diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 2d0f7cd867ea..06760503a819 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -14,6 +14,7 @@ conditions.
                         "arm,smmu-v1"
                         "arm,smmu-v2"
                         "arm,mmu-400"
+                        "arm,mmu-401"
                         "arm,mmu-500"
 
                   depending on the particular implementation and/or the
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 28b808c73e8e..14d162952c3b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1211,6 +1211,9 @@ void device_del(struct device *dev)
 	 */
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
+	if (dev->bus)
+		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+					     BUS_NOTIFY_REMOVED_DEVICE, dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
 	cleanup_device_parent(dev);
 	kobject_del(&dev->kobj);
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 801a1d6937e4..417de1f32960 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -507,7 +507,7 @@ int usnic_uiom_attach_dev_to_pd(struct usnic_uiom_pd *pd, struct device *dev)
 	if (err)
 		goto out_free_dev;
 
-	if (!iommu_domain_has_cap(pd->domain, IOMMU_CAP_CACHE_COHERENCY)) {
+	if (!iommu_capable(dev->bus, IOMMU_CAP_CACHE_COHERENCY)) {
 		usnic_err("IOMMU of %s does not support cache coherency\n",
 				dev_name(dev));
 		err = -EINVAL;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index ecb0109a5360..505a9adac2d5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -87,6 +87,27 @@ int amd_iommu_max_glx_val = -1;
 
 static struct dma_map_ops amd_iommu_dma_ops;
 
+/*
+ * This struct contains device specific data for the IOMMU
+ */
+struct iommu_dev_data {
+	struct list_head list;		  /* For domain->dev_list */
+	struct list_head dev_data_list;	  /* For global dev_data_list */
+	struct list_head alias_list;      /* Link alias-groups together */
+	struct iommu_dev_data *alias_data;/* The alias dev_data */
+	struct protection_domain *domain; /* Domain the device is bound to */
+	u16 devid;			  /* PCI Device ID */
+	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
+	bool passthrough;		  /* Default for device is pt_domain */
+	struct {
+		bool enabled;
+		int qdep;
+	} ats;				  /* ATS state */
+	bool pri_tlp;			  /* PASID TLB required for
+					     PPR completions */
+	u32 errata;			  /* Bitmap for errata to apply */
+};
+
 /*
  * general struct to manage commands send to an IOMMU
  */
@@ -114,8 +135,9 @@ static struct iommu_dev_data *alloc_dev_data(u16 devid)
 	if (!dev_data)
 		return NULL;
 
+	INIT_LIST_HEAD(&dev_data->alias_list);
+
 	dev_data->devid = devid;
-	atomic_set(&dev_data->bind, 0);
 
 	spin_lock_irqsave(&dev_data_list_lock, flags);
 	list_add_tail(&dev_data->dev_data_list, &dev_data_list);
@@ -260,17 +282,13 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static int init_iommu_group(struct device *dev)
+static void init_iommu_group(struct device *dev)
 {
 	struct iommu_group *group;
 
 	group = iommu_group_get_for_dev(dev);
-
-	if (IS_ERR(group))
-		return PTR_ERR(group);
-
-	iommu_group_put(group);
-	return 0;
+	if (!IS_ERR(group))
+		iommu_group_put(group);
 }
 
 static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -340,7 +358,6 @@ static int iommu_init_device(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct iommu_dev_data *dev_data;
 	u16 alias;
-	int ret;
 
 	if (dev->archdata.iommu)
 		return 0;
@@ -362,12 +379,9 @@ static int iommu_init_device(struct device *dev)
 			return -ENOTSUPP;
 		}
 		dev_data->alias_data = alias_data;
-	}
 
-	ret = init_iommu_group(dev);
-	if (ret) {
-		free_dev_data(dev_data);
-		return ret;
+		/* Add device to the alias_list */
+		list_add(&dev_data->alias_list, &alias_data->alias_list);
 	}
 
 	if (pci_iommuv2_capable(pdev)) {
@@ -455,6 +469,15 @@ int __init amd_iommu_init_devices(void)
 			goto out_free;
 	}
 
+	/*
+	 * Initialize IOMMU groups only after iommu_init_device() has
+	 * had a chance to populate any IVRS defined aliases.
+	 */
+	for_each_pci_dev(pdev) {
+		if (check_device(&pdev->dev))
+			init_iommu_group(&pdev->dev);
+	}
+
 	return 0;
 
 out_free:
@@ -1368,6 +1391,9 @@ static int iommu_map_page(struct protection_domain *dom,
 	count     = PAGE_SIZE_PTE_COUNT(page_size);
 	pte       = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
 
+	if (!pte)
+		return -ENOMEM;
+
 	for (i = 0; i < count; ++i)
 		if (IOMMU_PTE_PRESENT(pte[i]))
 			return -EBUSY;
@@ -2122,35 +2148,29 @@ static void do_detach(struct iommu_dev_data *dev_data)
 static int __attach_device(struct iommu_dev_data *dev_data,
 			   struct protection_domain *domain)
 {
+	struct iommu_dev_data *head, *entry;
 	int ret;
 
 	/* lock domain */
 	spin_lock(&domain->lock);
 
-	if (dev_data->alias_data != NULL) {
-		struct iommu_dev_data *alias_data = dev_data->alias_data;
+	head = dev_data;
 
-		/* Some sanity checks */
-		ret = -EBUSY;
-		if (alias_data->domain != NULL &&
-				alias_data->domain != domain)
-			goto out_unlock;
+	if (head->alias_data != NULL)
+		head = head->alias_data;
 
-		if (dev_data->domain != NULL &&
-				dev_data->domain != domain)
-			goto out_unlock;
+	/* Now we have the root of the alias group, if any */
 
-		/* Do real assignment */
-		if (alias_data->domain == NULL)
-			do_attach(alias_data, domain);
+	ret = -EBUSY;
+	if (head->domain != NULL)
+		goto out_unlock;
 
-		atomic_inc(&alias_data->bind);
-	}
+	/* Attach alias group root */
+	do_attach(head, domain);
 
-	if (dev_data->domain == NULL)
-		do_attach(dev_data, domain);
-
-	atomic_inc(&dev_data->bind);
+	/* Attach other devices in the alias group */
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_attach(entry, domain);
 
 	ret = 0;
 
@@ -2298,6 +2318,7 @@ static int attach_device(struct device *dev,
  */
 static void __detach_device(struct iommu_dev_data *dev_data)
 {
+	struct iommu_dev_data *head, *entry;
 	struct protection_domain *domain;
 	unsigned long flags;
 
@@ -2307,15 +2328,14 @@ static void __detach_device(struct iommu_dev_data *dev_data)
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (dev_data->alias_data != NULL) {
-		struct iommu_dev_data *alias_data = dev_data->alias_data;
+	head = dev_data;
+	if (head->alias_data != NULL)
+		head = head->alias_data;
 
-		if (atomic_dec_and_test(&alias_data->bind))
-			do_detach(alias_data);
-	}
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_detach(entry);
 
-	if (atomic_dec_and_test(&dev_data->bind))
-		do_detach(dev_data);
+	do_detach(head);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
@@ -2415,6 +2435,7 @@ static int device_change_notifier(struct notifier_block *nb,
 	case BUS_NOTIFY_ADD_DEVICE:
 
 		iommu_init_device(dev);
+		init_iommu_group(dev);
 
 		/*
 		 * dev_data is still NULL and
@@ -3158,7 +3179,6 @@ static void cleanup_domain(struct protection_domain *domain)
 		entry = list_first_entry(&domain->dev_list,
 					 struct iommu_dev_data, list);
 		__detach_device(entry);
-		atomic_set(&entry->bind, 0);
 	}
 
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -3384,20 +3404,20 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 	return paddr;
 }
 
-static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
-				    unsigned long cap)
+static bool amd_iommu_capable(enum iommu_cap cap)
 {
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
-		return 1;
+		return true;
 	case IOMMU_CAP_INTR_REMAP:
-		return irq_remapping_enabled;
+		return (irq_remapping_enabled == 1);
 	}
 
-	return 0;
+	return false;
 }
 
 static const struct iommu_ops amd_iommu_ops = {
+	.capable = amd_iommu_capable,
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
 	.attach_dev = amd_iommu_attach_device,
@@ -3405,7 +3425,6 @@ static const struct iommu_ops amd_iommu_ops = {
 	.map = amd_iommu_map,
 	.unmap = amd_iommu_unmap,
 	.iova_to_phys = amd_iommu_iova_to_phys,
-	.domain_has_cap = amd_iommu_domain_has_cap,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
@@ -4235,7 +4254,7 @@ static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 	return 0;
 }
 
-static int setup_hpet_msi(unsigned int irq, unsigned int id)
+static int alloc_hpet_msi(unsigned int irq, unsigned int id)
 {
 	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
@@ -4274,6 +4293,6 @@ struct irq_remap_ops amd_iommu_irq_ops = {
 	.compose_msi_msg	= compose_msi_msg,
 	.msi_alloc_irq		= msi_alloc_irq,
 	.msi_setup_irq		= msi_setup_irq,
-	.setup_hpet_msi		= setup_hpet_msi,
+	.alloc_hpet_msi		= alloc_hpet_msi,
 };
 #endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 3783e0b44df6..b0522f15730f 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -712,7 +712,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
 	set_iommu_for_device(iommu, devid);
 }
 
-static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
+static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
@@ -731,6 +731,8 @@ static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
 		pr_info("AMD-Vi: Command-line override present for %s id %d - ignoring\n",
 			type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id);
 
+		*devid = entry->devid;
+
 		return 0;
 	}
 
@@ -739,7 +741,7 @@ static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
 		return -ENOMEM;
 
 	entry->id	= id;
-	entry->devid	= devid;
+	entry->devid	= *devid;
 	entry->cmd_line	= cmd_line;
 
 	list_add_tail(&entry->list, list);
@@ -754,7 +756,7 @@ static int __init add_early_maps(void)
 	for (i = 0; i < early_ioapic_map_size; ++i) {
 		ret = add_special_device(IVHD_SPECIAL_IOAPIC,
 					 early_ioapic_map[i].id,
-					 early_ioapic_map[i].devid,
+					 &early_ioapic_map[i].devid,
 					 early_ioapic_map[i].cmd_line);
 		if (ret)
 			return ret;
@@ -763,7 +765,7 @@ static int __init add_early_maps(void)
 	for (i = 0; i < early_hpet_map_size; ++i) {
 		ret = add_special_device(IVHD_SPECIAL_HPET,
 					 early_hpet_map[i].id,
-					 early_hpet_map[i].devid,
+					 &early_hpet_map[i].devid,
 					 early_hpet_map[i].cmd_line);
 		if (ret)
 			return ret;
@@ -978,10 +980,17 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
 
-			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
-			ret = add_special_device(type, handle, devid, false);
+			ret = add_special_device(type, handle, &devid, false);
 			if (ret)
 				return ret;
+
+			/*
+			 * add_special_device might update the devid in case a
+			 * command-line override is present. So call
+			 * set_dev_entry_from_acpi after add_special_device.
+			 */
+			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+
 			break;
 		}
 		default:
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 8e43b7cba133..cec51a8ba844 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -417,27 +417,6 @@ struct protection_domain {
 
 };
 
-/*
- * This struct contains device specific data for the IOMMU
- */
-struct iommu_dev_data {
-	struct list_head list;		  /* For domain->dev_list */
-	struct list_head dev_data_list;	  /* For global dev_data_list */
-	struct iommu_dev_data *alias_data;/* The alias dev_data */
-	struct protection_domain *domain; /* Domain the device is bound to */
-	atomic_t bind;			  /* Domain attach reference count */
-	u16 devid;			  /* PCI Device ID */
-	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Default for device is pt_domain */
-	struct {
-		bool enabled;
-		int qdep;
-	} ats;				  /* ATS state */
-	bool pri_tlp;			  /* PASID TLB required for
-					     PPR completions */
-	u32 errata;			  /* Bitmap for errata to apply */
-};
-
 /*
  * For dynamic growth the aperture size is split into ranges of 128MB of
  * DMA address space each. This struct represents one such range.
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index a83cc2a2a2ca..60558f794922 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -24,7 +24,7 @@
  *	- v7/v8 long-descriptor format
  *	- Non-secure access to the SMMU
  *	- 4k and 64k pages, with contiguous pte hints.
- *	- Up to 42-bit addressing (dependent on VA_BITS)
+ *	- Up to 48-bit addressing (dependent on VA_BITS)
  *	- Context fault reporting
  */
 
@@ -59,7 +59,7 @@
 
 /* SMMU global address space */
 #define ARM_SMMU_GR0(smmu)		((smmu)->base)
-#define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
+#define ARM_SMMU_GR1(smmu)		((smmu)->base + (1 << (smmu)->pgshift))
 
 /*
  * SMMU global address space with conditional offset to access secure
@@ -224,7 +224,7 @@
 
 /* Translation context bank */
 #define ARM_SMMU_CB_BASE(smmu)		((smmu)->base + ((smmu)->size >> 1))
-#define ARM_SMMU_CB(smmu, n)		((n) * (smmu)->pagesize)
+#define ARM_SMMU_CB(smmu, n)		((n) * (1 << (smmu)->pgshift))
 
 #define ARM_SMMU_CB_SCTLR		0x0
 #define ARM_SMMU_CB_RESUME		0x8
@@ -326,6 +326,16 @@
 
 #define FSYNR0_WNR			(1 << 4)
 
+static int force_stage;
+module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(force_stage,
+	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
+
+enum arm_smmu_arch_version {
+	ARM_SMMU_V1 = 1,
+	ARM_SMMU_V2,
+};
+
 struct arm_smmu_smr {
 	u8				idx;
 	u16				mask;
@@ -349,7 +359,7 @@ struct arm_smmu_device {
 
 	void __iomem			*base;
 	unsigned long			size;
-	unsigned long			pagesize;
+	unsigned long			pgshift;
 
 #define ARM_SMMU_FEAT_COHERENT_WALK	(1 << 0)
 #define ARM_SMMU_FEAT_STREAM_MATCH	(1 << 1)
@@ -360,7 +370,7 @@ struct arm_smmu_device {
 
 #define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
 	u32				options;
-	int				version;
+	enum arm_smmu_arch_version	version;
 
 	u32				num_context_banks;
 	u32				num_s2_context_banks;
@@ -370,8 +380,9 @@ struct arm_smmu_device {
 	u32				num_mapping_groups;
 	DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);
 
-	unsigned long			input_size;
+	unsigned long			s1_input_size;
 	unsigned long			s1_output_size;
+	unsigned long			s2_input_size;
 	unsigned long			s2_output_size;
 
 	u32				num_global_irqs;
@@ -426,17 +437,17 @@ static void parse_driver_options(struct arm_smmu_device *smmu)
 	} while (arm_smmu_options[++i].opt);
 }
 
-static struct device *dev_get_master_dev(struct device *dev)
+static struct device_node *dev_get_dev_node(struct device *dev)
 {
 	if (dev_is_pci(dev)) {
 		struct pci_bus *bus = to_pci_dev(dev)->bus;
 
 		while (!pci_is_root_bus(bus))
 			bus = bus->parent;
-		return bus->bridge->parent;
+		return bus->bridge->parent->of_node;
 	}
 
-	return dev;
+	return dev->of_node;
 }
 
 static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
@@ -461,15 +472,17 @@ static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
 }
 
 static struct arm_smmu_master_cfg *
-find_smmu_master_cfg(struct arm_smmu_device *smmu, struct device *dev)
+find_smmu_master_cfg(struct device *dev)
 {
-	struct arm_smmu_master *master;
+	struct arm_smmu_master_cfg *cfg = NULL;
+	struct iommu_group *group = iommu_group_get(dev);
 
-	if (dev_is_pci(dev))
-		return dev->archdata.iommu;
+	if (group) {
+		cfg = iommu_group_get_iommudata(group);
+		iommu_group_put(group);
+	}
 
-	master = find_smmu_master(smmu, dev->of_node);
-	return master ? &master->cfg : NULL;
+	return cfg;
 }
 
 static int insert_smmu_master(struct arm_smmu_device *smmu,
@@ -545,7 +558,7 @@ static struct arm_smmu_device *find_smmu_for_device(struct device *dev)
 {
 	struct arm_smmu_device *smmu;
 	struct arm_smmu_master *master = NULL;
-	struct device_node *dev_node = dev_get_master_dev(dev)->of_node;
+	struct device_node *dev_node = dev_get_dev_node(dev);
 
 	spin_lock(&arm_smmu_devices_lock);
 	list_for_each_entry(smmu, &arm_smmu_devices, list) {
@@ -729,7 +742,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 
 	/* CBAR */
 	reg = cfg->cbar;
-	if (smmu->version == 1)
+	if (smmu->version == ARM_SMMU_V1)
 		reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;
 
 	/*
@@ -744,7 +757,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	}
 	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));
 
-	if (smmu->version > 1) {
+	if (smmu->version > ARM_SMMU_V1) {
 		/* CBA2R */
 #ifdef CONFIG_64BIT
 		reg = CBA2R_RW64_64BIT;
@@ -755,7 +768,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 			       gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
 
 		/* TTBCR2 */
-		switch (smmu->input_size) {
+		switch (smmu->s1_input_size) {
 		case 32:
 			reg = (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
 			break;
@@ -817,14 +830,14 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	 * TTBCR
 	 * We use long descriptor, with inner-shareable WBWA tables in TTBR0.
 	 */
-	if (smmu->version > 1) {
+	if (smmu->version > ARM_SMMU_V1) {
 		if (PAGE_SIZE == SZ_4K)
 			reg = TTBCR_TG0_4K;
 		else
 			reg = TTBCR_TG0_64K;
 
 		if (!stage1) {
-			reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
+			reg |= (64 - smmu->s2_input_size) << TTBCR_T0SZ_SHIFT;
 
 			switch (smmu->s2_output_size) {
 			case 32:
@@ -847,7 +860,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 				break;
 			}
 		} else {
-			reg |= (64 - smmu->input_size) << TTBCR_T0SZ_SHIFT;
+			reg |= (64 - smmu->s1_input_size) << TTBCR_T0SZ_SHIFT;
 		}
 	} else {
 		reg = 0;
@@ -914,7 +927,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		goto out_unlock;
 
 	cfg->cbndx = ret;
-	if (smmu->version == 1) {
+	if (smmu->version == ARM_SMMU_V1) {
 		cfg->irptndx = atomic_inc_return(&smmu->irptndx);
 		cfg->irptndx %= smmu->num_context_irqs;
 	} else {
@@ -1151,9 +1164,10 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
+	/* Devices in an IOMMU group may already be configured */
 	ret = arm_smmu_master_configure_smrs(smmu, cfg);
 	if (ret)
-		return ret;
+		return ret == -EEXIST ? 0 : ret;
 
 	for (i = 0; i < cfg->num_streamids; ++i) {
 		u32 idx, s2cr;
@@ -1174,6 +1188,10 @@ static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
+	/* An IOMMU group is torn down by the first device to be removed */
+	if ((smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) && !cfg->smrs)
+		return;
+
 	/*
 	 * We *must* clear the S2CR first, because freeing the SMR means
 	 * that it can be re-allocated immediately.
@@ -1195,12 +1213,17 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu, *dom_smmu;
 	struct arm_smmu_master_cfg *cfg;
 
-	smmu = dev_get_master_dev(dev)->archdata.iommu;
+	smmu = find_smmu_for_device(dev);
 	if (!smmu) {
 		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
 		return -ENXIO;
 	}
 
+	if (dev->archdata.iommu) {
+		dev_err(dev, "already attached to IOMMU domain\n");
+		return -EEXIST;
+	}
+
 	/*
 	 * Sanity check the domain. We don't support domains across
 	 * different SMMUs.
@@ -1223,11 +1246,14 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
+	cfg = find_smmu_master_cfg(dev);
 	if (!cfg)
 		return -ENODEV;
 
-	return arm_smmu_domain_add_master(smmu_domain, cfg);
+	ret = arm_smmu_domain_add_master(smmu_domain, cfg);
+	if (!ret)
+		dev->archdata.iommu = domain;
+	return ret;
 }
 
 static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1235,9 +1261,12 @@ static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_master_cfg *cfg;
 
-	cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
-	if (cfg)
-		arm_smmu_domain_remove_master(smmu_domain, cfg);
+	cfg = find_smmu_master_cfg(dev);
+	if (!cfg)
+		return;
+
+	dev->archdata.iommu = NULL;
+	arm_smmu_domain_remove_master(smmu_domain, cfg);
 }
 
 static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
@@ -1379,6 +1408,7 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, next, pfn,
 					      prot, stage);
 		phys += next - addr;
+		pfn = __phys_to_pfn(phys);
 	} while (pmd++, addr = next, addr < end);
 
 	return ret;
@@ -1431,9 +1461,11 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 
 	if (cfg->cbar == CBAR_TYPE_S2_TRANS) {
 		stage = 2;
+		input_mask = (1ULL << smmu->s2_input_size) - 1;
 		output_mask = (1ULL << smmu->s2_output_size) - 1;
 	} else {
 		stage = 1;
+		input_mask = (1ULL << smmu->s1_input_size) - 1;
 		output_mask = (1ULL << smmu->s1_output_size) - 1;
 	}
 
@@ -1443,7 +1475,6 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	if (size & ~PAGE_MASK)
 		return -EINVAL;
 
-	input_mask = (1ULL << smmu->input_size) - 1;
 	if ((phys_addr_t)iova & ~input_mask)
 		return -ERANGE;
 
@@ -1526,20 +1557,19 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 	return __pfn_to_phys(pte_pfn(pte)) | (iova & ~PAGE_MASK);
 }
 
-static int arm_smmu_domain_has_cap(struct iommu_domain *domain,
-				   unsigned long cap)
+static bool arm_smmu_capable(enum iommu_cap cap)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	u32 features = smmu ? smmu->features : 0;
-
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
-		return features & ARM_SMMU_FEAT_COHERENT_WALK;
+		/*
+		 * Return true here as the SMMU can always send out coherent
+		 * requests.
+		 */
+		return true;
 	case IOMMU_CAP_INTR_REMAP:
-		return 1; /* MSIs are just memory writes */
+		return true; /* MSIs are just memory writes */
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1549,17 +1579,19 @@ static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
 	return 0; /* Continue walking */
 }
 
+static void __arm_smmu_release_pci_iommudata(void *data)
+{
+	kfree(data);
+}
+
 static int arm_smmu_add_device(struct device *dev)
 {
 	struct arm_smmu_device *smmu;
+	struct arm_smmu_master_cfg *cfg;
 	struct iommu_group *group;
+	void (*releasefn)(void *) = NULL;
 	int ret;
 
-	if (dev->archdata.iommu) {
-		dev_warn(dev, "IOMMU driver already assigned to device\n");
-		return -EINVAL;
-	}
-
 	smmu = find_smmu_for_device(dev);
 	if (!smmu)
 		return -ENODEV;
@@ -1571,7 +1603,6 @@ static int arm_smmu_add_device(struct device *dev)
 	}
 
 	if (dev_is_pci(dev)) {
-		struct arm_smmu_master_cfg *cfg;
 		struct pci_dev *pdev = to_pci_dev(dev);
 
 		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
@@ -1587,11 +1618,20 @@ static int arm_smmu_add_device(struct device *dev)
 		 */
 		pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid,
 				       &cfg->streamids[0]);
-		dev->archdata.iommu = cfg;
+		releasefn = __arm_smmu_release_pci_iommudata;
 	} else {
-		dev->archdata.iommu = smmu;
+		struct arm_smmu_master *master;
+
+		master = find_smmu_master(smmu, dev->of_node);
+		if (!master) {
+			ret = -ENODEV;
+			goto out_put_group;
+		}
+
+		cfg = &master->cfg;
 	}
 
+	iommu_group_set_iommudata(group, cfg, releasefn);
 	ret = iommu_group_add_device(group, dev);
 
 out_put_group:
@@ -1601,14 +1641,11 @@ out_put_group:
 
 static void arm_smmu_remove_device(struct device *dev)
 {
-	if (dev_is_pci(dev))
-		kfree(dev->archdata.iommu);
-
-	dev->archdata.iommu = NULL;
 	iommu_group_remove_device(dev);
 }
 
 static const struct iommu_ops arm_smmu_ops = {
+	.capable	= arm_smmu_capable,
 	.domain_init	= arm_smmu_domain_init,
 	.domain_destroy	= arm_smmu_domain_destroy,
 	.attach_dev	= arm_smmu_attach_dev,
@@ -1616,7 +1653,6 @@ static const struct iommu_ops arm_smmu_ops = {
 	.map		= arm_smmu_map,
 	.unmap		= arm_smmu_unmap,
 	.iova_to_phys	= arm_smmu_iova_to_phys,
-	.domain_has_cap	= arm_smmu_domain_has_cap,
 	.add_device	= arm_smmu_add_device,
 	.remove_device	= arm_smmu_remove_device,
 	.pgsize_bitmap	= (SECTION_SIZE |
@@ -1702,10 +1738,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	u32 id;
 
 	dev_notice(smmu->dev, "probing hardware configuration...\n");
-
-	/* Primecell ID */
-	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_PIDR2);
-	smmu->version = ((id >> PIDR2_ARCH_SHIFT) & PIDR2_ARCH_MASK) + 1;
 	dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);
 
 	/* ID0 */
@@ -1716,6 +1748,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		return -ENODEV;
 	}
 #endif
+
+	/* Restrict available stages based on module parameter */
+	if (force_stage == 1)
+		id &= ~(ID0_S2TS | ID0_NTS);
+	else if (force_stage == 2)
+		id &= ~(ID0_S1TS | ID0_NTS);
+
 	if (id & ID0_S1TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
 		dev_notice(smmu->dev, "\tstage 1 translation\n");
@@ -1732,8 +1771,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	}
 
 	if (!(smmu->features &
-		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2 |
-		 ARM_SMMU_FEAT_TRANS_NESTED))) {
+		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2))) {
 		dev_err(smmu->dev, "\tno translation support!\n");
 		return -ENODEV;
 	}
@@ -1779,12 +1817,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* ID1 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
-	smmu->pagesize = (id & ID1_PAGESIZE) ? SZ_64K : SZ_4K;
+	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
 
 	/* Check for size mismatch of SMMU address space from mapped region */
 	size = 1 <<
 		(((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
-	size *= (smmu->pagesize << 1);
+	size *= 2 << smmu->pgshift;
 	if (smmu->size != size)
 		dev_warn(smmu->dev,
 			"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
@@ -1803,28 +1841,21 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	/* ID2 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
 	size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
+	smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
 
-	/*
-	 * Stage-1 output limited by stage-2 input size due to pgd
-	 * allocation (PTRS_PER_PGD).
-	 */
-	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+	/* Stage-2 input size limited due to pgd allocation (PTRS_PER_PGD) */
 #ifdef CONFIG_64BIT
-		smmu->s1_output_size = min_t(unsigned long, VA_BITS, size);
+	smmu->s2_input_size = min_t(unsigned long, VA_BITS, size);
 #else
-		smmu->s1_output_size = min(32UL, size);
+	smmu->s2_input_size = min(32UL, size);
 #endif
-	} else {
-		smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT,
-					     size);
-	}
 
 	/* The stage-2 output mask is also applied for bypass */
 	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
 	smmu->s2_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
 
-	if (smmu->version == 1) {
-		smmu->input_size = 32;
+	if (smmu->version == ARM_SMMU_V1) {
+		smmu->s1_input_size = 32;
 	} else {
 #ifdef CONFIG_64BIT
 		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
@@ -1832,7 +1863,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 #else
 		size = 32;
 #endif
-		smmu->input_size = size;
+		smmu->s1_input_size = size;
 
 		if ((PAGE_SIZE == SZ_4K && !(id & ID2_PTFS_4K)) ||
 		    (PAGE_SIZE == SZ_64K && !(id & ID2_PTFS_64K)) ||
@@ -1843,15 +1874,30 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		}
 	}
 
-	dev_notice(smmu->dev,
-		   "\t%lu-bit VA, %lu-bit IPA, %lu-bit PA\n",
-		   smmu->input_size, smmu->s1_output_size,
-		   smmu->s2_output_size);
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S1)
+		dev_notice(smmu->dev, "\tStage-1: %lu-bit VA -> %lu-bit IPA\n",
+			   smmu->s1_input_size, smmu->s1_output_size);
+
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S2)
+		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
+			   smmu->s2_input_size, smmu->s2_output_size);
+
 	return 0;
 }
 
+static const struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v1", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,smmu-v2", .data = (void *)ARM_SMMU_V2 },
+	{ .compatible = "arm,mmu-400", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-401", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-500", .data = (void *)ARM_SMMU_V2 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
 static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
 	struct resource *res;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
@@ -1866,6 +1912,9 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	}
 	smmu->dev = dev;
 
+	of_id = of_match_node(arm_smmu_of_match, dev->of_node);
+	smmu->version = (enum arm_smmu_arch_version)of_id->data;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
@@ -1930,7 +1979,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 
 	parse_driver_options(smmu);
 
-	if (smmu->version > 1 &&
+	if (smmu->version > ARM_SMMU_V1 &&
 	    smmu->num_context_banks != smmu->num_context_irqs) {
 		dev_err(dev,
 			"found only %d context interrupt(s) but %d required\n",
@@ -2011,17 +2060,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
-static struct of_device_id arm_smmu_of_match[] = {
-	{ .compatible = "arm,smmu-v1", },
-	{ .compatible = "arm,smmu-v2", },
-	{ .compatible = "arm,mmu-400", },
-	{ .compatible = "arm,mmu-500", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
-#endif
-
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.owner		= THIS_MODULE,
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 06d268abe951..c5c61cabd6e3 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -155,6 +155,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 	if (event == BUS_NOTIFY_ADD_DEVICE) {
 		for (tmp = dev; tmp; tmp = tmp->bus->self) {
 			level--;
+			info->path[level].bus = tmp->bus->number;
 			info->path[level].device = PCI_SLOT(tmp->devfn);
 			info->path[level].function = PCI_FUNC(tmp->devfn);
 			if (pci_is_root_bus(tmp->bus))
@@ -177,17 +178,33 @@ static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
 	int i;
 
 	if (info->bus != bus)
-		return false;
+		goto fallback;
 	if (info->level != count)
-		return false;
+		goto fallback;
 
 	for (i = 0; i < count; i++) {
 		if (path[i].device != info->path[i].device ||
 		    path[i].function != info->path[i].function)
-			return false;
+			goto fallback;
 	}
 
 	return true;
+
+fallback:
+
+	if (count != 1)
+		return false;
+
+	i = info->level - 1;
+	if (bus              == info->path[i].bus &&
+	    path[0].device   == info->path[i].device &&
+	    path[0].function == info->path[i].function) {
+		pr_info(FW_BUG "RMRR entry for device %02x:%02x.%x is broken - applying workaround\n",
+			bus, path[0].device, path[0].function);
+		return true;
+	}
+
+	return false;
 }
 
 /* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
@@ -247,7 +264,7 @@ int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
 
 	for_each_active_dev_scope(devices, count, index, tmp)
 		if (tmp == &info->dev->dev) {
-			rcu_assign_pointer(devices[index].dev, NULL);
+			RCU_INIT_POINTER(devices[index].dev, NULL);
 			synchronize_rcu();
 			put_device(tmp);
 			return 1;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index d037e87a1fe5..74233186f6f7 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -32,7 +32,7 @@
 typedef u32 sysmmu_iova_t;
 typedef u32 sysmmu_pte_t;
 
-/* We does not consider super section mapping (16MB) */
+/* We do not consider super section mapping (16MB) */
 #define SECT_ORDER 20
 #define LPAGE_ORDER 16
 #define SPAGE_ORDER 12
@@ -307,7 +307,7 @@ static void show_fault_information(const char *name,
 
 static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 {
-	/* SYSMMU is in blocked when interrupt occurred. */
+	/* SYSMMU is in blocked state when interrupt occurred. */
 	struct sysmmu_drvdata *data = dev_id;
 	enum exynos_sysmmu_inttype itype;
 	sysmmu_iova_t addr = -1;
@@ -567,8 +567,8 @@ static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
 		/*
 		 * L2TLB invalidation required
 		 * 4KB page: 1 invalidation
-		 * 64KB page: 16 invalidation
-		 * 1MB page: 64 invalidation
+		 * 64KB page: 16 invalidations
+		 * 1MB page: 64 invalidations
 		 * because it is set-associative TLB
 		 * with 8-way and 64 sets.
 		 * 1MB page can be cached in one of all sets.
@@ -714,7 +714,7 @@ static int exynos_iommu_domain_init(struct iommu_domain *domain)
 	if (!priv->lv2entcnt)
 		goto err_counter;
 
-	/* w/a of System MMU v3.3 to prevent caching 1MiB mapping */
+	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
 	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
 		priv->pgtable[i + 0] = ZERO_LV2LINK;
 		priv->pgtable[i + 1] = ZERO_LV2LINK;
@@ -861,14 +861,14 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
 		pgtable_flush(sent, sent + 1);
 
 		/*
-		 * If pretched SLPD is a fault SLPD in zero_l2_table, FLPD cache
-		 * may caches the address of zero_l2_table. This function
-		 * replaces the zero_l2_table with new L2 page table to write
-		 * valid mappings.
+		 * If pre-fetched SLPD is a faulty SLPD in zero_l2_table,
+		 * FLPD cache may cache the address of zero_l2_table. This
+		 * function replaces the zero_l2_table with new L2 page table
+		 * to write valid mappings.
 		 * Accessing the valid area may cause page fault since FLPD
-		 * cache may still caches zero_l2_table for the valid area
-		 * instead of new L2 page table that have the mapping
-		 * information of the valid area
+		 * cache may still cache zero_l2_table for the valid area
+		 * instead of new L2 page table that has the mapping
+		 * information of the valid area.
 		 * Thus any replacement of zero_l2_table with other valid L2
 		 * page table must involve FLPD cache invalidation for System
 		 * MMU v3.3.
@@ -963,27 +963,27 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
 /*
  * *CAUTION* to the I/O virtual memory managers that support exynos-iommu:
  *
- * System MMU v3.x have an advanced logic to improve address translation
+ * System MMU v3.x has advanced logic to improve address translation
  * performance with caching more page table entries by a page table walk.
- * However, the logic has a bug that caching fault page table entries and System
- * MMU reports page fault if the cached fault entry is hit even though the fault
- * entry is updated to a valid entry after the entry is cached.
- * To prevent caching fault page table entries which may be updated to valid
- * entries later, the virtual memory manager should care about the w/a about the
- * problem. The followings describe w/a.
+ * However, the logic has a bug that while caching faulty page table entries,
+ * System MMU reports page fault if the cached fault entry is hit even though
+ * the fault entry is updated to a valid entry after the entry is cached.
+ * To prevent caching faulty page table entries which may be updated to valid
+ * entries later, the virtual memory manager should care about the workaround
+ * for the problem. The following describes the workaround.
  *
  * Any two consecutive I/O virtual address regions must have a hole of 128KiB
- * in maximum to prevent misbehavior of System MMU 3.x. (w/a of h/w bug)
+ * at maximum to prevent misbehavior of System MMU 3.x (workaround for h/w bug).
  *
- * Precisely, any start address of I/O virtual region must be aligned by
+ * Precisely, any start address of I/O virtual region must be aligned with
  * the following sizes for System MMU v3.1 and v3.2.
  * System MMU v3.1: 128KiB
  * System MMU v3.2: 256KiB
  *
  * Because System MMU v3.3 caches page table entries more aggressively, it needs
- * more w/a.
- * - Any two consecutive I/O virtual regions must be have a hole of larger size
- *   than or equal size to 128KiB.
+ * more workarounds.
+ * - Any two consecutive I/O virtual regions must have a hole of size larger
+ *   than or equal to 128KiB.
  * - Start address of an I/O virtual region must be aligned by 128KiB.
  */
 static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
@@ -1061,7 +1061,8 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 			goto err;
 		}
 
-		*ent = ZERO_LV2LINK; /* w/a for h/w bug in Sysmem MMU v3.3 */
+		/* workaround for h/w bug in System MMU v3.3 */
+		*ent = ZERO_LV2LINK;
 		pgtable_flush(ent, ent + 1);
 		size = SECT_SIZE;
 		goto done;
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 56feed7cec15..c828f80d48b0 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -411,8 +411,7 @@ static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
 	return get_phys_addr(dma_domain, iova);
 }
 
-static int fsl_pamu_domain_has_cap(struct iommu_domain *domain,
-				      unsigned long cap)
+static bool fsl_pamu_capable(enum iommu_cap cap)
 {
 	return cap == IOMMU_CAP_CACHE_COHERENCY;
 }
@@ -1080,6 +1079,7 @@ static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
 }
 
 static const struct iommu_ops fsl_pamu_ops = {
+	.capable	= fsl_pamu_capable,
 	.domain_init	= fsl_pamu_domain_init,
 	.domain_destroy = fsl_pamu_domain_destroy,
 	.attach_dev	= fsl_pamu_attach_device,
@@ -1089,7 +1089,6 @@ static const struct iommu_ops fsl_pamu_ops = {
 	.domain_get_windows = fsl_pamu_get_windows,
 	.domain_set_windows = fsl_pamu_set_windows,
 	.iova_to_phys	= fsl_pamu_iova_to_phys,
-	.domain_has_cap = fsl_pamu_domain_has_cap,
 	.domain_set_attr = fsl_pamu_set_domain_attr,
 	.domain_get_attr = fsl_pamu_get_domain_attr,
 	.add_device	= fsl_pamu_add_device,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 5619f264862d..a27d6cb1a793 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3865,8 +3865,7 @@ static int device_notifier(struct notifier_block *nb,
 	if (iommu_dummy(dev))
 		return 0;
 
-	if (action != BUS_NOTIFY_UNBOUND_DRIVER &&
-	    action != BUS_NOTIFY_DEL_DEVICE)
+	if (action != BUS_NOTIFY_REMOVED_DEVICE)
 		return 0;
 
 	/*
@@ -4415,17 +4414,14 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
-static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
-				      unsigned long cap)
+static bool intel_iommu_capable(enum iommu_cap cap)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
-
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
-		return dmar_domain->iommu_snooping;
+		return domain_update_iommu_snooping(NULL) == 1;
 	if (cap == IOMMU_CAP_INTR_REMAP)
-		return irq_remapping_enabled;
+		return irq_remapping_enabled == 1;
 
-	return 0;
+	return false;
 }
 
 static int intel_iommu_add_device(struct device *dev)
@@ -4464,6 +4460,7 @@ static void intel_iommu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops intel_iommu_ops = {
+	.capable	= intel_iommu_capable,
 	.domain_init	= intel_iommu_domain_init,
 	.domain_destroy = intel_iommu_domain_destroy,
 	.attach_dev	= intel_iommu_attach_device,
@@ -4471,7 +4468,6 @@ static const struct iommu_ops intel_iommu_ops = {
 	.map		= intel_iommu_map,
 	.unmap		= intel_iommu_unmap,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
-	.domain_has_cap = intel_iommu_domain_has_cap,
 	.add_device	= intel_iommu_add_device,
 	.remove_device	= intel_iommu_remove_device,
 	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 0df41f6264f5..7c80661b35c1 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -438,8 +438,7 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
 		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
 
 	/* Set interrupt-remapping table pointer */
-	iommu->gcmd |= DMA_GCMD_SIRTP;
-	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+	writel(iommu->gcmd | DMA_GCMD_SIRTP, iommu->reg + DMAR_GCMD_REG);
 
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRTPS), sts);
@@ -1139,7 +1138,7 @@ static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 	return ret;
 }
 
-static int intel_setup_hpet_msi(unsigned int irq, unsigned int id)
+static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
 {
 	int ret = -1;
 	struct intel_iommu *iommu;
@@ -1170,5 +1169,5 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.compose_msi_msg	= intel_compose_msi_msg,
 	.msi_alloc_irq		= intel_msi_alloc_irq,
 	.msi_setup_irq		= intel_msi_setup_irq,
-	.setup_hpet_msi		= intel_setup_hpet_msi,
+	.alloc_hpet_msi		= intel_alloc_hpet_msi,
 };
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0639b9274b11..ed8b04867b1f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -30,6 +30,7 @@
 #include <linux/notifier.h>
 #include <linux/err.h>
 #include <linux/pci.h>
+#include <linux/bitops.h>
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
@@ -519,6 +520,9 @@ int iommu_group_id(struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_group_id);
 
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns);
+
 /*
  * To consider a PCI device isolated, we require ACS to support Source
  * Validation, Request Redirection, Completer Redirection, and Upstream
@@ -529,6 +533,86 @@ EXPORT_SYMBOL_GPL(iommu_group_id);
  */
 #define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
 
+/*
+ * For multifunction devices which are not isolated from each other, find
+ * all the other non-isolated functions and look for existing groups.  For
+ * each function, we also need to look for aliases to or from other devices
+ * that may already have a group.
+ */
+static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
+							unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
+		return NULL;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus ||
+		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
+		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
+			continue;
+
+		group = get_pci_alias_group(tmp, devfns);
+		if (group) {
+			pci_dev_put(tmp);
+			return group;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look for aliases to or from the given device for exisiting groups.  The
+ * dma_alias_devfn only supports aliases on the same bus, therefore the search
+ * space is quite small (especially since we're really only looking at pcie
+ * device, and therefore only expect multiple slots on the root complex or
+ * downstream switch ports).  It's conceivable though that a pair of
+ * multifunction devices could have aliases between them that would cause a
+ * loop.  To prevent this, we use a bitmap to track where we've been.
+ */
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
+		return NULL;
+
+	group = iommu_group_get(&pdev->dev);
+	if (group)
+		return group;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus)
+			continue;
+
+		/* We alias them or they alias us */
+		if (((pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     pdev->dma_alias_devfn == tmp->devfn) ||
+		    ((tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     tmp->dma_alias_devfn == pdev->devfn)) {
+
+			group = get_pci_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+
+			group = get_pci_function_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+		}
+	}
+
+	return NULL;
+}
+
 struct group_for_pci_data {
 	struct pci_dev *pdev;
 	struct iommu_group *group;
@@ -557,7 +641,7 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
 	struct group_for_pci_data data;
 	struct pci_bus *bus;
 	struct iommu_group *group = NULL;
-	struct pci_dev *tmp;
+	u64 devfns[4] = { 0 };
 
 	/*
 	 * Find the upstream DMA alias for the device.  A device must not
@@ -591,76 +675,21 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
 	}
 
 	/*
-	 * Next we need to consider DMA alias quirks.  If one device aliases
-	 * to another, they should be grouped together.  It's theoretically
-	 * possible that aliases could create chains of devices where each
-	 * device aliases another device.  If we then factor in multifunction
-	 * ACS grouping requirements, each alias could incorporate a new slot
-	 * with multiple functions, each with aliases.  This is all extremely
-	 * unlikely as DMA alias quirks are typically only used for PCIe
-	 * devices where we usually have a single slot per bus.  Furthermore,
-	 * the alias quirk is usually to another function within the slot
-	 * (and ACS multifunction is not supported) or to a different slot
-	 * that doesn't physically exist.  The likely scenario is therefore
-	 * that everything on the bus gets grouped together.  To reduce the
-	 * problem space, share the IOMMU group for all devices on the bus
-	 * if a DMA alias quirk is present on the bus.
+	 * Look for existing groups on device aliases.  If we alias another
+	 * device or another device aliases us, use the same group.
 	 */
-	tmp = NULL;
-	for_each_pci_dev(tmp) {
-		if (tmp->bus != pdev->bus ||
-		    !(tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN))
-			continue;
-
-		pci_dev_put(tmp);
-		tmp = NULL;
-
-		/* We have an alias quirk, search for an existing group */
-		for_each_pci_dev(tmp) {
-			struct iommu_group *group_tmp;
-
-			if (tmp->bus != pdev->bus)
-				continue;
-
-			group_tmp = iommu_group_get(&tmp->dev);
-			if (!group) {
-				group = group_tmp;
-				continue;
-			}
-
-			if (group_tmp) {
-				WARN_ON(group != group_tmp);
-				iommu_group_put(group_tmp);
-			}
-		}
-
-		return group ? group : iommu_group_alloc();
-	}
+	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
 
 	/*
-	 * Non-multifunction devices or multifunction devices supporting
-	 * ACS get their own group.
+	 * Look for existing groups on non-isolated functions on the same
+	 * slot and aliases of those funcions, if any.  No need to clear
+	 * the search bitmap, the tested devfns are still valid.
 	 */
-	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
-		return iommu_group_alloc();
-
-	/*
-	 * Multifunction devices not supporting ACS share a group with other
-	 * similar devices in the same slot.
-	 */
-	tmp = NULL;
-	for_each_pci_dev(tmp) {
-		if (tmp == pdev || tmp->bus != pdev->bus ||
-		    PCI_SLOT(tmp->devfn) !=  PCI_SLOT(pdev->devfn) ||
-		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
-			continue;
-
-		group = iommu_group_get(&tmp->dev);
-		if (group) {
-			pci_dev_put(tmp);
-			return group;
-		}
-	}
+	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
 
 	/* No shared group found, allocate new */
 	return iommu_group_alloc();
@@ -770,18 +799,26 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 	return 0;
 }
 
-static struct notifier_block iommu_bus_nb = {
-	.notifier_call = iommu_bus_notifier,
-};
-
-static void iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
+static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
 {
+	int err;
+	struct notifier_block *nb;
 	struct iommu_callback_data cb = {
 		.ops = ops,
 	};
 
-	bus_register_notifier(bus, &iommu_bus_nb);
-	bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (!nb)
+		return -ENOMEM;
+
+	nb->notifier_call = iommu_bus_notifier;
+
+	err = bus_register_notifier(bus, nb);
+	if (err) {
+		kfree(nb);
+		return err;
+	}
+	return bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
 }
 
 /**
@@ -805,9 +842,7 @@ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
 	bus->iommu_ops = ops;
 
 	/* Do IOMMU specific setup for this bus-type */
-	iommu_bus_init(bus, ops);
-
-	return 0;
+	return iommu_bus_init(bus, ops);
 }
 EXPORT_SYMBOL_GPL(bus_set_iommu);
 
@@ -817,6 +852,15 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	if (!bus->iommu_ops || !bus->iommu_ops->capable)
+		return false;
+
+	return bus->iommu_ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(iommu_capable);
+
 /**
  * iommu_set_fault_handler() - set a fault handler for an iommu domain
  * @domain: iommu domain
@@ -947,16 +991,6 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 }
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 
-int iommu_domain_has_cap(struct iommu_domain *domain,
-			 unsigned long cap)
-{
-	if (unlikely(domain->ops->domain_has_cap == NULL))
-		return 0;
-
-	return domain->ops->domain_has_cap(domain, cap);
-}
-EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
-
 static size_t iommu_pgsize(struct iommu_domain *domain,
 			   unsigned long addr_merge, size_t size)
 {
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 33c439524080..74a1767c89b5 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -12,6 +12,7 @@
 #include <asm/processor.h>
 #include <asm/x86_init.h>
 #include <asm/apic.h>
+#include <asm/hpet.h>
 
 #include "irq_remapping.h"
 
@@ -345,10 +346,16 @@ static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
 
 int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
 {
-	if (!remap_ops || !remap_ops->setup_hpet_msi)
+	int ret;
+
+	if (!remap_ops || !remap_ops->alloc_hpet_msi)
 		return -ENODEV;
 
-	return remap_ops->setup_hpet_msi(irq, id);
+	ret = remap_ops->alloc_hpet_msi(irq, id);
+	if (ret)
+		return -EINVAL;
+
+	return default_setup_hpet_msi(irq, id);
 }
 
 void panic_if_irq_remap(const char *msg)
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 90c4dae5a46b..fde250f86e60 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -80,7 +80,7 @@ struct irq_remap_ops {
 	int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
 
 	/* Setup interrupt remapping for an HPET MSI */
-	int (*setup_hpet_msi)(unsigned int, unsigned int);
+	int (*alloc_hpet_msi)(unsigned int, unsigned int);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 49f41d6e02f1..6e3dcc289d59 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -603,10 +603,9 @@ fail:
 	return ret;
 }
 
-static int msm_iommu_domain_has_cap(struct iommu_domain *domain,
-				    unsigned long cap)
+static bool msm_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static void print_ctx_regs(void __iomem *base, int ctx)
@@ -675,6 +674,7 @@ fail:
 }
 
 static const struct iommu_ops msm_iommu_ops = {
+	.capable = msm_iommu_capable,
 	.domain_init = msm_iommu_domain_init,
 	.domain_destroy = msm_iommu_domain_destroy,
 	.attach_dev = msm_iommu_attach_dev,
@@ -682,7 +682,6 @@ static const struct iommu_ops msm_iommu_ops = {
 	.map = msm_iommu_map,
 	.unmap = msm_iommu_unmap,
 	.iova_to_phys = msm_iommu_iova_to_phys,
-	.domain_has_cap = msm_iommu_domain_has_cap,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index e202b0c24120..36278870e84a 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -26,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/of_iommu.h>
 #include <linux/of_irq.h>
+#include <linux/of_platform.h>
 
 #include <asm/cacheflush.h>
 
@@ -892,19 +893,11 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 		goto err_enable;
 	flush_iotlb_all(obj);
 
-	if (!try_module_get(obj->owner)) {
-		err = -ENODEV;
-		goto err_module;
-	}
-
 	spin_unlock(&obj->iommu_lock);
 
 	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
 	return obj;
 
-err_module:
-	if (obj->refcount == 1)
-		iommu_disable(obj);
 err_enable:
 	obj->refcount--;
 	spin_unlock(&obj->iommu_lock);
@@ -925,8 +918,6 @@ static void omap_iommu_detach(struct omap_iommu *obj)
 	if (--obj->refcount == 0)
 		iommu_disable(obj);
 
-	module_put(obj->owner);
-
 	obj->iopgd = NULL;
 
 	spin_unlock(&obj->iommu_lock);
@@ -1006,7 +997,7 @@ static int omap_iommu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id omap_iommu_of_match[] = {
+static const struct of_device_id omap_iommu_of_match[] = {
 	{ .compatible = "ti,omap2-iommu" },
 	{ .compatible = "ti,omap4-iommu" },
 	{ .compatible = "ti,dra7-iommu"	},
@@ -1091,6 +1082,11 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 	int ret = 0;
 
+	if (!arch_data || !arch_data->name) {
+		dev_err(dev, "device doesn't have an associated iommu\n");
+		return -EINVAL;
+	}
+
 	spin_lock(&omap_domain->lock);
 
 	/* only a single device is supported per domain for now */
@@ -1239,6 +1235,7 @@ static int omap_iommu_add_device(struct device *dev)
 {
 	struct omap_iommu_arch_data *arch_data;
 	struct device_node *np;
+	struct platform_device *pdev;
 
 	/*
 	 * Allocate the archdata iommu structure for DT-based devices.
@@ -1253,13 +1250,19 @@ static int omap_iommu_add_device(struct device *dev)
 	if (!np)
 		return 0;
 
+	pdev = of_find_device_by_node(np);
+	if (WARN_ON(!pdev)) {
+		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(dev), GFP_KERNEL);
+	arch_data->name = kstrdup(dev_name(&pdev->dev), GFP_KERNEL);
 	dev->archdata.iommu = arch_data;
 
 	of_node_put(np);
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 1275a822934b..4f1b68c08c15 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -28,7 +28,6 @@ struct iotlb_entry {
 
 struct omap_iommu {
 	const char	*name;
-	struct module	*owner;
 	void __iomem	*regbase;
 	struct device	*dev;
 	void		*isr_priv;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index b10a8ecede8e..a6d76abf2c06 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -303,13 +303,13 @@ static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pa;
 }
 
-static int gart_iommu_domain_has_cap(struct iommu_domain *domain,
-				     unsigned long cap)
+static bool gart_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static const struct iommu_ops gart_iommu_ops = {
+	.capable	= gart_iommu_capable,
 	.domain_init	= gart_iommu_domain_init,
 	.domain_destroy	= gart_iommu_domain_destroy,
 	.attach_dev	= gart_iommu_attach_dev,
@@ -317,7 +317,6 @@ static const struct iommu_ops gart_iommu_ops = {
 	.map		= gart_iommu_map,
 	.unmap		= gart_iommu_unmap,
 	.iova_to_phys	= gart_iommu_iova_to_phys,
-	.domain_has_cap	= gart_iommu_domain_has_cap,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
 };
 
@@ -416,7 +415,7 @@ static const struct dev_pm_ops tegra_gart_pm_ops = {
 	.resume		= tegra_gart_resume,
 };
 
-static struct of_device_id tegra_gart_of_match[] = {
+static const struct of_device_id tegra_gart_of_match[] = {
 	{ .compatible = "nvidia,tegra20-gart", },
 	{ },
 };
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 3ded3894623c..3afdf43f732a 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -780,10 +780,9 @@ static phys_addr_t smmu_iommu_iova_to_phys(struct iommu_domain *domain,
 	return PFN_PHYS(pfn);
 }
 
-static int smmu_iommu_domain_has_cap(struct iommu_domain *domain,
-				     unsigned long cap)
+static bool smmu_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static int smmu_iommu_attach_dev(struct iommu_domain *domain,
@@ -949,6 +948,7 @@ static void smmu_iommu_domain_destroy(struct iommu_domain *domain)
 }
 
 static const struct iommu_ops smmu_iommu_ops = {
+	.capable	= smmu_iommu_capable,
 	.domain_init	= smmu_iommu_domain_init,
 	.domain_destroy	= smmu_iommu_domain_destroy,
 	.attach_dev	= smmu_iommu_attach_dev,
@@ -956,7 +956,6 @@ static const struct iommu_ops smmu_iommu_ops = {
 	.map		= smmu_iommu_map,
 	.unmap		= smmu_iommu_unmap,
 	.iova_to_phys	= smmu_iommu_iova_to_phys,
-	.domain_has_cap	= smmu_iommu_domain_has_cap,
 	.pgsize_bitmap	= SMMU_IOMMU_PGSIZES,
 };
 
@@ -1260,7 +1259,7 @@ static const struct dev_pm_ops tegra_smmu_pm_ops = {
 	.resume		= tegra_smmu_resume,
 };
 
-static struct of_device_id tegra_smmu_of_match[] = {
+static const struct of_device_id tegra_smmu_of_match[] = {
 	{ .compatible = "nvidia,tegra30-smmu", },
 	{ },
 };
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 583ccdb2c58f..4a9d666f1e91 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -723,14 +723,14 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	list_add(&group->next, &domain->group_list);
 
 	if (!allow_unsafe_interrupts &&
-	    !iommu_domain_has_cap(domain->domain, IOMMU_CAP_INTR_REMAP)) {
+	    !iommu_capable(bus, IOMMU_CAP_INTR_REMAP)) {
 		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
 		       __func__);
 		ret = -EPERM;
 		goto out_detach;
 	}
 
-	if (iommu_domain_has_cap(domain->domain, IOMMU_CAP_CACHE_COHERENCY))
+	if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
 		domain->prot |= IOMMU_CACHE;
 
 	/*
diff --git a/include/linux/device.h b/include/linux/device.h
index a608e237f0a8..ce1f21608b16 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -181,13 +181,14 @@ extern int bus_unregister_notifier(struct bus_type *bus,
  * with the device lock held in the core, so be careful.
  */
 #define BUS_NOTIFY_ADD_DEVICE		0x00000001 /* device added */
-#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device removed */
-#define BUS_NOTIFY_BIND_DRIVER		0x00000003 /* driver about to be
+#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device to be removed */
+#define BUS_NOTIFY_REMOVED_DEVICE	0x00000003 /* device removed */
+#define BUS_NOTIFY_BIND_DRIVER		0x00000004 /* driver about to be
 						      bound */
-#define BUS_NOTIFY_BOUND_DRIVER		0x00000004 /* driver bound to device */
-#define BUS_NOTIFY_UNBIND_DRIVER	0x00000005 /* driver about to be
+#define BUS_NOTIFY_BOUND_DRIVER		0x00000005 /* driver bound to device */
+#define BUS_NOTIFY_UNBIND_DRIVER	0x00000006 /* driver about to be
 						      unbound */
-#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000006 /* driver is unbound
+#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000007 /* driver is unbound
 						      from the device */
 
 extern struct kset *bus_get_kset(struct bus_type *bus);
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 1deece46a0ca..593fff99e6bf 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -56,13 +56,19 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_path {
+	u8 bus;
+	u8 device;
+	u8 function;
+};
+
 struct dmar_pci_notify_info {
 	struct pci_dev			*dev;
 	unsigned long			event;
 	int				bus;
 	u16				seg;
 	u16				level;
-	struct acpi_dmar_pci_path	path[];
+	struct dmar_pci_path		path[];
 }  __attribute__((packed));
 
 extern struct rw_semaphore dmar_global_lock;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 7b02bcc85b9e..e6a7c9ff72f2 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -57,8 +57,11 @@ struct iommu_domain {
 	struct iommu_domain_geometry geometry;
 };
 
-#define IOMMU_CAP_CACHE_COHERENCY	0x1
-#define IOMMU_CAP_INTR_REMAP		0x2	/* isolates device intrs */
+enum iommu_cap {
+	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
+					   transactions */
+	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
+};
 
 /*
  * Following constraints are specifc to FSL_PAMUV1:
@@ -95,7 +98,6 @@ enum iommu_attr {
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @iova_to_phys: translate iova to physical address
- * @domain_has_cap: domain capabilities query
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
  * @domain_get_attr: Query domain attributes
@@ -103,6 +105,7 @@ enum iommu_attr {
  * @pgsize_bitmap: bitmap of supported page sizes
  */
 struct iommu_ops {
+	bool (*capable)(enum iommu_cap);
 	int (*domain_init)(struct iommu_domain *domain);
 	void (*domain_destroy)(struct iommu_domain *domain);
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
@@ -112,8 +115,6 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
-	int (*domain_has_cap)(struct iommu_domain *domain,
-			      unsigned long cap);
 	int (*add_device)(struct device *dev);
 	void (*remove_device)(struct device *dev);
 	int (*device_group)(struct device *dev, unsigned int *groupid);
@@ -143,6 +144,7 @@ struct iommu_ops {
 
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern bool iommu_present(struct bus_type *bus);
+extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
 extern struct iommu_group *iommu_group_get_by_id(int id);
 extern void iommu_domain_free(struct iommu_domain *domain);
@@ -155,8 +157,6 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
-extern int iommu_domain_has_cap(struct iommu_domain *domain,
-				unsigned long cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
@@ -251,6 +251,11 @@ static inline bool iommu_present(struct bus_type *bus)
 	return false;
 }
 
+static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	return false;
+}
+
 static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
 {
 	return NULL;
@@ -305,12 +310,6 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad
 	return 0;
 }
 
-static inline int iommu_domain_has_cap(struct iommu_domain *domain,
-				       unsigned long cap)
-{
-	return 0;
-}
-
 static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 				iommu_fault_handler_t handler, void *token)
 {
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index e723bb91aa34..e51d9f9b995f 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -191,8 +191,7 @@ int kvm_assign_device(struct kvm *kvm,
 		return r;
 	}
 
-	noncoherent = !iommu_domain_has_cap(kvm->arch.iommu_domain,
-					    IOMMU_CAP_CACHE_COHERENCY);
+	noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
 
 	/* Check if need to update IOMMU page table for guest memory */
 	if (noncoherent != kvm->arch.iommu_noncoherent) {
@@ -254,8 +253,7 @@ int kvm_iommu_map_guest(struct kvm *kvm)
 	}
 
 	if (!allow_unsafe_assigned_interrupts &&
-	    !iommu_domain_has_cap(kvm->arch.iommu_domain,
-				  IOMMU_CAP_INTR_REMAP)) {
+	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
 		printk(KERN_WARNING "%s: No interrupt remapping support,"
 		       " disallowing device assignment."
 		       " Re-enble with \"allow_unsafe_assigned_interrupts=1\""