Merge tag 'iommu-updates-v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Big cleanup of almost unsused parts of the IOMMU API by Christoph
   Hellwig. This mostly affects the Freescale PAMU driver.

 - New IOMMU driver for Unisoc SOCs

 - ARM SMMU Updates from Will:
     - Drop vestigial PREFETCH_ADDR support (SMMUv3)
     - Elide TLB sync logic for empty gather (SMMUv3)
     - Fix "Service Failure Mode" handling (SMMUv3)
     - New Qualcomm compatible string (SMMUv2)

 - Removal of the AMD IOMMU performance counter writeable check on AMD.
   It caused long boot delays on some machines and is only needed to
   work around an errata on some older (possibly pre-production) chips.
   If someone is still hit by this hardware issue anyway the performance
   counters will just return 0.

 - Support for targeted invalidations in the AMD IOMMU driver. Before
   that the driver only invalidated a single 4k page or the whole IO/TLB
   for an address space. This has been extended now and is mostly useful
   for emulated AMD IOMMUs.

 - Several fixes for the Shared Virtual Memory support in the Intel VT-d
   driver

 - Mediatek drivers can now be built as modules

 - Re-introduction of the forcedac boot option which got lost when
   converting the Intel VT-d driver to the common dma-iommu
   implementation.

 - Extension of the IOMMU device registration interface and support
   iommu_ops to be const again when drivers are built as modules.

* tag 'iommu-updates-v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (84 commits)
  iommu: Streamline registration interface
  iommu: Statically set module owner
  iommu/mediatek-v1: Add error handle for mtk_iommu_probe
  iommu/mediatek-v1: Avoid build fail when build as module
  iommu/mediatek: Always enable the clk on resume
  iommu/fsl-pamu: Fix uninitialized variable warning
  iommu/vt-d: Force to flush iotlb before creating superpage
  iommu/amd: Put newline after closing bracket in warning
  iommu/vt-d: Fix an error handling path in 'intel_prepare_irq_remapping()'
  iommu/vt-d: Fix build error of pasid_enable_wpe() with !X86
  iommu/amd: Remove performance counter pre-initialization test
  Revert "iommu/amd: Fix performance counter initialization"
  iommu/amd: Remove duplicate check of devid
  iommu/exynos: Remove unneeded local variable initialization
  iommu/amd: Page-specific invalidations for more than one page
  iommu/arm-smmu-v3: Remove the unused fields for PREFETCH_CONFIG command
  iommu/vt-d: Avoid unnecessary cache flush in pasid entry teardown
  iommu/vt-d: Invalidate PASID cache when root/context entry changed
  iommu/vt-d: Remove WO permissions on second-level paging entries
  iommu/vt-d: Report the right page fault address
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -1877,13 +1877,6 @@
 			bypassed by not enabling DMAR with this option. In
 			this case, gfx device will use physical address for
 			DMA.
-		forcedac [X86-64]
-			With this option iommu will not optimize to look
-			for io virtual address below 32-bit forcing dual
-			address cycle on pci bus for cards supporting greater
-			than 32-bit addressing. The default is to look
-			for translation below 32-bit and if not available
-			then look in the higher range.
 		strict [Default Off]
 			With this option on every unmap_single operation will
 			result in a hardware IOTLB flush operation as opposed
@@ -1972,6 +1965,14 @@
 		nobypass	[PPC/POWERNV]
 			Disable IOMMU bypass, using IOMMU for PCI devices.
 
+	iommu.forcedac=	[ARM64, X86] Control IOVA allocation for PCI devices.
+			Format: { "0" | "1" }
+			0 - Try to allocate a 32-bit DMA address first, before
+			  falling back to the full range if needed.
+			1 - Allocate directly from the full usable range,
+			  forcing Dual Address Cycle for PCI cards supporting
+			  greater than 32-bit addressing.
+
 	iommu.strict=	[ARM64] Configure TLB invalidation behaviour
 			Format: { "0" | "1" }
 			0 - Lazy mode.

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

@@ -34,6 +34,7 @@ properties:
         items:
           - enum:
               - qcom,sc7180-smmu-500
+              - qcom,sc7280-smmu-500
               - qcom,sc8180x-smmu-500
               - qcom,sdm845-smmu-500
               - qcom,sm8150-smmu-500

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

@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright 2020 Unisoc Inc.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/sprd,iommu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Unisoc IOMMU and Multi-media MMU
+
+maintainers:
+  - Chunyan Zhang <[email protected]>
+
+properties:
+  compatible:
+    enum:
+      - sprd,iommu-v1
+
+  "#iommu-cells":
+    const: 0
+    description:
+      Unisoc IOMMUs are all single-master IOMMU devices, therefore no
+      additional information needs to associate with its master device.
+      Please refer to the generic bindings document for more details,
+      Documentation/devicetree/bindings/iommu/iommu.txt
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    description:
+      Reference to a gate clock phandle, since access to some of IOMMUs are
+      controlled by gate clock, but this is not required.
+
+required:
+  - compatible
+  - reg
+  - "#iommu-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    iommu_disp: iommu@63000800 {
+      compatible = "sprd,iommu-v1";
+      reg = <0x63000800 0x80>;
+      #iommu-cells = <0>;
+    };
+
+  - |
+    iommu_jpg: iommu@62300300 {
+      compatible = "sprd,iommu-v1";
+      reg = <0x62300300 0x80>;
+      #iommu-cells = <0>;
+      clocks = <&mm_gate 1>;
+    };
+
+...

arch/powerpc/include/asm/fsl_pamu_stash.h

@@ -7,21 +7,15 @@
 #ifndef __FSL_PAMU_STASH_H
 #define __FSL_PAMU_STASH_H
 
+struct iommu_domain;
+
 /* cache stash targets */
 enum pamu_stash_target {
 	PAMU_ATTR_CACHE_L1 = 1,
 	PAMU_ATTR_CACHE_L2,
 	PAMU_ATTR_CACHE_L3,
 };
 
-/*
- * This attribute allows configuring stashig specific parameters
- * in the PAMU hardware.
- */
-
-struct pamu_stash_attribute {
-	u32	cpu;	/* cpu number */
-	u32	cache;	/* cache to stash to: L1,L2,L3 */
-};
+int fsl_pamu_configure_l1_stash(struct iommu_domain *domain, u32 cpu);
 
 #endif  /* __FSL_PAMU_STASH_H */

arch/x86/events/amd/iommu.c

@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/cpumask.h>
 #include <linux/slab.h>
+#include <linux/amd-iommu.h>
 
 #include "../perf_event.h"
 #include "iommu.h"

arch/x86/events/amd/iommu.h

@@ -21,23 +21,4 @@
 #define PC_MAX_SPEC_BNKS			64
 #define PC_MAX_SPEC_CNTRS			16
 
-struct amd_iommu;
-
-/* amd_iommu_init.c external support functions */
-extern int amd_iommu_get_num_iommus(void);
-
-extern bool amd_iommu_pc_supported(void);
-
-extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
-
-extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
-
-extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
-				u8 fxn, u64 *value);
-
-extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
-				u8 fxn, u64 *value);
-
-extern struct amd_iommu *get_amd_iommu(int idx);
-
 #endif /*_PERF_EVENT_AMD_IOMMU_H_*/

drivers/acpi/arm64/iort.c

@@ -968,15 +968,16 @@ static int iort_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
 static void iort_named_component_init(struct device *dev,
 				      struct acpi_iort_node *node)
 {
+	struct property_entry props[2] = {};
 	struct acpi_iort_named_component *nc;
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec)
-		return;
 
 	nc = (struct acpi_iort_named_component *)node->node_data;
-	fwspec->num_pasid_bits = FIELD_GET(ACPI_IORT_NC_PASID_BITS,
-					   nc->node_flags);
+	props[0] = PROPERTY_ENTRY_U32("pasid-num-bits",
+				      FIELD_GET(ACPI_IORT_NC_PASID_BITS,
+						nc->node_flags));
+
+	if (device_add_properties(dev, props))
+		dev_warn(dev, "Could not add device properties\n");
 }
 
 static int iort_nc_iommu_map(struct device *dev, struct acpi_iort_node *node)

drivers/gpu/drm/amd/amdkfd/kfd_iommu.c

@@ -333,10 +333,6 @@ int kfd_iommu_resume(struct kfd_dev *kfd)
 	return 0;
 }
 
-extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
-
 /** kfd_iommu_add_perf_counters - Add IOMMU performance counters to topology
  */
 int kfd_iommu_add_perf_counters(struct kfd_topology_device *kdev)

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -188,10 +188,7 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
 
 void adreno_set_llc_attributes(struct iommu_domain *iommu)
 {
-	struct io_pgtable_domain_attr pgtbl_cfg;
-
-	pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
-	iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+	iommu_set_pgtable_quirks(iommu, IO_PGTABLE_QUIRK_ARM_OUTER_WBWA);
 }
 
 struct msm_gem_address_space *

drivers/iommu/Kconfig

@@ -349,7 +349,7 @@ config S390_AP_IOMMU
 	  is not implemented as it is not necessary for VFIO.
 
 config MTK_IOMMU
-	bool "MTK IOMMU Support"
+	tristate "MediaTek IOMMU Support"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
 	select IOMMU_API
@@ -364,7 +364,7 @@ config MTK_IOMMU
 	  If unsure, say N here.
 
 config MTK_IOMMU_V1
-	bool "MTK IOMMU Version 1 (M4U gen1) Support"
+	tristate "MediaTek IOMMU Version 1 (M4U gen1) Support"
 	depends on ARM
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
@@ -408,4 +408,16 @@ config VIRTIO_IOMMU
 
 	  Say Y here if you intend to run this kernel as a guest.
 
+config SPRD_IOMMU
+	tristate "Unisoc IOMMU Support"
+	depends on ARCH_SPRD || COMPILE_TEST
+	select IOMMU_API
+	help
+	  Support for IOMMU on Unisoc's SoCs, this IOMMU can be used by
+	  Unisoc's multimedia devices, such as display, Image codec(jpeg)
+	  and a few signal processors, including VSP(video), GSP(graphic),
+	  ISP(image), and CPP(camera pixel processor), etc.
+
+	  Say Y here if you want to use the multimedia devices listed above.
+
 endif # IOMMU_SUPPORT