KVM: arm64: PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation

As further patches will enable the selection of a PMU revision
from userspace, sample the supported PMU revision at VM creation
time, rather than building each time the ID_AA64DFR0_EL1 register
is accessed.

This shouldn't result in any change in behaviour.

Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-11-maz@kernel.org

arch/arm64/include/asm/kvm_host.h

@@ -163,6 +163,10 @@ struct kvm_arch {
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
+	struct {
+		u8 imp:4;
+		u8 unimp:4;
+	} dfr0_pmuver;
 
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;

arch/arm64/kvm/arm.c

@@ -164,6 +164,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	set_default_spectre(kvm);
 	kvm_arm_init_hypercalls(kvm);
 
+	/*
+	 * Initialise the default PMUver before there is a chance to
+	 * create an actual PMU.
+	 */
+	kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit();
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(&kvm->arch.mmu);

arch/arm64/kvm/pmu-emul.c

@@ -1047,3 +1047,14 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 	return -ENXIO;
 }
+
+u8 kvm_arm_pmu_get_pmuver_limit(void)
+{
+	u64 tmp;
+
+	tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	tmp = cpuid_feature_cap_perfmon_field(tmp,
+					      ID_AA64DFR0_EL1_PMUVer_SHIFT,
+					      ID_AA64DFR0_EL1_PMUVer_V3P4);
+	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
+}

arch/arm64/kvm/sys_regs.c

@@ -1062,6 +1062,27 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static u8 vcpu_pmuver(const struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_has_pmu(vcpu))
+		return vcpu->kvm->arch.dfr0_pmuver.imp;
+
+	return vcpu->kvm->arch.dfr0_pmuver.unimp;
+}
+
+static u8 pmuver_to_perfmon(u8 pmuver)
+{
+	switch (pmuver) {
+	case ID_AA64DFR0_EL1_PMUVer_IMP:
+		return ID_DFR0_PERFMON_8_0;
+	case ID_AA64DFR0_EL1_PMUVer_IMP_DEF:
+		return ID_DFR0_PERFMON_IMP_DEF;
+	default:
+		/* Anything ARMv8.1+ and NI have the same value. For now. */
+		return pmuver;
+	}
+}
+
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
 static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r)
 {
@@ -1111,18 +1132,17 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r
 		/* Limit debug to ARMv8.0 */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer);
 		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), 6);
-		/* Limit guests to PMUv3 for ARMv8.4 */
+		/* Set PMUver to the required version */
-		val = cpuid_feature_cap_perfmon_field(val,
+		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer);
-						      ID_AA64DFR0_EL1_PMUVer_SHIFT,
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer),
-						      kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_EL1_PMUVer_V3P4 : 0);
+				  vcpu_pmuver(vcpu));
 		/* Hide SPE from guests */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer);
 		break;
 	case SYS_ID_DFR0_EL1:
-		/* Limit guests to PMUv3 for ARMv8.4 */
+		val &= ~ARM64_FEATURE_MASK(ID_DFR0_PERFMON);
-		val = cpuid_feature_cap_perfmon_field(val,
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_PERFMON),
-						      ID_DFR0_PERFMON_SHIFT,
+				  pmuver_to_perfmon(vcpu_pmuver(vcpu)));
-						      kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0);
 		break;
 	}
 

include/kvm/arm_pmu.h

@@ -89,6 +89,8 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 			vcpu->arch.pmu.events = *kvm_get_pmu_events();	\
 	} while (0)
 
+u8 kvm_arm_pmu_get_pmuver_limit(void);
+
 #else
 struct kvm_pmu {
 };
@@ -154,6 +156,10 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
+static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
+{
+	return 0;
+}
 
 #endif