[PATCH v2 3/6] KVM: arm64: Allow userspace to limit the number of PMU counters for EL2 VMs

[Marc Zyngier]

As long as we had purely EL1 VMs, we could easily update the number
of guest-visible counters by letting userspace write to PMCR_EL0.N.

With VMs started at EL2, PMCR_EL1.N only reflects MDCR_EL2.HPMN,
and we don't have a good way to limit it.

For this purpose, introduce a new PMUv3 attribute that allows
limiting the maximum number of counters. This requires the explicit
selection of a PMU.

Suggested-by: Oliver Upton <oliver.upton at linux.dev>
Signed-off-by: Marc Zyngier <maz at kernel.org>
---
 Documentation/virt/kvm/devices/vcpu.rst | 24 ++++++++++++++++++++++++
 arch/arm64/include/uapi/asm/kvm.h       |  9 +++++----
 arch/arm64/kvm/pmu-emul.c               | 24 ++++++++++++++++++++++++
 3 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst
index 31a9576c07afa..6eef154a2e396 100644
--- a/Documentation/virt/kvm/devices/vcpu.rst
+++ b/Documentation/virt/kvm/devices/vcpu.rst
@@ -137,6 +137,30 @@ exit_reason = KVM_EXIT_FAIL_ENTRY and populate the fail_entry struct by setting
 hardare_entry_failure_reason field to KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED and
 the cpu field to the processor id.
 
+1.5 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_SET_PMCR_N
+---------------------------------------------
+
+:Parameters: in kvm_device_attr.addr the address to an unsigned int
+	     representing the maximum value taken by PMCR_EL0.N
+
+:Returns:
+
+	 =======  ====================================================
+	 -EBUSY   PMUv3 already initialized, a VCPU has already run or
+                  an event filter has already been set
+	 -EFAULT  Error accessing the value pointed to by addr
+	 -ENODEV  PMUv3 not supported or GIC not initialized
+	 -EINVAL  No PMUv3 explicitly selected, or value of N out of
+	 	  range
+	 =======  ====================================================
+
+Update the maximum value allowed in PMCR_EL0.N, defining the number of
+counters visible to the guest. This mandates that a PMU has
+explicitly been selected via KVM_ARM_VCPU_PMU_V3_SET_PMU, and will
+fail when no PMU has been explicitly selected, or the number of
+counters is out of range for the selected PMU. Selecting a new PMU
+cancels the effect of setting this attribute.
+
 2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
 =================================
 
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index af9d9acaf9975..a1b106780cf9d 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -431,10 +431,11 @@ enum {
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
-#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
-#define   KVM_ARM_VCPU_PMU_V3_INIT	1
-#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
-#define   KVM_ARM_VCPU_PMU_V3_SET_PMU	3
+#define   KVM_ARM_VCPU_PMU_V3_IRQ		0
+#define   KVM_ARM_VCPU_PMU_V3_INIT		1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER		2
+#define   KVM_ARM_VCPU_PMU_V3_SET_PMU		3
+#define   KVM_ARM_VCPU_PMU_V3_SET_PMCR_N	4
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index f3650f2f2d468..01fda19b0c825 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -1099,6 +1099,20 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
 	return ret;
 }
 
+static int kvm_arm_pmu_v3_set_pmcr_n(struct kvm_vcpu *vcpu, unsigned int n)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	if (!kvm->arch.arm_pmu)
+		return -EINVAL;
+
+	if (n > kvm_arm_pmu_get_max_counters(kvm))
+		return -EINVAL;
+
+	kvm->arch.pmcr_n = n;
+	return 0;
+}
+
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1195,6 +1209,15 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 		return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id);
 	}
+	case KVM_ARM_VCPU_PMU_V3_SET_PMCR_N: {
+		unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr;
+		unsigned int n;
+
+		if (get_user(n, uaddr))
+			return -EFAULT;
+
+		return kvm_arm_pmu_v3_set_pmcr_n(vcpu, n);
+	}
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 		return kvm_arm_pmu_v3_init(vcpu);
 	}
@@ -1233,6 +1256,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 	case KVM_ARM_VCPU_PMU_V3_FILTER:
 	case KVM_ARM_VCPU_PMU_V3_SET_PMU:
+	case KVM_ARM_VCPU_PMU_V3_SET_PMCR_N:
 		if (kvm_vcpu_has_pmu(vcpu))
 			return 0;
 	}
-- 
2.39.2