linux-kernel - Re: [PATCH 02/15] KVM: x86: Emulate RDPID only if RDTSCP is supported

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 5 May 2021 10:01:54 +0200
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Reiji Watanabe <reijiw@...gle.com>,
        Sean Christopherson <seanjc@...gle.com>
Cc:     Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, Xiaoyao Li <xiaoyao.li@...el.com>
Subject: Re: [PATCH 02/15] KVM: x86: Emulate RDPID only if RDTSCP is supported

On 05/05/21 05:51, Reiji Watanabe wrote:
>> --- a/arch/x86/kvm/cpuid.c
>> +++ b/arch/x86/kvm/cpuid.c
>> @@ -637,7 +637,8 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func)
>>          case 7:
>>                  entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
>>                  entry->eax = 0;
>> -               entry->ecx = F(RDPID);
>> +               if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP))
>> +                       entry->ecx = F(RDPID);
>>                  ++array->nent;
>>          default:
>>                  break;
> I'm wondering if entry->ecx should be set to F(RDPID) here
> even if the CPU supports RDPID natively.
> (i.e. kvm_cpu_cap_has(X86_FEATURE_RDPID) is true)
> 
> The document "Documentation/virt/kvm/api.rst" says:
> ---
> 4.88 KVM_GET_EMULATED_CPUID
> ---------------------------
> <...>
> Userspace can use the information returned by this ioctl to query
> which features are emulated by kvm instead of being present natively.
> ---

Setting it always is consistent with the treatment of MOVBE above. 
Either way is okay but it should be done for both bits.

Paolo