vfio: Replace the DMA unmapping notifier with a callback

Instead of having drivers register the notifier with explicit code just
have them provide a dma_unmap callback op in their driver ops and rely on
the core code to wire it up.

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v4-681e038e30fd+78-vfio_unmap_notif_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 44 insertions, 85 deletions

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index bd84ca7c5e35..83c375fa2421 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -231,6 +231,9 @@ int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops)
 {
 	struct vfio_iommu_driver *driver, *tmp;
 
+	if (WARN_ON(!ops->register_notifier != !ops->unregister_notifier))
+		return -EINVAL;
+
 	driver = kzalloc(sizeof(*driver), GFP_KERNEL);
 	if (!driver)
 		return -ENOMEM;
@@ -1079,8 +1082,20 @@ static void vfio_device_unassign_container(struct vfio_device *device)
 	up_write(&device->group->group_rwsem);
 }
 
+static int vfio_iommu_notifier(struct notifier_block *nb, unsigned long action,
+			       void *data)
+{
+	struct vfio_device *vfio_device =
+		container_of(nb, struct vfio_device, iommu_nb);
+	struct vfio_iommu_type1_dma_unmap *unmap = data;
+
+	vfio_device->ops->dma_unmap(vfio_device, unmap->iova, unmap->size);
+	return NOTIFY_OK;
+}
+
 static struct file *vfio_device_open(struct vfio_device *device)
 {
+	struct vfio_iommu_driver *iommu_driver;
 	struct file *filep;
 	int ret;
 
@@ -1111,6 +1126,18 @@ static struct file *vfio_device_open(struct vfio_device *device)
 			if (ret)
 				goto err_undo_count;
 		}
+
+		iommu_driver = device->group->container->iommu_driver;
+		if (device->ops->dma_unmap && iommu_driver &&
+		    iommu_driver->ops->register_notifier) {
+			unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+
+			device->iommu_nb.notifier_call = vfio_iommu_notifier;
+			iommu_driver->ops->register_notifier(
+				device->group->container->iommu_data, &events,
+				&device->iommu_nb);
+		}
+
 		up_read(&device->group->group_rwsem);
 	}
 	mutex_unlock(&device->dev_set->lock);
@@ -1145,8 +1172,16 @@ static struct file *vfio_device_open(struct vfio_device *device)
 err_close_device:
 	mutex_lock(&device->dev_set->lock);
 	down_read(&device->group->group_rwsem);
-	if (device->open_count == 1 && device->ops->close_device)
+	if (device->open_count == 1 && device->ops->close_device) {
 		device->ops->close_device(device);
+
+		iommu_driver = device->group->container->iommu_driver;
+		if (device->ops->dma_unmap && iommu_driver &&
+		    iommu_driver->ops->unregister_notifier)
+			iommu_driver->ops->unregister_notifier(
+				device->group->container->iommu_data,
+				&device->iommu_nb);
+	}
 err_undo_count:
 	up_read(&device->group->group_rwsem);
 	device->open_count--;
@@ -1341,12 +1376,20 @@ static const struct file_operations vfio_group_fops = {
 static int vfio_device_fops_release(struct inode *inode, struct file *filep)
 {
 	struct vfio_device *device = filep->private_data;
+	struct vfio_iommu_driver *iommu_driver;
 
 	mutex_lock(&device->dev_set->lock);
 	vfio_assert_device_open(device);
 	down_read(&device->group->group_rwsem);
 	if (device->open_count == 1 && device->ops->close_device)
 		device->ops->close_device(device);
+
+	iommu_driver = device->group->container->iommu_driver;
+	if (device->ops->dma_unmap && iommu_driver &&
+	    iommu_driver->ops->unregister_notifier)
+		iommu_driver->ops->unregister_notifier(
+			device->group->container->iommu_data,
+			&device->iommu_nb);
 	up_read(&device->group->group_rwsem);
 	device->open_count--;
 	if (device->open_count == 0)
@@ -2029,90 +2072,6 @@ int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data,
 }
 EXPORT_SYMBOL(vfio_dma_rw);
 
-static int vfio_register_iommu_notifier(struct vfio_group *group,
-					unsigned long *events,
-					struct notifier_block *nb)
-{
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-	int ret;
-
-	lockdep_assert_held_read(&group->group_rwsem);
-
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->register_notifier))
-		ret = driver->ops->register_notifier(container->iommu_data,
-						     events, nb);
-	else
-		ret = -ENOTTY;
-
-	return ret;
-}
-
-static int vfio_unregister_iommu_notifier(struct vfio_group *group,
-					  struct notifier_block *nb)
-{
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-	int ret;
-
-	lockdep_assert_held_read(&group->group_rwsem);
-
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->unregister_notifier))
-		ret = driver->ops->unregister_notifier(container->iommu_data,
-						       nb);
-	else
-		ret = -ENOTTY;
-
-	return ret;
-}
-
-int vfio_register_notifier(struct vfio_device *device,
-			   enum vfio_notify_type type, unsigned long *events,
-			   struct notifier_block *nb)
-{
-	struct vfio_group *group = device->group;
-	int ret;
-
-	if (!nb || !events || (*events == 0) ||
-	    !vfio_assert_device_open(device))
-		return -EINVAL;
-
-	switch (type) {
-	case VFIO_IOMMU_NOTIFY:
-		ret = vfio_register_iommu_notifier(group, events, nb);
-		break;
-	default:
-		ret = -EINVAL;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(vfio_register_notifier);
-
-int vfio_unregister_notifier(struct vfio_device *device,
-			     enum vfio_notify_type type,
-			     struct notifier_block *nb)
-{
-	struct vfio_group *group = device->group;
-	int ret;
-
-	if (!nb || !vfio_assert_device_open(device))
-		return -EINVAL;
-
-	switch (type) {
-	case VFIO_IOMMU_NOTIFY:
-		ret = vfio_unregister_iommu_notifier(group, nb);
-		break;
-	default:
-		ret = -EINVAL;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(vfio_unregister_notifier);
-
 /*
  * Module/class support
  */