Re: [PATCH v6 5/7] vfio: Enable cdev noiommu mode under iommufd

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

On 5/22/26 06:11, Jacob Pan wrote:
> Now that devices under noiommu mode can bind with IOMMUFD and perform
> IOAS operations, lift restrictions on cdev from VFIO side.
> Use cases are documented in Documentation/driver-api/vfio.rst
> 
> Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
> ---
> v6:
>    - Revert back to unified VFIO_NOIOMMU Kconfig for both cdev and group.
>      Use Kconfig dependency to restrict usages and avoid null group
>      checks. (Alex & Yi)
>    - Add CAP_SYS_RAWIO checks for cdev open to maintain security parity
>      with the group noiommu path. (Alex)
> v5:
>     - Add Kconfig VFIO_CDEV_NOIOMMU to select IOMMUFD_NOIOMMU
>       and its dependencies
>     - Add comment to explain vfio_noiommu conditional definition (Alex)
>     - Removed early return for group noiommu in bind/unbind
>     - Use consistent wording referring to VFIO noiommu mode (Kevin)
>     - Update unsafe_noiommu Kconfig help text (Kevin)
>     - Change dev_warn to dev_info for noiommu enabling msg (Kevin)
> v4:
>     - Remove early return in iommufd_bind for noiommu (Alex)
> v3:
>     - Consolidate into fewer patches
> v2:
>     - removed unnecessary device->noiommu set in
>       iommufd_vfio_compat_ioas_get_id()
> Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
> ---
>   drivers/vfio/Kconfig       |  8 +++++---
>   drivers/vfio/device_cdev.c |  3 +++
>   drivers/vfio/iommufd.c     |  6 +++---
>   drivers/vfio/vfio.h        | 20 +++++++++++++-------
>   drivers/vfio/vfio_main.c   | 23 +++++++++++++++++++----
>   include/linux/vfio.h       |  1 +
>   6 files changed, 44 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index ceae52fd7586..d3d8fef2855c 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -22,8 +22,7 @@ config VFIO_DEVICE_CDEV
>   	  The VFIO device cdev is another way for userspace to get device
>   	  access. Userspace gets device fd by opening device cdev under
>   	  /dev/vfio/devices/vfioX, and then bind the device fd with an iommufd
> -	  to set up secure DMA context for device access.  This interface does
> -	  not support noiommu.
> +	  to set up secure DMA context for device access.

if noiommu, it's unsafe DMA. :)

>   	  If you don't know what to do here, say N.
>   
> @@ -62,7 +61,10 @@ endif
>   
>   config VFIO_NOIOMMU
>   	bool "VFIO No-IOMMU support"
> -	depends on VFIO_GROUP
> +	depends on VFIO_GROUP || VFIO_DEVICE_CDEV
> +	depends on !VFIO_GROUP || VFIO_CONTAINER || IOMMUFD_VFIO_CONTAINER
> +	depends on !VFIO_DEVICE_CDEV || !GENERIC_ATOMIC64
> +	select IOMMUFD_NOIOMMU if VFIO_DEVICE_CDEV
>   	help
>   	  VFIO is built on the ability to isolate devices using the IOMMU.
>   	  Only with an IOMMU can userspace access to DMA capable devices be
> diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
> index 54abf312cf04..4e2c1e4fc1f8 100644
> --- a/drivers/vfio/device_cdev.c
> +++ b/drivers/vfio/device_cdev.c
> @@ -27,6 +27,9 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep)
>   	struct vfio_device_file *df;
>   	int ret;
>   
> +	if (device->noiommu && !capable(CAP_SYS_RAWIO))
> +		return -EPERM;
> +
>   	/* Paired with the put in vfio_device_fops_release() */
>   	if (!vfio_device_try_get_registration(device))
>   		return -ENODEV;
> diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
> index a38d262c6028..d4f2e2a0f2f3 100644
> --- a/drivers/vfio/iommufd.c
> +++ b/drivers/vfio/iommufd.c
> @@ -25,8 +25,8 @@ int vfio_df_iommufd_bind(struct vfio_device_file *df)
>   
>   	lockdep_assert_held(&vdev->dev_set->lock);
>   
> -	/* Returns 0 to permit device opening under noiommu mode */
> -	if (vfio_device_is_noiommu(vdev))
> +	/* Group noiommu via iommufd compat needs no device binding */
> +	if (df->group && vfio_device_is_noiommu(vdev))

seems like vfio_device_is_noiommu() implies group path, then no need
to use df->group.

static inline bool vfio_device_is_noiommu(struct vfio_device *vdev)
{
     return IS_ENABLED(CONFIG_VFIO_NOIOMMU) &&
            vdev->group->type == VFIO_NO_IOMMU;
}

>   		return 0;
>   
>   	return vdev->ops->bind_iommufd(vdev, ictx, &df->devid);
> @@ -58,7 +58,7 @@ void vfio_df_iommufd_unbind(struct vfio_device_file *df)
>   
>   	lockdep_assert_held(&vdev->dev_set->lock);
>   
> -	if (vfio_device_is_noiommu(vdev))
> +	if (df->group && vfio_device_is_noiommu(vdev))
>   		return;
>   
>   	if (vdev->ops->unbind_iommufd)
> diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
> index e4b72e79b7e3..6f0a2dfc8a00 100644
> --- a/drivers/vfio/vfio.h
> +++ b/drivers/vfio/vfio.h
> @@ -358,19 +358,13 @@ void vfio_init_device_cdev(struct vfio_device *device);
>   
>   static inline int vfio_device_add(struct vfio_device *device)
>   {
> -	/* cdev does not support noiommu device */
> -	if (vfio_device_is_noiommu(device))
> -		return device_add(&device->device);
>   	vfio_init_device_cdev(device);
>   	return cdev_device_add(&device->cdev, &device->device);
>   }
>   
>   static inline void vfio_device_del(struct vfio_device *device)
>   {
> -	if (vfio_device_is_noiommu(device))
> -		device_del(&device->device);
> -	else
> -		cdev_device_del(&device->cdev, &device->device);
> +	cdev_device_del(&device->cdev, &device->device);
>   }
>   
>   int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep);
> @@ -420,6 +414,18 @@ static inline void vfio_cdev_cleanup(void)
>   }
>   #endif /* CONFIG_VFIO_DEVICE_CDEV */
>   
> +#if IS_ENABLED(CONFIG_VFIO_NOIOMMU)
> +static inline bool vfio_device_is_cdev_noiommu(struct vfio_device *vdev)
> +{
> +	return vdev->noiommu;
> +}
> +#else
> +static inline bool vfio_device_is_cdev_noiommu(struct vfio_device *vdev)
> +{
> +	return false;
> +}
> +#endif
> +
>   #if IS_ENABLED(CONFIG_VFIO_VIRQFD)
>   int __init vfio_virqfd_init(void);
>   void vfio_virqfd_exit(void);
> diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
> index 6222376ab6ab..84381c500623 100644
> --- a/drivers/vfio/vfio_main.c
> +++ b/drivers/vfio/vfio_main.c
> @@ -321,6 +321,20 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev,
>   	return ret;
>   }
>   
> +static int vfio_device_set_noiommu_and_name(struct vfio_device *device)
> +{
> +	if (IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) && vfio_noiommu && !device->dev->iommu) {
> +		device->noiommu = true;
> +		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
> +		dev_warn(device->dev,
> +			 "Adding kernel taint for vfio-noiommu cdev on device\n");
> +	}
> +
> +	/* Just to be safe, expose to user explicitly noiommu cdev node */
> +	return dev_set_name(&device->device, "%svfio%d",
> +		     device->noiommu ? "noiommu-" : "", device->index);
> +}
> +
>   static int __vfio_register_dev(struct vfio_device *device,
>   			       enum vfio_group_type type)
>   {
> @@ -340,20 +354,21 @@ static int __vfio_register_dev(struct vfio_device *device,
>   	if (!device->dev_set)
>   		vfio_assign_device_set(device, device);
>   
> -	ret = dev_set_name(&device->device, "vfio%d", device->index);
> +	ret = vfio_device_set_group(device, type);
>   	if (ret)
>   		return ret;
>   
> -	ret = vfio_device_set_group(device, type);
> +	ret = vfio_device_set_noiommu_and_name(device);

the order of dev_set_name and vfio_device_set_group() are swapped, any
special reason?

>   	if (ret)
> -		return ret;
> +		goto err_out;
>   
>   	/*
>   	 * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
>   	 * restore cache coherency. It has to be checked here because it is only
>   	 * valid for cases where we are using iommu groups.
>   	 */
> -	if (type == VFIO_IOMMU && !vfio_device_is_noiommu(device) &&
> +	if (type == VFIO_IOMMU && !(vfio_device_is_noiommu(device) ||
> +				    vfio_device_is_cdev_noiommu(device)) &&

now, the group path and cdev path have their own is_noiommu helper, can
the two helpers be consolidated?

>   	    !device_iommu_capable(device->dev, IOMMU_CAP_CACHE_COHERENCY)) {
>   		ret = -EINVAL;
>   		goto err_out;
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 31b826efba00..45f08986359e 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -74,6 +74,7 @@ struct vfio_device {
>   	u8 iommufd_attached:1;
>   #endif
>   	u8 cdev_opened:1;
> +	u8 noiommu:1;
>   	/*
>   	 * debug_root is a static property of the vfio_device
>   	 * which must be set prior to registering the vfio_device.