KVM: arm/arm64: Report PMU overflow interrupts to userspace irqchip

When not using an in-kernel VGIC, but instead emulating an interrupt
controller in userspace, we should report the PMU overflow status to
that userspace interrupt controller using the KVM_CAP_ARM_USER_IRQ
feature.
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@linaro.org>

arch/arm/kvm/arm.c

@@ -635,11 +635,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		/*
 		 * If we have a singal pending, or need to notify a userspace
-		 * irqchip about timer level changes, then we exit (and update
-		 * the timer level state in kvm_timer_update_run below).
+		 * irqchip about timer or PMU level changes, then we exit (and
+		 * update the timer level state in kvm_timer_update_run
+		 * below).
 		 */
 		if (signal_pending(current) ||
-		    kvm_timer_should_notify_user(vcpu)) {
+		    kvm_timer_should_notify_user(vcpu) ||
+		    kvm_pmu_should_notify_user(vcpu)) {
 			ret = -EINTR;
 			run->exit_reason = KVM_EXIT_INTR;
 		}
@@ -712,7 +714,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	}
 
 	/* Tell userspace about in-kernel device output levels */
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
 		kvm_timer_update_run(vcpu);
+		kvm_pmu_update_run(vcpu);
+	}
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

include/kvm/arm_pmu.h

@@ -50,6 +50,8 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
+bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
+void kvm_pmu_update_run(struct kvm_vcpu *vcpu);
 void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
@@ -85,6 +87,11 @@ static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void kvm_pmu_update_run(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,

virt/kvm/arm/arch_timer.c

@@ -193,9 +193,6 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
 
-	if (likely(irqchip_in_kernel(vcpu->kvm)))
-		return;
-
 	/* Populate the device bitmap with the timer states */
 	regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
 				    KVM_ARM_DEV_EL1_PTIMER);

virt/kvm/arm/pmu.c

@@ -230,13 +230,44 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 		return;
 
 	overflow = !!kvm_pmu_overflow_status(vcpu);
-	if (pmu->irq_level != overflow) {
+	if (pmu->irq_level == overflow)
+		return;
+
 	pmu->irq_level = overflow;
-		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+
+	if (likely(irqchip_in_kernel(vcpu->kvm))) {
+		int ret;
+		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
 					  pmu->irq_num, overflow);
+		WARN_ON(ret);
 	}
 }
 
+bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
+	bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm)))
+		return false;
+
+	return pmu->irq_level != run_level;
+}
+
+/*
+ * Reflect the PMU overflow interrupt output level into the kvm_run structure
+ */
+void kvm_pmu_update_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Populate the timer bitmap for user space */
+	regs->device_irq_level &= ~KVM_ARM_DEV_PMU;
+	if (vcpu->arch.pmu.irq_level)
+		regs->device_irq_level |= KVM_ARM_DEV_PMU;
+}
+
 /**
  * kvm_pmu_flush_hwstate - flush pmu state to cpu
  * @vcpu: The vcpu pointer