From: Andrew Murray <andrew.murray@arm.com>
To: Xiang Zheng <zhengxiang9@huawei.com>
Cc: marc.zyngier@arm.com, kvmarm@lists.cs.columbia.edu,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] KVM: ARM64: Update perf event when setting PMU count value
Date: Tue, 21 May 2019 17:44:46 +0100 [thread overview]
Message-ID: <20190521164445.GW8268@e119886-lin.cambridge.arm.com> (raw)
In-Reply-To: <20190519100559.7188-1-zhengxiang9@huawei.com>
On Sun, May 19, 2019 at 06:05:59PM +0800, Xiang Zheng wrote:
> Guest will adjust the sample period and set PMU counter value when
> it takes a long time to handle the PMU interrupts.
>
> However, we don't have a corresponding change on the virtual PMU
> which is emulated via a perf event. It could cause a large number
> of PMU interrupts injected to guest. Then guest will get hang for
> handling these interrupts.
Yes this is indeed an issue. I believe I've addressed this in my 'chained
pmu' series - the relevant patch is here...
https://lists.cs.columbia.edu/pipermail/kvmarm/2019-May/035933.html
Some other comments below.
>
> So update the sample_period of perf event if the counter value is
> changed to avoid this case.
>
> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com>
> ---
> virt/kvm/arm/pmu.c | 54 +++++++++++++++++++++++++++++++++++++++++++++---------
> 1 file changed, 45 insertions(+), 9 deletions(-)
>
> diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
> index 1c5b76c..cbad3ec 100644
> --- a/virt/kvm/arm/pmu.c
> +++ b/virt/kvm/arm/pmu.c
> @@ -24,6 +24,11 @@
> #include <kvm/arm_pmu.h>
> #include <kvm/arm_vgic.h>
>
> +static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
> +static struct perf_event *kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu,
> + struct kvm_pmc *pmc,
> + struct perf_event_attr *attr);
> +
> /**
> * kvm_pmu_get_counter_value - get PMU counter value
> * @vcpu: The vcpu pointer
> @@ -57,11 +62,29 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
> */
> void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
> {
> - u64 reg;
> + u64 reg, counter, old_sample_period;
> + struct kvm_pmu *pmu = &vcpu->arch.pmu;
> + struct kvm_pmc *pmc = &pmu->pmc[select_idx];
> + struct perf_event *event;
> + struct perf_event_attr attr;
>
> reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
> ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
> __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
> +
> + if (pmc->perf_event) {
> + attr = pmc->perf_event->attr;
> + old_sample_period = attr.sample_period;
> + counter = kvm_pmu_get_counter_value(vcpu, select_idx);
> + attr.sample_period = (-counter) & pmc->bitmask;
> + if (attr.sample_period == old_sample_period)
> + return;
I'd be interested to know how often this would evaluate to true.
> +
> + kvm_pmu_stop_counter(vcpu, pmc);
> + event = kvm_pmu_create_perf_event(vcpu, pmc, &attr);
I'm not sure it's necessary to change the prototype of kvm_pmu_create_perf_event
as this function will recalculate the sample period based on the updated counter
value anyway.
Thanks,
Andrew Murray
> + if (event)
> + pmc->perf_event = event;
> + }
> }
>
> /**
> @@ -303,6 +326,24 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
> }
> }
>
> +static struct perf_event *kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu,
> + struct kvm_pmc *pmc,
> + struct perf_event_attr *attr)
> +{
> + struct perf_event *event;
> +
> + event = perf_event_create_kernel_counter(attr, -1, current,
> + kvm_pmu_perf_overflow, pmc);
> +
> + if (IS_ERR(event)) {
> + pr_err_once("kvm: pmu event creation failed %ld\n",
> + PTR_ERR(event));
> + return NULL;
> + }
> +
> + return event;
> +}
> +
> /**
> * kvm_pmu_software_increment - do software increment
> * @vcpu: The vcpu pointer
> @@ -416,15 +457,10 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
> /* The initial sample period (overflow count) of an event. */
> attr.sample_period = (-counter) & pmc->bitmask;
>
> - event = perf_event_create_kernel_counter(&attr, -1, current,
> - kvm_pmu_perf_overflow, pmc);
> - if (IS_ERR(event)) {
> - pr_err_once("kvm: pmu event creation failed %ld\n",
> - PTR_ERR(event));
> - return;
> - }
> + event = kvm_pmu_create_perf_event(vcpu, pmc, &attr);
>
> - pmc->perf_event = event;
> + if (event)
> + pmc->perf_event = event;
> }
>
> bool kvm_arm_support_pmu_v3(void)
> --
> 1.8.3.1
>
>
> _______________________________________________
> kvmarm mailing list
> kvmarm@lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2019-05-21 16:45 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-19 10:05 [PATCH] KVM: ARM64: Update perf event when setting PMU count value Xiang Zheng
2019-05-21 16:44 ` Andrew Murray [this message]
2019-06-12 13:47 ` Xiang Zheng
2019-06-17 19:24 ` Andrew Murray
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=20190521164445.GW8268@e119886-lin.cambridge.arm.com \
--to=andrew.murray@arm.com \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=marc.zyngier@arm.com \
--cc=zhengxiang9@huawei.com \
/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).