Re: [PATCH 07/10] KVM: arm/arm64: vgic: Allow HW interrupts to be queued to a guest

[Eric Auger <eric.auger@linaro.org>]

Hi Marc,
On 06/08/2015 07:04 PM, Marc Zyngier wrote:
> To allow a HW interrupt to be injected into a guest, we lookup the
> guest virtual interrupt in the irq_phys_map rbtree, and if we have
> a match, encode both interrupts in the LR.
> 
> We also mark the interrupt as "active" at the host distributor level.
> 
> On guest EOI on the virtual interrupt, the host interrupt will be
> deactivated.
a "standard" physical IRQ would be first handled by the host handler
which would ack and deactivate it a first time. Here, if my
understanding is correct, the virtual counter PPI never hits. Instead we
"emulate" it on world-switch by directly setting the dist state. Is that
correct? If yes it is quite a specific handling of an "HW" IRQ.

> 
> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> ---
>  virt/kvm/arm/vgic.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 68 insertions(+), 3 deletions(-)
> 
> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
> index c6604f2..495ac7d 100644
> --- a/virt/kvm/arm/vgic.c
> +++ b/virt/kvm/arm/vgic.c
> @@ -1120,6 +1120,26 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq,
>  	if (!vgic_irq_is_edge(vcpu, irq))
>  		vlr.state |= LR_EOI_INT;
>  
> +	if (vlr.irq >= VGIC_NR_SGIS) {
> +		struct irq_phys_map *map;
> +		map = vgic_irq_map_search(vcpu, irq);
> +
> +		if (map) {
> +			int ret;
> +
> +			BUG_ON(!map->active);
> +			vlr.hwirq = map->phys_irq;
> +			vlr.state |= LR_HW;
> +			vlr.state &= ~LR_EOI_INT;
> +
> +			ret = irq_set_irqchip_state(map->irq,
> +						    IRQCHIP_STATE_ACTIVE,
> +						    true);
> +			vgic_irq_set_queued(vcpu, irq);
queued state was used for level sensitive IRQs only. Forwarded or "HW"
IRQs theoretically can be edge or sensitive, right? If yes may be worth
to justify the usage of queued state for forwarded IRQ? Also
vgic_irq_set_queued rather was called in parent vgic_queue_hwirq today.

> +			WARN_ON(ret);
> +		}
> +	}
> +
>  	vgic_set_lr(vcpu, lr_nr, vlr);
>  	vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
>  }
> @@ -1344,6 +1364,35 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
>  	return level_pending;
>  }
>  
> +/* Return 1 if HW interrupt went from active to inactive, and 0 otherwise */
> +static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr)
> +{
> +	struct irq_phys_map *map;
> +	int ret;
> +
> +	if (!(vlr.state & LR_HW))
> +		return 0;
> +
> +	map = vgic_irq_map_search(vcpu, vlr.irq);
> +	BUG_ON(!map || !map->active);
> +
> +	ret = irq_get_irqchip_state(map->irq,
> +				    IRQCHIP_STATE_ACTIVE,
> +				    &map->active);
Doesn't it work because the virtual timer was disabled during the world
switch. Does it characterize all "shared" devices? Difficult for me to
understand how much this is specific to arch timer integration?
> +
> +	WARN_ON(ret);
> +
> +	if (map->active) {
> +		ret = irq_set_irqchip_state(map->irq,
> +					    IRQCHIP_STATE_ACTIVE,
> +					    false);
> +		WARN_ON(ret);
> +		return 0;
> +	}
> +
> +	return 1;
> +}
> +
>  /* Sync back the VGIC state after a guest run */
>  static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
>  {
> @@ -1358,14 +1407,30 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
>  	elrsr = vgic_get_elrsr(vcpu);
>  	elrsr_ptr = u64_to_bitmask(&elrsr);
>  
> -	/* Clear mappings for empty LRs */
> -	for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
> +	/* Deal with HW interrupts, and clear mappings for empty LRs */
> +	for (lr = 0; lr < vgic->nr_lr; lr++) {
>  		struct vgic_lr vlr;
>  
> -		if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
> +		if (!test_bit(lr, vgic_cpu->lr_used))
>  			continue;
>  
>  		vlr = vgic_get_lr(vcpu, lr);
> +		if (vgic_sync_hwirq(vcpu, vlr)) {
> +			/*
> +			 * So this is a HW interrupt that the guest
> +			 * EOI-ed. Clean the LR state and allow the
> +			 * interrupt to be queued again.
> +			 */
> +			vlr.state &= ~LR_HW;
> +			vlr.hwirq = 0;
> +			vgic_set_lr(vcpu, lr, vlr);
> +			vgic_irq_clear_queued(vcpu, vlr.irq)
not necessarily a level sensitive IRQ?

- Eric
> +		}
> +
> +		if (!test_bit(lr, elrsr_ptr))
> +			continue;
> +
> +		clear_bit(lr, vgic_cpu->lr_used);
>  
>  		BUG_ON(vlr.irq >= dist->nr_irqs);
>  		vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
>