[PATCH 10/17] KVM: arm64: Restrict KVM_ARM_VCPU_INIT and PSCI version for protected VMs

[Fuad Tabba]

EL2 masks a protected VM's vCPU features down to the set pKVM allows,
so a KVM_ARM_VCPU_INIT that requests more succeeds and produces a
guest without them. Reject such an init with -EINVAL. The host and
EL2 both take the allowed set from kvm_pkvm_vcpu_allowed_features().

EL2 returns 1.1 for a protected guest's PSCI_VERSION whatever the
host is configured for, and forwards the platform calls to the host.
Require KVM_ARM_VCPU_PSCI_0_2: without it the host dispatches the
forwarded calls as PSCI 0.1. Reject a KVM_REG_ARM_PSCI_VERSION write
below 1.1: below it the host rejects the SYSTEM_RESET2 that EL2
advertises. KVM_CAP_ARM_PSCI is no longer advertised to protected VMs.

Signed-off-by: Fuad Tabba <fuad.tabba at linux.dev>
---
 arch/arm64/include/asm/kvm_pkvm.h | 25 ++++++++++++++++++++++++-
 arch/arm64/kvm/arm.c              | 13 +++++++++++++
 arch/arm64/kvm/hyp/nvhe/pkvm.c    | 17 ++---------------
 arch/arm64/kvm/hypercalls.c       |  7 +++++++
 4 files changed, 46 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index c4c834d55e503..ee3ab505b01f7 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -33,7 +33,6 @@ static inline bool kvm_pkvm_ext_allowed(struct kvm *kvm, long ext)
 {
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_ARM_PSCI:
 	case KVM_CAP_ARM_PSCI_0_2:
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
@@ -62,6 +61,30 @@ static inline bool kvm_pkvm_ext_allowed(struct kvm *kvm, long ext)
 	}
 }
 
+/*
+ * The vCPU features a protected VM may use: checked by the host at
+ * KVM_ARM_VCPU_INIT, applied by EL2 when the hyp VM is created.
+ */
+static inline void kvm_pkvm_vcpu_allowed_features(struct kvm *kvm,
+						  unsigned long *allowed)
+{
+	bitmap_zero(allowed, KVM_VCPU_MAX_FEATURES);
+
+	set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed);
+
+	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PMU_V3))
+		set_bit(KVM_ARM_VCPU_PMU_V3, allowed);
+
+	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_ADDRESS))
+		set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed);
+
+	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_GENERIC))
+		set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed);
+
+	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_SVE))
+		set_bit(KVM_ARM_VCPU_SVE, allowed);
+}
+
 /*
  * Check whether the KVM VM IOCTL is allowed in pKVM.
  *
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 8b080804bc90b..3e00edce23a99 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1620,6 +1620,19 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 	if (features & ~system_supported_vcpu_features())
 		return -EINVAL;
 
+	/* Reject features EL2 would drop when it creates the hyp VM. */
+	if (kvm_vm_is_protected(vcpu->kvm)) {
+		DECLARE_BITMAP(allowed, KVM_VCPU_MAX_FEATURES);
+
+		kvm_pkvm_vcpu_allowed_features(vcpu->kvm, allowed);
+		if (!bitmap_subset(&features, allowed, KVM_VCPU_MAX_FEATURES))
+			return -EINVAL;
+
+		/* EL2 implements PSCI 1.1; the host must not dispatch as 0.1. */
+		if (!test_bit(KVM_ARM_VCPU_PSCI_0_2, &features))
+			return -EINVAL;
+	}
+
 	/*
 	 * For now make sure that both address/generic pointer authentication
 	 * features are requested by the userspace together.
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 4dce489837cd2..4fb4c3c6ee92a 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -367,23 +367,10 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_MTE))
 		kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_MTE_ENABLED);
 
-	bitmap_zero(allowed_features, KVM_VCPU_MAX_FEATURES);
+	kvm_pkvm_vcpu_allowed_features(kvm, allowed_features);
 
-	set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed_features);
-
-	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PMU_V3))
-		set_bit(KVM_ARM_VCPU_PMU_V3, allowed_features);
-
-	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_ADDRESS))
-		set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed_features);
-
-	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_GENERIC))
-		set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed_features);
-
-	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_SVE)) {
-		set_bit(KVM_ARM_VCPU_SVE, allowed_features);
+	if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_SVE))
 		kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SVE);
-	}
 
 	bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features,
 		   allowed_features, KVM_VCPU_MAX_FEATURES);
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index b11b8821c9fbc..121199bda1add 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -580,6 +580,13 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 		wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2);
 
+		/*
+		 * EL2 advertises PSCI 1.1; the host handles the forwarded calls
+		 * by this version.
+		 */
+		if (kvm_vm_is_protected(vcpu->kvm) && val < KVM_ARM_PSCI_1_1)
+			return -EINVAL;
+
 		switch (val) {
 		case KVM_ARM_PSCI_0_1:
 			if (wants_02)
-- 
2.39.5