[PATCH RFC v2 3/3] vfio: Add dev_data_len/uptr in struct vfio_device_bind_iommufd

[Nicolin Chen <nicolinc@xxxxxxxxxx>]

This allows user space to pass in an iommu specific device data with the
VFIO_DEVICE_BIND_IOMMUFD ioctl. The data is not mandatory. But it must be
provided if a non-zero data_len is passed along.

Signed-off-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
---
 drivers/vfio/device_cdev.c | 19 +++++++++++++++++--
 drivers/vfio/iommufd.c     | 13 +++++++++++++
 include/linux/vfio.h       |  2 ++
 include/uapi/linux/vfio.h  | 13 +++++++++++++
 4 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index b5824179cd48..70241d9c0fa9 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -104,9 +104,10 @@ static struct iommufd_ctx *vfio_get_iommufd_from_fd(int fd)
 long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
 				    struct vfio_device_bind_iommufd __user *arg)
 {
+	uint32_t mask = VFIO_DEVICE_BIND_IOMMUFD_FLAG_DATA;
 	struct vfio_device *device = df->device;
 	struct vfio_device_bind_iommufd bind;
-	unsigned long minsz;
+	unsigned long minsz, datasz;
 	bool is_noiommu;
 	int ret;
 
@@ -117,9 +118,23 @@ long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
 	if (copy_from_user(&bind, arg, minsz))
 		return -EFAULT;
 
-	if (bind.argsz < minsz || bind.flags)
+	if (bind.argsz < minsz || bind.flags & ~mask)
 		return -EINVAL;
 
+	if (bind.flags & VFIO_DEVICE_BIND_IOMMUFD_FLAG_DATA) {
+		datasz = offsetofend(struct vfio_device_bind_iommufd,
+				     dev_data_len);
+		if (bind.argsz < datasz)
+			return -EINVAL;
+		if (copy_from_user((void *)&bind + minsz,
+				   (void __user *)arg + minsz, datasz - minsz))
+			return -EFAULT;
+		if (!bind.dev_data_uptr ^ !bind.dev_data_len)
+			return -EINVAL;
+		device->user_data = u64_to_user_ptr(bind.dev_data_uptr);
+		device->user_data_len = bind.dev_data_len;
+	}
+
 	/* BIND_IOMMUFD only allowed for cdev fds */
 	if (df->group)
 		return -EINVAL;
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
index 16d6aac06180..0b985ccffcbe 100644
--- a/drivers/vfio/iommufd.c
+++ b/drivers/vfio/iommufd.c
@@ -91,6 +91,16 @@ int vfio_iommufd_physical_bind(struct vfio_device *vdev,
 	idev = iommufd_device_bind(ictx, vdev->dev, out_device_id);
 	if (IS_ERR(idev))
 		return PTR_ERR(idev);
+
+	if (vdev->user_data) {
+		int rc = iommufd_device_set_data(idev, vdev->user_data,
+						 vdev->user_data_len);
+		if (rc) {
+			iommufd_device_unbind(idev);
+			return rc;
+		}
+	}
+
 	vdev->iommufd_device = idev;
 	return 0;
 }
@@ -104,8 +114,11 @@ void vfio_iommufd_physical_unbind(struct vfio_device *vdev)
 		iommufd_device_detach(vdev->iommufd_device);
 		vdev->iommufd_attached = false;
 	}
+	iommufd_device_unset_data(vdev->iommufd_device);
 	iommufd_device_unbind(vdev->iommufd_device);
 	vdev->iommufd_device = NULL;
+	vdev->user_data = NULL;
+	vdev->user_data_len = 0;
 }
 EXPORT_SYMBOL_GPL(vfio_iommufd_physical_unbind);
 
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 46b313f8bfaf..e4bb63801472 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -68,6 +68,8 @@ struct vfio_device {
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
 	bool iommufd_attached;
+	void *user_data;
+	u32 user_data_len;
 #endif
 	bool noiommu;
 };
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 17c5a1dadd08..9cec823c2829 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -212,15 +212,28 @@ struct vfio_group_status {
  *		as long as the input @iommufd is valid. Otherwise, it is
  *		meaningless. devid is a handle for this device and can be
  *		used in IOMMUFD commands.
+ * @dev_data_uptr: User pointer of the device user data.
+ * @dev_data_len: Length of the device user data.
+ *
+ * A device user data is an iommu specific structure that must be defined in
+ * the include/uapi/linux/iommufd.h file. On some platform enabling the iommu
+ * nested translation configuration, a device behind the iommu, while working
+ * in a guest VM, needs to provide the host kernel a certain virtual ID in the
+ * guest VM. For example, ARM SMMUv3 requires a virtual Stream ID to sanity a
+ * cache invalidation command from the user space. User space wanting to pass a
+ * user data must set VFIO_DEVICE_BIND_IOMMUFD_FLAG_DATA flag.
  *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_device_bind_iommufd {
 	__u32		argsz;
 	__u32		flags;
+#define VFIO_DEVICE_BIND_IOMMUFD_FLAG_DATA		(1 << 0)
 	__s32		iommufd;
 #define VFIO_NOIOMMU_FD	(-1)
 	__u32		out_devid;
+	__aligned_u64	dev_data_uptr;
+	__u32		dev_data_len;
 };
 
 #define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 19)
-- 
2.40.0