KVM: arm64: Allow creating the PMU without the in-kernel GIC

Since we got support for devices in userspace which allows reporting the
PMU overflow output status to userspace, we should actually allow
creating the PMU on systems without an in-kernel irqchip, which in turn
requires us to slightly clarify error codes for the ABI and move things
around for the initialization phase.

Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>

4 files changed, 58 insertions, 19 deletions

diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virtual/kvm/devices/vcpu.txt
index 02f5068..d7236a3 100644
--- a/Documentation/virtual/kvm/devices/vcpu.txt
+++ b/Documentation/virtual/kvm/devices/vcpu.txt
@@ -16,7 +16,9 @@ Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
 Returns: -EBUSY: The PMU overflow interrupt is already set
          -ENXIO: The overflow interrupt not set when attempting to get it
          -ENODEV: PMUv3 not supported
-         -EINVAL: Invalid PMU overflow interrupt number supplied
+         -EINVAL: Invalid PMU overflow interrupt number supplied or
+                  trying to set the IRQ number without using an in-kernel
+                  irqchip.
 
 A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
 number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
@@ -25,11 +27,11 @@ all vcpus, while as an SPI it must be a separate number per vcpu.
 
 1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
 Parameters: no additional parameter in kvm_device_attr.addr
-Returns: -ENODEV: PMUv3 not supported
-         -ENXIO: PMUv3 not properly configured as required prior to calling this
-                 attribute
+Returns: -ENODEV: PMUv3 not supported or GIC not initialized
+         -ENXIO: PMUv3 not properly configured or in-kernel irqchip not
+                 configured as required prior to calling this attribute
          -EBUSY: PMUv3 already initialized
 
-Request the initialization of the PMUv3.  This must be done after creating the
-in-kernel irqchip.  Creating a PMU with a userspace irqchip is currently not
-supported.
+Request the initialization of the PMUv3.  If using the PMUv3 with an in-kernel
+virtual GIC implementation, this must be done after initializing the in-kernel
+irqchip.
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 1ab4633..f6e0306 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -35,6 +35,7 @@ struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	bool ready;
+	bool created;
 	bool irq_level;
 };
 
@@ -63,6 +64,7 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 #else
 struct kvm_pmu {
 };
@@ -112,6 +114,10 @@ static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 {
 	return -ENXIO;
 }
+static inline int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index cac5c2f..72816d3 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -527,6 +527,10 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	}
 
 	ret = kvm_timer_enable(vcpu);
+	if (ret)
+		return ret;
+
+	ret = kvm_arm_pmu_v3_enable(vcpu);
 
 	return ret;
 }
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 2451607..96a9cab 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -449,29 +449,50 @@ bool kvm_arm_support_pmu_v3(void)
 	return (perf_num_counters() > 0);
 }
 
-static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_arm_support_pmu_v3())
-		return -ENODEV;
+	if (!vcpu->arch.pmu.created)
+		return 0;
 
 	/*
-	 * We currently require an in-kernel VGIC to use the PMU emulation,
-	 * because we do not support forwarding PMU overflow interrupts to
-	 * userspace yet.
+	 * A valid interrupt configuration for the PMU is either to have a
+	 * properly configured interrupt number and using an in-kernel
+	 * irqchip, or to neither set an IRQ nor create an in-kernel irqchip.
 	 */
-	if (!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))
+	if (kvm_arm_pmu_irq_initialized(vcpu) != irqchip_in_kernel(vcpu->kvm))
+		return -EINVAL;
+
+	kvm_pmu_vcpu_reset(vcpu);
+	vcpu->arch.pmu.ready = true;
+
+	return 0;
+}
+
+static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_support_pmu_v3())
 		return -ENODEV;
 
-	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features) ||
-	    !kvm_arm_pmu_irq_initialized(vcpu))
+	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 		return -ENXIO;
 
-	if (kvm_arm_pmu_v3_ready(vcpu))
+	if (vcpu->arch.pmu.created)
 		return -EBUSY;
 
-	kvm_pmu_vcpu_reset(vcpu);
-	vcpu->arch.pmu.ready = true;
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		/*
+		 * If using the PMU with an in-kernel virtual GIC
+		 * implementation, we require the GIC to be already
+		 * initialized when initializing the PMU.
+		 */
+		if (!vgic_initialized(vcpu->kvm))
+			return -ENODEV;
+
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -ENXIO;
+	}
 
+	vcpu->arch.pmu.created = true;
 	return 0;
 }
 
@@ -510,6 +531,9 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		int __user *uaddr = (int __user *)(long)attr->addr;
 		int irq;
 
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
+
 		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 			return -ENODEV;
 
@@ -544,6 +568,9 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		int __user *uaddr = (int __user *)(long)attr->addr;
 		int irq;
 
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
+
 		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 			return -ENODEV;