1 files changed, 95 insertions, 31 deletions

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 3927fe52a3dd..338505cb0171 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -46,7 +46,8 @@ static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 |= HCR_FWB;
 
 	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
-	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) &&
+	    kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0) == read_cpuid(CTR_EL0))
 		vcpu->arch.hcr_el2 |= HCR_TID4;
 	else
 		vcpu->arch.hcr_el2 |= HCR_TID2;
@@ -166,8 +167,13 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	pkvm_vcpu_reset_hcr(vcpu);
 
-	if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu)))
+	if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) {
+		struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+		/* Trust the host for non-protected vcpu features. */
+		vcpu->arch.hcrx_el2 = host_vcpu->arch.hcrx_el2;
 		return 0;
+	}
 
 	ret = pkvm_check_pvm_cpu_features(vcpu);
 	if (ret)
@@ -175,6 +181,7 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	pvm_init_traps_hcr(vcpu);
 	pvm_init_traps_mdcr(vcpu);
+	vcpu_set_hcrx(vcpu);
 
 	return 0;
 }
@@ -239,10 +246,12 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 
 	hyp_spin_lock(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
-	if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx)
+	if (!hyp_vm || hyp_vm->kvm.created_vcpus <= vcpu_idx)
 		goto unlock;
 
 	hyp_vcpu = hyp_vm->vcpus[vcpu_idx];
+	if (!hyp_vcpu)
+		goto unlock;
 
 	/* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
 	if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
@@ -315,6 +324,9 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags);
 	DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES);
 
+	/* CTR_EL0 is always under host control, even for protected VMs. */
+	hyp_vm->kvm.arch.ctr_el0 = host_kvm->arch.ctr_el0;
+
 	if (test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &host_kvm->arch.flags))
 		set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags);
 
@@ -325,6 +337,10 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
 			    KVM_VCPU_MAX_FEATURES);
+
+		if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags))
+			hyp_vm->kvm.arch.midr_el1 = host_kvm->arch.midr_el1;
+
 		return;
 	}
 
@@ -356,13 +372,32 @@ static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu)
 		hyp_unpin_shared_mem(host_vcpu, host_vcpu + 1);
 }
 
+static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	void *sve_state;
+
+	if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE))
+		return;
+
+	sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state);
+	hyp_unpin_shared_mem(sve_state,
+			     sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu));
+}
+
 static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],
 			     unsigned int nr_vcpus)
 {
 	int i;
 
-	for (i = 0; i < nr_vcpus; i++)
-		unpin_host_vcpu(hyp_vcpus[i]->host_vcpu);
+	for (i = 0; i < nr_vcpus; i++) {
+		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vcpus[i];
+
+		if (!hyp_vcpu)
+			continue;
+
+		unpin_host_vcpu(hyp_vcpu->host_vcpu);
+		unpin_host_sve_state(hyp_vcpu);
+	}
 }
 
 static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
@@ -376,34 +411,56 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
 	pkvm_init_features_from_host(hyp_vm, host_kvm);
 }
 
-static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu)
+static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu)
 {
 	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
+	unsigned int sve_max_vl;
+	size_t sve_state_size;
+	void *sve_state;
+	int ret = 0;
 
-	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE))
+	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
 		vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED);
+		return 0;
+	}
+
+	/* Limit guest vector length to the maximum supported by the host. */
+	sve_max_vl = min(READ_ONCE(host_vcpu->arch.sve_max_vl), kvm_host_sve_max_vl);
+	sve_state_size = sve_state_size_from_vl(sve_max_vl);
+	sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state));
+
+	if (!sve_state || !sve_state_size) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = hyp_pin_shared_mem(sve_state, sve_state + sve_state_size);
+	if (ret)
+		goto err;
+
+	vcpu->arch.sve_state = sve_state;
+	vcpu->arch.sve_max_vl = sve_max_vl;
+
+	return 0;
+err:
+	clear_bit(KVM_ARM_VCPU_SVE, vcpu->kvm->arch.vcpu_features);
+	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,
-			      unsigned int vcpu_idx)
+			      struct kvm_vcpu *host_vcpu)
 {
 	int ret = 0;
 
 	if (hyp_pin_shared_mem(host_vcpu, host_vcpu + 1))
 		return -EBUSY;
 
-	if (host_vcpu->vcpu_idx != vcpu_idx) {
-		ret = -EINVAL;
-		goto done;
-	}
-
 	hyp_vcpu->host_vcpu = host_vcpu;
 
 	hyp_vcpu->vcpu.kvm = &hyp_vm->kvm;
 	hyp_vcpu->vcpu.vcpu_id = READ_ONCE(host_vcpu->vcpu_id);
-	hyp_vcpu->vcpu.vcpu_idx = vcpu_idx;
+	hyp_vcpu->vcpu.vcpu_idx = READ_ONCE(host_vcpu->vcpu_idx);
 
 	hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu;
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
@@ -416,7 +473,7 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 	if (ret)
 		goto done;
 
-	pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
+	ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
 done:
 	if (ret)
 		unpin_host_vcpu(host_vcpu);
@@ -641,27 +698,28 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
 		goto unlock;
 	}
 
-	idx = hyp_vm->nr_vcpus;
+	ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu);
+	if (ret)
+		goto unlock;
+
+	idx = hyp_vcpu->vcpu.vcpu_idx;
 	if (idx >= hyp_vm->kvm.created_vcpus) {
 		ret = -EINVAL;
 		goto unlock;
 	}
 
-	ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu, idx);
-	if (ret)
+	if (hyp_vm->vcpus[idx]) {
+		ret = -EINVAL;
 		goto unlock;
+	}
 
 	hyp_vm->vcpus[idx] = hyp_vcpu;
-	hyp_vm->nr_vcpus++;
 unlock:
 	hyp_spin_unlock(&vm_table_lock);
 
-	if (ret) {
+	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static void
@@ -678,7 +736,7 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size)
 
 int __pkvm_teardown_vm(pkvm_handle_t handle)
 {
-	struct kvm_hyp_memcache *mc;
+	struct kvm_hyp_memcache *mc, *stage2_mc;
 	struct pkvm_hyp_vm *hyp_vm;
 	struct kvm *host_kvm;
 	unsigned int idx;
@@ -706,18 +764,24 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
 
 	/* Reclaim guest pages (including page-table pages) */
 	mc = &host_kvm->arch.pkvm.teardown_mc;
-	reclaim_guest_pages(hyp_vm, mc);
-	unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->nr_vcpus);
+	stage2_mc = &host_kvm->arch.pkvm.stage2_teardown_mc;
+	reclaim_pgtable_pages(hyp_vm, stage2_mc);
+	unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->kvm.created_vcpus);
 
 	/* Push the metadata pages to the teardown memcache */
-	for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) {
+	for (idx = 0; idx < hyp_vm->kvm.created_vcpus; ++idx) {
 		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx];
-		struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
+		struct kvm_hyp_memcache *vcpu_mc;
+
+		if (!hyp_vcpu)
+			continue;
+
+		vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
 
 		while (vcpu_mc->nr_pages) {
 			void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt);
 
-			push_hyp_memcache(mc, addr, hyp_virt_to_phys);
+			push_hyp_memcache(stage2_mc, addr, hyp_virt_to_phys);
 			unmap_donated_memory_noclear(addr, PAGE_SIZE);
 		}