From: "Kang, Luwei" <luwei.kang@intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
"Liang, Kan" <kan.liang@linux.intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"mingo@redhat.com" <mingo@redhat.com>,
"acme@kernel.org" <acme@kernel.org>,
"mark.rutland@arm.com" <mark.rutland@arm.com>,
"alexander.shishkin@linux.intel.com"
<alexander.shishkin@linux.intel.com>,
"jolsa@redhat.com" <jolsa@redhat.com>,
"namhyung@kernel.org" <namhyung@kernel.org>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"bp@alien8.de" <bp@alien8.de>, "hpa@zytor.com" <hpa@zytor.com>,
"pbonzini@redhat.com" <pbonzini@redhat.com>,
"Christopherson, Sean J" <sean.j.christopherson@intel.com>,
"vkuznets@redhat.com" <vkuznets@redhat.com>,
"wanpengli@tencent.com" <wanpengli@tencent.com>,
"jmattson@google.com" <jmattson@google.com>,
"joro@8bytes.org" <joro@8bytes.org>,
"pawan.kumar.gupta@linux.intel.com"
<pawan.kumar.gupta@linux.intel.com>,
"ak@linux.intel.com" <ak@linux.intel.com>,
"thomas.lendacky@amd.com" <thomas.lendacky@amd.com>,
"Yu, Fenghua" <fenghua.yu@intel.com>,
"like.xu@linux.intel.com" <like.xu@linux.intel.com>,
"Wang, Wei W" <wei.w.wang@intel.com>
Subject: RE: [PATCH v1 01/11] perf/x86/core: Support KVM to assign a dedicated counter for guest PEBS
Date: Fri, 19 Jun 2020 09:30:06 +0000 [thread overview]
Message-ID: <DM5PR1101MB22663D2305EAC6A3D00F239580980@DM5PR1101MB2266.namprd11.prod.outlook.com> (raw)
In-Reply-To: <DM5PR1101MB22667E832B3E9C1EF5389F2280810@DM5PR1101MB2266.namprd11.prod.outlook.com>
> > > > Suppose your KVM thing claims counter 0/2 (ICL/SKL) for some
> > > > random PEBS event, and then the host wants to use PREC_DIST.. Then
> > > > one of them will be screwed for no reason what so ever.
> > > >
> > >
> > > The multiplexing should be triggered.
> > >
> > > For host, if both user A and user B requires PREC_DIST, the
> > > multiplexing should be triggered for them.
> > > Now, the user B is KVM. I don't think there is difference. The
> > > multiplexing should still be triggered. Why it is screwed?
> >
> > Becuase if KVM isn't PREC_DIST we should be able to reschedule it to a
> > different counter.
> >
> > > > How is that not destroying scheduling freedom? Any other situation
> > > > we'd have moved the !PREC_DIST PEBS event to another counter.
> > > >
> > >
> > > All counters are equivalent for them. It doesn't matter if we move
> > > it to another counter. There is no impact for the user.
> >
> > But we cannot move it to another counter, because you're pinning it.
>
> Hi Peter,
>
> To avoid the pinning counters, I have tried to do some evaluation about
> patching the PEBS record for guest in KVM. In this approach, about ~30% time
> increased on guest PEBS PMI handler latency ( e.g.perf record -e branch-
> loads:p -c 1000 ~/Tools/br_instr a).
>
> Some implementation details as below:
> 1. Patching the guest PEBS records "Applicable Counters" filed when the guest
> required counter is not the same with the host. Because the guest PEBS
> driver will drop these PEBS records if the "Applicable Counters" not the
> same with the required counter index.
> 2. Traping the guest driver's behavior(VM-exit) of disabling PEBS.
> It happens before reading PEBS records (e.g. PEBS PMI handler, before
> application exit and so on)
> 3. To patch the Guest PEBS records in KVM, we need to get the HPA of the
> guest PEBS buffer.
> <1> Trapping the guest write of IA32_DS_AREA register and get the GVA
> of guest DS_AREA.
> <2> Translate the DS AREA GVA to GPA(kvm_mmu_gva_to_gpa_read)
> and get the GVA of guest PEBS buffer from DS AREA
> (kvm_vcpu_read_guest_atomic).
> <3> Although we have got the GVA of PEBS buffer, we need to do the
> address translation(GVA->GPA->HPA) for each page. Because we can't
> assume the GPAs of Guest PEBS buffer are always continuous.
>
> But we met another issue about the PEBS counter reset field in DS AREA.
> pebs_event_reset in DS area has to be set for auto reload, which is per counter.
> Guest and Host may use different counters. Let's say guest wants to use
> counter 0, but host assign counter 1 to guest. Guest sets the reset value to
> pebs_event_reset[0]. However, since counter 1 is the one which is eventually
> scheduled, HW will use pebs_event_reset[1] as reset value.
>
> We can't copy the value of the guest pebs_event_reset[0] to
> pebs_event_reset[1] directly(Patching DS AREA) because the guest driver may
> confused, and we can't assume the guest counter 0 and 1 are not used for this
> PEBS task at the same time. And what's more, KVM can't aware the guest
> read/write to the DS AREA because it just a general memory for guest.
>
> What is your opinion or do you have a better proposal?
Kindly ping~
Thanks,
Luwei Kang
>
> Thanks,
> Luwei Kang
>
> >
> > > In the new proposal, KVM user is treated the same as other host
> > > events with event constraint. The scheduler is free to choose
> > > whether or not to assign a counter for it.
> >
> > That's what it does, I understand that. I'm saying that that is
> > creating artificial contention.
> >
> >
> > Why is this needed anyway? Can't we force the guest to flush and then
> > move it over to a new counter?
next prev parent reply other threads:[~2020-06-19 9:30 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-05 17:56 [PATCH v1 00/11] PEBS virtualization enabling via DS Luwei Kang
2020-03-05 16:51 ` Paolo Bonzini
2020-03-05 17:56 ` [PATCH v1 01/11] perf/x86/core: Support KVM to assign a dedicated counter for guest PEBS Luwei Kang
2020-03-06 13:53 ` Peter Zijlstra
2020-03-06 14:42 ` Liang, Kan
2020-03-09 10:04 ` Peter Zijlstra
2020-03-09 13:12 ` Liang, Kan
2020-03-09 15:05 ` Peter Zijlstra
2020-03-09 19:28 ` Liang, Kan
2020-03-12 10:28 ` Kang, Luwei
2020-03-26 14:03 ` Liang, Kan
2020-04-07 12:34 ` Kang, Luwei
2020-06-12 5:28 ` Kang, Luwei
2020-06-19 9:30 ` Kang, Luwei [this message]
2020-08-20 3:32 ` Like Xu
2020-03-09 15:44 ` Andi Kleen
2020-03-05 17:56 ` [PATCH v1 02/11] perf/x86/ds: Handle guest PEBS events overflow and inject fake PMI Luwei Kang
2020-03-05 17:56 ` [PATCH v1 03/11] perf/x86: Expose a function to disable auto-reload Luwei Kang
2020-03-05 17:56 ` [PATCH v1 04/11] KVM: x86/pmu: Decouple event enablement from event creation Luwei Kang
2020-03-05 17:56 ` [PATCH v1 05/11] KVM: x86/pmu: Add support to reprogram PEBS event for guest counters Luwei Kang
2020-03-06 16:28 ` kbuild test robot
2020-03-09 0:58 ` Xu, Like
2020-03-05 17:57 ` [PATCH v1 06/11] KVM: x86/pmu: Implement is_pebs_via_ds_supported pmu ops Luwei Kang
2020-03-05 17:57 ` [PATCH v1 07/11] KVM: x86/pmu: Expose CPUIDs feature bits PDCM, DS, DTES64 Luwei Kang
2020-03-05 17:57 ` [PATCH v1 08/11] KVM: x86/pmu: PEBS MSRs emulation Luwei Kang
2020-03-05 17:57 ` [PATCH v1 09/11] KVM: x86/pmu: Expose PEBS feature to guest Luwei Kang
2020-03-05 17:57 ` [PATCH v1 10/11] KVM: x86/pmu: Introduce the mask value for fixed counter Luwei Kang
2020-03-05 17:57 ` [PATCH v1 11/11] KVM: x86/pmu: Adaptive PEBS virtualization enabling Luwei Kang
2020-03-05 22:48 ` [PATCH v1 00/11] PEBS virtualization enabling via DS Andi Kleen
2020-03-06 5:37 ` Kang, Luwei
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=DM5PR1101MB22663D2305EAC6A3D00F239580980@DM5PR1101MB2266.namprd11.prod.outlook.com \
--to=luwei.kang@intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=bp@alien8.de \
--cc=fenghua.yu@intel.com \
--cc=hpa@zytor.com \
--cc=jmattson@google.com \
--cc=jolsa@redhat.com \
--cc=joro@8bytes.org \
--cc=kan.liang@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=like.xu@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=sean.j.christopherson@intel.com \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).