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 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>
 *
 * 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 "cpuid.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 <linux/hash.h>
#include <linux/pci.h>
#include <linux/timekeeper_internal.h>
#include <linux/pvclock_gtod.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/fpu-internal.h> /* Ugh! */
#include <asm/xcr.h>
#include <asm/pvclock.h>
#include <asm/div64.h>

#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32
#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)

#define emul_to_vcpu(ctxt) \
	container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt)

/* 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

#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 void process_nmi(struct kvm_vcpu *vcpu);

struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);

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

bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32  kvm_max_guest_tsc_khz;
EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);

/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
static u32 tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, 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 struct kvm_shared_msrs __percpu *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 }
};

u64 __read_mostly host_xcr0;

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 < roundup_pow_of_two(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_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)
{
	u64 value;
	unsigned int cpu = smp_processor_id();
	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);

	/* 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)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);

	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)
{
	unsigned int cpu = smp_processor_id();
	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);

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

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
	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 */
	kvm_lapic_set_base(vcpu, data);
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

asmlinkage void kvm_spurious_fault(void)
{
	/* Fault while not rebooting.  We want the trace. */
	BUG();
}
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;
}

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;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	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 */
		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 */
		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_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
	if (err)
		kvm_inject_gp(vcpu, 0);
	else
		kvm_x86_ops->skip_emulated_instruction(vcpu);
}
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.cr2 = fault->address;
	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);

void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
	else
		vcpu->arch.mmu.inject_page_fault(vcpu, 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);
}
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);

/*
 * This function will be used to read from the physical memory of the currently
 * running guest. The difference to kvm_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)
{
	gfn_t real_gfn;
	gpa_t ngpa;

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

	real_gfn = gpa_to_gfn(real_gfn);

	return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);

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);
}

/*
 * Load the pae pdptrs.  Return true is they are all valid.
 */
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 (is_present_gpte(pdpte[i]) &&
		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
			ret = 0;
			goto out;
		}
	}
	ret = 1;

	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->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.walk_mmu->pdptrs)];
	bool changed = true;
	int offset;
	gfn_t gfn;
	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;

	gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
	offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1);
	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
				       PFERR_USER_MASK | PFERR_WRITE_MASK);
	if (r < 0)
		goto out;
	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
out:

	return changed;
}

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.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);
	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);

int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	u64 xcr0;

	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
	if (index != XCR_XFEATURE_ENABLED_MASK)
		return 1;
	xcr0 = xcr;
	if (kvm_x86_ops->get_cpl(vcpu) != 0)
		return 1;
	if (!(xcr0 & XSTATE_FP))
		return 1;
	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
		return 1;
	if (xcr0 & ~host_xcr0)
		return 1;
	vcpu->arch.xcr0 = xcr0;
	vcpu->guest_xcr0_loaded = 0;
	return 0;
}

int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	if (__kvm_set_xcr(vcpu, index, xcr)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_xcr);

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;
	if (cr4 & CR4_RESERVED_BITS)
		return 1;

	if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
		return 1;

	if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
		return 1;

	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_RDWRGSFS))
		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.walk_mmu,
				   kvm_read_cr3(vcpu)))
		return 1;

	if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
		if (!guest_cpuid_has_pcid(vcpu))
			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) & pdptr_bits) ||
	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
		kvm_mmu_reset_context(vcpu);

	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
		kvm_update_cpuid(vcpu);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
		kvm_mmu_sync_roots(vcpu);
		kvm_mmu_flush_tlb(vcpu);
		return 0;
	}

	if (is_long_mode(vcpu)) {
		if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) {
			if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS)
				return 1;
		} else
			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, vcpu->arch.walk_mmu, 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;
	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
	vcpu->arch.mmu.new_cr3(vcpu);
	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 (irqchip_in_kernel(vcpu->kvm))
		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 (irqchip_in_kernel(vcpu->kvm))
		return kvm_lapic_get_cr8(vcpu);
	else
		return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);

static 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 = (dr7 & DR7_BP_EN_MASK);
}

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;
		kvm_update_dr7(vcpu);
		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);

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

	err = kvm_pmu_read_pmc(vcpu, ecx, &data);
	if (err)
		return err;
	kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
	kvm_register_write(vcpu, VCPU_REGS_RDX, 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.
 *
 * 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	10
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_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
	MSR_KVM_PV_EOI_EN,
	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
};

static unsigned num_msrs_to_save;

static const u32 emulated_msrs[] = {
	MSR_IA32_TSC_ADJUST,
	MSR_IA32_TSCDEADLINE,
	MSR_IA32_MISC_ENABLE,
	MSR_IA32_MCG_STATUS,
	MSR_IA32_MCG_CTL,
};

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);

	/* 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, struct msr_data *msr)
{
	return kvm_x86_ops->set_msr(vcpu, msr);
}

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

	msr.data = *data;
	msr.index = index;
	msr.host_initiated = true;
	return kvm_set_msr(vcpu, &msr);
}

#ifdef CONFIG_X86_64
struct pvclock_gtod_data {
	seqcount_t	seq;

	struct { /* extract of a clocksource struct */
		int vclock_mode;
		cycle_t	cycle_last;
		cycle_t	mask;
		u32	mult;
		u32	shift;
	} clock;

	/* open coded 'struct timespec' */
	u64		monotonic_time_snsec;
	time_t		monotonic_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->clock->archdata.vclock_mode;
	vdata->clock.cycle_last		= tk->clock->cycle_last;
	vdata->clock.mask		= tk->clock->mask;
	vdata->clock.mult		= tk->mult;
	vdata->clock.shift		= tk->shift;

	vdata->monotonic_time_sec	= tk->xtime_sec
					+ tk->wall_to_monotonic.tv_sec;
	vdata->monotonic_time_snsec	= tk->xtime_nsec
					+ (tk->wall_to_monotonic.tv_nsec
						<< tk->shift);
	while (vdata->monotonic_time_snsec >=
					(((u64)NSEC_PER_SEC) << tk->shift)) {
		vdata->monotonic_time_snsec -=
					((u64)NSEC_PER_SEC) << tk->shift;
		vdata->monotonic_time_sec++;
	}

	write_seqcount_end(&vdata->seq);
}
#endif


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_guest_time_update 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);

	if (kvm->arch.kvmclock_offset) {
		struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
		boot = timespec_sub(boot, ts);
	}
	wc.sec = boot.tv_sec;
	wc.nsec = boot.tv_nsec;