KVM: arm64: GICv3: Handle LR overflow when EOImode==0

Now that we can identify interrupts that have not made it into the LRs,
it becomes relatively easy to use EOIcount to walk the overflow list.

What is a bit odd is that we compute a fake LR for the original
state of the interrupt, clear the active bit, and feed into the existing
logic for processing. In a way, this is what would have happened if
the interrupt was in an LR.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-28-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>

1 files changed, 46 insertions, 0 deletions

diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 312226cc2565..d4f27f451c8f 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -112,16 +112,62 @@ static void vgic_v3_fold_lr(struct kvm_vcpu *vcpu, u64 val)
 	vgic_put_irq(vcpu->kvm, irq);
 }
 
+static u64 vgic_v3_compute_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq);
+
+static void vgic_v3_deactivate_phys(u32 intid)
+{
+	if (cpus_have_final_cap(ARM64_HAS_GICV5_LEGACY))
+		gic_insn(intid | FIELD_PREP(GICV5_GIC_CDDI_TYPE_MASK, 1), CDDI);
+	else
+		gic_write_dir(intid);
+}
+
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
+	u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr);
+	struct vgic_irq *irq;
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
 	for (int lr = 0; lr < cpuif->used_lrs; lr++)
 		vgic_v3_fold_lr(vcpu, cpuif->vgic_lr[lr]);
 
+	/*
+	 * EOIMode=0: use EOIcount to emulate deactivation. We are
+	 * guaranteed to deactivate in reverse order of the activation, so
+	 * just pick one active interrupt after the other in the ap_list,
+	 * and replay the deactivation as if the CPU was doing it. We also
+	 * rely on priority drop to have taken place, and the list to be
+	 * sorted by priority.
+	 */
+	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+		u64 lr;
+
+		/*
+		 * I would have loved to write this using a scoped_guard(),
+		 * but using 'continue' here is a total train wreck.
+		 */
+		if (!eoicount) {
+			break;
+		} else {
+			guard(raw_spinlock)(&irq->irq_lock);
+
+			if (!(likely(vgic_target_oracle(irq) == vcpu) &&
+			      irq->active))
+				continue;
+
+			lr = vgic_v3_compute_lr(vcpu, irq) & ~ICH_LR_ACTIVE_BIT;
+		}
+
+		if (lr & ICH_LR_HW)
+			vgic_v3_deactivate_phys(FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+
+		vgic_v3_fold_lr(vcpu, lr);
+		eoicount--;
+	}
+
 	cpuif->used_lrs = 0;
 }