[PATCH v6 55/64] KVM: arm64: nv: Tag shadow S2 entries with nested level

[Marc Zyngier]

Populate bits [56:55] of the leaf entry with the level provided
by the guest's S2 translation.

Signed-off-by: Marc Zyngier <maz at kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  7 +++++++
 arch/arm64/kvm/mmu.c                | 11 +++++++++++
 2 files changed, 18 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 847b652bd376..3b5838a2f29e 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -5,6 +5,8 @@
 #include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_pgtable.h>
+
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
 	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
@@ -140,4 +142,9 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 
 #define KVM_NV_GUEST_MAP_SZ	(KVM_PGTABLE_PROT_SW1 | KVM_PGTABLE_PROT_SW0)
 
+static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
+{
+	return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level);
+}
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 4b38f2f3c997..6caa48da1b2e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1281,11 +1281,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * 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).
+	 *
+	 * Also encode the level of the nested translation in the SW bits of
+	 * the PTE/PMD/PUD. This will be retrived on TLB invalidation from
+	 * the guest.
 	 */
 	if (kvm_is_shadow_s2_fault(vcpu)) {
 		writable &= kvm_s2_trans_writable(nested);
 		if (!kvm_s2_trans_readable(nested))
 			prot &= ~KVM_PGTABLE_PROT_R;
+
+		prot |= kvm_encode_nested_level(nested);
 	}
 
 	spin_lock(&kvm->mmu_lock);
@@ -1336,6 +1342,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
 	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
+		/*
+		 * Drop the SW bits in favour of those stored in the
+		 * PTE, which will be preserved.
+		 */
+		prot &= ~KVM_NV_GUEST_MAP_SZ;
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
-- 
2.30.2