[PATCH v18 1/4] iommu/arm-smmu-qcom: Add implementation for the adreno GPU SMMU

[Jordan Crouse <jcrouse@codeaurora.org>]

Add a special implementation for the SMMU attached to most Adreno GPU
target triggered from the qcom,adreno-smmu compatible string.

The new Adreno SMMU implementation will enable split pagetables
(TTBR1) for the domain attached to the GPU device (SID 0) and
hard code it context bank 0 so the GPU hardware can implement
per-instance pagetables.

Co-developed-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---

 drivers/iommu/arm/arm-smmu/arm-smmu-impl.c |   3 +
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 151 ++++++++++++++++++++-
 drivers/iommu/arm/arm-smmu/arm-smmu.h      |   1 +
 3 files changed, 153 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index 88f17cc33023..d199b4bff15d 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -223,6 +223,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
 		return qcom_smmu_impl_init(smmu);
 
+	if (of_device_is_compatible(smmu->dev->of_node, "qcom,adreno-smmu"))
+		return qcom_adreno_smmu_impl_init(smmu);
+
 	if (of_device_is_compatible(np, "marvell,ap806-smmu-500"))
 		smmu->impl = &mrvl_mmu500_impl;
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index be4318044f96..1e942eed2dfc 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2019, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/adreno-smmu-priv.h>
 #include <linux/of_device.h>
 #include <linux/qcom_scm.h>
 
@@ -12,6 +13,134 @@ struct qcom_smmu {
 	struct arm_smmu_device smmu;
 };
 
+#define QCOM_ADRENO_SMMU_GPU_SID 0
+
+static bool qcom_adreno_smmu_is_gpu_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i;
+
+	/*
+	 * The GPU will always use SID 0 so that is a handy way to uniquely
+	 * identify it and configure it for per-instance pagetables
+	 */
+	for (i = 0; i < fwspec->num_ids; i++) {
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+
+		if (sid == QCOM_ADRENO_SMMU_GPU_SID)
+			return true;
+	}
+
+	return false;
+}
+
+static const struct io_pgtable_cfg *qcom_adreno_smmu_get_ttbr1_cfg(
+		const void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct io_pgtable *pgtable =
+		io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops);
+	return &pgtable->cfg;
+}
+
+/*
+ * Local implementation to configure TTBR0 with the specified pagetable config.
+ * The GPU driver will call this to enable TTBR0 when per-instance pagetables
+ * are active
+ */
+
+static int qcom_adreno_smmu_set_ttbr0_cfg(const void *cookie,
+		const struct io_pgtable_cfg *pgtbl_cfg)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct io_pgtable *pgtable = io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops);
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_cb *cb = &smmu_domain->smmu->cbs[cfg->cbndx];
+
+	/* The domain must have split pagetables already enabled */
+	if (cb->tcr[0] & ARM_SMMU_TCR_EPD1)
+		return -EINVAL;
+
+	/* If the pagetable config is NULL, disable TTBR0 */
+	if (!pgtbl_cfg) {
+		/* Do nothing if it is already disabled */
+		if ((cb->tcr[0] & ARM_SMMU_TCR_EPD0))
+			return -EINVAL;
+
+		/* Set TCR to the original configuration */
+		cb->tcr[0] = arm_smmu_lpae_tcr(&pgtable->cfg);
+		cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid);
+	} else {
+		u32 tcr = cb->tcr[0];
+
+		/* Don't call this again if TTBR0 is already enabled */
+		if (!(cb->tcr[0] & ARM_SMMU_TCR_EPD0))
+			return -EINVAL;
+
+		tcr |= arm_smmu_lpae_tcr(pgtbl_cfg);
+		tcr &= ~(ARM_SMMU_TCR_EPD0 | ARM_SMMU_TCR_EPD1);
+
+		cb->tcr[0] = tcr;
+		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+		cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid);
+	}
+
+	arm_smmu_write_context_bank(smmu_domain->smmu, cb->cfg->cbndx);
+
+	return 0;
+}
+
+static int qcom_adreno_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
+					       struct arm_smmu_device *smmu,
+					       struct device *dev, int start)
+{
+	int count;
+
+	/*
+	 * Assign context bank 0 to the GPU device so the GPU hardware can
+	 * switch pagetables
+	 */
+	if (qcom_adreno_smmu_is_gpu_device(dev)) {
+		start = 0;
+		count = 1;
+	} else {
+		start = 1;
+		count = smmu->num_context_banks;
+	}
+
+	return __arm_smmu_alloc_bitmap(smmu->context_map, start, count);
+}
+
+static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	struct adreno_smmu_priv *priv;
+
+	/* Only enable split pagetables for the GPU device (SID 0) */
+	if (!qcom_adreno_smmu_is_gpu_device(dev))
+		return 0;
+
+	/*
+	 * All targets that use the qcom,adreno-smmu compatible string *should*
+	 * be AARCH64 stage 1 but double check because the arm-smmu code assumes
+	 * that is the case when the TTBR1 quirk is enabled
+	 */
+	if ((smmu_domain->stage == ARM_SMMU_DOMAIN_S1) &&
+	    (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64))
+		pgtbl_cfg->quirks |= IO_PGTABLE_QUIRK_ARM_TTBR1;
+
+	/*
+	 * Initialize private interface with GPU:
+	 */
+
+	priv = dev_get_drvdata(dev);
+	priv->cookie = smmu_domain;
+	priv->get_ttbr1_cfg = qcom_adreno_smmu_get_ttbr1_cfg;
+	priv->set_ttbr0_cfg = qcom_adreno_smmu_set_ttbr0_cfg;
+
+	return 0;
+}
+
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
 	{ .compatible = "qcom,mdp4" },
@@ -65,7 +194,15 @@ static const struct arm_smmu_impl qcom_smmu_impl = {
 	.reset = qcom_smmu500_reset,
 };
 
-struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
+	.init_context = qcom_adreno_smmu_init_context,
+	.def_domain_type = qcom_smmu_def_domain_type,
+	.reset = qcom_smmu500_reset,
+	.alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
+};
+
+static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
+		const struct arm_smmu_impl *impl)
 {
 	struct qcom_smmu *qsmmu;
 
@@ -75,8 +212,18 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
 
 	qsmmu->smmu = *smmu;
 
-	qsmmu->smmu.impl = &qcom_smmu_impl;
+	qsmmu->smmu.impl = impl;
 	devm_kfree(smmu->dev, smmu);
 
 	return &qsmmu->smmu;
 }
+
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	return qcom_smmu_create(smmu, &qcom_smmu_impl);
+}
+
+struct arm_smmu_device *qcom_adreno_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	return qcom_smmu_create(smmu, &qcom_adreno_smmu_impl);
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 1a746476927c..6c5ff9999eae 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -520,6 +520,7 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *qcom_adreno_smmu_impl_init(struct arm_smmu_device *smmu);
 
 void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx);
 int arm_mmu500_reset(struct arm_smmu_device *smmu);
-- 
2.25.1