Merge tag 'iommu-updates-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - Fix race conditions in device probe path
   - Retire IOMMU bus_ops
   - Support for passing custom allocators to page table drivers
   - Clean up Kconfig around IOMMU_SVA
   - Support for sharing SVA domains with all devices bound to a mm
   - Firmware data parsing cleanup
   - Tracing improvements for iommu-dma code
   - Some smaller fixes and cleanups

  ARM-SMMU drivers:
   - Device-tree binding updates:
      - Add additional compatible strings for Qualcomm SoCs
      - Document Adreno clocks for Qualcomm's SM8350 SoC
   - SMMUv2:
      - Implement support for the ->domain_alloc_paging() callback
      - Ensure Secure context is restored following suspend of Qualcomm
        SMMU implementation
   - SMMUv3:
      - Disable stalling mode for the "quiet" context descriptor
      - Minor refactoring and driver cleanups

  Intel VT-d driver:
   - Cleanup and refactoring

  AMD IOMMU driver:
   - Improve IO TLB invalidation logic
   - Small cleanups and improvements

  Rockchip IOMMU driver:
   - DT binding update to add Rockchip RK3588

  Apple DART driver:
   - Apple M1 USB4/Thunderbolt DART support
   - Cleanups

  Virtio IOMMU driver:
   - Add support for iotlb_sync_map
   - Enable deferred IO TLB flushes"

* tag 'iommu-updates-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (66 commits)
  iommu: Don't reserve 0-length IOVA region
  iommu/vt-d: Move inline helpers to header files
  iommu/vt-d: Remove unused vcmd interfaces
  iommu/vt-d: Remove unused parameter of intel_pasid_setup_pass_through()
  iommu/vt-d: Refactor device_to_iommu() to retrieve iommu directly
  iommu/sva: Fix memory leak in iommu_sva_bind_device()
  dt-bindings: iommu: rockchip: Add Rockchip RK3588
  iommu/dma: Trace bounce buffer usage when mapping buffers
  iommu/arm-smmu: Convert to domain_alloc_paging()
  iommu/arm-smmu: Pass arm_smmu_domain to internal functions
  iommu/arm-smmu: Implement IOMMU_DOMAIN_BLOCKED
  iommu/arm-smmu: Convert to a global static identity domain
  iommu/arm-smmu: Reorganize arm_smmu_domain_add_master()
  iommu/arm-smmu-v3: Remove ARM_SMMU_DOMAIN_NESTED
  iommu/arm-smmu-v3: Master cannot be NULL in arm_smmu_write_strtab_ent()
  iommu/arm-smmu-v3: Add a type for the STE
  iommu/arm-smmu-v3: disable stall for quiet_cd
  iommu/qcom: restore IOMMU state if needed
  iommu/arm-smmu-qcom: Add QCM2290 MDSS compatible
  iommu/arm-smmu-qcom: Add missing GMU entry to match table
  ...

Author: torvalds

Documentation/devicetree/bindings/iommu/apple,dart.yaml

@@ -24,6 +24,7 @@ properties:
   compatible:
     enum:
       - apple,t8103-dart
+      - apple,t8103-usb4-dart
       - apple,t8110-dart
       - apple,t6000-dart
 

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

@@ -56,6 +56,8 @@ properties:
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
           - const: qcom,smmu-500
           - const: arm,mmu-500
 
@@ -89,6 +91,8 @@ properties:
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
+              - qcom,sm8450-smmu-500
+              - qcom,sm8550-smmu-500
           - const: qcom,adreno-smmu
           - const: qcom,smmu-500
           - const: arm,mmu-500
@@ -429,6 +433,30 @@ allOf:
             - description: interface clock required to access smmu's registers
                 through the TCU's programming interface.
 
+  - if:
+      properties:
+        compatible:
+          items:
+            - enum:
+                - qcom,sm8350-smmu-500
+            - const: qcom,adreno-smmu
+            - const: qcom,smmu-500
+            - const: arm,mmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: bus
+            - const: iface
+            - const: ahb
+            - const: hlos1_vote_gpu_smmu
+            - const: cx_gmu
+            - const: hub_cx_int
+            - const: hub_aon
+        clocks:
+          minItems: 7
+          maxItems: 7
+
   - if:
       properties:
         compatible:
@@ -453,6 +481,50 @@ allOf:
             - description: Voter clock required for HLOS SMMU access
             - description: Interface clock required for register access
 
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8450-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: gmu
+            - const: hub
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: GMU clock
+            - description: GPU HUB clock
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8550-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
   # Disallow clocks for all other platforms with specific compatibles
   - if:
       properties:
@@ -472,9 +544,8 @@ allOf:
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm6375-smmu-500
-              - qcom,sm8350-smmu-500
-              - qcom,sm8450-smmu-500
-              - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
     then:
       properties:
         clock-names: false

Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml

@@ -19,9 +19,14 @@ description: |+
 
 properties:
   compatible:
-    enum:
-      - rockchip,iommu
-      - rockchip,rk3568-iommu
+    oneOf:
+      - enum:
+          - rockchip,iommu
+          - rockchip,rk3568-iommu
+      - items:
+          - enum:
+              - rockchip,rk3588-iommu
+          - const: rockchip,rk3568-iommu
 
   reg:
     items:

arch/Kconfig

@@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
+# The architecture has a per-task state that includes the mm's PASID
+config ARCH_HAS_CPU_PASID
+	bool
+	select IOMMU_MM_DATA
+
 config HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	bool
 	help

arch/arc/mm/dma.c

@@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
  * Plug in direct dma map ops.
  */
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent

arch/arm/mm/dma-mapping-nommu.c

@@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*

arch/arm/mm/dma-mapping.c

@@ -1710,7 +1710,7 @@ void arm_iommu_detach_device(struct device *dev)
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1745,7 +1745,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 #else
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 }
 
@@ -1754,7 +1754,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1773,8 +1773,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (iommu)
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+	if (device_iommu_mapped(dev))
+		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;

arch/arm64/mm/dma-mapping.c

@@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev)
 #endif
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (iommu)
+	if (device_iommu_mapped(dev))
 		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);

arch/mips/mm/dma-noncoherent.c

@@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+		bool coherent)
 {
 	dev->dma_coherent = coherent;
 }

arch/riscv/mm/dma-noncoherent.c

@@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,