Merge tag 'iommu-updates-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core:
   - IOMMU memory usage observability - This will make the memory used
     for IO page tables explicitly visible.
   - Simplify arch_setup_dma_ops()

  Intel VT-d:
   - Consolidate domain cache invalidation
   - Remove private data from page fault message
   - Allocate DMAR fault interrupts locally
   - Cleanup and refactoring

  ARM-SMMUv2:
   - Support for fault debugging hardware on Qualcomm implementations
   - Re-land support for the ->domain_alloc_paging() callback

  ARM-SMMUv3:
   - Improve handling of MSI allocation failure
   - Drop support for the "disable_bypass" cmdline option
   - Major rework of the CD creation code, following on directly from
     the STE rework merged last time around.
   - Add unit tests for the new STE/CD manipulation logic

  AMD-Vi:
   - Final part of SVA changes with generic IO page fault handling

  Renesas IPMMU:
   - Add support for R8A779H0 hardware

  ... and a couple smaller fixes and updates across the sub-tree"

* tag 'iommu-updates-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (80 commits)
  iommu/arm-smmu-v3: Make the kunit into a module
  arm64: Properly clean up iommu-dma remnants
  iommu/amd: Enable Guest Translation after reading IOMMU feature register
  iommu/vt-d: Decouple igfx_off from graphic identity mapping
  iommu/amd: Fix compilation error
  iommu/arm-smmu-v3: Add unit tests for arm_smmu_write_entry
  iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd()
  iommu/arm-smmu-v3: Move the CD generation for SVA into a function
  iommu/arm-smmu-v3: Allocate the CD table entry in advance
  iommu/arm-smmu-v3: Make arm_smmu_alloc_cd_ptr()
  iommu/arm-smmu-v3: Consolidate clearing a CD table entry
  iommu/arm-smmu-v3: Move the CD generation for S1 domains into a function
  iommu/arm-smmu-v3: Make CD programming use arm_smmu_write_entry()
  iommu/arm-smmu-v3: Add an ops indirection to the STE code
  iommu/arm-smmu-qcom: Don't build debug features as a kernel module
  iommu/amd: Add SVA domain support
  iommu: Add ops->domain_alloc_sva()
  iommu/amd: Initial SVA support for AMD IOMMU
  iommu/amd: Add support for enable/disable IOPF
  iommu/amd: Add IO page fault notifier handler
  ...

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -1435,7 +1435,7 @@ PAGE_SIZE multiple when read back.
 	  sec_pagetables
 		Amount of memory allocated for secondary page tables,
 		this currently includes KVM mmu allocations on x86
-		and arm64.
+		and arm64 and IOMMU page tables.
 
 	  percpu (npn)
 		Amount of memory used for storing per-cpu kernel

Documentation/devicetree/bindings/iommu/qcom,tbu.yaml

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/qcom,tbu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm TBU (Translation Buffer Unit)
+
+maintainers:
+  - Georgi Djakov <[email protected]>
+
+description:
+  The Qualcomm SMMU500 implementation consists of TCU and TBU. The TBU contains
+  a Translation Lookaside Buffer (TLB) that caches page tables. TBUs provides
+  debug features to trace and trigger debug transactions. There are multiple TBU
+  instances with each client core.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sc7280-tbu
+      - qcom,sdm845-tbu
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interconnects:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  qcom,stream-id-range:
+    description: |
+      Phandle of a SMMU device and Stream ID range (address and size) that
+      is assigned by the TBU
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - items:
+          - description: phandle of a smmu node
+          - description: stream id base address
+          - description: stream id size
+
+required:
+  - compatible
+  - reg
+  - qcom,stream-id-range
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sdm845.h>
+    #include <dt-bindings/interconnect/qcom,icc.h>
+    #include <dt-bindings/interconnect/qcom,sdm845.h>
+
+    tbu@150e1000 {
+        compatible = "qcom,sdm845-tbu";
+        reg = <0x150e1000 0x1000>;
+        clocks = <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>;
+        interconnects = <&system_noc MASTER_GNOC_SNOC QCOM_ICC_TAG_ACTIVE_ONLY
+                         &config_noc SLAVE_IMEM_CFG QCOM_ICC_TAG_ACTIVE_ONLY>;
+        power-domains = <&gcc HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC>;
+        qcom,stream-id-range = <&apps_smmu 0x1c00 0x400>;
+    };
+...

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml

@@ -50,6 +50,7 @@ properties:
               - renesas,ipmmu-r8a779a0           # R-Car V3U
               - renesas,ipmmu-r8a779f0           # R-Car S4-8
               - renesas,ipmmu-r8a779g0           # R-Car V4H
+              - renesas,ipmmu-r8a779h0           # R-Car V4M
           - const: renesas,rcar-gen4-ipmmu-vmsa  # R-Car Gen4
 
   reg:

Documentation/filesystems/proc.rst

@@ -1110,8 +1110,8 @@ KernelStack
 PageTables
               Memory consumed by userspace page tables
 SecPageTables
-              Memory consumed by secondary page tables, this currently
-              currently includes KVM mmu allocations on x86 and arm64.
+              Memory consumed by secondary page tables, this currently includes
+              KVM mmu and IOMMU allocations on x86 and arm64.
 NFS_Unstable
               Always zero. Previous counted pages which had been written to
               the server, but has not been committed to stable storage.

arch/arc/mm/dma.c

@@ -90,8 +90,7 @@ 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,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent

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

@@ -33,8 +33,7 @@ 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,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*

arch/arm/mm/dma-mapping.c

@@ -1709,11 +1709,15 @@ 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,
-				    bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
+	u64 dma_base = 0, size = 1ULL << 32;
 
+	if (dev->dma_range_map) {
+		dma_base = dma_range_map_min(dev->dma_range_map);
+		size = dma_range_map_max(dev->dma_range_map) - dma_base;
+	}
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
@@ -1744,17 +1748,15 @@ 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,
-				    bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 }
 
 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,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1774,7 +1776,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		return;
 
 	if (device_iommu_mapped(dev))
-		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
+		arm_setup_iommu_dma_ops(dev);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;

arch/arm64/Kconfig

@@ -46,7 +46,6 @@ config ARM64
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYSCALL_WRAPPER
-	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_ELF_PROT

arch/arm64/mm/dma-mapping.c

@@ -7,7 +7,6 @@
 #include <linux/gfp.h>
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/iommu.h>
 #include <xen/xen.h>
 
 #include <asm/cacheflush.h>
@@ -39,15 +38,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	dcache_clean_poc(start, start + size);
 }
 
-#ifdef CONFIG_IOMMU_DMA
-void arch_teardown_dma_ops(struct device *dev)
-{
-	dev->dma_ops = NULL;
-}
-#endif
-
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,8 +49,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (device_iommu_mapped(dev))
-		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
 }

arch/loongarch/kernel/dma.c

@@ -8,17 +8,12 @@
 void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
-	u64 mask, end = 0;
+	u64 mask, end;
 	const struct bus_dma_region *map = NULL;
 
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
-		const struct bus_dma_region *r = map;
-
-		for (end = 0; r->size; r++) {
-			if (r->dma_start + r->size - 1 > end)
-				end = r->dma_start + r->size - 1;
-		}
+		end = dma_range_map_max(map);
 
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;