Merge tag 'vfio-v5.11-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Fix uninitialized list walk in error path (Eric Auger)

 - Use io_remap_pfn_range() (Jason Gunthorpe)

 - Allow fallback support for NVLink on POWER8 (Alexey Kardashevskiy)

 - Enable mdev request interrupt with CCW support (Eric Farman)

 - Enable interface to iommu_domain from vfio_group (Lu Baolu)

* tag 'vfio-v5.11-rc1' of git://github.com/awilliam/linux-vfio:
  vfio/type1: Add vfio_group_iommu_domain()
  vfio-ccw: Wire in the request callback
  vfio-mdev: Wire in a request handler for mdev parent
  vfio/pci/nvlink2: Do not attempt NPU2 setup on POWER8NVL NPU
  vfio-pci: Use io_remap_pfn_range() for PCI IO memory
  vfio/pci: Move dummy_resources_list init in vfio_pci_probe()

drivers/s390/cio/vfio_ccw_ops.c

@@ -394,6 +394,7 @@ static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
 	switch (info->index) {
 	case VFIO_CCW_IO_IRQ_INDEX:
 	case VFIO_CCW_CRW_IRQ_INDEX:
+	case VFIO_CCW_REQ_IRQ_INDEX:
 		info->count = 1;
 		info->flags = VFIO_IRQ_INFO_EVENTFD;
 		break;
@@ -424,6 +425,9 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
 	case VFIO_CCW_CRW_IRQ_INDEX:
 		ctx = &private->crw_trigger;
 		break;
+	case VFIO_CCW_REQ_IRQ_INDEX:
+		ctx = &private->req_trigger;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -607,6 +611,27 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 	}
 }
 
+/* Request removal of the device*/
+static void vfio_ccw_mdev_request(struct mdev_device *mdev, unsigned int count)
+{
+	struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (!private)
+		return;
+
+	if (private->req_trigger) {
+		if (!(count % 10))
+			dev_notice_ratelimited(mdev_dev(private->mdev),
+					       "Relaying device request to user (#%u)\n",
+					       count);
+
+		eventfd_signal(private->req_trigger, 1);
+	} else if (count == 0) {
+		dev_notice(mdev_dev(private->mdev),
+			   "No device request channel registered, blocked until released by user\n");
+	}
+}
+
 static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
 	.owner			= THIS_MODULE,
 	.supported_type_groups  = mdev_type_groups,
@@ -617,6 +642,7 @@ static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
 	.read			= vfio_ccw_mdev_read,
 	.write			= vfio_ccw_mdev_write,
 	.ioctl			= vfio_ccw_mdev_ioctl,
+	.request		= vfio_ccw_mdev_request,
 };
 
 int vfio_ccw_mdev_reg(struct subchannel *sch)

drivers/s390/cio/vfio_ccw_private.h

@@ -84,7 +84,10 @@ struct vfio_ccw_crw {
  * @irb: irb info received from interrupt
  * @scsw: scsw info
  * @io_trigger: eventfd ctx for signaling userspace I/O results
+ * @crw_trigger: eventfd ctx for signaling userspace CRW information
+ * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
+ * @crw_work: work for deferral process of CRW handling
  */
 struct vfio_ccw_private {
 	struct subchannel	*sch;
@@ -108,6 +111,7 @@ struct vfio_ccw_private {
 
 	struct eventfd_ctx	*io_trigger;
 	struct eventfd_ctx	*crw_trigger;
+	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
 } __aligned(8);

drivers/vfio/mdev/mdev_core.c

@@ -154,6 +154,10 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	if (!dev)
 		return -EINVAL;
 
+	/* Not mandatory, but its absence could be a problem */
+	if (!ops->request)
+		dev_info(dev, "Driver cannot be asked to release device\n");
+
 	mutex_lock(&parent_list_lock);
 
 	/* Check for duplicate */

drivers/vfio/mdev/vfio_mdev.c

@@ -98,6 +98,18 @@ static int vfio_mdev_mmap(void *device_data, struct vm_area_struct *vma)
 	return parent->ops->mmap(mdev, vma);
 }
 
+static void vfio_mdev_request(void *device_data, unsigned int count)
+{
+	struct mdev_device *mdev = device_data;
+	struct mdev_parent *parent = mdev->parent;
+
+	if (parent->ops->request)
+		parent->ops->request(mdev, count);
+	else if (count == 0)
+		dev_notice(mdev_dev(mdev),
+			   "No mdev vendor driver request callback support, blocked until released by user\n");
+}
+
 static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.name		= "vfio-mdev",
 	.open		= vfio_mdev_open,
@@ -106,6 +118,7 @@ static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.read		= vfio_mdev_read,
 	.write		= vfio_mdev_write,
 	.mmap		= vfio_mdev_mmap,
+	.request	= vfio_mdev_request,
 };
 
 static int vfio_mdev_probe(struct device *dev)

drivers/vfio/pci/vfio_pci.c

@@ -161,8 +161,6 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
 	int i;
 	struct vfio_pci_dummy_resource *dummy_res;
 
-	INIT_LIST_HEAD(&vdev->dummy_resources_list);
-
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		int bar = i + PCI_STD_RESOURCES;
 
@@ -1635,8 +1633,8 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 
 	mutex_unlock(&vdev->vma_lock);
 
-	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start, vma->vm_page_prot))
 		ret = VM_FAULT_SIGBUS;
 
 up_out:
@@ -1966,6 +1964,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&vdev->igate);
 	spin_lock_init(&vdev->irqlock);
 	mutex_init(&vdev->ioeventfds_lock);
+	INIT_LIST_HEAD(&vdev->dummy_resources_list);
 	INIT_LIST_HEAD(&vdev->ioeventfds_list);
 	mutex_init(&vdev->vma_lock);
 	INIT_LIST_HEAD(&vdev->vma_list);

drivers/vfio/pci/vfio_pci_nvlink2.c

@@ -231,7 +231,7 @@ int vfio_pci_nvdia_v100_nvlink2_init(struct vfio_pci_device *vdev)
 		return -EINVAL;
 
 	if (of_property_read_u32(npu_node, "memory-region", &mem_phandle))
-		return -EINVAL;
+		return -ENODEV;
 
 	mem_node = of_find_node_by_phandle(mem_phandle);
 	if (!mem_node)
@@ -393,7 +393,7 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
 	int ret;
 	struct vfio_pci_npu2_data *data;
 	struct device_node *nvlink_dn;
-	u32 nvlink_index = 0;
+	u32 nvlink_index = 0, mem_phandle = 0;
 	struct pci_dev *npdev = vdev->pdev;
 	struct device_node *npu_node = pci_device_to_OF_node(npdev);
 	struct pci_controller *hose = pci_bus_to_host(npdev->bus);
@@ -408,6 +408,9 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
 	if (!pnv_pci_get_gpu_dev(vdev->pdev))
 		return -ENODEV;
 
+	if (of_property_read_u32(npu_node, "memory-region", &mem_phandle))
+		return -ENODEV;
+
 	/*
 	 * NPU2 normally has 8 ATSD registers (for concurrency) and 6 links
 	 * so we can allocate one register per link, using nvlink index as

drivers/vfio/vfio.c

@@ -2331,6 +2331,24 @@ int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type,
 }
 EXPORT_SYMBOL(vfio_unregister_notifier);
 
+struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
+{
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+
+	if (!group)
+		return ERR_PTR(-EINVAL);
+
+	container = group->container;
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->group_iommu_domain))
+		return driver->ops->group_iommu_domain(container->iommu_data,
+						       group->iommu_group);
+
+	return ERR_PTR(-ENOTTY);
+}
+EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
+
 /**
  * Module/class support
  */

drivers/vfio/vfio_iommu_type1.c

@@ -2980,6 +2980,29 @@ static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova,
 	return ret;
 }
 
+static struct iommu_domain *
+vfio_iommu_type1_group_iommu_domain(void *iommu_data,
+				    struct iommu_group *iommu_group)
+{
+	struct iommu_domain *domain = ERR_PTR(-ENODEV);
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_domain *d;
+
+	if (!iommu || !iommu_group)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		if (find_iommu_group(d, iommu_group)) {
+			domain = d->domain;
+			break;
+		}
+	}
+	mutex_unlock(&iommu->lock);
+
+	return domain;
+}
+
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.name			= "vfio-iommu-type1",
 	.owner			= THIS_MODULE,
@@ -2993,6 +3016,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.register_notifier	= vfio_iommu_type1_register_notifier,
 	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
 	.dma_rw			= vfio_iommu_type1_dma_rw,
+	.group_iommu_domain	= vfio_iommu_type1_group_iommu_domain,
 };
 
 static int __init vfio_iommu_type1_init(void)

include/linux/mdev.h

@@ -72,6 +72,9 @@ struct device *mdev_get_iommu_device(struct device *dev);
  * @mmap:		mmap callback
  *			@mdev: mediated device structure
  *			@vma: vma structure
+ * @request:		request callback to release device
+ *			@mdev: mediated device structure
+ *			@count: request sequence number
  * Parent device that support mediated device should be registered with mdev
  * module with mdev_parent_ops structure.
  **/
@@ -92,6 +95,7 @@ struct mdev_parent_ops {
 	long	(*ioctl)(struct mdev_device *mdev, unsigned int cmd,
 			 unsigned long arg);
 	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
+	void	(*request)(struct mdev_device *mdev, unsigned int count);
 };
 
 /* interface for exporting mdev supported type attributes */

include/linux/vfio.h

@@ -90,6 +90,8 @@ struct vfio_iommu_driver_ops {
 					       struct notifier_block *nb);
 	int		(*dma_rw)(void *iommu_data, dma_addr_t user_iova,
 				  void *data, size_t count, bool write);
+	struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
+						   struct iommu_group *group);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -126,6 +128,8 @@ extern int vfio_group_unpin_pages(struct vfio_group *group,
 extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
 		       void *data, size_t len, bool write);
 
+extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
+
 /* each type has independent events */
 enum vfio_notify_type {
 	VFIO_IOMMU_NOTIFY = 0,

include/uapi/linux/vfio.h

@@ -820,6 +820,7 @@ enum {
 enum {
 	VFIO_CCW_IO_IRQ_INDEX,
 	VFIO_CCW_CRW_IRQ_INDEX,
+	VFIO_CCW_REQ_IRQ_INDEX,
 	VFIO_CCW_NUM_IRQS
 };