Merge tag 'iommu-updates-v4.12' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - code optimizations for the Intel VT-d driver

 - ability to switch off a previously enabled Intel IOMMU

 - support for 'struct iommu_device' for OMAP, Rockchip and Mediatek
   IOMMUs

 - header optimizations for IOMMU core code headers and a few fixes that
   became necessary in other parts of the kernel because of that

 - ACPI/IORT updates and fixes

 - Exynos IOMMU optimizations

 - updates for the IOMMU dma-api code to bring it closer to use per-cpu
   iova caches

 - new command-line option to set default domain type allocated by the
   iommu core code

 - another command line option to allow the Intel IOMMU switched off in
   a tboot environment

 - ARM/SMMU: TLB sync optimisations for SMMUv2, Support for using an
   IDENTITY domain in conjunction with DMA ops, Support for SMR masking,
   Support for 16-bit ASIDs (was previously broken)

 - various other small fixes and improvements

* tag 'iommu-updates-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (63 commits)
  soc/qbman: Move dma-mapping.h include to qman_priv.h
  soc/qbman: Fix implicit header dependency now causing build fails
  iommu: Remove trace-events include from iommu.h
  iommu: Remove pci.h include from trace/events/iommu.h
  arm: dma-mapping: Don't override dma_ops in arch_setup_dma_ops()
  ACPI/IORT: Fix CONFIG_IOMMU_API dependency
  iommu/vt-d: Don't print the failure message when booting non-kdump kernel
  iommu: Move report_iommu_fault() to iommu.c
  iommu: Include device.h in iommu.h
  x86, iommu/vt-d: Add an option to disable Intel IOMMU force on
  iommu/arm-smmu: Return IOVA in iova_to_phys when SMMU is bypassed
  iommu/arm-smmu: Correct sid to mask
  iommu/amd: Fix incorrect error handling in amd_iommu_bind_pasid()
  iommu: Make iommu_bus_notifier return NOTIFY_DONE rather than error code
  omap3isp: Remove iommu_group related code
  iommu/omap: Add iommu-group support
  iommu/omap: Make use of 'struct iommu_device'
  iommu/omap: Store iommu_dev pointer in arch_data
  iommu/omap: Move data structures to omap-iommu.h
  iommu/omap: Drop legacy-style device support
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1578,6 +1578,15 @@
 			extended tables themselves, and also PASID support. With
 			this option set, extended tables will not be used even
 			on hardware which claims to support them.
+		tboot_noforce [Default Off]
+			Do not force the Intel IOMMU enabled under tboot.
+			By default, tboot will force Intel IOMMU on, which
+			could harm performance of some high-throughput
+			devices like 40GBit network cards, even if identity
+			mapping is enabled.
+			Note that using this option lowers the security
+			provided by tboot because it makes the system
+			vulnerable to DMA attacks.
 
 	intel_idle.max_cstate=	[KNL,HW,ACPI,X86]
 			0	disables intel_idle and fall back on acpi_idle.
@@ -1644,6 +1653,12 @@
 		nobypass	[PPC/POWERNV]
 			Disable IOMMU bypass, using IOMMU for PCI devices.
 
+	iommu.passthrough=
+			[ARM64] Configure DMA to bypass the IOMMU by default.
+			Format: { "0" | "1" }
+			0 - Use IOMMU translation for DMA.
+			1 - Bypass the IOMMU for DMA.
+			unset - Use IOMMU translation for DMA.
 
 	io7=		[HW] IO7 for Marvel based alpha systems
 			See comment before marvel_specify_io7 in

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

@@ -60,6 +60,17 @@ conditions.
                   aliases of secure registers have to be used during
                   SMMU configuration.
 
+- stream-match-mask : For SMMUs supporting stream matching and using
+                  #iommu-cells = <1>, specifies a mask of bits to ignore
+		  when matching stream IDs (e.g. this may be programmed
+		  into the SMRn.MASK field of every stream match register
+		  used). For cases where it is desirable to ignore some
+                  portion of every Stream ID (e.g. for certain MMU-500
+                  configurations given globally unique input IDs). This
+                  property is not valid for SMMUs using stream indexing,
+                  or using stream matching with #iommu-cells = <2>, and
+                  may be ignored if present in such cases.
+
 ** Deprecated properties:
 
 - mmu-masters (deprecated in favour of the generic "iommus" binding) :
@@ -109,3 +120,20 @@ conditions.
         master3 {
                 iommus = <&smmu2 1 0x30>;
         };
+
+
+        /* ARM MMU-500 with 10-bit stream ID input configuration */
+        smmu3: iommu {
+                compatible = "arm,mmu-500", "arm,smmu-v2";
+                ...
+                #iommu-cells = <1>;
+                /* always ignore appended 5-bit TBU number */
+                stream-match-mask = 0x7c00;
+        };
+
+        bus {
+                /* bus whose child devices emit one unique 10-bit stream
+                   ID each, but may master through multiple SMMU TBUs */
+                iommu-map = <0 &smmu3 0 0x400>;
+                ...
+        };

arch/arm/mm/dma-mapping.c

@@ -2408,6 +2408,15 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	const struct dma_map_ops *dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
+
+	/*
+	 * Don't override the dma_ops if they have already been set. Ideally
+	 * this should be the only location where dma_ops are set, remove this
+	 * check when all other callers of set_dma_ops will have disappeared.
+	 */
+	if (dev->dma_ops)
+		return;
+
 	if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu))
 		dma_ops = arm_get_iommu_dma_map_ops(coherent);
 	else

arch/arm64/mm/dma-mapping.c

@@ -28,6 +28,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
+#include <linux/pci.h>
 
 #include <asm/cacheflush.h>
 
@@ -879,34 +880,26 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.mapping_error = iommu_dma_mapping_error,
 };
 
-/*
- * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
- * everything it needs to - the device is only partially created and the
- * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we
- * need this delayed attachment dance. Once IOMMU probe ordering is sorted
- * to move the arch_setup_dma_ops() call later, all the notifier bits below
- * become unnecessary, and will go away.
- */
-struct iommu_dma_notifier_data {
-	struct list_head list;
-	struct device *dev;
-	const struct iommu_ops *ops;
-	u64 dma_base;
-	u64 size;
-};
-static LIST_HEAD(iommu_dma_masters);
-static DEFINE_MUTEX(iommu_dma_notifier_lock);
+static int __init __iommu_dma_init(void)
+{
+	return iommu_dma_init();
+}
+arch_initcall(__iommu_dma_init);
 
-static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
-			   u64 dma_base, u64 size)
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				  const struct iommu_ops *ops)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain;
+
+	if (!ops)
+		return;
 
 	/*
-	 * If the IOMMU driver has the DMA domain support that we require,
-	 * then the IOMMU core will have already configured a group for this
-	 * device, and allocated the default domain for that group.
+	 * The IOMMU core code allocates the default DMA domain, which the
+	 * underlying IOMMU driver needs to support via the dma-iommu layer.
 	 */
+	domain = iommu_get_domain_for_dev(dev);
+
 	if (!domain)
 		goto out_err;
 
@@ -917,109 +910,11 @@ static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
 		dev->dma_ops = &iommu_dma_ops;
 	}
 
-	return true;
+	return;
+
 out_err:
-	pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
 		 dev_name(dev));
-	return false;
-}
-
-static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
-			      u64 dma_base, u64 size)
-{
-	struct iommu_dma_notifier_data *iommudata;
-
-	iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL);
-	if (!iommudata)
-		return;
-
-	iommudata->dev = dev;
-	iommudata->ops = ops;
-	iommudata->dma_base = dma_base;
-	iommudata->size = size;
-
-	mutex_lock(&iommu_dma_notifier_lock);
-	list_add(&iommudata->list, &iommu_dma_masters);
-	mutex_unlock(&iommu_dma_notifier_lock);
-}
-
-static int __iommu_attach_notifier(struct notifier_block *nb,
-				   unsigned long action, void *data)
-{
-	struct iommu_dma_notifier_data *master, *tmp;
-
-	if (action != BUS_NOTIFY_BIND_DRIVER)
-		return 0;
-
-	mutex_lock(&iommu_dma_notifier_lock);
-	list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
-		if (data == master->dev && do_iommu_attach(master->dev,
-				master->ops, master->dma_base, master->size)) {
-			list_del(&master->list);
-			kfree(master);
-			break;
-		}
-	}
-	mutex_unlock(&iommu_dma_notifier_lock);
-	return 0;
-}
-
-static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
-{
-	struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
-	int ret;
-
-	if (!nb)
-		return -ENOMEM;
-
-	nb->notifier_call = __iommu_attach_notifier;
-
-	ret = bus_register_notifier(bus, nb);
-	if (ret) {
-		pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
-			bus->name);
-		kfree(nb);
-	}
-	return ret;
-}
-
-static int __init __iommu_dma_init(void)
-{
-	int ret;
-
-	ret = iommu_dma_init();
-	if (!ret)
-		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
-	if (!ret)
-		ret = register_iommu_dma_ops_notifier(&amba_bustype);
-#ifdef CONFIG_PCI
-	if (!ret)
-		ret = register_iommu_dma_ops_notifier(&pci_bus_type);
-#endif
-	return ret;
-}
-arch_initcall(__iommu_dma_init);
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  const struct iommu_ops *ops)
-{
-	struct iommu_group *group;
-
-	if (!ops)
-		return;
-	/*
-	 * TODO: As a concession to the future, we're ready to handle being
-	 * called both early and late (i.e. after bus_add_device). Once all
-	 * the platform bus code is reworked to call us late and the notifier
-	 * junk above goes away, move the body of do_iommu_attach here.
-	 */
-	group = iommu_group_get(dev);
-	if (group) {
-		do_iommu_attach(dev, ops, dma_base, size);
-		iommu_group_put(group);
-	} else {
-		queue_iommu_attach(dev, ops, dma_base, size);
-	}
 }
 
 void arch_teardown_dma_ops(struct device *dev)

arch/x86/kernel/tboot.c

@@ -514,6 +514,9 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
+	if (!intel_iommu_tboot_noforce)
+		return 1;
+
 	if (no_iommu || swiotlb || dmar_disabled)
 		pr_warning("Forcing Intel-IOMMU to enabled\n");
 

drivers/acpi/arm64/iort.c

@@ -618,6 +618,46 @@ static int arm_smmu_iort_xlate(struct device *dev, u32 streamid,
 	return ret;
 }
 
+static inline bool iort_iommu_driver_enabled(u8 type)
+{
+	switch (type) {
+	case ACPI_IORT_NODE_SMMU_V3:
+		return IS_BUILTIN(CONFIG_ARM_SMMU_V3);
+	case ACPI_IORT_NODE_SMMU:
+		return IS_BUILTIN(CONFIG_ARM_SMMU);
+	default:
+		pr_warn("IORT node type %u does not describe an SMMU\n", type);
+		return false;
+	}
+}
+
+#ifdef CONFIG_IOMMU_API
+static inline
+const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+{
+	return (fwspec && fwspec->ops) ? fwspec->ops : NULL;
+}
+
+static inline
+int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+{
+	int err = 0;
+
+	if (!IS_ERR_OR_NULL(ops) && ops->add_device && dev->bus &&
+	    !dev->iommu_group)
+		err = ops->add_device(dev);
+
+	return err;
+}
+#else
+static inline
+const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+{ return NULL; }
+static inline
+int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+{ return 0; }
+#endif
+
 static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
 					struct acpi_iort_node *node,
 					u32 streamid)
@@ -626,14 +666,31 @@ static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
 	int ret = -ENODEV;
 	struct fwnode_handle *iort_fwnode;
 
+	/*
+	 * If we already translated the fwspec there
+	 * is nothing left to do, return the iommu_ops.
+	 */
+	ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+	if (ops)
+		return ops;
+
 	if (node) {
 		iort_fwnode = iort_get_fwnode(node);
 		if (!iort_fwnode)
 			return NULL;
 
 		ops = iommu_ops_from_fwnode(iort_fwnode);
+		/*
+		 * If the ops look-up fails, this means that either
+		 * the SMMU drivers have not been probed yet or that
+		 * the SMMU drivers are not built in the kernel;
+		 * Depending on whether the SMMU drivers are built-in
+		 * in the kernel or not, defer the IOMMU configuration
+		 * or just abort it.
+		 */
 		if (!ops)
-			return NULL;
+			return iort_iommu_driver_enabled(node->type) ?
+			       ERR_PTR(-EPROBE_DEFER) : NULL;
 
 		ret = arm_smmu_iort_xlate(dev, streamid, iort_fwnode, ops);
 	}
@@ -676,6 +733,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 	struct acpi_iort_node *node, *parent;
 	const struct iommu_ops *ops = NULL;
 	u32 streamid = 0;
+	int err;
 
 	if (dev_is_pci(dev)) {
 		struct pci_bus *bus = to_pci_dev(dev)->bus;
@@ -707,13 +765,23 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 
 		while (parent) {
 			ops = iort_iommu_xlate(dev, parent, streamid);
+			if (IS_ERR_OR_NULL(ops))
+				return ops;
 
 			parent = iort_node_map_platform_id(node, &streamid,
 							   IORT_IOMMU_TYPE,
 							   i++);
 		}
 	}
 
+	/*
+	 * If we have reason to believe the IOMMU driver missed the initial
+	 * add_device callback for dev, replay it to get things in order.
+	 */
+	err = iort_add_device_replay(ops, dev);
+	if (err)
+		ops = ERR_PTR(err);
+
 	return ops;
 }
 
@@ -1052,6 +1120,4 @@ void __init acpi_iort_init(void)
 	}
 
 	iort_init_platform_devices();
-
-	acpi_probe_device_table(iort);
 }