Re: [PATCH v2 8/8] KVM: Use eoi to track RTC interrupt delivery status

[Gleb Natapov <gleb@redhat.com>]

On Mon, Mar 18, 2013 at 03:24:39PM +0800, Yang Zhang wrote:
> From: Yang Zhang <yang.z.zhang@Intel.com>
> 
> Current interrupt coalescing logci which only used by RTC has conflict
> with Posted Interrupt.
> This patch introduces a new mechinism to use eoi to track interrupt:
> When delivering an interrupt to vcpu, the need_eoi set to number of
> vcpu that received the interrupt. And decrease it when each vcpu writing
> eoi. No subsequent RTC interrupt can deliver to vcpu until all vcpus
> write eoi.
> 
> Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
> ---
>  virt/kvm/ioapic.c |   67 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 files changed, 67 insertions(+), 0 deletions(-)
> 
> diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
> index 7e47da8..8d498e5 100644
> --- a/virt/kvm/ioapic.c
> +++ b/virt/kvm/ioapic.c
> @@ -130,6 +130,48 @@ static void rtc_irq_get_dest_vcpu(struct kvm_ioapic *ioapic, int irq)
>  	kvm_get_dest_vcpu(ioapic->kvm, &irqe, ioapic->rtc_status.vcpu_map);
>  }
>  
> +static void rtc_irq_set_eoi(struct kvm_ioapic *ioapic, int irq)
> +{
> +	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
> +
> +	if (irq != 8)
> +		return;
> +
> +	if (likely(!bitmap_empty(ioapic->rtc_status.vcpu_map, KVM_MAX_VCPUS))) {
> +		if (entry->fields.delivery_mode == APIC_DM_LOWEST)
> +			ioapic->rtc_status.need_eoi = 1;
> +		else {
> +			int weight;
> +			weight = bitmap_weight(ioapic->rtc_status.vcpu_map,
> +					sizeof(ioapic->rtc_status.vcpu_map));
> +			ioapic->rtc_status.need_eoi = weight;
> +		}
> +	}
> +}
> +
> +static void rtc_irq_ack_eoi(struct kvm_vcpu *vcpu,
> +			struct rtc_status *rtc_status, int irq)
> +{
> +	if (irq != 8)
> +		return;
> +
> +	if (test_bit(vcpu->vcpu_id, rtc_status->vcpu_map))
If you do not use test_and_clear_bit() here the WARN_ON() bellow can
be triggered by a malicious guest. Lets define rtc_status->expected_eoi
bitmap and copy vcpu_map into expected_eoi on each RTC irq.

> +		--rtc_status->need_eoi;
> +
> +	WARN_ON(rtc_status->need_eoi < 0);
> +}
> +
> +static bool rtc_irq_check(struct kvm_ioapic *ioapic, int irq)
> +{
> +	if (irq != 8)
> +		return false;
> +
> +	if (ioapic->rtc_status.need_eoi > 0)
> +		return true; /* coalesced */
> +
> +	return false;
> +}
> +
>  #else
>  
>  static void rtc_irq_reset(struct kvm_ioapic *ioapic)
> @@ -146,6 +188,22 @@ static void rtc_irq_get_dest_vcpu(struct kvm_ioapic *ioapic, int irq)
>  {
>  	return;
>  }
> +
> +static void rtc_irq_set_eoi(struct kvm_ioapic *ioapic, int irq)
> +{
> +	return;
> +}
> +
> +static void rtc_irq_ack_eoi(struct kvm_vcpu *vcpu,
> +			struct rtc_status *rtc_status, int irq)
> +{
> +	return;
> +}
> +
> +static bool rtc_irq_check(struct kvm_ioapic *ioapic, int irq)
> +{
> +	return false;
> +}
>  #endif
>  
>  static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
> @@ -282,6 +340,8 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
>  	irqe.level = 1;
>  	irqe.shorthand = 0;
>  
> +	rtc_irq_set_eoi(ioapic, irq);
> +
>  	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
>  }
>  
> @@ -306,6 +366,11 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
>  		ret = 1;
>  	} else {
>  		int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
> +
> +		if (rtc_irq_check(ioapic, irq)) {
> +			ret = 0; /* coalesced */
> +			goto out;
> +		}
>  		ioapic->irr |= mask;
>  		if ((edge && old_irr != ioapic->irr) ||
>  		    (!edge && !entry.fields.remote_irr))
> @@ -313,6 +378,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
>  		else
>  			ret = 0; /* report coalesced interrupt */
>  	}
> +out:
>  	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
>  	spin_unlock(&ioapic->lock);
>  
> @@ -340,6 +406,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
>  		if (ent->fields.vector != vector)
>  			continue;
>  
> +		rtc_irq_ack_eoi(vcpu, &ioapic->rtc_status, i);
>  		/*
>  		 * We are dropping lock while calling ack notifiers because ack
>  		 * notifier callbacks for assigned devices call into IOAPIC
> -- 
> 1.7.1

--
			Gleb.