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
  ...

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,

arch/x86/Kconfig

@@ -72,6 +72,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE

arch/x86/kernel/traps.c

@@ -566,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
  */
 static bool try_fixup_enqcmd_gp(void)
 {
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	u32 pasid;
 
 	/*
@@ -592,7 +592,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (!mm_valid_pasid(current->mm))
 		return false;
 
-	pasid = current->mm->pasid;
+	pasid = mm_get_enqcmd_pasid(current->mm);
 
 	/*
 	 * Did this thread already have its PASID activated?

drivers/acpi/scan.c

@@ -1561,8 +1561,7 @@ static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev)
 	return fwspec ? fwspec->ops : NULL;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
 	int err;
 	const struct iommu_ops *ops;
@@ -1576,7 +1575,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	ops = acpi_iommu_fwspec_ops(dev);
 	if (ops) {
 		mutex_unlock(&iommu_probe_device_lock);
-		return ops;
+		return 0;
 	}
 
 	err = iort_iommu_configure_id(dev, id_in);
@@ -1593,12 +1592,14 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
 	if (err == -EPROBE_DEFER) {
-		return ERR_PTR(err);
+		return err;
 	} else if (err) {
 		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		return NULL;
+		return -ENODEV;
 	}
-	return acpi_iommu_fwspec_ops(dev);
+	if (!acpi_iommu_fwspec_ops(dev))
+		return -ENODEV;
+	return 0;
 }
 
 #else /* !CONFIG_IOMMU_API */
@@ -1610,10 +1611,9 @@ int acpi_iommu_fwspec_init(struct device *dev, u32 id,
 	return -ENODEV;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 #endif /* !CONFIG_IOMMU_API */
@@ -1627,7 +1627,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			  const u32 *input_id)
 {
-	const struct iommu_ops *iommu;
+	int ret;
 
 	if (attr == DEV_DMA_NOT_SUPPORTED) {
 		set_dma_ops(dev, &dma_dummy_ops);
@@ -1636,12 +1636,16 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 
 	acpi_arch_dma_setup(dev);
 
-	iommu = acpi_iommu_configure_id(dev, input_id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	ret = acpi_iommu_configure_id(dev, input_id);
+	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	arch_setup_dma_ops(dev, 0, U64_MAX,
-				iommu, attr == DEV_DMA_COHERENT);
+	/*
+	 * Historically this routine doesn't fail driver probing due to errors
+	 * in acpi_iommu_configure_id()
+	 */
+
+	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }

drivers/dma/tegra186-gpc-dma.c

@@ -1348,8 +1348,8 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
 static int tegra_dma_probe(struct platform_device *pdev)
 {
 	const struct tegra_dma_chip_data *cdata = NULL;
-	struct iommu_fwspec *iommu_spec;
-	unsigned int stream_id, i;
+	unsigned int i;
+	u32 stream_id;
 	struct tegra_dma *tdma;
 	int ret;
 
@@ -1378,12 +1378,10 @@ static int tegra_dma_probe(struct platform_device *pdev)
 
 	tdma->dma_dev.dev = &pdev->dev;
 
-	iommu_spec = dev_iommu_fwspec_get(&pdev->dev);
-	if (!iommu_spec) {
+	if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
 		dev_err(&pdev->dev, "Missing iommu stream-id\n");
 		return -EINVAL;
 	}
-	stream_id = iommu_spec->ids[0] & 0xffff;
 
 	ret = device_property_read_u32(&pdev->dev, "dma-channel-mask",
 				       &tdma->chan_mask);

drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c

@@ -28,19 +28,14 @@ static void
 gp10b_ltc_init(struct nvkm_ltc *ltc)
 {
 	struct nvkm_device *device = ltc->subdev.device;
-	struct iommu_fwspec *spec;
+	u32 sid;
 
 	nvkm_wr32(device, 0x17e27c, ltc->ltc_nr);
 	nvkm_wr32(device, 0x17e000, ltc->ltc_nr);
 	nvkm_wr32(device, 0x100800, ltc->ltc_nr);
 
-	spec = dev_iommu_fwspec_get(device->dev);
-	if (spec) {
-		u32 sid = spec->ids[0] & 0xffff;
-
-		/* stream ID */
+	if (tegra_dev_iommu_get_stream_id(device->dev, &sid))
 		nvkm_wr32(device, 0x160000, sid << 2);
-	}
 }
 
 static const struct nvkm_ltc_func

drivers/hv/hv_common.c

@@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent)
 	 * Hyper-V does not offer a vIOMMU in the guest
 	 * VM, so pass 0/NULL for the IOMMU settings
 	 */
-	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+	arch_setup_dma_ops(dev, 0, 0, coherent);
 }
 EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
 

drivers/iommu/Kconfig

@@ -160,6 +160,7 @@ config IOMMU_DMA
 
 # Shared Virtual Addressing
 config IOMMU_SVA
+	select IOMMU_MM_DATA
 	bool
 
 config FSL_PAMU

drivers/iommu/amd/amd_iommu.h

@@ -53,10 +53,16 @@ int amd_iommu_pdev_enable_cap_pri(struct pci_dev *pdev);
 void amd_iommu_pdev_disable_cap_pri(struct pci_dev *pdev);
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address);
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
 void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_complete(struct protection_domain *domain);
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size);
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
 int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3);

drivers/iommu/amd/amd_iommu_types.h

@@ -902,12 +902,6 @@ extern int amd_iommu_max_glx_val;
 extern u64 amd_iommu_efr;
 extern u64 amd_iommu_efr2;
 
-/*
- * This function flushes all internal caches of
- * the IOMMU used by this driver.
- */
-void iommu_flush_all_caches(struct amd_iommu *iommu);
-
 static inline int get_ioapic_devid(int id)
 {
 	struct devid_map *entry;

drivers/iommu/amd/init.c

@@ -2223,7 +2223,7 @@ static int __init amd_iommu_init_pci(void)
 		init_device_table_dma(pci_seg);
 
 	for_each_iommu(iommu)
-		iommu_flush_all_caches(iommu);
+		amd_iommu_flush_all_caches(iommu);
 
 	print_iommu_info();
 
@@ -2773,7 +2773,7 @@ static void early_enable_iommu(struct amd_iommu *iommu)
 	iommu_enable_xt(iommu);
 	iommu_enable_irtcachedis(iommu);
 	iommu_enable(iommu);
-	iommu_flush_all_caches(iommu);
+	amd_iommu_flush_all_caches(iommu);
 }
 
 /*
@@ -2829,7 +2829,7 @@ static void early_enable_iommus(void)
 			iommu_enable_xt(iommu);
 			iommu_enable_irtcachedis(iommu);
 			iommu_set_device_table(iommu);
-			iommu_flush_all_caches(iommu);
+			amd_iommu_flush_all_caches(iommu);
 		}
 	}
 }
@@ -3293,7 +3293,7 @@ static int __init state_next(void)
 				uninit_device_table_dma(pci_seg);
 
 			for_each_iommu(iommu)
-				iommu_flush_all_caches(iommu);
+				amd_iommu_flush_all_caches(iommu);
 		}
 	}
 	return ret;