1 files changed, 85 insertions, 40 deletions

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index f04cda40545b..cdeeb8f09e72 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -85,7 +85,7 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	/*
 	 * Let's treat memory allocation failures as benign: If we fail to
 	 * allocate anything, return an error and keep the allocated array
-	 * alive. Userspace may try to recover by intializing the vcpu
+	 * alive. Userspace may try to recover by initializing the vcpu
 	 * again, and there is no reason to affect the whole VM for this.
 	 */
 	num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;
@@ -124,14 +124,13 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 }
 
 struct s2_walk_info {
-	int	     (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
-	void	     *data;
-	u64	     baddr;
-	unsigned int max_oa_bits;
-	unsigned int pgshift;
-	unsigned int sl;
-	unsigned int t0sz;
-	bool	     be;
+	u64		baddr;
+	unsigned int	max_oa_bits;
+	unsigned int	pgshift;
+	unsigned int	sl;
+	unsigned int	t0sz;
+	bool		be;
+	bool		ha;
 };
 
 static u32 compute_fsc(int level, u32 fsc)
@@ -199,6 +198,42 @@ static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
 	return 0;
 }
 
+static int read_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 *desc,
+			      struct s2_walk_info *wi)
+{
+	u64 val;
+	int r;
+
+	r = kvm_read_guest(vcpu->kvm, pa, &val, sizeof(val));
+	if (r)
+		return r;
+
+	/*
+	 * Handle reversedescriptors if endianness differs between the
+	 * host and the guest hypervisor.
+	 */
+	if (wi->be)
+		*desc = be64_to_cpu((__force __be64)val);
+	else
+		*desc = le64_to_cpu((__force __le64)val);
+
+	return 0;
+}
+
+static int swap_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 old, u64 new,
+			      struct s2_walk_info *wi)
+{
+	if (wi->be) {
+		old = (__force u64)cpu_to_be64(old);
+		new = (__force u64)cpu_to_be64(new);
+	} else {
+		old = (__force u64)cpu_to_le64(old);
+		new = (__force u64)cpu_to_le64(new);
+	}
+
+	return __kvm_at_swap_desc(vcpu->kvm, pa, old, new);
+}
+
 /*
  * This is essentially a C-version of the pseudo code from the ARM ARM
  * AArch64.TranslationTableWalk  function.  I strongly recommend looking at
@@ -206,13 +241,13 @@ static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
  *
  * Must be called with the kvm->srcu read lock held
  */
-static int walk_nested_s2_pgd(phys_addr_t ipa,
+static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 			      struct s2_walk_info *wi, struct kvm_s2_trans *out)
 {
 	int first_block_level, level, stride, input_size, base_lower_bound;
 	phys_addr_t base_addr;
 	unsigned int addr_top, addr_bottom;
-	u64 desc;  /* page table entry */
+	u64 desc, new_desc;  /* page table entry */
 	int ret;
 	phys_addr_t paddr;
 
@@ -257,28 +292,30 @@ static int walk_nested_s2_pgd(phys_addr_t ipa,
 			>> (addr_bottom - 3);
 
 		paddr = base_addr | index;
-		ret = wi->read_desc(paddr, &desc, wi->data);
+		ret = read_guest_s2_desc(vcpu, paddr, &desc, wi);
 		if (ret < 0)
 			return ret;
 
-		/*
-		 * Handle reversedescriptors if endianness differs between the
-		 * host and the guest hypervisor.
-		 */
-		if (wi->be)
-			desc = be64_to_cpu((__force __be64)desc);
-		else
-			desc = le64_to_cpu((__force __le64)desc);
+		new_desc = desc;
 
 		/* Check for valid descriptor at this point */
-		if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) {
+		if (!(desc & KVM_PTE_VALID)) {
 			out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
 			out->desc = desc;
 			return 1;
 		}
 
-		/* We're at the final level or block translation level */
-		if ((desc & 3) == 1 || level == 3)
+		if (FIELD_GET(KVM_PTE_TYPE, desc) == KVM_PTE_TYPE_BLOCK) {
+			if (level < 3)
+				break;
+
+			out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+			out->desc = desc;
+			return 1;
+		}
+
+		/* We're at the final level */
+		if (level == 3)
 			break;
 
 		if (check_output_size(wi, desc)) {
@@ -305,7 +342,18 @@ static int walk_nested_s2_pgd(phys_addr_t ipa,
 		return 1;
 	}
 
-	if (!(desc & BIT(10))) {
+	if (wi->ha)
+		new_desc |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
+
+	if (new_desc != desc) {
+		ret = swap_guest_s2_desc(vcpu, paddr, desc, new_desc, wi);
+		if (ret)
+			return ret;
+
+		desc = new_desc;
+	}
+
+	if (!(desc & KVM_PTE_LEAF_ATTR_LO_S2_AF)) {
 		out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS);
 		out->desc = desc;
 		return 1;
@@ -318,20 +366,13 @@ static int walk_nested_s2_pgd(phys_addr_t ipa,
 		(ipa & GENMASK_ULL(addr_bottom - 1, 0));
 	out->output = paddr;
 	out->block_size = 1UL << ((3 - level) * stride + wi->pgshift);
-	out->readable = desc & (0b01 << 6);
-	out->writable = desc & (0b10 << 6);
+	out->readable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;
+	out->writable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 	out->level = level;
 	out->desc = desc;
 	return 0;
 }
 
-static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data)
-{
-	struct kvm_vcpu *vcpu = data;
-
-	return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc));
-}
-
 static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
 {
 	wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK;
@@ -350,6 +391,8 @@ static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
 	/* Global limit for now, should eventually be per-VM */
 	wi->max_oa_bits = min(get_kvm_ipa_limit(),
 			      ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr), false));
+
+	wi->ha = vtcr & VTCR_EL2_HA;
 }
 
 int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
@@ -364,15 +407,13 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	if (!vcpu_has_nv(vcpu))
 		return 0;
 
-	wi.read_desc = read_guest_s2_desc;
-	wi.data = vcpu;
 	wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
 
 	vtcr_to_walk_info(vtcr, &wi);
 
 	wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE;
 
-	ret = walk_nested_s2_pgd(gipa, &wi, result);
+	ret = walk_nested_s2_pgd(vcpu, gipa, &wi, result);
 	if (ret)
 		result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC);
 
@@ -788,7 +829,10 @@ 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 = !kvm_s2_trans_executable(trans);
+		if (vcpu_mode_priv(vcpu))
+			forward_fault = !kvm_s2_trans_exec_el1(vcpu->kvm, trans);
+		else
+			forward_fault = !kvm_s2_trans_exec_el0(vcpu->kvm, trans);
 	} else {
 		bool write_fault = kvm_is_write_fault(vcpu);
 
@@ -1555,12 +1599,13 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 	case SYS_ID_AA64MMFR1_EL1:
 		val &= ~(ID_AA64MMFR1_EL1_CMOW		|
 			 ID_AA64MMFR1_EL1_nTLBPA	|
-			 ID_AA64MMFR1_EL1_ETS		|
-			 ID_AA64MMFR1_EL1_XNX		|
-			 ID_AA64MMFR1_EL1_HAFDBS);
+			 ID_AA64MMFR1_EL1_ETS);
+
 		/* FEAT_E2H0 implies no VHE */
 		if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features))
 			val &= ~ID_AA64MMFR1_EL1_VH;
+
+		val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR1_EL1, HAFDBS, AF);
 		break;
 
 	case SYS_ID_AA64MMFR2_EL1: