[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231002115718.GB13957@noisy.programming.kicks-ass.net>
Date: Mon, 2 Oct 2023 13:57:18 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Sean Christopherson <seanjc@...gle.com>
Cc: Dapeng Mi <dapeng1.mi@...ux.intel.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Kan Liang <kan.liang@...ux.intel.com>,
Like Xu <likexu@...cent.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>, kvm@...r.kernel.org,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
Zhenyu Wang <zhenyuw@...ux.intel.com>,
Zhang Xiong <xiong.y.zhang@...el.com>,
Lv Zhiyuan <zhiyuan.lv@...el.com>,
Yang Weijiang <weijiang.yang@...el.com>,
Dapeng Mi <dapeng1.mi@...el.com>,
Jim Mattson <jmattson@...gle.com>,
David Dunn <daviddunn@...gle.com>,
Mingwei Zhang <mizhang@...gle.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...nel.org>
Subject: Re: [Patch v4 07/13] perf/x86: Add constraint for guest perf metrics
event
On Fri, Sep 29, 2023 at 03:46:55PM +0000, Sean Christopherson wrote:
> > I will firmly reject anything that takes the PMU away from the host
> > entirely through.
>
> Why? What is so wrong with supporting use cases where the platform owner *wants*
> to give up host PMU and NMI watchdog functionality? If disabling host PMU usage
> were complex, highly invasive, and/or difficult to maintain, then I can understand
> the pushback.
Because it sucks.
You're forcing people to choose between no host PMU or a slow guest PMU.
And that's simply not a sane choice for most people -- worse it's not a
choice based in technical reality.
It's a choice out of lazyness, disabling host PMU is not a requirement
for pass-through.
Like I wrote, all we need to do is ensure vCPU tasks will never have a
perf-event scheduled that covers guest mode. Currently this would be
achievable by having event creation for both:
- CPU events without attr::exclude_guest=1, and
- task events for vCPU task of interest without attr::exclude_guest=1
error with -EBUSY or something.
This ensures there are no events active for those vCPU tasks at VMENTER
time and you can haz pass-through.
Powered by blists - more mailing lists