Merge branches 'apple/dart', 'arm/smmu', 'iommu/fixes', 'x86/amd', 'x86/vt-d' and 'core' into next

Author: joergroedel

Documentation/ABI/testing/sysfs-kernel-iommu_groups

@@ -42,8 +42,12 @@ Description:	/sys/kernel/iommu_groups/<grp_id>/type shows the type of default
 		========  ======================================================
 		DMA       All the DMA transactions from the device in this group
 		          are translated by the iommu.
+		DMA-FQ    As above, but using batched invalidation to lazily
+		          remove translations after use. This may offer reduced
+			  overhead at the cost of reduced memory protection.
 		identity  All the DMA transactions from the device in this group
-		          are not translated by the iommu.
+		          are not translated by the iommu. Maximum performance
+			  but zero protection.
 		auto      Change to the type the device was booted with.
 		========  ======================================================
 

Documentation/admin-guide/kernel-parameters.txt

@@ -290,10 +290,7 @@
 	amd_iommu=	[HW,X86-64]
 			Pass parameters to the AMD IOMMU driver in the system.
 			Possible values are:
-			fullflush - enable flushing of IO/TLB entries when
-				    they are unmapped. Otherwise they are
-				    flushed before they will be reused, which
-				    is a lot of faster
+			fullflush - Deprecated, equivalent to iommu.strict=1
 			off	  - do not initialize any AMD IOMMU found in
 				    the system
 			force_isolation - Force device isolation for all
@@ -1944,18 +1941,17 @@
 			this case, gfx device will use physical address for
 			DMA.
 		strict [Default Off]
-			With this option on every unmap_single operation will
-			result in a hardware IOTLB flush operation as opposed
-			to batching them for performance.
+			Deprecated, equivalent to iommu.strict=1.
 		sp_off [Default Off]
 			By default, super page will be supported if Intel IOMMU
 			has the capability. With this option, super page will
 			not be supported.
-		sm_on [Default Off]
-			By default, scalable mode will be disabled even if the
-			hardware advertises that it has support for the scalable
-			mode translation. With this option set, scalable mode
-			will be used on hardware which claims to support it.
+		sm_on
+			Enable the Intel IOMMU scalable mode if the hardware
+			advertises that it has support for the scalable mode
+			translation.
+		sm_off
+			Disallow use of the Intel IOMMU scalable mode.
 		tboot_noforce [Default Off]
 			Do not force the Intel IOMMU enabled under tboot.
 			By default, tboot will force Intel IOMMU on, which
@@ -2047,13 +2043,12 @@
 			  throughput at the cost of reduced device isolation.
 			  Will fall back to strict mode if not supported by
 			  the relevant IOMMU driver.
-			1 - Strict mode (default).
+			1 - Strict mode.
 			  DMA unmap operations invalidate IOMMU hardware TLBs
 			  synchronously.
-			Note: on x86, the default behaviour depends on the
-			equivalent driver-specific parameters, but a strict
-			mode explicitly specified by either method takes
-			precedence.
+			unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
+			Note: on x86, strict mode specified via one of the
+			legacy driver-specific options takes precedence.
 
 	iommu.passthrough=
 			[ARM64, X86] Configure DMA to bypass the IOMMU by default.

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

@@ -0,0 +1,81 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/apple,dart.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Apple DART IOMMU
+
+maintainers:
+  - Sven Peter <[email protected]>
+
+description: |+
+  Apple SoCs may contain an implementation of their Device Address
+  Resolution Table which provides a mandatory layer of address
+  translations for various masters.
+
+  Each DART instance is capable of handling up to 16 different streams
+  with individual pagetables and page-level read/write protection flags.
+
+  This DART IOMMU also raises interrupts in response to various
+  fault conditions.
+
+properties:
+  compatible:
+    const: apple,t8103-dart
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    description:
+      Reference to the gate clock phandle if required for this IOMMU.
+      Optional since not all IOMMUs are attached to a clock gate.
+
+  '#iommu-cells':
+    const: 1
+    description:
+      Has to be one. The single cell describes the stream id emitted by
+      a master to the IOMMU.
+
+required:
+  - compatible
+  - reg
+  - '#iommu-cells'
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |+
+    dart1: iommu@82f80000 {
+      compatible = "apple,t8103-dart";
+      reg = <0x82f80000 0x4000>;
+      interrupts = <1 781 4>;
+      #iommu-cells = <1>;
+    };
+
+    master1 {
+      iommus = <&dart1 0>;
+    };
+
+  - |+
+    dart2a: iommu@82f00000 {
+      compatible = "apple,t8103-dart";
+      reg = <0x82f00000 0x4000>;
+      interrupts = <1 781 4>;
+      #iommu-cells = <1>;
+    };
+    dart2b: iommu@82f80000 {
+      compatible = "apple,t8103-dart";
+      reg = <0x82f80000 0x4000>;
+      interrupts = <1 781 4>;
+      #iommu-cells = <1>;
+    };
+
+    master2 {
+      iommus = <&dart2a 0>, <&dart2b 1>;
+    };

MAINTAINERS

@@ -1262,6 +1262,13 @@ L:	[email protected]
 S:	Odd fixes
 F:	drivers/input/mouse/bcm5974.c
 
+APPLE DART IOMMU DRIVER
+M:	Sven Peter <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	Documentation/devicetree/bindings/iommu/apple,dart.yaml
+F:	drivers/iommu/apple-dart.c
+
 APPLE SMC DRIVER
 M:	Henrik Rydberg <[email protected]>
 L:	[email protected]

drivers/iommu/Kconfig

@@ -79,16 +79,57 @@ config IOMMU_DEBUGFS
 	  debug/iommu directory, and then populate a subdirectory with
 	  entries as required.
 
-config IOMMU_DEFAULT_PASSTHROUGH
-	bool "IOMMU passthrough by default"
+choice
+	prompt "IOMMU default domain type"
 	depends on IOMMU_API
+	default IOMMU_DEFAULT_DMA_LAZY if AMD_IOMMU || INTEL_IOMMU
+	default IOMMU_DEFAULT_DMA_STRICT
 	help
-	  Enable passthrough by default, removing the need to pass in
-	  iommu.passthrough=on or iommu=pt through command line. If this
-	  is enabled, you can still disable with iommu.passthrough=off
-	  or iommu=nopt depending on the architecture.
+	  Choose the type of IOMMU domain used to manage DMA API usage by
+	  device drivers. The options here typically represent different
+	  levels of tradeoff between robustness/security and performance,
+	  depending on the IOMMU driver. Not all IOMMUs support all options.
+	  This choice can be overridden at boot via the command line, and for
+	  some devices also at runtime via sysfs.
 
-	  If unsure, say N here.
+	  If unsure, keep the default.
+
+config IOMMU_DEFAULT_DMA_STRICT
+	bool "Translated - Strict"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, with strict TLB invalidation on unmap. Equivalent
+	  to passing "iommu.passthrough=0 iommu.strict=1" on the command line.
+
+	  Untrusted devices always use this mode, with an additional layer of
+	  bounce-buffering such that they cannot gain access to any unrelated
+	  data within a mapped page.
+
+config IOMMU_DEFAULT_DMA_LAZY
+	bool "Translated - Lazy"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, but with "lazy" batched TLB invalidation. This
+	  mode allows higher performance with some IOMMUs due to reduced TLB
+	  flushing, but at the cost of reduced isolation since devices may be
+	  able to access memory for some time after it has been unmapped.
+	  Equivalent to passing "iommu.passthrough=0 iommu.strict=0" on the
+	  command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+config IOMMU_DEFAULT_PASSTHROUGH
+	bool "Passthrough"
+	help
+	  Trusted devices are identity-mapped, giving them unrestricted access
+	  to memory with minimal performance overhead. Equivalent to passing
+	  "iommu.passthrough=1" (historically "iommu=pt") on the command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+endchoice
 
 config OF_IOMMU
 	def_bool y
@@ -249,6 +290,20 @@ config SPAPR_TCE_IOMMU
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
 	  is not implemented as it is not necessary for VFIO.
 
+config APPLE_DART
+	tristate "Apple DART IOMMU Support"
+	depends on ARCH_APPLE || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	default ARCH_APPLE
+	help
+	  Support for Apple DART (Device Address Resolution Table) IOMMUs
+	  found in Apple ARM SoCs like the M1.
+	  This IOMMU is required for most peripherals using DMA to access
+	  the main memory.
+
+	  Say Y here if you are using an Apple SoC.
+
 # ARM IOMMU support
 config ARM_SMMU
 	tristate "ARM Ltd. System MMU (SMMU) Support"

drivers/iommu/Makefile

@@ -29,3 +29,4 @@ obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
 obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
 obj-$(CONFIG_IOMMU_SVA_LIB) += iommu-sva-lib.o io-pgfault.o
 obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o
+obj-$(CONFIG_APPLE_DART) += apple-dart.o

drivers/iommu/amd/amd_iommu_types.h

@@ -779,12 +779,6 @@ extern u16 amd_iommu_last_bdf;
 /* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
-/*
- * If true, the addresses will be flushed on unmap time, not when
- * they are reused
- */
-extern bool amd_iommu_unmap_flush;
-
 /* Smallest max PASID supported by any IOMMU in the system */
 extern u32 amd_iommu_max_pasid;
 

drivers/iommu/amd/init.c

@@ -161,7 +161,6 @@ u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 					   to handle */
 LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
 					   we find in ACPI */
-bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
 
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
 					   system */
@@ -1850,8 +1849,11 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 	if (ret)
 		return ret;
 
-	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE))
+	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) {
+		pr_info("Using strict mode due to virtualization\n");
+		iommu_set_dma_strict();
 		amd_iommu_np_cache = true;
+	}
 
 	init_iommu_perf_ctr(iommu);
 
@@ -3098,8 +3100,10 @@ static int __init parse_amd_iommu_intr(char *str)
 static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
-		if (strncmp(str, "fullflush", 9) == 0)
-			amd_iommu_unmap_flush = true;
+		if (strncmp(str, "fullflush", 9) == 0) {
+			pr_warn("amd_iommu=fullflush deprecated; use iommu.strict=1 instead\n");
+			iommu_set_dma_strict();
+		}
 		if (strncmp(str, "force_enable", 12) == 0)
 			amd_iommu_force_enable = true;
 		if (strncmp(str, "off", 3) == 0)

drivers/iommu/amd/io_pgtable.c

@@ -493,9 +493,6 @@ static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned lo
 	unsigned long offset_mask, pte_pgsize;
 	u64 *pte, __pte;
 
-	if (pgtable->mode == PAGE_MODE_NONE)
-		return iova;
-
 	pte = fetch_pte(pgtable, iova, &pte_pgsize);
 
 	if (!pte || !IOMMU_PTE_PRESENT(*pte))