linux-kernel - Re: [PATCH 0/1] KVM: x86/vPMU: Speed up vmexit for AMD Zen 4 CPUs

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]

Message-ID: <ZU2D3f6kc0MDzNR5@google.com>
Date:   Thu, 9 Nov 2023 17:14:05 -0800
From:   Sean Christopherson <seanjc@...gle.com>
To:     Jim Mattson <jmattson@...gle.com>
Cc:     Konstantin Khorenko <khorenko@...tuozzo.com>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org,
        "H . Peter Anvin" <hpa@...or.com>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, "Denis V. Lunev" <den@...tuozzo.com>
Subject: Re: [PATCH 0/1] KVM: x86/vPMU: Speed up vmexit for AMD Zen 4 CPUs

On Fri, Nov 10, 2023, Sean Christopherson wrote:
> On Thu, Nov 09, 2023, Jim Mattson wrote:
> > On Thu, Nov 9, 2023 at 3:42 PM Sean Christopherson <seanjc@...gle.com> wrote:
> > > static inline bool pmc_is_eventsel_match(struct kvm_pmc *pmc, u64 eventsel)
> > > {
> > >         return !((pmc->eventsel ^ eventsel) & AMD64_RAW_EVENT_MASK_NB);
> > > }
> > 
> > The top nybble of AMD's 3-nybble event select collides with Intel's
> > IN_TX and IN_TXCP bits. I think we can assert that the vCPU can't be
> > in a transaction if KVM is emulating an instruction, but this probably
> > merits a comment.
> 
> Argh, more pre-existing crud.  This is silly, the vendor mask is already in
> kvm_pmu_ops.EVENTSEL_EVENT.  What's one more patch...

Ah, I see what your saying.  Checking the bits is actually correct, probably through
sheer dumb luck.  I'll expand the comment to cover that and the reserved bits.