iommu/arm-smmu-v3: Add arm_smmu_strtab_l1/2_idx()

Don't open code the calculations of the indexes for each level, provide
two functions to do that math and call them in all the places. Update all
the places computing indexes.

Calculate the L1 table size directly based on the max required index from
the cap. Remove STRTAB_L1_SZ_SHIFT in favour of STRTAB_NUM_L2_STES.

Use STRTAB_NUM_L2_STES to replace remaining open coded 1 << STRTAB_SPLIT.
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v4-6416877274e1+1af-smmuv3_tidy_jgg@nvidia.comSigned-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -1710,17 +1710,15 @@ static void arm_smmu_init_initial_stes(struct arm_smmu_ste *strtab,
 static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 {
 	size_t size;
-	void *strtab;
 	dma_addr_t l2ptr_dma;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
-	struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];
+	struct arm_smmu_strtab_l1_desc *desc;
 
+	desc = &cfg->l1_desc[arm_smmu_strtab_l1_idx(sid)];
 	if (desc->l2ptr)
 		return 0;
 
-	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
-	strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
-
+	size = STRTAB_NUM_L2_STES * sizeof(struct arm_smmu_ste);
 	desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &l2ptr_dma,
 					  GFP_KERNEL);
 	if (!desc->l2ptr) {
@@ -1730,8 +1728,9 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 		return -ENOMEM;
 	}
 
-	arm_smmu_init_initial_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
-	arm_smmu_write_strtab_l1_desc(strtab, l2ptr_dma);
+	arm_smmu_init_initial_stes(desc->l2ptr, STRTAB_NUM_L2_STES);
+	arm_smmu_write_strtab_l1_desc(&cfg->strtab[arm_smmu_strtab_l1_idx(sid)],
+				      l2ptr_dma);
 	return 0;
 }
 
@@ -2486,12 +2485,9 @@ arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		unsigned int idx1, idx2;
-
 		/* Two-level walk */
-		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
-		return &cfg->l1_desc[idx1].l2ptr[idx2];
+		return &cfg->l1_desc[arm_smmu_strtab_l1_idx(sid)]
+				.l2ptr[arm_smmu_strtab_l2_idx(sid)];
 	} else {
 		/* Simple linear lookup */
 		return (struct arm_smmu_ste *)&cfg
@@ -3195,12 +3191,9 @@ struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
 
 static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
 {
-	unsigned long limit = smmu->strtab_cfg.num_l1_ents;
-
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
-		limit *= 1UL << STRTAB_SPLIT;
-
-	return sid < limit;
+		return arm_smmu_strtab_l1_idx(sid) < smmu->strtab_cfg.num_l1_ents;
+	return sid < smmu->strtab_cfg.num_l1_ents;
 }
 
 static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
@@ -3637,19 +3630,18 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 {
 	void *strtab;
 	u64 reg;
-	u32 size, l1size;
+	u32 l1size;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	unsigned int last_sid_idx =
+		arm_smmu_strtab_l1_idx((1 << smmu->sid_bits) - 1);
 
 	/* Calculate the L1 size, capped to the SIDSIZE. */
-	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
-	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
-	cfg->num_l1_ents = 1 << size;
-
-	size += STRTAB_SPLIT;
-	if (size < smmu->sid_bits)
+	cfg->num_l1_ents = min(last_sid_idx + 1, STRTAB_MAX_L1_ENTRIES);
+	if (cfg->num_l1_ents <= last_sid_idx)
 		dev_warn(smmu->dev,
 			 "2-level strtab only covers %u/%u bits of SID\n",
-			 size, smmu->sid_bits);
+			 ilog2(cfg->num_l1_ents * STRTAB_NUM_L2_STES),
+			 smmu->sid_bits);
 
 	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
 	strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
@@ -3664,7 +3656,8 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 
 	/* Configure strtab_base_cfg for 2 levels */
 	reg  = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_2LVL);
-	reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, size);
+	reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE,
+			  ilog2(cfg->num_l1_ents) + STRTAB_SPLIT);
 	reg |= FIELD_PREP(STRTAB_BASE_CFG_SPLIT, STRTAB_SPLIT);
 	cfg->strtab_base_cfg = reg;
 

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

@@ -204,7 +204,6 @@ struct arm_smmu_device;
  * 2lvl: 128k L1 entries,
  *       256 lazy entries per table (each table covers a PCI bus)
  */
-#define STRTAB_L1_SZ_SHIFT		20
 #define STRTAB_SPLIT			8
 
 #define STRTAB_L1_DESC_DWORDS		1
@@ -217,6 +216,19 @@ struct arm_smmu_ste {
 	__le64 data[STRTAB_STE_DWORDS];
 };
 
+#define STRTAB_NUM_L2_STES		(1 << STRTAB_SPLIT)
+#define STRTAB_MAX_L1_ENTRIES		(1 << 17)
+
+static inline u32 arm_smmu_strtab_l1_idx(u32 sid)
+{
+	return sid / STRTAB_NUM_L2_STES;
+}
+
+static inline u32 arm_smmu_strtab_l2_idx(u32 sid)
+{
+	return sid % STRTAB_NUM_L2_STES;
+}
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0