> -----Original Message-----
> From: Nicolin Chen <nicol...@nvidia.com>
> Sent: 17 September 2025 19:45
> To: Shameer Kolothum <shameerkolot...@gmail.com>
> Cc: qemu-...@nongnu.org; qemu-devel@nongnu.org;
> eric.au...@redhat.com; peter.mayd...@linaro.org; Jason Gunthorpe
> <j...@nvidia.com>; ddut...@redhat.com; berra...@redhat.com; Nathan
> Chen <nath...@nvidia.com>; Matt Ochs <mo...@nvidia.com>;
> smost...@google.com; linux...@huawei.com; wangzh...@hisilicon.com;
> jiangkun...@huawei.com; jonathan.came...@huawei.com;
> zhangfei....@linaro.org; zhenzhong.d...@intel.com; Shameer Kolothum
> <skolothum...@nvidia.com>
> Subject: Re: [RFC PATCH v3 06/15] hw/arm/smmuv3-accel: Restrict accelerated
> SMMUv3 to vfio-pci endpoints with iommufd
>
> On Tue, Sep 16, 2025 at 11:33:21AM +0100, Shameer Kolothum wrote:
> > > I found a new problem here that we initialize new as_sysmem per
> > > VFIO device. So, sdevs would return own individual AS pointers
> > > here at this get_address_space function, although they point to
> > > the same system address space.
> > >
> > > Since address space pointers are returned differently for VFIO
> > > devices, this fails to reuse ioas_id in iommufd_cdev_attach(),
> > > and ends up with allocating a new ioas for each device.
> > >
> > > I think we can try the following change to make sure all accel
> > > linked VFIO devices would share the same ioas_id, though I am
> > > not sure if SMMUBaseClass is the right place to go. Please take
> > > a look.
> >
> > Ok. I think it is better to move that to SMMUv3AccelState and call
> > address_space_init() in smmuv3_accel_init() instead. Something like
> > below. Please take a look and let me know.
>
> [...]
>
> > @@ -37,7 +37,6 @@ typedef struct SMMUS1Hwpt {
> >
> > typedef struct SMMUv3AccelDevice {
> > SMMUDevice sdev;
> > - AddressSpace as_sysmem;
> > HostIOMMUDeviceIOMMUFD *idev;
> > SMMUS1Hwpt *s1_hwpt;
> > SMMUViommu *viommu;
> > @@ -48,6 +47,7 @@ typedef struct SMMUv3AccelDevice {
> > typedef struct SMMUv3AccelState {
> > MemoryRegion root;
> > MemoryRegion sysmem;
> > + AddressSpace as_sysmem;
> > SMMUViommu *viommu;
> > struct iommu_hw_info_arm_smmuv3 info;
> > } SMMUv3AccelState;
>
> That's changing from an ioas_id per VFIO device to an ioas_id per
> vSMMU instance, right? I think it's still not enough.
>
> All vSMMU instances could share the same ioas_id. That is why I
> put in the SMMUBaseClass as it's shared structure across vSMMUs.
Ah..you mean it is basically per VM then. Got it.
Thanks,
Shameer
