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

Arm SMMU updates for 5.19

- Add new Qualcomm device-tree compatible strings

- Add new Nvidia device-tree compatible string for Tegra234

- Fix UAF in SMMUv3 shared virtual addressing code

- Force identity-mapped domains for users of ye olde SMMU legacy binding

- Minor cleanups

7 files changed, 82 insertions, 9 deletions

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index da5381c8ee11..76fc2c0f4d54 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -37,8 +37,10 @@ properties:
               - qcom,sc7180-smmu-500
               - qcom,sc7280-smmu-500
               - qcom,sc8180x-smmu-500
+              - qcom,sc8280xp-smmu-500
               - qcom,sdm845-smmu-500
               - qcom,sdx55-smmu-500
+              - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
@@ -62,8 +64,9 @@ properties:
           for improved performance.
         items:
           - enum:
-              - nvidia,tegra194-smmu
               - nvidia,tegra186-smmu
+              - nvidia,tegra194-smmu
+              - nvidia,tegra234-smmu
           - const: nvidia,smmu-500
       - items:
           - const: arm,mmu-500
@@ -157,6 +160,17 @@ properties:
   power-domains:
     maxItems: 1
 
+  nvidia,memory-controller:
+    description: |
+      A phandle to the memory controller on NVIDIA Tegra186 and later SoCs.
+      The memory controller needs to be programmed with a mapping of memory
+      client IDs to ARM SMMU stream IDs.
+
+      If this property is absent, the mapping programmed by early firmware
+      will be used and it is not guaranteed that IOMMU translations will be
+      enabled for any given device.
+    $ref: /schemas/types.yaml#/definitions/phandle
+
 required:
   - compatible
   - reg
@@ -172,13 +186,20 @@ allOf:
         compatible:
           contains:
             enum:
-              - nvidia,tegra194-smmu
               - nvidia,tegra186-smmu
+              - nvidia,tegra194-smmu
+              - nvidia,tegra234-smmu
     then:
       properties:
         reg:
           minItems: 1
           maxItems: 2
+
+      # The reference to the memory controller is required to ensure that the
+      # memory client to stream ID mapping can be done synchronously with the
+      # IOMMU attachment.
+      required:
+        - nvidia,memory-controller
     else:
       properties:
         reg:
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..1ef7bbb4acf3 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
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
 #include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 
 #include "arm-smmu-v3.h"
@@ -96,9 +97,14 @@ static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 	struct arm_smmu_ctx_desc *cd;
 	struct arm_smmu_ctx_desc *ret = NULL;
 
+	/* Don't free the mm until we release the ASID */
+	mmgrab(mm);
+
 	asid = arm64_mm_context_get(mm);
-	if (!asid)
-		return ERR_PTR(-ESRCH);
+	if (!asid) {
+		err = -ESRCH;
+		goto out_drop_mm;
+	}
 
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
 	if (!cd) {
@@ -165,6 +171,8 @@ out_free_cd:
 	kfree(cd);
 out_put_context:
 	arm64_mm_context_put(mm);
+out_drop_mm:
+	mmdrop(mm);
 	return err < 0 ? ERR_PTR(err) : ret;
 }
 
@@ -173,6 +181,7 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
 	if (arm_smmu_free_asid(cd)) {
 		/* Unpin ASID */
 		arm64_mm_context_put(cd->mm);
+		mmdrop(cd->mm);
 		kfree(cd);
 	}
 }
@@ -183,7 +192,14 @@ 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-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 627a3ed5ee8f..88817a3376ef 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3770,6 +3770,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Base address */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	if (resource_size(res) < arm_smmu_resource_size(smmu)) {
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index 2c25cce38060..658f3cc83278 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -211,7 +211,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
-	if (of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
+	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
 	    of_device_is_compatible(np, "nvidia,tegra186-smmu"))
 		return nvidia_smmu_impl_init(smmu);
 
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)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index ba6298c7140e..7820711c4560 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -408,6 +408,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sc7180-smmu-500" },
 	{ .compatible = "qcom,sc7280-smmu-500" },
 	{ .compatible = "qcom,sc8180x-smmu-500" },
+	{ .compatible = "qcom,sc8280xp-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 568cce590ccc..2ed3594f384e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1574,6 +1574,9 @@ static int arm_smmu_def_domain_type(struct device *dev)
 	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
 	const struct arm_smmu_impl *impl = cfg->smmu->impl;
 
+	if (using_legacy_binding)
+		return IOMMU_DOMAIN_IDENTITY;
+
 	if (impl && impl->def_domain_type)
 		return impl->def_domain_type(dev);
 
@@ -2092,11 +2095,10 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ioaddr = res->start;
-	smmu->base = devm_ioremap_resource(dev, res);
+	smmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
+	ioaddr = res->start;
 	/*
 	 * The resource size should effectively match the value of SMMU_TOP;
 	 * stash that temporarily until we know PAGESIZE to validate it with.