Merge tag 'iommu-updates-v4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "These changes include:

   - support for the ACPI IORT table on ARM systems and patches to make
     the ARM-SMMU driver make use of it

   - conversion of the Exynos IOMMU driver to device dependency links
     and implementation of runtime pm support based on that conversion

   - update the Mediatek IOMMU driver to use the new struct
     device->iommu_fwspec member

   - implementation of dma_map/unmap_resource in the generic ARM
     dma-iommu layer

   - a number of smaller fixes and improvements all over the place"

* tag 'iommu-updates-v4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (44 commits)
  ACPI/IORT: Make dma masks set-up IORT specific
  iommu/amd: Missing error code in amd_iommu_init_device()
  iommu/s390: Drop duplicate header pci.h
  ACPI/IORT: Introduce iort_iommu_configure
  ACPI/IORT: Add single mapping function
  ACPI/IORT: Replace rid map type with type mask
  iommu/arm-smmu: Add IORT configuration
  iommu/arm-smmu: Split probe functions into DT/generic portions
  iommu/arm-smmu-v3: Add IORT configuration
  iommu/arm-smmu-v3: Split probe functions into DT/generic portions
  ACPI/IORT: Add support for ARM SMMU platform devices creation
  ACPI/IORT: Add node match function
  ACPI: Implement acpi_dma_configure
  iommu/arm-smmu-v3: Convert struct device of_node to fwnode usage
  iommu/arm-smmu: Convert struct device of_node to fwnode usage
  iommu: Make of_iommu_set/get_ops() DT agnostic
  ACPI/IORT: Add support for IOMMU fwnode registration
  ACPI/IORT: Introduce linker section for IORT entries probing
  ACPI: Add FWNODE_ACPI_STATIC fwnode type
  iommu/arm-smmu: Set SMTNMB_TLBEN in ACR to enable caching of bypass entries
  ...

16 files changed, 524 insertions, 392 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 754595ee11b6..019e02707cd5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -373,6 +373,8 @@ static struct iommu_group *acpihid_device_group(struct device *dev)
 
 	if (!entry->group)
 		entry->group = generic_device_group(dev);
+	else
+		iommu_group_ref_get(entry->group);
 
 	return entry->group;
 }
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 157e93421fb8..971154cbbb03 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -28,6 +28,7 @@
 #include <linux/amd-iommu.h>
 #include <linux/export.h>
 #include <linux/iommu.h>
+#include <linux/kmemleak.h>
 #include <asm/pci-direct.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
@@ -2090,6 +2091,7 @@ static struct syscore_ops amd_iommu_syscore_ops = {
 
 static void __init free_on_init_error(void)
 {
+	kmemleak_free(irq_lookup_table);
 	free_pages((unsigned long)irq_lookup_table,
 		   get_order(rlookup_table_size));
 
@@ -2321,6 +2323,8 @@ static int __init early_amd_iommu_init(void)
 		irq_lookup_table = (void *)__get_free_pages(
 				GFP_KERNEL | __GFP_ZERO,
 				get_order(rlookup_table_size));
+		kmemleak_alloc(irq_lookup_table, rlookup_table_size,
+			       1, GFP_KERNEL);
 		if (!irq_lookup_table)
 			goto out;
 	}
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 594849a3a9be..f8ed8c95b685 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -805,8 +805,10 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 		goto out_free_domain;
 
 	group = iommu_group_get(&pdev->dev);
-	if (!group)
+	if (!group) {
+		ret = -EINVAL;
 		goto out_free_domain;
+	}
 
 	ret = iommu_attach_group(dev_state->domain, group);
 	if (ret != 0)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index e6f9b2d745ca..4d6ec444a9d6 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -20,6 +20,8 @@
  * This driver is powered by bad coffee and bombay mix.
  */
 
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/delay.h>
 #include <linux/dma-iommu.h>
 #include <linux/err.h>
@@ -1358,7 +1360,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
-static struct iommu_gather_ops arm_smmu_gather_ops = {
+static const struct iommu_gather_ops arm_smmu_gather_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync,
@@ -1723,13 +1725,14 @@ static struct platform_driver arm_smmu_driver;
 
 static int arm_smmu_match_node(struct device *dev, void *data)
 {
-	return dev->of_node == data;
+	return dev->fwnode == data;
 }
 
-static struct arm_smmu_device *arm_smmu_get_by_node(struct device_node *np)
+static
+struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
 {
 	struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL,
-						np, arm_smmu_match_node);
+						fwnode, arm_smmu_match_node);
 	put_device(dev);
 	return dev ? dev_get_drvdata(dev) : NULL;
 }
@@ -1765,7 +1768,7 @@ static int arm_smmu_add_device(struct device *dev)
 		master = fwspec->iommu_priv;
 		smmu = master->smmu;
 	} else {
-		smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 		if (!smmu)
 			return -ENODEV;
 		master = kzalloc(sizeof(*master), GFP_KERNEL);
@@ -2380,10 +2383,10 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	return 0;
 }
 
-static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
+static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
-	bool coherent;
+	bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
 
 	/* IDR0 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
@@ -2435,13 +2438,9 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 		smmu->features |= ARM_SMMU_FEAT_HYP;
 
 	/*
-	 * The dma-coherent property is used in preference to the ID
+	 * The coherency feature as set by FW is used in preference to the ID
 	 * register, but warn on mismatch.
 	 */
-	coherent = of_dma_is_coherent(smmu->dev->of_node);
-	if (coherent)
-		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
-
 	if (!!(reg & IDR0_COHACC) != coherent)
 		dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
 			 coherent ? "true" : "false");
@@ -2562,21 +2561,61 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 	return 0;
 }
 
-static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+#ifdef CONFIG_ACPI
+static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+				      struct arm_smmu_device *smmu)
+{
+	struct acpi_iort_smmu_v3 *iort_smmu;
+	struct device *dev = smmu->dev;
+	struct acpi_iort_node *node;
+
+	node = *(struct acpi_iort_node **)dev_get_platdata(dev);
+
+	/* Retrieve SMMUv3 specific data */
+	iort_smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+	if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
+		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+	return 0;
+}
+#else
+static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+					     struct arm_smmu_device *smmu)
+{
+	return -ENODEV;
+}
+#endif
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev,
+				    struct arm_smmu_device *smmu)
 {
-	int irq, ret;
-	struct resource *res;
-	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
-	bool bypass = true;
 	u32 cells;
+	int ret = -EINVAL;
 
 	if (of_property_read_u32(dev->of_node, "#iommu-cells", &cells))
 		dev_err(dev, "missing #iommu-cells property\n");
 	else if (cells != 1)
 		dev_err(dev, "invalid #iommu-cells value (%d)\n", cells);
 	else
-		bypass = false;
+		ret = 0;
+
+	parse_driver_options(smmu);
+
+	if (of_dma_is_coherent(dev->of_node))
+		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+	return ret;
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+	int irq, ret;
+	struct resource *res;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+	bool bypass;
 
 	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
 	if (!smmu) {
@@ -2613,10 +2652,19 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	if (irq > 0)
 		smmu->gerr_irq = irq;
 
-	parse_driver_options(smmu);
+	if (dev->of_node) {
+		ret = arm_smmu_device_dt_probe(pdev, smmu);
+	} else {
+		ret = arm_smmu_device_acpi_probe(pdev, smmu);
+		if (ret == -ENODEV)
+			return ret;
+	}
+
+	/* Set bypass mode according to firmware probing result */
+	bypass = !!ret;
 
 	/* Probe the h/w */
-	ret = arm_smmu_device_probe(smmu);
+	ret = arm_smmu_device_hw_probe(smmu);
 	if (ret)
 		return ret;
 
@@ -2634,7 +2682,8 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		return ret;
 
 	/* And we're up. Go go go! */
-	of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
+	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
+
 #ifdef CONFIG_PCI
 	if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
 		pci_request_acs();
@@ -2677,7 +2726,7 @@ static struct platform_driver arm_smmu_driver = {
 		.name		= "arm-smmu-v3",
 		.of_match_table	= of_match_ptr(arm_smmu_of_match),
 	},
-	.probe	= arm_smmu_device_dt_probe,
+	.probe	= arm_smmu_device_probe,
 	.remove	= arm_smmu_device_remove,
 };
 
@@ -2715,6 +2764,17 @@ static int __init arm_smmu_of_init(struct device_node *np)
 }
 IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", arm_smmu_of_init);
 
+#ifdef CONFIG_ACPI
+static int __init acpi_smmu_v3_init(struct acpi_table_header *table)
+{
+	if (iort_node_match(ACPI_IORT_NODE_SMMU_V3))
+		return arm_smmu_init();
+
+	return 0;
+}
+IORT_ACPI_DECLARE(arm_smmu_v3, ACPI_SIG_IORT, acpi_smmu_v3_init);
+#endif
+
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8f7281444551..a60cded8a6ed 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -28,6 +28,8 @@
 
 #define pr_fmt(fmt) "arm-smmu: " fmt
 
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/atomic.h>
 #include <linux/delay.h>
 #include <linux/dma-iommu.h>
@@ -247,6 +249,7 @@ enum arm_smmu_s2cr_privcfg {
 #define ARM_MMU500_ACTLR_CPRE		(1 << 1)
 
 #define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
+#define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
 
 #define CB_PAR_F			(1 << 0)
 
@@ -642,7 +645,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	}
 }
 
-static struct iommu_gather_ops arm_smmu_gather_ops = {
+static const struct iommu_gather_ops arm_smmu_gather_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync,
@@ -1379,13 +1382,14 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 
 static int arm_smmu_match_node(struct device *dev, void *data)
 {
-	return dev->of_node == data;
+	return dev->fwnode == data;
 }
 
-static struct arm_smmu_device *arm_smmu_get_by_node(struct device_node *np)
+static
+struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
 {
 	struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL,
-						np, arm_smmu_match_node);
+						fwnode, arm_smmu_match_node);
 	put_device(dev);
 	return dev ? dev_get_drvdata(dev) : NULL;
 }
@@ -1403,7 +1407,7 @@ static int arm_smmu_add_device(struct device *dev)
 		if (ret)
 			goto out_free;
 	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
-		smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
 		return -ENODEV;
 	}
@@ -1478,7 +1482,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	}
 
 	if (group)
-		return group;
+		return iommu_group_ref_get(group);
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1581,16 +1585,22 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	for (i = 0; i < smmu->num_mapping_groups; ++i)
 		arm_smmu_write_sme(smmu, i);
 
-	/*
-	 * Before clearing ARM_MMU500_ACTLR_CPRE, need to
-	 * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK
-	 * bit is only present in MMU-500r2 onwards.
-	 */
-	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7);
-	major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK;
-	if ((smmu->model == ARM_MMU500) && (major >= 2)) {
+	if (smmu->model == ARM_MMU500) {
+		/*
+		 * Before clearing ARM_MMU500_ACTLR_CPRE, need to
+		 * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK
+		 * bit is only present in MMU-500r2 onwards.
+		 */
+		reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7);
+		major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK;
 		reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sACR);
-		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+		if (major >= 2)
+			reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+		/*
+		 * Allow unmatched Stream IDs to allocate bypass
+		 * TLB entries for reduced latency.
+		 */
+		reg |= ARM_MMU500_ACR_SMTNMB_TLBEN;
 		writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR);
 	}
 
@@ -1667,7 +1677,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	unsigned long size;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 	u32 id;
-	bool cttw_dt, cttw_reg;
+	bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
 	int i;
 
 	dev_notice(smmu->dev, "probing hardware configuration...\n");
@@ -1712,20 +1722,17 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/*
 	 * In order for DMA API calls to work properly, we must defer to what
-	 * the DT says about coherency, regardless of what the hardware claims.
+	 * the FW says about coherency, regardless of what the hardware claims.
 	 * Fortunately, this also opens up a workaround for systems where the
 	 * ID register value has ended up configured incorrectly.
 	 */
-	cttw_dt = of_dma_is_coherent(smmu->dev->of_node);
 	cttw_reg = !!(id & ID0_CTTW);
-	if (cttw_dt)
-		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
-	if (cttw_dt || cttw_reg)
+	if (cttw_fw || cttw_reg)
 		dev_notice(smmu->dev, "\t%scoherent table walk\n",
-			   cttw_dt ? "" : "non-");
-	if (cttw_dt != cttw_reg)
+			   cttw_fw ? "" : "non-");
+	if (cttw_fw != cttw_reg)
 		dev_notice(smmu->dev,
-			   "\t(IDR0.CTTW overridden by dma-coherent property)\n");
+			   "\t(IDR0.CTTW overridden by FW configuration)\n");
 
 	/* Max. number of entries we have for stream matching/indexing */
 	size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
@@ -1906,15 +1913,83 @@ static const struct of_device_id arm_smmu_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
-static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+#ifdef CONFIG_ACPI
+static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
+{
+	int ret = 0;
+
+	switch (model) {
+	case ACPI_IORT_SMMU_V1:
+	case ACPI_IORT_SMMU_CORELINK_MMU400:
+		smmu->version = ARM_SMMU_V1;
+		smmu->model = GENERIC_SMMU;
+		break;
+	case ACPI_IORT_SMMU_V2:
+		smmu->version = ARM_SMMU_V2;
+		smmu->model = GENERIC_SMMU;
+		break;
+	case ACPI_IORT_SMMU_CORELINK_MMU500:
+		smmu->version = ARM_SMMU_V2;
+		smmu->model = ARM_MMU500;
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+	return ret;
+}
+
+static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+				      struct arm_smmu_device *smmu)
+{
+	struct device *dev = smmu->dev;
+	struct acpi_iort_node *node =
+		*(struct acpi_iort_node **)dev_get_platdata(dev);
+	struct acpi_iort_smmu *iort_smmu;
+	int ret;
+
+	/* Retrieve SMMU1/2 specific data */
+	iort_smmu = (struct acpi_iort_smmu *)node->node_data;
+
+	ret = acpi_smmu_get_data(iort_smmu->model, smmu);
+	if (ret < 0)
+		return ret;
+
+	/* Ignore the configuration access interrupt */
+	smmu->num_global_irqs = 1;
+
+	if (iort_smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK)
+		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+	return 0;
+}
+#else
+static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+					     struct arm_smmu_device *smmu)
+{
+	return -ENODEV;
+}
+#endif
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev,
+				    struct arm_smmu_device *smmu)
 {
 	const struct arm_smmu_match_data *data;
-	struct resource *res;
-	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
-	int num_irqs, i, err;
 	bool legacy_binding;
 
+	if (of_property_read_u32(dev->of_node, "#global-interrupts",
+				 &smmu->num_global_irqs)) {
+		dev_err(dev, "missing #global-interrupts property\n");
+		return -ENODEV;
+	}
+
+	data = of_device_get_match_data(dev);
+	smmu->version = data->version;
+	smmu->model = data->model;
+
+	parse_driver_options(smmu);
+
 	legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL);
 	if (legacy_binding && !using_generic_binding) {
 		if (!using_legacy_binding)
@@ -1927,6 +2002,19 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	if (of_dma_is_coherent(dev->of_node))
+		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+	return 0;
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+	int num_irqs, i, err;
+
 	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
 	if (!smmu) {
 		dev_err(dev, "failed to allocate arm_smmu_device\n");
@@ -1934,9 +2022,13 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	}
 	smmu->dev = dev;
 
-	data = of_device_get_match_data(dev);
-	smmu->version = data->version;
-	smmu->model = data->model;
+	if (dev->of_node)
+		err = arm_smmu_device_dt_probe(pdev, smmu);
+	else
+		err = arm_smmu_device_acpi_probe(pdev, smmu);
+
+	if (err)
+		return err;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	smmu->base = devm_ioremap_resource(dev, res);
@@ -1944,12 +2036,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		return PTR_ERR(smmu->base);
 	smmu->size = resource_size(res);
 
-	if (of_property_read_u32(dev->of_node, "#global-interrupts",
-				 &smmu->num_global_irqs)) {
-		dev_err(dev, "missing #global-interrupts property\n");
-		return -ENODEV;
-	}
-
 	num_irqs = 0;
 	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
 		num_irqs++;
@@ -1984,8 +2070,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	parse_driver_options(smmu);
-
 	if (smmu->version == ARM_SMMU_V2 &&
 	    smmu->num_context_banks != smmu->num_context_irqs) {
 		dev_err(dev,
@@ -2007,7 +2091,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		}
 	}
 
-	of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
+	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
 	platform_set_drvdata(pdev, smmu);
 	arm_smmu_device_reset(smmu);
 
@@ -2047,7 +2131,7 @@ static struct platform_driver arm_smmu_driver = {
 		.name		= "arm-smmu",
 		.of_match_table	= of_match_ptr(arm_smmu_of_match),
 	},
-	.probe	= arm_smmu_device_dt_probe,
+	.probe	= arm_smmu_device_probe,
 	.remove	= arm_smmu_device_remove,
 };
 
@@ -2090,6 +2174,17 @@ IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", arm_smmu_of_init);
 IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", arm_smmu_of_init);
 IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", arm_smmu_of_init);
 
+#ifdef CONFIG_ACPI
+static int __init arm_smmu_acpi_init(struct acpi_table_header *table)
+{
+	if (iort_node_match(ACPI_IORT_NODE_SMMU))
+		return arm_smmu_init();
+
+	return 0;
+}
+IORT_ACPI_DECLARE(arm_smmu, ACPI_SIG_IORT, arm_smmu_acpi_init);
+#endif
+
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c5ab8667e6f2..2db0d641cf45 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -432,13 +432,12 @@ int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
 	return ret;
 }
 
-dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, int prot)
+static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
+		size_t size, int prot)
 {
 	dma_addr_t dma_addr;
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iova_domain *iovad = cookie_iovad(domain);
-	phys_addr_t phys = page_to_phys(page) + offset;
 	size_t iova_off = iova_offset(iovad, phys);
 	size_t len = iova_align(iovad, size + iova_off);
 	struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev));
@@ -454,6 +453,12 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	return dma_addr + iova_off;
 }
 
+dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, int prot)
+{
+	return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot);
+}
+
 void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
@@ -624,6 +629,19 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), sg_dma_address(sg));
 }
 
+dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return __iommu_dma_map(dev, phys, size,
+			dma_direction_to_prot(dir, false) | IOMMU_MMIO);
+}
+
+void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
+}
+
 int iommu_dma_supported(struct device *dev, u64 mask)
 {
 	/*
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 30808e91b775..57ba0d3091ea 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -70,6 +70,36 @@ static short PG_ENT_SHIFT = -1;
 #define SYSMMU_PG_ENT_SHIFT 0
 #define SYSMMU_V5_PG_ENT_SHIFT 4
 
+static const sysmmu_pte_t *LV1_PROT;
+static const sysmmu_pte_t SYSMMU_LV1_PROT[] = {
+	((0 << 15) | (0 << 10)), /* no access */
+	((1 << 15) | (1 << 10)), /* IOMMU_READ only */
+	((0 << 15) | (1 << 10)), /* IOMMU_WRITE not supported, use read/write */
+	((0 << 15) | (1 << 10)), /* IOMMU_READ | IOMMU_WRITE */
+};
+static const sysmmu_pte_t SYSMMU_V5_LV1_PROT[] = {
+	(0 << 4), /* no access */
+	(1 << 4), /* IOMMU_READ only */
+	(2 << 4), /* IOMMU_WRITE only */
+	(3 << 4), /* IOMMU_READ | IOMMU_WRITE */
+};
+
+static const sysmmu_pte_t *LV2_PROT;
+static const sysmmu_pte_t SYSMMU_LV2_PROT[] = {
+	((0 << 9) | (0 << 4)), /* no access */
+	((1 << 9) | (1 << 4)), /* IOMMU_READ only */
+	((0 << 9) | (1 << 4)), /* IOMMU_WRITE not supported, use read/write */
+	((0 << 9) | (1 << 4)), /* IOMMU_READ | IOMMU_WRITE */
+};
+static const sysmmu_pte_t SYSMMU_V5_LV2_PROT[] = {
+	(0 << 2), /* no access */
+	(1 << 2), /* IOMMU_READ only */
+	(2 << 2), /* IOMMU_WRITE only */
+	(3 << 2), /* IOMMU_READ | IOMMU_WRITE */
+};
+
+#define SYSMMU_SUPPORTED_PROT_BITS (IOMMU_READ | IOMMU_WRITE)
+
 #define sect_to_phys(ent) (((phys_addr_t) ent) << PG_ENT_SHIFT)
 #define section_phys(sent) (sect_to_phys(*(sent)) & SECT_MASK)
 #define section_offs(iova) (iova & (SECT_SIZE - 1))
@@ -97,16 +127,17 @@ static u32 lv2ent_offset(sysmmu_iova_t iova)
 #define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE)
 #define lv2table_base(sent) (sect_to_phys(*(sent) & 0xFFFFFFC0))
 
-#define mk_lv1ent_sect(pa) ((pa >> PG_ENT_SHIFT) | 2)
+#define mk_lv1ent_sect(pa, prot) ((pa >> PG_ENT_SHIFT) | LV1_PROT[prot] | 2)
 #define mk_lv1ent_page(pa) ((pa >> PG_ENT_SHIFT) | 1)
-#define mk_lv2ent_lpage(pa) ((pa >> PG_ENT_SHIFT) | 1)
-#define mk_lv2ent_spage(pa) ((pa >> PG_ENT_SHIFT) | 2)
+#define mk_lv2ent_lpage(pa, prot) ((pa >> PG_ENT_SHIFT) | LV2_PROT[prot] | 1)
+#define mk_lv2ent_spage(pa, prot) ((pa >> PG_ENT_SHIFT) | LV2_PROT[prot] | 2)
 
 #define CTRL_ENABLE	0x5
 #define CTRL_BLOCK	0x7
 #define CTRL_DISABLE	0x0
 
 #define CFG_LRU		0x1
+#define CFG_EAP		(1 << 2)
 #define CFG_QOS(n)	((n & 0xF) << 7)
 #define CFG_ACGEN	(1 << 24) /* System MMU 3.3 only */
 #define CFG_SYSSEL	(1 << 22) /* System MMU 3.2 only */
@@ -206,6 +237,7 @@ static const struct sysmmu_fault_info sysmmu_v5_faults[] = {
 struct exynos_iommu_owner {
 	struct list_head controllers;	/* list of sysmmu_drvdata.owner_node */
 	struct iommu_domain *domain;	/* domain this device is attached */
+	struct mutex rpm_lock;		/* for runtime pm of all sysmmus */
 };
 
 /*
@@ -237,8 +269,8 @@ struct sysmmu_drvdata {
 	struct clk *aclk;		/* SYSMMU's aclk clock */
 	struct clk *pclk;		/* SYSMMU's pclk clock */
 	struct clk *clk_master;		/* master's device clock */
-	int activations;		/* number of calls to sysmmu_enable */
 	spinlock_t lock;		/* lock for modyfying state */
+	bool active;			/* current status */
 	struct exynos_iommu_domain *domain; /* domain we belong to */
 	struct list_head domain_node;	/* node for domain clients list */
 	struct list_head owner_node;	/* node for owner controllers list */
@@ -251,25 +283,6 @@ static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
 	return container_of(dom, struct exynos_iommu_domain, domain);
 }
 
-static bool set_sysmmu_active(struct sysmmu_drvdata *data)
-{
-	/* return true if the System MMU was not active previously
-	   and it needs to be initialized */
-	return ++data->activations == 1;
-}
-
-static bool set_sysmmu_inactive(struct sysmmu_drvdata *data)
-{
-	/* return true if the System MMU is needed to be disabled */
-	BUG_ON(data->activations < 1);
-	return --data->activations == 0;
-}
-
-static bool is_sysmmu_active(struct sysmmu_drvdata *data)
-{
-	return data->activations > 0;
-}
-
 static void sysmmu_unblock(struct sysmmu_drvdata *data)
 {
 	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
@@ -388,7 +401,7 @@ static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 	unsigned short reg_status, reg_clear;
 	int ret = -ENOSYS;
 
-	WARN_ON(!is_sysmmu_active(data));
+	WARN_ON(!data->active);
 
 	if (MMU_MAJ_VER(data->version) < 5) {
 		reg_status = REG_INT_STATUS;
@@ -434,40 +447,19 @@ static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void __sysmmu_disable_nocount(struct sysmmu_drvdata *data)
+static void __sysmmu_disable(struct sysmmu_drvdata *data)
 {
+	unsigned long flags;
+
 	clk_enable(data->clk_master);
 
+	spin_lock_irqsave(&data->lock, flags);
 	writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);
 	writel(0, data->sfrbase + REG_MMU_CFG);
-
-	__sysmmu_disable_clocks(data);
-}
-
-static bool __sysmmu_disable(struct sysmmu_drvdata *data)
-{
-	bool disabled;
-	unsigned long flags;
-
-	spin_lock_irqsave(&data->lock, flags);
-
-	disabled = set_sysmmu_inactive(data);
-
-	if (disabled) {
-		data->pgtable = 0;
-		data->domain = NULL;
-
-		__sysmmu_disable_nocount(data);
-
-		dev_dbg(data->sysmmu, "Disabled\n");
-	} else  {
-		dev_dbg(data->sysmmu, "%d times left to disable\n",
-					data->activations);
-	}
-
+	data->active = false;
 	spin_unlock_irqrestore(&data->lock, flags);
 
-	return disabled;
+	__sysmmu_disable_clocks(data);
 }
 
 static void __sysmmu_init_config(struct sysmmu_drvdata *data)
@@ -481,20 +473,24 @@ static void __sysmmu_init_config(struct sysmmu_drvdata *data)
 	else
 		cfg = CFG_QOS(15) | CFG_FLPDCACHE | CFG_ACGEN;
 
+	cfg |= CFG_EAP; /* enable access protection bits check */
+
 	writel(cfg, data->sfrbase + REG_MMU_CFG);
 }
 
-static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
+static void __sysmmu_enable(struct sysmmu_drvdata *data)
 {
+	unsigned long flags;
+
 	__sysmmu_enable_clocks(data);
 
+	spin_lock_irqsave(&data->lock, flags);
 	writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
-
 	__sysmmu_init_config(data);
-
 	__sysmmu_set_ptbase(data, data->pgtable);
-
 	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
+	data->active = true;
+	spin_unlock_irqrestore(&data->lock, flags);
 
 	/*
 	 * SYSMMU driver keeps master's clock enabled only for the short
@@ -505,48 +501,18 @@ static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
 	clk_disable(data->clk_master);
 }
 
-static int __sysmmu_enable(struct sysmmu_drvdata *data, phys_addr_t pgtable,
-			   struct exynos_iommu_domain *domain)
-{
-	int ret = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&data->lock, flags);
-	if (set_sysmmu_active(data)) {
-		data->pgtable = pgtable;
-		data->domain = domain;
-
-		__sysmmu_enable_nocount(data);
-
-		dev_dbg(data->sysmmu, "Enabled\n");
-	} else {
-		ret = (pgtable == data->pgtable) ? 1 : -EBUSY;
-
-		dev_dbg(data->sysmmu, "already enabled\n");
-	}
-
-	if (WARN_ON(ret < 0))
-		set_sysmmu_inactive(data); /* decrement count */
-
-	spin_unlock_irqrestore(&data->lock, flags);
-
-	return ret;
-}
-
 static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
 					    sysmmu_iova_t iova)
 {
 	unsigned long flags;
 
-
 	spin_lock_irqsave(&data->lock, flags);
-	if (is_sysmmu_active(data) && data->version >= MAKE_MMU_VER(3, 3)) {
+	if (data->active && data->version >= MAKE_MMU_VER(3, 3)) {
 		clk_enable(data->clk_master);
 		__sysmmu_tlb_invalidate_entry(data, iova, 1);
 		clk_disable(data->clk_master);
 	}
 	spin_unlock_irqrestore(&data->lock, flags);
-
 }
 
 static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
@@ -555,7 +521,7 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
 	unsigned long flags;
 
 	spin_lock_irqsave(&data->lock, flags);
-	if (is_sysmmu_active(data)) {
+	if (data->active) {
 		unsigned int num_inv = 1;
 
 		clk_enable(data->clk_master);
@@ -578,9 +544,6 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
 			sysmmu_unblock(data);
 		}
 		clk_disable(data->clk_master);
-	} else {
-		dev_dbg(data->master,
-			"disabled. Skipping TLB invalidation @ %#x\n", iova);
 	}
 	spin_unlock_irqrestore(&data->lock, flags);
 }
@@ -652,10 +615,15 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 
 	__sysmmu_get_version(data);
 	if (PG_ENT_SHIFT < 0) {
-		if (MMU_MAJ_VER(data->version) < 5)
+		if (MMU_MAJ_VER(data->version) < 5) {
 			PG_ENT_SHIFT = SYSMMU_PG_ENT_SHIFT;
-		else
+			LV1_PROT = SYSMMU_LV1_PROT;
+			LV2_PROT = SYSMMU_LV2_PROT;
+		} else {
 			PG_ENT_SHIFT = SYSMMU_V5_PG_ENT_SHIFT;
+			LV1_PROT = SYSMMU_V5_LV1_PROT;
+			LV2_PROT = SYSMMU_V5_LV2_PROT;
+		}
 	}
 
 	pm_runtime_enable(dev);
@@ -665,34 +633,46 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int exynos_sysmmu_suspend(struct device *dev)
+static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
 {
 	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+	struct device *master = data->master;
+
+	if (master) {
+		struct exynos_iommu_owner *owner = master->archdata.iommu;
 
-	dev_dbg(dev, "suspend\n");
-	if (is_sysmmu_active(data)) {
-		__sysmmu_disable_nocount(data);
-		pm_runtime_put(dev);
+		mutex_lock(&owner->rpm_lock);
+		if (data->domain) {
+			dev_dbg(data->sysmmu, "saving state\n");
+			__sysmmu_disable(data);
+		}
+		mutex_unlock(&owner->rpm_lock);
 	}
 	return 0;
 }
 
-static int exynos_sysmmu_resume(struct device *dev)
+static int __maybe_unused exynos_sysmmu_resume(struct device *dev)
 {
 	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+	struct device *master = data->master;
+
+	if (master) {
+		struct exynos_iommu_owner *owner = master->archdata.iommu;
 
-	dev_dbg(dev, "resume\n");
-	if (is_sysmmu_active(data)) {
-		pm_runtime_get_sync(dev);
-		__sysmmu_enable_nocount(data);
+		mutex_lock(&owner->rpm_lock);
+		if (data->domain) {
+			dev_dbg(data->sysmmu, "restoring state\n");
+			__sysmmu_enable(data);
+		}
+		mutex_unlock(&owner->rpm_lock);
 	}
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops sysmmu_pm_ops = {
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(exynos_sysmmu_suspend, exynos_sysmmu_resume)
+	SET_RUNTIME_PM_OPS(exynos_sysmmu_suspend, exynos_sysmmu_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static const struct of_device_id sysmmu_of_match[] __initconst = {
@@ -796,9 +776,12 @@ static void exynos_iommu_domain_free(struct iommu_domain *iommu_domain)
 	spin_lock_irqsave(&domain->lock, flags);
 
 	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
-		if (__sysmmu_disable(data))
-			data->master = NULL;
+		spin_lock(&data->lock);
+		__sysmmu_disable(data);
+		data->pgtable = 0;
+		data->domain = NULL;
 		list_del_init(&data->domain_node);
+		spin_unlock(&data->lock);
 	}
 
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -832,31 +815,34 @@ static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain,
 	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
 	struct sysmmu_drvdata *data, *next;
 	unsigned long flags;
-	bool found = false;
 
 	if (!has_sysmmu(dev) || owner->domain != iommu_domain)
 		return;
 
+	mutex_lock(&owner->rpm_lock);
+
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		pm_runtime_get_noresume(data->sysmmu);
+		if (pm_runtime_active(data->sysmmu))
+			__sysmmu_disable(data);
+		pm_runtime_put(data->sysmmu);
+	}
+
 	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
-		if (data->master == dev) {
-			if (__sysmmu_disable(data)) {
-				data->master = NULL;
-				list_del_init(&data->domain_node);
-			}
-			pm_runtime_put(data->sysmmu);
-			found = true;
-		}
+		spin_lock(&data->lock);
+		data->pgtable = 0;
+		data->domain = NULL;
+		list_del_init(&data->domain_node);
+		spin_unlock(&data->lock);
 	}
+	owner->domain = NULL;
 	spin_unlock_irqrestore(&domain->lock, flags);
 
-	owner->domain = NULL;
+	mutex_unlock(&owner->rpm_lock);
 
-	if (found)
-		dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
-					__func__, &pagetable);
-	else
-		dev_err(dev, "%s: No IOMMU is attached\n", __func__);
+	dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n", __func__,
+		&pagetable);
 }
 
 static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
@@ -867,7 +853,6 @@ static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
 	struct sysmmu_drvdata *data;
 	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
 	unsigned long flags;
-	int ret = -ENODEV;
 
 	if (!has_sysmmu(dev))
 		return -ENODEV;
@@ -875,29 +860,32 @@ static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
 	if (owner->domain)
 		exynos_iommu_detach_device(owner->domain, dev);
 
+	mutex_lock(&owner->rpm_lock);
+
+	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(data, &owner->controllers, owner_node) {
-		pm_runtime_get_sync(data->sysmmu);
-		ret = __sysmmu_enable(data, pagetable, domain);
-		if (ret >= 0) {
-			data->master = dev;
-
-			spin_lock_irqsave(&domain->lock, flags);
-			list_add_tail(&data->domain_node, &domain->clients);
-			spin_unlock_irqrestore(&domain->lock, flags);
-		}
+		spin_lock(&data->lock);
+		data->pgtable = pagetable;
+		data->domain = domain;
+		list_add_tail(&data->domain_node, &domain->clients);
+		spin_unlock(&data->lock);
 	}
+	owner->domain = iommu_domain;
+	spin_unlock_irqrestore(&domain->lock, flags);
 
-	if (ret < 0) {
-		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
-					__func__, &pagetable);
-		return ret;
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		pm_runtime_get_noresume(data->sysmmu);
+		if (pm_runtime_active(data->sysmmu))
+			__sysmmu_enable(data);
+		pm_runtime_put(data->sysmmu);
 	}
 
-	owner->domain = iommu_domain;
-	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa %s\n",
-		__func__, &pagetable, (ret == 0) ? "" : ", again");
+	mutex_unlock(&owner->rpm_lock);
 
-	return ret;
+	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa\n", __func__,
+		&pagetable);
+
+	return 0;
 }
 
 static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
@@ -954,7 +942,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 
 static int lv1set_section(struct exynos_iommu_domain *domain,
 			  sysmmu_pte_t *sent, sysmmu_iova_t iova,
-			  phys_addr_t paddr, short *pgcnt)
+			  phys_addr_t paddr, int prot, short *pgcnt)
 {
 	if (lv1ent_section(sent)) {
 		WARN(1, "Trying mapping on 1MiB@%#08x that is mapped",
@@ -973,7 +961,7 @@ static int lv1set_section(struct exynos_iommu_domain *domain,
 		*pgcnt = 0;
 	}
 
-	update_pte(sent, mk_lv1ent_sect(paddr));
+	update_pte(sent, mk_lv1ent_sect(paddr, prot));
 
 	spin_lock(&domain->lock);
 	if (lv1ent_page_zero(sent)) {
@@ -991,13 +979,13 @@ static int lv1set_section(struct exynos_iommu_domain *domain,
 }
 
 static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
-								short *pgcnt)
+		       int prot, short *pgcnt)
 {
 	if (size == SPAGE_SIZE) {
 		if (WARN_ON(!lv2ent_fault(pent)))
 			return -EADDRINUSE;
 
-		update_pte(pent, mk_lv2ent_spage(paddr));
+		update_pte(pent, mk_lv2ent_spage(paddr, prot));
 		*pgcnt -= 1;
 	} else { /* size == LPAGE_SIZE */
 		int i;
@@ -1013,7 +1001,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
 				return -EADDRINUSE;
 			}
 
-			*pent = mk_lv2ent_lpage(paddr);
+			*pent = mk_lv2ent_lpage(paddr, prot);
 		}
 		dma_sync_single_for_device(dma_dev, pent_base,
 					   sizeof(*pent) * SPAGES_PER_LPAGE,
@@ -1061,13 +1049,14 @@ static int exynos_iommu_map(struct iommu_domain *iommu_domain,
 	int ret = -ENOMEM;
 
 	BUG_ON(domain->pgtable == NULL);
+	prot &= SYSMMU_SUPPORTED_PROT_BITS;
 
 	spin_lock_irqsave(&domain->pgtablelock, flags);
 
 	entry = section_entry(domain->pgtable, iova);
 
 	if (size == SECT_SIZE) {
-		ret = lv1set_section(domain, entry, iova, paddr,
+		ret = lv1set_section(domain, entry, iova, paddr, prot,
 				     &domain->lv2entcnt[lv1ent_offset(iova)]);
 	} else {
 		sysmmu_pte_t *pent;
@@ -1078,7 +1067,7 @@ static int exynos_iommu_map(struct iommu_domain *iommu_domain,
 		if (IS_ERR(pent))
 			ret = PTR_ERR(pent);
 		else
-			ret = lv2set_page(pent, paddr, size,
+			ret = lv2set_page(pent, paddr, size, prot,
 				       &domain->lv2entcnt[lv1ent_offset(iova)]);
 	}
 
@@ -1268,10 +1257,20 @@ static int exynos_iommu_of_xlate(struct device *dev,
 			return -ENOMEM;
 
 		INIT_LIST_HEAD(&owner->controllers);
+		mutex_init(&owner->rpm_lock);
 		dev->archdata.iommu = owner;
 	}
 
 	list_add_tail(&data->owner_node, &owner->controllers);
+	data->master = dev;
+
+	/*
+	 * SYSMMU will be runtime activated via device link (dependency) to its
+	 * master device, so there are no direct calls to pm_runtime_get/put
+	 * in this driver.
+	 */
+	device_link_add(dev, data->sysmmu, DL_FLAG_PM_RUNTIME);
+
 	return 0;
 }
 
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index f50e51c1a9c8..0769276c0537 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -793,8 +793,7 @@ static int __init arm_v7s_do_selftests(void)
 	 * Distinct mappings of different granule sizes.
 	 */
 	iova = 0;
-	i = find_first_bit(&cfg.pgsize_bitmap, BITS_PER_LONG);
-	while (i != BITS_PER_LONG) {
+	for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
 		size = 1UL << i;
 		if (ops->map(ops, iova, iova, size, IOMMU_READ |
 						    IOMMU_WRITE |
@@ -811,8 +810,6 @@ static int __init arm_v7s_do_selftests(void)
 			return __FAIL(ops);
 
 		iova += SZ_16M;
-		i++;
-		i = find_next_bit(&cfg.pgsize_bitmap, BITS_PER_LONG, i);
 		loopnr++;
 	}
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index f5c90e1366ce..a40ce3406fef 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -916,7 +916,7 @@ static void dummy_tlb_sync(void *cookie)
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static struct iommu_gather_ops dummy_tlb_ops __initdata = {
+static const struct iommu_gather_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_add_flush	= dummy_tlb_add_flush,
 	.tlb_sync	= dummy_tlb_sync,
@@ -980,8 +980,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 		 * Distinct mappings of different granule sizes.
 		 */
 		iova = 0;
-		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
-		while (j != BITS_PER_LONG) {
+		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
 			size = 1UL << j;
 
 			if (ops->map(ops, iova, iova, size, IOMMU_READ |
@@ -999,8 +998,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 				return __FAIL(ops, i);
 
 			iova += SZ_1G;
-			j++;
-			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
 		}
 
 		/* Partial unmap */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 9a2f1960873b..dbe7f653bb7c 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -552,6 +552,19 @@ struct iommu_group *iommu_group_get(struct device *dev)
 EXPORT_SYMBOL_GPL(iommu_group_get);
 
 /**
+ * iommu_group_ref_get - Increment reference on a group
+ * @group: the group to use, must not be NULL
+ *
+ * This function is called by iommu drivers to take additional references on an
+ * existing group.  Returns the given group for convenience.
+ */
+struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
+{
+	kobject_get(group->devices_kobj);
+	return group;
+}
+
+/**
  * iommu_group_put - Decrement group reference
  * @group: the group to use
  *
@@ -1615,6 +1628,46 @@ out:
 	return ret;
 }
 
+struct iommu_instance {
+	struct list_head list;
+	struct fwnode_handle *fwnode;
+	const struct iommu_ops *ops;
+};
+static LIST_HEAD(iommu_instance_list);
+static DEFINE_SPINLOCK(iommu_instance_lock);
+
+void iommu_register_instance(struct fwnode_handle *fwnode,
+			     const struct iommu_ops *ops)
+{
+	struct iommu_instance *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+
+	if (WARN_ON(!iommu))
+		return;
+
+	of_node_get(to_of_node(fwnode));
+	INIT_LIST_HEAD(&iommu->list);
+	iommu->fwnode = fwnode;
+	iommu->ops = ops;
+	spin_lock(&iommu_instance_lock);
+	list_add_tail(&iommu->list, &iommu_instance_list);
+	spin_unlock(&iommu_instance_lock);
+}
+
+const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
+{
+	struct iommu_instance *instance;
+	const struct iommu_ops *ops = NULL;
+
+	spin_lock(&iommu_instance_lock);
+	list_for_each_entry(instance, &iommu_instance_list, list)
+		if (instance->fwnode == fwnode) {
+			ops = instance->ops;
+			break;
+		}
+	spin_unlock(&iommu_instance_lock);
+	return ops;
+}
+
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops)
 {
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index e23001bfcfee..080beca0197d 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(init_iova_domain);
 static struct rb_node *
 __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
 {
-	if ((*limit_pfn != iovad->dma_32bit_pfn) ||
+	if ((*limit_pfn > iovad->dma_32bit_pfn) ||
 		(iovad->cached32_node == NULL))
 		return rb_last(&iovad->rbroot);
 	else {
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b12c12d74c33..1479c76ece9e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -195,14 +195,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 static void mtk_iommu_config(struct mtk_iommu_data *data,
 			     struct device *dev, bool enable)
 {
-	struct mtk_iommu_client_priv *head, *cur, *next;
 	struct mtk_smi_larb_iommu    *larb_mmu;
 	unsigned int                 larbid, portid;
+	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+	int i;
 
-	head = dev->archdata.iommu;
-	list_for_each_entry_safe(cur, next, &head->client, client) {
-		larbid = MTK_M4U_TO_LARB(cur->mtk_m4u_id);
-		portid = MTK_M4U_TO_PORT(cur->mtk_m4u_id);
+	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->smi_imu.larb_imu[larbid];
 
 		dev_dbg(dev, "%s iommu port: %d\n",
@@ -282,14 +282,12 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 	int ret;
 
-	if (!priv)
+	if (!data)
 		return -ENODEV;
 
-	data = dev_get_drvdata(priv->m4udev);
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
 		ret = mtk_iommu_domain_finalise(data);
@@ -310,13 +308,11 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 static void mtk_iommu_detach_device(struct iommu_domain *domain,
 				    struct device *dev)
 {
-	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 
-	if (!priv)
+	if (!data)
 		return;
 
-	data = dev_get_drvdata(priv->m4udev);
 	mtk_iommu_config(data, dev, false);
 }
 
@@ -366,8 +362,8 @@ static int mtk_iommu_add_device(struct device *dev)
 {
 	struct iommu_group *group;
 
-	if (!dev->archdata.iommu) /* Not a iommu client device */
-		return -ENODEV;
+	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
+		return -ENODEV; /* Not a iommu client device */
 
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
@@ -379,44 +375,33 @@ static int mtk_iommu_add_device(struct device *dev)
 
 static void mtk_iommu_remove_device(struct device *dev)
 {
-	struct mtk_iommu_client_priv *head, *cur, *next;
-
-	head = dev->archdata.iommu;
-	if (!head)
+	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return;
 
-	list_for_each_entry_safe(cur, next, &head->client, client) {
-		list_del(&cur->client);
-		kfree(cur);
-	}
-	kfree(head);
-	dev->archdata.iommu = NULL;
-
 	iommu_group_remove_device(dev);
+	iommu_fwspec_free(dev);
 }
 
 static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 {
-	struct mtk_iommu_data *data;
-	struct mtk_iommu_client_priv *priv;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 
-	priv = dev->archdata.iommu;
-	if (!priv)
+	if (!data)
 		return ERR_PTR(-ENODEV);
 
 	/* All the client devices are in the same m4u iommu-group */
-	data = dev_get_drvdata(priv->m4udev);
 	if (!data->m4u_group) {
 		data->m4u_group = iommu_group_alloc();
 		if (IS_ERR(data->m4u_group))
 			dev_err(dev, "Failed to allocate M4U IOMMU group\n");
+	} else {
+		iommu_group_ref_get(data->m4u_group);
 	}
 	return data->m4u_group;
 }
 
 static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 {
-	struct mtk_iommu_client_priv *head, *priv, *next;
 	struct platform_device *m4updev;
 
 	if (args->args_count != 1) {
@@ -425,38 +410,16 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 		return -EINVAL;
 	}
 
-	if (!dev->archdata.iommu) {
+	if (!dev->iommu_fwspec->iommu_priv) {
 		/* Get the m4u device */
 		m4updev = of_find_device_by_node(args->np);
 		if (WARN_ON(!m4updev))
 			return -EINVAL;
 
-		head = kzalloc(sizeof(*head), GFP_KERNEL);
-		if (!head)
-			return -ENOMEM;
-
-		dev->archdata.iommu = head;
-		INIT_LIST_HEAD(&head->client);
-		head->m4udev = &m4updev->dev;
-	} else {
-		head = dev->archdata.iommu;
+		dev->iommu_fwspec->iommu_priv = platform_get_drvdata(m4updev);
 	}
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		goto err_free_mem;
-
-	priv->mtk_m4u_id = args->args[0];
-	list_add_tail(&priv->client, &head->client);
-
-	return 0;
-
-err_free_mem:
-	list_for_each_entry_safe(priv, next, &head->client, client)
-		kfree(priv);
-	kfree(head);
-	dev->archdata.iommu = NULL;
-	return -ENOMEM;
+	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
 static struct iommu_ops mtk_iommu_ops = {
@@ -583,17 +546,19 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 			continue;
 
 		plarbdev = of_find_device_by_node(larbnode);
-		of_node_put(larbnode);
 		if (!plarbdev) {
 			plarbdev = of_platform_device_create(
 						larbnode, NULL,
 						platform_bus_type.dev_root);
-			if (!plarbdev)
+			if (!plarbdev) {
+				of_node_put(larbnode);
 				return -EPROBE_DEFER;
+			}
 		}
 		data->smi_imu.larb_imu[i].dev = &plarbdev->dev;
 
-		component_match_add(dev, &match, compare_of, larbnode);
+		component_match_add_release(dev, &match, release_of,
+					    compare_of, larbnode);
 	}
 
 	platform_set_drvdata(pdev, data);
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 3dab13b4a211..50177f738e4e 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -34,12 +34,6 @@ struct mtk_iommu_suspend_reg {
 	u32				int_main_control;
 };
 
-struct mtk_iommu_client_priv {
-	struct list_head		client;
-	unsigned int			mtk_m4u_id;
-	struct device			*m4udev;
-};
-
 struct mtk_iommu_domain;
 
 struct mtk_iommu_data {
@@ -60,6 +54,11 @@ static inline int compare_of(struct device *dev, void *data)
 	return dev->of_node == data;
 }
 
+static inline void release_of(struct device *dev, void *data)
+{
+	of_node_put(data);
+}
+
 static inline int mtk_iommu_bind(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index b8aeb0768483..19e010083408 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -204,14 +204,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
 static void mtk_iommu_config(struct mtk_iommu_data *data,
 			     struct device *dev, bool enable)
 {
-	struct mtk_iommu_client_priv *head, *cur, *next;
 	struct mtk_smi_larb_iommu    *larb_mmu;
 	unsigned int                 larbid, portid;
+	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+	int i;
 
-	head = dev->archdata.iommu;
-	list_for_each_entry_safe(cur, next, &head->client, client) {
-		larbid = mt2701_m4u_to_larb(cur->mtk_m4u_id);
-		portid = mt2701_m4u_to_port(cur->mtk_m4u_id);
+	for (i = 0; i < fwspec->num_ids; ++i) {
+		larbid = mt2701_m4u_to_larb(fwspec->ids[i]);
+		portid = mt2701_m4u_to_port(fwspec->ids[i]);
 		larb_mmu = &data->smi_imu.larb_imu[larbid];
 
 		dev_dbg(dev, "%s iommu port: %d\n",
@@ -271,14 +271,12 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 	int ret;
 
-	if (!priv)
+	if (!data)
 		return -ENODEV;
 
-	data = dev_get_drvdata(priv->m4udev);
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
 		ret = mtk_iommu_domain_finalise(data);
@@ -295,13 +293,11 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 static void mtk_iommu_detach_device(struct iommu_domain *domain,
 				    struct device *dev)
 {
-	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 
-	if (!priv)
+	if (!data)
 		return;
 
-	data = dev_get_drvdata(priv->m4udev);
 	mtk_iommu_config(data, dev, false);
 }
 
@@ -366,6 +362,8 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pa;
 }
 
+static struct iommu_ops mtk_iommu_ops;
+
 /*
  * MTK generation one iommu HW only support one iommu domain, and all the client
  * sharing the same iova address space.
@@ -373,7 +371,7 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 static int mtk_iommu_create_mapping(struct device *dev,
 				    struct of_phandle_args *args)
 {
-	struct mtk_iommu_client_priv *head, *priv, *next;
+	struct mtk_iommu_data *data;
 	struct platform_device *m4updev;
 	struct dma_iommu_mapping *mtk_mapping;
 	struct device *m4udev;
@@ -385,41 +383,37 @@ static int mtk_iommu_create_mapping(struct device *dev,
 		return -EINVAL;
 	}
 
-	if (!dev->archdata.iommu) {
+	if (!dev->iommu_fwspec) {
+		ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_ops);
+		if (ret)
+			return ret;
+	} else if (dev->iommu_fwspec->ops != &mtk_iommu_ops) {
+		return -EINVAL;
+	}
+
+	if (!dev->iommu_fwspec->iommu_priv) {
 		/* Get the m4u device */
 		m4updev = of_find_device_by_node(args->np);
 		if (WARN_ON(!m4updev))
 			return -EINVAL;
 
-		head = kzalloc(sizeof(*head), GFP_KERNEL);
-		if (!head)
-			return -ENOMEM;
-
-		dev->archdata.iommu = head;
-		INIT_LIST_HEAD(&head->client);
-		head->m4udev = &m4updev->dev;
-	} else {
-		head = dev->archdata.iommu;
+		dev->iommu_fwspec->iommu_priv = platform_get_drvdata(m4updev);
 	}
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto err_free_mem;
-	}
-	priv->mtk_m4u_id = args->args[0];
-	list_add_tail(&priv->client, &head->client);
+	ret = iommu_fwspec_add_ids(dev, args->args, 1);
+	if (ret)
+		return ret;
 
-	m4udev = head->m4udev;
+	data = dev->iommu_fwspec->iommu_priv;
+	m4udev = data->dev;
 	mtk_mapping = m4udev->archdata.iommu;
 	if (!mtk_mapping) {
 		/* MTK iommu support 4GB iova address space. */
 		mtk_mapping = arm_iommu_create_mapping(&platform_bus_type,
 						0, 1ULL << 32);
-		if (IS_ERR(mtk_mapping)) {
-			ret = PTR_ERR(mtk_mapping);
-			goto err_free_mem;
-		}
+		if (IS_ERR(mtk_mapping))
+			return PTR_ERR(mtk_mapping);
+
 		m4udev->archdata.iommu = mtk_mapping;
 	}
 
@@ -432,11 +426,6 @@ static int mtk_iommu_create_mapping(struct device *dev,
 err_release_mapping:
 	arm_iommu_release_mapping(mtk_mapping);
 	m4udev->archdata.iommu = NULL;
-err_free_mem:
-	list_for_each_entry_safe(priv, next, &head->client, client)
-		kfree(priv);
-	kfree(head);
-	dev->archdata.iommu = NULL;
 	return ret;
 }
 
@@ -458,8 +447,8 @@ static int mtk_iommu_add_device(struct device *dev)
 		of_node_put(iommu_spec.np);
 	}
 
-	if (!dev->archdata.iommu) /* Not a iommu client device */
-		return -ENODEV;
+	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
+		return -ENODEV; /* Not a iommu client device */
 
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
@@ -471,37 +460,27 @@ static int mtk_iommu_add_device(struct device *dev)
 
 static void mtk_iommu_remove_device(struct device *dev)
 {
-	struct mtk_iommu_client_priv *head, *cur, *next;
-
-	head = dev->archdata.iommu;
-	if (!head)
+	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return;
 
-	list_for_each_entry_safe(cur, next, &head->client, client) {
-		list_del(&cur->client);
-		kfree(cur);
-	}
-	kfree(head);
-	dev->archdata.iommu = NULL;
-
 	iommu_group_remove_device(dev);
+	iommu_fwspec_free(dev);
 }
 
 static struct iommu_group *mtk_iommu_device_group(struct device *dev)
 {
-	struct mtk_iommu_data *data;
-	struct mtk_iommu_client_priv *priv;
+	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
 
-	priv = dev->archdata.iommu;
-	if (!priv)
+	if (!data)
 		return ERR_PTR(-ENODEV);
 
 	/* All the client devices are in the same m4u iommu-group */
-	data = dev_get_drvdata(priv->m4udev);
 	if (!data->m4u_group) {
 		data->m4u_group = iommu_group_alloc();
 		if (IS_ERR(data->m4u_group))
 			dev_err(dev, "Failed to allocate M4U IOMMU group\n");
+	} else {
+		iommu_group_ref_get(data->m4u_group);
 	}
 	return data->m4u_group;
 }
@@ -624,17 +603,19 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 			continue;
 
 		plarbdev = of_find_device_by_node(larb_spec.np);
-		of_node_put(larb_spec.np);
 		if (!plarbdev) {
 			plarbdev = of_platform_device_create(
 						larb_spec.np, NULL,
 						platform_bus_type.dev_root);
-			if (!plarbdev)
+			if (!plarbdev) {
+				of_node_put(larb_spec.np);
 				return -EPROBE_DEFER;
+			}
 		}
 
 		data->smi_imu.larb_imu[larb_nr].dev = &plarbdev->dev;
-		component_match_add(dev, &match, compare_of, larb_spec.np);
+		component_match_add_release(dev, &match, release_of,
+					    compare_of, larb_spec.np);
 		larb_nr++;
 	}
 
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 5b82862f571f..0f57ddc4ecc2 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -96,45 +96,6 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
 }
 EXPORT_SYMBOL_GPL(of_get_dma_window);
 
-struct of_iommu_node {
-	struct list_head list;
-	struct device_node *np;
-	const struct iommu_ops *ops;
-};
-static LIST_HEAD(of_iommu_list);
-static DEFINE_SPINLOCK(of_iommu_lock);
-
-void of_iommu_set_ops(struct device_node *np, const struct iommu_ops *ops)
-{
-	struct of_iommu_node *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
-
-	if (WARN_ON(!iommu))
-		return;
-
-	of_node_get(np);
-	INIT_LIST_HEAD(&iommu->list);
-	iommu->np = np;
-	iommu->ops = ops;
-	spin_lock(&of_iommu_lock);
-	list_add_tail(&iommu->list, &of_iommu_list);
-	spin_unlock(&of_iommu_lock);
-}
-
-const struct iommu_ops *of_iommu_get_ops(struct device_node *np)
-{
-	struct of_iommu_node *node;
-	const struct iommu_ops *ops = NULL;
-
-	spin_lock(&of_iommu_lock);
-	list_for_each_entry(node, &of_iommu_list, list)
-		if (node->np == np) {
-			ops = node->ops;
-			break;
-		}
-	spin_unlock(&of_iommu_lock);
-	return ops;
-}
-
 static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
 {
 	struct of_phandle_args *iommu_spec = data;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 3b44b1d82f3b..179e636a4d91 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -8,7 +8,6 @@
 #include <linux/pci.h>
 #include <linux/iommu.h>
 #include <linux/iommu-helper.h>
-#include <linux/pci.h>
 #include <linux/sizes.h>
 #include <asm/pci_dma.h>