* 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
tps64 = base_khz * 1000LL;
scaled64 = scaled_khz * 1000LL;
- while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000UL) {
+ while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
}
tps32 = (uint32_t)tps64;
- while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000UL) {
- if (scaled64 & 0xffffffff00000000UL || tps32 & 0x80000000)
+ while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
+ if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
scaled64 >>= 1;
else
tps32 <<= 1;
}
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);
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)) {
+ 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
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_CLOCK_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();
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;
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);
}
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;