Re: [Qemu-devel] [PATCH] x86-KVM: Supply TSC and APIC clock rates to guest like VMWare

[Paolo Bonzini]

On 18/01/2017 15:24, Phil Dennis-Jordan wrote:
> ---
>  target/i386/cpu.c |  1 +
>  target/i386/cpu.h |  4 ++++
>  target/i386/kvm.c | 40 ++++++++++++++++++++++++++++++++--------
>  3 files changed, 37 insertions(+), 8 deletions(-)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index aba11ae..e5523d4 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -3677,6 +3677,7 @@ static Property x86_cpu_properties[] = {
>      DEFINE_PROP_BOOL("cpuid-0xb", X86CPU, enable_cpuid_0xb, true),
>      DEFINE_PROP_BOOL("lmce", X86CPU, enable_lmce, false),
>      DEFINE_PROP_BOOL("l3-cache", X86CPU, enable_l3_cache, true),
> +    DEFINE_PROP_BOOL("vmware-tsc-apic-clocks", X86CPU, vmware_clock_rates, 
> false),

Maybe just vmware-cpuid-freq instead?  Whatever the choice, please make
the bool field in struct X86CPU consistent with the property name (e.g.
enable_vmware_cpuid_freq).

One issue is that the TSC frequency can change, for example on
migration.  Telling the guest about the TSC frequency makes little sense
if it can change.

So the leaf should be conditional on the INVTSC feature
(CPUID[0x80000007].EDX bit 8).  You can enable this unconditionally for
new machine types (i.e. making it true here, and turning it off in
include/hw/i386/pc.h's PC_COMPAT_2_8 macro), but only expose it if that
bit is also set.

>      DEFINE_PROP_END_OF_LIST()
>  };
>  
> diff --git a/target/i386/cpu.h b/target/i386/cpu.h
> index 6c1902b..1d8590b 100644
> --- a/target/i386/cpu.h
> +++ b/target/i386/cpu.h
> @@ -1213,6 +1213,10 @@ struct X86CPU {
>      bool host_features;
>      uint32_t apic_id;
>  
> +    /* Enables publishing of TSC increment and Local APIC bus frequencies to
> +     * the guest OS in CPUID page 0x40000010, the same way that VMWare does. 
> */
> +    bool vmware_clock_rates;
> +
>      /* if true the CPUID code directly forward host cache leaves to the 
> guest */
>      bool cache_info_passthrough;
>  
> diff --git a/target/i386/kvm.c b/target/i386/kvm.c
> index 10a9cd8..7830b3a 100644
> --- a/target/i386/kvm.c
> +++ b/target/i386/kvm.c
> @@ -778,10 +778,14 @@ int kvm_arch_init_vcpu(CPUState *cs)
>      }
>  
>      if (cpu->expose_kvm) {
> +        uint32_t kvm_max_page = KVM_CPUID_FEATURES | kvm_base;

s/page/leaf/

> +        if (cpu->vmware_clock_rates && kvm_base == KVM_CPUID_SIGNATURE) {
> +            kvm_max_page = MAX(kvm_max_page, KVM_CPUID_SIGNATURE | 0x10);
> +        }
>          memcpy(signature, "KVMKVMKVM\0\0\0", 12);
>          c = &cpuid_data.entries[cpuid_i++];
>          c->function = KVM_CPUID_SIGNATURE | kvm_base;
> -        c->eax = KVM_CPUID_FEATURES | kvm_base;
> +        c->eax = kvm_max_page;
>          c->ebx = signature[0];
>          c->ecx = signature[1];
>          c->edx = signature[2];
> @@ -910,7 +914,6 @@ int kvm_arch_init_vcpu(CPUState *cs)
>          }
>      }
>  
> -    cpuid_data.cpuid.nent = cpuid_i;
>  
>      if (((env->cpuid_version >> 8)&0xF) >= 6
>          && (env->features[FEAT_1_EDX] & (CPUID_MCE | CPUID_MCA)) ==
> @@ -973,12 +976,6 @@ int kvm_arch_init_vcpu(CPUState *cs)
>          vmstate_x86_cpu.unmigratable = 1;
>      }
>  
> -    cpuid_data.cpuid.padding = 0;
> -    r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
> -    if (r) {
> -        return r;
> -    }
> -
>      r = kvm_arch_set_tsc_khz(cs);
>      if (r < 0) {
>          return r;
> @@ -998,6 +995,33 @@ int kvm_arch_init_vcpu(CPUState *cs)
>          }
>      }
>  
> +    if (cpu->vmware_clock_rates) {

^^ Here is where you should also check invtsc.

> +        if (cpu->expose_kvm

I think this should not depend on cpu->expose_kvm.  This is not a KVM
leaf, it's a vmware leaf; if it were a KVM leaf, it would obey kvm_base.
 Of course checking kvm_base is still a good idea, to avoid stomping on
Hyper-V's CPUID space.

Thanks,

Paolo

> +            && kvm_base == KVM_CPUID_SIGNATURE
> +            && env->tsc_khz != 0) {
> +            /* Publish TSC and LAPIC resolution on CPUID page 0x40000010
> +             * like VMWare for benefit of Darwin guests. */
> +            c = &cpuid_data.entries[cpuid_i++];
> +            c->function = KVM_CPUID_SIGNATURE | 0x10;
> +            c->eax = env->tsc_khz;
> +            /* LAPIC resolution of 1ns (freq: 1GHz) is hardcoded in KVM's
> +             * APIC_BUS_CYCLE_NS*/
> +            c->ebx = 1000000;
> +            c->ecx = c->edx = 0;
> +        } else {
> +            error_report(
> +                "Warning: VMWare-style TSC/LAPIC clock reporting 
> impossible.");


> +        }
> +    }
> +
> +    cpuid_data.cpuid.nent = cpuid_i;
> +
> +    cpuid_data.cpuid.padding = 0;
> +    r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
> +    if (r) {
> +        return r;
> +    }
> +
>      if (has_xsave) {
>          env->kvm_xsave_buf = qemu_memalign(4096, sizeof(struct kvm_xsave));
>      }
>