Merge tag 'vfio-v5.14-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Module reference fixes, structure renaming (Max Gurtovoy)

 - Export and use common pci_dev_trylock() (Luis Chamberlain)

 - Enable direct mdev device creation and probing by parent (Christoph
   Hellwig & Jason Gunthorpe)

 - Fix mdpy error path leak (Colin Ian King)

 - Fix mtty list entry leak (Jason Gunthorpe)

 - Enforce mtty device limit (Alex Williamson)

 - Resolve concurrent vfio-pci mmap faults (Alex Williamson)

* tag 'vfio-v5.14-rc1' of git://github.com/awilliam/linux-vfio:
  vfio/pci: Handle concurrent vma faults
  vfio/mtty: Enforce available_instances
  vfio/mtty: Delete mdev_devices_list
  vfio: use the new pci_dev_trylock() helper to simplify try lock
  PCI: Export pci_dev_trylock() and pci_dev_unlock()
  vfio/mdpy: Fix memory leak of object mdev_state->vconfig
  vfio/iommu_type1: rename vfio_group struck to vfio_iommu_group
  vfio/mbochs: Convert to use vfio_register_group_dev()
  vfio/mdpy: Convert to use vfio_register_group_dev()
  vfio/mtty: Convert to use vfio_register_group_dev()
  vfio/mdev: Allow the mdev_parent_ops to specify the device driver to bind
  vfio/mdev: Remove CONFIG_VFIO_MDEV_DEVICE
  driver core: Export device_driver_attach()
  driver core: Don't return EPROBE_DEFER to userspace during sysfs bind
  driver core: Flow the return code from ->probe() through to sysfs bind
  driver core: Better distinguish probe errors in really_probe
  driver core: Pull required checks into driver_probe_device()
  vfio/platform: remove unneeded parent_module attribute
  vfio: centralize module refcount in subsystem layer

19 files changed, 220 insertions, 210 deletions

diff --git a/drivers/base/base.h b/drivers/base/base.h
index e5f9b7e656c3..404db83ee5ec 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -152,7 +152,6 @@ extern int driver_add_groups(struct device_driver *drv,
 			     const struct attribute_group **groups);
 extern void driver_remove_groups(struct device_driver *drv,
 				 const struct attribute_group **groups);
-int device_driver_attach(struct device_driver *drv, struct device *dev);
 void device_driver_detach(struct device *dev);
 
 extern char *make_class_name(const char *name, struct kobject *kobj);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 36d0c654ea61..1f6b4bd61056 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -210,15 +210,11 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf,
 	int err = -ENODEV;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
-	if (dev && dev->driver == NULL && driver_match_device(drv, dev)) {
+	if (dev && driver_match_device(drv, dev)) {
 		err = device_driver_attach(drv, dev);
-
-		if (err > 0) {
+		if (!err) {
 			/* success */
 			err = count;
-		} else if (err == 0) {
-			/* driver didn't accept device */
-			err = -ENODEV;
 		}
 	}
 	put_device(dev);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index ecd7cf848daf..daeb9b5763ae 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -471,6 +471,8 @@ static void driver_sysfs_remove(struct device *dev)
  * (It is ok to call with no other effort from a driver's probe() method.)
  *
  * This function must be called with the device lock held.
+ *
+ * Callers should prefer to use device_driver_attach() instead.
  */
 int device_bind_driver(struct device *dev)
 {
@@ -491,15 +493,6 @@ EXPORT_SYMBOL_GPL(device_bind_driver);
 static atomic_t probe_count = ATOMIC_INIT(0);
 static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
 
-static void driver_deferred_probe_add_trigger(struct device *dev,
-					      int local_trigger_count)
-{
-	driver_deferred_probe_add(dev);
-	/* Did a trigger occur while probing? Need to re-trigger if yes */
-	if (local_trigger_count != atomic_read(&deferred_trigger_count))
-		driver_deferred_probe_trigger();
-}
-
 static ssize_t state_synced_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
@@ -513,12 +506,43 @@ static ssize_t state_synced_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(state_synced);
 
+
+static int call_driver_probe(struct device *dev, struct device_driver *drv)
+{
+	int ret = 0;
+
+	if (dev->bus->probe)
+		ret = dev->bus->probe(dev);
+	else if (drv->probe)
+		ret = drv->probe(dev);
+
+	switch (ret) {
+	case 0:
+		break;
+	case -EPROBE_DEFER:
+		/* Driver requested deferred probing */
+		dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name);
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		pr_debug("%s: probe of %s rejects match %d\n",
+			 drv->name, dev_name(dev), ret);
+		break;
+	default:
+		/* driver matched but the probe failed */
+		pr_warn("%s: probe of %s failed with error %d\n",
+			drv->name, dev_name(dev), ret);
+		break;
+	}
+
+	return ret;
+}
+
 static int really_probe(struct device *dev, struct device_driver *drv)
 {
-	int ret = -EPROBE_DEFER;
-	int local_trigger_count = atomic_read(&deferred_trigger_count);
 	bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) &&
 			   !drv->suppress_bind_attrs;
+	int ret;
 
 	if (defer_all_probes) {
 		/*
@@ -527,17 +551,13 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 		 * wait_for_device_probe() right after that to avoid any races.
 		 */
 		dev_dbg(dev, "Driver %s force probe deferral\n", drv->name);
-		driver_deferred_probe_add(dev);
-		return ret;
+		return -EPROBE_DEFER;
 	}
 
 	ret = device_links_check_suppliers(dev);
-	if (ret == -EPROBE_DEFER)
-		driver_deferred_probe_add_trigger(dev, local_trigger_count);
 	if (ret)
 		return ret;
 
-	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
 		 drv->bus->name, __func__, drv->name, dev_name(dev));
 	if (!list_empty(&dev->devres_head)) {
@@ -572,14 +592,14 @@ re_probe:
 			goto probe_failed;
 	}
 
-	if (dev->bus->probe) {
-		ret = dev->bus->probe(dev);
-		if (ret)
-			goto probe_failed;
-	} else if (drv->probe) {
-		ret = drv->probe(dev);
-		if (ret)
-			goto probe_failed;
+	ret = call_driver_probe(dev, drv);
+	if (ret) {
+		/*
+		 * Return probe errors as positive values so that the callers
+		 * can distinguish them from other errors.
+		 */
+		ret = -ret;
+		goto probe_failed;
 	}
 
 	if (device_add_groups(dev, drv->dev_groups)) {
@@ -621,7 +641,6 @@ re_probe:
 		dev->pm_domain->sync(dev);
 
 	driver_bound(dev);
-	ret = 1;
 	pr_debug("bus: '%s': %s: bound device %s to driver %s\n",
 		 drv->bus->name, __func__, dev_name(dev), drv->name);
 	goto done;
@@ -650,31 +669,7 @@ pinctrl_bind_failed:
 		dev->pm_domain->dismiss(dev);
 	pm_runtime_reinit(dev);
 	dev_pm_set_driver_flags(dev, 0);
-
-	switch (ret) {
-	case -EPROBE_DEFER:
-		/* Driver requested deferred probing */
-		dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name);
-		driver_deferred_probe_add_trigger(dev, local_trigger_count);
-		break;
-	case -ENODEV:
-	case -ENXIO:
-		pr_debug("%s: probe of %s rejects match %d\n",
-			 drv->name, dev_name(dev), ret);
-		break;
-	default:
-		/* driver matched but the probe failed */
-		pr_warn("%s: probe of %s failed with error %d\n",
-			drv->name, dev_name(dev), ret);
-	}
-	/*
-	 * Ignore errors returned by ->probe so that the next driver can try
-	 * its luck.
-	 */
-	ret = 0;
 done:
-	atomic_dec(&probe_count);
-	wake_up_all(&probe_waitqueue);
 	return ret;
 }
 
@@ -728,25 +723,14 @@ void wait_for_device_probe(void)
 }
 EXPORT_SYMBOL_GPL(wait_for_device_probe);
 
-/**
- * driver_probe_device - attempt to bind device & driver together
- * @drv: driver to bind a device to
- * @dev: device to try to bind to the driver
- *
- * This function returns -ENODEV if the device is not registered,
- * 1 if the device is bound successfully and 0 otherwise.
- *
- * This function must be called with @dev lock held.  When called for a
- * USB interface, @dev->parent lock must be held as well.
- *
- * If the device has a parent, runtime-resume the parent before driver probing.
- */
-static int driver_probe_device(struct device_driver *drv, struct device *dev)
+static int __driver_probe_device(struct device_driver *drv, struct device *dev)
 {
 	int ret = 0;
 
-	if (!device_is_registered(dev))
+	if (dev->p->dead || !device_is_registered(dev))
 		return -ENODEV;
+	if (dev->driver)
+		return -EBUSY;
 
 	dev->can_match = true;
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
@@ -770,6 +754,42 @@ static int driver_probe_device(struct device_driver *drv, struct device *dev)
 	return ret;
 }
 
+/**
+ * driver_probe_device - attempt to bind device & driver together
+ * @drv: driver to bind a device to
+ * @dev: device to try to bind to the driver
+ *
+ * This function returns -ENODEV if the device is not registered, -EBUSY if it
+ * already has a driver, 0 if the device is bound successfully and a positive
+ * (inverted) error code for failures from the ->probe method.
+ *
+ * This function must be called with @dev lock held.  When called for a
+ * USB interface, @dev->parent lock must be held as well.
+ *
+ * If the device has a parent, runtime-resume the parent before driver probing.
+ */
+static int driver_probe_device(struct device_driver *drv, struct device *dev)
+{
+	int trigger_count = atomic_read(&deferred_trigger_count);
+	int ret;
+
+	atomic_inc(&probe_count);
+	ret = __driver_probe_device(drv, dev);
+	if (ret == -EPROBE_DEFER || ret == EPROBE_DEFER) {
+		driver_deferred_probe_add(dev);
+
+		/*
+		 * Did a trigger occur while probing? Need to re-trigger if yes
+		 */
+		if (trigger_count != atomic_read(&deferred_trigger_count) &&
+		    !defer_all_probes)
+			driver_deferred_probe_trigger();
+	}
+	atomic_dec(&probe_count);
+	wake_up_all(&probe_waitqueue);
+	return ret;
+}
+
 static inline bool cmdline_requested_async_probing(const char *drv_name)
 {
 	return parse_option_str(async_probe_drv_names, drv_name);
@@ -867,7 +887,14 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 	if (data->check_async && async_allowed != data->want_async)
 		return 0;
 
-	return driver_probe_device(drv, dev);
+	/*
+	 * Ignore errors returned by ->probe so that the next driver can try
+	 * its luck.
+	 */
+	ret = driver_probe_device(drv, dev);
+	if (ret < 0)
+		return ret;
+	return ret == 0;
 }
 
 static void __device_attach_async_helper(void *_dev, async_cookie_t cookie)
@@ -1023,43 +1050,34 @@ static void __device_driver_unlock(struct device *dev, struct device *parent)
  * @dev: Device to attach it to
  *
  * Manually attach driver to a device. Will acquire both @dev lock and
- * @dev->parent lock if needed.
+ * @dev->parent lock if needed. Returns 0 on success, -ERR on failure.
  */
 int device_driver_attach(struct device_driver *drv, struct device *dev)
 {
-	int ret = 0;
+	int ret;
 
 	__device_driver_lock(dev, dev->parent);
-
-	/*
-	 * If device has been removed or someone has already successfully
-	 * bound a driver before us just skip the driver probe call.
-	 */
-	if (!dev->p->dead && !dev->driver)
-		ret = driver_probe_device(drv, dev);
-
+	ret = __driver_probe_device(drv, dev);
 	__device_driver_unlock(dev, dev->parent);
 
+	/* also return probe errors as normal negative errnos */
+	if (ret > 0)
+		ret = -ret;
+	if (ret == -EPROBE_DEFER)
+		return -EAGAIN;
 	return ret;
 }
+EXPORT_SYMBOL_GPL(device_driver_attach);
 
 static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie)
 {
 	struct device *dev = _dev;
 	struct device_driver *drv;
-	int ret = 0;
+	int ret;
 
 	__device_driver_lock(dev, dev->parent);
-
 	drv = dev->p->async_driver;
-
-	/*
-	 * If device has been removed or someone has already successfully
-	 * bound a driver before us just skip the driver probe call.
-	 */
-	if (!dev->p->dead && !dev->driver)
-		ret = driver_probe_device(drv, dev);
-
+	ret = driver_probe_device(drv, dev);
 	__device_driver_unlock(dev, dev->parent);
 
 	dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret);
@@ -1114,7 +1132,9 @@ static int __driver_attach(struct device *dev, void *data)
 		return 0;
 	}
 
-	device_driver_attach(drv, dev);
+	__device_driver_lock(dev, dev->parent);
+	driver_probe_device(drv, dev);
+	__device_driver_unlock(dev, dev->parent);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b63d374dff23..f960f5d7664e 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -125,7 +125,7 @@ config DRM_I915_GVT_KVMGT
 	tristate "Enable KVM/VFIO support for Intel GVT-g"
 	depends on DRM_I915_GVT
 	depends on KVM
-	depends on VFIO_MDEV && VFIO_MDEV_DEVICE
+	depends on VFIO_MDEV
 	default n
 	help
 	  Choose this option if you want to enable KVMGT support for
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8d4ebe095d0c..e3bb0d073352 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5038,7 +5038,7 @@ static void pci_dev_lock(struct pci_dev *dev)
 }
 
 /* Return 1 on successful lock, 0 on contention */
-static int pci_dev_trylock(struct pci_dev *dev)
+int pci_dev_trylock(struct pci_dev *dev)
 {
 	if (pci_cfg_access_trylock(dev)) {
 		if (device_trylock(&dev->dev))
@@ -5048,12 +5048,14 @@ static int pci_dev_trylock(struct pci_dev *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_dev_trylock);
 
-static void pci_dev_unlock(struct pci_dev *dev)
+void pci_dev_unlock(struct pci_dev *dev)
 {
 	device_unlock(&dev->dev);
 	pci_cfg_access_unlock(dev);
 }
+EXPORT_SYMBOL_GPL(pci_dev_unlock);
 
 static void pci_dev_save_and_disable(struct pci_dev *dev)
 {
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index 980e59551301..90cad109583b 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -140,26 +140,18 @@ static int vfio_fsl_mc_open(struct vfio_device *core_vdev)
 {
 	struct vfio_fsl_mc_device *vdev =
 		container_of(core_vdev, struct vfio_fsl_mc_device, vdev);
-	int ret;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
+	int ret = 0;
 
 	mutex_lock(&vdev->reflck->lock);
 	if (!vdev->refcnt) {
 		ret = vfio_fsl_mc_regions_init(vdev);
 		if (ret)
-			goto err_reg_init;
+			goto out;
 	}
 	vdev->refcnt++;
-
+out:
 	mutex_unlock(&vdev->reflck->lock);
 
-	return 0;
-
-err_reg_init:
-	mutex_unlock(&vdev->reflck->lock);
-	module_put(THIS_MODULE);
 	return ret;
 }
 
@@ -196,8 +188,6 @@ static void vfio_fsl_mc_release(struct vfio_device *core_vdev)
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
-
-	module_put(THIS_MODULE);
 }
 
 static long vfio_fsl_mc_ioctl(struct vfio_device *core_vdev,
diff --git a/drivers/vfio/mdev/Kconfig b/drivers/vfio/mdev/Kconfig
index 5da27f2100f9..763c877a1318 100644
--- a/drivers/vfio/mdev/Kconfig
+++ b/drivers/vfio/mdev/Kconfig
@@ -9,10 +9,3 @@ config VFIO_MDEV
 	  See Documentation/driver-api/vfio-mediated-device.rst for more details.
 
 	  If you don't know what do here, say N.
-
-config VFIO_MDEV_DEVICE
-	tristate "VFIO driver for Mediated devices"
-	depends on VFIO && VFIO_MDEV
-	default n
-	help
-	  VFIO based driver for Mediated devices.
diff --git a/drivers/vfio/mdev/Makefile b/drivers/vfio/mdev/Makefile
index 101516fdf375..ff9ecd802125 100644
--- a/drivers/vfio/mdev/Makefile
+++ b/drivers/vfio/mdev/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o
+mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o vfio_mdev.o
 
 obj-$(CONFIG_VFIO_MDEV) += mdev.o
-obj-$(CONFIG_VFIO_MDEV_DEVICE) += vfio_mdev.o
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index 2a85d6fcb7dd..e4581ec093a6 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -94,9 +94,11 @@ static void mdev_device_remove_common(struct mdev_device *mdev)
 	mdev_remove_sysfs_files(mdev);
 	device_del(&mdev->dev);
 	lockdep_assert_held(&parent->unreg_sem);
-	ret = parent->ops->remove(mdev);
-	if (ret)
-		dev_err(&mdev->dev, "Remove failed: err=%d\n", ret);
+	if (parent->ops->remove) {
+		ret = parent->ops->remove(mdev);
+		if (ret)
+			dev_err(&mdev->dev, "Remove failed: err=%d\n", ret);
+	}
 
 	/* Balances with device_initialize() */
 	put_device(&mdev->dev);
@@ -127,7 +129,9 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	char *envp[] = { env_string, NULL };
 
 	/* check for mandatory ops */
-	if (!ops || !ops->create || !ops->remove || !ops->supported_type_groups)
+	if (!ops || !ops->supported_type_groups)
+		return -EINVAL;
+	if (!ops->device_driver && (!ops->create || !ops->remove))
 		return -EINVAL;
 
 	dev = get_device(dev);
@@ -256,6 +260,7 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 	int ret;
 	struct mdev_device *mdev, *tmp;
 	struct mdev_parent *parent = type->parent;
+	struct mdev_driver *drv = parent->ops->device_driver;
 
 	mutex_lock(&mdev_list_lock);
 
@@ -296,14 +301,22 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 		goto out_put_device;
 	}
 
-	ret = parent->ops->create(mdev);
-	if (ret)
-		goto out_unlock;
+	if (parent->ops->create) {
+		ret = parent->ops->create(mdev);
+		if (ret)
+			goto out_unlock;
+	}
 
 	ret = device_add(&mdev->dev);
 	if (ret)
 		goto out_remove;
 
+	if (!drv)
+		drv = &vfio_mdev_driver;
+	ret = device_driver_attach(&drv->driver, &mdev->dev);
+	if (ret)
+		goto out_del;
+
 	ret = mdev_create_sysfs_files(mdev);
 	if (ret)
 		goto out_del;
@@ -317,7 +330,8 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 out_del:
 	device_del(&mdev->dev);
 out_remove:
-	parent->ops->remove(mdev);
+	if (parent->ops->remove)
+		parent->ops->remove(mdev);
 out_unlock:
 	up_read(&parent->unreg_sem);
 out_put_device:
@@ -360,11 +374,24 @@ int mdev_device_remove(struct mdev_device *mdev)
 
 static int __init mdev_init(void)
 {
-	return mdev_bus_register();
+	int rc;
+
+	rc = mdev_bus_register();
+	if (rc)
+		return rc;
+	rc = mdev_register_driver(&vfio_mdev_driver);
+	if (rc)
+		goto err_bus;
+	return 0;
+err_bus:
+	mdev_bus_unregister();
+	return rc;
 }
 
 static void __exit mdev_exit(void)
 {
+	mdev_unregister_driver(&vfio_mdev_driver);
+
 	if (mdev_bus_compat_class)
 		class_compat_unregister(mdev_bus_compat_class);
 
@@ -378,4 +405,3 @@ MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_SOFTDEP("post: vfio_mdev");
diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c
index 041699571b7e..c368ec824e2b 100644
--- a/drivers/vfio/mdev/mdev_driver.c
+++ b/drivers/vfio/mdev/mdev_driver.c
@@ -71,10 +71,20 @@ static int mdev_remove(struct device *dev)
 	return 0;
 }
 
+static int mdev_match(struct device *dev, struct device_driver *drv)
+{
+	/*
+	 * No drivers automatically match. Drivers are only bound by explicit
+	 * device_driver_attach()
+	 */
+	return 0;
+}
+
 struct bus_type mdev_bus_type = {
 	.name		= "mdev",
 	.probe		= mdev_probe,
 	.remove		= mdev_remove,
+	.match		= mdev_match,
 };
 EXPORT_SYMBOL_GPL(mdev_bus_type);
 
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index 6999c89db7b1..afbad7b0a14a 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -37,6 +37,8 @@ struct mdev_type {
 #define to_mdev_type(_kobj)		\
 	container_of(_kobj, struct mdev_type, kobj)
 
+extern struct mdev_driver vfio_mdev_driver;
+
 int  parent_create_sysfs_files(struct mdev_parent *parent);
 void parent_remove_sysfs_files(struct mdev_parent *parent);
 
diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c
index 922729071c5a..39ef7489fe47 100644
--- a/drivers/vfio/mdev/vfio_mdev.c
+++ b/drivers/vfio/mdev/vfio_mdev.c
@@ -17,28 +17,15 @@
 
 #include "mdev_private.h"
 
-#define DRIVER_VERSION  "0.1"
-#define DRIVER_AUTHOR   "NVIDIA Corporation"
-#define DRIVER_DESC     "VFIO based driver for Mediated device"
-
 static int vfio_mdev_open(struct vfio_device *core_vdev)
 {
 	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
 	struct mdev_parent *parent = mdev->type->parent;
 
-	int ret;
-
 	if (unlikely(!parent->ops->open))
 		return -EINVAL;
 
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
-
-	ret = parent->ops->open(mdev);
-	if (ret)
-		module_put(THIS_MODULE);
-
-	return ret;
+	return parent->ops->open(mdev);
 }
 
 static void vfio_mdev_release(struct vfio_device *core_vdev)
@@ -48,8 +35,6 @@ static void vfio_mdev_release(struct vfio_device *core_vdev)
 
 	if (likely(parent->ops->release))
 		parent->ops->release(mdev);
-
-	module_put(THIS_MODULE);
 }
 
 static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev,
@@ -151,7 +136,7 @@ static void vfio_mdev_remove(struct mdev_device *mdev)
 	kfree(vdev);
 }
 
-static struct mdev_driver vfio_mdev_driver = {
+struct mdev_driver vfio_mdev_driver = {
 	.driver = {
 		.name = "vfio_mdev",
 		.owner = THIS_MODULE,
@@ -160,21 +145,3 @@ static struct mdev_driver vfio_mdev_driver = {
 	.probe	= vfio_mdev_probe,
 	.remove	= vfio_mdev_remove,
 };
-
-static int __init vfio_mdev_init(void)
-{
-	return mdev_register_driver(&vfio_mdev_driver);
-}
-
-static void __exit vfio_mdev_exit(void)
-{
-	mdev_unregister_driver(&vfio_mdev_driver);
-}
-
-module_init(vfio_mdev_init)
-module_exit(vfio_mdev_exit)
-
-MODULE_VERSION(DRIVER_VERSION);
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index bd7c482c948a..318864d52837 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -477,13 +477,10 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	 * We can not use the "try" reset interface here, which will
 	 * overwrite the previously restored configuration information.
 	 */
-	if (vdev->reset_works && pci_cfg_access_trylock(pdev)) {
-		if (device_trylock(&pdev->dev)) {
-			if (!__pci_reset_function_locked(pdev))
-				vdev->needs_reset = false;
-			device_unlock(&pdev->dev);
-		}
-		pci_cfg_access_unlock(pdev);
+	if (vdev->reset_works && pci_dev_trylock(pdev)) {
+		if (!__pci_reset_function_locked(pdev))
+			vdev->needs_reset = false;
+		pci_dev_unlock(pdev);
 	}
 
 	pci_restore_state(pdev);
@@ -558,8 +555,6 @@ static void vfio_pci_release(struct vfio_device *core_vdev)
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
-
-	module_put(THIS_MODULE);
 }
 
 static int vfio_pci_open(struct vfio_device *core_vdev)
@@ -568,9 +563,6 @@ static int vfio_pci_open(struct vfio_device *core_vdev)
 		container_of(core_vdev, struct vfio_pci_device, vdev);
 	int ret = 0;
 
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
-
 	mutex_lock(&vdev->reflck->lock);
 
 	if (!vdev->refcnt) {
@@ -584,8 +576,6 @@ static int vfio_pci_open(struct vfio_device *core_vdev)
 	vdev->refcnt++;
 error:
 	mutex_unlock(&vdev->reflck->lock);
-	if (ret)
-		module_put(THIS_MODULE);
 	return ret;
 }
 
@@ -1594,6 +1584,7 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 
 	mutex_lock(&vdev->vma_lock);
@@ -1601,24 +1592,36 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 
 	if (!__vfio_pci_memory_enabled(vdev)) {
 		ret = VM_FAULT_SIGBUS;
-		mutex_unlock(&vdev->vma_lock);
 		goto up_out;
 	}
 
-	if (__vfio_pci_add_vma(vdev, vma)) {
-		ret = VM_FAULT_OOM;
-		mutex_unlock(&vdev->vma_lock);
-		goto up_out;
+	/*
+	 * We populate the whole vma on fault, so we need to test whether
+	 * the vma has already been mapped, such as for concurrent faults
+	 * to the same vma.  io_remap_pfn_range() will trigger a BUG_ON if
+	 * we ask it to fill the same range again.
+	 */
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma)
+			goto up_out;
 	}
 
-	mutex_unlock(&vdev->vma_lock);
-
 	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			       vma->vm_end - vma->vm_start, vma->vm_page_prot))
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot)) {
 		ret = VM_FAULT_SIGBUS;
+		zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+	}
 
 up_out:
 	up_read(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
 	return ret;
 }
 
diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c
index f970eb2a999f..badfffea14fb 100644
--- a/drivers/vfio/platform/vfio_amba.c
+++ b/drivers/vfio/platform/vfio_amba.c
@@ -59,7 +59,6 @@ static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id)
 	vdev->flags = VFIO_DEVICE_FLAGS_AMBA;
 	vdev->get_resource = get_amba_resource;
 	vdev->get_irq = get_amba_irq;
-	vdev->parent_module = THIS_MODULE;
 	vdev->reset_required = false;
 
 	ret = vfio_platform_probe_common(vdev, &adev->dev);
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
index e4027799a154..68a1c87066d7 100644
--- a/drivers/vfio/platform/vfio_platform.c
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -50,7 +50,6 @@ static int vfio_platform_probe(struct platform_device *pdev)
 	vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM;
 	vdev->get_resource = get_platform_resource;
 	vdev->get_irq = get_platform_irq;
-	vdev->parent_module = THIS_MODULE;
 	vdev->reset_required = reset_required;
 
 	ret = vfio_platform_probe_common(vdev, &pdev->dev);
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index 470fcf7dac56..703164df7637 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -241,8 +241,6 @@ static void vfio_platform_release(struct vfio_device *core_vdev)
 	}
 
 	mutex_unlock(&driver_lock);
-
-	module_put(vdev->parent_module);
 }
 
 static int vfio_platform_open(struct vfio_device *core_vdev)
@@ -251,9 +249,6 @@ static int vfio_platform_open(struct vfio_device *core_vdev)
 		container_of(core_vdev, struct vfio_platform_device, vdev);
 	int ret;
 
-	if (!try_module_get(vdev->parent_module))
-		return -ENODEV;
-
 	mutex_lock(&driver_lock);
 
 	if (!vdev->refcnt) {
@@ -291,7 +286,6 @@ err_irq:
 	vfio_platform_regions_cleanup(vdev);
 err_reg:
 	mutex_unlock(&driver_lock);
-	module_put(vdev->parent_module);
 	return ret;
 }
 
diff --git a/drivers/vfio/platform/vfio_platform_private.h b/drivers/vfio/platform/vfio_platform_private.h
index a5ba82c8cbc3..dfb834c13659 100644
--- a/drivers/vfio/platform/vfio_platform_private.h
+++ b/drivers/vfio/platform/vfio_platform_private.h
@@ -50,7 +50,6 @@ struct vfio_platform_device {
 	u32				num_irqs;
 	int				refcnt;
 	struct mutex			igate;
-	struct module			*parent_module;
 	const char			*compat;
 	const char			*acpihid;
 	struct module			*reset_module;
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 5e631c359ef2..02cc51ce6891 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1369,8 +1369,14 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	if (IS_ERR(device))
 		return PTR_ERR(device);
 
+	if (!try_module_get(device->dev->driver->owner)) {
+		vfio_device_put(device);
+		return -ENODEV;
+	}
+
 	ret = device->ops->open(device);
 	if (ret) {
+		module_put(device->dev->driver->owner);
 		vfio_device_put(device);
 		return ret;
 	}
@@ -1382,6 +1388,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	ret = get_unused_fd_flags(O_CLOEXEC);
 	if (ret < 0) {
 		device->ops->release(device);
+		module_put(device->dev->driver->owner);
 		vfio_device_put(device);
 		return ret;
 	}
@@ -1392,6 +1399,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 		put_unused_fd(ret);
 		ret = PTR_ERR(filep);
 		device->ops->release(device);
+		module_put(device->dev->driver->owner);
 		vfio_device_put(device);
 		return ret;
 	}
@@ -1550,6 +1558,8 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)
 
 	device->ops->release(device);
 
+	module_put(device->dev->driver->owner);
+
 	vfio_group_try_dissolve_container(device->group);
 
 	vfio_device_put(device);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 4fce73a8a650..0b4f7c174c7a 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -110,7 +110,7 @@ struct vfio_batch {
 	int			offset;		/* of next entry in pages */
 };
 
-struct vfio_group {
+struct vfio_iommu_group {
 	struct iommu_group	*iommu_group;
 	struct list_head	next;
 	bool			mdev_group;	/* An mdev group */
@@ -160,8 +160,9 @@ struct vfio_regions {
 
 static int put_pfn(unsigned long pfn, int prot);
 
-static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
-					       struct iommu_group *iommu_group);
+static struct vfio_iommu_group*
+vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+			    struct iommu_group *iommu_group);
 
 /*
  * This code handles mapping and unmapping of user data buffers
@@ -836,7 +837,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 				      unsigned long *phys_pfn)
 {
 	struct vfio_iommu *iommu = iommu_data;
-	struct vfio_group *group;
+	struct vfio_iommu_group *group;
 	int i, j, ret;
 	unsigned long remote_vaddr;
 	struct vfio_dma *dma;
@@ -1875,10 +1876,10 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain)
 	__free_pages(pages, order);
 }
 
-static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
-					   struct iommu_group *iommu_group)
+static struct vfio_iommu_group *find_iommu_group(struct vfio_domain *domain,
+						 struct iommu_group *iommu_group)
 {
-	struct vfio_group *g;
+	struct vfio_iommu_group *g;
 
 	list_for_each_entry(g, &domain->group_list, next) {
 		if (g->iommu_group == iommu_group)
@@ -1888,11 +1889,12 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
-static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
-					       struct iommu_group *iommu_group)
+static struct vfio_iommu_group*
+vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+			    struct iommu_group *iommu_group)
 {
 	struct vfio_domain *domain;
-	struct vfio_group *group = NULL;
+	struct vfio_iommu_group *group = NULL;
 
 	list_for_each_entry(domain, &iommu->domain_list, next) {
 		group = find_iommu_group(domain, iommu_group);
@@ -1967,7 +1969,7 @@ static int vfio_mdev_detach_domain(struct device *dev, void *data)
 }
 
 static int vfio_iommu_attach_group(struct vfio_domain *domain,
-				   struct vfio_group *group)
+				   struct vfio_iommu_group *group)
 {
 	if (group->mdev_group)
 		return iommu_group_for_each_dev(group->iommu_group,
@@ -1978,7 +1980,7 @@ static int vfio_iommu_attach_group(struct vfio_domain *domain,
 }
 
 static void vfio_iommu_detach_group(struct vfio_domain *domain,
-				    struct vfio_group *group)
+				    struct vfio_iommu_group *group)
 {
 	if (group->mdev_group)
 		iommu_group_for_each_dev(group->iommu_group, domain->domain,
@@ -2242,7 +2244,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
 	struct vfio_iommu *iommu = iommu_data;
-	struct vfio_group *group;
+	struct vfio_iommu_group *group;
 	struct vfio_domain *domain, *d;
 	struct bus_type *bus = NULL;
 	int ret;
@@ -2518,7 +2520,7 @@ static int vfio_iommu_resv_refresh(struct vfio_iommu *iommu,
 				   struct list_head *iova_copy)
 {
 	struct vfio_domain *d;
-	struct vfio_group *g;
+	struct vfio_iommu_group *g;
 	struct vfio_iova *node;
 	dma_addr_t start, end;
 	LIST_HEAD(resv_regions);
@@ -2560,7 +2562,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_domain *domain;
-	struct vfio_group *group;
+	struct vfio_iommu_group *group;
 	bool update_dirty_scope = false;
 	LIST_HEAD(iova_copy);
 
@@ -2681,7 +2683,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 
 static void vfio_release_domain(struct vfio_domain *domain, bool external)
 {
-	struct vfio_group *group, *group_tmp;
+	struct vfio_iommu_group *group, *group_tmp;
 
 	list_for_each_entry_safe(group, group_tmp,
 				 &domain->group_list, next) {