Currently in Qualcomm  SoCs the default prefetch is set to 1 which allows
the TLB to fetch just the next page table. MMU-500 features ACTLR
register which is implementation defined and is used for Qualcomm SoCs
to have a custom prefetch setting enabling TLB to prefetch the next set
of page tables accordingly allowing for faster translations.

ACTLR value is unique for each SMR (Stream matching register) and stored
in a pre-populated table. This value is set to the register during
context bank initialisation.

Signed-off-by: Bibek Kumar Patro <quic_bibekkum@quicinc.com>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 33 ++++++++++++++++++++++
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h |  1 +
 2 files changed, 34 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 0e4f3fbda961..b595fee23836 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -235,14 +235,37 @@ static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu)
 	return true;
 }

+static void qcom_smmu_set_actlr_dev(struct device *dev, struct arm_smmu_device *smmu, int cbndx,
+		const struct of_device_id *client_match)
+{
+	const struct of_device_id *match =
+			of_match_device(client_match, dev);
+
+	if (!match) {
+		dev_dbg(dev, "no ACTLR settings present\n");
+		return;
+	}
+
+	arm_smmu_cb_write(smmu, cbndx, ARM_SMMU_CB_ACTLR, (unsigned long)match->data);
+}
+
 static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
 	const struct device_node *np = smmu_domain->smmu->dev->of_node;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	const struct of_device_id *client_match;
+	int cbndx = smmu_domain->cfg.cbndx;
 	struct adreno_smmu_priv *priv;

 	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;

+	client_match = qsmmu->data->client_match;
+
+	if (client_match)
+		qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match);
+
 	/* Only enable split pagetables for the GPU device (SID 0) */
 	if (!qcom_adreno_smmu_is_gpu_device(dev))
 		return 0;
@@ -306,8 +329,18 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	const struct of_device_id *client_match;
+	int cbndx = smmu_domain->cfg.cbndx;
+
 	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;

+	client_match = qsmmu->data->client_match;
+
+	if (client_match)
+		qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match);
+
 	return 0;
 }

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
index b55cd3e3ae48..8addd453f5f1 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
@@ -28,6 +28,7 @@ struct qcom_smmu_match_data {
 	const struct qcom_smmu_config *cfg;
 	const struct arm_smmu_impl *impl;
 	const struct arm_smmu_impl *adreno_impl;
+	const struct of_device_id * const client_match;
 };

 irqreturn_t qcom_smmu_context_fault(int irq, void *dev);
--
2.34.1