x86.c

/*
 * 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 affilates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <linux/kvm_host.h>
#include "irq.h"
#include "mmu.h"
#include "i8254.h"
#include "tss.h"
#include "kvm_cache_regs.h"
#include "x86.h"

#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/module.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 <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>

#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS						\
	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
#define CR4_RESERVED_BITS						\
	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE	\
			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR	\
			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))

#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)

#define KVM_MAX_MCE_BANKS 32
#define KVM_MCE_CAP_SUPPORTED MCG_CTL_P

/* 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 = 0xfffffffffffffafeULL;
#else
static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
#endif

#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
				    struct kvm_cpuid_entry2 __user *entries);

struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);

int ignore_msrs = 0;
module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);

#define KVM_NR_SHARED_MSRS 16

struct kvm_shared_msrs_global {
	int nr;
	u32 msrs[KVM_NR_SHARED_MSRS];
};

struct kvm_shared_msrs {
	struct user_return_notifier urn;
	bool registered;
	struct kvm_shared_msr_values {
		u64 host;
		u64 curr;
	} values[KVM_NR_SHARED_MSRS];
};

static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "pf_fixed", VCPU_STAT(pf_fixed) },
	{ "pf_guest", VCPU_STAT(pf_guest) },
	{ "tlb_flush", VCPU_STAT(tlb_flush) },
	{ "invlpg", VCPU_STAT(invlpg) },
	{ "exits", VCPU_STAT(exits) },
	{ "io_exits", VCPU_STAT(io_exits) },
	{ "mmio_exits", VCPU_STAT(mmio_exits) },
	{ "signal_exits", VCPU_STAT(signal_exits) },
	{ "irq_window", VCPU_STAT(irq_window_exits) },
	{ "nmi_window", VCPU_STAT(nmi_window_exits) },
	{ "halt_exits", VCPU_STAT(halt_exits) },
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
	{ "hypercalls", VCPU_STAT(hypercalls) },
	{ "request_irq", VCPU_STAT(request_irq_exits) },
	{ "irq_exits", VCPU_STAT(irq_exits) },
	{ "host_state_reload", VCPU_STAT(host_state_reload) },
	{ "efer_reload", VCPU_STAT(efer_reload) },
	{ "fpu_reload", VCPU_STAT(fpu_reload) },
	{ "insn_emulation", VCPU_STAT(insn_emulation) },
	{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
	{ "irq_injections", VCPU_STAT(irq_injections) },
	{ "nmi_injections", VCPU_STAT(nmi_injections) },
	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
	{ "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
	{ "mmu_flooded", VM_STAT(mmu_flooded) },
	{ "mmu_recycled", VM_STAT(mmu_recycled) },
	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
	{ "mmu_unsync", VM_STAT(mmu_unsync) },
	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
	{ "largepages", VM_STAT(lpages) },
	{ NULL }
};

static void kvm_on_user_return(struct user_return_notifier *urn)
{
	unsigned slot;
	struct kvm_shared_msrs *locals
		= container_of(urn, struct kvm_shared_msrs, urn);
	struct kvm_shared_msr_values *values;

	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
		values = &locals->values[slot];
		if (values->host != values->curr) {
			wrmsrl(shared_msrs_global.msrs[slot], values->host);
			values->curr = values->host;
		}
	}
	locals->registered = false;
	user_return_notifier_unregister(urn);
}

static void shared_msr_update(unsigned slot, u32 msr)
{
	struct kvm_shared_msrs *smsr;
	u64 value;

	smsr = &__get_cpu_var(shared_msrs);
	/* only read, and nobody should modify it at this time,
	 * so don't need lock */
	if (slot >= shared_msrs_global.nr) {
		printk(KERN_ERR "kvm: invalid MSR slot!");
		return;
	}
	rdmsrl_safe(msr, &value);
	smsr->values[slot].host = value;
	smsr->values[slot].curr = value;
}

void kvm_define_shared_msr(unsigned slot, u32 msr)
{
	if (slot >= shared_msrs_global.nr)
		shared_msrs_global.nr = slot + 1;
	shared_msrs_global.msrs[slot] = msr;
	/* we need ensured the shared_msr_global have been updated */
	smp_wmb();
}
EXPORT_SYMBOL_GPL(kvm_define_shared_msr);

static void kvm_shared_msr_cpu_online(void)
{
	unsigned i;

	for (i = 0; i < shared_msrs_global.nr; ++i)
		shared_msr_update(i, shared_msrs_global.msrs[i]);
}

void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);

	if (((value ^ smsr->values[slot].curr) & mask) == 0)
		return;
	smsr->values[slot].curr = value;
	wrmsrl(shared_msrs_global.msrs[slot], value);
	if (!smsr->registered) {
		smsr->urn.on_user_return = kvm_on_user_return;
		user_return_notifier_register(&smsr->urn);
		smsr->registered = true;
	}
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);

static void drop_user_return_notifiers(void *ignore)
{
	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);

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

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

void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
	/* TODO: reserve bits check */
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_base(vcpu, data);
	else
		vcpu->arch.apic_base = data;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

#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;
}

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

	if (!vcpu->arch.exception.pending) {
	queue:
		vcpu->arch.exception.pending = true;
		vcpu->arch.exception.has_error_code = has_error;
		vcpu->arch.exception.nr = nr;
		vcpu->arch.exception.error_code = error_code;
		vcpu->arch.exception.reinject = reinject;
		return;
	}

	/* to check exception */
	prev_nr = vcpu->arch.exception.nr;
	if (prev_nr == DF_VECTOR) {
		/* triple fault -> shutdown */
		set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
		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 */
		vcpu->arch.exception.pending = true;
		vcpu->arch.exception.has_error_code = true;
		vcpu->arch.exception.nr = DF_VECTOR;
		vcpu->arch.exception.error_code = 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);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);

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

void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
			   u32 error_code)
{
	++vcpu->stat.pf_guest;
	vcpu->arch.cr2 = addr;
	kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
}

void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
	vcpu->arch.nmi_pending = 1;
}
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);
}
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, 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);

/*
 * Load the pae pdptrs.  Return true is they are all valid.
 */
int load_pdptrs(struct kvm_vcpu *vcpu, 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(vcpu->arch.pdptrs)];

	ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
				  offset * sizeof(u64), sizeof(pdpte));
	if (ret < 0) {
		ret = 0;
		goto out;
	}
	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
		if (is_present_gpte(pdpte[i]) &&
		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
			ret = 0;
			goto out;
		}
	}
	ret = 1;

	memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_avail);
	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_dirty);
out:

	return ret;
}
EXPORT_SYMBOL_GPL(load_pdptrs);

static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
	u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
	bool changed = true;
	int r;

	if (is_long_mode(vcpu) || !is_pae(vcpu))
		return false;

	if (!test_bit(VCPU_EXREG_PDPTR,
		      (unsigned long *)&vcpu->arch.regs_avail))
		return true;

	r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
	if (r < 0)
		goto out;
	changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
out:

	return changed;
}

static int __kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	unsigned long old_cr0 = kvm_read_cr0(vcpu);
	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
				    X86_CR0_CD | X86_CR0_NW;

	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;

	if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
		if ((vcpu->arch.efer & EFER_LME)) {
			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;
		} else
#endif
		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3))
			return 1;
	}

	kvm_x86_ops->set_cr0(vcpu, cr0);

	if ((cr0 ^ old_cr0) & update_bits)
		kvm_mmu_reset_context(vcpu);
	return 0;
}

void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	if (__kvm_set_cr0(vcpu, cr0))
		kvm_inject_gp(vcpu, 0);
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);

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

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;

	if (cr4 & CR4_RESERVED_BITS)
		return 1;

	if (is_long_mode(vcpu)) {
		if (!(cr4 & X86_CR4_PAE))
			return 1;
	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
		   && ((cr4 ^ old_cr4) & pdptr_bits)
		   && !load_pdptrs(vcpu, vcpu->arch.cr3))
		return 1;

	if (cr4 & X86_CR4_VMXE)
		return 1;

	kvm_x86_ops->set_cr4(vcpu, cr4);

	if ((cr4 ^ old_cr4) & pdptr_bits)
		kvm_mmu_reset_context(vcpu);

	return 0;
}

void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	if (__kvm_set_cr4(vcpu, cr4))
		kvm_inject_gp(vcpu, 0);
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

static int __kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
		kvm_mmu_sync_roots(vcpu);
		kvm_mmu_flush_tlb(vcpu);
		return 0;
	}

	if (is_long_mode(vcpu)) {
		if (cr3 & CR3_L_MODE_RESERVED_BITS)
			return 1;
	} else {
		if (is_pae(vcpu)) {
			if (cr3 & CR3_PAE_RESERVED_BITS)
				return 1;
			if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3))
				return 1;
		}
		/*
		 * We don't check reserved bits in nonpae mode, because
		 * this isn't enforced, and VMware depends on this.
		 */
	}

	/*
	 * Does the new cr3 value map to physical memory? (Note, we
	 * catch an invalid cr3 even in real-mode, because it would
	 * cause trouble later on when we turn on paging anyway.)
	 *
	 * A real CPU would silently accept an invalid cr3 and would
	 * attempt to use it - with largely undefined (and often hard
	 * to debug) behavior on the guest side.
	 */
	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
		return 1;
	vcpu->arch.cr3 = cr3;
	vcpu->arch.mmu.new_cr3(vcpu);
	return 0;
}

void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	if (__kvm_set_cr3(vcpu, cr3))
		kvm_inject_gp(vcpu, 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 (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_tpr(vcpu, cr8);
	else
		vcpu->arch.cr8 = cr8;
	return 0;
}

void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	if (__kvm_set_cr8(vcpu, cr8))
		kvm_inject_gp(vcpu, 0);
}
EXPORT_SYMBOL_GPL(kvm_set_cr8);

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

static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	switch (dr) {
	case 0 ... 3:
		vcpu->arch.db[dr] = val;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
			vcpu->arch.eff_db[dr] = val;
		break;
	case 4:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1; /* #UD */
		/* fall through */
	case 6:
		if (val & 0xffffffff00000000ULL)
			return -1; /* #GP */
		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
		break;
	case 5:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1; /* #UD */
		/* fall through */
	default: /* 7 */
		if (val & 0xffffffff00000000ULL)
			return -1; /* #GP */
		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
			kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
			vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
		}
		break;
	}

	return 0;
}

int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	int res;

	res = __kvm_set_dr(vcpu, dr, val);
	if (res > 0)
		kvm_queue_exception(vcpu, UD_VECTOR);
	else if (res < 0)
		kvm_inject_gp(vcpu, 0);

	return res;
}
EXPORT_SYMBOL_GPL(kvm_set_dr);

static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	switch (dr) {
	case 0 ... 3:
		*val = vcpu->arch.db[dr];
		break;
	case 4:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1;
		/* fall through */
	case 6:
		*val = vcpu->arch.dr6;
		break;
	case 5:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1;
		/* fall through */
	default: /* 7 */
		*val = vcpu->arch.dr7;
		break;
	}

	return 0;
}

int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	if (_kvm_get_dr(vcpu, dr, val)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dr);

static inline u32 bit(int bitno)
{
	return 1 << (bitno & 31);
}

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * This list is modified at module load time to reflect the
 * capabilities of the host cpu. This capabilities test skips MSRs that are
 * kvm-specific. Those are put in the beginning of the list.
 */

#define KVM_SAVE_MSRS_BEGIN	7
static u32 msrs_to_save[] = {
	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_APIC_ASSIST_PAGE,
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_K6_STAR,
#ifdef CONFIG_X86_64
	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
	MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
};

static unsigned num_msrs_to_save;

static u32 emulated_msrs[] = {
	MSR_IA32_MISC_ENABLE,
};

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

	if (efer & efer_reserved_bits)
		return 1;

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

	if (efer & EFER_FFXSR) {
		struct kvm_cpuid_entry2 *feat;

		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
			return 1;
	}

	if (efer & EFER_SVME) {
		struct kvm_cpuid_entry2 *feat;

		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
			return 1;
	}

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

	kvm_x86_ops->set_efer(vcpu, efer);

	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
	kvm_mmu_reset_context(vcpu);

	/* 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);


/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
	return kvm_x86_ops->set_msr(vcpu, msr_index, data);
}

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

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

	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;

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

	/*
	 * The guest calculates current wall clock time by adding
	 * system time (updated by kvm_write_guest_time below) to the
	 * wall clock specified here.  guest system time equals host
	 * system time for us, thus we must fill in host boot time here.
	 */
	getboottime(&boot);

	wc.sec = boot.tv_sec;
	wc.nsec = boot.tv_nsec;
	wc.version = version;

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

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

static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
	uint32_t quotient, remainder;

	/* Don't try to replace with do_div(), this one calculates
	 * "(dividend << 32) / divisor" */
	__asm__ ( "divl %4"
		  : "=a" (quotient), "=d" (remainder)
		  : "0" (0), "1" (dividend), "r" (divisor) );
	return quotient;
}

static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
{
	uint64_t nsecs = 1000000000LL;
	int32_t  shift = 0;
	uint64_t tps64;
	uint32_t tps32;

	tps64 = tsc_khz * 1000LL;
	while (tps64 > nsecs*2) {
		tps64 >>= 1;
		shift--;
	}

	tps32 = (uint32_t)tps64;
	while (tps32 <= (uint32_t)nsecs) {
		tps32 <<= 1;
		shift++;
	}

	hv_clock->tsc_shift = shift;
	hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);

	pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
		 __func__, tsc_khz, hv_clock->tsc_shift,
		 hv_clock->tsc_to_system_mul);
}

static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);

static void kvm_write_guest_time(struct kvm_vcpu *v)
{
	struct timespec ts;
	unsigned long flags;
	struct kvm_vcpu_arch *vcpu = &v->arch;
	void *shared_kaddr;
	unsigned long this_tsc_khz;

	if ((!vcpu->time_page))
		return;

	this_tsc_khz = get_cpu_var(cpu_tsc_khz);
	if (unlikely(vcpu->hv_clock_tsc_khz != this_tsc_khz)) {
		kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
		vcpu->hv_clock_tsc_khz = this_tsc_khz;
	}
	put_cpu_var(cpu_tsc_khz);

	/* Keep irq disabled to prevent changes to the clock */
	local_irq_save(flags);
	kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
	ktime_get_ts(&ts);
	monotonic_to_bootbased(&ts);
	local_irq_restore(flags);

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

	vcpu->hv_clock.system_time = ts.tv_nsec +
				     (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;

	vcpu->hv_clock.flags = 0;

	/*
	 * The interface expects us to write an even number signaling that the
	 * update is finished. Since the guest won't see the intermediate
	 * state, we just increase by 2 at the end.
	 */
	vcpu->hv_clock.version += 2;

	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);

	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
	       sizeof(vcpu->hv_clock));

	kunmap_atomic(shared_kaddr, KM_USER0);

	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
}

static int kvm_request_guest_time_update(struct kvm_vcpu *v)
{
	struct kvm_vcpu_arch *vcpu = &v->arch;

	if (!vcpu->time_page)
		return 0;
	set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
	return 1;
}

static bool msr_mtrr_valid(unsigned msr)
{
	switch (msr) {
	case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
	case MSR_MTRRfix64K_00000:
	case MSR_MTRRfix16K_80000:
	case MSR_MTRRfix16K_A0000:
	case MSR_MTRRfix4K_C0000:
	case MSR_MTRRfix4K_C8000:
	case MSR_MTRRfix4K_D0000:
	case MSR_MTRRfix4K_D8000:
	case MSR_MTRRfix4K_E0000:
	case MSR_MTRRfix4K_E8000:
	case MSR_MTRRfix4K_F0000:
	case MSR_MTRRfix4K_F8000:
	case MSR_MTRRdefType:
	case MSR_IA32_CR_PAT:
		return true;
	case 0x2f8:
		return true;
	}
	return false;
}

static bool valid_pat_type(unsigned t)
{
	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
}

static bool valid_mtrr_type(unsigned t)
{
	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
}

static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	int i;

	if (!msr_mtrr_valid(msr))
		return false;

	if (msr == MSR_IA32_CR_PAT) {
		for (i = 0; i < 8; i++)
			if (!valid_pat_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	} else if (msr == MSR_MTRRdefType) {
		if (data & ~0xcff)
			return false;
		return valid_mtrr_type(data & 0xff);
	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
		for (i = 0; i < 8 ; i++)
			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	}

	/* variable MTRRs */
	return valid_mtrr_type(data & 0xff);
}

static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

	if (!mtrr_valid(vcpu, msr, data))
		return 1;

	if (msr == MSR_MTRRdefType) {
		vcpu->arch.mtrr_state.def_type = data;
		vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
	} else if (msr == MSR_MTRRfix64K_00000)
		p[0] = data;
	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
		p[1 + msr - MSR_MTRRfix16K_80000] = data;
	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
		p[3 + msr - MSR_MTRRfix4K_C0000] = data;
	else if (msr == MSR_IA32_CR_PAT)
		vcpu->arch.pat = data;
	else {	/* Variable MTRRs */
		int idx, is_mtrr_mask;
		u64 *pt;

		idx = (msr - 0x200) / 2;
		is_mtrr_mask = msr - 0x200 - 2 * idx;
		if (!is_mtrr_mask)
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
		else
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
		*pt = data;