[PATCH v3 6/9] KVM: arm64: vgic: Implement SW-driven deactivation

[Alexandru Elisei]

Hi Marc,

Some questions regarding how this is supposed to work.

On 5/10/21 2:48 PM, Marc Zyngier wrote:
> In order to deal with these systems that do not offer HW-based
> deactivation of interrupts, let implement a SW-based approach:
>
> - When the irq is queued into a LR, treat it as a pure virtual
>   interrupt and set the EOI flag in the LR.
>
> - When the interrupt state is read back from the LR, force a
>   deactivation when the state is invalid (neither active nor
>   pending)
>
> Interrupts requiring such treatment get the VGIC_SW_RESAMPLE flag.
>
> Signed-off-by: Marc Zyngier <maz at kernel.org>
> ---
>  arch/arm64/kvm/vgic/vgic-v2.c | 19 +++++++++++++++----
>  arch/arm64/kvm/vgic/vgic-v3.c | 19 +++++++++++++++----
>  include/kvm/arm_vgic.h        | 10 ++++++++++
>  3 files changed, 40 insertions(+), 8 deletions(-)
>
> diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
> index 11934c2af2f4..2c580204f1dc 100644
> --- a/arch/arm64/kvm/vgic/vgic-v2.c
> +++ b/arch/arm64/kvm/vgic/vgic-v2.c
> @@ -108,11 +108,22 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
>  		 * If this causes us to lower the level, we have to also clear
>  		 * the physical active state, since we will otherwise never be
>  		 * told when the interrupt becomes asserted again.
> +		 *
> +		 * Another case is when the interrupt requires a helping hand
> +		 * on deactivation (no HW deactivation, for example).
>  		 */
> -		if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) {
> -			irq->line_level = vgic_get_phys_line_level(irq);
> +		if (vgic_irq_is_mapped_level(irq)) {
> +			bool resample = false;
> +
> +			if (val & GICH_LR_PENDING_BIT) {
> +				irq->line_level = vgic_get_phys_line_level(irq);
> +				resample = !irq->line_level;
> +			} else if (vgic_irq_needs_resampling(irq) &&
> +				   !(irq->active || irq->pending_latch)) {

So this means that if the IRQ has the special flag, if it's not pending in the LR
or at the software level, and it's not active either, then perform interrupt
deactivation. I don't see where the state of the interrupt is checked again, am I
correct in assuming that we rely on the CPU interface to assert the interrupt to
the host while we run with interrupts enabled in the run loop, and the handler for
the interrupt will mark it pending for kvm_vgic_sync_hw_state->vgic_vx_fold_lr_state?

> +				resample = true;
> +			}
>  
> -			if (!irq->line_level)
> +			if (resample)

This name, "resample", is confusing to me, quite possibly because I'm not familiar
with the irqchip subsystem. It was my impression that "resample" means that at
some point, the physical interrupt state will be checked again, yet I don't see
that happening anywhere when VGIC_IRQ_SW_RESAMPLE is set. Am I mistaken in my
assumptions?

Thanks,

Alex

>  				vgic_irq_set_phys_active(irq, false);
>  		}
>  
> @@ -152,7 +163,7 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
>  	if (irq->group)
>  		val |= GICH_LR_GROUP1;
>  
> -	if (irq->hw) {
> +	if (irq->hw && !vgic_irq_needs_resampling(irq)) {
>  		val |= GICH_LR_HW;
>  		val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT;
>  		/*
> diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
> index 41ecf219c333..66004f61cd83 100644
> --- a/arch/arm64/kvm/vgic/vgic-v3.c
> +++ b/arch/arm64/kvm/vgic/vgic-v3.c
> @@ -101,11 +101,22 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
>  		 * If this causes us to lower the level, we have to also clear
>  		 * the physical active state, since we will otherwise never be
>  		 * told when the interrupt becomes asserted again.
> +		 *
> +		 * Another case is when the interrupt requires a helping hand
> +		 * on deactivation (no HW deactivation, for example).
>  		 */
> -		if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) {
> -			irq->line_level = vgic_get_phys_line_level(irq);
> +		if (vgic_irq_is_mapped_level(irq)) {
> +			bool resample = false;
> +
> +			if (val & ICH_LR_PENDING_BIT) {
> +				irq->line_level = vgic_get_phys_line_level(irq);
> +				resample = !irq->line_level;
> +			} else if (vgic_irq_needs_resampling(irq) &&
> +				   !(irq->active || irq->pending_latch)) {
> +				resample = true;
> +			}
>  
> -			if (!irq->line_level)
> +			if (resample)
>  				vgic_irq_set_phys_active(irq, false);
>  		}
>  
> @@ -136,7 +147,7 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
>  		}
>  	}
>  
> -	if (irq->hw) {
> +	if (irq->hw && !vgic_irq_needs_resampling(irq)) {
>  		val |= ICH_LR_HW;
>  		val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
>  		/*
> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
> index e5f06df000f2..e602d848fc1a 100644
> --- a/include/kvm/arm_vgic.h
> +++ b/include/kvm/arm_vgic.h
> @@ -99,6 +99,11 @@ enum vgic_irq_config {
>   * kvm_arm_get_running_vcpu() to get the vcpu pointer for private IRQs.
>   */
>  struct irq_ops {
> +	/* Per interrupt flags for special-cased interrupts */
> +	unsigned long flags;
> +
> +#define VGIC_IRQ_SW_RESAMPLE	BIT(0)	/* Clear the active state for resampling */
> +
>  	/*
>  	 * Callback function pointer to in-kernel devices that can tell us the
>  	 * state of the input level of mapped level-triggered IRQ faster than
> @@ -150,6 +155,11 @@ struct vgic_irq {
>  					   for in-kernel devices. */
>  };
>  
> +static inline bool vgic_irq_needs_resampling(struct vgic_irq *irq)
> +{
> +	return irq->ops && (irq->ops->flags & VGIC_IRQ_SW_RESAMPLE);
> +}
> +
>  struct vgic_register_region;
>  struct vgic_its;
>