1 files changed, 101 insertions, 52 deletions

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2feb6c6b63af..1c78864767c5 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -193,11 +193,6 @@ int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
 	return 0;
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-	return !pfn_is_map_memory(pfn);
-}
-
 static void *stage2_memcache_zalloc_page(void *arg)
 {
 	struct kvm_mmu_memory_cache *mc = arg;
@@ -1304,6 +1299,10 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
 	if (map_size == PAGE_SIZE)
 		return true;
 
+	/* pKVM only supports PMD_SIZE huge-mappings */
+	if (is_protected_kvm_enabled() && map_size != PMD_SIZE)
+		return false;
+
 	size = memslot->npages * PAGE_SIZE;
 
 	gpa_start = memslot->base_gfn << PAGE_SHIFT;
@@ -1466,6 +1465,18 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_MTE_ALLOWED;
 }
 
+static bool kvm_vma_is_cacheable(struct vm_area_struct *vma)
+{
+	switch (FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot))) {
+	case MT_NORMAL_NC:
+	case MT_DEVICE_nGnRnE:
+	case MT_DEVICE_nGnRE:
+		return false;
+	default:
+		return true;
+	}
+}
+
 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,
@@ -1473,8 +1484,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
-	bool exec_fault, mte_allowed;
-	bool device = false, vfio_allow_any_uc = false;
+	bool exec_fault, mte_allowed, is_vma_cacheable;
+	bool s2_force_noncacheable = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
@@ -1488,6 +1499,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 	struct page *page;
+	vm_flags_t vm_flags;
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
 
 	if (fault_is_perm)
@@ -1501,6 +1513,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
+	if (!is_protected_kvm_enabled())
+		memcache = &vcpu->arch.mmu_page_cache;
+	else
+		memcache = &vcpu->arch.pkvm_memcache;
+
 	/*
 	 * Permission faults just need to update the existing leaf entry,
 	 * and so normally don't require allocations from the memcache. The
@@ -1510,13 +1527,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!fault_is_perm || (logging_active && write_fault)) {
 		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
 
-		if (!is_protected_kvm_enabled()) {
-			memcache = &vcpu->arch.mmu_page_cache;
+		if (!is_protected_kvm_enabled())
 			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
-		} else {
-			memcache = &vcpu->arch.pkvm_memcache;
+		else
 			ret = topup_hyp_memcache(memcache, min_pages);
-		}
+
 		if (ret)
 			return ret;
 	}
@@ -1537,7 +1552,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * logging_active is guaranteed to never be true for VM_PFNMAP
 	 * memslots.
 	 */
-	if (logging_active || is_protected_kvm_enabled()) {
+	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
 	} else {
@@ -1612,6 +1627,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
 
+	vm_flags = vma->vm_flags;
+
+	is_vma_cacheable = kvm_vma_is_cacheable(vma);
+
 	/* Don't use the VMA after the unlock -- it may have vanished */
 	vma = NULL;
 
@@ -1635,18 +1654,39 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_noslot_pfn(pfn))
 		return -EFAULT;
 
-	if (kvm_is_device_pfn(pfn)) {
-		/*
-		 * If the page was identified as device early by looking at
-		 * the VMA flags, vma_pagesize is already representing the
-		 * largest quantity we can map.  If instead it was mapped
-		 * via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE
-		 * and must not be upgraded.
-		 *
-		 * In both cases, we don't let transparent_hugepage_adjust()
-		 * change things at the last minute.
-		 */
-		device = true;
+	/*
+	 * Check if this is non-struct page memory PFN, and cannot support
+	 * CMOs. It could potentially be unsafe to access as cachable.
+	 */
+	if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP) && !pfn_is_map_memory(pfn)) {
+		if (is_vma_cacheable) {
+			/*
+			 * Whilst the VMA owner expects cacheable mapping to this
+			 * PFN, hardware also has to support the FWB and CACHE DIC
+			 * features.
+			 *
+			 * ARM64 KVM relies on kernel VA mapping to the PFN to
+			 * perform cache maintenance as the CMO instructions work on
+			 * virtual addresses. VM_PFNMAP region are not necessarily
+			 * mapped to a KVA and hence the presence of hardware features
+			 * S2FWB and CACHE DIC are mandatory to avoid the need for
+			 * cache maintenance.
+			 */
+			if (!kvm_supports_cacheable_pfnmap())
+				return -EFAULT;
+		} else {
+			/*
+			 * If the page was identified as device early by looking at
+			 * the VMA flags, vma_pagesize is already representing the
+			 * largest quantity we can map.  If instead it was mapped
+			 * via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE
+			 * and must not be upgraded.
+			 *
+			 * In both cases, we don't let transparent_hugepage_adjust()
+			 * change things at the last minute.
+			 */
+			s2_force_noncacheable = true;
+		}
 	} else if (logging_active && !write_fault) {
 		/*
 		 * Only actually map the page as writable if this was a write
@@ -1655,7 +1695,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		writable = false;
 	}
 
-	if (exec_fault && device)
+	if (exec_fault && s2_force_noncacheable)
 		return -ENOEXEC;
 
 	/*
@@ -1688,7 +1728,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * If we are not forced to use page mapping, check if we are
 	 * backed by a THP and thus use block mapping if possible.
 	 */
-	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
+	if (vma_pagesize == PAGE_SIZE && !(force_pte || s2_force_noncacheable)) {
 		if (fault_is_perm && fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
@@ -1702,7 +1742,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 	}
 
-	if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
+	if (!fault_is_perm && !s2_force_noncacheable && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (mte_allowed) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1718,7 +1758,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault)
 		prot |= KVM_PGTABLE_PROT_X;
 
-	if (device) {
+	if (s2_force_noncacheable) {
 		if (vfio_allow_any_uc)
 			prot |= KVM_PGTABLE_PROT_NORMAL_NC;
 		else
@@ -1794,9 +1834,28 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
+	/* Synchronous External Abort? */
+	if (kvm_vcpu_abt_issea(vcpu)) {
+		/*
+		 * For RAS the host kernel may handle this abort.
+		 * There is no need to pass the error into the guest.
+		 */
+		if (kvm_handle_guest_sea())
+			return kvm_inject_serror(vcpu);
+
+		return 1;
+	}
+
 	esr = kvm_vcpu_get_esr(vcpu);
 
+	/*
+	 * The fault IPA should be reliable at this point as we're not dealing
+	 * with an SEA.
+	 */
 	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
+		return -EFAULT;
+
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	if (esr_fsc_is_translation_fault(esr)) {
@@ -1810,26 +1869,10 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
 			fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
 
-			if (is_iabt)
-				kvm_inject_pabt(vcpu, fault_ipa);
-			else
-				kvm_inject_dabt(vcpu, fault_ipa);
-			return 1;
+			return kvm_inject_sea(vcpu, is_iabt, fault_ipa);
 		}
 	}
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
-			kvm_inject_vabt(vcpu);
-
-		return 1;
-	}
-
 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
@@ -1898,8 +1941,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 
 		if (kvm_vcpu_abt_iss1tw(vcpu)) {
-			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-			ret = 1;
+			ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			goto out_unlock;
 		}
 
@@ -1944,10 +1986,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	if (ret == 0)
 		ret = 1;
 out:
-	if (ret == -ENOEXEC) {
-		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		ret = 1;
-	}
+	if (ret == -ENOEXEC)
+		ret = kvm_inject_sea_iabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 out_unlock:
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	return ret;
@@ -2207,6 +2247,15 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				ret = -EINVAL;
 				break;
 			}
+
+			/*
+			 * Cacheable PFNMAP is allowed only if the hardware
+			 * supports it.
+			 */
+			if (kvm_vma_is_cacheable(vma) && !kvm_supports_cacheable_pfnmap()) {
+				ret = -EINVAL;
+				break;
+			}
 		}
 		hva = min(reg_end, vma->vm_end);
 	} while (hva < reg_end);