[PATCH v11 37/43] 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 |  6 ++++++
 arch/arm64/kvm/mmu.c                | 16 ++++++++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 128c1d8281af..da7ebd2f6e24 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -5,6 +5,7 @@
 #include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_pgtable.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
@@ -134,4 +135,9 @@ int kvm_init_nv_sysregs(struct kvm *kvm);
 
 #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 8c77547f5582..61bdd8798f83 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1618,11 +1618,17 @@ 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 (nested) {
 		writable &= kvm_s2_trans_writable(nested);
 		if (!kvm_s2_trans_readable(nested))
 			prot &= ~KVM_PGTABLE_PROT_R;
+
+		prot |= kvm_encode_nested_level(nested);
 	}
 
 	read_lock(&kvm->mmu_lock);
@@ -1676,14 +1682,20 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_status == ESR_ELx_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
+	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache,
 					     KVM_PGTABLE_WALK_HANDLE_FAULT |
 					     KVM_PGTABLE_WALK_SHARED);
+	}
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret) {
-- 
2.39.2