Merge tag 'vfio-v5.7-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - vfio-pci SR-IOV support (Alex Williamson)

 - vfio DMA read/write interface (Yan Zhao)

 - Fix vfio-platform erroneous IRQ error log (Eric Auger)

 - Fix shared ATSD support for NVLink on POWER (Sam Bobroff)

 - Fix init error without CONFIG_IOMMU_DMA (Andre Przywara)

* tag 'vfio-v5.7-rc1' of git://github.com/awilliam/linux-vfio:
  vfio: Ignore -ENODEV when getting MSI cookie
  vfio-pci/nvlink2: Allow fallback to ibm,mmio-atsd[0]
  vfio/pci: Cleanup .probe() exit paths
  vfio/pci: Remove dev_fmt definition
  vfio/pci: Add sriov_configure support
  vfio: Introduce VFIO_DEVICE_FEATURE ioctl and first user
  vfio/pci: Introduce VF token
  vfio/pci: Implement match ops
  vfio: Include optional device match in vfio_device_ops callbacks
  vfio: avoid inefficient operations on VFIO group in vfio_pin/unpin_pages
  vfio: introduce vfio_dma_rw to read/write a range of IOVAs
  vfio: allow external user to get vfio group from device
  vfio: platform: Switch to platform_get_irq_optional()

drivers/vfio/pci/vfio_pci.c

@@ -9,7 +9,6 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#define dev_fmt pr_fmt
 
 #include <linux/device.h>
 #include <linux/eventfd.h>
@@ -54,6 +53,12 @@ module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(disable_idle_d3,
 		 "Disable using the PCI D3 low power state for idle, unused devices");
 
+static bool enable_sriov;
+#ifdef CONFIG_PCI_IOV
+module_param(enable_sriov, bool, 0644);
+MODULE_PARM_DESC(enable_sriov, "Enable support for SR-IOV configuration.  Enabling SR-IOV on a PF typically requires support of the userspace PF driver, enabling VFs without such support may result in non-functional VFs or PF.");
+#endif
+
 static inline bool vfio_vga_disabled(void)
 {
 #ifdef CONFIG_VFIO_PCI_VGA
@@ -466,6 +471,44 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 		vfio_pci_set_power_state(vdev, PCI_D3hot);
 }
 
+static struct pci_driver vfio_pci_driver;
+
+static struct vfio_pci_device *get_pf_vdev(struct vfio_pci_device *vdev,
+					   struct vfio_device **pf_dev)
+{
+	struct pci_dev *physfn = pci_physfn(vdev->pdev);
+
+	if (!vdev->pdev->is_virtfn)
+		return NULL;
+
+	*pf_dev = vfio_device_get_from_dev(&physfn->dev);
+	if (!*pf_dev)
+		return NULL;
+
+	if (pci_dev_driver(physfn) != &vfio_pci_driver) {
+		vfio_device_put(*pf_dev);
+		return NULL;
+	}
+
+	return vfio_device_data(*pf_dev);
+}
+
+static void vfio_pci_vf_token_user_add(struct vfio_pci_device *vdev, int val)
+{
+	struct vfio_device *pf_dev;
+	struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev, &pf_dev);
+
+	if (!pf_vdev)
+		return;
+
+	mutex_lock(&pf_vdev->vf_token->lock);
+	pf_vdev->vf_token->users += val;
+	WARN_ON(pf_vdev->vf_token->users < 0);
+	mutex_unlock(&pf_vdev->vf_token->lock);
+
+	vfio_device_put(pf_dev);
+}
+
 static void vfio_pci_release(void *device_data)
 {
 	struct vfio_pci_device *vdev = device_data;
@@ -473,6 +516,7 @@ static void vfio_pci_release(void *device_data)
 	mutex_lock(&vdev->reflck->lock);
 
 	if (!(--vdev->refcnt)) {
+		vfio_pci_vf_token_user_add(vdev, -1);
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
 	}
@@ -498,6 +542,7 @@ static int vfio_pci_open(void *device_data)
 			goto error;
 
 		vfio_spapr_pci_eeh_open(vdev->pdev);
+		vfio_pci_vf_token_user_add(vdev, 1);
 	}
 	vdev->refcnt++;
 error:
@@ -1140,6 +1185,65 @@ static long vfio_pci_ioctl(void *device_data,
 
 		return vfio_pci_ioeventfd(vdev, ioeventfd.offset,
 					  ioeventfd.data, count, ioeventfd.fd);
+	} else if (cmd == VFIO_DEVICE_FEATURE) {
+		struct vfio_device_feature feature;
+		uuid_t uuid;
+
+		minsz = offsetofend(struct vfio_device_feature, flags);
+
+		if (copy_from_user(&feature, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (feature.argsz < minsz)
+			return -EINVAL;
+
+		/* Check unknown flags */
+		if (feature.flags & ~(VFIO_DEVICE_FEATURE_MASK |
+				      VFIO_DEVICE_FEATURE_SET |
+				      VFIO_DEVICE_FEATURE_GET |
+				      VFIO_DEVICE_FEATURE_PROBE))
+			return -EINVAL;
+
+		/* GET & SET are mutually exclusive except with PROBE */
+		if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) &&
+		    (feature.flags & VFIO_DEVICE_FEATURE_SET) &&
+		    (feature.flags & VFIO_DEVICE_FEATURE_GET))
+			return -EINVAL;
+
+		switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) {
+		case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN:
+			if (!vdev->vf_token)
+				return -ENOTTY;
+
+			/*
+			 * We do not support GET of the VF Token UUID as this
+			 * could expose the token of the previous device user.
+			 */
+			if (feature.flags & VFIO_DEVICE_FEATURE_GET)
+				return -EINVAL;
+
+			if (feature.flags & VFIO_DEVICE_FEATURE_PROBE)
+				return 0;
+
+			/* Don't SET unless told to do so */
+			if (!(feature.flags & VFIO_DEVICE_FEATURE_SET))
+				return -EINVAL;
+
+			if (feature.argsz < minsz + sizeof(uuid))
+				return -EINVAL;
+
+			if (copy_from_user(&uuid, (void __user *)(arg + minsz),
+					   sizeof(uuid)))
+				return -EFAULT;
+
+			mutex_lock(&vdev->vf_token->lock);
+			uuid_copy(&vdev->vf_token->uuid, &uuid);
+			mutex_unlock(&vdev->vf_token->lock);
+
+			return 0;
+		default:
+			return -ENOTTY;
+		}
 	}
 
 	return -ENOTTY;
@@ -1278,6 +1382,150 @@ static void vfio_pci_request(void *device_data, unsigned int count)
 	mutex_unlock(&vdev->igate);
 }
 
+static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
+				      bool vf_token, uuid_t *uuid)
+{
+	/*
+	 * There's always some degree of trust or collaboration between SR-IOV
+	 * PF and VFs, even if just that the PF hosts the SR-IOV capability and
+	 * can disrupt VFs with a reset, but often the PF has more explicit
+	 * access to deny service to the VF or access data passed through the
+	 * VF.  We therefore require an opt-in via a shared VF token (UUID) to
+	 * represent this trust.  This both prevents that a VF driver might
+	 * assume the PF driver is a trusted, in-kernel driver, and also that
+	 * a PF driver might be replaced with a rogue driver, unknown to in-use
+	 * VF drivers.
+	 *
+	 * Therefore when presented with a VF, if the PF is a vfio device and
+	 * it is bound to the vfio-pci driver, the user needs to provide a VF
+	 * token to access the device, in the form of appending a vf_token to
+	 * the device name, for example:
+	 *
+	 * "0000:04:10.0 vf_token=bd8d9d2b-5a5f-4f5a-a211-f591514ba1f3"
+	 *
+	 * When presented with a PF which has VFs in use, the user must also
+	 * provide the current VF token to prove collaboration with existing
+	 * VF users.  If VFs are not in use, the VF token provided for the PF
+	 * device will act to set the VF token.
+	 *
+	 * If the VF token is provided but unused, an error is generated.
+	 */
+	if (!vdev->pdev->is_virtfn && !vdev->vf_token && !vf_token)
+		return 0; /* No VF token provided or required */
+
+	if (vdev->pdev->is_virtfn) {
+		struct vfio_device *pf_dev;
+		struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev, &pf_dev);
+		bool match;
+
+		if (!pf_vdev) {
+			if (!vf_token)
+				return 0; /* PF is not vfio-pci, no VF token */
+
+			pci_info_ratelimited(vdev->pdev,
+				"VF token incorrectly provided, PF not bound to vfio-pci\n");
+			return -EINVAL;
+		}
+
+		if (!vf_token) {
+			vfio_device_put(pf_dev);
+			pci_info_ratelimited(vdev->pdev,
+				"VF token required to access device\n");
+			return -EACCES;
+		}
+
+		mutex_lock(&pf_vdev->vf_token->lock);
+		match = uuid_equal(uuid, &pf_vdev->vf_token->uuid);
+		mutex_unlock(&pf_vdev->vf_token->lock);
+
+		vfio_device_put(pf_dev);
+
+		if (!match) {
+			pci_info_ratelimited(vdev->pdev,
+				"Incorrect VF token provided for device\n");
+			return -EACCES;
+		}
+	} else if (vdev->vf_token) {
+		mutex_lock(&vdev->vf_token->lock);
+		if (vdev->vf_token->users) {
+			if (!vf_token) {
+				mutex_unlock(&vdev->vf_token->lock);
+				pci_info_ratelimited(vdev->pdev,
+					"VF token required to access device\n");
+				return -EACCES;
+			}
+
+			if (!uuid_equal(uuid, &vdev->vf_token->uuid)) {
+				mutex_unlock(&vdev->vf_token->lock);
+				pci_info_ratelimited(vdev->pdev,
+					"Incorrect VF token provided for device\n");
+				return -EACCES;
+			}
+		} else if (vf_token) {
+			uuid_copy(&vdev->vf_token->uuid, uuid);
+		}
+
+		mutex_unlock(&vdev->vf_token->lock);
+	} else if (vf_token) {
+		pci_info_ratelimited(vdev->pdev,
+			"VF token incorrectly provided, not a PF or VF\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#define VF_TOKEN_ARG "vf_token="
+
+static int vfio_pci_match(void *device_data, char *buf)
+{
+	struct vfio_pci_device *vdev = device_data;
+	bool vf_token = false;
+	uuid_t uuid;
+	int ret;
+
+	if (strncmp(pci_name(vdev->pdev), buf, strlen(pci_name(vdev->pdev))))
+		return 0; /* No match */
+
+	if (strlen(buf) > strlen(pci_name(vdev->pdev))) {
+		buf += strlen(pci_name(vdev->pdev));
+
+		if (*buf != ' ')
+			return 0; /* No match: non-whitespace after name */
+
+		while (*buf) {
+			if (*buf == ' ') {
+				buf++;
+				continue;
+			}
+
+			if (!vf_token && !strncmp(buf, VF_TOKEN_ARG,
+						  strlen(VF_TOKEN_ARG))) {
+				buf += strlen(VF_TOKEN_ARG);
+
+				if (strlen(buf) < UUID_STRING_LEN)
+					return -EINVAL;
+
+				ret = uuid_parse(buf, &uuid);
+				if (ret)
+					return ret;
+
+				vf_token = true;
+				buf += UUID_STRING_LEN;
+			} else {
+				/* Unknown/duplicate option */
+				return -EINVAL;
+			}
+		}
+	}
+
+	ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid);
+	if (ret)
+		return ret;
+
+	return 1; /* Match */
+}
+
 static const struct vfio_device_ops vfio_pci_ops = {
 	.name		= "vfio-pci",
 	.open		= vfio_pci_open,
@@ -1287,10 +1535,40 @@ static const struct vfio_device_ops vfio_pci_ops = {
 	.write		= vfio_pci_write,
 	.mmap		= vfio_pci_mmap,
 	.request	= vfio_pci_request,
+	.match		= vfio_pci_match,
 };
 
 static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev);
 static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck);
+static struct pci_driver vfio_pci_driver;
+
+static int vfio_pci_bus_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct vfio_pci_device *vdev = container_of(nb,
+						    struct vfio_pci_device, nb);
+	struct device *dev = data;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev *physfn = pci_physfn(pdev);
+
+	if (action == BUS_NOTIFY_ADD_DEVICE &&
+	    pdev->is_virtfn && physfn == vdev->pdev) {
+		pci_info(vdev->pdev, "Captured SR-IOV VF %s driver_override\n",
+			 pci_name(pdev));
+		pdev->driver_override = kasprintf(GFP_KERNEL, "%s",
+						  vfio_pci_ops.name);
+	} else if (action == BUS_NOTIFY_BOUND_DRIVER &&
+		   pdev->is_virtfn && physfn == vdev->pdev) {
+		struct pci_driver *drv = pci_dev_driver(pdev);
+
+		if (drv && drv != &vfio_pci_driver)
+			pci_warn(vdev->pdev,
+				 "VF %s bound to driver %s while PF bound to vfio-pci\n",
+				 pci_name(pdev), drv->name);
+	}
+
+	return 0;
+}
 
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
@@ -1302,12 +1580,12 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -EINVAL;
 
 	/*
-	 * Prevent binding to PFs with VFs enabled, this too easily allows
-	 * userspace instance with VFs and PFs from the same device, which
-	 * cannot work.  Disabling SR-IOV here would initiate removing the
-	 * VFs, which would unbind the driver, which is prone to blocking
-	 * if that VF is also in use by vfio-pci.  Just reject these PFs
-	 * and let the user sort it out.
+	 * Prevent binding to PFs with VFs enabled, the VFs might be in use
+	 * by the host or other users.  We cannot capture the VFs if they
+	 * already exist, nor can we track VF users.  Disabling SR-IOV here
+	 * would initiate removing the VFs, which would unbind the driver,
+	 * which is prone to blocking if that VF is also in use by vfio-pci.
+	 * Just reject these PFs and let the user sort it out.
 	 */
 	if (pci_num_vf(pdev)) {
 		pci_warn(pdev, "Cannot bind to PF with SR-IOV enabled\n");
@@ -1320,8 +1598,8 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
 	if (!vdev) {
-		vfio_iommu_group_put(group, &pdev->dev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_group_put;
 	}
 
 	vdev->pdev = pdev;
@@ -1332,18 +1610,27 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&vdev->ioeventfds_list);
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
-	if (ret) {
-		vfio_iommu_group_put(group, &pdev->dev);
-		kfree(vdev);
-		return ret;
-	}
+	if (ret)
+		goto out_free;
 
 	ret = vfio_pci_reflck_attach(vdev);
-	if (ret) {
-		vfio_del_group_dev(&pdev->dev);
-		vfio_iommu_group_put(group, &pdev->dev);
-		kfree(vdev);
-		return ret;
+	if (ret)
+		goto out_del_group_dev;
+
+	if (pdev->is_physfn) {
+		vdev->vf_token = kzalloc(sizeof(*vdev->vf_token), GFP_KERNEL);
+		if (!vdev->vf_token) {
+			ret = -ENOMEM;
+			goto out_reflck;
+		}
+
+		mutex_init(&vdev->vf_token->lock);
+		uuid_gen(&vdev->vf_token->uuid);
+
+		vdev->nb.notifier_call = vfio_pci_bus_notifier;
+		ret = bus_register_notifier(&pci_bus_type, &vdev->nb);
+		if (ret)
+			goto out_vf_token;
 	}
 
 	if (vfio_pci_is_vga(pdev)) {
@@ -1369,16 +1656,39 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	return ret;
+
+out_vf_token:
+	kfree(vdev->vf_token);
+out_reflck:
+	vfio_pci_reflck_put(vdev->reflck);
+out_del_group_dev:
+	vfio_del_group_dev(&pdev->dev);
+out_free:
+	kfree(vdev);
+out_group_put:
+	vfio_iommu_group_put(group, &pdev->dev);
+	return ret;
 }
 
 static void vfio_pci_remove(struct pci_dev *pdev)
 {
 	struct vfio_pci_device *vdev;
 
+	pci_disable_sriov(pdev);
+
 	vdev = vfio_del_group_dev(&pdev->dev);
 	if (!vdev)
 		return;
 
+	if (vdev->vf_token) {
+		WARN_ON(vdev->vf_token->users);
+		mutex_destroy(&vdev->vf_token->lock);
+		kfree(vdev->vf_token);
+	}
+
+	if (vdev->nb.notifier_call)
+		bus_unregister_notifier(&pci_bus_type, &vdev->nb);
+
 	vfio_pci_reflck_put(vdev->reflck);
 
 	vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
@@ -1427,16 +1737,48 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
+static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
+{
+	struct vfio_pci_device *vdev;
+	struct vfio_device *device;
+	int ret = 0;
+
+	might_sleep();
+
+	if (!enable_sriov)
+		return -ENOENT;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (!device)
+		return -ENODEV;
+
+	vdev = vfio_device_data(device);
+	if (!vdev) {
+		vfio_device_put(device);
+		return -ENODEV;
+	}
+
+	if (nr_virtfn == 0)
+		pci_disable_sriov(pdev);
+	else
+		ret = pci_enable_sriov(pdev, nr_virtfn);
+
+	vfio_device_put(device);
+
+	return ret < 0 ? ret : nr_virtfn;
+}
+
 static const struct pci_error_handlers vfio_err_handlers = {
 	.error_detected = vfio_pci_aer_err_detected,
 };
 
 static struct pci_driver vfio_pci_driver = {
-	.name		= "vfio-pci",
-	.id_table	= NULL, /* only dynamic ids */
-	.probe		= vfio_pci_probe,
-	.remove		= vfio_pci_remove,
-	.err_handler	= &vfio_err_handlers,
+	.name			= "vfio-pci",
+	.id_table		= NULL, /* only dynamic ids */
+	.probe			= vfio_pci_probe,
+	.remove			= vfio_pci_remove,
+	.sriov_configure	= vfio_pci_sriov_configure,
+	.err_handler		= &vfio_err_handlers,
 };
 
 static DEFINE_MUTEX(reflck_lock);

drivers/vfio/pci/vfio_pci_nvlink2.c

@@ -422,8 +422,14 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
 
 	if (of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", nvlink_index,
 			&mmio_atsd)) {
-		dev_warn(&vdev->pdev->dev, "No available ATSD found\n");
-		mmio_atsd = 0;
+		if (of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", 0,
+				&mmio_atsd)) {
+			dev_warn(&vdev->pdev->dev, "No available ATSD found\n");
+			mmio_atsd = 0;
+		} else {
+			dev_warn(&vdev->pdev->dev,
+				 "Using fallback ibm,mmio-atsd[0] for ATSD.\n");
+		}
 	}
 
 	if (of_property_read_u64(npu_node, "ibm,device-tgt-addr", &tgt)) {

drivers/vfio/pci/vfio_pci_private.h

@@ -12,6 +12,8 @@
 #include <linux/pci.h>
 #include <linux/irqbypass.h>
 #include <linux/types.h>
+#include <linux/uuid.h>
+#include <linux/notifier.h>
 
 #ifndef VFIO_PCI_PRIVATE_H
 #define VFIO_PCI_PRIVATE_H
@@ -84,6 +86,12 @@ struct vfio_pci_reflck {
 	struct mutex		lock;
 };
 
+struct vfio_pci_vf_token {
+	struct mutex		lock;
+	uuid_t			uuid;
+	int			users;
+};
+
 struct vfio_pci_device {
 	struct pci_dev		*pdev;
 	void __iomem		*barmap[PCI_STD_NUM_BARS];
@@ -122,6 +130,8 @@ struct vfio_pci_device {
 	struct list_head	dummy_resources_list;
 	struct mutex		ioeventfds_lock;
 	struct list_head	ioeventfds_list;
+	struct vfio_pci_vf_token	*vf_token;
+	struct notifier_block	nb;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)

drivers/vfio/platform/vfio_platform.c

@@ -44,7 +44,7 @@ static int get_platform_irq(struct vfio_platform_device *vdev, int i)
 {
 	struct platform_device *pdev = (struct platform_device *) vdev->opaque;
 
-	return platform_get_irq(pdev, i);
+	return platform_get_irq_optional(pdev, i);
 }
 
 static int vfio_platform_probe(struct platform_device *pdev)

drivers/vfio/vfio.c

@@ -875,11 +875,23 @@ EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
 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) {
 			device = it;
 			vfio_device_get(device);
 			break;
@@ -1430,8 +1442,8 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 		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) {
@@ -1720,6 +1732,44 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep)
 }
 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)
 {
 	vfio_group_try_dissolve_container(group);
@@ -1961,6 +2011,146 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
 }
 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 (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,
+					     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,
 					struct notifier_block *nb)

drivers/vfio/vfio_iommu_type1.c

@@ -27,6 +27,7 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/rbtree.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
@@ -1786,7 +1787,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 
 	if (resv_msi) {
 		ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
-		if (ret)
+		if (ret && ret != -ENODEV)
 			goto out_detach;
 	}
 
@@ -2305,6 +2306,80 @@ static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
 	return blocking_notifier_chain_unregister(&iommu->notifier, nb);
 }
 
+static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
+					 dma_addr_t user_iova, void *data,
+					 size_t count, bool write,
+					 size_t *copied)
+{
+	struct mm_struct *mm;
+	unsigned long vaddr;
+	struct vfio_dma *dma;
+	bool kthread = current->mm == NULL;
+	size_t offset;
+
+	*copied = 0;
+
+	dma = vfio_find_dma(iommu, user_iova, 1);
+	if (!dma)
+		return -EINVAL;
+
+	if ((write && !(dma->prot & IOMMU_WRITE)) ||
+			!(dma->prot & IOMMU_READ))
+		return -EPERM;
+
+	mm = get_task_mm(dma->task);
+
+	if (!mm)
+		return -EPERM;
+
+	if (kthread)
+		use_mm(mm);
+	else if (current->mm != mm)
+		goto out;
+
+	offset = user_iova - dma->iova;
+
+	if (count > dma->size - offset)
+		count = dma->size - offset;
+
+	vaddr = dma->vaddr + offset;
+
+	if (write)
+		*copied = __copy_to_user((void __user *)vaddr, data,
+					 count) ? 0 : count;
+	else
+		*copied = __copy_from_user(data, (void __user *)vaddr,
+					   count) ? 0 : count;
+	if (kthread)
+		unuse_mm(mm);
+out:
+	mmput(mm);
+	return *copied ? 0 : -EFAULT;
+}
+
+static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova,
+				   void *data, size_t count, bool write)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	int ret = 0;
+	size_t done;
+
+	mutex_lock(&iommu->lock);
+	while (count > 0) {
+		ret = vfio_iommu_type1_dma_rw_chunk(iommu, user_iova, data,
+						    count, write, &done);
+		if (ret)
+			break;
+
+		count -= done;
+		data += done;
+		user_iova += done;
+	}
+
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.name			= "vfio-iommu-type1",
 	.owner			= THIS_MODULE,
@@ -2317,6 +2392,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.unpin_pages		= vfio_iommu_type1_unpin_pages,
 	.register_notifier	= vfio_iommu_type1_register_notifier,
 	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
+	.dma_rw			= vfio_iommu_type1_dma_rw,
 };
 
 static int __init vfio_iommu_type1_init(void)

include/linux/vfio.h

@@ -26,6 +26,9 @@
  *         operations documented below
  * @mmap: Perform mmap(2) on a region of the device file descriptor
  * @request: Request for the bus driver to release the device
+ * @match: Optional device name match callback (return: 0 for no-match, >0 for
+ *         match, -errno for abort (ex. match with insufficient or incorrect
+ *         additional args)
  */
 struct vfio_device_ops {
 	char	*name;
@@ -39,6 +42,7 @@ struct vfio_device_ops {
 			 unsigned long arg);
 	int	(*mmap)(void *device_data, struct vm_area_struct *vma);
 	void	(*request)(void *device_data, unsigned int count);
+	int	(*match)(void *device_data, char *buf);
 };
 
 extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
@@ -82,6 +86,8 @@ struct vfio_iommu_driver_ops {
 					     struct notifier_block *nb);
 	int		(*unregister_notifier)(void *iommu_data,
 					       struct notifier_block *nb);
+	int		(*dma_rw)(void *iommu_data, dma_addr_t user_iova,
+				  void *data, size_t count, bool write);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -94,6 +100,8 @@ extern void vfio_unregister_iommu_driver(
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
+extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device
+								*dev);
 extern bool vfio_external_group_match_file(struct vfio_group *group,
 					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
@@ -107,6 +115,15 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
 extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
 			    int npage);
 
+extern int vfio_group_pin_pages(struct vfio_group *group,
+				unsigned long *user_iova_pfn, int npage,
+				int prot, unsigned long *phys_pfn);
+extern int vfio_group_unpin_pages(struct vfio_group *group,
+				  unsigned long *user_iova_pfn, int npage);
+
+extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
+		       void *data, size_t len, bool write);
+
 /* each type has independent events */
 enum vfio_notify_type {
 	VFIO_IOMMU_NOTIFY = 0,

include/uapi/linux/vfio.h

@@ -707,6 +707,43 @@ struct vfio_device_ioeventfd {
 
 #define VFIO_DEVICE_IOEVENTFD		_IO(VFIO_TYPE, VFIO_BASE + 16)
 
+/**
+ * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17,
+ *			       struct vfio_device_feature)
+ *
+ * Get, set, or probe feature data of the device.  The feature is selected
+ * using the FEATURE_MASK portion of the flags field.  Support for a feature
+ * can be probed by setting both the FEATURE_MASK and PROBE bits.  A probe
+ * may optionally include the GET and/or SET bits to determine read vs write
+ * access of the feature respectively.  Probing a feature will return success
+ * if the feature is supported and all of the optionally indicated GET/SET
+ * methods are supported.  The format of the data portion of the structure is
+ * specific to the given feature.  The data portion is not required for
+ * probing.  GET and SET are mutually exclusive, except for use with PROBE.
+ *
+ * Return 0 on success, -errno on failure.
+ */
+struct vfio_device_feature {
+	__u32	argsz;
+	__u32	flags;
+#define VFIO_DEVICE_FEATURE_MASK	(0xffff) /* 16-bit feature index */
+#define VFIO_DEVICE_FEATURE_GET		(1 << 16) /* Get feature into data[] */
+#define VFIO_DEVICE_FEATURE_SET		(1 << 17) /* Set feature from data[] */
+#define VFIO_DEVICE_FEATURE_PROBE	(1 << 18) /* Probe feature support */
+	__u8	data[];
+};
+
+#define VFIO_DEVICE_FEATURE		_IO(VFIO_TYPE, VFIO_BASE + 17)
+
+/*
+ * Provide support for setting a PCI VF Token, which is used as a shared
+ * secret between PF and VF drivers.  This feature may only be set on a
+ * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing
+ * open VFs.  Data provided when setting this feature is a 16-byte array
+ * (__u8 b[16]), representing a UUID.
+ */
+#define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN	(0)
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**