1 files changed, 160 insertions, 93 deletions

diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index c93ef38f9cb0..eea03069161b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -90,103 +90,115 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static bool page_empty(void *ptr)
+static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
 {
-	struct page *ptr_page = virt_to_page(ptr);
-	return page_count(ptr_page) == 1;
+	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
+	pgd_clear(pgd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pud_free(NULL, pud_table);
+	put_page(virt_to_page(pgd));
 }
 
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
-	if (pud_huge(*pud)) {
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pmd_t *pmd_table = pmd_offset(pud, 0);
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pmd_free(NULL, pmd_table);
-	}
+	pmd_t *pmd_table = pmd_offset(pud, 0);
+	VM_BUG_ON(pud_huge(*pud));
+	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pmd_free(NULL, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
 static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
-	if (kvm_pmd_huge(*pmd)) {
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pte_t *pte_table = pte_offset_kernel(pmd, 0);
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pte_free_kernel(NULL, pte_table);
-	}
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(kvm_pmd_huge(*pmd));
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pte_free_kernel(NULL, pte_table);
 	put_page(virt_to_page(pmd));
 }
 
-static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
+static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+		       phys_addr_t addr, phys_addr_t end)
 {
-	if (pte_present(*pte)) {
-		kvm_set_pte(pte, __pte(0));
-		put_page(virt_to_page(pte));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	}
+	phys_addr_t start_addr = addr;
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			kvm_set_pte(pte, __pte(0));
+			put_page(virt_to_page(pte));
+			kvm_tlb_flush_vmid_ipa(kvm, addr);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (kvm_pte_table_empty(start_pte))
+		clear_pmd_entry(kvm, pmd, start_addr);
 }
 
-static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
-			unsigned long long start, u64 size)
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+		       phys_addr_t addr, phys_addr_t end)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	unsigned long long addr = start, end = start + size;
-	u64 next;
+	phys_addr_t next, start_addr = addr;
+	pmd_t *pmd, *start_pmd;
 
-	while (addr < end) {
-		pgd = pgdp + pgd_index(addr);
-		pud = pud_offset(pgd, addr);
-		if (pud_none(*pud)) {
-			addr = kvm_pud_addr_end(addr, end);
-			continue;
-		}
-
-		if (pud_huge(*pud)) {
-			/*
-			 * If we are dealing with a huge pud, just clear it and
-			 * move on.
-			 */
-			clear_pud_entry(kvm, pud, addr);
-			addr = kvm_pud_addr_end(addr, end);
-			continue;
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				pmd_clear(pmd);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pmd));
+			} else {
+				unmap_ptes(kvm, pmd, addr, next);
+			}
 		}
+	} while (pmd++, addr = next, addr != end);
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			addr = kvm_pmd_addr_end(addr, end);
-			continue;
-		}
+	if (kvm_pmd_table_empty(start_pmd))
+		clear_pud_entry(kvm, pud, start_addr);
+}
 
-		if (!kvm_pmd_huge(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr);
-			clear_pte_entry(kvm, pte, addr);
-			next = addr + PAGE_SIZE;
-		}
+static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pud_t *pud, *start_pud;
 
-		/*
-		 * If the pmd entry is to be cleared, walk back up the ladder
-		 */
-		if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
-			clear_pmd_entry(kvm, pmd, addr);
-			next = kvm_pmd_addr_end(addr, end);
-			if (page_empty(pmd) && !page_empty(pud)) {
-				clear_pud_entry(kvm, pud, addr);
-				next = kvm_pud_addr_end(addr, end);
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			if (pud_huge(*pud)) {
+				pud_clear(pud);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pud));
+			} else {
+				unmap_pmds(kvm, pud, addr, next);
 			}
 		}
+	} while (pud++, addr = next, addr != end);
 
-		addr = next;
-	}
+	if (kvm_pud_table_empty(start_pud))
+		clear_pgd_entry(kvm, pgd, start_addr);
+}
+
+
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+			phys_addr_t start, u64 size)
+{
+	pgd_t *pgd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	pgd = pgdp + pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		unmap_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
 }
 
 static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
@@ -734,21 +746,29 @@ static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
 	return false;
 }
 
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-			  struct kvm_memory_slot *memslot,
+			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
 {
 	int ret;
 	bool write_fault, writable, hugetlb = false, force_pte = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
-	unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	pfn_t pfn;
+	pgprot_t mem_type = PAGE_S2;
 
-	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
@@ -797,6 +817,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
+	if (kvm_is_mmio_pfn(pfn))
+		mem_type = PAGE_S2_DEVICE;
+
 	spin_lock(&kvm->mmu_lock);
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -804,7 +827,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
 	if (hugetlb) {
-		pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
+		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
 		if (writable) {
 			kvm_set_s2pmd_writable(&new_pmd);
@@ -813,13 +836,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
-		pte_t new_pte = pfn_pte(pfn, PAGE_S2);
+		pte_t new_pte = pfn_pte(pfn, mem_type);
 		if (writable) {
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
 		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
+				     mem_type == PAGE_S2_DEVICE);
 	}
 
 
@@ -846,7 +870,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	unsigned long fault_status;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
-	bool is_iabt;
+	unsigned long hva;
+	bool is_iabt, write_fault, writable;
 	gfn_t gfn;
 	int ret, idx;
 
@@ -857,17 +882,22 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	fault_status = kvm_vcpu_trap_get_fault(vcpu);
+	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
 	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
-		kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n",
-			kvm_vcpu_trap_get_class(vcpu), fault_status);
+		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+			kvm_vcpu_trap_get_class(vcpu),
+			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+			(unsigned long)kvm_vcpu_get_hsr(vcpu));
 		return -EFAULT;
 	}
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	gfn = fault_ipa >> PAGE_SHIFT;
-	if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+	write_fault = kvm_is_write_fault(vcpu);
+	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
 		if (is_iabt) {
 			/* Prefetch Abort on I/O address */
 			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
@@ -875,13 +905,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			goto out_unlock;
 		}
 
-		if (fault_status != FSC_FAULT) {
-			kvm_err("Unsupported fault status on io memory: %#lx\n",
-				fault_status);
-			ret = -EFAULT;
-			goto out_unlock;
-		}
-
 		/*
 		 * The IPA is reported as [MAX:12], so we need to
 		 * complement it with the bottom 12 bits from the
@@ -893,9 +916,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto out_unlock;
 	}
 
-	memslot = gfn_to_memslot(vcpu->kvm, gfn);
-
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
 out_unlock:
@@ -1099,3 +1120,49 @@ out:
 	free_hyp_pgds();
 	return err;
 }
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   enum kvm_mr_change change)
+{
+	gpa_t gpa = old->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = old->npages << PAGE_SHIFT;
+	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, gpa, size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
+{
+	return 0;
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
+{
+	return 0;
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+}