diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 48882c126245b28aa0e4d8c44ad675551385e398..e43d48956dea239fe6816bdb23f0174754c623ee 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -33,6 +33,7 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
+#include <linux/dma-contiguous.h>
 #include <asm/irq_remapping.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -126,6 +127,11 @@ static int __init alloc_passthrough_domain(void);
  *
  ****************************************************************************/
 
+static struct protection_domain *to_pdomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct protection_domain, domain);
+}
+
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -1321,7 +1327,9 @@ static u64 *alloc_pte(struct protection_domain *domain,
  * This function checks if there is a PTE for a given dma address. If
  * there is one, it returns the pointer to it.
  */
-static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
+static u64 *fetch_pte(struct protection_domain *domain,
+		      unsigned long address,
+		      unsigned long *page_size)
 {
 	int level;
 	u64 *pte;
@@ -1329,8 +1337,9 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
 	if (address > PM_LEVEL_SIZE(domain->mode))
 		return NULL;
 
-	level   =  domain->mode - 1;
-	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	level	   =  domain->mode - 1;
+	pte	   = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	*page_size =  PTE_LEVEL_PAGE_SIZE(level);
 
 	while (level > 0) {
 
@@ -1339,19 +1348,9 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
 			return NULL;
 
 		/* Large PTE */
-		if (PM_PTE_LEVEL(*pte) == 0x07) {
-			unsigned long pte_mask, __pte;
-
-			/*
-			 * If we have a series of large PTEs, make
-			 * sure to return a pointer to the first one.
-			 */
-			pte_mask = PTE_PAGE_SIZE(*pte);
-			pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1);
-			__pte    = ((unsigned long)pte) & pte_mask;
-
-			return (u64 *)__pte;
-		}
+		if (PM_PTE_LEVEL(*pte) == 7 ||
+		    PM_PTE_LEVEL(*pte) == 0)
+			break;
 
 		/* No level skipping support yet */
 		if (PM_PTE_LEVEL(*pte) != level)
@@ -1360,8 +1359,21 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
 		level -= 1;
 
 		/* Walk to the next level */
-		pte = IOMMU_PTE_PAGE(*pte);
-		pte = &pte[PM_LEVEL_INDEX(level, address)];
+		pte	   = IOMMU_PTE_PAGE(*pte);
+		pte	   = &pte[PM_LEVEL_INDEX(level, address)];
+		*page_size = PTE_LEVEL_PAGE_SIZE(level);
+	}
+
+	if (PM_PTE_LEVEL(*pte) == 0x07) {
+		unsigned long pte_mask;
+
+		/*
+		 * If we have a series of large PTEs, make
+		 * sure to return a pointer to the first one.
+		 */
+		*page_size = pte_mask = PTE_PAGE_SIZE(*pte);
+		pte_mask   = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1);
+		pte        = (u64 *)(((unsigned long)pte) & pte_mask);
 	}
 
 	return pte;
@@ -1383,13 +1395,14 @@ static int iommu_map_page(struct protection_domain *dom,
 	u64 __pte, *pte;
 	int i, count;
 
+	BUG_ON(!IS_ALIGNED(bus_addr, page_size));
+	BUG_ON(!IS_ALIGNED(phys_addr, page_size));
+
 	if (!(prot & IOMMU_PROT_MASK))
 		return -EINVAL;
 
-	bus_addr  = PAGE_ALIGN(bus_addr);
-	phys_addr = PAGE_ALIGN(phys_addr);
-	count     = PAGE_SIZE_PTE_COUNT(page_size);
-	pte       = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
+	count = PAGE_SIZE_PTE_COUNT(page_size);
+	pte   = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
 
 	if (!pte)
 		return -ENOMEM;
@@ -1398,7 +1411,7 @@ static int iommu_map_page(struct protection_domain *dom,
 		if (IOMMU_PTE_PRESENT(pte[i]))
 			return -EBUSY;
 
-	if (page_size > PAGE_SIZE) {
+	if (count > 1) {
 		__pte = PAGE_SIZE_PTE(phys_addr, page_size);
 		__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC;
 	} else
@@ -1421,7 +1434,8 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 				      unsigned long bus_addr,
 				      unsigned long page_size)
 {
-	unsigned long long unmap_size, unmapped;
+	unsigned long long unmapped;
+	unsigned long unmap_size;
 	u64 *pte;
 
 	BUG_ON(!is_power_of_2(page_size));
@@ -1430,28 +1444,12 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 
 	while (unmapped < page_size) {
 
-		pte = fetch_pte(dom, bus_addr);
-
-		if (!pte) {
-			/*
-			 * No PTE for this address
-			 * move forward in 4kb steps
-			 */
-			unmap_size = PAGE_SIZE;
-		} else if (PM_PTE_LEVEL(*pte) == 0) {
-			/* 4kb PTE found for this address */
-			unmap_size = PAGE_SIZE;
-			*pte       = 0ULL;
-		} else {
-			int count, i;
-
-			/* Large PTE found which maps this address */
-			unmap_size = PTE_PAGE_SIZE(*pte);
-
-			/* Only unmap from the first pte in the page */
-			if ((unmap_size - 1) & bus_addr)
-				break;
-			count      = PAGE_SIZE_PTE_COUNT(unmap_size);
+		pte = fetch_pte(dom, bus_addr, &unmap_size);
+
+		if (pte) {
+			int i, count;
+
+			count = PAGE_SIZE_PTE_COUNT(unmap_size);
 			for (i = 0; i < count; i++)
 				pte[i] = 0ULL;
 		}
@@ -1599,7 +1597,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 {
 	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	struct amd_iommu *iommu;
-	unsigned long i, old_size;
+	unsigned long i, old_size, pte_pgsize;
 
 #ifdef CONFIG_IOMMU_STRESS
 	populate = false;
@@ -1672,12 +1670,13 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 	 */
 	for (i = dma_dom->aperture[index]->offset;
 	     i < dma_dom->aperture_size;
-	     i += PAGE_SIZE) {
-		u64 *pte = fetch_pte(&dma_dom->domain, i);
+	     i += pte_pgsize) {
+		u64 *pte = fetch_pte(&dma_dom->domain, i, &pte_pgsize);
 		if (!pte || !IOMMU_PTE_PRESENT(*pte))
 			continue;
 
-		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT, 1);
+		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT,
+					  pte_pgsize >> 12);
 	}
 
 	update_domain(&dma_dom->domain);
@@ -2422,16 +2421,6 @@ static int device_change_notifier(struct notifier_block *nb,
 	dev_data = get_dev_data(dev);
 
 	switch (action) {
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-
-		domain = domain_for_device(dev);
-
-		if (!domain)
-			goto out;
-		if (dev_data->passthrough)
-			break;
-		detach_device(dev);
-		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 
 		iommu_init_device(dev);
@@ -2467,7 +2456,7 @@ static int device_change_notifier(struct notifier_block *nb,
 		dev->archdata.dma_ops = &amd_iommu_dma_ops;
 
 		break;
-	case BUS_NOTIFY_DEL_DEVICE:
+	case BUS_NOTIFY_REMOVED_DEVICE:
 
 		iommu_uninit_device(dev);
 
@@ -2923,38 +2912,42 @@ static void *alloc_coherent(struct device *dev, size_t size,
 			    dma_addr_t *dma_addr, gfp_t flag,
 			    struct dma_attrs *attrs)
 {
-	unsigned long flags;
-	void *virt_addr;
-	struct protection_domain *domain;
-	phys_addr_t paddr;
 	u64 dma_mask = dev->coherent_dma_mask;
+	struct protection_domain *domain;
+	unsigned long flags;
+	struct page *page;
 
 	INC_STATS_COUNTER(cnt_alloc_coherent);
 
 	domain = get_domain(dev);
 	if (PTR_ERR(domain) == -EINVAL) {
-		virt_addr = (void *)__get_free_pages(flag, get_order(size));
-		*dma_addr = __pa(virt_addr);
-		return virt_addr;
+		page = alloc_pages(flag, get_order(size));
+		*dma_addr = page_to_phys(page);
+		return page_address(page);
 	} else if (IS_ERR(domain))
 		return NULL;
 
+	size	  = PAGE_ALIGN(size);
 	dma_mask  = dev->coherent_dma_mask;
 	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-	flag     |= __GFP_ZERO;
 
-	virt_addr = (void *)__get_free_pages(flag, get_order(size));
-	if (!virt_addr)
-		return NULL;
+	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
+	if (!page) {
+		if (!(flag & __GFP_WAIT))
+			return NULL;
 
-	paddr = virt_to_phys(virt_addr);
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+						 get_order(size));
+		if (!page)
+			return NULL;
+	}
 
 	if (!dma_mask)
 		dma_mask = *dev->dma_mask;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	*dma_addr = __map_single(dev, domain->priv, paddr,
+	*dma_addr = __map_single(dev, domain->priv, page_to_phys(page),
 				 size, DMA_BIDIRECTIONAL, true, dma_mask);
 
 	if (*dma_addr == DMA_ERROR_CODE) {
@@ -2966,11 +2959,12 @@ static void *alloc_coherent(struct device *dev, size_t size,
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
-	return virt_addr;
+	return page_address(page);
 
 out_free:
 
-	free_pages((unsigned long)virt_addr, get_order(size));
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
 
 	return NULL;
 }
@@ -2982,11 +2976,15 @@ static void free_coherent(struct device *dev, size_t size,
 			  void *virt_addr, dma_addr_t dma_addr,
 			  struct dma_attrs *attrs)
 {
-	unsigned long flags;
 	struct protection_domain *domain;
+	unsigned long flags;
+	struct page *page;
 
 	INC_STATS_COUNTER(cnt_free_coherent);
 
+	page = virt_to_page(virt_addr);
+	size = PAGE_ALIGN(size);
+
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		goto free_mem;
@@ -3000,7 +2998,8 @@ static void free_coherent(struct device *dev, size_t size,
 	spin_unlock_irqrestore(&domain->lock, flags);
 
 free_mem:
-	free_pages((unsigned long)virt_addr, get_order(size));
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
 }
 
 /*
@@ -3236,42 +3235,45 @@ static int __init alloc_passthrough_domain(void)
 
 	return 0;
 }
-static int amd_iommu_domain_init(struct iommu_domain *dom)
+
+static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
-	struct protection_domain *domain;
+	struct protection_domain *pdomain;
 
-	domain = protection_domain_alloc();
-	if (!domain)
-		goto out_free;
+	/* We only support unmanaged domains for now */
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
 
-	domain->mode    = PAGE_MODE_3_LEVEL;
-	domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!domain->pt_root)
+	pdomain = protection_domain_alloc();
+	if (!pdomain)
 		goto out_free;
 
-	domain->iommu_domain = dom;
-
-	dom->priv = domain;
+	pdomain->mode    = PAGE_MODE_3_LEVEL;
+	pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!pdomain->pt_root)
+		goto out_free;
 
-	dom->geometry.aperture_start = 0;
-	dom->geometry.aperture_end   = ~0ULL;
-	dom->geometry.force_aperture = true;
+	pdomain->domain.geometry.aperture_start = 0;
+	pdomain->domain.geometry.aperture_end   = ~0ULL;
+	pdomain->domain.geometry.force_aperture = true;
 
-	return 0;
+	return &pdomain->domain;
 
 out_free:
-	protection_domain_free(domain);
+	protection_domain_free(pdomain);
 
-	return -ENOMEM;
+	return NULL;
 }
 
-static void amd_iommu_domain_destroy(struct iommu_domain *dom)
+static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain;
 
-	if (!domain)
+	if (!dom)
 		return;
 
+	domain = to_pdomain(dom);
+
 	if (domain->dev_cnt > 0)
 		cleanup_domain(domain);
 
@@ -3284,8 +3286,6 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom)
 		free_gcr3_table(domain);
 
 	protection_domain_free(domain);
-
-	dom->priv = NULL;
 }
 
 static void amd_iommu_detach_device(struct iommu_domain *dom,
@@ -3313,7 +3313,7 @@ static void amd_iommu_detach_device(struct iommu_domain *dom,
 static int amd_iommu_attach_device(struct iommu_domain *dom,
 				   struct device *dev)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	struct iommu_dev_data *dev_data;
 	struct amd_iommu *iommu;
 	int ret;
@@ -3340,7 +3340,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 			 phys_addr_t paddr, size_t page_size, int iommu_prot)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	int prot = 0;
 	int ret;
 
@@ -3362,7 +3362,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 			   size_t page_size)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	size_t unmap_size;
 
 	if (domain->mode == PAGE_MODE_NONE)
@@ -3380,28 +3380,22 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 					  dma_addr_t iova)
 {
-	struct protection_domain *domain = dom->priv;
-	unsigned long offset_mask;
-	phys_addr_t paddr;
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long offset_mask, pte_pgsize;
 	u64 *pte, __pte;
 
 	if (domain->mode == PAGE_MODE_NONE)
 		return iova;
 
-	pte = fetch_pte(domain, iova);
+	pte = fetch_pte(domain, iova, &pte_pgsize);
 
 	if (!pte || !IOMMU_PTE_PRESENT(*pte))
 		return 0;
 
-	if (PM_PTE_LEVEL(*pte) == 0)
-		offset_mask = PAGE_SIZE - 1;
-	else
-		offset_mask = PTE_PAGE_SIZE(*pte) - 1;
-
-	__pte = *pte & PM_ADDR_MASK;
-	paddr = (__pte & ~offset_mask) | (iova & offset_mask);
+	offset_mask = pte_pgsize - 1;
+	__pte	    = *pte & PM_ADDR_MASK;
 
-	return paddr;
+	return (__pte & ~offset_mask) | (iova & offset_mask);
 }
 
 static bool amd_iommu_capable(enum iommu_cap cap)
@@ -3420,8 +3414,8 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 
 static const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
-	.domain_init = amd_iommu_domain_init,
-	.domain_destroy = amd_iommu_domain_destroy,
+	.domain_alloc = amd_iommu_domain_alloc,
+	.domain_free  = amd_iommu_domain_free,
 	.attach_dev = amd_iommu_attach_device,
 	.detach_dev = amd_iommu_detach_device,
 	.map = amd_iommu_map,
@@ -3483,7 +3477,7 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier);
 
 void amd_iommu_domain_direct_map(struct iommu_domain *dom)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 
 	spin_lock_irqsave(&domain->lock, flags);
@@ -3504,7 +3498,7 @@ EXPORT_SYMBOL(amd_iommu_domain_direct_map);
 
 int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 	int levels, ret;
 
@@ -3616,7 +3610,7 @@ static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
 int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
 			 u64 address)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 	int ret;
 
@@ -3638,7 +3632,7 @@ static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
 
 int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 	int ret;
 
@@ -3718,7 +3712,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid)
 int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 			      unsigned long cr3)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 	int ret;
 
@@ -3732,7 +3726,7 @@ EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
 
 int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
 {
-	struct protection_domain *domain = dom->priv;
+	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
 	int ret;
 
@@ -3765,17 +3759,17 @@ EXPORT_SYMBOL(amd_iommu_complete_ppr);
 
 struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev)
 {
-	struct protection_domain *domain;
+	struct protection_domain *pdomain;
 
-	domain = get_domain(&pdev->dev);
-	if (IS_ERR(domain))
+	pdomain = get_domain(&pdev->dev);
+	if (IS_ERR(pdomain))
 		return NULL;
 
 	/* Only return IOMMUv2 domains */
-	if (!(domain->flags & PD_IOMMUV2_MASK))
+	if (!(pdomain->flags & PD_IOMMUV2_MASK))
 		return NULL;
 
-	return domain->iommu_domain;
+	return &pdomain->domain;
 }
 EXPORT_SYMBOL(amd_iommu_get_v2_domain);
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index c4fffb710c5873f85105f60419aa6dc96c6e1a70..05030e523771a6ee3befbe890ed45b47a86f8f7f 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -282,6 +282,12 @@
 #define PTE_PAGE_SIZE(pte) \
 	(1ULL << (1 + ffz(((pte) | 0xfffULL))))
 
+/*
+ * Takes a page-table level and returns the default page-size for this level
+ */
+#define PTE_LEVEL_PAGE_SIZE(level)			\
+	(1ULL << (12 + (9 * (level))))
+
 #define IOMMU_PTE_P  (1ULL << 0)
 #define IOMMU_PTE_TV (1ULL << 1)
 #define IOMMU_PTE_U  (1ULL << 59)
@@ -400,6 +406,8 @@ struct iommu_domain;
 struct protection_domain {
 	struct list_head list;  /* for list of all protection domains */
 	struct list_head dev_list; /* List of all devices in this domain */
+	struct iommu_domain domain; /* generic domain handle used by
+				       iommu core code */
 	spinlock_t lock;	/* mostly used to lock the page table*/
 	struct mutex api_lock;	/* protect page tables in the iommu-api path */
 	u16 id;			/* the domain id written to the device table */
@@ -411,10 +419,7 @@ struct protection_domain {
 	bool updated;		/* complete domain flush required */
 	unsigned dev_cnt;	/* devices assigned to this domain */
 	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
-	void *priv;		/* private data */
-	struct iommu_domain *iommu_domain; /* Pointer to generic
-					      domain structure */
-
+	void *priv;             /* private data */
 };
 
 /*
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 6d5a5c44453bf5fcc29a3cad394929d463405b33..a1cbba9056fdba15b1334bd923714c65957fc20c 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -417,7 +417,7 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	dev_state      = pasid_state->device_state;
 	run_inv_ctx_cb = !pasid_state->invalid;
 
-	if (run_inv_ctx_cb && pasid_state->device_state->inv_ctx_cb)
+	if (run_inv_ctx_cb && dev_state->inv_ctx_cb)
 		dev_state->inv_ctx_cb(dev_state->pdev, pasid_state->pasid);
 
 	unbind_pasid(pasid_state);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index a3adde6519f0a24b7150f8e69ceabed534ceaa38..9f7e1d34a32bc8ec75c6470260c66f839419f502 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -343,6 +343,7 @@ struct arm_smmu_domain {
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
+	struct iommu_domain		domain;
 };
 
 static struct iommu_ops arm_smmu_ops;
@@ -360,6 +361,11 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ 0, NULL},
 };
 
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
 static void parse_driver_options(struct arm_smmu_device *smmu)
 {
 	int i = 0;
@@ -645,7 +651,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	u32 fsr, far, fsynr, resume;
 	unsigned long iova;
 	struct iommu_domain *domain = dev;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *cb_base;
@@ -730,6 +736,20 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 	stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
 
+	if (smmu->version > ARM_SMMU_V1) {
+		/*
+		 * CBA2R.
+		 * *Must* be initialised before CBAR thanks to VMID16
+		 * architectural oversight affected some implementations.
+		 */
+#ifdef CONFIG_64BIT
+		reg = CBA2R_RW64_64BIT;
+#else
+		reg = CBA2R_RW64_32BIT;
+#endif
+		writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
+	}
+
 	/* CBAR */
 	reg = cfg->cbar;
 	if (smmu->version == ARM_SMMU_V1)
@@ -747,16 +767,6 @@ 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 > ARM_SMMU_V1) {
-		/* CBA2R */
-#ifdef CONFIG_64BIT
-		reg = CBA2R_RW64_64BIT;
-#else
-		reg = CBA2R_RW64_32BIT;
-#endif
-		writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
-	}
-
 	/* TTBRs */
 	if (stage1) {
 		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
@@ -836,7 +846,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	struct io_pgtable_ops *pgtbl_ops;
 	struct io_pgtable_cfg pgtbl_cfg;
 	enum io_pgtable_fmt fmt;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 
 	mutex_lock(&smmu_domain->init_mutex);
@@ -958,7 +968,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 
 static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	void __iomem *cb_base;
@@ -985,10 +995,12 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
 }
 
-static int arm_smmu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
 	/*
 	 * Allocate the domain and initialise some of its data structures.
 	 * We can't really do anything meaningful until we've added a
@@ -996,17 +1008,17 @@ static int arm_smmu_domain_init(struct iommu_domain *domain)
 	 */
 	smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
 	if (!smmu_domain)
-		return -ENOMEM;
+		return NULL;
 
 	mutex_init(&smmu_domain->init_mutex);
 	spin_lock_init(&smmu_domain->pgtbl_lock);
-	domain->priv = smmu_domain;
-	return 0;
+
+	return &smmu_domain->domain;
 }
 
-static void arm_smmu_domain_destroy(struct iommu_domain *domain)
+static void arm_smmu_domain_free(struct iommu_domain *domain)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
 	/*
 	 * Free the domain resources. We assume that all devices have
@@ -1143,7 +1155,7 @@ static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	int ret;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu;
 	struct arm_smmu_master_cfg *cfg;
 
@@ -1187,7 +1199,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_master_cfg *cfg;
 
 	cfg = find_smmu_master_cfg(dev);
@@ -1203,7 +1215,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 {
 	int ret;
 	unsigned long flags;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
 	if (!ops)
@@ -1220,7 +1232,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 {
 	size_t ret;
 	unsigned long flags;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
 	if (!ops)
@@ -1235,7 +1247,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 					      dma_addr_t iova)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
@@ -1281,7 +1293,7 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 {
 	phys_addr_t ret;
 	unsigned long flags;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
 	if (!ops)
@@ -1329,61 +1341,83 @@ static void __arm_smmu_release_pci_iommudata(void *data)
 	kfree(data);
 }
 
-static int arm_smmu_add_device(struct device *dev)
+static int arm_smmu_add_pci_device(struct pci_dev *pdev)
 {
-	struct arm_smmu_device *smmu;
-	struct arm_smmu_master_cfg *cfg;
+	int i, ret;
+	u16 sid;
 	struct iommu_group *group;
-	void (*releasefn)(void *) = NULL;
-	int ret;
-
-	smmu = find_smmu_for_device(dev);
-	if (!smmu)
-		return -ENODEV;
+	struct arm_smmu_master_cfg *cfg;
 
-	group = iommu_group_alloc();
-	if (IS_ERR(group)) {
-		dev_err(dev, "Failed to allocate IOMMU group\n");
+	group = iommu_group_get_for_dev(&pdev->dev);
+	if (IS_ERR(group))
 		return PTR_ERR(group);
-	}
-
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
 
+	cfg = iommu_group_get_iommudata(group);
+	if (!cfg) {
 		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
 		if (!cfg) {
 			ret = -ENOMEM;
 			goto out_put_group;
 		}
 
-		cfg->num_streamids = 1;
-		/*
-		 * Assume Stream ID == Requester ID for now.
-		 * We need a way to describe the ID mappings in FDT.
-		 */
-		pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid,
-				       &cfg->streamids[0]);
-		releasefn = __arm_smmu_release_pci_iommudata;
-	} else {
-		struct arm_smmu_master *master;
-
-		master = find_smmu_master(smmu, dev->of_node);
-		if (!master) {
-			ret = -ENODEV;
-			goto out_put_group;
-		}
+		iommu_group_set_iommudata(group, cfg,
+					  __arm_smmu_release_pci_iommudata);
+	}
 
-		cfg = &master->cfg;
+	if (cfg->num_streamids >= MAX_MASTER_STREAMIDS) {
+		ret = -ENOSPC;
+		goto out_put_group;
 	}
 
-	iommu_group_set_iommudata(group, cfg, releasefn);
-	ret = iommu_group_add_device(group, dev);
+	/*
+	 * Assume Stream ID == Requester ID for now.
+	 * We need a way to describe the ID mappings in FDT.
+	 */
+	pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid);
+	for (i = 0; i < cfg->num_streamids; ++i)
+		if (cfg->streamids[i] == sid)
+			break;
+
+	/* Avoid duplicate SIDs, as this can lead to SMR conflicts */
+	if (i == cfg->num_streamids)
+		cfg->streamids[cfg->num_streamids++] = sid;
 
+	return 0;
 out_put_group:
 	iommu_group_put(group);
 	return ret;
 }
 
+static int arm_smmu_add_platform_device(struct device *dev)
+{
+	struct iommu_group *group;
+	struct arm_smmu_master *master;
+	struct arm_smmu_device *smmu = find_smmu_for_device(dev);
+
+	if (!smmu)
+		return -ENODEV;
+
+	master = find_smmu_master(smmu, dev->of_node);
+	if (!master)
+		return -ENODEV;
+
+	/* No automatic group creation for platform devices */
+	group = iommu_group_alloc();
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	iommu_group_set_iommudata(group, &master->cfg, NULL);
+	return iommu_group_add_device(group, dev);
+}
+
+static int arm_smmu_add_device(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return arm_smmu_add_pci_device(to_pci_dev(dev));
+
+	return arm_smmu_add_platform_device(dev);
+}
+
 static void arm_smmu_remove_device(struct device *dev)
 {
 	iommu_group_remove_device(dev);
@@ -1392,7 +1426,7 @@ static void arm_smmu_remove_device(struct device *dev)
 static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr, void *data)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
 	switch (attr) {
 	case DOMAIN_ATTR_NESTING:
@@ -1407,7 +1441,7 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr, void *data)
 {
 	int ret = 0;
-	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
 	mutex_lock(&smmu_domain->init_mutex);
 
@@ -1435,8 +1469,8 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
-	.domain_init		= arm_smmu_domain_init,
-	.domain_destroy		= arm_smmu_domain_destroy,
+	.domain_alloc		= arm_smmu_domain_alloc,
+	.domain_free		= arm_smmu_domain_free,
 	.attach_dev		= arm_smmu_attach_dev,
 	.detach_dev		= arm_smmu_detach_dev,
 	.map			= arm_smmu_map,
@@ -1633,6 +1667,15 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
 	smmu->pa_size = size;
 
+	/*
+	 * What the page table walker can address actually depends on which
+	 * descriptor format is in use, but since a) we don't know that yet,
+	 * and b) it can vary per context bank, this will have to do...
+	 */
+	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(size)))
+		dev_warn(smmu->dev,
+			 "failed to set DMA mask for table walker\n");
+
 	if (smmu->version == ARM_SMMU_V1) {
 		smmu->va_size = smmu->ipa_size;
 		size = SZ_4K | SZ_2M | SZ_1G;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index dc14fec4ede123b0af6564f641d81dcfcb958b25..3e898504a7c45aee654857ab946d64380a1a1d0f 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -200,6 +200,7 @@ struct exynos_iommu_domain {
 	short *lv2entcnt; /* free lv2 entry counter for each section */
 	spinlock_t lock; /* lock for this structure */
 	spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
+	struct iommu_domain domain; /* generic domain data structure */
 };
 
 struct sysmmu_drvdata {
@@ -214,6 +215,11 @@ struct sysmmu_drvdata {
 	phys_addr_t pgtable;
 };
 
+static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct exynos_iommu_domain, domain);
+}
+
 static bool set_sysmmu_active(struct sysmmu_drvdata *data)
 {
 	/* return true if the System MMU was not active previously
@@ -696,58 +702,60 @@ static inline void pgtable_flush(void *vastart, void *vaend)
 				virt_to_phys(vaend));
 }
 
-static int exynos_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 {
-	struct exynos_iommu_domain *priv;
+	struct exynos_iommu_domain *exynos_domain;
 	int i;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	exynos_domain = kzalloc(sizeof(*exynos_domain), GFP_KERNEL);
+	if (!exynos_domain)
+		return NULL;
 
-	priv->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
-	if (!priv->pgtable)
+	exynos_domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
+	if (!exynos_domain->pgtable)
 		goto err_pgtable;
 
-	priv->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
-	if (!priv->lv2entcnt)
+	exynos_domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (!exynos_domain->lv2entcnt)
 		goto err_counter;
 
 	/* 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;
-		priv->pgtable[i + 2] = ZERO_LV2LINK;
-		priv->pgtable[i + 3] = ZERO_LV2LINK;
-		priv->pgtable[i + 4] = ZERO_LV2LINK;
-		priv->pgtable[i + 5] = ZERO_LV2LINK;
-		priv->pgtable[i + 6] = ZERO_LV2LINK;
-		priv->pgtable[i + 7] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 0] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 1] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 2] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 3] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 4] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 5] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 6] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 7] = ZERO_LV2LINK;
 	}
 
-	pgtable_flush(priv->pgtable, priv->pgtable + NUM_LV1ENTRIES);
+	pgtable_flush(exynos_domain->pgtable, exynos_domain->pgtable + NUM_LV1ENTRIES);
 
-	spin_lock_init(&priv->lock);
-	spin_lock_init(&priv->pgtablelock);
-	INIT_LIST_HEAD(&priv->clients);
+	spin_lock_init(&exynos_domain->lock);
+	spin_lock_init(&exynos_domain->pgtablelock);
+	INIT_LIST_HEAD(&exynos_domain->clients);
 
-	domain->geometry.aperture_start = 0;
-	domain->geometry.aperture_end   = ~0UL;
-	domain->geometry.force_aperture = true;
+	exynos_domain->domain.geometry.aperture_start = 0;
+	exynos_domain->domain.geometry.aperture_end   = ~0UL;
+	exynos_domain->domain.geometry.force_aperture = true;
 
-	domain->priv = priv;
-	return 0;
+	return &exynos_domain->domain;
 
 err_counter:
-	free_pages((unsigned long)priv->pgtable, 2);
+	free_pages((unsigned long)exynos_domain->pgtable, 2);
 err_pgtable:
-	kfree(priv);
-	return -ENOMEM;
+	kfree(exynos_domain);
+	return NULL;
 }
 
-static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
+static void exynos_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	struct exynos_iommu_owner *owner;
 	unsigned long flags;
 	int i;
@@ -773,15 +781,14 @@ static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
 
 	free_pages((unsigned long)priv->pgtable, 2);
 	free_pages((unsigned long)priv->lv2entcnt, 1);
-	kfree(domain->priv);
-	domain->priv = NULL;
+	kfree(priv);
 }
 
 static int exynos_iommu_attach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
 	unsigned long flags;
 	int ret;
@@ -812,7 +819,7 @@ static void exynos_iommu_detach_device(struct iommu_domain *domain,
 				    struct device *dev)
 {
 	struct exynos_iommu_owner *owner;
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
 	unsigned long flags;
 
@@ -988,7 +995,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
 static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
 			 phys_addr_t paddr, size_t size, int prot)
 {
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	sysmmu_pte_t *entry;
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
 	unsigned long flags;
@@ -1042,7 +1049,7 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv,
 static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 					unsigned long l_iova, size_t size)
 {
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
 	sysmmu_pte_t *ent;
 	size_t err_pgsize;
@@ -1119,7 +1126,7 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
-	struct exynos_iommu_domain *priv = domain->priv;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
 	sysmmu_pte_t *entry;
 	unsigned long flags;
 	phys_addr_t phys = 0;
@@ -1171,8 +1178,8 @@ static void exynos_iommu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops exynos_iommu_ops = {
-	.domain_init = exynos_iommu_domain_init,
-	.domain_destroy = exynos_iommu_domain_destroy,
+	.domain_alloc = exynos_iommu_domain_alloc,
+	.domain_free = exynos_iommu_domain_free,
 	.attach_dev = exynos_iommu_attach_device,
 	.detach_dev = exynos_iommu_detach_device,
 	.map = exynos_iommu_map,
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index ceebd287b6602e5dabd4230f4cd390a1765c9edf..1d452930c89090cd95a9a5808322782332d45a91 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -33,6 +33,11 @@ static struct kmem_cache *fsl_pamu_domain_cache;
 static struct kmem_cache *iommu_devinfo_cache;
 static DEFINE_SPINLOCK(device_domain_lock);
 
+static struct fsl_dma_domain *to_fsl_dma_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct fsl_dma_domain, iommu_domain);
+}
+
 static int __init iommu_init_mempool(void)
 {
 	fsl_pamu_domain_cache = kmem_cache_create("fsl_pamu_domain",
@@ -65,7 +70,7 @@ static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t i
 	struct dma_window *win_ptr = &dma_domain->win_arr[0];
 	struct iommu_domain_geometry *geom;
 
-	geom = &dma_domain->iommu_domain->geometry;
+	geom = &dma_domain->iommu_domain.geometry;
 
 	if (!win_cnt || !dma_domain->geom_size) {
 		pr_debug("Number of windows/geometry not configured for the domain\n");
@@ -123,7 +128,7 @@ static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
 {
 	int ret;
 	struct dma_window *wnd = &dma_domain->win_arr[0];
-	phys_addr_t wnd_addr = dma_domain->iommu_domain->geometry.aperture_start;
+	phys_addr_t wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
 	unsigned long flags;
 
 	spin_lock_irqsave(&iommu_lock, flags);
@@ -172,7 +177,7 @@ static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr
 	} else {
 		phys_addr_t wnd_addr;
 
-		wnd_addr = dma_domain->iommu_domain->geometry.aperture_start;
+		wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
 
 		ret = pamu_config_ppaace(liodn, wnd_addr,
 					 wnd->size,
@@ -384,7 +389,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
 static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
 					 dma_addr_t iova)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 
 	if (iova < domain->geometry.aperture_start ||
 	    iova > domain->geometry.aperture_end)
@@ -398,11 +403,9 @@ static bool fsl_pamu_capable(enum iommu_cap cap)
 	return cap == IOMMU_CAP_CACHE_COHERENCY;
 }
 
-static void fsl_pamu_domain_destroy(struct iommu_domain *domain)
+static void fsl_pamu_domain_free(struct iommu_domain *domain)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
-
-	domain->priv = NULL;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 
 	/* remove all the devices from the device list */
 	detach_device(NULL, dma_domain);
@@ -413,23 +416,24 @@ static void fsl_pamu_domain_destroy(struct iommu_domain *domain)
 	kmem_cache_free(fsl_pamu_domain_cache, dma_domain);
 }
 
-static int fsl_pamu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type)
 {
 	struct fsl_dma_domain *dma_domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
 	dma_domain = iommu_alloc_dma_domain();
 	if (!dma_domain) {
 		pr_debug("dma_domain allocation failed\n");
-		return -ENOMEM;
+		return NULL;
 	}
-	domain->priv = dma_domain;
-	dma_domain->iommu_domain = domain;
 	/* defaul geometry 64 GB i.e. maximum system address */
-	domain->geometry.aperture_start = 0;
-	domain->geometry.aperture_end = (1ULL << 36) - 1;
-	domain->geometry.force_aperture = true;
+	dma_domain->iommu_domain. geometry.aperture_start = 0;
+	dma_domain->iommu_domain.geometry.aperture_end = (1ULL << 36) - 1;
+	dma_domain->iommu_domain.geometry.force_aperture = true;
 
-	return 0;
+	return &dma_domain->iommu_domain;
 }
 
 /* Configure geometry settings for all LIODNs associated with domain */
@@ -499,7 +503,7 @@ static int disable_domain_win(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
 
 static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	unsigned long flags;
 	int ret;
 
@@ -530,7 +534,7 @@ static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr)
 static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 				  phys_addr_t paddr, u64 size, int prot)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	struct dma_window *wnd;
 	int pamu_prot = 0;
 	int ret;
@@ -607,7 +611,7 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain,
 				int num)
 {
 	unsigned long flags;
-	struct iommu_domain *domain = dma_domain->iommu_domain;
+	struct iommu_domain *domain = &dma_domain->iommu_domain;
 	int ret = 0;
 	int i;
 
@@ -653,7 +657,7 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain,
 static int fsl_pamu_attach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	const u32 *liodn;
 	u32 liodn_cnt;
 	int len, ret = 0;
@@ -691,7 +695,7 @@ static int fsl_pamu_attach_device(struct iommu_domain *domain,
 static void fsl_pamu_detach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	const u32 *prop;
 	int len;
 	struct pci_dev *pdev = NULL;
@@ -723,7 +727,7 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain,
 static  int configure_domain_geometry(struct iommu_domain *domain, void *data)
 {
 	struct iommu_domain_geometry *geom_attr = data;
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	dma_addr_t geom_size;
 	unsigned long flags;
 
@@ -813,7 +817,7 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en
 static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr_type, void *data)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	int ret = 0;
 
 	switch (attr_type) {
@@ -838,7 +842,7 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
 static int fsl_pamu_get_domain_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr_type, void *data)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	int ret = 0;
 
 	switch (attr_type) {
@@ -999,7 +1003,7 @@ static void fsl_pamu_remove_device(struct device *dev)
 
 static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 	unsigned long flags;
 	int ret;
 
@@ -1048,15 +1052,15 @@ static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
 
 static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
 {
-	struct fsl_dma_domain *dma_domain = domain->priv;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
 
 	return dma_domain->win_cnt;
 }
 
 static const struct iommu_ops fsl_pamu_ops = {
 	.capable	= fsl_pamu_capable,
-	.domain_init	= fsl_pamu_domain_init,
-	.domain_destroy = fsl_pamu_domain_destroy,
+	.domain_alloc	= fsl_pamu_domain_alloc,
+	.domain_free    = fsl_pamu_domain_free,
 	.attach_dev	= fsl_pamu_attach_device,
 	.detach_dev	= fsl_pamu_detach_device,
 	.domain_window_enable = fsl_pamu_window_enable,
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
index c90293f997095611f05de7ce559623bca490d6da..f2b0f741d3de66c6fbda832737a6e841c9c966af 100644
--- a/drivers/iommu/fsl_pamu_domain.h
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -71,7 +71,7 @@ struct fsl_dma_domain {
 	u32				stash_id;
 	struct pamu_stash_attribute	dma_stash;
 	u32				snoop_id;
-	struct iommu_domain		*iommu_domain;
+	struct iommu_domain		iommu_domain;
 	spinlock_t			domain_lock;
 };
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 4fc1f8a7f98e455dc8741a0895c8f279972dee16..a35927cd42e515cc81294a94e3c1c3500d51d293 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -339,7 +339,7 @@ struct dmar_domain {
 	DECLARE_BITMAP(iommu_bmp, DMAR_UNITS_SUPPORTED);
 					/* bitmap of iommus this domain uses*/
 
-	struct list_head devices; 	/* all devices' list */
+	struct list_head devices;	/* all devices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -358,6 +358,9 @@ struct dmar_domain {
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	spinlock_t	iommu_lock;	/* protect iommu set in domain */
 	u64		max_addr;	/* maximum mapped address */
+
+	struct iommu_domain domain;	/* generic domain data structure for
+					   iommu core */
 };
 
 /* PCI domain-device relationship */
@@ -449,6 +452,12 @@ static LIST_HEAD(device_domain_list);
 
 static const struct iommu_ops intel_iommu_ops;
 
+/* Convert generic 'struct iommu_domain to private struct dmar_domain */
+static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct dmar_domain, domain);
+}
+
 static int __init intel_iommu_setup(char *str)
 {
 	if (!str)
@@ -595,12 +604,13 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
-	int i, found = 0;
+	bool found = false;
+	int i;
 
 	domain->iommu_coherency = 1;
 
 	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) {
-		found = 1;
+		found = true;
 		if (!ecap_coherent(g_iommus[i]->ecap)) {
 			domain->iommu_coherency = 0;
 			break;
@@ -1267,7 +1277,7 @@ static struct device_domain_info *
 iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
 			 u8 bus, u8 devfn)
 {
-	int found = 0;
+	bool found = false;
 	unsigned long flags;
 	struct device_domain_info *info;
 	struct pci_dev *pdev;
@@ -1282,7 +1292,7 @@ iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
 	list_for_each_entry(info, &domain->devices, link)
 		if (info->iommu == iommu && info->bus == bus &&
 		    info->devfn == devfn) {
-			found = 1;
+			found = true;
 			break;
 		}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -4269,7 +4279,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 	struct device_domain_info *info, *tmp;
 	struct intel_iommu *iommu;
 	unsigned long flags;
-	int found = 0;
+	bool found = false;
 	u8 bus, devfn;
 
 	iommu = device_to_iommu(dev, &bus, &devfn);
@@ -4301,7 +4311,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 		 * update iommu count and coherency
 		 */
 		if (info->iommu == iommu)
-			found = 1;
+			found = true;
 	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -4339,44 +4349,45 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	return 0;
 }
 
-static int intel_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 {
 	struct dmar_domain *dmar_domain;
+	struct iommu_domain *domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
 
 	dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE);
 	if (!dmar_domain) {
 		printk(KERN_ERR
 			"intel_iommu_domain_init: dmar_domain == NULL\n");
-		return -ENOMEM;
+		return NULL;
 	}
 	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
 		printk(KERN_ERR
 			"intel_iommu_domain_init() failed\n");
 		domain_exit(dmar_domain);
-		return -ENOMEM;
+		return NULL;
 	}
 	domain_update_iommu_cap(dmar_domain);
-	domain->priv = dmar_domain;
 
+	domain = &dmar_domain->domain;
 	domain->geometry.aperture_start = 0;
 	domain->geometry.aperture_end   = __DOMAIN_MAX_ADDR(dmar_domain->gaw);
 	domain->geometry.force_aperture = true;
 
-	return 0;
+	return domain;
 }
 
-static void intel_iommu_domain_destroy(struct iommu_domain *domain)
+static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
-
-	domain->priv = NULL;
-	domain_exit(dmar_domain);
+	domain_exit(to_dmar_domain(domain));
 }
 
 static int intel_iommu_attach_device(struct iommu_domain *domain,
 				     struct device *dev)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu;
 	int addr_width;
 	u8 bus, devfn;
@@ -4441,16 +4452,14 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 static void intel_iommu_detach_device(struct iommu_domain *domain,
 				      struct device *dev)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
-
-	domain_remove_one_dev_info(dmar_domain, dev);
+	domain_remove_one_dev_info(to_dmar_domain(domain), dev);
 }
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
 			   size_t size, int iommu_prot)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;
 	int prot = 0;
 	int ret;
@@ -4487,7 +4496,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
 				unsigned long iova, size_t size)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct page *freelist = NULL;
 	struct intel_iommu *iommu;
 	unsigned long start_pfn, last_pfn;
@@ -4535,7 +4544,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 					    dma_addr_t iova)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct dma_pte *pte;
 	int level = 0;
 	u64 phys = 0;
@@ -4594,8 +4603,8 @@ 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,
+	.domain_alloc	= intel_iommu_domain_alloc,
+	.domain_free	= intel_iommu_domain_free,
 	.attach_dev	= intel_iommu_attach_device,
 	.detach_dev	= intel_iommu_detach_device,
 	.map		= intel_iommu_map,
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 14de1ab223c864c00a866ebbba6d68d3fc50cb6c..6c25b3c5b729b97dd61e5ae09a9167d7f05234cb 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -631,7 +631,7 @@ static int __init intel_enable_irq_remapping(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
-	int setup = 0;
+	bool setup = false;
 	int eim = 0;
 
 	if (x2apic_supported()) {
@@ -697,7 +697,7 @@ static int __init intel_enable_irq_remapping(void)
 	 */
 	for_each_iommu(iommu, drhd) {
 		iommu_set_irq_remapping(iommu, eim);
-		setup = 1;
+		setup = true;
 	}
 
 	if (!setup)
@@ -856,7 +856,7 @@ static int __init parse_ioapics_under_ir(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
-	int ir_supported = 0;
+	bool ir_supported = false;
 	int ioapic_idx;
 
 	for_each_iommu(iommu, drhd)
@@ -864,7 +864,7 @@ static int __init parse_ioapics_under_ir(void)
 			if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
 				return -1;
 
-			ir_supported = 1;
+			ir_supported = true;
 		}
 
 	if (!ir_supported)
@@ -917,7 +917,7 @@ static void disable_irq_remapping(void)
 static int reenable_irq_remapping(int eim)
 {
 	struct dmar_drhd_unit *drhd;
-	int setup = 0;
+	bool setup = false;
 	struct intel_iommu *iommu = NULL;
 
 	for_each_iommu(iommu, drhd)
@@ -933,7 +933,7 @@ static int reenable_irq_remapping(int eim)
 
 		/* Set up interrupt remapping for iommu.*/
 		iommu_set_irq_remapping(iommu, eim);
-		setup = 1;
+		setup = true;
 	}
 
 	if (!setup)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index b610a8dee23820573b6362472b4ab5ec31c4003f..4e460216bd1644e5bb8a26ba9a4c3891d7452393 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -116,6 +116,8 @@
 #define ARM_32_LPAE_TCR_EAE		(1 << 31)
 #define ARM_64_LPAE_S2_TCR_RES1		(1 << 31)
 
+#define ARM_LPAE_TCR_EPD1		(1 << 23)
+
 #define ARM_LPAE_TCR_TG0_4K		(0 << 14)
 #define ARM_LPAE_TCR_TG0_64K		(1 << 14)
 #define ARM_LPAE_TCR_TG0_16K		(2 << 14)
@@ -621,6 +623,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
+
+	/* Disable speculative walks through TTBR1 */
+	reg |= ARM_LPAE_TCR_EPD1;
 	cfg->arm_lpae_s1_cfg.tcr = reg;
 
 	/* MAIRs */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 72e683df0731727bd46d17c8bb21a2d53554804f..d4f527e5667936454bfb49e01db931703b180e73 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -901,36 +901,24 @@ EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
 struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
 {
 	struct iommu_domain *domain;
-	int ret;
 
 	if (bus == NULL || bus->iommu_ops == NULL)
 		return NULL;
 
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
 	if (!domain)
 		return NULL;
 
-	domain->ops = bus->iommu_ops;
-
-	ret = domain->ops->domain_init(domain);
-	if (ret)
-		goto out_free;
+	domain->ops  = bus->iommu_ops;
+	domain->type = IOMMU_DOMAIN_UNMANAGED;
 
 	return domain;
-
-out_free:
-	kfree(domain);
-
-	return NULL;
 }
 EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
 void iommu_domain_free(struct iommu_domain *domain)
 {
-	if (likely(domain->ops->domain_destroy != NULL))
-		domain->ops->domain_destroy(domain);
-
-	kfree(domain);
+	domain->ops->domain_free(domain);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
 
@@ -1049,6 +1037,9 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     domain->ops->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
+	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
+		return -EINVAL;
+
 	/* find out the minimum page size supported */
 	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
 
@@ -1100,6 +1091,9 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 		     domain->ops->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
+	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
+		return -EINVAL;
+
 	/* find out the minimum page size supported */
 	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index bc39bdf7b99bf170d793965e28777d3c7a279537..1a67c531a07eb908519e5c130dd22e0ebf377566 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -38,7 +38,7 @@ struct ipmmu_vmsa_device {
 
 struct ipmmu_vmsa_domain {
 	struct ipmmu_vmsa_device *mmu;
-	struct iommu_domain *io_domain;
+	struct iommu_domain io_domain;
 
 	struct io_pgtable_cfg cfg;
 	struct io_pgtable_ops *iop;
@@ -56,6 +56,11 @@ struct ipmmu_vmsa_archdata {
 static DEFINE_SPINLOCK(ipmmu_devices_lock);
 static LIST_HEAD(ipmmu_devices);
 
+static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct ipmmu_vmsa_domain, io_domain);
+}
+
 #define TLB_LOOP_TIMEOUT		100	/* 100us */
 
 /* -----------------------------------------------------------------------------
@@ -428,7 +433,7 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 	 * TODO: We need to look up the faulty device based on the I/O VA. Use
 	 * the IOMMU device for now.
 	 */
-	if (!report_iommu_fault(domain->io_domain, mmu->dev, iova, 0))
+	if (!report_iommu_fault(&domain->io_domain, mmu->dev, iova, 0))
 		return IRQ_HANDLED;
 
 	dev_err_ratelimited(mmu->dev,
@@ -448,7 +453,7 @@ static irqreturn_t ipmmu_irq(int irq, void *dev)
 		return IRQ_NONE;
 
 	io_domain = mmu->mapping->domain;
-	domain = io_domain->priv;
+	domain = to_vmsa_domain(io_domain);
 
 	return ipmmu_domain_irq(domain);
 }
@@ -457,25 +462,25 @@ static irqreturn_t ipmmu_irq(int irq, void *dev)
  * IOMMU Operations
  */
 
-static int ipmmu_domain_init(struct iommu_domain *io_domain)
+static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
 {
 	struct ipmmu_vmsa_domain *domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
-		return -ENOMEM;
+		return NULL;
 
 	spin_lock_init(&domain->lock);
 
-	io_domain->priv = domain;
-	domain->io_domain = io_domain;
-
-	return 0;
+	return &domain->io_domain;
 }
 
-static void ipmmu_domain_destroy(struct iommu_domain *io_domain)
+static void ipmmu_domain_free(struct iommu_domain *io_domain)
 {
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
 	/*
 	 * Free the domain resources. We assume that all devices have already
@@ -491,7 +496,7 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain,
 {
 	struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu;
 	struct ipmmu_vmsa_device *mmu = archdata->mmu;
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 	unsigned long flags;
 	unsigned int i;
 	int ret = 0;
@@ -532,7 +537,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain,
 				struct device *dev)
 {
 	struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu;
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 	unsigned int i;
 
 	for (i = 0; i < archdata->num_utlbs; ++i)
@@ -546,7 +551,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain,
 static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot)
 {
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
 	if (!domain)
 		return -ENODEV;
@@ -557,7 +562,7 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
 static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 			  size_t size)
 {
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
 	return domain->iop->unmap(domain->iop, iova, size);
 }
@@ -565,7 +570,7 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
 				      dma_addr_t iova)
 {
-	struct ipmmu_vmsa_domain *domain = io_domain->priv;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
 	/* TODO: Is locking needed ? */
 
@@ -737,8 +742,8 @@ static void ipmmu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops ipmmu_ops = {
-	.domain_init = ipmmu_domain_init,
-	.domain_destroy = ipmmu_domain_destroy,
+	.domain_alloc = ipmmu_domain_alloc,
+	.domain_free = ipmmu_domain_free,
 	.attach_dev = ipmmu_attach_device,
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index e1b05379ca0e20af17bca8b937263a3fb8a66271..15a2063812fa8ddf5aa2aa2eb912c526b8bc4da2 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -52,8 +52,14 @@ DEFINE_SPINLOCK(msm_iommu_lock);
 struct msm_priv {
 	unsigned long *pgtable;
 	struct list_head list_attached;
+	struct iommu_domain domain;
 };
 
+static struct msm_priv *to_msm_priv(struct iommu_domain *dom)
+{
+	return container_of(dom, struct msm_priv, domain);
+}
+
 static int __enable_clocks(struct msm_iommu_drvdata *drvdata)
 {
 	int ret;
@@ -79,7 +85,7 @@ static void __disable_clocks(struct msm_iommu_drvdata *drvdata)
 
 static int __flush_iotlb(struct iommu_domain *domain)
 {
-	struct msm_priv *priv = domain->priv;
+	struct msm_priv *priv = to_msm_priv(domain);
 	struct msm_iommu_drvdata *iommu_drvdata;
 	struct msm_iommu_ctx_drvdata *ctx_drvdata;
 	int ret = 0;
@@ -209,10 +215,14 @@ static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
 	SET_M(base, ctx, 1);
 }
 
-static int msm_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *msm_iommu_domain_alloc(unsigned type)
 {
-	struct msm_priv *priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	struct msm_priv *priv;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		goto fail_nomem;
 
@@ -224,20 +234,19 @@ static int msm_iommu_domain_init(struct iommu_domain *domain)
 		goto fail_nomem;
 
 	memset(priv->pgtable, 0, SZ_16K);
-	domain->priv = priv;
 
-	domain->geometry.aperture_start = 0;
-	domain->geometry.aperture_end   = (1ULL << 32) - 1;
-	domain->geometry.force_aperture = true;
+	priv->domain.geometry.aperture_start = 0;
+	priv->domain.geometry.aperture_end   = (1ULL << 32) - 1;
+	priv->domain.geometry.force_aperture = true;
 
-	return 0;
+	return &priv->domain;
 
 fail_nomem:
 	kfree(priv);
-	return -ENOMEM;
+	return NULL;
 }
 
-static void msm_iommu_domain_destroy(struct iommu_domain *domain)
+static void msm_iommu_domain_free(struct iommu_domain *domain)
 {
 	struct msm_priv *priv;
 	unsigned long flags;
@@ -245,20 +254,17 @@ static void msm_iommu_domain_destroy(struct iommu_domain *domain)
 	int i;
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
-	priv = domain->priv;
-	domain->priv = NULL;
+	priv = to_msm_priv(domain);
 
-	if (priv) {
-		fl_table = priv->pgtable;
+	fl_table = priv->pgtable;
 
-		for (i = 0; i < NUM_FL_PTE; i++)
-			if ((fl_table[i] & 0x03) == FL_TYPE_TABLE)
-				free_page((unsigned long) __va(((fl_table[i]) &
-								FL_BASE_MASK)));
+	for (i = 0; i < NUM_FL_PTE; i++)
+		if ((fl_table[i] & 0x03) == FL_TYPE_TABLE)
+			free_page((unsigned long) __va(((fl_table[i]) &
+							FL_BASE_MASK)));
 
-		free_pages((unsigned long)priv->pgtable, get_order(SZ_16K));
-		priv->pgtable = NULL;
-	}
+	free_pages((unsigned long)priv->pgtable, get_order(SZ_16K));
+	priv->pgtable = NULL;
 
 	kfree(priv);
 	spin_unlock_irqrestore(&msm_iommu_lock, flags);
@@ -276,9 +282,9 @@ static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
 
-	priv = domain->priv;
+	priv = to_msm_priv(domain);
 
-	if (!priv || !dev) {
+	if (!dev) {
 		ret = -EINVAL;
 		goto fail;
 	}
@@ -330,9 +336,9 @@ static void msm_iommu_detach_dev(struct iommu_domain *domain,
 	int ret;
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
-	priv = domain->priv;
+	priv = to_msm_priv(domain);
 
-	if (!priv || !dev)
+	if (!dev)
 		goto fail;
 
 	iommu_drvdata = dev_get_drvdata(dev->parent);
@@ -382,11 +388,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long va,
 		goto fail;
 	}
 
-	priv = domain->priv;
-	if (!priv) {
-		ret = -EINVAL;
-		goto fail;
-	}
+	priv = to_msm_priv(domain);
 
 	fl_table = priv->pgtable;
 
@@ -484,10 +486,7 @@ static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long va,
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
 
-	priv = domain->priv;
-
-	if (!priv)
-		goto fail;
+	priv = to_msm_priv(domain);
 
 	fl_table = priv->pgtable;
 
@@ -566,7 +565,7 @@ static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
 
-	priv = domain->priv;
+	priv = to_msm_priv(domain);
 	if (list_empty(&priv->list_attached))
 		goto fail;
 
@@ -674,8 +673,8 @@ irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
 
 static const struct iommu_ops msm_iommu_ops = {
 	.capable = msm_iommu_capable,
-	.domain_init = msm_iommu_domain_init,
-	.domain_destroy = msm_iommu_domain_destroy,
+	.domain_alloc = msm_iommu_domain_alloc,
+	.domain_free = msm_iommu_domain_free,
 	.attach_dev = msm_iommu_attach_dev,
 	.detach_dev = msm_iommu_detach_dev,
 	.map = msm_iommu_map,
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index a4ba851825c235b5bfa7ab93a8256adfca160ca7..a22c33d6a486c9dea9bfa820feea18a034623eec 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -59,6 +59,7 @@ struct omap_iommu_domain {
 	struct omap_iommu *iommu_dev;
 	struct device *dev;
 	spinlock_t lock;
+	struct iommu_domain domain;
 };
 
 #define MMU_LOCK_BASE_SHIFT	10
@@ -79,6 +80,15 @@ struct iotlb_lock {
 static struct platform_driver omap_iommu_driver;
 static struct kmem_cache *iopte_cachep;
 
+/**
+ * to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain
+ * @dom:	generic iommu domain handle
+ **/
+static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct omap_iommu_domain, domain);
+}
+
 /**
  * omap_iommu_save_ctx - Save registers for pm off-mode support
  * @dev:	client device
@@ -901,7 +911,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	u32 *iopgd, *iopte;
 	struct omap_iommu *obj = data;
 	struct iommu_domain *domain = obj->domain;
-	struct omap_iommu_domain *omap_domain = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 
 	if (!omap_domain->iommu_dev)
 		return IRQ_NONE;
@@ -1113,7 +1123,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz)
 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 = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu *oiommu = omap_domain->iommu_dev;
 	struct device *dev = oiommu->dev;
 	struct iotlb_entry e;
@@ -1140,7 +1150,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
 			    size_t size)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu *oiommu = omap_domain->iommu_dev;
 	struct device *dev = oiommu->dev;
 
@@ -1152,7 +1162,7 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
 static int
 omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu *oiommu;
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 	int ret = 0;
@@ -1212,17 +1222,20 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
 static void omap_iommu_detach_dev(struct iommu_domain *domain,
 				 struct device *dev)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 
 	spin_lock(&omap_domain->lock);
 	_omap_iommu_detach_dev(omap_domain, dev);
 	spin_unlock(&omap_domain->lock);
 }
 
-static int omap_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 {
 	struct omap_iommu_domain *omap_domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
 	omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL);
 	if (!omap_domain) {
 		pr_err("kzalloc failed\n");
@@ -1244,25 +1257,21 @@ static int omap_iommu_domain_init(struct iommu_domain *domain)
 	clean_dcache_area(omap_domain->pgtable, IOPGD_TABLE_SIZE);
 	spin_lock_init(&omap_domain->lock);
 
-	domain->priv = omap_domain;
+	omap_domain->domain.geometry.aperture_start = 0;
+	omap_domain->domain.geometry.aperture_end   = (1ULL << 32) - 1;
+	omap_domain->domain.geometry.force_aperture = true;
 
-	domain->geometry.aperture_start = 0;
-	domain->geometry.aperture_end   = (1ULL << 32) - 1;
-	domain->geometry.force_aperture = true;
-
-	return 0;
+	return &omap_domain->domain;
 
 fail_nomem:
 	kfree(omap_domain);
 out:
-	return -ENOMEM;
+	return NULL;
 }
 
-static void omap_iommu_domain_destroy(struct iommu_domain *domain)
+static void omap_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
-
-	domain->priv = NULL;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 
 	/*
 	 * An iommu device is still attached
@@ -1278,7 +1287,7 @@ static void omap_iommu_domain_destroy(struct iommu_domain *domain)
 static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t da)
 {
-	struct omap_iommu_domain *omap_domain = domain->priv;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu *oiommu = omap_domain->iommu_dev;
 	struct device *dev = oiommu->dev;
 	u32 *pgd, *pte;
@@ -1358,8 +1367,8 @@ static void omap_iommu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops omap_iommu_ops = {
-	.domain_init	= omap_iommu_domain_init,
-	.domain_destroy	= omap_iommu_domain_destroy,
+	.domain_alloc	= omap_iommu_domain_alloc,
+	.domain_free	= omap_iommu_domain_free,
 	.attach_dev	= omap_iommu_attach_dev,
 	.detach_dev	= omap_iommu_detach_dev,
 	.map		= omap_iommu_map,
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 9f74fddcd304f76bd8a9d546f1d2caf74e7dc588..4015560bf486db22e82f1652799731b90277b864 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -80,6 +80,8 @@ struct rk_iommu_domain {
 	u32 *dt; /* page directory table */
 	spinlock_t iommus_lock; /* lock for iommus list */
 	spinlock_t dt_lock; /* lock for modifying page directory table */
+
+	struct iommu_domain domain;
 };
 
 struct rk_iommu {
@@ -100,6 +102,11 @@ static inline void rk_table_flush(u32 *va, unsigned int count)
 	outer_flush_range(pa_start, pa_end);
 }
 
+static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct rk_iommu_domain, domain);
+}
+
 /**
  * Inspired by _wait_for in intel_drv.h
  * This is NOT safe for use in interrupt context.
@@ -503,7 +510,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
 static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain,
 					 dma_addr_t iova)
 {
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 	phys_addr_t pt_phys, phys = 0;
 	u32 dte, pte;
@@ -639,7 +646,7 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 			phys_addr_t paddr, size_t size, int prot)
 {
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 	dma_addr_t iova = (dma_addr_t)_iova;
 	u32 *page_table, *pte_addr;
@@ -670,7 +677,7 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
 			     size_t size)
 {
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 	dma_addr_t iova = (dma_addr_t)_iova;
 	phys_addr_t pt_phys;
@@ -726,7 +733,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
 	struct rk_iommu *iommu;
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 	int ret;
 	phys_addr_t dte_addr;
@@ -778,7 +785,7 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
 	struct rk_iommu *iommu;
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 
 	/* Allow 'virtual devices' (eg drm) to detach from domain */
@@ -804,13 +811,16 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
 	dev_info(dev, "Detached from iommu domain\n");
 }
 
-static int rk_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 {
 	struct rk_iommu_domain *rk_domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
 	rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL);
 	if (!rk_domain)
-		return -ENOMEM;
+		return NULL;
 
 	/*
 	 * rk32xx iommus use a 2 level pagetable.
@@ -827,17 +837,16 @@ static int rk_iommu_domain_init(struct iommu_domain *domain)
 	spin_lock_init(&rk_domain->dt_lock);
 	INIT_LIST_HEAD(&rk_domain->iommus);
 
-	domain->priv = rk_domain;
+	return &rk_domain->domain;
 
-	return 0;
 err_dt:
 	kfree(rk_domain);
-	return -ENOMEM;
+	return NULL;
 }
 
-static void rk_iommu_domain_destroy(struct iommu_domain *domain)
+static void rk_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct rk_iommu_domain *rk_domain = domain->priv;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	int i;
 
 	WARN_ON(!list_empty(&rk_domain->iommus));
@@ -852,8 +861,7 @@ static void rk_iommu_domain_destroy(struct iommu_domain *domain)
 	}
 
 	free_page((unsigned long)rk_domain->dt);
-	kfree(domain->priv);
-	domain->priv = NULL;
+	kfree(rk_domain);
 }
 
 static bool rk_iommu_is_dev_iommu_master(struct device *dev)
@@ -952,8 +960,8 @@ static void rk_iommu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops rk_iommu_ops = {
-	.domain_init = rk_iommu_domain_init,
-	.domain_destroy = rk_iommu_domain_destroy,
+	.domain_alloc = rk_iommu_domain_alloc,
+	.domain_free = rk_iommu_domain_free,
 	.attach_dev = rk_iommu_attach_device,
 	.detach_dev = rk_iommu_detach_device,
 	.map = rk_iommu_map,
diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c
index f1b00774e4de980511cf741895a219059f52d6fa..a0287519a1d4be90d710c39ec951b480832426e9 100644
--- a/drivers/iommu/shmobile-iommu.c
+++ b/drivers/iommu/shmobile-iommu.c
@@ -42,11 +42,17 @@ struct shmobile_iommu_domain {
 	spinlock_t map_lock;
 	spinlock_t attached_list_lock;
 	struct list_head attached_list;
+	struct iommu_domain domain;
 };
 
 static struct shmobile_iommu_archdata *ipmmu_archdata;
 static struct kmem_cache *l1cache, *l2cache;
 
+static struct shmobile_iommu_domain *to_sh_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct shmobile_iommu_domain, domain);
+}
+
 static int pgtable_alloc(struct shmobile_iommu_domain_pgtable *pgtable,
 			 struct kmem_cache *cache, size_t size)
 {
@@ -82,31 +88,33 @@ static void pgtable_write(struct shmobile_iommu_domain_pgtable *pgtable,
 				   sizeof(val) * count, DMA_TO_DEVICE);
 }
 
-static int shmobile_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *shmobile_iommu_domain_alloc(unsigned type)
 {
 	struct shmobile_iommu_domain *sh_domain;
 	int i, ret;
 
-	sh_domain = kmalloc(sizeof(*sh_domain), GFP_KERNEL);
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	sh_domain = kzalloc(sizeof(*sh_domain), GFP_KERNEL);
 	if (!sh_domain)
-		return -ENOMEM;
+		return NULL;
 	ret = pgtable_alloc(&sh_domain->l1, l1cache, L1_SIZE);
 	if (ret < 0) {
 		kfree(sh_domain);
-		return ret;
+		return NULL;
 	}
 	for (i = 0; i < L1_LEN; i++)
 		sh_domain->l2[i].pgtable = NULL;
 	spin_lock_init(&sh_domain->map_lock);
 	spin_lock_init(&sh_domain->attached_list_lock);
 	INIT_LIST_HEAD(&sh_domain->attached_list);
-	domain->priv = sh_domain;
-	return 0;
+	return &sh_domain->domain;
 }
 
-static void shmobile_iommu_domain_destroy(struct iommu_domain *domain)
+static void shmobile_iommu_domain_free(struct iommu_domain *domain)
 {
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 	int i;
 
 	for (i = 0; i < L1_LEN; i++) {
@@ -115,14 +123,13 @@ static void shmobile_iommu_domain_destroy(struct iommu_domain *domain)
 	}
 	pgtable_free(&sh_domain->l1, l1cache, L1_SIZE);
 	kfree(sh_domain);
-	domain->priv = NULL;
 }
 
 static int shmobile_iommu_attach_device(struct iommu_domain *domain,
 					struct device *dev)
 {
 	struct shmobile_iommu_archdata *archdata = dev->archdata.iommu;
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 	int ret = -EBUSY;
 
 	if (!archdata)
@@ -151,7 +158,7 @@ static void shmobile_iommu_detach_device(struct iommu_domain *domain,
 					 struct device *dev)
 {
 	struct shmobile_iommu_archdata *archdata = dev->archdata.iommu;
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 
 	if (!archdata)
 		return;
@@ -214,7 +221,7 @@ static int shmobile_iommu_map(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t size, int prot)
 {
 	struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL };
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 	unsigned int l1index, l2index;
 	int ret;
 
@@ -258,7 +265,7 @@ static size_t shmobile_iommu_unmap(struct iommu_domain *domain,
 				   unsigned long iova, size_t size)
 {
 	struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL };
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 	unsigned int l1index, l2index;
 	uint32_t l2entry = 0;
 	size_t ret = 0;
@@ -298,7 +305,7 @@ static size_t shmobile_iommu_unmap(struct iommu_domain *domain,
 static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain,
 					       dma_addr_t iova)
 {
-	struct shmobile_iommu_domain *sh_domain = domain->priv;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
 	uint32_t l1entry = 0, l2entry = 0;
 	unsigned int l1index, l2index;
 
@@ -355,8 +362,8 @@ static int shmobile_iommu_add_device(struct device *dev)
 }
 
 static const struct iommu_ops shmobile_iommu_ops = {
-	.domain_init = shmobile_iommu_domain_init,
-	.domain_destroy = shmobile_iommu_domain_destroy,
+	.domain_alloc = shmobile_iommu_domain_alloc,
+	.domain_free = shmobile_iommu_domain_free,
 	.attach_dev = shmobile_iommu_attach_device,
 	.detach_dev = shmobile_iommu_detach_device,
 	.map = shmobile_iommu_map,
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index c48da057dbb1e5b6be38e6b28daced1046454687..37e708fdbb5aac0bb66ac0cf17db030aa30a3a1e 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -63,11 +63,21 @@ struct gart_device {
 	struct device		*dev;
 };
 
+struct gart_domain {
+	struct iommu_domain domain;		/* generic domain handle */
+	struct gart_device *gart;		/* link to gart device   */
+};
+
 static struct gart_device *gart_handle; /* unique for a system */
 
 #define GART_PTE(_pfn)						\
 	(GART_ENTRY_PHYS_ADDR_VALID | ((_pfn) << PAGE_SHIFT))
 
+static struct gart_domain *to_gart_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct gart_domain, domain);
+}
+
 /*
  * Any interaction between any block on PPSB and a block on APB or AHB
  * must have these read-back to ensure the APB/AHB bus transaction is
@@ -156,20 +166,11 @@ static inline bool gart_iova_range_valid(struct gart_device *gart,
 static int gart_iommu_attach_dev(struct iommu_domain *domain,
 				 struct device *dev)
 {
-	struct gart_device *gart;
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
 	struct gart_client *client, *c;
 	int err = 0;
 
-	gart = gart_handle;
-	if (!gart)
-		return -EINVAL;
-	domain->priv = gart;
-
-	domain->geometry.aperture_start = gart->iovmm_base;
-	domain->geometry.aperture_end   = gart->iovmm_base +
-					gart->page_count * GART_PAGE_SIZE - 1;
-	domain->geometry.force_aperture = true;
-
 	client = devm_kzalloc(gart->dev, sizeof(*c), GFP_KERNEL);
 	if (!client)
 		return -ENOMEM;
@@ -198,7 +199,8 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain,
 static void gart_iommu_detach_dev(struct iommu_domain *domain,
 				  struct device *dev)
 {
-	struct gart_device *gart = domain->priv;
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
 	struct gart_client *c;
 
 	spin_lock(&gart->client_lock);
@@ -216,33 +218,55 @@ static void gart_iommu_detach_dev(struct iommu_domain *domain,
 	spin_unlock(&gart->client_lock);
 }
 
-static int gart_iommu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *gart_iommu_domain_alloc(unsigned type)
 {
-	return 0;
-}
+	struct gart_domain *gart_domain;
+	struct gart_device *gart;
 
-static void gart_iommu_domain_destroy(struct iommu_domain *domain)
-{
-	struct gart_device *gart = domain->priv;
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
 
+	gart = gart_handle;
 	if (!gart)
-		return;
+		return NULL;
 
-	spin_lock(&gart->client_lock);
-	if (!list_empty(&gart->client)) {
-		struct gart_client *c;
+	gart_domain = kzalloc(sizeof(*gart_domain), GFP_KERNEL);
+	if (!gart_domain)
+		return NULL;
+
+	gart_domain->gart = gart;
+	gart_domain->domain.geometry.aperture_start = gart->iovmm_base;
+	gart_domain->domain.geometry.aperture_end = gart->iovmm_base +
+					gart->page_count * GART_PAGE_SIZE - 1;
+	gart_domain->domain.geometry.force_aperture = true;
+
+	return &gart_domain->domain;
+}
+
+static void gart_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+
+	if (gart) {
+		spin_lock(&gart->client_lock);
+		if (!list_empty(&gart->client)) {
+			struct gart_client *c;
 
-		list_for_each_entry(c, &gart->client, list)
-			gart_iommu_detach_dev(domain, c->dev);
+			list_for_each_entry(c, &gart->client, list)
+				gart_iommu_detach_dev(domain, c->dev);
+		}
+		spin_unlock(&gart->client_lock);
 	}
-	spin_unlock(&gart->client_lock);
-	domain->priv = NULL;
+
+	kfree(gart_domain);
 }
 
 static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
 			  phys_addr_t pa, size_t bytes, int prot)
 {
-	struct gart_device *gart = domain->priv;
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
 	unsigned long flags;
 	unsigned long pfn;
 
@@ -265,7 +289,8 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
 static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			       size_t bytes)
 {
-	struct gart_device *gart = domain->priv;
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
 	unsigned long flags;
 
 	if (!gart_iova_range_valid(gart, iova, bytes))
@@ -281,7 +306,8 @@ static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
-	struct gart_device *gart = domain->priv;
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
 	unsigned long pte;
 	phys_addr_t pa;
 	unsigned long flags;
@@ -310,8 +336,8 @@ static bool gart_iommu_capable(enum iommu_cap cap)
 
 static const struct iommu_ops gart_iommu_ops = {
 	.capable	= gart_iommu_capable,
-	.domain_init	= gart_iommu_domain_init,
-	.domain_destroy	= gart_iommu_domain_destroy,
+	.domain_alloc	= gart_iommu_domain_alloc,
+	.domain_free	= gart_iommu_domain_free,
 	.attach_dev	= gart_iommu_attach_dev,
 	.detach_dev	= gart_iommu_detach_dev,
 	.map		= gart_iommu_map,
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 6e134c7c227fced6a0c186f3e403fc6d9e1d49f7..c845d99ecf6b8c50757998f08c86224c70064acb 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitops.h>
 #include <linux/err.h>
 #include <linux/iommu.h>
 #include <linux/kernel.h>
@@ -24,6 +25,8 @@ struct tegra_smmu {
 	struct tegra_mc *mc;
 	const struct tegra_smmu_soc *soc;
 
+	unsigned long pfn_mask;
+
 	unsigned long *asids;
 	struct mutex lock;
 
@@ -31,7 +34,7 @@ struct tegra_smmu {
 };
 
 struct tegra_smmu_as {
-	struct iommu_domain *domain;
+	struct iommu_domain domain;
 	struct tegra_smmu *smmu;
 	unsigned int use_count;
 	struct page *count;
@@ -40,6 +43,11 @@ struct tegra_smmu_as {
 	u32 attr;
 };
 
+static struct tegra_smmu_as *to_smmu_as(struct iommu_domain *dom)
+{
+	return container_of(dom, struct tegra_smmu_as, domain);
+}
+
 static inline void smmu_writel(struct tegra_smmu *smmu, u32 value,
 			       unsigned long offset)
 {
@@ -105,8 +113,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
 #define SMMU_PDE_SHIFT 22
 #define SMMU_PTE_SHIFT 12
 
-#define SMMU_PFN_MASK 0x000fffff
-
 #define SMMU_PD_READABLE	(1 << 31)
 #define SMMU_PD_WRITABLE	(1 << 30)
 #define SMMU_PD_NONSECURE	(1 << 29)
@@ -224,30 +230,32 @@ static bool tegra_smmu_capable(enum iommu_cap cap)
 	return false;
 }
 
-static int tegra_smmu_domain_init(struct iommu_domain *domain)
+static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
 {
 	struct tegra_smmu_as *as;
 	unsigned int i;
 	uint32_t *pd;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
 	as = kzalloc(sizeof(*as), GFP_KERNEL);
 	if (!as)
-		return -ENOMEM;
+		return NULL;
 
 	as->attr = SMMU_PD_READABLE | SMMU_PD_WRITABLE | SMMU_PD_NONSECURE;
-	as->domain = domain;
 
 	as->pd = alloc_page(GFP_KERNEL | __GFP_DMA);
 	if (!as->pd) {
 		kfree(as);
-		return -ENOMEM;
+		return NULL;
 	}
 
 	as->count = alloc_page(GFP_KERNEL);
 	if (!as->count) {
 		__free_page(as->pd);
 		kfree(as);
-		return -ENOMEM;
+		return NULL;
 	}
 
 	/* clear PDEs */
@@ -264,14 +272,17 @@ static int tegra_smmu_domain_init(struct iommu_domain *domain)
 	for (i = 0; i < SMMU_NUM_PDE; i++)
 		pd[i] = 0;
 
-	domain->priv = as;
+	/* setup aperture */
+	as->domain.geometry.aperture_start = 0;
+	as->domain.geometry.aperture_end = 0xffffffff;
+	as->domain.geometry.force_aperture = true;
 
-	return 0;
+	return &as->domain;
 }
 
-static void tegra_smmu_domain_destroy(struct iommu_domain *domain)
+static void tegra_smmu_domain_free(struct iommu_domain *domain)
 {
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 
 	/* TODO: free page directory and page tables */
 	ClearPageReserved(as->pd);
@@ -395,7 +406,7 @@ static int tegra_smmu_attach_dev(struct iommu_domain *domain,
 				 struct device *dev)
 {
 	struct tegra_smmu *smmu = dev->archdata.iommu;
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 	struct device_node *np = dev->of_node;
 	struct of_phandle_args args;
 	unsigned int index = 0;
@@ -428,7 +439,7 @@ static int tegra_smmu_attach_dev(struct iommu_domain *domain,
 
 static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 	struct device_node *np = dev->of_node;
 	struct tegra_smmu *smmu = as->smmu;
 	struct of_phandle_args args;
@@ -481,7 +492,7 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
 		smmu_flush_tlb_section(smmu, as->id, iova);
 		smmu_flush(smmu);
 	} else {
-		page = pfn_to_page(pd[pde] & SMMU_PFN_MASK);
+		page = pfn_to_page(pd[pde] & smmu->pfn_mask);
 		pt = page_address(page);
 	}
 
@@ -503,7 +514,7 @@ static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova)
 	u32 *pd = page_address(as->pd), *pt;
 	struct page *page;
 
-	page = pfn_to_page(pd[pde] & SMMU_PFN_MASK);
+	page = pfn_to_page(pd[pde] & as->smmu->pfn_mask);
 	pt = page_address(page);
 
 	/*
@@ -524,7 +535,7 @@ static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova)
 static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
 			  phys_addr_t paddr, size_t size, int prot)
 {
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 	struct tegra_smmu *smmu = as->smmu;
 	unsigned long offset;
 	struct page *page;
@@ -548,7 +559,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
 static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 			       size_t size)
 {
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 	struct tegra_smmu *smmu = as->smmu;
 	unsigned long offset;
 	struct page *page;
@@ -572,13 +583,13 @@ static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
-	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
 	struct page *page;
 	unsigned long pfn;
 	u32 *pte;
 
 	pte = as_get_pte(as, iova, &page);
-	pfn = *pte & SMMU_PFN_MASK;
+	pfn = *pte & as->smmu->pfn_mask;
 
 	return PFN_PHYS(pfn);
 }
@@ -633,8 +644,8 @@ static void tegra_smmu_remove_device(struct device *dev)
 
 static const struct iommu_ops tegra_smmu_ops = {
 	.capable = tegra_smmu_capable,
-	.domain_init = tegra_smmu_domain_init,
-	.domain_destroy = tegra_smmu_domain_destroy,
+	.domain_alloc = tegra_smmu_domain_alloc,
+	.domain_free = tegra_smmu_domain_free,
 	.attach_dev = tegra_smmu_attach_dev,
 	.detach_dev = tegra_smmu_detach_dev,
 	.add_device = tegra_smmu_add_device,
@@ -702,6 +713,10 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev,
 	smmu->dev = dev;
 	smmu->mc = mc;
 
+	smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1;
+	dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n",
+		mc->soc->num_address_bits, smmu->pfn_mask);
+
 	value = SMMU_PTC_CONFIG_ENABLE | SMMU_PTC_CONFIG_INDEX_MAP(0x3f);
 
 	if (soc->supports_request_limit)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 38daa453f2e532f0c36d7ba81b10860ccc28b478..0546b8710ce308540abd841944aee07ba24fedfb 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -51,9 +51,33 @@ struct iommu_domain_geometry {
 	bool force_aperture;       /* DMA only allowed in mappable range? */
 };
 
+/* Domain feature flags */
+#define __IOMMU_DOMAIN_PAGING	(1U << 0)  /* Support for iommu_map/unmap */
+#define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
+					      implementation              */
+#define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
+
+/*
+ * This are the possible domain-types
+ *
+ *	IOMMU_DOMAIN_BLOCKED	- All DMA is blocked, can be used to isolate
+ *				  devices
+ *	IOMMU_DOMAIN_IDENTITY	- DMA addresses are system physical addresses
+ *	IOMMU_DOMAIN_UNMANAGED	- DMA mappings managed by IOMMU-API user, used
+ *				  for VMs
+ *	IOMMU_DOMAIN_DMA	- Internally used for DMA-API implementations.
+ *				  This flag allows IOMMU drivers to implement
+ *				  certain optimizations for these domains
+ */
+#define IOMMU_DOMAIN_BLOCKED	(0U)
+#define IOMMU_DOMAIN_IDENTITY	(__IOMMU_DOMAIN_PT)
+#define IOMMU_DOMAIN_UNMANAGED	(__IOMMU_DOMAIN_PAGING)
+#define IOMMU_DOMAIN_DMA	(__IOMMU_DOMAIN_PAGING |	\
+				 __IOMMU_DOMAIN_DMA_API)
+
 struct iommu_domain {
+	unsigned type;
 	const struct iommu_ops *ops;
-	void *priv;
 	iommu_fault_handler_t handler;
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
@@ -113,8 +137,11 @@ enum iommu_attr {
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
-	int (*domain_init)(struct iommu_domain *domain);
-	void (*domain_destroy)(struct iommu_domain *domain);
+
+	/* Domain allocation and freeing by the iommu driver */
+	struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type);
+	void (*domain_free)(struct iommu_domain *);
+
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,