vfio: Add VFIO_DEVICE_[AT|DE]TACH_IOMMUFD_PT

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 or 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.

Reviewed-by: Jason Gunthorpe <[e-mail]>
Tested-by: Nicolin Chen <[e-mail]>
Tested-by: Matthew Rosato <[e-mail]>
Tested-by: Yanting Jiang <[e-mail]>
Tested-by: Shameer Kolothum <[e-mail]>
Tested-by: Terrence Xu <[e-mail]>
Tested-by: Zhenzhong Duan <[e-mail]>
Signed-off-by: Yi Liu <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alex Williamson <[e-mail]>

drivers/vfio/device_cdev.c

···
 	vfio_device_unblock_group(device);
 }
 
+int vfio_df_ioctl_attach_pt(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;
+
+	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;
+
+	mutex_lock(&device->dev_set->lock);
+	ret = device->ops->attach_ioas(device, &attach.pt_id);
+	if (ret)
+		goto out_unlock;
+
+	if (copy_to_user(&arg->pt_id, &attach.pt_id, sizeof(attach.pt_id))) {
+		ret = -EFAULT;
+		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_df_ioctl_detach_pt(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;
+
+	mutex_lock(&device->dev_set->lock);
+	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));

drivers/vfio/vfio.h

···
 }
 #endif
 
+int vfio_df_ioctl_attach_pt(struct vfio_device_file *df,
+			    struct vfio_device_attach_iommufd_pt __user *arg);
+int vfio_df_ioctl_detach_pt(struct vfio_device_file *df,
+			    struct vfio_device_detach_iommufd_pt __user *arg);
+
 #if IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV)
 void vfio_init_device_cdev(struct vfio_device *device);
 

drivers/vfio/vfio_main.c

···
 	if (ret)
 		return ret;
 
+	/* cdev only ioctls */
+	if (IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) && !df->group) {
+		switch (cmd) {
+		case VFIO_DEVICE_ATTACH_IOMMUFD_PT:
+			ret = vfio_df_ioctl_attach_pt(df, uptr);
+			goto out;
+
+		case VFIO_DEVICE_DETACH_IOMMUFD_PT:
+			ret = vfio_df_ioctl_detach_pt(df, uptr);
+			goto out;
+		}
+	}
+
 	switch (cmd) {
 	case VFIO_DEVICE_FEATURE:
 		ret = vfio_ioctl_device_feature(device, uptr);
···
 			ret = device->ops->ioctl(device, cmd, arg);
 		break;
 	}
-
+out:
 	vfio_device_pm_runtime_put(device);
 	return ret;
 }

include/uapi/linux/vfio.h

···
 #define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 18)
 
 /*
+ * VFIO_DEVICE_ATTACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 19,
+ *					struct vfio_device_attach_iommufd_pt)
+ * @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 input ioas id or 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.
+ *
+ * Associate the device with an address space within the bound iommufd.
+ * Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close.  This is only
+ * allowed on cdev fds.
+ *
+ * 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 + 19)
+
+/*
+ * VFIO_DEVICE_DETACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 20,
+ *					struct vfio_device_detach_iommufd_pt)
+ * @argsz:	User filled size of this data.
+ * @flags:	Must be 0.
+ *
+ * Remove the association of the device and its current associated address
+ * space.  After it, the device should be in a blocking DMA state.  This is only
+ * allowed on cdev fds.
+ *
+ * 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 + 20)
+
+/*
  * Provide support for setting a PCI VF Token, which is used as a shared
  * secret between PF and VF drivers.  This feature may only be set on a
  * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing