Merge tag 'vfio-v4.10-rc3' of git://github.com/awilliam/linux-vfio

Pull VFIO fixes from Alex Williamson:
 - Add mtty sample driver properly into build system (Alex Williamson)
 - Restore type1 mapping performance after mdev (Alex Williamson)
 - Fix mdev device race (Alex Williamson)
 - Cleanups to the mdev ABI used by vendor drivers (Alex Williamson)
 - Build fix for old compilers (Arnd Bergmann)
 - Fix sample driver error path (Dan Carpenter)
 - Handle pci_iomap() error (Arvind Yadav)
 - Fix mdev ioctl return type (Paul Gortmaker)

* tag 'vfio-v4.10-rc3' of git://github.com/awilliam/linux-vfio:
  vfio-mdev: fix non-standard ioctl return val causing i386 build fail
  vfio-pci: Handle error from pci_iomap
  vfio-mdev: fix some error codes in the sample code
  vfio-pci: use 32-bit comparisons for register address for gcc-4.5
  vfio-mdev: Make mdev_device private and abstract interfaces
  vfio-mdev: Make mdev_parent private
  vfio-mdev: de-polute the namespace, rename parent_device & parent_ops
  vfio-mdev: Fix remove race
  vfio/type1: Restore mapping performance with mdev support
  vfio-mdev: Fix mtty sample driver building

Documentation/vfio-mediated-device.txt

@@ -127,22 +127,22 @@ the VFIO when devices are unbound from the driver.
 Physical Device Driver Interface
 --------------------------------
 
-The physical device driver interface provides the parent_ops[3] structure to
-define the APIs to manage work in the mediated core driver that is related to
-the physical device.
+The physical device driver interface provides the mdev_parent_ops[3] structure
+to define the APIs to manage work in the mediated core driver that is related
+to the physical device.
 
-The structures in the parent_ops structure are as follows:
+The structures in the mdev_parent_ops structure are as follows:
 
 * dev_attr_groups: attributes of the parent device
 * mdev_attr_groups: attributes of the mediated device
 * supported_config: attributes to define supported configurations
 
-The functions in the parent_ops structure are as follows:
+The functions in the mdev_parent_ops structure are as follows:
 
 * create: allocate basic resources in a driver for a mediated device
 * remove: free resources in a driver when a mediated device is destroyed
 
-The callbacks in the parent_ops structure are as follows:
+The callbacks in the mdev_parent_ops structure are as follows:
 
 * open: open callback of mediated device
 * close: close callback of mediated device
@@ -151,14 +151,14 @@ The callbacks in the parent_ops structure are as follows:
 * write: write emulation callback
 * mmap: mmap emulation callback
 
-A driver should use the parent_ops structure in the function call to register
-itself with the mdev core driver:
+A driver should use the mdev_parent_ops structure in the function call to
+register itself with the mdev core driver:
 
 extern int  mdev_register_device(struct device *dev,
-                                 const struct parent_ops *ops);
+                                 const struct mdev_parent_ops *ops);
 
-However, the parent_ops structure is not required in the function call that a
-driver should use to unregister itself with the mdev core driver:
+However, the mdev_parent_ops structure is not required in the function call
+that a driver should use to unregister itself with the mdev core driver:
 
 extern void mdev_unregister_device(struct device *dev);
 
@@ -223,6 +223,9 @@ Directories and files under the sysfs for Each Physical Device
 
 	sprintf(buf, "%s-%s", dev_driver_string(parent->dev), group->name);
 
+  (or using mdev_parent_dev(mdev) to arrive at the parent device outside
+   of the core mdev code)
+
 * device_api
 
   This attribute should show which device API is being created, for example,
@@ -394,5 +397,5 @@ References
 
 [1] See Documentation/vfio.txt for more information on VFIO.
 [2] struct mdev_driver in include/linux/mdev.h
-[3] struct parent_ops in include/linux/mdev.h
+[3] struct mdev_parent_ops in include/linux/mdev.h
 [4] struct vfio_iommu_driver_ops in include/linux/vfio.h

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -169,7 +169,7 @@ static void __gvt_cache_remove_entry(struct intel_vgpu *vgpu,
 
 static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn)
 {
-	struct device *dev = &vgpu->vdev.mdev->dev;
+	struct device *dev = mdev_dev(vgpu->vdev.mdev);
 	struct gvt_dma *this;
 	unsigned long g1;
 	int rc;
@@ -198,7 +198,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu)
 {
 	struct gvt_dma *dma;
 	struct rb_node *node = NULL;
-	struct device *dev = &vgpu->vdev.mdev->dev;
+	struct device *dev = mdev_dev(vgpu->vdev.mdev);
 	unsigned long gfn;
 
 	mutex_lock(&vgpu->vdev.cache_lock);
@@ -399,7 +399,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 	struct device *pdev;
 	void *gvt;
 
-	pdev = mdev->parent->dev;
+	pdev = mdev_parent_dev(mdev);
 	gvt = kdev_to_i915(pdev)->gvt;
 
 	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
@@ -421,7 +421,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 	mdev_set_drvdata(mdev, vgpu);
 
 	gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n",
-		     dev_name(&mdev->dev));
+		     dev_name(mdev_dev(mdev)));
 	return 0;
 }
 
@@ -485,7 +485,7 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	vgpu->vdev.group_notifier.notifier_call = intel_vgpu_group_notifier;
 
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(&mdev->dev, VFIO_IOMMU_NOTIFY, &events,
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &events,
 				&vgpu->vdev.iommu_notifier);
 	if (ret != 0) {
 		gvt_err("vfio_register_notifier for iommu failed: %d\n", ret);
@@ -493,7 +493,7 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	}
 
 	events = VFIO_GROUP_NOTIFY_SET_KVM;
-	ret = vfio_register_notifier(&mdev->dev, VFIO_GROUP_NOTIFY, &events,
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &events,
 				&vgpu->vdev.group_notifier);
 	if (ret != 0) {
 		gvt_err("vfio_register_notifier for group failed: %d\n", ret);
@@ -508,11 +508,11 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	return ret;
 
 undo_group:
-	vfio_unregister_notifier(&mdev->dev, VFIO_GROUP_NOTIFY,
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
 					&vgpu->vdev.group_notifier);
 
 undo_iommu:
-	vfio_unregister_notifier(&mdev->dev, VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 					&vgpu->vdev.iommu_notifier);
 out:
 	return ret;
@@ -529,11 +529,11 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 	if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
 		return;
 
-	ret = vfio_unregister_notifier(&vgpu->vdev.mdev->dev, VFIO_IOMMU_NOTIFY,
+	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
 					&vgpu->vdev.iommu_notifier);
 	WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
 
-	ret = vfio_unregister_notifier(&vgpu->vdev.mdev->dev, VFIO_GROUP_NOTIFY,
+	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_GROUP_NOTIFY,
 					&vgpu->vdev.group_notifier);
 	WARN(ret, "vfio_unregister_notifier for group failed: %d\n", ret);
 
@@ -1111,7 +1111,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 	return 0;
 }
 
-static const struct parent_ops intel_vgpu_ops = {
+static const struct mdev_parent_ops intel_vgpu_ops = {
 	.supported_type_groups	= intel_vgpu_type_groups,
 	.create			= intel_vgpu_create,
 	.remove			= intel_vgpu_remove,
@@ -1398,7 +1398,7 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 		return pfn;
 
 	pfn = INTEL_GVT_INVALID_ADDR;
-	dev = &info->vgpu->vdev.mdev->dev;
+	dev = mdev_dev(info->vgpu->vdev.mdev);
 	rc = vfio_pin_pages(dev, &gfn, 1, IOMMU_READ | IOMMU_WRITE, &pfn);
 	if (rc != 1) {
 		gvt_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", gfn, rc);

drivers/vfio/mdev/mdev_core.c

@@ -27,6 +27,45 @@ static LIST_HEAD(parent_list);
 static DEFINE_MUTEX(parent_list_lock);
 static struct class_compat *mdev_bus_compat_class;
 
+static LIST_HEAD(mdev_list);
+static DEFINE_MUTEX(mdev_list_lock);
+
+struct device *mdev_parent_dev(struct mdev_device *mdev)
+{
+	return mdev->parent->dev;
+}
+EXPORT_SYMBOL(mdev_parent_dev);
+
+void *mdev_get_drvdata(struct mdev_device *mdev)
+{
+	return mdev->driver_data;
+}
+EXPORT_SYMBOL(mdev_get_drvdata);
+
+void mdev_set_drvdata(struct mdev_device *mdev, void *data)
+{
+	mdev->driver_data = data;
+}
+EXPORT_SYMBOL(mdev_set_drvdata);
+
+struct device *mdev_dev(struct mdev_device *mdev)
+{
+	return &mdev->dev;
+}
+EXPORT_SYMBOL(mdev_dev);
+
+struct mdev_device *mdev_from_dev(struct device *dev)
+{
+	return dev_is_mdev(dev) ? to_mdev_device(dev) : NULL;
+}
+EXPORT_SYMBOL(mdev_from_dev);
+
+uuid_le mdev_uuid(struct mdev_device *mdev)
+{
+	return mdev->uuid;
+}
+EXPORT_SYMBOL(mdev_uuid);
+
 static int _find_mdev_device(struct device *dev, void *data)
 {
 	struct mdev_device *mdev;
@@ -42,7 +81,7 @@ static int _find_mdev_device(struct device *dev, void *data)
 	return 0;
 }
 
-static bool mdev_device_exist(struct parent_device *parent, uuid_le uuid)
+static bool mdev_device_exist(struct mdev_parent *parent, uuid_le uuid)
 {
 	struct device *dev;
 
@@ -56,9 +95,9 @@ static bool mdev_device_exist(struct parent_device *parent, uuid_le uuid)
 }
 
 /* Should be called holding parent_list_lock */
-static struct parent_device *__find_parent_device(struct device *dev)
+static struct mdev_parent *__find_parent_device(struct device *dev)
 {
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 
 	list_for_each_entry(parent, &parent_list, next) {
 		if (parent->dev == dev)
@@ -69,8 +108,8 @@ static struct parent_device *__find_parent_device(struct device *dev)
 
 static void mdev_release_parent(struct kref *kref)
 {
-	struct parent_device *parent = container_of(kref, struct parent_device,
-						    ref);
+	struct mdev_parent *parent = container_of(kref, struct mdev_parent,
+						  ref);
 	struct device *dev = parent->dev;
 
 	kfree(parent);
@@ -78,7 +117,7 @@ static void mdev_release_parent(struct kref *kref)
 }
 
 static
-inline struct parent_device *mdev_get_parent(struct parent_device *parent)
+inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_get(&parent->ref);
@@ -86,7 +125,7 @@ inline struct parent_device *mdev_get_parent(struct parent_device *parent)
 	return parent;
 }
 
-static inline void mdev_put_parent(struct parent_device *parent)
+static inline void mdev_put_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_put(&parent->ref, mdev_release_parent);
@@ -95,7 +134,7 @@ static inline void mdev_put_parent(struct parent_device *parent)
 static int mdev_device_create_ops(struct kobject *kobj,
 				  struct mdev_device *mdev)
 {
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	ret = parent->ops->create(kobj, mdev);
@@ -122,7 +161,7 @@ static int mdev_device_create_ops(struct kobject *kobj,
  */
 static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
 {
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	/*
@@ -153,10 +192,10 @@ static int mdev_device_remove_cb(struct device *dev, void *data)
  * Add device to list of registered parent devices.
  * Returns a negative value on error, otherwise 0.
  */
-int mdev_register_device(struct device *dev, const struct parent_ops *ops)
+int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 {
 	int ret;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 
 	/* check for mandatory ops */
 	if (!ops || !ops->create || !ops->remove || !ops->supported_type_groups)
@@ -229,7 +268,7 @@ EXPORT_SYMBOL(mdev_register_device);
 
 void mdev_unregister_device(struct device *dev)
 {
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	bool force_remove = true;
 
 	mutex_lock(&parent_list_lock);
@@ -266,7 +305,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 {
 	int ret;
 	struct mdev_device *mdev;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	struct mdev_type *type = to_mdev_type(kobj);
 
 	parent = mdev_get_parent(type->parent);
@@ -316,6 +355,11 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 	dev_dbg(&mdev->dev, "MDEV: created\n");
 
 	mutex_unlock(&parent->lock);
+
+	mutex_lock(&mdev_list_lock);
+	list_add(&mdev->next, &mdev_list);
+	mutex_unlock(&mdev_list_lock);
+
 	return ret;
 
 create_failed:
@@ -329,12 +373,30 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 
 int mdev_device_remove(struct device *dev, bool force_remove)
 {
-	struct mdev_device *mdev;
-	struct parent_device *parent;
+	struct mdev_device *mdev, *tmp;
+	struct mdev_parent *parent;
 	struct mdev_type *type;
 	int ret;
+	bool found = false;
 
 	mdev = to_mdev_device(dev);
+
+	mutex_lock(&mdev_list_lock);
+	list_for_each_entry(tmp, &mdev_list, next) {
+		if (tmp == mdev) {
+			found = true;
+			break;
+		}
+	}
+
+	if (found)
+		list_del(&mdev->next);
+
+	mutex_unlock(&mdev_list_lock);
+
+	if (!found)
+		return -ENODEV;
+
 	type = to_mdev_type(mdev->type_kobj);
 	parent = mdev->parent;
 	mutex_lock(&parent->lock);
@@ -342,6 +404,11 @@ int mdev_device_remove(struct device *dev, bool force_remove)
 	ret = mdev_device_remove_ops(mdev, force_remove);
 	if (ret) {
 		mutex_unlock(&parent->lock);
+
+		mutex_lock(&mdev_list_lock);
+		list_add(&mdev->next, &mdev_list);
+		mutex_unlock(&mdev_list_lock);
+
 		return ret;
 	}
 
@@ -349,7 +416,8 @@ int mdev_device_remove(struct device *dev, bool force_remove)
 	device_unregister(dev);
 	mutex_unlock(&parent->lock);
 	mdev_put_parent(parent);
-	return ret;
+
+	return 0;
 }
 
 static int __init mdev_init(void)

drivers/vfio/mdev/mdev_private.h

@@ -16,10 +16,33 @@
 int  mdev_bus_register(void);
 void mdev_bus_unregister(void);
 
+struct mdev_parent {
+	struct device *dev;
+	const struct mdev_parent_ops *ops;
+	struct kref ref;
+	struct mutex lock;
+	struct list_head next;
+	struct kset *mdev_types_kset;
+	struct list_head type_list;
+};
+
+struct mdev_device {
+	struct device dev;
+	struct mdev_parent *parent;
+	uuid_le uuid;
+	void *driver_data;
+	struct kref ref;
+	struct list_head next;
+	struct kobject *type_kobj;
+};
+
+#define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
+#define dev_is_mdev(d)		((d)->bus == &mdev_bus_type)
+
 struct mdev_type {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
-	struct parent_device *parent;
+	struct mdev_parent *parent;
 	struct list_head next;
 	struct attribute_group *group;
 };
@@ -29,8 +52,8 @@ struct mdev_type {
 #define to_mdev_type(_kobj)		\
 	container_of(_kobj, struct mdev_type, kobj)
 
-int  parent_create_sysfs_files(struct parent_device *parent);
-void parent_remove_sysfs_files(struct parent_device *parent);
+int  parent_create_sysfs_files(struct mdev_parent *parent);
+void parent_remove_sysfs_files(struct mdev_parent *parent);
 
 int  mdev_create_sysfs_files(struct device *dev, struct mdev_type *type);
 void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type);

drivers/vfio/mdev/mdev_sysfs.c

@@ -92,7 +92,7 @@ static struct kobj_type mdev_type_ktype = {
 	.release = mdev_type_release,
 };
 
-struct mdev_type *add_mdev_supported_type(struct parent_device *parent,
+struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 					  struct attribute_group *group)
 {
 	struct mdev_type *type;
@@ -158,7 +158,7 @@ static void remove_mdev_supported_type(struct mdev_type *type)
 	kobject_put(&type->kobj);
 }
 
-static int add_mdev_supported_type_groups(struct parent_device *parent)
+static int add_mdev_supported_type_groups(struct mdev_parent *parent)
 {
 	int i;
 
@@ -183,7 +183,7 @@ static int add_mdev_supported_type_groups(struct parent_device *parent)
 }
 
 /* mdev sysfs functions */
-void parent_remove_sysfs_files(struct parent_device *parent)
+void parent_remove_sysfs_files(struct mdev_parent *parent)
 {
 	struct mdev_type *type, *tmp;
 
@@ -196,7 +196,7 @@ void parent_remove_sysfs_files(struct parent_device *parent)
 	kset_unregister(parent->mdev_types_kset);
 }
 
-int parent_create_sysfs_files(struct parent_device *parent)
+int parent_create_sysfs_files(struct mdev_parent *parent)
 {
 	int ret;
 

drivers/vfio/mdev/vfio_mdev.c

@@ -27,7 +27,7 @@
 static int vfio_mdev_open(void *device_data)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 	int ret;
 
 	if (unlikely(!parent->ops->open))
@@ -46,7 +46,7 @@ static int vfio_mdev_open(void *device_data)
 static void vfio_mdev_release(void *device_data)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (likely(parent->ops->release))
 		parent->ops->release(mdev);
@@ -58,7 +58,7 @@ static long vfio_mdev_unlocked_ioctl(void *device_data,
 				     unsigned int cmd, unsigned long arg)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->ioctl))
 		return -EINVAL;
@@ -70,7 +70,7 @@ static ssize_t vfio_mdev_read(void *device_data, char __user *buf,
 			      size_t count, loff_t *ppos)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->read))
 		return -EINVAL;
@@ -82,7 +82,7 @@ static ssize_t vfio_mdev_write(void *device_data, const char __user *buf,
 			       size_t count, loff_t *ppos)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->write))
 		return -EINVAL;
@@ -93,7 +93,7 @@ static ssize_t vfio_mdev_write(void *device_data, const char __user *buf,
 static int vfio_mdev_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct mdev_device *mdev = device_data;
-	struct parent_device *parent = mdev->parent;
+	struct mdev_parent *parent = mdev->parent;
 
 	if (unlikely(!parent->ops->mmap))
 		return -EINVAL;

drivers/vfio/pci/vfio_pci.c

@@ -1142,6 +1142,10 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 			return ret;
 
 		vdev->barmap[index] = pci_iomap(pdev, index, 0);
+		if (!vdev->barmap[index]) {
+			pci_release_selected_regions(pdev, 1 << index);
+			return -ENOMEM;
+		}
 	}
 
 	vma->vm_private_data = vdev;

drivers/vfio/pci/vfio_pci_rdwr.c

@@ -193,7 +193,10 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
 	if (!vdev->has_vga)
 		return -EINVAL;
 
-	switch (pos) {
+	if (pos > 0xbfffful)
+		return -EINVAL;
+
+	switch ((u32)pos) {
 	case 0xa0000 ... 0xbffff:
 		count = min(count, (size_t)(0xc0000 - pos));
 		iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);

drivers/vfio/vfio_iommu_type1.c

@@ -268,28 +268,38 @@ static void vfio_lock_acct(struct task_struct *task, long npage)
 {
 	struct vwork *vwork;
 	struct mm_struct *mm;
+	bool is_current;
 
 	if (!npage)
 		return;
 
-	mm = get_task_mm(task);
+	is_current = (task->mm == current->mm);
+
+	mm = is_current ? task->mm : get_task_mm(task);
 	if (!mm)
-		return; /* process exited or nothing to do */
+		return; /* process exited */
 
 	if (down_write_trylock(&mm->mmap_sem)) {
 		mm->locked_vm += npage;
 		up_write(&mm->mmap_sem);
-		mmput(mm);
+		if (!is_current)
+			mmput(mm);
 		return;
 	}
 
+	if (is_current) {
+		mm = get_task_mm(task);
+		if (!mm)
+			return;
+	}
+
 	/*
 	 * Couldn't get mmap_sem lock, so must setup to update
 	 * mm->locked_vm later. If locked_vm were atomic, we
 	 * wouldn't need this silliness
 	 */
 	vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
-	if (!vwork) {
+	if (WARN_ON(!vwork)) {
 		mmput(mm);
 		return;
 	}
@@ -393,77 +403,71 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 				  long npage, unsigned long *pfn_base)
 {
-	unsigned long limit;
-	bool lock_cap = ns_capable(task_active_pid_ns(dma->task)->user_ns,
-				   CAP_IPC_LOCK);
-	struct mm_struct *mm;
-	long ret, i = 0, lock_acct = 0;
+	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	bool lock_cap = capable(CAP_IPC_LOCK);
+	long ret, pinned = 0, lock_acct = 0;
 	bool rsvd;
 	dma_addr_t iova = vaddr - dma->vaddr + dma->iova;
 
-	mm = get_task_mm(dma->task);
-	if (!mm)
+	/* This code path is only user initiated */
+	if (!current->mm)
 		return -ENODEV;
 
-	ret = vaddr_get_pfn(mm, vaddr, dma->prot, pfn_base);
+	ret = vaddr_get_pfn(current->mm, vaddr, dma->prot, pfn_base);
 	if (ret)
-		goto pin_pg_remote_exit;
+		return ret;
 
+	pinned++;
 	rsvd = is_invalid_reserved_pfn(*pfn_base);
-	limit = task_rlimit(dma->task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
 	/*
 	 * Reserved pages aren't counted against the user, externally pinned
 	 * pages are already counted against the user.
 	 */
 	if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-		if (!lock_cap && mm->locked_vm + 1 > limit) {
+		if (!lock_cap && current->mm->locked_vm + 1 > limit) {
 			put_pfn(*pfn_base, dma->prot);
 			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
 					limit << PAGE_SHIFT);
-			ret = -ENOMEM;
-			goto pin_pg_remote_exit;
+			return -ENOMEM;
 		}
 		lock_acct++;
 	}
 
-	i++;
-	if (likely(!disable_hugepages)) {
-		/* Lock all the consecutive pages from pfn_base */
-		for (vaddr += PAGE_SIZE, iova += PAGE_SIZE; i < npage;
-		     i++, vaddr += PAGE_SIZE, iova += PAGE_SIZE) {
-			unsigned long pfn = 0;
+	if (unlikely(disable_hugepages))
+		goto out;
 
-			ret = vaddr_get_pfn(mm, vaddr, dma->prot, &pfn);
-			if (ret)
-				break;
+	/* Lock all the consecutive pages from pfn_base */
+	for (vaddr += PAGE_SIZE, iova += PAGE_SIZE; pinned < npage;
+	     pinned++, vaddr += PAGE_SIZE, iova += PAGE_SIZE) {
+		unsigned long pfn = 0;
 
-			if (pfn != *pfn_base + i ||
-			    rsvd != is_invalid_reserved_pfn(pfn)) {
+		ret = vaddr_get_pfn(current->mm, vaddr, dma->prot, &pfn);
+		if (ret)
+			break;
+
+		if (pfn != *pfn_base + pinned ||
+		    rsvd != is_invalid_reserved_pfn(pfn)) {
+			put_pfn(pfn, dma->prot);
+			break;
+		}
+
+		if (!rsvd && !vfio_find_vpfn(dma, iova)) {
+			if (!lock_cap &&
+			    current->mm->locked_vm + lock_acct + 1 > limit) {
 				put_pfn(pfn, dma->prot);
+				pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
+					__func__, limit << PAGE_SHIFT);
 				break;
 			}
-
-			if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-				if (!lock_cap &&
-				    mm->locked_vm + lock_acct + 1 > limit) {
-					put_pfn(pfn, dma->prot);
-					pr_warn("%s: RLIMIT_MEMLOCK (%ld) "
-						"exceeded\n", __func__,
-						limit << PAGE_SHIFT);
-					break;
-				}
-				lock_acct++;
-			}
+			lock_acct++;
 		}
 	}
 
-	vfio_lock_acct(dma->task, lock_acct);
-	ret = i;
+out:
+	vfio_lock_acct(current, lock_acct);
 
-pin_pg_remote_exit:
-	mmput(mm);
-	return ret;
+	return pinned;
 }
 
 static long vfio_unpin_pages_remote(struct vfio_dma *dma, dma_addr_t iova,
@@ -473,10 +477,10 @@ static long vfio_unpin_pages_remote(struct vfio_dma *dma, dma_addr_t iova,
 	long unlocked = 0, locked = 0;
 	long i;
 
-	for (i = 0; i < npage; i++) {
+	for (i = 0; i < npage; i++, iova += PAGE_SIZE) {
 		if (put_pfn(pfn++, dma->prot)) {
 			unlocked++;
-			if (vfio_find_vpfn(dma, iova + (i << PAGE_SHIFT)))
+			if (vfio_find_vpfn(dma, iova))
 				locked++;
 		}
 	}

include/linux/mdev.h

@@ -13,34 +13,10 @@
 #ifndef MDEV_H
 #define MDEV_H
 
-/* Parent device */
-struct parent_device {
-	struct device		*dev;
-	const struct parent_ops	*ops;
-
-	/* internal */
-	struct kref		ref;
-	struct mutex		lock;
-	struct list_head	next;
-	struct kset		*mdev_types_kset;
-	struct list_head	type_list;
-};
-
-/* Mediated device */
-struct mdev_device {
-	struct device		dev;
-	struct parent_device	*parent;
-	uuid_le			uuid;
-	void			*driver_data;
-
-	/* internal */
-	struct kref		ref;
-	struct list_head	next;
-	struct kobject		*type_kobj;
-};
+struct mdev_device;
 
 /**
- * struct parent_ops - Structure to be registered for each parent device to
+ * struct mdev_parent_ops - Structure to be registered for each parent device to
  * register the device to mdev module.
  *
  * @owner:		The module owner.
@@ -86,10 +62,9 @@ struct mdev_device {
  *			@mdev: mediated device structure
  *			@vma: vma structure
  * Parent device that support mediated device should be registered with mdev
- * module with parent_ops structure.
+ * module with mdev_parent_ops structure.
  **/
-
-struct parent_ops {
+struct mdev_parent_ops {
 	struct module   *owner;
 	const struct attribute_group **dev_attr_groups;
 	const struct attribute_group **mdev_attr_groups;
@@ -103,7 +78,7 @@ struct parent_ops {
 			size_t count, loff_t *ppos);
 	ssize_t (*write)(struct mdev_device *mdev, const char __user *buf,
 			 size_t count, loff_t *ppos);
-	ssize_t (*ioctl)(struct mdev_device *mdev, unsigned int cmd,
+	long	(*ioctl)(struct mdev_device *mdev, unsigned int cmd,
 			 unsigned long arg);
 	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
 };
@@ -142,27 +117,22 @@ struct mdev_driver {
 };
 
 #define to_mdev_driver(drv)	container_of(drv, struct mdev_driver, driver)
-#define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
-
-static inline void *mdev_get_drvdata(struct mdev_device *mdev)
-{
-	return mdev->driver_data;
-}
 
-static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data)
-{
-	mdev->driver_data = data;
-}
+extern void *mdev_get_drvdata(struct mdev_device *mdev);
+extern void mdev_set_drvdata(struct mdev_device *mdev, void *data);
+extern uuid_le mdev_uuid(struct mdev_device *mdev);
 
 extern struct bus_type mdev_bus_type;
 
-#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type)
-
 extern int  mdev_register_device(struct device *dev,
-				 const struct parent_ops *ops);
+				 const struct mdev_parent_ops *ops);
 extern void mdev_unregister_device(struct device *dev);
 
 extern int  mdev_register_driver(struct mdev_driver *drv, struct module *owner);
 extern void mdev_unregister_driver(struct mdev_driver *drv);
 
+extern struct device *mdev_parent_dev(struct mdev_device *mdev);
+extern struct device *mdev_dev(struct mdev_device *mdev);
+extern struct mdev_device *mdev_from_dev(struct device *dev);
+
 #endif /* MDEV_H */

samples/Kconfig

@@ -105,4 +105,11 @@ config SAMPLE_BLACKFIN_GPTIMERS
 	help
 	  Build samples of blackfin gptimers sample module.
 
+config SAMPLE_VFIO_MDEV_MTTY
+	tristate "Build VFIO mtty example mediated device sample code -- loadable modules only"
+	depends on VFIO_MDEV_DEVICE && m
+	help
+	  Build a virtual tty sample driver for use as a VFIO
+	  mediated device
+
 endif # SAMPLES

samples/Makefile

@@ -2,4 +2,5 @@
 
 obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ livepatch/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
-			   configfs/ connector/ v4l/ trace_printk/ blackfin/
+			   configfs/ connector/ v4l/ trace_printk/ blackfin/ \
+			   vfio-mdev/

samples/vfio-mdev/Makefile

-#
-# Makefile for mtty.c file
-#
-KERNEL_DIR:=/lib/modules/$(shell uname -r)/build
-
-obj-m:=mtty.o
-
-modules clean modules_install:
-	$(MAKE) -C $(KERNEL_DIR) SUBDIRS=$(PWD) $@
-
-default: modules
-
-module: modules
+obj-$(CONFIG_SAMPLE_VFIO_MDEV_MTTY) += mtty.o

samples/vfio-mdev/mtty.c

@@ -164,7 +164,7 @@ static struct mdev_state *find_mdev_state_by_uuid(uuid_le uuid)
 	struct mdev_state *mds;
 
 	list_for_each_entry(mds, &mdev_devices_list, next) {
-		if (uuid_le_cmp(mds->mdev->uuid, uuid) == 0)
+		if (uuid_le_cmp(mdev_uuid(mds->mdev), uuid) == 0)
 			return mds;
 	}
 
@@ -341,7 +341,8 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: Fifo level trigger\n",
 					index);
 #endif
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 			}
 		} else {
 #if defined(DEBUG_INTR)
@@ -355,7 +356,8 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 			 */
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 								UART_IER_RLSI)
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 		break;
@@ -374,7 +376,8 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: IER_THRI write\n",
 					index);
 #endif
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+						mdev_uuid(mdev_state->mdev));
 			}
 
 			mutex_unlock(&mdev_state->rxtx_lock);
@@ -445,7 +448,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR_OUT2 write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_state->mdev->uuid);
+			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
 		}
 
 		if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
@@ -453,7 +456,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR RTS/DTR write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_state->mdev->uuid);
+			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
 		}
 		break;
 
@@ -504,7 +507,8 @@ static void handle_bar_read(unsigned int index, struct mdev_state *mdev_state,
 #endif
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 							 UART_IER_THRI)
-				mtty_trigger_interrupt(mdev_state->mdev->uuid);
+				mtty_trigger_interrupt(
+					mdev_uuid(mdev_state->mdev));
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 
@@ -734,7 +738,7 @@ int mtty_create(struct kobject *kobj, struct mdev_device *mdev)
 
 	for (i = 0; i < 2; i++) {
 		snprintf(name, MTTY_STRING_LEN, "%s-%d",
-			dev_driver_string(mdev->parent->dev), i + 1);
+			dev_driver_string(mdev_parent_dev(mdev)), i + 1);
 		if (!strcmp(kobj->name, name)) {
 			nr_ports = i + 1;
 			break;
@@ -1298,10 +1302,8 @@ static ssize_t
 sample_mdev_dev_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
-	struct mdev_device *mdev = to_mdev_device(dev);
-
-	if (mdev)
-		return sprintf(buf, "This is MDEV %s\n", dev_name(&mdev->dev));
+	if (mdev_from_dev(dev))
+		return sprintf(buf, "This is MDEV %s\n", dev_name(dev));
 
 	return sprintf(buf, "\n");
 }
@@ -1402,7 +1404,7 @@ struct attribute_group *mdev_type_groups[] = {
 	NULL,
 };
 
-struct parent_ops mdev_fops = {
+struct mdev_parent_ops mdev_fops = {
 	.owner                  = THIS_MODULE,
 	.dev_attr_groups        = mtty_dev_groups,
 	.mdev_attr_groups       = mdev_dev_groups,
@@ -1447,6 +1449,7 @@ static int __init mtty_dev_init(void)
 
 	if (IS_ERR(mtty_dev.vd_class)) {
 		pr_err("Error: failed to register mtty_dev class\n");
+		ret = PTR_ERR(mtty_dev.vd_class);
 		goto failed1;
 	}
 
@@ -1458,7 +1461,8 @@ static int __init mtty_dev_init(void)
 	if (ret)
 		goto failed2;
 
-	if (mdev_register_device(&mtty_dev.dev, &mdev_fops) != 0)
+	ret = mdev_register_device(&mtty_dev.dev, &mdev_fops);
+	if (ret)
 		goto failed3;
 
 	mutex_init(&mdev_list_lock);