Merge branch 'for-joerg/arm-smmu/updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

6 files changed, 260 insertions, 110 deletions

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..41b67ce999bf 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;
 	}
@@ -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/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..8d3e847d4845 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1615,6 +1615,46 @@ 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/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;