Re: [PATCH v2 13/14] vfio: Add ioctls for device cdev using iommufd

[Yan Zhao]

On Mon, Feb 06, 2023 at 01:05:31AM -0800, Yi Liu wrote:
...

> +void vfio_device_cdev_close(struct vfio_device_file *df)
> +{
> +	mutex_lock(&df->device->dev_set->lock);
> +	vfio_device_close(df);
> +	vfio_device_put_kvm(df->device);
> +	mutex_unlock(&df->device->dev_set->lock);
> +}
> +

...

> +long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
> +				    unsigned long arg)
> +{
> +	struct vfio_device *device = df->device;
> +	struct vfio_device_bind_iommufd bind;
> +	struct iommufd_ctx *iommufd = NULL;
> +	unsigned long minsz;
> +	struct fd f;
> +	int ret;
> +
> +	minsz = offsetofend(struct vfio_device_bind_iommufd, iommufd);
> +
> +	if (copy_from_user(&bind, (void __user *)arg, minsz))
> +		return -EFAULT;
> +
> +	if (bind.argsz < minsz || bind.flags)
> +		return -EINVAL;
> +
> +	if (!device->ops->bind_iommufd)
> +		return -ENODEV;
> +
> +	mutex_lock(&device->dev_set->lock);
> +	/*
> +	 * If already been bound to an iommufd, or already set noiommu
> +	 * then fail it.
> +	 */
> +	if (df->iommufd || df->noiommu) {
> +		ret = -EINVAL;
> +		goto out_unlock;
> +	}
> +
> +	/* iommufd < 0 means noiommu mode */
> +	if (bind.iommufd < 0) {
> +		if (!capable(CAP_SYS_RAWIO)) {
> +			ret = -EPERM;
> +			goto out_unlock;
> +		}
> +		df->noiommu = true;
> +	} else {
> +		f = fdget(bind.iommufd);
> +		if (!f.file) {
> +			ret = -EBADF;
> +			goto out_unlock;
> +		}
> +		iommufd = iommufd_ctx_from_file(f.file);
> +		if (IS_ERR(iommufd)) {
> +			ret = PTR_ERR(iommufd);
> +			goto out_put_file;
> +		}
> +	}
> +
> +	/*
> +	 * Before the first device open, get the KVM pointer currently
> +	 * associated with the device file (if there is) and obtain a
> +	 * reference. This reference is held until device closed. Save
> +	 * the pointer in the device for use by drivers.
> +	 */
> +	vfio_device_get_kvm_safe(df);
> +
> +	df->iommufd = iommufd;
> +	ret = vfio_device_open(df, &bind.out_devid, NULL);
> +	if (ret)
> +		goto out_put_kvm;
> +
> +	ret = copy_to_user((void __user *)arg + minsz,
> +			   &bind.out_devid,
> +			   sizeof(bind.out_devid)) ? -EFAULT : 0;
> +	if (ret)
> +		goto out_close_device;
> +
> +	if (iommufd)
> +		fdput(f);
> +	else if (df->noiommu)
> +		dev_warn(device->dev, "vfio-noiommu device used by user "
> +			 "(%s:%d)\n", current->comm, task_pid_nr(current));
> +	mutex_unlock(&device->dev_set->lock);
> +	return 0;
> +
> +out_close_device:
> +	vfio_device_close(df);
vfio_device_close() is called here if any error after vfio_device_open().
But it will also be called unconditionally in vfio_device_cdev_close() and
cause a wrong value of device->open_count.

df->access_granted in patch 07 can also be of wrong true value after
this vfio_device_close().


> +out_put_kvm:
> +	vfio_device_put_kvm(device);
> +out_put_file:
> +	if (iommufd)
> +		fdput(f);
> +out_unlock:
> +	df->iommufd = NULL;
> +	df->noiommu = false;
> +	mutex_unlock(&device->dev_set->lock);
> +	return ret;
> +}
> +