linux-kernel - Re: [PATCH v2 12/15] KVM: x86/vmx: Disable Arch LBREn bit in #DB and warm reset

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:   Sun, 25 Dec 2022 12:12:21 +0800
From:   "Yang, Weijiang" <weijiang.yang@...el.com>
To:     Like Xu <like.xu.linux@...il.com>
CC:     <kan.liang@...ux.intel.com>, <wei.w.wang@...el.com>,
        <seanjc@...gle.com>, <pbonzini@...hat.com>, <jmattson@...gle.com>,
        <kvm@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 12/15] KVM: x86/vmx: Disable Arch LBREn bit in #DB and
 warm reset


On 12/22/2022 7:22 PM, Like Xu wrote:
> On 25/11/2022 12:06 pm, Yang Weijiang wrote:
>> +static void disable_arch_lbr_ctl(struct kvm_vcpu *vcpu)
>> +{
>> +    struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
>> +    struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
>> +
>> +    if (kvm_cpu_cap_has(X86_FEATURE_ARCH_LBR) &&
>> +        test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use) &&
>> +        lbr_desc->event) {
>> +        u64 ctl = vmcs_read64(GUEST_IA32_LBR_CTL);
>> +
>> +        vmcs_write64(GUEST_IA32_LBR_CTL, ctl & ~ARCH_LBR_CTL_LBREN);
>> +    }
>> +}
>> +
>>   static void vmx_inject_exception(struct kvm_vcpu *vcpu)
>>   {
>>       struct kvm_queued_exception *ex = &vcpu->arch.exception;
>> @@ -1738,6 +1752,9 @@ static void vmx_inject_exception(struct 
>> kvm_vcpu *vcpu)
>>       vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
>>         vmx_clear_hlt(vcpu);
>> +
>> +    if (ex->vector == DB_VECTOR)
>> +        disable_arch_lbr_ctl(vcpu);
>
> Please verify this with KUT testcase, once I failed and did not confirm
> if it is a hardware issue. Good Luck.


Can  you detail what you want to verify with?



>
>>   }