Re: [PATCH v12 05/13] iommu/arm-smmu-qcom: Add implementation for the adreno GPU SMMU

[Will Deacon]

On Mon, Aug 10, 2020 at 04:26:49PM -0600, Jordan Crouse wrote:
> Add a special implementation for the SMMU attached to most Adreno GPU
> target triggered from the qcom,adreno-smmu compatible string.
> 
> The new Adreno SMMU implementation will enable split pagetables
> (TTBR1) for the domain attached to the GPU device (SID 0) and
> hard code it context bank 0 so the GPU hardware can implement
> per-instance pagetables.
> 
> Signed-off-by: Jordan Crouse <jcrouse@xxxxxxxxxxxxxx>
> ---
> 
>  drivers/iommu/arm/arm-smmu/arm-smmu-impl.c |   3 +
>  drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 156 ++++++++++++++++++++-
>  2 files changed, 157 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> index 88f17cc33023..d199b4bff15d 100644
> --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> @@ -223,6 +223,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
>  	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
>  		return qcom_smmu_impl_init(smmu);
>  
> +	if (of_device_is_compatible(smmu->dev->of_node, "qcom,adreno-smmu"))
> +		return qcom_adreno_smmu_impl_init(smmu);
> +
>  	if (of_device_is_compatible(np, "marvell,ap806-smmu-500"))
>  		smmu->impl = &mrvl_mmu500_impl;
>  
> diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
> index be4318044f96..3be10145bf57 100644
> --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
> +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
> @@ -12,6 +12,138 @@ struct qcom_smmu {
>  	struct arm_smmu_device smmu;
>  };
>  
> +#define QCOM_ADRENO_SMMU_GPU_SID 0
> +
> +static bool qcom_adreno_smmu_is_gpu_device(struct device *dev)
> +{
> +	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
> +	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
> +	int idx, i;
> +
> +	/*
> +	 * The GPU will always use SID 0 so that is a handy way to uniquely
> +	 * identify it and configure it for per-instance pagetables
> +	 */
> +	for_each_cfg_sme(cfg, fwspec, i, idx) {
> +		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
> +
> +		if (sid == QCOM_ADRENO_SMMU_GPU_SID)
> +			return true;
> +	}

Is for_each_cfg_sme() really what you want here? You're not using idx for
anything, so I guess it should really be a loop over the sids (e.g. a bog
standard for loop from 0 to fw->num_ids - 1)?

Will