All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Like Xu <like.xu.linux@gmail.com>
Cc: Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	kvm@vger.kernel.org, x86@kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] KVM: x86/pmu: Introduce pmc->is_paused to reduce the call time of perf interfaces
Date: Mon, 2 Aug 2021 17:46:20 +0200	[thread overview]
Message-ID: <0e1526dd-12e6-ad35-e69c-4eb58ed032e0@redhat.com> (raw)
In-Reply-To: <20210728120705.6855-1-likexu@tencent.com>

On 28/07/21 14:07, Like Xu wrote:
> From: Like Xu <likexu@tencent.com>
> 
> Based on our observations, after any vm-exit associated with vPMU, there
> are at least two or more perf interfaces to be called for guest counter
> emulation, such as perf_event_{pause, read_value, period}(), and each one
> will {lock, unlock} the same perf_event_ctx. The frequency of calls becomes
> more severe when guest use counters in a multiplexed manner.
> 
> Holding a lock once and completing the KVM request operations in the perf
> context would introduce a set of impractical new interfaces. So we can
> further optimize the vPMU implementation by avoiding repeated calls to
> these interfaces in the KVM context for at least one pattern:
> 
> After we call perf_event_pause() once, the event will be disabled and its
> internal count will be reset to 0. So there is no need to pause it again
> or read its value. Once the event is paused, event period will not be
> updated until the next time it's resumed or reprogrammed. And there is
> also no need to call perf_event_period twice for a non-running counter,
> considering the perf_event for a running counter is never paused.
> 
> Based on this implementation, for the following common usage of
> sampling 4 events using perf on a 4u8g guest:
> 
>    echo 0 > /proc/sys/kernel/watchdog
>    echo 25 > /proc/sys/kernel/perf_cpu_time_max_percent
>    echo 10000 > /proc/sys/kernel/perf_event_max_sample_rate
>    echo 0 > /proc/sys/kernel/perf_cpu_time_max_percent
>    for i in `seq 1 1 10`
>    do
>    taskset -c 0 perf record \
>    -e cpu-cycles -e instructions -e branch-instructions -e cache-misses \
>    /root/br_instr a
>    done
> 
> the average latency of the guest NMI handler is reduced from
> 37646.7 ns to 32929.3 ns (~1.14x speed up) on the Intel ICX server.
> Also, in addition to collecting more samples, no loss of sampling
> accuracy was observed compared to before the optimization.
> 
> Signed-off-by: Like Xu <likexu@tencent.com>
> ---
>   arch/x86/include/asm/kvm_host.h | 1 +
>   arch/x86/kvm/pmu.c              | 5 ++++-
>   arch/x86/kvm/pmu.h              | 2 +-
>   arch/x86/kvm/vmx/pmu_intel.c    | 4 ++--
>   4 files changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 99f37781a6fc..a079880d4cd5 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -482,6 +482,7 @@ struct kvm_pmc {
>   	 * ctrl value for fixed counters.
>   	 */
>   	u64 current_config;
> +	bool is_paused;
>   };
>   
>   struct kvm_pmu {
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index 827886c12c16..0772bad9165c 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -137,18 +137,20 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
>   	pmc->perf_event = event;
>   	pmc_to_pmu(pmc)->event_count++;
>   	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
> +	pmc->is_paused = false;
>   }
>   
>   static void pmc_pause_counter(struct kvm_pmc *pmc)
>   {
>   	u64 counter = pmc->counter;
>   
> -	if (!pmc->perf_event)
> +	if (!pmc->perf_event || pmc->is_paused)
>   		return;
>   
>   	/* update counter, reset event value to avoid redundant accumulation */
>   	counter += perf_event_pause(pmc->perf_event, true);
>   	pmc->counter = counter & pmc_bitmask(pmc);
> +	pmc->is_paused = true;
>   }
>   
>   static bool pmc_resume_counter(struct kvm_pmc *pmc)
> @@ -163,6 +165,7 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
>   
>   	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
>   	perf_event_enable(pmc->perf_event);
> +	pmc->is_paused = false;
>   
>   	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
>   	return true;
> diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
> index 67e753edfa22..0e4f2b1fa9fb 100644
> --- a/arch/x86/kvm/pmu.h
> +++ b/arch/x86/kvm/pmu.h
> @@ -55,7 +55,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
>   	u64 counter, enabled, running;
>   
>   	counter = pmc->counter;
> -	if (pmc->perf_event)
> +	if (pmc->perf_event && !pmc->is_paused)
>   		counter += perf_event_read_value(pmc->perf_event,
>   						 &enabled, &running);
>   	/* FIXME: Scaling needed? */
> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> index 9efc1a6b8693..10cc4f65c4ef 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -437,13 +437,13 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
>   				data = (s64)(s32)data;
>   			pmc->counter += data - pmc_read_counter(pmc);
> -			if (pmc->perf_event)
> +			if (pmc->perf_event && !pmc->is_paused)
>   				perf_event_period(pmc->perf_event,
>   						  get_sample_period(pmc, data));
>   			return 0;
>   		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
>   			pmc->counter += data - pmc_read_counter(pmc);
> -			if (pmc->perf_event)
> +			if (pmc->perf_event && !pmc->is_paused)
>   				perf_event_period(pmc->perf_event,
>   						  get_sample_period(pmc, data));
>   			return 0;
> 

Queued, thanks.

Paolo


      parent reply	other threads:[~2021-08-02 15:46 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-28 12:07 Like Xu
2021-07-29 12:58 ` Peter Zijlstra
2021-07-29 13:46   ` Like Xu
2021-08-02 15:46 ` Paolo Bonzini [this message]

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=0e1526dd-12e6-ad35-e69c-4eb58ed032e0@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=like.xu.linux@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH] KVM: x86/pmu: Introduce pmc->is_paused to reduce the call time of perf interfaces' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.