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
  ...

20 files changed, 1160 insertions, 403 deletions

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 6b81746cd13c..e0d2e6e6e40c 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -19,8 +19,17 @@
 #define pr_fmt(fmt)	"ACPI: IORT: " fmt
 
 #include <linux/acpi_iort.h>
+#include <linux/iommu.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define IORT_TYPE_MASK(type)	(1 << (type))
+#define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
+#define IORT_IOMMU_TYPE		((1 << ACPI_IORT_NODE_SMMU) |	\
+				(1 << ACPI_IORT_NODE_SMMU_V3))
 
 struct iort_its_msi_chip {
 	struct list_head	list;
@@ -28,6 +37,90 @@ struct iort_its_msi_chip {
 	u32			translation_id;
 };
 
+struct iort_fwnode {
+	struct list_head list;
+	struct acpi_iort_node *iort_node;
+	struct fwnode_handle *fwnode;
+};
+static LIST_HEAD(iort_fwnode_list);
+static DEFINE_SPINLOCK(iort_fwnode_lock);
+
+/**
+ * iort_set_fwnode() - Create iort_fwnode and use it to register
+ *		       iommu data in the iort_fwnode_list
+ *
+ * @node: IORT table node associated with the IOMMU
+ * @fwnode: fwnode associated with the IORT node
+ *
+ * Returns: 0 on success
+ *          <0 on failure
+ */
+static inline int iort_set_fwnode(struct acpi_iort_node *iort_node,
+				  struct fwnode_handle *fwnode)
+{
+	struct iort_fwnode *np;
+
+	np = kzalloc(sizeof(struct iort_fwnode), GFP_ATOMIC);
+
+	if (WARN_ON(!np))
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&np->list);
+	np->iort_node = iort_node;
+	np->fwnode = fwnode;
+
+	spin_lock(&iort_fwnode_lock);
+	list_add_tail(&np->list, &iort_fwnode_list);
+	spin_unlock(&iort_fwnode_lock);
+
+	return 0;
+}
+
+/**
+ * iort_get_fwnode() - Retrieve fwnode associated with an IORT node
+ *
+ * @node: IORT table node to be looked-up
+ *
+ * Returns: fwnode_handle pointer on success, NULL on failure
+ */
+static inline
+struct fwnode_handle *iort_get_fwnode(struct acpi_iort_node *node)
+{
+	struct iort_fwnode *curr;
+	struct fwnode_handle *fwnode = NULL;
+
+	spin_lock(&iort_fwnode_lock);
+	list_for_each_entry(curr, &iort_fwnode_list, list) {
+		if (curr->iort_node == node) {
+			fwnode = curr->fwnode;
+			break;
+		}
+	}
+	spin_unlock(&iort_fwnode_lock);
+
+	return fwnode;
+}
+
+/**
+ * iort_delete_fwnode() - Delete fwnode associated with an IORT node
+ *
+ * @node: IORT table node associated with fwnode to delete
+ */
+static inline void iort_delete_fwnode(struct acpi_iort_node *node)
+{
+	struct iort_fwnode *curr, *tmp;
+
+	spin_lock(&iort_fwnode_lock);
+	list_for_each_entry_safe(curr, tmp, &iort_fwnode_list, list) {
+		if (curr->iort_node == node) {
+			list_del(&curr->list);
+			kfree(curr);
+			break;
+		}
+	}
+	spin_unlock(&iort_fwnode_lock);
+}
+
 typedef acpi_status (*iort_find_node_callback)
 	(struct acpi_iort_node *node, void *context);
 
@@ -141,6 +234,21 @@ static struct acpi_iort_node *iort_scan_node(enum acpi_iort_node_type type,
 	return NULL;
 }
 
+static acpi_status
+iort_match_type_callback(struct acpi_iort_node *node, void *context)
+{
+	return AE_OK;
+}
+
+bool iort_node_match(u8 type)
+{
+	struct acpi_iort_node *node;
+
+	node = iort_scan_node(type, iort_match_type_callback, NULL);
+
+	return node != NULL;
+}
+
 static acpi_status iort_match_node_callback(struct acpi_iort_node *node,
 					    void *context)
 {
@@ -212,9 +320,48 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 	return 0;
 }
 
+static
+struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
+					u32 *id_out, u8 type_mask,
+					int index)
+{
+	struct acpi_iort_node *parent;
+	struct acpi_iort_id_mapping *map;
+
+	if (!node->mapping_offset || !node->mapping_count ||
+				     index >= node->mapping_count)
+		return NULL;
+
+	map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, node,
+			   node->mapping_offset);
+
+	/* Firmware bug! */
+	if (!map->output_reference) {
+		pr_err(FW_BUG "[node %p type %d] ID map has NULL parent reference\n",
+		       node, node->type);
+		return NULL;
+	}
+
+	parent = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+			       map->output_reference);
+
+	if (!(IORT_TYPE_MASK(parent->type) & type_mask))
+		return NULL;
+
+	if (map[index].flags & ACPI_IORT_ID_SINGLE_MAPPING) {
+		if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
+		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+			*id_out = map[index].output_base;
+			return parent;
+		}
+	}
+
+	return NULL;
+}
+
 static struct acpi_iort_node *iort_node_map_rid(struct acpi_iort_node *node,
 						u32 rid_in, u32 *rid_out,
-						u8 type)
+						u8 type_mask)
 {
 	u32 rid = rid_in;
 
@@ -223,7 +370,7 @@ static struct acpi_iort_node *iort_node_map_rid(struct acpi_iort_node *node,
 		struct acpi_iort_id_mapping *map;
 		int i;
 
-		if (node->type == type) {
+		if (IORT_TYPE_MASK(node->type) & type_mask) {
 			if (rid_out)
 				*rid_out = rid;
 			return node;
@@ -296,7 +443,7 @@ u32 iort_msi_map_rid(struct device *dev, u32 req_id)
 	if (!node)
 		return req_id;
 
-	iort_node_map_rid(node, req_id, &dev_id, ACPI_IORT_NODE_ITS_GROUP);
+	iort_node_map_rid(node, req_id, &dev_id, IORT_MSI_TYPE);
 	return dev_id;
 }
 
@@ -318,7 +465,7 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id,
 	if (!node)
 		return -ENXIO;
 
-	node = iort_node_map_rid(node, req_id, NULL, ACPI_IORT_NODE_ITS_GROUP);
+	node = iort_node_map_rid(node, req_id, NULL, IORT_MSI_TYPE);
 	if (!node)
 		return -ENXIO;
 
@@ -356,13 +503,459 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id)
 	return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
 }
 
+static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
+{
+	u32 *rid = data;
+
+	*rid = alias;
+	return 0;
+}
+
+static int arm_smmu_iort_xlate(struct device *dev, u32 streamid,
+			       struct fwnode_handle *fwnode,
+			       const struct iommu_ops *ops)
+{
+	int ret = iommu_fwspec_init(dev, fwnode, ops);
+
+	if (!ret)
+		ret = iommu_fwspec_add_ids(dev, &streamid, 1);
+
+	return ret;
+}
+
+static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
+					struct acpi_iort_node *node,
+					u32 streamid)
+{
+	const struct iommu_ops *ops = NULL;
+	int ret = -ENODEV;
+	struct fwnode_handle *iort_fwnode;
+
+	if (node) {
+		iort_fwnode = iort_get_fwnode(node);
+		if (!iort_fwnode)
+			return NULL;
+
+		ops = iommu_get_instance(iort_fwnode);
+		if (!ops)
+			return NULL;
+
+		ret = arm_smmu_iort_xlate(dev, streamid, iort_fwnode, ops);
+	}
+
+	return ret ? NULL : ops;
+}
+
+/**
+ * iort_set_dma_mask - Set-up dma mask for a device.
+ *
+ * @dev: device to configure
+ */
+void iort_set_dma_mask(struct device *dev)
+{
+	/*
+	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
+	 * setup the correct supported mask.
+	 */
+	if (!dev->coherent_dma_mask)
+		dev->coherent_dma_mask = DMA_BIT_MASK(32);
+
+	/*
+	 * Set it to coherent_dma_mask by default if the architecture
+	 * code has not set it.
+	 */
+	if (!dev->dma_mask)
+		dev->dma_mask = &dev->coherent_dma_mask;
+}
+
+/**
+ * iort_iommu_configure - Set-up IOMMU configuration for a device.
+ *
+ * @dev: device to configure
+ *
+ * Returns: iommu_ops pointer on configuration success
+ *          NULL on configuration failure
+ */
+const struct iommu_ops *iort_iommu_configure(struct device *dev)
+{
+	struct acpi_iort_node *node, *parent;
+	const struct iommu_ops *ops = NULL;
+	u32 streamid = 0;
+
+	if (dev_is_pci(dev)) {
+		struct pci_bus *bus = to_pci_dev(dev)->bus;
+		u32 rid;
+
+		pci_for_each_dma_alias(to_pci_dev(dev), __get_pci_rid,
+				       &rid);
+
+		node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+				      iort_match_node_callback, &bus->dev);
+		if (!node)
+			return NULL;
+
+		parent = iort_node_map_rid(node, rid, &streamid,
+					   IORT_IOMMU_TYPE);
+
+		ops = iort_iommu_xlate(dev, parent, streamid);
+
+	} else {
+		int i = 0;
+
+		node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
+				      iort_match_node_callback, dev);
+		if (!node)
+			return NULL;
+
+		parent = iort_node_get_id(node, &streamid,
+					  IORT_IOMMU_TYPE, i++);
+
+		while (parent) {
+			ops = iort_iommu_xlate(dev, parent, streamid);
+
+			parent = iort_node_get_id(node, &streamid,
+						  IORT_IOMMU_TYPE, i++);
+		}
+	}
+
+	return ops;
+}
+
+static void __init acpi_iort_register_irq(int hwirq, const char *name,
+					  int trigger,
+					  struct resource *res)
+{
+	int irq = acpi_register_gsi(NULL, hwirq, trigger,
+				    ACPI_ACTIVE_HIGH);
+
+	if (irq <= 0) {
+		pr_err("could not register gsi hwirq %d name [%s]\n", hwirq,
+								      name);
+		return;
+	}
+
+	res->start = irq;
+	res->end = irq;
+	res->flags = IORESOURCE_IRQ;
+	res->name = name;
+}
+
+static int __init arm_smmu_v3_count_resources(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+	/* Always present mem resource */
+	int num_res = 1;
+
+	/* Retrieve SMMUv3 specific data */
+	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+	if (smmu->event_gsiv)
+		num_res++;
+
+	if (smmu->pri_gsiv)
+		num_res++;
+
+	if (smmu->gerr_gsiv)
+		num_res++;
+
+	if (smmu->sync_gsiv)
+		num_res++;
+
+	return num_res;
+}
+
+static void __init arm_smmu_v3_init_resources(struct resource *res,
+					      struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+	int num_res = 0;
+
+	/* Retrieve SMMUv3 specific data */
+	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+	res[num_res].start = smmu->base_address;
+	res[num_res].end = smmu->base_address + SZ_128K - 1;
+	res[num_res].flags = IORESOURCE_MEM;
+
+	num_res++;
+
+	if (smmu->event_gsiv)
+		acpi_iort_register_irq(smmu->event_gsiv, "eventq",
+				       ACPI_EDGE_SENSITIVE,
+				       &res[num_res++]);
+
+	if (smmu->pri_gsiv)
+		acpi_iort_register_irq(smmu->pri_gsiv, "priq",
+				       ACPI_EDGE_SENSITIVE,
+				       &res[num_res++]);
+
+	if (smmu->gerr_gsiv)
+		acpi_iort_register_irq(smmu->gerr_gsiv, "gerror",
+				       ACPI_EDGE_SENSITIVE,
+				       &res[num_res++]);
+
+	if (smmu->sync_gsiv)
+		acpi_iort_register_irq(smmu->sync_gsiv, "cmdq-sync",
+				       ACPI_EDGE_SENSITIVE,
+				       &res[num_res++]);
+}
+
+static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+
+	/* Retrieve SMMUv3 specific data */
+	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
+}
+
+static int __init arm_smmu_count_resources(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu *smmu;
+
+	/* Retrieve SMMU specific data */
+	smmu = (struct acpi_iort_smmu *)node->node_data;
+
+	/*
+	 * Only consider the global fault interrupt and ignore the
+	 * configuration access interrupt.
+	 *
+	 * MMIO address and global fault interrupt resources are always
+	 * present so add them to the context interrupt count as a static
+	 * value.
+	 */
+	return smmu->context_interrupt_count + 2;
+}
+
+static void __init arm_smmu_init_resources(struct resource *res,
+					   struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu *smmu;
+	int i, hw_irq, trigger, num_res = 0;
+	u64 *ctx_irq, *glb_irq;
+
+	/* Retrieve SMMU specific data */
+	smmu = (struct acpi_iort_smmu *)node->node_data;
+
+	res[num_res].start = smmu->base_address;
+	res[num_res].end = smmu->base_address + smmu->span - 1;
+	res[num_res].flags = IORESOURCE_MEM;
+	num_res++;
+
+	glb_irq = ACPI_ADD_PTR(u64, node, smmu->global_interrupt_offset);
+	/* Global IRQs */
+	hw_irq = IORT_IRQ_MASK(glb_irq[0]);
+	trigger = IORT_IRQ_TRIGGER_MASK(glb_irq[0]);
+
+	acpi_iort_register_irq(hw_irq, "arm-smmu-global", trigger,
+				     &res[num_res++]);
+
+	/* Context IRQs */
+	ctx_irq = ACPI_ADD_PTR(u64, node, smmu->context_interrupt_offset);
+	for (i = 0; i < smmu->context_interrupt_count; i++) {
+		hw_irq = IORT_IRQ_MASK(ctx_irq[i]);
+		trigger = IORT_IRQ_TRIGGER_MASK(ctx_irq[i]);
+
+		acpi_iort_register_irq(hw_irq, "arm-smmu-context", trigger,
+				       &res[num_res++]);
+	}
+}
+
+static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu *smmu;
+
+	/* Retrieve SMMU specific data */
+	smmu = (struct acpi_iort_smmu *)node->node_data;
+
+	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
+}
+
+struct iort_iommu_config {
+	const char *name;
+	int (*iommu_init)(struct acpi_iort_node *node);
+	bool (*iommu_is_coherent)(struct acpi_iort_node *node);
+	int (*iommu_count_resources)(struct acpi_iort_node *node);
+	void (*iommu_init_resources)(struct resource *res,
+				     struct acpi_iort_node *node);
+};
+
+static const struct iort_iommu_config iort_arm_smmu_v3_cfg __initconst = {
+	.name = "arm-smmu-v3",
+	.iommu_is_coherent = arm_smmu_v3_is_coherent,
+	.iommu_count_resources = arm_smmu_v3_count_resources,
+	.iommu_init_resources = arm_smmu_v3_init_resources
+};
+
+static const struct iort_iommu_config iort_arm_smmu_cfg __initconst = {
+	.name = "arm-smmu",
+	.iommu_is_coherent = arm_smmu_is_coherent,
+	.iommu_count_resources = arm_smmu_count_resources,
+	.iommu_init_resources = arm_smmu_init_resources
+};
+
+static __init
+const struct iort_iommu_config *iort_get_iommu_cfg(struct acpi_iort_node *node)
+{
+	switch (node->type) {
+	case ACPI_IORT_NODE_SMMU_V3:
+		return &iort_arm_smmu_v3_cfg;
+	case ACPI_IORT_NODE_SMMU:
+		return &iort_arm_smmu_cfg;
+	default:
+		return NULL;
+	}
+}
+
+/**
+ * iort_add_smmu_platform_device() - Allocate a platform device for SMMU
+ * @node: Pointer to SMMU ACPI IORT node
+ *
+ * Returns: 0 on success, <0 failure
+ */
+static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
+{
+	struct fwnode_handle *fwnode;
+	struct platform_device *pdev;
+	struct resource *r;
+	enum dev_dma_attr attr;
+	int ret, count;
+	const struct iort_iommu_config *ops = iort_get_iommu_cfg(node);
+
+	if (!ops)
+		return -ENODEV;
+
+	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return PTR_ERR(pdev);
+
+	count = ops->iommu_count_resources(node);
+
+	r = kcalloc(count, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+		goto dev_put;
+	}
+
+	ops->iommu_init_resources(r, node);
+
+	ret = platform_device_add_resources(pdev, r, count);
+	/*
+	 * Resources are duplicated in platform_device_add_resources,
+	 * free their allocated memory
+	 */
+	kfree(r);
+
+	if (ret)
+		goto dev_put;
+
+	/*
+	 * Add a copy of IORT node pointer to platform_data to
+	 * be used to retrieve IORT data information.
+	 */
+	ret = platform_device_add_data(pdev, &node, sizeof(node));
+	if (ret)
+		goto dev_put;
+
+	/*
+	 * We expect the dma masks to be equivalent for
+	 * all SMMUs set-ups
+	 */
+	pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+
+	fwnode = iort_get_fwnode(node);
+
+	if (!fwnode) {
+		ret = -ENODEV;
+		goto dev_put;
+	}
+
+	pdev->dev.fwnode = fwnode;
+
+	attr = ops->iommu_is_coherent(node) ?
+			     DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(&pdev->dev, attr);
+
+	ret = platform_device_add(pdev);
+	if (ret)
+		goto dma_deconfigure;
+
+	return 0;
+
+dma_deconfigure:
+	acpi_dma_deconfigure(&pdev->dev);
+dev_put:
+	platform_device_put(pdev);
+
+	return ret;
+}
+
+static void __init iort_init_platform_devices(void)
+{
+	struct acpi_iort_node *iort_node, *iort_end;
+	struct acpi_table_iort *iort;
+	struct fwnode_handle *fwnode;
+	int i, ret;
+
+	/*
+	 * iort_table and iort both point to the start of IORT table, but
+	 * have different struct types
+	 */
+	iort = (struct acpi_table_iort *)iort_table;
+
+	/* Get the first IORT node */
+	iort_node = ACPI_ADD_PTR(struct acpi_iort_node, iort,
+				 iort->node_offset);
+	iort_end = ACPI_ADD_PTR(struct acpi_iort_node, iort,
+				iort_table->length);
+
+	for (i = 0; i < iort->node_count; i++) {
+		if (iort_node >= iort_end) {
+			pr_err("iort node pointer overflows, bad table\n");
+			return;
+		}
+
+		if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
+			(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
+
+			fwnode = acpi_alloc_fwnode_static();
+			if (!fwnode)
+				return;
+
+			iort_set_fwnode(iort_node, fwnode);
+
+			ret = iort_add_smmu_platform_device(iort_node);
+			if (ret) {
+				iort_delete_fwnode(iort_node);
+				acpi_free_fwnode_static(fwnode);
+				return;
+			}
+		}
+
+		iort_node = ACPI_ADD_PTR(struct acpi_iort_node, iort_node,
+					 iort_node->length);
+	}
+}
+
 void __init acpi_iort_init(void)
 {
 	acpi_status status;
 
 	status = acpi_get_table(ACPI_SIG_IORT, 0, &iort_table);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		const char *msg = acpi_format_exception(status);
-		pr_err("Failed to get table, %s\n", msg);
+	if (ACPI_FAILURE(status)) {
+		if (status != AE_NOT_FOUND) {
+			const char *msg = acpi_format_exception(status);
+
+			pr_err("Failed to get table, %s\n", msg);
+		}
+
+		return;
 	}
+
+	iort_init_platform_devices();
+
+	acpi_probe_device_table(iort);
 }
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 5ea5dc219f56..f8d65647ea79 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -227,8 +227,7 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 
 	attr = acpi_get_dma_attr(acpi_dev);
 	if (attr != DEV_DMA_NOT_SUPPORTED)
-		arch_setup_dma_ops(dev, 0, 0, NULL,
-				   attr == DEV_DMA_COHERENT);
+		acpi_dma_configure(dev, attr);
 
 	acpi_physnode_link_name(physical_node_name, node_id);
 	retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
@@ -251,6 +250,7 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 	return 0;
 
  err:
+	acpi_dma_deconfigure(dev);
 	ACPI_COMPANION_SET(dev, NULL);
 	put_device(dev);
 	put_device(&acpi_dev->dev);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 3d1856f1f4d0..93b00cf4eb39 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/signal.h>
 #include <linux/kthread.h>
 #include <linux/dmi.h>
@@ -1370,6 +1371,38 @@ enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
 		return DEV_DMA_NON_COHERENT;
 }
 
+/**
+ * acpi_dma_configure - Set-up DMA configuration for the device.
+ * @dev: The pointer to the device
+ * @attr: device dma attributes
+ */
+void acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
+{
+	const struct iommu_ops *iommu;
+
+	iort_set_dma_mask(dev);
+
+	iommu = iort_iommu_configure(dev);
+
+	/*
+	 * Assume dma valid range starts at 0 and covers the whole
+	 * coherent_dma_mask.
+	 */
+	arch_setup_dma_ops(dev, 0, dev->coherent_dma_mask + 1, iommu,
+			   attr == DEV_DMA_COHERENT);
+}
+EXPORT_SYMBOL_GPL(acpi_dma_configure);
+
+/**
+ * acpi_dma_deconfigure - Tear-down DMA configuration for the device.
+ * @dev: The pointer to the device
+ */
+void acpi_dma_deconfigure(struct device *dev)
+{
+	arch_teardown_dma_ops(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_dma_deconfigure);
+
 static void acpi_init_coherency(struct acpi_device *adev)
 {
 	unsigned long long cca = 0;
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