linux-kernel - Re: [PATCH v3 6/6] KVM: x86/vPMU: Add lazy mechanism to release perf

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:   Tue, 22 Oct 2019 12:47:11 +0200
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Like Xu <like.xu@...ux.intel.com>, peterz@...radead.org,
        kvm@...r.kernel.org
Cc:     like.xu@...el.com, linux-kernel@...r.kernel.org,
        jmattson@...gle.com, sean.j.christopherson@...el.com,
        wei.w.wang@...el.com, kan.liang@...el.com
Subject: Re: [PATCH v3 6/6] KVM: x86/vPMU: Add lazy mechanism to release
 perf_event per vPMC

On 21/10/19 18:06, Like Xu wrote:
>  
> +		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
>  		reprogram_fixed_counter(pmc, new_ctrl, i);
>  	}
>  
> @@ -329,6 +330,11 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
>  	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
>  	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
>  		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
> +
> +	bitmap_set(pmu->all_valid_pmc_idx,
> +		0, pmu->nr_arch_gp_counters);
> +	bitmap_set(pmu->all_valid_pmc_idx,
> +		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);

The offset needs to be INTEL_PMC_IDX_FIXED for GP counters, and 0 for
fixed counters, otherwise pmc_in_use and all_valid_pmc_idx are not in sync.

Paolo