Re: [PATCH] KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick

[Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>]

Hi,

On 03/18/2016 03:27 AM, Radim Krčmář wrote:
> 2016-03-18 02:44+0700, Suravee Suthikulpanit:
>> On 3/10/16 03:55, Radim Krčmář wrote:
>>> 2016-03-04 14:46-0600, Suravee Suthikulpanit:
>>>>> From: Suravee Suthikulpanit<suravee.suthikulpanit@amd.com>
>>>>>
>>>>> Introduce VMEXIT handlers, avic_incp_ipi_interception() and
>>>>> avic_noaccel_interception().
>>>>>
>>>>> Signed-off-by: Suravee Suthikulpanit<suravee.suthikulpanit@amd.com>
>>>>> ---
>>>>> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
>>>>> @@ -3690,6 +3690,264 @@ static int mwait_interception(struct vcpu_svm *svm)
>>>>> +	case AVIC_INCMP_IPI_ERR_TARGET_NOT_RUN: {
>>>>> +		kvm_for_each_vcpu(i, vcpu, kvm) {
>>>>> +			if (!kvm_apic_match_dest(vcpu, apic,
>>>>> +						 icrl & APIC_SHORT_MASK,
>>>>> +						 GET_APIC_DEST_FIELD(icrh),
>>>>> +						 icrl & APIC_DEST_MASK))
>>>>> +				continue;
>>>>> +
>>>>> +			kvm_vcpu_kick(vcpu);
>>> KVM shouldn't kick VCPUs that are running.  (Imagine a broadcast when
>>> most VCPUs are in guest mode.)
>>
>> So, besides checking if the vcpu match the destination, I will add the check
>> to see if the is_running bit is set before calling kvm_vcpu_kick()
>
> That will do.
>
>>> I think a new helper might be useful here: we only want to wake up from
>>> wait queue, but never force VCPU out of guest mode ... kvm_vcpu_kick()
>>> does both.
>>
>> If I only kick non-running vcpu, do I still need this new helper function?
>
> I would prefer it.  It's a minor performance optimization (non-running
> VCPUs aren't in guest mode) and makes our intent clear.  Please use
> include the following patch and use kvm_vcpu_wake_up instead.
>
> ---8<---
> AVIC has a use for kvm_vcpu_wake_up.
>
> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
> ---
>   include/linux/kvm_host.h |  1 +
>   virt/kvm/kvm_main.c      | 19 +++++++++++++------
>   2 files changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 861f690aa791..7b269626a3b3 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -650,6 +650,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
>   void kvm_vcpu_block(struct kvm_vcpu *vcpu);
>   void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
>   void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
> +void kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
>   void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
>   int kvm_vcpu_yield_to(struct kvm_vcpu *target);
>   void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 1eae05236347..c39c54afdb74 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -2054,13 +2054,8 @@ out:
>   EXPORT_SYMBOL_GPL(kvm_vcpu_block);
>
>   #ifndef CONFIG_S390
> -/*
> - * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
> - */
> -void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
> +void kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
>   {
> -	int me;
> -	int cpu = vcpu->cpu;
>   	wait_queue_head_t *wqp;
>
>   	wqp = kvm_arch_vcpu_wq(vcpu);
> @@ -2068,6 +2063,18 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
>   		wake_up_interruptible(wqp);
>   		++vcpu->stat.halt_wakeup;
>   	}
> +}
> +EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
> +
> +/*
> + * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
> + */
> +void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
> +{
> +	int me;
> +	int cpu = vcpu->cpu;
> +
> +	kvm_vcpu_wake_up(vcpu);
>
>   	me = get_cpu();
>   	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
>

Sure, I'll include this in my V3.

Thanks,
Suravee