[PATCH v5 11/27] iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd()

[Mostafa Saleh]

Hi Jason,

On Mon, Mar 04, 2024 at 07:43:59PM -0400, Jason Gunthorpe wrote:
> Half the code was living in arm_smmu_domain_finalise_s1(), just move it
> here and take the values directly from the pgtbl_ops instead of storing
> copies.
> 
> Tested-by: Nicolin Chen <nicolinc at nvidia.com>
> Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 47 ++++++++-------------
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  3 --
>  2 files changed, 18 insertions(+), 32 deletions(-)
> 
> 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 50d17e3ce0a956..dfdd48cf217c4e 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -1301,15 +1301,25 @@ void arm_smmu_make_s1_cd(struct arm_smmu_cd *target,
>  			 struct arm_smmu_domain *smmu_domain)
>  {
>  	struct arm_smmu_ctx_desc *cd = &smmu_domain->cd;
> +	const struct io_pgtable_cfg *pgtbl_cfg =
> +		&io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops)->cfg;
> +	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr =
> +		&pgtbl_cfg->arm_lpae_s1_cfg.tcr;
>  
>  	memset(target, 0, sizeof(*target));
>  
>  	target->data[0] = cpu_to_le64(
> -		cd->tcr |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
> +		CTXDESC_CD_0_TCR_EPD1 |
>  #ifdef __BIG_ENDIAN
>  		CTXDESC_CD_0_ENDI |
>  #endif
>  		CTXDESC_CD_0_V |
> +		FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
>  		CTXDESC_CD_0_AA64 |
>  		(master->stall_enabled ? CTXDESC_CD_0_S : 0) |
>  		CTXDESC_CD_0_R |
> @@ -1317,9 +1327,9 @@ void arm_smmu_make_s1_cd(struct arm_smmu_cd *target,
>  		CTXDESC_CD_0_ASET |
>  		FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid)
>  		);
> -
> -	target->data[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
> -	target->data[3] = cpu_to_le64(cd->mair);
> +	target->data[1] = cpu_to_le64(pgtbl_cfg->arm_lpae_s1_cfg.ttbr &
> +				      CTXDESC_CD_1_TTB0_MASK);
> +	target->data[3] = cpu_to_le64(pgtbl_cfg->arm_lpae_s1_cfg.mair);
>  }
>  
>  void arm_smmu_clear_cd(struct arm_smmu_master *master, ioasid_t ssid)
> @@ -2305,13 +2315,11 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
>  }
>  
>  static int arm_smmu_domain_finalise_s1(struct arm_smmu_device *smmu,
> -				       struct arm_smmu_domain *smmu_domain,
> -				       struct io_pgtable_cfg *pgtbl_cfg)
> +				       struct arm_smmu_domain *smmu_domain)
>  {
>  	int ret;
>  	u32 asid;
>  	struct arm_smmu_ctx_desc *cd = &smmu_domain->cd;
> -	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
>  
>  	refcount_set(&cd->refs, 1);
>  
> @@ -2319,31 +2327,13 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_device *smmu,
>  	mutex_lock(&arm_smmu_asid_lock);
>  	ret = xa_alloc(&arm_smmu_asid_xa, &asid, cd,
>  		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
> -	if (ret)
> -		goto out_unlock;
> -
>  	cd->asid	= (u16)asid;
> -	cd->ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
> -	cd->tcr		= FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
> -			  FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
> -			  FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
> -			  FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
> -			  FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
> -			  FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
> -			  CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
> -	cd->mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
> -
> -	mutex_unlock(&arm_smmu_asid_lock);
> -	return 0;
> -
> -out_unlock:
>  	mutex_unlock(&arm_smmu_asid_lock);
>  	return ret;
>  }
>  
>  static int arm_smmu_domain_finalise_s2(struct arm_smmu_device *smmu,
> -				       struct arm_smmu_domain *smmu_domain,
> -				       struct io_pgtable_cfg *pgtbl_cfg)
> +				       struct arm_smmu_domain *smmu_domain)
>  {
>  	int vmid;
>  	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
> @@ -2367,8 +2357,7 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
>  	struct io_pgtable_cfg pgtbl_cfg;
>  	struct io_pgtable_ops *pgtbl_ops;
>  	int (*finalise_stage_fn)(struct arm_smmu_device *smmu,
> -				 struct arm_smmu_domain *smmu_domain,
> -				 struct io_pgtable_cfg *pgtbl_cfg);
> +				 struct arm_smmu_domain *smmu_domain);
>  
>  	/* Restrict the stage to what we can actually support */
>  	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
> @@ -2411,7 +2400,7 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
>  	smmu_domain->domain.geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1;
>  	smmu_domain->domain.geometry.force_aperture = true;
>  
> -	ret = finalise_stage_fn(smmu, smmu_domain, &pgtbl_cfg);
> +	ret = finalise_stage_fn(smmu, smmu_domain);
>  	if (ret < 0) {
>  		free_io_pgtable_ops(pgtbl_ops);
>  		return ret;
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> index 8eabcccb9420ba..468cd33b80ac35 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> @@ -587,9 +587,6 @@ struct arm_smmu_strtab_l1_desc {
>  
>  struct arm_smmu_ctx_desc {
>  	u16				asid;
> -	u64				ttbr;
> -	u64				tcr;
> -	u64				mair;
>  
>  	refcount_t			refs;
>  	struct mm_struct		*mm;
> -- 
> 2.43.2
>

Reviewed-by: Mostafa Saleh <smostafa at google.com>

Thanks,
Mostafa