blob: 91a5e989abcfe86f60df7bcb2a2919e25f87df6a [file] [log] [blame]
/*
* 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 <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 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 }
};
u64 __read_mostly host_xcr0;
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)
{
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;
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;
}
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 (kvm_x86_ops->set_cr4(vcpu, cr4))
return 1;
if ((cr4 ^ old_cr4) & pdptr_bits)
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 (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 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);
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 9
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_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 u32 emulated_msrs[] = {
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);
vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
/* 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_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);
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_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
s8 *pshift, u32 *pmultiplier)
{
uint64_t scaled64;
int32_t shift = 0;
uint64_t tps64;
uint32_t tps32;
tps64 = base_khz * 1000LL;
scaled64 = scaled_khz * 1000LL;
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);
pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
__func__, base_khz, scaled_khz, shift, *pmultiplier);
}
static inline u64 get_kernel_ns(void)
{
struct timespec ts;
WARN_ON(preemptible());
ktime_get_ts(&ts);
monotonic_to_bootbased(&ts);
return timespec_to_ns(&ts);
}
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
unsigned long max_tsc_khz;
static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
{
return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
vcpu->arch.virtual_tsc_shift);
}
static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
u64 v = (u64)khz * (1000000 + ppm);
do_div(v, 1000000);
return v;
}
static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
{
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
/* Compute a scale to convert nanoseconds in TSC cycles */
kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
&vcpu->arch.virtual_tsc_shift,
&vcpu->arch.virtual_tsc_mult);
vcpu->arch.virtual_tsc_khz = this_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 (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
use_scaling = 1;
}
kvm_x86_ops->set_tsc_khz(vcpu, this_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;
}
void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
{
struct kvm *kvm = vcpu->kvm;
u64 offset, ns, elapsed;
unsigned long flags;
s64 usdiff;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
ns = get_kernel_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
/* n.b - signed multiplication and division required */
usdiff = data - kvm->arch.last_tsc_write;
#ifdef CONFIG_X86_64
usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
#else
/* do_div() only does unsigned */
asm("idivl %2; xor %%edx, %%edx"
: "=A"(usdiff)
: "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
#endif
do_div(elapsed, 1000);
usdiff -= elapsed;
if (usdiff < 0)
usdiff = -usdiff;
/*
* 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.
*
* 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 (usdiff < USEC_PER_SEC &&
vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
if (!check_tsc_unstable()) {
offset = kvm->arch.cur_tsc_offset;
pr_debug("kvm: matched tsc offset for %llu\n", data);
} else {
u64 delta = nsec_to_cycles(vcpu, elapsed);
data += delta;
offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
}
} 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 computaion 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;
pr_debug("kvm: new tsc generation %u, clock %llu\n",
kvm->arch.cur_tsc_generation, data);
}
/*
* 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;
/* Reset of TSC must disable overshoot protection below */
vcpu->arch.hv_clock.tsc_timestamp = 0;
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_x86_ops->write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
}
EXPORT_SYMBOL_GPL(kvm_write_tsc);
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags;
struct kvm_vcpu_arch *vcpu = &v->arch;
void *shared_kaddr;
unsigned long this_tsc_khz;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
tsc_timestamp = kvm_x86_ops->read_l1_tsc(v);
kernel_ns = get_kernel_ns();
this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
if (unlikely(this_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
}
/*
* 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);
if (!vcpu->time_page)
return 0;
/*
* Time as measured by the TSC may go backwards when resetting the base
* tsc_timestamp. The reason for this is that the TSC resolution is
* higher than the resolution of the other clock scales. Thus, many
* possible measurments of the TSC correspond to one measurement of any
* other clock, and so a spread of values is possible. This is not a
* problem for the computation of the nanosecond clock; with TSC rates
* around 1GHZ, there can only be a few cycles which correspond to one
* nanosecond value, and any path through this code will inevitably
* take longer than that. However, with the kernel_ns value itself,
* the precision may be much lower, down to HZ granularity. If the
* first sampling of TSC against kernel_ns ends in the low part of the
* range, and the second in the high end of the range, we can get:
*
* (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
*
* As the sampling errors potentially range in the thousands of cycles,
* it is possible such a time value has already been observed by the
* guest. To protect against this, we must compute the system time as
* observed by the guest and ensure the new system time is greater.
*/
max_kernel_ns = 0;
if (vcpu->hv_clock.tsc_timestamp) {
max_kernel_ns = vcpu->last_guest_tsc -
vcpu->hv_clock.tsc_timestamp;
max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
vcpu->hv_clock.tsc_to_system_mul,
vcpu->hv_clock.tsc_shift);
max_kernel_ns += vcpu->last_kernel_ns;
}
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
vcpu->hw_tsc_khz = this_tsc_khz;
}
if (max_kernel_ns > kernel_ns)
kernel_ns = max_kernel_ns;
/* With all the info we got, fill in the values */
vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_kernel_ns = kernel_ns;
vcpu->last_guest_tsc = tsc_timestamp;
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);
memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
sizeof(vcpu->hv_clock));
kunmap_atomic(shared_kaddr);
mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
return 0;
}
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;
}
kvm_mmu_reset_context(vcpu);
return 0;
}
static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
u64 mcg_cap = vcpu->arch.mcg_cap;
unsigned bank_num = mcg_cap & 0xff;
switch (msr) {
case MSR_IA32_MCG_STATUS:
vcpu->arch.mcg_status = data;
break;
case MSR_IA32_MCG_CTL:
if (!(mcg_cap & MCG_CTL_P))
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_MC0_CTL + 4 * bank_num) {
u32 offset = msr - 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;
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;
int r;
r = -E2BIG;
if (page_num >= blob_size)
goto out;
r = -ENOMEM;
page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE);
if (IS_ERR(page)) {
r = PTR_ERR(page);
goto out;
}
if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
goto out_free;
r = 0;
out_free:
kfree(page);
out:
return r;
}
static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
}
static bool kvm_hv_msr_partition_wide(u32 msr)
{
bool r = false;
switch (msr) {
case HV_X64_MSR_GUEST_OS_ID:
case HV_X64_MSR_HYPERCALL:
r = true;
break;
}
return r;
}
static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
struct kvm *kvm = vcpu->kvm;
switch (msr) {
case HV_X64_MSR_GUEST_OS_ID:
kvm->arch.hv_guest_os_id = data;
/* setting guest os id to zero disables hypercall page */
if (!kvm->arch.hv_guest_os_id)
kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
break;
case HV_X64_MSR_HYPERCALL: {
u64 gfn;
unsigned long addr;
u8 instructions[4];
/* if guest os id is not set hypercall should remain disabled */
if (!kvm->arch.hv_guest_os_id)
break;
if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
kvm->arch.hv_hypercall = data;
break;
}
gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
addr = gfn_to_hva(kvm, gfn);
if (kvm_is_error_hva(addr))
return 1;
kvm_x86_ops->patch_hypercall(vcpu, instructions);
((unsigned char *)instructions)[3] = 0xc3; /* ret */
if (__copy_to_user((void __user *)addr, instructions, 4))
return 1;
kvm->arch.hv_hypercall = data;
break;
}
default:
pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
"data 0x%llx\n", msr, data);
return 1;
}
return 0;
}
static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
switch (msr) {
case HV_X64_MSR_APIC_ASSIST_PAGE: {
unsigned long addr;
if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
vcpu->arch.hv_vapic = data;
break;
}
addr = gfn_to_hva(vcpu->kvm, data >>
HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
if (kvm_is_error_hva(addr))
return 1;
if (__clear_user((void __user *)addr, PAGE_SIZE))
return 1;
vcpu->arch.hv_vapic = data;
break;
}
case HV_X64_MSR_EOI:
return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
case HV_X64_MSR_ICR:
return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
case HV_X64_MSR_TPR:
return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
default:
pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
"data 0x%llx\n", msr, data);
return 1;
}
return 0;
}
static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
gpa_t gpa = data & ~0x3f;
/* Bits 2:5 are resrved, Should be zero */
if (data & 0x3c)
return 1;
vcpu->arch.apf.msr_val = data;
if (!(data & KVM_ASYNC_PF_ENABLED)) {
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))
return 1;
vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
kvm_async_pf_wakeup_all(vcpu);
return 0;
}
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
if (vcpu->arch.time_page) {
kvm_release_page_dirty(vcpu->arch.time_page);
vcpu->arch.time_page = NULL;
}
}
static void accumulate_steal_time(struct kvm_vcpu *vcpu)
{
u64 delta;
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
delta = current->sched_info.run_delay - vcpu->arch.st.last_steal;
vcpu->arch.st.last_steal = current->sched_info.run_delay;
vcpu->arch.st.accum_steal = delta;
}
static void record_steal_time(struct kvm_vcpu *vcpu)
{
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal;
vcpu->arch.st.steal.version += 2;
vcpu->arch.st.accum_steal = 0;
kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
}
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
bool pr = false;
switch (msr) {
case MSR_EFER:
return set_efer(vcpu, data);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
data &= ~(u64)0x100; /* ignore ignne emulation enable */
data &= ~(u64)0x8; /* ignore TLB cache disable */
if (data != 0) {
pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
data);
return 1;
}
break;
case MSR_FAM10H_MMIO_CONF_BASE:
if (data != 0) {
pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: "
"0x%llx\n", data);
return 1;
}
break;
case MSR_AMD64_NB_CFG:
break;
case MSR_IA32_DEBUGCTLMSR:
if (!data) {
/* We support the non-activated case already */
break;
} else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) {
/* Values other than LBR and BTF are vendor-specific,
thus reserved and should throw a #GP */
return 1;
}
pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
__func__, data);
break;
case MSR_IA32_UCODE_REV:
case MSR_IA32_UCODE_WRITE:
case MSR_VM_HSAVE_PA:
case MSR_AMD64_PATCH_LOADER:
break;
case 0x200 ... 0x2ff:
return set_msr_mtrr(vcpu, msr, data);
case MSR_IA32_APICBASE:
kvm_set_apic_base(vcpu, data);
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
return kvm_x2apic_msr_write(vcpu, msr, data);
case MSR_IA32_TSCDEADLINE:
kvm_set_lapic_tscdeadline_msr(vcpu, data);
break;
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
kvm_write_wall_clock(vcpu->kvm, data);
break;
case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
kvmclock_reset(vcpu);
vcpu->arch.time = data;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* we verify if the enable bit is set... */
if (!(data & 1))
break;
/* ...but clean it before doing the actual write */
vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
vcpu->arch.time_page =
gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
if (is_error_page(vcpu->arch.time_page)) {
kvm_release_page_clean(vcpu->arch.time_page);
vcpu->arch.time_page = NULL;
}
break;
}
case MSR_KVM_ASYNC_PF_EN:
if (kvm_pv_enable_async_pf(vcpu, data))
return 1;
break;
case MSR_KVM_STEAL_TIME:
if (unlikely(!sched_info_on()))
return 1;
if (data & KVM_STEAL_RESERVED_MASK)
return 1;
if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
data & KVM_STEAL_VALID_BITS))
return 1;
vcpu->arch.st.msr_val = data;
if (!(data & KVM_MSR_ENABLED))
break;
vcpu->arch.st.last_steal = current->sched_info.run_delay;
preempt_disable();
accumulate_steal_time(vcpu);
preempt_enable();
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
break;
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
return set_msr_mce(vcpu, msr, data);
/* Performance counters are not protected by a CPUID bit,
* so we should check all of them in the generic path for the sake of
* cross vendor migration.
* Writing a zero into the event select MSRs disables them,
* which we perfectly emulate ;-). Any other value should be at least
* reported, some guests depend on them.
*/
case MSR_K7_EVNTSEL0:
case MSR_K7_EVNTSEL1:
case MSR_K7_EVNTSEL2:
case MSR_K7_EVNTSEL3:
if (data != 0)
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
/* at least RHEL 4 unconditionally writes to the perfctr registers,
* so we ignore writes to make it happy.
*/
case MSR_K7_PERFCTR0:
case MSR_K7_PERFCTR1:
case MSR_K7_PERFCTR2:
case MSR_K7_PERFCTR3:
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
case MSR_P6_PERFCTR0:
case MSR_P6_PERFCTR1:
pr = true;
case MSR_P6_EVNTSEL0:
case MSR_P6_EVNTSEL1:
if (kvm_pmu_msr(vcpu, msr))
return kvm_pmu_set_msr(vcpu, msr, data);
if (pr || data != 0)
pr_unimpl(vcpu, "disabled perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
case MSR_K7_CLK_CTL:
/*
* Ignore all writes to this no longer documented MSR.
* Writes are only relevant for old K7 processors,
* all pre-dating SVM, but a recommended workaround from
* AMD for these chips. It is possible to speicify the
* affected processor models on the command line, hence
* the need to ignore the workaround.
*/
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
if (kvm_hv_msr_partition_wide(msr)) {
int r;
mutex_lock(&vcpu->kvm->lock);
r = set_msr_hyperv_pw(vcpu, msr, data);
mutex_unlock(&vcpu->kvm->lock);
return r;
} else
return set_msr_hyperv(vcpu, msr, data);
break;
case MSR_IA32_BBL_CR_CTL3:
/* Drop writes to this legacy MSR -- see rdmsr
* counterpart for further detail.
*/
pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
vcpu->arch.osvw.length = data;
break;
case MSR_AMD64_OSVW_STATUS:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
vcpu->arch.osvw.status = data;
break;
default:
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
if (kvm_pmu_msr(vcpu, msr))
return kvm_pmu_set_msr(vcpu, msr, data);
if (!ignore_msrs) {
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
msr, data);
return 1;
} else {
pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
msr, data);
break;
}
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);
/*
* Reads an msr value (of 'msr_index') into 'pdata'.
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
}
static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
if (!msr_mtrr_valid(msr))
return 1;
if (msr == MSR_MTRRdefType)
*pdata = vcpu->arch.mtrr_state.def_type +
(vcpu->arch.mtrr_state.enabled << 10);
else if (msr == MSR_MTRRfix64K_00000)
*pdata = p[0];
else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
*pdata = p[1 + msr - MSR_MTRRfix16K_80000];
else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
*pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
else if (msr == MSR_IA32_CR_PAT)
*pdata = vcpu->arch.pat;
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;
*pdata = *pt;
}
return 0;
}
static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
u64 mcg_cap = vcpu->arch.mcg_cap;
unsigned bank_num = mcg_cap & 0xff;
switch (msr) {
case MSR_IA32_P5_MC_ADDR:
case MSR_IA32_P5_MC_TYPE:
data = 0;
break;
case MSR_IA32_MCG_CAP:
data = vcpu->arch.mcg_cap;
break;
case MSR_IA32_MCG_CTL:
if (!(mcg_cap & MCG_CTL_P))
return 1;
data = vcpu->arch.mcg_ctl;
break;
case MSR_IA32_MCG_STATUS:
data = vcpu->arch.mcg_status;
break;
default:
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
u32 offset = msr - MSR_IA32_MC0_CTL;
data = vcpu->arch.mce_banks[offset];
break;
}
return 1;
}
*pdata = data;
return 0;
}
static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data = 0;
struct kvm *kvm = vcpu->kvm;
switch (msr) {
case HV_X64_MSR_GUEST_OS_ID:
data = kvm->arch.hv_guest_os_id;
break;
case HV_X64_MSR_HYPERCALL:
data = kvm->arch.hv_hypercall;
break;
default:
pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
}
*pdata = data;
return 0;
}
static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data = 0;
switch (msr) {
case HV_X64_MSR_VP_INDEX: {
int r;
struct kvm_vcpu *v;
kvm_for_each_vcpu(r, v, vcpu->kvm)
if (v == vcpu)
data = r;
break;
}
case HV_X64_MSR_EOI:
return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
case HV_X64_MSR_ICR:
return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
case HV_X64_MSR_TPR:
return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
case HV_X64_MSR_APIC_ASSIST_PAGE:
data = vcpu->arch.hv_vapic;
break;
default:
pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
}
*pdata = data;
return 0;
}
int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
switch (msr) {
case MSR_IA32_PLATFORM_ID:
case MSR_IA32_EBL_CR_POWERON:
case MSR_IA32_DEBUGCTLMSR:
case MSR_IA32_LASTBRANCHFROMIP:
case MSR_IA32_LASTBRANCHTOIP:
case MSR_IA32_LASTINTFROMIP:
case MSR_IA32_LASTINTTOIP:
case MSR_K8_SYSCFG:
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
case MSR_K7_EVNTSEL0:
case MSR_K7_PERFCTR0:
case MSR_K8_INT_PENDING_MSG:
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
data = 0;
break;
case MSR_P6_PERFCTR0:
case MSR_P6_PERFCTR1:
case MSR_P6_EVNTSEL0:
case MSR_P6_EVNTSEL1:
if (kvm_pmu_msr(vcpu, msr))
return kvm_pmu_get_msr(vcpu, msr, pdata);
data = 0;
break;
case MSR_IA32_UCODE_REV:
data = 0x100000000ULL;
break;
case MSR_MTRRcap:
data = 0x500 | KVM_NR_VAR_MTRR;
break;
case 0x200 ... 0x2ff:
return get_msr_mtrr(vcpu, msr, pdata);
case 0xcd: /* fsb frequency */
data = 3;
break;
/*
* MSR_EBC_FREQUENCY_ID
* Conservative value valid for even the basic CPU models.
* Models 0,1: 000 in bits 23:21 indicating a bus speed of
* 100MHz, model 2 000 in bits 18:16 indicating 100MHz,
* and 266MHz for model 3, or 4. Set Core Clock
* Frequency to System Bus Frequency Ratio to 1 (bits
* 31:24) even though these are only valid for CPU
* models > 2, however guests may end up dividing or
* multiplying by zero otherwise.
*/
case MSR_EBC_FREQUENCY_ID:
data = 1 << 24;
break;
case MSR_IA32_APICBASE:
data = kvm_get_apic_base(vcpu);
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
return kvm_x2apic_msr_read(vcpu, msr, pdata);
break;
case MSR_IA32_TSCDEADLINE:
data = kvm_get_lapic_tscdeadline_msr(vcpu);
break;
case MSR_IA32_MISC_ENABLE:
data = vcpu->arch.ia32_misc_enable_msr;
break;
case MSR_IA32_PERF_STATUS:
/* TSC increment by tick */
data = 1000ULL;
/* CPU multiplier */
data |= (((uint64_t)4ULL) << 40);
break;
case MSR_EFER:
data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
case MSR_KVM_WALL_CLOCK_NEW:
data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
case MSR_KVM_SYSTEM_TIME_NEW:
data = vcpu->arch.time;
break;
case MSR_KVM_ASYNC_PF_EN:
data = vcpu->arch.apf.msr_val;
break;
case MSR_KVM_STEAL_TIME:
data = vcpu->arch.st.msr_val;
break;
case MSR_IA32_P5_MC_ADDR:
case MSR_IA32_P5_MC_TYPE:
case MSR_IA32_MCG_CAP:
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
return get_msr_mce(vcpu, msr, pdata);
case MSR_K7_CLK_CTL:
/*
* Provide expected ramp-up count for K7. All other
* are set to zero, indicating minimum divisors for
* every field.
*
* This prevents guest kernels on AMD host with CPU
* type 6, model 8 and higher from exploding due to
* the rdmsr failing.
*/
data = 0x20000000;
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
if (kvm_hv_msr_partition_wide(msr)) {
int r;
mutex_lock(&vcpu->kvm->lock);
r = get_msr_hyperv_pw(vcpu, msr, pdata);
mutex_unlock(&vcpu->kvm->lock);
return r;
} else
return get_msr_hyperv(vcpu, msr, pdata);
break;
case MSR_IA32_BBL_CR_CTL3:
/* This legacy MSR exists but isn't fully documented in current
* silicon. It is however accessed by winxp in very narrow
* scenarios where it sets bit #19, itself documented as
* a "reserved" bit. Best effort attempt to source coherent
* read data here should the balance of the register be
* interpreted by the guest:
*
* L2 cache control register 3: 64GB range, 256KB size,
* enabled, latency 0x1, configured
*/
data = 0xbe702111;
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
data = vcpu->arch.osvw.length;
break;
case MSR_AMD64_OSVW_STATUS:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
data = vcpu->arch.osvw.status;
break;
default:
if (kvm_pmu_msr(vcpu, msr))
return kvm_pmu_get_msr(vcpu, msr, pdata);
if (!ignore_msrs) {
pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
return 1;
} else {
pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
data = 0;
}
break;
}
*pdata = data;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);
/*
* Read or write a bunch of msrs. All parameters are kernel addresses.
*
* @return number of msrs set successfully.
*/
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
struct kvm_msr_entry *entries,
int (*do_msr)(struct kvm_vcpu *vcpu,
unsigned index, u64 *data))
{
int i, idx;
idx = srcu_read_lock(&vcpu->kvm->srcu);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return i;
}
/*
* Read or write a bunch of msrs. Parameters are user addresses.
*
* @return number of msrs set successfully.
*/
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
int (*do_msr)(struct kvm_vcpu *vcpu,
unsigned index, u64 *data),
int writeback)
{
struct kvm_msrs msrs;
struct kvm_msr_entry *entries;
int r, n;
unsigned size;
r = -EFAULT;
if (copy_from_user(&msrs, user_msrs, sizeof msrs))
goto out;
r = -E2BIG;
if (msrs.nmsrs >= MAX_IO_MSRS)
goto out;
size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
entries = memdup_user(user_msrs->entries, size);
if (IS_ERR(entries)) {
r = PTR_ERR(entries);
goto out;
}
r = n = __msr_io(vcpu, &msrs, entries, do_msr);
if (r < 0)
goto out_free;
r = -EFAULT;
if (writeback && copy_to_user(user_msrs->entries, entries, size))
goto out_free;
r = n;
out_free:
kfree(entries);
out:
return r;
}
int kvm_dev_ioctl_check_extension(long ext)
{
int r;
switch (ext) {
case KVM_CAP_IRQCHIP:
case KVM_CAP_HLT:
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
case KVM_CAP_MP_STATE:
case KVM_CAP_SYNC_MMU:
case KVM_CAP_USER_NMI:
case KVM_CAP_REINJECT_CONTROL:
case KVM_CAP_IRQ_INJECT_STATUS:
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_IRQFD:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_PIT2:
case KVM_CAP_PIT_STATE2:
case KVM_CAP_SET_IDENTITY_MAP_ADDR:
case KVM_CAP_XEN_HVM:
case KVM_CAP_ADJUST_CLOCK:
case KVM_CAP_VCPU_EVENTS:
case KVM_CAP_HYPERV:
case KVM_CAP_HYPERV_VAPIC:
case KVM_CAP_HYPERV_SPIN:
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
case KVM_CAP_XSAVE:
case KVM_CAP_ASYNC_PF:
case KVM_CAP_GET_TSC_KHZ:
case KVM_CAP_PCI_2_3:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
r = KVM_COALESCED_MMIO_PAGE_OFFSET;
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
break;
case KVM_CAP_NR_VCPUS:
r = KVM_SOFT_MAX_VCPUS;
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_MEMORY_SLOTS;
break;
case KVM_CAP_PV_MMU: /* obsolete */
r = 0;
break;
case KVM_CAP_IOMMU:
r = iommu_present(&pci_bus_type);
break;
case KVM_CAP_MCE:
r = KVM_MAX_MCE_BANKS;
break;
case KVM_CAP_XCRS:
r = cpu_has_xsave;
break;
case KVM_CAP_TSC_CONTROL:
r = kvm_has_tsc_control;
break;
case KVM_CAP_TSC_DEADLINE_TIMER:
r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
break;
default:
r = 0;
break;
}
return r;
}
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
void __user *argp = (void __user *)arg;
long r;
switch (ioctl) {
case KVM_GET_MSR_INDEX_LIST: {
struct kvm_msr_list __user *user_msr_list = argp;
struct kvm_msr_list msr_list;
unsigned n;
r = -EFAULT;
if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
goto out;
n = msr_list.nmsrs;
msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
goto out;
r = -E2BIG;
if (n < msr_list.nmsrs)
goto out;
r = -EFAULT;
if (copy_to_user(user_msr_list->indices, &msrs_to_save,
num_msrs_to_save * sizeof(u32)))
goto out;
if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
&emulated_msrs,
ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
goto out;
r = 0;
break;
}
case KVM_GET_SUPPORTED_CPUID: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
cpuid_arg->entries);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
goto out;
r = 0;
break;
}
case KVM_X86_GET_MCE_CAP_SUPPORTED: {
u64 mce_cap;
mce_cap = KVM_MCE_CAP_SUPPORTED;
r = -EFAULT;
if (copy_to_user(argp, &mce_cap, sizeof mce_cap))
goto out;
r = 0;
break;
}
default:
r = -EINVAL;
}
out:
return r;
}
static void wbinvd_ipi(void *garbage)
{
wbinvd();
}
static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
{
return vcpu->kvm->arch.iommu_domain &&
!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY);
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
/* Address WBINVD may be executed by guest */
if (need_emulate_wbinvd(vcpu)) {
if (kvm_x86_ops->has_wbinvd_exit())
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
smp_call_function_single(vcpu->cpu,
wbinvd_ipi, NULL, 1);
}
kvm_x86_ops->vcpu_load(vcpu, cpu);
/* Apply any externally detected TSC adjustments (due to suspend) */
if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
vcpu->arch.tsc_offset_adjustment = 0;
set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
}
if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
native_read_tsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
if (check_tsc_unstable()) {
u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
if (vcpu->cpu != cpu)
kvm_migrate_timers(vcpu);
vcpu->cpu = cpu;
}
accumulate_steal_time(vcpu);
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
vcpu->arch.last_host_tsc = native_read_tsc();
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
return 0;
}
static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
kvm_apic_post_state_restore(vcpu);
update_cr8_intercept(vcpu);
return 0;
}
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
if (irq->irq < 0 || irq->irq >= 256)
return -EINVAL;
if (irqchip_in_kernel(vcpu->kvm))
return -ENXIO;
kvm_queue_interrupt(vcpu, irq->irq, false);
kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
{
kvm_inject_nmi(vcpu);
return 0;
}
static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
struct kvm_tpr_access_ctl *tac)
{
if (tac->flags)
return -EINVAL;
vcpu->arch.tpr_access_reporting = !!tac->enabled;
return 0;
}
static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
u64 mcg_cap)
{
int r;
unsigned bank_num = mcg_cap & 0xff, bank;
r = -EINVAL;
if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
goto out;
if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
goto out;
r = 0;
vcpu->arch.mcg_cap = mcg_cap;
/* Init IA32_MCG_CTL to all 1s */
if (mcg_cap & MCG_CTL_P)
vcpu->arch.mcg_ctl = ~(u64)0;
/* Init IA32_MCi_CTL to all 1s */
for (bank = 0; bank < bank_num; bank++)
vcpu->arch.mce_banks[bank*4] = ~(u64)0;
out:
return r;
}
static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
struct kvm_x86_mce *mce)
{
u64 mcg_cap = vcpu->arch.mcg_cap;
unsigned bank_num = mcg_cap & 0xff;
u64 *banks = vcpu->arch.mce_banks;
if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL))
return -EINVAL;
/*
* if IA32_MCG_CTL is not all 1s, the uncorrected error
* reporting is disabled
*/
if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) &&
vcpu->arch.mcg_ctl != ~(u64)0)
return 0;
banks += 4 * mce->bank;
/*
* if IA32_MCi_CTL is not all 1s, the uncorrected error
* reporting is disabled for the bank
*/
if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0)
return 0;
if (mce->status & MCI_STATUS_UC) {
if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
!kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return 0;
}
if (banks[1] & MCI_STATUS_VAL)
mce->status |= MCI_STATUS_OVER;
banks[2] = mce->addr;
banks[3] = mce->misc;
vcpu->arch.mcg_status = mce->mcg_status;
banks[1] = mce->status;
kvm_queue_exception(vcpu, MC_VECTOR);
} else if (!(banks[1] & MCI_STATUS_VAL)
|| !(banks[1] & MCI_STATUS_UC)) {
if (banks[1] & MCI_STATUS_VAL)
mce->status |= MCI_STATUS_OVER;
banks[2] = mce->addr;
banks[3] = mce->misc;
banks[1] = mce->status;
} else
banks[1] |= MCI_STATUS_OVER;
return 0;
}
static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
process_nmi(vcpu);
events->exception.injected =
vcpu->arch.exception.pending &&
!kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
events->exception.pad = 0;
events->exception.error_code = vcpu->arch.exception.error_code;
events->interrupt.injected =
vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
events->interrupt.soft = 0;
events->interrupt.shadow =
kvm_x86_ops->get_interrupt_shadow(vcpu,
KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending != 0;
events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
events->nmi.pad = 0;
events->sipi_vector = vcpu->arch.sipi_vector;
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW);
memset(&events->reserved, 0, sizeof(events->reserved));
}
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW))
return -EINVAL;
process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
vcpu->arch.exception.error_code = events->exception.error_code;
vcpu->arch.interrupt.pending = events->interrupt.injected;
vcpu->arch.interrupt.nr = events->interrupt.nr;
vcpu->arch.interrupt.soft = events->interrupt.soft;
if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
kvm_x86_ops->set_interrupt_shadow(vcpu,
events->interrupt.shadow);
vcpu->arch.nmi_injected = events->nmi.injected;
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
vcpu->arch.nmi_pending = events->nmi.pending;
kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
vcpu->arch.sipi_vector = events->sipi_vector;
kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
struct kvm_debugregs *dbgregs)
{
memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
dbgregs->dr6 = vcpu->arch.dr6;
dbgregs->dr7 = vcpu->arch.dr7;
dbgregs->flags = 0;
memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
}
static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
struct kvm_debugregs *dbgregs)
{
if (dbgregs->flags)
return -EINVAL;
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
vcpu->arch.dr6 = dbgregs->dr6;
vcpu->arch.dr7 = dbgregs->dr7;
return 0;
}
static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
if (cpu_has_xsave)
memcpy(guest_xsave->region,
&vcpu->arch.guest_fpu.state->xsave,
xstate_size);
else {
memcpy(guest_xsave->region,
&vcpu->arch.guest_fpu.state->fxsave,
sizeof(struct i387_fxsave_struct));
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
XSTATE_FPSSE;
}
}
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
if (cpu_has_xsave)
memcpy(&vcpu->arch.guest_fpu.state->xsave,
guest_xsave->region, xstate_size);
else {
if (xstate_bv & ~XSTATE_FPSSE)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state->fxsave,
guest_xsave->region, sizeof(struct i387_fxsave_struct));
}
return 0;
}
static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
struct kvm_xcrs *guest_xcrs)
{
if (!cpu_has_xsave) {
guest_xcrs->nr_xcrs = 0;
return;
}
guest_xcrs->nr_xcrs = 1;
guest_xcrs->flags = 0;
guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
}
static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
struct kvm_xcrs *guest_xcrs)
{
int i, r = 0;
if (!cpu_has_xsave)
return -EINVAL;
if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
return -EINVAL;
for (i = 0; i < guest_xcrs->nr_xcrs; i++)
/* Only support XCR0 currently */
if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
guest_xcrs->xcrs[0].value);
break;
}
if (r)
r = -EINVAL;
return r;
}
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
int r;
union {
struct kvm_lapic_state *lapic;
struct kvm_xsave *xsave;
struct kvm_xcrs *xcrs;
void *buffer;
} u;
u.buffer = NULL;
switch (ioctl) {
case KVM_GET_LAPIC: {
r = -EINVAL;
if (!vcpu->arch.apic)
goto out;
u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
r = -ENOMEM;
if (!u.lapic)
goto out;
r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state)))
goto out;
r = 0;
break;
}
case KVM_SET_LAPIC: {
r = -EINVAL;
if (!vcpu->arch.apic)
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
if (IS_ERR(u.lapic)) {
r = PTR_ERR(u.lapic);
goto out;
}
r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
if (r)
goto out;
r = 0;
break;
}
case KVM_INTERRUPT: {
struct kvm_interrupt irq;
r = -EFAULT;
if (copy_from_user(&irq, argp, sizeof irq))
goto out;
r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
if (r)
goto out;
r = 0;
break;
}
case KVM_NMI: {
r = kvm_vcpu_ioctl_nmi(vcpu);
if (r)
goto out;
r = 0;
break;
}
case KVM_SET_CPUID: {
struct kvm_cpuid __user *cpuid_arg = argp;
struct kvm_cpuid cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
if (r)
goto out;
break;
}
case KVM_SET_CPUID2: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
cpuid_arg->entries);
if (r)
goto out;
break;
}
case KVM_GET_CPUID2: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
cpuid_arg->entries);
if (r)
goto out;
r = -EFAULT