[PATCH v8 8/8] KVM: Enable and expose KVM_MEM_PRIVATE

[Chao Peng]

Expose KVM_MEM_PRIVATE and memslot fields private_fd/offset to
userspace. KVM will register/unregister private memslot to fd-based
memory backing store and response to invalidation event from
inaccessible_notifier to zap the existing memory mappings in the
secondary page table.

Whether KVM_MEM_PRIVATE is actually exposed to userspace is determined
by architecture code which can turn on it by overriding the default
kvm_arch_has_private_mem().

A 'kvm' reference is added in memslot structure since in
inaccessible_notifier callback we can only obtain a memslot reference
but 'kvm' is needed to do the zapping.

Co-developed-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
Signed-off-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
---
 include/linux/kvm_host.h |   1 +
 virt/kvm/kvm_main.c      | 116 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 111 insertions(+), 6 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b9906cdf468b..cb4eefac709c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -589,6 +589,7 @@ struct kvm_memory_slot {
 	struct file *private_file;
 	loff_t private_offset;
 	struct inaccessible_notifier notifier;
+	struct kvm *kvm;
 };
 
 static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 97d893f7482c..87e239d35b96 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -983,6 +983,57 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
 		xa_erase(&kvm->mem_attr_array, index);
 	return r;
 }
+
+static void kvm_private_notifier_invalidate(struct inaccessible_notifier *notifier,
+					    pgoff_t start, pgoff_t end)
+{
+	struct kvm_memory_slot *slot = container_of(notifier,
+						    struct kvm_memory_slot,
+						    notifier);
+	unsigned long base_pgoff = slot->private_offset >> PAGE_SHIFT;
+	gfn_t start_gfn = slot->base_gfn;
+	gfn_t end_gfn = slot->base_gfn + slot->npages;
+
+
+	if (start > base_pgoff)
+		start_gfn = slot->base_gfn + start - base_pgoff;
+
+	if (end < base_pgoff + slot->npages)
+		end_gfn = slot->base_gfn + end - base_pgoff;
+
+	if (start_gfn >= end_gfn)
+		return;
+
+	kvm_zap_gfn_range(slot->kvm, start_gfn, end_gfn);
+}
+
+static struct inaccessible_notifier_ops kvm_private_notifier_ops = {
+	.invalidate = kvm_private_notifier_invalidate,
+};
+
+static inline void kvm_private_mem_register(struct kvm_memory_slot *slot)
+{
+	slot->notifier.ops = &kvm_private_notifier_ops;
+	inaccessible_register_notifier(slot->private_file, &slot->notifier);
+}
+
+static inline void kvm_private_mem_unregister(struct kvm_memory_slot *slot)
+{
+	inaccessible_unregister_notifier(slot->private_file, &slot->notifier);
+}
+
+#else /* !CONFIG_HAVE_KVM_PRIVATE_MEM */
+
+static inline void kvm_private_mem_register(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+
+static inline void kvm_private_mem_unregister(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+
 #endif /* CONFIG_HAVE_KVM_PRIVATE_MEM */
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
@@ -1029,6 +1080,11 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_PRIVATE) {
+		kvm_private_mem_unregister(slot);
+		fput(slot->private_file);
+	}
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1600,10 +1656,16 @@ bool __weak kvm_arch_has_private_mem(struct kvm *kvm)
 	return false;
 }
 
-static int check_memory_region_flags(const struct kvm_user_mem_region *mem)
+static int check_memory_region_flags(struct kvm *kvm,
+				     const struct kvm_user_mem_region *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+#ifdef CONFIG_HAVE_KVM_PRIVATE_MEM
+	if (kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_PRIVATE;
+#endif
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -1679,6 +1741,9 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
 {
 	int r;
 
+	if (change == KVM_MR_CREATE && new->flags & KVM_MEM_PRIVATE)
+		kvm_private_mem_register(new);
+
 	/*
 	 * If dirty logging is disabled, nullify the bitmap; the old bitmap
 	 * will be freed on "commit".  If logging is enabled in both old and
@@ -1707,6 +1772,9 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
 	if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
 		kvm_destroy_dirty_bitmap(new);
 
+	if (r && change == KVM_MR_CREATE && new->flags & KVM_MEM_PRIVATE)
+		kvm_private_mem_unregister(new);
+
 	return r;
 }
 
@@ -2004,7 +2072,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -2023,6 +2091,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
+	if (mem->flags & KVM_MEM_PRIVATE &&
+		(mem->private_offset & (PAGE_SIZE - 1) ||
+		 mem->private_offset > U64_MAX - mem->memory_size))
+		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
@@ -2061,6 +2133,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_PRIVATE)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2089,10 +2164,27 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	if (mem->flags & KVM_MEM_PRIVATE) {
+		new->private_file = fget(mem->private_fd);
+		if (!new->private_file) {
+			r = -EINVAL;
+			goto out;
+		}
+		new->private_offset = mem->private_offset;
+	}
+
+	new->kvm = kvm;
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out;
+
+	return 0;
+
+out:
+	if (new->private_file)
+		fput(new->private_file);
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
@@ -4747,16 +4839,28 @@ static long kvm_vm_ioctl(struct file *filp,
 	}
 	case KVM_SET_USER_MEMORY_REGION: {
 		struct kvm_user_mem_region mem;
-		unsigned long size = sizeof(struct kvm_userspace_memory_region);
+		unsigned int flags_offset = offsetof(typeof(mem), flags);
+		unsigned long size;
+		u32 flags;
 
 		kvm_sanity_check_user_mem_region_alias();
 
+		memset(&mem, 0, sizeof(mem));
+
 		r = -EFAULT;
-		if (copy_from_user(&mem, argp, size);
+		if (get_user(flags, (u32 __user *)(argp + flags_offset)))
+			goto out;
+
+		if (flags & KVM_MEM_PRIVATE)
+			size = sizeof(struct kvm_userspace_memory_region_ext);
+		else
+			size = sizeof(struct kvm_userspace_memory_region);
+
+		if (copy_from_user(&mem, argp, size))
 			goto out;
 
 		r = -EINVAL;
-		if (mem.flags & KVM_MEM_PRIVATE)
+		if ((flags ^ mem.flags) & KVM_MEM_PRIVATE)
 			goto out;
 
 		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
-- 
2.25.1