iommu: arm-smmu: disable large page mappings for Nvidia arm-smmu

Tegra194 and Tegra234 SoCs have the erratum that causes walk cache
entries to not be invalidated correctly. The problem is that the walk
cache index generated for IOVA is not same across translation and
invalidation requests. This is leading to page faults when PMD entry is
released during unmap and populated with new PTE table during subsequent
map request. Disabling large page mappings avoids the release of PMD
entry and avoid translations seeing stale PMD entry in walk cache.
Fix this by limiting the page mappings to PAGE_SIZE for Tegra194 and
Tegra234 devices. This is recommended fix from Tegra hardware design
team.

Acked-by: Robin Murphy <[email protected]>
Reviewed-by: Krishna Reddy <[email protected]>
Co-developed-by: Pritesh Raithatha <[email protected]>
Signed-off-by: Pritesh Raithatha <[email protected]>
Signed-off-by: Ashish Mhetre <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: ashishmhetre8

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

@@ -258,6 +258,34 @@ static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct devi
 			dev_name(dev), err);
 }
 
+static int nvidia_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;
+	const struct device_node *np = smmu->dev->of_node;
+
+	/*
+	 * Tegra194 and Tegra234 SoCs have the erratum that causes walk cache
+	 * entries to not be invalidated correctly. The problem is that the walk
+	 * cache index generated for IOVA is not same across translation and
+	 * invalidation requests. This is leading to page faults when PMD entry
+	 * is released during unmap and populated with new PTE table during
+	 * subsequent map request. Disabling large page mappings avoids the
+	 * release of PMD entry and avoid translations seeing stale PMD entry in
+	 * walk cache.
+	 * Fix this by limiting the page mappings to PAGE_SIZE on Tegra194 and
+	 * Tegra234.
+	 */
+	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra194-smmu")) {
+		smmu->pgsize_bitmap = PAGE_SIZE;
+		pgtbl_cfg->pgsize_bitmap = smmu->pgsize_bitmap;
+	}
+
+	return 0;
+}
+
 static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.read_reg = nvidia_smmu_read_reg,
 	.write_reg = nvidia_smmu_write_reg,
@@ -268,10 +296,12 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.global_fault = nvidia_smmu_global_fault,
 	.context_fault = nvidia_smmu_context_fault,
 	.probe_finalize = nvidia_smmu_probe_finalize,
+	.init_context = nvidia_smmu_init_context,
 };
 
 static const struct arm_smmu_impl nvidia_smmu_single_impl = {
 	.probe_finalize = nvidia_smmu_probe_finalize,
+	.init_context = nvidia_smmu_init_context,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)