1 files changed, 199 insertions, 32 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4f35f0dfe681..deff4b3eb972 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -51,6 +51,7 @@
 #include <linux/slab.h>
 #include <linux/sort.h>
 #include <linux/bsearch.h>
+#include <linux/kthread.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -92,7 +93,7 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
  *	kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_SPINLOCK(kvm_lock);
+DEFINE_MUTEX(kvm_lock);
 static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
@@ -141,10 +142,30 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 {
 }
 
+bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+{
+	/*
+	 * The metadata used by is_zone_device_page() to determine whether or
+	 * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
+	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
+	 * page_count() is zero to help detect bad usage of this helper.
+	 */
+	if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+		return false;
+
+	return is_zone_device_page(pfn_to_page(pfn));
+}
+
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 {
+	/*
+	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+	 * perspective they are "normal" pages, albeit with slightly different
+	 * usage rules.
+	 */
 	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn));
+		return PageReserved(pfn_to_page(pfn)) &&
+		       !kvm_is_zone_device_pfn(pfn);
 
 	return true;
 }
@@ -596,8 +617,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 
 		stat_data->kvm = kvm;
 		stat_data->offset = p->offset;
+		stat_data->mode = p->mode ? p->mode : 0644;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		if (!debugfs_create_file(p->name, 0644,
+		if (!debugfs_create_file(p->name, stat_data->mode,
 					 kvm->debugfs_dentry,
 					 stat_data,
 					 stat_fops_per_vm[p->kind]))
@@ -606,6 +628,23 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 	return 0;
 }
 
+/*
+ * Called after the VM is otherwise initialized, but just before adding it to
+ * the vm_list.
+ */
+int __weak kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+/*
+ * Called just after removing the VM from the vm_list, but before doing any
+ * other destruction.
+ */
+void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+}
+
 static struct kvm *kvm_create_vm(unsigned long type)
 {
 	int r, i;
@@ -660,22 +699,31 @@ static struct kvm *kvm_create_vm(unsigned long type)
 		rcu_assign_pointer(kvm->buses[i],
 			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
 		if (!kvm->buses[i])
-			goto out_err;
+			goto out_err_no_mmu_notifier;
 	}
 
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
+		goto out_err_no_mmu_notifier;
+
+	r = kvm_arch_post_init_vm(kvm);
+	if (r)
 		goto out_err;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	preempt_notifier_inc();
 
 	return kvm;
 
 out_err:
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+	if (kvm->mmu_notifier.ops)
+		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
+#endif
+out_err_no_mmu_notifier:
 	cleanup_srcu_struct(&kvm->irq_srcu);
 out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
@@ -715,9 +763,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
 	kvm_destroy_vm_debugfs(kvm);
 	kvm_arch_sync_events(kvm);
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
+	kvm_arch_pre_destroy_vm(kvm);
+
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
@@ -856,6 +906,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 		int as_id, struct kvm_memslots *slots)
 {
 	struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
+	u64 gen;
 
 	/*
 	 * Set the low bit in the generation, which disables SPTE caching
@@ -878,9 +929,11 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 	 * space 0 will use generations 0, 4, 8, ... while * address space 1 will
 	 * use generations 2, 6, 10, 14, ...
 	 */
-	slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1;
+	gen = slots->generation + KVM_ADDRESS_SPACE_NUM * 2 - 1;
 
-	kvm_arch_memslots_updated(kvm, slots);
+	kvm_arch_memslots_updated(kvm, gen);
+
+	slots->generation = gen;
 
 	return old_memslots;
 }
@@ -1697,7 +1750,7 @@ static void kvm_release_pfn_dirty(kvm_pfn_t pfn)
 
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn)) {
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 
 		if (!PageReserved(page))
@@ -1708,7 +1761,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn))
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
@@ -1962,7 +2015,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
 
 int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			   void *data, int offset, unsigned long len)
+				  void *data, unsigned int offset,
+				  unsigned long len)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
@@ -2310,6 +2364,29 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 #endif
 }
 
+/*
+ * Unlike kvm_arch_vcpu_runnable, this function is called outside
+ * a vcpu_load/vcpu_put pair.  However, for most architectures
+ * kvm_arch_vcpu_runnable does not require vcpu_load.
+ */
+bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_vcpu_runnable(vcpu);
+}
+
+static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (kvm_arch_dy_runnable(vcpu))
+		return true;
+
+#ifdef CONFIG_KVM_ASYNC_PF
+	if (!list_empty_careful(&vcpu->async_pf.done))
+		return true;
+#endif
+
+	return false;
+}
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 {
 	struct kvm *kvm = me->kvm;
@@ -2339,7 +2416,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+			if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
 				continue;
 			if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
 				continue;
@@ -2808,6 +2885,9 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
 {
 	struct kvm_device *dev = filp->private_data;
 
+	if (dev->kvm->mm != current->mm)
+		return -EIO;
+
 	switch (ioctl) {
 	case KVM_SET_DEVICE_ATTR:
 		return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
@@ -2879,12 +2959,14 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	struct kvm_device_ops *ops = NULL;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int type;
 	int ret;
 
 	if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
 		return -ENODEV;
 
-	ops = kvm_device_ops_table[cd->type];
+	type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+	ops = kvm_device_ops_table[type];
 	if (ops == NULL)
 		return -ENODEV;
 
@@ -2899,7 +2981,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	dev->kvm = kvm;
 
 	mutex_lock(&kvm->lock);
-	ret = ops->create(dev, cd->type);
+	ret = ops->create(dev, type);
 	if (ret < 0) {
 		mutex_unlock(&kvm->lock);
 		kfree(dev);
@@ -2911,8 +2993,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	if (ops->init)
 		ops->init(dev);
 
+	kvm_get_kvm(kvm);
 	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
 	if (ret < 0) {
+		kvm_put_kvm(kvm);
 		mutex_lock(&kvm->lock);
 		list_del(&dev->vm_node);
 		mutex_unlock(&kvm->lock);
@@ -2920,7 +3004,6 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 		return ret;
 	}
 
-	kvm_get_kvm(kvm);
 	cd->fd = ret;
 	return 0;
 }
@@ -2954,8 +3037,6 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_MULTI_ADDRESS_SPACE:
 		return KVM_ADDRESS_SPACE_NUM;
 #endif
-	case KVM_CAP_MAX_VCPU_ID:
-		return KVM_MAX_VCPU_ID;
 	default:
 		break;
 	}
@@ -3682,7 +3763,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 	if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
 		return -ENOENT;
 
-	if (simple_attr_open(inode, file, get, set, fmt)) {
+	if (simple_attr_open(inode, file, get,
+			     stat_data->mode & S_IWUGO ? set : NULL,
+			     fmt)) {
 		kvm_put_kvm(stat_data->kvm);
 		return -ENOMEM;
 	}
@@ -3796,13 +3879,13 @@ static int vm_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -3815,12 +3898,12 @@ static int vm_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -3835,13 +3918,13 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -3854,12 +3937,12 @@ static int vcpu_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -3880,7 +3963,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	if (!kvm_dev.this_device || !kvm)
 		return;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	if (type == KVM_EVENT_CREATE_VM) {
 		kvm_createvm_count++;
 		kvm_active_vms++;
@@ -3889,7 +3972,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	created = kvm_createvm_count;
 	active = kvm_active_vms;
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL);
 	if (!env)
@@ -3906,7 +3989,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
-	if (kvm->debugfs_dentry) {
+	if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
 		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
 
 		if (p) {
@@ -3933,7 +4016,8 @@ static int kvm_init_debug(void)
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+		int mode = p->mode ? p->mode : 0644;
+		if (!debugfs_create_file(p->name, mode, kvm_debugfs_dir,
 					 (void *)(long)p->offset,
 					 stat_fops[p->kind]))
 			goto out_dir;
@@ -4120,3 +4204,86 @@ void kvm_exit(void)
 	kvm_vfio_ops_exit();
 }
 EXPORT_SYMBOL_GPL(kvm_exit);
+
+struct kvm_vm_worker_thread_context {
+	struct kvm *kvm;
+	struct task_struct *parent;
+	struct completion init_done;
+	kvm_vm_thread_fn_t thread_fn;
+	uintptr_t data;
+	int err;
+};
+
+static int kvm_vm_worker_thread(void *context)
+{
+	/*
+	 * The init_context is allocated on the stack of the parent thread, so
+	 * we have to locally copy anything that is needed beyond initialization
+	 */
+	struct kvm_vm_worker_thread_context *init_context = context;
+	struct kvm *kvm = init_context->kvm;
+	kvm_vm_thread_fn_t thread_fn = init_context->thread_fn;
+	uintptr_t data = init_context->data;
+	int err;
+
+	err = kthread_park(current);
+	/* kthread_park(current) is never supposed to return an error */
+	WARN_ON(err != 0);
+	if (err)
+		goto init_complete;
+
+	err = cgroup_attach_task_all(init_context->parent, current);
+	if (err) {
+		kvm_err("%s: cgroup_attach_task_all failed with err %d\n",
+			__func__, err);
+		goto init_complete;
+	}
+
+	set_user_nice(current, task_nice(init_context->parent));
+
+init_complete:
+	init_context->err = err;
+	complete(&init_context->init_done);
+	init_context = NULL;
+
+	if (err)
+		return err;
+
+	/* Wait to be woken up by the spawner before proceeding. */
+	kthread_parkme();
+
+	if (!kthread_should_stop())
+		err = thread_fn(kvm, data);
+
+	return err;
+}
+
+int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
+				uintptr_t data, const char *name,
+				struct task_struct **thread_ptr)
+{
+	struct kvm_vm_worker_thread_context init_context = {};
+	struct task_struct *thread;
+
+	*thread_ptr = NULL;
+	init_context.kvm = kvm;
+	init_context.parent = current;
+	init_context.thread_fn = thread_fn;
+	init_context.data = data;
+	init_completion(&init_context.init_done);
+
+	thread = kthread_run(kvm_vm_worker_thread, &init_context,
+			     "%s-%d", name, task_pid_nr(current));
+	if (IS_ERR(thread))
+		return PTR_ERR(thread);
+
+	/* kthread_run is never supposed to return NULL */
+	WARN_ON(thread == NULL);
+
+	wait_for_completion(&init_context.init_done);
+
+	if (!init_context.err)
+		*thread_ptr = thread;
+
+	return init_context.err;
+}