1 bit per field) */
441
442
443
444
445
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
446
		} seg[8];
447
	} segment_cache;
448
	int vpid;
449
	bool emulation_required;
450
451
452
453
454

	/* Support for vnmi-less CPUs */
	int soft_vnmi_blocked;
	ktime_t entry_time;
	s64 vnmi_blocked_time;
455
	u32 exit_reason;
456
457

	bool rdtscp_enabled;
458

459
460
461
	/* Posted interrupt descriptor */
	struct pi_desc pi_desc;

462
463
	/* Support for a guest hypervisor (nested VMX) */
	struct nested_vmx nested;
464
465
};

466
467
468
469
470
471
472
473
474
enum segment_cache_field {
	SEG_FIELD_SEL = 0,
	SEG_FIELD_BASE = 1,
	SEG_FIELD_LIMIT = 2,
	SEG_FIELD_AR = 3,

	SEG_FIELD_NR = 4
};

475
476
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
{
477
	return container_of(vcpu, struct vcpu_vmx, vcpu);
478
479
}

480
481
482
483
484
#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
#define FIELD(number, name)	[number] = VMCS12_OFFSET(name)
#define FIELD64(number, name)	[number] = VMCS12_OFFSET(name), \
				[number##_HIGH] = VMCS12_OFFSET(name)+4

485
static const unsigned short vmcs_field_to_offset_table[] = {
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
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
	FIELD(GUEST_SS_SELECTOR, guest_ss_selector),
	FIELD(GUEST_DS_SELECTOR, guest_ds_selector),
	FIELD(GUEST_FS_SELECTOR, guest_fs_selector),
	FIELD(GUEST_GS_SELECTOR, guest_gs_selector),
	FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
	FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
	FIELD(HOST_ES_SELECTOR, host_es_selector),
	FIELD(HOST_CS_SELECTOR, host_cs_selector),
	FIELD(HOST_SS_SELECTOR, host_ss_selector),
	FIELD(HOST_DS_SELECTOR, host_ds_selector),
	FIELD(HOST_FS_SELECTOR, host_fs_selector),
	FIELD(HOST_GS_SELECTOR, host_gs_selector),
	FIELD(HOST_TR_SELECTOR, host_tr_selector),
	FIELD64(IO_BITMAP_A, io_bitmap_a),
	FIELD64(IO_BITMAP_B, io_bitmap_b),
	FIELD64(MSR_BITMAP, msr_bitmap),
	FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
	FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
	FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
	FIELD64(TSC_OFFSET, tsc_offset),
	FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
	FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
	FIELD64(EPT_POINTER, ept_pointer),
	FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
	FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
	FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
	FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
	FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
	FIELD64(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl),
	FIELD64(GUEST_PDPTR0, guest_pdptr0),
	FIELD64(GUEST_PDPTR1, guest_pdptr1),
	FIELD64(GUEST_PDPTR2, guest_pdptr2),
	FIELD64(GUEST_PDPTR3, guest_pdptr3),
	FIELD64(HOST_IA32_PAT, host_ia32_pat),
	FIELD64(HOST_IA32_EFER, host_ia32_efer),
	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
	FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
	FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
	FIELD(EXCEPTION_BITMAP, exception_bitmap),
	FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask),
	FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match),
	FIELD(CR3_TARGET_COUNT, cr3_target_count),
	FIELD(VM_EXIT_CONTROLS, vm_exit_controls),
	FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count),
	FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count),
	FIELD(VM_ENTRY_CONTROLS, vm_entry_controls),
	FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count),
	FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field),
	FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code),
	FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len),
	FIELD(TPR_THRESHOLD, tpr_threshold),
	FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control),
	FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error),
	FIELD(VM_EXIT_REASON, vm_exit_reason),
	FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info),
	FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code),
	FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field),
	FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code),
	FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len),
	FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info),
	FIELD(GUEST_ES_LIMIT, guest_es_limit),
	FIELD(GUEST_CS_LIMIT, guest_cs_limit),
	FIELD(GUEST_SS_LIMIT, guest_ss_limit),
	FIELD(GUEST_DS_LIMIT, guest_ds_limit),
	FIELD(GUEST_FS_LIMIT, guest_fs_limit),
	FIELD(GUEST_GS_LIMIT, guest_gs_limit),
	FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit),
	FIELD(GUEST_TR_LIMIT, guest_tr_limit),
	FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit),
	FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit),
	FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes),
	FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes),
	FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes),
	FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes),
	FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes),
	FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes),
	FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes),
	FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes),
	FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info),
	FIELD(GUEST_ACTIVITY_STATE, guest_activity_state),
	FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs),
	FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs),
571
	FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value),
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
	FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask),
	FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask),
	FIELD(CR0_READ_SHADOW, cr0_read_shadow),
	FIELD(CR4_READ_SHADOW, cr4_read_shadow),
	FIELD(CR3_TARGET_VALUE0, cr3_target_value0),
	FIELD(CR3_TARGET_VALUE1, cr3_target_value1),
	FIELD(CR3_TARGET_VALUE2, cr3_target_value2),
	FIELD(CR3_TARGET_VALUE3, cr3_target_value3),
	FIELD(EXIT_QUALIFICATION, exit_qualification),
	FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address),
	FIELD(GUEST_CR0, guest_cr0),
	FIELD(GUEST_CR3, guest_cr3),
	FIELD(GUEST_CR4, guest_cr4),
	FIELD(GUEST_ES_BASE, guest_es_base),
	FIELD(GUEST_CS_BASE, guest_cs_base),
	FIELD(GUEST_SS_BASE, guest_ss_base),
	FIELD(GUEST_DS_BASE, guest_ds_base),
	FIELD(GUEST_FS_BASE, guest_fs_base),
	FIELD(GUEST_GS_BASE, guest_gs_base),
	FIELD(GUEST_LDTR_BASE, guest_ldtr_base),
	FIELD(GUEST_TR_BASE, guest_tr_base),
	FIELD(GUEST_GDTR_BASE, guest_gdtr_base),
	FIELD(GUEST_IDTR_BASE, guest_idtr_base),
	FIELD(GUEST_DR7, guest_dr7),
	FIELD(GUEST_RSP, guest_rsp),
	FIELD(GUEST_RIP, guest_rip),
	FIELD(GUEST_RFLAGS, guest_rflags),
	FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions),
	FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp),
	FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip),
	FIELD(HOST_CR0, host_cr0),
	FIELD(HOST_CR3, host_cr3),
	FIELD(HOST_CR4, host_cr4),
	FIELD(HOST_FS_BASE, host_fs_base),
	FIELD(HOST_GS_BASE, host_gs_base),
	FIELD(HOST_TR_BASE, host_tr_base),
	FIELD(HOST_GDTR_BASE, host_gdtr_base),
	FIELD(HOST_IDTR_BASE, host_idtr_base),
	FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp),
	FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip),
	FIELD(HOST_RSP, host_rsp),
	FIELD(HOST_RIP, host_rip),
};
static const int max_vmcs_field = ARRAY_SIZE(vmcs_field_to_offset_table);

static inline short vmcs_field_to_offset(unsigned long field)
{
	if (field >= max_vmcs_field || vmcs_field_to_offset_table[field] == 0)
		return -1;
	return vmcs_field_to_offset_table[field];
}

624
625
626
627
628
629
630
631
static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
{
	return to_vmx(vcpu)->nested.current_vmcs12;
}

static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
{
	struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
632
	if (is_error_page(page))
633
		return NULL;
634

635
636
637
638
639
640
641
642
643
644
645
646
647
	return page;
}

static void nested_release_page(struct page *page)
{
	kvm_release_page_dirty(page);
}

static void nested_release_page_clean(struct page *page)
{
	kvm_release_page_clean(page);
}

648
static u64 construct_eptp(unsigned long root_hpa);
649
650
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
651
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
652
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
653
654
655
656
static void vmx_set_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
static void vmx_get_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
657
658
static bool guest_state_valid(struct kvm_vcpu *vcpu);
static u32 vmx_segment_access_rights(struct kvm_segment *var);
659
static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
660

Avi Kivity's avatar
Avi Kivity committed
661
662
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
663
664
665
666
667
/*
 * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed
 * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
 */
static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
668
static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
Avi Kivity's avatar
Avi Kivity committed
669

670
671
static unsigned long *vmx_io_bitmap_a;
static unsigned long *vmx_io_bitmap_b;
672
673
static unsigned long *vmx_msr_bitmap_legacy;
static unsigned long *vmx_msr_bitmap_longmode;
674
675
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;
676

677
static bool cpu_has_load_ia32_efer;
678
static bool cpu_has_load_perf_global_ctrl;
679

680
681
682
static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);

683
static struct vmcs_config {
Avi Kivity's avatar
Avi Kivity committed
684
685
686
	int size;
	int order;
	u32 revision_id;
687
688
	u32 pin_based_exec_ctrl;
	u32 cpu_based_exec_ctrl;
689
	u32 cpu_based_2nd_exec_ctrl;
690
691
692
	u32 vmexit_ctrl;
	u32 vmentry_ctrl;
} vmcs_config;
Avi Kivity's avatar
Avi Kivity committed
693

Hannes Eder's avatar
Hannes Eder committed
694
static struct vmx_capability {
Sheng Yang's avatar
Sheng Yang committed
695
696
697
698
	u32 ept;
	u32 vpid;
} vmx_capability;

Avi Kivity's avatar
Avi Kivity committed
699
700
701
702
703
704
705
706
#define VMX_SEGMENT_FIELD(seg)					\
	[VCPU_SREG_##seg] = {                                   \
		.selector = GUEST_##seg##_SELECTOR,		\
		.base = GUEST_##seg##_BASE,		   	\
		.limit = GUEST_##seg##_LIMIT,		   	\
		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
	}

707
static const struct kvm_vmx_segment_field {
Avi Kivity's avatar
Avi Kivity committed
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
	unsigned selector;
	unsigned base;
	unsigned limit;
	unsigned ar_bytes;
} kvm_vmx_segment_fields[] = {
	VMX_SEGMENT_FIELD(CS),
	VMX_SEGMENT_FIELD(DS),
	VMX_SEGMENT_FIELD(ES),
	VMX_SEGMENT_FIELD(FS),
	VMX_SEGMENT_FIELD(GS),
	VMX_SEGMENT_FIELD(SS),
	VMX_SEGMENT_FIELD(TR),
	VMX_SEGMENT_FIELD(LDTR),
};

723
724
static u64 host_efer;

Avi Kivity's avatar
Avi Kivity committed
725
726
static void ept_save_pdptrs(struct kvm_vcpu *vcpu);

727
/*
Brian Gerst's avatar
Brian Gerst committed
728
 * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it
729
730
 * away by decrementing the array size.
 */
Avi Kivity's avatar
Avi Kivity committed
731
static const u32 vmx_msr_index[] = {
732
#ifdef CONFIG_X86_64
733
	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
Avi Kivity's avatar
Avi Kivity committed
734
#endif
Brian Gerst's avatar
Brian Gerst committed
735
	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
Avi Kivity's avatar
Avi Kivity committed
736
};
737
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
Avi Kivity's avatar
Avi Kivity committed
738

739
static inline bool is_page_fault(u32 intr_info)
Avi Kivity's avatar
Avi Kivity committed
740
741
742
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
743
		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
Avi Kivity's avatar
Avi Kivity committed
744
745
}

746
static inline bool is_no_device(u32 intr_info)
747
748
749
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
750
		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
751
752
}

753
static inline bool is_invalid_opcode(u32 intr_info)
754
755
756
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
757
		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
758
759
}

760
static inline bool is_external_interrupt(u32 intr_info)
Avi Kivity's avatar
Avi Kivity committed
761
762
763
764
765
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}

766
static inline bool is_machine_check(u32 intr_info)
767
768
769
770
771
772
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}

773
static inline bool cpu_has_vmx_msr_bitmap(void)
774
{
775
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
776
777
}

778
static inline bool cpu_has_vmx_tpr_shadow(void)
779
{
780
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
781
782
}

783
static inline bool vm_need_tpr_shadow(struct kvm *kvm)
784
{
785
	return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
786
787
}

788
static inline bool cpu_has_secondary_exec_ctrls(void)
789
{
790
791
	return vmcs_config.cpu_based_exec_ctrl &
		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
792
793
}

794
static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
795
{
796
797
798
799
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
}

800
801
802
803
804
805
static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
}

806
807
808
809
810
811
static inline bool cpu_has_vmx_apic_register_virt(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_APIC_REGISTER_VIRT;
}

812
813
814
815
816
817
static inline bool cpu_has_vmx_virtual_intr_delivery(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
}

818
819
820
821
822
823
824
825
826
827
828
829
static inline bool cpu_has_vmx_posted_intr(void)
{
	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
}

static inline bool cpu_has_vmx_apicv(void)
{
	return cpu_has_vmx_apic_register_virt() &&
		cpu_has_vmx_virtual_intr_delivery() &&
		cpu_has_vmx_posted_intr();
}

830
831
832
833
static inline bool cpu_has_vmx_flexpriority(void)
{
	return cpu_has_vmx_tpr_shadow() &&
		cpu_has_vmx_virtualize_apic_accesses();
834
835
}

836
837
static inline bool cpu_has_vmx_ept_execute_only(void)
{
838
	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
839
840
841
842
}

static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
843
	return vmx_capability.ept & VMX_EPTP_UC_BIT;
844
845
846
847
}

static inline bool cpu_has_vmx_eptp_writeback(void)
{
848
	return vmx_capability.ept & VMX_EPTP_WB_BIT;
849
850
851
852
}

static inline bool cpu_has_vmx_ept_2m_page(void)
{
853
	return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
854
855
}

856
857
static inline bool cpu_has_vmx_ept_1g_page(void)
{
858
	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
859
860
}

861
862
863
864
865
static inline bool cpu_has_vmx_ept_4levels(void)
{
	return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
}

866
867
868
869
870
static inline bool cpu_has_vmx_ept_ad_bits(void)
{
	return vmx_capability.ept & VMX_EPT_AD_BIT;
}

871
static inline bool cpu_has_vmx_invept_context(void)
Sheng Yang's avatar
Sheng Yang committed
872
{
873
	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
Sheng Yang's avatar
Sheng Yang committed
874
875
}

876
static inline bool cpu_has_vmx_invept_global(void)
Sheng Yang's avatar
Sheng Yang committed
877
{
878
	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
Sheng Yang's avatar
Sheng Yang committed
879
880
}

881
882
883
884
885
static inline bool cpu_has_vmx_invvpid_single(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
}

886
887
888
889
890
static inline bool cpu_has_vmx_invvpid_global(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}

891
static inline bool cpu_has_vmx_ept(void)
Sheng Yang's avatar
Sheng Yang committed
892
{
893
894
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_EPT;
Sheng Yang's avatar
Sheng Yang committed
895
896
}

897
static inline bool cpu_has_vmx_unrestricted_guest(void)
898
899
900
901
902
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_UNRESTRICTED_GUEST;
}

903
static inline bool cpu_has_vmx_ple(void)
904
905
906
907
908
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}

909
static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
910
{
911
	return flexpriority_enabled && irqchip_in_kernel(kvm);
912
913
}

914
static inline bool cpu_has_vmx_vpid(void)
915
{
916
917
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_VPID;
918
919
}

920
static inline bool cpu_has_vmx_rdtscp(void)
921
922
923
924
925
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_RDTSCP;
}

926
927
928
929
930
931
static inline bool cpu_has_vmx_invpcid(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_INVPCID;
}

932
static inline bool cpu_has_virtual_nmis(void)
933
934
935
936
{
	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}

937
938
939
940
941
942
static inline bool cpu_has_vmx_wbinvd_exit(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_WBINVD_EXITING;
}

943
944
945
946
947
static inline bool report_flexpriority(void)
{
	return flexpriority_enabled;
}

948
949
950
951
952
953
954
955
956
957
958
959
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
	return vmcs12->cpu_based_vm_exec_control & bit;
}

static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
{
	return (vmcs12->cpu_based_vm_exec_control &
			CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
		(vmcs12->secondary_vm_exec_control & bit);
}

960
961
962
963
964
965
966
967
968
969
970
971
972
static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
	struct kvm_vcpu *vcpu)
{
	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
}

static inline bool is_exception(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
		== (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
}

static void nested_vmx_vmexit(struct kvm_vcpu *vcpu);
973
974
975
976
static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
			struct vmcs12 *vmcs12,
			u32 reason, unsigned long qualification);

977
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
978
979
980
{
	int i;

981
	for (i = 0; i < vmx->nmsrs; ++i)
982
		if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
983
984
985
986
			return i;
	return -1;
}

987
988
989
990
991
992
993
994
static inline void __invvpid(int ext, u16 vpid, gva_t gva)
{
    struct {
	u64 vpid : 16;
	u64 rsvd : 48;
	u64 gva;
    } operand = { vpid, 0, gva };

995
    asm volatile (__ex(ASM_VMX_INVVPID)
996
997
998
999
1000
		  /* CF==1 or ZF==1 --> rc = -1 */
		  "; ja 1f ; ud2 ; 1:"
		  : : "a"(&operand), "c"(ext) : "cc", "memory");
}