diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index f39ab7554fc9..d3de8e1ae915 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -4,6 +4,7 @@ config DRM_MSM
 	depends on DRM
 	depends on ARCH_MSM
 	depends on ARCH_MSM8960
+	depends on MSM_IOMMU
 	select DRM_KMS_HELPER
 	select SHMEM
 	select TMPFS
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 3e7fdbb4916b..79bbc21c1d01 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -207,6 +207,7 @@ config SHMOBILE_IOMMU
 	bool "IOMMU for Renesas IPMMU/IPMMUI"
 	default n
 	depends on ARM
+	depends on SH_MOBILE || COMPILE_TEST
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
 	select SHMOBILE_IPMMU
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 72531f008a5e..faf0da4bb3a2 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -248,8 +248,8 @@ static bool check_device(struct device *dev)
 	if (!dev || !dev->dma_mask)
 		return false;
 
-	/* No device or no PCI device */
-	if (dev->bus != &pci_bus_type)
+	/* No PCI device */
+	if (!dev_is_pci(dev))
 		return false;
 
 	devid = get_device_id(dev);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e46a88700b68..8911850c9444 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -24,7 +24,7 @@
  *	- v7/v8 long-descriptor format
  *	- Non-secure access to the SMMU
  *	- 4k and 64k pages, with contiguous pte hints.
- *	- Up to 39-bit addressing
+ *	- Up to 42-bit addressing (dependent on VA_BITS)
  *	- Context fault reporting
  */
 
@@ -61,12 +61,13 @@
 #define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
 
 /* Page table bits */
-#define ARM_SMMU_PTE_PAGE		(((pteval_t)3) << 0)
+#define ARM_SMMU_PTE_XN			(((pteval_t)3) << 53)
 #define ARM_SMMU_PTE_CONT		(((pteval_t)1) << 52)
 #define ARM_SMMU_PTE_AF			(((pteval_t)1) << 10)
 #define ARM_SMMU_PTE_SH_NS		(((pteval_t)0) << 8)
 #define ARM_SMMU_PTE_SH_OS		(((pteval_t)2) << 8)
 #define ARM_SMMU_PTE_SH_IS		(((pteval_t)3) << 8)
+#define ARM_SMMU_PTE_PAGE		(((pteval_t)3) << 0)
 
 #if PAGE_SIZE == SZ_4K
 #define ARM_SMMU_PTE_CONT_ENTRIES	16
@@ -1205,7 +1206,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 				   unsigned long pfn, int flags, int stage)
 {
 	pte_t *pte, *start;
-	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF;
+	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF | ARM_SMMU_PTE_XN;
 
 	if (pmd_none(*pmd)) {
 		/* Allocate a new set of tables */
@@ -1244,7 +1245,9 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 	}
 
 	/* If no access, create a faulting entry to avoid TLB fills */
-	if (!(flags & (IOMMU_READ | IOMMU_WRITE)))
+	if (flags & IOMMU_EXEC)
+		pteval &= ~ARM_SMMU_PTE_XN;
+	else if (!(flags & (IOMMU_READ | IOMMU_WRITE)))
 		pteval &= ~ARM_SMMU_PTE_PAGE;
 
 	pteval |= ARM_SMMU_PTE_SH_IS;
@@ -1494,6 +1497,13 @@ static int arm_smmu_add_device(struct device *dev)
 {
 	struct arm_smmu_device *child, *parent, *smmu;
 	struct arm_smmu_master *master = NULL;
+	struct iommu_group *group;
+	int ret;
+
+	if (dev->archdata.iommu) {
+		dev_warn(dev, "IOMMU driver already assigned to device\n");
+		return -EINVAL;
+	}
 
 	spin_lock(&arm_smmu_devices_lock);
 	list_for_each_entry(parent, &arm_smmu_devices, list) {
@@ -1526,13 +1536,23 @@ static int arm_smmu_add_device(struct device *dev)
 	if (!master)
 		return -ENODEV;
 
+	group = iommu_group_alloc();
+	if (IS_ERR(group)) {
+		dev_err(dev, "Failed to allocate IOMMU group\n");
+		return PTR_ERR(group);
+	}
+
+	ret = iommu_group_add_device(group, dev);
+	iommu_group_put(group);
 	dev->archdata.iommu = smmu;
-	return 0;
+
+	return ret;
 }
 
 static void arm_smmu_remove_device(struct device *dev)
 {
 	dev->archdata.iommu = NULL;
+	iommu_group_remove_device(dev);
 }
 
 static struct iommu_ops arm_smmu_ops = {
@@ -1730,7 +1750,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	 * allocation (PTRS_PER_PGD).
 	 */
 #ifdef CONFIG_64BIT
-	/* Current maximum output size of 39 bits */
 	smmu->s1_output_size = min(39UL, size);
 #else
 	smmu->s1_output_size = min(32UL, size);
@@ -1745,7 +1764,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	} else {
 #ifdef CONFIG_64BIT
 		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
-		size = min(39, arm_smmu_id_size_to_bits(size));
+		size = min(VA_BITS, arm_smmu_id_size_to_bits(size));
 #else
 		size = 32;
 #endif
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 8b452c9676d9..158156543410 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -52,6 +52,9 @@ LIST_HEAD(dmar_drhd_units);
 struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
 
+static int alloc_iommu(struct dmar_drhd_unit *drhd);
+static void free_iommu(struct intel_iommu *iommu);
+
 static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
@@ -100,7 +103,6 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 	if (!pdev) {
 		pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n",
 			segment, scope->bus, path->device, path->function);
-		*dev = NULL;
 		return 0;
 	}
 	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
@@ -151,7 +153,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 			ret = dmar_parse_one_dev_scope(scope,
 				&(*devices)[index], segment);
 			if (ret) {
-				kfree(*devices);
+				dmar_free_dev_scope(devices, cnt);
 				return ret;
 			}
 			index ++;
@@ -162,6 +164,17 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 	return 0;
 }
 
+void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
+{
+	if (*devices && *cnt) {
+		while (--*cnt >= 0)
+			pci_dev_put((*devices)[*cnt]);
+		kfree(*devices);
+		*devices = NULL;
+		*cnt = 0;
+	}
+}
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
@@ -193,25 +206,28 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	return 0;
 }
 
+static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
+{
+	if (dmaru->devices && dmaru->devices_cnt)
+		dmar_free_dev_scope(&dmaru->devices, &dmaru->devices_cnt);
+	if (dmaru->iommu)
+		free_iommu(dmaru->iommu);
+	kfree(dmaru);
+}
+
 static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
 {
 	struct acpi_dmar_hardware_unit *drhd;
-	int ret = 0;
 
 	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
 
 	if (dmaru->include_all)
 		return 0;
 
-	ret = dmar_parse_dev_scope((void *)(drhd + 1),
-				((void *)drhd) + drhd->header.length,
-				&dmaru->devices_cnt, &dmaru->devices,
-				drhd->segment);
-	if (ret) {
-		list_del(&dmaru->list);
-		kfree(dmaru);
-	}
-	return ret;
+	return dmar_parse_dev_scope((void *)(drhd + 1),
+				    ((void *)drhd) + drhd->header.length,
+				    &dmaru->devices_cnt, &dmaru->devices,
+				    drhd->segment);
 }
 
 #ifdef CONFIG_ACPI_NUMA
@@ -423,7 +439,7 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 int __init dmar_dev_scope_init(void)
 {
 	static int dmar_dev_scope_initialized;
-	struct dmar_drhd_unit *drhd, *drhd_n;
+	struct dmar_drhd_unit *drhd;
 	int ret = -ENODEV;
 
 	if (dmar_dev_scope_initialized)
@@ -432,7 +448,7 @@ int __init dmar_dev_scope_init(void)
 	if (list_empty(&dmar_drhd_units))
 		goto fail;
 
-	list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
+	list_for_each_entry(drhd, &dmar_drhd_units, list) {
 		ret = dmar_parse_dev(drhd);
 		if (ret)
 			goto fail;
@@ -456,24 +472,23 @@ int __init dmar_table_init(void)
 	static int dmar_table_initialized;
 	int ret;
 
-	if (dmar_table_initialized)
-		return 0;
+	if (dmar_table_initialized == 0) {
+		ret = parse_dmar_table();
+		if (ret < 0) {
+			if (ret != -ENODEV)
+				pr_info("parse DMAR table failure.\n");
+		} else  if (list_empty(&dmar_drhd_units)) {
+			pr_info("No DMAR devices found\n");
+			ret = -ENODEV;
+		}
 
-	dmar_table_initialized = 1;
-
-	ret = parse_dmar_table();
-	if (ret) {
-		if (ret != -ENODEV)
-			pr_info("parse DMAR table failure.\n");
-		return ret;
+		if (ret < 0)
+			dmar_table_initialized = ret;
+		else
+			dmar_table_initialized = 1;
 	}
 
-	if (list_empty(&dmar_drhd_units)) {
-		pr_info("No DMAR devices found\n");
-		return -ENODEV;
-	}
-
-	return 0;
+	return dmar_table_initialized < 0 ? dmar_table_initialized : 0;
 }
 
 static void warn_invalid_dmar(u64 addr, const char *message)
@@ -488,7 +503,7 @@ static void warn_invalid_dmar(u64 addr, const char *message)
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
 }
 
-int __init check_zero_address(void)
+static int __init check_zero_address(void)
 {
 	struct acpi_table_dmar *dmar;
 	struct acpi_dmar_header *entry_header;
@@ -546,14 +561,6 @@ int __init detect_intel_iommu(void)
 	if (ret)
 		ret = check_zero_address();
 	{
-		struct acpi_table_dmar *dmar;
-
-		dmar = (struct acpi_table_dmar *) dmar_tbl;
-
-		if (ret && irq_remapping_enabled && cpu_has_x2apic &&
-		    dmar->flags & 0x1)
-			pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
-
 		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
 			iommu_detected = 1;
 			/* Make sure ACS will be enabled */
@@ -565,7 +572,7 @@ int __init detect_intel_iommu(void)
 			x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
 	}
-	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
+	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
 
 	return ret ? 1 : -ENODEV;
@@ -647,7 +654,7 @@ out:
 	return err;
 }
 
-int alloc_iommu(struct dmar_drhd_unit *drhd)
+static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
 	u32 ver, sts;
@@ -721,12 +728,19 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	return err;
 }
 
-void free_iommu(struct intel_iommu *iommu)
+static void free_iommu(struct intel_iommu *iommu)
 {
-	if (!iommu)
-		return;
+	if (iommu->irq) {
+		free_irq(iommu->irq, iommu);
+		irq_set_handler_data(iommu->irq, NULL);
+		destroy_irq(iommu->irq);
+	}
 
-	free_dmar_iommu(iommu);
+	if (iommu->qi) {
+		free_page((unsigned long)iommu->qi->desc);
+		kfree(iommu->qi->desc_status);
+		kfree(iommu->qi);
+	}
 
 	if (iommu->reg)
 		unmap_iommu(iommu);
@@ -1050,7 +1064,7 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
 	if (!desc_page) {
 		kfree(qi);
-		iommu->qi = 0;
+		iommu->qi = NULL;
 		return -ENOMEM;
 	}
 
@@ -1060,7 +1074,7 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 	if (!qi->desc_status) {
 		free_page((unsigned long) qi->desc);
 		kfree(qi);
-		iommu->qi = 0;
+		iommu->qi = NULL;
 		return -ENOMEM;
 	}
 
@@ -1111,9 +1125,7 @@ static const char *irq_remap_fault_reasons[] =
 	"Blocked an interrupt request due to source-id verification failure",
 };
 
-#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)
-
-const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
+static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
 {
 	if (fault_reason >= 0x20 && (fault_reason - 0x20 <
 					ARRAY_SIZE(irq_remap_fault_reasons))) {
@@ -1303,15 +1315,14 @@ int dmar_set_interrupt(struct intel_iommu *iommu)
 int __init enable_drhd_fault_handling(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 
 	/*
 	 * Enable fault control interrupt.
 	 */
-	for_each_drhd_unit(drhd) {
-		int ret;
-		struct intel_iommu *iommu = drhd->iommu;
+	for_each_iommu(iommu, drhd) {
 		u32 fault_status;
-		ret = dmar_set_interrupt(iommu);
+		int ret = dmar_set_interrupt(iommu);
 
 		if (ret) {
 			pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n",
@@ -1366,4 +1377,22 @@ int __init dmar_ir_support(void)
 		return 0;
 	return dmar->flags & 0x1;
 }
+
+static int __init dmar_free_unused_resources(void)
+{
+	struct dmar_drhd_unit *dmaru, *dmaru_n;
+
+	/* DMAR units are in use */
+	if (irq_remapping_enabled || intel_iommu_enabled)
+		return 0;
+
+	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
+		list_del(&dmaru->list);
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+late_initcall(dmar_free_unused_resources);
 IOMMU_INIT_POST(detect_intel_iommu);
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index c857c30da979..93072ba44b1d 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -691,7 +691,7 @@ static int fsl_pamu_attach_device(struct iommu_domain *domain,
 	 * Use LIODN of the PCI controller while attaching a
 	 * PCI device.
 	 */
-	if (dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev)) {
 		pdev = to_pci_dev(dev);
 		pci_ctl = pci_bus_to_host(pdev->bus);
 		/*
@@ -729,7 +729,7 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain,
 	 * Use LIODN of the PCI controller while detaching a
 	 * PCI device.
 	 */
-	if (dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev)) {
 		pdev = to_pci_dev(dev);
 		pci_ctl = pci_bus_to_host(pdev->bus);
 		/*
@@ -1056,7 +1056,7 @@ static int fsl_pamu_add_device(struct device *dev)
 	 * For platform devices we allocate a separate group for
 	 * each of the devices.
 	 */
-	if (dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev)) {
 		pdev = to_pci_dev(dev);
 		/* Don't create device groups for virtual PCI bridges */
 		if (pdev->subordinate)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 59779e19315e..a22c86c867fa 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -63,6 +63,7 @@
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
 
 #define MAX_AGAW_WIDTH 64
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
 
 #define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1)
 #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1)
@@ -106,12 +107,12 @@ static inline int agaw_to_level(int agaw)
 
 static inline int agaw_to_width(int agaw)
 {
-	return 30 + agaw * LEVEL_STRIDE;
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
 }
 
 static inline int width_to_agaw(int width)
 {
-	return (width - 30) / LEVEL_STRIDE;
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
 }
 
 static inline unsigned int level_to_offset_bits(int level)
@@ -141,7 +142,7 @@ static inline unsigned long align_to_level(unsigned long pfn, int level)
 
 static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 {
-	return  1 << ((lvl - 1) * LEVEL_STRIDE);
+	return  1 << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
 }
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
@@ -288,26 +289,6 @@ static inline void dma_clear_pte(struct dma_pte *pte)
 	pte->val = 0;
 }
 
-static inline void dma_set_pte_readable(struct dma_pte *pte)
-{
-	pte->val |= DMA_PTE_READ;
-}
-
-static inline void dma_set_pte_writable(struct dma_pte *pte)
-{
-	pte->val |= DMA_PTE_WRITE;
-}
-
-static inline void dma_set_pte_snp(struct dma_pte *pte)
-{
-	pte->val |= DMA_PTE_SNP;
-}
-
-static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot)
-{
-	pte->val = (pte->val & ~3) | (prot & 3);
-}
-
 static inline u64 dma_pte_addr(struct dma_pte *pte)
 {
 #ifdef CONFIG_64BIT
@@ -318,11 +299,6 @@ static inline u64 dma_pte_addr(struct dma_pte *pte)
 #endif
 }
 
-static inline void dma_set_pte_pfn(struct dma_pte *pte, unsigned long pfn)
-{
-	pte->val |= (uint64_t)pfn << VTD_PAGE_SHIFT;
-}
-
 static inline bool dma_pte_present(struct dma_pte *pte)
 {
 	return (pte->val & 3) != 0;
@@ -406,7 +382,7 @@ struct device_domain_info {
 
 static void flush_unmaps_timeout(unsigned long data);
 
-DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
+static DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
 
 #define HIGH_WATER_MARK 250
 struct deferred_flush_tables {
@@ -652,9 +628,7 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 	struct dmar_drhd_unit *drhd = NULL;
 	int i;
 
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
+	for_each_active_drhd_unit(drhd) {
 		if (segment != drhd->segment)
 			continue;
 
@@ -865,7 +839,6 @@ static int dma_pte_clear_range(struct dmar_domain *domain,
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	unsigned int large_page = 1;
 	struct dma_pte *first_pte, *pte;
-	int order;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
 	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
@@ -890,8 +863,7 @@ static int dma_pte_clear_range(struct dmar_domain *domain,
 
 	} while (start_pfn && start_pfn <= last_pfn);
 
-	order = (large_page - 1) * 9;
-	return order;
+	return min_t(int, (large_page - 1) * 9, MAX_AGAW_PFN_WIDTH);
 }
 
 static void dma_pte_free_level(struct dmar_domain *domain, int level,
@@ -1255,8 +1227,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	unsigned long nlongs;
 
 	ndomains = cap_ndoms(iommu->cap);
-	pr_debug("IOMMU %d: Number of Domains supported <%ld>\n", iommu->seq_id,
-			ndomains);
+	pr_debug("IOMMU%d: Number of Domains supported <%ld>\n",
+		 iommu->seq_id, ndomains);
 	nlongs = BITS_TO_LONGS(ndomains);
 
 	spin_lock_init(&iommu->lock);
@@ -1266,13 +1238,17 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	 */
 	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
 	if (!iommu->domain_ids) {
-		printk(KERN_ERR "Allocating domain id array failed\n");
+		pr_err("IOMMU%d: allocating domain id array failed\n",
+		       iommu->seq_id);
 		return -ENOMEM;
 	}
 	iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *),
 			GFP_KERNEL);
 	if (!iommu->domains) {
-		printk(KERN_ERR "Allocating domain array failed\n");
+		pr_err("IOMMU%d: allocating domain array failed\n",
+		       iommu->seq_id);
+		kfree(iommu->domain_ids);
+		iommu->domain_ids = NULL;
 		return -ENOMEM;
 	}
 
@@ -1289,10 +1265,10 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 static void domain_exit(struct dmar_domain *domain);
 static void vm_domain_exit(struct dmar_domain *domain);
 
-void free_dmar_iommu(struct intel_iommu *iommu)
+static void free_dmar_iommu(struct intel_iommu *iommu)
 {
 	struct dmar_domain *domain;
-	int i;
+	int i, count;
 	unsigned long flags;
 
 	if ((iommu->domains) && (iommu->domain_ids)) {
@@ -1301,28 +1277,24 @@ void free_dmar_iommu(struct intel_iommu *iommu)
 			clear_bit(i, iommu->domain_ids);
 
 			spin_lock_irqsave(&domain->iommu_lock, flags);
-			if (--domain->iommu_count == 0) {
+			count = --domain->iommu_count;
+			spin_unlock_irqrestore(&domain->iommu_lock, flags);
+			if (count == 0) {
 				if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE)
 					vm_domain_exit(domain);
 				else
 					domain_exit(domain);
 			}
-			spin_unlock_irqrestore(&domain->iommu_lock, flags);
 		}
 	}
 
 	if (iommu->gcmd & DMA_GCMD_TE)
 		iommu_disable_translation(iommu);
 
-	if (iommu->irq) {
-		irq_set_handler_data(iommu->irq, NULL);
-		/* This will mask the irq */
-		free_irq(iommu->irq, iommu);
-		destroy_irq(iommu->irq);
-	}
-
 	kfree(iommu->domains);
 	kfree(iommu->domain_ids);
+	iommu->domains = NULL;
+	iommu->domain_ids = NULL;
 
 	g_iommus[iommu->seq_id] = NULL;
 
@@ -2245,8 +2217,6 @@ static int __init si_domain_init(int hw)
 	if (!si_domain)
 		return -EFAULT;
 
-	pr_debug("Identity mapping domain is domain %d\n", si_domain->id);
-
 	for_each_active_iommu(iommu, drhd) {
 		ret = iommu_attach_domain(si_domain, iommu);
 		if (ret) {
@@ -2261,6 +2231,8 @@ static int __init si_domain_init(int hw)
 	}
 
 	si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY;
+	pr_debug("IOMMU: identity mapping domain is domain %d\n",
+		 si_domain->id);
 
 	if (hw)
 		return 0;
@@ -2492,11 +2464,7 @@ static int __init init_dmars(void)
 		goto error;
 	}
 
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
-
-		iommu = drhd->iommu;
+	for_each_active_iommu(iommu, drhd) {
 		g_iommus[iommu->seq_id] = iommu;
 
 		ret = iommu_init_domains(iommu);
@@ -2520,12 +2488,7 @@ static int __init init_dmars(void)
 	/*
 	 * Start from the sane iommu hardware state.
 	 */
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
-
-		iommu = drhd->iommu;
-
+	for_each_active_iommu(iommu, drhd) {
 		/*
 		 * If the queued invalidation is already initialized by us
 		 * (for example, while enabling interrupt-remapping) then
@@ -2545,12 +2508,7 @@ static int __init init_dmars(void)
 		dmar_disable_qi(iommu);
 	}
 
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
-
-		iommu = drhd->iommu;
-
+	for_each_active_iommu(iommu, drhd) {
 		if (dmar_enable_qi(iommu)) {
 			/*
 			 * Queued Invalidate not enabled, use Register Based
@@ -2633,17 +2591,16 @@ static int __init init_dmars(void)
 	 *   global invalidate iotlb
 	 *   enable translation
 	 */
-	for_each_drhd_unit(drhd) {
+	for_each_iommu(iommu, drhd) {
 		if (drhd->ignored) {
 			/*
 			 * we always have to disable PMRs or DMA may fail on
 			 * this device
 			 */
 			if (force_on)
-				iommu_disable_protect_mem_regions(drhd->iommu);
+				iommu_disable_protect_mem_regions(iommu);
 			continue;
 		}
-		iommu = drhd->iommu;
 
 		iommu_flush_write_buffer(iommu);
 
@@ -2665,12 +2622,9 @@ static int __init init_dmars(void)
 
 	return 0;
 error:
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
-		iommu = drhd->iommu;
-		free_iommu(iommu);
-	}
+	for_each_active_iommu(iommu, drhd)
+		free_dmar_iommu(iommu);
+	kfree(deferred_flush);
 	kfree(g_iommus);
 	return ret;
 }
@@ -2758,7 +2712,7 @@ static int iommu_no_mapping(struct device *dev)
 	struct pci_dev *pdev;
 	int found;
 
-	if (unlikely(dev->bus != &pci_bus_type))
+	if (unlikely(!dev_is_pci(dev)))
 		return 1;
 
 	pdev = to_pci_dev(dev);
@@ -3318,9 +3272,9 @@ static void __init init_no_remapping_devices(void)
 		}
 	}
 
-	for_each_drhd_unit(drhd) {
+	for_each_active_drhd_unit(drhd) {
 		int i;
-		if (drhd->ignored || drhd->include_all)
+		if (drhd->include_all)
 			continue;
 
 		for (i = 0; i < drhd->devices_cnt; i++)
@@ -3514,18 +3468,12 @@ static int __init
 rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
-	int ret;
 
 	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
-	ret = dmar_parse_dev_scope((void *)(rmrr + 1),
-		((void *)rmrr) + rmrr->header.length,
-		&rmrru->devices_cnt, &rmrru->devices, rmrr->segment);
-
-	if (ret || (rmrru->devices_cnt == 0)) {
-		list_del(&rmrru->list);
-		kfree(rmrru);
-	}
-	return ret;
+	return dmar_parse_dev_scope((void *)(rmrr + 1),
+				    ((void *)rmrr) + rmrr->header.length,
+				    &rmrru->devices_cnt, &rmrru->devices,
+				    rmrr->segment);
 }
 
 static LIST_HEAD(dmar_atsr_units);
@@ -3550,23 +3498,39 @@ int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 
 static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
 {
-	int rc;
 	struct acpi_dmar_atsr *atsr;
 
 	if (atsru->include_all)
 		return 0;
 
 	atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
-	rc = dmar_parse_dev_scope((void *)(atsr + 1),
-				(void *)atsr + atsr->header.length,
-				&atsru->devices_cnt, &atsru->devices,
-				atsr->segment);
-	if (rc || !atsru->devices_cnt) {
-		list_del(&atsru->list);
-		kfree(atsru);
+	return dmar_parse_dev_scope((void *)(atsr + 1),
+				    (void *)atsr + atsr->header.length,
+				    &atsru->devices_cnt, &atsru->devices,
+				    atsr->segment);
+}
+
+static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
+{
+	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
+	kfree(atsru);
+}
+
+static void intel_iommu_free_dmars(void)
+{
+	struct dmar_rmrr_unit *rmrru, *rmrr_n;
+	struct dmar_atsr_unit *atsru, *atsr_n;
+
+	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
+		list_del(&rmrru->list);
+		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
+		kfree(rmrru);
 	}
 
-	return rc;
+	list_for_each_entry_safe(atsru, atsr_n, &dmar_atsr_units, list) {
+		list_del(&atsru->list);
+		intel_iommu_free_atsr(atsru);
+	}
 }
 
 int dmar_find_matched_atsr_unit(struct pci_dev *dev)
@@ -3610,17 +3574,17 @@ found:
 
 int __init dmar_parse_rmrr_atsr_dev(void)
 {
-	struct dmar_rmrr_unit *rmrr, *rmrr_n;
-	struct dmar_atsr_unit *atsr, *atsr_n;
+	struct dmar_rmrr_unit *rmrr;
+	struct dmar_atsr_unit *atsr;
 	int ret = 0;
 
-	list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
+	list_for_each_entry(rmrr, &dmar_rmrr_units, list) {
 		ret = rmrr_parse_dev(rmrr);
 		if (ret)
 			return ret;
 	}
 
-	list_for_each_entry_safe(atsr, atsr_n, &dmar_atsr_units, list) {
+	list_for_each_entry(atsr, &dmar_atsr_units, list) {
 		ret = atsr_parse_dev(atsr);
 		if (ret)
 			return ret;
@@ -3667,8 +3631,9 @@ static struct notifier_block device_nb = {
 
 int __init intel_iommu_init(void)
 {
-	int ret = 0;
+	int ret = -ENODEV;
 	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
@@ -3676,36 +3641,29 @@ int __init intel_iommu_init(void)
 	if (dmar_table_init()) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR table\n");
-		return 	-ENODEV;
+		goto out_free_dmar;
 	}
 
 	/*
 	 * Disable translation if already enabled prior to OS handover.
 	 */
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu;
-
-		if (drhd->ignored)
-			continue;
-
-		iommu = drhd->iommu;
+	for_each_active_iommu(iommu, drhd)
 		if (iommu->gcmd & DMA_GCMD_TE)
 			iommu_disable_translation(iommu);
-	}
 
 	if (dmar_dev_scope_init() < 0) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR device scope\n");
-		return 	-ENODEV;
+		goto out_free_dmar;
 	}
 
 	if (no_iommu || dmar_disabled)
-		return -ENODEV;
+		goto out_free_dmar;
 
 	if (iommu_init_mempool()) {
 		if (force_on)
 			panic("tboot: Failed to initialize iommu memory\n");
-		return 	-ENODEV;
+		goto out_free_dmar;
 	}
 
 	if (list_empty(&dmar_rmrr_units))
@@ -3717,7 +3675,7 @@ int __init intel_iommu_init(void)
 	if (dmar_init_reserved_ranges()) {
 		if (force_on)
 			panic("tboot: Failed to reserve iommu ranges\n");
-		return 	-ENODEV;
+		goto out_free_mempool;
 	}
 
 	init_no_remapping_devices();
@@ -3727,9 +3685,7 @@ int __init intel_iommu_init(void)
 		if (force_on)
 			panic("tboot: Failed to initialize DMARs\n");
 		printk(KERN_ERR "IOMMU: dmar init failed\n");
-		put_iova_domain(&reserved_iova_list);
-		iommu_exit_mempool();
-		return ret;
+		goto out_free_reserved_range;
 	}
 	printk(KERN_INFO
 	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
@@ -3749,6 +3705,14 @@ int __init intel_iommu_init(void)
 	intel_iommu_enabled = 1;
 
 	return 0;
+
+out_free_reserved_range:
+	put_iova_domain(&reserved_iova_list);
+out_free_mempool:
+	iommu_exit_mempool();
+out_free_dmar:
+	intel_iommu_free_dmars();
+	return ret;
 }
 
 static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
@@ -3877,7 +3841,7 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 }
 
 /* domain id for virtual machine, it won't be set in context */
-static unsigned long vm_domid;
+static atomic_t vm_domid = ATOMIC_INIT(0);
 
 static struct dmar_domain *iommu_alloc_vm_domain(void)
 {
@@ -3887,7 +3851,7 @@ static struct dmar_domain *iommu_alloc_vm_domain(void)
 	if (!domain)
 		return NULL;
 
-	domain->id = vm_domid++;
+	domain->id = atomic_inc_return(&vm_domid);
 	domain->nid = -1;
 	memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp));
 	domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
@@ -3934,11 +3898,7 @@ static void iommu_free_vm_domain(struct dmar_domain *domain)
 	unsigned long i;
 	unsigned long ndomains;
 
-	for_each_drhd_unit(drhd) {
-		if (drhd->ignored)
-			continue;
-		iommu = drhd->iommu;
-
+	for_each_active_iommu(iommu, drhd) {
 		ndomains = cap_ndoms(iommu->cap);
 		for_each_set_bit(i, iommu->domain_ids, ndomains) {
 			if (iommu->domains[i] == domain) {
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 0cb7528b30a1..ef5f65dbafe9 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -40,13 +40,15 @@ static int ir_ioapic_num, ir_hpet_num;
 
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
 
+static int __init parse_ioapics_under_ir(void);
+
 static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
 	struct irq_cfg *cfg = irq_get_chip_data(irq);
 	return cfg ? &cfg->irq_2_iommu : NULL;
 }
 
-int get_irte(int irq, struct irte *entry)
+static int get_irte(int irq, struct irte *entry)
 {
 	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
@@ -69,19 +71,13 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	struct ir_table *table = iommu->ir_table;
 	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct irq_cfg *cfg = irq_get_chip_data(irq);
-	u16 index, start_index;
 	unsigned int mask = 0;
 	unsigned long flags;
-	int i;
+	int index;
 
 	if (!count || !irq_iommu)
 		return -1;
 
-	/*
-	 * start the IRTE search from index 0.
-	 */
-	index = start_index = 0;
-
 	if (count > 1) {
 		count = __roundup_pow_of_two(count);
 		mask = ilog2(count);
@@ -96,32 +92,17 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	}
 
 	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-	do {
-		for (i = index; i < index + count; i++)
-			if  (table->base[i].present)
-				break;
-		/* empty index found */
-		if (i == index + count)
-			break;
-
-		index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
-
-		if (index == start_index) {
-			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-			printk(KERN_ERR "can't allocate an IRTE\n");
-			return -1;
-		}
-	} while (1);
-
-	for (i = index; i < index + count; i++)
-		table->base[i].present = 1;
-
-	cfg->remapped = 1;
-	irq_iommu->iommu = iommu;
-	irq_iommu->irte_index =  index;
-	irq_iommu->sub_handle = 0;
-	irq_iommu->irte_mask = mask;
-
+	index = bitmap_find_free_region(table->bitmap,
+					INTR_REMAP_TABLE_ENTRIES, mask);
+	if (index < 0) {
+		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
+	} else {
+		cfg->remapped = 1;
+		irq_iommu->iommu = iommu;
+		irq_iommu->irte_index =  index;
+		irq_iommu->sub_handle = 0;
+		irq_iommu->irte_mask = mask;
+	}
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return index;
@@ -254,6 +235,8 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 		set_64bit(&entry->low, 0);
 		set_64bit(&entry->high, 0);
 	}
+	bitmap_release_region(iommu->ir_table->bitmap, index,
+			      irq_iommu->irte_mask);
 
 	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 }
@@ -336,7 +319,7 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 		return -1;
 	}
 
-	set_irte_sid(irte, 1, 0, sid);
+	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, sid);
 
 	return 0;
 }
@@ -453,6 +436,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu, int mode)
 {
 	struct ir_table *ir_table;
 	struct page *pages;
+	unsigned long *bitmap;
 
 	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
 					     GFP_ATOMIC);
@@ -464,13 +448,23 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu, int mode)
 				 INTR_REMAP_PAGE_ORDER);
 
 	if (!pages) {
-		printk(KERN_ERR "failed to allocate pages of order %d\n",
-		       INTR_REMAP_PAGE_ORDER);
+		pr_err("IR%d: failed to allocate pages of order %d\n",
+		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
 		kfree(iommu->ir_table);
 		return -ENOMEM;
 	}
 
+	bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES),
+			 sizeof(long), GFP_ATOMIC);
+	if (bitmap == NULL) {
+		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
+		__free_pages(pages, INTR_REMAP_PAGE_ORDER);
+		kfree(ir_table);
+		return -ENOMEM;
+	}
+
 	ir_table->base = page_address(pages);
+	ir_table->bitmap = bitmap;
 
 	iommu_set_irq_remapping(iommu, mode);
 	return 0;
@@ -521,6 +515,7 @@ static int __init dmar_x2apic_optout(void)
 static int __init intel_irq_remapping_supported(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 
 	if (disable_irq_remap)
 		return 0;
@@ -539,12 +534,9 @@ static int __init intel_irq_remapping_supported(void)
 	if (!dmar_ir_support())
 		return 0;
 
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu = drhd->iommu;
-
+	for_each_iommu(iommu, drhd)
 		if (!ecap_ir_support(iommu->ecap))
 			return 0;
-	}
 
 	return 1;
 }
@@ -552,6 +544,7 @@ static int __init intel_irq_remapping_supported(void)
 static int __init intel_enable_irq_remapping(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 	bool x2apic_present;
 	int setup = 0;
 	int eim = 0;
@@ -564,6 +557,8 @@ static int __init intel_enable_irq_remapping(void)
 	}
 
 	if (x2apic_present) {
+		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
+
 		eim = !dmar_x2apic_optout();
 		if (!eim)
 			printk(KERN_WARNING
@@ -572,9 +567,7 @@ static int __init intel_enable_irq_remapping(void)
 				"Use 'intremap=no_x2apic_optout' to override BIOS request.\n");
 	}
 
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu = drhd->iommu;
-
+	for_each_iommu(iommu, drhd) {
 		/*
 		 * If the queued invalidation is already initialized,
 		 * shouldn't disable it.
@@ -599,9 +592,7 @@ static int __init intel_enable_irq_remapping(void)
 	/*
 	 * check for the Interrupt-remapping support
 	 */
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu = drhd->iommu;
-
+	for_each_iommu(iommu, drhd) {
 		if (!ecap_ir_support(iommu->ecap))
 			continue;
 
@@ -615,10 +606,8 @@ static int __init intel_enable_irq_remapping(void)
 	/*
 	 * Enable queued invalidation for all the DRHD's.
 	 */
-	for_each_drhd_unit(drhd) {
-		int ret;
-		struct intel_iommu *iommu = drhd->iommu;
-		ret = dmar_enable_qi(iommu);
+	for_each_iommu(iommu, drhd) {
+		int ret = dmar_enable_qi(iommu);
 
 		if (ret) {
 			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
@@ -631,9 +620,7 @@ static int __init intel_enable_irq_remapping(void)
 	/*
 	 * Setup Interrupt-remapping for all the DRHD's now.
 	 */
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu = drhd->iommu;
-
+	for_each_iommu(iommu, drhd) {
 		if (!ecap_ir_support(iommu->ecap))
 			continue;
 
@@ -774,22 +761,20 @@ static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
  * Finds the assocaition between IOAPIC's and its Interrupt-remapping
  * hardware unit.
  */
-int __init parse_ioapics_under_ir(void)
+static int __init parse_ioapics_under_ir(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 	int ir_supported = 0;
 	int ioapic_idx;
 
-	for_each_drhd_unit(drhd) {
-		struct intel_iommu *iommu = drhd->iommu;
-
+	for_each_iommu(iommu, drhd)
 		if (ecap_ir_support(iommu->ecap)) {
 			if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
 				return -1;
 
 			ir_supported = 1;
 		}
-	}
 
 	if (!ir_supported)
 		return 0;
@@ -807,7 +792,7 @@ int __init parse_ioapics_under_ir(void)
 	return 1;
 }
 
-int __init ir_dev_scope_init(void)
+static int __init ir_dev_scope_init(void)
 {
 	if (!irq_remapping_enabled)
 		return 0;
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 39f81aeefcd6..228632c99adb 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -150,7 +150,7 @@ static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
 		return do_setup_msix_irqs(dev, nvec);
 }
 
-void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
+static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
 {
 	/*
 	 * Intr-remapping uses pin number as the virtual vector
@@ -295,8 +295,8 @@ int setup_ioapic_remapped_entry(int irq,
 					     vector, attr);
 }
 
-int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask,
-			      bool force)
+static int set_remapped_irq_affinity(struct irq_data *data,
+				     const struct cpumask *mask, bool force)
 {
 	if (!config_enabled(CONFIG_SMP) || !remap_ops ||
 	    !remap_ops->set_affinity)
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index ee249bc959f8..e550ccb7634e 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -20,6 +20,7 @@
 #include <linux/export.h>
 #include <linux/limits.h>
 #include <linux/of.h>
+#include <linux/of_iommu.h>
 
 /**
  * of_get_dma_window - Parse *dma-window property and returns 0 if found.
diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c
index d572863dfccd..7a3b928fad1c 100644
--- a/drivers/iommu/shmobile-iommu.c
+++ b/drivers/iommu/shmobile-iommu.c
@@ -380,14 +380,13 @@ int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu)
 		kmem_cache_destroy(l1cache);
 		return -ENOMEM;
 	}
-	archdata = kmalloc(sizeof(*archdata), GFP_KERNEL);
+	archdata = kzalloc(sizeof(*archdata), GFP_KERNEL);
 	if (!archdata) {
 		kmem_cache_destroy(l1cache);
 		kmem_cache_destroy(l2cache);
 		return -ENOMEM;
 	}
 	spin_lock_init(&archdata->attach_lock);
-	archdata->attached = NULL;
 	archdata->ipmmu = ipmmu;
 	ipmmu_archdata = archdata;
 	bus_set_iommu(&platform_bus_type, &shmobile_iommu_ops);
diff --git a/drivers/iommu/shmobile-ipmmu.c b/drivers/iommu/shmobile-ipmmu.c
index 8321f89596c4..e3bc2e19b6dd 100644
--- a/drivers/iommu/shmobile-ipmmu.c
+++ b/drivers/iommu/shmobile-ipmmu.c
@@ -35,12 +35,12 @@ void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu)
 	if (!ipmmu)
 		return;
 
-	mutex_lock(&ipmmu->flush_lock);
+	spin_lock(&ipmmu->flush_lock);
 	if (ipmmu->tlb_enabled)
 		ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH | IMCTR1_TLBEN);
 	else
 		ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH);
-	mutex_unlock(&ipmmu->flush_lock);
+	spin_unlock(&ipmmu->flush_lock);
 }
 
 void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size,
@@ -49,7 +49,7 @@ void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size,
 	if (!ipmmu)
 		return;
 
-	mutex_lock(&ipmmu->flush_lock);
+	spin_lock(&ipmmu->flush_lock);
 	switch (size) {
 	default:
 		ipmmu->tlb_enabled = 0;
@@ -85,7 +85,7 @@ void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size,
 	}
 	ipmmu_reg_write(ipmmu, IMTTBR, phys);
 	ipmmu_reg_write(ipmmu, IMASID, asid);
-	mutex_unlock(&ipmmu->flush_lock);
+	spin_unlock(&ipmmu->flush_lock);
 }
 
 static int ipmmu_probe(struct platform_device *pdev)
@@ -104,7 +104,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "cannot allocate device data\n");
 		return -ENOMEM;
 	}
-	mutex_init(&ipmmu->flush_lock);
+	spin_lock_init(&ipmmu->flush_lock);
 	ipmmu->dev = &pdev->dev;
 	ipmmu->ipmmu_base = devm_ioremap_nocache(&pdev->dev, res->start,
 						resource_size(res));
diff --git a/drivers/iommu/shmobile-ipmmu.h b/drivers/iommu/shmobile-ipmmu.h
index 4d53684673e1..9524743ca1fb 100644
--- a/drivers/iommu/shmobile-ipmmu.h
+++ b/drivers/iommu/shmobile-ipmmu.h
@@ -14,7 +14,7 @@ struct shmobile_ipmmu {
 	struct device *dev;
 	void __iomem *ipmmu_base;
 	int tlb_enabled;
-	struct mutex flush_lock;
+	spinlock_t flush_lock;
 	const char * const *dev_names;
 	unsigned int num_dev_names;
 };
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index 57c9a8ae4f2d..7ac17f57250e 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -27,7 +27,6 @@ struct root_entry;
 
 
 #ifdef CONFIG_INTEL_IOMMU
-extern void free_dmar_iommu(struct intel_iommu *iommu);
 extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
@@ -41,9 +40,6 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
 {
 	return 0;
 }
-static inline void free_dmar_iommu(struct intel_iommu *iommu)
-{
-}
 #define dmar_disabled	(1)
 #define intel_iommu_enabled (0)
 #endif
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index b029d1aa2d12..eccb0c0c6cf6 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -33,6 +33,7 @@ struct acpi_dmar_header;
 #define DMAR_X2APIC_OPT_OUT	0x2
 
 struct intel_iommu;
+
 #ifdef CONFIG_DMAR_TABLE
 extern struct acpi_table_header *dmar_tbl;
 struct dmar_drhd_unit {
@@ -52,6 +53,10 @@ extern struct list_head dmar_drhd_units;
 #define for_each_drhd_unit(drhd) \
 	list_for_each_entry(drhd, &dmar_drhd_units, list)
 
+#define for_each_active_drhd_unit(drhd)					\
+	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+		if (drhd->ignored) {} else
+
 #define for_each_active_iommu(i, drhd)					\
 	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, drhd->ignored) {} else
@@ -62,13 +67,13 @@ extern struct list_head dmar_drhd_units;
 
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
+extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
+				struct pci_dev ***devices, u16 segment);
+extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
 
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
-
-extern int parse_ioapics_under_ir(void);
-extern int alloc_iommu(struct dmar_drhd_unit *);
 #else
 static inline int detect_intel_iommu(void)
 {
@@ -157,8 +162,6 @@ struct dmar_atsr_unit {
 int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
-extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment);
 extern int intel_iommu_init(void);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d380c5e68008..2c4bed593b32 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -288,6 +288,7 @@ struct q_inval {
 
 struct ir_table {
 	struct irte *base;
+	unsigned long *bitmap;
 };
 #endif
 
@@ -347,8 +348,6 @@ static inline void __iommu_flush_cache(
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
 
-extern int alloc_iommu(struct dmar_drhd_unit *drhd);
-extern void free_iommu(struct intel_iommu *iommu);
 extern int dmar_enable_qi(struct intel_iommu *iommu);
 extern void dmar_disable_qi(struct intel_iommu *iommu);
 extern int dmar_reenable_qi(struct intel_iommu *iommu);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index a444c790fa72..b96a5b2136e4 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -24,9 +24,10 @@
 #include <linux/types.h>
 #include <trace/events/iommu.h>
 
-#define IOMMU_READ	(1)
-#define IOMMU_WRITE	(2)
-#define IOMMU_CACHE	(4) /* DMA cache coherency */
+#define IOMMU_READ	(1 << 0)
+#define IOMMU_WRITE	(1 << 1)
+#define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
+#define IOMMU_EXEC	(1 << 3)
 
 struct iommu_ops;
 struct iommu_group;
@@ -247,6 +248,11 @@ static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
 	return NULL;
 }
 
+static inline struct iommu_group *iommu_group_get_by_id(int id)
+{
+	return NULL;
+}
+
 static inline void iommu_domain_free(struct iommu_domain *domain)
 {
 }
@@ -291,8 +297,8 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad
 	return 0;
 }
 
-static inline int domain_has_cap(struct iommu_domain *domain,
-				 unsigned long cap)
+static inline int iommu_domain_has_cap(struct iommu_domain *domain,
+				       unsigned long cap)
 {
 	return 0;
 }