[PATCH v2 04/28] KVM: arm64: nv: Only shadow writable-dirty guest descs as writable

[Oliver Upton <oupton@kernel.org>]

KVM will soon add support for hardware dirty state management for nested
guests. In order to emulate dirty state transitions on the guest
desciptor, KVM will need to use read-only hardware mappings and re-walk
the guest page tables upon taking a permission fault.

Prepare by limiting shadow stage-2 and shadow VNCR translations to
read-only for writable-clean guest translations.

Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  2 ++
 arch/arm64/kvm/at.c                 |  2 ++
 arch/arm64/kvm/mmu.c                |  2 +-
 arch/arm64/kvm/nested.c             | 15 +++++++++++----
 4 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 01645a5b224f..e8d5ae7afb9a 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -100,6 +100,7 @@ struct kvm_s2_trans {
 	u32		esr;
 	bool		writable;
 	bool		readable;
+	bool		dirty;
 	bool		px;
 	bool		ux;
 };
@@ -344,6 +345,7 @@ struct s1_walk_result {
 			bool	pr;
 			bool	pw;
 			bool	px;
+			bool	dirty;
 		};
 		struct {
 			u8	fst;
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 12ffd54be2b8..4e505433299b 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1315,6 +1315,7 @@ static void compute_s1_permissions(struct kvm_vcpu *vcpu,
 			  (pan3_enabled(vcpu, wi->regime) && wr->ux));
 	wr->pw &= !pan;
 	wr->pr &= !pan;
+	wr->dirty = !(wr->desc & BIT(7));
 }
 
 static int handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr, u64 *par)
@@ -1673,6 +1674,7 @@ int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
 	if (wr->level == S1_MMU_DISABLED) {
 		wr->ur = wr->uw = wr->ux = true;
 		wr->pr = wr->pw = wr->px = true;
+		wr->dirty = true;
 	} else {
 		ret = walk_s1(vcpu, wi, wr, va);
 		if (ret)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index cbf3cfb426ba..84aa1bb31095 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1703,7 +1703,7 @@ static int topup_mmu_memcache(struct kvm_s2_mmu *mmu, void *memcache)
 static enum kvm_pgtable_prot adjust_nested_fault_perms(struct kvm_s2_trans *nested,
 						       enum kvm_pgtable_prot prot)
 {
-	if (!nested->writable)
+	if (!(nested->writable && nested->dirty))
 		prot &= ~KVM_PGTABLE_PROT_W;
 	if (!nested->readable)
 		prot &= ~KVM_PGTABLE_PROT_R;
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 15c22a218609..9b2ea83aeccd 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -288,6 +288,8 @@ static void compute_s2_permissions(struct kvm_vcpu *vcpu, struct s2_walk_info *w
 
 	trans->readable = s2ap & BIT(0);
 	trans->writable = s2ap & BIT(1);
+
+	trans->dirty = ws->desc & BIT(7);
 }
 
 /*
@@ -1587,6 +1589,11 @@ static u64 read_vncr_el2(struct kvm_vcpu *vcpu)
 	return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48);
 }
 
+static bool vncr_can_map_writable(struct vncr_tlb *vt)
+{
+	return vt->wr.pw && vt->wr.dirty && vt->hpa_writable;
+}
+
 static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 {
 	struct kvm_memory_slot *memslot;
@@ -1683,10 +1690,10 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 		atomic_set(&vt->cpu, -1);
 
 		kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
-		kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw && vt->hpa_writable);
+		kvm_release_faultin_page(vcpu->kvm, page, false, vncr_can_map_writable(vt));
 	}
 
-	if (vt->wr.pw && vt->hpa_writable)
+	if (vncr_can_map_writable(vt))
 		mark_page_dirty(vcpu->kvm, gfn);
 
 	return 0;
@@ -1781,7 +1788,7 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 		kvm_inject_nested_sync(vcpu, esr);
 		break;
 	case 0:
-		perm = kvm_is_write_fault(vcpu) ? vt->wr.pw && vt->hpa_writable : vt->wr.pr;
+		perm = kvm_is_write_fault(vcpu) ? vncr_can_map_writable(vt) : vt->wr.pr;
 		if (!perm)
 			handle_vncr_perm(vcpu);
 		break;
@@ -1824,7 +1831,7 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid)
 		return;
 
-	if (vt->hpa_writable && vt->wr.pw && vt->wr.pr)
+	if (vncr_can_map_writable(vt) && vt->wr.pr)
 		prot = PAGE_KERNEL;
 	else if (vt->wr.pr)
 		prot = PAGE_KERNEL_RO;
-- 
2.47.3