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

Arm SMMU updates for 5.9

- Support for SMMU-500 implementation in Marvell Armada-AP806 SoC

- Support for SMMU-500 implementation in NVIDIA Tegra194 SoC

- DT compatible string updates

- Remove unused IOMMU_SYS_CACHE_ONLY flag

Author: joergroedel

Documentation/arm64/silicon-errata.rst

@@ -125,6 +125,9 @@ stable kernels.
 | Cavium         | ThunderX2 Core  | #219            | CAVIUM_TX2_ERRATUM_219      |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| Marvell        | ARM-MMU-500     | #582743         | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -37,7 +37,18 @@ properties:
           - enum:
               - qcom,sc7180-smmu-500
               - qcom,sdm845-smmu-500
+              - qcom,sm8150-smmu-500
+              - qcom,sm8250-smmu-500
           - const: arm,mmu-500
+      - description: Marvell SoCs implementing "arm,mmu-500"
+        items:
+          - const: marvell,ap806-smmu-500
+          - const: arm,mmu-500
+      - description: NVIDIA SoCs that program two ARM MMU-500s identically
+        items:
+          - enum:
+              - nvidia,tegra194-smmu
+          - const: nvidia,smmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -55,7 +66,8 @@ properties:
           - cavium,smmu-v2
 
   reg:
-    maxItems: 1
+    minItems: 1
+    maxItems: 2
 
   '#global-interrupts':
     description: The number of global interrupts exposed by the device.
@@ -138,6 +150,23 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 2
+    else:
+      properties:
+        reg:
+          maxItems: 1
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */

MAINTAINERS

@@ -16810,8 +16810,10 @@ F:	drivers/i2c/busses/i2c-tegra.c
 
 TEGRA IOMMU DRIVERS
 M:	Thierry Reding <[email protected]>
+R:	Krishna Reddy <[email protected]>
 L:	[email protected]
 S:	Supported
+F:	drivers/iommu/arm-smmu-nvidia.c
 F:	drivers/iommu/tegra*
 
 TEGRA KBC DRIVER

drivers/iommu/Makefile

@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o

drivers/iommu/arm-smmu-impl.c

@@ -147,16 +147,57 @@ static const struct arm_smmu_impl arm_mmu500_impl = {
 	.reset = arm_mmu500_reset,
 };
 
+static u64 mrvl_mmu500_readq(struct arm_smmu_device *smmu, int page, int off)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the readq to double readl
+	 */
+	return hi_lo_readq_relaxed(arm_smmu_page(smmu, page) + off);
+}
+
+static void mrvl_mmu500_writeq(struct arm_smmu_device *smmu, int page, int off,
+			       u64 val)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the writeq to double writel
+	 */
+	hi_lo_writeq_relaxed(val, arm_smmu_page(smmu, page) + off);
+}
+
+static int mrvl_mmu500_cfg_probe(struct arm_smmu_device *smmu)
+{
+
+	/*
+	 * Armada-AP806 erratum #582743.
+	 * Hide the SMMU_IDR2.PTFSv8 fields to sidestep the AArch64
+	 * formats altogether and allow using 32 bits access on the
+	 * interconnect.
+	 */
+	smmu->features &= ~(ARM_SMMU_FEAT_FMT_AARCH64_4K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_16K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_64K);
+
+	return 0;
+}
+
+static const struct arm_smmu_impl mrvl_mmu500_impl = {
+	.read_reg64 = mrvl_mmu500_readq,
+	.write_reg64 = mrvl_mmu500_writeq,
+	.cfg_probe = mrvl_mmu500_cfg_probe,
+	.reset = arm_mmu500_reset,
+};
+
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 {
 	const struct device_node *np = smmu->dev->of_node;
 
 	/*
-	 * We will inevitably have to combine model-specific implementation
-	 * quirks with platform-specific integration quirks, but everything
-	 * we currently support happens to work out as straightforward
-	 * mutually-exclusive assignments.
+	 * Set the impl for model-specific implementation quirks first,
+	 * such that platform integration quirks can pick it up and
+	 * inherit from it if necessary.
 	 */
 	switch (smmu->model) {
 	case ARM_MMU500:
@@ -168,12 +209,21 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 		break;
 	}
 
+	/* This is implicitly MMU-400 */
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
+	if (of_device_is_compatible(np, "nvidia,tegra194-smmu"))
+		return nvidia_smmu_impl_init(smmu);
+
 	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
-	    of_device_is_compatible(np, "qcom,sc7180-smmu-500"))
+	    of_device_is_compatible(np, "qcom,sc7180-smmu-500") ||
+	    of_device_is_compatible(np, "qcom,sm8150-smmu-500") ||
+	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
 		return qcom_smmu_impl_init(smmu);
 
+	if (of_device_is_compatible(np, "marvell,ap806-smmu-500"))
+		smmu->impl = &mrvl_mmu500_impl;
+
 	return smmu;
 }