[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAL715WJfOXOovUJSBtC0SfXVTuXEXwRF3sQBUzGaPDXe99dRoQ@mail.gmail.com>
Date: Fri, 30 Jun 2023 11:03:34 -0700
From: Mingwei Zhang <mizhang@...gle.com>
To: Jim Mattson <jmattson@...gle.com>
Cc: Sean Christopherson <seanjc@...gle.com>,
Roman Kagan <rkagan@...zon.de>,
Paolo Bonzini <pbonzini@...hat.com>,
Eric Hankland <ehankland@...gle.com>, kvm@...r.kernel.org,
Dave Hansen <dave.hansen@...ux.intel.com>,
Like Xu <likexu@...cent.com>, x86@...nel.org,
Thomas Gleixner <tglx@...utronix.de>,
linux-kernel@...r.kernel.org, "H. Peter Anvin" <hpa@...or.com>,
Borislav Petkov <bp@...en8.de>, Ingo Molnar <mingo@...hat.com>
Subject: Re: [PATCH] KVM: x86: vPMU: truncate counter value to allowed width
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index 48a0528080ab..8d28158e58f2 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -322,7 +322,7 @@ static void reprogram_counter(struct kvm_pmc *pmc)
> if (!pmc_event_is_allowed(pmc))
> goto reprogram_complete;
>
> - if (pmc->counter < pmc->prev_counter)
> + if (pmc->counter == 0)
> __kvm_perf_overflow(pmc, false);
>
> if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
>
> Since this is software emulation, we (KVM) should only handle overflow
> by plusing one?
Sign. Please ignore this as it is not only hacky but also not working.
Powered by blists - more mailing lists