Merge tag 'iommu-updates-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Intel VT-d driver updates:
     - Domain force snooping improvement.
     - Cleanups, no intentional functional changes.

 - ARM SMMU driver updates:
     - Add new Qualcomm device-tree compatible strings
     - Add new Nvidia device-tree compatible string for Tegra234
     - Fix UAF in SMMUv3 shared virtual addressing code
     - Force identity-mapped domains for users of ye olde SMMU legacy
       binding
     - Minor cleanups

 - Fix a BUG_ON in the vfio_iommu_group_notifier:
     - Groundwork for upcoming iommufd framework
     - Introduction of DMA ownership so that an entire IOMMU group is
       either controlled by the kernel or by user-space

 - MT8195 and MT8186 support in the Mediatek IOMMU driver

 - Make forcing of cache-coherent DMA more coherent between IOMMU
   drivers

 - Fixes for thunderbolt device DMA protection

 - Various smaller fixes and cleanups

* tag 'iommu-updates-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (88 commits)
  iommu/amd: Increase timeout waiting for GA log enablement
  iommu/s390: Tolerate repeat attach_dev calls
  iommu/vt-d: Remove hard coding PGSNP bit in PASID entries
  iommu/vt-d: Remove domain_update_iommu_snooping()
  iommu/vt-d: Check domain force_snooping against attached devices
  iommu/vt-d: Block force-snoop domain attaching if no SC support
  iommu/vt-d: Size Page Request Queue to avoid overflow condition
  iommu/vt-d: Fold dmar_insert_one_dev_info() into its caller
  iommu/vt-d: Change return type of dmar_insert_one_dev_info()
  iommu/vt-d: Remove unneeded validity check on dev
  iommu/dma: Explicitly sort PCI DMA windows
  iommu/dma: Fix iova map result check bug
  iommu/mediatek: Fix NULL pointer dereference when printing dev_name
  iommu: iommu_group_claim_dma_owner() must always assign a domain
  iommu/arm-smmu: Force identity domains for legacy binding
  iommu/arm-smmu: Support Tegra234 SMMU
  dt-bindings: arm-smmu: Add compatible for Tegra234 SOC
  dt-bindings: arm-smmu: Document nvidia,memory-controller property
  iommu/arm-smmu-qcom: Add SC8280XP support
  dt-bindings: arm-smmu: Add compatible for Qualcomm SC8280XP
  ...

21 files changed, 1362 insertions, 714 deletions

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 47108ed44fbb..72d0f5e2f651 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -407,6 +407,7 @@
 /* IOMMU IVINFO */
 #define IOMMU_IVINFO_OFFSET     36
 #define IOMMU_IVINFO_EFRSUP     BIT(0)
+#define IOMMU_IVINFO_DMA_REMAP  BIT(1)
 
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
 #define IOMMU_FEAT_GASUP_SHIFT	6
@@ -449,6 +450,9 @@ extern struct irq_remap_table **irq_lookup_table;
 /* Interrupt remapping feature used? */
 extern bool amd_iommu_irq_remap;
 
+/* IVRS indicates that pre-boot remapping was enabled */
+extern bool amdr_ivrs_remap_support;
+
 /* kmem_cache to get tables with 128 byte alignement */
 extern struct kmem_cache *amd_iommu_irq_cache;
 
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 1a3ad58ba846..1d08f87e734b 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -83,7 +83,7 @@
 #define ACPI_DEVFLAG_LINT1              0x80
 #define ACPI_DEVFLAG_ATSDIS             0x10000000
 
-#define LOOP_TIMEOUT	100000
+#define LOOP_TIMEOUT	2000000
 /*
  * ACPI table definitions
  *
@@ -181,6 +181,7 @@ u32 amd_iommu_max_pasid __read_mostly = ~0;
 
 bool amd_iommu_v2_present __read_mostly;
 static bool amd_iommu_pc_present __read_mostly;
+bool amdr_ivrs_remap_support __read_mostly;
 
 bool amd_iommu_force_isolation __read_mostly;
 
@@ -325,6 +326,8 @@ static void __init early_iommu_features_init(struct amd_iommu *iommu,
 {
 	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP)
 		iommu->features = h->efr_reg;
+	if (amd_iommu_ivinfo & IOMMU_IVINFO_DMA_REMAP)
+		amdr_ivrs_remap_support = true;
 }
 
 /* Access to l1 and l2 indexed register spaces */
@@ -1985,8 +1988,7 @@ static int __init amd_iommu_init_pci(void)
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
 
-	if (!ret)
-		print_iommu_info();
+	print_iommu_info();
 
 out:
 	return ret;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b47220ac09ea..840831d5d2ad 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1838,20 +1838,10 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 	amd_iommu_domain_flush_complete(domain);
 }
 
-static void __init amd_iommu_init_dma_ops(void)
-{
-	if (iommu_default_passthrough() || sme_me_mask)
-		x86_swiotlb_enable = true;
-	else
-		x86_swiotlb_enable = false;
-}
-
 int __init amd_iommu_init_api(void)
 {
 	int err;
 
-	amd_iommu_init_dma_ops();
-
 	err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
 	if (err)
 		return err;
@@ -2165,6 +2155,8 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 		return (irq_remapping_enabled == 1);
 	case IOMMU_CAP_NOEXEC:
 		return false;
+	case IOMMU_CAP_PRE_BOOT_PROTECTION:
+		return amdr_ivrs_remap_support;
 	default:
 		break;
 	}
@@ -2274,6 +2266,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	return 0;
 }
 
+static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	/* IOMMU_PTE_FC is always set */
+	return true;
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -2296,6 +2294,7 @@ const struct iommu_ops amd_iommu_ops = {
 		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
 		.iotlb_sync	= amd_iommu_iotlb_sync,
 		.free		= amd_iommu_domain_free,
+		.enforce_cache_coherency = amd_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index e56b137ceabd..afb3efd565b7 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -956,6 +956,7 @@ static void __exit amd_iommu_v2_exit(void)
 {
 	struct device_state *dev_state, *next;
 	unsigned long flags;
+	LIST_HEAD(freelist);
 
 	if (!amd_iommu_v2_supported())
 		return;
@@ -975,11 +976,20 @@ static void __exit amd_iommu_v2_exit(void)
 
 		put_device_state(dev_state);
 		list_del(&dev_state->list);
-		free_device_state(dev_state);
+		list_add_tail(&dev_state->list, &freelist);
 	}
 
 	spin_unlock_irqrestore(&state_lock, flags);
 
+	/*
+	 * Since free_device_state waits on the count to be zero,
+	 * we need to free dev_state outside the spinlock.
+	 */
+	list_for_each_entry_safe(dev_state, next, &freelist, list) {
+		list_del(&dev_state->list);
+		free_device_state(dev_state);
+	}
+
 	destroy_workqueue(iommu_wq);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index c623dae1e115..1ef7bbb4acf3 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
 #include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 
 #include "arm-smmu-v3.h"
@@ -96,9 +97,14 @@ static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 	struct arm_smmu_ctx_desc *cd;
 	struct arm_smmu_ctx_desc *ret = NULL;
 
+	/* Don't free the mm until we release the ASID */
+	mmgrab(mm);
+
 	asid = arm64_mm_context_get(mm);
-	if (!asid)
-		return ERR_PTR(-ESRCH);
+	if (!asid) {
+		err = -ESRCH;
+		goto out_drop_mm;
+	}
 
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
 	if (!cd) {
@@ -165,6 +171,8 @@ out_free_cd:
 	kfree(cd);
 out_put_context:
 	arm64_mm_context_put(mm);
+out_drop_mm:
+	mmdrop(mm);
 	return err < 0 ? ERR_PTR(err) : ret;
 }
 
@@ -173,6 +181,7 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
 	if (arm_smmu_free_asid(cd)) {
 		/* Unpin ASID */
 		arm64_mm_context_put(cd->mm);
+		mmdrop(cd->mm);
 		kfree(cd);
 	}
 }
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 627a3ed5ee8f..88817a3376ef 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3770,6 +3770,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Base address */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	if (resource_size(res) < arm_smmu_resource_size(smmu)) {
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index 2c25cce38060..658f3cc83278 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -211,7 +211,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
-	if (of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
+	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
 	    of_device_is_compatible(np, "nvidia,tegra186-smmu"))
 		return nvidia_smmu_impl_init(smmu);
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index ba6298c7140e..7820711c4560 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -408,6 +408,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sc7180-smmu-500" },
 	{ .compatible = "qcom,sc7280-smmu-500" },
 	{ .compatible = "qcom,sc8180x-smmu-500" },
+	{ .compatible = "qcom,sc8280xp-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 568cce590ccc..2ed3594f384e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1574,6 +1574,9 @@ static int arm_smmu_def_domain_type(struct device *dev)
 	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
 	const struct arm_smmu_impl *impl = cfg->smmu->impl;
 
+	if (using_legacy_binding)
+		return IOMMU_DOMAIN_IDENTITY;
+
 	if (impl && impl->def_domain_type)
 		return impl->def_domain_type(dev);
 
@@ -2092,11 +2095,10 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ioaddr = res->start;
-	smmu->base = devm_ioremap_resource(dev, res);
+	smmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
+	ioaddr = res->start;
 	/*
 	 * The resource size should effectively match the value of SMMU_TOP;
 	 * stash that temporarily until we know PAGESIZE to validate it with.
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 09f6e1c0f9c0..f90251572a5d 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/iova.h>
 #include <linux/irq.h>
+#include <linux/list_sort.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -414,6 +415,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
 	return 0;
 }
 
+static int iommu_dma_ranges_sort(void *priv, const struct list_head *a,
+		const struct list_head *b)
+{
+	struct resource_entry *res_a = list_entry(a, typeof(*res_a), node);
+	struct resource_entry *res_b = list_entry(b, typeof(*res_b), node);
+
+	return res_a->res->start > res_b->res->start;
+}
+
 static int iova_reserve_pci_windows(struct pci_dev *dev,
 		struct iova_domain *iovad)
 {
@@ -432,6 +442,7 @@ static int iova_reserve_pci_windows(struct pci_dev *dev,
 	}
 
 	/* Get reserved DMA windows from host bridge */
+	list_sort(NULL, &bridge->dma_ranges, iommu_dma_ranges_sort);
 	resource_list_for_each_entry(window, &bridge->dma_ranges) {
 		end = window->res->start - window->offset;
 resv_iova:
@@ -440,7 +451,7 @@ resv_iova:
 			hi = iova_pfn(iovad, end);
 			reserve_iova(iovad, lo, hi);
 		} else if (end < start) {
-			/* dma_ranges list should be sorted */
+			/* DMA ranges should be non-overlapping */
 			dev_err(&dev->dev,
 				"Failed to reserve IOVA [%pa-%pa]\n",
 				&start, &end);
@@ -776,6 +787,7 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	dma_addr_t iova;
+	ssize_t ret;
 
 	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
 	    iommu_deferred_attach(dev, domain))
@@ -813,8 +825,8 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot)
-			< size)
+	ret = iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot);
+	if (ret < 0 || ret < size)
 		goto out_free_sg;
 
 	sgt->sgl->dma_address = iova;
@@ -971,6 +983,11 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 		void *padding_start;
 		size_t padding_size, aligned_size;
 
+		if (!is_swiotlb_active(dev)) {
+			dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
+			return DMA_MAPPING_ERROR;
+		}
+
 		aligned_size = iova_align(iovad, size);
 		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
 					      iova_mask(iovad), dir, attrs);
@@ -1209,7 +1226,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	 * implementation - it knows better than we do.
 	 */
 	ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot);
-	if (ret < iova_len)
+	if (ret < 0 || ret < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index fc38b1fba7cf..0d03f837a5d4 100644
--- a/drivers/iommu/fsl_pamu.c
+++ b/drivers/iommu/fsl_pamu.c
@@ -11,6 +11,9 @@
 #include <linux/fsl/guts.h>
 #include <linux/interrupt.h>
 #include <linux/genalloc.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
 
 #include <asm/mpc85xx.h>
 
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 69a4a62dc3b9..94b4589dc67c 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -9,6 +9,7 @@
 
 #include "fsl_pamu_domain.h"
 
+#include <linux/platform_device.h>
 #include <sysdev/fsl_pci.h>
 
 /*
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ba9a63cac47c..44016594831d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -533,33 +533,6 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 	rcu_read_unlock();
 }
 
-static bool domain_update_iommu_snooping(struct intel_iommu *skip)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool ret = true;
-
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (iommu != skip) {
-			/*
-			 * If the hardware is operating in the scalable mode,
-			 * the snooping control is always supported since we
-			 * always set PASID-table-entry.PGSNP bit if the domain
-			 * is managed outside (UNMANAGED).
-			 */
-			if (!sm_supported(iommu) &&
-			    !ecap_sc_support(iommu->ecap)) {
-				ret = false;
-				break;
-			}
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
 static int domain_update_iommu_superpage(struct dmar_domain *domain,
 					 struct intel_iommu *skip)
 {
@@ -641,7 +614,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
-	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
 	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
 
 	/*
@@ -2460,7 +2432,7 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 	if (level == 5)
 		flags |= PASID_FLAG_FL5LP;
 
-	if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED)
+	if (domain->force_snooping)
 		flags |= PASID_FLAG_PAGE_SNOOP;
 
 	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
@@ -2474,64 +2446,6 @@ static bool dev_is_real_dma_subdevice(struct device *dev)
 	       pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
 }
 
-static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
-						    int bus, int devfn,
-						    struct device *dev,
-						    struct dmar_domain *domain)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info->domain = domain;
-	spin_lock(&iommu->lock);
-	ret = domain_attach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
-	if (ret) {
-		spin_unlock_irqrestore(&device_domain_lock, flags);
-		return NULL;
-	}
-	list_add(&info->link, &domain->devices);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	/* PASID table is mandatory for a PCI device in scalable mode. */
-	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
-		ret = intel_pasid_alloc_table(dev);
-		if (ret) {
-			dev_err(dev, "PASID table allocation failed\n");
-			dmar_remove_one_dev_info(dev);
-			return NULL;
-		}
-
-		/* Setup the PASID entry for requests without PASID: */
-		spin_lock_irqsave(&iommu->lock, flags);
-		if (hw_pass_through && domain_type_is_si(domain))
-			ret = intel_pasid_setup_pass_through(iommu, domain,
-					dev, PASID_RID2PASID);
-		else if (domain_use_first_level(domain))
-			ret = domain_setup_first_level(iommu, domain, dev,
-					PASID_RID2PASID);
-		else
-			ret = intel_pasid_setup_second_level(iommu, domain,
-					dev, PASID_RID2PASID);
-		spin_unlock_irqrestore(&iommu->lock, flags);
-		if (ret) {
-			dev_err(dev, "Setup RID2PASID failed\n");
-			dmar_remove_one_dev_info(dev);
-			return NULL;
-		}
-	}
-
-	if (dev && domain_context_mapping(domain, dev)) {
-		dev_err(dev, "Domain context map failed\n");
-		dmar_remove_one_dev_info(dev);
-		return NULL;
-	}
-
-	return domain;
-}
-
 static int iommu_domain_identity_map(struct dmar_domain *domain,
 				     unsigned long first_vpfn,
 				     unsigned long last_vpfn)
@@ -2607,17 +2521,62 @@ static int __init si_domain_init(int hw)
 
 static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
 {
-	struct dmar_domain *ndomain;
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu;
+	unsigned long flags;
 	u8 bus, devfn;
+	int ret;
 
 	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return -ENODEV;
 
-	ndomain = dmar_insert_one_dev_info(iommu, bus, devfn, dev, domain);
-	if (ndomain != domain)
-		return -EBUSY;
+	spin_lock_irqsave(&device_domain_lock, flags);
+	info->domain = domain;
+	spin_lock(&iommu->lock);
+	ret = domain_attach_iommu(domain, iommu);
+	spin_unlock(&iommu->lock);
+	if (ret) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		return ret;
+	}
+	list_add(&info->link, &domain->devices);
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	/* PASID table is mandatory for a PCI device in scalable mode. */
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
+		ret = intel_pasid_alloc_table(dev);
+		if (ret) {
+			dev_err(dev, "PASID table allocation failed\n");
+			dmar_remove_one_dev_info(dev);
+			return ret;
+		}
+
+		/* Setup the PASID entry for requests without PASID: */
+		spin_lock_irqsave(&iommu->lock, flags);
+		if (hw_pass_through && domain_type_is_si(domain))
+			ret = intel_pasid_setup_pass_through(iommu, domain,
+					dev, PASID_RID2PASID);
+		else if (domain_use_first_level(domain))
+			ret = domain_setup_first_level(iommu, domain, dev,
+					PASID_RID2PASID);
+		else
+			ret = intel_pasid_setup_second_level(iommu, domain,
+					dev, PASID_RID2PASID);
+		spin_unlock_irqrestore(&iommu->lock, flags);
+		if (ret) {
+			dev_err(dev, "Setup RID2PASID failed\n");
+			dmar_remove_one_dev_info(dev);
+			return ret;
+		}
+	}
+
+	ret = domain_context_mapping(domain, dev);
+	if (ret) {
+		dev_err(dev, "Domain context map failed\n");
+		dmar_remove_one_dev_info(dev);
+		return ret;
+	}
 
 	return 0;
 }
@@ -3607,12 +3566,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 			iommu->name);
 		return -ENXIO;
 	}
-	if (!ecap_sc_support(iommu->ecap) &&
-	    domain_update_iommu_snooping(iommu)) {
-		pr_warn("%s: Doesn't support snooping.\n",
-			iommu->name);
-		return -ENXIO;
-	}
+
 	sp = domain_update_iommu_superpage(NULL, iommu) - 1;
 	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
 		pr_warn("%s: Doesn't support large page.\n",
@@ -4304,7 +4258,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->agaw = width_to_agaw(adjust_width);
 
 	domain->iommu_coherency = false;
-	domain->iommu_snooping = false;
 	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 
@@ -4369,6 +4322,9 @@ static int prepare_domain_attach_device(struct iommu_domain *domain,
 	if (!iommu)
 		return -ENODEV;
 
+	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
+		return -EOPNOTSUPP;
+
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
 	if (addr_width > cap_mgaw(iommu->cap))
@@ -4443,7 +4399,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+	if (dmar_domain->set_pte_snp)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4566,12 +4522,71 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static bool domain_support_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	bool support = true;
+
+	assert_spin_locked(&device_domain_lock);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!ecap_sc_support(info->iommu->ecap)) {
+			support = false;
+			break;
+		}
+	}
+
+	return support;
+}
+
+static void domain_set_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+
+	assert_spin_locked(&device_domain_lock);
+
+	/*
+	 * Second level page table supports per-PTE snoop control. The
+	 * iommu_map() interface will handle this by setting SNP bit.
+	 */
+	if (!domain_use_first_level(domain)) {
+		domain->set_pte_snp = true;
+		return;
+	}
+
+	list_for_each_entry(info, &domain->devices, link)
+		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
+						     PASID_RID2PASID);
+}
+
+static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
+
+	if (dmar_domain->force_snooping)
+		return true;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (!domain_support_force_snooping(dmar_domain)) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		return false;
+	}
+
+	domain_set_force_snooping(dmar_domain);
+	dmar_domain->force_snooping = true;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return true;
+}
+
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
-		return domain_update_iommu_snooping(NULL);
+		return true;
 	if (cap == IOMMU_CAP_INTR_REMAP)
 		return irq_remapping_enabled == 1;
+	if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION)
+		return dmar_platform_optin();
 
 	return false;
 }
@@ -4919,6 +4934,7 @@ const struct iommu_ops intel_iommu_ops = {
 		.iotlb_sync		= intel_iommu_tlb_sync,
 		.iova_to_phys		= intel_iommu_iova_to_phys,
 		.free			= intel_iommu_domain_free,
+		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index f8d215d85695..cb4c1d0cf25c 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -710,9 +710,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
-	if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED)
-		pasid_set_pgsnp(pte);
-
 	/*
 	 * Since it is a second level only translation setup, we should
 	 * set SRE bit as well (addresses are expected to be GPAs).
@@ -762,3 +759,45 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+/*
+ * Set the page snoop control for a pasid entry which has been set up.
+ */
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid)
+{
+	struct pasid_entry *pte;
+	u16 did;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte || !pasid_pte_is_present(pte))) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	pasid_set_pgsnp(pte);
+	did = pasid_get_domain_id(pte);
+	spin_unlock(&iommu->lock);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 3.4 table23 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	/* Device IOTLB doesn't need to be flushed in caching mode. */
+	if (!cap_caching_mode(iommu->cap))
+		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index ab4408c824a5..583ea67fc783 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -123,4 +123,6 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 bool fault_ignore);
 int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
 void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 857d4c2fd1a2..847ad47a2dfd 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -18,7 +18,6 @@
 #include <linux/errno.h>
 #include <linux/iommu.h>
 #include <linux/idr.h>
-#include <linux/notifier.h>
 #include <linux/err.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
@@ -40,14 +39,16 @@ struct iommu_group {
 	struct kobject *devices_kobj;
 	struct list_head devices;
 	struct mutex mutex;
-	struct blocking_notifier_head notifier;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
 	char *name;
 	int id;
 	struct iommu_domain *default_domain;
+	struct iommu_domain *blocking_domain;
 	struct iommu_domain *domain;
 	struct list_head entry;
+	unsigned int owner_cnt;
+	void *owner;
 };
 
 struct group_device {
@@ -82,8 +83,8 @@ static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev);
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group);
-static void __iommu_detach_group(struct iommu_domain *domain,
-				 struct iommu_group *group);
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain);
 static int iommu_create_device_direct_mappings(struct iommu_group *group,
 					       struct device *dev);
 static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
@@ -294,7 +295,11 @@ int iommu_probe_device(struct device *dev)
 	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
 
-	if (group->default_domain) {
+	/*
+	 * If device joined an existing group which has been claimed, don't
+	 * attach the default domain.
+	 */
+	if (group->default_domain && !group->owner) {
 		ret = __iommu_attach_device(group->default_domain, dev);
 		if (ret) {
 			mutex_unlock(&group->mutex);
@@ -599,6 +604,8 @@ static void iommu_group_release(struct kobject *kobj)
 
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
+	if (group->blocking_domain)
+		iommu_domain_free(group->blocking_domain);
 
 	kfree(group->name);
 	kfree(group);
@@ -633,7 +640,6 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
-	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
@@ -906,10 +912,6 @@ rename:
 	if (ret)
 		goto err_put_group;
 
-	/* Notify any listeners about change to group. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
-
 	trace_add_device_to_group(group->id, dev);
 
 	dev_info(dev, "Adding to iommu group %d\n", group->id);
@@ -951,10 +953,6 @@ void iommu_group_remove_device(struct device *dev)
 
 	dev_info(dev, "Removing from iommu group %d\n", group->id);
 
-	/* Pre-notify listeners that a device is being removed. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);
-
 	mutex_lock(&group->mutex);
 	list_for_each_entry(tmp_device, &group->devices, list) {
 		if (tmp_device->dev == dev) {
@@ -1077,36 +1075,6 @@ void iommu_group_put(struct iommu_group *group)
 EXPORT_SYMBOL_GPL(iommu_group_put);
 
 /**
- * iommu_group_register_notifier - Register a notifier for group changes
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * This function allows iommu group users to track changes in a group.
- * See include/linux/iommu.h for actions sent via this notifier.  Caller
- * should hold a reference to the group throughout notifier registration.
- */
-int iommu_group_register_notifier(struct iommu_group *group,
-				  struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_register_notifier);
-
-/**
- * iommu_group_unregister_notifier - Unregister a notifier
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * Unregister a previously registered group notifier block.
- */
-int iommu_group_unregister_notifier(struct iommu_group *group,
-				    struct notifier_block *nb)
-{
-	return blocking_notifier_chain_unregister(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
-
-/**
  * iommu_register_device_fault_handler() - Register a device fault handler
  * @dev: the device
  * @handler: the fault handler
@@ -1651,14 +1619,8 @@ static int remove_iommu_group(struct device *dev, void *data)
 static int iommu_bus_notifier(struct notifier_block *nb,
 			      unsigned long action, void *data)
 {
-	unsigned long group_action = 0;
 	struct device *dev = data;
-	struct iommu_group *group;
 
-	/*
-	 * ADD/DEL call into iommu driver ops if provided, which may
-	 * result in ADD/DEL notifiers to group->notifier
-	 */
 	if (action == BUS_NOTIFY_ADD_DEVICE) {
 		int ret;
 
@@ -1669,34 +1631,6 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 		return NOTIFY_OK;
 	}
 
-	/*
-	 * Remaining BUS_NOTIFYs get filtered and republished to the
-	 * group, if anyone is listening
-	 */
-	group = iommu_group_get(dev);
-	if (!group)
-		return 0;
-
-	switch (action) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER;
-		break;
-	case BUS_NOTIFY_BOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER;
-		break;
-	}
-
-	if (group_action)
-		blocking_notifier_call_chain(&group->notifier,
-					     group_action, dev);
-
-	iommu_group_put(group);
 	return 0;
 }
 
@@ -1913,6 +1847,29 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+/**
+ * device_iommu_capable() - check for a general IOMMU capability
+ * @dev: device to which the capability would be relevant, if available
+ * @cap: IOMMU capability
+ *
+ * Return: true if an IOMMU is present and supports the given capability
+ * for the given device, otherwise false.
+ */
+bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu || !dev->iommu->iommu_dev)
+		return false;
+
+	ops = dev_iommu_ops(dev);
+	if (!ops->capable)
+		return false;
+
+	return ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(device_iommu_capable);
+
 bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
 {
 	if (!bus->iommu_ops || !bus->iommu_ops->capable)
@@ -1983,6 +1940,24 @@ void iommu_domain_free(struct iommu_domain *domain)
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
 
+/*
+ * Put the group's domain back to the appropriate core-owned domain - either the
+ * standard kernel-mode DMA configuration or an all-DMA-blocked domain.
+ */
+static void __iommu_group_set_core_domain(struct iommu_group *group)
+{
+	struct iommu_domain *new_domain;
+	int ret;
+
+	if (group->owner)
+		new_domain = group->blocking_domain;
+	else
+		new_domain = group->default_domain;
+
+	ret = __iommu_group_set_domain(group, new_domain);
+	WARN(ret, "iommu driver failed to attach the default/blocking domain");
+}
+
 static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
@@ -2039,9 +2014,6 @@ static void __iommu_detach_device(struct iommu_domain *domain,
 	if (iommu_is_attach_deferred(dev))
 		return;
 
-	if (unlikely(domain->ops->detach_dev == NULL))
-		return;
-
 	domain->ops->detach_dev(domain, dev);
 	trace_detach_device_from_domain(dev);
 }
@@ -2055,12 +2027,10 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
 		return;
 
 	mutex_lock(&group->mutex);
-	if (iommu_group_device_count(group) != 1) {
-		WARN_ON(1);
+	if (WARN_ON(domain != group->domain) ||
+	    WARN_ON(iommu_group_device_count(group) != 1))
 		goto out_unlock;
-	}
-
-	__iommu_detach_group(domain, group);
+	__iommu_group_set_core_domain(group);
 
 out_unlock:
 	mutex_unlock(&group->mutex);
@@ -2116,7 +2086,8 @@ static int __iommu_attach_group(struct iommu_domain *domain,
 {
 	int ret;
 
-	if (group->default_domain && group->domain != group->default_domain)
+	if (group->domain && group->domain != group->default_domain &&
+	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
 	ret = __iommu_group_for_each_dev(group, domain,
@@ -2148,34 +2119,49 @@ static int iommu_group_do_detach_device(struct device *dev, void *data)
 	return 0;
 }
 
-static void __iommu_detach_group(struct iommu_domain *domain,
-				 struct iommu_group *group)
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain)
 {
 	int ret;
 
-	if (!group->default_domain) {
-		__iommu_group_for_each_dev(group, domain,
+	if (group->domain == new_domain)
+		return 0;
+
+	/*
+	 * New drivers should support default domains and so the detach_dev() op
+	 * will never be called. Otherwise the NULL domain represents some
+	 * platform specific behavior.
+	 */
+	if (!new_domain) {
+		if (WARN_ON(!group->domain->ops->detach_dev))
+			return -EINVAL;
+		__iommu_group_for_each_dev(group, group->domain,
 					   iommu_group_do_detach_device);
 		group->domain = NULL;
-		return;
+		return 0;
 	}
 
-	if (group->domain == group->default_domain)
-		return;
-
-	/* Detach by re-attaching to the default domain */
-	ret = __iommu_group_for_each_dev(group, group->default_domain,
+	/*
+	 * Changing the domain is done by calling attach_dev() on the new
+	 * domain. This switch does not have to be atomic and DMA can be
+	 * discarded during the transition. DMA must only be able to access
+	 * either new_domain or group->domain, never something else.
+	 *
+	 * Note that this is called in error unwind paths, attaching to a
+	 * domain that has already been attached cannot fail.
+	 */
+	ret = __iommu_group_for_each_dev(group, new_domain,
 					 iommu_group_do_attach_device);
-	if (ret != 0)
-		WARN_ON(1);
-	else
-		group->domain = group->default_domain;
+	if (ret)
+		return ret;
+	group->domain = new_domain;
+	return 0;
 }
 
 void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
 {
 	mutex_lock(&group->mutex);
-	__iommu_detach_group(domain, group);
+	__iommu_group_set_core_domain(group);
 	mutex_unlock(&group->mutex);
 }
 EXPORT_SYMBOL_GPL(iommu_detach_group);
@@ -3102,3 +3088,167 @@ out:
 
 	return ret;
 }
+
+/**
+ * iommu_device_use_default_domain() - Device driver wants to handle device
+ *                                     DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver about to bind @dev wants to do DMA through the kernel
+ * DMA API. Return 0 if it is allowed, otherwise an error.
+ */
+int iommu_device_use_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+	int ret = 0;
+
+	if (!group)
+		return 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		if (group->domain != group->default_domain ||
+		    group->owner) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+	}
+
+	group->owner_cnt++;
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+/**
+ * iommu_device_unuse_default_domain() - Device driver stops handling device
+ *                                       DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver doesn't want to do DMA through kernel DMA API anymore.
+ * It must be called after iommu_device_use_default_domain().
+ */
+void iommu_device_unuse_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	if (!WARN_ON(!group->owner_cnt))
+		group->owner_cnt--;
+
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
+
+static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
+{
+	struct group_device *dev =
+		list_first_entry(&group->devices, struct group_device, list);
+
+	if (group->blocking_domain)
+		return 0;
+
+	group->blocking_domain =
+		__iommu_domain_alloc(dev->dev->bus, IOMMU_DOMAIN_BLOCKED);
+	if (!group->blocking_domain) {
+		/*
+		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
+		 * create an empty domain instead.
+		 */
+		group->blocking_domain = __iommu_domain_alloc(
+			dev->dev->bus, IOMMU_DOMAIN_UNMANAGED);
+		if (!group->blocking_domain)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * iommu_group_claim_dma_owner() - Set DMA ownership of a group
+ * @group: The group.
+ * @owner: Caller specified pointer. Used for exclusive ownership.
+ *
+ * This is to support backward compatibility for vfio which manages
+ * the dma ownership in iommu_group level. New invocations on this
+ * interface should be prohibited.
+ */
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		ret = -EPERM;
+		goto unlock_out;
+	} else {
+		if (group->domain && group->domain != group->default_domain) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+
+		ret = __iommu_group_alloc_blocking_domain(group);
+		if (ret)
+			goto unlock_out;
+
+		ret = __iommu_group_set_domain(group, group->blocking_domain);
+		if (ret)
+			goto unlock_out;
+		group->owner = owner;
+	}
+
+	group->owner_cnt++;
+unlock_out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);
+
+/**
+ * iommu_group_release_dma_owner() - Release DMA ownership of a group
+ * @group: The group.
+ *
+ * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
+ */
+void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	if (WARN_ON(!group->owner_cnt || !group->owner))
+		goto unlock_out;
+
+	group->owner_cnt = 0;
+	group->owner = NULL;
+	ret = __iommu_group_set_domain(group, group->default_domain);
+	WARN(ret, "iommu driver failed to attach the default domain");
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);
+
+/**
+ * iommu_group_dma_owner_claimed() - Query group dma ownership status
+ * @group: The group.
+ *
+ * This provides status query on a given group. It is racy and only for
+ * non-binding status reporting.
+ */
+bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	unsigned int user;
+
+	mutex_lock(&group->mutex);
+	user = group->owner_cnt;
+	mutex_unlock(&group->mutex);
+
+	return user;
+}
+EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 50f57624610f..f09aedfdd462 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -583,7 +583,7 @@ static void print_ctx_regs(void __iomem *base, int ctx)
 	       GET_SCTLR(base, ctx), GET_ACTLR(base, ctx));
 }
 
-static void insert_iommu_master(struct device *dev,
+static int insert_iommu_master(struct device *dev,
 				struct msm_iommu_dev **iommu,
 				struct of_phandle_args *spec)
 {
@@ -592,6 +592,10 @@ static void insert_iommu_master(struct device *dev,
 
 	if (list_empty(&(*iommu)->ctx_list)) {
 		master = kzalloc(sizeof(*master), GFP_ATOMIC);
+		if (!master) {
+			dev_err(dev, "Failed to allocate iommu_master\n");
+			return -ENOMEM;
+		}
 		master->of_node = dev->of_node;
 		list_add(&master->list, &(*iommu)->ctx_list);
 		dev_iommu_priv_set(dev, master);
@@ -601,30 +605,34 @@ static void insert_iommu_master(struct device *dev,
 		if (master->mids[sid] == spec->args[0]) {
 			dev_warn(dev, "Stream ID 0x%hx repeated; ignoring\n",
 				 sid);
-			return;
+			return 0;
 		}
 
 	master->mids[master->num_mids++] = spec->args[0];
+	return 0;
 }
 
 static int qcom_iommu_of_xlate(struct device *dev,
 			       struct of_phandle_args *spec)
 {
-	struct msm_iommu_dev *iommu;
+	struct msm_iommu_dev *iommu = NULL, *iter;
 	unsigned long flags;
 	int ret = 0;
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
-	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node)
-		if (iommu->dev->of_node == spec->np)
+	list_for_each_entry(iter, &qcom_iommu_devices, dev_node) {
+		if (iter->dev->of_node == spec->np) {
+			iommu = iter;
 			break;
+		}
+	}
 
-	if (!iommu || iommu->dev->of_node != spec->np) {
+	if (!iommu) {
 		ret = -ENODEV;
 		goto fail;
 	}
 
-	insert_iommu_master(dev, &iommu, spec);
+	ret = insert_iommu_master(dev, &iommu, spec);
 fail:
 	spin_unlock_irqrestore(&msm_iommu_lock, flags);
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6fd75a60abd6..bb9dd92c9898 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -14,12 +14,14 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
+#include <linux/io-pgtable.h>
 #include <linux/list.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
@@ -29,7 +31,7 @@
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
 
-#include "mtk_iommu.h"
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define REG_MMU_PT_BASE_ADDR			0x000
 #define MMU_PT_ADDR_MASK			GENMASK(31, 7)
@@ -51,6 +53,8 @@
 #define F_MMU_STANDARD_AXI_MODE_MASK		(BIT(3) | BIT(19))
 
 #define REG_MMU_DCM_DIS				0x050
+#define F_MMU_DCM				BIT(8)
+
 #define REG_MMU_WR_LEN_CTRL			0x054
 #define F_MMU_WR_THROT_DIS_MASK			(BIT(5) | BIT(21))
 
@@ -103,10 +107,15 @@
 #define REG_MMU1_INT_ID				0x154
 #define F_MMU_INT_ID_COMM_ID(a)			(((a) >> 9) & 0x7)
 #define F_MMU_INT_ID_SUB_COMM_ID(a)		(((a) >> 7) & 0x3)
+#define F_MMU_INT_ID_COMM_ID_EXT(a)		(((a) >> 10) & 0x7)
+#define F_MMU_INT_ID_SUB_COMM_ID_EXT(a)		(((a) >> 7) & 0x7)
 #define F_MMU_INT_ID_LARB_ID(a)			(((a) >> 7) & 0x7)
 #define F_MMU_INT_ID_PORT_ID(a)			(((a) >> 2) & 0x1f)
 
 #define MTK_PROTECT_PA_ALIGN			256
+#define MTK_IOMMU_BANK_SZ			0x1000
+
+#define PERICFG_IOMMU_1				0x714
 
 #define HAS_4GB_MODE			BIT(0)
 /* HW will use the EMI clock if there isn't the "bclk". */
@@ -114,25 +123,147 @@
 #define HAS_VLD_PA_RNG			BIT(2)
 #define RESET_AXI			BIT(3)
 #define OUT_ORDER_WR_EN			BIT(4)
-#define HAS_SUB_COMM			BIT(5)
-#define WR_THROT_EN			BIT(6)
-#define HAS_LEGACY_IVRP_PADDR		BIT(7)
-#define IOVA_34_EN			BIT(8)
+#define HAS_SUB_COMM_2BITS		BIT(5)
+#define HAS_SUB_COMM_3BITS		BIT(6)
+#define WR_THROT_EN			BIT(7)
+#define HAS_LEGACY_IVRP_PADDR		BIT(8)
+#define IOVA_34_EN			BIT(9)
+#define SHARE_PGTABLE			BIT(10) /* 2 HW share pgtable */
+#define DCM_DISABLE			BIT(11)
+#define STD_AXI_MODE			BIT(12) /* For non MM iommu */
+/* 2 bits: iommu type */
+#define MTK_IOMMU_TYPE_MM		(0x0 << 13)
+#define MTK_IOMMU_TYPE_INFRA		(0x1 << 13)
+#define MTK_IOMMU_TYPE_MASK		(0x3 << 13)
+/* PM and clock always on. e.g. infra iommu */
+#define PM_CLK_AO			BIT(15)
+#define IFA_IOMMU_PCIE_SUPPORT		BIT(16)
+
+#define MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, mask)	\
+				((((pdata)->flags) & (mask)) == (_x))
+
+#define MTK_IOMMU_HAS_FLAG(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, _x)
+#define MTK_IOMMU_IS_TYPE(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x,\
+							MTK_IOMMU_TYPE_MASK)
+
+#define MTK_INVALID_LARBID		MTK_LARB_NR_MAX
+
+#define MTK_LARB_COM_MAX	8
+#define MTK_LARB_SUBCOM_MAX	8
+
+#define MTK_IOMMU_GROUP_MAX	8
+#define MTK_IOMMU_BANK_MAX	5
+
+enum mtk_iommu_plat {
+	M4U_MT2712,
+	M4U_MT6779,
+	M4U_MT8167,
+	M4U_MT8173,
+	M4U_MT8183,
+	M4U_MT8186,
+	M4U_MT8192,
+	M4U_MT8195,
+};
+
+struct mtk_iommu_iova_region {
+	dma_addr_t		iova_base;
+	unsigned long long	size;
+};
+
+struct mtk_iommu_suspend_reg {
+	u32			misc_ctrl;
+	u32			dcm_dis;
+	u32			ctrl_reg;
+	u32			vld_pa_rng;
+	u32			wr_len_ctrl;
+
+	u32			int_control[MTK_IOMMU_BANK_MAX];
+	u32			int_main_control[MTK_IOMMU_BANK_MAX];
+	u32			ivrp_paddr[MTK_IOMMU_BANK_MAX];
+};
+
+struct mtk_iommu_plat_data {
+	enum mtk_iommu_plat	m4u_plat;
+	u32			flags;
+	u32			inv_sel_reg;
+
+	char			*pericfg_comp_str;
+	struct list_head	*hw_list;
+	unsigned int		iova_region_nr;
+	const struct mtk_iommu_iova_region	*iova_region;
+
+	u8                  banks_num;
+	bool                banks_enable[MTK_IOMMU_BANK_MAX];
+	unsigned int        banks_portmsk[MTK_IOMMU_BANK_MAX];
+	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
+};
+
+struct mtk_iommu_bank_data {
+	void __iomem			*base;
+	int				irq;
+	u8				id;
+	struct device			*parent_dev;
+	struct mtk_iommu_data		*parent_data;
+	spinlock_t			tlb_lock; /* lock for tlb range flush */
+	struct mtk_iommu_domain		*m4u_dom; /* Each bank has a domain */
+};
+
+struct mtk_iommu_data {
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_suspend_reg	reg;
+	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
+	bool                            enable_4GB;
 
-#define MTK_IOMMU_HAS_FLAG(pdata, _x) \
-		((((pdata)->flags) & (_x)) == (_x))
+	struct iommu_device		iommu;
+	const struct mtk_iommu_plat_data *plat_data;
+	struct device			*smicomm_dev;
+
+	struct mtk_iommu_bank_data	*bank;
+
+	struct dma_iommu_mapping	*mapping; /* For mtk_iommu_v1.c */
+	struct regmap			*pericfg;
+
+	struct mutex			mutex; /* Protect m4u_group/m4u_dom above */
+
+	/*
+	 * In the sharing pgtable case, list data->list to the global list like m4ulist.
+	 * In the non-sharing pgtable case, list data->list to the itself hw_list_head.
+	 */
+	struct list_head		*hw_list;
+	struct list_head		hw_list_head;
+	struct list_head		list;
+	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
+};
 
 struct mtk_iommu_domain {
 	struct io_pgtable_cfg		cfg;
 	struct io_pgtable_ops		*iop;
 
-	struct mtk_iommu_data		*data;
+	struct mtk_iommu_bank_data	*bank;
 	struct iommu_domain		domain;
+
+	struct mutex			mutex; /* Protect "data" in this structure */
 };
 
+static int mtk_iommu_bind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->larb_imu);
+}
+
+static void mtk_iommu_unbind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->larb_imu);
+}
+
 static const struct iommu_ops mtk_iommu_ops;
 
-static int mtk_iommu_hw_init(const struct mtk_iommu_data *data);
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data, unsigned int bankid);
 
 #define MTK_IOMMU_TLB_ADDR(iova) ({					\
 	dma_addr_t _addr = iova;					\
@@ -165,42 +296,28 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data);
 
 static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
 
-#define for_each_m4u(data)	list_for_each_entry(data, &m4ulist, list)
-
-struct mtk_iommu_iova_region {
-	dma_addr_t		iova_base;
-	unsigned long long	size;
-};
+#define for_each_m4u(data, head)  list_for_each_entry(data, head, list)
 
 static const struct mtk_iommu_iova_region single_domain[] = {
 	{.iova_base = 0,		.size = SZ_4G},
 };
 
 static const struct mtk_iommu_iova_region mt8192_multi_dom[] = {
-	{ .iova_base = 0x0,		.size = SZ_4G},		/* disp: 0 ~ 4G */
+	{ .iova_base = 0x0,		.size = SZ_4G},		/* 0 ~ 4G */
 	#if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)
-	{ .iova_base = SZ_4G,		.size = SZ_4G},		/* vdec: 4G ~ 8G */
-	{ .iova_base = SZ_4G * 2,	.size = SZ_4G},		/* CAM/MDP: 8G ~ 12G */
+	{ .iova_base = SZ_4G,		.size = SZ_4G},		/* 4G ~ 8G */
+	{ .iova_base = SZ_4G * 2,	.size = SZ_4G},		/* 8G ~ 12G */
+	{ .iova_base = SZ_4G * 3,	.size = SZ_4G},		/* 12G ~ 16G */
+
 	{ .iova_base = 0x240000000ULL,	.size = 0x4000000},	/* CCU0 */
 	{ .iova_base = 0x244000000ULL,	.size = 0x4000000},	/* CCU1 */
 	#endif
 };
 
-/*
- * There may be 1 or 2 M4U HWs, But we always expect they are in the same domain
- * for the performance.
- *
- * Here always return the mtk_iommu_data of the first probed M4U where the
- * iommu domain information is recorded.
- */
-static struct mtk_iommu_data *mtk_iommu_get_m4u_data(void)
+/* If 2 M4U share a domain(use the same hwlist), Put the corresponding info in first data.*/
+static struct mtk_iommu_data *mtk_iommu_get_frst_data(struct list_head *hwlist)
 {
-	struct mtk_iommu_data *data;
-
-	for_each_m4u(data)
-		return data;
-
-	return NULL;
+	return list_first_entry(hwlist, struct mtk_iommu_data, list);
 }
 
 static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
@@ -210,46 +327,72 @@ static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
 
 static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
 {
+	/* Tlb flush all always is in bank0. */
+	struct mtk_iommu_bank_data *bank = &data->bank[0];
+	void __iomem *base = bank->base;
 	unsigned long flags;
 
-	spin_lock_irqsave(&data->tlb_lock, flags);
-	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
-		       data->base + data->plat_data->inv_sel_reg);
-	writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
+	spin_lock_irqsave(&bank->tlb_lock, flags);
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0, base + data->plat_data->inv_sel_reg);
+	writel_relaxed(F_ALL_INVLD, base + REG_MMU_INVALIDATE);
 	wmb(); /* Make sure the tlb flush all done */
-	spin_unlock_irqrestore(&data->tlb_lock, flags);
+	spin_unlock_irqrestore(&bank->tlb_lock, flags);
 }
 
 static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
-					   size_t granule,
-					   struct mtk_iommu_data *data)
+					   struct mtk_iommu_bank_data *bank)
 {
+	struct list_head *head = bank->parent_data->hw_list;
+	struct mtk_iommu_bank_data *curbank;
+	struct mtk_iommu_data *data;
+	bool check_pm_status;
 	unsigned long flags;
+	void __iomem *base;
 	int ret;
 	u32 tmp;
 
-	for_each_m4u(data) {
-		if (pm_runtime_get_if_in_use(data->dev) <= 0)
-			continue;
+	for_each_m4u(data, head) {
+		/*
+		 * To avoid resume the iommu device frequently when the iommu device
+		 * is not active, it doesn't always call pm_runtime_get here, then tlb
+		 * flush depends on the tlb flush all in the runtime resume.
+		 *
+		 * There are 2 special cases:
+		 *
+		 * Case1: The iommu dev doesn't have power domain but has bclk. This case
+		 * should also avoid the tlb flush while the dev is not active to mute
+		 * the tlb timeout log. like mt8173.
+		 *
+		 * Case2: The power/clock of infra iommu is always on, and it doesn't
+		 * have the device link with the master devices. This case should avoid
+		 * the PM status check.
+		 */
+		check_pm_status = !MTK_IOMMU_HAS_FLAG(data->plat_data, PM_CLK_AO);
 
-		spin_lock_irqsave(&data->tlb_lock, flags);
+		if (check_pm_status) {
+			if (pm_runtime_get_if_in_use(data->dev) <= 0)
+				continue;
+		}
+
+		curbank = &data->bank[bank->id];
+		base = curbank->base;
+
+		spin_lock_irqsave(&curbank->tlb_lock, flags);
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
-			       data->base + data->plat_data->inv_sel_reg);
+			       base + data->plat_data->inv_sel_reg);
 
-		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova),
-			       data->base + REG_MMU_INVLD_START_A);
+		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova), base + REG_MMU_INVLD_START_A);
 		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova + size - 1),
-			       data->base + REG_MMU_INVLD_END_A);
-		writel_relaxed(F_MMU_INV_RANGE,
-			       data->base + REG_MMU_INVALIDATE);
+			       base + REG_MMU_INVLD_END_A);
+		writel_relaxed(F_MMU_INV_RANGE, base + REG_MMU_INVALIDATE);
 
 		/* tlb sync */
-		ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
+		ret = readl_poll_timeout_atomic(base + REG_MMU_CPE_DONE,
 						tmp, tmp != 0, 10, 1000);
 
 		/* Clear the CPE status */
-		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
-		spin_unlock_irqrestore(&data->tlb_lock, flags);
+		writel_relaxed(0, base + REG_MMU_CPE_DONE);
+		spin_unlock_irqrestore(&curbank->tlb_lock, flags);
 
 		if (ret) {
 			dev_warn(data->dev,
@@ -257,70 +400,103 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 			mtk_iommu_tlb_flush_all(data);
 		}
 
-		pm_runtime_put(data->dev);
+		if (check_pm_status)
+			pm_runtime_put(data->dev);
 	}
 }
 
 static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 {
-	struct mtk_iommu_data *data = dev_id;
-	struct mtk_iommu_domain *dom = data->m4u_dom;
-	unsigned int fault_larb, fault_port, sub_comm = 0;
+	struct mtk_iommu_bank_data *bank = dev_id;
+	struct mtk_iommu_data *data = bank->parent_data;
+	struct mtk_iommu_domain *dom = bank->m4u_dom;
+	unsigned int fault_larb = MTK_INVALID_LARBID, fault_port = 0, sub_comm = 0;
 	u32 int_state, regval, va34_32, pa34_32;
+	const struct mtk_iommu_plat_data *plat_data = data->plat_data;
+	void __iomem *base = bank->base;
 	u64 fault_iova, fault_pa;
 	bool layer, write;
 
 	/* Read error info from registers */
-	int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST1);
+	int_state = readl_relaxed(base + REG_MMU_FAULT_ST1);
 	if (int_state & F_REG_MMU0_FAULT_MASK) {
-		regval = readl_relaxed(data->base + REG_MMU0_INT_ID);
-		fault_iova = readl_relaxed(data->base + REG_MMU0_FAULT_VA);
-		fault_pa = readl_relaxed(data->base + REG_MMU0_INVLD_PA);
+		regval = readl_relaxed(base + REG_MMU0_INT_ID);
+		fault_iova = readl_relaxed(base + REG_MMU0_FAULT_VA);
+		fault_pa = readl_relaxed(base + REG_MMU0_INVLD_PA);
 	} else {
-		regval = readl_relaxed(data->base + REG_MMU1_INT_ID);
-		fault_iova = readl_relaxed(data->base + REG_MMU1_FAULT_VA);
-		fault_pa = readl_relaxed(data->base + REG_MMU1_INVLD_PA);
+		regval = readl_relaxed(base + REG_MMU1_INT_ID);
+		fault_iova = readl_relaxed(base + REG_MMU1_FAULT_VA);
+		fault_pa = readl_relaxed(base + REG_MMU1_INVLD_PA);
 	}
 	layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
 	write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
-	if (MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN)) {
+	if (MTK_IOMMU_HAS_FLAG(plat_data, IOVA_34_EN)) {
 		va34_32 = FIELD_GET(F_MMU_INVAL_VA_34_32_MASK, fault_iova);
-		pa34_32 = FIELD_GET(F_MMU_INVAL_PA_34_32_MASK, fault_iova);
 		fault_iova = fault_iova & F_MMU_INVAL_VA_31_12_MASK;
 		fault_iova |= (u64)va34_32 << 32;
-		fault_pa |= (u64)pa34_32 << 32;
 	}
-
-	fault_port = F_MMU_INT_ID_PORT_ID(regval);
-	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_SUB_COMM)) {
-		fault_larb = F_MMU_INT_ID_COMM_ID(regval);
-		sub_comm = F_MMU_INT_ID_SUB_COMM_ID(regval);
-	} else {
-		fault_larb = F_MMU_INT_ID_LARB_ID(regval);
+	pa34_32 = FIELD_GET(F_MMU_INVAL_PA_34_32_MASK, fault_iova);
+	fault_pa |= (u64)pa34_32 << 32;
+
+	if (MTK_IOMMU_IS_TYPE(plat_data, MTK_IOMMU_TYPE_MM)) {
+		fault_port = F_MMU_INT_ID_PORT_ID(regval);
+		if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_2BITS)) {
+			fault_larb = F_MMU_INT_ID_COMM_ID(regval);
+			sub_comm = F_MMU_INT_ID_SUB_COMM_ID(regval);
+		} else if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_3BITS)) {
+			fault_larb = F_MMU_INT_ID_COMM_ID_EXT(regval);
+			sub_comm = F_MMU_INT_ID_SUB_COMM_ID_EXT(regval);
+		} else {
+			fault_larb = F_MMU_INT_ID_LARB_ID(regval);
+		}
+		fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm];
 	}
-	fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm];
 
-	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
+	if (report_iommu_fault(&dom->domain, bank->parent_dev, fault_iova,
 			       write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
 		dev_err_ratelimited(
-			data->dev,
-			"fault type=0x%x iova=0x%llx pa=0x%llx larb=%d port=%d layer=%d %s\n",
-			int_state, fault_iova, fault_pa, fault_larb, fault_port,
+			bank->parent_dev,
+			"fault type=0x%x iova=0x%llx pa=0x%llx master=0x%x(larb=%d port=%d) layer=%d %s\n",
+			int_state, fault_iova, fault_pa, regval, fault_larb, fault_port,
 			layer, write ? "write" : "read");
 	}
 
 	/* Interrupt clear */
-	regval = readl_relaxed(data->base + REG_MMU_INT_CONTROL0);
+	regval = readl_relaxed(base + REG_MMU_INT_CONTROL0);
 	regval |= F_INT_CLR_BIT;
-	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL0);
+	writel_relaxed(regval, base + REG_MMU_INT_CONTROL0);
 
 	mtk_iommu_tlb_flush_all(data);
 
 	return IRQ_HANDLED;
 }
 
-static int mtk_iommu_get_domain_id(struct device *dev,
-				   const struct mtk_iommu_plat_data *plat_data)
+static unsigned int mtk_iommu_get_bank_id(struct device *dev,
+					  const struct mtk_iommu_plat_data *plat_data)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	unsigned int i, portmsk = 0, bankid = 0;
+
+	if (plat_data->banks_num == 1)
+		return bankid;
+
+	for (i = 0; i < fwspec->num_ids; i++)
+		portmsk |= BIT(MTK_M4U_TO_PORT(fwspec->ids[i]));
+
+	for (i = 0; i < plat_data->banks_num && i < MTK_IOMMU_BANK_MAX; i++) {
+		if (!plat_data->banks_enable[i])
+			continue;
+
+		if (portmsk & plat_data->banks_portmsk[i]) {
+			bankid = i;
+			break;
+		}
+	}
+	return bankid; /* default is 0 */
+}
+
+static int mtk_iommu_get_iova_region_id(struct device *dev,
+					const struct mtk_iommu_plat_data *plat_data)
 {
 	const struct mtk_iommu_iova_region *rgn = plat_data->iova_region;
 	const struct bus_dma_region *dma_rgn = dev->dma_range_map;
@@ -349,46 +525,65 @@ static int mtk_iommu_get_domain_id(struct device *dev,
 	return -EINVAL;
 }
 
-static void mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev,
-			     bool enable, unsigned int domid)
+static int mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev,
+			    bool enable, unsigned int regionid)
 {
 	struct mtk_smi_larb_iommu    *larb_mmu;
 	unsigned int                 larbid, portid;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	const struct mtk_iommu_iova_region *region;
-	int i;
+	u32 peri_mmuen, peri_mmuen_msk;
+	int i, ret = 0;
 
 	for (i = 0; i < fwspec->num_ids; ++i) {
 		larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
 		portid = MTK_M4U_TO_PORT(fwspec->ids[i]);
 
-		larb_mmu = &data->larb_imu[larbid];
-
-		region = data->plat_data->iova_region + domid;
-		larb_mmu->bank[portid] = upper_32_bits(region->iova_base);
-
-		dev_dbg(dev, "%s iommu for larb(%s) port %d dom %d bank %d.\n",
-			enable ? "enable" : "disable", dev_name(larb_mmu->dev),
-			portid, domid, larb_mmu->bank[portid]);
-
-		if (enable)
-			larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
-		else
-			larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+		if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+			larb_mmu = &data->larb_imu[larbid];
+
+			region = data->plat_data->iova_region + regionid;
+			larb_mmu->bank[portid] = upper_32_bits(region->iova_base);
+
+			dev_dbg(dev, "%s iommu for larb(%s) port %d region %d rgn-bank %d.\n",
+				enable ? "enable" : "disable", dev_name(larb_mmu->dev),
+				portid, regionid, larb_mmu->bank[portid]);
+
+			if (enable)
+				larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
+			else
+				larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+		} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+			peri_mmuen_msk = BIT(portid);
+			/* PCI dev has only one output id, enable the next writing bit for PCIe */
+			if (dev_is_pci(dev))
+				peri_mmuen_msk |= BIT(portid + 1);
+
+			peri_mmuen = enable ? peri_mmuen_msk : 0;
+			ret = regmap_update_bits(data->pericfg, PERICFG_IOMMU_1,
+						 peri_mmuen_msk, peri_mmuen);
+			if (ret)
+				dev_err(dev, "%s iommu(%s) inframaster 0x%x fail(%d).\n",
+					enable ? "enable" : "disable",
+					dev_name(data->dev), peri_mmuen_msk, ret);
+		}
 	}
+	return ret;
 }
 
 static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
 				     struct mtk_iommu_data *data,
-				     unsigned int domid)
+				     unsigned int region_id)
 {
 	const struct mtk_iommu_iova_region *region;
-
-	/* Use the exist domain as there is only one pgtable here. */
-	if (data->m4u_dom) {
-		dom->iop = data->m4u_dom->iop;
-		dom->cfg = data->m4u_dom->cfg;
-		dom->domain.pgsize_bitmap = data->m4u_dom->cfg.pgsize_bitmap;
+	struct mtk_iommu_domain	*m4u_dom;
+
+	/* Always use bank0 in sharing pgtable case */
+	m4u_dom = data->bank[0].m4u_dom;
+	if (m4u_dom) {
+		dom->iop = m4u_dom->iop;
+		dom->cfg = m4u_dom->cfg;
+		dom->domain.pgsize_bitmap = m4u_dom->cfg.pgsize_bitmap;
 		goto update_iova_region;
 	}
 
@@ -417,7 +612,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
 
 update_iova_region:
 	/* Update the iova region for this domain */
-	region = data->plat_data->iova_region + domid;
+	region = data->plat_data->iova_region + region_id;
 	dom->domain.geometry.aperture_start = region->iova_base;
 	dom->domain.geometry.aperture_end = region->iova_base + region->size - 1;
 	dom->domain.geometry.force_aperture = true;
@@ -428,12 +623,13 @@ static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
 {
 	struct mtk_iommu_domain *dom;
 
-	if (type != IOMMU_DOMAIN_DMA)
+	if (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_UNMANAGED)
 		return NULL;
 
 	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
 	if (!dom)
 		return NULL;
+	mutex_init(&dom->mutex);
 
 	return &dom->domain;
 }
@@ -446,40 +642,60 @@ static void mtk_iommu_domain_free(struct iommu_domain *domain)
 static int mtk_iommu_attach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
-	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev), *frstdata;
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct list_head *hw_list = data->hw_list;
 	struct device *m4udev = data->dev;
-	int ret, domid;
+	struct mtk_iommu_bank_data *bank;
+	unsigned int bankid;
+	int ret, region_id;
 
-	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
-	if (domid < 0)
-		return domid;
+	region_id = mtk_iommu_get_iova_region_id(dev, data->plat_data);
+	if (region_id < 0)
+		return region_id;
 
-	if (!dom->data) {
-		if (mtk_iommu_domain_finalise(dom, data, domid))
+	bankid = mtk_iommu_get_bank_id(dev, data->plat_data);
+	mutex_lock(&dom->mutex);
+	if (!dom->bank) {
+		/* Data is in the frstdata in sharing pgtable case. */
+		frstdata = mtk_iommu_get_frst_data(hw_list);
+
+		ret = mtk_iommu_domain_finalise(dom, frstdata, region_id);
+		if (ret) {
+			mutex_unlock(&dom->mutex);
 			return -ENODEV;
-		dom->data = data;
+		}
+		dom->bank = &data->bank[bankid];
 	}
+	mutex_unlock(&dom->mutex);
 
-	if (!data->m4u_dom) { /* Initialize the M4U HW */
+	mutex_lock(&data->mutex);
+	bank = &data->bank[bankid];
+	if (!bank->m4u_dom) { /* Initialize the M4U HW for each a BANK */
 		ret = pm_runtime_resume_and_get(m4udev);
-		if (ret < 0)
-			return ret;
+		if (ret < 0) {
+			dev_err(m4udev, "pm get fail(%d) in attach.\n", ret);
+			goto err_unlock;
+		}
 
-		ret = mtk_iommu_hw_init(data);
+		ret = mtk_iommu_hw_init(data, bankid);
 		if (ret) {
 			pm_runtime_put(m4udev);
-			return ret;
+			goto err_unlock;
 		}
-		data->m4u_dom = dom;
+		bank->m4u_dom = dom;
 		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
-		       data->base + REG_MMU_PT_BASE_ADDR);
+		       bank->base + REG_MMU_PT_BASE_ADDR);
 
 		pm_runtime_put(m4udev);
 	}
+	mutex_unlock(&data->mutex);
 
-	mtk_iommu_config(data, dev, true, domid);
-	return 0;
+	return mtk_iommu_config(data, dev, true, region_id);
+
+err_unlock:
+	mutex_unlock(&data->mutex);
+	return ret;
 }
 
 static void mtk_iommu_detach_device(struct iommu_domain *domain,
@@ -496,7 +712,7 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 
 	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
-	if (dom->data->enable_4GB)
+	if (dom->bank->parent_data->enable_4GB)
 		paddr |= BIT_ULL(32);
 
 	/* Synchronize with the tlb_lock */
@@ -517,7 +733,7 @@ static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 
-	mtk_iommu_tlb_flush_all(dom->data);
+	mtk_iommu_tlb_flush_all(dom->bank->parent_data);
 }
 
 static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
@@ -526,8 +742,7 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	size_t length = gather->end - gather->start + 1;
 
-	mtk_iommu_tlb_flush_range_sync(gather->start, length, gather->pgsize,
-				       dom->data);
+	mtk_iommu_tlb_flush_range_sync(gather->start, length, dom->bank);
 }
 
 static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
@@ -535,7 +750,7 @@ static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 
-	mtk_iommu_tlb_flush_range_sync(iova, size, size, dom->data);
+	mtk_iommu_tlb_flush_range_sync(iova, size, dom->bank);
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -546,7 +761,7 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
 	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
-	    dom->data->enable_4GB &&
+	    dom->bank->parent_data->enable_4GB &&
 	    pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
 		pa &= ~BIT_ULL(32);
 
@@ -566,12 +781,18 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 
 	data = dev_iommu_priv_get(dev);
 
+	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
+		return &data->iommu;
+
 	/*
 	 * Link the consumer device with the smi-larb device(supplier).
 	 * The device that connects with each a larb is a independent HW.
 	 * All the ports in each a device should be in the same larbs.
 	 */
 	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+	if (larbid >= MTK_LARB_NR_MAX)
+		return ERR_PTR(-EINVAL);
+
 	for (i = 1; i < fwspec->num_ids; i++) {
 		larbidx = MTK_M4U_TO_LARB(fwspec->ids[i]);
 		if (larbid != larbidx) {
@@ -581,6 +802,9 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 		}
 	}
 	larbdev = data->larb_imu[larbid].dev;
+	if (!larbdev)
+		return ERR_PTR(-EINVAL);
+
 	link = device_link_add(dev, larbdev,
 			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
 	if (!link)
@@ -599,34 +823,55 @@ static void mtk_iommu_release_device(struct device *dev)
 		return;
 
 	data = dev_iommu_priv_get(dev);
-	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
-	larbdev = data->larb_imu[larbid].dev;
-	device_link_remove(dev, larbdev);
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+		larbdev = data->larb_imu[larbid].dev;
+		device_link_remove(dev, larbdev);
+	}
 
 	iommu_fwspec_free(dev);
 }
 
+static int mtk_iommu_get_group_id(struct device *dev, const struct mtk_iommu_plat_data *plat_data)
+{
+	unsigned int bankid;
+
+	/*
+	 * If the bank function is enabled, each bank is a iommu group/domain.
+	 * Otherwise, each iova region is a iommu group/domain.
+	 */
+	bankid = mtk_iommu_get_bank_id(dev, plat_data);
+	if (bankid)
+		return bankid;
+
+	return mtk_iommu_get_iova_region_id(dev, plat_data);
+}
+
 static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 {
-	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	struct mtk_iommu_data *c_data = dev_iommu_priv_get(dev), *data;
+	struct list_head *hw_list = c_data->hw_list;
 	struct iommu_group *group;
-	int domid;
+	int groupid;
 
+	data = mtk_iommu_get_frst_data(hw_list);
 	if (!data)
 		return ERR_PTR(-ENODEV);
 
-	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
-	if (domid < 0)
-		return ERR_PTR(domid);
+	groupid = mtk_iommu_get_group_id(dev, data->plat_data);
+	if (groupid < 0)
+		return ERR_PTR(groupid);
 
-	group = data->m4u_group[domid];
+	mutex_lock(&data->mutex);
+	group = data->m4u_group[groupid];
 	if (!group) {
 		group = iommu_group_alloc();
 		if (!IS_ERR(group))
-			data->m4u_group[domid] = group;
+			data->m4u_group[groupid] = group;
 	} else {
 		iommu_group_ref_get(group);
 	}
+	mutex_unlock(&data->mutex);
 	return group;
 }
 
@@ -656,14 +901,14 @@ static void mtk_iommu_get_resv_regions(struct device *dev,
 				       struct list_head *head)
 {
 	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
-	unsigned int domid = mtk_iommu_get_domain_id(dev, data->plat_data), i;
+	unsigned int regionid = mtk_iommu_get_iova_region_id(dev, data->plat_data), i;
 	const struct mtk_iommu_iova_region *resv, *curdom;
 	struct iommu_resv_region *region;
 	int prot = IOMMU_WRITE | IOMMU_READ;
 
-	if ((int)domid < 0)
+	if ((int)regionid < 0)
 		return;
-	curdom = data->plat_data->iova_region + domid;
+	curdom = data->plat_data->iova_region + regionid;
 	for (i = 0; i < data->plat_data->iova_region_nr; i++) {
 		resv = data->plat_data->iova_region + i;
 
@@ -704,42 +949,24 @@ static const struct iommu_ops mtk_iommu_ops = {
 	}
 };
 
-static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data, unsigned int bankid)
 {
+	const struct mtk_iommu_bank_data *bankx = &data->bank[bankid];
+	const struct mtk_iommu_bank_data *bank0 = &data->bank[0];
 	u32 regval;
 
+	/*
+	 * Global control settings are in bank0. May re-init these global registers
+	 * since no sure if there is bank0 consumers.
+	 */
 	if (data->plat_data->m4u_plat == M4U_MT8173) {
 		regval = F_MMU_PREFETCH_RT_REPLACE_MOD |
 			 F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173;
 	} else {
-		regval = readl_relaxed(data->base + REG_MMU_CTRL_REG);
+		regval = readl_relaxed(bank0->base + REG_MMU_CTRL_REG);
 		regval |= F_MMU_TF_PROT_TO_PROGRAM_ADDR;
 	}
-	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
-
-	regval = F_L2_MULIT_HIT_EN |
-		F_TABLE_WALK_FAULT_INT_EN |
-		F_PREETCH_FIFO_OVERFLOW_INT_EN |
-		F_MISS_FIFO_OVERFLOW_INT_EN |
-		F_PREFETCH_FIFO_ERR_INT_EN |
-		F_MISS_FIFO_ERR_INT_EN;
-	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL0);
-
-	regval = F_INT_TRANSLATION_FAULT |
-		F_INT_MAIN_MULTI_HIT_FAULT |
-		F_INT_INVALID_PA_FAULT |
-		F_INT_ENTRY_REPLACEMENT_FAULT |
-		F_INT_TLB_MISS_FAULT |
-		F_INT_MISS_TRANSACTION_FIFO_FAULT |
-		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
-	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
-
-	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR))
-		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
-	else
-		regval = lower_32_bits(data->protect_base) |
-			 upper_32_bits(data->protect_base);
-	writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);
+	writel_relaxed(regval, bank0->base + REG_MMU_CTRL_REG);
 
 	if (data->enable_4GB &&
 	    MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_VLD_PA_RNG)) {
@@ -748,31 +975,61 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		 * 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30].
 		 */
 		regval = F_MMU_VLD_PA_RNG(7, 4);
-		writel_relaxed(regval, data->base + REG_MMU_VLD_PA_RNG);
+		writel_relaxed(regval, bank0->base + REG_MMU_VLD_PA_RNG);
 	}
-	writel_relaxed(0, data->base + REG_MMU_DCM_DIS);
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, DCM_DISABLE))
+		writel_relaxed(F_MMU_DCM, bank0->base + REG_MMU_DCM_DIS);
+	else
+		writel_relaxed(0, bank0->base + REG_MMU_DCM_DIS);
+
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, WR_THROT_EN)) {
 		/* write command throttling mode */
-		regval = readl_relaxed(data->base + REG_MMU_WR_LEN_CTRL);
+		regval = readl_relaxed(bank0->base + REG_MMU_WR_LEN_CTRL);
 		regval &= ~F_MMU_WR_THROT_DIS_MASK;
-		writel_relaxed(regval, data->base + REG_MMU_WR_LEN_CTRL);
+		writel_relaxed(regval, bank0->base + REG_MMU_WR_LEN_CTRL);
 	}
 
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) {
 		/* The register is called STANDARD_AXI_MODE in this case */
 		regval = 0;
 	} else {
-		regval = readl_relaxed(data->base + REG_MMU_MISC_CTRL);
-		regval &= ~F_MMU_STANDARD_AXI_MODE_MASK;
+		regval = readl_relaxed(bank0->base + REG_MMU_MISC_CTRL);
+		if (!MTK_IOMMU_HAS_FLAG(data->plat_data, STD_AXI_MODE))
+			regval &= ~F_MMU_STANDARD_AXI_MODE_MASK;
 		if (MTK_IOMMU_HAS_FLAG(data->plat_data, OUT_ORDER_WR_EN))
 			regval &= ~F_MMU_IN_ORDER_WR_EN_MASK;
 	}
-	writel_relaxed(regval, data->base + REG_MMU_MISC_CTRL);
+	writel_relaxed(regval, bank0->base + REG_MMU_MISC_CTRL);
 
-	if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
-			     dev_name(data->dev), (void *)data)) {
-		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
-		dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq);
+	/* Independent settings for each bank */
+	regval = F_L2_MULIT_HIT_EN |
+		F_TABLE_WALK_FAULT_INT_EN |
+		F_PREETCH_FIFO_OVERFLOW_INT_EN |
+		F_MISS_FIFO_OVERFLOW_INT_EN |
+		F_PREFETCH_FIFO_ERR_INT_EN |
+		F_MISS_FIFO_ERR_INT_EN;
+	writel_relaxed(regval, bankx->base + REG_MMU_INT_CONTROL0);
+
+	regval = F_INT_TRANSLATION_FAULT |
+		F_INT_MAIN_MULTI_HIT_FAULT |
+		F_INT_INVALID_PA_FAULT |
+		F_INT_ENTRY_REPLACEMENT_FAULT |
+		F_INT_TLB_MISS_FAULT |
+		F_INT_MISS_TRANSACTION_FIFO_FAULT |
+		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
+	writel_relaxed(regval, bankx->base + REG_MMU_INT_MAIN_CONTROL);
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR))
+		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
+	else
+		regval = lower_32_bits(data->protect_base) |
+			 upper_32_bits(data->protect_base);
+	writel_relaxed(regval, bankx->base + REG_MMU_IVRP_PADDR);
+
+	if (devm_request_irq(bankx->parent_dev, bankx->irq, mtk_iommu_isr, 0,
+			     dev_name(bankx->parent_dev), (void *)bankx)) {
+		writel_relaxed(0, bankx->base + REG_MMU_PT_BASE_ADDR);
+		dev_err(bankx->parent_dev, "Failed @ IRQ-%d Request\n", bankx->irq);
 		return -ENODEV;
 	}
 
@@ -784,21 +1041,91 @@ static const struct component_master_ops mtk_iommu_com_ops = {
 	.unbind		= mtk_iommu_unbind,
 };
 
+static int mtk_iommu_mm_dts_parse(struct device *dev, struct component_match **match,
+				  struct mtk_iommu_data *data)
+{
+	struct device_node *larbnode, *smicomm_node, *smi_subcomm_node;
+	struct platform_device *plarbdev;
+	struct device_link *link;
+	int i, larb_nr, ret;
+
+	larb_nr = of_count_phandle_with_args(dev->of_node, "mediatek,larbs", NULL);
+	if (larb_nr < 0)
+		return larb_nr;
+
+	for (i = 0; i < larb_nr; i++) {
+		u32 id;
+
+		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
+		if (!larbnode)
+			return -EINVAL;
+
+		if (!of_device_is_available(larbnode)) {
+			of_node_put(larbnode);
+			continue;
+		}
+
+		ret = of_property_read_u32(larbnode, "mediatek,larb-id", &id);
+		if (ret)/* The id is consecutive if there is no this property */
+			id = i;
+
+		plarbdev = of_find_device_by_node(larbnode);
+		if (!plarbdev) {
+			of_node_put(larbnode);
+			return -ENODEV;
+		}
+		if (!plarbdev->dev.driver) {
+			of_node_put(larbnode);
+			return -EPROBE_DEFER;
+		}
+		data->larb_imu[id].dev = &plarbdev->dev;
+
+		component_match_add_release(dev, match, component_release_of,
+					    component_compare_of, larbnode);
+	}
+
+	/* Get smi-(sub)-common dev from the last larb. */
+	smi_subcomm_node = of_parse_phandle(larbnode, "mediatek,smi", 0);
+	if (!smi_subcomm_node)
+		return -EINVAL;
+
+	/*
+	 * It may have two level smi-common. the node is smi-sub-common if it
+	 * has a new mediatek,smi property. otherwise it is smi-commmon.
+	 */
+	smicomm_node = of_parse_phandle(smi_subcomm_node, "mediatek,smi", 0);
+	if (smicomm_node)
+		of_node_put(smi_subcomm_node);
+	else
+		smicomm_node = smi_subcomm_node;
+
+	plarbdev = of_find_device_by_node(smicomm_node);
+	of_node_put(smicomm_node);
+	data->smicomm_dev = &plarbdev->dev;
+
+	link = device_link_add(data->smicomm_dev, dev,
+			       DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
+	if (!link) {
+		dev_err(dev, "Unable to link %s.\n", dev_name(data->smicomm_dev));
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int mtk_iommu_probe(struct platform_device *pdev)
 {
 	struct mtk_iommu_data   *data;
 	struct device           *dev = &pdev->dev;
-	struct device_node	*larbnode, *smicomm_node;
-	struct platform_device	*plarbdev;
-	struct device_link	*link;
 	struct resource         *res;
 	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
 	struct regmap		*infracfg;
 	void                    *protect;
-	int                     i, larb_nr, ret;
+	int                     ret, banks_num, i = 0;
 	u32			val;
 	char                    *p;
+	struct mtk_iommu_bank_data *bank;
+	void __iomem		*base;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -835,15 +1162,36 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
 	}
 
+	banks_num = data->plat_data->banks_num;
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	data->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(data->base))
-		return PTR_ERR(data->base);
+	if (resource_size(res) < banks_num * MTK_IOMMU_BANK_SZ) {
+		dev_err(dev, "banknr %d. res %pR is not enough.\n", banks_num, res);
+		return -EINVAL;
+	}
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 	ioaddr = res->start;
 
-	data->irq = platform_get_irq(pdev, 0);
-	if (data->irq < 0)
-		return data->irq;
+	data->bank = devm_kmalloc(dev, banks_num * sizeof(*data->bank), GFP_KERNEL);
+	if (!data->bank)
+		return -ENOMEM;
+
+	do {
+		if (!data->plat_data->banks_enable[i])
+			continue;
+		bank = &data->bank[i];
+		bank->id = i;
+		bank->base = base + i * MTK_IOMMU_BANK_SZ;
+		bank->m4u_dom = NULL;
+
+		bank->irq = platform_get_irq(pdev, i);
+		if (bank->irq < 0)
+			return bank->irq;
+		bank->parent_dev = dev;
+		bank->parent_data = data;
+		spin_lock_init(&bank->tlb_lock);
+	} while (++i < banks_num);
 
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_BCLK)) {
 		data->bclk = devm_clk_get(dev, "bclk");
@@ -851,62 +1199,27 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 			return PTR_ERR(data->bclk);
 	}
 
-	larb_nr = of_count_phandle_with_args(dev->of_node,
-					     "mediatek,larbs", NULL);
-	if (larb_nr < 0)
-		return larb_nr;
-
-	for (i = 0; i < larb_nr; i++) {
-		u32 id;
-
-		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
-		if (!larbnode)
-			return -EINVAL;
-
-		if (!of_device_is_available(larbnode)) {
-			of_node_put(larbnode);
-			continue;
-		}
-
-		ret = of_property_read_u32(larbnode, "mediatek,larb-id", &id);
-		if (ret)/* The id is consecutive if there is no this property */
-			id = i;
+	pm_runtime_enable(dev);
 
-		plarbdev = of_find_device_by_node(larbnode);
-		if (!plarbdev) {
-			of_node_put(larbnode);
-			return -ENODEV;
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		ret = mtk_iommu_mm_dts_parse(dev, &match, data);
+		if (ret) {
+			dev_err(dev, "mm dts parse fail(%d).", ret);
+			goto out_runtime_disable;
 		}
-		if (!plarbdev->dev.driver) {
-			of_node_put(larbnode);
-			return -EPROBE_DEFER;
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
+		   data->plat_data->pericfg_comp_str) {
+		infracfg = syscon_regmap_lookup_by_compatible(data->plat_data->pericfg_comp_str);
+		if (IS_ERR(infracfg)) {
+			ret = PTR_ERR(infracfg);
+			goto out_runtime_disable;
 		}
-		data->larb_imu[id].dev = &plarbdev->dev;
-
-		component_match_add_release(dev, &match, component_release_of,
-					    component_compare_of, larbnode);
-	}
-
-	/* Get smi-common dev from the last larb. */
-	smicomm_node = of_parse_phandle(larbnode, "mediatek,smi", 0);
-	if (!smicomm_node)
-		return -EINVAL;
-
-	plarbdev = of_find_device_by_node(smicomm_node);
-	of_node_put(smicomm_node);
-	data->smicomm_dev = &plarbdev->dev;
-
-	pm_runtime_enable(dev);
 
-	link = device_link_add(data->smicomm_dev, dev,
-			DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
-	if (!link) {
-		dev_err(dev, "Unable to link %s.\n", dev_name(data->smicomm_dev));
-		ret = -EINVAL;
-		goto out_runtime_disable;
+		data->pericfg = infracfg;
 	}
 
 	platform_set_drvdata(pdev, data);
+	mutex_init(&data->mutex);
 
 	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
 				     "mtk-iommu.%pa", &ioaddr);
@@ -917,8 +1230,14 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_sysfs_remove;
 
-	spin_lock_init(&data->tlb_lock);
-	list_add_tail(&data->list, &m4ulist);
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
+		list_add_tail(&data->list, data->plat_data->hw_list);
+		data->hw_list = data->plat_data->hw_list;
+	} else {
+		INIT_LIST_HEAD(&data->hw_list_head);
+		list_add_tail(&data->list, &data->hw_list_head);
+		data->hw_list = &data->hw_list_head;
+	}
 
 	if (!iommu_present(&platform_bus_type)) {
 		ret = bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
@@ -926,9 +1245,20 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 			goto out_list_del;
 	}
 
-	ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
-	if (ret)
-		goto out_bus_set_null;
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+		if (ret)
+			goto out_bus_set_null;
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
+		   MTK_IOMMU_HAS_FLAG(data->plat_data, IFA_IOMMU_PCIE_SUPPORT)) {
+#ifdef CONFIG_PCI
+		if (!iommu_present(&pci_bus_type)) {
+			ret = bus_set_iommu(&pci_bus_type, &mtk_iommu_ops);
+			if (ret) /* PCIe fail don't affect platform_bus. */
+				goto out_list_del;
+		}
+#endif
+	}
 	return ret;
 
 out_bus_set_null:
@@ -939,7 +1269,8 @@ out_list_del:
 out_sysfs_remove:
 	iommu_device_sysfs_remove(&data->iommu);
 out_link_remove:
-	device_link_remove(data->smicomm_dev, dev);
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
+		device_link_remove(data->smicomm_dev, dev);
 out_runtime_disable:
 	pm_runtime_disable(dev);
 	return ret;
@@ -948,18 +1279,30 @@ out_runtime_disable:
 static int mtk_iommu_remove(struct platform_device *pdev)
 {
 	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
+	struct mtk_iommu_bank_data *bank;
+	int i;
 
 	iommu_device_sysfs_remove(&data->iommu);
 	iommu_device_unregister(&data->iommu);
 
-	if (iommu_present(&platform_bus_type))
-		bus_set_iommu(&platform_bus_type, NULL);
+	list_del(&data->list);
 
-	clk_disable_unprepare(data->bclk);
-	device_link_remove(data->smicomm_dev, &pdev->dev);
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		device_link_remove(data->smicomm_dev, &pdev->dev);
+		component_master_del(&pdev->dev, &mtk_iommu_com_ops);
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
+		   MTK_IOMMU_HAS_FLAG(data->plat_data, IFA_IOMMU_PCIE_SUPPORT)) {
+#ifdef CONFIG_PCI
+		bus_set_iommu(&pci_bus_type, NULL);
+#endif
+	}
 	pm_runtime_disable(&pdev->dev);
-	devm_free_irq(&pdev->dev, data->irq, data);
-	component_master_del(&pdev->dev, &mtk_iommu_com_ops);
+	for (i = 0; i < data->plat_data->banks_num; i++) {
+		bank = &data->bank[i];
+		if (!bank->m4u_dom)
+			continue;
+		devm_free_irq(&pdev->dev, bank->irq, bank);
+	}
 	return 0;
 }
 
@@ -967,16 +1310,23 @@ static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
 	struct mtk_iommu_suspend_reg *reg = &data->reg;
-	void __iomem *base = data->base;
+	void __iomem *base;
+	int i = 0;
 
+	base = data->bank[i].base;
 	reg->wr_len_ctrl = readl_relaxed(base + REG_MMU_WR_LEN_CTRL);
 	reg->misc_ctrl = readl_relaxed(base + REG_MMU_MISC_CTRL);
 	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM_DIS);
 	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
-	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
-	reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
-	reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
 	reg->vld_pa_rng = readl_relaxed(base + REG_MMU_VLD_PA_RNG);
+	do {
+		if (!data->plat_data->banks_enable[i])
+			continue;
+		base = data->bank[i].base;
+		reg->int_control[i] = readl_relaxed(base + REG_MMU_INT_CONTROL0);
+		reg->int_main_control[i] = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
+		reg->ivrp_paddr[i] = readl_relaxed(base + REG_MMU_IVRP_PADDR);
+	} while (++i < data->plat_data->banks_num);
 	clk_disable_unprepare(data->bclk);
 	return 0;
 }
@@ -985,9 +1335,9 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
 	struct mtk_iommu_suspend_reg *reg = &data->reg;
-	struct mtk_iommu_domain *m4u_dom = data->m4u_dom;
-	void __iomem *base = data->base;
-	int ret;
+	struct mtk_iommu_domain *m4u_dom;
+	void __iomem *base;
+	int ret, i = 0;
 
 	ret = clk_prepare_enable(data->bclk);
 	if (ret) {
@@ -999,18 +1349,26 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 	 * Uppon first resume, only enable the clk and return, since the values of the
 	 * registers are not yet set.
 	 */
-	if (!m4u_dom)
+	if (!reg->wr_len_ctrl)
 		return 0;
 
+	base = data->bank[i].base;
 	writel_relaxed(reg->wr_len_ctrl, base + REG_MMU_WR_LEN_CTRL);
 	writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL);
 	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS);
 	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
-	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
-	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
-	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
-	writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK, base + REG_MMU_PT_BASE_ADDR);
+	do {
+		m4u_dom = data->bank[i].m4u_dom;
+		if (!data->plat_data->banks_enable[i] || !m4u_dom)
+			continue;
+		base = data->bank[i].base;
+		writel_relaxed(reg->int_control[i], base + REG_MMU_INT_CONTROL0);
+		writel_relaxed(reg->int_main_control[i], base + REG_MMU_INT_MAIN_CONTROL);
+		writel_relaxed(reg->ivrp_paddr[i], base + REG_MMU_IVRP_PADDR);
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
+		       base + REG_MMU_PT_BASE_ADDR);
+	} while (++i < data->plat_data->banks_num);
 
 	/*
 	 * Users may allocate dma buffer before they call pm_runtime_get,
@@ -1029,17 +1387,24 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = {
 
 static const struct mtk_iommu_plat_data mt2712_data = {
 	.m4u_plat     = M4U_MT2712,
-	.flags        = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG,
+	.flags        = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG | SHARE_PGTABLE |
+			MTK_IOMMU_TYPE_MM,
+	.hw_list      = &m4ulist,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
 	.iova_region  = single_domain,
+	.banks_num    = 1,
+	.banks_enable = {true},
 	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}},
 };
 
 static const struct mtk_iommu_plat_data mt6779_data = {
 	.m4u_plat      = M4U_MT6779,
-	.flags         = HAS_SUB_COMM | OUT_ORDER_WR_EN | WR_THROT_EN,
+	.flags         = HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | WR_THROT_EN |
+			 MTK_IOMMU_TYPE_MM,
 	.inv_sel_reg   = REG_MMU_INV_SEL_GEN2,
+	.banks_num    = 1,
+	.banks_enable = {true},
 	.iova_region   = single_domain,
 	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap  = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}},
@@ -1047,8 +1412,10 @@ static const struct mtk_iommu_plat_data mt6779_data = {
 
 static const struct mtk_iommu_plat_data mt8167_data = {
 	.m4u_plat     = M4U_MT8167,
-	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR,
+	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
 	.iova_region  = single_domain,
 	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */
@@ -1057,8 +1424,10 @@ static const struct mtk_iommu_plat_data mt8167_data = {
 static const struct mtk_iommu_plat_data mt8173_data = {
 	.m4u_plat     = M4U_MT8173,
 	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
-			HAS_LEGACY_IVRP_PADDR,
+			HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
 	.iova_region  = single_domain,
 	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */
@@ -1066,31 +1435,100 @@ static const struct mtk_iommu_plat_data mt8173_data = {
 
 static const struct mtk_iommu_plat_data mt8183_data = {
 	.m4u_plat     = M4U_MT8183,
-	.flags        = RESET_AXI,
+	.flags        = RESET_AXI | MTK_IOMMU_TYPE_MM,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
 	.iova_region  = single_domain,
 	.iova_region_nr = ARRAY_SIZE(single_domain),
 	.larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}},
 };
 
+static const struct mtk_iommu_plat_data mt8186_data_mm = {
+	.m4u_plat       = M4U_MT8186,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
+	.larbid_remap   = {{0}, {1, MTK_INVALID_LARBID, 8}, {4}, {7}, {2}, {9, 11, 19, 20},
+			   {MTK_INVALID_LARBID, 14, 16},
+			   {MTK_INVALID_LARBID, 13, MTK_INVALID_LARBID, 17}},
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+};
+
 static const struct mtk_iommu_plat_data mt8192_data = {
 	.m4u_plat       = M4U_MT8192,
-	.flags          = HAS_BCLK | HAS_SUB_COMM | OUT_ORDER_WR_EN |
-			  WR_THROT_EN | IOVA_34_EN,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
 	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
 	.iova_region    = mt8192_multi_dom,
 	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
 	.larbid_remap   = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20},
 			   {0, 14, 16}, {0, 13, 18, 17}},
 };
 
+static const struct mtk_iommu_plat_data mt8195_data_infra = {
+	.m4u_plat	  = M4U_MT8195,
+	.flags            = WR_THROT_EN | DCM_DISABLE | STD_AXI_MODE | PM_CLK_AO |
+			    MTK_IOMMU_TYPE_INFRA | IFA_IOMMU_PCIE_SUPPORT,
+	.pericfg_comp_str = "mediatek,mt8195-pericfg_ao",
+	.inv_sel_reg      = REG_MMU_INV_SEL_GEN2,
+	.banks_num	  = 5,
+	.banks_enable     = {true, false, false, false, true},
+	.banks_portmsk    = {[0] = GENMASK(19, 16),     /* PCIe */
+			     [4] = GENMASK(31, 20),     /* USB */
+			    },
+	.iova_region      = single_domain,
+	.iova_region_nr   = ARRAY_SIZE(single_domain),
+};
+
+static const struct mtk_iommu_plat_data mt8195_data_vdo = {
+	.m4u_plat	= M4U_MT8195,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region	= mt8192_multi_dom,
+	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{2, 0}, {21}, {24}, {7}, {19}, {9, 10, 11},
+			   {13, 17, 15/* 17b */, 25}, {5}},
+};
+
+static const struct mtk_iommu_plat_data mt8195_data_vpp = {
+	.m4u_plat	= M4U_MT8195,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_3BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region	= mt8192_multi_dom,
+	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{1}, {3},
+			   {22, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 23},
+			   {8}, {20}, {12},
+			   /* 16: 16a; 29: 16b; 30: CCUtop0; 31: CCUtop1 */
+			   {14, 16, 29, 26, 30, 31, 18},
+			   {4, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 6}},
+};
+
 static const struct of_device_id mtk_iommu_of_ids[] = {
 	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
 	{ .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data},
 	{ .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data},
 	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
 	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
+	{ .compatible = "mediatek,mt8186-iommu-mm",    .data = &mt8186_data_mm}, /* mm: m4u */
 	{ .compatible = "mediatek,mt8192-m4u", .data = &mt8192_data},
+	{ .compatible = "mediatek,mt8195-iommu-infra", .data = &mt8195_data_infra},
+	{ .compatible = "mediatek,mt8195-iommu-vdo",   .data = &mt8195_data_vdo},
+	{ .compatible = "mediatek,mt8195-iommu-vpp",   .data = &mt8195_data_vpp},
 	{}
 };
 
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
deleted file mode 100644
index b742432220c5..000000000000
--- a/drivers/iommu/mtk_iommu.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (c) 2015-2016 MediaTek Inc.
- * Author: Honghui Zhang <honghui.zhang@mediatek.com>
- */
-
-#ifndef _MTK_IOMMU_H_
-#define _MTK_IOMMU_H_
-
-#include <linux/clk.h>
-#include <linux/component.h>
-#include <linux/device.h>
-#include <linux/io.h>
-#include <linux/io-pgtable.h>
-#include <linux/iommu.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/dma-mapping.h>
-#include <soc/mediatek/smi.h>
-#include <dt-bindings/memory/mtk-memory-port.h>
-
-#define MTK_LARB_COM_MAX	8
-#define MTK_LARB_SUBCOM_MAX	4
-
-#define MTK_IOMMU_GROUP_MAX	8
-
-struct mtk_iommu_suspend_reg {
-	union {
-		u32			standard_axi_mode;/* v1 */
-		u32			misc_ctrl;/* v2 */
-	};
-	u32				dcm_dis;
-	u32				ctrl_reg;
-	u32				int_control0;
-	u32				int_main_control;
-	u32				ivrp_paddr;
-	u32				vld_pa_rng;
-	u32				wr_len_ctrl;
-};
-
-enum mtk_iommu_plat {
-	M4U_MT2701,
-	M4U_MT2712,
-	M4U_MT6779,
-	M4U_MT8167,
-	M4U_MT8173,
-	M4U_MT8183,
-	M4U_MT8192,
-};
-
-struct mtk_iommu_iova_region;
-
-struct mtk_iommu_plat_data {
-	enum mtk_iommu_plat m4u_plat;
-	u32                 flags;
-	u32                 inv_sel_reg;
-
-	unsigned int				iova_region_nr;
-	const struct mtk_iommu_iova_region	*iova_region;
-	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
-};
-
-struct mtk_iommu_domain;
-
-struct mtk_iommu_data {
-	void __iomem			*base;
-	int				irq;
-	struct device			*dev;
-	struct clk			*bclk;
-	phys_addr_t			protect_base; /* protect memory base */
-	struct mtk_iommu_suspend_reg	reg;
-	struct mtk_iommu_domain		*m4u_dom;
-	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
-	bool                            enable_4GB;
-	spinlock_t			tlb_lock; /* lock for tlb range flush */
-
-	struct iommu_device		iommu;
-	const struct mtk_iommu_plat_data *plat_data;
-	struct device			*smicomm_dev;
-
-	struct dma_iommu_mapping	*mapping; /* For mtk_iommu_v1.c */
-
-	struct list_head		list;
-	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
-};
-
-static inline int mtk_iommu_bind(struct device *dev)
-{
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-
-	return component_bind_all(dev, &data->larb_imu);
-}
-
-static inline void mtk_iommu_unbind(struct device *dev)
-{
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-
-	component_unbind_all(dev, &data->larb_imu);
-}
-
-#endif
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index ecff800656e6..e1cb51b9866c 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -7,7 +7,6 @@
  *
  * Based on driver/iommu/mtk_iommu.c
  */
-#include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -28,10 +27,9 @@
 #include <linux/spinlock.h>
 #include <asm/barrier.h>
 #include <asm/dma-iommu.h>
-#include <linux/init.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
 #include <dt-bindings/memory/mt2701-larb-port.h>
 #include <soc/mediatek/smi.h>
-#include "mtk_iommu.h"
 
 #define REG_MMU_PT_BASE_ADDR			0x000
 
@@ -80,6 +78,7 @@
 /* MTK generation one iommu HW only support 4K size mapping */
 #define MT2701_IOMMU_PAGE_SHIFT			12
 #define MT2701_IOMMU_PAGE_SIZE			(1UL << MT2701_IOMMU_PAGE_SHIFT)
+#define MT2701_LARB_NR_MAX			3
 
 /*
  * MTK m4u support 4GB iova address space, and only support 4K page
@@ -87,17 +86,53 @@
  */
 #define M2701_IOMMU_PGT_SIZE			SZ_4M
 
-struct mtk_iommu_domain {
+struct mtk_iommu_v1_suspend_reg {
+	u32			standard_axi_mode;
+	u32			dcm_dis;
+	u32			ctrl_reg;
+	u32			int_control0;
+};
+
+struct mtk_iommu_v1_data {
+	void __iomem			*base;
+	int				irq;
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_v1_domain	*m4u_dom;
+
+	struct iommu_device		iommu;
+	struct dma_iommu_mapping	*mapping;
+	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
+
+	struct mtk_iommu_v1_suspend_reg	reg;
+};
+
+struct mtk_iommu_v1_domain {
 	spinlock_t			pgtlock; /* lock for page table */
 	struct iommu_domain		domain;
 	u32				*pgt_va;
 	dma_addr_t			pgt_pa;
-	struct mtk_iommu_data		*data;
+	struct mtk_iommu_v1_data	*data;
 };
 
-static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
+static int mtk_iommu_v1_bind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->larb_imu);
+}
+
+static void mtk_iommu_v1_unbind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->larb_imu);
+}
+
+static struct mtk_iommu_v1_domain *to_mtk_domain(struct iommu_domain *dom)
 {
-	return container_of(dom, struct mtk_iommu_domain, domain);
+	return container_of(dom, struct mtk_iommu_v1_domain, domain);
 }
 
 static const int mt2701_m4u_in_larb[] = {
@@ -123,7 +158,7 @@ static inline int mt2701_m4u_to_port(int id)
 	return id - mt2701_m4u_in_larb[larb];
 }
 
-static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
+static void mtk_iommu_v1_tlb_flush_all(struct mtk_iommu_v1_data *data)
 {
 	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			data->base + REG_MMU_INV_SEL);
@@ -131,8 +166,8 @@ static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
 	wmb(); /* Make sure the tlb flush all done */
 }
 
-static void mtk_iommu_tlb_flush_range(struct mtk_iommu_data *data,
-				unsigned long iova, size_t size)
+static void mtk_iommu_v1_tlb_flush_range(struct mtk_iommu_v1_data *data,
+					 unsigned long iova, size_t size)
 {
 	int ret;
 	u32 tmp;
@@ -150,16 +185,16 @@ static void mtk_iommu_tlb_flush_range(struct mtk_iommu_data *data,
 	if (ret) {
 		dev_warn(data->dev,
 			 "Partial TLB flush timed out, falling back to full flush\n");
-		mtk_iommu_tlb_flush_all(data);
+		mtk_iommu_v1_tlb_flush_all(data);
 	}
 	/* Clear the CPE status */
 	writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
 }
 
-static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
+static irqreturn_t mtk_iommu_v1_isr(int irq, void *dev_id)
 {
-	struct mtk_iommu_data *data = dev_id;
-	struct mtk_iommu_domain *dom = data->m4u_dom;
+	struct mtk_iommu_v1_data *data = dev_id;
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
 	u32 int_state, regval, fault_iova, fault_pa;
 	unsigned int fault_larb, fault_port;
 
@@ -189,13 +224,13 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 	regval |= F_INT_CLR_BIT;
 	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
 
-	mtk_iommu_tlb_flush_all(data);
+	mtk_iommu_v1_tlb_flush_all(data);
 
 	return IRQ_HANDLED;
 }
 
-static void mtk_iommu_config(struct mtk_iommu_data *data,
-			     struct device *dev, bool enable)
+static void mtk_iommu_v1_config(struct mtk_iommu_v1_data *data,
+				struct device *dev, bool enable)
 {
 	struct mtk_smi_larb_iommu    *larb_mmu;
 	unsigned int                 larbid, portid;
@@ -217,9 +252,9 @@ static void mtk_iommu_config(struct mtk_iommu_data *data,
 	}
 }
 
-static int mtk_iommu_domain_finalise(struct mtk_iommu_data *data)
+static int mtk_iommu_v1_domain_finalise(struct mtk_iommu_v1_data *data)
 {
-	struct mtk_iommu_domain *dom = data->m4u_dom;
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
 
 	spin_lock_init(&dom->pgtlock);
 
@@ -235,9 +270,9 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_data *data)
 	return 0;
 }
 
-static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
+static struct iommu_domain *mtk_iommu_v1_domain_alloc(unsigned type)
 {
-	struct mtk_iommu_domain *dom;
+	struct mtk_iommu_v1_domain *dom;
 
 	if (type != IOMMU_DOMAIN_UNMANAGED)
 		return NULL;
@@ -249,21 +284,20 @@ static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
 	return &dom->domain;
 }
 
-static void mtk_iommu_domain_free(struct iommu_domain *domain)
+static void mtk_iommu_v1_domain_free(struct iommu_domain *domain)
 {
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	struct mtk_iommu_data *data = dom->data;
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_data *data = dom->data;
 
 	dma_free_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
 			dom->pgt_va, dom->pgt_pa);
 	kfree(to_mtk_domain(domain));
 }
 
-static int mtk_iommu_attach_device(struct iommu_domain *domain,
-				   struct device *dev)
+static int mtk_iommu_v1_attach_device(struct iommu_domain *domain, struct device *dev)
 {
-	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
 	struct dma_iommu_mapping *mtk_mapping;
 	int ret;
 
@@ -274,29 +308,28 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
-		ret = mtk_iommu_domain_finalise(data);
+		ret = mtk_iommu_v1_domain_finalise(data);
 		if (ret) {
 			data->m4u_dom = NULL;
 			return ret;
 		}
 	}
 
-	mtk_iommu_config(data, dev, true);
+	mtk_iommu_v1_config(data, dev, true);
 	return 0;
 }
 
-static void mtk_iommu_detach_device(struct iommu_domain *domain,
-				    struct device *dev)
+static void mtk_iommu_v1_detach_device(struct iommu_domain *domain, struct device *dev)
 {
-	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
 
-	mtk_iommu_config(data, dev, false);
+	mtk_iommu_v1_config(data, dev, false);
 }
 
-static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+static int mtk_iommu_v1_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
 	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
 	unsigned long flags;
 	unsigned int i;
@@ -317,16 +350,15 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
-	mtk_iommu_tlb_flush_range(dom->data, iova, size);
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, size);
 
 	return map_size == size ? 0 : -EEXIST;
 }
 
-static size_t mtk_iommu_unmap(struct iommu_domain *domain,
-			      unsigned long iova, size_t size,
-			      struct iommu_iotlb_gather *gather)
+static size_t mtk_iommu_v1_unmap(struct iommu_domain *domain, unsigned long iova,
+				 size_t size, struct iommu_iotlb_gather *gather)
 {
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
 	unsigned long flags;
 	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
 	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
@@ -335,15 +367,14 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	memset(pgt_base_iova, 0, page_num * sizeof(u32));
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
-	mtk_iommu_tlb_flush_range(dom->data, iova, size);
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, size);
 
 	return size;
 }
 
-static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
-					  dma_addr_t iova)
+static phys_addr_t mtk_iommu_v1_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
-	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
 	unsigned long flags;
 	phys_addr_t pa;
 
@@ -355,17 +386,16 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pa;
 }
 
-static const struct iommu_ops mtk_iommu_ops;
+static const struct iommu_ops mtk_iommu_v1_ops;
 
 /*
  * MTK generation one iommu HW only support one iommu domain, and all the client
  * sharing the same iova address space.
  */
-static int mtk_iommu_create_mapping(struct device *dev,
-				    struct of_phandle_args *args)
+static int mtk_iommu_v1_create_mapping(struct device *dev, struct of_phandle_args *args)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_v1_data *data;
 	struct platform_device *m4updev;
 	struct dma_iommu_mapping *mtk_mapping;
 	int ret;
@@ -377,11 +407,11 @@ static int mtk_iommu_create_mapping(struct device *dev,
 	}
 
 	if (!fwspec) {
-		ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_ops);
+		ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_v1_ops);
 		if (ret)
 			return ret;
 		fwspec = dev_iommu_fwspec_get(dev);
-	} else if (dev_iommu_fwspec_get(dev)->ops != &mtk_iommu_ops) {
+	} else if (dev_iommu_fwspec_get(dev)->ops != &mtk_iommu_v1_ops) {
 		return -EINVAL;
 	}
 
@@ -413,16 +443,16 @@ static int mtk_iommu_create_mapping(struct device *dev,
 	return 0;
 }
 
-static int mtk_iommu_def_domain_type(struct device *dev)
+static int mtk_iommu_v1_def_domain_type(struct device *dev)
 {
 	return IOMMU_DOMAIN_UNMANAGED;
 }
 
-static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
+static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct of_phandle_args iommu_spec;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_v1_data *data;
 	int err, idx = 0, larbid, larbidx;
 	struct device_link *link;
 	struct device *larbdev;
@@ -440,7 +470,7 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 					   "#iommu-cells",
 					   idx, &iommu_spec)) {
 
-		err = mtk_iommu_create_mapping(dev, &iommu_spec);
+		err = mtk_iommu_v1_create_mapping(dev, &iommu_spec);
 		of_node_put(iommu_spec.np);
 		if (err)
 			return ERR_PTR(err);
@@ -450,13 +480,16 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 		idx++;
 	}
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
+	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
 		return ERR_PTR(-ENODEV); /* Not a iommu client device */
 
 	data = dev_iommu_priv_get(dev);
 
 	/* Link the consumer device with the smi-larb device(supplier) */
 	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	if (larbid >= MT2701_LARB_NR_MAX)
+		return ERR_PTR(-EINVAL);
+
 	for (idx = 1; idx < fwspec->num_ids; idx++) {
 		larbidx = mt2701_m4u_to_larb(fwspec->ids[idx]);
 		if (larbid != larbidx) {
@@ -467,6 +500,9 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 	}
 
 	larbdev = data->larb_imu[larbid].dev;
+	if (!larbdev)
+		return ERR_PTR(-EINVAL);
+
 	link = device_link_add(dev, larbdev,
 			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
 	if (!link)
@@ -475,10 +511,10 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 	return &data->iommu;
 }
 
-static void mtk_iommu_probe_finalize(struct device *dev)
+static void mtk_iommu_v1_probe_finalize(struct device *dev)
 {
 	struct dma_iommu_mapping *mtk_mapping;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_v1_data *data;
 	int err;
 
 	data        = dev_iommu_priv_get(dev);
@@ -489,14 +525,14 @@ static void mtk_iommu_probe_finalize(struct device *dev)
 		dev_err(dev, "Can't create IOMMU mapping - DMA-OPS will not work\n");
 }
 
-static void mtk_iommu_release_device(struct device *dev)
+static void mtk_iommu_v1_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_v1_data *data;
 	struct device *larbdev;
 	unsigned int larbid;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
+	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
 		return;
 
 	data = dev_iommu_priv_get(dev);
@@ -507,7 +543,7 @@ static void mtk_iommu_release_device(struct device *dev)
 	iommu_fwspec_free(dev);
 }
 
-static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
+static int mtk_iommu_v1_hw_init(const struct mtk_iommu_v1_data *data)
 {
 	u32 regval;
 	int ret;
@@ -537,7 +573,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 
 	writel_relaxed(F_MMU_DCM_ON, data->base + REG_MMU_DCM);
 
-	if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
+	if (devm_request_irq(data->dev, data->irq, mtk_iommu_v1_isr, 0,
 			     dev_name(data->dev), (void *)data)) {
 		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
 		clk_disable_unprepare(data->bclk);
@@ -548,39 +584,39 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 	return 0;
 }
 
-static const struct iommu_ops mtk_iommu_ops = {
-	.domain_alloc	= mtk_iommu_domain_alloc,
-	.probe_device	= mtk_iommu_probe_device,
-	.probe_finalize = mtk_iommu_probe_finalize,
-	.release_device	= mtk_iommu_release_device,
-	.def_domain_type = mtk_iommu_def_domain_type,
+static const struct iommu_ops mtk_iommu_v1_ops = {
+	.domain_alloc	= mtk_iommu_v1_domain_alloc,
+	.probe_device	= mtk_iommu_v1_probe_device,
+	.probe_finalize = mtk_iommu_v1_probe_finalize,
+	.release_device	= mtk_iommu_v1_release_device,
+	.def_domain_type = mtk_iommu_v1_def_domain_type,
 	.device_group	= generic_device_group,
 	.pgsize_bitmap	= ~0UL << MT2701_IOMMU_PAGE_SHIFT,
 	.owner          = THIS_MODULE,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
-		.attach_dev	= mtk_iommu_attach_device,
-		.detach_dev	= mtk_iommu_detach_device,
-		.map		= mtk_iommu_map,
-		.unmap		= mtk_iommu_unmap,
-		.iova_to_phys	= mtk_iommu_iova_to_phys,
-		.free		= mtk_iommu_domain_free,
+		.attach_dev	= mtk_iommu_v1_attach_device,
+		.detach_dev	= mtk_iommu_v1_detach_device,
+		.map		= mtk_iommu_v1_map,
+		.unmap		= mtk_iommu_v1_unmap,
+		.iova_to_phys	= mtk_iommu_v1_iova_to_phys,
+		.free		= mtk_iommu_v1_domain_free,
 	}
 };
 
-static const struct of_device_id mtk_iommu_of_ids[] = {
+static const struct of_device_id mtk_iommu_v1_of_ids[] = {
 	{ .compatible = "mediatek,mt2701-m4u", },
 	{}
 };
 
-static const struct component_master_ops mtk_iommu_com_ops = {
-	.bind		= mtk_iommu_bind,
-	.unbind		= mtk_iommu_unbind,
+static const struct component_master_ops mtk_iommu_v1_com_ops = {
+	.bind		= mtk_iommu_v1_bind,
+	.unbind		= mtk_iommu_v1_unbind,
 };
 
-static int mtk_iommu_probe(struct platform_device *pdev)
+static int mtk_iommu_v1_probe(struct platform_device *pdev)
 {
-	struct mtk_iommu_data		*data;
 	struct device			*dev = &pdev->dev;
+	struct mtk_iommu_v1_data	*data;
 	struct resource			*res;
 	struct component_match		*match = NULL;
 	void				*protect;
@@ -647,7 +683,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, data);
 
-	ret = mtk_iommu_hw_init(data);
+	ret = mtk_iommu_v1_hw_init(data);
 	if (ret)
 		return ret;
 
@@ -656,17 +692,17 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
 	if (ret)
 		goto out_sysfs_remove;
 
 	if (!iommu_present(&platform_bus_type)) {
-		ret = bus_set_iommu(&platform_bus_type,  &mtk_iommu_ops);
+		ret = bus_set_iommu(&platform_bus_type,  &mtk_iommu_v1_ops);
 		if (ret)
 			goto out_dev_unreg;
 	}
 
-	ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+	ret = component_master_add_with_match(dev, &mtk_iommu_v1_com_ops, match);
 	if (ret)
 		goto out_bus_set_null;
 	return ret;
@@ -680,9 +716,9 @@ out_sysfs_remove:
 	return ret;
 }
 
-static int mtk_iommu_remove(struct platform_device *pdev)
+static int mtk_iommu_v1_remove(struct platform_device *pdev)
 {
-	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
+	struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev);
 
 	iommu_device_sysfs_remove(&data->iommu);
 	iommu_device_unregister(&data->iommu);
@@ -692,14 +728,14 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(data->bclk);
 	devm_free_irq(&pdev->dev, data->irq, data);
-	component_master_del(&pdev->dev, &mtk_iommu_com_ops);
+	component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops);
 	return 0;
 }
 
-static int __maybe_unused mtk_iommu_suspend(struct device *dev)
+static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev)
 {
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
 	void __iomem *base = data->base;
 
 	reg->standard_axi_mode = readl_relaxed(base +
@@ -710,10 +746,10 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused mtk_iommu_resume(struct device *dev)
+static int __maybe_unused mtk_iommu_v1_resume(struct device *dev)
 {
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
 	void __iomem *base = data->base;
 
 	writel_relaxed(data->m4u_dom->pgt_pa, base + REG_MMU_PT_BASE_ADDR);
@@ -726,20 +762,20 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	return 0;
 }
 
-static const struct dev_pm_ops mtk_iommu_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(mtk_iommu_suspend, mtk_iommu_resume)
+static const struct dev_pm_ops mtk_iommu_v1_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(mtk_iommu_v1_suspend, mtk_iommu_v1_resume)
 };
 
-static struct platform_driver mtk_iommu_driver = {
-	.probe	= mtk_iommu_probe,
-	.remove	= mtk_iommu_remove,
+static struct platform_driver mtk_iommu_v1_driver = {
+	.probe	= mtk_iommu_v1_probe,
+	.remove	= mtk_iommu_v1_remove,
 	.driver	= {
 		.name = "mtk-iommu-v1",
-		.of_match_table = mtk_iommu_of_ids,
-		.pm = &mtk_iommu_pm_ops,
+		.of_match_table = mtk_iommu_v1_of_ids,
+		.pm = &mtk_iommu_v1_pm_ops,
 	}
 };
-module_platform_driver(mtk_iommu_driver);
+module_platform_driver(mtk_iommu_v1_driver);
 
 MODULE_DESCRIPTION("IOMMU API for MediaTek M4U v1 implementations");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 3833e86c6e7b..c898bcbbce11 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -99,7 +99,7 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 	if (!domain_device)
 		return -ENOMEM;
 
-	if (zdev->dma_table) {
+	if (zdev->dma_table && !zdev->s390_domain) {
 		cc = zpci_dma_exit_device(zdev);
 		if (cc) {
 			rc = -EIO;
@@ -107,6 +107,9 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 		}
 	}
 
+	if (zdev->s390_domain)
+		zpci_unregister_ioat(zdev, 0);
+
 	zdev->dma_table = s390_domain->dma_table;
 	cc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				virt_to_phys(zdev->dma_table));
@@ -136,7 +139,13 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 	return 0;
 
 out_restore:
-	zpci_dma_init_device(zdev);
+	if (!zdev->s390_domain) {
+		zpci_dma_init_device(zdev);
+	} else {
+		zdev->dma_table = zdev->s390_domain->dma_table;
+		zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+				   virt_to_phys(zdev->dma_table));
+	}
 out_free:
 	kfree(domain_device);
 
@@ -167,7 +176,7 @@ static void s390_iommu_detach_device(struct iommu_domain *domain,
 	}
 	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
 
-	if (found) {
+	if (found && (zdev->s390_domain == s390_domain)) {
 		zdev->s390_domain = NULL;
 		zpci_unregister_ioat(zdev, 0);
 		zpci_dma_init_device(zdev);