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;
@@ -707,6 +765,8 @@ 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,
@@ -714,6 +774,14 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 		}
 	}
 
+	/*
+	 * 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);
 }

drivers/acpi/glue.c

@@ -179,7 +179,6 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 	struct list_head *physnode_list;
 	unsigned int node_id;
 	int retval = -EINVAL;
-	enum dev_dma_attr attr;
 
 	if (has_acpi_companion(dev)) {
 		if (acpi_dev) {
@@ -236,10 +235,6 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 	if (!has_acpi_companion(dev))
 		ACPI_COMPANION_SET(dev, acpi_dev);
 
-	attr = acpi_get_dma_attr(acpi_dev);
-	if (attr != DEV_DMA_NOT_SUPPORTED)
-		acpi_dma_configure(dev, attr);
-
 	acpi_physnode_link_name(physical_node_name, node_id);
 	retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
 				   physical_node_name);

drivers/acpi/scan.c

@@ -1363,20 +1363,25 @@ enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
  * @dev: The pointer to the device
  * @attr: device dma attributes
  */
-void acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
+int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 {
 	const struct iommu_ops *iommu;
+	u64 size;
 
 	iort_set_dma_mask(dev);
 
 	iommu = iort_iommu_configure(dev);
+	if (IS_ERR(iommu))
+		return PTR_ERR(iommu);
 
+	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
 	/*
 	 * Assume dma valid range starts at 0 and covers the whole
 	 * coherent_dma_mask.
 	 */
-	arch_setup_dma_ops(dev, 0, dev->coherent_dma_mask + 1, iommu,
-			   attr == DEV_DMA_COHERENT);
+	arch_setup_dma_ops(dev, 0, size, iommu, attr == DEV_DMA_COHERENT);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dma_configure);
 

drivers/base/dd.c

@@ -19,6 +19,7 @@
 
 #include <linux/device.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/wait.h>
@@ -356,6 +357,10 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	if (ret)
 		goto pinctrl_bind_failed;
 
+	ret = dma_configure(dev);
+	if (ret)
+		goto dma_failed;
+
 	if (driver_sysfs_add(dev)) {
 		printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
 			__func__, dev_name(dev));
@@ -417,6 +422,8 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	goto done;
 
 probe_failed:
+	dma_deconfigure(dev);
+dma_failed:
 	if (dev->bus)
 		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
 					     BUS_NOTIFY_DRIVER_NOT_BOUND, dev);
@@ -826,6 +833,8 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 			drv->remove(dev);
 
 		device_links_driver_cleanup(dev);
+		dma_deconfigure(dev);
+
 		devres_release_all(dev);
 		dev->driver = NULL;
 		dev_set_drvdata(dev, NULL);

drivers/base/dma-mapping.c

@@ -7,9 +7,11 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/acpi.h>
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
@@ -340,3 +342,42 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
 	vunmap(cpu_addr);
 }
 #endif
+
+/*
+ * Common configuration to enable DMA API use for a device
+ */
+#include <linux/pci.h>
+
+int dma_configure(struct device *dev)
+{
+	struct device *bridge = NULL, *dma_dev = dev;
+	enum dev_dma_attr attr;
+	int ret = 0;
+
+	if (dev_is_pci(dev)) {
+		bridge = pci_get_host_bridge_device(to_pci_dev(dev));
+		dma_dev = bridge;
+		if (IS_ENABLED(CONFIG_OF) && dma_dev->parent &&
+		    dma_dev->parent->of_node)
+			dma_dev = dma_dev->parent;
+	}
+
+	if (dma_dev->of_node) {
+		ret = of_dma_configure(dev, dma_dev->of_node);
+	} else if (has_acpi_companion(dma_dev)) {
+		attr = acpi_get_dma_attr(to_acpi_device_node(dma_dev->fwnode));
+		if (attr != DEV_DMA_NOT_SUPPORTED)
+			ret = acpi_dma_configure(dev, attr);
+	}
+
+	if (bridge)
+		pci_put_host_bridge_device(bridge);
+
+	return ret;
+}
+
+void dma_deconfigure(struct device *dev)
+{
+	of_dma_deconfigure(dev);
+	acpi_dma_deconfigure(dev);
+}

drivers/infiniband/hw/qedr/main.c

@@ -35,6 +35,7 @@
 #include <rdma/ib_user_verbs.h>
 #include <linux/netdevice.h>
 #include <linux/iommu.h>
+#include <linux/pci.h>
 #include <net/addrconf.h>
 #include <linux/qed/qede_roce.h>
 #include <linux/qed/qed_chain.h>

drivers/iommu/amd_iommu_v2.c

@@ -696,9 +696,9 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 
 out_unregister:
 	mmu_notifier_unregister(&pasid_state->mn, mm);
+	mmput(mm);
 
 out_free:
-	mmput(mm);
 	free_pasid_state(pasid_state);
 
 out:

drivers/iommu/arm-smmu-v3.c

@@ -554,9 +554,14 @@ struct arm_smmu_s2_cfg {
 };
 
 struct arm_smmu_strtab_ent {
-	bool				valid;
-
-	bool				bypass;	/* Overrides s1/s2 config */
+	/*
+	 * An STE is "assigned" if the master emitting the corresponding SID
+	 * is attached to a domain. The behaviour of an unassigned STE is
+	 * determined by the disable_bypass parameter, whereas an assigned
+	 * STE behaves according to s1_cfg/s2_cfg, which themselves are
+	 * configured according to the domain type.
+	 */
+	bool				assigned;
 	struct arm_smmu_s1_cfg		*s1_cfg;
 	struct arm_smmu_s2_cfg		*s2_cfg;
 };
@@ -632,6 +637,7 @@ 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 {
@@ -1005,9 +1011,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	 * This is hideously complicated, but we only really care about
 	 * three cases at the moment:
 	 *
-	 * 1. Invalid (all zero) -> bypass  (init)
-	 * 2. Bypass -> translation (attach)
-	 * 3. Translation -> bypass (detach)
+	 * 1. Invalid (all zero) -> bypass/fault (init)
+	 * 2. Bypass/fault -> translation/bypass (attach)
+	 * 3. Translation/bypass -> bypass/fault (detach)
 	 *
 	 * Given that we can't update the STE atomically and the SMMU
 	 * doesn't read the thing in a defined order, that leaves us
@@ -1046,11 +1052,15 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	}
 
 	/* Nuke the existing STE_0 value, as we're going to rewrite it */
-	val = ste->valid ? STRTAB_STE_0_V : 0;
+	val = STRTAB_STE_0_V;
+
+	/* Bypass/fault */
+	if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
+		if (!ste->assigned && disable_bypass)
+			val |= STRTAB_STE_0_CFG_ABORT;
+		else
+			val |= STRTAB_STE_0_CFG_BYPASS;
 
-	if (ste->bypass) {
-		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
-				      : STRTAB_STE_0_CFG_BYPASS;
 		dst[0] = cpu_to_le64(val);
 		dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
 			 << STRTAB_STE_1_SHCFG_SHIFT);
@@ -1111,10 +1121,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
 {
 	unsigned int i;
-	struct arm_smmu_strtab_ent ste = {
-		.valid	= true,
-		.bypass	= true,
-	};
+	struct arm_smmu_strtab_ent ste = { .assigned = false };
 
 	for (i = 0; i < nent; ++i) {
 		arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
@@ -1378,7 +1385,9 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+	if (type != IOMMU_DOMAIN_UNMANAGED &&
+	    type != IOMMU_DOMAIN_DMA &&
+	    type != IOMMU_DOMAIN_IDENTITY)
 		return NULL;
 
 	/*
@@ -1509,6 +1518,11 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+		return 0;
+	}
+
 	/* Restrict the stage to what we can actually support */
 	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
 		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
@@ -1579,7 +1593,7 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 	return step;
 }
 
-static int arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
+static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
 {
 	int i;
 	struct arm_smmu_master_data *master = fwspec->iommu_priv;
@@ -1591,17 +1605,14 @@ static int arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
 
 		arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste);
 	}
-
-	return 0;
 }
 
 static void arm_smmu_detach_dev(struct device *dev)
 {
 	struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv;
 
-	master->ste.bypass = true;
-	if (arm_smmu_install_ste_for_dev(dev->iommu_fwspec) < 0)
-		dev_warn(dev, "failed to install bypass STE\n");
+	master->ste.assigned = false;
+	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1620,7 +1631,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	ste = &master->ste;
 
 	/* Already attached to a different domain? */
-	if (!ste->bypass)
+	if (ste->assigned)
 		arm_smmu_detach_dev(dev);
 
 	mutex_lock(&smmu_domain->init_mutex);
@@ -1641,10 +1652,12 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		goto out_unlock;
 	}
 
-	ste->bypass = false;
-	ste->valid = true;
+	ste->assigned = true;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) {
+		ste->s1_cfg = NULL;
+		ste->s2_cfg = NULL;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		ste->s1_cfg = &smmu_domain->s1_cfg;
 		ste->s2_cfg = NULL;
 		arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
@@ -1653,10 +1666,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		ste->s2_cfg = &smmu_domain->s2_cfg;
 	}
 
-	ret = arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
-	if (ret < 0)
-		ste->valid = false;
-
+	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
 	return ret;
@@ -1704,6 +1714,9 @@ arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
+		return iova;
+
 	if (!ops)
 		return 0;
 
@@ -1807,7 +1820,7 @@ static void arm_smmu_remove_device(struct device *dev)
 
 	master = fwspec->iommu_priv;
 	smmu = master->smmu;
-	if (master && master->ste.valid)
+	if (master && master->ste.assigned)
 		arm_smmu_detach_dev(dev);
 	iommu_group_remove_device(dev);
 	iommu_device_unlink(&smmu->iommu, dev);
@@ -1837,6 +1850,9 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	switch (attr) {
 	case DOMAIN_ATTR_NESTING:
 		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
@@ -1852,6 +1868,9 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 	int ret = 0;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	mutex_lock(&smmu_domain->init_mutex);
 
 	switch (attr) {
@@ -1893,6 +1912,8 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 		return;
 
 	list_add_tail(&region->list, head);
+
+	iommu_dma_get_resv_regions(dev, head);
 }
 
 static void arm_smmu_put_resv_regions(struct device *dev,
@@ -2761,51 +2782,9 @@ static struct platform_driver arm_smmu_driver = {
 	.probe	= arm_smmu_device_probe,
 	.remove	= arm_smmu_device_remove,
 };
+module_platform_driver(arm_smmu_driver);
 
-static int __init arm_smmu_init(void)
-{
-	static bool registered;
-	int ret = 0;
-
-	if (!registered) {
-		ret = platform_driver_register(&arm_smmu_driver);
-		registered = !ret;
-	}
-	return ret;
-}
-
-static void __exit arm_smmu_exit(void)
-{
-	return platform_driver_unregister(&arm_smmu_driver);
-}
-
-subsys_initcall(arm_smmu_init);
-module_exit(arm_smmu_exit);
-
-static int __init arm_smmu_of_init(struct device_node *np)
-{
-	int ret = arm_smmu_init();
-
-	if (ret)
-		return ret;
-
-	if (!of_platform_device_create(np, NULL, platform_bus_type.dev_root))
-		return -ENODEV;
-
-	return 0;
-}
-IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", arm_smmu_of_init);
-
-#ifdef CONFIG_ACPI
-static int __init acpi_smmu_v3_init(struct acpi_table_header *table)
-{
-	if (iort_node_match(ACPI_IORT_NODE_SMMU_V3))
-		return arm_smmu_init();
-
-	return 0;
-}
-IORT_ACPI_DECLARE(arm_smmu_v3, ACPI_SIG_IORT, acpi_smmu_v3_init);
-#endif
+IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL);
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");

drivers/iommu/dmar.c

@@ -311,7 +311,7 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
 				((void *)drhd) + drhd->header.length,
 				dmaru->segment,
 				dmaru->devices, dmaru->devices_cnt);
-		if (ret != 0)
+		if (ret)
 			break;
 	}
 	if (ret >= 0)
@@ -391,7 +391,7 @@ static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
-	int ret = 0;
+	int ret;
 
 	drhd = (struct acpi_dmar_hardware_unit *)header;
 	dmaru = dmar_find_dmaru(drhd);
@@ -551,17 +551,16 @@ static int __init dmar_table_detect(void)
 		status = AE_NOT_FOUND;
 	}
 
-	return (ACPI_SUCCESS(status) ? 1 : 0);
+	return ACPI_SUCCESS(status) ? 0 : -ENOENT;
 }
 
 static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
 				       size_t len, struct dmar_res_callback *cb)
 {
-	int ret = 0;
 	struct acpi_dmar_header *iter, *next;
 	struct acpi_dmar_header *end = ((void *)start) + len;
 
-	for (iter = start; iter < end && ret == 0; iter = next) {
+	for (iter = start; iter < end; iter = next) {
 		next = (void *)iter + iter->length;
 		if (iter->length == 0) {
 			/* Avoid looping forever on bad ACPI tables */
@@ -570,8 +569,7 @@ static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
 		} else if (next > end) {
 			/* Avoid passing table end */
 			pr_warn(FW_BUG "Record passes table end\n");
-			ret = -EINVAL;
-			break;
+			return -EINVAL;
 		}
 
 		if (cb->print_entry)
@@ -582,15 +580,19 @@ static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
 			pr_debug("Unknown DMAR structure type %d\n",
 				 iter->type);
 		} else if (cb->cb[iter->type]) {
+			int ret;
+
 			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+			if (ret)
+				return ret;
 		} else if (!cb->ignore_unhandled) {
 			pr_warn("No handler for DMAR structure type %d\n",
 				iter->type);
-			ret = -EINVAL;
+			return -EINVAL;
 		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
@@ -607,8 +609,8 @@ static int __init
 parse_dmar_table(void)
 {
 	struct acpi_table_dmar *dmar;
-	int ret = 0;
 	int drhd_count = 0;
+	int ret;
 	struct dmar_res_callback cb = {
 		.print_entry = true,
 		.ignore_unhandled = true,
@@ -891,17 +893,17 @@ int __init detect_intel_iommu(void)
 
 	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
-	if (ret)
-		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
-					    &validate_drhd_cb);
-	if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+	if (!ret)
+		ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+					   &validate_drhd_cb);
+	if (!ret && !no_iommu && !iommu_detected && !dmar_disabled) {
 		iommu_detected = 1;
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
 
 #ifdef CONFIG_X86
-	if (ret)
+	if (!ret)
 		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
 
@@ -911,10 +913,9 @@ int __init detect_intel_iommu(void)
 	}
 	up_write(&dmar_global_lock);
 
-	return ret ? 1 : -ENODEV;
+	return ret ? ret : 1;
 }
 
-
 static void unmap_iommu(struct intel_iommu *iommu)
 {
 	iounmap(iommu->reg);

drivers/iommu/exynos-iommu.c

@@ -171,6 +171,9 @@ static u32 lv2ent_offset(sysmmu_iova_t iova)
 #define REG_V5_PT_BASE_PFN	0x00C
 #define REG_V5_MMU_FLUSH_ALL	0x010
 #define REG_V5_MMU_FLUSH_ENTRY	0x014
+#define REG_V5_MMU_FLUSH_RANGE	0x018
+#define REG_V5_MMU_FLUSH_START	0x020
+#define REG_V5_MMU_FLUSH_END	0x024
 #define REG_V5_INT_STATUS	0x060
 #define REG_V5_INT_CLEAR	0x064
 #define REG_V5_FAULT_AR_VA	0x070
@@ -319,14 +322,23 @@ static void __sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
 {
 	unsigned int i;
 
-	for (i = 0; i < num_inv; i++) {
-		if (MMU_MAJ_VER(data->version) < 5)
+	if (MMU_MAJ_VER(data->version) < 5) {
+		for (i = 0; i < num_inv; i++) {
 			writel((iova & SPAGE_MASK) | 1,
 				     data->sfrbase + REG_MMU_FLUSH_ENTRY);
-		else
+			iova += SPAGE_SIZE;
+		}
+	} else {
+		if (num_inv == 1) {
 			writel((iova & SPAGE_MASK) | 1,
 				     data->sfrbase + REG_V5_MMU_FLUSH_ENTRY);
-		iova += SPAGE_SIZE;
+		} else {
+			writel((iova & SPAGE_MASK),
+				     data->sfrbase + REG_V5_MMU_FLUSH_START);
+			writel((iova & SPAGE_MASK) + (num_inv - 1) * SPAGE_SIZE,
+				     data->sfrbase + REG_V5_MMU_FLUSH_END);
+			writel(1, data->sfrbase + REG_V5_MMU_FLUSH_RANGE);
+		}
 	}
 }
 
@@ -747,16 +759,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 		goto err_counter;
 
 	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
-	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
-		domain->pgtable[i + 0] = ZERO_LV2LINK;
-		domain->pgtable[i + 1] = ZERO_LV2LINK;
-		domain->pgtable[i + 2] = ZERO_LV2LINK;
-		domain->pgtable[i + 3] = ZERO_LV2LINK;
-		domain->pgtable[i + 4] = ZERO_LV2LINK;
-		domain->pgtable[i + 5] = ZERO_LV2LINK;
-		domain->pgtable[i + 6] = ZERO_LV2LINK;
-		domain->pgtable[i + 7] = ZERO_LV2LINK;
-	}
+	for (i = 0; i < NUM_LV1ENTRIES; i++)
+		domain->pgtable[i] = ZERO_LV2LINK;
 
 	handle = dma_map_single(dma_dev, domain->pgtable, LV1TABLE_SIZE,
 				DMA_TO_DEVICE);

drivers/iommu/fsl_pamu.h

@@ -20,6 +20,7 @@
 #define __FSL_PAMU_H
 
 #include <linux/iommu.h>
+#include <linux/pci.h>
 
 #include <asm/fsl_pamu_stash.h>
 

drivers/iommu/intel-iommu.c

@@ -183,6 +183,7 @@ static int rwbf_quirk;
  * (used when kernel is launched w/ TXT)
  */
 static int force_on = 0;
+int intel_iommu_tboot_noforce;
 
 /*
  * 0: Present
@@ -607,6 +608,10 @@ static int __init intel_iommu_setup(char *str)
 				"Intel-IOMMU: enable pre-production PASID support\n");
 			intel_iommu_pasid28 = 1;
 			iommu_identity_mapping |= IDENTMAP_GFX;
+		} else if (!strncmp(str, "tboot_noforce", 13)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
+			intel_iommu_tboot_noforce = 1;
 		}
 
 		str += strcspn(str, ",");
@@ -4730,6 +4735,15 @@ static int intel_iommu_cpu_dead(unsigned int cpu)
 	return 0;
 }
 
+static void intel_disable_iommus(void)
+{
+	struct intel_iommu *iommu = NULL;
+	struct dmar_drhd_unit *drhd;
+
+	for_each_iommu(iommu, drhd)
+		iommu_disable_translation(iommu);
+}
+
 static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	return container_of(dev, struct intel_iommu, iommu.dev);
@@ -4840,8 +4854,28 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
-	if (no_iommu || dmar_disabled)
+	if (no_iommu || dmar_disabled) {
+		/*
+		 * We exit the function here to ensure IOMMU's remapping and
+		 * mempool aren't setup, which means that the IOMMU's PMRs
+		 * won't be disabled via the call to init_dmars(). So disable
+		 * it explicitly here. The PMRs were setup by tboot prior to
+		 * calling SENTER, but the kernel is expected to reset/tear
+		 * down the PMRs.
+		 */
+		if (intel_iommu_tboot_noforce) {
+			for_each_iommu(iommu, drhd)
+				iommu_disable_protect_mem_regions(iommu);
+		}
+
+		/*
+		 * Make sure the IOMMUs are switched off, even when we
+		 * boot into a kexec kernel and the previous kernel left
+		 * them enabled
+		 */
+		intel_disable_iommus();
 		goto out_free_dmar;
+	}
 
 	if (list_empty(&dmar_rmrr_units))
 		pr_info("No RMRR found\n");

drivers/iommu/intel_irq_remapping.c

@@ -408,14 +408,6 @@ static int iommu_load_old_irte(struct intel_iommu *iommu)
 	size_t size;
 	u64 irta;
 
-	if (!is_kdump_kernel()) {
-		pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
-			iommu->name);
-		clear_ir_pre_enabled(iommu);
-		iommu_disable_irq_remapping(iommu);
-		return -EINVAL;
-	}
-
 	/* Check whether the old ir-table has the same size as ours */
 	irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
 	if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
@@ -567,7 +559,12 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 	init_ir_status(iommu);
 
 	if (ir_pre_enabled(iommu)) {
-		if (iommu_load_old_irte(iommu))
+		if (!is_kdump_kernel()) {
+			pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
+				iommu->name);
+			clear_ir_pre_enabled(iommu);
+			iommu_disable_irq_remapping(iommu);
+		} else if (iommu_load_old_irte(iommu))
 			pr_err("Failed to copy IR table for %s from previous kernel\n",
 			       iommu->name);
 		else

drivers/iommu/io-pgtable-arm.c

@@ -74,7 +74,7 @@
 
 /* Calculate the block/page mapping size at level l for pagetable in d. */
 #define ARM_LPAE_BLOCK_SIZE(l,d)					\
-	(1 << (ilog2(sizeof(arm_lpae_iopte)) +				\
+	(1ULL << (ilog2(sizeof(arm_lpae_iopte)) +			\
 		((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
 
 /* Page table bits */

drivers/iommu/iommu.c

@@ -36,6 +36,7 @@
 
 static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
+static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
 
 struct iommu_callback_data {
 	const struct iommu_ops *ops;
@@ -112,6 +113,18 @@ static int __iommu_attach_group(struct iommu_domain *domain,
 static void __iommu_detach_group(struct iommu_domain *domain,
 				 struct iommu_group *group);
 
+static int __init iommu_set_def_domain_type(char *str)
+{
+	bool pt;
+
+	if (!str || strtobool(str, &pt))
+		return -EINVAL;
+
+	iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
+	return 0;
+}
+early_param("iommu.passthrough", iommu_set_def_domain_type);
+
 static ssize_t iommu_group_attr_show(struct kobject *kobj,
 				     struct attribute *__attr, char *buf)
 {
@@ -1015,10 +1028,19 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	 * IOMMU driver.
 	 */
 	if (!group->default_domain) {
-		group->default_domain = __iommu_domain_alloc(dev->bus,
-							     IOMMU_DOMAIN_DMA);
+		struct iommu_domain *dom;
+
+		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
+		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
+			dev_warn(dev,
+				 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+				 iommu_def_domain_type);
+			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+		}
+
+		group->default_domain = dom;
 		if (!group->domain)
-			group->domain = group->default_domain;
+			group->domain = dom;
 	}
 
 	ret = iommu_group_add_device(group, dev);
@@ -1083,8 +1105,12 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 	 * result in ADD/DEL notifiers to group->notifier
 	 */
 	if (action == BUS_NOTIFY_ADD_DEVICE) {
-		if (ops->add_device)
-			return ops->add_device(dev);
+		if (ops->add_device) {
+			int ret;
+
+			ret = ops->add_device(dev);
+			return (ret) ? NOTIFY_DONE : NOTIFY_OK;
+		}
 	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
 		if (ops->remove_device && dev->iommu_group) {
 			ops->remove_device(dev);
@@ -1652,6 +1678,48 @@ void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr)
 }
 EXPORT_SYMBOL_GPL(iommu_domain_window_disable);
 
+/**
+ * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
+ * @domain: the iommu domain where the fault has happened
+ * @dev: the device where the fault has happened
+ * @iova: the faulting address
+ * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
+ *
+ * This function should be called by the low-level IOMMU implementations
+ * whenever IOMMU faults happen, to allow high-level users, that are
+ * interested in such events, to know about them.
+ *
+ * This event may be useful for several possible use cases:
+ * - mere logging of the event
+ * - dynamic TLB/PTE loading
+ * - if restarting of the faulting device is required
+ *
+ * Returns 0 on success and an appropriate error code otherwise (if dynamic
+ * PTE/TLB loading will one day be supported, implementations will be able
+ * to tell whether it succeeded or not according to this return value).
+ *
+ * Specifically, -ENOSYS is returned if a fault handler isn't installed
+ * (though fault handlers can also return -ENOSYS, in case they want to
+ * elicit the default behavior of the IOMMU drivers).
+ */
+int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
+		       unsigned long iova, int flags)
+{
+	int ret = -ENOSYS;
+
+	/*
+	 * if upper layers showed interest and installed a fault handler,
+	 * invoke it.
+	 */
+	if (domain->handler)
+		ret = domain->handler(domain, dev, iova, flags,
+						domain->handler_token);
+
+	trace_io_page_fault(dev, iova, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(report_iommu_fault);
+
 static int __init iommu_init(void)
 {
 	iommu_group_kset = kset_create_and_add("iommu_groups",

drivers/iommu/iova.c

@@ -166,7 +166,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 				break;	/* found a free slot */
 		}
 adjust_limit_pfn:
-		limit_pfn = curr_iova->pfn_lo - 1;
+		limit_pfn = curr_iova->pfn_lo ? (curr_iova->pfn_lo - 1) : 0;
 move_left:
 		prev = curr;
 		curr = rb_prev(curr);

drivers/iommu/mtk_iommu_v1.c

@@ -431,9 +431,10 @@ static int mtk_iommu_create_mapping(struct device *dev,
 
 static int mtk_iommu_add_device(struct device *dev)
 {
-	struct iommu_group *group;
 	struct of_phandle_args iommu_spec;
 	struct of_phandle_iterator it;
+	struct mtk_iommu_data *data;
+	struct iommu_group *group;
 	int err;
 
 	of_for_each_phandle(&it, err, dev->of_node, "iommus",
@@ -450,6 +451,9 @@ static int mtk_iommu_add_device(struct device *dev)
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return -ENODEV; /* Not a iommu client device */
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_link(&data->iommu, dev);
+
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
 		return PTR_ERR(group);
@@ -460,9 +464,14 @@ static int mtk_iommu_add_device(struct device *dev)
 
 static void mtk_iommu_remove_device(struct device *dev)
 {
+	struct mtk_iommu_data *data;
+
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return;
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_unlink(&data->iommu, dev);
+
 	iommu_group_remove_device(dev);
 	iommu_fwspec_free(dev);
 }
@@ -627,6 +636,17 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(&pdev->dev));
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&data->iommu, &mtk_iommu_ops);
+
+	ret = iommu_device_register(&data->iommu);
+	if (ret)
+		return ret;
+
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type,  &mtk_iommu_ops);
 
@@ -637,6 +657,9 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 {
 	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
 
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
 	if (iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, NULL);
 

drivers/iommu/of_iommu.c

@@ -96,6 +96,49 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
 }
 EXPORT_SYMBOL_GPL(of_get_dma_window);
 
+static bool of_iommu_driver_present(struct device_node *np)
+{
+	/*
+	 * If the IOMMU still isn't ready by the time we reach init, assume
+	 * it never will be. We don't want to defer indefinitely, nor attempt
+	 * to dereference __iommu_of_table after it's been freed.
+	 */
+	if (system_state > SYSTEM_BOOTING)
+		return false;
+
+	return of_match_node(&__iommu_of_table, np);
+}
+
+static const struct iommu_ops
+*of_iommu_xlate(struct device *dev, struct of_phandle_args *iommu_spec)
+{
+	const struct iommu_ops *ops;
+	struct fwnode_handle *fwnode = &iommu_spec->np->fwnode;
+	int err;
+
+	ops = iommu_ops_from_fwnode(fwnode);
+	if ((ops && !ops->of_xlate) ||
+	    (!ops && !of_iommu_driver_present(iommu_spec->np)))
+		return NULL;
+
+	err = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
+	if (err)
+		return ERR_PTR(err);
+	/*
+	 * The otherwise-empty fwspec handily serves to indicate the specific
+	 * IOMMU device we're waiting for, which will be useful if we ever get
+	 * a proper probe-ordering dependency mechanism in future.
+	 */
+	if (!ops)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	err = ops->of_xlate(dev, iommu_spec);
+	if (err)
+		return ERR_PTR(err);
+
+	return ops;
+}
+
 static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
 {
 	struct of_phandle_args *iommu_spec = data;
@@ -105,10 +148,11 @@ static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
 }
 
 static const struct iommu_ops
-*of_pci_iommu_configure(struct pci_dev *pdev, struct device_node *bridge_np)
+*of_pci_iommu_init(struct pci_dev *pdev, struct device_node *bridge_np)
 {
 	const struct iommu_ops *ops;
 	struct of_phandle_args iommu_spec;
+	int err;
 
 	/*
 	 * Start by tracing the RID alias down the PCI topology as
@@ -123,56 +167,76 @@ static const struct iommu_ops
 	 * bus into the system beyond, and which IOMMU it ends up at.
 	 */
 	iommu_spec.np = NULL;
-	if (of_pci_map_rid(bridge_np, iommu_spec.args[0], "iommu-map",
-			   "iommu-map-mask", &iommu_spec.np, iommu_spec.args))
-		return NULL;
+	err = of_pci_map_rid(bridge_np, iommu_spec.args[0], "iommu-map",
+			     "iommu-map-mask", &iommu_spec.np,
+			     iommu_spec.args);
+	if (err)
+		return err == -ENODEV ? NULL : ERR_PTR(err);
 
-	ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode);
-	if (!ops || !ops->of_xlate ||
-	    iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) ||
-	    ops->of_xlate(&pdev->dev, &iommu_spec))
-		ops = NULL;
+	ops = of_iommu_xlate(&pdev->dev, &iommu_spec);
 
 	of_node_put(iommu_spec.np);
 	return ops;
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np)
+static const struct iommu_ops
+*of_platform_iommu_init(struct device *dev, struct device_node *np)
 {
 	struct of_phandle_args iommu_spec;
-	struct device_node *np;
 	const struct iommu_ops *ops = NULL;
 	int idx = 0;
 
-	if (dev_is_pci(dev))
-		return of_pci_iommu_configure(to_pci_dev(dev), master_np);
-
 	/*
 	 * We don't currently walk up the tree looking for a parent IOMMU.
 	 * See the `Notes:' section of
 	 * Documentation/devicetree/bindings/iommu/iommu.txt
 	 */
-	while (!of_parse_phandle_with_args(master_np, "iommus",
-					   "#iommu-cells", idx,
-					   &iommu_spec)) {
-		np = iommu_spec.np;
-		ops = iommu_ops_from_fwnode(&np->fwnode);
-
-		if (!ops || !ops->of_xlate ||
-		    iommu_fwspec_init(dev, &np->fwnode, ops) ||
-		    ops->of_xlate(dev, &iommu_spec))
-			goto err_put_node;
-
-		of_node_put(np);
+	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells",
+					   idx, &iommu_spec)) {
+		ops = of_iommu_xlate(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
 		idx++;
+		if (IS_ERR_OR_NULL(ops))
+			break;
 	}
 
 	return ops;
+}
+
+const struct iommu_ops *of_iommu_configure(struct device *dev,
+					   struct device_node *master_np)
+{
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+
+	if (!master_np)
+		return NULL;
+
+	if (fwspec) {
+		if (fwspec->ops)
+			return fwspec->ops;
+
+		/* In the deferred case, start again from scratch */
+		iommu_fwspec_free(dev);
+	}
 
-err_put_node:
-	of_node_put(np);
-	return NULL;
+	if (dev_is_pci(dev))
+		ops = of_pci_iommu_init(to_pci_dev(dev), master_np);
+	else
+		ops = of_platform_iommu_init(dev, master_np);
+	/*
+	 * If we have reason to believe the IOMMU driver missed the initial
+	 * add_device callback for dev, replay it to get things in order.
+	 */
+	if (!IS_ERR_OR_NULL(ops) && ops->add_device &&
+	    dev->bus && !dev->iommu_group) {
+		int err = ops->add_device(dev);
+
+		if (err)
+			ops = ERR_PTR(err);
+	}
+
+	return ops;
 }
 
 static int __init of_iommu_init(void)
@@ -183,7 +247,7 @@ static int __init of_iommu_init(void)
 	for_each_matching_node_and_match(np, matches, &match) {
 		const of_iommu_init_fn init_fn = match->data;
 
-		if (init_fn(np))
+		if (init_fn && init_fn(np))
 			pr_err("Failed to initialise IOMMU %s\n",
 				of_node_full_name(np));
 	}

drivers/iommu/omap-iommu.c

@@ -36,28 +36,14 @@
 #include "omap-iopgtable.h"
 #include "omap-iommu.h"
 
+static const struct iommu_ops omap_iommu_ops;
+
 #define to_iommu(dev)							\
 	((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))
 
 /* bitmap of the page sizes currently supported */
 #define OMAP_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
 
-/**
- * struct omap_iommu_domain - omap iommu domain
- * @pgtable:	the page table
- * @iommu_dev:	an omap iommu device attached to this domain. only a single
- *		iommu device can be attached for now.
- * @dev:	Device using this domain.
- * @lock:	domain lock, should be taken when attaching/detaching
- */
-struct omap_iommu_domain {
-	u32 *pgtable;
-	struct omap_iommu *iommu_dev;
-	struct device *dev;
-	spinlock_t lock;
-	struct iommu_domain domain;
-};
-
 #define MMU_LOCK_BASE_SHIFT	10
 #define MMU_LOCK_BASE_MASK	(0x1f << MMU_LOCK_BASE_SHIFT)
 #define MMU_LOCK_BASE(x)	\
@@ -818,33 +804,14 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	return IRQ_NONE;
 }
 
-static int device_match_by_alias(struct device *dev, void *data)
-{
-	struct omap_iommu *obj = to_iommu(dev);
-	const char *name = data;
-
-	pr_debug("%s: %s %s\n", __func__, obj->name, name);
-
-	return strcmp(obj->name, name) == 0;
-}
-
 /**
  * omap_iommu_attach() - attach iommu device to an iommu domain
- * @name:	name of target omap iommu device
+ * @obj:	target omap iommu device
  * @iopgd:	page table
  **/
-static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
+static int omap_iommu_attach(struct omap_iommu *obj, u32 *iopgd)
 {
 	int err;
-	struct device *dev;
-	struct omap_iommu *obj;
-
-	dev = driver_find_device(&omap_iommu_driver.driver, NULL, (void *)name,
-				 device_match_by_alias);
-	if (!dev)
-		return ERR_PTR(-ENODEV);
-
-	obj = to_iommu(dev);
 
 	spin_lock(&obj->iommu_lock);
 
@@ -857,11 +824,13 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 	spin_unlock(&obj->iommu_lock);
 
 	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
-	return obj;
+
+	return 0;
 
 err_enable:
 	spin_unlock(&obj->iommu_lock);
-	return ERR_PTR(err);
+
+	return err;
 }
 
 /**
@@ -928,28 +897,26 @@ static int omap_iommu_probe(struct platform_device *pdev)
 	int irq;
 	struct omap_iommu *obj;
 	struct resource *res;
-	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct device_node *of = pdev->dev.of_node;
 
+	if (!of) {
+		pr_err("%s: only DT-based devices are supported\n", __func__);
+		return -ENODEV;
+	}
+
 	obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
 	if (!obj)
 		return -ENOMEM;
 
-	if (of) {
-		obj->name = dev_name(&pdev->dev);
-		obj->nr_tlb_entries = 32;
-		err = of_property_read_u32(of, "ti,#tlb-entries",
-					   &obj->nr_tlb_entries);
-		if (err && err != -EINVAL)
-			return err;
-		if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
-			return -EINVAL;
-		if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
-			obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
-	} else {
-		obj->nr_tlb_entries = pdata->nr_tlb_entries;
-		obj->name = pdata->name;
-	}
+	obj->name = dev_name(&pdev->dev);
+	obj->nr_tlb_entries = 32;
+	err = of_property_read_u32(of, "ti,#tlb-entries", &obj->nr_tlb_entries);
+	if (err && err != -EINVAL)
+		return err;
+	if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
+		return -EINVAL;
+	if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
+		obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
 
 	obj->dev = &pdev->dev;
 	obj->ctx = (void *)obj + sizeof(*obj);
@@ -976,19 +943,46 @@ static int omap_iommu_probe(struct platform_device *pdev)
 		return err;
 	platform_set_drvdata(pdev, obj);
 
+	obj->group = iommu_group_alloc();
+	if (IS_ERR(obj->group))
+		return PTR_ERR(obj->group);
+
+	err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL, obj->name);
+	if (err)
+		goto out_group;
+
+	iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);
+
+	err = iommu_device_register(&obj->iommu);
+	if (err)
+		goto out_sysfs;
+
 	pm_runtime_irq_safe(obj->dev);
 	pm_runtime_enable(obj->dev);
 
 	omap_iommu_debugfs_add(obj);
 
 	dev_info(&pdev->dev, "%s registered\n", obj->name);
+
 	return 0;
+
+out_sysfs:
+	iommu_device_sysfs_remove(&obj->iommu);
+out_group:
+	iommu_group_put(obj->group);
+	return err;
 }
 
 static int omap_iommu_remove(struct platform_device *pdev)
 {
 	struct omap_iommu *obj = platform_get_drvdata(pdev);
 
+	iommu_group_put(obj->group);
+	obj->group = NULL;
+
+	iommu_device_sysfs_remove(&obj->iommu);
+	iommu_device_unregister(&obj->iommu);
+
 	omap_iommu_debugfs_remove(obj);
 
 	pm_runtime_disable(obj->dev);
@@ -1077,11 +1071,11 @@ static int
 omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu;
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu *oiommu;
 	int ret = 0;
 
-	if (!arch_data || !arch_data->name) {
+	if (!arch_data || !arch_data->iommu_dev) {
 		dev_err(dev, "device doesn't have an associated iommu\n");
 		return -EINVAL;
 	}
@@ -1095,15 +1089,16 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		goto out;
 	}
 
+	oiommu = arch_data->iommu_dev;
+
 	/* get a handle to and enable the omap iommu */
-	oiommu = omap_iommu_attach(arch_data->name, omap_domain->pgtable);
-	if (IS_ERR(oiommu)) {
-		ret = PTR_ERR(oiommu);
+	ret = omap_iommu_attach(oiommu, omap_domain->pgtable);
+	if (ret) {
 		dev_err(dev, "can't get omap iommu: %d\n", ret);
 		goto out;
 	}
 
-	omap_domain->iommu_dev = arch_data->iommu_dev = oiommu;
+	omap_domain->iommu_dev = oiommu;
 	omap_domain->dev = dev;
 	oiommu->domain = domain;
 
@@ -1116,7 +1111,6 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
 				   struct device *dev)
 {
 	struct omap_iommu *oiommu = dev_to_omap_iommu(dev);
-	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 
 	/* only a single device is supported per domain for now */
 	if (omap_domain->iommu_dev != oiommu) {
@@ -1128,7 +1122,7 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
 
 	omap_iommu_detach(oiommu);
 
-	omap_domain->iommu_dev = arch_data->iommu_dev = NULL;
+	omap_domain->iommu_dev = NULL;
 	omap_domain->dev = NULL;
 	oiommu->domain = NULL;
 }
@@ -1232,8 +1226,11 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 static int omap_iommu_add_device(struct device *dev)
 {
 	struct omap_iommu_arch_data *arch_data;
+	struct omap_iommu *oiommu;
+	struct iommu_group *group;
 	struct device_node *np;
 	struct platform_device *pdev;
+	int ret;
 
 	/*
 	 * Allocate the archdata iommu structure for DT-based devices.
@@ -1254,15 +1251,41 @@ static int omap_iommu_add_device(struct device *dev)
 		return -EINVAL;
 	}
 
+	oiommu = platform_get_drvdata(pdev);
+	if (!oiommu) {
+		of_node_put(np);
+		return -EINVAL;
+	}
+
 	arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
 	if (!arch_data) {
 		of_node_put(np);
 		return -ENOMEM;
 	}
 
-	arch_data->name = kstrdup(dev_name(&pdev->dev), GFP_KERNEL);
+	ret = iommu_device_link(&oiommu->iommu, dev);
+	if (ret) {
+		kfree(arch_data);
+		of_node_put(np);
+		return ret;
+	}
+
+	arch_data->iommu_dev = oiommu;
 	dev->archdata.iommu = arch_data;
 
+	/*
+	 * IOMMU group initialization calls into omap_iommu_device_group, which
+	 * needs a valid dev->archdata.iommu pointer
+	 */
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group)) {
+		iommu_device_unlink(&oiommu->iommu, dev);
+		dev->archdata.iommu = NULL;
+		kfree(arch_data);
+		return PTR_ERR(group);
+	}
+	iommu_group_put(group);
+
 	of_node_put(np);
 
 	return 0;
@@ -1275,8 +1298,23 @@ static void omap_iommu_remove_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	kfree(arch_data->name);
+	iommu_device_unlink(&arch_data->iommu_dev->iommu, dev);
+	iommu_group_remove_device(dev);
+
+	dev->archdata.iommu = NULL;
 	kfree(arch_data);
+
+}
+
+static struct iommu_group *omap_iommu_device_group(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct iommu_group *group = NULL;
+
+	if (arch_data->iommu_dev)
+		group = arch_data->iommu_dev->group;
+
+	return group;
 }
 
 static const struct iommu_ops omap_iommu_ops = {
@@ -1290,6 +1328,7 @@ static const struct iommu_ops omap_iommu_ops = {
 	.iova_to_phys	= omap_iommu_iova_to_phys,
 	.add_device	= omap_iommu_add_device,
 	.remove_device	= omap_iommu_remove_device,
+	.device_group	= omap_iommu_device_group,
 	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
 };
 
@@ -1299,6 +1338,7 @@ static int __init omap_iommu_init(void)
 	const unsigned long flags = SLAB_HWCACHE_ALIGN;
 	size_t align = 1 << 10; /* L2 pagetable alignement */
 	struct device_node *np;
+	int ret;
 
 	np = of_find_matching_node(NULL, omap_iommu_of_match);
 	if (!np)
@@ -1312,11 +1352,25 @@ static int __init omap_iommu_init(void)
 		return -ENOMEM;
 	iopte_cachep = p;
 
-	bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
-
 	omap_iommu_debugfs_init();
 
-	return platform_driver_register(&omap_iommu_driver);
+	ret = platform_driver_register(&omap_iommu_driver);
+	if (ret) {
+		pr_err("%s: failed to register driver\n", __func__);
+		goto fail_driver;
+	}
+
+	ret = bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
+	if (ret)
+		goto fail_bus;
+
+	return 0;
+
+fail_bus:
+	platform_driver_unregister(&omap_iommu_driver);
+fail_driver:
+	kmem_cache_destroy(iopte_cachep);
+	return ret;
 }
 subsys_initcall(omap_iommu_init);
 /* must be ready before omap3isp is probed */

drivers/iommu/omap-iommu.h

@@ -14,6 +14,7 @@
 #define _OMAP_IOMMU_H
 
 #include <linux/bitops.h>
+#include <linux/iommu.h>
 
 #define for_each_iotlb_cr(obj, n, __i, cr)				\
 	for (__i = 0;							\
@@ -27,6 +28,23 @@ struct iotlb_entry {
 	u32 endian, elsz, mixed;
 };
 
+/**
+ * struct omap_iommu_domain - omap iommu domain
+ * @pgtable:	the page table
+ * @iommu_dev:	an omap iommu device attached to this domain. only a single
+ *		iommu device can be attached for now.
+ * @dev:	Device using this domain.
+ * @lock:	domain lock, should be taken when attaching/detaching
+ * @domain:	generic domain handle used by iommu core code
+ */
+struct omap_iommu_domain {
+	u32 *pgtable;
+	struct omap_iommu *iommu_dev;
+	struct device *dev;
+	spinlock_t lock;
+	struct iommu_domain domain;
+};
+
 struct omap_iommu {
 	const char	*name;
 	void __iomem	*regbase;
@@ -50,6 +68,22 @@ struct omap_iommu {
 
 	int has_bus_err_back;
 	u32 id;
+
+	struct iommu_device iommu;
+	struct iommu_group *group;
+};
+
+/**
+ * struct omap_iommu_arch_data - omap iommu private data
+ * @iommu_dev: handle of the iommu device
+ *
+ * This is an omap iommu private data object, which binds an iommu user
+ * to its iommu device. This object should be placed at the iommu user's
+ * dev_archdata so generic IOMMU API can be used without having to
+ * utilize omap-specific plumbing anymore.
+ */
+struct omap_iommu_arch_data {
+	struct omap_iommu *iommu_dev;
 };
 
 struct cr_regs {

drivers/iommu/rockchip-iommu.c

@@ -8,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dma-iommu.h>
+#include <linux/dma-mapping.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -90,6 +91,7 @@ struct rk_iommu {
 	void __iomem **bases;
 	int num_mmu;
 	int irq;
+	struct iommu_device iommu;
 	struct list_head node; /* entry in rk_iommu_domain.iommus */
 	struct iommu_domain *domain; /* domain to which iommu is attached */
 };
@@ -1032,6 +1034,7 @@ static int rk_iommu_group_set_iommudata(struct iommu_group *group,
 static int rk_iommu_add_device(struct device *dev)
 {
 	struct iommu_group *group;
+	struct rk_iommu *iommu;
 	int ret;
 
 	if (!rk_iommu_is_dev_iommu_master(dev))
@@ -1054,6 +1057,10 @@ static int rk_iommu_add_device(struct device *dev)
 	if (ret)
 		goto err_remove_device;
 
+	iommu = rk_iommu_from_dev(dev);
+	if (iommu)
+		iommu_device_link(&iommu->iommu, dev);
+
 	iommu_group_put(group);
 
 	return 0;
@@ -1067,9 +1074,15 @@ static int rk_iommu_add_device(struct device *dev)
 
 static void rk_iommu_remove_device(struct device *dev)
 {
+	struct rk_iommu *iommu;
+
 	if (!rk_iommu_is_dev_iommu_master(dev))
 		return;
 
+	iommu = rk_iommu_from_dev(dev);
+	if (iommu)
+		iommu_device_unlink(&iommu->iommu, dev);
+
 	iommu_group_remove_device(dev);
 }
 
@@ -1117,7 +1130,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct rk_iommu *iommu;
 	struct resource *res;
 	int num_res = pdev->num_resources;
-	int i;
+	int err, i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
@@ -1150,11 +1163,25 @@ static int rk_iommu_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	return 0;
+	err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
+	if (err)
+		return err;
+
+	iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops);
+	err = iommu_device_register(&iommu->iommu);
+
+	return err;
 }
 
 static int rk_iommu_remove(struct platform_device *pdev)
 {
+	struct rk_iommu *iommu = platform_get_drvdata(pdev);
+
+	if (iommu) {
+		iommu_device_sysfs_remove(&iommu->iommu);
+		iommu_device_unregister(&iommu->iommu);
+	}
+
 	return 0;
 }
 

drivers/iommu/tegra-smmu.c

@@ -15,6 +15,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #include <soc/tegra/ahb.h>
 #include <soc/tegra/mc.h>

drivers/media/platform/mtk-vpu/mtk_vpu.c

@@ -23,6 +23,7 @@
 #include <linux/of_reserved_mem.h>
 #include <linux/sched.h>
 #include <linux/sizes.h>
+#include <linux/dma-mapping.h>
 
 #include "mtk_vpu.h"
 

drivers/media/platform/omap3isp/isp.c

@@ -1943,30 +1943,13 @@ static void isp_detach_iommu(struct isp_device *isp)
 {
 	arm_iommu_release_mapping(isp->mapping);
 	isp->mapping = NULL;
-	iommu_group_remove_device(isp->dev);
 }
 
 static int isp_attach_iommu(struct isp_device *isp)
 {
 	struct dma_iommu_mapping *mapping;
-	struct iommu_group *group;
 	int ret;
 
-	/* Create a device group and add the device to it. */
-	group = iommu_group_alloc();
-	if (IS_ERR(group)) {
-		dev_err(isp->dev, "failed to allocate IOMMU group\n");
-		return PTR_ERR(group);
-	}
-
-	ret = iommu_group_add_device(group, isp->dev);
-	iommu_group_put(group);
-
-	if (ret < 0) {
-		dev_err(isp->dev, "failed to add device to IPMMU group\n");
-		return ret;
-	}
-
 	/*
 	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
 	 * VAs. This will allocate a corresponding IOMMU domain.

drivers/media/platform/omap3isp/isp.h

@@ -23,7 +23,6 @@
 #include <linux/clk-provider.h>
 #include <linux/device.h>
 #include <linux/io.h>
-#include <linux/iommu.h>
 #include <linux/platform_device.h>
 #include <linux/wait.h>
 

drivers/of/device.c

@@ -82,7 +82,7 @@ int of_device_add(struct platform_device *ofdev)
  * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
  * to fix up DMA configuration.
  */
-void of_dma_configure(struct device *dev, struct device_node *np)
+int of_dma_configure(struct device *dev, struct device_node *np)
 {
 	u64 dma_addr, paddr, size;
 	int ret;
@@ -107,7 +107,7 @@ void of_dma_configure(struct device *dev, struct device_node *np)
 	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
 	if (ret < 0) {
 		dma_addr = offset = 0;
-		size = dev->coherent_dma_mask + 1;
+		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
 	} else {
 		offset = PFN_DOWN(paddr - dma_addr);
 
@@ -123,7 +123,7 @@ void of_dma_configure(struct device *dev, struct device_node *np)
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
-			return;
+			return -EINVAL;
 		}
 		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
@@ -144,13 +144,30 @@ void of_dma_configure(struct device *dev, struct device_node *np)
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np);
+	if (IS_ERR(iommu))
+		return PTR_ERR(iommu);
+
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
 	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure);
 
+/**
+ * of_dma_deconfigure - Clean up DMA configuration
+ * @dev:	Device for which to clean up DMA configuration
+ *
+ * Clean up all configuration performed by of_dma_configure_ops() and free all
+ * resources that have been allocated.
+ */
+void of_dma_deconfigure(struct device *dev)
+{
+	arch_teardown_dma_ops(dev);
+}
+
 int of_device_register(struct platform_device *pdev)
 {
 	device_initialize(&pdev->dev);

drivers/of/platform.c

@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_iommu.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
@@ -158,11 +159,6 @@ struct platform_device *of_device_alloc(struct device_node *np,
 }
 EXPORT_SYMBOL(of_device_alloc);
 
-static void of_dma_deconfigure(struct device *dev)
-{
-	arch_teardown_dma_ops(dev);
-}
-
 /**
  * of_platform_device_create_pdata - Alloc, initialize and register an of_device
  * @np: pointer to node to create device for
@@ -191,11 +187,9 @@ static struct platform_device *of_platform_device_create_pdata(
 
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
-	of_dma_configure(&dev->dev, dev->dev.of_node);
 	of_msi_configure(&dev->dev, dev->dev.of_node);
 
 	if (of_device_add(dev) != 0) {
-		of_dma_deconfigure(&dev->dev);
 		platform_device_put(dev);
 		goto err_clear_flag;
 	}
@@ -253,7 +247,6 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 		dev_set_name(&dev->dev, "%s", bus_id);
 	else
 		of_device_make_bus_id(&dev->dev);
-	of_dma_configure(&dev->dev, dev->dev.of_node);
 
 	/* Allow the HW Peripheral ID to be overridden */
 	prop = of_get_property(node, "arm,primecell-periphid", NULL);
@@ -547,7 +540,6 @@ static int of_platform_device_destroy(struct device *dev, void *data)
 		amba_device_unregister(to_amba_device(dev));
 #endif
 
-	of_dma_deconfigure(dev);
 	of_node_clear_flag(dev->of_node, OF_POPULATED);
 	of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
 	return 0;

drivers/pci/probe.c

@@ -1914,33 +1914,6 @@ static void pci_set_msi_domain(struct pci_dev *dev)
 	dev_set_msi_domain(&dev->dev, d);
 }
 
-/**
- * pci_dma_configure - Setup DMA configuration
- * @dev: ptr to pci_dev struct of the PCI device
- *
- * Function to update PCI devices's DMA configuration using the same
- * info from the OF node or ACPI node of host bridge's parent (if any).
- */
-static void pci_dma_configure(struct pci_dev *dev)
-{
-	struct device *bridge = pci_get_host_bridge_device(dev);
-
-	if (IS_ENABLED(CONFIG_OF) &&
-		bridge->parent && bridge->parent->of_node) {
-			of_dma_configure(&dev->dev, bridge->parent->of_node);
-	} else if (has_acpi_companion(bridge)) {
-		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
-		enum dev_dma_attr attr = acpi_get_dma_attr(adev);
-
-		if (attr == DEV_DMA_NOT_SUPPORTED)
-			dev_warn(&dev->dev, "DMA not supported.\n");
-		else
-			acpi_dma_configure(&dev->dev, attr);
-	}
-
-	pci_put_host_bridge_device(bridge);
-}
-
 void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 {
 	int ret;
@@ -1954,7 +1927,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 	dev->dev.dma_mask = &dev->dma_mask;
 	dev->dev.dma_parms = &dev->dma_parms;
 	dev->dev.coherent_dma_mask = 0xffffffffull;
-	pci_dma_configure(dev);
 
 	pci_set_dma_max_seg_size(dev, 65536);
 	pci_set_dma_seg_boundary(dev, 0xffffffff);

drivers/soc/fsl/qbman/qman_priv.h

@@ -33,6 +33,7 @@
 #include "dpaa_sys.h"
 
 #include <soc/fsl/qman.h>
+#include <linux/dma-mapping.h>
 #include <linux/iommu.h>
 
 #if defined(CONFIG_FSL_PAMU)

include/acpi/acpi_bus.h

@@ -577,7 +577,7 @@ struct acpi_pci_root {
 
 bool acpi_dma_supported(struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
-void acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
+int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
 void acpi_dma_deconfigure(struct device *dev);
 
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,

include/asm-generic/vmlinux.lds.h

@@ -566,7 +566,6 @@
 	IRQCHIP_OF_MATCH_TABLE()					\
 	ACPI_PROBE_TABLE(irqchip)					\
 	ACPI_PROBE_TABLE(clksrc)					\
-	ACPI_PROBE_TABLE(iort)						\
 	EARLYCON_TABLE()
 
 #define INIT_TEXT							\

include/linux/acpi.h

@@ -770,8 +770,11 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
 	return DEV_DMA_NOT_SUPPORTED;
 }
 
-static inline void acpi_dma_configure(struct device *dev,
-				      enum dev_dma_attr attr) { }
+static inline int acpi_dma_configure(struct device *dev,
+				     enum dev_dma_attr attr)
+{
+	return 0;
+}
 
 static inline void acpi_dma_deconfigure(struct device *dev) { }
 

include/linux/acpi_iort.h

@@ -55,7 +55,4 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 { return NULL; }
 #endif
 
-#define IORT_ACPI_DECLARE(name, table_id, fn)		\
-	ACPI_DECLARE_PROBE_ENTRY(iort, name, table_id, 0, NULL, 0, fn)
-
 #endif /* __ACPI_IORT_H__ */

include/linux/dma-iommu.h

@@ -20,6 +20,7 @@
 #include <asm/errno.h>
 
 #ifdef CONFIG_IOMMU_DMA
+#include <linux/dma-mapping.h>
 #include <linux/iommu.h>
 #include <linux/msi.h>
 
@@ -71,6 +72,7 @@ int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 /* The DMA API isn't _quite_ the whole story, though... */
 void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg);
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
 #else
 
@@ -100,6 +102,10 @@ static inline void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
 {
 }
 
+static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
+{
+}
+
 #endif	/* CONFIG_IOMMU_DMA */
 #endif	/* __KERNEL__ */
 #endif	/* __DMA_IOMMU_H */

include/linux/dma-mapping.h

@@ -728,6 +728,18 @@ dma_mark_declared_memory_occupied(struct device *dev,
 }
 #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 
+#ifdef CONFIG_HAS_DMA
+int dma_configure(struct device *dev);
+void dma_deconfigure(struct device *dev);
+#else
+static inline int dma_configure(struct device *dev)
+{
+	return 0;
+}
+
+static inline void dma_deconfigure(struct device *dev) {}
+#endif
+
 /*
  * Managed DMA API
  */

include/linux/dma_remapping.h

@@ -39,6 +39,7 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
+extern int intel_iommu_tboot_noforce;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {

include/linux/intel-iommu.h

@@ -30,6 +30,8 @@
 #include <linux/mmu_notifier.h>
 #include <linux/list.h>
 #include <linux/iommu.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 
@@ -72,24 +74,8 @@
 
 #define OFFSET_STRIDE		(9)
 
-#ifdef CONFIG_64BIT
 #define dmar_readq(a) readq(a)
 #define dmar_writeq(a,v) writeq(v,a)
-#else
-static inline u64 dmar_readq(void __iomem *addr)
-{
-	u32 lo, hi;
-	lo = readl(addr);
-	hi = readl(addr + 4);
-	return (((u64) hi) << 32) + lo;
-}
-
-static inline void dmar_writeq(void __iomem *addr, u64 val)
-{
-	writel((u32)val, addr);
-	writel((u32)(val >> 32), addr + 4);
-}
-#endif
 
 #define DMAR_VER_MAJOR(v)		(((v) & 0xf0) >> 4)
 #define DMAR_VER_MINOR(v)		((v) & 0x0f)

include/linux/iommu.h

@@ -19,12 +19,12 @@
 #ifndef __LINUX_IOMMU_H
 #define __LINUX_IOMMU_H
 
+#include <linux/scatterlist.h>
+#include <linux/device.h>
+#include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <trace/events/iommu.h>
 
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
@@ -32,10 +32,13 @@
 #define IOMMU_NOEXEC	(1 << 3)
 #define IOMMU_MMIO	(1 << 4) /* e.g. things like MSI doorbells */
 /*
- * This is to make the IOMMU API setup privileged
- * mapppings accessible by the master only at higher
- * privileged execution level and inaccessible at
- * less privileged levels.
+ * Where the bus hardware includes a privilege level as part of its access type
+ * markings, and certain devices are capable of issuing transactions marked as
+ * either 'supervisor' or 'user', the IOMMU_PRIV flag requests that the other
+ * given permission flags only apply to accesses at the higher privilege level,
+ * and that unprivileged transactions should have as little access as possible.
+ * This would usually imply the same permissions as kernel mappings on the CPU,
+ * if the IOMMU page table format is equivalent.
  */
 #define IOMMU_PRIV	(1 << 5)
 
@@ -336,46 +339,9 @@ extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 				      phys_addr_t offset, u64 size,
 				      int prot);
 extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr);
-/**
- * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
- * @domain: the iommu domain where the fault has happened
- * @dev: the device where the fault has happened
- * @iova: the faulting address
- * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
- *
- * This function should be called by the low-level IOMMU implementations
- * whenever IOMMU faults happen, to allow high-level users, that are
- * interested in such events, to know about them.
- *
- * This event may be useful for several possible use cases:
- * - mere logging of the event
- * - dynamic TLB/PTE loading
- * - if restarting of the faulting device is required
- *
- * Returns 0 on success and an appropriate error code otherwise (if dynamic
- * PTE/TLB loading will one day be supported, implementations will be able
- * to tell whether it succeeded or not according to this return value).
- *
- * Specifically, -ENOSYS is returned if a fault handler isn't installed
- * (though fault handlers can also return -ENOSYS, in case they want to
- * elicit the default behavior of the IOMMU drivers).
- */
-static inline int report_iommu_fault(struct iommu_domain *domain,
-		struct device *dev, unsigned long iova, int flags)
-{
-	int ret = -ENOSYS;
-
-	/*
-	 * if upper layers showed interest and installed a fault handler,
-	 * invoke it.
-	 */
-	if (domain->handler)
-		ret = domain->handler(domain, dev, iova, flags,
-						domain->handler_token);
 
-	trace_io_page_fault(dev, iova, flags);
-	return ret;
-}
+extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
+			      unsigned long iova, int flags);
 
 static inline size_t iommu_map_sg(struct iommu_domain *domain,
 				  unsigned long iova, struct scatterlist *sg,

include/linux/of_device.h

@@ -54,7 +54,8 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-void of_dma_configure(struct device *dev, struct device_node *np);
+int of_dma_configure(struct device *dev, struct device_node *np);
+void of_dma_deconfigure(struct device *dev);
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -102,7 +103,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 {
 	return NULL;
 }
-static inline void of_dma_configure(struct device *dev, struct device_node *np)
+
+static inline int of_dma_configure(struct device *dev, struct device_node *np)
+{
+	return 0;
+}
+static inline void of_dma_deconfigure(struct device *dev)
 {}
 #endif /* CONFIG_OF */
 

include/linux/platform_data/iommu-omap.h

@@ -12,28 +12,8 @@
 
 #include <linux/platform_device.h>
 
-#define MMU_REG_SIZE		256
-
-/**
- * struct iommu_arch_data - omap iommu private data
- * @name: name of the iommu device
- * @iommu_dev: handle of the iommu device
- *
- * This is an omap iommu private data object, which binds an iommu user
- * to its iommu device. This object should be placed at the iommu user's
- * dev_archdata so generic IOMMU API can be used without having to
- * utilize omap-specific plumbing anymore.
- */
-struct omap_iommu_arch_data {
-	const char *name;
-	struct omap_iommu *iommu_dev;
-};
-
 struct iommu_platform_data {
-	const char *name;
 	const char *reset_name;
-	int nr_tlb_entries;
-
 	int (*assert_reset)(struct platform_device *pdev, const char *name);
 	int (*deassert_reset)(struct platform_device *pdev, const char *name);
 };

include/trace/events/iommu.h

@@ -11,7 +11,6 @@
 #define _TRACE_IOMMU_H
 
 #include <linux/tracepoint.h>
-#include <linux/pci.h>
 
 struct device;