vmx.c

/*
 * 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.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * 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.
 *
 */

#include "irq.h"
#include "mmu.h"
#include "cpuid.h"

#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/mod_devicetable.h>
#include <linux/ftrace_event.h>
#include <linux/slab.h>
#include <linux/tboot.h>
#include "kvm_cache_regs.h"
#include "x86.h"

#include <asm/io.h>
#include <asm/desc.h>
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>
#include <asm/perf_event.h>
#include <asm/kexec.h>

#include "trace.h"

#define __ex(x) __kvm_handle_fault_on_reboot(x)
#define __ex_clear(x, reg) \
	____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

static const struct x86_cpu_id vmx_cpu_id[] = {
	X86_FEATURE_MATCH(X86_FEATURE_VMX),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);

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

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

static bool __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);

static bool __read_mostly enable_unrestricted_guest = 1;
module_param_named(unrestricted_guest,
			enable_unrestricted_guest, bool, S_IRUGO);

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

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

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

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

static bool __read_mostly enable_apicv_reg_vid;

/*
 * 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.
 */
static bool __read_mostly nested = 0;
module_param(nested, bool, S_IRUGO);

#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)
#define KVM_VM_CR0_ALWAYS_ON						\
	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_CR4_GUEST_OWNED_BITS				      \
	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
	 | X86_CR4_OSXMMEXCPT)

#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 RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))

/*
 * 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.
 *             According to test, this time is usually smaller than 128 cycles.
 * 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.
 */
#define KVM_VMX_DEFAULT_PLE_GAP    128
#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);

extern const ulong vmx_return;

#define NR_AUTOLOAD_MSRS 8
#define VMCS02_POOL_SIZE 1

struct vmcs {
	u32 revision_id;
	u32 abort;
	char data[0];
};

/*
 * 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;
};

struct shared_msr_entry {
	unsigned index;
	u64 data;
	u64 mask;
};

/*
 * 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.
 */
typedef u64 natural_width;
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;

	u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
	u32 padding[7]; /* room for future expansion */

	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;
	u32 vmx_preemption_timer_value;
	u32 padding32[7]; /* room for future expansion */
	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;
};

/*
 * 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

/* 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;
};

/*
 * 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;

	/* 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;

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

struct vcpu_vmx {
	struct kvm_vcpu       vcpu;
	unsigned long         host_rsp;
	u8                    fail;
	u8                    cpl;
	bool                  nmi_known_unmasked;
	u32                   exit_intr_info;
	u32                   idt_vectoring_info;
	ulong                 rflags;
	struct shared_msr_entry *guest_msrs;
	int                   nmsrs;
	int                   save_nmsrs;
#ifdef CONFIG_X86_64
	u64 		      msr_host_kernel_gs_base;
	u64 		      msr_guest_kernel_gs_base;
#endif
	/*
	 * 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 */
	struct msr_autoload {
		unsigned nr;
		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
	} msr_autoload;
	struct {
		int           loaded;
		u16           fs_sel, gs_sel, ldt_sel;
#ifdef CONFIG_X86_64
		u16           ds_sel, es_sel;
#endif
		int           gs_ldt_reload_needed;
		int           fs_reload_needed;
	} host_state;
	struct {
		int vm86_active;
		ulong save_rflags;
		struct kvm_segment segs[8];
	} rmode;
	struct {
		u32 bitmask; /* 4 bits per segment (1 bit per field) */
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
		} seg[8];
	} segment_cache;
	int vpid;
	bool emulation_required;

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

	bool rdtscp_enabled;

	/* Support for a guest hypervisor (nested VMX) */
	struct nested_vmx nested;
};

enum segment_cache_field {
	SEG_FIELD_SEL = 0,
	SEG_FIELD_BASE = 1,
	SEG_FIELD_LIMIT = 2,
	SEG_FIELD_AR = 3,

	SEG_FIELD_NR = 4
};

static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
{
	return container_of(vcpu, struct vcpu_vmx, vcpu);
}

#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

static const unsigned short vmcs_field_to_offset_table[] = {
	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),
	FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value),
	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];
}

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);
	if (is_error_page(page))
		return NULL;

	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);
}

static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
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);
static bool guest_state_valid(struct kvm_vcpu *vcpu);
static u32 vmx_segment_access_rights(struct kvm_segment *var);

static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
/*
 * 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);
static DEFINE_PER_CPU(struct desc_ptr, host_gdt);

static unsigned long *vmx_io_bitmap_a;
static unsigned long *vmx_io_bitmap_b;
static unsigned long *vmx_msr_bitmap_legacy;
static unsigned long *vmx_msr_bitmap_longmode;
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;

static bool cpu_has_load_ia32_efer;
static bool cpu_has_load_perf_global_ctrl;

static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);

static struct vmcs_config {
	int size;
	int order;
	u32 revision_id;
	u32 pin_based_exec_ctrl;
	u32 cpu_based_exec_ctrl;
	u32 cpu_based_2nd_exec_ctrl;
	u32 vmexit_ctrl;
	u32 vmentry_ctrl;
} vmcs_config;

static struct vmx_capability {
	u32 ept;
	u32 vpid;
} vmx_capability;

#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,	   	\
	}

static const struct kvm_vmx_segment_field {
	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),
};

static u64 host_efer;

static void ept_save_pdptrs(struct kvm_vcpu *vcpu);

/*
 * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it
 * away by decrementing the array size.
 */
static const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)

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

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

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

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

static inline bool is_machine_check(u32 intr_info)
{
	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);
}

static inline bool cpu_has_vmx_msr_bitmap(void)
{
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}

static inline bool cpu_has_vmx_tpr_shadow(void)
{
	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}

static inline bool vm_need_tpr_shadow(struct kvm *kvm)
{
	return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
}

static inline bool cpu_has_secondary_exec_ctrls(void)
{
	return vmcs_config.cpu_based_exec_ctrl &
		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
}

static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
}

static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
}

static inline bool cpu_has_vmx_apic_register_virt(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_APIC_REGISTER_VIRT;
}

static inline bool cpu_has_vmx_virtual_intr_delivery(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
}

static inline bool cpu_has_vmx_flexpriority(void)
{
	return cpu_has_vmx_tpr_shadow() &&
		cpu_has_vmx_virtualize_apic_accesses();
}

static inline bool cpu_has_vmx_ept_execute_only(void)
{
	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}

static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
	return vmx_capability.ept & VMX_EPTP_UC_BIT;
}

static inline bool cpu_has_vmx_eptp_writeback(void)
{
	return vmx_capability.ept & VMX_EPTP_WB_BIT;
}

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

static inline bool cpu_has_vmx_ept_1g_page(void)
{
	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
}

static inline bool cpu_has_vmx_ept_4levels(void)
{
	return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
}

static inline bool cpu_has_vmx_ept_ad_bits(void)
{
	return vmx_capability.ept & VMX_EPT_AD_BIT;
}

static inline bool cpu_has_vmx_invept_context(void)
{
	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_invept_global(void)
{
	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}

static inline bool cpu_has_vmx_invvpid_single(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_invvpid_global(void)
{
	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}

static inline bool cpu_has_vmx_ept(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_EPT;
}

static inline bool cpu_has_vmx_unrestricted_guest(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_UNRESTRICTED_GUEST;
}

static inline bool cpu_has_vmx_ple(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}

static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
	return flexpriority_enabled && irqchip_in_kernel(kvm);
}

static inline bool cpu_has_vmx_vpid(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_VPID;
}

static inline bool cpu_has_vmx_rdtscp(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_RDTSCP;
}

static inline bool cpu_has_vmx_invpcid(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_ENABLE_INVPCID;
}

static inline bool cpu_has_virtual_nmis(void)
{
	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}

static inline bool cpu_has_vmx_wbinvd_exit(void)
{
	return vmcs_config.cpu_based_2nd_exec_ctrl &
		SECONDARY_EXEC_WBINVD_EXITING;
}

static inline bool report_flexpriority(void)
{
	return flexpriority_enabled;
}

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);
}

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);
static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
			struct vmcs12 *vmcs12,
			u32 reason, unsigned long qualification);

static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
	int i;

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

static inline void __invvpid(int ext, u16 vpid, gva_t gva)
{
    struct {
	u64 vpid : 16;
	u64 rsvd : 48;
	u64 gva;
    } operand = { vpid, 0, gva };

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

static inline void __invept(int ext, u64 eptp, gpa_t gpa)
{
	struct {
		u64 eptp, gpa;
	} operand = {eptp, gpa};

	asm volatile (__ex(ASM_VMX_INVEPT)
			/* CF==1 or ZF==1 --> rc = -1 */
			"; ja 1f ; ud2 ; 1:\n"
			: : "a" (&operand), "c" (ext) : "cc", "memory");
}

static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
	int i;

	i = __find_msr_index(vmx, msr);
	if (i >= 0)
		return &vmx->guest_msrs[i];
	return NULL;
}

static void vmcs_clear(struct vmcs *vmcs)
{
	u64 phys_addr = __pa(vmcs);
	u8 error;

	asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) "; setna %0"
		      : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
		      : "cc", "memory");
	if (error)
		printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
		       vmcs, phys_addr);
}

static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
{
	vmcs_clear(loaded_vmcs->vmcs);
	loaded_vmcs->cpu = -1;
	loaded_vmcs->launched = 0;
}

static void vmcs_load(struct vmcs *vmcs)