Re: [PATCH v7 4/8] KVM: arm/arm64: vgic: Support level-triggered mapped interrupts

[Auger Eric <eric.auger@redhat.com>]

Hi Christoffer,

On 07/12/17 11:54, Christoffer Dall wrote:
> Level-triggered mapped IRQs are special because we only observe rising
> edges as input to the VGIC, and we don't set the EOI flag and therefore
> are not told when the level goes down, so that we can re-queue a new
> interrupt when the level goes up.
> 
> One way to solve this problem is to side-step the logic of the VGIC and
> special case the validation in the injection path, but it has the
> unfortunate drawback of having to peak into the physical GIC state
> whenever we want to know if the interrupt is pending on the virtual
> distributor.
> 
> Instead, we can maintain the current semantics of a level triggered
> interrupt by sort of treating it as an edge-triggered interrupt,
> following from the fact that we only observe an asserting edge.  This
> requires us to be a bit careful when populating the LRs and when folding
> the state back in though:
> 
>  * We lower the line level when populating the LR, so that when
>    subsequently observing an asserting edge, the VGIC will do the right
>    thing.
> 
>  * If the guest never acked the interrupt while running (for example if
>    it had masked interrupts at the CPU level while running), we have
>    to preserve the pending state of the LR and move it back to the
>    line_level field of the struct irq when folding LR state.
> 
>    If the guest never acked the interrupt while running, but changed the
>    device state and lowered the line (again with interrupts masked) then
>    we need to observe this change in the line_level.
> 
>    Both of the above situations are solved by sampling the physical line
>    and set the line level when folding the LR back.
> 
>  * Finally, if the guest never acked the interrupt while running and
>    sampling the line reveals that the device state has changed and the
>    line has been lowered, we must clear the physical active state, since
>    we will otherwise never be told when the interrupt becomes asserted
>    again.
> 
> This has the added benefit of making the timer optimization patches
> (https://lists.cs.columbia.edu/pipermail/kvmarm/2017-July/026343.html) a
> bit simpler, because the timer code doesn't have to clear the active
> state on the sync anymore.  It also potentially improves the performance
> of the timer implementation because the GIC knows the state or the LR
> and only needs to clear the
> active state when the pending bit in the LR is still set, where the
> timer has to always clear it when returning from running the guest with
> an injected timer interrupt.
> 
> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Looks good to me.
Reviewed-by: Eric Auger <eric.auger@redhat.com>

Thanks

Eric

> ---
>  virt/kvm/arm/vgic/vgic-v2.c | 29 +++++++++++++++++++++++++++++
>  virt/kvm/arm/vgic/vgic-v3.c | 29 +++++++++++++++++++++++++++++
>  virt/kvm/arm/vgic/vgic.c    | 23 +++++++++++++++++++++++
>  virt/kvm/arm/vgic/vgic.h    |  7 +++++++
>  4 files changed, 88 insertions(+)
> 
> diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
> index 80897102da26..c32d7b93ffd1 100644
> --- a/virt/kvm/arm/vgic/vgic-v2.c
> +++ b/virt/kvm/arm/vgic/vgic-v2.c
> @@ -105,6 +105,26 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
>  				irq->pending_latch = false;
>  		}
>  
> +		/*
> +		 * Level-triggered mapped IRQs are special because we only
> +		 * observe rising edges as input to the VGIC.
> +		 *
> +		 * If the guest never acked the interrupt we have to sample
> +		 * the physical line and set the line level, because the
> +		 * device state could have changed or we simply need to
> +		 * process the still pending interrupt later.
> +		 *
> +		 * 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.
> +		 */
> +		if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) {
> +			irq->line_level = vgic_get_phys_line_level(irq);
> +
> +			if (!irq->line_level)
> +				vgic_irq_set_phys_active(irq, false);
> +		}
> +
>  		spin_unlock_irqrestore(&irq->irq_lock, flags);
>  		vgic_put_irq(vcpu->kvm, irq);
>  	}
> @@ -162,6 +182,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
>  			val |= GICH_LR_EOI;
>  	}
>  
> +	/*
> +	 * Level-triggered mapped IRQs are special because we only observe
> +	 * rising edges as input to the VGIC.  We therefore lower the line
> +	 * level here, so that we can take new virtual IRQs.  See
> +	 * vgic_v2_fold_lr_state for more info.
> +	 */
> +	if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT))
> +		irq->line_level = false;
> +
>  	/* The GICv2 LR only holds five bits of priority. */
>  	val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT;
>  
> diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
> index 2f05f732d3fd..a14423a0d383 100644
> --- a/virt/kvm/arm/vgic/vgic-v3.c
> +++ b/virt/kvm/arm/vgic/vgic-v3.c
> @@ -96,6 +96,26 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
>  				irq->pending_latch = false;
>  		}
>  
> +		/*
> +		 * Level-triggered mapped IRQs are special because we only
> +		 * observe rising edges as input to the VGIC.
> +		 *
> +		 * If the guest never acked the interrupt we have to sample
> +		 * the physical line and set the line level, because the
> +		 * device state could have changed or we simply need to
> +		 * process the still pending interrupt later.
> +		 *
> +		 * 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.
> +		 */
> +		if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) {
> +			irq->line_level = vgic_get_phys_line_level(irq);
> +
> +			if (!irq->line_level)
> +				vgic_irq_set_phys_active(irq, false);
> +		}
> +
>  		spin_unlock_irqrestore(&irq->irq_lock, flags);
>  		vgic_put_irq(vcpu->kvm, irq);
>  	}
> @@ -145,6 +165,15 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
>  			val |= ICH_LR_EOI;
>  	}
>  
> +	/*
> +	 * Level-triggered mapped IRQs are special because we only observe
> +	 * rising edges as input to the VGIC.  We therefore lower the line
> +	 * level here, so that we can take new virtual IRQs.  See
> +	 * vgic_v3_fold_lr_state for more info.
> +	 */
> +	if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT))
> +		irq->line_level = false;
> +
>  	/*
>  	 * We currently only support Group1 interrupts, which is a
>  	 * known defect. This needs to be addressed at some point.
> diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
> index b168a328a9e0..607cbbc27a1c 100644
> --- a/virt/kvm/arm/vgic/vgic.c
> +++ b/virt/kvm/arm/vgic/vgic.c
> @@ -144,6 +144,29 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
>  	kfree(irq);
>  }
>  
> +/* Get the input level of a mapped IRQ directly from the physical GIC */
> +bool vgic_get_phys_line_level(struct vgic_irq *irq)
> +{
> +	bool line_level;
> +
> +	BUG_ON(!irq->hw);
> +
> +	WARN_ON(irq_get_irqchip_state(irq->host_irq,
> +				      IRQCHIP_STATE_PENDING,
> +				      &line_level));
> +	return line_level;
> +}
> +
> +/* Set/Clear the physical active state */
> +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
> +{
> +
> +	BUG_ON(!irq->hw);
> +	WARN_ON(irq_set_irqchip_state(irq->host_irq,
> +				      IRQCHIP_STATE_ACTIVE,
> +				      active));
> +}
> +
>  /**
>   * kvm_vgic_target_oracle - compute the target vcpu for an irq
>   *
> diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
> index efbcf8f96f9c..d0787983a357 100644
> --- a/virt/kvm/arm/vgic/vgic.h
> +++ b/virt/kvm/arm/vgic/vgic.h
> @@ -104,6 +104,11 @@ static inline bool irq_is_pending(struct vgic_irq *irq)
>  		return irq->pending_latch || irq->line_level;
>  }
>  
> +static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
> +{
> +	return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
> +}
> +
>  /*
>   * This struct provides an intermediate representation of the fields contained
>   * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
> @@ -140,6 +145,8 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
>  struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
>  			      u32 intid);
>  void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
> +bool vgic_get_phys_line_level(struct vgic_irq *irq);
> +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
>  bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
>  			   unsigned long flags);
>  void vgic_kick_vcpus(struct kvm *kvm);
>