Re: [PATCH rc v4 3/4] iommu/arm-smmu-v3: Mark STE EATS safe when computing the update sequence

[Mostafa Saleh <smostafa@google.com>]

On Tue, Dec 16, 2025 at 08:26:01PM -0800, Nicolin Chen wrote:
> From: Jason Gunthorpe <jgg@nvidia.com>
> 
> If a VM wants to toggle EATS off at the same time as changing the CFG, the
> hypervisor will see EATS change to 0 and insert a V=0 breaking update into
> the STE even though the VM did not ask for that.
> 
> In bare metal, EATS is ignored by CFG=ABORT/BYPASS, which is why this does
> not cause a problem until we have nested where CFG is always a variation of
> S2 trans that does use EATS.
> 
> Relax the rules for EATS sequencing, we don't need it to be exact because
> the enclosing code will always disable ATS at the PCI device if we are
> changing EATS. This ensures there are no ATS transactions that can race
> with an EATS change so we don't need to carefully sequence these bits.
> 
> Fixes: 1e8be08d1c91 ("iommu/arm-smmu-v3: Support IOMMU_DOMAIN_NESTED")
> Cc: stable@vger.kernel.org
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
> 
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index 12a9669bcc83..a3b29ad20a82 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -1095,6 +1095,15 @@ void arm_smmu_get_ste_update_safe(__le64 *safe_bits)
>  	 *  fault records even when MEV == 0.
>  	 */
>  	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
> +
> +	/*
> +	 * EATS is used to reject and control the ATS behavior of the device. If
> +	 * we are changing it away from 0 then we already trust the device to
> +	 * use ATS properly and we have sequenced the device's ATS enable in PCI
> +	 * config space to prevent it from issuing ATS while we are changing
> +	 * EATS.
> +	 */

I am not sure about this one, Is it only about trusting the device?

I’d be worried about cases where we switch domains, that means that
briefly the HW observers EATS=1 while it was not intended, especially
that EATS is in a different DWORD from S2TTB and CDptr. With all the
IOMMUFD/VFIO stuff it makes it harder to reason about. But I can’t
come up with an example to break this.

Thanks,
Mostafa

> +	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_EATS);
>  }
>  EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
>  
> -- 
> 2.43.0
>