1 files changed, 443 insertions, 87 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7db96875ac..0f50960b0e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -533,31 +533,44 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
-typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
-typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
-			     unsigned long end);
+typedef void (*on_lock_fn_t)(struct kvm *kvm);
 
-typedef void (*on_unlock_fn_t)(struct kvm *kvm);
-
-struct kvm_hva_range {
-	unsigned long start;
-	unsigned long end;
+struct kvm_mmu_notifier_range {
+	/*
+	 * 64-bit addresses, as KVM notifiers can operate on host virtual
+	 * addresses (unsigned long) and guest physical addresses (64-bit).
+	 */
+	u64 start;
+	u64 end;
 	union kvm_mmu_notifier_arg arg;
-	hva_handler_t handler;
+	gfn_handler_t handler;
 	on_lock_fn_t on_lock;
-	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
 
 /*
+ * The inner-most helper returns a tuple containing the return value from the
+ * arch- and action-specific handler, plus a flag indicating whether or not at
+ * least one memslot was found, i.e. if the handler found guest memory.
+ *
+ * Note, most notifiers are averse to booleans, so even though KVM tracks the
+ * return from arch code as a bool, outer helpers will cast it to an int. :-(
+ */
+typedef struct kvm_mmu_notifier_return {
+	bool ret;
+	bool found_memslot;
+} kvm_mn_ret_t;
+
+/*
  * Use a dedicated stub instead of NULL to indicate that there is no callback
  * function/handler.  The compiler technically can't guarantee that a real
  * function will have a non-zero address, and so it will generate code to
@@ -578,26 +591,29 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
 	     node;							     \
 	     node = interval_tree_iter_next(node, start, last))	     \
 
-static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
-						  const struct kvm_hva_range *range)
+static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
+							   const struct kvm_mmu_notifier_range *range)
 {
-	bool ret = false, locked = false;
+	struct kvm_mmu_notifier_return r = {
+		.ret = false,
+		.found_memslot = false,
+	};
 	struct kvm_gfn_range gfn_range;
 	struct kvm_memory_slot *slot;
 	struct kvm_memslots *slots;
 	int i, idx;
 
 	if (WARN_ON_ONCE(range->end <= range->start))
-		return 0;
+		return r;
 
 	/* A null handler is allowed if and only if on_lock() is provided. */
 	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
 			 IS_KVM_NULL_FN(range->handler)))
-		return 0;
+		return r;
 
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct interval_tree_node *node;
 
 		slots = __kvm_memslots(kvm, i);
@@ -606,9 +622,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			unsigned long hva_start, hva_end;
 
 			slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
-			hva_start = max(range->start, slot->userspace_addr);
-			hva_end = min(range->end, slot->userspace_addr +
-						  (slot->npages << PAGE_SHIFT));
+			hva_start = max_t(unsigned long, range->start, slot->userspace_addr);
+			hva_end = min_t(unsigned long, range->end,
+					slot->userspace_addr + (slot->npages << PAGE_SHIFT));
 
 			/*
 			 * To optimize for the likely case where the address
@@ -627,71 +643,66 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
 
-			if (!locked) {
-				locked = true;
+			if (!r.found_memslot) {
+				r.found_memslot = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm, range->start, range->end);
+					range->on_lock(kvm);
+
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
-			ret |= range->handler(kvm, &gfn_range);
+			r.ret |= range->handler(kvm, &gfn_range);
 		}
 	}
 
-	if (range->flush_on_ret && ret)
+	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked) {
+	if (r.found_memslot)
 		KVM_MMU_UNLOCK(kvm);
-		if (!IS_KVM_NULL_FN(range->on_unlock))
-			range->on_unlock(kvm);
-	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	/* The notifiers are averse to booleans. :-( */
-	return (int)ret;
+	return r;
 }
 
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 						unsigned long start,
 						unsigned long end,
 						union kvm_mmu_notifier_arg arg,
-						hva_handler_t handler)
+						gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.arg		= arg,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
 							 unsigned long start,
 							 unsigned long end,
-							 hva_handler_t handler)
+							 gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -736,16 +747,29 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_invalidate_in_progress++;
+
 	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = INVALID_GPA;
+		kvm->mmu_invalidate_range_end = INVALID_GPA;
+	}
+}
+
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);
+
+	if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
 		kvm->mmu_invalidate_range_start = start;
 		kvm->mmu_invalidate_range_end = end;
 	} else {
@@ -765,16 +789,21 @@ void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
 	}
 }
 
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.handler	= kvm_unmap_gfn_range,
+		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
-		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -806,14 +835,21 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
-	__kvm_handle_hva_range(kvm, &hva_range);
+	/*
+	 * If one or more memslots were found and thus zapped, notify arch code
+	 * that guest memory has been reclaimed.  This needs to be done *after*
+	 * dropping mmu_lock, as x86's reclaim path is slooooow.
+	 */
+	if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot)
+		kvm_arch_guest_memory_reclaimed(kvm);
 
 	return 0;
 }
 
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -827,18 +863,24 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
 	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
 	kvm->mmu_invalidate_in_progress--;
+	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
+
+	/*
+	 * Assert that at least one range was added between start() and end().
+	 * Not adding a range isn't fatal, but it is a KVM bug.
+	 */
+	WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -857,8 +899,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 */
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
-
-	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
@@ -932,14 +972,14 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */
+#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 static int kvm_init_mmu_notifier(struct kvm *kvm)
 {
 	return 0;
 }
 
-#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
@@ -985,6 +1025,9 @@ 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_GUEST_MEMFD)
+		kvm_gmem_unbind(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1166,6 +1209,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	spin_lock_init(&kvm->mn_invalidate_lock);
 	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
 	xa_init(&kvm->vcpu_array);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_init(&kvm->mem_attr_array);
+#endif
 
 	INIT_LIST_HEAD(&kvm->gpc_list);
 	spin_lock_init(&kvm->gpc_lock);
@@ -1190,7 +1236,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		goto out_err_no_irq_srcu;
 
 	refcount_set(&kvm->users_count, 1);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
 
@@ -1222,7 +1268,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_disable;
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
@@ -1256,7 +1302,7 @@ out_err:
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
@@ -1315,7 +1361,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
@@ -1324,20 +1370,30 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	 * No threads can be waiting in kvm_swap_active_memslots() as the
 	 * last reference on KVM has been dropped, but freeing
 	 * memslots would deadlock without this manual intervention.
+	 *
+	 * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU
+	 * notifier between a start() and end(), then there shouldn't be any
+	 * in-progress invalidations.
 	 */
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
-	kvm->mn_active_invalidate_count = 0;
+	if (kvm->mn_active_invalidate_count)
+		kvm->mn_active_invalidate_count = 0;
+	else
+		WARN_ON(kvm->mmu_invalidate_in_progress);
 #else
 	kvm_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		kvm_free_memslots(kvm, &kvm->__memslots[i][0]);
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_destroy(&kvm->mem_attr_array);
+#endif
 	kvm_arch_free_vm(kvm);
 	preempt_notifier_dec();
 	hardware_disable_all();
@@ -1538,12 +1594,34 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+/*
+ * Flags that do not access any of the extra space of struct
+ * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
+ * only allows these.
+ */
+#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
+	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
+
+static int check_memory_region_flags(struct kvm *kvm,
+				     const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_GUEST_MEMFD;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
 #ifdef __KVM_HAVE_READONLY_MEM
-	valid_flags |= KVM_MEM_READONLY;
+	/*
+	 * GUEST_MEMFD is incompatible with read-only memslots, as writes to
+	 * read-only memslots have emulated MMIO, not page fault, semantics,
+	 * and KVM doesn't allow emulated MMIO for private memory.
+	 */
+	if (!(mem->flags & KVM_MEM_GUEST_MEMFD))
+		valid_flags |= KVM_MEM_READONLY;
 #endif
 
 	if (mem->flags & ~valid_flags)
@@ -1603,7 +1681,7 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
 	 * use generations 1, 3, 5, ...
 	 */
-	gen += KVM_ADDRESS_SPACE_NUM;
+	gen += kvm_arch_nr_memslot_as_ids(kvm);
 
 	kvm_arch_memslots_updated(kvm, gen);
 
@@ -1940,7 +2018,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * Must be called holding kvm->slots_lock for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+			    const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -1950,7 +2028,7 @@ 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;
 
@@ -1969,7 +2047,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
+	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+		return -EINVAL;
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
@@ -2007,6 +2089,9 @@ 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_GUEST_MEMFD)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2035,16 +2120,29 @@ 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_GUEST_MEMFD) {
+		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+		if (r)
+			goto out;
+	}
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out_unbind;
+
+	return 0;
+
+out_unbind:
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(new);
+out:
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+			  const struct kvm_userspace_memory_region2 *mem)
 {
 	int r;
 
@@ -2056,7 +2154,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-					  struct kvm_userspace_memory_region *mem)
+					  struct kvm_userspace_memory_region2 *mem)
 {
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -2089,7 +2187,7 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2151,7 +2249,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2263,7 +2361,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	if (log->first_page & 63)
@@ -2335,6 +2433,200 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+/*
+ * Returns true if _all_ gfns in the range [@start, @end) have attributes
+ * matching @attrs.
+ */
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs)
+{
+	XA_STATE(xas, &kvm->mem_attr_array, start);
+	unsigned long index;
+	bool has_attrs;
+	void *entry;
+
+	rcu_read_lock();
+
+	if (!attrs) {
+		has_attrs = !xas_find(&xas, end - 1);
+		goto out;
+	}
+
+	has_attrs = true;
+	for (index = start; index < end; index++) {
+		do {
+			entry = xas_next(&xas);
+		} while (xas_retry(&xas, entry));
+
+		if (xas.xa_index != index || xa_to_value(entry) != attrs) {
+			has_attrs = false;
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return has_attrs;
+}
+
+static u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+	if (!kvm || kvm_arch_has_private_mem(kvm))
+		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+
+	return 0;
+}
+
+static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
+						 struct kvm_mmu_notifier_range *range)
+{
+	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
+	struct kvm_memslot_iter iter;
+	bool found_memslot = false;
+	bool ret = false;
+	int i;
+
+	gfn_range.arg = range->arg;
+	gfn_range.may_block = range->may_block;
+
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
+		slots = __kvm_memslots(kvm, i);
+
+		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
+			slot = iter.slot;
+			gfn_range.slot = slot;
+
+			gfn_range.start = max(range->start, slot->base_gfn);
+			gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
+			if (gfn_range.start >= gfn_range.end)
+				continue;
+
+			if (!found_memslot) {
+				found_memslot = true;
+				KVM_MMU_LOCK(kvm);
+				if (!IS_KVM_NULL_FN(range->on_lock))
+					range->on_lock(kvm);
+			}
+
+			ret |= range->handler(kvm, &gfn_range);
+		}
+	}
+
+	if (range->flush_on_ret && ret)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
+					  struct kvm_gfn_range *range)
+{
+	/*
+	 * Unconditionally add the range to the invalidation set, regardless of
+	 * whether or not the arch callback actually needs to zap SPTEs.  E.g.
+	 * if KVM supports RWX attributes in the future and the attributes are
+	 * going from R=>RW, zapping isn't strictly necessary.  Unconditionally
+	 * adding the range allows KVM to require that MMU invalidations add at
+	 * least one range between begin() and end(), e.g. allows KVM to detect
+	 * bugs where the add() is missed.  Relaxing the rule *might* be safe,
+	 * but it's not obvious that allowing new mappings while the attributes
+	 * are in flux is desirable or worth the complexity.
+	 */
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+
+	return kvm_arch_pre_set_memory_attributes(kvm, range);
+}
+
+/* Set @attributes for the gfn range [@start, @end). */
+static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attributes)
+{
+	struct kvm_mmu_notifier_range pre_set_range = {
+		.start = start,
+		.end = end,
+		.handler = kvm_pre_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_begin,
+		.flush_on_ret = true,
+		.may_block = true,
+	};
+	struct kvm_mmu_notifier_range post_set_range = {
+		.start = start,
+		.end = end,
+		.arg.attributes = attributes,
+		.handler = kvm_arch_post_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_end,
+		.may_block = true,
+	};
+	unsigned long i;
+	void *entry;
+	int r = 0;
+
+	entry = attributes ? xa_mk_value(attributes) : NULL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	/* Nothing to do if the entire range as the desired attributes. */
+	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
+		goto out_unlock;
+
+	/*
+	 * Reserve memory ahead of time to avoid having to deal with failures
+	 * partway through setting the new attributes.
+	 */
+	for (i = start; i < end; i++) {
+		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
+		if (r)
+			goto out_unlock;
+	}
+
+	kvm_handle_gfn_range(kvm, &pre_set_range);
+
+	for (i = start; i < end; i++) {
+		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
+				    GFP_KERNEL_ACCOUNT));
+		KVM_BUG_ON(r, kvm);
+	}
+
+	kvm_handle_gfn_range(kvm, &post_set_range);
+
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
+					   struct kvm_memory_attributes *attrs)
+{
+	gfn_t start, end;
+
+	/* flags is currently not used. */
+	if (attrs->flags)
+		return -EINVAL;
+	if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
+		return -EINVAL;
+	if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
+		return -EINVAL;
+	if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
+		return -EINVAL;
+
+	start = attrs->address >> PAGE_SHIFT;
+	end = (attrs->address + attrs->size) >> PAGE_SHIFT;
+
+	/*
+	 * xarray tracks data using "unsigned long", and as a result so does
+	 * KVM.  For simplicity, supports generic attributes only on 64-bit
+	 * architectures.
+	 */
+	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
+
+	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -4527,13 +4819,14 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
 	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
 	case KVM_CAP_INTERNAL_ERROR_DATA:
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD:
 #endif
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
@@ -4555,9 +4848,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
-#if KVM_ADDRESS_SPACE_NUM > 1
+#if KVM_MAX_NR_ADDRESS_SPACES > 1
 	case KVM_CAP_MULTI_ADDRESS_SPACE:
-		return KVM_ADDRESS_SPACE_NUM;
+		if (kvm)
+			return kvm_arch_nr_memslot_as_ids(kvm);
+		return KVM_MAX_NR_ADDRESS_SPACES;
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
@@ -4578,7 +4873,16 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
+	case KVM_CAP_DEVICE_CTRL:
 		return 1;
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_CAP_MEMORY_ATTRIBUTES:
+		return kvm_supported_mem_attributes(kvm);
+#endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CAP_GUEST_MEMFD:
+		return !kvm || kvm_arch_has_private_mem(kvm);
+#endif
 	default:
 		break;
 	}
@@ -4657,7 +4961,7 @@ bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	lockdep_assert_held(&kvm->slots_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
 			return false;
 	}
@@ -4783,6 +5087,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 	return fd;
 }
 
+#define SANITY_CHECK_MEM_REGION_FIELD(field)					\
+do {										\
+	BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) !=		\
+		     offsetof(struct kvm_userspace_memory_region2, field));	\
+	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
+		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
+} while (0)
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4805,15 +5117,39 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
 		break;
 	}
+	case KVM_SET_USER_MEMORY_REGION2:
 	case KVM_SET_USER_MEMORY_REGION: {
-		struct kvm_userspace_memory_region kvm_userspace_mem;
+		struct kvm_userspace_memory_region2 mem;
+		unsigned long size;
+
+		if (ioctl == KVM_SET_USER_MEMORY_REGION) {
+			/*
+			 * Fields beyond struct kvm_userspace_memory_region shouldn't be
+			 * accessed, but avoid leaking kernel memory in case of a bug.
+			 */
+			memset(&mem, 0, sizeof(mem));
+			size = sizeof(struct kvm_userspace_memory_region);
+		} else {
+			size = sizeof(struct kvm_userspace_memory_region2);
+		}
+
+		/* Ensure the common parts of the two structs are identical. */
+		SANITY_CHECK_MEM_REGION_FIELD(slot);
+		SANITY_CHECK_MEM_REGION_FIELD(flags);
+		SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+		SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+		SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
 
 		r = -EFAULT;
-		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof(kvm_userspace_mem)))
+		if (copy_from_user(&mem, argp, size))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+		r = -EINVAL;
+		if (ioctl == KVM_SET_USER_MEMORY_REGION &&
+		    (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
+			goto out;
+
+		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
@@ -4927,9 +5263,8 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		if (routing.nr) {
 			urouting = argp;
-			entries = vmemdup_user(urouting->entries,
-					       array_size(sizeof(*entries),
-							  routing.nr));
+			entries = vmemdup_array_user(urouting->entries,
+						     routing.nr, sizeof(*entries));
 			if (IS_ERR(entries)) {
 				r = PTR_ERR(entries);
 				goto out;
@@ -4941,6 +5276,18 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_SET_MEMORY_ATTRIBUTES: {
+		struct kvm_memory_attributes attrs;
+
+		r = -EFAULT;
+		if (copy_from_user(&attrs, argp, sizeof(attrs)))
+			goto out;
+
+		r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
+		break;
+	}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 	case KVM_CREATE_DEVICE: {
 		struct kvm_create_device cd;
 
@@ -4968,6 +5315,18 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CREATE_GUEST_MEMFD: {
+		struct kvm_create_guest_memfd guest_memfd;
+
+		r = -EFAULT;
+		if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+			goto out;
+
+		r = kvm_gmem_create(kvm, &guest_memfd);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -5139,11 +5498,6 @@ static long kvm_dev_ioctl(struct file *filp,
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
-	case KVM_TRACE_ENABLE:
-	case KVM_TRACE_PAUSE:
-	case KVM_TRACE_DISABLE:
-		r = -EOPNOTSUPP;
-		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
 	}
@@ -6104,6 +6458,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
+	kvm_gmem_init(module);
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!