IOMMU Updates for Linux v6.8

Including:
 
 	- 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
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEr9jSbILcajRFYWYyK/BELZcBGuMFAmWecQoACgkQK/BELZcB
 GuN5ZxAAzC5QUKAzANx0puk7QhPpKKlbSvj6Q7iRgCLk00KJO1+VQh9v4ouCmXqF
 kn3Ko8gddjhtrgwN0OQ54F39cLUrp1SBemy71K5YOR+vu8VKtwtmawZGeeRZ+k+B
 Eohw58oaXTiR1maYvoLixLYczLrjklqyJOQ1vZ0GxFGxDqrFByAryHDgG/3OCpJx
 C9e6PsLbbfhfqA8Kv97iKcBqniGbXxAMuodqSUG0buQ3oZgfpIP6Bt3EgUzFGPGk
 3BTlYxowS/gkjUWd3fgjQFIFLTA01u9FhpA2Jb0a4v67pUCR64YxHN7rBQ6ZChtG
 kB9laQfU9re79RsHhqQzr0JT9x/eyq7pzGzjp5TV5TPW6IW+sqjMIPhzd9P08Ef7
 BclkCVobx0jSAHOhnnG4QJiKANr2Y2oM3HfsAJccMMY45RRhUKmVqM7jxMPfGn3A
 i+inlee73xTjZXJse1EWG1fmKKMLvX9LDEp4DyOfn9CqVT+7hpZvzPjfbGr937Rm
 JlwXhF3rQXEpOCagEsbt1vOf+V0e9QiCLf1Y2KpkIkDbE5wwSD/2qLm3tFhJG3oF
 fkW+J14Cid0pj+hY0afGe0kOUOIYlimu0nFmSf0pzMH+UktZdKogSfyb1gSDsy+S
 rsZRGPFhMJ832ExqhlDfxqBebqh+jsfKynlskui6Td5C9ZULaHA=
 =q751
 -----END PGP SIGNATURE-----

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,sm8650-smmu-500
-              - qcom,sm8450-smmu-500
+              - qcom,x1e80100-smmu-500
-              - qcom,sm8550-smmu-500
     then:
       properties:
         clock-names: false

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

@@ -19,9 +19,14 @@ description: |+
 
 properties:
   compatible:
-    enum:
+    oneOf:
-      - rockchip,iommu
+      - enum:
-      - rockchip,rk3568-iommu
+          - 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)
+	if (device_iommu_mapped(dev))
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+		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,
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
-						       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,
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
-						       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);
+	ret = acpi_iommu_configure_id(dev, input_id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	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 i;
-	unsigned int stream_id, 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 (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
-	if (!iommu_spec) {
 		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 (tegra_dev_iommu_get_stream_id(device->dev, &sid))
-	if (spec) {
-		u32 sid = spec->ids[0] & 0xffff;
-
-		/* stream ID */
 		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;

drivers/iommu/amd/io_pgtable.c

@@ -369,6 +369,8 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	bool updated = false;
 	u64 __pte, *pte;
 	int ret, i, count;
+	size_t size = pgcount << __ffs(pgsize);
+	unsigned long o_iova = iova;
 
 	BUG_ON(!IS_ALIGNED(iova, pgsize));
 	BUG_ON(!IS_ALIGNED(paddr, pgsize));
@@ -424,8 +426,7 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 		 * Updates and flushing already happened in
 		 * increase_address_space().
 		 */
-		amd_iommu_domain_flush_tlb_pde(dom);
+		amd_iommu_domain_flush_pages(dom, o_iova, size);
-		amd_iommu_domain_flush_complete(dom);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 

drivers/iommu/amd/io_pgtable_v2.c

@@ -244,7 +244,6 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	unsigned long mapped_size = 0;
 	unsigned long o_iova = iova;
 	size_t size = pgcount << __ffs(pgsize);
-	int count = 0;
 	int ret = 0;
 	bool updated = false;
 
@@ -265,19 +264,14 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 
 		*pte = set_pte_attr(paddr, map_size, prot);
 
-		count++;
 		iova += map_size;
 		paddr += map_size;
 		mapped_size += map_size;
 	}
 
 out:
-	if (updated) {
+	if (updated)
-		if (count > 1)
+		amd_iommu_domain_flush_pages(pdom, o_iova, size);
-			amd_iommu_flush_tlb(&pdom->domain, 0);
-		else
-			amd_iommu_flush_page(&pdom->domain, 0, o_iova);
-	}
 
 	if (mapped)
 		*mapped += mapped_size;

drivers/iommu/amd/iommu.c

@@ -64,7 +64,7 @@ LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
 
 const struct iommu_ops amd_iommu_ops;
-const struct iommu_dirty_ops amd_dirty_ops;
+static const struct iommu_dirty_ops amd_dirty_ops;
 
 int amd_iommu_max_glx_val = -1;
 
@@ -85,6 +85,11 @@ static void detach_device(struct device *dev);
  *
  ****************************************************************************/
 
+static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom)
+{
+	return (pdom && (pdom->flags & PD_IOMMUV2_MASK));
+}
+
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
@@ -551,8 +556,6 @@ static void amd_iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	dev_iommu_priv_set(dev, NULL);
-
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
@@ -1124,68 +1127,44 @@ static inline u64 build_inv_address(u64 address, size_t size)
 }
 
 static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid, int pde)
+				  size_t size, u16 domid,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[1] |= domid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
+	/* PDE bit - we want to flush everything, not only the PTEs */
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	if (gn) {
+		cmd->data[0] |= pasid;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	if (pde) /* PDE bit - we want to flush everything, not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
-				  u64 address, size_t size)
+				  u64 address, size_t size,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[0]  = devid;
 	cmd->data[0] |= (qdep & 0xff) << 24;
 	cmd->data[1]  = devid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+	if (gn) {
-}
+		cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
+		cmd->data[1] |= (pasid & 0xff) << 16;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
-				  u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
-
-	cmd->data[0]  = pasid;
-	cmd->data[1]  = domid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-}
-
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
-				  int qdep, u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
-
-	cmd->data[0]  = devid;
-	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
-	cmd->data[0] |= (qdep  & 0xff) << 24;
-	cmd->data[1]  = devid;
-	cmd->data[1] |= (pasid & 0xff) << 16;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	cmd->data[3]  = upper_32_bits(address);
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
@@ -1341,7 +1320,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id, 1);
+				      dom_id, IOMMU_NO_PASID, false);
 		iommu_queue_command(iommu, &cmd);
 	}
 
@@ -1353,7 +1332,7 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
 	struct iommu_cmd cmd;
 
 	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			      dom_id, 1);
+			      dom_id, IOMMU_NO_PASID, false);
 	iommu_queue_command(iommu, &cmd);
 
 	iommu_completion_wait(iommu);
@@ -1392,7 +1371,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
-void iommu_flush_all_caches(struct amd_iommu *iommu)
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
 {
 	if (check_feature(FEATURE_IA)) {
 		amd_iommu_flush_all(iommu);
@@ -1406,8 +1385,8 @@ void iommu_flush_all_caches(struct amd_iommu *iommu)
 /*
  * Command send function for flushing on-device TLB
  */
-static int device_flush_iotlb(struct iommu_dev_data *dev_data,
+static int device_flush_iotlb(struct iommu_dev_data *dev_data, u64 address,
-			      u64 address, size_t size)
+			      size_t size, ioasid_t pasid, bool gn)
 {
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
@@ -1418,7 +1397,8 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	if (!iommu)
 		return -EINVAL;
 
-	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
+	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address,
+			      size, pasid, gn);
 
 	return iommu_queue_command(iommu, &cmd);
 }
@@ -1464,8 +1444,11 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 			return ret;
 	}
 
-	if (dev_data->ats_enabled)
+	if (dev_data->ats_enabled) {
-		ret = device_flush_iotlb(dev_data, 0, ~0UL);
+		/* Invalidate the entire contents of an IOTLB */
+		ret = device_flush_iotlb(dev_data, 0, ~0UL,
+					 IOMMU_NO_PASID, false);
+	}
 
 	return ret;
 }
@@ -1476,13 +1459,18 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
  * page. Otherwise it flushes the whole TLB of the IOMMU.
  */
 static void __domain_flush_pages(struct protection_domain *domain,
-				 u64 address, size_t size, int pde)
+				 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
 	int ret = 0, i;
+	ioasid_t pasid = IOMMU_NO_PASID;
+	bool gn = false;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
+	if (pdom_is_v2_pgtbl_mode(domain))
+		gn = true;
+
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, gn);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -1500,17 +1488,21 @@ static void __domain_flush_pages(struct protection_domain *domain,
 		if (!dev_data->ats_enabled)
 			continue;
 
-		ret |= device_flush_iotlb(dev_data, address, size);
+		ret |= device_flush_iotlb(dev_data, address, size, pasid, gn);
 	}
 
 	WARN_ON(ret);
 }
 
-static void domain_flush_pages(struct protection_domain *domain,
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size, int pde)
+				  u64 address, size_t size)
 {
 	if (likely(!amd_iommu_np_cache)) {
-		__domain_flush_pages(domain, address, size, pde);
+		__domain_flush_pages(domain, address, size);
+
+		/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+		amd_iommu_domain_flush_complete(domain);
+
 		return;
 	}
 
@@ -1543,16 +1535,20 @@ static void domain_flush_pages(struct protection_domain *domain,
 
 		flush_size = 1ul << min_alignment;
 
-		__domain_flush_pages(domain, address, flush_size, pde);
+		__domain_flush_pages(domain, address, flush_size);
 		address += flush_size;
 		size -= flush_size;
 	}
+
+	/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+	amd_iommu_domain_flush_complete(domain);
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
+static void amd_iommu_domain_flush_all(struct protection_domain *domain)
 {
-	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
+	amd_iommu_domain_flush_pages(domain, 0,
+				     CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 void amd_iommu_domain_flush_complete(struct protection_domain *domain)
@@ -1579,8 +1575,7 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 		unsigned long flags;
 
 		spin_lock_irqsave(&domain->lock, flags);
-		domain_flush_pages(domain, iova, size, 1);
+		amd_iommu_domain_flush_pages(domain, iova, size);
-		amd_iommu_domain_flush_complete(domain);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
 }
@@ -1858,11 +1853,8 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
 
-	/* Flush IOTLB */
+	/* Flush IOTLB and wait for the flushes to finish */
-	amd_iommu_domain_flush_tlb_pde(domain);
+	amd_iommu_domain_flush_all(domain);
-
-	/* Wait for the flushes to finish */
-	amd_iommu_domain_flush_complete(domain);
 
 	/* decrease reference counters - needs to happen after the flushes */
 	domain->dev_iommu[iommu->index] -= 1;
@@ -1896,15 +1888,6 @@ static int attach_device(struct device *dev,
 
 	do_attach(dev_data, domain);
 
-	/*
-	 * We might boot into a crash-kernel here. The crashed kernel
-	 * left the caches in the IOMMU dirty. So we have to flush
-	 * here to evict all dirty stuff.
-	 */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	amd_iommu_domain_flush_complete(domain);
-
 out:
 	spin_unlock(&dev_data->lock);
 
@@ -2048,8 +2031,7 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 	amd_iommu_update_and_flush_device_table(domain);
 
 	/* Flush domain TLB(s) and wait for completion */
-	amd_iommu_domain_flush_tlb_pde(domain);
+	amd_iommu_domain_flush_all(domain);
-	amd_iommu_domain_flush_complete(domain);
 }
 
 /*****************************************************************************
@@ -2482,10 +2464,9 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 	}
 
 	/* Flush IOTLB to mark IOPTE dirty on the next translation(s) */
-	if (domain_flush) {
+	if (domain_flush)
-		amd_iommu_domain_flush_tlb_pde(pdomain);
+		amd_iommu_domain_flush_all(pdomain);
-		amd_iommu_domain_flush_complete(pdomain);
+
-	}
 	pdomain->dirty_tracking = enable;
 	spin_unlock_irqrestore(&pdomain->lock, flags);
 
@@ -2588,8 +2569,7 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	amd_iommu_domain_flush_tlb_pde(dom);
+	amd_iommu_domain_flush_all(dom);
-	amd_iommu_domain_flush_complete(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2600,8 +2580,8 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
+	amd_iommu_domain_flush_pages(dom, gather->start,
-	amd_iommu_domain_flush_complete(dom);
+				     gather->end - gather->start + 1);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2635,7 +2615,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 	return true;
 }
 
-const struct iommu_dirty_ops amd_dirty_ops = {
+static const struct iommu_dirty_ops amd_dirty_ops = {
 	.set_dirty_tracking = amd_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = amd_iommu_read_and_clear_dirty,
 };
@@ -2666,7 +2646,7 @@ const struct iommu_ops amd_iommu_ops = {
 };
 
 static int __flush_pasid(struct protection_domain *domain, u32 pasid,
-			 u64 address, bool size)
+			 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
@@ -2675,7 +2655,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 	if (!(domain->flags & PD_IOMMUV2_MASK))
 		return -EINVAL;
 
-	build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, true);
 
 	/*
 	 * IOMMU TLB needs to be flushed before Device TLB to
@@ -2709,8 +2689,8 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 		iommu = rlookup_amd_iommu(dev_data->dev);
 		if (!iommu)
 			continue;
-		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
+		build_inv_iotlb_pages(&cmd, dev_data->devid, qdep,
-				      qdep, address, size);
+				      address, size, pasid, true);
 
 		ret = iommu_queue_command(iommu, &cmd);
 		if (ret != 0)
@@ -2730,7 +2710,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
-	return __flush_pasid(domain, pasid, address, false);
+	return __flush_pasid(domain, pasid, address, PAGE_SIZE);
 }
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
@@ -2749,8 +2729,7 @@ int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 
 static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
-	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+	return __flush_pasid(domain, pasid, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
-			     true);
 }
 
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
@@ -3111,8 +3090,8 @@ static int alloc_irq_index(struct amd_iommu *iommu, u16 devid, int count,
 	return index;
 }
 
-static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
-			  struct irte_ga *irte)
+			    struct irte_ga *irte)
 {
 	struct irq_remap_table *table;
 	struct irte_ga *entry;
@@ -3139,6 +3118,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
+	return 0;
+}
+
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte)
+{
+	bool ret;
+
+	ret = __modify_irte_ga(iommu, devid, index, irte);
+	if (ret)
+		return ret;
+
 	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
@@ -3822,8 +3813,8 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	}
 	entry->lo.fields_vapic.is_run = is_run;
 
-	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry);
+				ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif

drivers/iommu/apple-dart.c

@@ -81,6 +81,7 @@
 #define DART_T8020_TCR_BYPASS_DAPF      BIT(12)
 
 #define DART_T8020_TTBR       0x200
+#define DART_T8020_USB4_TTBR  0x400
 #define DART_T8020_TTBR_VALID BIT(31)
 #define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0
 #define DART_T8020_TTBR_SHIFT 12
@@ -368,12 +369,14 @@ apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map,
 			     u32 command)
 {
 	unsigned long flags;
-	int ret;
+	int ret, i;
 	u32 command_reg;
 
 	spin_lock_irqsave(&stream_map->dart->lock, flags);
 
-	writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT);
+	for (i = 0; i < BITS_TO_U32(stream_map->dart->num_streams); i++)
+		writel(stream_map->sidmap[i],
+		       stream_map->dart->regs + DART_T8020_STREAM_SELECT + 4 * i);
 	writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND);
 
 	ret = readl_poll_timeout_atomic(
@@ -740,7 +743,6 @@ static void apple_dart_release_device(struct device *dev)
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -908,7 +910,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 
 		ret = apple_dart_merge_master_cfg(group_master_cfg, cfg);
 		if (ret) {
-			dev_err(dev, "Failed to merge DART IOMMU grups.\n");
+			dev_err(dev, "Failed to merge DART IOMMU groups.\n");
 			iommu_group_put(group);
 			res = ERR_PTR(ret);
 			goto out;
@@ -1215,6 +1217,33 @@ static const struct apple_dart_hw apple_dart_hw_t8103 = {
 	.ttbr_shift = DART_T8020_TTBR_SHIFT,
 	.ttbr_count = 4,
 };
+
+static const struct apple_dart_hw apple_dart_hw_t8103_usb4 = {
+	.type = DART_T8020,
+	.irq_handler = apple_dart_t8020_irq,
+	.invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb,
+	.oas = 36,
+	.fmt = APPLE_DART,
+	.max_sid_count = 64,
+
+	.enable_streams = DART_T8020_STREAMS_ENABLE,
+	.lock = DART_T8020_CONFIG,
+	.lock_bit = DART_T8020_CONFIG_LOCK,
+
+	.error = DART_T8020_ERROR,
+
+	.tcr = DART_T8020_TCR,
+	.tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE,
+	.tcr_disabled = 0,
+	.tcr_bypass = 0,
+
+	.ttbr = DART_T8020_USB4_TTBR,
+	.ttbr_valid = DART_T8020_TTBR_VALID,
+	.ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT,
+	.ttbr_shift = DART_T8020_TTBR_SHIFT,
+	.ttbr_count = 4,
+};
+
 static const struct apple_dart_hw apple_dart_hw_t6000 = {
 	.type = DART_T6000,
 	.irq_handler = apple_dart_t8020_irq,
@@ -1272,7 +1301,7 @@ static __maybe_unused int apple_dart_suspend(struct device *dev)
 	unsigned int sid, idx;
 
 	for (sid = 0; sid < dart->num_streams; sid++) {
-		dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid));
+		dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid));
 		for (idx = 0; idx < dart->hw->ttbr_count; idx++)
 			dart->save_ttbr[sid][idx] =
 				readl(dart->regs + DART_TTBR(dart, sid, idx));
@@ -1307,6 +1336,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dar
 
 static const struct of_device_id apple_dart_of_match[] = {
 	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t8103-usb4-dart", .data = &apple_dart_hw_t8103_usb4 },
 	{ .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 },
 	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c

@@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						    smmu_domain);
 	}
 
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start,
+				size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
 	 * but disable translation.
 	 */
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 &quiet_cd);
 
 	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0);
 
 	smmu_mn->cleared = true;
 	mutex_unlock(&sva_lock);
@@ -325,10 +327,13 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd);
+		ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm),
+					      cd);
 		if (ret) {
-			list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head)
+			list_for_each_entry_from_reverse(
-				arm_smmu_write_ctx_desc(master, mm->pasid, NULL);
+				master, &smmu_domain->devices, domain_head)
+				arm_smmu_write_ctx_desc(
+					master, mm_get_enqcmd_pasid(mm), NULL);
 			break;
 		}
 	}
@@ -358,7 +363,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 
 	list_del(&smmu_mn->list);
 
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 NULL);
 
 	/*
 	 * If we went through clear(), we've already invalidated, and no
@@ -366,7 +372,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 	 */
 	if (!smmu_mn->cleared) {
 		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
-		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+		arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0,
+					0);
 	}
 
 	/* Frees smmu_mn */

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	bool cd_live;
 	__le64 *cdptr;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
 
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
@@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (!cd) { /* (5) */
 		val = 0;
 	} else if (cd == &quiet_cd) { /* (4) */
+		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
@@ -1249,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
-				      __le64 *dst)
+				      struct arm_smmu_ste *dst)
 {
 	/*
 	 * This is hideously complicated, but we only really care about
@@ -1267,12 +1270,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
 	 * 3. Update Config, sync
 	 */
-	u64 val = le64_to_cpu(dst[0]);
+	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
-	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
-	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1280,18 +1283,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		},
 	};
 
-	if (master) {
-		smmu_domain = master->domain;
-		smmu = master->smmu;
-	}
-
 	if (smmu_domain) {
 		switch (smmu_domain->stage) {
 		case ARM_SMMU_DOMAIN_S1:
 			cd_table = &master->cd_table;
 			break;
 		case ARM_SMMU_DOMAIN_S2:
-		case ARM_SMMU_DOMAIN_NESTED:
 			s2_cfg = &smmu_domain->s2_cfg;
 			break;
 		default:
@@ -1325,10 +1322,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
-		dst[0] = cpu_to_le64(val);
+		dst->data[0] = cpu_to_le64(val);
-		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
 						STRTAB_STE_1_SHCFG_INCOMING));
-		dst[2] = 0; /* Nuke the VMID */
+		dst->data[2] = 0; /* Nuke the VMID */
 		/*
 		 * The SMMU can perform negative caching, so we must sync
 		 * the STE regardless of whether the old value was live.
@@ -1343,7 +1340,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
 
 		BUG_ON(ste_live);
-		dst[1] = cpu_to_le64(
+		dst->data[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1352,7 +1349,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		    !master->stall_enabled)
-			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+			dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
 			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
@@ -1362,7 +1359,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	if (s2_cfg) {
 		BUG_ON(ste_live);
-		dst[2] = cpu_to_le64(
+		dst->data[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
 #ifdef __BIG_ENDIAN
@@ -1371,18 +1368,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
 	}
 
 	if (master->ats_enabled)
-		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+		dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 	/* See comment in arm_smmu_write_ctx_desc() */
-	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	WRITE_ONCE(dst->data[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1390,7 +1387,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab,
+				      unsigned int nent, bool force)
 {
 	unsigned int i;
 	u64 val = STRTAB_STE_0_V;
@@ -1401,11 +1399,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		strtab[0] = cpu_to_le64(val);
+		strtab->data[0] = cpu_to_le64(val);
-		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		strtab->data[1] = cpu_to_le64(FIELD_PREP(
-						   STRTAB_STE_1_SHCFG_INCOMING));
+			STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
-		strtab[2] = 0;
+		strtab->data[2] = 0;
-		strtab += STRTAB_STE_DWORDS;
+		strtab++;
 	}
 }
 
@@ -2171,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
-	case ARM_SMMU_DOMAIN_NESTED:
 	case ARM_SMMU_DOMAIN_S2:
 		ias = smmu->ias;
 		oas = smmu->oas;
@@ -2209,26 +2206,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	return 0;
 }
 
-static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+static struct arm_smmu_ste *
+arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 {
-	__le64 *step;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		struct arm_smmu_strtab_l1_desc *l1_desc;
+		unsigned int idx1, idx2;
-		int idx;
 
 		/* Two-level walk */
-		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		l1_desc = &cfg->l1_desc[idx];
+		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
-		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
+		return &cfg->l1_desc[idx1].l2ptr[idx2];
-		step = &l1_desc->l2ptr[idx];
 	} else {
 		/* Simple linear lookup */
-		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+		return (struct arm_smmu_ste *)&cfg
+			       ->strtab[sid * STRTAB_STE_DWORDS];
 	}
-
-	return step;
 }
 
 static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
@@ -2238,7 +2232,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i].id;
-		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step =
+			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
@@ -2649,9 +2644,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return ERR_PTR(-ENODEV);
-
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
 		return ERR_PTR(-EBUSY);
 
@@ -2698,7 +2690,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
@@ -2742,7 +2733,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
 	if (smmu_domain->smmu)
 		ret = -EPERM;
 	else
-		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
 	mutex_unlock(&smmu_domain->init_mutex);
 
 	return ret;
@@ -3769,7 +3760,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
 	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
 
 	list_for_each_entry(e, &rmr_list, list) {
-		__le64 *step;
+		struct arm_smmu_ste *step;
 		struct iommu_iort_rmr_data *rmr;
 		int ret, i;
 

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

@@ -206,6 +206,11 @@
 #define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
 
 #define STRTAB_STE_DWORDS		8
+
+struct arm_smmu_ste {
+	__le64 data[STRTAB_STE_DWORDS];
+};
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0
@@ -571,7 +576,7 @@ struct arm_smmu_priq {
 struct arm_smmu_strtab_l1_desc {
 	u8				span;
 
-	__le64				*l2ptr;
+	struct arm_smmu_ste		*l2ptr;
 	dma_addr_t			l2ptr_dma;
 };
 
@@ -710,7 +715,6 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -243,8 +243,10 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
+	{ .compatible = "qcom,adreno-gmu" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,qcm2290-mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
 	{ .compatible = "qcom,sc7280-mdss" },

drivers/iommu/arm/arm-smmu/arm-smmu.c

@@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 		pm_runtime_put_autosuspend(smmu->dev);
 }
 
+static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu)
+{
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -392,8 +409,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	u32 fsr, fsynr, cbfrsynra;
 	unsigned long iova;
-	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain = dev;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	int idx = smmu_domain->cfg.cbndx;
 	int ret;
@@ -406,7 +422,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
 	cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
 
-	ret = report_iommu_fault(domain, NULL, iova,
+	ret = report_iommu_fault(&smmu_domain->domain, NULL, iova,
 		fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ);
 
 	if (ret == -ENOSYS)
@@ -607,7 +623,7 @@ static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
 	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
 }
 
-static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+static int arm_smmu_init_domain_context(struct arm_smmu_domain *smmu_domain,
 					struct arm_smmu_device *smmu,
 					struct device *dev)
 {
@@ -616,7 +632,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	struct io_pgtable_ops *pgtbl_ops;
 	struct io_pgtable_cfg pgtbl_cfg;
 	enum io_pgtable_fmt fmt;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct iommu_domain *domain = &smmu_domain->domain;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	irqreturn_t (*context_fault)(int irq, void *dev);
 
@@ -624,12 +640,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
-		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
-		smmu_domain->smmu = smmu;
-		goto out_unlock;
-	}
-
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -796,8 +806,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	else
 		context_fault = arm_smmu_context_fault;
 
-	ret = devm_request_irq(smmu->dev, irq, context_fault,
+	ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED,
-			       IRQF_SHARED, "arm-smmu-context-fault", domain);
+			       "arm-smmu-context-fault", smmu_domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
@@ -818,14 +828,13 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	return ret;
 }
 
-static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
 
-	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (!smmu)
 		return;
 
 	ret = arm_smmu_rpm_get(smmu);
@@ -841,7 +850,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[cfg->irptndx];
-		devm_free_irq(smmu->dev, irq, domain);
+		devm_free_irq(smmu->dev, irq, smmu_domain);
 	}
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
@@ -850,14 +859,10 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	arm_smmu_rpm_put(smmu);
 }
 
-static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
-		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
-			return NULL;
-	}
 	/*
 	 * Allocate the domain and initialise some of its data structures.
 	 * We can't really do anything meaningful until we've added a
@@ -870,6 +875,15 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 	mutex_init(&smmu_domain->init_mutex);
 	spin_lock_init(&smmu_domain->cb_lock);
 
+	if (dev) {
+		struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+
+		if (arm_smmu_init_domain_context(smmu_domain, cfg->smmu, dev)) {
+			kfree(smmu_domain);
+			return NULL;
+		}
+	}
+
 	return &smmu_domain->domain;
 }
 
@@ -881,7 +895,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	 * Free the domain resources. We assume that all devices have
 	 * already been detached.
 	 */
-	arm_smmu_destroy_domain_context(domain);
+	arm_smmu_destroy_domain_context(smmu_domain);
 	kfree(smmu_domain);
 }
 
@@ -1081,21 +1095,14 @@ static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg,
 	mutex_unlock(&smmu->stream_map_mutex);
 }
 
-static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
+static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg,
-				      struct arm_smmu_master_cfg *cfg,
+					  enum arm_smmu_s2cr_type type,
-				      struct iommu_fwspec *fwspec)
+					  u8 cbndx, struct iommu_fwspec *fwspec)
 {
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_device *smmu = cfg->smmu;
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
-	u8 cbndx = smmu_domain->cfg.cbndx;
-	enum arm_smmu_s2cr_type type;
 	int i, idx;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
-		type = S2CR_TYPE_BYPASS;
-	else
-		type = S2CR_TYPE_TRANS;
-
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
 			continue;
@@ -1105,7 +1112,6 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
-	return 0;
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1116,11 +1122,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu;
 	int ret;
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops) {
-		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
-		return -ENXIO;
-	}
-
 	/*
 	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
 	 * domains between of_xlate() and probe_device() - we have no way to cope
@@ -1139,7 +1140,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return ret;
 
 	/* Ensure that the domain is finalised */
-	ret = arm_smmu_init_domain_context(domain, smmu, dev);
+	ret = arm_smmu_init_domain_context(smmu_domain, smmu, dev);
 	if (ret < 0)
 		goto rpm_put;
 
@@ -1153,27 +1154,66 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec);
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS,
-
+				      smmu_domain->cfg.cbndx, fwspec);
-	/*
+	arm_smmu_rpm_use_autosuspend(smmu);
-	 * Setup an autosuspend delay to avoid bouncing runpm state.
-	 * Otherwise, if a driver for a suspended consumer device
-	 * unmaps buffers, it will runpm resume/suspend for each one.
-	 *
-	 * For example, when used by a GPU device, when an application
-	 * or game exits, it can trigger unmapping 100s or 1000s of
-	 * buffers.  With a runpm cycle for each buffer, that adds up
-	 * to 5-10sec worth of reprogramming the context bank, while
-	 * the system appears to be locked up to the user.
-	 */
-	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
-	pm_runtime_use_autosuspend(smmu->dev);
-
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
+static int arm_smmu_attach_dev_type(struct device *dev,
+				    enum arm_smmu_s2cr_type type)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!cfg)
+		return -ENODEV;
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	arm_smmu_master_install_s2crs(cfg, type, 0, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
+	arm_smmu_rpm_put(smmu);
+	return 0;
+}
+
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS);
+}
+
+static const struct iommu_domain_ops arm_smmu_identity_ops = {
+	.attach_dev = arm_smmu_attach_dev_identity,
+};
+
+static struct iommu_domain arm_smmu_identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &arm_smmu_identity_ops,
+};
+
+static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT);
+}
+
+static const struct iommu_domain_ops arm_smmu_blocked_ops = {
+	.attach_dev = arm_smmu_attach_dev_blocked,
+};
+
+static struct iommu_domain arm_smmu_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &arm_smmu_blocked_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1357,10 +1397,8 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (ret)
 			goto out_free;
-	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
-		return ERR_PTR(-ENODEV);
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	}
 
 	ret = -EINVAL;
@@ -1427,7 +1465,6 @@ static void arm_smmu_release_device(struct device *dev)
 
 	arm_smmu_rpm_put(cfg->smmu);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -1560,8 +1597,10 @@ static int arm_smmu_def_domain_type(struct device *dev)
 }
 
 static struct iommu_ops arm_smmu_ops = {
+	.identity_domain	= &arm_smmu_identity_domain,
+	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
-	.domain_alloc		= arm_smmu_domain_alloc,
+	.domain_alloc_paging	= arm_smmu_domain_alloc_paging,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.probe_finalize		= arm_smmu_probe_finalize,
@@ -2161,7 +2200,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops,
+				    using_legacy_binding ? NULL : dev);
 	if (err) {
 		dev_err(dev, "Failed to register iommu\n");
 		iommu_device_sysfs_remove(&smmu->iommu);

drivers/iommu/arm/arm-smmu/arm-smmu.h

@@ -361,7 +361,6 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {

drivers/iommu/arm/arm-smmu/qcom_iommu.c

@@ -79,16 +79,6 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
 
 static const struct iommu_ops qcom_iommu_ops;
 
-static struct qcom_iommu_dev * to_iommu(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec || fwspec->ops != &qcom_iommu_ops)
-		return NULL;
-
-	return dev_iommu_priv_get(dev);
-}
-
 static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid)
 {
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
@@ -372,7 +362,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 
 static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	int ret;
 
@@ -404,7 +394,7 @@ static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct qcom_iommu_domain *qcom_domain;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	unsigned int i;
 
 	if (domain == identity_domain || !domain)
@@ -535,7 +525,7 @@ static bool qcom_iommu_capable(struct device *dev, enum iommu_cap cap)
 
 static struct iommu_device *qcom_iommu_probe_device(struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct device_link *link;
 
 	if (!qcom_iommu)
@@ -900,8 +890,16 @@ static void qcom_iommu_device_remove(struct platform_device *pdev)
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+	int ret;
 
-	return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	ret = clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	if (ret < 0)
+		return ret;
+
+	if (dev->pm_domain)
+		return qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, 0);
+
+	return ret;
 }
 
 static int __maybe_unused qcom_iommu_suspend(struct device *dev)

drivers/iommu/dma-iommu.c

@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
+#include <trace/events/swiotlb.h>
 
 #include "dma-iommu.h"
 
@@ -1156,6 +1157,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 			return DMA_MAPPING_ERROR;
 		}
 
+		trace_swiotlb_bounced(dev, phys, size);
+
 		aligned_size = iova_align(iovad, size);
 		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
 					      iova_mask(iovad), dir, attrs);

drivers/iommu/intel/debugfs.c

@@ -106,9 +106,6 @@ static const struct iommu_regset iommu_regs_64[] = {
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
-	IOMMU_REGSET_ENTRY(VCCAP),
-	IOMMU_REGSET_ENTRY(VCMD),
-	IOMMU_REGSET_ENTRY(VCRSP),
 };
 
 static struct dentry *intel_iommu_debug;

drivers/iommu/intel/iommu.c

@@ -46,9 +46,6 @@
 
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
 
-#define MAX_AGAW_WIDTH 64
-#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
-
 #define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1)
 #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1)
 
@@ -63,74 +60,6 @@
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 
-/* page table handling */
-#define LEVEL_STRIDE		(9)
-#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
-
-static inline int agaw_to_level(int agaw)
-{
-	return agaw + 2;
-}
-
-static inline int agaw_to_width(int agaw)
-{
-	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
-}
-
-static inline int width_to_agaw(int width)
-{
-	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
-}
-
-static inline unsigned int level_to_offset_bits(int level)
-{
-	return (level - 1) * LEVEL_STRIDE;
-}
-
-static inline int pfn_level_offset(u64 pfn, int level)
-{
-	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
-}
-
-static inline u64 level_mask(int level)
-{
-	return -1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 level_size(int level)
-{
-	return 1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 align_to_level(u64 pfn, int level)
-{
-	return (pfn + level_size(level) - 1) & level_mask(level);
-}
-
-static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
-{
-	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
-}
-
-/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
-   are never going to work. */
-static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
-{
-	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
-}
-static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
-{
-	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
-}
-static inline unsigned long page_to_dma_pfn(struct page *pg)
-{
-	return mm_to_dma_pfn_start(page_to_pfn(pg));
-}
-static inline unsigned long virt_to_dma_pfn(void *p)
-{
-	return page_to_dma_pfn(virt_to_page(p));
-}
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
@@ -168,78 +97,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_set_present(struct context_entry *context)
-{
-	context->lo |= 1;
-}
-
-static inline void context_set_fault_enable(struct context_entry *context)
-{
-	context->lo &= (((u64)-1) << 2) | 1;
-}
-
-static inline void context_set_translation_type(struct context_entry *context,
-						unsigned long value)
-{
-	context->lo &= (((u64)-1) << 4) | 3;
-	context->lo |= (value & 3) << 2;
-}
-
-static inline void context_set_address_root(struct context_entry *context,
-					    unsigned long value)
-{
-	context->lo &= ~VTD_PAGE_MASK;
-	context->lo |= value & VTD_PAGE_MASK;
-}
-
-static inline void context_set_address_width(struct context_entry *context,
-					     unsigned long value)
-{
-	context->hi |= value & 7;
-}
-
-static inline void context_set_domain_id(struct context_entry *context,
-					 unsigned long value)
-{
-	context->hi |= (value & ((1 << 16) - 1)) << 8;
-}
-
-static inline void context_set_pasid(struct context_entry *context)
-{
-	context->lo |= CONTEXT_PASIDE;
-}
-
-static inline int context_domain_id(struct context_entry *c)
-{
-	return((c->hi >> 8) & 0xffff);
-}
-
-static inline void context_clear_entry(struct context_entry *context)
-{
-	context->lo = 0;
-	context->hi = 0;
-}
-
-static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	if (!iommu->copied_tables)
-		return false;
-
-	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.
@@ -383,13 +240,12 @@ void free_pgtable_page(void *vaddr)
 	free_page((unsigned long)vaddr);
 }
 
-static inline int domain_type_is_si(struct dmar_domain *domain)
+static int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
 }
 
-static inline int domain_pfn_supported(struct dmar_domain *domain,
+static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn)
-				       unsigned long pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 
@@ -451,7 +307,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu)
 	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 }
 
-static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 {
 	return sm_supported(iommu) ?
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
@@ -703,7 +559,7 @@ static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
 	return false;
 }
 
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct pci_dev *pdev = NULL;
@@ -1574,9 +1430,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 }
 
 /* Notification for newly created mappings */
-static inline void __mapping_notify_one(struct intel_iommu *iommu,
+static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain,
-					struct dmar_domain *domain,
+				 unsigned long pfn, unsigned int pages)
-					unsigned long pfn, unsigned int pages)
 {
 	/*
 	 * It's a non-present to present mapping. Only flush if caching mode
@@ -1843,7 +1698,7 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	spin_unlock(&iommu->lock);
 }
 
-static inline int guestwidth_to_adjustwidth(int gaw)
+static int guestwidth_to_adjustwidth(int gaw)
 {
 	int agaw;
 	int r = (gaw - 12) % 9;
@@ -1877,7 +1732,7 @@ static void domain_exit(struct dmar_domain *domain)
  * Value of X in the PDTS field of a scalable mode context entry
  * indicates PASID directory with 2^(X + 7) entries.
  */
-static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+static unsigned long context_get_sm_pds(struct pasid_table *table)
 {
 	unsigned long pds, max_pde;
 
@@ -1889,38 +1744,6 @@ static inline unsigned long context_get_sm_pds(struct pasid_table *table)
 	return pds - 7;
 }
 
-/*
- * Set the RID_PASID field of a scalable mode context entry. The
- * IOMMU hardware will use the PASID value set in this field for
- * DMA translations of DMA requests without PASID.
- */
-static inline void
-context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
-{
-	context->hi |= pasid & ((1 << 20) - 1);
-}
-
-/*
- * Set the DTE(Device-TLB Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_dte(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(2);
-}
-
-/*
- * Set the PRE(Page Request Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_pre(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(4);
-}
-
-/* Convert value to context PASID directory size field coding. */
-#define context_pdts(pds)	(((pds) & 0x7) << 9)
-
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
 				      struct pasid_table *table,
@@ -2081,14 +1904,11 @@ static int domain_context_mapping_cb(struct pci_dev *pdev,
 static int
 domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct domain_context_mapping_data data;
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct pasid_table *table;
-	struct intel_iommu *iommu;
-	u8 bus, devfn;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
 
 	table = intel_pasid_get_table(dev);
 
@@ -2105,18 +1925,15 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 }
 
 /* Returns a number of VTD pages, but aligned to MM page size */
-static inline unsigned long aligned_nrpages(unsigned long host_addr,
+static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
-					    size_t size)
 {
 	host_addr &= ~PAGE_MASK;
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
 /* Return largest possible superpage level for a given mapping */
-static inline int hardware_largepage_caps(struct dmar_domain *domain,
+static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
-					  unsigned long iov_pfn,
+				   unsigned long phy_pfn, unsigned long pages)
-					  unsigned long phy_pfn,
-					  unsigned long pages)
 {
 	int support, level = 1;
 	unsigned long pfnmerge;
@@ -2449,15 +2266,10 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
-	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
 	ret = domain_attach_iommu(domain, iommu);
 	if (ret)
 		return ret;
@@ -2470,7 +2282,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		/* Setup the PASID entry for requests without PASID: */
 		if (hw_pass_through && domain_type_is_si(domain))
-			ret = intel_pasid_setup_pass_through(iommu, domain,
+			ret = intel_pasid_setup_pass_through(iommu,
 					dev, IOMMU_NO_PASID);
 		else if (domain->use_first_level)
 			ret = domain_setup_first_level(iommu, domain, dev,
@@ -3615,7 +3427,7 @@ void intel_iommu_shutdown(void)
 	up_write(&dmar_global_lock);
 }
 
-static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
+static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
 
@@ -3694,7 +3506,7 @@ const struct attribute_group *intel_iommu_groups[] = {
 	NULL,
 };
 
-static inline bool has_external_pci(void)
+static bool has_external_pci(void)
 {
 	struct pci_dev *pdev = NULL;
 
@@ -4119,14 +3931,11 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 int prepare_domain_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	int addr_width;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return -ENODEV;
-
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
@@ -4403,7 +4212,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_lookup_iommu(dev, &bus, &devfn);
 	if (!iommu || !iommu->iommu.ops)
 		return ERR_PTR(-ENODEV);
 
@@ -4461,7 +4270,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
-			dev_iommu_priv_set(dev, NULL);
 			kfree(info);
 			return ERR_PTR(ret);
 		}
@@ -4479,7 +4287,6 @@ static void intel_iommu_release_device(struct device *dev)
 	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
-	dev_iommu_priv_set(dev, NULL);
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
@@ -4739,8 +4546,9 @@ static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 	unsigned long flags;
@@ -4811,8 +4619,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		goto out_free;
 
 	if (domain_type_is_si(dmar_domain))
-		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
+		ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
-						     dev, pasid);
 	else if (dmar_domain->use_first_level)
 		ret = domain_setup_first_level(iommu, dmar_domain,
 					       dev, pasid);

drivers/iommu/intel/iommu.h

@@ -140,9 +140,6 @@
 #define DMAR_ECEO_REG		0x408
 #define DMAR_ECRSP_REG		0x410
 #define DMAR_ECCAP_REG		0x430
-#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
-#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
-#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
 
 #define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
 #define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
@@ -854,6 +851,181 @@ static inline bool context_present(struct context_entry *context)
 	return (context->lo & 1);
 }
 
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+#define MAX_AGAW_WIDTH		(64)
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
+}
+
+static inline int width_to_agaw(int width)
+{
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(u64 pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline u64 level_mask(int level)
+{
+	return -1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 level_size(int level)
+{
+	return 1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 align_to_level(u64 pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo &= ~VTD_PAGE_MASK;
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_set_pasid(struct context_entry *context)
+{
+	context->lo |= CONTEXT_PASIDE;
+}
+
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+#ifdef CONFIG_INTEL_IOMMU
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+#endif /* CONFIG_INTEL_IOMMU */
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
 struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 int dmar_enable_qi(struct intel_iommu *iommu);
@@ -900,7 +1072,6 @@ int dmar_ir_support(void);
 void *alloc_pgtable_page(int node, gfp_t gfp);
 void free_pgtable_page(void *vaddr);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data);
 

drivers/iommu/intel/pasid.c

@@ -26,63 +26,6 @@
  */
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	int ret = 0;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		*pasid = VCMD_VRSP_RESULT_PASID(res);
-		break;
-	case VCMD_VRSP_SC_NO_PASID_AVAIL:
-		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
-		ret = -ENOSPC;
-		break;
-	default:
-		ret = -ENODEV;
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-
-	return ret;
-}
-
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
-		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		break;
-	case VCMD_VRSP_SC_INVALID_PASID:
-		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
-		break;
-	default:
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-}
-
 /*
  * Per device pasid table management:
  */
@@ -230,30 +173,6 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
 /*
  * Interfaces for PASID table entry manipulation:
  */
-static inline void pasid_clear_entry(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], 0);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
-static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
 static void
 intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
@@ -269,192 +188,6 @@ intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 		pasid_clear_entry(pe);
 }
 
-static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
-{
-	u64 old;
-
-	old = READ_ONCE(*ptr);
-	WRITE_ONCE(*ptr, (old & ~mask) | bits);
-}
-
-static inline u64 pasid_get_bits(u64 *ptr)
-{
-	return READ_ONCE(*ptr);
-}
-
-/*
- * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_domain_id(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
-}
-
-/*
- * Get domain ID value of a scalable mode PASID entry.
- */
-static inline u16
-pasid_get_domain_id(struct pasid_entry *pe)
-{
-	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
-}
-
-/*
- * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_slptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
- * entry.
- */
-static inline void
-pasid_set_address_width(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
-}
-
-/*
- * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_translation_type(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
-}
-
-/*
- * Enable fault processing by clearing the FPD(Fault Processing
- * Disable) field (Bit 1) of a scalable mode PASID entry.
- */
-static inline void pasid_set_fault_enable(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 1, 0);
-}
-
-/*
- * Enable second level A/D bits by setting the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
-}
-
-/*
- * Disable second level A/D bits by clearing the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_clear_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 0);
-}
-
-/*
- * Checks if second level A/D bits specifically the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry is set.
- */
-static inline bool pasid_get_ssade(struct pasid_entry *pe)
-{
-	return pasid_get_bits(&pe->val[0]) & (1 << 9);
-}
-
-/*
- * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_sre(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 0, 1);
-}
-
-/*
- * Setup the WPE(Write Protect Enable) field (Bit 132) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_wpe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
-}
-
-/*
- * Setup the P(Present) field (Bit 0) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_present(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 0, 1);
-}
-
-/*
- * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
-{
-	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
-}
-
-/*
- * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
- * entry. It is required when XD bit of the first level page table
- * entry is about to be set.
- */
-static inline void pasid_set_nxe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
-}
-
-/*
- * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_pgsnp(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
-}
-
-/*
- * Setup the First Level Page table Pointer field (Bit 140~191)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_flptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the First Level Paging Mode field (Bit 130~131) of a
- * scalable mode PASID entry.
- */
-static inline void
-pasid_set_flpm(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
-}
-
-/*
- * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
- * of a scalable mode PASID entry.
- */
-static inline void pasid_set_eafe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
-}
-
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, u32 pasid)
@@ -613,9 +346,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
  * Skip top levels of page tables for iommu which has less agaw
  * than default. Unnecessary for PT mode.
  */
-static inline int iommu_skip_agaw(struct dmar_domain *domain,
+static int iommu_skip_agaw(struct dmar_domain *domain,
-				  struct intel_iommu *iommu,
+			   struct intel_iommu *iommu,
-				  struct dma_pte **pgd)
+			   struct dma_pte **pgd)
 {
 	int agaw;
 
@@ -767,7 +500,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
  * Set up the scalable mode pasid entry for passthrough translation type.
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;

drivers/iommu/intel/pasid.h

@@ -22,16 +22,6 @@
 #define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
 #define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
-/* Virtual command interface for enlightened pasid management. */
-#define VCMD_CMD_ALLOC			0x1
-#define VCMD_CMD_FREE			0x2
-#define VCMD_VRSP_IP			0x1
-#define VCMD_VRSP_SC(e)			(((e) & 0xff) >> 1)
-#define VCMD_VRSP_SC_SUCCESS		0
-#define VCMD_VRSP_SC_NO_PASID_AVAIL	16
-#define VCMD_VRSP_SC_INVALID_PASID	16
-#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 16) & 0xfffff)
-#define VCMD_CMD_OPERAND(e)		((e) << 16)
 /*
  * Domain ID reserved for pasid entries programmed for first-level
  * only and pass-through transfer modes.
@@ -96,6 +86,216 @@ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte)
 	return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7);
 }
 
+static inline void pasid_clear_entry(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
+{
+	u64 old;
+
+	old = READ_ONCE(*ptr);
+	WRITE_ONCE(*ptr, (old & ~mask) | bits);
+}
+
+static inline u64 pasid_get_bits(u64 *ptr)
+{
+	return READ_ONCE(*ptr);
+}
+
+/*
+ * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_domain_id(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
+}
+
+/*
+ * Get domain ID value of a scalable mode PASID entry.
+ */
+static inline u16
+pasid_get_domain_id(struct pasid_entry *pe)
+{
+	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
+}
+
+/*
+ * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_slptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
+ * entry.
+ */
+static inline void
+pasid_set_address_width(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
+}
+
+/*
+ * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_translation_type(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
+}
+
+/*
+ * Enable fault processing by clearing the FPD(Fault Processing
+ * Disable) field (Bit 1) of a scalable mode PASID entry.
+ */
+static inline void pasid_set_fault_enable(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 1, 0);
+}
+
+/*
+ * Enable second level A/D bits by setting the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
+}
+
+/*
+ * Disable second level A/D bits by clearing the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_clear_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 0);
+}
+
+/*
+ * Checks if second level A/D bits specifically the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry is set.
+ */
+static inline bool pasid_get_ssade(struct pasid_entry *pe)
+{
+	return pasid_get_bits(&pe->val[0]) & (1 << 9);
+}
+
+/*
+ * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_sre(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 0, 1);
+}
+
+/*
+ * Setup the WPE(Write Protect Enable) field (Bit 132) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_wpe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
+}
+
+/*
+ * Setup the P(Present) field (Bit 0) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 1);
+}
+
+/*
+ * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+{
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+}
+
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
+/*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_pgsnp(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
+}
+
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
@@ -111,15 +311,12 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 				     struct device *dev, u32 pasid,
 				     bool enabled);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */

drivers/iommu/intel/svm.c

@@ -316,21 +316,22 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 }
 
 static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
-			     struct mm_struct *mm)
+			     struct iommu_domain *domain, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct mm_struct *mm = domain->mm;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
 	unsigned long sflags;
 	int ret = 0;
 
-	svm = pasid_private_find(mm->pasid);
+	svm = pasid_private_find(pasid);
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
 			return -ENOMEM;
 
-		svm->pasid = mm->pasid;
+		svm->pasid = pasid;
 		svm->mm = mm;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
@@ -368,7 +369,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
 		goto free_sdev;
@@ -382,7 +383,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 free_svm:
 	if (list_empty(&svm->devs)) {
 		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(mm->pasid);
+		pasid_private_remove(pasid);
 		kfree(svm);
 	}
 
@@ -392,14 +393,9 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
-	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	struct mm_struct *mm;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return;
-
 	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
 		return;
 	mm = svm->mm;
@@ -750,25 +746,16 @@ int intel_svm_page_response(struct device *dev,
 			    struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct iommu_fault_page_request *prm;
-	struct intel_iommu *iommu;
 	bool private_present;
 	bool pasid_present;
 	bool last_page;
-	u8 bus, devfn;
 	int ret = 0;
 	u16 sid;
 
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
-	if (!msg || !evt)
-		return -EINVAL;
-
 	prm = &evt->fault.prm;
 	sid = PCI_DEVID(bus, devfn);
 	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
@@ -822,9 +809,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
-	struct mm_struct *mm = domain->mm;
 
-	return intel_svm_bind_mm(iommu, dev, mm);
+	return intel_svm_bind_mm(iommu, dev, domain, pasid);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)

drivers/iommu/io-pgtable-arm.c

@@ -188,20 +188,28 @@ static dma_addr_t __arm_lpae_dma_addr(void *pages)
 }
 
 static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
-				    struct io_pgtable_cfg *cfg)
+				    struct io_pgtable_cfg *cfg,
+				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
 	int order = get_order(size);
-	struct page *p;
 	dma_addr_t dma;
 	void *pages;
 
 	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+
-	if (!p)
+	if (cfg->alloc) {
+		pages = cfg->alloc(cookie, size, gfp);
+	} else {
+		struct page *p;
+
+		p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+		pages = p ? page_address(p) : NULL;
+	}
+
+	if (!pages)
 		return NULL;
 
-	pages = page_address(p);
 	if (!cfg->coherent_walk) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -220,18 +228,28 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 out_unmap:
 	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
 	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+
 out_free:
-	__free_pages(p, order);
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, order);
+
 	return NULL;
 }
 
 static void __arm_lpae_free_pages(void *pages, size_t size,
-				  struct io_pgtable_cfg *cfg)
+				  struct io_pgtable_cfg *cfg,
+				  void *cookie)
 {
 	if (!cfg->coherent_walk)
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
-	free_pages((unsigned long)pages, get_order(size));
+
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, get_order(size));
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
@@ -373,13 +391,13 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg, data->iop.cookie);
 		if (!cptep)
 			return -ENOMEM;
 
 		pte = arm_lpae_install_table(cptep, ptep, 0, data);
 		if (pte)
-			__arm_lpae_free_pages(cptep, tblsz, cfg);
+			__arm_lpae_free_pages(cptep, tblsz, cfg, data->iop.cookie);
 	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
 		__arm_lpae_sync_pte(ptep, 1, cfg);
 	}
@@ -524,7 +542,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
 	}
 
-	__arm_lpae_free_pages(start, table_size, &data->iop.cfg);
+	__arm_lpae_free_pages(start, table_size, &data->iop.cfg, data->iop.cookie);
 }
 
 static void arm_lpae_free_pgtable(struct io_pgtable *iop)
@@ -552,7 +570,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
 		return 0;
 
-	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg);
+	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
@@ -575,7 +593,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
 	if (pte != blk_pte) {
-		__arm_lpae_free_pages(tablep, tablesz, cfg);
+		__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
 		/*
 		 * We may race against someone unmapping another part of this
 		 * block, but anything else is invalid. We can't misinterpret
@@ -882,7 +900,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Looking good; allocate a pgd */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -984,7 +1002,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1059,7 +1077,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
-					   cfg);
+					   cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1080,26 +1098,31 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_mali_lpae_alloc_pgtable,
 	.free	= arm_lpae_free_pgtable,
 };

drivers/iommu/io-pgtable.c

@@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 };
 
+static int check_custom_allocator(enum io_pgtable_fmt fmt,
+				  struct io_pgtable_cfg *cfg)
+{
+	/* No custom allocator, no need to check the format. */
+	if (!cfg->alloc && !cfg->free)
+		return 0;
+
+	/* When passing a custom allocator, both the alloc and free
+	 * functions should be provided.
+	 */
+	if (!cfg->alloc || !cfg->free)
+		return -EINVAL;
+
+	/* Make sure the format supports custom allocators. */
+	if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR)
+		return 0;
+
+	return -EINVAL;
+}
+
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
 					    void *cookie)
@@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 	if (fmt >= IO_PGTABLE_NUM_FMTS)
 		return NULL;
 
+	if (check_custom_allocator(fmt, cfg))
+		return NULL;
+
 	fns = io_pgtable_init_table[fmt];
 	if (!fns)
 		return NULL;

drivers/iommu/iommu-sva.c

@@ -12,32 +12,42 @@
 static DEFINE_MUTEX(iommu_sva_lock);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
+	struct iommu_mm_data *iommu_mm;
 	ioasid_t pasid;
-	int ret = 0;
+
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
+	if (iommu_mm) {
-		if (mm->pasid >= dev->iommu->max_pasids)
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
-			ret = -EOVERFLOW;
+			return ERR_PTR(-EOVERFLOW);
-		goto out;
+		return iommu_mm;
 	}
 
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
+
 	pasid = iommu_alloc_global_pasid(dev);
 	if (pasid == IOMMU_PASID_INVALID) {
-		ret = -ENOSPC;
+		kfree(iommu_mm);
-		goto out;
+		return ERR_PTR(-ENOSPC);
 	}
-	mm->pasid = pasid;
+	iommu_mm->pasid = pasid;
-	ret = 0;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
-out:
+	/*
-	mutex_unlock(&iommu_sva_lock);
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
-	return ret;
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -58,57 +68,60 @@ static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
-	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, dev);
-	if (ret)
-		return ERR_PTR(ret);
-
-	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-
 	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
+
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
+	/* Allocate mm->pasid if necessary. */
-						IOMMU_DOMAIN_SVA);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
-	if (IS_ERR(domain)) {
+	if (IS_ERR(iommu_mm)) {
-		ret = PTR_ERR(domain);
+		ret = PTR_ERR(iommu_mm);
 		goto out_unlock;
 	}
 
-	if (domain) {
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-		domain->users++;
+	if (!handle) {
-		goto out;
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
 	domain = iommu_sva_domain_alloc(dev, mm);
 	if (!domain) {
 		ret = -ENOMEM;
-		goto out_unlock;
+		goto out_free_handle;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+	list_add(&domain->next, &mm->iommu_mm->sva_domains);
+
 out:
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+out_free_handle:
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -124,12 +137,13 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
 	mutex_unlock(&iommu_sva_lock);
@@ -141,7 +155,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
 
-	return domain->mm->pasid;
+	return mm_get_enqcmd_pasid(domain->mm);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
 
@@ -205,8 +219,11 @@ iommu_sva_handle_iopf(struct iommu_fault *fault, void *data)
 
 void mm_pasid_drop(struct mm_struct *mm)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
 		return;
 
-	iommu_free_global_pasid(mm->pasid);
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
 }

drivers/iommu/iommu.c

@@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
-static struct bus_type * const iommu_buses[] = {
+static const struct bus_type * const iommu_buses[] = {
 	&platform_bus_type,
 #ifdef CONFIG_PCI
 	&pci_bus_type,
@@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu,
 	/* We need to be able to take module references appropriately */
 	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
 		return -EINVAL;
-	/*
-	 * Temporarily enforce global restriction to a single driver. This was
-	 * already the de-facto behaviour, since any possible combination of
-	 * existing drivers would compete for at least the PCI or platform bus.
-	 */
-	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
-		return -EBUSY;
 
 	iommu->ops = ops;
 	if (hwdev)
@@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++)
-		iommu_buses[i]->iommu_ops = ops;
 		err = bus_iommu_probe(iommu_buses[i]);
-	}
 	if (err)
 		iommu_device_unregister(iommu);
 	return err;
@@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	bus->iommu_ops = ops;
 	err = bus_iommu_probe(bus);
 	if (err) {
 		iommu_device_unregister_bus(iommu, bus, nb);
@@ -344,6 +334,8 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
 
+	lockdep_assert_held(&iommu_probe_device_lock);
+
 	if (param)
 		return param;
 
@@ -368,6 +360,15 @@ static void dev_iommu_free(struct device *dev)
 	kfree(param);
 }
 
+/*
+ * Internal equivalent of device_iommu_mapped() for when we care that a device
+ * actually has API ops, and don't want false positives from VFIO-only groups.
+ */
+static bool dev_has_iommu(struct device *dev)
+{
+	return dev->iommu && dev->iommu->iommu_dev;
+}
+
 static u32 dev_iommu_get_max_pasids(struct device *dev)
 {
 	u32 max_pasids = 0, bits = 0;
@@ -386,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev)
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+void dev_iommu_priv_set(struct device *dev, void *priv)
+{
+	/* FSL_PAMU does something weird */
+	if (!IS_ENABLED(CONFIG_FSL_PAMU))
+		lockdep_assert_held(&iommu_probe_device_lock);
+	dev->iommu->priv = priv;
+}
+EXPORT_SYMBOL_GPL(dev_iommu_priv_set);
+
 /*
  * Init the dev->iommu and dev->iommu_group in the struct device and get the
  * driver probed
@@ -489,11 +499,26 @@ DEFINE_MUTEX(iommu_probe_device_lock);
 
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec;
 	struct iommu_group *group;
 	struct group_device *gdev;
 	int ret;
 
+	/*
+	 * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU
+	 * instances with non-NULL fwnodes, and client devices should have been
+	 * identified with a fwspec by this point. Otherwise, we can currently
+	 * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can
+	 * be present, and that any of their registered instances has suitable
+	 * ops for probing, and thus cheekily co-opt the same mechanism.
+	 */
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec && fwspec->ops)
+		ops = fwspec->ops;
+	else
+		ops = iommu_ops_from_fwnode(NULL);
+
 	if (!ops)
 		return -ENODEV;
 	/*
@@ -618,7 +643,7 @@ static void __iommu_group_remove_device(struct device *dev)
 
 		list_del(&device->list);
 		__iommu_group_free_device(group, device);
-		if (dev->iommu && dev->iommu->iommu_dev)
+		if (dev_has_iommu(dev))
 			iommu_deinit_device(dev);
 		else
 			dev->iommu_group = NULL;
@@ -817,7 +842,7 @@ int iommu_get_group_resv_regions(struct iommu_group *group,
 		 * Non-API groups still expose reserved_regions in sysfs,
 		 * so filter out calls that get here that way.
 		 */
-		if (!device->dev->iommu)
+		if (!dev_has_iommu(device->dev))
 			break;
 
 		INIT_LIST_HEAD(&dev_resv_regions);
@@ -1223,6 +1248,12 @@ void iommu_group_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
+static struct device *iommu_group_first_dev(struct iommu_group *group)
+{
+	lockdep_assert_held(&group->mutex);
+	return list_first_entry(&group->devices, struct group_device, list)->dev;
+}
+
 /**
  * iommu_group_for_each_dev - iterate over each device in the group
  * @group: the group
@@ -1750,23 +1781,6 @@ __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	return __iommu_group_domain_alloc(group, req_type);
 }
 
-/*
- * Returns the iommu_ops for the devices in an iommu group.
- *
- * It is assumed that all devices in an iommu group are managed by a single
- * IOMMU unit. Therefore, this returns the dev_iommu_ops of the first device
- * in the group.
- */
-static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
-{
-	struct group_device *device =
-		list_first_entry(&group->devices, struct group_device, list);
-
-	lockdep_assert_held(&group->mutex);
-
-	return dev_iommu_ops(device->dev);
-}
-
 /*
  * req_type of 0 means "auto" which means to select a domain based on
  * iommu_def_domain_type or what the driver actually supports.
@@ -1774,7 +1788,7 @@ static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
 static struct iommu_domain *
 iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group));
 	struct iommu_domain *dom;
 
 	lockdep_assert_held(&group->mutex);
@@ -1854,7 +1868,7 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 static int iommu_get_def_domain_type(struct iommu_group *group,
 				     struct device *dev, int cur_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
 	if (!ops->def_domain_type)
@@ -2003,9 +2017,28 @@ int bus_iommu_probe(const struct bus_type *bus)
 	return 0;
 }
 
+/**
+ * iommu_present() - make platform-specific assumptions about an IOMMU
+ * @bus: bus to check
+ *
+ * Do not use this function. You want device_iommu_mapped() instead.
+ *
+ * Return: true if some IOMMU is present and aware of devices on the given bus;
+ * in general it may not be the only IOMMU, and it may not have anything to do
+ * with whatever device you are ultimately interested in.
+ */
 bool iommu_present(const struct bus_type *bus)
 {
-	return bus->iommu_ops != NULL;
+	bool ret = false;
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
+		if (iommu_buses[i] == bus) {
+			spin_lock(&iommu_device_lock);
+			ret = !list_empty(&iommu_device_list);
+			spin_unlock(&iommu_device_lock);
+		}
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
@@ -2021,7 +2054,7 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	const struct iommu_ops *ops;
 
-	if (!dev->iommu || !dev->iommu->iommu_dev)
+	if (!dev_has_iommu(dev))
 		return false;
 
 	ops = dev_iommu_ops(dev);
@@ -2107,6 +2140,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 		return ERR_PTR(-ENOMEM);
 
 	domain->type = type;
+	domain->owner = ops;
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
@@ -2132,21 +2166,37 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 static struct iommu_domain *
 __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 {
-	struct device *dev =
+	struct device *dev = iommu_group_first_dev(group);
-		list_first_entry(&group->devices, struct group_device, list)
-			->dev;
 
-	return __iommu_domain_alloc(group_iommu_ops(group), dev, type);
+	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
+}
+
+static int __iommu_domain_alloc_dev(struct device *dev, void *data)
+{
+	const struct iommu_ops **ops = data;
+
+	if (!dev_has_iommu(dev))
+		return 0;
+
+	if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
+		      "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
+		      dev_bus_name(dev)))
+		return -EBUSY;
+
+	*ops = dev_iommu_ops(dev);
+	return 0;
 }
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
+	const struct iommu_ops *ops = NULL;
+	int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
 	struct iommu_domain *domain;
 
-	if (bus == NULL || bus->iommu_ops == NULL)
+	if (err || !ops)
 		return NULL;
-	domain = __iommu_domain_alloc(bus->iommu_ops, NULL,
+
-				    IOMMU_DOMAIN_UNMANAGED);
+	domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
 	if (IS_ERR(domain))
 		return NULL;
 	return domain;
@@ -2284,10 +2334,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
+	struct device *dev;
+
 	if (group->domain && group->domain != group->default_domain &&
 	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
+	dev = iommu_group_first_dev(group);
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	return __iommu_group_set_domain(group, domain);
 }
 
@@ -3004,8 +3060,8 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
  */
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
+	if (dev_has_iommu(dev)) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_enable_feat)
 			return ops->dev_enable_feat(dev, feat);
@@ -3020,8 +3076,8 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
  */
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
+	if (dev_has_iommu(dev)) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_disable_feat)
 			return ops->dev_disable_feat(dev, feat);
@@ -3481,6 +3537,9 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	if (!group)
 		return -ENODEV;
 
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	mutex_lock(&group->mutex);
 	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
 	if (curr) {
@@ -3569,6 +3628,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
 	domain->type = IOMMU_DOMAIN_SVA;
 	mmgrab(mm);
 	domain->mm = mm;
+	domain->owner = ops;
 	domain->iopf_handler = iommu_sva_handle_iopf;
 	domain->fault_data = mm;
 

drivers/iommu/iommufd/hw_pagetable.c

@@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			hwpt->domain = NULL;
 			goto out_abort;
 		}
+		hwpt->domain->owner = ops;
 	} else {
 		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
 		if (!hwpt->domain) {
@@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		hwpt->domain = NULL;
 		goto out_abort;
 	}
+	hwpt->domain->owner = ops;
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;

drivers/iommu/mtk_iommu.c

@@ -863,16 +863,11 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct device_link *link;
 	struct device *larbdev;
 	unsigned int larbid, larbidx, i;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
-	data = dev_iommu_priv_get(dev);
-
 	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		return &data->iommu;
 

drivers/iommu/mtk_iommu_v1.c

@@ -481,9 +481,6 @@ static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
 		idx++;
 	}
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
 	data = dev_iommu_priv_get(dev);
 
 	/* Link the consumer device with the smi-larb device(supplier) */

drivers/iommu/of_iommu.c

@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/fsl/mc.h>
 
-#define NO_IOMMU	1
-
 static int of_iommu_xlate(struct device *dev,
 			  struct of_phandle_args *iommu_spec)
 {
@@ -29,7 +27,7 @@ static int of_iommu_xlate(struct device *dev,
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
 	    !of_device_is_available(iommu_spec->np))
-		return NO_IOMMU;
+		return -ENODEV;
 
 	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
 	if (ret)
@@ -61,7 +59,7 @@ static int of_iommu_configure_dev_id(struct device_node *master_np,
 			 "iommu-map-mask", &iommu_spec.np,
 			 iommu_spec.args);
 	if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+		return err;
 
 	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
@@ -72,7 +70,7 @@ static int of_iommu_configure_dev(struct device_node *master_np,
 				  struct device *dev)
 {
 	struct of_phandle_args iommu_spec;
-	int err = NO_IOMMU, idx = 0;
+	int err = -ENODEV, idx = 0;
 
 	while (!of_parse_phandle_with_args(master_np, "iommus",
 					   "#iommu-cells",
@@ -107,16 +105,21 @@ static int of_iommu_configure_device(struct device_node *master_np,
 		      of_iommu_configure_dev(master_np, dev);
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
+/*
-					   struct device_node *master_np,
+ * Returns:
-					   const u32 *id)
+ *  0 on success, an iommu was configured
+ *  -ENODEV if the device does not have any IOMMU
+ *  -EPROBEDEFER if probing should be tried again
+ *  -errno fatal errors
+ */
+int of_iommu_configure(struct device *dev, struct device_node *master_np,
+		       const u32 *id)
 {
-	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
-	int err = NO_IOMMU;
+	int err;
 
 	if (!master_np)
-		return NULL;
+		return -ENODEV;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
@@ -124,7 +127,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	if (fwspec) {
 		if (fwspec->ops) {
 			mutex_unlock(&iommu_probe_device_lock);
-			return fwspec->ops;
+			return 0;
 		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
@@ -147,36 +150,21 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	} else {
 		err = of_iommu_configure_device(master_np, dev, id);
 	}
-
-	/*
-	 * Two success conditions can be represented by non-negative err here:
-	 * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
-	 *  0 : we found an IOMMU, and dev->fwspec is initialised appropriately
-	 * <0 : any actual error
-	 */
-	if (!err) {
-		/* The fwspec pointer changed, read it again */
-		fwspec = dev_iommu_fwspec_get(dev);
-		ops    = fwspec->ops;
-	}
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
+	if (err == -ENODEV || err == -EPROBE_DEFER)
-	 * If we have reason to believe the IOMMU driver missed the initial
+		return err;
-	 * probe for dev, replay it to get things in order.
+	if (err)
-	 */
+		goto err_log;
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
 
-	/* Ignore all other errors apart from EPROBE_DEFER */
+	err = iommu_probe_device(dev);
-	if (err == -EPROBE_DEFER) {
+	if (err)
-		ops = ERR_PTR(err);
+		goto err_log;
-	} else if (err < 0) {
+	return 0;
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		ops = NULL;
-	}
 
-	return ops;
+err_log:
+	dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+	return err;
 }
 
 static enum iommu_resv_type __maybe_unused
@@ -260,7 +248,14 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				phys_addr_t iova;
 				size_t length;
 
+				if (of_dma_is_coherent(dev->of_node))
+					prot |= IOMMU_CACHE;
+
 				maps = of_translate_dma_region(np, maps, &iova, &length);
+				if (length == 0) {
+					dev_warn(dev, "Cannot reserve IOVA region of 0 size\n");
+					continue;
+				}
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
 				region = iommu_alloc_resv_region(iova, length, prot, type,

drivers/iommu/omap-iommu.c

@@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(arch_data);
 
 }

drivers/iommu/sprd-iommu.c

@@ -385,13 +385,7 @@ static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static struct iommu_device *sprd_iommu_probe_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
-	struct sprd_iommu_device *sdev;
-
-	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
-		return ERR_PTR(-ENODEV);
-
-	sdev = dev_iommu_priv_get(dev);
 
 	return &sdev->iommu;
 }

drivers/iommu/virtio-iommu.c

@@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			.flags		= cpu_to_le32(flags),
 		};
 
-		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
 		if (ret) {
 			viommu_del_mappings(vdomain, iova, end);
 			return ret;
@@ -912,6 +912,33 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
 	viommu_sync_req(vdomain->viommu);
 }
 
+static int viommu_iotlb_sync_map(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return 0;
+	return viommu_sync_req(vdomain->viommu);
+}
+
+static void viommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return;
+	viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -969,9 +996,6 @@ static struct iommu_device *viommu_probe_device(struct device *dev)
 	struct viommu_dev *viommu = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &viommu_ops)
-		return ERR_PTR(-ENODEV);
-
 	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
 	if (!viommu)
 		return ERR_PTR(-ENODEV);
@@ -1037,6 +1061,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
+	case IOMMU_CAP_DEFERRED_FLUSH:
+		return true;
 	default:
 		return false;
 	}
@@ -1057,7 +1083,9 @@ static struct iommu_ops viommu_ops = {
 		.map_pages		= viommu_map_pages,
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
+		.flush_iotlb_all	= viommu_flush_iotlb_all,
 		.iotlb_sync		= viommu_iotlb_sync,
+		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
 	}
 };

drivers/memory/tegra/tegra186.c

@@ -114,9 +114,12 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
 static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 {
 #if IS_ENABLED(CONFIG_IOMMU_API)
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct of_phandle_args args;
 	unsigned int i, index = 0;
+	u32 sid;
+
+	if (!tegra_dev_iommu_get_stream_id(dev, &sid))
+		return 0;
 
 	while (!of_parse_phandle_with_args(dev->of_node, "interconnects", "#interconnect-cells",
 					   index, &args)) {
@@ -124,11 +127,10 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 			for (i = 0; i < mc->soc->num_clients; i++) {
 				const struct tegra_mc_client *client = &mc->soc->clients[i];
 
-				if (client->id == args.args[0]) {
+				if (client->id == args.args[0])
-					u32 sid = fwspec->ids[0] & MC_SID_STREAMID_OVERRIDE_MASK;
+					tegra186_mc_client_sid_override(
-
+						mc, client,
-					tegra186_mc_client_sid_override(mc, client, sid);
+						sid & MC_SID_STREAMID_OVERRIDE_MASK);
-				}
 			}
 		}
 

drivers/of/device.c

@@ -93,12 +93,12 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	const struct iommu_ops *iommu;
 	const struct bus_dma_region *map = NULL;
 	struct device_node *bus_np;
 	u64 dma_start = 0;
 	u64 mask, end, size = 0;
 	bool coherent;
+	int iommu_ret;
 	int ret;
 
 	if (np == dev->of_node)
@@ -181,21 +181,29 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np, id);
+	iommu_ret = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+	if (iommu_ret == -EPROBE_DEFER) {
 		/* Don't touch range map if it wasn't set from a valid dma-ranges */
 		if (!ret)
 			dev->dma_range_map = NULL;
 		kfree(map);
 		return -EPROBE_DEFER;
-	}
+	} else if (iommu_ret == -ENODEV) {
+		dev_dbg(dev, "device is not behind an iommu\n");
+	} else if (iommu_ret) {
+		dev_err(dev, "iommu configuration for device failed with %pe\n",
+			ERR_PTR(iommu_ret));
 
-	dev_dbg(dev, "device is%sbehind an iommu\n",
+		/*
-		iommu ? " " : " not ");
+		 * Historically this routine doesn't fail driver probing
+		 * due to errors in of_iommu_configure()
+		 */
+	} else
+		dev_dbg(dev, "device is behind an iommu\n");
 
-	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
-	if (!iommu)
+	if (iommu_ret)
 		of_dma_set_restricted_buffer(dev, np);
 
 	return 0;

include/acpi/acpi_bus.h

@@ -719,6 +719,8 @@ struct acpi_pci_root {
 
 /* helper */
 
+struct iommu_ops;
+
 bool acpi_dma_supported(const struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,

include/linux/device.h

@@ -42,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;

include/linux/device/bus.h

@@ -62,9 +62,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -104,8 +101,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 

include/linux/dma-map-ops.h

@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 struct cma;
+struct iommu_ops;
 
 /*
  * Values for struct dma_map_ops.flags:
@@ -426,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 
 #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);
 #else
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+		u64 size, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */

include/linux/io-pgtable.h

@@ -100,6 +100,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -241,16 +265,26 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 		iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
 }
 
+/**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
 /**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;

include/linux/iommu.h

@@ -106,7 +106,7 @@ struct iommu_domain {
 	unsigned type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
-
+	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
@@ -121,6 +121,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -812,6 +817,11 @@ struct iommu_sva {
 	struct iommu_domain		*domain;
 };
 
+struct iommu_mm_data {
+	u32			pasid;
+	struct list_head	sva_domains;
+};
+
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
@@ -840,10 +850,7 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
+void dev_iommu_priv_set(struct device *dev, void *priv);
-{
-	dev->iommu->priv = priv;
-}
 
 extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
@@ -1337,15 +1344,33 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
 }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
+}
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
@@ -1368,6 +1393,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
 #endif /* CONFIG_IOMMU_SVA */
 

include/linux/mm_types.h

@@ -730,6 +730,7 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
 		/*
@@ -941,8 +942,8 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
-		u32 pasid;
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*

include/linux/of_iommu.h

@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
-					struct device_node *master_np,
+			      const u32 *id);
-					const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
+static inline int of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
+				     struct device_node *master_np,
-					 const u32 *id)
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,

include/linux/sched.h

@@ -957,7 +957,7 @@ struct task_struct {
 	/* Recursion prevention for eventfd_signal() */
 	unsigned			in_eventfd:1;
 #endif
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	unsigned			pasid_activated:1;
 #endif
 #ifdef	CONFIG_CPU_SUP_INTEL

kernel/fork.c

@@ -1173,7 +1173,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->use_memdelay = 0;
 #endif
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	tsk->pasid_activated = 0;
 #endif
 

mm/Kconfig

@@ -1258,6 +1258,9 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config IOMMU_MM_DATA
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu

mm/init-mm.c

@@ -44,9 +44,6 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_SVA
-	.pasid		= IOMMU_PASID_INVALID,
-#endif
 	INIT_MM_CONTEXT(init_mm)
 };