From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp

---
 kernel/drivers/vfio/vfio.c |  506 +++++++++++++++++++++++++++++++++++---------------------
 1 files changed, 315 insertions(+), 191 deletions(-)

diff --git a/kernel/drivers/vfio/vfio.c b/kernel/drivers/vfio/vfio.c
index 7a386fb..90db9d6 100644
--- a/kernel/drivers/vfio/vfio.c
+++ b/kernel/drivers/vfio/vfio.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * VFIO core
  *
  * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
  *     Author: Alex Williamson <alex.williamson@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  *
  * Derived from original vfio:
  * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
@@ -49,7 +46,6 @@
 	struct mutex			group_lock;
 	struct cdev			group_cdev;
 	dev_t				group_devt;
-	wait_queue_head_t		release_q;
 } vfio;
 
 struct vfio_iommu_driver {
@@ -88,17 +84,9 @@
 	atomic_t			opened;
 	wait_queue_head_t		container_q;
 	bool				noiommu;
+	unsigned int			dev_counter;
 	struct kvm			*kvm;
 	struct blocking_notifier_head	notifier;
-};
-
-struct vfio_device {
-	struct kref			kref;
-	struct device			*dev;
-	const struct vfio_device_ops	*ops;
-	struct vfio_group		*group;
-	struct list_head		group_next;
-	void				*device_data;
 };
 
 #ifdef CONFIG_VFIO_NOIOMMU
@@ -534,65 +522,17 @@
 /**
  * Device objects - create, release, get, put, search
  */
-static
-struct vfio_device *vfio_group_create_device(struct vfio_group *group,
-					     struct device *dev,
-					     const struct vfio_device_ops *ops,
-					     void *device_data)
-{
-	struct vfio_device *device;
-
-	device = kzalloc(sizeof(*device), GFP_KERNEL);
-	if (!device)
-		return ERR_PTR(-ENOMEM);
-
-	kref_init(&device->kref);
-	device->dev = dev;
-	device->group = group;
-	device->ops = ops;
-	device->device_data = device_data;
-	dev_set_drvdata(dev, device);
-
-	/* No need to get group_lock, caller has group reference */
-	vfio_group_get(group);
-
-	mutex_lock(&group->device_lock);
-	list_add(&device->group_next, &group->device_list);
-	mutex_unlock(&group->device_lock);
-
-	return device;
-}
-
-static void vfio_device_release(struct kref *kref)
-{
-	struct vfio_device *device = container_of(kref,
-						  struct vfio_device, kref);
-	struct vfio_group *group = device->group;
-
-	list_del(&device->group_next);
-	mutex_unlock(&group->device_lock);
-
-	dev_set_drvdata(device->dev, NULL);
-
-	kfree(device);
-
-	/* vfio_del_group_dev may be waiting for this device */
-	wake_up(&vfio.release_q);
-}
-
 /* Device reference always implies a group reference */
 void vfio_device_put(struct vfio_device *device)
 {
-	struct vfio_group *group = device->group;
-	kref_put_mutex(&device->kref, vfio_device_release, &group->device_lock);
-	vfio_group_put(group);
+	if (refcount_dec_and_test(&device->refcount))
+		complete(&device->comp);
 }
 EXPORT_SYMBOL_GPL(vfio_device_put);
 
-static void vfio_device_get(struct vfio_device *device)
+static bool vfio_device_try_get(struct vfio_device *device)
 {
-	vfio_group_get(device->group);
-	kref_get(&device->kref);
+	return refcount_inc_not_zero(&device->refcount);
 }
 
 static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
@@ -602,8 +542,7 @@
 
 	mutex_lock(&group->device_lock);
 	list_for_each_entry(device, &group->device_list, group_next) {
-		if (device->dev == dev) {
-			vfio_device_get(device);
+		if (device->dev == dev && vfio_device_try_get(device)) {
 			mutex_unlock(&group->device_lock);
 			return device;
 		}
@@ -627,9 +566,10 @@
  * that error notification via MSI can be affected for platforms that handle
  * MSI within the same IOVA space as DMA.
  */
-static const char * const vfio_driver_whitelist[] = { "pci-stub" };
+static const char * const vfio_driver_allowed[] = { "pci-stub" };
 
-static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
+static bool vfio_dev_driver_allowed(struct device *dev,
+				    struct device_driver *drv)
 {
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
@@ -638,8 +578,8 @@
 			return true;
 	}
 
-	return match_string(vfio_driver_whitelist,
-			    ARRAY_SIZE(vfio_driver_whitelist),
+	return match_string(vfio_driver_allowed,
+			    ARRAY_SIZE(vfio_driver_allowed),
 			    drv->name) >= 0;
 }
 
@@ -648,7 +588,7 @@
  * one of the following states:
  *  - driver-less
  *  - bound to a vfio driver
- *  - bound to a whitelisted driver
+ *  - bound to an otherwise allowed driver
  *  - a PCI interconnect device
  *
  * We use two methods to determine whether a device is bound to a vfio
@@ -674,7 +614,7 @@
 	}
 	mutex_unlock(&group->unbound_lock);
 
-	if (!ret || !drv || vfio_dev_whitelisted(dev, drv))
+	if (!ret || !drv || vfio_dev_driver_allowed(dev, drv))
 		return 0;
 
 	device = vfio_group_get_device(group, dev);
@@ -705,8 +645,8 @@
 		return 0;
 
 	/* TODO Prevent device auto probing */
-	WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
-	     iommu_group_id(group->iommu_group));
+	dev_WARN(dev, "Device added to live group %d!\n",
+		 iommu_group_id(group->iommu_group));
 
 	return 0;
 }
@@ -749,25 +689,22 @@
 		 */
 		break;
 	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
-		pr_debug("%s: Device %s, group %d binding to driver\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group));
+		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
+			iommu_group_id(group->iommu_group));
 		break;
 	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
-		pr_debug("%s: Device %s, group %d bound to driver %s\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group), dev->driver->name);
+		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
+			iommu_group_id(group->iommu_group), dev->driver->name);
 		BUG_ON(vfio_group_nb_verify(group, dev));
 		break;
 	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
-		pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group), dev->driver->name);
+		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
+			__func__, iommu_group_id(group->iommu_group),
+			dev->driver->name);
 		break;
 	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
-		pr_debug("%s: Device %s, group %d unbound from driver\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group));
+		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
+			iommu_group_id(group->iommu_group));
 		/*
 		 * XXX An unbound device in a live group is ok, but we'd
 		 * really like to avoid the above BUG_ON by preventing other
@@ -803,14 +740,23 @@
 /**
  * VFIO driver API
  */
-int vfio_add_group_dev(struct device *dev,
-		       const struct vfio_device_ops *ops, void *device_data)
+void vfio_init_group_dev(struct vfio_device *device, struct device *dev,
+			 const struct vfio_device_ops *ops, void *device_data)
 {
+	init_completion(&device->comp);
+	device->dev = dev;
+	device->ops = ops;
+	device->device_data = device_data;
+}
+EXPORT_SYMBOL_GPL(vfio_init_group_dev);
+
+int vfio_register_group_dev(struct vfio_device *device)
+{
+	struct vfio_device *existing_device;
 	struct iommu_group *iommu_group;
 	struct vfio_group *group;
-	struct vfio_device *device;
 
-	iommu_group = iommu_group_get(dev);
+	iommu_group = iommu_group_get(device->dev);
 	if (!iommu_group)
 		return -EINVAL;
 
@@ -829,29 +775,50 @@
 		iommu_group_put(iommu_group);
 	}
 
-	device = vfio_group_get_device(group, dev);
-	if (device) {
-		WARN(1, "Device %s already exists on group %d\n",
-		     dev_name(dev), iommu_group_id(iommu_group));
-		vfio_device_put(device);
+	existing_device = vfio_group_get_device(group, device->dev);
+	if (existing_device) {
+		dev_WARN(device->dev, "Device already exists on group %d\n",
+			 iommu_group_id(iommu_group));
+		vfio_device_put(existing_device);
 		vfio_group_put(group);
 		return -EBUSY;
 	}
 
-	device = vfio_group_create_device(group, dev, ops, device_data);
-	if (IS_ERR(device)) {
-		vfio_group_put(group);
-		return PTR_ERR(device);
-	}
+	/* Our reference on group is moved to the device */
+	device->group = group;
 
-	/*
-	 * Drop all but the vfio_device reference.  The vfio_device holds
-	 * a reference to the vfio_group, which holds a reference to the
-	 * iommu_group.
-	 */
-	vfio_group_put(group);
+	/* Refcounting can't start until the driver calls register */
+	refcount_set(&device->refcount, 1);
+
+	mutex_lock(&group->device_lock);
+	list_add(&device->group_next, &group->device_list);
+	group->dev_counter++;
+	mutex_unlock(&group->device_lock);
 
 	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_register_group_dev);
+
+int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops,
+		       void *device_data)
+{
+	struct vfio_device *device;
+	int ret;
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	vfio_init_group_dev(device, dev, ops, device_data);
+	ret = vfio_register_group_dev(device);
+	if (ret)
+		goto err_kfree;
+	dev_set_drvdata(dev, device);
+	return 0;
+
+err_kfree:
+	kfree(device);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vfio_add_group_dev);
 
@@ -881,13 +848,24 @@
 static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
 						     char *buf)
 {
-	struct vfio_device *it, *device = NULL;
+	struct vfio_device *it, *device = ERR_PTR(-ENODEV);
 
 	mutex_lock(&group->device_lock);
 	list_for_each_entry(it, &group->device_list, group_next) {
-		if (!strcmp(dev_name(it->dev), buf)) {
+		int ret;
+
+		if (it->ops->match) {
+			ret = it->ops->match(it->device_data, buf);
+			if (ret < 0) {
+				device = ERR_PTR(ret);
+				break;
+			}
+		} else {
+			ret = !strcmp(dev_name(it->dev), buf);
+		}
+
+		if (ret && vfio_device_try_get(it)) {
 			device = it;
-			vfio_device_get(device);
 			break;
 		}
 	}
@@ -908,21 +886,13 @@
 /*
  * Decrement the device reference count and wait for the device to be
  * removed.  Open file descriptors for the device... */
-void *vfio_del_group_dev(struct device *dev)
+void vfio_unregister_group_dev(struct vfio_device *device)
 {
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	struct vfio_device *device = dev_get_drvdata(dev);
 	struct vfio_group *group = device->group;
-	void *device_data = device->device_data;
 	struct vfio_unbound_dev *unbound;
 	unsigned int i = 0;
 	bool interrupted = false;
-
-	/*
-	 * The group exists so long as we have a device reference.  Get
-	 * a group reference and use it to scan for the device going away.
-	 */
-	vfio_group_get(group);
+	long rc;
 
 	/*
 	 * When the device is removed from the group, the group suddenly
@@ -935,7 +905,7 @@
 	 */
 	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
 	if (unbound) {
-		unbound->dev = dev;
+		unbound->dev = device->dev;
 		mutex_lock(&group->unbound_lock);
 		list_add(&unbound->unbound_next, &group->unbound_list);
 		mutex_unlock(&group->unbound_lock);
@@ -943,44 +913,33 @@
 	WARN_ON(!unbound);
 
 	vfio_device_put(device);
-
-	/*
-	 * If the device is still present in the group after the above
-	 * 'put', then it is in use and we need to request it from the
-	 * bus driver.  The driver may in turn need to request the
-	 * device from the user.  We send the request on an arbitrary
-	 * interval with counter to allow the driver to take escalating
-	 * measures to release the device if it has the ability to do so.
-	 */
-	add_wait_queue(&vfio.release_q, &wait);
-
-	do {
-		device = vfio_group_get_device(group, dev);
-		if (!device)
-			break;
-
+	rc = try_wait_for_completion(&device->comp);
+	while (rc <= 0) {
 		if (device->ops->request)
-			device->ops->request(device_data, i++);
-
-		vfio_device_put(device);
+			device->ops->request(device->device_data, i++);
 
 		if (interrupted) {
-			wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
+			rc = wait_for_completion_timeout(&device->comp,
+							 HZ * 10);
 		} else {
-			wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
-			if (signal_pending(current)) {
+			rc = wait_for_completion_interruptible_timeout(
+				&device->comp, HZ * 10);
+			if (rc < 0) {
 				interrupted = true;
-				dev_warn(dev,
+				dev_warn(device->dev,
 					 "Device is currently in use, task"
 					 " \"%s\" (%d) "
 					 "blocked until device is released",
 					 current->comm, task_pid_nr(current));
 			}
 		}
+	}
 
-	} while (1);
+	mutex_lock(&group->device_lock);
+	list_del(&device->group_next);
+	group->dev_counter--;
+	mutex_unlock(&group->device_lock);
 
-	remove_wait_queue(&vfio.release_q, &wait);
 	/*
 	 * In order to support multiple devices per group, devices can be
 	 * plucked from the group while other devices in the group are still
@@ -998,8 +957,19 @@
 	if (list_empty(&group->device_list))
 		wait_event(group->container_q, !group->container);
 
+	/* Matches the get in vfio_register_group_dev() */
 	vfio_group_put(group);
+}
+EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
 
+void *vfio_del_group_dev(struct device *dev)
+{
+	struct vfio_device *device = dev_get_drvdata(dev);
+	void *device_data = device->device_data;
+
+	vfio_unregister_group_dev(device);
+	dev_set_drvdata(dev, NULL);
+	kfree(device);
 	return device_data;
 }
 EXPORT_SYMBOL_GPL(vfio_del_group_dev);
@@ -1190,15 +1160,6 @@
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
-static long vfio_fops_compat_ioctl(struct file *filep,
-				   unsigned int cmd, unsigned long arg)
-{
-	arg = (unsigned long)compat_ptr(arg);
-	return vfio_fops_unl_ioctl(filep, cmd, arg);
-}
-#endif	/* CONFIG_COMPAT */
-
 static int vfio_fops_open(struct inode *inode, struct file *filep)
 {
 	struct vfio_container *container;
@@ -1281,9 +1242,7 @@
 	.read		= vfio_fops_read,
 	.write		= vfio_fops_write,
 	.unlocked_ioctl	= vfio_fops_unl_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= vfio_fops_compat_ioctl,
-#endif
+	.compat_ioctl	= compat_ptr_ioctl,
 	.mmap		= vfio_fops_mmap,
 };
 
@@ -1447,8 +1406,8 @@
 		return -EPERM;
 
 	device = vfio_device_get_from_name(group, buf);
-	if (!device)
-		return -ENODEV;
+	if (IS_ERR(device))
+		return PTR_ERR(device);
 
 	ret = device->ops->open(device->device_data);
 	if (ret) {
@@ -1562,15 +1521,6 @@
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
-static long vfio_group_fops_compat_ioctl(struct file *filep,
-					 unsigned int cmd, unsigned long arg)
-{
-	arg = (unsigned long)compat_ptr(arg);
-	return vfio_group_fops_unl_ioctl(filep, cmd, arg);
-}
-#endif	/* CONFIG_COMPAT */
-
 static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 {
 	struct vfio_group *group;
@@ -1626,9 +1576,7 @@
 static const struct file_operations vfio_group_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= vfio_group_fops_unl_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= vfio_group_fops_compat_ioctl,
-#endif
+	.compat_ioctl	= compat_ptr_ioctl,
 	.open		= vfio_group_fops_open,
 	.release	= vfio_group_fops_release,
 };
@@ -1693,24 +1641,13 @@
 	return device->ops->mmap(device->device_data, vma);
 }
 
-#ifdef CONFIG_COMPAT
-static long vfio_device_fops_compat_ioctl(struct file *filep,
-					  unsigned int cmd, unsigned long arg)
-{
-	arg = (unsigned long)compat_ptr(arg);
-	return vfio_device_fops_unl_ioctl(filep, cmd, arg);
-}
-#endif	/* CONFIG_COMPAT */
-
 static const struct file_operations vfio_device_fops = {
 	.owner		= THIS_MODULE,
 	.release	= vfio_device_fops_release,
 	.read		= vfio_device_fops_read,
 	.write		= vfio_device_fops_write,
 	.unlocked_ioctl	= vfio_device_fops_unl_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= vfio_device_fops_compat_ioctl,
-#endif
+	.compat_ioctl	= compat_ptr_ioctl,
 	.mmap		= vfio_device_fops_mmap,
 };
 
@@ -1758,6 +1695,44 @@
 	return group;
 }
 EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
+
+/**
+ * External user API, exported by symbols to be linked dynamically.
+ * The external user passes in a device pointer
+ * to verify that:
+ *	- A VFIO group is assiciated with the device;
+ *	- IOMMU is set for the group.
+ * If both checks passed, vfio_group_get_external_user_from_dev()
+ * increments the container user counter to prevent the VFIO group
+ * from disposal before external user exits and returns the pointer
+ * to the VFIO group.
+ *
+ * When the external user finishes using the VFIO group, it calls
+ * vfio_group_put_external_user() to release the VFIO group and
+ * decrement the container user counter.
+ *
+ * @dev [in]	: device
+ * Return error PTR or pointer to VFIO group.
+ */
+
+struct vfio_group *vfio_group_get_external_user_from_dev(struct device *dev)
+{
+	struct vfio_group *group;
+	int ret;
+
+	group = vfio_group_get_from_dev(dev);
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
+	ret = vfio_group_add_container_user(group);
+	if (ret) {
+		vfio_group_put(group);
+		return ERR_PTR(ret);
+	}
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(vfio_group_get_external_user_from_dev);
 
 void vfio_group_put_external_user(struct vfio_group *group)
 {
@@ -1808,6 +1783,7 @@
 	buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
 	if (!buf) {
 		kfree(caps->buf);
+		caps->buf = NULL;
 		caps->size = 0;
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1934,6 +1910,11 @@
 	if (!group)
 		return -ENODEV;
 
+	if (group->dev_counter > 1) {
+		ret = -EINVAL;
+		goto err_pin_pages;
+	}
+
 	ret = vfio_group_add_container_user(group);
 	if (ret)
 		goto err_pin_pages;
@@ -1941,7 +1922,8 @@
 	container = group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
-		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
+		ret = driver->ops->pin_pages(container->iommu_data,
+					     group->iommu_group, user_pfn,
 					     npage, prot, phys_pfn);
 	else
 		ret = -ENOTTY;
@@ -1999,6 +1981,149 @@
 	return ret;
 }
 EXPORT_SYMBOL(vfio_unpin_pages);
+
+/*
+ * Pin a set of guest IOVA PFNs and return their associated host PFNs for a
+ * VFIO group.
+ *
+ * The caller needs to call vfio_group_get_external_user() or
+ * vfio_group_get_external_user_from_dev() prior to calling this interface,
+ * so as to prevent the VFIO group from disposal in the middle of the call.
+ * But it can keep the reference to the VFIO group for several calls into
+ * this interface.
+ * After finishing using of the VFIO group, the caller needs to release the
+ * VFIO group by calling vfio_group_put_external_user().
+ *
+ * @group [in]		: VFIO group
+ * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be pinned.
+ * @npage [in]		: count of elements in user_iova_pfn array.
+ *			  This count should not be greater
+ *			  VFIO_PIN_PAGES_MAX_ENTRIES.
+ * @prot [in]		: protection flags
+ * @phys_pfn [out]	: array of host PFNs
+ * Return error or number of pages pinned.
+ */
+int vfio_group_pin_pages(struct vfio_group *group,
+			 unsigned long *user_iova_pfn, int npage,
+			 int prot, unsigned long *phys_pfn)
+{
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+	int ret;
+
+	if (!group || !user_iova_pfn || !phys_pfn || !npage)
+		return -EINVAL;
+
+	if (group->dev_counter > 1)
+		return -EINVAL;
+
+	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
+		return -E2BIG;
+
+	container = group->container;
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->pin_pages))
+		ret = driver->ops->pin_pages(container->iommu_data,
+					     group->iommu_group, user_iova_pfn,
+					     npage, prot, phys_pfn);
+	else
+		ret = -ENOTTY;
+
+	return ret;
+}
+EXPORT_SYMBOL(vfio_group_pin_pages);
+
+/*
+ * Unpin a set of guest IOVA PFNs for a VFIO group.
+ *
+ * The caller needs to call vfio_group_get_external_user() or
+ * vfio_group_get_external_user_from_dev() prior to calling this interface,
+ * so as to prevent the VFIO group from disposal in the middle of the call.
+ * But it can keep the reference to the VFIO group for several calls into
+ * this interface.
+ * After finishing using of the VFIO group, the caller needs to release the
+ * VFIO group by calling vfio_group_put_external_user().
+ *
+ * @group [in]		: vfio group
+ * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be unpinned.
+ * @npage [in]		: count of elements in user_iova_pfn array.
+ *			  This count should not be greater than
+ *			  VFIO_PIN_PAGES_MAX_ENTRIES.
+ * Return error or number of pages unpinned.
+ */
+int vfio_group_unpin_pages(struct vfio_group *group,
+			   unsigned long *user_iova_pfn, int npage)
+{
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+	int ret;
+
+	if (!group || !user_iova_pfn || !npage)
+		return -EINVAL;
+
+	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
+		return -E2BIG;
+
+	container = group->container;
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->unpin_pages))
+		ret = driver->ops->unpin_pages(container->iommu_data,
+					       user_iova_pfn, npage);
+	else
+		ret = -ENOTTY;
+
+	return ret;
+}
+EXPORT_SYMBOL(vfio_group_unpin_pages);
+
+
+/*
+ * This interface allows the CPUs to perform some sort of virtual DMA on
+ * behalf of the device.
+ *
+ * CPUs read/write from/into a range of IOVAs pointing to user space memory
+ * into/from a kernel buffer.
+ *
+ * As the read/write of user space memory is conducted via the CPUs and is
+ * not a real device DMA, it is not necessary to pin the user space memory.
+ *
+ * The caller needs to call vfio_group_get_external_user() or
+ * vfio_group_get_external_user_from_dev() prior to calling this interface,
+ * so as to prevent the VFIO group from disposal in the middle of the call.
+ * But it can keep the reference to the VFIO group for several calls into
+ * this interface.
+ * After finishing using of the VFIO group, the caller needs to release the
+ * VFIO group by calling vfio_group_put_external_user().
+ *
+ * @group [in]		: VFIO group
+ * @user_iova [in]	: base IOVA of a user space buffer
+ * @data [in]		: pointer to kernel buffer
+ * @len [in]		: kernel buffer length
+ * @write		: indicate read or write
+ * Return error code on failure or 0 on success.
+ */
+int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
+		void *data, size_t len, bool write)
+{
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+	int ret = 0;
+
+	if (!group || !data || len <= 0)
+		return -EINVAL;
+
+	container = group->container;
+	driver = container->iommu_driver;
+
+	if (likely(driver && driver->ops->dma_rw))
+		ret = driver->ops->dma_rw(container->iommu_data,
+					  user_iova, data, len, write);
+	else
+		ret = -ENOTTY;
+
+	return ret;
+}
+EXPORT_SYMBOL(vfio_dma_rw);
 
 static int vfio_register_iommu_notifier(struct vfio_group *group,
 					unsigned long *events,
@@ -2192,7 +2317,6 @@
 	mutex_init(&vfio.iommu_drivers_lock);
 	INIT_LIST_HEAD(&vfio.group_list);
 	INIT_LIST_HEAD(&vfio.iommu_drivers_list);
-	init_waitqueue_head(&vfio.release_q);
 
 	ret = misc_register(&vfio_dev);
 	if (ret) {
@@ -2209,12 +2333,12 @@
 
 	vfio.class->devnode = vfio_devnode;
 
-	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK, "vfio");
+	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
 	if (ret)
 		goto err_alloc_chrdev;
 
 	cdev_init(&vfio.group_cdev, &vfio_group_fops);
-	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK);
+	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK + 1);
 	if (ret)
 		goto err_cdev_add;
 
@@ -2226,7 +2350,7 @@
 	return 0;
 
 err_cdev_add:
-	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
 err_alloc_chrdev:
 	class_destroy(vfio.class);
 	vfio.class = NULL;
@@ -2244,7 +2368,7 @@
 #endif
 	idr_destroy(&vfio.group_idr);
 	cdev_del(&vfio.group_cdev);
-	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
 	class_destroy(vfio.class);
 	vfio.class = NULL;
 	misc_deregister(&vfio_dev);

--
Gitblit v1.6.2