diff mbox series

[v4,04/16] iommu/arm-smmu-v3: Move the STE generation for S1 and S2 domains into functions

Message ID 4-v4-c93b774edcc4+42d2b-smmuv3_newapi_p1_jgg@nvidia.com (mailing list archive)
State New, archived
Headers show
Series Update SMMUv3 to the modern iommu API (part 1/3) | expand

Commit Message

Jason Gunthorpe Jan. 25, 2024, 11:57 p.m. UTC 
This is preparation to move the STE calculation higher up in to the call
chain and remove arm_smmu_write_strtab_ent(). These new functions will be
called directly from attach_dev.

Reviewed-by: Moritz Fischer <mdf@kernel.org>
Reviewed-by: Michael Shavit <mshavit@google.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Moritz Fischer <moritzf@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 115 +++++++++++---------
 1 file changed, 62 insertions(+), 53 deletions(-)

Comments

Mostafa Saleh Jan. 31, 2024, 2:50 p.m. UTC | #1 
Hi Jason,

On Thu, Jan 25, 2024 at 07:57:14PM -0400, Jason Gunthorpe wrote:
> This is preparation to move the STE calculation higher up in to the call
> chain and remove arm_smmu_write_strtab_ent(). These new functions will be
> called directly from attach_dev.
> 
> Reviewed-by: Moritz Fischer <mdf@kernel.org>
> Reviewed-by: Michael Shavit <mshavit@google.com>
> Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
> Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> Tested-by: Nicolin Chen <nicolinc@nvidia.com>
> Tested-by: Moritz Fischer <moritzf@google.com>
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 115 +++++++++++---------
>  1 file changed, 62 insertions(+), 53 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 df8fc7b87a7907..910156881423e0 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -1516,13 +1516,68 @@ static void arm_smmu_make_bypass_ste(struct arm_smmu_ste *target)
>  		FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
>  }
>  
> +static void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target,
> +				      struct arm_smmu_master *master,
> +				      struct arm_smmu_ctx_desc_cfg *cd_table)
master already include cd_table in "master->cd_table", why do we need to
pass it separately?
> +{
> +	struct arm_smmu_device *smmu = master->smmu;
> +
> +	memset(target, 0, sizeof(*target));
> +	target->data[0] = cpu_to_le64(
> +		STRTAB_STE_0_V |
> +		FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
> +		FIELD_PREP(STRTAB_STE_0_S1FMT, cd_table->s1fmt) |
> +		(cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
> +		FIELD_PREP(STRTAB_STE_0_S1CDMAX, cd_table->s1cdmax));
> +
> +	target->data[1] = cpu_to_le64(
> +		FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
> +		FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
> +		FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
> +		FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
> +		((smmu->features & ARM_SMMU_FEAT_STALLS &&
> +		  !master->stall_enabled) ?
> +			 STRTAB_STE_1_S1STALLD :
> +			 0) |
> +		FIELD_PREP(STRTAB_STE_1_EATS,
> +			   master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0) |
> +		FIELD_PREP(STRTAB_STE_1_STRW,
> +			   (smmu->features & ARM_SMMU_FEAT_E2H) ?
> +				   STRTAB_STE_1_STRW_EL2 :
> +				   STRTAB_STE_1_STRW_NSEL1));
> +}
> +
> +static void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target,
> +					struct arm_smmu_master *master,
> +					struct arm_smmu_domain *smmu_domain)
Similary, master already has the domain in "master->domain".
> +{
> +	struct arm_smmu_s2_cfg *s2_cfg = &smmu_domain->s2_cfg;
> +
> +	memset(target, 0, sizeof(*target));
> +	target->data[0] = cpu_to_le64(
> +		STRTAB_STE_0_V |
> +		FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS));
> +
> +	target->data[1] = cpu_to_le64(
> +		FIELD_PREP(STRTAB_STE_1_EATS,
> +			   master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0));
> +
> +	target->data[2] = cpu_to_le64(
> +		FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
> +		FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
> +		STRTAB_STE_2_S2AA64 |
> +#ifdef __BIG_ENDIAN
> +		STRTAB_STE_2_S2ENDI |
> +#endif
> +		STRTAB_STE_2_S2PTW |
> +		STRTAB_STE_2_S2R);
> +
> +	target->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
> +}
> +
>  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
>  				      struct arm_smmu_ste *dst)
>  {
> -	u64 val;
> -	struct arm_smmu_device *smmu = master->smmu;
> -	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
> -	struct arm_smmu_s2_cfg *s2_cfg = NULL;
>  	struct arm_smmu_domain *smmu_domain = master->domain;
>  	struct arm_smmu_ste target = {};
>  
> @@ -1537,61 +1592,15 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
>  
>  	switch (smmu_domain->stage) {
>  	case ARM_SMMU_DOMAIN_S1:
> -		cd_table = &master->cd_table;
> +		arm_smmu_make_cdtable_ste(&target, master, &master->cd_table);
>  		break;
>  	case ARM_SMMU_DOMAIN_S2:
> -		s2_cfg = &smmu_domain->s2_cfg;
> +		arm_smmu_make_s2_domain_ste(&target, master, smmu_domain);
>  		break;
>  	case ARM_SMMU_DOMAIN_BYPASS:
>  		arm_smmu_make_bypass_ste(&target);
> -		arm_smmu_write_ste(master, sid, dst, &target);
> -		return;
> +		break;
>  	}
> -
> -	/* Nuke the existing STE_0 value, as we're going to rewrite it */
> -	val = STRTAB_STE_0_V;
> -
> -	if (cd_table) {
> -		u64 strw = smmu->features & ARM_SMMU_FEAT_E2H ?
> -			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
> -
> -		target.data[1] = cpu_to_le64(
> -			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
> -			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
> -			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
> -			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
> -			 FIELD_PREP(STRTAB_STE_1_STRW, strw));
> -
> -		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
> -		    !master->stall_enabled)
> -			target.data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
> -
> -		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
> -			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
> -			FIELD_PREP(STRTAB_STE_0_S1CDMAX, cd_table->s1cdmax) |
> -			FIELD_PREP(STRTAB_STE_0_S1FMT, cd_table->s1fmt);
> -	}
> -
> -	if (s2_cfg) {
> -		target.data[2] = cpu_to_le64(
> -			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
> -			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
> -#ifdef __BIG_ENDIAN
> -			 STRTAB_STE_2_S2ENDI |
> -#endif
> -			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
> -			 STRTAB_STE_2_S2R);
> -
> -		target.data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
> -
> -		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
> -	}
> -
> -	if (master->ats_enabled)
> -		target.data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
> -						 STRTAB_STE_1_EATS_TRANS));
> -
> -	target.data[0] = cpu_to_le64(val);
>  	arm_smmu_write_ste(master, sid, dst, &target);
>  }
>  
> -- 
> 2.43.0

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

Thanks,
Mostafa
Jason Gunthorpe Jan. 31, 2024, 3:05 p.m. UTC | #2 
On Wed, Jan 31, 2024 at 02:50:42PM +0000, Mostafa Saleh wrote:
> > 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 df8fc7b87a7907..910156881423e0 100644
> > --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> > +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> > @@ -1516,13 +1516,68 @@ static void arm_smmu_make_bypass_ste(struct arm_smmu_ste *target)
> >  		FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
> >  }
> >  
> > +static void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target,
> > +				      struct arm_smmu_master *master,
> > +				      struct arm_smmu_ctx_desc_cfg *cd_table)
> master already include cd_table in "master->cd_table", why do we need to
> pass it separately?

Indeed, it could be like that, I will change it

> > +static void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target,
> > +					struct arm_smmu_master *master,
> > +					struct arm_smmu_domain *smmu_domain)
> Similary, master already has the domain in "master->domain".

A couple patches further on will delete master->domain.

Thanks,
Jason
diff mbox series

Patch

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 df8fc7b87a7907..910156881423e0 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1516,13 +1516,68 @@  static void arm_smmu_make_bypass_ste(struct arm_smmu_ste *target)
 		FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
 }
 
+static void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target,
+				      struct arm_smmu_master *master,
+				      struct arm_smmu_ctx_desc_cfg *cd_table)
+{
+	struct arm_smmu_device *smmu = master->smmu;
+
+	memset(target, 0, sizeof(*target));
+	target->data[0] = cpu_to_le64(
+		STRTAB_STE_0_V |
+		FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
+		FIELD_PREP(STRTAB_STE_0_S1FMT, cd_table->s1fmt) |
+		(cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
+		FIELD_PREP(STRTAB_STE_0_S1CDMAX, cd_table->s1cdmax));
+
+	target->data[1] = cpu_to_le64(
+		FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
+		FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
+		FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
+		FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
+		((smmu->features & ARM_SMMU_FEAT_STALLS &&
+		  !master->stall_enabled) ?
+			 STRTAB_STE_1_S1STALLD :
+			 0) |
+		FIELD_PREP(STRTAB_STE_1_EATS,
+			   master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0) |
+		FIELD_PREP(STRTAB_STE_1_STRW,
+			   (smmu->features & ARM_SMMU_FEAT_E2H) ?
+				   STRTAB_STE_1_STRW_EL2 :
+				   STRTAB_STE_1_STRW_NSEL1));
+}
+
+static void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target,
+					struct arm_smmu_master *master,
+					struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_s2_cfg *s2_cfg = &smmu_domain->s2_cfg;
+
+	memset(target, 0, sizeof(*target));
+	target->data[0] = cpu_to_le64(
+		STRTAB_STE_0_V |
+		FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS));
+
+	target->data[1] = cpu_to_le64(
+		FIELD_PREP(STRTAB_STE_1_EATS,
+			   master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0));
+
+	target->data[2] = cpu_to_le64(
+		FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
+		FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
+		STRTAB_STE_2_S2AA64 |
+#ifdef __BIG_ENDIAN
+		STRTAB_STE_2_S2ENDI |
+#endif
+		STRTAB_STE_2_S2PTW |
+		STRTAB_STE_2_S2R);
+
+	target->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+}
+
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 				      struct arm_smmu_ste *dst)
 {
-	u64 val;
-	struct arm_smmu_device *smmu = master->smmu;
-	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
-	struct arm_smmu_s2_cfg *s2_cfg = NULL;
 	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_ste target = {};
 
@@ -1537,61 +1592,15 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	switch (smmu_domain->stage) {
 	case ARM_SMMU_DOMAIN_S1:
-		cd_table = &master->cd_table;
+		arm_smmu_make_cdtable_ste(&target, master, &master->cd_table);
 		break;
 	case ARM_SMMU_DOMAIN_S2:
-		s2_cfg = &smmu_domain->s2_cfg;
+		arm_smmu_make_s2_domain_ste(&target, master, smmu_domain);
 		break;
 	case ARM_SMMU_DOMAIN_BYPASS:
 		arm_smmu_make_bypass_ste(&target);
-		arm_smmu_write_ste(master, sid, dst, &target);
-		return;
+		break;
 	}
-
-	/* Nuke the existing STE_0 value, as we're going to rewrite it */
-	val = STRTAB_STE_0_V;
-
-	if (cd_table) {
-		u64 strw = smmu->features & ARM_SMMU_FEAT_E2H ?
-			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
-
-		target.data[1] = cpu_to_le64(
-			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
-			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
-			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
-			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
-			 FIELD_PREP(STRTAB_STE_1_STRW, strw));
-
-		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
-		    !master->stall_enabled)
-			target.data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
-
-		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
-			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
-			FIELD_PREP(STRTAB_STE_0_S1CDMAX, cd_table->s1cdmax) |
-			FIELD_PREP(STRTAB_STE_0_S1FMT, cd_table->s1fmt);
-	}
-
-	if (s2_cfg) {
-		target.data[2] = cpu_to_le64(
-			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
-			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
-#ifdef __BIG_ENDIAN
-			 STRTAB_STE_2_S2ENDI |
-#endif
-			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
-			 STRTAB_STE_2_S2R);
-
-		target.data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
-
-		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
-	}
-
-	if (master->ats_enabled)
-		target.data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
-						 STRTAB_STE_1_EATS_TRANS));
-
-	target.data[0] = cpu_to_le64(val);
 	arm_smmu_write_ste(master, sid, dst, &target);
 }