Merge tag 'kvmarm-fixes-7.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 7.0, take #1

- Make sure we don't leak any S1POE state from guest to guest when
  the feature is supported on the HW, but not enabled on the host

- Propagate the ID registers from the host into non-protected VMs
  managed by pKVM, ensuring that the guest sees the intended feature set

- Drop double kern_hyp_va() from unpin_host_sve_state(), which could
  bite us if we were to change kern_hyp_va() to not being idempotent

- Don't leak stage-2 mappings in protected mode

- Correctly align the faulting address when dealing with single page
  stage-2 mappings for PAGE_SIZE > 4kB

- Fix detection of virtualisation-capable GICv5 IRS, due to the
  maintainer being obviously fat fingered...

- Remove duplication of code retrieving the ASID for the purpose of
  S1 PT handling

- Fix slightly abusive const-ification in vgic_set_kvm_info()

Author: bonzini

arch/arm64/include/asm/kvm_host.h

@@ -1616,7 +1616,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP))
 
 #define kvm_has_s1poe(k)				\
-	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+	(system_supports_poe() &&			\
+	 kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
 #define kvm_has_ras(k)					\
 	(kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP))

arch/arm64/include/asm/kvm_nested.h

@@ -397,6 +397,8 @@ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu);
 int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu);
 void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val);
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime);
+
 #define vncr_fixmap(c)						\
 	({							\
 		u32 __c = (c);					\

arch/arm64/kvm/at.c

@@ -540,31 +540,8 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
 	wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0);
 
 	wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG);
-	if (wr->nG) {
-		u64 asid_ttbr, tcr;
-
-		switch (wi->regime) {
-		case TR_EL10:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL1) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL1));
-			break;
-		case TR_EL20:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-			break;
-		default:
-			BUG();
-		}
-
-		wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			wr->asid &= GENMASK(7, 0);
-	}
+	if (wr->nG)
+		wr->asid = get_asid_by_regime(vcpu, wi->regime);
 
 	return 0;
 

arch/arm64/kvm/hyp/nvhe/pkvm.c

@@ -342,6 +342,7 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	/* No restrictions for non-protected VMs. */
 	if (!kvm_vm_is_protected(kvm)) {
 		hyp_vm->kvm.arch.flags = host_arch_flags;
+		hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED);
 
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
@@ -391,7 +392,7 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 	if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE))
 		return;
 
-	sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state);
+	sve_state = hyp_vcpu->vcpu.arch.sve_state;
 	hyp_unpin_shared_mem(sve_state,
 			     sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu));
 }
@@ -471,6 +472,35 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h
 	return ret;
 }
 
+static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
+	const struct kvm *host_kvm = hyp_vm->host_kvm;
+	struct kvm *kvm = &hyp_vm->kvm;
+
+	if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags))
+		return -EINVAL;
+
+	if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))
+		return 0;
+
+	memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs));
+
+	return 0;
+}
+
+static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	int ret = 0;
+
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	else
+		ret = vm_copy_id_regs(hyp_vcpu);
+
+	return ret;
+}
+
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 			      struct pkvm_hyp_vm *hyp_vm,
 			      struct kvm_vcpu *host_vcpu)
@@ -490,8 +520,9 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
 	hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 
-	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
-		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	ret = pkvm_vcpu_init_sysregs(hyp_vcpu);
+	if (ret)
+		goto done;
 
 	ret = pkvm_vcpu_init_traps(hyp_vcpu);
 	if (ret)

arch/arm64/kvm/mmu.c

@@ -1754,14 +1754,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	/*
-	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
-	 * ensure we find the right PFN and lay down the mapping in the right
-	 * place.
+	 * Both the canonical IPA and fault IPA must be aligned to the
+	 * mapping size to ensure we find the right PFN and lay down the
+	 * mapping in the right place.
 	 */
-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
-		fault_ipa &= ~(vma_pagesize - 1);
-		ipa &= ~(vma_pagesize - 1);
-	}
+	fault_ipa = ALIGN_DOWN(fault_ipa, vma_pagesize);
+	ipa = ALIGN_DOWN(ipa, vma_pagesize);
 
 	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);

arch/arm64/kvm/nested.c

@@ -854,6 +854,33 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
 	return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime)
+{
+	enum vcpu_sysreg ttbr_elx;
+	u64 tcr;
+	u16 asid;
+
+	switch (regime) {
+	case TR_EL10:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1;
+		break;
+	case TR_EL20:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2;
+		break;
+	default:
+		BUG();
+	}
+
+	asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx));
+	if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+	    !(tcr & TCR_ASID16))
+		asid &= GENMASK(7, 0);
+
+	return asid;
+}
+
 static void invalidate_vncr(struct vncr_tlb *vt)
 {
 	vt->valid = false;
@@ -1154,9 +1181,6 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	int i;
 
-	if (!kvm->arch.nested_mmus_size)
-		return;
-
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
@@ -1336,20 +1360,8 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return false;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		return asid == vt->wr.asid;
-	}
+	if (vt->wr.nG)
+		return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid;
 
 	return true;
 }
@@ -1452,21 +1464,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		if (asid != vt->wr.asid)
-			return;
-	}
+	if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid)
+		return;
 
 	vt->cpu = smp_processor_id();
 

arch/arm64/kvm/sys_regs.c

@@ -1816,6 +1816,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		       ID_AA64MMFR3_EL1_SCTLRX |
 		       ID_AA64MMFR3_EL1_S1POE |
 		       ID_AA64MMFR3_EL1_S1PIE;
+
+		if (!system_supports_poe())
+			val &= ~ID_AA64MMFR3_EL1_S1POE;
 		break;
 	case SYS_ID_MMFR4_EL1:
 		val &= ~ID_MMFR4_EL1_CCIDX;

drivers/irqchip/irq-gic-v5-irs.c

@@ -699,7 +699,7 @@ static int __init gicv5_irs_init(struct gicv5_irs_chip_data *irs_data)
 	 */
 	if (list_empty(&irs_nodes)) {
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR0);
-		gicv5_global_data.virt_capable = !FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
+		gicv5_global_data.virt_capable = !!FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
 
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1);
 		irs_setup_pri_bits(idr);