* Copyright (C) 2006 Qumranet, Inc.
* Copyright (C) 2008 Qumranet, Inc.
* Copyright IBM Corporation, 2008
- * Copyright 2010 Red Hat, Inc. and/or its affilates.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
#define KVM_MAX_MCE_BANKS 32
-#define KVM_MCE_CAP_SUPPORTED MCG_CTL_P
+#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
/* EFER defaults:
* - enable syscall per default because its emulated by KVM
u32 prev_nr;
int class1, class2;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
if (!vcpu->arch.exception.pending) {
queue:
vcpu->arch.exception.pending = true;
void kvm_propagate_fault(struct kvm_vcpu *vcpu)
{
- u32 nested, error;
-
- error = vcpu->arch.fault.error_code;
- nested = error & PFERR_NESTED_MASK;
- error = error & ~PFERR_NESTED_MASK;
-
- vcpu->arch.fault.error_code = error;
-
- if (mmu_is_nested(vcpu) && !nested)
+ if (mmu_is_nested(vcpu) && !vcpu->arch.fault.nested)
vcpu->arch.nested_mmu.inject_page_fault(vcpu);
else
vcpu->arch.mmu.inject_page_fault(vcpu);
+
+ vcpu->arch.fault.nested = false;
}
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
vcpu->arch.nmi_pending = 1;
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);
/*
* The guest calculates current wall clock time by adding
- * system time (updated by kvm_write_guest_time below) to the
+ * 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.
*/
return quotient;
}
-static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+ s8 *pshift, u32 *pmultiplier)
{
- uint64_t nsecs = 1000000000LL;
+ uint64_t scaled64;
int32_t shift = 0;
uint64_t tps64;
uint32_t tps32;
- tps64 = tsc_khz * 1000LL;
- while (tps64 > nsecs*2) {
+ tps64 = base_khz * 1000LL;
+ scaled64 = scaled_khz * 1000LL;
+ while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
}
tps32 = (uint32_t)tps64;
- while (tps32 <= (uint32_t)nsecs) {
- tps32 <<= 1;
+ while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
+ if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
+ scaled64 >>= 1;
+ else
+ tps32 <<= 1;
shift++;
}
- hv_clock->tsc_shift = shift;
- hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+ *pshift = shift;
+ *pmultiplier = div_frac(scaled64, 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);
+ 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)
}
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+unsigned long max_tsc_khz;
static inline int kvm_tsc_changes_freq(void)
{
return ret;
}
+static void kvm_arch_set_tsc_khz(struct kvm *kvm, u32 this_tsc_khz)
+{
+ /* Compute a scale to convert nanoseconds in TSC cycles */
+ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+ &kvm->arch.virtual_tsc_shift,
+ &kvm->arch.virtual_tsc_mult);
+ kvm->arch.virtual_tsc_khz = this_tsc_khz;
+}
+
+static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
+{
+ u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec,
+ vcpu->kvm->arch.virtual_tsc_mult,
+ vcpu->kvm->arch.virtual_tsc_shift);
+ tsc += vcpu->arch.last_tsc_write;
+ return tsc;
+}
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
{
struct kvm *kvm = vcpu->kvm;
/* Reset of TSC must disable overshoot protection below */
vcpu->arch.hv_clock.tsc_timestamp = 0;
+ vcpu->arch.last_tsc_write = data;
+ vcpu->arch.last_tsc_nsec = ns;
}
EXPORT_SYMBOL_GPL(kvm_write_tsc);
-static int kvm_write_guest_time(struct kvm_vcpu *v)
+static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags;
struct kvm_vcpu_arch *vcpu = &v->arch;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp;
- if ((!vcpu->time_page))
- return 0;
-
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
kernel_ns = get_kernel_ns();
this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
- local_irq_restore(flags);
if (unlikely(this_tsc_khz == 0)) {
- kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
+ 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) {
+ kvm_x86_ops->adjust_tsc_offset(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
}
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
+ 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;
}
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;
/*
return 0;
}
-static int kvm_request_guest_time_update(struct kvm_vcpu *v)
-{
- struct kvm_vcpu_arch *vcpu = &v->arch;
-
- if (!vcpu->time_page)
- return 0;
- kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
- return 1;
-}
-
static bool msr_mtrr_valid(unsigned msr)
{
switch (msr) {
}
vcpu->arch.time = data;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* we verify if the enable bit is set... */
if (!(data & 1))
kvm_release_page_clean(vcpu->arch.time_page);
vcpu->arch.time_page = NULL;
}
-
- kvm_request_guest_time_update(vcpu);
break;
}
case MSR_IA32_MCG_CTL:
native_read_tsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (check_tsc_unstable())
+ if (check_tsc_unstable()) {
kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta);
- kvm_migrate_timers(vcpu);
+ vcpu->arch.tsc_catchup = 1;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+ }
+ if (vcpu->cpu != cpu)
+ kvm_migrate_timers(vcpu);
vcpu->cpu = cpu;
}
}
0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
0 /* Reserved, DCA */ | F(XMM4_1) |
F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
- 0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
+ 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+ F(F16C);
/* cpuid 0x80000001.ecx */
const u32 kvm_supported_word6_x86_features =
F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
- F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
- 0 /* SKINIT */ | 0 /* WDT */;
+ F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+ 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
return -ENXIO;
kvm_queue_interrupt(vcpu, irq->irq, false);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
vcpu->arch.sipi_vector = events->sipi_vector;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- raw_spin_lock(&pic_irqchip(kvm)->lock);
+ spin_lock(&pic_irqchip(kvm)->lock);
memcpy(&pic_irqchip(kvm)->pics[0],
&chip->chip.pic,
sizeof(struct kvm_pic_state));
- raw_spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic_irqchip(kvm)->lock);
break;
case KVM_IRQCHIP_PIC_SLAVE:
- raw_spin_lock(&pic_irqchip(kvm)->lock);
+ spin_lock(&pic_irqchip(kvm)->lock);
memcpy(&pic_irqchip(kvm)->pics[1],
&chip->chip.pic,
sizeof(struct kvm_pic_state));
- raw_spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic_irqchip(kvm)->lock);
break;
case KVM_IRQCHIP_IOAPIC:
r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
goto out;
r = 0;
+ local_irq_disable();
now_ns = get_kernel_ns();
delta = user_ns.clock - now_ns;
+ local_irq_enable();
kvm->arch.kvmclock_offset = delta;
break;
}
struct kvm_clock_data user_ns;
u64 now_ns;
+ local_irq_disable();
now_ns = get_kernel_ns();
user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
+ local_irq_enable();
user_ns.flags = 0;
r = -EFAULT;
access |= PFERR_USER_MASK;
t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &error);
if (t_gpa == UNMAPPED_GVA)
- vcpu->arch.fault.error_code |= PFERR_NESTED_MASK;
+ vcpu->arch.fault.nested = true;
return t_gpa;
}
memcpy(c->regs, vcpu->arch.regs, sizeof c->regs);
}
+int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq)
+{
+ struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
+ int ret;
+
+ init_emulate_ctxt(vcpu);
+
+ vcpu->arch.emulate_ctxt.decode.op_bytes = 2;
+ vcpu->arch.emulate_ctxt.decode.ad_bytes = 2;
+ vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip;
+ ret = emulate_int_real(&vcpu->arch.emulate_ctxt, &emulate_ops, irq);
+
+ if (ret != X86EMUL_CONTINUE)
+ return EMULATE_FAIL;
+
+ vcpu->arch.emulate_ctxt.eip = c->eip;
+ memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
+ kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
+ kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+
+ if (irq == NMI_VECTOR)
+ vcpu->arch.nmi_pending = false;
+ else
+ vcpu->arch.interrupt.pending = false;
+
+ return EMULATE_DONE;
+}
+EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);
+
static int handle_emulation_failure(struct kvm_vcpu *vcpu)
{
++vcpu->stat.insn_emulation_fail;
toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
continue;
- if (!kvm_request_guest_time_update(vcpu))
- continue;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
if (vcpu->cpu != smp_processor_id())
send_ipi = 1;
}
{
int cpu;
+ max_tsc_khz = tsc_khz;
register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+#ifdef CONFIG_CPU_FREQ
+ struct cpufreq_policy policy;
+ memset(&policy, 0, sizeof(policy));
+ cpufreq_get_policy(&policy, get_cpu());
+ if (policy.cpuinfo.max_freq)
+ max_tsc_khz = policy.cpuinfo.max_freq;
+#endif
cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
+ pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
for_each_online_cpu(cpu)
smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
}
kvm_mmu_unload(vcpu);
if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
__kvm_migrate_timers(vcpu);
- if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu)) {
- r = kvm_write_guest_time(vcpu);
+ if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
+ r = kvm_guest_time_update(vcpu);
if (unlikely(r))
goto out;
}
if (unlikely(r))
goto out;
+ if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
+ inject_pending_event(vcpu);
+
+ /* enable NMI/IRQ window open exits if needed */
+ if (vcpu->arch.nmi_pending)
+ kvm_x86_ops->enable_nmi_window(vcpu);
+ else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
+ kvm_x86_ops->enable_irq_window(vcpu);
+
+ if (kvm_lapic_enabled(vcpu)) {
+ update_cr8_intercept(vcpu);
+ kvm_lapic_sync_to_vapic(vcpu);
+ }
+ }
+
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
smp_wmb();
local_irq_enable();
preempt_enable();
+ kvm_x86_ops->cancel_injection(vcpu);
r = 1;
goto out;
}
- inject_pending_event(vcpu);
-
- /* enable NMI/IRQ window open exits if needed */
- if (vcpu->arch.nmi_pending)
- kvm_x86_ops->enable_nmi_window(vcpu);
- else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
- kvm_x86_ops->enable_irq_window(vcpu);
-
- if (kvm_lapic_enabled(vcpu)) {
- update_cr8_intercept(vcpu);
- kvm_lapic_sync_to_vapic(vcpu);
- }
-
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_guest_enter();
vcpu->arch.exception.pending = false;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
struct kvm_mp_state *mp_state)
{
vcpu->arch.mp_state = mp_state->mp_state;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);
!is_protmode(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
vcpu->arch.dr6 = DR6_FIXED_1;
vcpu->arch.dr7 = DR7_FIXED_1;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
if (vcpu->cpu == smp_processor_id())
- kvm_request_guest_time_update(vcpu);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
return kvm_x86_ops->hardware_enable(garbage);
}
}
vcpu->arch.pio_data = page_address(page);
+ if (!kvm->arch.virtual_tsc_khz)
+ kvm_arch_set_tsc_khz(kvm, max_tsc_khz);
+
r = kvm_mmu_create(vcpu);
if (r < 0)
goto fail_free_pio_data;
kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
rflags |= X86_EFLAGS_TF;
kvm_x86_ops->set_rflags(vcpu, rflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);