Merge tag 'arm-smmu-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into iommu/fixes

Arm SMMU fixes for 5.18

- Fix off-by-one in SMMUv3 SVA TLB invalidation

- Disable large mappings to workaround nvidia erratum

2 files changed, 38 insertions, 1 deletions

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 22ddd05bbdcd..c623dae1e115 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -183,7 +183,14 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
 {
 	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
 	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
-	size_t size = end - start + 1;
+	size_t size;
+
+	/*
+	 * The mm_types defines vm_end as the first byte after the end address,
+	 * different from IOMMU subsystem using the last address of an address
+	 * range. So do a simple translation here by calculating size correctly.
+	 */
+	size = end - start;
 
 	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM))
 		arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 01e9b50b10a1..87bf522b9d2e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/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)