Re: [PATCH v1 0/4] iommu: Fix attach handle publication ordering

[Nicolin Chen <nicolinc@nvidia.com>]

On Tue, Sep 29, 2026 at 02:51:50PM -0700, Nicolin Chen wrote:
> Jason pointed out an issue in the attach handle replacing path:
> https://lore.kernel.org/linux-iommu/20260923233920.GJ2545495@nvidia.com/
> 
> When an attachment is detached or replaced, the IOMMU core can still leave
> the outgoing attach handle published while calling into the driver. A fault
> report looks up the handle without the group mutex, so it can find the old
> handle after the driver's fault flush and just before the caller frees it.
> 
> These four patches unpublish the outgoing handle before a driver callback
> for both group and PASID detach and replace operations. Both replace paths
> store XA_ZERO_ENTRY to reserve the slot and restore the old entry on error.
> 
> This blocks new lookups, but does not retire a fault that already obtained
> the old handle. The driver must still synchronize those readers before the
> handle is freed. A same-domain replacement skips the driver callback, so it
> still needs a separate lifetime mechanism or fence.
> 
> This is on GitHub:
> https://github.com/nicolinc/iommufd/commits/fix_iommu_attach_handle-v1
> 
> Nicolin Chen (4):
>   iommu: Unpublish the attach handle before the group detach callback
>   iommu: Unpublish the attach handle before the PASID detach callback
>   iommu: Unpublish the old attach handle before the group replace
>     callback
>   iommu: Unpublish the old attach handle before the PASID replace
>     callback

Baolu/Kevin/Yi,

Would it be possible for you to take a look at these fixes?

Thanks
Nicolin