From: David Woodhouse The kvm_guest_time_update() function scales the host TSC frequency to the guest's using kvm_scale_tsc() and the v->arch.l1_tsc_scaling_ratio scaling ratio previously calculated for that vCPU. Then calculates the scaling factors for the KVM clock itself based on that guest TSC frequency. However, it uses kHz as the unit when scaling, and then multiplies by 1000 only at the end. With a host TSC frequency of 3000MHz and a guest set to 2500MHz, the result of kvm_scale_tsc() will actually come out at 2,499,999kHz. So the KVM clock advertised to the guest is based on a frequency of 2,499,999,000 Hz. By using Hz as the unit from the beginning, the KVM clock would be based on a more accurate frequency of 2,499,999,999 Hz in this example. Use u64 for the hw_tsc_hz field since an unsigned int would overflow for TSC frequencies above 4GHz. Use div_u64() for the Xen CPUID leaf to play nice with 32-bit kernels. Fixes: 78db6a503796 ("KVM: x86: rewrite handling of scaled TSC for kvmclock") Reviewed-by: Paul Durrant Signed-off-by: David Woodhouse Tested-by: Dongli Zhang Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/cpuid.c | 3 ++- arch/x86/kvm/x86.c | 18 ++++++++++-------- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 283847619ff8..6ddc988576d0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -864,7 +864,7 @@ struct kvm_vcpu_arch { gpa_t time; s8 pvclock_tsc_shift; u32 pvclock_tsc_mul; - unsigned int hw_tsc_khz; + u64 hw_tsc_hz; struct gfn_to_pfn_cache pv_time; /* set guest stopped flag in pvclock flags field */ bool pvclock_set_guest_stopped_request; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9e9cf6538a96..7049f5a5597b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -2146,7 +2147,7 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, *ecx = vcpu->arch.pvclock_tsc_mul; *edx = vcpu->arch.pvclock_tsc_shift; } else if (index == 2) { - *eax = vcpu->arch.hw_tsc_khz; + *eax = div_u64(vcpu->arch.hw_tsc_hz, HZ_PER_KHZ); } } } else { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d3b47e38698c..ce6d155b2ee6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -61,6 +61,7 @@ #include #include #include +#include #include #include @@ -1763,7 +1764,8 @@ static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock, int kvm_guest_time_update(struct kvm_vcpu *v) { struct pvclock_vcpu_time_info hv_clock = {}; - unsigned long flags, tgt_tsc_khz; + unsigned long flags; + u64 tgt_tsc_hz; unsigned seq; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; @@ -1789,8 +1791,8 @@ int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - tgt_tsc_khz = get_cpu_tsc_khz(); - if (unlikely(tgt_tsc_khz == 0)) { + tgt_tsc_hz = (u64)get_cpu_tsc_khz() * HZ_PER_KHZ; + if (unlikely(tgt_tsc_hz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); return 1; @@ -1831,16 +1833,16 @@ int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ if (kvm_caps.has_tsc_control) { - tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, + tgt_tsc_hz = kvm_scale_tsc(tgt_tsc_hz, v->arch.l1_tsc_scaling_ratio); - tgt_tsc_khz = tgt_tsc_khz ? : 1; + tgt_tsc_hz = tgt_tsc_hz ? : 1; } - if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { - kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, + if (unlikely(vcpu->hw_tsc_hz != tgt_tsc_hz)) { + kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_hz, &vcpu->pvclock_tsc_shift, &vcpu->pvclock_tsc_mul); - vcpu->hw_tsc_khz = tgt_tsc_khz; + vcpu->hw_tsc_hz = tgt_tsc_hz; } hv_clock.tsc_shift = vcpu->pvclock_tsc_shift; -- 2.55.0.571.g244d577d93-goog