diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 597d563d636a..b822e484b7e5 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -155,8 +155,7 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 
 		order = __ffs(tegra->domain->pgsize_bitmap);
 		init_iova_domain(&tegra->carveout.domain, 1UL << order,
-				 carveout_start >> order,
-				 carveout_end >> order);
+				 carveout_start >> order);
 
 		tegra->carveout.shift = iova_shift(&tegra->carveout.domain);
 		tegra->carveout.limit = carveout_end >> tegra->carveout.shift;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 7f22c5c37660..5267c62e8896 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -198,8 +198,7 @@ static int host1x_probe(struct platform_device *pdev)
 
 		order = __ffs(host->domain->pgsize_bitmap);
 		init_iova_domain(&host->iova, 1UL << order,
-				 geometry->aperture_start >> order,
-				 geometry->aperture_end >> order);
+				 geometry->aperture_start >> order);
 		host->iova_end = geometry->aperture_end;
 	}
 
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 8e8874d23717..9dc7facfd2e5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -63,7 +63,6 @@
 /* IO virtual address start page frame number */
 #define IOVA_START_PFN		(1)
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 
 /* Reserved IOVA ranges */
 #define MSI_RANGE_START		(0xfee00000)
@@ -1547,10 +1546,11 @@ static unsigned long dma_ops_alloc_iova(struct device *dev,
 
 	if (dma_mask > DMA_BIT_MASK(32))
 		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-				      IOVA_PFN(DMA_BIT_MASK(32)));
+				      IOVA_PFN(DMA_BIT_MASK(32)), false);
 
 	if (!pfn)
-		pfn = alloc_iova_fast(&dma_dom->iovad, pages, IOVA_PFN(dma_mask));
+		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
+				      IOVA_PFN(dma_mask), true);
 
 	return (pfn << PAGE_SHIFT);
 }
@@ -1788,8 +1788,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
 
-	init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&dma_dom->iovad, PAGE_SIZE, IOVA_START_PFN);
 
 	if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
 		goto free_dma_dom;
@@ -2696,8 +2695,7 @@ static int init_reserved_iova_ranges(void)
 	struct pci_dev *pdev = NULL;
 	struct iova *val;
 
-	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE, IOVA_START_PFN);
 
 	lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
 			  &reserved_rbtree_key);
@@ -3663,11 +3661,11 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count, bool align)
 {
 	struct irq_remap_table *table;
+	int index, c, alignment = 1;
 	unsigned long flags;
-	int index, c;
 	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
 	if (!iommu)
@@ -3677,16 +3675,22 @@ static int alloc_irq_index(u16 devid, int count)
 	if (!table)
 		return -ENODEV;
 
+	if (align)
+		alignment = roundup_pow_of_two(count);
+
 	spin_lock_irqsave(&table->lock, flags);
 
 	/* Scan table for free entries */
-	for (c = 0, index = table->min_index;
+	for (index = ALIGN(table->min_index, alignment), c = 0;
 	     index < MAX_IRQS_PER_TABLE;
-	     ++index) {
-		if (!iommu->irte_ops->is_allocated(table, index))
+	     index++) {
+		if (!iommu->irte_ops->is_allocated(table, index)) {
 			c += 1;
-		else
-			c = 0;
+		} else {
+			c     = 0;
+			index = ALIGN(index, alignment);
+			continue;
+		}
 
 		if (c == count)	{
 			for (; c != 0; --c)
@@ -4099,7 +4103,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		else
 			ret = -ENOMEM;
 	} else {
-		index = alloc_irq_index(devid, nr_irqs);
+		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
+
+		index = alloc_irq_index(devid, nr_irqs, align);
 	}
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index e67ba6c40faf..ee0c7b73cff7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1743,6 +1743,14 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+
+	if (smmu)
+		__arm_smmu_tlb_sync(smmu);
+}
+
 static phys_addr_t
 arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
@@ -1963,6 +1971,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 3bdb799d3b4b..e4a82d70d446 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -250,6 +250,7 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
+	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
@@ -735,7 +736,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	const struct iommu_gather_ops *tlb_ops;
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)
@@ -813,7 +813,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			ias = min(ias, 32UL);
 			oas = min(oas, 32UL);
 		}
-		tlb_ops = &arm_smmu_s1_tlb_ops;
+		smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
 		break;
 	case ARM_SMMU_DOMAIN_NESTED:
 		/*
@@ -833,9 +833,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			oas = min(oas, 40UL);
 		}
 		if (smmu->version == ARM_SMMU_V2)
-			tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
 		else
-			tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
 		break;
 	default:
 		ret = -EINVAL;
@@ -863,7 +863,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
-		.tlb		= tlb_ops,
+		.tlb		= smmu_domain->tlb_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1259,6 +1259,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+}
+
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 					      dma_addr_t iova)
 {
@@ -1562,6 +1570,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9d1cebe7f6cb..25914d36c5ac 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -292,18 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		/* ...then finally give it a kicking to make sure it fits */
 		base_pfn = max_t(unsigned long, base_pfn,
 				domain->geometry.aperture_start >> order);
-		end_pfn = min_t(unsigned long, end_pfn,
-				domain->geometry.aperture_end >> order);
 	}
-	/*
-	 * PCI devices may have larger DMA masks, but still prefer allocating
-	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
-	 * apply to the typical platform device, so for those we may as well
-	 * leave the cache limit at the top of their range to save an rb_last()
-	 * traversal on every allocation.
-	 */
-	if (dev && dev_is_pci(dev))
-		end_pfn &= DMA_BIT_MASK(32) >> order;
 
 	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
@@ -312,16 +301,11 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		/*
-		 * If we have devices with different DMA masks, move the free
-		 * area cache limit down for the benefit of the smaller one.
-		 */
-		iovad->dma_32bit_pfn = min(end_pfn + 1, iovad->dma_32bit_pfn);
 
 		return 0;
 	}
 
-	init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
+	init_iova_domain(iovad, 1UL << order, base_pfn);
 	if (!dev)
 		return 0;
 
@@ -386,10 +370,12 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 
 	/* Try to get PCI devices a SAC address */
 	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
-		iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
+		iova = alloc_iova_fast(iovad, iova_len,
+				       DMA_BIT_MASK(32) >> shift, false);
 
 	if (!iova)
-		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
+		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
+				       true);
 
 	return (dma_addr_t)iova << shift;
 }
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 57c920c1372d..1ea7cd537873 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -801,13 +801,16 @@ int __init dmar_dev_scope_init(void)
 				dmar_free_pci_notify_info(info);
 			}
 		}
-
-		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 	}
 
 	return dmar_dev_scope_status;
 }
 
+void dmar_register_bus_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+}
+
 
 int __init dmar_table_init(void)
 {
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 25c2c75f5332..79c45650f8de 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -263,6 +263,7 @@ struct exynos_iommu_domain {
 struct sysmmu_drvdata {
 	struct device *sysmmu;		/* SYSMMU controller device */
 	struct device *master;		/* master device (owner) */
+	struct device_link *link;	/* runtime PM link to master */
 	void __iomem *sfrbase;		/* our registers */
 	struct clk *clk;		/* SYSMMU's clock */
 	struct clk *aclk;		/* SYSMMU's aclk clock */
@@ -1250,6 +1251,8 @@ static struct iommu_group *get_device_iommu_group(struct device *dev)
 
 static int exynos_iommu_add_device(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 	struct iommu_group *group;
 
 	if (!has_sysmmu(dev))
@@ -1260,6 +1263,15 @@ static int exynos_iommu_add_device(struct device *dev)
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		/*
+		 * SYSMMU will be runtime activated via device link
+		 * (dependency) to its master device, so there are no
+		 * direct calls to pm_runtime_get/put in this driver.
+		 */
+		data->link = device_link_add(dev, data->sysmmu,
+					     DL_FLAG_PM_RUNTIME);
+	}
 	iommu_group_put(group);
 
 	return 0;
@@ -1268,6 +1280,7 @@ static int exynos_iommu_add_device(struct device *dev)
 static void exynos_iommu_remove_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 
 	if (!has_sysmmu(dev))
 		return;
@@ -1283,6 +1296,9 @@ static void exynos_iommu_remove_device(struct device *dev)
 		}
 	}
 	iommu_group_remove_device(dev);
+
+	list_for_each_entry(data, &owner->controllers, owner_node)
+		device_link_del(data->link);
 }
 
 static int exynos_iommu_of_xlate(struct device *dev,
@@ -1316,13 +1332,6 @@ static int exynos_iommu_of_xlate(struct device *dev,
 	list_add_tail(&data->owner_node, &owner->controllers);
 	data->master = dev;
 
-	/*
-	 * SYSMMU will be runtime activated via device link (dependency) to its
-	 * master device, so there are no direct calls to pm_runtime_get/put
-	 * in this driver.
-	 */
-	device_link_add(dev, data->sysmmu, DL_FLAG_PM_RUNTIME);
-
 	return 0;
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6784a05dd6b2..a0babdbf7146 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -82,8 +82,6 @@
 #define IOVA_START_PFN		(1)
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
-#define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
 
 /* page table handling */
 #define LEVEL_STRIDE		(9)
@@ -1878,8 +1876,7 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1938,8 +1935,7 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
 	unsigned long sagaw;
 	int err;
 
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
 
 	err = init_iova_flush_queue(&domain->iovad,
 				    iommu_flush_iova, iova_entry_free);
@@ -2058,7 +2054,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	if (context_copied(context)) {
 		u16 did_old = context_domain_id(context);
 
-		if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) {
+		if (did_old < cap_ndoms(iommu->cap)) {
 			iommu->flush.flush_context(iommu, did_old,
 						   (((u16)bus) << 8) | devfn,
 						   DMA_CCMD_MASK_NOBIT,
@@ -3473,11 +3469,12 @@ static unsigned long intel_alloc_iova(struct device *dev,
 		 * from higher range
 		 */
 		iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
-					   IOVA_PFN(DMA_BIT_MASK(32)));
+					   IOVA_PFN(DMA_BIT_MASK(32)), false);
 		if (iova_pfn)
 			return iova_pfn;
 	}
-	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages, IOVA_PFN(dma_mask));
+	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
+				   IOVA_PFN(dma_mask), true);
 	if (unlikely(!iova_pfn)) {
 		pr_err("Allocating %ld-page iova for %s failed",
 		       nrpages, dev_name(dev));
@@ -4752,6 +4749,16 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
+	up_write(&dmar_global_lock);
+
+	/*
+	 * The bus notifier takes the dmar_global_lock, so lockdep will
+	 * complain later when we register it under the lock.
+	 */
+	dmar_register_bus_notifier();
+
+	down_write(&dmar_global_lock);
+
 	if (no_iommu || dmar_disabled) {
 		/*
 		 * We exit the function here to ensure IOMMU's remapping and
@@ -4897,8 +4904,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 6961fc393f0b..2ca08dc9331c 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -660,16 +660,11 @@ static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			 size_t size)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	size_t unmapped;
 
 	if (WARN_ON(upper_32_bits(iova)))
 		return 0;
 
-	unmapped = __arm_v7s_unmap(data, iova, size, 1, data->pgd);
-	if (unmapped)
-		io_pgtable_tlb_sync(&data->iop);
-
-	return unmapped;
+	return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
 }
 
 static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index e8018a308868..51e5c43caed1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -609,7 +609,6 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			  size_t size)
 {
-	size_t unmapped;
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	arm_lpae_iopte *ptep = data->pgd;
 	int lvl = ARM_LPAE_START_LVL(data);
@@ -617,11 +616,7 @@ static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
 		return 0;
 
-	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
-	if (unmapped)
-		io_pgtable_tlb_sync(&data->iop);
-
-	return unmapped;
+	return __arm_lpae_unmap(data, iova, size, lvl, ptep);
 }
 
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 33edfa794ae9..84bda3a4dafc 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -24,6 +24,9 @@
 #include <linux/bitops.h>
 #include <linux/cpu.h>
 
+/* The anchor node sits above the top of the usable address space */
+#define IOVA_ANCHOR	~0UL
+
 static bool iova_rcache_insert(struct iova_domain *iovad,
 			       unsigned long pfn,
 			       unsigned long size);
@@ -37,7 +40,7 @@ static void fq_flush_timeout(unsigned long data);
 
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long granule,
-	unsigned long start_pfn, unsigned long pfn_32bit)
+	unsigned long start_pfn)
 {
 	/*
 	 * IOVA granularity will normally be equal to the smallest
@@ -48,12 +51,16 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
-	iovad->cached32_node = NULL;
+	iovad->cached_node = &iovad->anchor.node;
+	iovad->cached32_node = &iovad->anchor.node;
 	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
-	iovad->dma_32bit_pfn = pfn_32bit + 1;
+	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
 	iovad->flush_cb = NULL;
 	iovad->fq = NULL;
+	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
+	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
+	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
 	init_iova_rcaches(iovad);
 }
 EXPORT_SYMBOL_GPL(init_iova_domain);
@@ -108,50 +115,36 @@ int init_iova_flush_queue(struct iova_domain *iovad,
 EXPORT_SYMBOL_GPL(init_iova_flush_queue);
 
 static struct rb_node *
-__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
 {
-	if ((*limit_pfn > iovad->dma_32bit_pfn) ||
-		(iovad->cached32_node == NULL))
-		return rb_last(&iovad->rbroot);
-	else {
-		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
-		struct iova *curr_iova =
-			rb_entry(iovad->cached32_node, struct iova, node);
-		*limit_pfn = curr_iova->pfn_lo;
-		return prev_node;
-	}
+	if (limit_pfn <= iovad->dma_32bit_pfn)
+		return iovad->cached32_node;
+
+	return iovad->cached_node;
 }
 
 static void
-__cached_rbnode_insert_update(struct iova_domain *iovad,
-	unsigned long limit_pfn, struct iova *new)
+__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
 {
-	if (limit_pfn != iovad->dma_32bit_pfn)
-		return;
-	iovad->cached32_node = &new->node;
+	if (new->pfn_hi < iovad->dma_32bit_pfn)
+		iovad->cached32_node = &new->node;
+	else
+		iovad->cached_node = &new->node;
 }
 
 static void
 __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 {
 	struct iova *cached_iova;
-	struct rb_node *curr;
 
-	if (!iovad->cached32_node)
-		return;
-	curr = iovad->cached32_node;
-	cached_iova = rb_entry(curr, struct iova, node);
+	cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
+	if (free->pfn_hi < iovad->dma_32bit_pfn &&
+	    free->pfn_lo >= cached_iova->pfn_lo)
+		iovad->cached32_node = rb_next(&free->node);
 
-	if (free->pfn_lo >= cached_iova->pfn_lo) {
-		struct rb_node *node = rb_next(&free->node);
-		struct iova *iova = rb_entry(node, struct iova, node);
-
-		/* only cache if it's below 32bit pfn */
-		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
-			iovad->cached32_node = node;
-		else
-			iovad->cached32_node = NULL;
-	}
+	cached_iova = rb_entry(iovad->cached_node, struct iova, node);
+	if (free->pfn_lo >= cached_iova->pfn_lo)
+		iovad->cached_node = rb_next(&free->node);
 }
 
 /* Insert the iova into domain rbtree by holding writer lock */
@@ -182,63 +175,43 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova,
 	rb_insert_color(&iova->node, root);
 }
 
-/*
- * Computes the padding size required, to make the start address
- * naturally aligned on the power-of-two order of its size
- */
-static unsigned int
-iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
-{
-	return (limit_pfn - size) & (__roundup_pow_of_two(size) - 1);
-}
-
 static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		unsigned long size, unsigned long limit_pfn,
 			struct iova *new, bool size_aligned)
 {
-	struct rb_node *prev, *curr = NULL;
+	struct rb_node *curr, *prev;
+	struct iova *curr_iova;
 	unsigned long flags;
-	unsigned long saved_pfn;
-	unsigned int pad_size = 0;
+	unsigned long new_pfn;
+	unsigned long align_mask = ~0UL;
+
+	if (size_aligned)
+		align_mask <<= fls_long(size - 1);
 
 	/* Walk the tree backwards */
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	saved_pfn = limit_pfn;
-	curr = __get_cached_rbnode(iovad, &limit_pfn);
-	prev = curr;
-	while (curr) {
-		struct iova *curr_iova = rb_entry(curr, struct iova, node);
-
-		if (limit_pfn <= curr_iova->pfn_lo) {
-			goto move_left;
-		} else if (limit_pfn > curr_iova->pfn_hi) {
-			if (size_aligned)
-				pad_size = iova_get_pad_size(size, limit_pfn);
-			if ((curr_iova->pfn_hi + size + pad_size) < limit_pfn)
-				break;	/* found a free slot */
-		}
-		limit_pfn = curr_iova->pfn_lo;
-move_left:
+	curr = __get_cached_rbnode(iovad, limit_pfn);
+	curr_iova = rb_entry(curr, struct iova, node);
+	do {
+		limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
+		new_pfn = (limit_pfn - size) & align_mask;
 		prev = curr;
 		curr = rb_prev(curr);
-	}
+		curr_iova = rb_entry(curr, struct iova, node);
+	} while (curr && new_pfn <= curr_iova->pfn_hi);
 
-	if (!curr) {
-		if (size_aligned)
-			pad_size = iova_get_pad_size(size, limit_pfn);
-		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
-			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-			return -ENOMEM;
-		}
+	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+		return -ENOMEM;
 	}
 
 	/* pfn_lo will point to size aligned address if size_aligned is set */
-	new->pfn_lo = limit_pfn - (size + pad_size);
+	new->pfn_lo = new_pfn;
 	new->pfn_hi = new->pfn_lo + size - 1;
 
 	/* If we have 'prev', it's a valid place to start the insertion. */
 	iova_insert_rbtree(&iovad->rbroot, new, prev);
-	__cached_rbnode_insert_update(iovad, saved_pfn, new);
+	__cached_rbnode_insert_update(iovad, new);
 
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 
@@ -258,7 +231,8 @@ EXPORT_SYMBOL(alloc_iova_mem);
 
 void free_iova_mem(struct iova *iova)
 {
-	kmem_cache_free(iova_cache, iova);
+	if (iova->pfn_lo != IOVA_ANCHOR)
+		kmem_cache_free(iova_cache, iova);
 }
 EXPORT_SYMBOL(free_iova_mem);
 
@@ -342,15 +316,12 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn)
 	while (node) {
 		struct iova *iova = rb_entry(node, struct iova, node);
 
-		/* If pfn falls within iova's range, return iova */
-		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
-			return iova;
-		}
-
 		if (pfn < iova->pfn_lo)
 			node = node->rb_left;
-		else if (pfn > iova->pfn_lo)
+		else if (pfn > iova->pfn_hi)
 			node = node->rb_right;
+		else
+			return iova;	/* pfn falls within iova's range */
 	}
 
 	return NULL;
@@ -424,18 +395,19 @@ EXPORT_SYMBOL_GPL(free_iova);
  * @iovad: - iova domain in question
  * @size: - size of page frames to allocate
  * @limit_pfn: - max limit address
+ * @flush_rcache: - set to flush rcache on regular allocation failure
  * This function tries to satisfy an iova allocation from the rcache,
- * and falls back to regular allocation on failure.
+ * and falls back to regular allocation on failure. If regular allocation
+ * fails too and the flush_rcache flag is set then the rcache will be flushed.
 */
 unsigned long
 alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
-		unsigned long limit_pfn)
+		unsigned long limit_pfn, bool flush_rcache)
 {
-	bool flushed_rcache = false;
 	unsigned long iova_pfn;
 	struct iova *new_iova;
 
-	iova_pfn = iova_rcache_get(iovad, size, limit_pfn);
+	iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
 	if (iova_pfn)
 		return iova_pfn;
 
@@ -444,11 +416,11 @@ retry:
 	if (!new_iova) {
 		unsigned int cpu;
 
-		if (flushed_rcache)
+		if (!flush_rcache)
 			return 0;
 
 		/* Try replenishing IOVAs by flushing rcache. */
-		flushed_rcache = true;
+		flush_rcache = false;
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
 		goto retry;
@@ -612,21 +584,12 @@ EXPORT_SYMBOL_GPL(queue_iova);
  */
 void put_iova_domain(struct iova_domain *iovad)
 {
-	struct rb_node *node;
-	unsigned long flags;
+	struct iova *iova, *tmp;
 
 	free_iova_flush_queue(iovad);
 	free_iova_rcaches(iovad);
-	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	node = rb_first(&iovad->rbroot);
-	while (node) {
-		struct iova *iova = rb_entry(node, struct iova, node);
-
-		rb_erase(node, &iovad->rbroot);
+	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
 		free_iova_mem(iova);
-		node = rb_first(&iovad->rbroot);
-	}
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 }
 EXPORT_SYMBOL_GPL(put_iova_domain);
 
@@ -695,6 +658,10 @@ reserve_iova(struct iova_domain *iovad,
 	struct iova *iova;
 	unsigned int overlap = 0;
 
+	/* Don't allow nonsensical pfns */
+	if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
+		return NULL;
+
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
@@ -738,6 +705,9 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 		struct iova *iova = rb_entry(node, struct iova, node);
 		struct iova *new_iova;
 
+		if (iova->pfn_lo == IOVA_ANCHOR)
+			continue;
+
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
 		if (!new_iova)
 			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
@@ -855,12 +825,21 @@ static bool iova_magazine_empty(struct iova_magazine *mag)
 static unsigned long iova_magazine_pop(struct iova_magazine *mag,
 				       unsigned long limit_pfn)
 {
+	int i;
+	unsigned long pfn;
+
 	BUG_ON(iova_magazine_empty(mag));
 
-	if (mag->pfns[mag->size - 1] >= limit_pfn)
-		return 0;
+	/* Only fall back to the rbtree if we have no suitable pfns at all */
+	for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
+		if (i == 0)
+			return 0;
 
-	return mag->pfns[--mag->size];
+	/* Swap it to pop it */
+	pfn = mag->pfns[i];
+	mag->pfns[i] = mag->pfns[--mag->size];
+
+	return pfn;
 }
 
 static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
@@ -1011,27 +990,7 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
 		return 0;
 
-	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn);
-}
-
-/*
- * Free a cpu's rcache.
- */
-static void free_cpu_iova_rcache(unsigned int cpu, struct iova_domain *iovad,
-				 struct iova_rcache *rcache)
-{
-	struct iova_cpu_rcache *cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
-	unsigned long flags;
-
-	spin_lock_irqsave(&cpu_rcache->lock, flags);
-
-	iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
-	iova_magazine_free(cpu_rcache->loaded);
-
-	iova_magazine_free_pfns(cpu_rcache->prev, iovad);
-	iova_magazine_free(cpu_rcache->prev);
-
-	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
 }
 
 /*
@@ -1040,21 +999,20 @@ static void free_cpu_iova_rcache(unsigned int cpu, struct iova_domain *iovad,
 static void free_iova_rcaches(struct iova_domain *iovad)
 {
 	struct iova_rcache *rcache;
-	unsigned long flags;
+	struct iova_cpu_rcache *cpu_rcache;
 	unsigned int cpu;
 	int i, j;
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
-		for_each_possible_cpu(cpu)
-			free_cpu_iova_rcache(cpu, iovad, rcache);
-		spin_lock_irqsave(&rcache->lock, flags);
-		free_percpu(rcache->cpu_rcaches);
-		for (j = 0; j < rcache->depot_size; ++j) {
-			iova_magazine_free_pfns(rcache->depot[j], iovad);
-			iova_magazine_free(rcache->depot[j]);
+		for_each_possible_cpu(cpu) {
+			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+			iova_magazine_free(cpu_rcache->loaded);
+			iova_magazine_free(cpu_rcache->prev);
 		}
-		spin_unlock_irqrestore(&rcache->lock, flags);
+		free_percpu(rcache->cpu_rcaches);
+		for (j = 0; j < rcache->depot_size; ++j)
+			iova_magazine_free(rcache->depot[j]);
 	}
 }
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 195d6e93ac71..af8140054273 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -619,6 +619,14 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 	return domain->iop->unmap(domain->iop, iova, size);
 }
 
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (domain->mmu)
+		ipmmu_tlb_flush_all(domain);
+}
+
 static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
 				      dma_addr_t iova)
 {
@@ -876,6 +884,8 @@ static const struct iommu_ops ipmmu_ops = {
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
 	.unmap = ipmmu_unmap,
+	.flush_iotlb_all = ipmmu_iotlb_sync,
+	.iotlb_sync = ipmmu_iotlb_sync,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = ipmmu_iova_to_phys,
 	.add_device = ipmmu_add_device_dma,
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 16d33ac19db0..f227d73e7bf6 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -392,6 +392,11 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	return unmapsz;
 }
 
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
@@ -491,6 +496,8 @@ static struct iommu_ops mtk_iommu_ops = {
 	.map		= mtk_iommu_map,
 	.unmap		= mtk_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = mtk_iommu_iotlb_sync,
+	.iotlb_sync	= mtk_iommu_iotlb_sync,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
 	.remove_device	= mtk_iommu_remove_device,
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index bd67e1b2c64e..e135ab830ebf 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -2,6 +2,7 @@
  * omap iommu: tlb and pagetable primitives
  *
  * Copyright (C) 2008-2010 Nokia Corporation
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  *
  * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>,
  *		Paul Mundt and Toshihiro Kobayashi
@@ -71,13 +72,23 @@ static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
  **/
 void omap_iommu_save_ctx(struct device *dev)
 {
-	struct omap_iommu *obj = dev_to_omap_iommu(dev);
-	u32 *p = obj->ctx;
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu *obj;
+	u32 *p;
 	int i;
 
-	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
-		p[i] = iommu_read_reg(obj, i * sizeof(u32));
-		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+			p[i] = iommu_read_reg(obj, i * sizeof(u32));
+			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
+				p[i]);
+		}
+		arch_data++;
 	}
 }
 EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
@@ -88,13 +99,23 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
  **/
 void omap_iommu_restore_ctx(struct device *dev)
 {
-	struct omap_iommu *obj = dev_to_omap_iommu(dev);
-	u32 *p = obj->ctx;
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu *obj;
+	u32 *p;
 	int i;
 
-	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
-		iommu_write_reg(obj, p[i], i * sizeof(u32));
-		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+			iommu_write_reg(obj, p[i], i * sizeof(u32));
+			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
+				p[i]);
+		}
+		arch_data++;
 	}
 }
 EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx);
@@ -805,7 +826,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	struct iommu_domain *domain = obj->domain;
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 
-	if (!omap_domain->iommu_dev)
+	if (!omap_domain->dev)
 		return IRQ_NONE;
 
 	errs = iommu_report_fault(obj, &da);
@@ -893,6 +914,24 @@ static void omap_iommu_detach(struct omap_iommu *obj)
 	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
 }
 
+static bool omap_iommu_can_register(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+
+	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
+		return true;
+
+	/*
+	 * restrict IOMMU core registration only for processor-port MDMA MMUs
+	 * on DRA7 DSPs
+	 */
+	if ((!strcmp(dev_name(&pdev->dev), "40d01000.mmu")) ||
+	    (!strcmp(dev_name(&pdev->dev), "41501000.mmu")))
+		return true;
+
+	return false;
+}
+
 static int omap_iommu_dra7_get_dsp_system_cfg(struct platform_device *pdev,
 					      struct omap_iommu *obj)
 {
@@ -984,19 +1023,22 @@ 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);
+	if (omap_iommu_can_register(pdev)) {
+		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;
+		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);
+		iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);
 
-	err = iommu_device_register(&obj->iommu);
-	if (err)
-		goto out_sysfs;
+		err = iommu_device_register(&obj->iommu);
+		if (err)
+			goto out_sysfs;
+	}
 
 	pm_runtime_irq_safe(obj->dev);
 	pm_runtime_enable(obj->dev);
@@ -1018,11 +1060,13 @@ 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;
+	if (obj->group) {
+		iommu_group_put(obj->group);
+		obj->group = NULL;
 
-	iommu_device_sysfs_remove(&obj->iommu);
-	iommu_device_unregister(&obj->iommu);
+		iommu_device_sysfs_remove(&obj->iommu);
+		iommu_device_unregister(&obj->iommu);
+	}
 
 	omap_iommu_debugfs_remove(obj);
 
@@ -1068,11 +1112,13 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 			  phys_addr_t pa, size_t bytes, int prot)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
-	struct device *dev = oiommu->dev;
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
 	struct iotlb_entry e;
 	int omap_pgsz;
-	u32 ret;
+	u32 ret = -EINVAL;
+	int i;
 
 	omap_pgsz = bytes_to_iopgsz(bytes);
 	if (omap_pgsz < 0) {
@@ -1084,9 +1130,24 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 
 	iotlb_init_entry(&e, da, pa, omap_pgsz);
 
-	ret = omap_iopgtable_store_entry(oiommu, &e);
-	if (ret)
-		dev_err(dev, "omap_iopgtable_store_entry failed: %d\n", ret);
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		ret = omap_iopgtable_store_entry(oiommu, &e);
+		if (ret) {
+			dev_err(dev, "omap_iopgtable_store_entry failed: %d\n",
+				ret);
+			break;
+		}
+	}
+
+	if (ret) {
+		while (i--) {
+			iommu--;
+			oiommu = iommu->iommu_dev;
+			iopgtable_clear_entry(oiommu, da);
+		}
+	}
 
 	return ret;
 }
@@ -1095,12 +1156,90 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
 			       size_t size)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
-	struct device *dev = oiommu->dev;
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	bool error = false;
+	size_t bytes = 0;
+	int i;
 
 	dev_dbg(dev, "unmapping da 0x%lx size %u\n", da, size);
 
-	return iopgtable_clear_entry(oiommu, da);
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		bytes = iopgtable_clear_entry(oiommu, da);
+		if (!bytes)
+			error = true;
+	}
+
+	/*
+	 * simplify return - we are only checking if any of the iommus
+	 * reported an error, but not if all of them are unmapping the
+	 * same number of entries. This should not occur due to the
+	 * mirror programming.
+	 */
+	return error ? 0 : bytes;
+}
+
+static int omap_iommu_count(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	int count = 0;
+
+	while (arch_data->iommu_dev) {
+		count++;
+		arch_data++;
+	}
+
+	return count;
+}
+
+/* caller should call cleanup if this function fails */
+static int omap_iommu_attach_init(struct device *dev,
+				  struct omap_iommu_domain *odomain)
+{
+	struct omap_iommu_device *iommu;
+	int i;
+
+	odomain->num_iommus = omap_iommu_count(dev);
+	if (!odomain->num_iommus)
+		return -EINVAL;
+
+	odomain->iommus = kcalloc(odomain->num_iommus, sizeof(*iommu),
+				  GFP_ATOMIC);
+	if (!odomain->iommus)
+		return -ENOMEM;
+
+	iommu = odomain->iommus;
+	for (i = 0; i < odomain->num_iommus; i++, iommu++) {
+		iommu->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_ATOMIC);
+		if (!iommu->pgtable)
+			return -ENOMEM;
+
+		/*
+		 * should never fail, but please keep this around to ensure
+		 * we keep the hardware happy
+		 */
+		if (WARN_ON(!IS_ALIGNED((long)iommu->pgtable,
+					IOPGD_TABLE_SIZE)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void omap_iommu_detach_fini(struct omap_iommu_domain *odomain)
+{
+	int i;
+	struct omap_iommu_device *iommu = odomain->iommus;
+
+	for (i = 0; iommu && i < odomain->num_iommus; i++, iommu++)
+		kfree(iommu->pgtable);
+
+	kfree(odomain->iommus);
+	odomain->num_iommus = 0;
+	odomain->iommus = NULL;
 }
 
 static int
@@ -1108,8 +1247,10 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu_device *iommu;
 	struct omap_iommu *oiommu;
 	int ret = 0;
+	int i;
 
 	if (!arch_data || !arch_data->iommu_dev) {
 		dev_err(dev, "device doesn't have an associated iommu\n");
@@ -1118,26 +1259,49 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	spin_lock(&omap_domain->lock);
 
-	/* only a single device is supported per domain for now */
-	if (omap_domain->iommu_dev) {
+	/* only a single client device can be attached to a domain */
+	if (omap_domain->dev) {
 		dev_err(dev, "iommu domain is already attached\n");
 		ret = -EBUSY;
 		goto out;
 	}
 
-	oiommu = arch_data->iommu_dev;
-
-	/* get a handle to and enable the omap iommu */
-	ret = omap_iommu_attach(oiommu, omap_domain->pgtable);
+	ret = omap_iommu_attach_init(dev, omap_domain);
 	if (ret) {
-		dev_err(dev, "can't get omap iommu: %d\n", ret);
-		goto out;
+		dev_err(dev, "failed to allocate required iommu data %d\n",
+			ret);
+		goto init_fail;
 	}
 
-	omap_domain->iommu_dev = oiommu;
-	omap_domain->dev = dev;
-	oiommu->domain = domain;
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++, arch_data++) {
+		/* configure and enable the omap iommu */
+		oiommu = arch_data->iommu_dev;
+		ret = omap_iommu_attach(oiommu, iommu->pgtable);
+		if (ret) {
+			dev_err(dev, "can't get omap iommu: %d\n", ret);
+			goto attach_fail;
+		}
 
+		oiommu->domain = domain;
+		iommu->iommu_dev = oiommu;
+	}
+
+	omap_domain->dev = dev;
+
+	goto out;
+
+attach_fail:
+	while (i--) {
+		iommu--;
+		arch_data--;
+		oiommu = iommu->iommu_dev;
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
+init_fail:
+	omap_iommu_detach_fini(omap_domain);
 out:
 	spin_unlock(&omap_domain->lock);
 	return ret;
@@ -1146,21 +1310,40 @@ out:
 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;
+	struct omap_iommu_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu;
+	int i;
 
-	/* only a single device is supported per domain for now */
-	if (omap_domain->iommu_dev != oiommu) {
-		dev_err(dev, "invalid iommu device\n");
+	if (!omap_domain->dev) {
+		dev_err(dev, "domain has no attached device\n");
 		return;
 	}
 
-	iopgtable_clear_entry_all(oiommu);
+	/* only a single device is supported per domain for now */
+	if (omap_domain->dev != dev) {
+		dev_err(dev, "invalid attached device\n");
+		return;
+	}
 
-	omap_iommu_detach(oiommu);
+	/*
+	 * cleanup in the reverse order of attachment - this addresses
+	 * any h/w dependencies between multiple instances, if any
+	 */
+	iommu += (omap_domain->num_iommus - 1);
+	arch_data += (omap_domain->num_iommus - 1);
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu--, arch_data--) {
+		oiommu = iommu->iommu_dev;
+		iopgtable_clear_entry_all(oiommu);
+
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
+
+	omap_iommu_detach_fini(omap_domain);
 
-	omap_domain->iommu_dev = NULL;
 	omap_domain->dev = NULL;
-	oiommu->domain = NULL;
 }
 
 static void omap_iommu_detach_dev(struct iommu_domain *domain,
@@ -1182,18 +1365,7 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 
 	omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL);
 	if (!omap_domain)
-		goto out;
-
-	omap_domain->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_KERNEL);
-	if (!omap_domain->pgtable)
-		goto fail_nomem;
-
-	/*
-	 * should never fail, but please keep this around to ensure
-	 * we keep the hardware happy
-	 */
-	if (WARN_ON(!IS_ALIGNED((long)omap_domain->pgtable, IOPGD_TABLE_SIZE)))
-		goto fail_align;
+		return NULL;
 
 	spin_lock_init(&omap_domain->lock);
 
@@ -1202,13 +1374,6 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 	omap_domain->domain.geometry.force_aperture = true;
 
 	return &omap_domain->domain;
-
-fail_align:
-	kfree(omap_domain->pgtable);
-fail_nomem:
-	kfree(omap_domain);
-out:
-	return NULL;
 }
 
 static void omap_iommu_domain_free(struct iommu_domain *domain)
@@ -1219,10 +1384,9 @@ static void omap_iommu_domain_free(struct iommu_domain *domain)
 	 * An iommu device is still attached
 	 * (currently, only one device can be attached) ?
 	 */
-	if (omap_domain->iommu_dev)
+	if (omap_domain->dev)
 		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);
 
-	kfree(omap_domain->pgtable);
 	kfree(omap_domain);
 }
 
@@ -1230,11 +1394,16 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t da)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
+	struct omap_iommu_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu = iommu->iommu_dev;
 	struct device *dev = oiommu->dev;
 	u32 *pgd, *pte;
 	phys_addr_t ret = 0;
 
+	/*
+	 * all the iommus within the domain will have identical programming,
+	 * so perform the lookup using just the first iommu
+	 */
 	iopgtable_lookup_entry(oiommu, da, &pgd, &pte);
 
 	if (pte) {
@@ -1260,11 +1429,12 @@ 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_arch_data *arch_data, *tmp;
 	struct omap_iommu *oiommu;
 	struct iommu_group *group;
 	struct device_node *np;
 	struct platform_device *pdev;
+	int num_iommus, i;
 	int ret;
 
 	/*
@@ -1276,36 +1446,57 @@ static int omap_iommu_add_device(struct device *dev)
 	if (!dev->of_node)
 		return 0;
 
-	np = of_parse_phandle(dev->of_node, "iommus", 0);
-	if (!np)
+	/*
+	 * retrieve the count of IOMMU nodes using phandle size as element size
+	 * since #iommu-cells = 0 for OMAP
+	 */
+	num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus",
+						     sizeof(phandle));
+	if (num_iommus < 0)
 		return 0;
 
-	pdev = of_find_device_by_node(np);
-	if (WARN_ON(!pdev)) {
-		of_node_put(np);
-		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);
+	arch_data = kzalloc((num_iommus + 1) * sizeof(*arch_data), GFP_KERNEL);
+	if (!arch_data)
 		return -ENOMEM;
+
+	for (i = 0, tmp = arch_data; i < num_iommus; i++, tmp++) {
+		np = of_parse_phandle(dev->of_node, "iommus", i);
+		if (!np) {
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		pdev = of_find_device_by_node(np);
+		if (WARN_ON(!pdev)) {
+			of_node_put(np);
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		oiommu = platform_get_drvdata(pdev);
+		if (!oiommu) {
+			of_node_put(np);
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		tmp->iommu_dev = oiommu;
+
+		of_node_put(np);
 	}
 
+	/*
+	 * use the first IOMMU alone for the sysfs device linking.
+	 * TODO: Evaluate if a single iommu_group needs to be
+	 * maintained for both IOMMUs
+	 */
+	oiommu = arch_data->iommu_dev;
 	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;
 
 	/*
@@ -1321,8 +1512,6 @@ static int omap_iommu_add_device(struct device *dev)
 	}
 	iommu_group_put(group);
 
-	of_node_put(np);
-
 	return 0;
 }
 
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index a675af29a6ec..1703159ef5af 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -28,18 +28,27 @@ struct iotlb_entry {
 	u32 endian, elsz, mixed;
 };
 
+/**
+ * struct omap_iommu_device - omap iommu device data
+ * @pgtable:	page table used by an omap iommu attached to a domain
+ * @iommu_dev:	pointer to store an omap iommu instance attached to a domain
+ */
+struct omap_iommu_device {
+	u32 *pgtable;
+	struct omap_iommu *iommu_dev;
+};
+
 /**
  * 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.
+ * @num_iommus: number of iommus in this domain
+ * @iommus:	omap iommu device data for all iommus in this domain
  * @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;
+	u32 num_iommus;
+	struct omap_iommu_device *iommus;
 	struct device *dev;
 	spinlock_t lock;
 	struct iommu_domain domain;
@@ -97,17 +106,6 @@ struct iotlb_lock {
 	short vict;
 };
 
-/**
- * dev_to_omap_iommu() - retrieves an omap iommu object from a user device
- * @dev: iommu client device
- */
-static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
-{
-	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
-
-	return arch_data->iommu_dev;
-}
-
 /*
  * MMU Register offsets
  */
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c8a587d034b0..4a2c4378b3db 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -443,6 +443,19 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
+						  struct io_pgtable, ops);
+	if (!qcom_domain->pgtbl_ops)
+		return;
+
+	pm_runtime_get_sync(qcom_domain->iommu->dev);
+	qcom_iommu_tlb_sync(pgtable->cookie);
+	pm_runtime_put_sync(qcom_domain->iommu->dev);
+}
+
 static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -570,6 +583,8 @@ static const struct iommu_ops qcom_iommu_ops = {
 	.map		= qcom_iommu_map,
 	.unmap		= qcom_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = qcom_iommu_iotlb_sync,
+	.iotlb_sync	= qcom_iommu_iotlb_sync,
 	.iova_to_phys	= qcom_iommu_iova_to_phys,
 	.add_device	= qcom_iommu_add_device,
 	.remove_device	= qcom_iommu_remove_device,
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index 329727e00e97..c824329f7012 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -39,8 +39,7 @@ void scif_rma_ep_init(struct scif_endpt *ep)
 	struct scif_endpt_rma_info *rma = &ep->rma_info;
 
 	mutex_init(&rma->rma_lock);
-	init_iova_domain(&rma->iovad, PAGE_SIZE, SCIF_IOVA_START_PFN,
-			 SCIF_DMA_64BIT_PFN);
+	init_iova_domain(&rma->iovad, PAGE_SIZE, SCIF_IOVA_START_PFN);
 	spin_lock_init(&rma->tc_lock);
 	mutex_init(&rma->mmn_lock);
 	INIT_LIST_HEAD(&rma->reg_list);
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e8ffba1052d3..e2433bc50210 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -112,6 +112,7 @@ static inline bool dmar_rcu_check(void)
 
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
+extern void dmar_register_bus_notifier(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
 				struct dmar_dev_scope **devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
diff --git a/include/linux/iova.h b/include/linux/iova.h
index d179b9bf7814..928442dda565 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -70,10 +70,12 @@ struct iova_fq {
 struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
-	struct rb_node	*cached32_node; /* Save last alloced node */
+	struct rb_node	*cached_node;	/* Save last alloced node */
+	struct rb_node	*cached32_node; /* Save last 32-bit alloced node */
 	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
+	struct iova	anchor;		/* rbtree lookup anchor */
 	struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE];	/* IOVA range caches */
 
 	iova_flush_cb	flush_cb;	/* Call-Back function to flush IOMMU
@@ -148,12 +150,12 @@ void queue_iova(struct iova_domain *iovad,
 		unsigned long pfn, unsigned long pages,
 		unsigned long data);
 unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
-			      unsigned long limit_pfn);
+			      unsigned long limit_pfn, bool flush_rcache);
 struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
 void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
-	unsigned long start_pfn, unsigned long pfn_32bit);
+	unsigned long start_pfn);
 int init_iova_flush_queue(struct iova_domain *iovad,
 			  iova_flush_cb flush_cb, iova_entry_dtor entry_dtor);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
@@ -210,7 +212,8 @@ static inline void queue_iova(struct iova_domain *iovad,
 
 static inline unsigned long alloc_iova_fast(struct iova_domain *iovad,
 					    unsigned long size,
-					    unsigned long limit_pfn)
+					    unsigned long limit_pfn,
+					    bool flush_rcache)
 {
 	return 0;
 }
@@ -229,8 +232,7 @@ static inline void copy_reserved_iova(struct iova_domain *from,
 
 static inline void init_iova_domain(struct iova_domain *iovad,
 				    unsigned long granule,
-				    unsigned long start_pfn,
-				    unsigned long pfn_32bit)
+				    unsigned long start_pfn)
 {
 }