Re: [PATCH V2 03/11] iommufd: Allow binding to a noiommu device

[Jacob Pan <jacob.pan@linux.microsoft.com>]

Hi Mostafa,

On Sun, 22 Mar 2026 09:54:15 +0000
Mostafa Saleh <smostafa@google.com> wrote:

> From: Mostafa Saleh <smostafa@google.com>
> To: Jacob Pan <jacob.pan@linux.microsoft.com>
> Cc: linux-kernel@vger.kernel.org,  "iommu@lists.linux.dev"
> <iommu@lists.linux.dev>,  Jason Gunthorpe <jgg@nvidia.com>,  Alex
> Williamson <alex@shazbot.org>, Joerg Roedel <joro@8bytes.org>,  David
> Matlack <dmatlack@google.com>,  Robin Murphy <robin.murphy@arm.com>,
> Nicolin Chen <nicolinc@nvidia.com>,  "Tian, Kevin"
> <kevin.tian@intel.com>, Yi Liu <yi.l.liu@intel.com>,
> skhawaja@google.com, pasha.tatashin@soleen.com,  Will Deacon
> <will@kernel.org>, Baolu Lu <baolu.lu@linux.intel.com> Subject: Re:
> [PATCH V2 03/11] iommufd: Allow binding to a noiommu device Date:
> Sun, 22 Mar 2026 09:54:15 +0000
> 
> On Thu, Mar 12, 2026 at 08:56:29AM -0700, Jacob Pan wrote:
> > From: Jason Gunthorpe <jgg@nvidia.com>
> > 
> > Allow iommufd to bind devices without an IOMMU (noiommu mode) by
> > creating a dummy IOMMU group for such devices and skipping hwpt
> > operations.
> > 
> > This enables noiommu devices to operate through the same iommufd
> > API as IOMMU- capable devices.
> > 
> > Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> > Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
> > ---
> >  drivers/iommu/iommufd/device.c | 113
> > ++++++++++++++++++++++----------- 1 file changed, 76 insertions(+),
> > 37 deletions(-)
> > 
> > diff --git a/drivers/iommu/iommufd/device.c
> > b/drivers/iommu/iommufd/device.c index 54d73016468f..c38d3efa3d6f
> > 100644 --- a/drivers/iommu/iommufd/device.c
> > +++ b/drivers/iommu/iommufd/device.c
> > @@ -23,6 +23,11 @@ struct iommufd_attach {
> >  	struct xarray device_array;
> >  };
> >  
> > +static bool is_vfio_noiommu(struct iommufd_device *idev)
> > +{
> > +	return !device_iommu_mapped(idev->dev) ||
> > !idev->dev->iommu;  
> 
> Do this need to check for CONFIG_VFIO_NOIOMMU and maybe the module
> param enable_unsafe_noiommu_mode similar to the legacy implemenation?
> 
Checking for CONFIG_VFIO_NOIOMMU is not needed since all the conditions
are not restricted by CONFIG_VFIO_NOIOMMU. I felt it is cleaner this
way by not tying iommufd private code with vfio.

I guess we could do something like below but not necessary IMHO.
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -23,11 +23,6 @@ struct iommufd_attach {
        struct xarray device_array;
 };
 
-static bool is_vfio_noiommu(struct iommufd_device *idev)
-{
-       return !device_iommu_mapped(idev->dev) || !idev->dev->iommu;
-}
-
 static void iommufd_group_release(struct kref *kref)
 {
        struct iommufd_group *igroup =
diff --git a/drivers/iommu/iommufd/iommufd_private.h
b/drivers/iommu/iommufd/iommufd_private.h index
3302c6a1f99e..cba5550e3f2b 100644 ---
a/drivers/iommu/iommufd/iommufd_private.h +++
b/drivers/iommu/iommufd/iommufd_private.h @@ -711,6 +711,18 @@
iommufd_get_vdevice(struct iommufd_ctx *ictx, u32 id) struct
iommufd_vdevice, obj); }
 
+#ifdef CONFIG_VFIO_NOIOMMU
+static inline bool is_vfio_noiommu(struct iommufd_device *idev)
+{
+       return !device_iommu_mapped(idev->dev) || !idev->dev->iommu;
+}
+#else
+static inline bool is_vfio_noiommu(struct iommufd_device *idev)
+{
+       return false;
+}
+#endif
+