[PATCH v6 22/24] vfio: Add VFIO_DEVICE_AT[DE]TACH_IOMMUFD_PT

[Yi Liu <yi.l.liu@intel.com>]

This adds ioctl for userspace to attach device cdev fd to and detach
from IOAS/hw_pagetable managed by iommufd.

    VFIO_DEVICE_ATTACH_IOMMUFD_PT: attach vfio device to IOAS, hw_pagetable
				   managed by iommufd. Attach can be
				   undo by VFIO_DEVICE_DETACH_IOMMUFD_PT
				   or device fd close.
    VFIO_DEVICE_DETACH_IOMMUFD_PT: detach vfio device from the current attached
				   IOAS or hw_pagetable managed by iommufd.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Terrence Xu <terrence.xu@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
---
 drivers/vfio/device_cdev.c | 85 ++++++++++++++++++++++++++++++++++++++
 drivers/vfio/vfio.h        | 16 +++++++
 drivers/vfio/vfio_main.c   |  8 ++++
 include/uapi/linux/vfio.h  | 52 +++++++++++++++++++++++
 4 files changed, 161 insertions(+)

diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index 568cc9da16c7..77e0f34f6bc7 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -210,6 +210,91 @@ long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
 	return ret;
 }
 
+int vfio_ioctl_device_attach(struct vfio_device_file *df,
+			     struct vfio_device_attach_iommufd_pt __user *arg)
+{
+	struct vfio_device *device = df->device;
+	struct vfio_device_attach_iommufd_pt attach;
+	unsigned long minsz;
+	int ret;
+
+	static_assert(__same_type(arg->pt_id, attach.pt_id));
+
+	minsz = offsetofend(struct vfio_device_attach_iommufd_pt, pt_id);
+
+	if (copy_from_user(&attach, arg, minsz))
+		return -EFAULT;
+
+	if (attach.argsz < minsz || attach.flags)
+		return -EINVAL;
+
+	if (!device->ops->bind_iommufd)
+		return -ENODEV;
+
+	/* ATTACH only allowed for cdev fds */
+	if (df->group)
+		return -EINVAL;
+
+	mutex_lock(&device->dev_set->lock);
+	/* noiommufd mode doesn't allow attach */
+	if (!df->iommufd) {
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
+	ret = device->ops->attach_ioas(device, &attach.pt_id);
+	if (ret)
+		goto out_unlock;
+
+	ret = copy_to_user(&arg->pt_id, &attach.pt_id,
+			   sizeof(attach.pt_id)) ? -EFAULT : 0;
+	if (ret)
+		goto out_detach;
+	mutex_unlock(&device->dev_set->lock);
+
+	return 0;
+
+out_detach:
+	device->ops->detach_ioas(device);
+out_unlock:
+	mutex_unlock(&device->dev_set->lock);
+	return ret;
+}
+
+int vfio_ioctl_device_detach(struct vfio_device_file *df,
+			     struct vfio_device_detach_iommufd_pt __user *arg)
+{
+	struct vfio_device *device = df->device;
+	struct vfio_device_detach_iommufd_pt detach;
+	unsigned long minsz;
+
+	minsz = offsetofend(struct vfio_device_detach_iommufd_pt, flags);
+
+	if (copy_from_user(&detach, arg, minsz))
+		return -EFAULT;
+
+	if (detach.argsz < minsz || detach.flags)
+		return -EINVAL;
+
+	if (!device->ops->bind_iommufd)
+		return -ENODEV;
+
+	/* DETACH only allowed for cdev fds */
+	if (df->group)
+		return -EINVAL;
+
+	mutex_lock(&device->dev_set->lock);
+	/* noiommufd mode doesn't support detach */
+	if (!df->iommufd) {
+		mutex_unlock(&device->dev_set->lock);
+		return -EOPNOTSUPP;
+	}
+	device->ops->detach_ioas(device);
+	mutex_unlock(&device->dev_set->lock);
+
+	return 0;
+}
+
 static char *vfio_device_devnode(const struct device *dev, umode_t *mode)
 {
 	return kasprintf(GFP_KERNEL, "vfio/devices/%s", dev_name(dev));
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 5df737b24102..8b70e2af4ece 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -278,6 +278,10 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep);
 void vfio_device_cdev_close(struct vfio_device_file *df);
 long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
 				    struct vfio_device_bind_iommufd __user *arg);
+int vfio_ioctl_device_attach(struct vfio_device_file *df,
+			     struct vfio_device_attach_iommufd_pt __user *arg);
+int vfio_ioctl_device_detach(struct vfio_device_file *df,
+			     struct vfio_device_detach_iommufd_pt __user *arg);
 int vfio_cdev_init(struct class *device_class);
 void vfio_cdev_cleanup(void);
 #else
@@ -311,6 +315,18 @@ static inline long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
 	return -EOPNOTSUPP;
 }
 
+static inline int vfio_ioctl_device_attach(struct vfio_device_file *df,
+					   struct vfio_device_attach_iommufd_pt __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int vfio_ioctl_device_detach(struct vfio_device_file *df,
+					   struct vfio_device_detach_iommufd_pt __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int vfio_cdev_init(struct class *device_class)
 {
 	return 0;
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 08bb1705d02d..e5f4738692ac 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -1170,6 +1170,14 @@ static long vfio_device_fops_unl_ioctl(struct file *filep,
 		ret = vfio_ioctl_device_feature(device, (void __user *)arg);
 		break;
 
+	case VFIO_DEVICE_ATTACH_IOMMUFD_PT:
+		ret = vfio_ioctl_device_attach(df, (void __user *)arg);
+		break;
+
+	case VFIO_DEVICE_DETACH_IOMMUFD_PT:
+		ret = vfio_ioctl_device_detach(df, (void __user *)arg);
+		break;
+
 	default:
 		if (unlikely(!device->ops->ioctl))
 			ret = -EINVAL;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index a53afe349a34..692156a708bb 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -231,6 +231,58 @@ struct vfio_device_bind_iommufd {
 
 #define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 19)
 
+/*
+ * VFIO_DEVICE_ATTACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 20,
+ *					struct vfio_device_attach_iommufd_pt)
+ *
+ * Attach a vfio device to an iommufd address space specified by IOAS
+ * id or hw_pagetable (hwpt) id.
+ *
+ * Available only after a device has been bound to iommufd via
+ * VFIO_DEVICE_BIND_IOMMUFD
+ *
+ * Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close.
+ *
+ * @argsz:	user filled size of this data.
+ * @flags:	must be 0.
+ * @pt_id:	Input the target id which can represent an ioas or a hwpt
+ *		allocated via iommufd subsystem.
+ *		Output the attached hwpt id which could be the specified
+ *		hwpt itself or a hwpt automatically created for the
+ *		specified ioas by kernel during the attachment.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_attach_iommufd_pt {
+	__u32	argsz;
+	__u32	flags;
+	__u32	pt_id;
+};
+
+#define VFIO_DEVICE_ATTACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 20)
+
+/*
+ * VFIO_DEVICE_DETACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 21,
+ *					struct vfio_device_detach_iommufd_pt)
+ *
+ * Detach a vfio device from the iommufd address space it has been
+ * attached to. After it, device should be in a blocking DMA state.
+ *
+ * Available only after a device has been bound to iommufd via
+ * VFIO_DEVICE_BIND_IOMMUFD.
+ *
+ * @argsz:	user filled size of this data.
+ * @flags:	must be 0.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_detach_iommufd_pt {
+	__u32	argsz;
+	__u32	flags;
+};
+
+#define VFIO_DEVICE_DETACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 21)
+
 /**
  * VFIO_DEVICE_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 7,
  *						struct vfio_device_info)
-- 
2.34.1