Date:   Tue, 18 May 2021 20:40:42 +0800
From:   "Xu, Like" <like.xu@...el.com>
To:     Liuxiangdong <liuxiangdong5@...wei.com>
Cc:     Borislav Petkov <bp@...en8.de>,
        Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, weijiang.yang@...el.com,
        Kan Liang <kan.liang@...ux.intel.com>, ak@...ux.intel.com,
        wei.w.wang@...el.com, eranian@...gle.com,
        linux-kernel@...r.kernel.org, x86@...nel.org, kvm@...r.kernel.org,
        "Fangyi (Eric)" <eric.fangyi@...wei.com>,
        Xiexiangyou <xiexiangyou@...wei.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Like Xu <like.xu@...ux.intel.com>
Subject: Re: [PATCH v6 00/16] KVM: x86/pmu: Add *basic* support to enable
 guest PEBS via DS

On 2021/5/18 20:23, Liuxiangdong wrote:
>
>
> On 2021/5/17 14:38, Like Xu wrote:
>> Hi xiangdong,
>>
>> On 2021/5/15 18:30, Liuxiangdong wrote:
>>>
>>>
>>> On 2021/5/11 10:41, Like Xu wrote:
>>>> A new kernel cycle has begun, and this version looks promising.
>>>>
>>>> The guest Precise Event Based Sampling (PEBS) feature can provide
>>>> an architectural state of the instruction executed after the guest
>>>> instruction that exactly caused the event. It needs new hardware
>>>> facility only available on Intel Ice Lake Server platforms. This
>>>> patch set enables the basic PEBS feature for KVM guests on ICX.
>>>>
>>>> We can use PEBS feature on the Linux guest like native:
>>>>
>>>>    # perf record -e instructions:ppp ./br_instr a
>>>>    # perf record -c 100000 -e instructions:pp ./br_instr a
>>>
>>> Hi, Like.
>>> Has the qemu patch been modified?
>>>
>>> https://lore.kernel.org/kvm/f4dcb068-2ddf-428f-50ad-39f65cad3710@intel.com/ 
>>> ?
>>
>> I think the qemu part still works based on
>> 609d7596524ab204ccd71ef42c9eee4c7c338ea4 (tag: v6.0.0).
>>
>
> Yes. I applied these two qemu patches to qemu v6.0.0 and this kvm patches 
> set to latest kvm tree.
>
> I can see pebs flags in Guest(linux 5.11) on the IceLake( Model: 106  
> Model name: Intel(R) Xeon(R) Platinum 8378A CPU),
> and i can use PEBS like this.
>
>     #perf record -e instructions:pp
>
> It can work normally.
>
> But  there is no sampling when i use "perf record -e events:pp" or just 
> "perf record" in guest
> unless i delete patch 09 and patch 13 from this kvm patches set.
>
>

With patch 9 and 13, does the basic counter sampling still work ?
You may retry w/ "echo 0 > /proc/sys/kernel/watchdog" on the host and guest.

> Have you tried "perf record -e events:pp" in this patches set? Does it 
> work normally?

All my PEBS testcases passed. You may dump guest msr traces from your 
testcase with me.

>
>
>
> Thanks!
> Xiangdong Liu
>
>
>
>> When the LBR qemu patch receives the ACK from the maintainer,
>> I will submit PBES qemu support because their changes are very similar.
>>
>> Please help review this version and
>> feel free to add your comments or "Reviewed-by".
>>
>> Thanks,
>> Like Xu
>>
>>>
>>>
>>>> To emulate guest PEBS facility for the above perf usages,
>>>> we need to implement 2 code paths:
>>>>
>>>> 1) Fast path
>>>>
>>>> This is when the host assigned physical PMC has an identical index as
>>>> the virtual PMC (e.g. using physical PMC0 to emulate virtual PMC0).
>>>> This path is used in most common use cases.
>>>>
>>>> 2) Slow path
>>>>
>>>> This is when the host assigned physical PMC has a different index
>>>> from the virtual PMC (e.g. using physical PMC1 to emulate virtual PMC0)
>>>> In this case, KVM needs to rewrite the PEBS records to change the
>>>> applicable counter indexes to the virtual PMC indexes, which would
>>>> otherwise contain the physical counter index written by PEBS facility,
>>>> and switch the counter reset values to the offset corresponding to
>>>> the physical counter indexes in the DS data structure.
>>>>
>>>> The previous version [0] enables both fast path and slow path, which
>>>> seems a bit more complex as the first step. In this patchset, we want
>>>> to start with the fast path to get the basic guest PEBS enabled while
>>>> keeping the slow path disabled. More focused discussion on the slow
>>>> path [1] is planned to be put to another patchset in the next step.
>>>>
>>>> Compared to later versions in subsequent steps, the functionality
>>>> to support host-guest PEBS both enabled and the functionality to
>>>> emulate guest PEBS when the counter is cross-mapped are missing
>>>> in this patch set (neither of these are typical scenarios).
>>>>
>>>> With the basic support, the guest can retrieve the correct PEBS
>>>> information from its own PEBS records on the Ice Lake servers.
>>>> And we expect it should work when migrating to another Ice Lake
>>>> and no regression about host perf is expected.
>>>>
>>>> Here are the results of pebs test from guest/host for same workload:
>>>>
>>>> perf report on guest:
>>>> # Samples: 2K of event 'instructions:ppp', # Event count (approx.): 
>>>> 1473377250
>>>> # Overhead  Command   Shared Object      Symbol
>>>>    57.74%  br_instr  br_instr           [.] lfsr_cond
>>>>    41.40%  br_instr  br_instr           [.] cmp_end
>>>>     0.21%  br_instr  [kernel.kallsyms]  [k] __lock_acquire
>>>>
>>>> perf report on host:
>>>> # Samples: 2K of event 'instructions:ppp', # Event count (approx.): 
>>>> 1462721386
>>>> # Overhead  Command   Shared Object     Symbol
>>>>    57.90%  br_instr  br_instr          [.] lfsr_cond
>>>>    41.95%  br_instr  br_instr          [.] cmp_end
>>>>     0.05%  br_instr  [kernel.vmlinux]  [k] lock_acquire
>>>>     Conclusion: the profiling results on the guest are similar tothat 
>>>> on the host.
>>>>
>>>> A minimum guest kernel version may be v5.4 or a backport version
>>>> support Icelake server PEBS.
>>>>
>>>> Please check more details in each commit and feel free to comment.
>>>>
>>>> Previous:
>>>> https://lore.kernel.org/kvm/20210415032016.166201-1-like.xu@linux.intel.com/ 
>>>>
>>>>
>>>> [0] 
>>>> https://lore.kernel.org/kvm/20210104131542.495413-1-like.xu@linux.intel.com/
>>>> [1] 
>>>> https://lore.kernel.org/kvm/20210115191113.nktlnmivc3edstiv@two.firstfloor.org/ 
>>>>
>>>>
>>>> V5 -> V6 Changelog:
>>>> - Rebased on the latest kvm/queue tree;
>>>> - Fix a git rebase issue (Liuxiangdong);
>>>> - Adjust the patch sequence 06/07 for bisection (Liuxiangdong);
>>>>
>>>> Like Xu (16):
>>>>    perf/x86/intel: Add EPT-Friendly PEBS for Ice Lake Server
>>>>    perf/x86/intel: Handle guest PEBS overflow PMI for KVM guest
>>>>    perf/x86/core: Pass "struct kvm_pmu *" to determine the guest values
>>>>    KVM: x86/pmu: Set MSR_IA32_MISC_ENABLE_EMON bit when vPMU is enabled
>>>>    KVM: x86/pmu: Introduce the ctrl_mask value for fixed counter
>>>>    KVM: x86/pmu: Add IA32_PEBS_ENABLE MSR emulation for extended PEBS
>>>>    KVM: x86/pmu: Reprogram PEBS event to emulate guest PEBS counter
>>>>    KVM: x86/pmu: Add IA32_DS_AREA MSR emulation to support guest DS
>>>>    KVM: x86/pmu: Add PEBS_DATA_CFG MSR emulation to support adaptive PEBS
>>>>    KVM: x86: Set PEBS_UNAVAIL in IA32_MISC_ENABLE when PEBS is enabled
>>>>    KVM: x86/pmu: Adjust precise_ip to emulate Ice Lake guest PDIR counter
>>>>    KVM: x86/pmu: Move pmc_speculative_in_use() to arch/x86/kvm/pmu.h
>>>>    KVM: x86/pmu: Disable guest PEBS temporarily in two rare situations
>>>>    KVM: x86/pmu: Add kvm_pmu_cap to optimize perf_get_x86_pmu_capability
>>>>    KVM: x86/cpuid: Refactor host/guest CPU model consistency check
>>>>    KVM: x86/pmu: Expose CPUIDs feature bits PDCM, DS, DTES64
>>>>
>>>>   arch/x86/events/core.c            |   5 +-
>>>>   arch/x86/events/intel/core.c      | 129 ++++++++++++++++++++++++------
>>>>   arch/x86/events/perf_event.h      |   5 +-
>>>>   arch/x86/include/asm/kvm_host.h   |  16 ++++
>>>>   arch/x86/include/asm/msr-index.h  |   6 ++
>>>>   arch/x86/include/asm/perf_event.h |   5 +-
>>>>   arch/x86/kvm/cpuid.c              |  24 ++----
>>>>   arch/x86/kvm/cpuid.h              |   5 ++
>>>>   arch/x86/kvm/pmu.c                |  50 +++++++++---
>>>>   arch/x86/kvm/pmu.h                |  38 +++++++++
>>>>   arch/x86/kvm/vmx/capabilities.h   |  26 ++++--
>>>>   arch/x86/kvm/vmx/pmu_intel.c      | 115 +++++++++++++++++++++-----
>>>>   arch/x86/kvm/vmx/vmx.c            |  24 +++++-
>>>>   arch/x86/kvm/vmx/vmx.h            |   2 +-
>>>>   arch/x86/kvm/x86.c                |  14 ++--
>>>>   15 files changed, 368 insertions(+), 96 deletions(-)
>>>>
>>
>

Powered by blists - more mailing lists