Merge tag 'v5.5-rc1' into core/kprobes, to resolve conflicts

Signed-off-by: Ingo Molnar <mingo@kernel.org>

30 files changed, 1204 insertions, 1195 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index e3842eabcfdd..0b9d78a0f3ac 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -3,6 +3,10 @@
 config IOMMU_IOVA
 	tristate
 
+# The IOASID library may also be used by non-IOMMU_API users
+config IOASID
+	tristate
+
 # IOMMU_API always gets selected by whoever wants it.
 config IOMMU_API
 	bool
@@ -138,6 +142,7 @@ config AMD_IOMMU
 	select PCI_PASID
 	select IOMMU_API
 	select IOMMU_IOVA
+	select IOMMU_DMA
 	depends on X86_64 && PCI && ACPI
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in
@@ -207,6 +212,7 @@ config INTEL_IOMMU_SVM
 	bool "Support for Shared Virtual Memory with Intel IOMMU"
 	depends on INTEL_IOMMU && X86
 	select PCI_PASID
+	select PCI_PRI
 	select MMU_NOTIFIER
 	help
 	  Shared Virtual Memory (SVM) provides a facility for devices
@@ -467,7 +473,7 @@ config QCOM_IOMMU
 
 config HYPERV_IOMMU
 	bool "Hyper-V x2APIC IRQ Handling"
-	depends on HYPERV
+	depends on HYPERV && X86
 	select IOMMU_API
 	default HYPERV
 	help
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 4f405f926e73..97814cc861ea 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -7,13 +7,14 @@ obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOASID) += ioasid.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index dd555078258c..bd25674ee4db 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -20,6 +20,7 @@
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
 #include <linux/iommu.h>
 #include <linux/delay.h>
@@ -88,8 +89,6 @@ const struct iommu_ops amd_iommu_ops;
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
 int amd_iommu_max_glx_val = -1;
 
-static const struct dma_map_ops amd_iommu_dma_ops;
-
 /*
  * general struct to manage commands send to an IOMMU
  */
@@ -102,21 +101,6 @@ struct kmem_cache *amd_iommu_irq_cache;
 static void update_domain(struct protection_domain *domain);
 static int protection_domain_init(struct protection_domain *domain);
 static void detach_device(struct device *dev);
-static void iova_domain_flush_tlb(struct iova_domain *iovad);
-
-/*
- * Data container for a dma_ops specific protection domain
- */
-struct dma_ops_domain {
-	/* generic protection domain information */
-	struct protection_domain domain;
-
-	/* IOVA RB-Tree */
-	struct iova_domain iovad;
-};
-
-static struct iova_domain reserved_iova_ranges;
-static struct lock_class_key reserved_rbtree_key;
 
 /****************************************************************************
  *
@@ -124,30 +108,6 @@ static struct lock_class_key reserved_rbtree_key;
  *
  ****************************************************************************/
 
-static inline int match_hid_uid(struct device *dev,
-				struct acpihid_map_entry *entry)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const char *hid, *uid;
-
-	if (!adev)
-		return -ENODEV;
-
-	hid = acpi_device_hid(adev);
-	uid = acpi_device_uid(adev);
-
-	if (!hid || !(*hid))
-		return -ENODEV;
-
-	if (!uid || !(*uid))
-		return strcmp(hid, entry->hid);
-
-	if (!(*entry->uid))
-		return strcmp(hid, entry->hid);
-
-	return (strcmp(hid, entry->hid) || strcmp(uid, entry->uid));
-}
-
 static inline u16 get_pci_device_id(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -158,10 +118,14 @@ static inline u16 get_pci_device_id(struct device *dev)
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
+	struct acpi_device *adev = ACPI_COMPANION(dev);
 	struct acpihid_map_entry *p;
 
+	if (!adev)
+		return -ENODEV;
+
 	list_for_each_entry(p, &acpihid_map, list) {
-		if (!match_hid_uid(dev, p)) {
+		if (acpi_dev_hid_uid_match(adev, p->hid, p->uid)) {
 			if (entry)
 				*entry = p;
 			return p->devid;
@@ -187,12 +151,6 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom)
 	return container_of(dom, struct protection_domain, domain);
 }
 
-static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain)
-{
-	BUG_ON(domain->flags != PD_DMA_OPS_MASK);
-	return container_of(domain, struct dma_ops_domain, domain);
-}
-
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -226,71 +184,61 @@ static struct iommu_dev_data *search_dev_data(u16 devid)
 	return NULL;
 }
 
-static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
+static int clone_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
-	*(u16 *)data = alias;
-	return 0;
-}
-
-static u16 get_alias(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	u16 devid, ivrs_alias, pci_alias;
-
-	/* The callers make sure that get_device_id() does not fail here */
-	devid = get_device_id(dev);
+	u16 devid = pci_dev_id(pdev);
 
-	/* For ACPI HID devices, we simply return the devid as such */
-	if (!dev_is_pci(dev))
-		return devid;
+	if (devid == alias)
+		return 0;
 
-	ivrs_alias = amd_iommu_alias_table[devid];
+	amd_iommu_rlookup_table[alias] =
+		amd_iommu_rlookup_table[devid];
+	memcpy(amd_iommu_dev_table[alias].data,
+	       amd_iommu_dev_table[devid].data,
+	       sizeof(amd_iommu_dev_table[alias].data));
 
-	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
+	return 0;
+}
 
-	if (ivrs_alias == pci_alias)
-		return ivrs_alias;
+static void clone_aliases(struct pci_dev *pdev)
+{
+	if (!pdev)
+		return;
 
 	/*
-	 * DMA alias showdown
-	 *
-	 * The IVRS is fairly reliable in telling us about aliases, but it
-	 * can't know about every screwy device.  If we don't have an IVRS
-	 * reported alias, use the PCI reported alias.  In that case we may
-	 * still need to initialize the rlookup and dev_table entries if the
-	 * alias is to a non-existent device.
+	 * The IVRS alias stored in the alias table may not be
+	 * part of the PCI DMA aliases if it's bus differs
+	 * from the original device.
 	 */
-	if (ivrs_alias == devid) {
-		if (!amd_iommu_rlookup_table[pci_alias]) {
-			amd_iommu_rlookup_table[pci_alias] =
-				amd_iommu_rlookup_table[devid];
-			memcpy(amd_iommu_dev_table[pci_alias].data,
-			       amd_iommu_dev_table[devid].data,
-			       sizeof(amd_iommu_dev_table[pci_alias].data));
-		}
+	clone_alias(pdev, amd_iommu_alias_table[pci_dev_id(pdev)], NULL);
 
-		return pci_alias;
-	}
+	pci_for_each_dma_alias(pdev, clone_alias, NULL);
+}
 
-	pci_info(pdev, "Using IVRS reported alias %02x:%02x.%d "
-		"for device [%04x:%04x], kernel reported alias "
-		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
-		PCI_FUNC(ivrs_alias), pdev->vendor, pdev->device,
-		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
-		PCI_FUNC(pci_alias));
+static struct pci_dev *setup_aliases(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 ivrs_alias;
+
+	/* For ACPI HID devices, there are no aliases */
+	if (!dev_is_pci(dev))
+		return NULL;
 
 	/*
-	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
-	 * bus, then the IVRS table may know about a quirk that we don't.
+	 * Add the IVRS alias to the pci aliases if it is on the same
+	 * bus. The IVRS table may know about a quirk that we don't.
 	 */
-	if (pci_alias == devid &&
+	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
+	if (ivrs_alias != pci_dev_id(pdev) &&
 	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
 		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
 		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
 			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
 	}
 
-	return ivrs_alias;
+	clone_aliases(pdev);
+
+	return pdev;
 }
 
 static struct iommu_dev_data *find_dev_data(u16 devid)
@@ -428,7 +376,7 @@ static int iommu_init_device(struct device *dev)
 	if (!dev_data)
 		return -ENOMEM;
 
-	dev_data->alias = get_alias(dev);
+	dev_data->pdev = setup_aliases(dev);
 
 	/*
 	 * By default we use passthrough mode for IOMMUv2 capable device.
@@ -453,20 +401,16 @@ static int iommu_init_device(struct device *dev)
 
 static void iommu_ignore_device(struct device *dev)
 {
-	u16 alias;
 	int devid;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return;
 
-	alias = get_alias(dev);
-
+	amd_iommu_rlookup_table[devid] = NULL;
 	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
-	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
 
-	amd_iommu_rlookup_table[devid] = NULL;
-	amd_iommu_rlookup_table[alias] = NULL;
+	setup_aliases(dev);
 }
 
 static void iommu_uninit_device(struct device *dev)
@@ -640,8 +584,7 @@ retry:
 			pasid, address, flags);
 		break;
 	case EVENT_TYPE_INV_PPR_REQ:
-		pasid = ((event[0] >> 16) & 0xFFFF)
-			| ((event[1] << 6) & 0xF0000);
+		pasid = PPR_PASID(*((u64 *)__evt));
 		tag = event[1] & 0x03FF;
 		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
@@ -876,17 +819,18 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu,
 			       struct iommu_cmd *cmd)
 {
 	u8 *target;
-
-	target = iommu->cmd_buf + iommu->cmd_buf_tail;
-
-	iommu->cmd_buf_tail += sizeof(*cmd);
-	iommu->cmd_buf_tail %= CMD_BUFFER_SIZE;
+	u32 tail;
 
 	/* Copy command to buffer */
+	tail = iommu->cmd_buf_tail;
+	target = iommu->cmd_buf + tail;
 	memcpy(target, cmd, sizeof(*cmd));
 
+	tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
+	iommu->cmd_buf_tail = tail;
+
 	/* Tell the IOMMU about it */
-	writel(iommu->cmd_buf_tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 }
 
 static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
@@ -1236,6 +1180,13 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	return iommu_queue_command(iommu, &cmd);
 }
 
+static int device_flush_dte_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct amd_iommu *iommu = data;
+
+	return iommu_flush_dte(iommu, alias);
+}
+
 /*
  * Command send function for invalidating a device table entry
  */
@@ -1246,14 +1197,22 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 	int ret;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
-	ret = iommu_flush_dte(iommu, dev_data->devid);
-	if (!ret && alias != dev_data->devid)
-		ret = iommu_flush_dte(iommu, alias);
+	if (dev_data->pdev)
+		ret = pci_for_each_dma_alias(dev_data->pdev,
+					     device_flush_dte_alias, iommu);
+	else
+		ret = iommu_flush_dte(iommu, dev_data->devid);
 	if (ret)
 		return ret;
 
+	alias = amd_iommu_alias_table[dev_data->devid];
+	if (alias != dev_data->devid) {
+		ret = iommu_flush_dte(iommu, alias);
+		if (ret)
+			return ret;
+	}
+
 	if (dev_data->ats.enabled)
 		ret = device_flush_iotlb(dev_data, 0, ~0UL);
 
@@ -1302,12 +1261,6 @@ static void domain_flush_pages(struct protection_domain *domain,
 	__domain_flush_pages(domain, address, size, 0);
 }
 
-/* Flush the whole IO/TLB for a given protection domain */
-static void domain_flush_tlb(struct protection_domain *domain)
-{
-	__domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
-}
-
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
 static void domain_flush_tlb_pde(struct protection_domain *domain)
 {
@@ -1755,43 +1708,6 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 
 /****************************************************************************
  *
- * The next functions belong to the address allocator for the dma_ops
- * interface functions.
- *
- ****************************************************************************/
-
-
-static unsigned long dma_ops_alloc_iova(struct device *dev,
-					struct dma_ops_domain *dma_dom,
-					unsigned int pages, u64 dma_mask)
-{
-	unsigned long pfn = 0;
-
-	pages = __roundup_pow_of_two(pages);
-
-	if (dma_mask > DMA_BIT_MASK(32))
-		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-				      IOVA_PFN(DMA_BIT_MASK(32)), false);
-
-	if (!pfn)
-		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-				      IOVA_PFN(dma_mask), true);
-
-	return (pfn << PAGE_SHIFT);
-}
-
-static void dma_ops_free_iova(struct dma_ops_domain *dma_dom,
-			      unsigned long address,
-			      unsigned int pages)
-{
-	pages = __roundup_pow_of_two(pages);
-	address >>= PAGE_SHIFT;
-
-	free_iova_fast(&dma_dom->iovad, address, pages);
-}
-
-/****************************************************************************
- *
  * The next functions belong to the domain allocation. A domain is
  * allocated for every IOMMU as the default domain. If device isolation
  * is enabled, every device get its own domain. The most important thing
@@ -1866,42 +1782,23 @@ static void free_gcr3_table(struct protection_domain *domain)
 	free_page((unsigned long)domain->gcr3_tbl);
 }
 
-static void dma_ops_domain_flush_tlb(struct dma_ops_domain *dom)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dom->domain.lock, flags);
-	domain_flush_tlb(&dom->domain);
-	domain_flush_complete(&dom->domain);
-	spin_unlock_irqrestore(&dom->domain.lock, flags);
-}
-
-static void iova_domain_flush_tlb(struct iova_domain *iovad)
-{
-	struct dma_ops_domain *dom;
-
-	dom = container_of(iovad, struct dma_ops_domain, iovad);
-
-	dma_ops_domain_flush_tlb(dom);
-}
-
 /*
  * Free a domain, only used if something went wrong in the
  * allocation path and we need to free an already allocated page table
  */
-static void dma_ops_domain_free(struct dma_ops_domain *dom)
+static void dma_ops_domain_free(struct protection_domain *domain)
 {
-	if (!dom)
+	if (!domain)
 		return;
 
-	put_iova_domain(&dom->iovad);
+	iommu_put_dma_cookie(&domain->domain);
 
-	free_pagetable(&dom->domain);
+	free_pagetable(domain);
 
-	if (dom->domain.id)
-		domain_id_free(dom->domain.id);
+	if (domain->id)
+		domain_id_free(domain->id);
 
-	kfree(dom);
+	kfree(domain);
 }
 
 /*
@@ -1909,35 +1806,30 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
  * It also initializes the page table and the address allocator data
  * structures required for the dma_ops interface
  */
-static struct dma_ops_domain *dma_ops_domain_alloc(void)
+static struct protection_domain *dma_ops_domain_alloc(void)
 {
-	struct dma_ops_domain *dma_dom;
+	struct protection_domain *domain;
 
-	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
-	if (!dma_dom)
+	domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL);
+	if (!domain)
 		return NULL;
 
-	if (protection_domain_init(&dma_dom->domain))
-		goto free_dma_dom;
-
-	dma_dom->domain.mode = PAGE_MODE_3_LEVEL;
-	dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-	dma_dom->domain.flags = PD_DMA_OPS_MASK;
-	if (!dma_dom->domain.pt_root)
-		goto free_dma_dom;
-
-	init_iova_domain(&dma_dom->iovad, PAGE_SIZE, IOVA_START_PFN);
+	if (protection_domain_init(domain))
+		goto free_domain;
 
-	if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
-		goto free_dma_dom;
+	domain->mode = PAGE_MODE_3_LEVEL;
+	domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	domain->flags = PD_DMA_OPS_MASK;
+	if (!domain->pt_root)
+		goto free_domain;
 
-	/* Initialize reserved ranges */
-	copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad);
+	if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM)
+		goto free_domain;
 
-	return dma_dom;
+	return domain;
 
-free_dma_dom:
-	dma_ops_domain_free(dma_dom);
+free_domain:
+	dma_ops_domain_free(domain);
 
 	return NULL;
 }
@@ -2035,11 +1927,9 @@ static void do_attach(struct iommu_dev_data *dev_data,
 		      struct protection_domain *domain)
 {
 	struct amd_iommu *iommu;
-	u16 alias;
 	bool ats;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 	ats   = dev_data->ats.enabled;
 
 	/* Update data structures */
@@ -2052,8 +1942,7 @@ static void do_attach(struct iommu_dev_data *dev_data,
 
 	/* Update device table */
 	set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
-	if (alias != dev_data->devid)
-		set_dte_entry(alias, domain, ats, dev_data->iommu_v2);
+	clone_aliases(dev_data->pdev);
 
 	device_flush_dte(dev_data);
 }
@@ -2062,17 +1951,14 @@ static void do_detach(struct iommu_dev_data *dev_data)
 {
 	struct protection_domain *domain = dev_data->domain;
 	struct amd_iommu *iommu;
-	u16 alias;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
 	/* Update data structures */
 	dev_data->domain = NULL;
 	list_del(&dev_data->list);
 	clear_dte_entry(dev_data->devid);
-	if (alias != dev_data->devid)
-		clear_dte_entry(alias);
+	clone_aliases(dev_data->pdev);
 
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
@@ -2305,8 +2191,8 @@ static int amd_iommu_add_device(struct device *dev)
 	domain = iommu_get_domain_for_dev(dev);
 	if (domain->type == IOMMU_DOMAIN_IDENTITY)
 		dev_data->passthrough = true;
-	else
-		dev->dma_ops = &amd_iommu_dma_ops;
+	else if (domain->type == IOMMU_DOMAIN_DMA)
+		iommu_setup_dma_ops(dev, IOVA_START_PFN << PAGE_SHIFT, 0);
 
 out:
 	iommu_completion_wait(iommu);
@@ -2340,43 +2226,32 @@ static struct iommu_group *amd_iommu_device_group(struct device *dev)
 	return acpihid_device_group(dev);
 }
 
+static int amd_iommu_domain_get_attr(struct iommu_domain *domain,
+		enum iommu_attr attr, void *data)
+{
+	switch (domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		return -ENODEV;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			*(int *)data = !amd_iommu_unmap_flush;
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+}
+
 /*****************************************************************************
  *
  * The next functions belong to the dma_ops mapping/unmapping code.
  *
  *****************************************************************************/
 
-/*
- * In the dma_ops path we only have the struct device. This function
- * finds the corresponding IOMMU, the protection domain and the
- * requestor id for a given device.
- * If the device is not yet associated with a domain this is also done
- * in this function.
- */
-static struct protection_domain *get_domain(struct device *dev)
-{
-	struct protection_domain *domain;
-	struct iommu_domain *io_domain;
-
-	if (!check_device(dev))
-		return ERR_PTR(-EINVAL);
-
-	domain = get_dev_data(dev)->domain;
-	if (domain == NULL && get_dev_data(dev)->defer_attach) {
-		get_dev_data(dev)->defer_attach = false;
-		io_domain = iommu_get_domain_for_dev(dev);
-		domain = to_pdomain(io_domain);
-		attach_device(dev, domain);
-	}
-	if (domain == NULL)
-		return ERR_PTR(-EBUSY);
-
-	if (!dma_ops_domain(domain))
-		return ERR_PTR(-EBUSY);
-
-	return domain;
-}
-
 static void update_device_table(struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
@@ -2384,13 +2259,7 @@ static void update_device_table(struct protection_domain *domain)
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
 			      dev_data->iommu_v2);
-
-		if (dev_data->devid == dev_data->alias)
-			continue;
-
-		/* There is an alias, update device table entry for it */
-		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled,
-			      dev_data->iommu_v2);
+		clone_aliases(dev_data->pdev);
 	}
 }
 
@@ -2402,458 +2271,6 @@ static void update_domain(struct protection_domain *domain)
 	domain_flush_tlb_pde(domain);
 }
 
-static int dir2prot(enum dma_data_direction direction)
-{
-	if (direction == DMA_TO_DEVICE)
-		return IOMMU_PROT_IR;
-	else if (direction == DMA_FROM_DEVICE)
-		return IOMMU_PROT_IW;
-	else if (direction == DMA_BIDIRECTIONAL)
-		return IOMMU_PROT_IW | IOMMU_PROT_IR;
-	else
-		return 0;
-}
-
-/*
- * This function contains common code for mapping of a physically
- * contiguous memory region into DMA address space. It is used by all
- * mapping functions provided with this IOMMU driver.
- * Must be called with the domain lock held.
- */
-static dma_addr_t __map_single(struct device *dev,
-			       struct dma_ops_domain *dma_dom,
-			       phys_addr_t paddr,
-			       size_t size,
-			       enum dma_data_direction direction,
-			       u64 dma_mask)
-{
-	dma_addr_t offset = paddr & ~PAGE_MASK;
-	dma_addr_t address, start, ret;
-	unsigned long flags;
-	unsigned int pages;
-	int prot = 0;
-	int i;
-
-	pages = iommu_num_pages(paddr, size, PAGE_SIZE);
-	paddr &= PAGE_MASK;
-
-	address = dma_ops_alloc_iova(dev, dma_dom, pages, dma_mask);
-	if (!address)
-		goto out;
-
-	prot = dir2prot(direction);
-
-	start = address;
-	for (i = 0; i < pages; ++i) {
-		ret = iommu_map_page(&dma_dom->domain, start, paddr,
-				     PAGE_SIZE, prot, GFP_ATOMIC);
-		if (ret)
-			goto out_unmap;
-
-		paddr += PAGE_SIZE;
-		start += PAGE_SIZE;
-	}
-	address += offset;
-
-	domain_flush_np_cache(&dma_dom->domain, address, size);
-
-out:
-	return address;
-
-out_unmap:
-
-	for (--i; i >= 0; --i) {
-		start -= PAGE_SIZE;
-		iommu_unmap_page(&dma_dom->domain, start, PAGE_SIZE);
-	}
-
-	spin_lock_irqsave(&dma_dom->domain.lock, flags);
-	domain_flush_tlb(&dma_dom->domain);
-	domain_flush_complete(&dma_dom->domain);
-	spin_unlock_irqrestore(&dma_dom->domain.lock, flags);
-
-	dma_ops_free_iova(dma_dom, address, pages);
-
-	return DMA_MAPPING_ERROR;
-}
-
-/*
- * Does the reverse of the __map_single function. Must be called with
- * the domain lock held too
- */
-static void __unmap_single(struct dma_ops_domain *dma_dom,
-			   dma_addr_t dma_addr,
-			   size_t size,
-			   int dir)
-{
-	dma_addr_t i, start;
-	unsigned int pages;
-
-	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
-	dma_addr &= PAGE_MASK;
-	start = dma_addr;
-
-	for (i = 0; i < pages; ++i) {
-		iommu_unmap_page(&dma_dom->domain, start, PAGE_SIZE);
-		start += PAGE_SIZE;
-	}
-
-	if (amd_iommu_unmap_flush) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&dma_dom->domain.lock, flags);
-		domain_flush_tlb(&dma_dom->domain);
-		domain_flush_complete(&dma_dom->domain);
-		spin_unlock_irqrestore(&dma_dom->domain.lock, flags);
-		dma_ops_free_iova(dma_dom, dma_addr, pages);
-	} else {
-		pages = __roundup_pow_of_two(pages);
-		queue_iova(&dma_dom->iovad, dma_addr >> PAGE_SHIFT, pages, 0);
-	}
-}
-
-/*
- * The exported map_single function for dma_ops.
- */
-static dma_addr_t map_page(struct device *dev, struct page *page,
-			   unsigned long offset, size_t size,
-			   enum dma_data_direction dir,
-			   unsigned long attrs)
-{
-	phys_addr_t paddr = page_to_phys(page) + offset;
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	u64 dma_mask;
-
-	domain = get_domain(dev);
-	if (PTR_ERR(domain) == -EINVAL)
-		return (dma_addr_t)paddr;
-	else if (IS_ERR(domain))
-		return DMA_MAPPING_ERROR;
-
-	dma_mask = *dev->dma_mask;
-	dma_dom = to_dma_ops_domain(domain);
-
-	return __map_single(dev, dma_dom, paddr, size, dir, dma_mask);
-}
-
-/*
- * The exported unmap_single function for dma_ops.
- */
-static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
-		       enum dma_data_direction dir, unsigned long attrs)
-{
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		return;
-
-	dma_dom = to_dma_ops_domain(domain);
-
-	__unmap_single(dma_dom, dma_addr, size, dir);
-}
-
-static int sg_num_pages(struct device *dev,
-			struct scatterlist *sglist,
-			int nelems)
-{
-	unsigned long mask, boundary_size;
-	struct scatterlist *s;
-	int i, npages = 0;
-
-	mask          = dma_get_seg_boundary(dev);
-	boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
-				   1UL << (BITS_PER_LONG - PAGE_SHIFT);
-
-	for_each_sg(sglist, s, nelems, i) {
-		int p, n;
-
-		s->dma_address = npages << PAGE_SHIFT;
-		p = npages % boundary_size;
-		n = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
-		if (p + n > boundary_size)
-			npages += boundary_size - p;
-		npages += n;
-	}
-
-	return npages;
-}
-
-/*
- * The exported map_sg function for dma_ops (handles scatter-gather
- * lists).
- */
-static int map_sg(struct device *dev, struct scatterlist *sglist,
-		  int nelems, enum dma_data_direction direction,
-		  unsigned long attrs)
-{
-	int mapped_pages = 0, npages = 0, prot = 0, i;
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	struct scatterlist *s;
-	unsigned long address;
-	u64 dma_mask;
-	int ret;
-
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		return 0;
-
-	dma_dom  = to_dma_ops_domain(domain);
-	dma_mask = *dev->dma_mask;
-
-	npages = sg_num_pages(dev, sglist, nelems);
-
-	address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask);
-	if (!address)
-		goto out_err;
-
-	prot = dir2prot(direction);
-
-	/* Map all sg entries */
-	for_each_sg(sglist, s, nelems, i) {
-		int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
-
-		for (j = 0; j < pages; ++j) {
-			unsigned long bus_addr, phys_addr;
-
-			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
-			phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
-			ret = iommu_map_page(domain, bus_addr, phys_addr,
-					     PAGE_SIZE, prot,
-					     GFP_ATOMIC | __GFP_NOWARN);
-			if (ret)
-				goto out_unmap;
-
-			mapped_pages += 1;
-		}
-	}
-
-	/* Everything is mapped - write the right values into s->dma_address */
-	for_each_sg(sglist, s, nelems, i) {
-		/*
-		 * Add in the remaining piece of the scatter-gather offset that
-		 * was masked out when we were determining the physical address
-		 * via (sg_phys(s) & PAGE_MASK) earlier.
-		 */
-		s->dma_address += address + (s->offset & ~PAGE_MASK);
-		s->dma_length   = s->length;
-	}
-
-	if (s)
-		domain_flush_np_cache(domain, s->dma_address, s->dma_length);
-
-	return nelems;
-
-out_unmap:
-	dev_err(dev, "IOMMU mapping error in map_sg (io-pages: %d reason: %d)\n",
-		npages, ret);
-
-	for_each_sg(sglist, s, nelems, i) {
-		int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
-
-		for (j = 0; j < pages; ++j) {
-			unsigned long bus_addr;
-
-			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
-			iommu_unmap_page(domain, bus_addr, PAGE_SIZE);
-
-			if (--mapped_pages == 0)
-				goto out_free_iova;
-		}
-	}
-
-out_free_iova:
-	free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages);
-
-out_err:
-	return 0;
-}
-
-/*
- * The exported map_sg function for dma_ops (handles scatter-gather
- * lists).
- */
-static void unmap_sg(struct device *dev, struct scatterlist *sglist,
-		     int nelems, enum dma_data_direction dir,
-		     unsigned long attrs)
-{
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	unsigned long startaddr;
-	int npages;
-
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		return;
-
-	startaddr = sg_dma_address(sglist) & PAGE_MASK;
-	dma_dom   = to_dma_ops_domain(domain);
-	npages    = sg_num_pages(dev, sglist, nelems);
-
-	__unmap_single(dma_dom, startaddr, npages << PAGE_SHIFT, dir);
-}
-
-/*
- * The exported alloc_coherent function for dma_ops.
- */
-static void *alloc_coherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_addr, gfp_t flag,
-			    unsigned long attrs)
-{
-	u64 dma_mask = dev->coherent_dma_mask;
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	struct page *page;
-
-	domain = get_domain(dev);
-	if (PTR_ERR(domain) == -EINVAL) {
-		page = alloc_pages(flag, get_order(size));
-		*dma_addr = page_to_phys(page);
-		return page_address(page);
-	} else if (IS_ERR(domain))
-		return NULL;
-
-	dma_dom   = to_dma_ops_domain(domain);
-	size	  = PAGE_ALIGN(size);
-	dma_mask  = dev->coherent_dma_mask;
-	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-	flag     |= __GFP_ZERO;
-
-	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
-	if (!page) {
-		if (!gfpflags_allow_blocking(flag))
-			return NULL;
-
-		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
-					get_order(size), flag & __GFP_NOWARN);
-		if (!page)
-			return NULL;
-	}
-
-	if (!dma_mask)
-		dma_mask = *dev->dma_mask;
-
-	*dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
-				 size, DMA_BIDIRECTIONAL, dma_mask);
-
-	if (*dma_addr == DMA_MAPPING_ERROR)
-		goto out_free;
-
-	return page_address(page);
-
-out_free:
-
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
-
-	return NULL;
-}
-
-/*
- * The exported free_coherent function for dma_ops.
- */
-static void free_coherent(struct device *dev, size_t size,
-			  void *virt_addr, dma_addr_t dma_addr,
-			  unsigned long attrs)
-{
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	struct page *page;
-
-	page = virt_to_page(virt_addr);
-	size = PAGE_ALIGN(size);
-
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		goto free_mem;
-
-	dma_dom = to_dma_ops_domain(domain);
-
-	__unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
-
-free_mem:
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
-}
-
-/*
- * This function is called by the DMA layer to find out if we can handle a
- * particular device. It is part of the dma_ops.
- */
-static int amd_iommu_dma_supported(struct device *dev, u64 mask)
-{
-	if (!dma_direct_supported(dev, mask))
-		return 0;
-	return check_device(dev);
-}
-
-static const struct dma_map_ops amd_iommu_dma_ops = {
-	.alloc		= alloc_coherent,
-	.free		= free_coherent,
-	.map_page	= map_page,
-	.unmap_page	= unmap_page,
-	.map_sg		= map_sg,
-	.unmap_sg	= unmap_sg,
-	.dma_supported	= amd_iommu_dma_supported,
-	.mmap		= dma_common_mmap,
-	.get_sgtable	= dma_common_get_sgtable,
-};
-
-static int init_reserved_iova_ranges(void)
-{
-	struct pci_dev *pdev = NULL;
-	struct iova *val;
-
-	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE, IOVA_START_PFN);
-
-	lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
-			  &reserved_rbtree_key);
-
-	/* MSI memory range */
-	val = reserve_iova(&reserved_iova_ranges,
-			   IOVA_PFN(MSI_RANGE_START), IOVA_PFN(MSI_RANGE_END));
-	if (!val) {
-		pr_err("Reserving MSI range failed\n");
-		return -ENOMEM;
-	}
-
-	/* HT memory range */
-	val = reserve_iova(&reserved_iova_ranges,
-			   IOVA_PFN(HT_RANGE_START), IOVA_PFN(HT_RANGE_END));
-	if (!val) {
-		pr_err("Reserving HT range failed\n");
-		return -ENOMEM;
-	}
-
-	/*
-	 * Memory used for PCI resources
-	 * FIXME: Check whether we can reserve the PCI-hole completly
-	 */
-	for_each_pci_dev(pdev) {
-		int i;
-
-		for (i = 0; i < PCI_NUM_RESOURCES; ++i) {
-			struct resource *r = &pdev->resource[i];
-
-			if (!(r->flags & IORESOURCE_MEM))
-				continue;
-
-			val = reserve_iova(&reserved_iova_ranges,
-					   IOVA_PFN(r->start),
-					   IOVA_PFN(r->end));
-			if (!val) {
-				pci_err(pdev, "Reserve pci-resource range %pR failed\n", r);
-				return -ENOMEM;
-			}
-		}
-	}
-
-	return 0;
-}
-
 int __init amd_iommu_init_api(void)
 {
 	int ret, err = 0;
@@ -2862,10 +2279,6 @@ int __init amd_iommu_init_api(void)
 	if (ret)
 		return ret;
 
-	ret = init_reserved_iova_ranges();
-	if (ret)
-		return ret;
-
 	err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
 	if (err)
 		return err;
@@ -2936,7 +2349,6 @@ static void protection_domain_free(struct protection_domain *domain)
 static int protection_domain_init(struct protection_domain *domain)
 {
 	spin_lock_init(&domain->lock);
-	mutex_init(&domain->api_lock);
 	domain->id = domain_id_alloc();
 	if (!domain->id)
 		return -ENOMEM;
@@ -2967,7 +2379,6 @@ out_err:
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
-	struct dma_ops_domain *dma_domain;
 
 	switch (type) {
 	case IOMMU_DOMAIN_UNMANAGED:
@@ -2988,12 +2399,11 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 
 		break;
 	case IOMMU_DOMAIN_DMA:
-		dma_domain = dma_ops_domain_alloc();
-		if (!dma_domain) {
+		pdomain = dma_ops_domain_alloc();
+		if (!pdomain) {
 			pr_err("Failed to allocate\n");
 			return NULL;
 		}
-		pdomain = &dma_domain->domain;
 		break;
 	case IOMMU_DOMAIN_IDENTITY:
 		pdomain = protection_domain_alloc();
@@ -3012,7 +2422,6 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
 	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
 
 	domain = to_pdomain(dom);
 
@@ -3027,8 +2436,7 @@ static void amd_iommu_domain_free(struct iommu_domain *dom)
 	switch (dom->type) {
 	case IOMMU_DOMAIN_DMA:
 		/* Now release the domain */
-		dma_dom = to_dma_ops_domain(domain);
-		dma_ops_domain_free(dma_dom);
+		dma_ops_domain_free(domain);
 		break;
 	default:
 		if (domain->mode != PAGE_MODE_NONE)
@@ -3084,6 +2492,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 		return -EINVAL;
 
 	dev_data = dev->archdata.iommu;
+	dev_data->defer_attach = false;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
 	if (!iommu)
@@ -3109,7 +2518,8 @@ 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)
+			 phys_addr_t paddr, size_t page_size, int iommu_prot,
+			 gfp_t gfp)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	int prot = 0;
@@ -3123,9 +2533,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= IOMMU_PROT_IW;
 
-	mutex_lock(&domain->api_lock);
-	ret = iommu_map_page(domain, iova, paddr, page_size, prot, GFP_KERNEL);
-	mutex_unlock(&domain->api_lock);
+	ret = iommu_map_page(domain, iova, paddr, page_size, prot, gfp);
 
 	domain_flush_np_cache(domain, iova, page_size);
 
@@ -3137,16 +2545,11 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct protection_domain *domain = to_pdomain(dom);
-	size_t unmap_size;
 
 	if (domain->mode == PAGE_MODE_NONE)
 		return 0;
 
-	mutex_lock(&domain->api_lock);
-	unmap_size = iommu_unmap_page(domain, iova, page_size);
-	mutex_unlock(&domain->api_lock);
-
-	return unmap_size;
+	return iommu_unmap_page(domain, iova, page_size);
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
@@ -3247,19 +2650,6 @@ static void amd_iommu_put_resv_regions(struct device *dev,
 		kfree(entry);
 }
 
-static void amd_iommu_apply_resv_region(struct device *dev,
-				      struct iommu_domain *domain,
-				      struct iommu_resv_region *region)
-{
-	struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
-	unsigned long start, end;
-
-	start = IOVA_PFN(region->start);
-	end   = IOVA_PFN(region->start + region->length - 1);
-
-	WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
-}
-
 static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
 					 struct device *dev)
 {
@@ -3296,9 +2686,9 @@ const struct iommu_ops amd_iommu_ops = {
 	.add_device = amd_iommu_add_device,
 	.remove_device = amd_iommu_remove_device,
 	.device_group = amd_iommu_device_group,
+	.domain_get_attr = amd_iommu_domain_get_attr,
 	.get_resv_regions = amd_iommu_get_resv_regions,
 	.put_resv_regions = amd_iommu_put_resv_regions,
-	.apply_resv_region = amd_iommu_apply_resv_region,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
@@ -3610,9 +3000,23 @@ EXPORT_SYMBOL(amd_iommu_complete_ppr);
 struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev)
 {
 	struct protection_domain *pdomain;
+	struct iommu_domain *io_domain;
+	struct device *dev = &pdev->dev;
 
-	pdomain = get_domain(&pdev->dev);
-	if (IS_ERR(pdomain))
+	if (!check_device(dev))
+		return NULL;
+
+	pdomain = get_dev_data(dev)->domain;
+	if (pdomain == NULL && get_dev_data(dev)->defer_attach) {
+		get_dev_data(dev)->defer_attach = false;
+		io_domain = iommu_get_domain_for_dev(dev);
+		pdomain = to_pdomain(io_domain);
+		attach_device(dev, pdomain);
+	}
+	if (pdomain == NULL)
+		return NULL;
+
+	if (!dma_ops_domain(pdomain))
 		return NULL;
 
 	/* Only return IOMMUv2 domains */
@@ -3752,7 +3156,20 @@ static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
 	iommu_flush_dte(iommu, devid);
 }
 
-static struct irq_remap_table *alloc_irq_table(u16 devid)
+static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias,
+				       void *data)
+{
+	struct irq_remap_table *table = data;
+
+	irq_lookup_table[alias] = table;
+	set_dte_irq_entry(alias, table);
+
+	iommu_flush_dte(amd_iommu_rlookup_table[alias], alias);
+
+	return 0;
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid, struct pci_dev *pdev)
 {
 	struct irq_remap_table *table = NULL;
 	struct irq_remap_table *new_table = NULL;
@@ -3798,7 +3215,12 @@ static struct irq_remap_table *alloc_irq_table(u16 devid)
 	table = new_table;
 	new_table = NULL;
 
-	set_remap_table_entry(iommu, devid, table);
+	if (pdev)
+		pci_for_each_dma_alias(pdev, set_remap_table_entry_alias,
+				       table);
+	else
+		set_remap_table_entry(iommu, devid, table);
+
 	if (devid != alias)
 		set_remap_table_entry(iommu, alias, table);
 
@@ -3815,7 +3237,8 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count, bool align)
+static int alloc_irq_index(u16 devid, int count, bool align,
+			   struct pci_dev *pdev)
 {
 	struct irq_remap_table *table;
 	int index, c, alignment = 1;
@@ -3825,7 +3248,7 @@ static int alloc_irq_index(u16 devid, int count, bool align)
 	if (!iommu)
 		return -ENODEV;
 
-	table = alloc_irq_table(devid);
+	table = alloc_irq_table(devid, pdev);
 	if (!table)
 		return -ENODEV;
 
@@ -4258,7 +3681,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		struct irq_remap_table *table;
 		struct amd_iommu *iommu;
 
-		table = alloc_irq_table(devid);
+		table = alloc_irq_table(devid, NULL);
 		if (table) {
 			if (!table->min_index) {
 				/*
@@ -4275,11 +3698,15 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		} else {
 			index = -ENOMEM;
 		}
-	} else {
+	} else if (info->type == X86_IRQ_ALLOC_TYPE_MSI ||
+		   info->type == X86_IRQ_ALLOC_TYPE_MSIX) {
 		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
 
-		index = alloc_irq_index(devid, nr_irqs, align);
+		index = alloc_irq_index(devid, nr_irqs, align, info->msi_dev);
+	} else {
+		index = alloc_irq_index(devid, nr_irqs, false, NULL);
 	}
+
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
 		ret = index;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 17bd5a349119..f52f59d5c6bd 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -468,7 +468,6 @@ struct protection_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 */
 	int mode;		/* paging mode (0-6 levels) */
 	u64 *pt_root;		/* page table root pointer */
@@ -639,8 +638,8 @@ struct iommu_dev_data {
 	struct list_head list;		  /* For domain->dev_list */
 	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
+	struct pci_dev *pdev;
 	u16 devid;			  /* PCI Device ID */
-	u16 alias;			  /* Alias Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	bool passthrough;		  /* Device is identity mapped */
 	struct {
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index 5c87a38620c4..b2fe72a8f019 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -109,7 +109,7 @@ static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smm
 #define ARM_MMU500_ACR_S2CRB_TLBEN	(1 << 10)
 #define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
 
-static int arm_mmu500_reset(struct arm_smmu_device *smmu)
+int arm_mmu500_reset(struct arm_smmu_device *smmu)
 {
 	u32 reg, major;
 	int i;
@@ -170,5 +170,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 				  "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
+	if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm845-smmu-500"))
+		return qcom_smmu_impl_init(smmu);
+
 	return smmu;
 }
diff --git a/drivers/iommu/arm-smmu-qcom.c b/drivers/iommu/arm-smmu-qcom.c
new file mode 100644
index 000000000000..24c071c1d8b0
--- /dev/null
+++ b/drivers/iommu/arm-smmu-qcom.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/qcom_scm.h>
+
+#include "arm-smmu.h"
+
+struct qcom_smmu {
+	struct arm_smmu_device smmu;
+};
+
+static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	arm_mmu500_reset(smmu);
+
+	/*
+	 * To address performance degradation in non-real time clients,
+	 * such as USB and UFS, turn off wait-for-safe on sdm845 based boards,
+	 * such as MTP and db845, whose firmwares implement secure monitor
+	 * call handlers to turn on/off the wait-for-safe logic.
+	 */
+	ret = qcom_scm_qsmmu500_wait_safe_toggle(0);
+	if (ret)
+		dev_warn(smmu->dev, "Failed to turn off SAFE logic\n");
+
+	return ret;
+}
+
+static const struct arm_smmu_impl qcom_smmu_impl = {
+	.reset = qcom_sdm845_smmu500_reset,
+};
+
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	struct qcom_smmu *qsmmu;
+
+	qsmmu = devm_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL);
+	if (!qsmmu)
+		return ERR_PTR(-ENOMEM);
+
+	qsmmu->smmu = *smmu;
+
+	qsmmu->smmu.impl = &qcom_smmu_impl;
+	devm_kfree(smmu->dev, smmu);
+
+	return &qsmmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8da93e730d6f..effe72eb89e7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2172,7 +2172,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	cfg->cd.asid	= (u16)asid;
 	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
 	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
+	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
 	return 0;
 
 out_free_asid:
@@ -2448,7 +2448,7 @@ out_unlock:
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 
@@ -3611,19 +3611,19 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Interrupt lines */
 
-	irq = platform_get_irq_byname(pdev, "combined");
+	irq = platform_get_irq_byname_optional(pdev, "combined");
 	if (irq > 0)
 		smmu->combined_irq = irq;
 	else {
-		irq = platform_get_irq_byname(pdev, "eventq");
+		irq = platform_get_irq_byname_optional(pdev, "eventq");
 		if (irq > 0)
 			smmu->evtq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "priq");
+		irq = platform_get_irq_byname_optional(pdev, "priq");
 		if (irq > 0)
 			smmu->priq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "gerror");
+		irq = platform_get_irq_byname_optional(pdev, "gerror");
 		if (irq > 0)
 			smmu->gerr_irq = irq;
 	}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 7c503a6bc585..4f1a350d9529 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 
 #include <linux/amba/bus.h>
@@ -122,7 +123,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -244,6 +245,9 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 	unsigned int spin_cnt, delay;
 	u32 reg;
 
+	if (smmu->impl && unlikely(smmu->impl->tlb_sync))
+		return smmu->impl->tlb_sync(smmu, page, sync, status);
+
 	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
 	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
 		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
@@ -268,9 +272,8 @@ static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
 	spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
 }
 
-static void arm_smmu_tlb_sync_context(void *cookie)
+static void arm_smmu_tlb_sync_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	unsigned long flags;
 
@@ -280,13 +283,6 @@ static void arm_smmu_tlb_sync_context(void *cookie)
 	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 }
 
-static void arm_smmu_tlb_sync_vmid(void *cookie)
-{
-	struct arm_smmu_domain *smmu_domain = cookie;
-
-	arm_smmu_tlb_sync_global(smmu_domain->smmu);
-}
-
 static void arm_smmu_tlb_inv_context_s1(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
@@ -297,7 +293,7 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	wmb();
 	arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
 			  ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
-	arm_smmu_tlb_sync_context(cookie);
+	arm_smmu_tlb_sync_context(smmu_domain);
 }
 
 static void arm_smmu_tlb_inv_context_s2(void *cookie)
@@ -312,18 +308,16 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
 }
 
 static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
-				      size_t granule, bool leaf, void *cookie)
+				      size_t granule, void *cookie, int reg)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	int reg, idx = cfg->cbndx;
+	int idx = cfg->cbndx;
 
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		wmb();
 
-	reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
-
 	if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
 		iova = (iova >> 12) << 12;
 		iova |= cfg->asid;
@@ -342,16 +336,15 @@ static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
 }
 
 static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
-				      size_t granule, bool leaf, void *cookie)
+				      size_t granule, void *cookie, int reg)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	int reg, idx = smmu_domain->cfg.cbndx;
+	int idx = smmu_domain->cfg.cbndx;
 
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		wmb();
 
-	reg = leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L : ARM_SMMU_CB_S2_TLBIIPAS2;
 	iova >>= 12;
 	do {
 		if (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64)
@@ -362,85 +355,98 @@ static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
-/*
- * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
- * almost negligible, but the benefit of getting the first one in as far ahead
- * of the sync as possible is significant, hence we don't just make this a
- * no-op and set .tlb_sync to arm_smmu_tlb_inv_context_s2() as you might think.
- */
-static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
-					 size_t granule, bool leaf, void *cookie)
+static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
-		wmb();
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVA);
+	arm_smmu_tlb_sync_context(cookie);
+}
 
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+static void arm_smmu_tlb_inv_leaf_s1(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVAL);
+	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
-				  size_t granule, void *cookie)
+static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVAL);
+}
 
-	ops->tlb_inv_range(iova, size, granule, false, cookie);
-	ops->tlb_sync(cookie);
+static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2);
+	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
-				  size_t granule, void *cookie)
+static void arm_smmu_tlb_inv_leaf_s2(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2L);
+	arm_smmu_tlb_sync_context(cookie);
+}
 
-	ops->tlb_inv_range(iova, size, granule, true, cookie);
-	ops->tlb_sync(cookie);
+static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2L);
 }
 
-static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
-				  unsigned long iova, size_t granule,
-				  void *cookie)
+static void arm_smmu_tlb_inv_any_s2_v1(unsigned long iova, size_t size,
+				       size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_context_s2(cookie);
+}
+/*
+ * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
+ * almost negligible, but the benefit of getting the first one in as far ahead
+ * of the sync as possible is significant, hence we don't just make this a
+ * no-op and call arm_smmu_tlb_inv_context_s2() from .iotlb_sync as you might
+ * think.
+ */
+static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather,
+					unsigned long iova, size_t granule,
+					void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
 
-	ops->tlb_inv_range(iova, granule, granule, true, cookie);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
 }
 
-static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
-	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_range_s1,
-	.tlb_sync		= arm_smmu_tlb_sync_context,
+static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s1,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
-	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_range_s2,
-	.tlb_sync		= arm_smmu_tlb_sync_context,
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
-	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_vmid_nosync,
-	.tlb_sync		= arm_smmu_tlb_sync_vmid,
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_any_s2_v1,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -472,6 +478,8 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 {
 	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
 	struct arm_smmu_device *smmu = dev;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
 
 	gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
 	gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0);
@@ -481,11 +489,19 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 	if (!gfsr)
 		return IRQ_NONE;
 
-	dev_err_ratelimited(smmu->dev,
-		"Unexpected global fault, this could be serious\n");
-	dev_err_ratelimited(smmu->dev,
-		"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
-		gfsr, gfsynr0, gfsynr1, gfsynr2);
+	if (__ratelimit(&rs)) {
+		if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
+		    (gfsr & sGFSR_USF))
+			dev_err(smmu->dev,
+				"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
+				(u16)gfsynr1);
+		else
+			dev_err(smmu->dev,
+				"Unexpected global fault, this could be serious\n");
+		dev_err(smmu->dev,
+			"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+			gfsr, gfsynr0, gfsynr1, gfsynr2);
+	}
 
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, gfsr);
 	return IRQ_HANDLED;
@@ -536,8 +552,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr;
 			cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr;
 		} else {
-			cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
-			cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair[1];
+			cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair;
+			cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32;
 		}
 	}
 }
@@ -770,7 +786,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.ias		= ias,
 		.oas		= oas,
 		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
-		.tlb		= &smmu_domain->flush_ops->tlb,
+		.tlb		= smmu_domain->flush_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1039,8 +1055,6 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (!group)
-		group = ERR_PTR(-ENOMEM);
 	if (IS_ERR(group)) {
 		ret = PTR_ERR(group);
 		goto out_err;
@@ -1154,13 +1168,27 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	/* Looks ok, so add the device to the domain */
 	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
@@ -1200,7 +1228,7 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
 
 	if (smmu_domain->flush_ops) {
 		arm_smmu_rpm_get(smmu);
-		smmu_domain->flush_ops->tlb.tlb_flush_all(smmu_domain);
+		smmu_domain->flush_ops->tlb_flush_all(smmu_domain);
 		arm_smmu_rpm_put(smmu);
 	}
 }
@@ -1211,11 +1239,16 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	if (smmu_domain->flush_ops) {
-		arm_smmu_rpm_get(smmu);
-		smmu_domain->flush_ops->tlb_sync(smmu_domain);
-		arm_smmu_rpm_put(smmu);
-	}
+	if (!smmu)
+		return;
+
+	arm_smmu_rpm_get(smmu);
+	if (smmu->version == ARM_SMMU_V2 ||
+	    smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+		arm_smmu_tlb_sync_context(smmu_domain);
+	else
+		arm_smmu_tlb_sync_global(smmu);
+	arm_smmu_rpm_put(smmu);
 }
 
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
@@ -2062,10 +2095,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	for (i = 0; i < num_irqs; ++i) {
 		int irq = platform_get_irq(pdev, i);
 
-		if (irq < 0) {
-			dev_err(dev, "failed to get irq index %d\n", i);
+		if (irq < 0)
 			return -ENODEV;
-		}
 		smmu->irqs[i] = irq;
 	}
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index b19b6cae9b5e..62b9f0cec49b 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -79,6 +79,8 @@
 #define ID7_MINOR			GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_sGFSR		0x48
+#define sGFSR_USF			BIT(1)
+
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
 #define ARM_SMMU_GR0_sGFSYNR2		0x58
@@ -304,17 +306,10 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
-struct arm_smmu_flush_ops {
-	struct iommu_flush_ops		tlb;
-	void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule,
-			      bool leaf, void *cookie);
-	void (*tlb_sync)(void *cookie);
-};
-
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct arm_smmu_flush_ops	*flush_ops;
+	const struct iommu_flush_ops	*flush_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
@@ -335,6 +330,8 @@ struct arm_smmu_impl {
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
 	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
+			 int status);
 };
 
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
@@ -398,5 +395,8 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 	arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
+
+int arm_mmu500_reset(struct arm_smmu_device *smmu);
 
 #endif /* _ARM_SMMU_H */
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f321279baf9e..0cc702a70a96 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -22,6 +22,7 @@
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -353,6 +354,21 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	return iova_reserve_iommu_regions(dev, domain);
 }
 
+static int iommu_dma_deferred_attach(struct device *dev,
+		struct iommu_domain *domain)
+{
+	const struct iommu_ops *ops = domain->ops;
+
+	if (!is_kdump_kernel())
+		return 0;
+
+	if (unlikely(ops->is_attach_deferred &&
+			ops->is_attach_deferred(domain, dev)))
+		return iommu_attach_device(domain, dev);
+
+	return 0;
+}
+
 /**
  * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
  *                    page flags.
@@ -405,8 +421,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
-	if (dev->bus_dma_mask)
-		dma_limit &= dev->bus_dma_mask;
+	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
@@ -462,7 +477,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot)
+		size_t size, int prot, dma_addr_t dma_mask)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -470,13 +485,16 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	size_t iova_off = iova_offset(iovad, phys);
 	dma_addr_t iova;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return DMA_MAPPING_ERROR;
+
 	size = iova_align(iovad, size + iova_off);
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
 		return DMA_MAPPING_ERROR;
 	}
@@ -579,6 +597,9 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 
 	*dma_handle = DMA_MAPPING_ERROR;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return NULL;
+
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
 		min_size = PAGE_SIZE;
@@ -611,7 +632,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
+	if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
@@ -659,7 +680,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_cpu(dev, phys, size, dir);
+	arch_sync_dma_for_cpu(phys, size, dir);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -671,7 +692,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_device(dev, phys, size, dir);
+	arch_sync_dma_for_device(phys, size, dir);
 }
 
 static void iommu_dma_sync_sg_for_cpu(struct device *dev,
@@ -685,7 +706,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -699,7 +720,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -711,10 +732,10 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dma_handle;
 
-	dma_handle =__iommu_dma_map(dev, phys, size, prot);
+	dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev));
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    dma_handle != DMA_MAPPING_ERROR)
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return dma_handle;
 }
 
@@ -821,6 +842,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long mask = dma_get_seg_boundary(dev);
 	int i;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return 0;
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
@@ -871,7 +895,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
+	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
@@ -911,7 +935,8 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
+			dma_get_mask(dev));
 }
 
 static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -1017,7 +1042,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	if (!cpu_addr)
 		return NULL;
 
-	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot);
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
+			dev->coherent_dma_mask);
 	if (*handle == DMA_MAPPING_ERROR) {
 		__iommu_dma_free(dev, size, cpu_addr);
 		return NULL;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index eecd6a421667..3acfa6a25fa2 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -895,8 +895,11 @@ int __init detect_intel_iommu(void)
 	}
 
 #ifdef CONFIG_X86
-	if (!ret)
+	if (!ret) {
 		x86_init.iommu.iommu_init = intel_iommu_init;
+		x86_platform.iommu_shutdown = intel_iommu_shutdown;
+	}
+
 #endif
 
 	if (dmar_tbl) {
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 9c94e16fb127..186ff5cc975c 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1073,7 +1073,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
  */
 static int exynos_iommu_map(struct iommu_domain *iommu_domain,
 			    unsigned long l_iova, phys_addr_t paddr, size_t size,
-			    int prot)
+			    int prot, gfp_t gfp)
 {
 	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_pte_t *entry;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6db6d969e31c..0c8d81f56a30 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2420,14 +2420,24 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-/*
- * find_domain
- * Note: we use struct device->archdata.iommu stores the info
- */
 static struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
+	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
+		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+		return NULL;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->archdata.iommu;
+	if (likely(info))
+		return info->domain;
+
+	return NULL;
+}
+
+static struct dmar_domain *deferred_attach_domain(struct device *dev)
+{
 	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
 		struct iommu_domain *domain;
 
@@ -2437,12 +2447,7 @@ static struct dmar_domain *find_domain(struct device *dev)
 			intel_iommu_attach_device(domain, dev);
 	}
 
-	/* No lock here, assumes no domain exit in normal case */
-	info = dev->archdata.iommu;
-
-	if (likely(info))
-		return info->domain;
-	return NULL;
+	return find_domain(dev);
 }
 
 static inline struct device_domain_info *
@@ -3512,7 +3517,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;
 
@@ -3732,7 +3737,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	if (!iommu_need_mapping(dev))
 		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (!domain)
 		return 0;
 
@@ -3827,7 +3832,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	int prot = 0;
 	int ret;
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (WARN_ON(dir == DMA_NONE || !domain))
 		return DMA_MAPPING_ERROR;
 
@@ -4314,13 +4319,19 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
+	int ret;
+
+	rmrr = (struct acpi_dmar_reserved_memory *)header;
+	ret = arch_rmrr_sanity_check(rmrr);
+	if (ret)
+		return ret;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
 		goto out;
 
 	rmrru->hdr = header;
-	rmrr = (struct acpi_dmar_reserved_memory *)header;
+
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
 
@@ -4759,6 +4770,26 @@ static void intel_disable_iommus(void)
 		iommu_disable_translation(iommu);
 }
 
+void intel_iommu_shutdown(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	if (no_iommu || dmar_disabled)
+		return;
+
+	down_write(&dmar_global_lock);
+
+	/* Disable PMRs explicitly here. */
+	for_each_iommu(iommu, drhd)
+		iommu_disable_protect_mem_regions(iommu);
+
+	/* Make sure the IOMMUs are switched off */
+	intel_disable_iommus();
+
+	up_write(&dmar_global_lock);
+}
+
 static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
@@ -5440,7 +5471,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
-			   size_t size, int iommu_prot)
+			   size_t size, int iommu_prot, gfp_t gfp)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 4cb394937700..7c3bd2c3cdca 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -846,27 +846,28 @@ struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns = {
 
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S_SELFTEST
 
-static struct io_pgtable_cfg *cfg_cookie;
+static struct io_pgtable_cfg *cfg_cookie __initdata;
 
-static void dummy_tlb_flush_all(void *cookie)
+static void __init dummy_tlb_flush_all(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
-			    void *cookie)
+static void __init dummy_tlb_flush(unsigned long iova, size_t size,
+				   size_t granule, void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
-			       unsigned long iova, size_t granule, void *cookie)
+static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t granule,
+				      void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
-static const struct iommu_flush_ops dummy_tlb_ops = {
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index ca51036aa53c..bdf47f745268 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -32,39 +32,31 @@
 	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
 
 /*
- * For consistency with the architecture, we always consider
- * ARM_LPAE_MAX_LEVELS levels, with the walk starting at level n >=0
- */
-#define ARM_LPAE_START_LVL(d)		(ARM_LPAE_MAX_LEVELS - (d)->levels)
-
-/*
  * Calculate the right shift amount to get to the portion describing level l
  * in a virtual address mapped by the pagetable in d.
  */
 #define ARM_LPAE_LVL_SHIFT(l,d)						\
-	((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1))		\
-	  * (d)->bits_per_level) + (d)->pg_shift)
+	(((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level) +		\
+	ilog2(sizeof(arm_lpae_iopte)))
 
-#define ARM_LPAE_GRANULE(d)		(1UL << (d)->pg_shift)
-
-#define ARM_LPAE_PAGES_PER_PGD(d)					\
-	DIV_ROUND_UP((d)->pgd_size, ARM_LPAE_GRANULE(d))
+#define ARM_LPAE_GRANULE(d)						\
+	(sizeof(arm_lpae_iopte) << (d)->bits_per_level)
+#define ARM_LPAE_PGD_SIZE(d)						\
+	(sizeof(arm_lpae_iopte) << (d)->pgd_bits)
 
 /*
  * Calculate the index at level l used to map virtual address a using the
  * pagetable in d.
  */
 #define ARM_LPAE_PGD_IDX(l,d)						\
-	((l) == ARM_LPAE_START_LVL(d) ? ilog2(ARM_LPAE_PAGES_PER_PGD(d)) : 0)
+	((l) == (d)->start_level ? (d)->pgd_bits - (d)->bits_per_level : 0)
 
 #define ARM_LPAE_LVL_IDX(a,l,d)						\
 	(((u64)(a) >> ARM_LPAE_LVL_SHIFT(l,d)) &			\
 	 ((1 << ((d)->bits_per_level + ARM_LPAE_PGD_IDX(l,d))) - 1))
 
 /* Calculate the block/page mapping size at level l for pagetable in d. */
-#define ARM_LPAE_BLOCK_SIZE(l,d)					\
-	(1ULL << (ilog2(sizeof(arm_lpae_iopte)) +			\
-		((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
+#define ARM_LPAE_BLOCK_SIZE(l,d)	(1ULL << ARM_LPAE_LVL_SHIFT(l,d))
 
 /* Page table bits */
 #define ARM_LPAE_PTE_TYPE_SHIFT		0
@@ -180,10 +172,9 @@
 struct arm_lpae_io_pgtable {
 	struct io_pgtable	iop;
 
-	int			levels;
-	size_t			pgd_size;
-	unsigned long		pg_shift;
-	unsigned long		bits_per_level;
+	int			pgd_bits;
+	int			start_level;
+	int			bits_per_level;
 
 	void			*pgd;
 };
@@ -213,7 +204,7 @@ static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte,
 {
 	u64 paddr = pte & ARM_LPAE_PTE_ADDR_MASK;
 
-	if (data->pg_shift < 16)
+	if (ARM_LPAE_GRANULE(data) < SZ_64K)
 		return paddr;
 
 	/* Rotate the packed high-order bits back to the top */
@@ -392,7 +383,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
 
 	/* If we can install a leaf entry at this level, then do so */
-	if (size == block_size && (size & cfg->pgsize_bitmap))
+	if (size == block_size)
 		return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep);
 
 	/* We can't allocate tables at the final level */
@@ -464,7 +455,7 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		else if (prot & IOMMU_CACHE)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
-		else if (prot & IOMMU_QCOM_SYS_CACHE)
+		else if (prot & IOMMU_SYS_CACHE_ONLY)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
@@ -479,16 +470,19 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 			phys_addr_t paddr, size_t size, int iommu_prot)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
-	int ret, lvl = ARM_LPAE_START_LVL(data);
+	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
 		return 0;
 
-	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
-		    paddr >= (1ULL << data->iop.cfg.oas)))
+	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
+		return -EINVAL;
+
+	if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
@@ -508,8 +502,8 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 	arm_lpae_iopte *start, *end;
 	unsigned long table_size;
 
-	if (lvl == ARM_LPAE_START_LVL(data))
-		table_size = data->pgd_size;
+	if (lvl == data->start_level)
+		table_size = ARM_LPAE_PGD_SIZE(data);
 	else
 		table_size = ARM_LPAE_GRANULE(data);
 
@@ -537,7 +531,7 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_to_data(iop);
 
-	__arm_lpae_free_pgtable(data, ARM_LPAE_START_LVL(data), data->pgd);
+	__arm_lpae_free_pgtable(data, data->start_level, data->pgd);
 	kfree(data);
 }
 
@@ -652,13 +646,16 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			     size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
-	int lvl = ARM_LPAE_START_LVL(data);
 
-	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
+	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
+		return 0;
+
+	if (WARN_ON(iova >> data->iop.cfg.ias))
 		return 0;
 
-	return __arm_lpae_unmap(data, gather, iova, size, lvl, ptep);
+	return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
 }
 
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
@@ -666,7 +663,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	arm_lpae_iopte pte, *ptep = data->pgd;
-	int lvl = ARM_LPAE_START_LVL(data);
+	int lvl = data->start_level;
 
 	do {
 		/* Valid IOPTE pointer? */
@@ -743,8 +740,8 @@ static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
 static struct arm_lpae_io_pgtable *
 arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 {
-	unsigned long va_bits, pgd_bits;
 	struct arm_lpae_io_pgtable *data;
+	int levels, va_bits, pg_shift;
 
 	arm_lpae_restrict_pgsizes(cfg);
 
@@ -766,15 +763,15 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (!data)
 		return NULL;
 
-	data->pg_shift = __ffs(cfg->pgsize_bitmap);
-	data->bits_per_level = data->pg_shift - ilog2(sizeof(arm_lpae_iopte));
+	pg_shift = __ffs(cfg->pgsize_bitmap);
+	data->bits_per_level = pg_shift - ilog2(sizeof(arm_lpae_iopte));
 
-	va_bits = cfg->ias - data->pg_shift;
-	data->levels = DIV_ROUND_UP(va_bits, data->bits_per_level);
+	va_bits = cfg->ias - pg_shift;
+	levels = DIV_ROUND_UP(va_bits, data->bits_per_level);
+	data->start_level = ARM_LPAE_MAX_LEVELS - levels;
 
 	/* Calculate the actual size of our pgd (without concatenation) */
-	pgd_bits = va_bits - (data->bits_per_level * (data->levels - 1));
-	data->pgd_size = 1UL << (pgd_bits + ilog2(sizeof(arm_lpae_iopte)));
+	data->pgd_bits = va_bits - (data->bits_per_level * (levels - 1));
 
 	data->iop.ops = (struct io_pgtable_ops) {
 		.map		= arm_lpae_map,
@@ -864,11 +861,11 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	      (ARM_LPAE_MAIR_ATTR_INC_OWBRWA
 	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE));
 
-	cfg->arm_lpae_s1_cfg.mair[0] = reg;
-	cfg->arm_lpae_s1_cfg.mair[1] = 0;
+	cfg->arm_lpae_s1_cfg.mair = reg;
 
 	/* Looking good; allocate a pgd */
-	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
+					   GFP_KERNEL, cfg);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -903,13 +900,13 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	 * Concatenate PGDs at level 1 if possible in order to reduce
 	 * the depth of the stage-2 walk.
 	 */
-	if (data->levels == ARM_LPAE_MAX_LEVELS) {
+	if (data->start_level == 0) {
 		unsigned long pgd_pages;
 
-		pgd_pages = data->pgd_size >> ilog2(sizeof(arm_lpae_iopte));
+		pgd_pages = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte);
 		if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) {
-			data->pgd_size = pgd_pages << data->pg_shift;
-			data->levels--;
+			data->pgd_bits += data->bits_per_level;
+			data->start_level++;
 		}
 	}
 
@@ -919,7 +916,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
 	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
 
-	sl = ARM_LPAE_START_LVL(data);
+	sl = data->start_level;
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
@@ -965,7 +962,8 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	cfg->arm_lpae_s2_cfg.vtcr = reg;
 
 	/* Allocate pgd pages */
-	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
+					   GFP_KERNEL, cfg);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1034,9 +1032,9 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		return NULL;
 
 	/* Mali seems to need a full 4-level table regardless of IAS */
-	if (data->levels < ARM_LPAE_MAX_LEVELS) {
-		data->levels = ARM_LPAE_MAX_LEVELS;
-		data->pgd_size = sizeof(arm_lpae_iopte);
+	if (data->start_level > 0) {
+		data->start_level = 0;
+		data->pgd_bits = 0;
 	}
 	/*
 	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
@@ -1053,7 +1051,8 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
 		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
-	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
+					   cfg);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1097,22 +1096,23 @@ struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
 
 #ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
 
-static struct io_pgtable_cfg *cfg_cookie;
+static struct io_pgtable_cfg *cfg_cookie __initdata;
 
-static void dummy_tlb_flush_all(void *cookie)
+static void __init dummy_tlb_flush_all(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
-			    void *cookie)
+static void __init dummy_tlb_flush(unsigned long iova, size_t size,
+				   size_t granule, void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
-			       unsigned long iova, size_t granule, void *cookie)
+static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t granule,
+				      void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
@@ -1131,9 +1131,9 @@ static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
 
 	pr_err("cfg: pgsize_bitmap 0x%lx, ias %u-bit\n",
 		cfg->pgsize_bitmap, cfg->ias);
-	pr_err("data: %d levels, 0x%zx pgd_size, %lu pg_shift, %lu bits_per_level, pgd @ %p\n",
-		data->levels, data->pgd_size, data->pg_shift,
-		data->bits_per_level, data->pgd);
+	pr_err("data: %d levels, 0x%zx pgd_size, %u pg_shift, %u bits_per_level, pgd @ %p\n",
+		ARM_LPAE_MAX_LEVELS - data->start_level, ARM_LPAE_PGD_SIZE(data),
+		ilog2(ARM_LPAE_GRANULE(data)), data->bits_per_level, data->pgd);
 }
 
 #define __FAIL(ops, i)	({						\
@@ -1145,7 +1145,7 @@ static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
 
 static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 {
-	static const enum io_pgtable_fmt fmts[] = {
+	static const enum io_pgtable_fmt fmts[] __initconst = {
 		ARM_64_LPAE_S1,
 		ARM_64_LPAE_S2,
 	};
@@ -1244,13 +1244,13 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 
 static int __init arm_lpae_do_selftests(void)
 {
-	static const unsigned long pgsize[] = {
+	static const unsigned long pgsize[] __initconst = {
 		SZ_4K | SZ_2M | SZ_1G,
 		SZ_16K | SZ_32M,
 		SZ_64K | SZ_512M,
 	};
 
-	static const unsigned int ias[] = {
+	static const unsigned int ias[] __initconst = {
 		32, 36, 40, 42, 44, 48,
 	};
 
diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c
new file mode 100644
index 000000000000..0f8dd377aada
--- /dev/null
+++ b/drivers/iommu/ioasid.c
@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O Address Space ID allocator. There is one global IOASID space, split into
+ * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and
+ * free IOASIDs with ioasid_alloc and ioasid_free.
+ */
+#include <linux/ioasid.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+
+struct ioasid_data {
+	ioasid_t id;
+	struct ioasid_set *set;
+	void *private;
+	struct rcu_head rcu;
+};
+
+/*
+ * struct ioasid_allocator_data - Internal data structure to hold information
+ * about an allocator. There are two types of allocators:
+ *
+ * - Default allocator always has its own XArray to track the IOASIDs allocated.
+ * - Custom allocators may share allocation helpers with different private data.
+ *   Custom allocators that share the same helper functions also share the same
+ *   XArray.
+ * Rules:
+ * 1. Default allocator is always available, not dynamically registered. This is
+ *    to prevent race conditions with early boot code that want to register
+ *    custom allocators or allocate IOASIDs.
+ * 2. Custom allocators take precedence over the default allocator.
+ * 3. When all custom allocators sharing the same helper functions are
+ *    unregistered (e.g. due to hotplug), all outstanding IOASIDs must be
+ *    freed. Otherwise, outstanding IOASIDs will be lost and orphaned.
+ * 4. When switching between custom allocators sharing the same helper
+ *    functions, outstanding IOASIDs are preserved.
+ * 5. When switching between custom allocator and default allocator, all IOASIDs
+ *    must be freed to ensure unadulterated space for the new allocator.
+ *
+ * @ops:	allocator helper functions and its data
+ * @list:	registered custom allocators
+ * @slist:	allocators share the same ops but different data
+ * @flags:	attributes of the allocator
+ * @xa:		xarray holds the IOASID space
+ * @rcu:	used for kfree_rcu when unregistering allocator
+ */
+struct ioasid_allocator_data {
+	struct ioasid_allocator_ops *ops;
+	struct list_head list;
+	struct list_head slist;
+#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */
+	unsigned long flags;
+	struct xarray xa;
+	struct rcu_head rcu;
+};
+
+static DEFINE_SPINLOCK(ioasid_allocator_lock);
+static LIST_HEAD(allocators_list);
+
+static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque);
+static void default_free(ioasid_t ioasid, void *opaque);
+
+static struct ioasid_allocator_ops default_ops = {
+	.alloc = default_alloc,
+	.free = default_free,
+};
+
+static struct ioasid_allocator_data default_allocator = {
+	.ops = &default_ops,
+	.flags = 0,
+	.xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC),
+};
+
+static struct ioasid_allocator_data *active_allocator = &default_allocator;
+
+static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque)
+{
+	ioasid_t id;
+
+	if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) {
+		pr_err("Failed to alloc ioasid from %d to %d\n", min, max);
+		return INVALID_IOASID;
+	}
+
+	return id;
+}
+
+static void default_free(ioasid_t ioasid, void *opaque)
+{
+	struct ioasid_data *ioasid_data;
+
+	ioasid_data = xa_erase(&default_allocator.xa, ioasid);
+	kfree_rcu(ioasid_data, rcu);
+}
+
+/* Allocate and initialize a new custom allocator with its helper functions */
+static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *ia_data;
+
+	ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC);
+	if (!ia_data)
+		return NULL;
+
+	xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC);
+	INIT_LIST_HEAD(&ia_data->slist);
+	ia_data->flags |= IOASID_ALLOCATOR_CUSTOM;
+	ia_data->ops = ops;
+
+	/* For tracking custom allocators that share the same ops */
+	list_add_tail(&ops->list, &ia_data->slist);
+
+	return ia_data;
+}
+
+static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b)
+{
+	return (a->free == b->free) && (a->alloc == b->alloc);
+}
+
+/**
+ * ioasid_register_allocator - register a custom allocator
+ * @ops: the custom allocator ops to be registered
+ *
+ * Custom allocators take precedence over the default xarray based allocator.
+ * Private data associated with the IOASID allocated by the custom allocators
+ * are managed by IOASID framework similar to data stored in xa by default
+ * allocator.
+ *
+ * There can be multiple allocators registered but only one is active. In case
+ * of runtime removal of a custom allocator, the next one is activated based
+ * on the registration ordering.
+ *
+ * Multiple allocators can share the same alloc() function, in this case the
+ * IOASID space is shared.
+ */
+int ioasid_register_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *ia_data;
+	struct ioasid_allocator_data *pallocator;
+	int ret = 0;
+
+	spin_lock(&ioasid_allocator_lock);
+
+	ia_data = ioasid_alloc_allocator(ops);
+	if (!ia_data) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/*
+	 * No particular preference, we activate the first one and keep
+	 * the later registered allocators in a list in case the first one gets
+	 * removed due to hotplug.
+	 */
+	if (list_empty(&allocators_list)) {
+		WARN_ON(active_allocator != &default_allocator);
+		/* Use this new allocator if default is not active */
+		if (xa_empty(&active_allocator->xa)) {
+			rcu_assign_pointer(active_allocator, ia_data);
+			list_add_tail(&ia_data->list, &allocators_list);
+			goto out_unlock;
+		}
+		pr_warn("Default allocator active with outstanding IOASID\n");
+		ret = -EAGAIN;
+		goto out_free;
+	}
+
+	/* Check if the allocator is already registered */
+	list_for_each_entry(pallocator, &allocators_list, list) {
+		if (pallocator->ops == ops) {
+			pr_err("IOASID allocator already registered\n");
+			ret = -EEXIST;
+			goto out_free;
+		} else if (use_same_ops(pallocator->ops, ops)) {
+			/*
+			 * If the new allocator shares the same ops,
+			 * then they will share the same IOASID space.
+			 * We should put them under the same xarray.
+			 */
+			list_add_tail(&ops->list, &pallocator->slist);
+			goto out_free;
+		}
+	}
+	list_add_tail(&ia_data->list, &allocators_list);
+
+	spin_unlock(&ioasid_allocator_lock);
+	return 0;
+out_free:
+	kfree(ia_data);
+out_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ioasid_register_allocator);
+
+/**
+ * ioasid_unregister_allocator - Remove a custom IOASID allocator ops
+ * @ops: the custom allocator to be removed
+ *
+ * Remove an allocator from the list, activate the next allocator in
+ * the order it was registered. Or revert to default allocator if all
+ * custom allocators are unregistered without outstanding IOASIDs.
+ */
+void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *pallocator;
+	struct ioasid_allocator_ops *sops;
+
+	spin_lock(&ioasid_allocator_lock);
+	if (list_empty(&allocators_list)) {
+		pr_warn("No custom IOASID allocators active!\n");
+		goto exit_unlock;
+	}
+
+	list_for_each_entry(pallocator, &allocators_list, list) {
+		if (!use_same_ops(pallocator->ops, ops))
+			continue;
+
+		if (list_is_singular(&pallocator->slist)) {
+			/* No shared helper functions */
+			list_del(&pallocator->list);
+			/*
+			 * All IOASIDs should have been freed before
+			 * the last allocator that shares the same ops
+			 * is unregistered.
+			 */
+			WARN_ON(!xa_empty(&pallocator->xa));
+			if (list_empty(&allocators_list)) {
+				pr_info("No custom IOASID allocators, switch to default.\n");
+				rcu_assign_pointer(active_allocator, &default_allocator);
+			} else if (pallocator == active_allocator) {
+				rcu_assign_pointer(active_allocator,
+						list_first_entry(&allocators_list,
+								struct ioasid_allocator_data, list));
+				pr_info("IOASID allocator changed");
+			}
+			kfree_rcu(pallocator, rcu);
+			break;
+		}
+		/*
+		 * Find the matching shared ops to delete,
+		 * but keep outstanding IOASIDs
+		 */
+		list_for_each_entry(sops, &pallocator->slist, list) {
+			if (sops == ops) {
+				list_del(&ops->list);
+				break;
+			}
+		}
+		break;
+	}
+
+exit_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+}
+EXPORT_SYMBOL_GPL(ioasid_unregister_allocator);
+
+/**
+ * ioasid_set_data - Set private data for an allocated ioasid
+ * @ioasid: the ID to set data
+ * @data:   the private data
+ *
+ * For IOASID that is already allocated, private data can be set
+ * via this API. Future lookup can be done via ioasid_find.
+ */
+int ioasid_set_data(ioasid_t ioasid, void *data)
+{
+	struct ioasid_data *ioasid_data;
+	int ret = 0;
+
+	spin_lock(&ioasid_allocator_lock);
+	ioasid_data = xa_load(&active_allocator->xa, ioasid);
+	if (ioasid_data)
+		rcu_assign_pointer(ioasid_data->private, data);
+	else
+		ret = -ENOENT;
+	spin_unlock(&ioasid_allocator_lock);
+
+	/*
+	 * Wait for readers to stop accessing the old private data, so the
+	 * caller can free it.
+	 */
+	if (!ret)
+		synchronize_rcu();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ioasid_set_data);
+
+/**
+ * ioasid_alloc - Allocate an IOASID
+ * @set: the IOASID set
+ * @min: the minimum ID (inclusive)
+ * @max: the maximum ID (inclusive)
+ * @private: data private to the caller
+ *
+ * Allocate an ID between @min and @max. The @private pointer is stored
+ * internally and can be retrieved with ioasid_find().
+ *
+ * Return: the allocated ID on success, or %INVALID_IOASID on failure.
+ */
+ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
+		      void *private)
+{
+	struct ioasid_data *data;
+	void *adata;
+	ioasid_t id;
+
+	data = kzalloc(sizeof(*data), GFP_ATOMIC);
+	if (!data)
+		return INVALID_IOASID;
+
+	data->set = set;
+	data->private = private;
+
+	/*
+	 * Custom allocator needs allocator data to perform platform specific
+	 * operations.
+	 */
+	spin_lock(&ioasid_allocator_lock);
+	adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data;
+	id = active_allocator->ops->alloc(min, max, adata);
+	if (id == INVALID_IOASID) {
+		pr_err("Failed ASID allocation %lu\n", active_allocator->flags);
+		goto exit_free;
+	}
+
+	if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) &&
+	     xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) {
+		/* Custom allocator needs framework to store and track allocation results */
+		pr_err("Failed to alloc ioasid from %d\n", id);
+		active_allocator->ops->free(id, active_allocator->ops->pdata);
+		goto exit_free;
+	}
+	data->id = id;
+
+	spin_unlock(&ioasid_allocator_lock);
+	return id;
+exit_free:
+	spin_unlock(&ioasid_allocator_lock);
+	kfree(data);
+	return INVALID_IOASID;
+}
+EXPORT_SYMBOL_GPL(ioasid_alloc);
+
+/**
+ * ioasid_free - Free an IOASID
+ * @ioasid: the ID to remove
+ */
+void ioasid_free(ioasid_t ioasid)
+{
+	struct ioasid_data *ioasid_data;
+
+	spin_lock(&ioasid_allocator_lock);
+	ioasid_data = xa_load(&active_allocator->xa, ioasid);
+	if (!ioasid_data) {
+		pr_err("Trying to free unknown IOASID %u\n", ioasid);
+		goto exit_unlock;
+	}
+
+	active_allocator->ops->free(ioasid, active_allocator->ops->pdata);
+	/* Custom allocator needs additional steps to free the xa element */
+	if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) {
+		ioasid_data = xa_erase(&active_allocator->xa, ioasid);
+		kfree_rcu(ioasid_data, rcu);
+	}
+
+exit_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+}
+EXPORT_SYMBOL_GPL(ioasid_free);
+
+/**
+ * ioasid_find - Find IOASID data
+ * @set: the IOASID set
+ * @ioasid: the IOASID to find
+ * @getter: function to call on the found object
+ *
+ * The optional getter function allows to take a reference to the found object
+ * under the rcu lock. The function can also check if the object is still valid:
+ * if @getter returns false, then the object is invalid and NULL is returned.
+ *
+ * If the IOASID exists, return the private pointer passed to ioasid_alloc.
+ * Private data can be NULL if not set. Return an error if the IOASID is not
+ * found, or if @set is not NULL and the IOASID does not belong to the set.
+ */
+void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+		  bool (*getter)(void *))
+{
+	void *priv;
+	struct ioasid_data *ioasid_data;
+	struct ioasid_allocator_data *idata;
+
+	rcu_read_lock();
+	idata = rcu_dereference(active_allocator);
+	ioasid_data = xa_load(&idata->xa, ioasid);
+	if (!ioasid_data) {
+		priv = ERR_PTR(-ENOENT);
+		goto unlock;
+	}
+	if (set && ioasid_data->set != set) {
+		/* data found but does not belong to the set */
+		priv = ERR_PTR(-EACCES);
+		goto unlock;
+	}
+	/* Now IOASID and its set is verified, we can return the private data */
+	priv = rcu_dereference(ioasid_data->private);
+	if (getter && !getter(priv))
+		priv = NULL;
+unlock:
+	rcu_read_unlock();
+
+	return priv;
+}
+EXPORT_SYMBOL_GPL(ioasid_find);
+
+MODULE_AUTHOR("Jean-Philippe Brucker <jean-philippe.brucker@arm.com>");
+MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>");
+MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d658c7c6a2ab..db7bfd4f2d20 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1665,6 +1665,36 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+			   struct iommu_cache_invalidate_info *inv_info)
+{
+	if (unlikely(!domain->ops->cache_invalidate))
+		return -ENODEV;
+
+	return domain->ops->cache_invalidate(domain, dev, inv_info);
+}
+EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+
+int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+			   struct device *dev, struct iommu_gpasid_bind_data *data)
+{
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, data);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid)
+{
+	if (unlikely(!domain->ops->sva_unbind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_unbind_gpasid(dev, pasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
@@ -1854,8 +1884,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 	return pgsize;
 }
 
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
+int __iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
@@ -1892,8 +1922,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
 
-		ret = ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
 			break;
 
@@ -1913,8 +1943,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	return ret;
 }
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	might_sleep();
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map);
 
+int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_atomic);
+
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
 			    struct iommu_iotlb_gather *iotlb_gather)
@@ -1991,8 +2035,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
+size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot,
+		    gfp_t gfp)
 {
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
@@ -2003,7 +2048,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		phys_addr_t s_phys = sg_phys(sg);
 
 		if (len && s_phys != start + len) {
-			ret = iommu_map(domain, iova + mapped, start, len, prot);
+			ret = __iommu_map(domain, iova + mapped, start,
+					len, prot, gfp);
+
 			if (ret)
 				goto out_err;
 
@@ -2031,8 +2078,22 @@ out_err:
 	return 0;
 
 }
+
+size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	might_sleep();
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
+size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_sg_atomic);
+
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 			       phys_addr_t paddr, u64 size, int prot)
 {
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 2639fc718117..d02edd2751f3 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -50,6 +50,9 @@ struct ipmmu_features {
 	bool twobit_imttbcr_sl0;
 	bool reserved_context;
 	bool cache_snoop;
+	unsigned int ctx_offset_base;
+	unsigned int ctx_offset_stride;
+	unsigned int utlb_offset_base;
 };
 
 struct ipmmu_vmsa_device {
@@ -99,125 +102,49 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev)
 
 #define IM_NS_ALIAS_OFFSET		0x800
 
-#define IM_CTX_SIZE			0x40
-
-#define IMCTR				0x0000
-#define IMCTR_TRE			(1 << 17)
-#define IMCTR_AFE			(1 << 16)
-#define IMCTR_RTSEL_MASK		(3 << 4)
-#define IMCTR_RTSEL_SHIFT		4
-#define IMCTR_TREN			(1 << 3)
-#define IMCTR_INTEN			(1 << 2)
-#define IMCTR_FLUSH			(1 << 1)
-#define IMCTR_MMUEN			(1 << 0)
-
-#define IMCAAR				0x0004
-
-#define IMTTBCR				0x0008
-#define IMTTBCR_EAE			(1 << 31)
-#define IMTTBCR_PMB			(1 << 30)
-#define IMTTBCR_SH1_NON_SHAREABLE	(0 << 28)	/* R-Car Gen2 only */
-#define IMTTBCR_SH1_OUTER_SHAREABLE	(2 << 28)	/* R-Car Gen2 only */
-#define IMTTBCR_SH1_INNER_SHAREABLE	(3 << 28)	/* R-Car Gen2 only */
-#define IMTTBCR_SH1_MASK		(3 << 28)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN1_NC		(0 << 26)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN1_WB_WA		(1 << 26)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN1_WT		(2 << 26)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN1_WB		(3 << 26)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN1_MASK		(3 << 26)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN1_NC		(0 << 24)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN1_WB_WA		(1 << 24)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN1_WT		(2 << 24)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN1_WB		(3 << 24)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN1_MASK		(3 << 24)	/* R-Car Gen2 only */
-#define IMTTBCR_TSZ1_MASK		(7 << 16)
-#define IMTTBCR_TSZ1_SHIFT		16
-#define IMTTBCR_SH0_NON_SHAREABLE	(0 << 12)	/* R-Car Gen2 only */
-#define IMTTBCR_SH0_OUTER_SHAREABLE	(2 << 12)	/* R-Car Gen2 only */
+/* MMU "context" registers */
+#define IMCTR				0x0000		/* R-Car Gen2/3 */
+#define IMCTR_INTEN			(1 << 2)	/* R-Car Gen2/3 */
+#define IMCTR_FLUSH			(1 << 1)	/* R-Car Gen2/3 */
+#define IMCTR_MMUEN			(1 << 0)	/* R-Car Gen2/3 */
+
+#define IMTTBCR				0x0008		/* R-Car Gen2/3 */
+#define IMTTBCR_EAE			(1 << 31)	/* R-Car Gen2/3 */
 #define IMTTBCR_SH0_INNER_SHAREABLE	(3 << 12)	/* R-Car Gen2 only */
-#define IMTTBCR_SH0_MASK		(3 << 12)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN0_NC		(0 << 10)	/* R-Car Gen2 only */
 #define IMTTBCR_ORGN0_WB_WA		(1 << 10)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN0_WT		(2 << 10)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN0_WB		(3 << 10)	/* R-Car Gen2 only */
-#define IMTTBCR_ORGN0_MASK		(3 << 10)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN0_NC		(0 << 8)	/* R-Car Gen2 only */
 #define IMTTBCR_IRGN0_WB_WA		(1 << 8)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN0_WT		(2 << 8)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN0_WB		(3 << 8)	/* R-Car Gen2 only */
-#define IMTTBCR_IRGN0_MASK		(3 << 8)	/* R-Car Gen2 only */
-#define IMTTBCR_SL0_TWOBIT_LVL_3	(0 << 6)	/* R-Car Gen3 only */
-#define IMTTBCR_SL0_TWOBIT_LVL_2	(1 << 6)	/* R-Car Gen3 only */
 #define IMTTBCR_SL0_TWOBIT_LVL_1	(2 << 6)	/* R-Car Gen3 only */
-#define IMTTBCR_SL0_LVL_2		(0 << 4)
-#define IMTTBCR_SL0_LVL_1		(1 << 4)
-#define IMTTBCR_TSZ0_MASK		(7 << 0)
-#define IMTTBCR_TSZ0_SHIFT		O
-
-#define IMBUSCR				0x000c
-#define IMBUSCR_DVM			(1 << 2)
-#define IMBUSCR_BUSSEL_SYS		(0 << 0)
-#define IMBUSCR_BUSSEL_CCI		(1 << 0)
-#define IMBUSCR_BUSSEL_IMCAAR		(2 << 0)
-#define IMBUSCR_BUSSEL_CCI_IMCAAR	(3 << 0)
-#define IMBUSCR_BUSSEL_MASK		(3 << 0)
-
-#define IMTTLBR0			0x0010
-#define IMTTUBR0			0x0014
-#define IMTTLBR1			0x0018
-#define IMTTUBR1			0x001c
-
-#define IMSTR				0x0020
-#define IMSTR_ERRLVL_MASK		(3 << 12)
-#define IMSTR_ERRLVL_SHIFT		12
-#define IMSTR_ERRCODE_TLB_FORMAT	(1 << 8)
-#define IMSTR_ERRCODE_ACCESS_PERM	(4 << 8)
-#define IMSTR_ERRCODE_SECURE_ACCESS	(5 << 8)
-#define IMSTR_ERRCODE_MASK		(7 << 8)
-#define IMSTR_MHIT			(1 << 4)
-#define IMSTR_ABORT			(1 << 2)
-#define IMSTR_PF			(1 << 1)
-#define IMSTR_TF			(1 << 0)
-
-#define IMMAIR0				0x0028
-#define IMMAIR1				0x002c
-#define IMMAIR_ATTR_MASK		0xff
-#define IMMAIR_ATTR_DEVICE		0x04
-#define IMMAIR_ATTR_NC			0x44
-#define IMMAIR_ATTR_WBRWA		0xff
-#define IMMAIR_ATTR_SHIFT(n)		((n) << 3)
-#define IMMAIR_ATTR_IDX_NC		0
-#define IMMAIR_ATTR_IDX_WBRWA		1
-#define IMMAIR_ATTR_IDX_DEV		2
-
-#define IMELAR				0x0030	/* IMEAR on R-Car Gen2 */
-#define IMEUAR				0x0034	/* R-Car Gen3 only */
-
-#define IMPCTR				0x0200
-#define IMPSTR				0x0208
-#define IMPEAR				0x020c
-#define IMPMBA(n)			(0x0280 + ((n) * 4))
-#define IMPMBD(n)			(0x02c0 + ((n) * 4))
+#define IMTTBCR_SL0_LVL_1		(1 << 4)	/* R-Car Gen2 only */
+
+#define IMBUSCR				0x000c		/* R-Car Gen2 only */
+#define IMBUSCR_DVM			(1 << 2)	/* R-Car Gen2 only */
+#define IMBUSCR_BUSSEL_MASK		(3 << 0)	/* R-Car Gen2 only */
+
+#define IMTTLBR0			0x0010		/* R-Car Gen2/3 */
+#define IMTTUBR0			0x0014		/* R-Car Gen2/3 */
+
+#define IMSTR				0x0020		/* R-Car Gen2/3 */
+#define IMSTR_MHIT			(1 << 4)	/* R-Car Gen2/3 */
+#define IMSTR_ABORT			(1 << 2)	/* R-Car Gen2/3 */
+#define IMSTR_PF			(1 << 1)	/* R-Car Gen2/3 */
+#define IMSTR_TF			(1 << 0)	/* R-Car Gen2/3 */
 
+#define IMMAIR0				0x0028		/* R-Car Gen2/3 */
+
+#define IMELAR				0x0030		/* R-Car Gen2/3, IMEAR on R-Car Gen2 */
+#define IMEUAR				0x0034		/* R-Car Gen3 only */
+
+/* uTLB registers */
 #define IMUCTR(n)			((n) < 32 ? IMUCTR0(n) : IMUCTR32(n))
-#define IMUCTR0(n)			(0x0300 + ((n) * 16))
-#define IMUCTR32(n)			(0x0600 + (((n) - 32) * 16))
-#define IMUCTR_FIXADDEN			(1 << 31)
-#define IMUCTR_FIXADD_MASK		(0xff << 16)
-#define IMUCTR_FIXADD_SHIFT		16
-#define IMUCTR_TTSEL_MMU(n)		((n) << 4)
-#define IMUCTR_TTSEL_PMB		(8 << 4)
-#define IMUCTR_TTSEL_MASK		(15 << 4)
-#define IMUCTR_FLUSH			(1 << 1)
-#define IMUCTR_MMUEN			(1 << 0)
+#define IMUCTR0(n)			(0x0300 + ((n) * 16))		/* R-Car Gen2/3 */
+#define IMUCTR32(n)			(0x0600 + (((n) - 32) * 16))	/* R-Car Gen3 only */
+#define IMUCTR_TTSEL_MMU(n)		((n) << 4)	/* R-Car Gen2/3 */
+#define IMUCTR_FLUSH			(1 << 1)	/* R-Car Gen2/3 */
+#define IMUCTR_MMUEN			(1 << 0)	/* R-Car Gen2/3 */
 
 #define IMUASID(n)			((n) < 32 ? IMUASID0(n) : IMUASID32(n))
-#define IMUASID0(n)			(0x0308 + ((n) * 16))
-#define IMUASID32(n)			(0x0608 + (((n) - 32) * 16))
-#define IMUASID_ASID8_MASK		(0xff << 8)
-#define IMUASID_ASID8_SHIFT		8
-#define IMUASID_ASID0_MASK		(0xff << 0)
-#define IMUASID_ASID0_SHIFT		0
+#define IMUASID0(n)			(0x0308 + ((n) * 16))		/* R-Car Gen2/3 */
+#define IMUASID32(n)			(0x0608 + (((n) - 32) * 16))	/* R-Car Gen3 only */
 
 /* -----------------------------------------------------------------------------
  * Root device handling
@@ -264,29 +191,61 @@ static void ipmmu_write(struct ipmmu_vmsa_device *mmu, unsigned int offset,
 	iowrite32(data, mmu->base + offset);
 }
 
+static unsigned int ipmmu_ctx_reg(struct ipmmu_vmsa_device *mmu,
+				  unsigned int context_id, unsigned int reg)
+{
+	return mmu->features->ctx_offset_base +
+	       context_id * mmu->features->ctx_offset_stride + reg;
+}
+
+static u32 ipmmu_ctx_read(struct ipmmu_vmsa_device *mmu,
+			  unsigned int context_id, unsigned int reg)
+{
+	return ipmmu_read(mmu, ipmmu_ctx_reg(mmu, context_id, reg));
+}
+
+static void ipmmu_ctx_write(struct ipmmu_vmsa_device *mmu,
+			    unsigned int context_id, unsigned int reg, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_ctx_reg(mmu, context_id, reg), data);
+}
+
 static u32 ipmmu_ctx_read_root(struct ipmmu_vmsa_domain *domain,
 			       unsigned int reg)
 {
-	return ipmmu_read(domain->mmu->root,
-			  domain->context_id * IM_CTX_SIZE + reg);
+	return ipmmu_ctx_read(domain->mmu->root, domain->context_id, reg);
 }
 
 static void ipmmu_ctx_write_root(struct ipmmu_vmsa_domain *domain,
 				 unsigned int reg, u32 data)
 {
-	ipmmu_write(domain->mmu->root,
-		    domain->context_id * IM_CTX_SIZE + reg, data);
+	ipmmu_ctx_write(domain->mmu->root, domain->context_id, reg, data);
 }
 
 static void ipmmu_ctx_write_all(struct ipmmu_vmsa_domain *domain,
 				unsigned int reg, u32 data)
 {
 	if (domain->mmu != domain->mmu->root)
-		ipmmu_write(domain->mmu,
-			    domain->context_id * IM_CTX_SIZE + reg, data);
+		ipmmu_ctx_write(domain->mmu, domain->context_id, reg, data);
 
-	ipmmu_write(domain->mmu->root,
-		    domain->context_id * IM_CTX_SIZE + reg, data);
+	ipmmu_ctx_write(domain->mmu->root, domain->context_id, reg, data);
+}
+
+static u32 ipmmu_utlb_reg(struct ipmmu_vmsa_device *mmu, unsigned int reg)
+{
+	return mmu->features->utlb_offset_base + reg;
+}
+
+static void ipmmu_imuasid_write(struct ipmmu_vmsa_device *mmu,
+				unsigned int utlb, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_utlb_reg(mmu, IMUASID(utlb)), data);
+}
+
+static void ipmmu_imuctr_write(struct ipmmu_vmsa_device *mmu,
+			       unsigned int utlb, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_utlb_reg(mmu, IMUCTR(utlb)), data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -334,11 +293,10 @@ static void ipmmu_utlb_enable(struct ipmmu_vmsa_domain *domain,
 	 */
 
 	/* TODO: What should we set the ASID to ? */
-	ipmmu_write(mmu, IMUASID(utlb), 0);
+	ipmmu_imuasid_write(mmu, utlb, 0);
 	/* TODO: Do we need to flush the microTLB ? */
-	ipmmu_write(mmu, IMUCTR(utlb),
-		    IMUCTR_TTSEL_MMU(domain->context_id) | IMUCTR_FLUSH |
-		    IMUCTR_MMUEN);
+	ipmmu_imuctr_write(mmu, utlb, IMUCTR_TTSEL_MMU(domain->context_id) |
+				      IMUCTR_FLUSH | IMUCTR_MMUEN);
 	mmu->utlb_ctx[utlb] = domain->context_id;
 }
 
@@ -350,7 +308,7 @@ static void ipmmu_utlb_disable(struct ipmmu_vmsa_domain *domain,
 {
 	struct ipmmu_vmsa_device *mmu = domain->mmu;
 
-	ipmmu_write(mmu, IMUCTR(utlb), 0);
+	ipmmu_imuctr_write(mmu, utlb, 0);
 	mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID;
 }
 
@@ -438,7 +396,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 
 	/* MAIR0 */
 	ipmmu_ctx_write_root(domain, IMMAIR0,
-			     domain->cfg.arm_lpae_s1_cfg.mair[0]);
+			     domain->cfg.arm_lpae_s1_cfg.mair);
 
 	/* IMBUSCR */
 	if (domain->mmu->features->setup_imbuscr)
@@ -724,7 +682,7 @@ 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)
+		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
@@ -783,6 +741,7 @@ static int ipmmu_init_platform_device(struct device *dev,
 
 static const struct soc_device_attribute soc_rcar_gen3[] = {
 	{ .soc_id = "r8a774a1", },
+	{ .soc_id = "r8a774b1", },
 	{ .soc_id = "r8a774c0", },
 	{ .soc_id = "r8a7795", },
 	{ .soc_id = "r8a7796", },
@@ -794,6 +753,7 @@ static const struct soc_device_attribute soc_rcar_gen3[] = {
 };
 
 static const struct soc_device_attribute soc_rcar_gen3_whitelist[] = {
+	{ .soc_id = "r8a774b1", },
 	{ .soc_id = "r8a774c0", },
 	{ .soc_id = "r8a7795", .revision = "ES3.*" },
 	{ .soc_id = "r8a77965", },
@@ -985,7 +945,7 @@ static void ipmmu_device_reset(struct ipmmu_vmsa_device *mmu)
 
 	/* Disable all contexts. */
 	for (i = 0; i < mmu->num_ctx; ++i)
-		ipmmu_write(mmu, i * IM_CTX_SIZE + IMCTR, 0);
+		ipmmu_ctx_write(mmu, i, IMCTR, 0);
 }
 
 static const struct ipmmu_features ipmmu_features_default = {
@@ -997,6 +957,9 @@ static const struct ipmmu_features ipmmu_features_default = {
 	.twobit_imttbcr_sl0 = false,
 	.reserved_context = false,
 	.cache_snoop = true,
+	.ctx_offset_base = 0,
+	.ctx_offset_stride = 0x40,
+	.utlb_offset_base = 0,
 };
 
 static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
@@ -1008,6 +971,9 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
 	.twobit_imttbcr_sl0 = true,
 	.reserved_context = true,
 	.cache_snoop = false,
+	.ctx_offset_base = 0,
+	.ctx_offset_stride = 0x40,
+	.utlb_offset_base = 0,
 };
 
 static const struct of_device_id ipmmu_of_ids[] = {
@@ -1018,6 +984,9 @@ static const struct of_device_id ipmmu_of_ids[] = {
 		.compatible = "renesas,ipmmu-r8a774a1",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
+		.compatible = "renesas,ipmmu-r8a774b1",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
 		.compatible = "renesas,ipmmu-r8a774c0",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index be99d408cf35..93f14bca26ee 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -504,7 +504,7 @@ fail:
 }
 
 static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t pa, size_t len, int prot)
+			 phys_addr_t pa, size_t len, int prot, gfp_t gfp)
 {
 	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 67a483c1a935..6fc1f5ecf91e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -101,8 +101,6 @@
 #define MTK_M4U_TO_PORT(id)		((id) & 0x1f)
 
 struct mtk_iommu_domain {
-	spinlock_t			pgtlock; /* lock for page table */
-
 	struct io_pgtable_cfg		cfg;
 	struct io_pgtable_ops		*iop;
 
@@ -173,13 +171,16 @@ static void mtk_iommu_tlb_flush_all(void *cookie)
 	}
 }
 
-static void mtk_iommu_tlb_add_flush_nosync(unsigned long iova, size_t size,
-					   size_t granule, bool leaf,
-					   void *cookie)
+static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
+					   size_t granule, void *cookie)
 {
 	struct mtk_iommu_data *data = cookie;
+	unsigned long flags;
+	int ret;
+	u32 tmp;
 
 	for_each_m4u(data) {
+		spin_lock_irqsave(&data->tlb_lock, flags);
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + REG_MMU_INV_SEL);
 
@@ -188,23 +189,10 @@ static void mtk_iommu_tlb_add_flush_nosync(unsigned long iova, size_t size,
 			       data->base + REG_MMU_INVLD_END_A);
 		writel_relaxed(F_MMU_INV_RANGE,
 			       data->base + REG_MMU_INVALIDATE);
-		data->tlb_flush_active = true;
-	}
-}
-
-static void mtk_iommu_tlb_sync(void *cookie)
-{
-	struct mtk_iommu_data *data = cookie;
-	int ret;
-	u32 tmp;
-
-	for_each_m4u(data) {
-		/* Avoid timing out if there's nothing to wait for */
-		if (!data->tlb_flush_active)
-			return;
 
+		/* tlb sync */
 		ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
-						tmp, tmp != 0, 10, 100000);
+						tmp, tmp != 0, 10, 1000);
 		if (ret) {
 			dev_warn(data->dev,
 				 "Partial TLB flush timed out, falling back to full flush\n");
@@ -212,35 +200,24 @@ static void mtk_iommu_tlb_sync(void *cookie)
 		}
 		/* Clear the CPE status */
 		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
-		data->tlb_flush_active = false;
+		spin_unlock_irqrestore(&data->tlb_lock, flags);
 	}
 }
 
-static void mtk_iommu_tlb_flush_walk(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, false, cookie);
-	mtk_iommu_tlb_sync(cookie);
-}
-
-static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, true, cookie);
-	mtk_iommu_tlb_sync(cookie);
-}
-
 static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
 					    unsigned long iova, size_t granule,
 					    void *cookie)
 {
-	mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
+	struct mtk_iommu_data *data = cookie;
+	struct iommu_domain *domain = &data->m4u_dom->domain;
+
+	iommu_iotlb_gather_add_page(domain, gather, iova, granule);
 }
 
 static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
-	.tlb_flush_walk = mtk_iommu_tlb_flush_walk,
-	.tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
+	.tlb_flush_walk = mtk_iommu_tlb_flush_range_sync,
+	.tlb_flush_leaf = mtk_iommu_tlb_flush_range_sync,
 	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
 };
 
@@ -316,8 +293,6 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 {
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 
-	spin_lock_init(&dom->pgtlock);
-
 	dom->cfg = (struct io_pgtable_cfg) {
 		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
 			IO_PGTABLE_QUIRK_NO_PERMS |
@@ -412,22 +387,17 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-	unsigned long flags;
-	int ret;
 
 	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
 	if (data->enable_4GB)
 		paddr |= BIT_ULL(32);
 
-	spin_lock_irqsave(&dom->pgtlock, flags);
-	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
-
-	return ret;
+	/* Synchronize with the tlb_lock */
+	return dom->iop->map(dom->iop, iova, paddr, size, prot);
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
@@ -435,25 +405,26 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	unsigned long flags;
-	size_t unmapsz;
-
-	spin_lock_irqsave(&dom->pgtlock, flags);
-	unmapsz = dom->iop->unmap(dom->iop, iova, size, gather);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
-	return unmapsz;
+	return dom->iop->unmap(dom->iop, iova, size, gather);
 }
 
 static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
-	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+	mtk_iommu_tlb_flush_all(mtk_iommu_get_m4u_data());
 }
 
 static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
-	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	size_t length = gather->end - gather->start;
+
+	if (gather->start == ULONG_MAX)
+		return;
+
+	mtk_iommu_tlb_flush_range_sync(gather->start, length, gather->pgsize,
+				       data);
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -461,13 +432,9 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-	unsigned long flags;
 	phys_addr_t pa;
 
-	spin_lock_irqsave(&dom->pgtlock, flags);
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
-
 	if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
 		pa &= ~BIT_ULL(32);
 
@@ -733,6 +700,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	spin_lock_init(&data->tlb_lock);
 	list_add_tail(&data->list, &m4ulist);
 
 	if (!iommu_present(&platform_bus_type))
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index fc0f16eabacd..ea949a324e33 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -57,7 +57,7 @@ struct mtk_iommu_data {
 	struct mtk_iommu_domain		*m4u_dom;
 	struct iommu_group		*m4u_group;
 	bool                            enable_4GB;
-	bool				tlb_flush_active;
+	spinlock_t			tlb_lock; /* lock for tlb range flush */
 
 	struct iommu_device		iommu;
 	const struct mtk_iommu_plat_data *plat_data;
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index b5efd6dac953..e93b94ecac45 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 614a93aa5305..026ad2b29dcd 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -8,6 +8,8 @@
 #include <linux/export.h>
 #include <linux/iommu.h>
 #include <linux/limits.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
 #include <linux/of_pci.h>
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 09c6e1c680db..be551cc34be4 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1339,7 +1339,7 @@ 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)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct device *dev = omap_domain->dev;
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c31e7bc4ccbe..52f38292df5b 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -284,9 +284,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[0]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair);
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[1]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
 
 		/* SCTLR */
 		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
@@ -423,7 +423,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	unsigned long flags;
@@ -539,8 +539,8 @@ static int qcom_iommu_add_device(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR_OR_NULL(group))
-		return PTR_ERR_OR_ZERO(group);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
 
 	iommu_group_put(group);
 	iommu_device_link(&qcom_iommu->iommu, dev);
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 4dcbf68dfda4..b33cdd5aad81 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -527,7 +527,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
 	int i, err;
 
 	err = pm_runtime_get_if_in_use(iommu->dev);
-	if (WARN_ON_ONCE(err <= 0))
+	if (!err || WARN_ON_ONCE(err < 0))
 		return ret;
 
 	if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)))
@@ -758,7 +758,7 @@ unwind:
 }
 
 static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
@@ -980,13 +980,13 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 	if (!dma_dev)
 		return NULL;
 
-	rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL);
+	rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL);
 	if (!rk_domain)
 		return NULL;
 
 	if (type == IOMMU_DOMAIN_DMA &&
 	    iommu_get_dma_cookie(&rk_domain->domain))
-		return NULL;
+		goto err_free_domain;
 
 	/*
 	 * rk32xx iommus use a 2 level pagetable.
@@ -1021,6 +1021,8 @@ err_free_dt:
 err_put_cookie:
 	if (type == IOMMU_DOMAIN_DMA)
 		iommu_put_dma_cookie(&rk_domain->domain);
+err_free_domain:
+	kfree(rk_domain);
 
 	return NULL;
 }
@@ -1049,6 +1051,7 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
 
 	if (domain->type == IOMMU_DOMAIN_DMA)
 		iommu_put_dma_cookie(&rk_domain->domain);
+	kfree(rk_domain);
 }
 
 static int rk_iommu_add_device(struct device *dev)
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 3b0b18e23187..1137f3ddcb85 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -265,7 +265,7 @@ undo_cpu_trans:
 }
 
 static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
 	int flags = ZPCI_PTE_VALID, rc = 0;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 3924f7c05544..3fb7ba72507d 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova,
 }
 
 static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t pa, size_t bytes, int prot)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct gart_device *gart = gart_handle;
 	int ret;
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 7293fc3f796d..63a147b623e6 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -159,9 +159,9 @@ static bool smmu_dma_addr_valid(struct tegra_smmu *smmu, dma_addr_t addr)
 	return (addr & smmu->pfn_mask) == addr;
 }
 
-static dma_addr_t smmu_pde_to_dma(u32 pde)
+static dma_addr_t smmu_pde_to_dma(struct tegra_smmu *smmu, u32 pde)
 {
-	return pde << 12;
+	return (dma_addr_t)(pde & smmu->pfn_mask) << 12;
 }
 
 static void smmu_flush_ptc_all(struct tegra_smmu *smmu)
@@ -240,7 +240,7 @@ static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
 
 static inline void smmu_flush(struct tegra_smmu *smmu)
 {
-	smmu_readl(smmu, SMMU_CONFIG);
+	smmu_readl(smmu, SMMU_PTB_ASID);
 }
 
 static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
@@ -351,6 +351,20 @@ static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
 	unsigned int i;
 	u32 value;
 
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value |= SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	} else {
+		pr_warn("%s group from swgroup %u not found\n", __func__,
+				swgroup);
+		/* No point moving ahead if group was not found */
+		return;
+	}
+
 	for (i = 0; i < smmu->soc->num_clients; i++) {
 		const struct tegra_mc_client *client = &smmu->soc->clients[i];
 
@@ -361,15 +375,6 @@ static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
 		value |= BIT(client->smmu.bit);
 		smmu_writel(smmu, value, client->smmu.reg);
 	}
-
-	group = tegra_smmu_find_swgroup(smmu, swgroup);
-	if (group) {
-		value = smmu_readl(smmu, group->reg);
-		value &= ~SMMU_ASID_MASK;
-		value |= SMMU_ASID_VALUE(asid);
-		value |= SMMU_ASID_ENABLE;
-		smmu_writel(smmu, value, group->reg);
-	}
 }
 
 static void tegra_smmu_disable(struct tegra_smmu *smmu, unsigned int swgroup,
@@ -549,6 +554,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
 				  dma_addr_t *dmap)
 {
 	unsigned int pd_index = iova_pd_index(iova);
+	struct tegra_smmu *smmu = as->smmu;
 	struct page *pt_page;
 	u32 *pd;
 
@@ -557,7 +563,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
 		return NULL;
 
 	pd = page_address(as->pd);
-	*dmap = smmu_pde_to_dma(pd[pd_index]);
+	*dmap = smmu_pde_to_dma(smmu, pd[pd_index]);
 
 	return tegra_smmu_pte_offset(pt_page, iova);
 }
@@ -599,7 +605,7 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
 	} else {
 		u32 *pd = page_address(as->pd);
 
-		*dmap = smmu_pde_to_dma(pd[pde]);
+		*dmap = smmu_pde_to_dma(smmu, pd[pde]);
 	}
 
 	return tegra_smmu_pte_offset(as->pts[pde], iova);
@@ -624,7 +630,7 @@ static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova)
 	if (--as->count[pde] == 0) {
 		struct tegra_smmu *smmu = as->smmu;
 		u32 *pd = page_address(as->pd);
-		dma_addr_t pte_dma = smmu_pde_to_dma(pd[pde]);
+		dma_addr_t pte_dma = smmu_pde_to_dma(smmu, pd[pde]);
 
 		tegra_smmu_set_pde(as, iova, 0);
 
@@ -650,7 +656,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
 }
 
 static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 3ea9d7682999..315c7cc4f99d 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -153,7 +153,6 @@ static off_t viommu_get_write_desc_offset(struct viommu_dev *viommu,
  */
 static int __viommu_sync_req(struct viommu_dev *viommu)
 {
-	int ret = 0;
 	unsigned int len;
 	size_t write_len;
 	struct viommu_request *req;
@@ -182,7 +181,7 @@ static int __viommu_sync_req(struct viommu_dev *viommu)
 		kfree(req);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int viommu_sync_req(struct viommu_dev *viommu)
@@ -713,7 +712,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 }
 
 static int viommu_map(struct iommu_domain *domain, unsigned long iova,
-		      phys_addr_t paddr, size_t size, int prot)
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	u32 flags;