From: Paolo Bonzini <pbonzini@redhat.com>
To: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH 5/6] KVM: x86: do not scan IRR twice on APICv vmentry
Date: Wed, 8 Feb 2017 15:10:49 +0100 [thread overview]
Message-ID: <7d5ef520-77b2-abd6-8840-f7b309676aa1@redhat.com> (raw)
In-Reply-To: <20170207201955.GD31091@potion>
On 07/02/2017 21:19, Radim Krčmář wrote:
> 2016-12-19 17:17+0100, Paolo Bonzini:
>> Calls to apic_find_highest_irr are scanning IRR twice, once
>> in vmx_sync_pir_from_irr and once in apic_search_irr. Change
>> sync_pir_from_irr to get the new maximum IRR from kvm_apic_update_irr;
>> now that it does the computation, it can also do the RVI write.
>>
>> In order to avoid complications in svm.c, make the callback optional.
>>
>> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
>> ---
>> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
>> @@ -8734,20 +8736,24 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
>> }
>> }
>>
>> -static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
>> +static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
>> {
>> struct vcpu_vmx *vmx = to_vmx(vcpu);
>> + int max_irr;
>>
>> - if (!pi_test_on(&vmx->pi_desc))
>> - return;
>> -
>> - pi_clear_on(&vmx->pi_desc);
>> - /*
>> - * IOMMU can write to PIR.ON, so the barrier matters even on UP.
>> - * But on x86 this is just a compiler barrier anyway.
>> - */
>> - smp_mb__after_atomic();
>> - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
>> + if (vcpu->arch.apicv_active && pi_test_on(&vmx->pi_desc)) {
>> + pi_clear_on(&vmx->pi_desc);
>> + /*
>> + * IOMMU can write to PIR.ON, so the barrier matters even on UP.
>> + * But on x86 this is just a compiler barrier anyway.
>> + */
>> + smp_mb__after_atomic();
>> + max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
>> + } else {
>> + max_irr = kvm_lapic_find_highest_irr(vcpu);
>> + }
>> + vmx_hwapic_irr_update(vcpu, max_irr);
>
> Btw. a v1 discussion revolved about the need to have
> vmx_hwapic_irr_update() here when the maximal IRR should always be in
> RVI, and, uh, I didn't follow up (negligible attention span) ...
>
> There is one place where that doesn't hold: we don't update RVI after a
> EXTERNAL_INTERRUPT nested VM exit without VM_EXIT_ACK_INTR_ON_EXIT, but
> IRR has likely changed. Isn't that the problem?
I'm not sure... there shouldn't be any issue with missed RVI updates in
this series, since it does
if (kvm_lapic_enabled(vcpu)) {
/*
* This handles the case where a posted interrupt was
* notified with kvm_vcpu_kick.
*/
if (kvm_x86_ops->sync_pir_to_irr)
kvm_x86_ops->sync_pir_to_irr(vcpu);
}
on every VM entry (and kvm_lapic_find_highest_irr inside the callback).
That is not something I really like, but it's no worse than what was
there before
if (vcpu->arch.apicv_active)
kvm_x86_ops->hwapic_irr_update(vcpu,
kvm_lapic_find_highest_irr(vcpu));
}
and obviously better than going unnecessarily through KVM_REQ_EVENT
processing.
Paolo
next prev parent reply other threads:[~2017-02-08 14:18 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-19 16:17 [PATCH v2 0/6] KVM: x86: cleanup and speedup for APICv Paolo Bonzini
2016-12-19 16:17 ` [PATCH 1/6] KVM: vmx: clear pending interrupts on KVM_SET_LAPIC Paolo Bonzini
2017-02-07 17:42 ` Radim Krčmář
2016-12-19 16:17 ` [PATCH 2/6] kvm: nVMX: move nested events check to kvm_vcpu_running Paolo Bonzini
2017-02-07 18:16 ` Radim Krčmář
2016-12-19 16:17 ` [PATCH 3/6] KVM: x86: preparatory changes for APICv cleanups Paolo Bonzini
2017-02-07 18:20 ` Radim Krčmář
2016-12-19 16:17 ` [PATCH 4/6] KVM: vmx: move sync_pir_to_irr from apic_find_highest_irr to callers Paolo Bonzini
2016-12-19 16:17 ` [PATCH 5/6] KVM: x86: do not scan IRR twice on APICv vmentry Paolo Bonzini
2017-02-07 20:19 ` Radim Krčmář
2017-02-07 21:49 ` Radim Krčmář
2017-02-08 14:10 ` Paolo Bonzini [this message]
2017-02-08 14:24 ` Radim Krčmář
2016-12-19 16:17 ` [PATCH 6/6] kvm: x86: do not use KVM_REQ_EVENT for APICv interrupt injection Paolo Bonzini
2017-02-07 19:58 ` Radim Krčmář
2017-02-08 16:23 ` Paolo Bonzini
2017-02-09 15:11 ` Radim Krčmář
2017-03-09 1:23 ` Wanpeng Li
2017-03-09 9:40 ` Wanpeng Li
2017-03-09 10:03 ` Paolo Bonzini
2017-02-07 17:23 ` [PATCH v2 0/6] KVM: x86: cleanup and speedup for APICv Paolo Bonzini
2017-02-07 21:52 ` Radim Krčmář
2017-02-08 10:04 ` Paolo Bonzini
2017-02-08 13:33 ` Radim Krčmář
2017-02-08 15:01 ` Paolo Bonzini
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=7d5ef520-77b2-abd6-8840-f7b309676aa1@redhat.com \
--to=pbonzini@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rkrcmar@redhat.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).