KVM: arm64: Add support for protected guest memory with pKVM

index 5f9d56754e39..7f25f2bca90c 100644
@@ -27,7 +27,6 @@ extern struct host_mmu host_mmu;
 enum pkvm_component_id {
 	PKVM_ID_HOST,
 	PKVM_ID_HYP,
-	PKVM_ID_FFA,
 };
 
 extern unsigned long hyp_nr_cpus;

index 410ffd41fd73..3589fc08266c 100644
@@ -236,7 +236,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		 */
 		ret = pkvm_init_host_vm(kvm);
 		if (ret)
-			goto err_free_cpumask;
+			goto err_uninit_mmu;
 	}
 
 	kvm_vgic_early_init(kvm);

@@ -252,6 +252,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	return 0;
 
+err_uninit_mmu:
+	kvm_uninit_stage2_mmu(kvm);
 err_free_cpumask:
 	free_cpumask_var(kvm->arch.supported_cpus);
 err_unshare_kvm:

index d7a0f69a9982..7797813f4dbe 100644
@@ -329,9 +329,6 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 	struct pkvm_mapping *mapping;
 	int ret;
 
-	if (!handle)
-		return 0;
-
 	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
 		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
 					mapping->nr_pages);

@@ -347,6 +344,12 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
 					u64 addr, u64 size)
 {
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+
+	if (!handle)
+		return;
+
 	__pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
 }
 

index 7797813f4dbe..42f6e50825ac 100644
@@ -322,7 +322,7 @@ int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	return 0;
 }
 
-static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 end)
+static int __pkvm_pgtable_stage2_unshare(struct kvm_pgtable *pgt, u64 start, u64 end)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;

@@ -350,7 +350,7 @@ void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
 	if (!handle)
 		return;
 
-	__pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+	__pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 }
 
 void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)

@@ -386,7 +386,7 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			return -EAGAIN;
 
 		/* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */
-		ret = __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+		ret = __pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 		if (ret)
 			return ret;
 		mapping = NULL;

@@ -409,7 +409,7 @@ int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(pgt->mmu)->mmu_lock);
 
-	return __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+	return __pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 }
 
 int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)

index 757076ad4ec9..7041e398fb4c 100644
@@ -40,8 +40,6 @@ static inline bool kvm_pkvm_ext_allowed(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPU_ID:
 	case KVM_CAP_MSI_DEVID:
 	case KVM_CAP_ARM_VM_IPA_SIZE:
-	case KVM_CAP_ARM_PMU_V3:
-	case KVM_CAP_ARM_SVE:
 	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
 		return true;

index 06d28621722e..0a84140afa28 100644
@@ -392,6 +392,14 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 	/* Cache maintenance by set/way operations are restricted. */
 
 	/* Debug and Trace Registers are restricted. */
+	RAZ_WI(SYS_DBGBVRn_EL1(0)),
+	RAZ_WI(SYS_DBGBCRn_EL1(0)),
+	RAZ_WI(SYS_DBGWVRn_EL1(0)),
+	RAZ_WI(SYS_DBGWCRn_EL1(0)),
+	RAZ_WI(SYS_MDSCR_EL1),
+	RAZ_WI(SYS_OSLAR_EL1),
+	RAZ_WI(SYS_OSLSR_EL1),
+	RAZ_WI(SYS_OSDLR_EL1),
 
 	/* Group 1 ID registers */
 	HOST_HANDLED(SYS_REVIDR_EL1),

index a1ad12c72ebf..7b72aac4730d 100644
@@ -51,7 +51,7 @@
 #include <linux/mm.h>
 
 enum __kvm_host_smccc_func {
-	/* Hypercalls available only prior to pKVM finalisation */
+	/* Hypercalls that are unavailable once pKVM has finalised. */
 	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
 	__KVM_HOST_SMCCC_FUNC___pkvm_init = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
 	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,

@@ -60,16 +60,9 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config,
 	__KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize,
+	__KVM_HOST_SMCCC_FUNC_MIN_PKVM = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize,
 
-	/* Hypercalls available after pKVM finalisation */
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
-	__KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
+	/* Hypercalls that are always available and common to [nh]VHE/pKVM. */
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,

@@ -81,6 +74,17 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs,
+	__KVM_HOST_SMCCC_FUNC_MAX_NO_PKVM = __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs,
+
+	/* Hypercalls that are available only when pKVM has finalised. */
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_reserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,

148 lines not on this page · raw message

index 17d64a1e11e5..5e7821fe0fc4 100644
@@ -340,6 +340,9 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
 			    u64 size, bool may_block)
 {
+	if (kvm_vm_is_protected(kvm_s2_mmu_to_kvm(mmu)))
+		return;
+
 	__unmap_stage2_range(mmu, start, size, may_block);
 }
 

@@ -2223,7 +2226,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	if (!kvm->arch.mmu.pgt)
+	if (!kvm->arch.mmu.pgt || kvm_vm_is_protected(kvm))
 		return false;
 
 	__unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT,

@@ -2238,7 +2241,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
 
-	if (!kvm->arch.mmu.pgt)
+	if (!kvm->arch.mmu.pgt || kvm_vm_is_protected(kvm))
 		return false;
 
 	return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,

@@ -2254,7 +2257,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
 
-	if (!kvm->arch.mmu.pgt)
+	if (!kvm->arch.mmu.pgt || kvm_vm_is_protected(kvm))
 		return false;
 
 	return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,

index 42f6e50825ac..20d50abb3b94 100644
@@ -407,7 +407,12 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 
 int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(pgt->mmu)->mmu_lock);
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+
+	if (WARN_ON(kvm_vm_is_protected(kvm)))
+		return -EPERM;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	return __pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 }

@@ -419,6 +424,9 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	struct pkvm_mapping *mapping;
 	int ret = 0;
 
+	if (WARN_ON(kvm_vm_is_protected(kvm)))
+		return -EPERM;
+
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
 		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,

@@ -450,6 +458,9 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
 	struct pkvm_mapping *mapping;
 	bool young = false;
 
+	if (WARN_ON(kvm_vm_is_protected(kvm)))
+		return -EPERM;
+
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
 		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,

@@ -461,12 +472,18 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
 int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
 				    enum kvm_pgtable_walk_flags flags)
 {
+	if (WARN_ON(kvm_vm_is_protected(kvm_s2_mmu_to_kvm(pgt->mmu))))
+		return -EPERM;
+
 	return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot);
 }
 
 void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
 				 enum kvm_pgtable_walk_flags flags)
 {
+	if (WARN_ON(kvm_vm_is_protected(kvm_s2_mmu_to_kvm(pgt->mmu))))
+		return;
+
 	WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT));
 }
 

index 5e7821fe0fc4..b3cc5dfe5723 100644
@@ -2414,6 +2414,19 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	hva_t hva, reg_end;
 	int ret = 0;
 
+	if (kvm_vm_is_protected(kvm)) {
+		/* Cannot modify memslots once a pVM has run. */
+		if (pkvm_hyp_vm_is_created(kvm) &&
+		    (change == KVM_MR_DELETE || change == KVM_MR_MOVE)) {
+			return -EPERM;
+		}
+
+		if (new &&
+		    new->flags & (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)) {
+			return -EPERM;
+		}
+	}
+
 	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
 			change != KVM_MR_FLAGS_ONLY)
 		return 0;

index d815265bd374..7d22893ab1dc 100644
@@ -461,8 +461,15 @@ static bool range_is_memory(u64 start, u64 end)
 static inline int __host_stage2_idmap(u64 start, u64 end,
 				      enum kvm_pgtable_prot prot)
 {
+	/*
+	 * We don't make permission changes to the host idmap after
+	 * initialisation, so we can squash -EAGAIN to save callers
+	 * having to treat it like success in the case that they try to
+	 * map something that is already mapped.
+	 */
 	return kvm_pgtable_stage2_map(&host_mmu.pgt, start, end - start, start,
-				      prot, &host_s2_pool, 0);
+				      prot, &host_s2_pool,
+				      KVM_PGTABLE_WALK_IGNORE_EAGAIN);
 }
 
 /*

@@ -504,7 +511,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		return ret;
 
 	if (kvm_pte_valid(pte))
-		return -EAGAIN;
+		return -EEXIST;
 
 	if (pte) {
 		WARN_ON(addr_is_memory(addr) &&

@@ -609,7 +616,6 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_vcpu_fault_info fault;
 	u64 esr, addr;
-	int ret = 0;
 
 	esr = read_sysreg_el2(SYS_ESR);
 	if (!__get_fault_info(esr, &fault)) {

@@ -628,8 +634,13 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 	BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
 	addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
 
-	ret = host_stage2_idmap(addr);
-	BUG_ON(ret && ret != -EAGAIN);
+	switch (host_stage2_idmap(addr)) {
+	case -EEXIST:
+	case 0:
+		break;
+	default:
+		BUG();
+	}
 }
 
 struct check_walk_data {

index 7b72aac4730d..df6b661701b6 100644
@@ -89,7 +89,8 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
-	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
+	__KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm,
+	__KVM_HOST_SMCCC_FUNC___pkvm_finalize_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
 	__KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,

index 70cb9cfd760a..31b9454bb74d 100644
@@ -255,6 +255,13 @@ struct kvm_protected_vm {
 	struct kvm_hyp_memcache stage2_teardown_mc;
 	bool is_protected;
 	bool is_created;
+
+	/*
+	 * True when the guest is being torn down. When in this state, the
+	 * guest's vCPUs can't be loaded anymore, but its pages can be
+	 * reclaimed by the host.
+	 */
+	bool is_dying;
 };
 
 struct kvm_mpidr_data {

index 184ad7a39950..04c7ca703014 100644
@@ -73,7 +73,9 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 		   unsigned long pgd_hva);
 int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
 		     unsigned long vcpu_hva);
-int __pkvm_teardown_vm(pkvm_handle_t handle);
+
+int __pkvm_start_teardown_vm(pkvm_handle_t handle);
+int __pkvm_finalize_teardown_vm(pkvm_handle_t handle);
 
 struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);

index 127decc2dd2b..634ea2766240 100644
@@ -553,11 +553,18 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
 }
 
-static void handle___pkvm_teardown_vm(struct kvm_cpu_context *host_ctxt)
+static void handle___pkvm_start_teardown_vm(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
 
-	cpu_reg(host_ctxt, 1) = __pkvm_teardown_vm(handle);
+	cpu_reg(host_ctxt, 1) = __pkvm_start_teardown_vm(handle);
+}
+
+static void handle___pkvm_finalize_teardown_vm(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+
+	cpu_reg(host_ctxt, 1) = __pkvm_finalize_teardown_vm(handle);
 }
 
 typedef void (*hcall_t)(struct kvm_cpu_context *);

@@ -598,7 +605,8 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_unreserve_vm),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
-	HANDLE_FUNC(__pkvm_teardown_vm),
+	HANDLE_FUNC(__pkvm_start_teardown_vm),
+	HANDLE_FUNC(__pkvm_finalize_teardown_vm),
 	HANDLE_FUNC(__pkvm_vcpu_load),
 	HANDLE_FUNC(__pkvm_vcpu_put),
 	HANDLE_FUNC(__pkvm_tlb_flush_vmid),

index 2f029bfe4755..c4e05ab8b605 100644
@@ -255,7 +255,10 @@ 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->kvm.created_vcpus <= vcpu_idx)
+	if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying)
+		goto unlock;
+
+	if (hyp_vm->kvm.created_vcpus <= vcpu_idx)
 		goto unlock;
 
 	hyp_vcpu = hyp_vm->vcpus[vcpu_idx];

@@ -859,7 +862,32 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size)
 	unmap_donated_memory_noclear(addr, size);
 }
 
-int __pkvm_teardown_vm(pkvm_handle_t handle)
+int __pkvm_start_teardown_vm(pkvm_handle_t handle)
+{
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = 0;
+
+	hyp_spin_lock(&vm_table_lock);
+	hyp_vm = get_vm_by_handle(handle);
+	if (!hyp_vm) {
+		ret = -ENOENT;
+		goto unlock;
+	} else if (WARN_ON(hyp_page_count(hyp_vm))) {
+		ret = -EBUSY;
+		goto unlock;
+	} else if (hyp_vm->kvm.arch.pkvm.is_dying) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	hyp_vm->kvm.arch.pkvm.is_dying = true;
+unlock:
+	hyp_spin_unlock(&vm_table_lock);
+
+	return ret;
+}
+
+int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
 {
 	struct kvm_hyp_memcache *mc, *stage2_mc;
 	struct pkvm_hyp_vm *hyp_vm;

@@ -873,9 +901,7 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
 	if (!hyp_vm) {
 		err = -ENOENT;
 		goto err_unlock;
-	}
-
-	if (WARN_ON(hyp_page_count(hyp_vm))) {
+	} else if (!hyp_vm->kvm.arch.pkvm.is_dying) {
 		err = -EBUSY;
 		goto err_unlock;
 	}

index 20d50abb3b94..a39dacd1d617 100644
@@ -88,7 +88,7 @@ void __init kvm_hyp_reserve(void)
 static void __pkvm_destroy_hyp_vm(struct kvm *kvm)
 {
 	if (pkvm_hyp_vm_is_created(kvm)) {
-		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
+		WARN_ON(kvm_call_hyp_nvhe(__pkvm_finalize_teardown_vm,
 					  kvm->arch.pkvm.handle));
 	} else if (kvm->arch.pkvm.handle) {
 		/*

@@ -350,6 +350,11 @@ void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
 	if (!handle)
 		return;
 
+	if (pkvm_hyp_vm_is_created(kvm) && !kvm->arch.pkvm.is_dying) {
+		WARN_ON(kvm_call_hyp_nvhe(__pkvm_start_teardown_vm, handle));
+		kvm->arch.pkvm.is_dying = true;
+	}
+
 	__pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 }
 

index df6b661701b6..dfc6625c8269 100644
@@ -79,6 +79,7 @@ enum __kvm_host_smccc_func {
 	/* Hypercalls that are available only when pKVM has finalised. */
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_donate_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,

index c201168f2857..50caca311ef5 100644
@@ -100,7 +100,7 @@ typedef u64 kvm_pte_t;
 					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
 
 #define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
-#define KVM_MAX_OWNER_ID		1
+#define KVM_MAX_OWNER_ID		2
 
 /*
  * Used to indicate a pte for which a 'break-before-make' sequence is in

index 7f25f2bca90c..7061b0be340a 100644
@@ -27,6 +27,7 @@ extern struct host_mmu host_mmu;
 enum pkvm_component_id {
 	PKVM_ID_HOST,
 	PKVM_ID_HYP,
+	PKVM_ID_GUEST,
 };
 
 extern unsigned long hyp_nr_cpus;

@@ -38,6 +39,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
 int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
+int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
 			    enum kvm_pgtable_prot prot);
 int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);

index 634ea2766240..970656318cf2 100644
@@ -241,6 +241,26 @@ static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu)
 			       &host_vcpu->arch.pkvm_memcache);
 }
 
+static void handle___pkvm_host_donate_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || !pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = pkvm_refill_memcache(hyp_vcpu);
+	if (ret)
+		goto out;
+
+	ret = __pkvm_host_donate_guest(pfn, gfn, hyp_vcpu);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
 static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(u64, pfn, host_ctxt, 1);

@@ -595,6 +615,7 @@ static const hcall_t host_hcall[] = {
 
 	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_host_unshare_hyp),
+	HANDLE_FUNC(__pkvm_host_donate_guest),
 	HANDLE_FUNC(__pkvm_host_share_guest),
 	HANDLE_FUNC(__pkvm_host_unshare_guest),
 	HANDLE_FUNC(__pkvm_host_relax_perms_guest),

index 7d22893ab1dc..03e6fa124253 100644
@@ -971,6 +971,36 @@ static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *s
 	return 0;
 }
 
+int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED);
+	if (ret)
+		goto unlock;
+
+	ret = __guest_check_page_state_range(vm, ipa, PAGE_SIZE, PKVM_NOPAGE);
+	if (ret)
+		goto unlock;
+
+	WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_GUEST));
+	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED),
+				       &vcpu->vcpu.arch.pkvm_memcache, 0));
+
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
+
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
 			    enum kvm_pgtable_prot prot)
 {

index a39dacd1d617..1814e17d600e 100644
@@ -373,31 +373,55 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	struct kvm_hyp_memcache *cache = mc;
 	u64 gfn = addr >> PAGE_SHIFT;
 	u64 pfn = phys >> PAGE_SHIFT;
+	u64 end = addr + size;
 	int ret;
 
-	if (size != PAGE_SIZE && size != PMD_SIZE)
-		return -EINVAL;
-
 	lockdep_assert_held_write(&kvm->mmu_lock);
+	mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, end - 1);
 
-	/*
-	 * Calling stage2_map() on top of existing mappings is either happening because of a race
-	 * with another vCPU, or because we're changing between page and block mappings. As per
-	 * user_mem_abort(), same-size permission faults are handled in the relax_perms() path.
-	 */
-	mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, addr + size - 1);
-	if (mapping) {
-		if (size == (mapping->nr_pages * PAGE_SIZE))
+	if (kvm_vm_is_protected(kvm)) {
+		/* Protected VMs are mapped using RWX page-granular mappings */
+		if (WARN_ON_ONCE(size != PAGE_SIZE))
+			return -EINVAL;
+
+		if (WARN_ON_ONCE(prot != KVM_PGTABLE_PROT_RWX))
+			return -EINVAL;
+
+		/*
+		 * We raced with another vCPU.
+		 */
+		if (mapping)
 			return -EAGAIN;
 
-		/* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */
-		ret = __pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
-		if (ret)
-			return ret;
-		mapping = NULL;
+		ret = kvm_call_hyp_nvhe(__pkvm_host_donate_guest, pfn, gfn);
+	} else {
+		if (WARN_ON_ONCE(size != PAGE_SIZE && size != PMD_SIZE))
+			return -EINVAL;
+
+		/*
+		 * We either raced with another vCPU or we're changing between
+		 * page and block mappings. As per user_mem_abort(), same-size
+		 * permission faults are handled in the relax_perms() path.
+		 */
+		if (mapping) {
+			if (size == (mapping->nr_pages * PAGE_SIZE))
+				return -EAGAIN;
+
+			/*
+			 * Remove _any_ pkvm_mapping overlapping with the range,
+			 * bigger or smaller.
+			 */
+			ret = __pkvm_pgtable_stage2_unshare(pgt, addr, end);
+			if (ret)
+				return ret;
+
+			mapping = NULL;
+		}
+
+		ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn,
+					size / PAGE_SIZE, prot);
 	}
 
-	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, size / PAGE_SIZE, prot);
 	if (WARN_ON(ret))
 		return ret;
 

index b3cc5dfe5723..6a4151e3e4a3 100644
@@ -1642,6 +1642,74 @@ static int gmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	return ret != -EAGAIN ? ret : 0;
 }
 
+static int pkvm_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+		struct kvm_memory_slot *memslot, unsigned long hva)
+{
+	unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;
+	struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt;
+	struct mm_struct *mm = current->mm;
+	struct kvm *kvm = vcpu->kvm;
+	void *hyp_memcache;
+	struct page *page;
+	int ret;
+
+	ret = prepare_mmu_memcache(vcpu, true, &hyp_memcache);
+	if (ret)
+		return -ENOMEM;
+
+	ret = account_locked_vm(mm, 1, true);
+	if (ret)
+		return ret;
+
+	mmap_read_lock(mm);
+	ret = pin_user_pages(hva, 1, flags, &page);
+	mmap_read_unlock(mm);
+
+	if (ret == -EHWPOISON) {
+		kvm_send_hwpoison_signal(hva, PAGE_SHIFT);
+		ret = 0;
+		goto dec_account;
+	} else if (ret != 1) {
+		ret = -EFAULT;
+		goto dec_account;
+	} else if (!folio_test_swapbacked(page_folio(page))) {
+		/*
+		 * We really can't deal with page-cache pages returned by GUP
+		 * because (a) we may trigger writeback of a page for which we
+		 * no longer have access and (b) page_mkclean() won't find the
+		 * stage-2 mapping in the rmap so we can get out-of-whack with
+		 * the filesystem when marking the page dirty during unpinning
+		 * (see cc5095747edf ("ext4: don't BUG if someone dirty pages
+		 * without asking ext4 first")).
+		 *
+		 * Ideally we'd just restrict ourselves to anonymous pages, but
+		 * we also want to allow memfd (i.e. shmem) pages, so check for
+		 * pages backed by swap in the knowledge that the GUP pin will
+		 * prevent try_to_unmap() from succeeding.
+		 */
+		ret = -EIO;
+		goto unpin;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	ret = pkvm_pgtable_stage2_map(pgt, fault_ipa, PAGE_SIZE,
+				      page_to_phys(page), KVM_PGTABLE_PROT_RWX,
+				      hyp_memcache, 0);
+	write_unlock(&kvm->mmu_lock);
+	if (ret) {
+		if (ret == -EAGAIN)
+			ret = 0;
+		goto unpin;
+	}
+
+	return 0;
+unpin:
+	unpin_user_pages(&page, 1);
+dec_account:
+	account_locked_vm(mm, 1, false);
+	return ret;
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_s2_trans *nested,
 			  struct kvm_memory_slot *memslot, unsigned long hva,

@@ -2205,15 +2273,20 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) &&
-			!write_fault && !kvm_vcpu_trap_is_exec_fault(vcpu));
+	if (kvm_vm_is_protected(vcpu->kvm)) {
+		ret = pkvm_mem_abort(vcpu, fault_ipa, memslot, hva);
+	} else {
+		VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) &&
+				!write_fault &&
+				!kvm_vcpu_trap_is_exec_fault(vcpu));
 
-	if (kvm_slot_has_gmem(memslot))
-		ret = gmem_abort(vcpu, fault_ipa, nested, memslot,
-				 esr_fsc_is_permission_fault(esr));
-	else
-		ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
-				     esr_fsc_is_permission_fault(esr));
+		if (kvm_slot_has_gmem(memslot))
+			ret = gmem_abort(vcpu, fault_ipa, nested, memslot,
+					 esr_fsc_is_permission_fault(esr));
+		else
+			ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
+					     esr_fsc_is_permission_fault(esr));
+	}
 	if (ret == 0)
 		ret = 1;
 out:

index dfc6625c8269..b6df8f64d573 100644
@@ -90,6 +90,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
+	__KVM_HOST_SMCCC_FUNC___pkvm_reclaim_dying_guest_page,
 	__KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_finalize_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,

index 7061b0be340a..29f81a1d9e1f 100644
@@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu);
+int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
 			    enum kvm_pgtable_prot prot);
 int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);

index 04c7ca703014..506831804f64 100644
@@ -74,6 +74,7 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
 		     unsigned long vcpu_hva);
 
+int __pkvm_reclaim_dying_guest_page(pkvm_handle_t handle, u64 gfn);
 int __pkvm_start_teardown_vm(pkvm_handle_t handle);
 int __pkvm_finalize_teardown_vm(pkvm_handle_t handle);
 

index 970656318cf2..7294c94f9296 100644
@@ -573,6 +573,14 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
 }
 
+static void handle___pkvm_reclaim_dying_guest_page(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+
+	cpu_reg(host_ctxt, 1) = __pkvm_reclaim_dying_guest_page(handle, gfn);
+}
+
 static void handle___pkvm_start_teardown_vm(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);

@@ -626,6 +634,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_unreserve_vm),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
+	HANDLE_FUNC(__pkvm_reclaim_dying_guest_page),
 	HANDLE_FUNC(__pkvm_start_teardown_vm),
 	HANDLE_FUNC(__pkvm_finalize_teardown_vm),
 	HANDLE_FUNC(__pkvm_vcpu_load),

91 lines not on this page · raw message

index c4e05ab8b605..a2d45f4b0cf6 100644
@@ -862,6 +862,20 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size)
 	unmap_donated_memory_noclear(addr, size);
 }
 
+int __pkvm_reclaim_dying_guest_page(pkvm_handle_t handle, u64 gfn)
+{
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	hyp_spin_lock(&vm_table_lock);
+	hyp_vm = get_vm_by_handle(handle);
+	if (hyp_vm && hyp_vm->kvm.arch.pkvm.is_dying)
+		ret = __pkvm_host_reclaim_page_guest(gfn, hyp_vm);
+	hyp_spin_unlock(&vm_table_lock);
+
+	return ret;
+}
+
 int __pkvm_start_teardown_vm(pkvm_handle_t handle)
 {
 	struct pkvm_hyp_vm *hyp_vm;

index 1814e17d600e..8be91051699e 100644
@@ -322,6 +322,32 @@ int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	return 0;
 }
 
+static int __pkvm_pgtable_stage2_reclaim(struct kvm_pgtable *pgt, u64 start, u64 end)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	int ret;
+
+	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
+		struct page *page;
+
+		ret = kvm_call_hyp_nvhe(__pkvm_reclaim_dying_guest_page,
+					handle, mapping->gfn);
+		if (WARN_ON(ret))
+			return ret;
+
+		page = pfn_to_page(mapping->pfn);
+		WARN_ON_ONCE(mapping->nr_pages != 1);
+		unpin_user_pages_dirty_lock(&page, 1, true);
+		account_locked_vm(current->mm, 1, false);
+		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
+		kfree(mapping);
+	}
+
+	return 0;
+}
+
 static int __pkvm_pgtable_stage2_unshare(struct kvm_pgtable *pgt, u64 start, u64 end)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);

@@ -355,7 +381,10 @@ void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
 		kvm->arch.pkvm.is_dying = true;
 	}
 
-	__pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
+	if (kvm_vm_is_protected(kvm))
+		__pkvm_pgtable_stage2_reclaim(pgt, addr, addr + size);
+	else
+		__pkvm_pgtable_stage2_unshare(pgt, addr, addr + size);
 }
 
 void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)

index 7294c94f9296..adfc0bc15398 100644
@@ -705,43 +705,40 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 	kvm_skip_host_instr();
 }
 
-/*
- * Inject an Undefined Instruction exception into the host.
- *
- * This is open-coded to allow control over PSTATE construction without
- * complicating the generic exception entry helpers.
- */
-static void inject_undef64(void)
+static void inject_host_exception(u64 esr)
 {
-	u64 spsr_mask, vbar, sctlr, old_spsr, new_spsr, esr, offset;
+	u64 sctlr, spsr_el1, spsr_el2, exc_offset = except_type_sync;
+	const u64 spsr_mask = PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT |
+			      PSR_V_BIT | PSR_DIT_BIT | PSR_PAN_BIT;
 
-	spsr_mask = PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT | PSR_DIT_BIT | PSR_PAN_BIT;
+	exc_offset += CURRENT_EL_SP_ELx_VECTOR;
+
+	spsr_el1 = spsr_el2 = read_sysreg_el2(SYS_SPSR);
+	spsr_el2 &= spsr_mask;
+	spsr_el2 |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT |
+		    PSR_MODE_EL1h;
 
-	vbar = read_sysreg_el1(SYS_VBAR);
 	sctlr = read_sysreg_el1(SYS_SCTLR);
-	old_spsr = read_sysreg_el2(SYS_SPSR);
-
-	new_spsr = old_spsr & spsr_mask;
-	new_spsr |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT;
-	new_spsr |= PSR_MODE_EL1h;
-
 	if (!(sctlr & SCTLR_EL1_SPAN))
-		new_spsr |= PSR_PAN_BIT;
+		spsr_el2 |= PSR_PAN_BIT;
 
 	if (sctlr & SCTLR_ELx_DSSBS)
-		new_spsr |= PSR_SSBS_BIT;
+		spsr_el2 |= PSR_SSBS_BIT;
 
 	if (system_supports_mte())
-		new_spsr |= PSR_TCO_BIT;
-
-	esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) | ESR_ELx_IL;
-	offset = CURRENT_EL_SP_ELx_VECTOR + except_type_sync;
+		spsr_el2 |= PSR_TCO_BIT;
 
 	write_sysreg_el1(esr, SYS_ESR);
 	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
-	write_sysreg_el1(old_spsr, SYS_SPSR);
-	write_sysreg_el2(vbar + offset, SYS_ELR);
-	write_sysreg_el2(new_spsr, SYS_SPSR);
+	write_sysreg_el1(spsr_el1, SYS_SPSR);
+	write_sysreg_el2(read_sysreg_el1(SYS_VBAR) + exc_offset, SYS_ELR);
+	write_sysreg_el2(spsr_el2, SYS_SPSR);
+}
+
+static void inject_host_undef64(void)
+{
+	inject_host_exception((ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) |
+			       ESR_ELx_IL);
 }
 
 static bool handle_host_mte(u64 esr)

@@ -764,7 +761,7 @@ static bool handle_host_mte(u64 esr)
 		return false;
 	}
 
-	inject_undef64();
+	inject_host_undef64();
 	return true;
 }
 

index ba5382c12787..32d7b7746e8e 100644
@@ -16,4 +16,6 @@
 				__always_unused int ___check_reg_ ## reg;	\
 				type name = (type)cpu_reg(ctxt, (reg))
 
+void inject_host_exception(u64 esr);
+
 #endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */

index adfc0bc15398..6db5aebd92dc 100644
@@ -705,15 +705,24 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 	kvm_skip_host_instr();
 }
 
-static void inject_host_exception(u64 esr)
+void inject_host_exception(u64 esr)
 {
 	u64 sctlr, spsr_el1, spsr_el2, exc_offset = except_type_sync;
 	const u64 spsr_mask = PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT |
 			      PSR_V_BIT | PSR_DIT_BIT | PSR_PAN_BIT;
 
-	exc_offset += CURRENT_EL_SP_ELx_VECTOR;
-
 	spsr_el1 = spsr_el2 = read_sysreg_el2(SYS_SPSR);
+	switch (spsr_el1 & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
+	case PSR_MODE_EL0t:
+		exc_offset += LOWER_EL_AArch64_VECTOR;
+		break;
+	case PSR_MODE_EL0t | PSR_MODE32_BIT:
+		exc_offset += LOWER_EL_AArch32_VECTOR;
+		break;
+	default:
+		exc_offset += CURRENT_EL_SP_ELx_VECTOR;
+	}
+
 	spsr_el2 &= spsr_mask;
 	spsr_el2 |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT |
 		    PSR_MODE_EL1h;

@@ -728,6 +737,9 @@ static void inject_host_exception(u64 esr)
 	if (system_supports_mte())
 		spsr_el2 |= PSR_TCO_BIT;
 
+	if (esr_fsc_is_translation_fault(esr))
+		write_sysreg_el1(read_sysreg_el2(SYS_FAR), SYS_FAR);
+
 	write_sysreg_el1(esr, SYS_ESR);
 	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
 	write_sysreg_el1(spsr_el1, SYS_SPSR);

index ca266a4d9d50..0e57dc1881e0 100644
@@ -18,6 +18,7 @@
 #include <nvhe/memory.h>
 #include <nvhe/mem_protect.h>
 #include <nvhe/mm.h>
+#include <nvhe/trap_handler.h>
 
 #define KVM_HOST_S2_FLAGS (KVM_PGTABLE_S2_AS_S1 | KVM_PGTABLE_S2_IDMAP)
 

@@ -612,6 +613,39 @@ static int host_stage2_idmap(u64 addr)
 	return ret;
 }
 
+static void host_inject_mem_abort(struct kvm_cpu_context *host_ctxt)
+{
+	u64 ec, esr, spsr;
+
+	esr = read_sysreg_el2(SYS_ESR);
+	spsr = read_sysreg_el2(SYS_SPSR);
+
+	/* Repaint the ESR to report a same-level fault if taken from EL1 */
+	if ((spsr & PSR_MODE_MASK) != PSR_MODE_EL0t) {
+		ec = ESR_ELx_EC(esr);
+		if (ec == ESR_ELx_EC_DABT_LOW)
+			ec = ESR_ELx_EC_DABT_CUR;
+		else if (ec == ESR_ELx_EC_IABT_LOW)
+			ec = ESR_ELx_EC_IABT_CUR;
+		else
+			WARN_ON(1);
+		esr &= ~ESR_ELx_EC_MASK;
+		esr |= ec << ESR_ELx_EC_SHIFT;
+	}
+
+	/*
+	 * Since S1PTW should only ever be set for stage-2 faults, we're pretty
+	 * much guaranteed that it won't be set in ESR_EL1 by the hardware. So,
+	 * let's use that bit to allow the host abort handler to differentiate
+	 * this abort from normal userspace faults.
+	 *
+	 * Note: although S1PTW is RES0 at EL1, it is guaranteed by the
+	 * architecture to be backed by flops, so it should be safe to use.
+	 */
+	esr |= ESR_ELx_S1PTW;
+	inject_host_exception(esr);
+}
+
 void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_vcpu_fault_info fault;

@@ -635,6 +669,9 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 	addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
 
 	switch (host_stage2_idmap(addr)) {
+	case -EPERM:
+		host_inject_mem_abort(host_ctxt);
+		fallthrough;
 	case -EEXIST:
 	case 0:
 		break;

index be9dab2c7d6a..3abfc7272d63 100644
@@ -43,6 +43,7 @@
 #include <asm/system_misc.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
+#include <asm/virt.h>
 
 struct fault_info {
 	int	(*fn)(unsigned long far, unsigned long esr,

@@ -269,6 +270,15 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr
 	return false;
 }
 
+static bool is_pkvm_stage2_abort(unsigned int esr)
+{
+	/*
+	 * S1PTW should only ever be set in ESR_EL1 if the pkvm hypervisor
+	 * injected a stage-2 abort -- see host_inject_mem_abort().
+	 */
+	return is_pkvm_initialized() && (esr & ESR_ELx_S1PTW);
+}
+
 static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 							unsigned long esr,
 							struct pt_regs *regs)

@@ -279,6 +289,9 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr))
 		return false;
 
+	if (is_pkvm_stage2_abort(esr))
+		return false;
+
 	local_irq_save(flags);
 	asm volatile("at s1e1r, %0" :: "r" (addr));
 	isb();

@@ -395,6 +408,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 			msg = "read from unreadable memory";
 	} else if (addr < PAGE_SIZE) {
 		msg = "NULL pointer dereference";
+	} else if (is_pkvm_stage2_abort(esr)) {
+		msg = "access to hypervisor-protected memory";
 	} else {
 		if (esr_fsc_is_translation_fault(esr) &&
 		    kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))

@@ -621,6 +636,13 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 					 addr, esr, regs);
 	}
 
+	if (is_pkvm_stage2_abort(esr)) {
+		if (!user_mode(regs))
+			goto no_context;
+		arm64_force_sig_fault(SIGSEGV, SEGV_ACCERR, far, "stage-2 fault");
+		return 0;
+	}
+
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
 	if (!(mm_flags & FAULT_FLAG_USER))

index 0e57dc1881e0..bf5102594fc8 100644
@@ -551,23 +551,27 @@ static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_
 
 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
-	int ret;
+	int ret = -EINVAL;
 
 	if (!range_is_memory(addr, addr + size))
 		return -EPERM;
 
-	ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
-			      addr, size, &host_s2_pool, owner_id);
-	if (ret)
-		return ret;
+	switch (owner_id) {
+	case PKVM_ID_HOST:
+		ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
+		if (!ret)
+			__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
+		break;
+	case PKVM_ID_GUEST:
+	case PKVM_ID_HYP:
+		ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
+				      addr, size, &host_s2_pool, owner_id);
+		if (!ret)
+			__host_update_page_state(addr, size, PKVM_NOPAGE);
+		break;
+	}
 
-	/* Don't forget to update the vmemmap tracking for the host */
-	if (owner_id == PKVM_ID_HOST)
-		__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
-	else
-		__host_update_page_state(addr, size, PKVM_NOPAGE);
-
-	return 0;
+	return ret;
 }
 
 static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)

index 50caca311ef5..e36c2908bdb2 100644
@@ -100,13 +100,25 @@ typedef u64 kvm_pte_t;
 					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
 
 #define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
-#define KVM_MAX_OWNER_ID		2
 
-/*
- * Used to indicate a pte for which a 'break-before-make' sequence is in
- * progress.
- */
-#define KVM_INVALID_PTE_LOCKED		BIT(10)
+/* pKVM invalid pte encodings */
+#define KVM_INVALID_PTE_TYPE_MASK	GENMASK(63, 60)
+#define KVM_INVALID_PTE_ANNOT_MASK	~(KVM_PTE_VALID | \
+					  KVM_INVALID_PTE_TYPE_MASK)
+
+enum kvm_invalid_pte_type {
+	/*
+	 * Used to indicate a pte for which a 'break-before-make'
+	 * sequence is in progress.
+	 */
+	KVM_INVALID_PTE_TYPE_LOCKED	= 1,
+
+	/*
+	 * pKVM has unmapped the page from the host due to a change of
+	 * ownership.
+	 */
+	KVM_HOST_INVALID_PTE_TYPE_DONATION,
+};
 
 static inline bool kvm_pte_valid(kvm_pte_t pte)
 {

@@ -658,14 +670,18 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   void *mc, enum kvm_pgtable_walk_flags flags);
 
 /**
- * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to
- *				    track ownership.
+ * kvm_pgtable_stage2_annotate() - Unmap and annotate pages in the IPA space
+ *				   to track ownership (and more).
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Base intermediate physical address to annotate.
  * @size:	Size of the annotated range.
  * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
  *		page-table pages.
- * @owner_id:	Unique identifier for the owner of the page.
+ * @type:	The type of the annotation, determining its meaning and format.
+ * @annotation:	A 59-bit value that will be stored in the page tables.
+ *		@annotation[0] and @annotation[63:60] must be 0.
+ * 		@annotation[59:1] is stored in the page tables, along
+ *		with @type.
  *
  * By default, all page-tables are owned by identifier 0. This function can be
  * used to mark portions of the IPA space as owned by other entities. When a

@@ -674,8 +690,9 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
  *
  * Return: 0 on success, negative error code on failure.
  */
-int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
-				 void *mc, u8 owner_id);
+int kvm_pgtable_stage2_annotate(struct kvm_pgtable *pgt, u64 addr, u64 size,
+				void *mc, enum kvm_invalid_pte_type type,
+				kvm_pte_t annotation);
 
 /**
  * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table.

index bf5102594fc8..aea6ec981801 100644
@@ -549,10 +549,19 @@ static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_
 		set_host_state(page, state);
 }
 
+static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
+{
+	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
+}
+
 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
+	kvm_pte_t annotation;
 	int ret = -EINVAL;
 
+	if (!FIELD_FIT(KVM_INVALID_PTE_OWNER_MASK, owner_id))
+		return -EINVAL;
+
 	if (!range_is_memory(addr, addr + size))
 		return -EPERM;
 

@@ -564,8 +573,11 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 		break;
 	case PKVM_ID_GUEST:
 	case PKVM_ID_HYP:
-		ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
-				      addr, size, &host_s2_pool, owner_id);
+		annotation = kvm_init_invalid_leaf_owner(owner_id);
+		ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
+				      addr, size, &host_s2_pool,
+				      KVM_HOST_INVALID_PTE_TYPE_DONATION,
+				      annotation);
 		if (!ret)
 			__host_update_page_state(addr, size, PKVM_NOPAGE);
 		break;

index 9b480f947da2..84c7a1df845d 100644
@@ -114,11 +114,6 @@ static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
 	return pte;
 }
 
-static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
-{
-	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
-}
-
 static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data,
 				  const struct kvm_pgtable_visit_ctx *ctx,
 				  enum kvm_pgtable_walk_flags visit)

@@ -581,7 +576,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
 struct stage2_map_data {
 	const u64			phys;
 	kvm_pte_t			attr;
-	u8				owner_id;
+	kvm_pte_t			pte_annot;
 
 	kvm_pte_t			*anchor;
 	kvm_pte_t			*childp;

@@ -798,7 +793,11 @@ static bool stage2_pte_is_counted(kvm_pte_t pte)
 
 static bool stage2_pte_is_locked(kvm_pte_t pte)
 {
-	return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED);
+	if (kvm_pte_valid(pte))
+		return false;
+
+	return FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) ==
+	       KVM_INVALID_PTE_TYPE_LOCKED;
 }
 
 static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)

@@ -829,6 +828,7 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 				 struct kvm_s2_mmu *mmu)
 {
 	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+	kvm_pte_t locked_pte;
 
 	if (stage2_pte_is_locked(ctx->old)) {
 		/*

@@ -839,7 +839,9 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 		return false;
 	}
 
-	if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED))
+	locked_pte = FIELD_PREP(KVM_INVALID_PTE_TYPE_MASK,
+				KVM_INVALID_PTE_TYPE_LOCKED);
+	if (!stage2_try_set_pte(ctx, locked_pte))
 		return false;
 
 	if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) {

@@ -964,7 +966,7 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!data->annotation)
 		new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
 	else
-		new = kvm_init_invalid_leaf_owner(data->owner_id);
+		new = data->pte_annot;
 
 	/*
 	 * Skip updating the PTE if we are trying to recreate the exact

@@ -1118,16 +1120,18 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return ret;
 }
 
-int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
-				 void *mc, u8 owner_id)
+int kvm_pgtable_stage2_annotate(struct kvm_pgtable *pgt, u64 addr, u64 size,
+				void *mc, enum kvm_invalid_pte_type type,
+				kvm_pte_t pte_annot)
 {
 	int ret;
 	struct stage2_map_data map_data = {
 		.mmu		= pgt->mmu,
 		.memcache	= mc,
-		.owner_id	= owner_id,
 		.force_pte	= true,
 		.annotation	= true,
+		.pte_annot	= pte_annot |
+				  FIELD_PREP(KVM_INVALID_PTE_TYPE_MASK, type),
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_map_walker,

@@ -1136,7 +1140,10 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		.arg		= &map_data,
 	};
 
-	if (owner_id > KVM_MAX_OWNER_ID)
+	if (pte_annot & ~KVM_INVALID_PTE_ANNOT_MASK)
+		return -EINVAL;
+
+	if (!type || type == KVM_INVALID_PTE_TYPE_LOCKED)
 		return -EINVAL;
 
 	ret = kvm_pgtable_walk(pgt, addr, size, &walker);

index e36c2908bdb2..2df22640833c 100644
@@ -99,8 +99,6 @@ typedef u64 kvm_pte_t;
 					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
 					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
 
-#define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
-
 /* pKVM invalid pte encodings */
 #define KVM_INVALID_PTE_TYPE_MASK	GENMASK(63, 60)
 #define KVM_INVALID_PTE_ANNOT_MASK	~(KVM_PTE_VALID | \

69 lines not on this page · raw message

index 31b9454bb74d..0c5e7ce5f187 100644
@@ -247,7 +247,7 @@ struct kvm_smccc_features {
 	unsigned long vendor_hyp_bmap_2; /* Function numbers 64-127 */
 };
 
-typedef unsigned int pkvm_handle_t;
+typedef u16 pkvm_handle_t;
 
 struct kvm_protected_vm {
 	pkvm_handle_t handle;

index a2d45f4b0cf6..a7253a884163 100644
@@ -222,6 +222,7 @@ static struct pkvm_hyp_vm **vm_table;
 
 void pkvm_hyp_vm_table_init(void *tbl)
 {
+	BUILD_BUG_ON((u64)HANDLE_OFFSET + KVM_MAX_PVMS > (pkvm_handle_t)-1);
 	WARN_ON(vm_table);
 	vm_table = tbl;
 }

index 90003cbf5603..51cb5c89fd20 100644
@@ -593,7 +593,6 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 		if (!ret)
 			__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
 		break;
-	case PKVM_ID_GUEST:
 	case PKVM_ID_HYP:
 		ret = host_stage2_set_owner_metadata_locked(addr, size,
 							    owner_id, 0);

@@ -603,6 +602,20 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 	return ret;
 }
 
+#define KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK	GENMASK(15, 0)
+/* We need 40 bits for the GFN to cover a 52-bit IPA with 4k pages and LPA2 */
+#define KVM_HOST_PTE_OWNER_GUEST_GFN_MASK	GENMASK(55, 16)
+static u64 host_stage2_encode_gfn_meta(struct pkvm_hyp_vm *vm, u64 gfn)
+{
+	pkvm_handle_t handle = vm->kvm.arch.pkvm.handle;
+
+	BUILD_BUG_ON((pkvm_handle_t)-1 > KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK);
+	WARN_ON(!FIELD_FIT(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn));
+
+	return FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, handle) |
+	       FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn);
+}
+
 static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
 {
 	/*

@@ -1125,6 +1138,7 @@ int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu)
 	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
 	u64 phys = hyp_pfn_to_phys(pfn);
 	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 meta;
 	int ret;
 
 	host_lock_component();

@@ -1138,7 +1152,9 @@ int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu)
 	if (ret)
 		goto unlock;
 
-	WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_GUEST));
+	meta = host_stage2_encode_gfn_meta(vm, gfn);
+	WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE,
+						      PKVM_ID_GUEST, meta));
 	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
 				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED),
 				       &vcpu->vcpu.arch.pkvm_memcache, 0));

index b6df8f64d573..04a230e906a7 100644
@@ -90,6 +90,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
+	__KVM_HOST_SMCCC_FUNC___pkvm_force_reclaim_guest_page,
 	__KVM_HOST_SMCCC_FUNC___pkvm_reclaim_dying_guest_page,
 	__KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_finalize_teardown_vm,

index 2df22640833c..41a8687938eb 100644
@@ -116,6 +116,12 @@ enum kvm_invalid_pte_type {
 	 * ownership.
 	 */
 	KVM_HOST_INVALID_PTE_TYPE_DONATION,
+
+	/*
+	 * The page has been forcefully reclaimed from the guest by the
+	 * host.
+	 */
+	KVM_GUEST_INVALID_PTE_TYPE_POISONED,
 };
 
 static inline bool kvm_pte_valid(kvm_pte_t pte)

index 29f81a1d9e1f..acc031103600 100644
@@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu);
+int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys);
 int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
 			    enum kvm_pgtable_prot prot);

index dee1a406b0c2..4cedb720c75d 100644
@@ -30,6 +30,12 @@ enum pkvm_page_state {
 	 * struct hyp_page.
 	 */
 	PKVM_NOPAGE			= BIT(0) | BIT(1),
+
+	/*
+	 * 'Meta-states' which aren't encoded directly in the PTE's SW bits (or
+	 * the hyp_vmemmap entry for the host)
+	 */
+	PKVM_POISON			= BIT(2),
 };
 #define PKVM_PAGE_STATE_MASK		(BIT(0) | BIT(1))
 

index 506831804f64..a5a7bb453f3e 100644
@@ -78,6 +78,7 @@ int __pkvm_reclaim_dying_guest_page(pkvm_handle_t handle, u64 gfn);
 int __pkvm_start_teardown_vm(pkvm_handle_t handle);
 int __pkvm_finalize_teardown_vm(pkvm_handle_t handle);
 
+struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle);
 struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);
 void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);

index 6db5aebd92dc..456c83207717 100644
@@ -573,6 +573,13 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
 }
 
+static void handle___pkvm_force_reclaim_guest_page(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(phys_addr_t, phys, host_ctxt, 1);
+
+	cpu_reg(host_ctxt, 1) = __pkvm_host_force_reclaim_page_guest(phys);
+}
+
 static void handle___pkvm_reclaim_dying_guest_page(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);

@@ -634,6 +641,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_unreserve_vm),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
+	HANDLE_FUNC(__pkvm_force_reclaim_guest_page),
 	HANDLE_FUNC(__pkvm_reclaim_dying_guest_page),
 	HANDLE_FUNC(__pkvm_start_teardown_vm),
 	HANDLE_FUNC(__pkvm_finalize_teardown_vm),

159 lines not on this page · raw message

index a7253a884163..5269ac20d2fb 100644
@@ -230,10 +230,12 @@ void pkvm_hyp_vm_table_init(void *tbl)
 /*
  * Return the hyp vm structure corresponding to the handle.
  */
-static struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle)
+struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle)
 {
 	unsigned int idx = vm_handle_to_idx(handle);
 
+	hyp_assert_lock_held(&vm_table_lock);
+
 	if (unlikely(idx >= KVM_MAX_PVMS))
 		return NULL;
 

index b51ab6840f9c..b546703c3ab9 100644
@@ -94,6 +94,15 @@ static inline bool is_pkvm_initialized(void)
 	       static_branch_likely(&kvm_protected_mode_initialized);
 }
 
+#ifdef CONFIG_KVM
+bool pkvm_force_reclaim_guest_page(phys_addr_t phys);
+#else
+static inline bool pkvm_force_reclaim_guest_page(phys_addr_t phys)
+{
+	return false;
+}
+#endif
+
 /* Reports the availability of HYP mode */
 static inline bool is_hyp_mode_available(void)
 {

index 8be91051699e..32294bd21dde 100644
@@ -563,3 +563,15 @@ int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	WARN_ON_ONCE(1);
 	return -EINVAL;
 }
+
+/*
+ * Forcefully reclaim a page from the guest, zeroing its contents and
+ * poisoning the stage-2 pte so that pages can no longer be mapped at
+ * the same IPA. The page remains pinned until the guest is destroyed.
+ */
+bool pkvm_force_reclaim_guest_page(phys_addr_t phys)
+{
+	int ret = kvm_call_hyp_nvhe(__pkvm_force_reclaim_guest_page, phys);
+
+	return !ret || ret == -EAGAIN;
+}

index 3abfc7272d63..7eacc7b45c1f 100644
@@ -289,9 +289,6 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr))
 		return false;
 
-	if (is_pkvm_stage2_abort(esr))
-		return false;
-
 	local_irq_save(flags);
 	asm volatile("at s1e1r, %0" :: "r" (addr));
 	isb();

@@ -302,8 +299,14 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	 * If we now have a valid translation, treat the translation fault as
 	 * spurious.
 	 */
-	if (!(par & SYS_PAR_EL1_F))
+	if (!(par & SYS_PAR_EL1_F)) {
+		if (is_pkvm_stage2_abort(esr)) {
+			par &= SYS_PAR_EL1_PA;
+			return pkvm_force_reclaim_guest_page(par);
+		}
+
 		return true;
+	}
 
 	/*
 	 * If we got a different type of fault from the AT instruction,

@@ -389,9 +392,11 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 	if (!is_el1_instruction_abort(esr) && fixup_exception(regs, esr))
 		return;
 
-	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
-	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
+	if (is_spurious_el1_translation_fault(addr, esr, regs)) {
+		WARN_RATELIMIT(!is_pkvm_stage2_abort(esr),
+			"Ignoring spurious kernel translation fault at virtual address %016lx\n", addr);
 		return;
+	}
 
 	if (is_el1_mte_sync_tag_check_fault(esr)) {
 		do_tag_recovery(addr, esr, regs);

index 04a230e906a7..6c79f7504d80 100644
@@ -90,6 +90,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_in_poison_fault,
 	__KVM_HOST_SMCCC_FUNC___pkvm_force_reclaim_guest_page,
 	__KVM_HOST_SMCCC_FUNC___pkvm_reclaim_dying_guest_page,
 	__KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm,

index acc031103600..8bc9a2489298 100644
@@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu);
+int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu);
 int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys);
 int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,

index 456c83207717..90e3b14fe287 100644
@@ -573,6 +573,15 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
 }
 
+static void handle___pkvm_vcpu_in_poison_fault(struct kvm_cpu_context *host_ctxt)
+{
+	int ret;
+	struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+
+	ret = hyp_vcpu ? __pkvm_vcpu_in_poison_fault(hyp_vcpu) : -EINVAL;
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
 static void handle___pkvm_force_reclaim_guest_page(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(phys_addr_t, phys, host_ctxt, 1);

@@ -641,6 +650,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_unreserve_vm),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
+	HANDLE_FUNC(__pkvm_vcpu_in_poison_fault),
 	HANDLE_FUNC(__pkvm_force_reclaim_guest_page),
 	HANDLE_FUNC(__pkvm_reclaim_dying_guest_page),
 	HANDLE_FUNC(__pkvm_start_teardown_vm),

49 lines not on this page · raw message

index 32294bd21dde..da0a45dab203 100644
@@ -417,10 +417,13 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			return -EINVAL;
 
 		/*
-		 * We raced with another vCPU.
+		 * We either raced with another vCPU or the guest PTE
+		 * has been poisoned by an erroneous host access.
 		 */
-		if (mapping)
-			return -EAGAIN;
+		if (mapping) {
+			ret = kvm_call_hyp_nvhe(__pkvm_vcpu_in_poison_fault);
+			return ret ? -EFAULT : -EAGAIN;
+		}
 
 		ret = kvm_call_hyp_nvhe(__pkvm_host_donate_guest, pfn, gfn);
 	} else {

index a5a7bb453f3e..c904647d2f76 100644
@@ -88,6 +88,7 @@ struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
 struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle);
 void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
 
+bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code);
 bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
 bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
 void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu);

index 5269ac20d2fb..8b32bf37acc3 100644
@@ -4,6 +4,8 @@
  * Author: Fuad Tabba <[email protected]>
  */
 
+#include <kvm/arm_hypercalls.h>
+
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
 

@@ -965,3 +967,38 @@ int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
 	hyp_spin_unlock(&vm_table_lock);
 	return err;
 }
+/*
+ * Handler for protected VM HVC calls.
+ *
+ * Returns true if the hypervisor has handled the exit (and control
+ * should return to the guest) or false if it hasn't (and the handling
+ * should be performed by the host).
+ */
+bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 val[4] = { SMCCC_RET_INVALID_PARAMETER };
+	bool handled = true;
+
+	switch (smccc_get_function(vcpu)) {
+	case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
+		val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES);
+		val[0] |= BIT(ARM_SMCCC_KVM_FUNC_HYP_MEMINFO);
+		break;
+	case ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID:
+		if (smccc_get_arg1(vcpu) ||
+		    smccc_get_arg2(vcpu) ||
+		    smccc_get_arg3(vcpu)) {
+			break;
+		}
+
+		val[0] = PAGE_SIZE;
+		break;
+	default:
+		/* Punt everything else back to the host, for now. */
+		handled = false;
+	}
+
+	if (handled)
+		smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]);
+	return handled;
+}

index 779089e42681..51bd88dc6012 100644
@@ -190,6 +190,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 
 static const exit_handler_fn pvm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_HVC64]		= kvm_handle_pvm_hvc64,
 	[ESR_ELx_EC_SYS64]		= kvm_handle_pvm_sys64,
 	[ESR_ELx_EC_SVE]		= kvm_handle_pvm_restricted,
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,

index 8bc9a2489298..fea8aecae5ef 100644
@@ -34,6 +34,7 @@ extern unsigned long hyp_nr_cpus;
 
 int __pkvm_prot_finalize(void);
 int __pkvm_host_share_hyp(u64 pfn);
+int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn);
 int __pkvm_host_unshare_hyp(u64 pfn);
 int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
 int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);

index 6fc2c77a6920..e005a5690c65 100644
@@ -959,6 +959,38 @@ int __pkvm_host_share_hyp(u64 pfn)
 	return ret;
 }
 
+int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 phys, ipa = hyp_pfn_to_phys(gfn);
+	kvm_pte_t pte;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = get_valid_guest_pte(vm, ipa, &pte, &phys);
+	if (ret)
+		goto unlock;
+
+	ret = -EPERM;
+	if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_OWNED)
+		goto unlock;
+	if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_NOPAGE))
+		goto unlock;
+
+	ret = 0;
+	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED),
+				       &vcpu->vcpu.arch.pkvm_memcache, 0));
+	WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED));
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
+
 int __pkvm_host_unshare_hyp(u64 pfn)
 {
 	u64 phys = hyp_pfn_to_phys(pfn);

79 lines not on this page · raw message

index fea8aecae5ef..99d8398afe20 100644
@@ -35,6 +35,7 @@ extern unsigned long hyp_nr_cpus;
 int __pkvm_prot_finalize(void);
 int __pkvm_host_share_hyp(u64 pfn);
 int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn);
+int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn);
 int __pkvm_host_unshare_hyp(u64 pfn);
 int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
 int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);

index e005a5690c65..898bd5d767ce 100644
@@ -991,6 +991,40 @@ int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
 	return ret;
 }
 
+int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 meta, phys, ipa = hyp_pfn_to_phys(gfn);
+	kvm_pte_t pte;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = get_valid_guest_pte(vm, ipa, &pte, &phys);
+	if (ret)
+		goto unlock;
+
+	ret = -EPERM;
+	if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_SHARED_OWNED)
+		goto unlock;
+	if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED))
+		goto unlock;
+
+	ret = 0;
+	meta = host_stage2_encode_gfn_meta(vm, gfn);
+	WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE,
+						      PKVM_ID_GUEST, meta));
+	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED),
+				       &vcpu->vcpu.arch.pkvm_memcache, 0));
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
+
 int __pkvm_host_unshare_hyp(u64 pfn)
 {
 	u64 phys = hyp_pfn_to_phys(pfn);

index 1dc9225073c4..ebfd9904ede6 100644
@@ -1019,6 +1019,19 @@ static bool pkvm_memshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
+static void pkvm_memunshare_call(u64 *ret, struct kvm_vcpu *vcpu)
+{
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	u64 ipa = smccc_get_arg1(vcpu);
+
+	if (!PAGE_ALIGNED(ipa))
+		return;
+
+	hyp_vcpu = container_of(vcpu, struct pkvm_hyp_vcpu, vcpu);
+	if (!__pkvm_guest_unshare_host(hyp_vcpu, hyp_phys_to_pfn(ipa)))
+		ret[0] = SMCCC_RET_SUCCESS;
+}
+
 /*
  * Handler for protected VM HVC calls.
  *

@@ -1036,6 +1049,7 @@ bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES);
 		val[0] |= BIT(ARM_SMCCC_KVM_FUNC_HYP_MEMINFO);
 		val[0] |= BIT(ARM_SMCCC_KVM_FUNC_MEM_SHARE);
+		val[0] |= BIT(ARM_SMCCC_KVM_FUNC_MEM_UNSHARE);
 		break;
 	case ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID:
 		if (smccc_get_arg1(vcpu) ||

@@ -1054,6 +1068,14 @@ bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 		handled = pkvm_memshare_call(val, vcpu, exit_code);
 		break;
+	case ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID:
+		if (smccc_get_arg2(vcpu) ||
+		    smccc_get_arg3(vcpu)) {
+			break;
+		}
+
+		pkvm_memunshare_call(val, vcpu);
+		break;
 	default:
 		/* Punt everything else back to the host, for now. */
 		handled = false;

index 7041e398fb4c..2954b311128c 100644
@@ -17,7 +17,7 @@
 
 #define HYP_MEMBLOCK_REGIONS 128
 
-int pkvm_init_host_vm(struct kvm *kvm);
+int pkvm_init_host_vm(struct kvm *kvm, unsigned long type);
 int pkvm_create_hyp_vm(struct kvm *kvm);
 bool pkvm_hyp_vm_is_created(struct kvm *kvm);
 void pkvm_destroy_hyp_vm(struct kvm *kvm);

index 3589fc08266c..c2b666a46893 100644
@@ -203,6 +203,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int ret;
 
+	if (type & ~KVM_VM_TYPE_ARM_MASK)
+		return -EINVAL;
+
 	mutex_init(&kvm->arch.config_lock);
 
 #ifdef CONFIG_LOCKDEP

@@ -234,9 +237,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		 * If any failures occur after this is successful, make sure to
 		 * call __pkvm_unreserve_vm to unreserve the VM in hyp.
 		 */
-		ret = pkvm_init_host_vm(kvm);
+		ret = pkvm_init_host_vm(kvm, type);
 		if (ret)
 			goto err_uninit_mmu;
+	} else if (type & KVM_VM_TYPE_ARM_PROTECTED) {
+		ret = -EINVAL;
+		goto err_uninit_mmu;
 	}
 
 	kvm_vgic_early_init(kvm);

index 6a4151e3e4a3..45358ae8a300 100644
@@ -881,9 +881,6 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	u64 mmfr0, mmfr1;
 	u32 phys_shift;
 
-	if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
-		return -EINVAL;
-
 	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
 	if (is_protected_kvm_enabled()) {
 		phys_shift = kvm_ipa_limit;

index da0a45dab203..632852648012 100644
@@ -219,9 +219,10 @@ void pkvm_destroy_hyp_vm(struct kvm *kvm)
 	mutex_unlock(&kvm->arch.config_lock);
 }
 
-int pkvm_init_host_vm(struct kvm *kvm)
+int pkvm_init_host_vm(struct kvm *kvm, unsigned long type)
 {
 	int ret;
+	bool protected = type & KVM_VM_TYPE_ARM_PROTECTED;
 
 	if (pkvm_hyp_vm_is_created(kvm))
 		return -EINVAL;

@@ -236,6 +237,11 @@ int pkvm_init_host_vm(struct kvm *kvm)
 		return ret;
 
 	kvm->arch.pkvm.handle = ret;
+	kvm->arch.pkvm.is_protected = protected;
+	if (protected) {
+		pr_warn_once("kvm: protected VMs are experimental and for development only, tainting kernel\n");
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+	}
 
 	return 0;
 }

index 80364d4dbebb..073b2bcaf560 100644
@@ -703,6 +703,11 @@ struct kvm_enable_cap {
 #define KVM_VM_TYPE_ARM_IPA_SIZE_MASK	0xffULL
 #define KVM_VM_TYPE_ARM_IPA_SIZE(x)		\
 	((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+
+#define KVM_VM_TYPE_ARM_PROTECTED	(1UL << 31)
+#define KVM_VM_TYPE_ARM_MASK		(KVM_VM_TYPE_ARM_IPA_SIZE_MASK | \
+					 KVM_VM_TYPE_ARM_PROTECTED)
+
 /*
  * ioctls for /dev/kvm fds:
  */

index 898bd5d767ce..6525f9fa274c 100644
@@ -1749,6 +1749,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
 	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
+	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
 
 	selftest_state.host = PKVM_PAGE_OWNED;
 	selftest_state.hyp = PKVM_NOPAGE;

@@ -1768,6 +1769,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
 	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
+	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
 
 	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
 	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);

@@ -1780,6 +1782,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
 	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
+	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
 
 	hyp_unpin_shared_mem(virt, virt + size);
 	assert_page_state();

@@ -1799,6 +1802,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
 	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
+	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 
 	selftest_state.host = PKVM_PAGE_OWNED;

@@ -1815,6 +1819,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 
 	selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED;

@@ -1828,6 +1833,23 @@ void pkvm_ownership_selftest(void *base)
 	selftest_state.host = PKVM_PAGE_OWNED;
 	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn + 1, 1, vm);
 
+	selftest_state.host = PKVM_NOPAGE;
+	selftest_state.guest[0] = PKVM_PAGE_OWNED;
+	assert_transition_res(0,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+
+	selftest_state.host = PKVM_PAGE_OWNED;
+	selftest_state.guest[0] = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_reclaim_page_guest, gfn, vm);
+
 	selftest_state.host = PKVM_NOPAGE;
 	selftest_state.hyp = PKVM_PAGE_OWNED;
 	assert_transition_res(0,	__pkvm_host_donate_hyp, pfn, 1);

index 99d8398afe20..5031879ccb87 100644
@@ -76,6 +76,8 @@ static __always_inline void __load_host_stage2(void)
 
 #ifdef CONFIG_NVHE_EL2_DEBUG
 void pkvm_ownership_selftest(void *base);
+struct pkvm_hyp_vcpu *init_selftest_vm(void *virt);
+void teardown_selftest_vm(void);
 #else
 static inline void pkvm_ownership_selftest(void *base) { }
 #endif

93 lines not on this page · raw message

55 lines not on this page · raw message

index b2c9ea105701..05a5b145e303 100644
@@ -1813,8 +1813,20 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 
 	selftest_state.host = PKVM_PAGE_OWNED;
-	selftest_state.guest[0] = PKVM_NOPAGE;
-	assert_transition_res(0,	__pkvm_host_reclaim_page_guest, gfn, vm);
+	selftest_state.guest[0] = PKVM_POISON;
+	assert_transition_res(0,	__pkvm_host_force_reclaim_page_guest, phys);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+
+	selftest_state.host = PKVM_NOPAGE;
+	selftest_state.guest[1] = PKVM_PAGE_OWNED;
+	assert_transition_res(0,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
+
+	selftest_state.host = PKVM_PAGE_OWNED;
+	selftest_state.guest[1] = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_reclaim_page_guest, gfn + 1, vm);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
 
 	selftest_state.host = PKVM_NOPAGE;
 	selftest_state.hyp = PKVM_PAGE_OWNED;

index 05a5b145e303..0921efb8a16f 100644
@@ -1812,11 +1812,41 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 
+	selftest_state.host = PKVM_PAGE_SHARED_BORROWED;
+	selftest_state.guest[0] = PKVM_PAGE_SHARED_OWNED;
+	assert_transition_res(0,	__pkvm_guest_share_host, vcpu, gfn);
+	assert_transition_res(-EPERM,	__pkvm_guest_share_host, vcpu, gfn);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+
+	selftest_state.host = PKVM_NOPAGE;
+	selftest_state.guest[0] = PKVM_PAGE_OWNED;
+	assert_transition_res(0,	__pkvm_guest_unshare_host, vcpu, gfn);
+	assert_transition_res(-EPERM,	__pkvm_guest_unshare_host, vcpu, gfn);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+
 	selftest_state.host = PKVM_PAGE_OWNED;
 	selftest_state.guest[0] = PKVM_POISON;
 	assert_transition_res(0,	__pkvm_host_force_reclaim_page_guest, phys);
 	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+	assert_transition_res(-EHWPOISON, __pkvm_guest_share_host, vcpu, gfn);
+	assert_transition_res(-EHWPOISON, __pkvm_guest_unshare_host, vcpu, gfn);
 
 	selftest_state.host = PKVM_NOPAGE;
 	selftest_state.guest[1] = PKVM_PAGE_OWNED;

index 4cedb720c75d..b50712d47f6d 100644
@@ -37,7 +37,7 @@ enum pkvm_page_state {
 	 */
 	PKVM_POISON			= BIT(2),
 };
-#define PKVM_PAGE_STATE_MASK		(BIT(0) | BIT(1))
+#define PKVM_PAGE_STATE_VMEMMAP_MASK	(BIT(0) | BIT(1))
 
 #define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
 static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,

@@ -114,12 +114,12 @@ static inline void set_host_state(struct hyp_page *p, enum pkvm_page_state state
 
 static inline enum pkvm_page_state get_hyp_state(struct hyp_page *p)
 {
-	return p->__hyp_state_comp ^ PKVM_PAGE_STATE_MASK;
+	return p->__hyp_state_comp ^ PKVM_PAGE_STATE_VMEMMAP_MASK;
 }
 
 static inline void set_hyp_state(struct hyp_page *p, enum pkvm_page_state state)
 {
-	p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_MASK;
+	p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_VMEMMAP_MASK;
 }
 
 /*