iommu/arm-smmu-v3: Add SMMUv3.2 range invalidation support

Arm SMMUv3.2 adds support for TLB range invalidate operations.
Support for range invalidate is determined by the RIL bit in the IDR3
register.

The range invalidate is in units of the leaf page size and operates on
1-32 chunks of a power of 2 multiple pages. First, we determine from the
size what power of 2 multiple we can use. Then we calculate how many
chunks (1-31) of the power of 2 size for the range on the iteration. On
each iteration, we move up in size by at least 5 bits.

Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm-smmu-v3.c

@@ -69,6 +69,9 @@
 #define IDR1_SSIDSIZE			GENMASK(10, 6)
 #define IDR1_SIDSIZE			GENMASK(5, 0)
 
+#define ARM_SMMU_IDR3			0xc
+#define IDR3_RIL			(1 << 10)
+
 #define ARM_SMMU_IDR5			0x14
 #define IDR5_STALL_MAX			GENMASK(31, 16)
 #define IDR5_GRAN64K			(1 << 6)
@@ -346,9 +349,14 @@
 #define CMDQ_CFGI_1_LEAF		(1UL << 0)
 #define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
 
+#define CMDQ_TLBI_0_NUM			GENMASK_ULL(16, 12)
+#define CMDQ_TLBI_RANGE_NUM_MAX		31
+#define CMDQ_TLBI_0_SCALE		GENMASK_ULL(24, 20)
 #define CMDQ_TLBI_0_VMID		GENMASK_ULL(47, 32)
 #define CMDQ_TLBI_0_ASID		GENMASK_ULL(63, 48)
 #define CMDQ_TLBI_1_LEAF		(1UL << 0)
+#define CMDQ_TLBI_1_TTL			GENMASK_ULL(9, 8)
+#define CMDQ_TLBI_1_TG			GENMASK_ULL(11, 10)
 #define CMDQ_TLBI_1_VA_MASK		GENMASK_ULL(63, 12)
 #define CMDQ_TLBI_1_IPA_MASK		GENMASK_ULL(51, 12)
 
@@ -473,9 +481,13 @@ struct arm_smmu_cmdq_ent {
 		#define CMDQ_OP_TLBI_S2_IPA	0x2a
 		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
 		struct {
+			u8			num;
+			u8			scale;
 			u16			asid;
 			u16			vmid;
 			bool			leaf;
+			u8			ttl;
+			u8			tg;
 			u64			addr;
 		} tlbi;
 
@@ -632,6 +644,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_HYP		(1 << 12)
 #define ARM_SMMU_FEAT_STALL_FORCE	(1 << 13)
 #define ARM_SMMU_FEAT_VAX		(1 << 14)
+#define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
@@ -900,14 +913,22 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
 		break;
 	case CMDQ_OP_TLBI_S2_IPA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK;
 		break;
 	case CMDQ_OP_TLBI_NH_ASID:
@@ -2252,7 +2273,8 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 				   struct arm_smmu_domain *smmu_domain)
 {
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	unsigned long start = iova, end = iova + size;
+	unsigned long start = iova, end = iova + size, num_pages = 0, tg = 0;
+	size_t inv_range = granule;
 	struct arm_smmu_cmdq_batch cmds = {};
 	struct arm_smmu_cmdq_ent cmd = {
 		.tlbi = {
@@ -2271,10 +2293,48 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
 	}
 
+	if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
+		/* Get the leaf page size */
+		tg = __ffs(smmu_domain->domain.pgsize_bitmap);
+
+		/* Convert page size of 12,14,16 (log2) to 1,2,3 */
+		cmd.tlbi.tg = (tg - 10) / 2;
+
+		/* Determine what level the granule is at */
+		cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
+
+		num_pages = size >> tg;
+	}
+
 	while (iova < end) {
+		if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
+			/*
+			 * On each iteration of the loop, the range is 5 bits
+			 * worth of the aligned size remaining.
+			 * The range in pages is:
+			 *
+			 * range = (num_pages & (0x1f << __ffs(num_pages)))
+			 */
+			unsigned long scale, num;
+
+			/* Determine the power of 2 multiple number of pages */
+			scale = __ffs(num_pages);
+			cmd.tlbi.scale = scale;
+
+			/* Determine how many chunks of 2^scale size we have */
+			num = (num_pages >> scale) & CMDQ_TLBI_RANGE_NUM_MAX;
+			cmd.tlbi.num = num - 1;
+
+			/* range is num * 2^scale * pgsize */
+			inv_range = num << (scale + tg);
+
+			/* Clear out the lower order bits for the next iteration */
+			num_pages -= num << scale;
+		}
+
 		cmd.tlbi.addr = iova;
 		arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
-		iova += granule;
+		iova += inv_range;
 	}
 	arm_smmu_cmdq_batch_submit(smmu, &cmds);
 
@@ -3783,6 +3843,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	if (smmu->sid_bits <= STRTAB_SPLIT)
 		smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;
 
+	/* IDR3 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
+	if (FIELD_GET(IDR3_RIL, reg))
+		smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
+
 	/* IDR5 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);