arch/x86/kvm/x86.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * derived from drivers/kvm/kvm_main.c
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2008 Qumranet, Inc.
 * Copyright IBM Corporation, 2008
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 */

#include <linux/kvm_host.h>
#include "irq.h"
#include "ioapic.h"
#include "mmu.h"
#include "i8254.h"
#include "tss.h"
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"
#include "x86.h"
#include "cpuid.h"
#include "pmu.h"
#include "hyperv.h"
#include "lapic.h"

#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <linux/moduleparam.h>
#include <linux/mman.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
#include <linux/cpufreq.h>
#include <linux/user-return-notifier.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/pci.h>
#include <linux/timekeeper_internal.h>
#include <linux/pvclock_gtod.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
#include <linux/sched/stat.h>
#include <linux/sched/isolation.h>
#include <linux/mem_encrypt.h>
#include <linux/entry-kvm.h>

#include <trace/events/kvm.h>

#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mce.h>
#include <asm/pkru.h>
#include <linux/kernel_stat.h>
#include <asm/fpu/api.h>
#include <asm/fpu/xcr.h>
#include <asm/fpu/xstate.h>
#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
#include <asm/mshyperv.h>
#include <asm/hypervisor.h>
#include <asm/tlbflush.h>
#include <asm/intel_pt.h>
#include <asm/emulate_prefix.h>
#include <asm/sgx.h>
#include <clocksource/hyperv_timer.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32
u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);

#define emul_to_vcpu(ctxt) \
	((struct kvm_vcpu *)(ctxt)->vcpu)

/* EFER defaults:
 * - enable syscall per default because its emulated by KVM
 * - enable LME and LMA per default on 64 bit KVM
 */
#ifdef CONFIG_X86_64
static
u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
#else
static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
#endif

static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;

#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                    KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)

static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
static void process_smi(struct kvm_vcpu *vcpu);
static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
static void store_regs(struct kvm_vcpu *vcpu);
static int sync_regs(struct kvm_vcpu *vcpu);

struct kvm_x86_ops kvm_x86_ops __read_mostly;
EXPORT_SYMBOL_GPL(kvm_x86_ops);

static bool __read_mostly ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);

bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
EXPORT_SYMBOL_GPL(report_ignored_msrs);

unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);

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

bool __read_mostly kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32  __read_mostly kvm_max_guest_tsc_khz;
EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
u8   __read_mostly kvm_tsc_scaling_ratio_frac_bits;
EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits);
u64  __read_mostly kvm_max_tsc_scaling_ratio;
EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
u64 __read_mostly kvm_default_tsc_scaling_ratio;
EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
bool __read_mostly kvm_has_bus_lock_exit;
EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit);
bool __read_mostly kvm_has_notify_vmexit;
EXPORT_SYMBOL_GPL(kvm_has_notify_vmexit);

/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);

/*
 * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
 * adaptive tuning starting from default advancment of 1000ns.  '0' disables
 * advancement entirely.  Any other value is used as-is and disables adaptive
 * tuning, i.e. allows priveleged userspace to set an exact advancement time.
 */
static int __read_mostly lapic_timer_advance_ns = -1;
module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);

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

bool __read_mostly enable_vmware_backdoor = false;
module_param(enable_vmware_backdoor, bool, S_IRUGO);
EXPORT_SYMBOL_GPL(enable_vmware_backdoor);

static bool __read_mostly force_emulation_prefix = false;
module_param(force_emulation_prefix, bool, S_IRUGO);

int __read_mostly pi_inject_timer = -1;
module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);

/*
 * Restoring the host value for MSRs that are only consumed when running in
 * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
 * returns to userspace, i.e. the kernel can run with the guest's value.
 */
#define KVM_MAX_NR_USER_RETURN_MSRS 16

struct kvm_user_return_msrs_global {
	int nr;
	u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS];
};

struct kvm_user_return_msrs {
	struct user_return_notifier urn;
	bool registered;
	struct kvm_user_return_msr_values {
		u64 host;
		u64 curr;
	} values[KVM_MAX_NR_USER_RETURN_MSRS];
};

static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global;
static struct kvm_user_return_msrs __percpu *user_return_msrs;

#define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
				| XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \
				| XFEATURE_MASK_PKRU)

u64 __read_mostly host_efer;
EXPORT_SYMBOL_GPL(host_efer);

bool __read_mostly allow_smaller_maxphyaddr = 0;
EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);

static u64 __read_mostly host_xss;
u64 __read_mostly supported_xss;
EXPORT_SYMBOL_GPL(supported_xss);

struct kvm_stats_debugfs_item debugfs_entries[] = {
	VCPU_STAT("pf_fixed", pf_fixed),
	VCPU_STAT("pf_guest", pf_guest),
	VCPU_STAT("tlb_flush", tlb_flush),
	VCPU_STAT("invlpg", invlpg),
	VCPU_STAT("exits", exits),
	VCPU_STAT("io_exits", io_exits),
	VCPU_STAT("mmio_exits", mmio_exits),
	VCPU_STAT("signal_exits", signal_exits),
	VCPU_STAT("irq_window", irq_window_exits),
	VCPU_STAT("nmi_window", nmi_window_exits),
	VCPU_STAT("halt_exits", halt_exits),
	VCPU_STAT("halt_successful_poll", halt_successful_poll),
	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
	VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
	VCPU_STAT("halt_wakeup", halt_wakeup),
	VCPU_STAT("hypercalls", hypercalls),
	VCPU_STAT("request_irq", request_irq_exits),
	VCPU_STAT("irq_exits", irq_exits),
	VCPU_STAT("host_state_reload", host_state_reload),
	VCPU_STAT("fpu_reload", fpu_reload),
	VCPU_STAT("insn_emulation", insn_emulation),
	VCPU_STAT("insn_emulation_fail", insn_emulation_fail),
	VCPU_STAT("irq_injections", irq_injections),
	VCPU_STAT("nmi_injections", nmi_injections),
	VCPU_STAT("req_event", req_event),
	VCPU_STAT("l1d_flush", l1d_flush),
	VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
	VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
	VCPU_STAT("preemption_reported", preemption_reported),
	VCPU_STAT("preemption_other", preemption_other),
	VCPU_STAT("notify_window_exits", notify_window_exits),
	VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped),
	VM_STAT("mmu_pte_write", mmu_pte_write),
	VM_STAT("mmu_pde_zapped", mmu_pde_zapped),
	VM_STAT("mmu_flooded", mmu_flooded),
	VM_STAT("mmu_recycled", mmu_recycled),
	VM_STAT("mmu_cache_miss", mmu_cache_miss),
	VM_STAT("mmu_unsync", mmu_unsync),
	VM_STAT("remote_tlb_flush", remote_tlb_flush),
	VM_STAT("largepages", lpages, .mode = 0444),
	VM_STAT("nx_largepages_splitted", nx_lpage_splits, .mode = 0444),
	VM_STAT("max_mmu_page_hash_collisions", max_mmu_page_hash_collisions),
	{ "vcpu_stat", 0, KVM_STAT_DFX },
	{ NULL }
};

/* debugfs entries of Detail For vcpu stat EXtension */
struct dfx_kvm_stats_debugfs_item dfx_debugfs_entries[] = {
	DFX_STAT("pid", pid),
	DFX_STAT("pf_fixed", pf_fixed),
	DFX_STAT("pf_guest", pf_guest),
	DFX_STAT("tlb_flush", tlb_flush),
	DFX_STAT("invlpg", invlpg),
	DFX_STAT("exits", exits),
	DFX_STAT("io_exits", io_exits),
	DFX_STAT("mmio_exits", mmio_exits),
	DFX_STAT("signal_exits", signal_exits),
	DFX_STAT("irq_window", irq_window_exits),
	DFX_STAT("nmi_window", nmi_window_exits),
	DFX_STAT("halt_exits", halt_exits),
	DFX_STAT("halt_successful_poll", halt_successful_poll),
	DFX_STAT("halt_attempted_poll", halt_attempted_poll),
	DFX_STAT("halt_wakeup", halt_wakeup),
	DFX_STAT("request_irq", request_irq_exits),
	DFX_STAT("irq_exits", irq_exits),
	DFX_STAT("host_state_reload", host_state_reload),
	DFX_STAT("fpu_reload", fpu_reload),
	DFX_STAT("insn_emulation", insn_emulation),
	DFX_STAT("insn_emulation_fail", insn_emulation_fail),
	DFX_STAT("hypercalls", hypercalls),
	DFX_STAT("irq_injections", irq_injections),
	DFX_STAT("nmi_injections", nmi_injections),
	DFX_STAT("cr_exits", cr_exits),
	DFX_STAT("msr_rd_exits", msr_rd_exits),
	DFX_STAT("msr_wr_exits", msr_wr_exits),
	DFX_STAT("apic_wr_exits", apic_wr_exits),
	DFX_STAT("ept_vio_exits", ept_vio_exits),
	DFX_STAT("ept_mis_exits", ept_mis_exits),
	DFX_STAT("pause_exits", pause_exits),
	DFX_STAT("steal", steal),
	DFX_STAT("st_max", st_max),
	DFX_STAT("utime", utime),
	DFX_STAT("stime", stime),
	DFX_STAT("gtime", gtime),
	DFX_STAT("preemption_timer_exits", preemption_timer_exits),
	DFX_STAT("preemption_reported", preemption_reported),
	DFX_STAT("preemption_other", preemption_other),
	{ NULL }
};

u64 __read_mostly host_xcr0;
u64 __read_mostly supported_xcr0;
EXPORT_SYMBOL_GPL(supported_xcr0);

static struct kmem_cache *x86_emulator_cache;

/*
 * When called, it means the previous get/set msr reached an invalid msr.
 * Return true if we want to ignore/silent this failed msr access.
 */
static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
				  u64 data, bool write)
{
	const char *op = write ? "wrmsr" : "rdmsr";

	if (ignore_msrs) {
		if (report_ignored_msrs)
			kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
				      op, msr, data);
		/* Mask the error */
		return true;
	} else {
		kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
				      op, msr, data);
		return false;
	}
}

static struct kmem_cache *kvm_alloc_emulator_cache(void)
{
	unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src);
	unsigned int size = sizeof(struct x86_emulate_ctxt);

	return kmem_cache_create_usercopy("x86_emulator", size,
					  __alignof__(struct x86_emulate_ctxt),
					  SLAB_ACCOUNT, useroffset,
					  size - useroffset, NULL);
}

static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);

static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
{
	int i;
	for (i = 0; i < ASYNC_PF_PER_VCPU; i++)
		vcpu->arch.apf.gfns[i] = ~0;
}

static void kvm_on_user_return(struct user_return_notifier *urn)
{
	unsigned slot;
	struct kvm_user_return_msrs *msrs
		= container_of(urn, struct kvm_user_return_msrs, urn);
	struct kvm_user_return_msr_values *values;
	unsigned long flags;

	/*
	 * Disabling irqs at this point since the following code could be
	 * interrupted and executed through kvm_arch_hardware_disable()
	 */
	local_irq_save(flags);
	if (msrs->registered) {
		msrs->registered = false;
		user_return_notifier_unregister(urn);
	}
	local_irq_restore(flags);
	for (slot = 0; slot < user_return_msrs_global.nr; ++slot) {
		values = &msrs->values[slot];
		if (values->host != values->curr) {
			wrmsrl(user_return_msrs_global.msrs[slot], values->host);
			values->curr = values->host;
		}
	}
}

int kvm_probe_user_return_msr(u32 msr)
{
	u64 val;
	int ret;

	preempt_disable();
	ret = rdmsrl_safe(msr, &val);
	if (ret)
		goto out;
	ret = wrmsrl_safe(msr, val);
out:
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL_GPL(kvm_probe_user_return_msr);

void kvm_define_user_return_msr(unsigned slot, u32 msr)
{
	BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS);
	user_return_msrs_global.msrs[slot] = msr;
	if (slot >= user_return_msrs_global.nr)
		user_return_msrs_global.nr = slot + 1;
}
EXPORT_SYMBOL_GPL(kvm_define_user_return_msr);

static void kvm_user_return_msr_cpu_online(void)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
	u64 value;
	int i;

	for (i = 0; i < user_return_msrs_global.nr; ++i) {
		rdmsrl_safe(user_return_msrs_global.msrs[i], &value);
		msrs->values[i].host = value;
		msrs->values[i].curr = value;
	}
}

int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
	int err;

	value = (value & mask) | (msrs->values[slot].host & ~mask);
	if (value == msrs->values[slot].curr)
		return 0;
	err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value);
	if (err)
		return 1;

	msrs->values[slot].curr = value;
	if (!msrs->registered) {
		msrs->urn.on_user_return = kvm_on_user_return;
		user_return_notifier_register(&msrs->urn);
		msrs->registered = true;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);

static void drop_user_return_notifiers(void)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);

	if (msrs->registered)
		kvm_on_user_return(&msrs->urn);
}

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);

enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
{
	return kvm_apic_mode(kvm_get_apic_base(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_get_apic_mode);

int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
	enum lapic_mode new_mode = kvm_apic_mode(msr_info->data);
	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff |
		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);

	if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
		return 1;
	if (!msr_info->host_initiated) {
		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
			return 1;
		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
			return 1;
	}

	kvm_lapic_set_base(vcpu, msr_info->data);
	kvm_recalculate_apic_map(vcpu->kvm);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

asmlinkage __visible noinstr void kvm_spurious_fault(void)
{
	/* Fault while not rebooting.  We want the trace. */
	BUG_ON(!kvm_rebooting);
}
EXPORT_SYMBOL_GPL(kvm_spurious_fault);

#define EXCPT_BENIGN		0
#define EXCPT_CONTRIBUTORY	1
#define EXCPT_PF		2

static int exception_class(int vector)
{
	switch (vector) {
	case PF_VECTOR:
		return EXCPT_PF;
	case DE_VECTOR:
	case TS_VECTOR:
	case NP_VECTOR:
	case SS_VECTOR:
	case GP_VECTOR:
		return EXCPT_CONTRIBUTORY;
	default:
		break;
	}
	return EXCPT_BENIGN;
}

#define EXCPT_FAULT		0
#define EXCPT_TRAP		1
#define EXCPT_ABORT		2
#define EXCPT_INTERRUPT		3

static int exception_type(int vector)
{
	unsigned int mask;

	if (WARN_ON(vector > 31 || vector == NMI_VECTOR))
		return EXCPT_INTERRUPT;

	mask = 1 << vector;

	/* #DB is trap, as instruction watchpoints are handled elsewhere */
	if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR)))
		return EXCPT_TRAP;

	if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR)))
		return EXCPT_ABORT;

	/* Reserved exceptions will result in fault */
	return EXCPT_FAULT;
}

void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
{
	unsigned nr = vcpu->arch.exception.nr;
	bool has_payload = vcpu->arch.exception.has_payload;
	unsigned long payload = vcpu->arch.exception.payload;

	if (!has_payload)
		return;

	switch (nr) {
	case DB_VECTOR:
		/*
		 * "Certain debug exceptions may clear bit 0-3.  The
		 * remaining contents of the DR6 register are never
		 * cleared by the processor".
		 */
		vcpu->arch.dr6 &= ~DR_TRAP_BITS;
		/*
		 * In order to reflect the #DB exception payload in guest
		 * dr6, three components need to be considered: active low
		 * bit, FIXED_1 bits and active high bits (e.g. DR6_BD,
		 * DR6_BS and DR6_BT)
		 * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits.
		 * In the target guest dr6:
		 * FIXED_1 bits should always be set.
		 * Active low bits should be cleared if 1-setting in payload.
		 * Active high bits should be set if 1-setting in payload.
		 *
		 * Note, the payload is compatible with the pending debug
		 * exceptions/exit qualification under VMX, that active_low bits
		 * are active high in payload.
		 * So they need to be flipped for DR6.
		 */
		vcpu->arch.dr6 |= DR6_ACTIVE_LOW;
		vcpu->arch.dr6 |= payload;
		vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW;

		/*
		 * The #DB payload is defined as compatible with the 'pending
		 * debug exceptions' field under VMX, not DR6. While bit 12 is
		 * defined in the 'pending debug exceptions' field (enabled
		 * breakpoint), it is reserved and must be zero in DR6.
		 */
		vcpu->arch.dr6 &= ~BIT(12);
		break;
	case PF_VECTOR:
		vcpu->arch.cr2 = payload;
		break;
	}

	vcpu->arch.exception.has_payload = false;
	vcpu->arch.exception.payload = 0;
}
EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);

static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
		unsigned nr, bool has_error, u32 error_code,
	        bool has_payload, unsigned long payload, bool reinject)
{
	u32 prev_nr;
	int class1, class2;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
	queue:
		if (reinject) {
			/*
			 * On vmentry, vcpu->arch.exception.pending is only
			 * true if an event injection was blocked by
			 * nested_run_pending.  In that case, however,
			 * vcpu_enter_guest requests an immediate exit,
			 * and the guest shouldn't proceed far enough to
			 * need reinjection.
			 */
			WARN_ON_ONCE(vcpu->arch.exception.pending);
			vcpu->arch.exception.injected = true;
			if (WARN_ON_ONCE(has_payload)) {
				/*
				 * A reinjected event has already
				 * delivered its payload.
				 */
				has_payload = false;
				payload = 0;
			}
		} else {
			vcpu->arch.exception.pending = true;
			vcpu->arch.exception.injected = false;
		}
		vcpu->arch.exception.has_error_code = has_error;
		vcpu->arch.exception.nr = nr;
		vcpu->arch.exception.error_code = error_code;
		vcpu->arch.exception.has_payload = has_payload;
		vcpu->arch.exception.payload = payload;
		if (!is_guest_mode(vcpu))
			kvm_deliver_exception_payload(vcpu);
		return;
	}

	/* to check exception */
	prev_nr = vcpu->arch.exception.nr;
	if (prev_nr == DF_VECTOR) {
		/* triple fault -> shutdown */
		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}
	class1 = exception_class(prev_nr);
	class2 = exception_class(nr);
	if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
		|| (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
		/*
		 * Generate double fault per SDM Table 5-5.  Set
		 * exception.pending = true so that the double fault
		 * can trigger a nested vmexit.
		 */
		vcpu->arch.exception.pending = true;
		vcpu->arch.exception.injected = false;
		vcpu->arch.exception.has_error_code = true;
		vcpu->arch.exception.nr = DF_VECTOR;
		vcpu->arch.exception.error_code = 0;
		vcpu->arch.exception.has_payload = false;
		vcpu->arch.exception.payload = 0;
	} else
		/* replace previous exception with a new one in a hope
		   that instruction re-execution will regenerate lost
		   exception */
		goto queue;
}

void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);

void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);

void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
			   unsigned long payload)
{
	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_p);

static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
				    u32 error_code, unsigned long payload)
{
	kvm_multiple_exception(vcpu, nr, true, error_code,
			       true, payload, false);
}

int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
	if (err)
		kvm_inject_gp(vcpu, 0);
	else
		return kvm_skip_emulated_instruction(vcpu);

	return 1;
}
EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);

void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
	++vcpu->stat.pf_guest;
	vcpu->arch.exception.nested_apf =
		is_guest_mode(vcpu) && fault->async_page_fault;
	if (vcpu->arch.exception.nested_apf) {
		vcpu->arch.apf.nested_apf_token = fault->address;
		kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
	} else {
		kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
					fault->address);
	}
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);

bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
				    struct x86_exception *fault)
{
	struct kvm_mmu *fault_mmu;
	WARN_ON_ONCE(fault->vector != PF_VECTOR);

	fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu :
					       vcpu->arch.walk_mmu;

	/*
	 * Invalidate the TLB entry for the faulting address, if it exists,
	 * else the access will fault indefinitely (and to emulate hardware).
	 */
	if ((fault->error_code & PFERR_PRESENT_MASK) &&
	    !(fault->error_code & PFERR_RSVD_MASK))
		kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address,
				       fault_mmu->root_hpa);

	fault_mmu->inject_page_fault(vcpu, fault);
	return fault->nested_page_fault;
}
EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault);

void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
	atomic_inc(&vcpu->arch.nmi_queued);
	kvm_make_request(KVM_REQ_NMI, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);

void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);

void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);

/*
 * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
 * a #GP and return false.
 */
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
{
	if (kvm_x86_ops.get_cpl(vcpu) <= required_cpl)
		return true;
	kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
	return false;
}
EXPORT_SYMBOL_GPL(kvm_require_cpl);

bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr)
{
	if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE))
		return true;

	kvm_queue_exception(vcpu, UD_VECTOR);
	return false;
}
EXPORT_SYMBOL_GPL(kvm_require_dr);

/*
 * This function will be used to read from the physical memory of the currently
 * running guest. The difference to kvm_vcpu_read_guest_page is that this function
 * can read from guest physical or from the guest's guest physical memory.
 */
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
			    gfn_t ngfn, void *data, int offset, int len,
			    u32 access)
{
	struct x86_exception exception;
	gfn_t real_gfn;
	gpa_t ngpa;

	ngpa     = gfn_to_gpa(ngfn);
	real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception);
	if (real_gfn == UNMAPPED_GVA)
		return -EFAULT;

	real_gfn = gpa_to_gfn(real_gfn);

	return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);

static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
			       void *data, int offset, int len, u32 access)
{
	return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn,
				       data, offset, len, access);
}

static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
{
	return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) |
	       rsvd_bits(1, 2);
}

/*
 * Load the pae pdptrs.  Return 1 if they are all valid, 0 otherwise.
 */
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
{
	gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
	unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
	int i;
	int ret;
	u64 pdpte[ARRAY_SIZE(mmu->pdptrs)];

	ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte,
				      offset * sizeof(u64), sizeof(pdpte),
				      PFERR_USER_MASK|PFERR_WRITE_MASK);
	if (ret < 0) {
		ret = 0;
		goto out;
	}
	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
		if ((pdpte[i] & PT_PRESENT_MASK) &&
		    (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
			ret = 0;
			goto out;
		}
	}
	ret = 1;

	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);

out:

	return ret;
}
EXPORT_SYMBOL_GPL(load_pdptrs);

bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
	int offset;
	gfn_t gfn;
	int r;

	if (!is_pae_paging(vcpu))
		return false;

	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
		return true;

	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
	offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1);
	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
				       PFERR_USER_MASK | PFERR_WRITE_MASK);
	if (r < 0)
		return true;

	return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
}
EXPORT_SYMBOL_GPL(pdptrs_changed);

int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	unsigned long old_cr0 = kvm_read_cr0(vcpu);
	unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG;
	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;

	cr0 |= X86_CR0_ET;

#ifdef CONFIG_X86_64
	if (cr0 & 0xffffffff00000000UL)
		return 1;
#endif

	cr0 &= ~CR0_RESERVED_BITS;

	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD))
		return 1;

	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE))
		return 1;

#ifdef CONFIG_X86_64
	if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) &&
	    (cr0 & X86_CR0_PG)) {
		int cs_db, cs_l;

		if (!is_pae(vcpu))
			return 1;
		kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
		if (cs_l)
			return 1;
	}
#endif
	if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) &&
	    is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) &&
	    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
		return 1;

	if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
		return 1;

	kvm_x86_ops.set_cr0(vcpu, cr0);

	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_async_pf_hash_reset(vcpu);
	}

	if ((cr0 ^ old_cr0) & update_bits)
		kvm_mmu_reset_context(vcpu);

	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);

void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
	(void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);

void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
{
	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {

		if (vcpu->arch.xcr0 != host_xcr0)
			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);

		if (vcpu->arch.xsaves_enabled &&
		    vcpu->arch.ia32_xss != host_xss)
			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
	}

	if (static_cpu_has(X86_FEATURE_PKU) &&
	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
	    vcpu->arch.pkru != vcpu->arch.host_pkru)
		write_pkru(vcpu->arch.pkru);
}
EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);

void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
{
	if (static_cpu_has(X86_FEATURE_PKU) &&
	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
		vcpu->arch.pkru = rdpkru();
		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
			write_pkru(vcpu->arch.host_pkru);
	}

	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {

		if (vcpu->arch.xcr0 != host_xcr0)
			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);

		if (vcpu->arch.xsaves_enabled &&
		    vcpu->arch.ia32_xss != host_xss)
			wrmsrl(MSR_IA32_XSS, host_xss);
	}

}
EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);

static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	u64 xcr0 = xcr;
	u64 old_xcr0 = vcpu->arch.xcr0;
	u64 valid_bits;

	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
	if (index != XCR_XFEATURE_ENABLED_MASK)
		return 1;
	if (!(xcr0 & XFEATURE_MASK_FP))
		return 1;
	if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE))
		return 1;

	/*
	 * Do not allow the guest to set bits that we do not support
	 * saving.  However, xcr0 bit 0 is always set, even if the
	 * emulated CPU does not support XSAVE (see fx_init).
	 */
	valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
	if (xcr0 & ~valid_bits)
		return 1;

	if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) !=
	    (!(xcr0 & XFEATURE_MASK_BNDCSR)))
		return 1;

	if (xcr0 & XFEATURE_MASK_AVX512) {
		if (!(xcr0 & XFEATURE_MASK_YMM))
			return 1;
		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
			return 1;
	}
	vcpu->arch.xcr0 = xcr0;

	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
		kvm_update_cpuid_runtime(vcpu);
	return 0;
}

int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	if (kvm_x86_ops.get_cpl(vcpu) != 0 ||
	    __kvm_set_xcr(vcpu, index, xcr)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_xcr);

int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	if (cr4 & cr4_reserved_bits)
		return -EINVAL;

	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
		return -EINVAL;

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_valid_cr4);

int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	unsigned long old_cr4 = kvm_read_cr4(vcpu);
	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
				   X86_CR4_SMEP;
	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;

	if (kvm_valid_cr4(vcpu, cr4))
		return 1;

	if (is_long_mode(vcpu)) {
		if (!(cr4 & X86_CR4_PAE))
			return 1;
		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
			return 1;
	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
		   && ((cr4 ^ old_cr4) & pdptr_bits)
		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
				   kvm_read_cr3(vcpu)))
		return 1;

	if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
		if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
			return 1;

		/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
		if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
			return 1;
	}

	if (kvm_x86_ops.set_cr4(vcpu, cr4))
		return 1;

	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
		kvm_mmu_reset_context(vcpu);

	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
		kvm_update_cpuid_runtime(vcpu);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	bool skip_tlb_flush = false;
#ifdef CONFIG_X86_64
	bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);

	if (pcid_enabled) {
		skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH;
		cr3 &= ~X86_CR3_PCID_NOFLUSH;
	}
#endif

	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
		if (!skip_tlb_flush) {
			kvm_mmu_sync_roots(vcpu);
			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
		}
		return 0;
	}

	if (is_long_mode(vcpu) &&
	    (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
		return 1;
	else if (is_pae_paging(vcpu) &&
		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
		return 1;

	kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush);
	vcpu->arch.cr3 = cr3;
	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);

int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	if (cr8 & CR8_RESERVED_BITS)
		return 1;
	if (lapic_in_kernel(vcpu))
		kvm_lapic_set_tpr(vcpu, cr8);
	else
		vcpu->arch.cr8 = cr8;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr8);

unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
{
	if (lapic_in_kernel(vcpu))
		return kvm_lapic_get_cr8(vcpu);
	else
		return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);

static void kvm_update_dr0123(struct kvm_vcpu *vcpu)
{
	int i;

	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
		for (i = 0; i < KVM_NR_DB_REGS; i++)
			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
	}
}

void kvm_update_dr7(struct kvm_vcpu *vcpu)
{
	unsigned long dr7;

	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
		dr7 = vcpu->arch.guest_debug_dr7;
	else
		dr7 = vcpu->arch.dr7;
	kvm_x86_ops.set_dr7(vcpu, dr7);
	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED;
	if (dr7 & DR7_BP_EN_MASK)
		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
}
EXPORT_SYMBOL_GPL(kvm_update_dr7);

static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
{
	u64 fixed = DR6_FIXED_1;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM))
		fixed |= DR6_RTM;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
		fixed |= DR6_BUS_LOCK;
	return fixed;
}

static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	size_t size = ARRAY_SIZE(vcpu->arch.db);

	switch (dr) {
	case 0 ... 3:
		vcpu->arch.db[array_index_nospec(dr, size)] = val;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
			vcpu->arch.eff_db[dr] = val;
		break;
	case 4:
	case 6:
		if (!kvm_dr6_valid(val))
			return -1; /* #GP */
		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
		break;
	case 5:
	default: /* 7 */
		if (!kvm_dr7_valid(val))
			return -1; /* #GP */
		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
		kvm_update_dr7(vcpu);
		break;
	}

	return 0;
}

int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	if (__kvm_set_dr(vcpu, dr, val)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_dr);

int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	size_t size = ARRAY_SIZE(vcpu->arch.db);

	switch (dr) {
	case 0 ... 3:
		*val = vcpu->arch.db[array_index_nospec(dr, size)];
		break;
	case 4:
	case 6:
		*val = vcpu->arch.dr6;
		break;
	case 5:
	default: /* 7 */
		*val = vcpu->arch.dr7;
		break;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dr);

bool kvm_rdpmc(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data;
	int err;

	err = kvm_pmu_rdpmc(vcpu, ecx, &data);
	if (err)
		return err;
	kvm_rax_write(vcpu, (u32)data);
	kvm_rdx_write(vcpu, data >> 32);
	return err;
}
EXPORT_SYMBOL_GPL(kvm_rdpmc);

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
 * extract the supported MSRs from the related const lists.
 * msrs_to_save is selected from the msrs_to_save_all to reflect the
 * capabilities of the host cpu. This capabilities test skips MSRs that are
 * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
 * may depend on host virtualization features rather than host cpu features.
 */

static const u32 msrs_to_save_all[] = {
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_STAR,
#ifdef CONFIG_X86_64
	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
	MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
	MSR_IA32_SPEC_CTRL,
	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
	MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
	MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
	MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
	MSR_IA32_UMWAIT_CONTROL,

	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
	MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
	MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
	MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7,
	MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9,
	MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11,
	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
	MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7,
	MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9,
	MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11,
	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,

	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
};

static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
static unsigned num_msrs_to_save;

static const u32 emulated_msrs_all[] = {
	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
	HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
	HV_X64_MSR_RESET,
	HV_X64_MSR_VP_INDEX,
	HV_X64_MSR_VP_RUNTIME,
	HV_X64_MSR_SCONTROL,
	HV_X64_MSR_STIMER0_CONFIG,
	HV_X64_MSR_VP_ASSIST_PAGE,
	HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL,
	HV_X64_MSR_TSC_EMULATION_STATUS,
	HV_X64_MSR_SYNDBG_OPTIONS,
	HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
	HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
	HV_X64_MSR_SYNDBG_PENDING_BUFFER,

	MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
	MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK,

	MSR_IA32_TSC_ADJUST,
	MSR_IA32_TSCDEADLINE,
	MSR_IA32_ARCH_CAPABILITIES,
	MSR_IA32_PERF_CAPABILITIES,
	MSR_IA32_MISC_ENABLE,
	MSR_IA32_MCG_STATUS,
	MSR_IA32_MCG_CTL,
	MSR_IA32_MCG_EXT_CTL,
	MSR_IA32_SMBASE,
	MSR_SMI_COUNT,
	MSR_PLATFORM_INFO,
	MSR_MISC_FEATURES_ENABLES,
	MSR_AMD64_VIRT_SPEC_CTRL,
	MSR_IA32_POWER_CTL,
	MSR_IA32_UCODE_REV,

	/*
	 * The following list leaves out MSRs whose values are determined
	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
	 * We always support the "true" VMX control MSRs, even if the host
	 * processor does not, so I am putting these registers here rather
	 * than in msrs_to_save_all.
	 */
	MSR_IA32_VMX_BASIC,
	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
	MSR_IA32_VMX_TRUE_EXIT_CTLS,
	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
	MSR_IA32_VMX_MISC,
	MSR_IA32_VMX_CR0_FIXED0,
	MSR_IA32_VMX_CR4_FIXED0,
	MSR_IA32_VMX_VMCS_ENUM,
	MSR_IA32_VMX_PROCBASED_CTLS2,
	MSR_IA32_VMX_EPT_VPID_CAP,
	MSR_IA32_VMX_VMFUNC,

	MSR_K7_HWCR,
	MSR_KVM_POLL_CONTROL,
};

static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
static unsigned num_emulated_msrs;

/*
 * List of msr numbers which are used to expose MSR-based features that
 * can be used by a hypervisor to validate requested CPU features.
 */
static const u32 msr_based_features_all[] = {
	MSR_IA32_VMX_BASIC,
	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
	MSR_IA32_VMX_PINBASED_CTLS,
	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
	MSR_IA32_VMX_PROCBASED_CTLS,
	MSR_IA32_VMX_TRUE_EXIT_CTLS,
	MSR_IA32_VMX_EXIT_CTLS,
	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
	MSR_IA32_VMX_ENTRY_CTLS,
	MSR_IA32_VMX_MISC,
	MSR_IA32_VMX_CR0_FIXED0,
	MSR_IA32_VMX_CR0_FIXED1,
	MSR_IA32_VMX_CR4_FIXED0,
	MSR_IA32_VMX_CR4_FIXED1,
	MSR_IA32_VMX_VMCS_ENUM,
	MSR_IA32_VMX_PROCBASED_CTLS2,
	MSR_IA32_VMX_EPT_VPID_CAP,
	MSR_IA32_VMX_VMFUNC,

	MSR_F10H_DECFG,
	MSR_IA32_UCODE_REV,
	MSR_IA32_ARCH_CAPABILITIES,
	MSR_IA32_PERF_CAPABILITIES,
};

static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
static unsigned int num_msr_based_features;

static u64 kvm_get_arch_capabilities(void)
{
	u64 data = 0;

	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);

	/*
	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
	 * the nested hypervisor runs with NX huge pages.  If it is not,
	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
	 * L1 guests, so it need not worry about its own (L2) guests.
	 */
	data |= ARCH_CAP_PSCHANGE_MC_NO;

	/*
	 * If we're doing cache flushes (either "always" or "cond")
	 * we will do one whenever the guest does a vmlaunch/vmresume.
	 * If an outer hypervisor is doing the cache flush for us
	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
	 * capability to the guest too, and if EPT is disabled we're not
	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
	 * require a nested hypervisor to do a flush of its own.
	 */
	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;

	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
		data |= ARCH_CAP_RDCL_NO;
	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
		data |= ARCH_CAP_SSB_NO;
	if (!boot_cpu_has_bug(X86_BUG_MDS))
		data |= ARCH_CAP_MDS_NO;

	if (!boot_cpu_has(X86_FEATURE_RTM)) {
		/*
		 * If RTM=0 because the kernel has disabled TSX, the host might
		 * have TAA_NO or TSX_CTRL.  Clear TAA_NO (the guest sees RTM=0
		 * and therefore knows that there cannot be TAA) but keep
		 * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts,
		 * and we want to allow migrating those guests to tsx=off hosts.
		 */
		data &= ~ARCH_CAP_TAA_NO;
	} else if (!boot_cpu_has_bug(X86_BUG_TAA)) {
		data |= ARCH_CAP_TAA_NO;
	} else {
		/*
		 * Nothing to do here; we emulate TSX_CTRL if present on the
		 * host so the guest can choose between disabling TSX or
		 * using VERW to clear CPU buffers.
		 */
	}

	/* Guests don't need to know "Fill buffer clear control" exists */
	data &= ~ARCH_CAP_FB_CLEAR_CTRL;

	return data;
}

static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
{
	switch (msr->index) {
	case MSR_IA32_ARCH_CAPABILITIES:
		msr->data = kvm_get_arch_capabilities();
		break;
	case MSR_IA32_UCODE_REV:
		rdmsrl_safe(msr->index, &msr->data);
		break;
	default:
		return kvm_x86_ops.get_msr_feature(msr);
	}
	return 0;
}

static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	struct kvm_msr_entry msr;
	int r;

	msr.index = index;
	r = kvm_get_msr_feature(&msr);

	if (r == KVM_MSR_RET_INVALID) {
		/* Unconditionally clear the output for simplicity */
		*data = 0;
		if (kvm_msr_ignored_check(vcpu, index, 0, false))
			r = 0;
	}

	if (r)
		return r;

	*data = msr.data;

	return 0;
}

static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
		return false;

	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
		return false;

	if (efer & (EFER_LME | EFER_LMA) &&
	    !guest_cpuid_has(vcpu, X86_FEATURE_LM))
		return false;

	if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX))
		return false;

	return true;

}
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	if (efer & efer_reserved_bits)
		return false;

	return __kvm_valid_efer(vcpu, efer);
}
EXPORT_SYMBOL_GPL(kvm_valid_efer);

static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	u64 old_efer = vcpu->arch.efer;
	u64 efer = msr_info->data;
	int r;

	if (efer & efer_reserved_bits)
		return 1;

	if (!msr_info->host_initiated) {
		if (!__kvm_valid_efer(vcpu, efer))
			return 1;

		if (is_paging(vcpu) &&
		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
			return 1;
	}

	efer &= ~EFER_LMA;
	efer |= vcpu->arch.efer & EFER_LMA;

	r = kvm_x86_ops.set_efer(vcpu, efer);
	if (r) {
		WARN_ON(r > 0);
		return r;
	}

	/* Update reserved bits */
	if ((efer ^ old_efer) & EFER_NX)
		kvm_mmu_reset_context(vcpu);

	return 0;
}

void kvm_enable_efer_bits(u64 mask)
{
       efer_reserved_bits &= ~mask;
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);

bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
{
	struct kvm_x86_msr_filter *msr_filter;
	struct msr_bitmap_range *ranges;
	struct kvm *kvm = vcpu->kvm;
	bool allowed;
	int idx;
	u32 i;

	/* x2APIC MSRs do not support filtering. */
	if (index >= 0x800 && index <= 0x8ff)
		return true;

	idx = srcu_read_lock(&kvm->srcu);

	msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
	if (!msr_filter) {
		allowed = true;
		goto out;
	}

	allowed = msr_filter->default_allow;
	ranges = msr_filter->ranges;

	for (i = 0; i < msr_filter->count; i++) {
		u32 start = ranges[i].base;
		u32 end = start + ranges[i].nmsrs;
		u32 flags = ranges[i].flags;
		unsigned long *bitmap = ranges[i].bitmap;

		if ((index >= start) && (index < end) && (flags & type)) {
			allowed = !!test_bit(index - start, bitmap);
			break;
		}
	}

out:
	srcu_read_unlock(&kvm->srcu, idx);

	return allowed;
}
EXPORT_SYMBOL_GPL(kvm_msr_allowed);

/*
 * Write @data into the MSR specified by @index.  Select MSR specific fault
 * checks are bypassed if @host_initiated is %true.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
			 bool host_initiated)
{
	struct msr_data msr;

	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
		return KVM_MSR_RET_FILTERED;

	switch (index) {
	case MSR_FS_BASE:
	case MSR_GS_BASE:
	case MSR_KERNEL_GS_BASE:
	case MSR_CSTAR:
	case MSR_LSTAR:
		if (is_noncanonical_address(data, vcpu))
			return 1;
		break;
	case MSR_IA32_SYSENTER_EIP:
	case MSR_IA32_SYSENTER_ESP:
		/*
		 * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
		 * non-canonical address is written on Intel but not on
		 * AMD (which ignores the top 32-bits, because it does
		 * not implement 64-bit SYSENTER).
		 *
		 * 64-bit code should hence be able to write a non-canonical
		 * value on AMD.  Making the address canonical ensures that
		 * vmentry does not fail on Intel after writing a non-canonical
		 * value, and that something deterministic happens if the guest
		 * invokes 64-bit SYSENTER.
		 */
		data = get_canonical(data, vcpu_virt_addr_bits(vcpu));
	}

	msr.data = data;
	msr.index = index;
	msr.host_initiated = host_initiated;

	return kvm_x86_ops.set_msr(vcpu, &msr);
}

static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
				     u32 index, u64 data, bool host_initiated)
{
	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);

	if (ret == KVM_MSR_RET_INVALID)
		if (kvm_msr_ignored_check(vcpu, index, data, true))
			ret = 0;

	return ret;
}

/*
 * Read the MSR specified by @index into @data.  Select MSR specific fault
 * checks are bypassed if @host_initiated is %true.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
		  bool host_initiated)
{
	struct msr_data msr;
	int ret;

	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
		return KVM_MSR_RET_FILTERED;

	msr.index = index;
	msr.host_initiated = host_initiated;

	ret = kvm_x86_ops.get_msr(vcpu, &msr);
	if (!ret)
		*data = msr.data;
	return ret;
}

static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
				     u32 index, u64 *data, bool host_initiated)
{
	int ret = __kvm_get_msr(vcpu, index, data, host_initiated);

	if (ret == KVM_MSR_RET_INVALID) {
		/* Unconditionally clear *data for simplicity */
		*data = 0;
		if (kvm_msr_ignored_check(vcpu, index, 0, false))
			ret = 0;
	}

	return ret;
}

int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
{
	return kvm_get_msr_ignored_check(vcpu, index, data, false);
}
EXPORT_SYMBOL_GPL(kvm_get_msr);

int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
{
	return kvm_set_msr_ignored_check(vcpu, index, data, false);
}
EXPORT_SYMBOL_GPL(kvm_set_msr);

static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
{
	if (vcpu->run->msr.error) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	} else if (is_read) {
		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
	}

	return kvm_skip_emulated_instruction(vcpu);
}

static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
{
	return complete_emulated_msr(vcpu, true);
}

static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
{
	return complete_emulated_msr(vcpu, false);
}

static u64 kvm_msr_reason(int r)
{
	switch (r) {
	case KVM_MSR_RET_INVALID:
		return KVM_MSR_EXIT_REASON_UNKNOWN;
	case KVM_MSR_RET_FILTERED:
		return KVM_MSR_EXIT_REASON_FILTER;
	default:
		return KVM_MSR_EXIT_REASON_INVAL;
	}
}

static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
			      u32 exit_reason, u64 data,
			      int (*completion)(struct kvm_vcpu *vcpu),
			      int r)
{
	u64 msr_reason = kvm_msr_reason(r);

	/* Check if the user wanted to know about this MSR fault */
	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
		return 0;

	vcpu->run->exit_reason = exit_reason;
	vcpu->run->msr.error = 0;
	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
	vcpu->run->msr.reason = msr_reason;
	vcpu->run->msr.index = index;
	vcpu->run->msr.data = data;
	vcpu->arch.complete_userspace_io = completion;

	return 1;
}

static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r)
{
	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0,
				   complete_emulated_rdmsr, r);
}

static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r)
{
	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data,
				   complete_emulated_wrmsr, r);
}

int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data;
	int r;

	vcpu->stat.msr_rd_exits++;
	r = kvm_get_msr(vcpu, ecx, &data);

	/* MSR read failed? See if we should ask user space */
	if (r && kvm_get_msr_user_space(vcpu, ecx, r)) {
		/* Bounce to user space */
		return 0;
	}

	/* MSR read failed? Inject a #GP */
	if (r) {
		trace_kvm_msr_read_ex(ecx);
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	trace_kvm_msr_read(ecx, data);

	kvm_rax_write(vcpu, data & -1u);
	kvm_rdx_write(vcpu, (data >> 32) & -1u);
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);

int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
{
	u32 ecx = kvm_rcx_read(vcpu);
	u64 data = kvm_read_edx_eax(vcpu);
	int r;

	vcpu->stat.msr_wr_exits++;
	r = kvm_set_msr(vcpu, ecx, data);

	/* MSR write failed? See if we should ask user space */
	if (r && kvm_set_msr_user_space(vcpu, ecx, data, r))
		/* Bounce to user space */
		return 0;

	/* Signal all other negative errors to userspace */
	if (r < 0)
		return r;

	/* MSR write failed? Inject a #GP */
	if (r > 0) {
		trace_kvm_msr_write_ex(ecx, data);
		kvm_inject_gp(vcpu, 0);
		return 1;
	}

	trace_kvm_msr_write(ecx, data);
	return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);

bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
{
	return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) ||
		xfer_to_guest_mode_work_pending();
}
EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request);

/*
 * The fast path for frequent and performance sensitive wrmsr emulation,
 * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces
 * the latency of virtual IPI by avoiding the expensive bits of transitioning
 * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the
 * other cases which must be called after interrupts are enabled on the host.
 */
static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data)
{
	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic))
		return 1;

	if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) &&
		((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
		((data & APIC_MODE_MASK) == APIC_DM_FIXED) &&
		((u32)(data >> 32) != X2APIC_BROADCAST)) {

		data &= ~(1 << 12);
		kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32));
		kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32));
		kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR, (u32)data);
		trace_kvm_apic_write(APIC_ICR, (u32)data);
		return 0;
	}

	return 1;
}

static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data)
{
	if (!kvm_can_use_hv_timer(vcpu))
		return 1;

	kvm_set_lapic_tscdeadline_msr(vcpu, data);
	return 0;
}

fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu)
{
	u32 msr = kvm_rcx_read(vcpu);
	u64 data;
	fastpath_t ret = EXIT_FASTPATH_NONE;

	switch (msr) {
	case APIC_BASE_MSR + (APIC_ICR >> 4):
		data = kvm_read_edx_eax(vcpu);
		if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) {
			kvm_skip_emulated_instruction(vcpu);
			ret = EXIT_FASTPATH_EXIT_HANDLED;
		}
		break;
	case MSR_IA32_TSCDEADLINE:
		data = kvm_read_edx_eax(vcpu);
		if (!handle_fastpath_set_tscdeadline(vcpu, data)) {
			kvm_skip_emulated_instruction(vcpu);
			ret = EXIT_FASTPATH_REENTER_GUEST;
		}
		break;
	default:
		break;
	}

	if (ret != EXIT_FASTPATH_NONE)
		trace_kvm_msr_write(msr, data);

	return ret;
}
EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff);

/*
 * Adapt set_msr() to msr_io()'s calling convention
 */
static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_get_msr_ignored_check(vcpu, index, data, true);
}

static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_set_msr_ignored_check(vcpu, index, *data, true);
}

#ifdef CONFIG_X86_64
struct pvclock_clock {
	int vclock_mode;
	u64 cycle_last;
	u64 mask;
	u32 mult;
	u32 shift;
	u64 base_cycles;
	u64 offset;
};

struct pvclock_gtod_data {
	seqcount_t	seq;

	struct pvclock_clock clock; /* extract of a clocksource struct */
	struct pvclock_clock raw_clock; /* extract of a clocksource struct */

	ktime_t		offs_boot;
	u64		wall_time_sec;
};

static struct pvclock_gtod_data pvclock_gtod_data;

static void update_pvclock_gtod(struct timekeeper *tk)
{
	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;

	write_seqcount_begin(&vdata->seq);

	/* copy pvclock gtod data */
	vdata->clock.vclock_mode	= tk->tkr_mono.clock->vdso_clock_mode;
	vdata->clock.cycle_last		= tk->tkr_mono.cycle_last;
	vdata->clock.mask		= tk->tkr_mono.mask;
	vdata->clock.mult		= tk->tkr_mono.mult;
	vdata->clock.shift		= tk->tkr_mono.shift;
	vdata->clock.base_cycles	= tk->tkr_mono.xtime_nsec;
	vdata->clock.offset		= tk->tkr_mono.base;

	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->vdso_clock_mode;
	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
	vdata->raw_clock.mask		= tk->tkr_raw.mask;
	vdata->raw_clock.mult		= tk->tkr_raw.mult;
	vdata->raw_clock.shift		= tk->tkr_raw.shift;
	vdata->raw_clock.base_cycles	= tk->tkr_raw.xtime_nsec;
	vdata->raw_clock.offset		= tk->tkr_raw.base;

	vdata->wall_time_sec            = tk->xtime_sec;

	vdata->offs_boot		= tk->offs_boot;

	write_seqcount_end(&vdata->seq);
}

static s64 get_kvmclock_base_ns(void)
{
	/* Count up from boot time, but with the frequency of the raw clock.  */
	return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot));
}
#else
static s64 get_kvmclock_base_ns(void)
{
	/* Master clock not used, so we can just use CLOCK_BOOTTIME.  */
	return ktime_get_boottime_ns();
}
#endif

static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
	int version;
	int r;
	struct pvclock_wall_clock wc;
	u64 wall_nsec;

	kvm->arch.wall_clock = wall_clock;

	if (!wall_clock)
		return;

	r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
	if (r)
		return;

	if (version & 1)
		++version;  /* first time write, random junk */

	++version;

	if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version)))
		return;

	/*
	 * The guest calculates current wall clock time by adding
	 * system time (updated by kvm_guest_time_update below) to the
	 * wall clock specified here.  We do the reverse here.
	 */
	wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm);

	wc.nsec = do_div(wall_nsec, 1000000000);
	wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */
	wc.version = version;

	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));

	version++;
	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
}

static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
				  bool old_msr, bool host_initiated)
{
	struct kvm_arch *ka = &vcpu->kvm->arch;

	if (vcpu->vcpu_id == 0 && !host_initiated) {
		if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);

		ka->boot_vcpu_runs_old_kvmclock = old_msr;
	}

	vcpu->arch.time = system_time;
	kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);

	/* we verify if the enable bit is set... */
	vcpu->arch.pv_time_enabled = false;
	if (!(system_time & 1))
		return;

	if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
				       &vcpu->arch.pv_time, system_time & ~1ULL,
				       sizeof(struct pvclock_vcpu_time_info)))
		vcpu->arch.pv_time_enabled = true;

	return;
}

static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
	do_shl32_div32(dividend, divisor);
	return dividend;
}

static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
			       s8 *pshift, u32 *pmultiplier)
{
	uint64_t scaled64;
	int32_t  shift = 0;
	uint64_t tps64;
	uint32_t tps32;

	tps64 = base_hz;
	scaled64 = scaled_hz;
	while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
		tps64 >>= 1;
		shift--;
	}

	tps32 = (uint32_t)tps64;
	while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
		if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
			scaled64 >>= 1;
		else
			tps32 <<= 1;
		shift++;
	}

	*pshift = shift;
	*pmultiplier = div_frac(scaled64, tps32);
}

#ifdef CONFIG_X86_64
static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
#endif

static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
static unsigned long max_tsc_khz;

static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
	u64 v = (u64)khz * (1000000 + ppm);
	do_div(v, 1000000);
	return v;
}

static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
{
	u64 ratio;

	/* Guest TSC same frequency as host TSC? */
	if (!scale) {
		vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
		return 0;
	}

	/* TSC scaling supported? */
	if (!kvm_has_tsc_control) {
		if (user_tsc_khz > tsc_khz) {
			vcpu->arch.tsc_catchup = 1;
			vcpu->arch.tsc_always_catchup = 1;
			return 0;
		} else {
			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
			return -1;
		}
	}

	/* TSC scaling required  - calculate ratio */
	ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits,
				user_tsc_khz, tsc_khz);

	if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
			            user_tsc_khz);
		return -1;
	}

	vcpu->arch.tsc_scaling_ratio = ratio;
	return 0;
}

static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
{
	u32 thresh_lo, thresh_hi;
	int use_scaling = 0;

	/* tsc_khz can be zero if TSC calibration fails */
	if (user_tsc_khz == 0) {
		/* set tsc_scaling_ratio to a safe value */
		vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
		return -1;
	}

	/* Compute a scale to convert nanoseconds in TSC cycles */
	kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
			   &vcpu->arch.virtual_tsc_shift,
			   &vcpu->arch.virtual_tsc_mult);
	vcpu->arch.virtual_tsc_khz = user_tsc_khz;

	/*
	 * Compute the variation in TSC rate which is acceptable
	 * within the range of tolerance and decide if the
	 * rate being applied is within that bounds of the hardware
	 * rate.  If so, no scaling or compensation need be done.
	 */
	thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
	thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
	if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
		pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
		use_scaling = 1;
	}
	return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
}

static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
{
	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
				      vcpu->arch.virtual_tsc_mult,
				      vcpu->arch.virtual_tsc_shift);
	tsc += vcpu->arch.this_tsc_write;
	return tsc;
}

static inline int gtod_is_based_on_tsc(int mode)
{
	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
}

static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
	bool vcpus_matched;
	struct kvm_arch *ka = &vcpu->kvm->arch;
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;

	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
			 atomic_read(&vcpu->kvm->online_vcpus));

	/*
	 * Once the masterclock is enabled, always perform request in
	 * order to update it.
	 *
	 * In order to enable masterclock, the host clocksource must be TSC
	 * and the vcpus need to have matched TSCs.  When that happens,
	 * perform request to enable masterclock.
	 */
	if (ka->use_master_clock ||
	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);

	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
			    atomic_read(&vcpu->kvm->online_vcpus),
		            ka->use_master_clock, gtod->clock.vclock_mode);
#endif
}

/*
 * Multiply tsc by a fixed point number represented by ratio.
 *
 * The most significant 64-N bits (mult) of ratio represent the
 * integral part of the fixed point number; the remaining N bits
 * (frac) represent the fractional part, ie. ratio represents a fixed
 * point number (mult + frac * 2^(-N)).
 *
 * N equals to kvm_tsc_scaling_ratio_frac_bits.
 */
static inline u64 __scale_tsc(u64 ratio, u64 tsc)
{
	return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits);
}

u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc)
{
	u64 _tsc = tsc;
	u64 ratio = vcpu->arch.tsc_scaling_ratio;

	if (ratio != kvm_default_tsc_scaling_ratio)
		_tsc = __scale_tsc(ratio, tsc);

	return _tsc;
}
EXPORT_SYMBOL_GPL(kvm_scale_tsc);

static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
{
	u64 tsc;

	tsc = kvm_scale_tsc(vcpu, rdtsc());

	return target_tsc - tsc;
}

u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
	return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);

static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
	vcpu->arch.l1_tsc_offset = offset;
	vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset);
}

static inline bool kvm_check_tsc_unstable(void)
{
#ifdef CONFIG_X86_64
	/*
	 * TSC is marked unstable when we're running on Hyper-V,
	 * 'TSC page' clocksource is good.
	 */
	if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK)
		return false;
#endif
	return check_tsc_unstable();
}

static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u64 offset, ns, elapsed;
	unsigned long flags;
	bool matched;
	bool already_matched;
	bool synchronizing = false;

	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
	offset = kvm_compute_tsc_offset(vcpu, data);
	ns = get_kvmclock_base_ns();
	elapsed = ns - kvm->arch.last_tsc_nsec;

	if (vcpu->arch.virtual_tsc_khz) {
		if (data == 0) {
			/*
			 * detection of vcpu initialization -- need to sync
			 * with other vCPUs. This particularly helps to keep
			 * kvm_clock stable after CPU hotplug
			 */
			synchronizing = true;
		} else {
			u64 tsc_exp = kvm->arch.last_tsc_write +
						nsec_to_cycles(vcpu, elapsed);
			u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL;
			/*
			 * Special case: TSC write with a small delta (1 second)
			 * of virtual cycle time against real time is
			 * interpreted as an attempt to synchronize the CPU.
			 */
			synchronizing = data < tsc_exp + tsc_hz &&
					data + tsc_hz > tsc_exp;
		}
	}

	/*
	 * For a reliable TSC, we can match TSC offsets, and for an unstable
	 * TSC, we add elapsed time in this computation.  We could let the
	 * compensation code attempt to catch up if we fall behind, but
	 * it's better to try to match offsets from the beginning.
         */
	if (synchronizing &&
	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
		if (!kvm_check_tsc_unstable()) {
			offset = kvm->arch.cur_tsc_offset;
		} else {
			u64 delta = nsec_to_cycles(vcpu, elapsed);
			data += delta;
			offset = kvm_compute_tsc_offset(vcpu, data);
		}
		matched = true;
		already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
	} else {
		/*
		 * We split periods of matched TSC writes into generations.
		 * For each generation, we track the original measured
		 * nanosecond time, offset, and write, so if TSCs are in
		 * sync, we can match exact offset, and if not, we can match
		 * exact software computation in compute_guest_tsc()
		 *
		 * These values are tracked in kvm->arch.cur_xxx variables.
		 */
		kvm->arch.cur_tsc_generation++;
		kvm->arch.cur_tsc_nsec = ns;
		kvm->arch.cur_tsc_write = data;
		kvm->arch.cur_tsc_offset = offset;
		matched = false;
	}

	/*
	 * We also track th most recent recorded KHZ, write and time to
	 * allow the matching interval to be extended at each write.
	 */
	kvm->arch.last_tsc_nsec = ns;
	kvm->arch.last_tsc_write = data;
	kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;

	vcpu->arch.last_guest_tsc = data;

	/* Keep track of which generation this VCPU has synchronized to */
	vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;

	kvm_vcpu_write_tsc_offset(vcpu, offset);
	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);

	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
	if (!matched) {
		kvm->arch.nr_vcpus_matched_tsc = 0;
	} else if (!already_matched) {
		kvm->arch.nr_vcpus_matched_tsc++;
	}

	kvm_track_tsc_matching(vcpu);
	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
}

static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
					   s64 adjustment)
{
	u64 tsc_offset = vcpu->arch.l1_tsc_offset;
	kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment);
}

static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
{
	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio)
		WARN_ON(adjustment < 0);
	adjustment = kvm_scale_tsc(vcpu, (u64) adjustment);
	adjust_tsc_offset_guest(vcpu, adjustment);
}

#ifdef CONFIG_X86_64

static u64 read_tsc(void)
{
	u64 ret = (u64)rdtsc_ordered();
	u64 last = pvclock_gtod_data.clock.cycle_last;

	if (likely(ret >= last))
		return ret;

	/*
	 * GCC likes to generate cmov here, but this branch is extremely
	 * predictable (it's just a function of time and the likely is
	 * very likely) and there's a data dependence, so force GCC
	 * to generate a branch instead.  I don't barrier() because
	 * we don't actually need a barrier, and if this function
	 * ever gets inlined it will generate worse code.
	 */
	asm volatile ("");
	return last;
}

static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
			  int *mode)
{
	long v;
	u64 tsc_pg_val;

	switch (clock->vclock_mode) {
	case VDSO_CLOCKMODE_HVCLOCK:
		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
						  tsc_timestamp);
		if (tsc_pg_val != U64_MAX) {
			/* TSC page valid */
			*mode = VDSO_CLOCKMODE_HVCLOCK;
			v = (tsc_pg_val - clock->cycle_last) &
				clock->mask;
		} else {
			/* TSC page invalid */
			*mode = VDSO_CLOCKMODE_NONE;
		}
		break;
	case VDSO_CLOCKMODE_TSC:
		*mode = VDSO_CLOCKMODE_TSC;
		*tsc_timestamp = read_tsc();
		v = (*tsc_timestamp - clock->cycle_last) &
			clock->mask;
		break;
	default:
		*mode = VDSO_CLOCKMODE_NONE;
	}

	if (*mode == VDSO_CLOCKMODE_NONE)
		*tsc_timestamp = v = 0;

	return v * clock->mult;
}

static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
{
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
	unsigned long seq;
	int mode;
	u64 ns;

	do {
		seq = read_seqcount_begin(&gtod->seq);
		ns = gtod->raw_clock.base_cycles;
		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
		ns >>= gtod->raw_clock.shift;
		ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot));
	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
	*t = ns;

	return mode;
}

static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
{
	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
	unsigned long seq;
	int mode;
	u64 ns;

	do {
		seq = read_seqcount_begin(&gtod->seq);
		ts->tv_sec = gtod->wall_time_sec;
		ns = gtod->clock.base_cycles;
		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
		ns >>= gtod->clock.shift;
	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));

	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
	ts->tv_nsec = ns;

	return mode;
}

/* returns true if host is using TSC based clocksource */
static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
{
	/* checked again under seqlock below */
	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
		return false;

	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
						      tsc_timestamp));
}

/* returns true if host is using TSC based clocksource */
static bool kvm_get_walltime_and_clockread(struct timespec64 *ts,
					   u64 *tsc_timestamp)
{
	/* checked again under seqlock below */
	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
		return false;

	return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
}
#endif

/*
 *
 * Assuming a stable TSC across physical CPUS, and a stable TSC
 * across virtual CPUs, the following condition is possible.
 * Each numbered line represents an event visible to both
 * CPUs at the next numbered event.
 *
 * "timespecX" represents host monotonic time. "tscX" represents
 * RDTSC value.
 *
 * 		VCPU0 on CPU0		|	VCPU1 on CPU1
 *
 * 1.  read timespec0,tsc0
 * 2.					| timespec1 = timespec0 + N
 * 					| tsc1 = tsc0 + M
 * 3. transition to guest		| transition to guest
 * 4. ret0 = timespec0 + (rdtsc - tsc0) |
 * 5.				        | ret1 = timespec1 + (rdtsc - tsc1)
 * 				        | ret1 = timespec0 + N + (rdtsc - (tsc0 + M))
 *
 * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity:
 *
 * 	- ret0 < ret1
 *	- timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M))
 *		...
 *	- 0 < N - M => M < N
 *
 * That is, when timespec0 != timespec1, M < N. Unfortunately that is not
 * always the case (the difference between two distinct xtime instances
 * might be smaller then the difference between corresponding TSC reads,
 * when updating guest vcpus pvclock areas).
 *
 * To avoid that problem, do not allow visibility of distinct
 * system_timestamp/tsc_timestamp values simultaneously: use a master
 * copy of host monotonic time values. Update that master copy
 * in lockstep.
 *
 * Rely on synchronization of host TSCs and guest TSCs for monotonicity.
 *
 */

static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
{
#ifdef CONFIG_X86_64
	struct kvm_arch *ka = &kvm->arch;
	int vclock_mode;
	bool host_tsc_clocksource, vcpus_matched;

	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
			atomic_read(&kvm->online_vcpus));

	/*
	 * If the host uses TSC clock, then passthrough TSC as stable
	 * to the guest.
	 */
	host_tsc_clocksource = kvm_get_time_and_clockread(
					&ka->master_kernel_ns,
					&ka->master_cycle_now);

	ka->use_master_clock = host_tsc_clocksource && vcpus_matched
				&& !ka->backwards_tsc_observed
				&& !ka->boot_vcpu_runs_old_kvmclock;

	if (ka->use_master_clock)
		atomic_set(&kvm_guest_has_master_clock, 1);

	vclock_mode = pvclock_gtod_data.clock.vclock_mode;
	trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode,
					vcpus_matched);
#endif
}

void kvm_make_mclock_inprogress_request(struct kvm *kvm)
{
	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
}

static void kvm_gen_update_masterclock(struct kvm *kvm)
{
#ifdef CONFIG_X86_64
	int i;
	struct kvm_vcpu *vcpu;
	struct kvm_arch *ka = &kvm->arch;

	spin_lock(&ka->pvclock_gtod_sync_lock);
	kvm_make_mclock_inprogress_request(kvm);
	/* no guest entries from this point */
	pvclock_update_vm_gtod_copy(kvm);

	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

	/* guest entries allowed */
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);

	spin_unlock(&ka->pvclock_gtod_sync_lock);
#endif
}

u64 get_kvmclock_ns(struct kvm *kvm)
{
	struct kvm_arch *ka = &kvm->arch;
	struct pvclock_vcpu_time_info hv_clock;
	u64 ret;

	spin_lock(&ka->pvclock_gtod_sync_lock);
	if (!ka->use_master_clock) {
		spin_unlock(&ka->pvclock_gtod_sync_lock);
		return get_kvmclock_base_ns() + ka->kvmclock_offset;
	}

	hv_clock.tsc_timestamp = ka->master_cycle_now;
	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
	spin_unlock(&ka->pvclock_gtod_sync_lock);

	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
	get_cpu();

	if (__this_cpu_read(cpu_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
				   &hv_clock.tsc_shift,
				   &hv_clock.tsc_to_system_mul);
		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
	} else
		ret = get_kvmclock_base_ns() + ka->kvmclock_offset;

	put_cpu();

	return ret;
}

static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
{
	struct kvm_vcpu_arch *vcpu = &v->arch;
	struct pvclock_vcpu_time_info guest_hv_clock;

	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
		&guest_hv_clock, sizeof(guest_hv_clock))))
		return;

	/* This VCPU is paused, but it's legal for a guest to read another
	 * VCPU's kvmclock, so we really have to follow the specification where
	 * it says that version is odd if data is being modified, and even after
	 * it is consistent.
	 *
	 * Version field updates must be kept separate.  This is because
	 * kvm_write_guest_cached might use a "rep movs" instruction, and
	 * writes within a string instruction are weakly ordered.  So there
	 * are three writes overall.
	 *
	 * As a small optimization, only write the version field in the first
	 * and third write.  The vcpu->pv_time cache is still valid, because the
	 * version field is the first in the struct.
	 */
	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);

	if (guest_hv_clock.version & 1)
		++guest_hv_clock.version;  /* first time write, random junk */

	vcpu->hv_clock.version = guest_hv_clock.version + 1;
	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
				&vcpu->hv_clock,
				sizeof(vcpu->hv_clock.version));

	smp_wmb();

	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
	vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);

	if (vcpu->pvclock_set_guest_stopped_request) {
		vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
		vcpu->pvclock_set_guest_stopped_request = false;
	}

	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);

	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
				&vcpu->hv_clock,
				sizeof(vcpu->hv_clock));

	smp_wmb();

	vcpu->hv_clock.version++;
	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
				&vcpu->hv_clock,
				sizeof(vcpu->hv_clock.version));
}

static int kvm_guest_time_update(struct kvm_vcpu *v)
{
	unsigned long flags, tgt_tsc_khz;
	struct kvm_vcpu_arch *vcpu = &v->arch;
	struct kvm_arch *ka = &v->kvm->arch;
	s64 kernel_ns;
	u64 tsc_timestamp, host_tsc;
	u8 pvclock_flags;
	bool use_master_clock;

	kernel_ns = 0;
	host_tsc = 0;

	/*
	 * If the host uses TSC clock, then passthrough TSC as stable
	 * to the guest.
	 */
	spin_lock(&ka->pvclock_gtod_sync_lock);
	use_master_clock = ka->use_master_clock;
	if (use_master_clock) {
		host_tsc = ka->master_cycle_now;
		kernel_ns = ka->master_kernel_ns;
	}
	spin_unlock(&ka->pvclock_gtod_sync_lock);

	/* Keep irq disabled to prevent changes to the clock */
	local_irq_save(flags);
	tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
	if (unlikely(tgt_tsc_khz == 0)) {
		local_irq_restore(flags);
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
		return 1;
	}
	if (!use_master_clock) {
		host_tsc = rdtsc();
		kernel_ns = get_kvmclock_base_ns();
	}

	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);

	/*
	 * We may have to catch up the TSC to match elapsed wall clock
	 * time for two reasons, even if kvmclock is used.
	 *   1) CPU could have been running below the maximum TSC rate
	 *   2) Broken TSC compensation resets the base at each VCPU
	 *      entry to avoid unknown leaps of TSC even when running
	 *      again on the same CPU.  This may cause apparent elapsed
	 *      time to disappear, and the guest to stand still or run
	 *	very slowly.
	 */
	if (vcpu->tsc_catchup) {
		u64 tsc = compute_guest_tsc(v, kernel_ns);
		if (tsc > tsc_timestamp) {
			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
			tsc_timestamp = tsc;
		}
	}

	local_irq_restore(flags);

	/* With all the info we got, fill in the values */

	if (kvm_has_tsc_control)
		tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);

	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
				   &vcpu->hv_clock.tsc_shift,
				   &vcpu->hv_clock.tsc_to_system_mul);
		vcpu->hw_tsc_khz = tgt_tsc_khz;
	}

	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	vcpu->last_guest_tsc = tsc_timestamp;

	/* If the host uses TSC clocksource, then it is stable */
	pvclock_flags = 0;
	if (use_master_clock)
		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;

	vcpu->hv_clock.flags = pvclock_flags;

	if (vcpu->pv_time_enabled)
		kvm_setup_pvclock_page(v);
	if (v == kvm_get_vcpu(v->kvm, 0))
		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
	return 0;
}

/*
 * kvmclock updates which are isolated to a given vcpu, such as
 * vcpu->cpu migration, should not allow system_timestamp from
 * the rest of the vcpus to remain static. Otherwise ntp frequency
 * correction applies to one vcpu's system_timestamp but not
 * the others.
 *
 * So in those cases, request a kvmclock update for all vcpus.
 * We need to rate-limit these requests though, as they can
 * considerably slow guests that have a large number of vcpus.
 * The time for a remote vcpu to update its kvmclock is bound
 * by the delay we use to rate-limit the updates.
 */

#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100)

static void kvmclock_update_fn(struct work_struct *work)
{
	int i;
	struct delayed_work *dwork = to_delayed_work(work);
	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
					   kvmclock_update_work);
	struct kvm *kvm = container_of(ka, struct kvm, arch);
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
		kvm_vcpu_kick(vcpu);
	}
}

static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
{
	struct kvm *kvm = v->kvm;

	kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
					KVMCLOCK_UPDATE_DELAY);
}

#define KVMCLOCK_SYNC_PERIOD (300 * HZ)

static void kvmclock_sync_fn(struct work_struct *work)
{
	struct delayed_work *dwork = to_delayed_work(work);
	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
					   kvmclock_sync_work);
	struct kvm *kvm = container_of(ka, struct kvm, arch);

	if (!kvmclock_periodic_sync)
		return;

	schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
					KVMCLOCK_SYNC_PERIOD);
}

/*
 * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP.
 */
static bool can_set_mci_status(struct kvm_vcpu *vcpu)
{
	/* McStatusWrEn enabled? */
	if (guest_cpuid_is_amd_or_hygon(vcpu))
		return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));

	return false;
}

static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;
	u32 msr = msr_info->index;
	u64 data = msr_info->data;

	switch (msr) {
	case MSR_IA32_MCG_STATUS:
		vcpu->arch.mcg_status = data;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P) &&
		    (data || !msr_info->host_initiated))
			return 1;
		if (data != 0 && data != ~(u64)0)
			return 1;
		vcpu->arch.mcg_ctl = data;
		break;
	default:
		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MCx_CTL(bank_num)) {
			u32 offset = array_index_nospec(
				msr - MSR_IA32_MC0_CTL,
				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);

			/* only 0 or all 1s can be written to IA32_MCi_CTL
			 * some Linux kernels though clear bit 10 in bank 4 to
			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
			 * this to avoid an uncatched #GP in the guest
			 */
			if ((offset & 0x3) == 0 &&
			    data != 0 && (data | (1 << 10)) != ~(u64)0)
				return -1;

			/* MCi_STATUS */
			if (!msr_info->host_initiated &&
			    (offset & 0x3) == 1 && data != 0) {
				if (!can_set_mci_status(vcpu))
					return -1;
			}

			vcpu->arch.mce_banks[offset] = data;
			break;
		}
		return 1;
	}
	return 0;
}

static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	int lm = is_long_mode(vcpu);
	u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
		: (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
	u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
		: kvm->arch.xen_hvm_config.blob_size_32;
	u32 page_num = data & ~PAGE_MASK;
	u64 page_addr = data & PAGE_MASK;
	u8 *page;

	if (page_num >= blob_size)
		return 1;

	page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE);
	if (IS_ERR(page))
		return PTR_ERR(page);

	if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
		kfree(page);
		return 1;
	}
	return 0;
}

static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu)
{
	u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT;

	return (vcpu->arch.apf.msr_en_val & mask) == mask;
}

static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
	gpa_t gpa = data & ~0x3f;

	/* Bits 4:5 are reserved, Should be zero */
	if (data & 0x30)
		return 1;

	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) &&
	    (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT))
		return 1;

	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) &&
	    (data & KVM_ASYNC_PF_DELIVERY_AS_INT))
		return 1;

	if (!lapic_in_kernel(vcpu))
		return data ? 1 : 0;

	vcpu->arch.apf.msr_en_val = data;

	if (!kvm_pv_async_pf_enabled(vcpu)) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_async_pf_hash_reset(vcpu);
		return 0;
	}

	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
					sizeof(u64)))
		return 1;

	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;

	kvm_async_pf_wakeup_all(vcpu);

	return 0;
}

static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
{
	/* Bits 8-63 are reserved */
	if (data >> 8)
		return 1;

	if (!lapic_in_kernel(vcpu))
		return 1;

	vcpu->arch.apf.msr_int_val = data;

	vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK;

	return 0;
}

static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
	vcpu->arch.pv_time_enabled = false;
	vcpu->arch.time = 0;
}

static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.tlb_flush;
	kvm_x86_ops.tlb_flush_all(vcpu);
}

static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.tlb_flush;
	kvm_x86_ops.tlb_flush_guest(vcpu);
}

static u64 accumulate_stat_steal_time(u64 *last_steal)
{
	u64 delta;

	if (*last_steal == 0)
		delta = 0;
	else
		delta = current->sched_info.run_delay - *last_steal;

	*last_steal = current->sched_info.run_delay;
	return delta;
}

static void update_stat_steal_time(struct kvm_vcpu *vcpu)
{
	u64 delta;

	delta = accumulate_stat_steal_time(&vcpu->stat.steal);
	vcpu->stat.st_max = max(vcpu->stat.st_max, delta);
}

static void record_steal_time(struct kvm_vcpu *vcpu)
{
	struct kvm_host_map map;
	struct kvm_steal_time *st;

	update_stat_steal_time(vcpu);
	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
		return;

	/* -EAGAIN is returned in atomic context so we can just return. */
	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
			&map, &vcpu->arch.st.cache, false))
		return;

	st = map.hva +
		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);

	/*
	 * Doing a TLB flush here, on the guest's behalf, can avoid
	 * expensive IPIs.
	 */
	if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) {
		trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
				       st->preempted & KVM_VCPU_FLUSH_TLB);
		if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
			kvm_vcpu_flush_tlb_guest(vcpu);
	} else {
		st->preempted = 0;
	}

	vcpu->arch.st.preempted = 0;

	if (st->version & 1)
		st->version += 1;  /* first time write, random junk */