arm/arm64: KVM: map MMIO regions at creation time

There is really no point in faulting in memory regions page by page
if they are not backed by demand paged system RAM but by a linear
passthrough mapping of a host MMIO region. So instead, detect such
regions at setup time and install the mappings for the backing all
at once.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

arch/arm/kvm/mmu.c

@@ -1134,13 +1134,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   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,
@@ -1148,7 +1141,69 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
+	hva_t hva = mem->userspace_addr;
+	hva_t reg_end = hva + mem->memory_size;
+	bool writable = !(mem->flags & KVM_MEM_READONLY);
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE)
 		return 0;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we can map
+	 * any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = mem->guest_phys_addr +
+				    (vm_start - mem->userspace_addr);
+			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
+					 vm_start - vma->vm_start;
+
+			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
+						    vm_end - vm_start,
+						    writable);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (ret) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+	return ret;
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -1173,4 +1228,10 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	unmap_stage2_range(kvm, gpa, size);
+	spin_unlock(&kvm->mmu_lock);
 }