Merge tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Gleb Natapov:
 "Highlights of the updates are:

  general:
   - new emulated device API
   - legacy device assignment is now optional
   - irqfd interface is more generic and can be shared between arches

  x86:
   - VMCS shadow support and other nested VMX improvements
   - APIC virtualization and Posted Interrupt hardware support
   - Optimize mmio spte zapping

  ppc:
    - BookE: in-kernel MPIC emulation with irqfd support
    - Book3S: in-kernel XICS emulation (incomplete)
    - Book3S: HV: migration fixes
    - BookE: more debug support preparation
    - BookE: e6500 support

  ARM:
   - reworking of Hyp idmaps

  s390:
   - ioeventfd for virtio-ccw

  And many other bug fixes, cleanups and improvements"

* tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  kvm: Add compat_ioctl for device control API
  KVM: x86: Account for failing enable_irq_window for NMI window request
  KVM: PPC: Book3S: Add API for in-kernel XICS emulation
  kvm/ppc/mpic: fix missing unlock in set_base_addr()
  kvm/ppc: Hold srcu lock when calling kvm_io_bus_read/write
  kvm/ppc/mpic: remove users
  kvm/ppc/mpic: fix mmio region lists when multiple guests used
  kvm/ppc/mpic: remove default routes from documentation
  kvm: KVM_CAP_IOMMU only available with device assignment
  ARM: KVM: iterate over all CPUs for CPU compatibility check
  KVM: ARM: Fix spelling in error message
  ARM: KVM: define KVM_ARM_MAX_VCPUS unconditionally
  KVM: ARM: Fix API documentation for ONE_REG encoding
  ARM: KVM: promote vfp_host pointer to generic host cpu context
  ARM: KVM: add architecture specific hook for capabilities
  ARM: KVM: perform HYP initilization for hotplugged CPUs
  ARM: KVM: switch to a dual-step HYP init code
  ARM: KVM: rework HYP page table freeing
  ARM: KVM: enforce maximum size for identity mapped code
  ARM: KVM: move to a KVM provided HYP idmap
  ...

1 files changed, 211 insertions, 47 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f18013f09e68..45f09362ee7b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -217,9 +217,9 @@ void kvm_make_mclock_inprogress_request(struct kvm *kvm)
 	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
 }
 
-void kvm_make_update_eoibitmap_request(struct kvm *kvm)
+void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
-	make_all_cpus_request(kvm, KVM_REQ_EOIBITMAP);
+	make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
 }
 
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
@@ -244,6 +244,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 	kvm_vcpu_set_in_spin_loop(vcpu, false);
 	kvm_vcpu_set_dy_eligible(vcpu, false);
+	vcpu->preempted = false;
 
 	r = kvm_arch_vcpu_init(vcpu);
 	if (r < 0)
@@ -503,6 +504,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
+	INIT_LIST_HEAD(&kvm->devices);
 
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
@@ -580,6 +582,19 @@ void kvm_free_physmem(struct kvm *kvm)
 	kfree(kvm->memslots);
 }
 
+static void kvm_destroy_devices(struct kvm *kvm)
+{
+	struct list_head *node, *tmp;
+
+	list_for_each_safe(node, tmp, &kvm->devices) {
+		struct kvm_device *dev =
+			list_entry(node, struct kvm_device, vm_node);
+
+		list_del(node);
+		dev->ops->destroy(dev);
+	}
+}
+
 static void kvm_destroy_vm(struct kvm *kvm)
 {
 	int i;
@@ -599,6 +614,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
+	kvm_destroy_devices(kvm);
 	kvm_free_physmem(kvm);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
@@ -719,24 +735,6 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 }
 
 /*
- * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
- * - create a new memory slot
- * - delete an existing memory slot
- * - modify an existing memory slot
- *   -- move it in the guest physical memory space
- *   -- just change its flags
- *
- * Since flags can be changed by some of these operations, the following
- * differentiation is the best we can do for __kvm_set_memory_region():
- */
-enum kvm_mr_change {
-	KVM_MR_CREATE,
-	KVM_MR_DELETE,
-	KVM_MR_MOVE,
-	KVM_MR_FLAGS_ONLY,
-};
-
-/*
  * Allocate some memory and give it an address in the guest physical address
  * space.
  *
@@ -745,8 +743,7 @@ enum kvm_mr_change {
  * Must be called holding mmap_sem for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    struct kvm_userspace_memory_region *mem,
-			    bool user_alloc)
+			    struct kvm_userspace_memory_region *mem)
 {
 	int r;
 	gfn_t base_gfn;
@@ -767,7 +764,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		goto out;
 	/* We can read the guest memory with __xxx_user() later on. */
-	if (user_alloc &&
+	if ((mem->slot < KVM_USER_MEM_SLOTS) &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
 	     !access_ok(VERIFY_WRITE,
 			(void __user *)(unsigned long)mem->userspace_addr,
@@ -875,7 +872,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		slots = old_memslots;
 	}
 
-	r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc);
+	r = kvm_arch_prepare_memory_region(kvm, &new, mem, change);
 	if (r)
 		goto out_slots;
 
@@ -915,7 +912,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	old_memslots = install_new_memslots(kvm, slots, &new);
 
-	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
+	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
 	kvm_free_physmem_slot(&old, &new);
 	kfree(old_memslots);
@@ -932,26 +929,23 @@ out:
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  struct kvm_userspace_memory_region *mem,
-			  bool user_alloc)
+			  struct kvm_userspace_memory_region *mem)
 {
 	int r;
 
 	mutex_lock(&kvm->slots_lock);
-	r = __kvm_set_memory_region(kvm, mem, user_alloc);
+	r = __kvm_set_memory_region(kvm, mem);
 	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-				   struct
-				   kvm_userspace_memory_region *mem,
-				   bool user_alloc)
+				   struct kvm_userspace_memory_region *mem)
 {
 	if (mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
-	return kvm_set_memory_region(kvm, mem, user_alloc);
+	return kvm_set_memory_region(kvm, mem);
 }
 
 int kvm_get_dirty_log(struct kvm *kvm,
@@ -1099,7 +1093,7 @@ static int kvm_read_hva_atomic(void *data, void __user *hva, int len)
 	return __copy_from_user_inatomic(data, hva, len);
 }
 
-int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
+static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
 	unsigned long start, int write, struct page **page)
 {
 	int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
@@ -1719,6 +1713,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 #endif /* !CONFIG_S390 */
 
 void kvm_resched(struct kvm_vcpu *vcpu)
@@ -1816,6 +1811,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			} else if (pass && i > last_boosted_vcpu)
 				break;
+			if (!ACCESS_ONCE(vcpu->preempted))
+				continue;
 			if (vcpu == me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
@@ -2204,6 +2201,119 @@ out:
 }
 #endif
 
+static int kvm_device_ioctl_attr(struct kvm_device *dev,
+				 int (*accessor)(struct kvm_device *dev,
+						 struct kvm_device_attr *attr),
+				 unsigned long arg)
+{
+	struct kvm_device_attr attr;
+
+	if (!accessor)
+		return -EPERM;
+
+	if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+		return -EFAULT;
+
+	return accessor(dev, &attr);
+}
+
+static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
+			     unsigned long arg)
+{
+	struct kvm_device *dev = filp->private_data;
+
+	switch (ioctl) {
+	case KVM_SET_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
+	case KVM_GET_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg);
+	case KVM_HAS_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg);
+	default:
+		if (dev->ops->ioctl)
+			return dev->ops->ioctl(dev, ioctl, arg);
+
+		return -ENOTTY;
+	}
+}
+
+static int kvm_device_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_device *dev = filp->private_data;
+	struct kvm *kvm = dev->kvm;
+
+	kvm_put_kvm(kvm);
+	return 0;
+}
+
+static const struct file_operations kvm_device_fops = {
+	.unlocked_ioctl = kvm_device_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = kvm_device_ioctl,
+#endif
+	.release = kvm_device_release,
+};
+
+struct kvm_device *kvm_device_from_filp(struct file *filp)
+{
+	if (filp->f_op != &kvm_device_fops)
+		return NULL;
+
+	return filp->private_data;
+}
+
+static int kvm_ioctl_create_device(struct kvm *kvm,
+				   struct kvm_create_device *cd)
+{
+	struct kvm_device_ops *ops = NULL;
+	struct kvm_device *dev;
+	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int ret;
+
+	switch (cd->type) {
+#ifdef CONFIG_KVM_MPIC
+	case KVM_DEV_TYPE_FSL_MPIC_20:
+	case KVM_DEV_TYPE_FSL_MPIC_42:
+		ops = &kvm_mpic_ops;
+		break;
+#endif
+#ifdef CONFIG_KVM_XICS
+	case KVM_DEV_TYPE_XICS:
+		ops = &kvm_xics_ops;
+		break;
+#endif
+	default:
+		return -ENODEV;
+	}
+
+	if (test)
+		return 0;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->ops = ops;
+	dev->kvm = kvm;
+
+	ret = ops->create(dev, cd->type);
+	if (ret < 0) {
+		kfree(dev);
+		return ret;
+	}
+
+	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR);
+	if (ret < 0) {
+		ops->destroy(dev);
+		return ret;
+	}
+
+	list_add(&dev->vm_node, &kvm->devices);
+	kvm_get_kvm(kvm);
+	cd->fd = ret;
+	return 0;
+}
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2225,7 +2335,7 @@ static long kvm_vm_ioctl(struct file *filp,
 						sizeof kvm_userspace_mem))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, true);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
@@ -2304,7 +2414,8 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 
-		r = kvm_vm_ioctl_irq_line(kvm, &irq_event);
+		r = kvm_vm_ioctl_irq_line(kvm, &irq_event,
+					ioctl == KVM_IRQ_LINE_STATUS);
 		if (r)
 			goto out;
 
@@ -2318,6 +2429,54 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+	case KVM_SET_GSI_ROUTING: {
+		struct kvm_irq_routing routing;
+		struct kvm_irq_routing __user *urouting;
+		struct kvm_irq_routing_entry *entries;
+
+		r = -EFAULT;
+		if (copy_from_user(&routing, argp, sizeof(routing)))
+			goto out;
+		r = -EINVAL;
+		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+			goto out;
+		if (routing.flags)
+			goto out;
+		r = -ENOMEM;
+		entries = vmalloc(routing.nr * sizeof(*entries));
+		if (!entries)
+			goto out;
+		r = -EFAULT;
+		urouting = argp;
+		if (copy_from_user(entries, urouting->entries,
+				   routing.nr * sizeof(*entries)))
+			goto out_free_irq_routing;
+		r = kvm_set_irq_routing(kvm, entries, routing.nr,
+					routing.flags);
+	out_free_irq_routing:
+		vfree(entries);
+		break;
+	}
+#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+	case KVM_CREATE_DEVICE: {
+		struct kvm_create_device cd;
+
+		r = -EFAULT;
+		if (copy_from_user(&cd, argp, sizeof(cd)))
+			goto out;
+
+		r = kvm_ioctl_create_device(kvm, &cd);
+		if (r)
+			goto out;
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &cd, sizeof(cd)))
+			goto out;
+
+		r = 0;
+		break;
+	}
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2447,8 +2606,11 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+	case KVM_CAP_IRQFD_RESAMPLE:
+#endif
 		return 1;
-#ifdef KVM_CAP_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
@@ -2618,14 +2780,6 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	return NOTIFY_OK;
 }
 
-
-asmlinkage void kvm_spurious_fault(void)
-{
-	/* Fault while not rebooting.  We want the trace. */
-	BUG();
-}
-EXPORT_SYMBOL_GPL(kvm_spurious_fault);
-
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
@@ -2658,7 +2812,7 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	kfree(bus);
 }
 
-int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 {
 	const struct kvm_io_range *r1 = p1;
 	const struct kvm_io_range *r2 = p2;
@@ -2670,7 +2824,7 @@ int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 	return 0;
 }
 
-int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
+static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 			  gpa_t addr, int len)
 {
 	bus->range[bus->dev_count++] = (struct kvm_io_range) {
@@ -2685,7 +2839,7 @@ int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 	return 0;
 }
 
-int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
+static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 			     gpa_t addr, int len)
 {
 	struct kvm_io_range *range, key;
@@ -2929,6 +3083,8 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
 static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+	if (vcpu->preempted)
+		vcpu->preempted = false;
 
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
@@ -2938,6 +3094,8 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
+	if (current->state == TASK_RUNNING)
+		vcpu->preempted = true;
 	kvm_arch_vcpu_put(vcpu);
 }
 
@@ -2947,6 +3105,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	int r;
 	int cpu;
 
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
 	r = kvm_arch_init(opaque);
 	if (r)
 		goto out_fail;
@@ -3027,6 +3188,8 @@ out_free_0a:
 out_free_0:
 	kvm_arch_exit();
 out_fail:
+	kvm_irqfd_exit();
+out_irqfd:
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_init);
@@ -3043,6 +3206,7 @@ void kvm_exit(void)
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
+	kvm_irqfd_exit();
 	free_cpumask_var(cpus_hardware_enabled);
 }
 EXPORT_SYMBOL_GPL(kvm_exit);