[PATCH v2] iommu/arm-smmu-v3-iommufd: Allow attaching nested domain for GBPA cases

[Shuai Xue]

在 2025/11/4 01:27, Nicolin Chen 写道:
> A vDEVICE has been a hard requirement for attaching a nested domain to the
> device. This makes sense when installing a guest STE, since a vSID must be
> present and given to the kernel during the vDEVICE allocation.
> 
> But, when CR0.SMMUEN is disabled, VM doesn't really need a vSID to program
> the vSMMU behavior as GBPA will take effect, in which case the vSTE in the
> nested domain could have carried the bypass or abort configuration in GBPA
> register. Thus, having such a hard requirement doesn't work well for GBPA.
> 
> Skip vmaster allocation in arm_smmu_attach_prepare_vmaster() for an abort
> or bypass vSTE. Note that device on this attachment won't report vevents.
> 
> Update the uAPI doc accordingly.
> 
> Tested-by: Shameer Kolothum <skolothumtho at nvidia.com>
> Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>
> ---

I've tested this patch and can confirm it resolves the GBPA hwpt
attachment issue.

Without this patch, IOMMUFD fails to attach bypass hwpt with the
following error:

   smmu_reset_exit
   qemu-system-aarch64: [iommufd=303] error attach 0008:01:00.0 (304) to id=6: No such file or directory
   Failed to attach GBPA hwpt id 6 for dev id 1

With this patch applied, the attachment succeeds:

   smmu_reset_exit
   iommufd_cdev_attach_ioas_hwpt  [iommufd=303] Successfully attached device 0008:01:00.0 (304) to id=6

Testing was performed on top of Shameer's vSMMU v5 series:

   https://patchew.org/QEMU/20251031105005.24618-1-skolothumtho@nvidia.com/

Tested-by: Shuai Xue  <xueshuai at linux.alibaba.com>

Thanks.
Shuai