Merge tag 'iommu-updates-v4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - OF_IOMMU support for the Rockchip iommu driver so that it can use
   generic DT bindings

 - rework of locking in the AMD IOMMU interrupt remapping code to make
   it work better in RT kernels

 - support for improved iotlb flushing in the AMD IOMMU driver

 - support for 52-bit physical and virtual addressing in the ARM-SMMU

 - various other small fixes and cleanups

* tag 'iommu-updates-v4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (53 commits)
  iommu/io-pgtable-arm: Avoid warning with 32-bit phys_addr_t
  iommu/rockchip: Support sharing IOMMU between masters
  iommu/rockchip: Add runtime PM support
  iommu/rockchip: Fix error handling in init
  iommu/rockchip: Use OF_IOMMU to attach devices automatically
  iommu/rockchip: Use IOMMU device for dma mapping operations
  dt-bindings: iommu/rockchip: Add clock property
  iommu/rockchip: Control clocks needed to access the IOMMU
  iommu/rockchip: Fix TLB flush of secondary IOMMUs
  iommu/rockchip: Use iopoll helpers to wait for hardware
  iommu/rockchip: Fix error handling in attach
  iommu/rockchip: Request irqs in rk_iommu_probe()
  iommu/rockchip: Fix error handling in probe
  iommu/rockchip: Prohibit unbind and remove
  iommu/amd: Return proper error code in irq_remapping_alloc()
  iommu/amd: Make amd_iommu_devtable_lock a spin_lock
  iommu/amd: Drop the lock while allocating new irq remap table
  iommu/amd: Factor out setting the remap table for a devid
  iommu/amd: Use `table' instead `irt' as variable name in amd_iommu_update_ga()
  iommu/amd: Remove the special case from alloc_irq_table()
  ...

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt

@@ -11,6 +11,8 @@ Required Properties:
     the device is compatible with the R-Car Gen2 VMSA-compatible IPMMU.
 
     - "renesas,ipmmu-r8a73a4" for the R8A73A4 (R-Mobile APE6) IPMMU.
+    - "renesas,ipmmu-r8a7743" for the R8A7743 (RZ/G1M) IPMMU.
+    - "renesas,ipmmu-r8a7745" for the R8A7745 (RZ/G1E) IPMMU.
     - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU.
     - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU.
     - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.
@@ -19,7 +21,8 @@ Required Properties:
     - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU.
     - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU.
     - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU.
-    - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU.
+    - "renesas,ipmmu-vmsa" for generic R-Car Gen2 or RZ/G1 VMSA-compatible
+			   IPMMU.
 
   - reg: Base address and size of the IPMMU registers.
   - interrupts: Specifiers for the MMU fault interrupts. For instances that

Documentation/devicetree/bindings/iommu/rockchip,iommu.txt

@@ -14,6 +14,11 @@ Required properties:
                     "single-master" device, and needs no additional information
                     to associate with its master device.  See:
                     Documentation/devicetree/bindings/iommu/iommu.txt
+- clocks          : A list of clocks required for the IOMMU to be accessible by
+                    the host CPU.
+- clock-names     : Should contain the following:
+	"iface" - Main peripheral bus clock (PCLK/HCL) (required)
+	"aclk"  - AXI bus clock (required)
 
 Optional properties:
 - rockchip,disable-mmu-reset : Don't use the mmu reset operation.
@@ -27,5 +32,7 @@ Example:
 		reg = <0xff940300 0x100>;
 		interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "vopl_mmu";
+		clocks = <&cru ACLK_VOP1>, <&cru HCLK_VOP1>;
+		clock-names = "aclk", "iface";
 		#iommu-cells = <0>;
 	};

drivers/acpi/arm64/iort.c

@@ -34,6 +34,7 @@
 struct iort_its_msi_chip {
 	struct list_head	list;
 	struct fwnode_handle	*fw_node;
+	phys_addr_t		base_addr;
 	u32			translation_id;
 };
 
@@ -156,14 +157,16 @@ static LIST_HEAD(iort_msi_chip_list);
 static DEFINE_SPINLOCK(iort_msi_chip_lock);
 
 /**
- * iort_register_domain_token() - register domain token and related ITS ID
- * to the list from where we can get it back later on.
+ * iort_register_domain_token() - register domain token along with related
+ * ITS ID and base address to the list from where we can get it back later on.
  * @trans_id: ITS ID.
+ * @base: ITS base address.
  * @fw_node: Domain token.
  *
  * Returns: 0 on success, -ENOMEM if no memory when allocating list element
  */
-int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
+int iort_register_domain_token(int trans_id, phys_addr_t base,
+			       struct fwnode_handle *fw_node)
 {
 	struct iort_its_msi_chip *its_msi_chip;
 
@@ -173,6 +176,7 @@ int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
 
 	its_msi_chip->fw_node = fw_node;
 	its_msi_chip->translation_id = trans_id;
+	its_msi_chip->base_addr = base;
 
 	spin_lock(&iort_msi_chip_lock);
 	list_add(&its_msi_chip->list, &iort_msi_chip_list);
@@ -569,6 +573,24 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
 	return -ENODEV;
 }
 
+static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base)
+{
+	struct iort_its_msi_chip *its_msi_chip;
+	int ret = -ENODEV;
+
+	spin_lock(&iort_msi_chip_lock);
+	list_for_each_entry(its_msi_chip, &iort_msi_chip_list, list) {
+		if (its_msi_chip->translation_id == its_id) {
+			*base = its_msi_chip->base_addr;
+			ret = 0;
+			break;
+		}
+	}
+	spin_unlock(&iort_msi_chip_lock);
+
+	return ret;
+}
+
 /**
  * iort_dev_find_its_id() - Find the ITS identifier for a device
  * @dev: The device.
@@ -754,6 +776,24 @@ static inline bool iort_iommu_driver_enabled(u8 type)
 }
 
 #ifdef CONFIG_IOMMU_API
+static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
+{
+	struct acpi_iort_node *iommu;
+	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+
+	iommu = iort_get_iort_node(fwspec->iommu_fwnode);
+
+	if (iommu && (iommu->type == ACPI_IORT_NODE_SMMU_V3)) {
+		struct acpi_iort_smmu_v3 *smmu;
+
+		smmu = (struct acpi_iort_smmu_v3 *)iommu->node_data;
+		if (smmu->model == ACPI_IORT_SMMU_V3_HISILICON_HI161X)
+			return iommu;
+	}
+
+	return NULL;
+}
+
 static inline const struct iommu_ops *iort_fwspec_iommu_ops(
 				struct iommu_fwspec *fwspec)
 {
@@ -770,6 +810,69 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
 
 	return err;
 }
+
+/**
+ * iort_iommu_msi_get_resv_regions - Reserved region driver helper
+ * @dev: Device from iommu_get_resv_regions()
+ * @head: Reserved region list from iommu_get_resv_regions()
+ *
+ * Returns: Number of msi reserved regions on success (0 if platform
+ *          doesn't require the reservation or no associated msi regions),
+ *          appropriate error value otherwise. The ITS interrupt translation
+ *          spaces (ITS_base + SZ_64K, SZ_64K) associated with the device
+ *          are the msi reserved regions.
+ */
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{
+	struct acpi_iort_its_group *its;
+	struct acpi_iort_node *iommu_node, *its_node = NULL;
+	int i, resv = 0;
+
+	iommu_node = iort_get_msi_resv_iommu(dev);
+	if (!iommu_node)
+		return 0;
+
+	/*
+	 * Current logic to reserve ITS regions relies on HW topologies
+	 * where a given PCI or named component maps its IDs to only one
+	 * ITS group; if a PCI or named component can map its IDs to
+	 * different ITS groups through IORT mappings this function has
+	 * to be reworked to ensure we reserve regions for all ITS groups
+	 * a given PCI or named component may map IDs to.
+	 */
+
+	for (i = 0; i < dev->iommu_fwspec->num_ids; i++) {
+		its_node = iort_node_map_id(iommu_node,
+					dev->iommu_fwspec->ids[i],
+					NULL, IORT_MSI_TYPE);
+		if (its_node)
+			break;
+	}
+
+	if (!its_node)
+		return 0;
+
+	/* Move to ITS specific data */
+	its = (struct acpi_iort_its_group *)its_node->node_data;
+
+	for (i = 0; i < its->its_count; i++) {
+		phys_addr_t base;
+
+		if (!iort_find_its_base(its->identifiers[i], &base)) {
+			int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+			struct iommu_resv_region *region;
+
+			region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K,
+							 prot, IOMMU_RESV_MSI);
+			if (region) {
+				list_add_tail(&region->list, head);
+				resv++;
+			}
+		}
+	}
+
+	return (resv == its->its_count) ? resv : -ENODEV;
+}
 #else
 static inline const struct iommu_ops *iort_fwspec_iommu_ops(
 				struct iommu_fwspec *fwspec)
@@ -777,6 +880,8 @@ static inline const struct iommu_ops *iort_fwspec_iommu_ops(
 static inline int iort_add_device_replay(const struct iommu_ops *ops,
 					 struct device *dev)
 { return 0; }
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{ return 0; }
 #endif
 
 static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,

drivers/iommu/amd_iommu.c

@@ -81,11 +81,12 @@
  */
 #define AMD_IOMMU_PGSIZES	((~0xFFFUL) & ~(2ULL << 38))
 
-static DEFINE_RWLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(pd_bitmap_lock);
+static DEFINE_SPINLOCK(iommu_table_lock);
 
 /* List of all available dev_data structures */
-static LIST_HEAD(dev_data_list);
-static DEFINE_SPINLOCK(dev_data_list_lock);
+static LLIST_HEAD(dev_data_list);
 
 LIST_HEAD(ioapic_map);
 LIST_HEAD(hpet_map);
@@ -204,40 +205,33 @@ static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
-	unsigned long flags;
 
 	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
 	if (!dev_data)
 		return NULL;
 
 	dev_data->devid = devid;
-
-	spin_lock_irqsave(&dev_data_list_lock, flags);
-	list_add_tail(&dev_data->dev_data_list, &dev_data_list);
-	spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
 	ratelimit_default_init(&dev_data->rs);
 
+	llist_add(&dev_data->dev_data_list, &dev_data_list);
 	return dev_data;
 }
 
 static struct iommu_dev_data *search_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
-	unsigned long flags;
+	struct llist_node *node;
 
-	spin_lock_irqsave(&dev_data_list_lock, flags);
-	list_for_each_entry(dev_data, &dev_data_list, dev_data_list) {
+	if (llist_empty(&dev_data_list))
+		return NULL;
+
+	node = dev_data_list.first;
+	llist_for_each_entry(dev_data, node, dev_data_list) {
 		if (dev_data->devid == devid)
-			goto out_unlock;
+			return dev_data;
 	}
 
-	dev_data = NULL;
-
-out_unlock:
-	spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
-	return dev_data;
+	return NULL;
 }
 
 static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -311,6 +305,8 @@ static struct iommu_dev_data *find_dev_data(u16 devid)
 
 	if (dev_data == NULL) {
 		dev_data = alloc_dev_data(devid);
+		if (!dev_data)
+			return NULL;
 
 		if (translation_pre_enabled(iommu))
 			dev_data->defer_attach = true;
@@ -548,6 +544,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
+	struct device *dev = iommu->iommu.dev;
 	int type, devid, domid, flags;
 	volatile u32 *event = __evt;
 	int count = 0;
@@ -574,53 +571,53 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 		amd_iommu_report_page_fault(devid, domid, address, flags);
 		return;
 	} else {
-		printk(KERN_ERR "AMD-Vi: Event logged [");
+		dev_err(dev, "AMD-Vi: Event logged [");
 	}
 
 	switch (type) {
 	case EVENT_TYPE_ILL_DEV:
-		printk("ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
+		dev_err(dev, "ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
 			"address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address, flags);
 		dump_dte_entry(devid);
 		break;
 	case EVENT_TYPE_DEV_TAB_ERR:
-		printk("DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
+		dev_err(dev, "DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
 			"address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		printk("PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
+		dev_err(dev, "PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
 			"domain=0x%04x address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			domid, address, flags);
 		break;
 	case EVENT_TYPE_ILL_CMD:
-		printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
+		dev_err(dev, "ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
 		dump_command(address);
 		break;
 	case EVENT_TYPE_CMD_HARD_ERR:
-		printk("COMMAND_HARDWARE_ERROR address=0x%016llx "
+		dev_err(dev, "COMMAND_HARDWARE_ERROR address=0x%016llx "
 			"flags=0x%04x]\n", address, flags);
 		break;
 	case EVENT_TYPE_IOTLB_INV_TO:
-		printk("IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
+		dev_err(dev, "IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
 			"address=0x%016llx]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address);
 		break;
 	case EVENT_TYPE_INV_DEV_REQ:
-		printk("INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
+		dev_err(dev, "INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
 			"address=0x%016llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address, flags);
 		break;
 	default:
-		printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x "
-		       "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
-		       type, event[0], event[1], event[2], event[3]);
+		dev_err(dev, KERN_ERR "UNKNOWN event[0]=0x%08x event[1]=0x%08x "
+			"event[2]=0x%08x event[3]=0x%08x\n",
+			event[0], event[1], event[2], event[3]);
 	}
 
 	memset(__evt, 0, 4 * sizeof(u32));
@@ -1057,9 +1054,9 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
 	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	raw_spin_lock_irqsave(&iommu->lock, flags);
 	ret = __iommu_queue_command_sync(iommu, cmd, sync);
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return ret;
 }
@@ -1085,7 +1082,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
 	build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	raw_spin_lock_irqsave(&iommu->lock, flags);
 
 	iommu->cmd_sem = 0;
 
@@ -1096,7 +1093,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	ret = wait_on_sem(&iommu->cmd_sem);
 
 out_unlock:
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return ret;
 }
@@ -1606,29 +1603,26 @@ static void del_domain_from_list(struct protection_domain *domain)
 
 static u16 domain_id_alloc(void)
 {
-	unsigned long flags;
 	int id;
 
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock(&pd_bitmap_lock);
 	id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
 	BUG_ON(id == 0);
 	if (id > 0 && id < MAX_DOMAIN_ID)
 		__set_bit(id, amd_iommu_pd_alloc_bitmap);
 	else
 		id = 0;
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock(&pd_bitmap_lock);
 
 	return id;
 }
 
 static void domain_id_free(int id)
 {
-	unsigned long flags;
-
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock(&pd_bitmap_lock);
 	if (id > 0 && id < MAX_DOMAIN_ID)
 		__clear_bit(id, amd_iommu_pd_alloc_bitmap);
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock(&pd_bitmap_lock);
 }
 
 #define DEFINE_FREE_PT_FN(LVL, FN)				\
@@ -2104,9 +2098,9 @@ static int attach_device(struct device *dev,
 	}
 
 skip_ats_check:
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	ret = __attach_device(dev_data, domain);
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
 	/*
 	 * We might boot into a crash-kernel here. The crashed kernel
@@ -2156,9 +2150,9 @@ static void detach_device(struct device *dev)
 	domain   = dev_data->domain;
 
 	/* lock device table */
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	__detach_device(dev_data);
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
 	if (!dev_is_pci(dev))
 		return;
@@ -2795,7 +2789,7 @@ static void cleanup_domain(struct protection_domain *domain)
 	struct iommu_dev_data *entry;
 	unsigned long flags;
 
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
 
 	while (!list_empty(&domain->dev_list)) {
 		entry = list_first_entry(&domain->dev_list,
@@ -2803,7 +2797,7 @@ static void cleanup_domain(struct protection_domain *domain)
 		__detach_device(entry);
 	}
 
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 }
 
 static void protection_domain_free(struct protection_domain *domain)
@@ -3025,15 +3019,12 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 	size_t unmap_size;
 
 	if (domain->mode == PAGE_MODE_NONE)
-		return -EINVAL;
+		return 0;
 
 	mutex_lock(&domain->api_lock);
 	unmap_size = iommu_unmap_page(domain, iova, page_size);
 	mutex_unlock(&domain->api_lock);
 
-	domain_flush_tlb_pde(domain);
-	domain_flush_complete(domain);
-
 	return unmap_size;
 }
 
@@ -3151,6 +3142,19 @@ static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
 	return dev_data->defer_attach;
 }
 
+static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct protection_domain *dom = to_pdomain(domain);
+
+	domain_flush_tlb_pde(dom);
+	domain_flush_complete(dom);
+}
+
+static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
+				      unsigned long iova, size_t size)
+{
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -3169,6 +3173,9 @@ const struct iommu_ops amd_iommu_ops = {
 	.apply_resv_region = amd_iommu_apply_resv_region,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
+	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
+	.iotlb_range_add = amd_iommu_iotlb_range_add,
+	.iotlb_sync = amd_iommu_flush_iotlb_all,
 };
 
 /*****************************************************************************
@@ -3570,14 +3577,62 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
 	amd_iommu_dev_table[devid].data[2] = dte;
 }
 
-static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
+static struct irq_remap_table *get_irq_table(u16 devid)
+{
+	struct irq_remap_table *table;
+
+	if (WARN_ONCE(!amd_iommu_rlookup_table[devid],
+		      "%s: no iommu for devid %x\n", __func__, devid))
+		return NULL;
+
+	table = irq_lookup_table[devid];
+	if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid))
+		return NULL;
+
+	return table;
+}
+
+static struct irq_remap_table *__alloc_irq_table(void)
+{
+	struct irq_remap_table *table;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return NULL;
+
+	table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL);
+	if (!table->table) {
+		kfree(table);
+		return NULL;
+	}
+	raw_spin_lock_init(&table->lock);
+
+	if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+		memset(table->table, 0,
+		       MAX_IRQS_PER_TABLE * sizeof(u32));
+	else
+		memset(table->table, 0,
+		       (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+	return table;
+}
+
+static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
+				  struct irq_remap_table *table)
+{
+	irq_lookup_table[devid] = table;
+	set_dte_irq_entry(devid, table);
+	iommu_flush_dte(iommu, devid);
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid)
 {
 	struct irq_remap_table *table = NULL;
+	struct irq_remap_table *new_table = NULL;
 	struct amd_iommu *iommu;
 	unsigned long flags;
 	u16 alias;
 
-	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	spin_lock_irqsave(&iommu_table_lock, flags);
 
 	iommu = amd_iommu_rlookup_table[devid];
 	if (!iommu)
@@ -3590,60 +3645,45 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	alias = amd_iommu_alias_table[devid];
 	table = irq_lookup_table[alias];
 	if (table) {
-		irq_lookup_table[devid] = table;
-		set_dte_irq_entry(devid, table);
-		iommu_flush_dte(iommu, devid);
-		goto out;
+		set_remap_table_entry(iommu, devid, table);
+		goto out_wait;
 	}
+	spin_unlock_irqrestore(&iommu_table_lock, flags);
 
 	/* Nothing there yet, allocate new irq remapping table */
-	table = kzalloc(sizeof(*table), GFP_ATOMIC);
-	if (!table)
-		goto out_unlock;
-
-	/* Initialize table spin-lock */
-	spin_lock_init(&table->lock);
+	new_table = __alloc_irq_table();
+	if (!new_table)
+		return NULL;
 
-	if (ioapic)
-		/* Keep the first 32 indexes free for IOAPIC interrupts */
-		table->min_index = 32;
+	spin_lock_irqsave(&iommu_table_lock, flags);
 
-	table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC);
-	if (!table->table) {
-		kfree(table);
-		table = NULL;
+	table = irq_lookup_table[devid];
+	if (table)
 		goto out_unlock;
-	}
-
-	if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
-		memset(table->table, 0,
-		       MAX_IRQS_PER_TABLE * sizeof(u32));
-	else
-		memset(table->table, 0,
-		       (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
-
-	if (ioapic) {
-		int i;
 
-		for (i = 0; i < 32; ++i)
-			iommu->irte_ops->set_allocated(table, i);
+	table = irq_lookup_table[alias];
+	if (table) {
+		set_remap_table_entry(iommu, devid, table);
+		goto out_wait;
 	}
 
-	irq_lookup_table[devid] = table;
-	set_dte_irq_entry(devid, table);
-	iommu_flush_dte(iommu, devid);
-	if (devid != alias) {
-		irq_lookup_table[alias] = table;
-		set_dte_irq_entry(alias, table);
-		iommu_flush_dte(iommu, alias);
-	}
+	table = new_table;
+	new_table = NULL;
 
-out:
+	set_remap_table_entry(iommu, devid, table);
+	if (devid != alias)
+		set_remap_table_entry(iommu, alias, table);
+
+out_wait:
 	iommu_completion_wait(iommu);
 
 out_unlock:
-	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	spin_unlock_irqrestore(&iommu_table_lock, flags);
 
+	if (new_table) {
+		kmem_cache_free(amd_iommu_irq_cache, new_table->table);
+		kfree(new_table);
+	}
 	return table;
 }
 
@@ -3657,14 +3697,14 @@ static int alloc_irq_index(u16 devid, int count, bool align)
 	if (!iommu)
 		return -ENODEV;
 
-	table = get_irq_table(devid, false);
+	table = alloc_irq_table(devid);
 	if (!table)
 		return -ENODEV;
 
 	if (align)
 		alignment = roundup_pow_of_two(count);
 
-	spin_lock_irqsave(&table->lock, flags);
+	raw_spin_lock_irqsave(&table->lock, flags);
 
 	/* Scan table for free entries */
 	for (index = ALIGN(table->min_index, alignment), c = 0;
@@ -3691,7 +3731,7 @@ static int alloc_irq_index(u16 devid, int count, bool align)
 	index = -ENOSPC;
 
 out:
-	spin_unlock_irqrestore(&table->lock, flags);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
 
 	return index;
 }
@@ -3708,11 +3748,11 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 	if (iommu == NULL)
 		return -EINVAL;
 
-	table = get_irq_table(devid, false);
+	table = get_irq_table(devid);
 	if (!table)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&table->lock, flags);
+	raw_spin_lock_irqsave(&table->lock, flags);
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
@@ -3723,7 +3763,7 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 	if (data)
 		data->ref = entry;
 
-	spin_unlock_irqrestore(&table->lock, flags);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
 
 	iommu_flush_irt(iommu, devid);
 	iommu_completion_wait(iommu);
@@ -3741,13 +3781,13 @@ static int modify_irte(u16 devid, int index, union irte *irte)
 	if (iommu == NULL)
 		return -EINVAL;
 
-	table = get_irq_table(devid, false);
+	table = get_irq_table(devid);
 	if (!table)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&table->lock, flags);
+	raw_spin_lock_irqsave(&table->lock, flags);
 	table->table[index] = irte->val;
-	spin_unlock_irqrestore(&table->lock, flags);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
 
 	iommu_flush_irt(iommu, devid);
 	iommu_completion_wait(iommu);
@@ -3765,13 +3805,13 @@ static void free_irte(u16 devid, int index)
 	if (iommu == NULL)
 		return;
 
-	table = get_irq_table(devid, false);
+	table = get_irq_table(devid);
 	if (!table)
 		return;
 
-	spin_lock_irqsave(&table->lock, flags);
+	raw_spin_lock_irqsave(&table->lock, flags);
 	iommu->irte_ops->clear_allocated(table, index);
-	spin_unlock_irqrestore(&table->lock, flags);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
 
 	iommu_flush_irt(iommu, devid);
 	iommu_completion_wait(iommu);
@@ -3852,10 +3892,8 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
 				 u8 vector, u32 dest_apicid)
 {
 	struct irte_ga *irte = (struct irte_ga *) entry;
-	struct iommu_dev_data *dev_data = search_dev_data(devid);
 
-	if (!dev_data || !dev_data->use_vapic ||
-	    !irte->lo.fields_remap.guest_mode) {
+	if (!irte->lo.fields_remap.guest_mode) {
 		irte->hi.fields.vector = vector;
 		irte->lo.fields_remap.destination = dest_apicid;
 		modify_irte_ga(devid, index, irte, NULL);
@@ -4061,7 +4099,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 	struct amd_ir_data *data = NULL;
 	struct irq_cfg *cfg;
 	int i, ret, devid;
-	int index = -1;
+	int index;
 
 	if (!info)
 		return -EINVAL;
@@ -4085,10 +4123,26 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		return ret;
 
 	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
-		if (get_irq_table(devid, true))
+		struct irq_remap_table *table;
+		struct amd_iommu *iommu;
+
+		table = alloc_irq_table(devid);
+		if (table) {
+			if (!table->min_index) {
+				/*
+				 * Keep the first 32 indexes free for IOAPIC
+				 * interrupts.
+				 */
+				table->min_index = 32;
+				iommu = amd_iommu_rlookup_table[devid];
+				for (i = 0; i < 32; ++i)
+					iommu->irte_ops->set_allocated(table, i);
+			}
+			WARN_ON(table->min_index != 32);
 			index = info->ioapic_pin;
-		else
-			ret = -ENOMEM;
+		} else {
+			index = -ENOMEM;
+		}
 	} else {
 		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
 
@@ -4354,7 +4408,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 {
 	unsigned long flags;
 	struct amd_iommu *iommu;
-	struct irq_remap_table *irt;
+	struct irq_remap_table *table;
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	int devid = ir_data->irq_2_irte.devid;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -4368,11 +4422,11 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	if (!iommu)
 		return -ENODEV;
 
-	irt = get_irq_table(devid, false);
-	if (!irt)
+	table = get_irq_table(devid);
+	if (!table)
 		return -ENODEV;
 
-	spin_lock_irqsave(&irt->lock, flags);
+	raw_spin_lock_irqsave(&table->lock, flags);
 
 	if (ref->lo.fields_vapic.guest_mode) {
 		if (cpu >= 0)
@@ -4381,7 +4435,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 		barrier();
 	}
 
-	spin_unlock_irqrestore(&irt->lock, flags);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
 
 	iommu_flush_irt(iommu, devid);
 	iommu_completion_wait(iommu);

drivers/iommu/amd_iommu_init.c

@@ -1474,7 +1474,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 {
 	int ret;
 
-	spin_lock_init(&iommu->lock);
+	raw_spin_lock_init(&iommu->lock);
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);

drivers/iommu/amd_iommu_types.h

@@ -408,7 +408,7 @@ extern bool amd_iommu_iotlb_sup;
 #define IRQ_TABLE_ALIGNMENT	128
 
 struct irq_remap_table {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	unsigned min_index;
 	u32 *table;
 };
@@ -490,7 +490,7 @@ struct amd_iommu {
 	int index;
 
 	/* locks the accesses to the hardware */
-	spinlock_t lock;
+	raw_spinlock_t lock;
 
 	/* Pointer to PCI device of this IOMMU */
 	struct pci_dev *dev;
@@ -627,7 +627,7 @@ struct devid_map {
  */
 struct iommu_dev_data {
 	struct list_head list;		  /* For domain->dev_list */
-	struct list_head dev_data_list;	  /* For global dev_data_list */
+	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
 	u16 devid;			  /* PCI Device ID */
 	u16 alias;			  /* Alias Device ID */

drivers/iommu/dma-iommu.c

@@ -19,6 +19,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi_iort.h>
 #include <linux/device.h>
 #include <linux/dma-iommu.h>
 #include <linux/gfp.h>
@@ -167,13 +168,18 @@ EXPORT_SYMBOL(iommu_put_dma_cookie);
  *
  * IOMMU drivers can use this to implement their .get_resv_regions callback
  * for general non-IOMMU-specific reservations. Currently, this covers host
- * bridge windows for PCI devices.
+ * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI
+ * based ARM platforms that may require HW MSI reservation.
  */
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
 {
 	struct pci_host_bridge *bridge;
 	struct resource_entry *window;
 
+	if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) &&
+		iort_iommu_msi_get_resv_regions(dev, list) < 0)
+		return;
+
 	if (!dev_is_pci(dev))
 		return;
 

drivers/iommu/dmar.c

@@ -806,7 +806,7 @@ int __init dmar_dev_scope_init(void)
 	return dmar_dev_scope_status;
 }
 
-void dmar_register_bus_notifier(void)
+void __init dmar_register_bus_notifier(void)
 {
 	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 }

drivers/iommu/exynos-iommu.c

@@ -1239,17 +1239,6 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
 	return phys;
 }
 
-static struct iommu_group *get_device_iommu_group(struct device *dev)
-{
-	struct iommu_group *group;
-
-	group = iommu_group_get(dev);
-	if (!group)
-		group = iommu_group_alloc();
-
-	return group;
-}
-
 static int exynos_iommu_add_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
@@ -1345,7 +1334,7 @@ static const struct iommu_ops exynos_iommu_ops = {
 	.unmap = exynos_iommu_unmap,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = exynos_iommu_iova_to_phys,
-	.device_group = get_device_iommu_group,
+	.device_group = generic_device_group,
 	.add_device = exynos_iommu_add_device,
 	.remove_device = exynos_iommu_remove_device,
 	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,

drivers/iommu/intel-iommu.c

@@ -5043,7 +5043,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct page *freelist = NULL;
-	struct intel_iommu *iommu;
 	unsigned long start_pfn, last_pfn;
 	unsigned int npages;
 	int iommu_id, level = 0;
@@ -5062,12 +5061,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 
 	npages = last_pfn - start_pfn + 1;
 
-	for_each_domain_iommu(iommu_id, dmar_domain) {
-		iommu = g_iommus[iommu_id];
-
+	for_each_domain_iommu(iommu_id, dmar_domain)
 		iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
 				      start_pfn, npages, !freelist, 0);
-	}
 
 	dma_free_pagelist(freelist);
 

drivers/iommu/intel-svm.c

@@ -396,6 +396,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				pasid_max - 1, GFP_KERNEL);
 		if (ret < 0) {
 			kfree(svm);
+			kfree(sdev);
 			goto out;
 		}
 		svm->pasid = ret;
@@ -422,17 +423,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		iommu->pasid_table[svm->pasid].val = pasid_entry_val;
 
 		wmb();
-		/* In caching mode, we still have to flush with PASID 0 when
-		 * a PASID table entry becomes present. Not entirely clear
-		 * *why* that would be the case — surely we could just issue
-		 * a flush with the PASID value that we've changed? The PASID
-		 * is the index into the table, after all. It's not like domain
-		 * IDs in the case of the equivalent context-entry change in
-		 * caching mode. And for that matter it's not entirely clear why
-		 * a VMM would be in the business of caching the PASID table
-		 * anyway. Surely that can be left entirely to the guest? */
+
+		/*
+		 * Flush PASID cache when a PASID table entry becomes
+		 * present.
+		 */
 		if (cap_caching_mode(iommu->cap))
-			intel_flush_pasid_dev(svm, sdev, 0);
+			intel_flush_pasid_dev(svm, sdev, svm->pasid);
 	}
 	list_add_rcu(&sdev->list, &svm->devs);
 

drivers/iommu/io-pgtable-arm-v7s.c

@@ -357,7 +357,7 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
 	return false;
 }
 
-static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
 			      size_t, int, arm_v7s_iopte *);
 
 static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
@@ -541,9 +541,10 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
 	return pte;
 }
 
-static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
+static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 				      unsigned long iova, size_t size,
-				   arm_v7s_iopte blk_pte, arm_v7s_iopte *ptep)
+				      arm_v7s_iopte blk_pte,
+				      arm_v7s_iopte *ptep)
 {
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_v7s_iopte pte, *tablep;
@@ -584,7 +585,7 @@ static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 	return size;
 }
 
-static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 			      unsigned long iova, size_t size, int lvl,
 			      arm_v7s_iopte *ptep)
 {
@@ -656,7 +657,7 @@ static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 	return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep);
 }
 
-static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			    size_t size)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);

drivers/iommu/io-pgtable-arm.c

@@ -21,6 +21,7 @@
 #define pr_fmt(fmt)	"arm-lpae io-pgtable: " fmt
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
 #include <linux/iommu.h>
 #include <linux/kernel.h>
 #include <linux/sizes.h>
@@ -32,7 +33,7 @@
 
 #include "io-pgtable.h"
 
-#define ARM_LPAE_MAX_ADDR_BITS		48
+#define ARM_LPAE_MAX_ADDR_BITS		52
 #define ARM_LPAE_S2_MAX_CONCAT_PAGES	16
 #define ARM_LPAE_MAX_LEVELS		4
 
@@ -86,6 +87,8 @@
 #define ARM_LPAE_PTE_TYPE_TABLE		3
 #define ARM_LPAE_PTE_TYPE_PAGE		3
 
+#define ARM_LPAE_PTE_ADDR_MASK		GENMASK_ULL(47,12)
+
 #define ARM_LPAE_PTE_NSTABLE		(((arm_lpae_iopte)1) << 63)
 #define ARM_LPAE_PTE_XN			(((arm_lpae_iopte)3) << 53)
 #define ARM_LPAE_PTE_AF			(((arm_lpae_iopte)1) << 10)
@@ -159,6 +162,7 @@
 #define ARM_LPAE_TCR_PS_42_BIT		0x3ULL
 #define ARM_LPAE_TCR_PS_44_BIT		0x4ULL
 #define ARM_LPAE_TCR_PS_48_BIT		0x5ULL
+#define ARM_LPAE_TCR_PS_52_BIT		0x6ULL
 
 #define ARM_LPAE_MAIR_ATTR_SHIFT(n)	((n) << 3)
 #define ARM_LPAE_MAIR_ATTR_MASK		0xff
@@ -170,9 +174,7 @@
 #define ARM_LPAE_MAIR_ATTR_IDX_DEV	2
 
 /* IOPTE accessors */
-#define iopte_deref(pte,d)					\
-	(__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)	\
-	& ~(ARM_LPAE_GRANULE(d) - 1ULL)))
+#define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
 #define iopte_type(pte,l)					\
 	(((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK)
@@ -184,12 +186,6 @@
 		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) :	\
 		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK))
 
-#define iopte_to_pfn(pte,d)					\
-	(((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift)
-
-#define pfn_to_iopte(pfn,d)					\
-	(((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1))
-
 struct arm_lpae_io_pgtable {
 	struct io_pgtable	iop;
 
@@ -203,6 +199,27 @@ struct arm_lpae_io_pgtable {
 
 typedef u64 arm_lpae_iopte;
 
+static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr,
+				     struct arm_lpae_io_pgtable *data)
+{
+	arm_lpae_iopte pte = paddr;
+
+	/* Of the bits which overlap, either 51:48 or 15:12 are always RES0 */
+	return (pte | (pte >> (48 - 12))) & ARM_LPAE_PTE_ADDR_MASK;
+}
+
+static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte,
+				  struct arm_lpae_io_pgtable *data)
+{
+	u64 paddr = pte & ARM_LPAE_PTE_ADDR_MASK;
+
+	if (data->pg_shift < 16)
+		return paddr;
+
+	/* Rotate the packed high-order bits back to the top */
+	return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4);
+}
+
 static bool selftest_running = false;
 
 static dma_addr_t __arm_lpae_dma_addr(void *pages)
@@ -268,7 +285,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
 		__arm_lpae_sync_pte(ptep, cfg);
 }
 
-static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			       unsigned long iova, size_t size, int lvl,
 			       arm_lpae_iopte *ptep);
 
@@ -287,7 +304,7 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
 
 	pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS;
-	pte |= pfn_to_iopte(paddr >> data->pg_shift, data);
+	pte |= paddr_to_iopte(paddr, data);
 
 	__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
 }
@@ -506,7 +523,7 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
 	kfree(data);
 }
 
-static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 				       unsigned long iova, size_t size,
 				       arm_lpae_iopte blk_pte, int lvl,
 				       arm_lpae_iopte *ptep)
@@ -528,7 +545,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	if (size == split_sz)
 		unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data);
 
-	blk_paddr = iopte_to_pfn(blk_pte, data) << data->pg_shift;
+	blk_paddr = iopte_to_paddr(blk_pte, data);
 	pte = iopte_prot(blk_pte);
 
 	for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) {
@@ -560,7 +577,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	return size;
 }
 
-static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			       unsigned long iova, size_t size, int lvl,
 			       arm_lpae_iopte *ptep)
 {
@@ -606,7 +623,7 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 	return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
 }
 
-static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			     size_t size)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
@@ -652,12 +669,13 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 
 found_translation:
 	iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
-	return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova;
+	return iopte_to_paddr(pte, data) | iova;
 }
 
 static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
 {
-	unsigned long granule;
+	unsigned long granule, page_sizes;
+	unsigned int max_addr_bits = 48;
 
 	/*
 	 * We need to restrict the supported page sizes to match the
@@ -677,17 +695,24 @@ static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
 
 	switch (granule) {
 	case SZ_4K:
-		cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+		page_sizes = (SZ_4K | SZ_2M | SZ_1G);
 		break;
 	case SZ_16K:
-		cfg->pgsize_bitmap &= (SZ_16K | SZ_32M);
+		page_sizes = (SZ_16K | SZ_32M);
 		break;
 	case SZ_64K:
-		cfg->pgsize_bitmap &= (SZ_64K | SZ_512M);
+		max_addr_bits = 52;
+		page_sizes = (SZ_64K | SZ_512M);
+		if (cfg->oas > 48)
+			page_sizes |= 1ULL << 42; /* 4TB */
 		break;
 	default:
-		cfg->pgsize_bitmap = 0;
+		page_sizes = 0;
 	}
+
+	cfg->pgsize_bitmap &= page_sizes;
+	cfg->ias = min(cfg->ias, max_addr_bits);
+	cfg->oas = min(cfg->oas, max_addr_bits);
 }
 
 static struct arm_lpae_io_pgtable *
@@ -784,6 +809,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	case 48:
 		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
 		break;
+	case 52:
+		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
 	default:
 		goto out_free_data;
 	}
@@ -891,6 +919,9 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	case 48:
 		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
 		break;
+	case 52:
+		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
 	default:
 		goto out_free_data;
 	}

drivers/iommu/io-pgtable.h

@@ -119,7 +119,7 @@ struct io_pgtable_cfg {
 struct io_pgtable_ops {
 	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot);
-	int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
+	size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
 			size_t size);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
 				    unsigned long iova);

drivers/iommu/iommu.c

@@ -1573,10 +1573,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 
 	if (unlikely(ops->unmap == NULL ||
 		     domain->pgsize_bitmap == 0UL))
-		return -ENODEV;
+		return 0;
 
 	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
-		return -EINVAL;
+		return 0;
 
 	/* find out the minimum page size supported */
 	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
@@ -1589,7 +1589,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	if (!IS_ALIGNED(iova | size, min_pagesz)) {
 		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
 		       iova, size, min_pagesz);
-		return -EINVAL;
+		return 0;
 	}
 
 	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);

drivers/iommu/mtk_iommu.c

@@ -60,7 +60,7 @@
 	(((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data))
 
 #define REG_MMU_IVRP_PADDR			0x114
-#define F_MMU_IVRP_PA_SET(pa, ext)		(((pa) >> 1) | ((!!(ext)) << 31))
+
 #define REG_MMU_VLD_PA_RNG			0x118
 #define F_MMU_VLD_PA_RNG(EA, SA)		(((EA) << 8) | (SA))
 
@@ -539,8 +539,13 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
 	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
 
-	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
-		       data->base + REG_MMU_IVRP_PADDR);
+	if (data->m4u_plat == M4U_MT8173)
+		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
+	else
+		regval = lower_32_bits(data->protect_base) |
+			 upper_32_bits(data->protect_base);
+	writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);
+
 	if (data->enable_4GB && data->m4u_plat != M4U_MT8173) {
 		/*
 		 * If 4GB mode is enabled, the validate PA range is from
@@ -695,6 +700,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
 	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
 	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
 	reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
+	reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
 	clk_disable_unprepare(data->bclk);
 	return 0;
 }
@@ -717,8 +723,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
 	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
 	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
-	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
-		       base + REG_MMU_IVRP_PADDR);
+	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	if (data->m4u_dom)
 		writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0],
 		       base + REG_MMU_PT_BASE_ADDR);

drivers/iommu/mtk_iommu.h

@@ -32,6 +32,7 @@ struct mtk_iommu_suspend_reg {
 	u32				ctrl_reg;
 	u32				int_control0;
 	u32				int_main_control;
+	u32				ivrp_paddr;
 };
 
 enum mtk_iommu_plat {

drivers/iommu/mtk_iommu_v1.c

@@ -417,20 +417,12 @@ static int mtk_iommu_create_mapping(struct device *dev,
 		m4udev->archdata.iommu = mtk_mapping;
 	}
 
-	ret = arm_iommu_attach_device(dev, mtk_mapping);
-	if (ret)
-		goto err_release_mapping;
-
 	return 0;
-
-err_release_mapping:
-	arm_iommu_release_mapping(mtk_mapping);
-	m4udev->archdata.iommu = NULL;
-	return ret;
 }
 
 static int mtk_iommu_add_device(struct device *dev)
 {
+	struct dma_iommu_mapping *mtk_mapping;
 	struct of_phandle_args iommu_spec;
 	struct of_phandle_iterator it;
 	struct mtk_iommu_data *data;
@@ -451,15 +443,30 @@ static int mtk_iommu_add_device(struct device *dev)
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return -ENODEV; /* Not a iommu client device */
 
-	data = dev->iommu_fwspec->iommu_priv;
-	iommu_device_link(&data->iommu, dev);
-
-	group = iommu_group_get_for_dev(dev);
+	/*
+	 * This is a short-term bodge because the ARM DMA code doesn't
+	 * understand multi-device groups, but we have to call into it
+	 * successfully (and not just rely on a normal IOMMU API attach
+	 * here) in order to set the correct DMA API ops on @dev.
+	 */
+	group = iommu_group_alloc();
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
+	err = iommu_group_add_device(group, dev);
 	iommu_group_put(group);
-	return 0;
+	if (err)
+		return err;
+
+	data = dev->iommu_fwspec->iommu_priv;
+	mtk_mapping = data->dev->archdata.iommu;
+	err = arm_iommu_attach_device(dev, mtk_mapping);
+	if (err) {
+		iommu_group_remove_device(dev);
+		return err;
+	}
+
+	return iommu_device_link(&data->iommu, dev);;
 }
 
 static void mtk_iommu_remove_device(struct device *dev)
@@ -476,24 +483,6 @@ static void mtk_iommu_remove_device(struct device *dev)
 	iommu_fwspec_free(dev);
 }
 
-static struct iommu_group *mtk_iommu_device_group(struct device *dev)
-{
-	struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
-
-	if (!data)
-		return ERR_PTR(-ENODEV);
-
-	/* All the client devices are in the same m4u iommu-group */
-	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_hw_init(const struct mtk_iommu_data *data)
 {
 	u32 regval;
@@ -546,7 +535,6 @@ static struct iommu_ops mtk_iommu_ops = {
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
 	.remove_device	= mtk_iommu_remove_device,
-	.device_group	= mtk_iommu_device_group,
 	.pgsize_bitmap	= ~0UL << MT2701_IOMMU_PAGE_SHIFT,
 };
 

drivers/iommu/omap-iommu.c

@@ -1536,7 +1536,7 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev)
 	struct iommu_group *group = ERR_PTR(-EINVAL);
 
 	if (arch_data->iommu_dev)
-		group = arch_data->iommu_dev->group;
+		group = iommu_group_ref_get(arch_data->iommu_dev->group);
 
 	return group;
 }

drivers/irqchip/irq-gic-v3-its.c

@@ -3612,7 +3612,8 @@ static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header,
 		return -ENOMEM;
 	}
 
-	err = iort_register_domain_token(its_entry->translation_id, dom_handle);
+	err = iort_register_domain_token(its_entry->translation_id, res.start,
+					 dom_handle);
 	if (err) {
 		pr_err("ITS@%pa: Unable to register GICv3 ITS domain token (ITS ID %d) to IORT\n",
 		       &res.start, its_entry->translation_id);

include/linux/acpi_iort.h

@@ -26,7 +26,8 @@
 #define IORT_IRQ_MASK(irq)		(irq & 0xffffffffULL)
 #define IORT_IRQ_TRIGGER_MASK(irq)	((irq >> 32) & 0xffffffffULL)
 
-int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node);
+int iort_register_domain_token(int trans_id, phys_addr_t base,
+			       struct fwnode_handle *fw_node);
 void iort_deregister_domain_token(int trans_id);
 struct fwnode_handle *iort_find_domain_token(int trans_id);
 #ifdef CONFIG_ACPI_IORT
@@ -38,6 +39,7 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 /* IOMMU interface */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
 const struct iommu_ops *iort_iommu_configure(struct device *dev);
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 #else
 static inline void acpi_iort_init(void) { }
 static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
@@ -52,6 +54,9 @@ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 static inline const struct iommu_ops *iort_iommu_configure(
 				      struct device *dev)
 { return NULL; }
+static inline
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{ return 0; }
 #endif
 
 #endif /* __ACPI_IORT_H__ */

include/linux/intel-iommu.h

@@ -209,12 +209,12 @@
 #define DMA_FECTL_IM (((u32)1) << 31)
 
 /* FSTS_REG */
-#define DMA_FSTS_PPF ((u32)2)
-#define DMA_FSTS_PFO ((u32)1)
-#define DMA_FSTS_IQE (1 << 4)
-#define DMA_FSTS_ICE (1 << 5)
-#define DMA_FSTS_ITE (1 << 6)
-#define DMA_FSTS_PRO (1 << 7)
+#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */
+#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */
+#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */
+#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */
+#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */
+#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */
 #define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff)
 
 /* FRCD_REG, 32 bits access */

include/linux/iommu.h

@@ -465,23 +465,23 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return -ENODEV;
 }
 
-static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			      size_t size)
+static inline size_t iommu_unmap(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
 {
-	return -ENODEV;
+	return 0;
 }
 
-static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova,
-				   int gfp_order)
+static inline size_t iommu_unmap_fast(struct iommu_domain *domain,
+				      unsigned long iova, int gfp_order)
 {
-	return -ENODEV;
+	return 0;
 }
 
 static inline size_t iommu_map_sg(struct iommu_domain *domain,
 				  unsigned long iova, struct scatterlist *sg,
 				  unsigned int nents, int prot)
 {
-	return -ENODEV;
+	return 0;
 }
 
 static inline void iommu_flush_tlb_all(struct iommu_domain *domain)