[PATCH v9 18/50] KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's

[Marc Zyngier]

When mapping a page in a shadow stage-2, special care must be
taken not to be more permissive than the guest is (writable or
readable page when the guest hasn't set that permission).

Reviewed-by: Alexandru Elisei <alexandru.elisei at arm.com>
Signed-off-by: Marc Zyngier <maz at kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 15 +++++++++++++++
 arch/arm64/kvm/mmu.c                | 14 +++++++++++++-
 arch/arm64/kvm/nested.c             |  2 +-
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 33a25ac0e258..d414749cb791 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -91,6 +91,21 @@ static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
 	return trans->esr;
 }
 
+static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans)
+{
+	return trans->readable;
+}
+
+static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans)
+{
+	return trans->writable;
+}
+
+static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans)
+{
+	return !(trans->upper_attr & BIT(54));
+}
+
 extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 			      struct kvm_s2_trans *result);
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index e08001a45a89..6ef930365cc3 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1425,6 +1425,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
+	/*
+	 * Potentially reduce shadow S2 permissions to match the guest's own
+	 * S2. For exec faults, we'd only reach this point if the guest
+	 * actually allowed it (see kvm_s2_handle_perm_fault).
+	 */
+	if (nested) {
+		writable &= kvm_s2_trans_writable(nested);
+		if (!kvm_s2_trans_readable(nested))
+			prot &= ~KVM_PGTABLE_PROT_R;
+	}
+
 	read_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq))
@@ -1467,7 +1478,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (device)
 		prot |= KVM_PGTABLE_PROT_DEVICE;
-	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC) &&
+		 (!nested || kvm_s2_trans_executable(nested)))
 		prot |= KVM_PGTABLE_PROT_X;
 
 	/*
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 1cf2ad18a5cd..bca209cf3fac 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -502,7 +502,7 @@ int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
 		return 0;
 
 	if (kvm_vcpu_trap_is_iabt(vcpu)) {
-		forward_fault = (trans->upper_attr & BIT(54));
+		forward_fault = !kvm_s2_trans_executable(trans);
 	} else {
 		bool write_fault = kvm_is_write_fault(vcpu);
 
-- 
2.34.1