diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 43c31e9..22d7b51 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2274,23 +2274,39 @@
 
 	ivrs_ioapic	[HW,X86-64]
 			Provide an override to the IOAPIC-ID<->DEVICE-ID
-			mapping provided in the IVRS ACPI table. For
-			example, to map IOAPIC-ID decimal 10 to
-			PCI device 00:14.0 write the parameter as:
+			mapping provided in the IVRS ACPI table.
+			By default, PCI segment is 0, and can be omitted.
+			For example:
+			* To map IOAPIC-ID decimal 10 to PCI device 00:14.0
+			  write the parameter as:
 				ivrs_ioapic[10]=00:14.0
+			* To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
+			  PCI device 00:14.0 write the parameter as:
+				ivrs_ioapic[10]=0001:00:14.0
 
 	ivrs_hpet	[HW,X86-64]
 			Provide an override to the HPET-ID<->DEVICE-ID
-			mapping provided in the IVRS ACPI table. For
-			example, to map HPET-ID decimal 0 to
-			PCI device 00:14.0 write the parameter as:
+			mapping provided in the IVRS ACPI table.
+			By default, PCI segment is 0, and can be omitted.
+			For example:
+			* To map HPET-ID decimal 0 to PCI device 00:14.0
+			  write the parameter as:
 				ivrs_hpet[0]=00:14.0
+			* To map HPET-ID decimal 10 to PCI segment 0x1 and
+			  PCI device 00:14.0 write the parameter as:
+				ivrs_ioapic[10]=0001:00:14.0
 
 	ivrs_acpihid	[HW,X86-64]
 			Provide an override to the ACPI-HID:UID<->DEVICE-ID
-			mapping provided in the IVRS ACPI table. For
-			example, to map UART-HID:UID AMD0020:0 to
-			PCI device 00:14.5 write the parameter as:
+			mapping provided in the IVRS ACPI table.
+
+			For example, to map UART-HID:UID AMD0020:0 to
+			PCI segment 0x1 and PCI device ID 00:14.5,
+			write the parameter as:
+				ivrs_acpihid[0001:00:14.5]=AMD0020:0
+
+			By default, PCI segment is 0, and can be omitted.
+			For example, PCI device 00:14.5 write the parameter as:
 				ivrs_acpihid[00:14.5]=AMD0020:0
 
 	js=		[HW,JOY] Analog joystick
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index 76fc2c0f..9066e6d 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -42,6 +42,7 @@
               - qcom,sdx55-smmu-500
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
+              - qcom,sm6375-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml
index 2ae3bba..fee0241b 100644
--- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml
+++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml
@@ -101,6 +101,10 @@
     items:
       - const: bclk
 
+  mediatek,infracfg:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: The phandle to the mediatek infracfg syscon
+
   mediatek,larbs:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     minItems: 1
@@ -167,6 +171,18 @@
       required:
         - power-domains
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - mediatek,mt2712-m4u
+              - mediatek,mt8173-m4u
+
+    then:
+      required:
+        - mediatek,infracfg
+
   - if: # The IOMMUs don't have larbs.
       not:
         properties:
@@ -191,6 +207,7 @@
             interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_LOW>;
             clocks = <&infracfg CLK_INFRA_M4U>;
             clock-names = "bclk";
+            mediatek,infracfg = <&infracfg>;
             mediatek,larbs = <&larb0>, <&larb1>, <&larb2>,
                              <&larb3>, <&larb4>, <&larb5>;
             #iommu-cells = <1>;
diff --git a/MAINTAINERS b/MAINTAINERS
index 89e42cf..c8375b6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10233,7 +10233,6 @@
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 F:	drivers/iommu/intel/
-F:	include/linux/intel-iommu.h
 F:	include/linux/intel-svm.h
 
 INTEL IOP-ADMA DMA DRIVER
@@ -10605,9 +10604,20 @@
 F:	fs/iomap/
 F:	include/linux/iomap.h
 
-IOMMU DRIVERS
+IOMMU DMA-API LAYER
+M:	Robin Murphy <robin.murphy@arm.com>
+L:	iommu@lists.linux.dev
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+F:	drivers/iommu/dma-iommu.c
+F:	drivers/iommu/iova.c
+F:	include/linux/dma-iommu.h
+F:	include/linux/iova.h
+
+IOMMU SUBSYSTEM
 M:	Joerg Roedel <joro@8bytes.org>
 M:	Will Deacon <will@kernel.org>
+R:	Robin Murphy <robin.murphy@arm.com>
 L:	iommu@lists.linux.dev
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 0c1154a..3bacd93 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -6,7 +6,6 @@
  * Copyright (c) 2006-2009, Intel Corporation
  */
 
-#include <linux/intel-iommu.h>
 #include <linux/init_task.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
@@ -516,17 +515,3 @@
 
 	return dmar_tbl;
 }
-
-int tboot_force_iommu(void)
-{
-	if (!tboot_enabled())
-		return 0;
-
-	if (no_iommu || dmar_disabled)
-		pr_warn("Forcing Intel-IOMMU to enabled\n");
-
-	dmar_disabled = 0;
-	no_iommu = 0;
-
-	return 1;
-}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 33560bf..79a8a74 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -41,7 +41,6 @@
 #include <linux/mman.h>
 #include <linux/highmem.h>
 #include <linux/iommu.h>
-#include <linux/intel-iommu.h>
 #include <linux/cpufreq.h>
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index f2f8f05..ca2aed8 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -788,6 +788,294 @@
 }
 
 #ifdef CONFIG_IOMMU_API
+static void iort_rmr_free(struct device *dev,
+			  struct iommu_resv_region *region)
+{
+	struct iommu_iort_rmr_data *rmr_data;
+
+	rmr_data = container_of(region, struct iommu_iort_rmr_data, rr);
+	kfree(rmr_data->sids);
+	kfree(rmr_data);
+}
+
+static struct iommu_iort_rmr_data *iort_rmr_alloc(
+					struct acpi_iort_rmr_desc *rmr_desc,
+					int prot, enum iommu_resv_type type,
+					u32 *sids, u32 num_sids)
+{
+	struct iommu_iort_rmr_data *rmr_data;
+	struct iommu_resv_region *region;
+	u32 *sids_copy;
+	u64 addr = rmr_desc->base_address, size = rmr_desc->length;
+
+	rmr_data = kmalloc(sizeof(*rmr_data), GFP_KERNEL);
+	if (!rmr_data)
+		return NULL;
+
+	/* Create a copy of SIDs array to associate with this rmr_data */
+	sids_copy = kmemdup(sids, num_sids * sizeof(*sids), GFP_KERNEL);
+	if (!sids_copy) {
+		kfree(rmr_data);
+		return NULL;
+	}
+	rmr_data->sids = sids_copy;
+	rmr_data->num_sids = num_sids;
+
+	if (!IS_ALIGNED(addr, SZ_64K) || !IS_ALIGNED(size, SZ_64K)) {
+		/* PAGE align base addr and size */
+		addr &= PAGE_MASK;
+		size = PAGE_ALIGN(size + offset_in_page(rmr_desc->base_address));
+
+		pr_err(FW_BUG "RMR descriptor[0x%llx - 0x%llx] not aligned to 64K, continue with [0x%llx - 0x%llx]\n",
+		       rmr_desc->base_address,
+		       rmr_desc->base_address + rmr_desc->length - 1,
+		       addr, addr + size - 1);
+	}
+
+	region = &rmr_data->rr;
+	INIT_LIST_HEAD(&region->list);
+	region->start = addr;
+	region->length = size;
+	region->prot = prot;
+	region->type = type;
+	region->free = iort_rmr_free;
+
+	return rmr_data;
+}
+
+static void iort_rmr_desc_check_overlap(struct acpi_iort_rmr_desc *desc,
+					u32 count)
+{
+	int i, j;
+
+	for (i = 0; i < count; i++) {
+		u64 end, start = desc[i].base_address, length = desc[i].length;
+
+		if (!length) {
+			pr_err(FW_BUG "RMR descriptor[0x%llx] with zero length, continue anyway\n",
+			       start);
+			continue;
+		}
+
+		end = start + length - 1;
+
+		/* Check for address overlap */
+		for (j = i + 1; j < count; j++) {
+			u64 e_start = desc[j].base_address;
+			u64 e_end = e_start + desc[j].length - 1;
+
+			if (start <= e_end && end >= e_start)
+				pr_err(FW_BUG "RMR descriptor[0x%llx - 0x%llx] overlaps, continue anyway\n",
+				       start, end);
+		}
+	}
+}
+
+/*
+ * Please note, we will keep the already allocated RMR reserve
+ * regions in case of a memory allocation failure.
+ */
+static void iort_get_rmrs(struct acpi_iort_node *node,
+			  struct acpi_iort_node *smmu,
+			  u32 *sids, u32 num_sids,
+			  struct list_head *head)
+{
+	struct acpi_iort_rmr *rmr = (struct acpi_iort_rmr *)node->node_data;
+	struct acpi_iort_rmr_desc *rmr_desc;
+	int i;
+
+	rmr_desc = ACPI_ADD_PTR(struct acpi_iort_rmr_desc, node,
+				rmr->rmr_offset);
+
+	iort_rmr_desc_check_overlap(rmr_desc, rmr->rmr_count);
+
+	for (i = 0; i < rmr->rmr_count; i++, rmr_desc++) {
+		struct iommu_iort_rmr_data *rmr_data;
+		enum iommu_resv_type type;
+		int prot = IOMMU_READ | IOMMU_WRITE;
+
+		if (rmr->flags & ACPI_IORT_RMR_REMAP_PERMITTED)
+			type = IOMMU_RESV_DIRECT_RELAXABLE;
+		else
+			type = IOMMU_RESV_DIRECT;
+
+		if (rmr->flags & ACPI_IORT_RMR_ACCESS_PRIVILEGE)
+			prot |= IOMMU_PRIV;
+
+		/* Attributes 0x00 - 0x03 represents device memory */
+		if (ACPI_IORT_RMR_ACCESS_ATTRIBUTES(rmr->flags) <=
+				ACPI_IORT_RMR_ATTR_DEVICE_GRE)
+			prot |= IOMMU_MMIO;
+		else if (ACPI_IORT_RMR_ACCESS_ATTRIBUTES(rmr->flags) ==
+				ACPI_IORT_RMR_ATTR_NORMAL_IWB_OWB)
+			prot |= IOMMU_CACHE;
+
+		rmr_data = iort_rmr_alloc(rmr_desc, prot, type,
+					  sids, num_sids);
+		if (!rmr_data)
+			return;
+
+		list_add_tail(&rmr_data->rr.list, head);
+	}
+}
+
+static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start,
+				u32 new_count)
+{
+	u32 *new_sids;
+	u32 total_count = count + new_count;
+	int i;
+
+	new_sids = krealloc_array(sids, count + new_count,
+				  sizeof(*new_sids), GFP_KERNEL);
+	if (!new_sids)
+		return NULL;
+
+	for (i = count; i < total_count; i++)
+		new_sids[i] = id_start++;
+
+	return new_sids;
+}
+
+static bool iort_rmr_has_dev(struct device *dev, u32 id_start,
+			     u32 id_count)
+{
+	int i;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	/*
+	 * Make sure the kernel has preserved the boot firmware PCIe
+	 * configuration. This is required to ensure that the RMR PCIe
+	 * StreamIDs are still valid (Refer: ARM DEN 0049E.d Section 3.1.1.5).
+	 */
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		struct pci_host_bridge *host = pci_find_host_bridge(pdev->bus);
+
+		if (!host->preserve_config)
+			return false;
+	}
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		if (fwspec->ids[i] >= id_start &&
+		    fwspec->ids[i] <= id_start + id_count)
+			return true;
+	}
+
+	return false;
+}
+
+static void iort_node_get_rmr_info(struct acpi_iort_node *node,
+				   struct acpi_iort_node *iommu,
+				   struct device *dev, struct list_head *head)
+{
+	struct acpi_iort_node *smmu = NULL;
+	struct acpi_iort_rmr *rmr;
+	struct acpi_iort_id_mapping *map;
+	u32 *sids = NULL;
+	u32 num_sids = 0;
+	int i;
+
+	if (!node->mapping_offset || !node->mapping_count) {
+		pr_err(FW_BUG "Invalid ID mapping, skipping RMR node %p\n",
+		       node);
+		return;
+	}
+
+	rmr = (struct acpi_iort_rmr *)node->node_data;
+	if (!rmr->rmr_offset || !rmr->rmr_count)
+		return;
+
+	map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, node,
+			   node->mapping_offset);
+
+	/*
+	 * Go through the ID mappings and see if we have a match for SMMU
+	 * and dev(if !NULL). If found, get the sids for the Node.
+	 * Please note, id_count is equal to the number of IDs  in the
+	 * range minus one.
+	 */
+	for (i = 0; i < node->mapping_count; i++, map++) {
+		struct acpi_iort_node *parent;
+
+		if (!map->id_count)
+			continue;
+
+		parent = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+				      map->output_reference);
+		if (parent != iommu)
+			continue;
+
+		/* If dev is valid, check RMR node corresponds to the dev SID */
+		if (dev && !iort_rmr_has_dev(dev, map->output_base,
+					     map->id_count))
+			continue;
+
+		/* Retrieve SIDs associated with the Node. */
+		sids = iort_rmr_alloc_sids(sids, num_sids, map->output_base,
+					   map->id_count + 1);
+		if (!sids)
+			return;
+
+		num_sids += map->id_count + 1;
+	}
+
+	if (!sids)
+		return;
+
+	iort_get_rmrs(node, smmu, sids, num_sids, head);
+	kfree(sids);
+}
+
+static void iort_find_rmrs(struct acpi_iort_node *iommu, struct device *dev,
+			   struct list_head *head)
+{
+	struct acpi_table_iort *iort;
+	struct acpi_iort_node *iort_node, *iort_end;
+	int i;
+
+	/* Only supports ARM DEN 0049E.d onwards */
+	if (iort_table->revision < 5)
+		return;
+
+	iort = (struct acpi_table_iort *)iort_table;
+
+	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 (WARN_TAINT(iort_node >= iort_end, TAINT_FIRMWARE_WORKAROUND,
+			       "IORT node pointer overflows, bad table!\n"))
+			return;
+
+		if (iort_node->type == ACPI_IORT_NODE_RMR)
+			iort_node_get_rmr_info(iort_node, iommu, dev, head);
+
+		iort_node = ACPI_ADD_PTR(struct acpi_iort_node, iort_node,
+					 iort_node->length);
+	}
+}
+
+/*
+ * Populate the RMR list associated with a given IOMMU and dev(if provided).
+ * If dev is NULL, the function populates all the RMRs associated with the
+ * given IOMMU.
+ */
+static void iort_iommu_rmr_get_resv_regions(struct fwnode_handle *iommu_fwnode,
+					    struct device *dev,
+					    struct list_head *head)
+{
+	struct acpi_iort_node *iommu;
+
+	iommu = iort_get_iort_node(iommu_fwnode);
+	if (!iommu)
+		return;
+
+	iort_find_rmrs(iommu, dev, head);
+}
+
 static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
 {
 	struct acpi_iort_node *iommu;
@@ -806,27 +1094,22 @@
 	return NULL;
 }
 
-/**
- * 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.
+/*
+ * Retrieve platform specific HW MSI reserve regions.
+ * The ITS interrupt translation spaces (ITS_base + SZ_64K, SZ_64K)
+ * associated with the device are the HW MSI reserved regions.
  */
-int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+static void iort_iommu_msi_get_resv_regions(struct device *dev,
+					    struct list_head *head)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct acpi_iort_its_group *its;
 	struct acpi_iort_node *iommu_node, *its_node = NULL;
-	int i, resv = 0;
+	int i;
 
 	iommu_node = iort_get_msi_resv_iommu(dev);
 	if (!iommu_node)
-		return 0;
+		return;
 
 	/*
 	 * Current logic to reserve ITS regions relies on HW topologies
@@ -846,7 +1129,7 @@
 	}
 
 	if (!its_node)
-		return 0;
+		return;
 
 	/* Move to ITS specific data */
 	its = (struct acpi_iort_its_group *)its_node->node_data;
@@ -860,16 +1143,53 @@
 
 			region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K,
 							 prot, IOMMU_RESV_MSI);
-			if (region) {
+			if (region)
 				list_add_tail(&region->list, head);
-				resv++;
-			}
 		}
 	}
-
-	return (resv == its->its_count) ? resv : -ENODEV;
 }
 
+/**
+ * iort_iommu_get_resv_regions - Generic helper to retrieve reserved regions.
+ * @dev: Device from iommu_get_resv_regions()
+ * @head: Reserved region list from iommu_get_resv_regions()
+ */
+void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	iort_iommu_msi_get_resv_regions(dev, head);
+	iort_iommu_rmr_get_resv_regions(fwspec->iommu_fwnode, dev, head);
+}
+
+/**
+ * iort_get_rmr_sids - Retrieve IORT RMR node reserved regions with
+ *                     associated StreamIDs information.
+ * @iommu_fwnode: fwnode associated with IOMMU
+ * @head: Resereved region list
+ */
+void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode,
+		       struct list_head *head)
+{
+	iort_iommu_rmr_get_resv_regions(iommu_fwnode, NULL, head);
+}
+EXPORT_SYMBOL_GPL(iort_get_rmr_sids);
+
+/**
+ * iort_put_rmr_sids - Free memory allocated for RMR reserved regions.
+ * @iommu_fwnode: fwnode associated with IOMMU
+ * @head: Resereved region list
+ */
+void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode,
+		       struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		entry->free(NULL, entry);
+}
+EXPORT_SYMBOL_GPL(iort_put_rmr_sids);
+
 static inline bool iort_iommu_driver_enabled(u8 type)
 {
 	switch (type) {
@@ -1034,8 +1354,8 @@
 }
 
 #else
-int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
-{ return 0; }
+void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head)
+{ }
 int iort_iommu_configure_id(struct device *dev, const u32 *input_id)
 { return -ENODEV; }
 #endif
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index fe7e210..bf6716f 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -20,7 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/pagemap.h>
 #include <linux/agp_backend.h>
-#include <linux/intel-iommu.h>
+#include <linux/iommu.h>
 #include <linux/delay.h>
 #include <asm/smp.h>
 #include "agp.h"
@@ -573,18 +573,15 @@
  */
 static inline int needs_ilk_vtd_wa(void)
 {
-#ifdef CONFIG_INTEL_IOMMU
 	const unsigned short gpu_devid = intel_private.pcidev->device;
 
-	/* Query intel_iommu to see if we need the workaround. Presumably that
-	 * was loaded first.
+	/*
+	 * Query iommu subsystem to see if we need the workaround. Presumably
+	 * that was loaded first.
 	 */
-	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG ||
-	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
-	     intel_iommu_gfx_mapped)
-		return 1;
-#endif
-	return 0;
+	return ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG ||
+		 gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
+		device_iommu_mapped(&intel_private.pcidev->dev));
 }
 
 static bool intel_gtt_can_wc(void)
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a0f84cb..fc5d948 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -27,7 +27,6 @@
 #include <acpi/video.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
-#include <linux/intel-iommu.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/dma-resv.h>
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index b7b2c14..cd75b0c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -6,7 +6,6 @@
 
 #include <linux/dma-resv.h>
 #include <linux/highmem.h>
-#include <linux/intel-iommu.h>
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c79a0df..50bc696 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -144,6 +144,32 @@
 	select IRQ_MSI_IOMMU
 	select NEED_SG_DMA_LENGTH
 
+config IOMMU_DMA_PCI_SAC
+	bool "Enable 64-bit legacy PCI optimisation by default"
+	depends on IOMMU_DMA
+	help
+	  Enable by default an IOMMU optimisation for 64-bit legacy PCI devices,
+	  wherein the DMA API layer will always first try to allocate a 32-bit
+	  DMA address suitable for a single address cycle, before falling back
+	  to allocating from the device's full usable address range. If your
+	  system has 64-bit legacy PCI devices in 32-bit slots where using dual
+	  address cycles reduces DMA throughput significantly, this may be
+	  beneficial to overall performance.
+
+	  If you have a modern PCI Express based system, this feature mostly just
+	  represents extra overhead in the allocation path for no practical
+	  benefit, and it should usually be preferable to say "n" here.
+
+	  However, beware that this feature has also historically papered over
+	  bugs where the IOMMU address width and/or device DMA mask is not set
+	  correctly. If device DMA problems and IOMMU faults start occurring
+	  after disabling this option, it is almost certainly indicative of a
+	  latent driver or firmware/BIOS bug, which would previously have only
+	  manifested with several gigabytes worth of concurrent DMA mappings.
+
+	  If this option is not set, the feature can still be re-enabled at
+	  boot time with the "iommu.forcedac=0" command-line argument.
+
 # Shared Virtual Addressing
 config IOMMU_SVA
 	bool
@@ -363,6 +389,16 @@
 	  When running on a Qualcomm platform that has the custom variant
 	  of the ARM SMMU, this needs to be built into the SMMU driver.
 
+config ARM_SMMU_QCOM_DEBUG
+	bool "ARM SMMU QCOM implementation defined debug support"
+	depends on ARM_SMMU_QCOM
+	help
+	  Support for implementation specific debug features in ARM SMMU
+	  hardware found in QTI platforms.
+
+	  Say Y here to enable debug for issues such as TLB sync timeouts
+	  which requires implementation defined register dumps.
+
 config ARM_SMMU_V3
 	tristate "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
 	depends on ARM64
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 1ab3107..84e5bb1 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -13,12 +13,13 @@
 
 extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_apply_erratum_63(u16 devid);
+extern void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid);
 extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
 extern void amd_iommu_uninit_devices(void);
 extern void amd_iommu_init_notifier(void);
 extern int amd_iommu_init_api(void);
+extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
@@ -114,10 +115,17 @@
 	amd_iommu_domain_set_pt_root(domain, 0);
 }
 
+static inline int get_pci_sbdf_id(struct pci_dev *pdev)
+{
+	int seg = pci_domain_nr(pdev->bus);
+	u16 devid = pci_dev_id(pdev);
+
+	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
+}
 
 extern bool translation_pre_enabled(struct amd_iommu *iommu);
 extern bool amd_iommu_is_attach_deferred(struct device *dev);
-extern int __init add_special_device(u8 type, u8 id, u16 *devid,
+extern int __init add_special_device(u8 type, u8 id, u32 *devid,
 				     bool cmd_line);
 
 #ifdef CONFIG_DMI
@@ -128,4 +136,10 @@
 
 extern void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
 					 u64 *root, int mode);
+extern struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
+
+extern u64 amd_iommu_efr;
+extern u64 amd_iommu_efr2;
+
+extern bool amd_iommu_snp_en;
 #endif
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 72d0f5e2..5b1019d 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -67,6 +67,7 @@
 #define MMIO_INTCAPXT_EVT_OFFSET	0x0170
 #define MMIO_INTCAPXT_PPR_OFFSET	0x0178
 #define MMIO_INTCAPXT_GALOG_OFFSET	0x0180
+#define MMIO_EXT_FEATURES2	0x01A0
 #define MMIO_CMD_HEAD_OFFSET	0x2000
 #define MMIO_CMD_TAIL_OFFSET	0x2008
 #define MMIO_EVT_HEAD_OFFSET	0x2010
@@ -102,6 +103,12 @@
 #define FEATURE_GLXVAL_SHIFT	14
 #define FEATURE_GLXVAL_MASK	(0x03ULL << FEATURE_GLXVAL_SHIFT)
 
+/* Extended Feature 2 Bits */
+#define FEATURE_SNPAVICSUP_SHIFT	5
+#define FEATURE_SNPAVICSUP_MASK		(0x07ULL << FEATURE_SNPAVICSUP_SHIFT)
+#define FEATURE_SNPAVICSUP_GAM(x) \
+	((x & FEATURE_SNPAVICSUP_MASK) >> FEATURE_SNPAVICSUP_SHIFT == 0x1)
+
 /* Note:
  * The current driver only support 16-bit PASID.
  * Currently, hardware only implement upto 16-bit PASID
@@ -143,27 +150,28 @@
 #define EVENT_FLAG_I		0x008
 
 /* feature control bits */
-#define CONTROL_IOMMU_EN        0x00ULL
-#define CONTROL_HT_TUN_EN       0x01ULL
-#define CONTROL_EVT_LOG_EN      0x02ULL
-#define CONTROL_EVT_INT_EN      0x03ULL
-#define CONTROL_COMWAIT_EN      0x04ULL
-#define CONTROL_INV_TIMEOUT	0x05ULL
-#define CONTROL_PASSPW_EN       0x08ULL
-#define CONTROL_RESPASSPW_EN    0x09ULL
-#define CONTROL_COHERENT_EN     0x0aULL
-#define CONTROL_ISOC_EN         0x0bULL
-#define CONTROL_CMDBUF_EN       0x0cULL
-#define CONTROL_PPRLOG_EN       0x0dULL
-#define CONTROL_PPRINT_EN       0x0eULL
-#define CONTROL_PPR_EN          0x0fULL
-#define CONTROL_GT_EN           0x10ULL
-#define CONTROL_GA_EN           0x11ULL
-#define CONTROL_GAM_EN          0x19ULL
-#define CONTROL_GALOG_EN        0x1CULL
-#define CONTROL_GAINT_EN        0x1DULL
-#define CONTROL_XT_EN           0x32ULL
-#define CONTROL_INTCAPXT_EN     0x33ULL
+#define CONTROL_IOMMU_EN	0
+#define CONTROL_HT_TUN_EN	1
+#define CONTROL_EVT_LOG_EN	2
+#define CONTROL_EVT_INT_EN	3
+#define CONTROL_COMWAIT_EN	4
+#define CONTROL_INV_TIMEOUT	5
+#define CONTROL_PASSPW_EN	8
+#define CONTROL_RESPASSPW_EN	9
+#define CONTROL_COHERENT_EN	10
+#define CONTROL_ISOC_EN		11
+#define CONTROL_CMDBUF_EN	12
+#define CONTROL_PPRLOG_EN	13
+#define CONTROL_PPRINT_EN	14
+#define CONTROL_PPR_EN		15
+#define CONTROL_GT_EN		16
+#define CONTROL_GA_EN		17
+#define CONTROL_GAM_EN		25
+#define CONTROL_GALOG_EN	28
+#define CONTROL_GAINT_EN	29
+#define CONTROL_XT_EN		50
+#define CONTROL_INTCAPXT_EN	51
+#define CONTROL_SNPAVIC_EN	61
 
 #define CTRL_INV_TO_MASK	(7 << CONTROL_INV_TIMEOUT)
 #define CTRL_INV_TO_NONE	0
@@ -445,8 +453,6 @@
 	u32 *table;
 };
 
-extern struct irq_remap_table **irq_lookup_table;
-
 /* Interrupt remapping feature used? */
 extern bool amd_iommu_irq_remap;
 
@@ -456,6 +462,16 @@
 /* kmem_cache to get tables with 128 byte alignement */
 extern struct kmem_cache *amd_iommu_irq_cache;
 
+#define PCI_SBDF_TO_SEGID(sbdf)		(((sbdf) >> 16) & 0xffff)
+#define PCI_SBDF_TO_DEVID(sbdf)		((sbdf) & 0xffff)
+#define PCI_SEG_DEVID_TO_SBDF(seg, devid)	((((u32)(seg) & 0xffff) << 16) | \
+						 ((devid) & 0xffff))
+
+/* Make iterating over all pci segment easier */
+#define for_each_pci_segment(pci_seg) \
+	list_for_each_entry((pci_seg), &amd_iommu_pci_seg_list, list)
+#define for_each_pci_segment_safe(pci_seg, next) \
+	list_for_each_entry_safe((pci_seg), (next), &amd_iommu_pci_seg_list, list)
 /*
  * Make iterating over all IOMMUs easier
  */
@@ -478,13 +494,14 @@
 struct amd_iommu_fault {
 	u64 address;    /* IO virtual address of the fault*/
 	u32 pasid;      /* Address space identifier */
-	u16 device_id;  /* Originating PCI device id */
+	u32 sbdf;	/* Originating PCI device id */
 	u16 tag;        /* PPR tag */
 	u16 flags;      /* Fault flags */
 
 };
 
 
+struct amd_iommu;
 struct iommu_domain;
 struct irq_domain;
 struct amd_irte_ops;
@@ -531,6 +548,75 @@
 };
 
 /*
+ * This structure contains information about one PCI segment in the system.
+ */
+struct amd_iommu_pci_seg {
+	/* List with all PCI segments in the system */
+	struct list_head list;
+
+	/* List of all available dev_data structures */
+	struct llist_head dev_data_list;
+
+	/* PCI segment number */
+	u16 id;
+
+	/* Largest PCI device id we expect translation requests for */
+	u16 last_bdf;
+
+	/* Size of the device table */
+	u32 dev_table_size;
+
+	/* Size of the alias table */
+	u32 alias_table_size;
+
+	/* Size of the rlookup table */
+	u32 rlookup_table_size;
+
+	/*
+	 * device table virtual address
+	 *
+	 * Pointer to the per PCI segment device table.
+	 * It is indexed by the PCI device id or the HT unit id and contains
+	 * information about the domain the device belongs to as well as the
+	 * page table root pointer.
+	 */
+	struct dev_table_entry *dev_table;
+
+	/*
+	 * The rlookup iommu table is used to find the IOMMU which is
+	 * responsible for a specific device. It is indexed by the PCI
+	 * device id.
+	 */
+	struct amd_iommu **rlookup_table;
+
+	/*
+	 * This table is used to find the irq remapping table for a given
+	 * device id quickly.
+	 */
+	struct irq_remap_table **irq_lookup_table;
+
+	/*
+	 * Pointer to a device table which the content of old device table
+	 * will be copied to. It's only be used in kdump kernel.
+	 */
+	struct dev_table_entry *old_dev_tbl_cpy;
+
+	/*
+	 * The alias table is a driver specific data structure which contains the
+	 * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
+	 * More than one device can share the same requestor id.
+	 */
+	u16 *alias_table;
+
+	/*
+	 * A list of required unity mappings we find in ACPI. It is not locked
+	 * because as runtime it is only read. It is created at ACPI table
+	 * parsing time.
+	 */
+	struct list_head unity_map;
+};
+
+/*
  * Structure where we save information about one hardware AMD IOMMU in the
  * system.
  */
@@ -567,6 +653,9 @@
 	/* Extended features */
 	u64 features;
 
+	/* Extended features 2 */
+	u64 features2;
+
 	/* IOMMUv2 */
 	bool is_iommu_v2;
 
@@ -581,7 +670,7 @@
 	u16 cap_ptr;
 
 	/* pci domain of this IOMMU */
-	u16 pci_seg;
+	struct amd_iommu_pci_seg *pci_seg;
 
 	/* start of exclusion range of that IOMMU */
 	u64 exclusion_start;
@@ -666,8 +755,8 @@
 	struct list_head list;
 	u8 uid[ACPIHID_UID_LEN];
 	u8 hid[ACPIHID_HID_LEN];
-	u16 devid;
-	u16 root_devid;
+	u32 devid;
+	u32 root_devid;
 	bool cmd_line;
 	struct iommu_group *group;
 };
@@ -675,7 +764,7 @@
 struct devid_map {
 	struct list_head list;
 	u8 id;
-	u16 devid;
+	u32 devid;
 	bool cmd_line;
 };
 
@@ -689,7 +778,7 @@
 	struct list_head list;		  /* For domain->dev_list */
 	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
-	struct pci_dev *pdev;
+	struct device *dev;
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	struct {
@@ -710,6 +799,12 @@
 extern struct list_head acpihid_map;
 
 /*
+ * List with all PCI segments in the system. This list is not locked because
+ * it is only written at driver initialization time
+ */
+extern struct list_head amd_iommu_pci_seg_list;
+
+/*
  * List with all IOMMUs in the system. This list is not locked because it is
  * only written and read at driver initialization or suspend time
  */
@@ -749,38 +844,12 @@
 };
 
 /*
- * List of all unity mappings. It is not locked because as runtime it is only
- * read. It is created at ACPI table parsing time.
- */
-extern struct list_head amd_iommu_unity_map;
-
-/*
  * Data structures for device handling
  */
 
-/*
- * Device table used by hardware. Read and write accesses by software are
- * locked with the amd_iommu_pd_table lock.
- */
-extern struct dev_table_entry *amd_iommu_dev_table;
-
-/*
- * Alias table to find requestor ids to device ids. Not locked because only
- * read on runtime.
- */
-extern u16 *amd_iommu_alias_table;
-
-/*
- * Reverse lookup table to find the IOMMU which translates a specific device.
- */
-extern struct amd_iommu **amd_iommu_rlookup_table;
-
 /* size of the dma_ops aperture as power of 2 */
 extern unsigned amd_iommu_aperture_order;
 
-/* largest PCI device id we expect translation requests for */
-extern u16 amd_iommu_last_bdf;
-
 /* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
@@ -913,6 +982,7 @@
 
 struct amd_ir_data {
 	u32 cached_ga_tag;
+	struct amd_iommu *iommu;
 	struct irq_2_irte irq_2_irte;
 	struct msi_msg msi_entry;
 	void *entry;    /* Pointer to union irte or struct irte_ga */
@@ -930,9 +1000,9 @@
 
 struct amd_irte_ops {
 	void (*prepare)(void *, u32, bool, u8, u32, int);
-	void (*activate)(void *, u16, u16);
-	void (*deactivate)(void *, u16, u16);
-	void (*set_affinity)(void *, u16, u16, u8, u32);
+	void (*activate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*deactivate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*set_affinity)(struct amd_iommu *iommu, void *, u16, u16, u8, u32);
 	void *(*get)(struct irq_remap_table *, int);
 	void (*set_allocated)(struct irq_remap_table *, int);
 	bool (*is_allocated)(struct irq_remap_table *, int);
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 1d08f87..fdc6423 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -84,6 +84,10 @@
 #define ACPI_DEVFLAG_ATSDIS             0x10000000
 
 #define LOOP_TIMEOUT	2000000
+
+#define IVRS_GET_SBDF_ID(seg, bus, dev, fd)	(((seg & 0xffff) << 16) | ((bus & 0xff) << 8) \
+						 | ((dev & 0x1f) << 3) | (fn & 0x7))
+
 /*
  * ACPI table definitions
  *
@@ -110,7 +114,7 @@
 
 	/* Following only valid on IVHD type 11h and 40h */
 	u64 efr_reg; /* Exact copy of MMIO_EXT_FEATURES */
-	u64 res;
+	u64 efr_reg2;
 } __attribute__((packed));
 
 /*
@@ -141,7 +145,8 @@
 	u16 length;
 	u16 devid;
 	u16 aux;
-	u64 resv;
+	u16 pci_seg;
+	u8  resv[6];
 	u64 range_start;
 	u64 range_length;
 } __attribute__((packed));
@@ -159,11 +164,15 @@
 static bool amd_iommu_force_enable __initdata;
 static int amd_iommu_target_ivhd_type;
 
-u16 amd_iommu_last_bdf;			/* largest PCI device id we have
-					   to handle */
-LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
-					   we find in ACPI */
+/* Global EFR and EFR2 registers */
+u64 amd_iommu_efr;
+u64 amd_iommu_efr2;
 
+/* SNP is enabled on the system? */
+bool amd_iommu_snp_en;
+EXPORT_SYMBOL(amd_iommu_snp_en);
+
+LIST_HEAD(amd_iommu_pci_seg_list);	/* list of all PCI segments */
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
 					   system */
 
@@ -186,47 +195,11 @@
 bool amd_iommu_force_isolation __read_mostly;
 
 /*
- * Pointer to the device table which is shared by all AMD IOMMUs
- * it is indexed by the PCI device id or the HT unit id and contains
- * information about the domain the device belongs to as well as the
- * page table root pointer.
- */
-struct dev_table_entry *amd_iommu_dev_table;
-/*
- * Pointer to a device table which the content of old device table
- * will be copied to. It's only be used in kdump kernel.
- */
-static struct dev_table_entry *old_dev_tbl_cpy;
-
-/*
- * The alias table is a driver specific data structure which contains the
- * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
- * More than one device can share the same requestor id.
- */
-u16 *amd_iommu_alias_table;
-
-/*
- * The rlookup table is used to find the IOMMU which is responsible
- * for a specific device. It is also indexed by the PCI device id.
- */
-struct amd_iommu **amd_iommu_rlookup_table;
-
-/*
- * This table is used to find the irq remapping table for a given device id
- * quickly.
- */
-struct irq_remap_table **irq_lookup_table;
-
-/*
  * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
  * to know which ones are already in use.
  */
 unsigned long *amd_iommu_pd_alloc_bitmap;
 
-static u32 dev_table_size;	/* size of the device table */
-static u32 alias_table_size;	/* size of the alias table */
-static u32 rlookup_table_size;	/* size if the rlookup table */
-
 enum iommu_init_state {
 	IOMMU_START_STATE,
 	IOMMU_IVRS_DETECTED,
@@ -256,7 +229,7 @@
 
 static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
-static void init_device_table_dma(void);
+static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg);
 
 static bool amd_iommu_pre_enabled = true;
 
@@ -281,16 +254,10 @@
 		iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
 }
 
-static inline void update_last_devid(u16 devid)
-{
-	if (devid > amd_iommu_last_bdf)
-		amd_iommu_last_bdf = devid;
-}
-
-static inline unsigned long tbl_size(int entry_size)
+static inline unsigned long tbl_size(int entry_size, int last_bdf)
 {
 	unsigned shift = PAGE_SHIFT +
-			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
+			 get_order((last_bdf + 1) * entry_size);
 
 	return 1UL << shift;
 }
@@ -300,21 +267,46 @@
 	return amd_iommus_present;
 }
 
-#ifdef CONFIG_IRQ_REMAP
-static bool check_feature_on_all_iommus(u64 mask)
+/*
+ * Iterate through all the IOMMUs to get common EFR
+ * masks among all IOMMUs and warn if found inconsistency.
+ */
+static void get_global_efr(void)
 {
-	bool ret = false;
 	struct amd_iommu *iommu;
 
 	for_each_iommu(iommu) {
-		ret = iommu_feature(iommu, mask);
-		if (!ret)
-			return false;
+		u64 tmp = iommu->features;
+		u64 tmp2 = iommu->features2;
+
+		if (list_is_first(&iommu->list, &amd_iommu_list)) {
+			amd_iommu_efr = tmp;
+			amd_iommu_efr2 = tmp2;
+			continue;
+		}
+
+		if (amd_iommu_efr == tmp &&
+		    amd_iommu_efr2 == tmp2)
+			continue;
+
+		pr_err(FW_BUG
+		       "Found inconsistent EFR/EFR2 %#llx,%#llx (global %#llx,%#llx) on iommu%d (%04x:%02x:%02x.%01x).\n",
+		       tmp, tmp2, amd_iommu_efr, amd_iommu_efr2,
+		       iommu->index, iommu->pci_seg->id,
+		       PCI_BUS_NUM(iommu->devid), PCI_SLOT(iommu->devid),
+		       PCI_FUNC(iommu->devid));
+
+		amd_iommu_efr &= tmp;
+		amd_iommu_efr2 &= tmp2;
 	}
 
-	return true;
+	pr_info("Using global IVHD EFR:%#llx, EFR2:%#llx\n", amd_iommu_efr, amd_iommu_efr2);
 }
-#endif
+
+static bool check_feature_on_all_iommus(u64 mask)
+{
+	return !!(amd_iommu_efr & mask);
+}
 
 /*
  * For IVHD type 0x11/0x40, EFR is also available via IVHD.
@@ -324,8 +316,10 @@
 static void __init early_iommu_features_init(struct amd_iommu *iommu,
 					     struct ivhd_header *h)
 {
-	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP)
+	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP) {
 		iommu->features = h->efr_reg;
+		iommu->features2 = h->efr_reg2;
+	}
 	if (amd_iommu_ivinfo & IOMMU_IVINFO_DMA_REMAP)
 		amdr_ivrs_remap_support = true;
 }
@@ -399,7 +393,7 @@
 	u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
 	u64 entry = start & PM_ADDR_MASK;
 
-	if (!iommu_feature(iommu, FEATURE_SNP))
+	if (!check_feature_on_all_iommus(FEATURE_SNP))
 		return;
 
 	/* Note:
@@ -421,10 +415,12 @@
 static void iommu_set_device_table(struct amd_iommu *iommu)
 {
 	u64 entry;
+	u32 dev_table_size = iommu->pci_seg->dev_table_size;
+	void *dev_table = (void *)get_dev_table(iommu);
 
 	BUG_ON(iommu->mmio_base == NULL);
 
-	entry = iommu_virt_to_phys(amd_iommu_dev_table);
+	entry = iommu_virt_to_phys(dev_table);
 	entry |= (dev_table_size >> 12) - 1;
 	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
 			&entry, sizeof(entry));
@@ -557,6 +553,7 @@
 {
 	u8 *p = (void *)h, *end = (void *)h;
 	struct ivhd_entry *dev;
+	int last_devid = -EINVAL;
 
 	u32 ivhd_size = get_ivhd_header_size(h);
 
@@ -573,14 +570,14 @@
 		switch (dev->type) {
 		case IVHD_DEV_ALL:
 			/* Use maximum BDF value for DEV_ALL */
-			update_last_devid(0xffff);
-			break;
+			return 0xffff;
 		case IVHD_DEV_SELECT:
 		case IVHD_DEV_RANGE_END:
 		case IVHD_DEV_ALIAS:
 		case IVHD_DEV_EXT_SELECT:
 			/* all the above subfield types refer to device ids */
-			update_last_devid(dev->devid);
+			if (dev->devid > last_devid)
+				last_devid = dev->devid;
 			break;
 		default:
 			break;
@@ -590,7 +587,7 @@
 
 	WARN_ON(p != end);
 
-	return 0;
+	return last_devid;
 }
 
 static int __init check_ivrs_checksum(struct acpi_table_header *table)
@@ -614,38 +611,125 @@
  * id which we need to handle. This is the first of three functions which parse
  * the ACPI table. So we check the checksum here.
  */
-static int __init find_last_devid_acpi(struct acpi_table_header *table)
+static int __init find_last_devid_acpi(struct acpi_table_header *table, u16 pci_seg)
 {
 	u8 *p = (u8 *)table, *end = (u8 *)table;
 	struct ivhd_header *h;
+	int last_devid, last_bdf = 0;
 
 	p += IVRS_HEADER_LENGTH;
 
 	end += table->length;
 	while (p < end) {
 		h = (struct ivhd_header *)p;
-		if (h->type == amd_iommu_target_ivhd_type) {
-			int ret = find_last_devid_from_ivhd(h);
+		if (h->pci_seg == pci_seg &&
+		    h->type == amd_iommu_target_ivhd_type) {
+			last_devid = find_last_devid_from_ivhd(h);
 
-			if (ret)
-				return ret;
+			if (last_devid < 0)
+				return -EINVAL;
+			if (last_devid > last_bdf)
+				last_bdf = last_devid;
 		}
 		p += h->length;
 	}
 	WARN_ON(p != end);
 
-	return 0;
+	return last_bdf;
 }
 
 /****************************************************************************
  *
  * The following functions belong to the code path which parses the ACPI table
  * the second time. In this ACPI parsing iteration we allocate IOMMU specific
- * data structures, initialize the device/alias/rlookup table and also
- * basically initialize the hardware.
+ * data structures, initialize the per PCI segment device/alias/rlookup table
+ * and also basically initialize the hardware.
  *
  ****************************************************************************/
 
+/* Allocate per PCI segment device table */
+static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32,
+						      get_order(pci_seg->dev_table_size));
+	if (!pci_seg->dev_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->dev_table,
+		    get_order(pci_seg->dev_table_size));
+	pci_seg->dev_table = NULL;
+}
+
+/* Allocate per PCI segment IOMMU rlookup table. */
+static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->rlookup_table = (void *)__get_free_pages(
+						GFP_KERNEL | __GFP_ZERO,
+						get_order(pci_seg->rlookup_table_size));
+	if (pci_seg->rlookup_table == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->rlookup_table,
+		   get_order(pci_seg->rlookup_table_size));
+	pci_seg->rlookup_table = NULL;
+}
+
+static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->irq_lookup_table = (void *)__get_free_pages(
+					     GFP_KERNEL | __GFP_ZERO,
+					     get_order(pci_seg->rlookup_table_size));
+	kmemleak_alloc(pci_seg->irq_lookup_table,
+		       pci_seg->rlookup_table_size, 1, GFP_KERNEL);
+	if (pci_seg->irq_lookup_table == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	kmemleak_free(pci_seg->irq_lookup_table);
+	free_pages((unsigned long)pci_seg->irq_lookup_table,
+		   get_order(pci_seg->rlookup_table_size));
+	pci_seg->irq_lookup_table = NULL;
+}
+
+static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	int i;
+
+	pci_seg->alias_table = (void *)__get_free_pages(GFP_KERNEL,
+					get_order(pci_seg->alias_table_size));
+	if (!pci_seg->alias_table)
+		return -ENOMEM;
+
+	/*
+	 * let all alias entries point to itself
+	 */
+	for (i = 0; i <= pci_seg->last_bdf; ++i)
+		pci_seg->alias_table[i] = i;
+
+	return 0;
+}
+
+static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->alias_table,
+		   get_order(pci_seg->alias_table_size));
+	pci_seg->alias_table = NULL;
+}
+
 /*
  * Allocates the command buffer. This buffer is per AMD IOMMU. We can
  * write commands to that buffer later and the IOMMU will execute them
@@ -724,7 +808,7 @@
 	void *buf = (void *)__get_free_pages(gfp, order);
 
 	if (buf &&
-	    iommu_feature(iommu, FEATURE_SNP) &&
+	    check_feature_on_all_iommus(FEATURE_SNP) &&
 	    set_memory_4k((unsigned long)buf, (1 << order))) {
 		free_pages((unsigned long)buf, order);
 		buf = NULL;
@@ -815,20 +899,15 @@
 #endif
 }
 
+#ifdef CONFIG_IRQ_REMAP
 static int iommu_ga_log_enable(struct amd_iommu *iommu)
 {
-#ifdef CONFIG_IRQ_REMAP
 	u32 status, i;
 	u64 entry;
 
 	if (!iommu->ga_log)
 		return -EINVAL;
 
-	/* Check if already running */
-	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
-	if (WARN_ON(status & (MMIO_STATUS_GALOG_RUN_MASK)))
-		return 0;
-
 	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
 	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
 		    &entry, sizeof(entry));
@@ -852,13 +931,12 @@
 
 	if (WARN_ON(i >= LOOP_TIMEOUT))
 		return -EINVAL;
-#endif /* CONFIG_IRQ_REMAP */
+
 	return 0;
 }
 
 static int iommu_init_ga_log(struct amd_iommu *iommu)
 {
-#ifdef CONFIG_IRQ_REMAP
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
 		return 0;
 
@@ -876,10 +954,8 @@
 err_out:
 	free_ga_log(iommu);
 	return -EINVAL;
-#else
-	return 0;
-#endif /* CONFIG_IRQ_REMAP */
 }
+#endif /* CONFIG_IRQ_REMAP */
 
 static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
 {
@@ -916,56 +992,59 @@
 }
 
 /* sets a specific bit in the device table entry. */
-static void set_dev_entry_bit(u16 devid, u8 bit)
+static void __set_dev_entry_bit(struct dev_table_entry *dev_table,
+				u16 devid, u8 bit)
 {
 	int i = (bit >> 6) & 0x03;
 	int _bit = bit & 0x3f;
 
-	amd_iommu_dev_table[devid].data[i] |= (1UL << _bit);
+	dev_table[devid].data[i] |= (1UL << _bit);
 }
 
-static int get_dev_entry_bit(u16 devid, u8 bit)
+static void set_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit)
+{
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	return __set_dev_entry_bit(dev_table, devid, bit);
+}
+
+static int __get_dev_entry_bit(struct dev_table_entry *dev_table,
+			       u16 devid, u8 bit)
 {
 	int i = (bit >> 6) & 0x03;
 	int _bit = bit & 0x3f;
 
-	return (amd_iommu_dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
+	return (dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
 }
 
-
-static bool copy_device_table(void)
+static int get_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit)
 {
-	u64 int_ctl, int_tab_len, entry = 0, last_entry = 0;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	return __get_dev_entry_bit(dev_table, devid, bit);
+}
+
+static bool __copy_device_table(struct amd_iommu *iommu)
+{
+	u64 int_ctl, int_tab_len, entry = 0;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 	struct dev_table_entry *old_devtb = NULL;
 	u32 lo, hi, devid, old_devtb_size;
 	phys_addr_t old_devtb_phys;
-	struct amd_iommu *iommu;
 	u16 dom_id, dte_v, irq_v;
 	gfp_t gfp_flag;
 	u64 tmp;
 
-	if (!amd_iommu_pre_enabled)
+	/* Each IOMMU use separate device table with the same size */
+	lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET);
+	hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
+	entry = (((u64) hi) << 32) + lo;
+
+	old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
+	if (old_devtb_size != pci_seg->dev_table_size) {
+		pr_err("The device table size of IOMMU:%d is not expected!\n",
+			iommu->index);
 		return false;
-
-	pr_warn("Translation is already enabled - trying to copy translation structures\n");
-	for_each_iommu(iommu) {
-		/* All IOMMUs should use the same device table with the same size */
-		lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET);
-		hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
-		entry = (((u64) hi) << 32) + lo;
-		if (last_entry && last_entry != entry) {
-			pr_err("IOMMU:%d should use the same dev table as others!\n",
-				iommu->index);
-			return false;
-		}
-		last_entry = entry;
-
-		old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
-		if (old_devtb_size != dev_table_size) {
-			pr_err("The device table size of IOMMU:%d is not expected!\n",
-				iommu->index);
-			return false;
-		}
 	}
 
 	/*
@@ -981,38 +1060,38 @@
 	}
 	old_devtb = (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) && is_kdump_kernel())
 		    ? (__force void *)ioremap_encrypted(old_devtb_phys,
-							dev_table_size)
-		    : memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB);
+							pci_seg->dev_table_size)
+		    : memremap(old_devtb_phys, pci_seg->dev_table_size, MEMREMAP_WB);
 
 	if (!old_devtb)
 		return false;
 
 	gfp_flag = GFP_KERNEL | __GFP_ZERO | GFP_DMA32;
-	old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
-				get_order(dev_table_size));
-	if (old_dev_tbl_cpy == NULL) {
+	pci_seg->old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
+						    get_order(pci_seg->dev_table_size));
+	if (pci_seg->old_dev_tbl_cpy == NULL) {
 		pr_err("Failed to allocate memory for copying old device table!\n");
 		memunmap(old_devtb);
 		return false;
 	}
 
-	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
-		old_dev_tbl_cpy[devid] = old_devtb[devid];
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		pci_seg->old_dev_tbl_cpy[devid] = old_devtb[devid];
 		dom_id = old_devtb[devid].data[1] & DEV_DOMID_MASK;
 		dte_v = old_devtb[devid].data[0] & DTE_FLAG_V;
 
 		if (dte_v && dom_id) {
-			old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0];
-			old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1];
+			pci_seg->old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0];
+			pci_seg->old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1];
 			__set_bit(dom_id, amd_iommu_pd_alloc_bitmap);
 			/* If gcr3 table existed, mask it out */
 			if (old_devtb[devid].data[0] & DTE_FLAG_GV) {
 				tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B;
 				tmp |= DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C;
-				old_dev_tbl_cpy[devid].data[1] &= ~tmp;
+				pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp;
 				tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A;
 				tmp |= DTE_FLAG_GV;
-				old_dev_tbl_cpy[devid].data[0] &= ~tmp;
+				pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp;
 			}
 		}
 
@@ -1027,7 +1106,7 @@
 				return false;
 			}
 
-		        old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2];
+			pci_seg->old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2];
 		}
 	}
 	memunmap(old_devtb);
@@ -1035,21 +1114,42 @@
 	return true;
 }
 
-void amd_iommu_apply_erratum_63(u16 devid)
+static bool copy_device_table(void)
+{
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+
+	if (!amd_iommu_pre_enabled)
+		return false;
+
+	pr_warn("Translation is already enabled - trying to copy translation structures\n");
+
+	/*
+	 * All IOMMUs within PCI segment shares common device table.
+	 * Hence copy device table only once per PCI segment.
+	 */
+	for_each_pci_segment(pci_seg) {
+		for_each_iommu(iommu) {
+			if (pci_seg->id != iommu->pci_seg->id)
+				continue;
+			if (!__copy_device_table(iommu))
+				return false;
+			break;
+		}
+	}
+
+	return true;
+}
+
+void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid)
 {
 	int sysmgt;
 
-	sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
-		 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);
+	sysmgt = get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1) |
+		 (get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2) << 1);
 
 	if (sysmgt == 0x01)
-		set_dev_entry_bit(devid, DEV_ENTRY_IW);
-}
-
-/* Writes the specific IOMMU for a device into the rlookup table */
-static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
-{
-	amd_iommu_rlookup_table[devid] = iommu;
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_IW);
 }
 
 /*
@@ -1060,26 +1160,26 @@
 					   u16 devid, u32 flags, u32 ext_flags)
 {
 	if (flags & ACPI_DEVFLAG_INITPASS)
-		set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_INIT_PASS);
 	if (flags & ACPI_DEVFLAG_EXTINT)
-		set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_EINT_PASS);
 	if (flags & ACPI_DEVFLAG_NMI)
-		set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_NMI_PASS);
 	if (flags & ACPI_DEVFLAG_SYSMGT1)
-		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1);
 	if (flags & ACPI_DEVFLAG_SYSMGT2)
-		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2);
 	if (flags & ACPI_DEVFLAG_LINT0)
-		set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT0_PASS);
 	if (flags & ACPI_DEVFLAG_LINT1)
-		set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT1_PASS);
 
-	amd_iommu_apply_erratum_63(devid);
+	amd_iommu_apply_erratum_63(iommu, devid);
 
-	set_iommu_for_device(iommu, devid);
+	amd_iommu_set_rlookup_table(iommu, devid);
 }
 
-int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
+int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
@@ -1116,7 +1216,7 @@
 	return 0;
 }
 
-static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u16 *devid,
+static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u32 *devid,
 				      bool cmd_line)
 {
 	struct acpihid_map_entry *entry;
@@ -1195,10 +1295,11 @@
 {
 	u8 *p = (u8 *)h;
 	u8 *end = p, flags = 0;
-	u16 devid = 0, devid_start = 0, devid_to = 0;
+	u16 devid = 0, devid_start = 0, devid_to = 0, seg_id;
 	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 	u32 ivhd_size;
 	int ret;
 
@@ -1230,19 +1331,21 @@
 
 	while (p < end) {
 		e = (struct ivhd_entry *)p;
+		seg_id = pci_seg->id;
+
 		switch (e->type) {
 		case IVHD_DEV_ALL:
 
 			DUMP_printk("  DEV_ALL\t\t\tflags: %02x\n", e->flags);
 
-			for (dev_i = 0; dev_i <= amd_iommu_last_bdf; ++dev_i)
+			for (dev_i = 0; dev_i <= pci_seg->last_bdf; ++dev_i)
 				set_dev_entry_from_acpi(iommu, dev_i, e->flags, 0);
 			break;
 		case IVHD_DEV_SELECT:
 
-			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
+			DUMP_printk("  DEV_SELECT\t\t\t devid: %04x:%02x:%02x.%x "
 				    "flags: %02x\n",
-				    PCI_BUS_NUM(e->devid),
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags);
@@ -1253,8 +1356,8 @@
 		case IVHD_DEV_SELECT_RANGE_START:
 
 			DUMP_printk("  DEV_SELECT_RANGE_START\t "
-				    "devid: %02x:%02x.%x flags: %02x\n",
-				    PCI_BUS_NUM(e->devid),
+				    "devid: %04x:%02x:%02x.%x flags: %02x\n",
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags);
@@ -1266,9 +1369,9 @@
 			break;
 		case IVHD_DEV_ALIAS:
 
-			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
+			DUMP_printk("  DEV_ALIAS\t\t\t devid: %04x:%02x:%02x.%x "
 				    "flags: %02x devid_to: %02x:%02x.%x\n",
-				    PCI_BUS_NUM(e->devid),
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags,
@@ -1280,18 +1383,18 @@
 			devid_to = e->ext >> 8;
 			set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
 			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
-			amd_iommu_alias_table[devid] = devid_to;
+			pci_seg->alias_table[devid] = devid_to;
 			break;
 		case IVHD_DEV_ALIAS_RANGE:
 
 			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
-				    "devid: %02x:%02x.%x flags: %02x "
-				    "devid_to: %02x:%02x.%x\n",
-				    PCI_BUS_NUM(e->devid),
+				    "devid: %04x:%02x:%02x.%x flags: %02x "
+				    "devid_to: %04x:%02x:%02x.%x\n",
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags,
-				    PCI_BUS_NUM(e->ext >> 8),
+				    seg_id, PCI_BUS_NUM(e->ext >> 8),
 				    PCI_SLOT(e->ext >> 8),
 				    PCI_FUNC(e->ext >> 8));
 
@@ -1303,9 +1406,9 @@
 			break;
 		case IVHD_DEV_EXT_SELECT:
 
-			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
+			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %04x:%02x:%02x.%x "
 				    "flags: %02x ext: %08x\n",
-				    PCI_BUS_NUM(e->devid),
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags, e->ext);
@@ -1317,8 +1420,8 @@
 		case IVHD_DEV_EXT_SELECT_RANGE:
 
 			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
-				    "%02x:%02x.%x flags: %02x ext: %08x\n",
-				    PCI_BUS_NUM(e->devid),
+				    "%04x:%02x:%02x.%x flags: %02x ext: %08x\n",
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid),
 				    e->flags, e->ext);
@@ -1330,15 +1433,15 @@
 			break;
 		case IVHD_DEV_RANGE_END:
 
-			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
-				    PCI_BUS_NUM(e->devid),
+			DUMP_printk("  DEV_RANGE_END\t\t devid: %04x:%02x:%02x.%x\n",
+				    seg_id, PCI_BUS_NUM(e->devid),
 				    PCI_SLOT(e->devid),
 				    PCI_FUNC(e->devid));
 
 			devid = e->devid;
 			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
 				if (alias) {
-					amd_iommu_alias_table[dev_i] = devid_to;
+					pci_seg->alias_table[dev_i] = devid_to;
 					set_dev_entry_from_acpi(iommu,
 						devid_to, flags, ext_flags);
 				}
@@ -1349,11 +1452,11 @@
 		case IVHD_DEV_SPECIAL: {
 			u8 handle, type;
 			const char *var;
-			u16 devid;
+			u32 devid;
 			int ret;
 
 			handle = e->ext & 0xff;
-			devid  = (e->ext >>  8) & 0xffff;
+			devid = PCI_SEG_DEVID_TO_SBDF(seg_id, (e->ext >> 8));
 			type   = (e->ext >> 24) & 0xff;
 
 			if (type == IVHD_SPECIAL_IOAPIC)
@@ -1363,9 +1466,9 @@
 			else
 				var = "UNKNOWN";
 
-			DUMP_printk("  DEV_SPECIAL(%s[%d])\t\tdevid: %02x:%02x.%x\n",
+			DUMP_printk("  DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x\n",
 				    var, (int)handle,
-				    PCI_BUS_NUM(devid),
+				    seg_id, PCI_BUS_NUM(devid),
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
 
@@ -1383,7 +1486,7 @@
 			break;
 		}
 		case IVHD_DEV_ACPI_HID: {
-			u16 devid;
+			u32 devid;
 			u8 hid[ACPIHID_HID_LEN];
 			u8 uid[ACPIHID_UID_LEN];
 			int ret;
@@ -1426,9 +1529,9 @@
 				break;
 			}
 
-			devid = e->devid;
-			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
-				    hid, uid,
+			devid = PCI_SEG_DEVID_TO_SBDF(seg_id, e->devid);
+			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x\n",
+				    hid, uid, seg_id,
 				    PCI_BUS_NUM(devid),
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
@@ -1458,6 +1561,74 @@
 	return 0;
 }
 
+/* Allocate PCI segment data structure */
+static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
+					  struct acpi_table_header *ivrs_base)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	int last_bdf;
+
+	/*
+	 * First parse ACPI tables to find the largest Bus/Dev/Func we need to
+	 * handle in this PCI segment. Upon this information the shared data
+	 * structures for the PCI segments in the system will be allocated.
+	 */
+	last_bdf = find_last_devid_acpi(ivrs_base, id);
+	if (last_bdf < 0)
+		return NULL;
+
+	pci_seg = kzalloc(sizeof(struct amd_iommu_pci_seg), GFP_KERNEL);
+	if (pci_seg == NULL)
+		return NULL;
+
+	pci_seg->last_bdf = last_bdf;
+	DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf);
+	pci_seg->dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE, last_bdf);
+
+	pci_seg->id = id;
+	init_llist_head(&pci_seg->dev_data_list);
+	INIT_LIST_HEAD(&pci_seg->unity_map);
+	list_add_tail(&pci_seg->list, &amd_iommu_pci_seg_list);
+
+	if (alloc_dev_table(pci_seg))
+		return NULL;
+	if (alloc_alias_table(pci_seg))
+		return NULL;
+	if (alloc_rlookup_table(pci_seg))
+		return NULL;
+
+	return pci_seg;
+}
+
+static struct amd_iommu_pci_seg *__init get_pci_segment(u16 id,
+					struct acpi_table_header *ivrs_base)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id == id)
+			return pci_seg;
+	}
+
+	return alloc_pci_segment(id, ivrs_base);
+}
+
+static void __init free_pci_segments(void)
+{
+	struct amd_iommu_pci_seg *pci_seg, *next;
+
+	for_each_pci_segment_safe(pci_seg, next) {
+		list_del(&pci_seg->list);
+		free_irq_lookup_table(pci_seg);
+		free_rlookup_table(pci_seg);
+		free_alias_table(pci_seg);
+		free_dev_table(pci_seg);
+		kfree(pci_seg);
+	}
+}
+
 static void __init free_iommu_one(struct amd_iommu *iommu)
 {
 	free_cwwb_sem(iommu);
@@ -1542,9 +1713,15 @@
  * together and also allocates the command buffer and programs the
  * hardware. It does NOT enable the IOMMU. This is done afterwards.
  */
-static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
+static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,
+				 struct acpi_table_header *ivrs_base)
 {
-	int ret;
+	struct amd_iommu_pci_seg *pci_seg;
+
+	pci_seg = get_pci_segment(h->pci_seg, ivrs_base);
+	if (pci_seg == NULL)
+		return -ENOMEM;
+	iommu->pci_seg = pci_seg;
 
 	raw_spin_lock_init(&iommu->lock);
 	iommu->cmd_sem_val = 0;
@@ -1566,7 +1743,6 @@
 	 */
 	iommu->devid   = h->devid;
 	iommu->cap_ptr = h->cap_ptr;
-	iommu->pci_seg = h->pci_seg;
 	iommu->mmio_phys = h->mmio_phys;
 
 	switch (h->type) {
@@ -1621,6 +1797,13 @@
 	if (!iommu->mmio_base)
 		return -ENOMEM;
 
+	return init_iommu_from_acpi(iommu, h);
+}
+
+static int __init init_iommu_one_late(struct amd_iommu *iommu)
+{
+	int ret;
+
 	if (alloc_cwwb_sem(iommu))
 		return -ENOMEM;
 
@@ -1642,10 +1825,6 @@
 	if (amd_iommu_pre_enabled)
 		amd_iommu_pre_enabled = translation_pre_enabled(iommu);
 
-	ret = init_iommu_from_acpi(iommu, h);
-	if (ret)
-		return ret;
-
 	if (amd_iommu_irq_remap) {
 		ret = amd_iommu_create_irq_domain(iommu);
 		if (ret)
@@ -1656,7 +1835,7 @@
 	 * Make sure IOMMU is not considered to translate itself. The IVRS
 	 * table tells us so, but this is a lie!
 	 */
-	amd_iommu_rlookup_table[iommu->devid] = NULL;
+	iommu->pci_seg->rlookup_table[iommu->devid] = NULL;
 
 	return 0;
 }
@@ -1701,15 +1880,16 @@
 	end += table->length;
 	p += IVRS_HEADER_LENGTH;
 
+	/* Phase 1: Process all IVHD blocks */
 	while (p < end) {
 		h = (struct ivhd_header *)p;
 		if (*p == amd_iommu_target_ivhd_type) {
 
-			DUMP_printk("device: %02x:%02x.%01x cap: %04x "
-				    "seg: %d flags: %01x info %04x\n",
-				    PCI_BUS_NUM(h->devid), PCI_SLOT(h->devid),
-				    PCI_FUNC(h->devid), h->cap_ptr,
-				    h->pci_seg, h->flags, h->info);
+			DUMP_printk("device: %04x:%02x:%02x.%01x cap: %04x "
+				    "flags: %01x info %04x\n",
+				    h->pci_seg, PCI_BUS_NUM(h->devid),
+				    PCI_SLOT(h->devid), PCI_FUNC(h->devid),
+				    h->cap_ptr, h->flags, h->info);
 			DUMP_printk("       mmio-addr: %016llx\n",
 				    h->mmio_phys);
 
@@ -1717,7 +1897,7 @@
 			if (iommu == NULL)
 				return -ENOMEM;
 
-			ret = init_iommu_one(iommu, h);
+			ret = init_iommu_one(iommu, h, table);
 			if (ret)
 				return ret;
 		}
@@ -1726,6 +1906,16 @@
 	}
 	WARN_ON(p != end);
 
+	/* Phase 2 : Early feature support check */
+	get_global_efr();
+
+	/* Phase 3 : Enabling IOMMU features */
+	for_each_iommu(iommu) {
+		ret = init_iommu_one_late(iommu);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -1762,7 +1952,7 @@
 				       char *buf)
 {
 	struct amd_iommu *iommu = dev_to_amd_iommu(dev);
-	return sprintf(buf, "%llx\n", iommu->features);
+	return sprintf(buf, "%llx:%llx\n", iommu->features2, iommu->features);
 }
 static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL);
 
@@ -1789,16 +1979,18 @@
  */
 static void __init late_iommu_features_init(struct amd_iommu *iommu)
 {
-	u64 features;
+	u64 features, features2;
 
 	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
 		return;
 
 	/* read extended feature bits */
 	features = readq(iommu->mmio_base + MMIO_EXT_FEATURES);
+	features2 = readq(iommu->mmio_base + MMIO_EXT_FEATURES2);
 
 	if (!iommu->features) {
 		iommu->features = features;
+		iommu->features2 = features2;
 		return;
 	}
 
@@ -1806,9 +1998,13 @@
 	 * Sanity check and warn if EFR values from
 	 * IVHD and MMIO conflict.
 	 */
-	if (features != iommu->features)
-		pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx).\n",
-			features, iommu->features);
+	if (features != iommu->features ||
+	    features2 != iommu->features2) {
+		pr_warn(FW_WARN
+			"EFR mismatch. Use IVHD EFR (%#llx : %#llx), EFR2 (%#llx : %#llx).\n",
+			features, iommu->features,
+			features2, iommu->features2);
+	}
 }
 
 static int __init iommu_init_pci(struct amd_iommu *iommu)
@@ -1816,7 +2012,8 @@
 	int cap_ptr = iommu->cap_ptr;
 	int ret;
 
-	iommu->dev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(iommu->devid),
+	iommu->dev = pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+						 PCI_BUS_NUM(iommu->devid),
 						 iommu->devid & 0xff);
 	if (!iommu->dev)
 		return -ENODEV;
@@ -1863,10 +2060,6 @@
 	if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu))
 		return -ENOMEM;
 
-	ret = iommu_init_ga_log(iommu);
-	if (ret)
-		return ret;
-
 	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) {
 		pr_info("Using strict mode due to virtualization\n");
 		iommu_set_dma_strict();
@@ -1879,7 +2072,8 @@
 		int i, j;
 
 		iommu->root_pdev =
-			pci_get_domain_bus_and_slot(0, iommu->dev->bus->number,
+			pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+						    iommu->dev->bus->number,
 						    PCI_DEVFN(0, 0));
 
 		/*
@@ -1906,8 +2100,11 @@
 	amd_iommu_erratum_746_workaround(iommu);
 	amd_iommu_ats_write_check_workaround(iommu);
 
-	iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
+	ret = iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
 			       amd_iommu_groups, "ivhd%d", iommu->index);
+	if (ret)
+		return ret;
+
 	iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
 
 	return pci_enable_device(iommu->dev);
@@ -1928,7 +2125,7 @@
 		pci_info(pdev, "Found IOMMU cap 0x%x\n", iommu->cap_ptr);
 
 		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
-			pr_info("Extended features (%#llx):", iommu->features);
+			pr_info("Extended features (%#llx, %#llx):", iommu->features, iommu->features2);
 
 			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
 				if (iommu_feature(iommu, (1ULL << i)))
@@ -1938,13 +2135,14 @@
 			if (iommu->features & FEATURE_GAM_VAPIC)
 				pr_cont(" GA_vAPIC");
 
+			if (iommu->features & FEATURE_SNP)
+				pr_cont(" SNP");
+
 			pr_cont("\n");
 		}
 	}
 	if (irq_remapping_enabled) {
 		pr_info("Interrupt remapping enabled\n");
-		if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
-			pr_info("Virtual APIC enabled\n");
 		if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
 			pr_info("X2APIC enabled\n");
 	}
@@ -1953,6 +2151,7 @@
 static int __init amd_iommu_init_pci(void)
 {
 	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
 	int ret;
 
 	for_each_iommu(iommu) {
@@ -1983,7 +2182,8 @@
 		goto out;
 	}
 
-	init_device_table_dma();
+	for_each_pci_segment(pci_seg)
+		init_device_table_dma(pci_seg);
 
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
@@ -2232,9 +2432,6 @@
 
 	if (iommu->ppr_log != NULL)
 		iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
-
-	iommu_ga_log_enable(iommu);
-
 	return 0;
 }
 
@@ -2249,19 +2446,28 @@
 static void __init free_unity_maps(void)
 {
 	struct unity_map_entry *entry, *next;
+	struct amd_iommu_pci_seg *p, *pci_seg;
 
-	list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) {
-		list_del(&entry->list);
-		kfree(entry);
+	for_each_pci_segment_safe(pci_seg, p) {
+		list_for_each_entry_safe(entry, next, &pci_seg->unity_map, list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
 	}
 }
 
 /* called for unity map ACPI definition */
-static int __init init_unity_map_range(struct ivmd_header *m)
+static int __init init_unity_map_range(struct ivmd_header *m,
+				       struct acpi_table_header *ivrs_base)
 {
 	struct unity_map_entry *e = NULL;
+	struct amd_iommu_pci_seg *pci_seg;
 	char *s;
 
+	pci_seg = get_pci_segment(m->pci_seg, ivrs_base);
+	if (pci_seg == NULL)
+		return -ENOMEM;
+
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (e == NULL)
 		return -ENOMEM;
@@ -2277,7 +2483,7 @@
 	case ACPI_IVMD_TYPE_ALL:
 		s = "IVMD_TYPE_ALL\t\t";
 		e->devid_start = 0;
-		e->devid_end = amd_iommu_last_bdf;
+		e->devid_end = pci_seg->last_bdf;
 		break;
 	case ACPI_IVMD_TYPE_RANGE:
 		s = "IVMD_TYPE_RANGE\t\t";
@@ -2299,14 +2505,16 @@
 	if (m->flags & IVMD_FLAG_EXCL_RANGE)
 		e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1;
 
-	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
-		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
+	DUMP_printk("%s devid_start: %04x:%02x:%02x.%x devid_end: "
+		    "%04x:%02x:%02x.%x range_start: %016llx range_end: %016llx"
+		    " flags: %x\n", s, m->pci_seg,
 		    PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),
-		    PCI_FUNC(e->devid_start), PCI_BUS_NUM(e->devid_end),
+		    PCI_FUNC(e->devid_start), m->pci_seg,
+		    PCI_BUS_NUM(e->devid_end),
 		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
 		    e->address_start, e->address_end, m->flags);
 
-	list_add_tail(&e->list, &amd_iommu_unity_map);
+	list_add_tail(&e->list, &pci_seg->unity_map);
 
 	return 0;
 }
@@ -2323,7 +2531,7 @@
 	while (p < end) {
 		m = (struct ivmd_header *)p;
 		if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
-			init_unity_map_range(m);
+			init_unity_map_range(m, table);
 
 		p += m->length;
 	}
@@ -2334,35 +2542,48 @@
 /*
  * Init the device table to not allow DMA access for devices
  */
-static void init_device_table_dma(void)
+static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
 {
 	u32 devid;
+	struct dev_table_entry *dev_table = pci_seg->dev_table;
 
-	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
-		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
-		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
+	if (dev_table == NULL)
+		return;
+
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		__set_dev_entry_bit(dev_table, devid, DEV_ENTRY_VALID);
+		if (!amd_iommu_snp_en)
+			__set_dev_entry_bit(dev_table, devid, DEV_ENTRY_TRANSLATION);
 	}
 }
 
-static void __init uninit_device_table_dma(void)
+static void __init uninit_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
 {
 	u32 devid;
+	struct dev_table_entry *dev_table = pci_seg->dev_table;
 
-	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
-		amd_iommu_dev_table[devid].data[0] = 0ULL;
-		amd_iommu_dev_table[devid].data[1] = 0ULL;
+	if (dev_table == NULL)
+		return;
+
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		dev_table[devid].data[0] = 0ULL;
+		dev_table[devid].data[1] = 0ULL;
 	}
 }
 
 static void init_device_table(void)
 {
+	struct amd_iommu_pci_seg *pci_seg;
 	u32 devid;
 
 	if (!amd_iommu_irq_remap)
 		return;
 
-	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid)
-		set_dev_entry_bit(devid, DEV_ENTRY_IRQ_TBL_EN);
+	for_each_pci_segment(pci_seg) {
+		for (devid = 0; devid <= pci_seg->last_bdf; ++devid)
+			__set_dev_entry_bit(pci_seg->dev_table,
+					    devid, DEV_ENTRY_IRQ_TBL_EN);
+	}
 }
 
 static void iommu_init_flags(struct amd_iommu *iommu)
@@ -2440,8 +2661,6 @@
 #ifdef CONFIG_IRQ_REMAP
 	switch (amd_iommu_guest_ir) {
 	case AMD_IOMMU_GUEST_IR_VAPIC:
-		iommu_feature_enable(iommu, CONTROL_GAM_EN);
-		fallthrough;
 	case AMD_IOMMU_GUEST_IR_LEGACY_GA:
 		iommu_feature_enable(iommu, CONTROL_GA_EN);
 		iommu->irte_ops = &irte_128_ops;
@@ -2478,7 +2697,7 @@
 static void early_enable_iommus(void)
 {
 	struct amd_iommu *iommu;
-
+	struct amd_iommu_pci_seg *pci_seg;
 
 	if (!copy_device_table()) {
 		/*
@@ -2488,9 +2707,14 @@
 		 */
 		if (amd_iommu_pre_enabled)
 			pr_err("Failed to copy DEV table from previous kernel.\n");
-		if (old_dev_tbl_cpy != NULL)
-			free_pages((unsigned long)old_dev_tbl_cpy,
-					get_order(dev_table_size));
+
+		for_each_pci_segment(pci_seg) {
+			if (pci_seg->old_dev_tbl_cpy != NULL) {
+				free_pages((unsigned long)pci_seg->old_dev_tbl_cpy,
+						get_order(pci_seg->dev_table_size));
+				pci_seg->old_dev_tbl_cpy = NULL;
+			}
+		}
 
 		for_each_iommu(iommu) {
 			clear_translation_pre_enabled(iommu);
@@ -2498,9 +2722,13 @@
 		}
 	} else {
 		pr_info("Copied DEV table from previous kernel.\n");
-		free_pages((unsigned long)amd_iommu_dev_table,
-				get_order(dev_table_size));
-		amd_iommu_dev_table = old_dev_tbl_cpy;
+
+		for_each_pci_segment(pci_seg) {
+			free_pages((unsigned long)pci_seg->dev_table,
+				   get_order(pci_seg->dev_table_size));
+			pci_seg->dev_table = pci_seg->old_dev_tbl_cpy;
+		}
+
 		for_each_iommu(iommu) {
 			iommu_disable_command_buffer(iommu);
 			iommu_disable_event_buffer(iommu);
@@ -2512,19 +2740,6 @@
 			iommu_flush_all_caches(iommu);
 		}
 	}
-
-#ifdef CONFIG_IRQ_REMAP
-	/*
-	 * Note: We have already checked GASup from IVRS table.
-	 *       Now, we need to make sure that GAMSup is set.
-	 */
-	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
-	    !check_feature_on_all_iommus(FEATURE_GAM_VAPIC))
-		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
-
-	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
-		amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
-#endif
 }
 
 static void enable_iommus_v2(void)
@@ -2537,10 +2752,72 @@
 	}
 }
 
+static void enable_iommus_vapic(void)
+{
+#ifdef CONFIG_IRQ_REMAP
+	u32 status, i;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		/*
+		 * Disable GALog if already running. It could have been enabled
+		 * in the previous boot before kdump.
+		 */
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+		if (!(status & MMIO_STATUS_GALOG_RUN_MASK))
+			continue;
+
+		iommu_feature_disable(iommu, CONTROL_GALOG_EN);
+		iommu_feature_disable(iommu, CONTROL_GAINT_EN);
+
+		/*
+		 * Need to set and poll check the GALOGRun bit to zero before
+		 * we can set/ modify GA Log registers safely.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+			if (!(status & MMIO_STATUS_GALOG_RUN_MASK))
+				break;
+			udelay(10);
+		}
+
+		if (WARN_ON(i >= LOOP_TIMEOUT))
+			return;
+	}
+
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+	    !check_feature_on_all_iommus(FEATURE_GAM_VAPIC)) {
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+		return;
+	}
+
+	if (amd_iommu_snp_en &&
+	    !FEATURE_SNPAVICSUP_GAM(amd_iommu_efr2)) {
+		pr_warn("Force to disable Virtual APIC due to SNP\n");
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+		return;
+	}
+
+	/* Enabling GAM and SNPAVIC support */
+	for_each_iommu(iommu) {
+		if (iommu_init_ga_log(iommu) ||
+		    iommu_ga_log_enable(iommu))
+			return;
+
+		iommu_feature_enable(iommu, CONTROL_GAM_EN);
+		if (amd_iommu_snp_en)
+			iommu_feature_enable(iommu, CONTROL_SNPAVIC_EN);
+	}
+
+	amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
+	pr_info("Virtual APIC enabled\n");
+#endif
+}
+
 static void enable_iommus(void)
 {
 	early_enable_iommus();
-
+	enable_iommus_vapic();
 	enable_iommus_v2();
 }
 
@@ -2590,27 +2867,11 @@
 
 static void __init free_iommu_resources(void)
 {
-	kmemleak_free(irq_lookup_table);
-	free_pages((unsigned long)irq_lookup_table,
-		   get_order(rlookup_table_size));
-	irq_lookup_table = NULL;
-
 	kmem_cache_destroy(amd_iommu_irq_cache);
 	amd_iommu_irq_cache = NULL;
 
-	free_pages((unsigned long)amd_iommu_rlookup_table,
-		   get_order(rlookup_table_size));
-	amd_iommu_rlookup_table = NULL;
-
-	free_pages((unsigned long)amd_iommu_alias_table,
-		   get_order(alias_table_size));
-	amd_iommu_alias_table = NULL;
-
-	free_pages((unsigned long)amd_iommu_dev_table,
-		   get_order(dev_table_size));
-	amd_iommu_dev_table = NULL;
-
 	free_iommu_all();
+	free_pci_segments();
 }
 
 /* SB IOAPIC is always on this device in AMD systems */
@@ -2709,7 +2970,7 @@
 static int __init early_amd_iommu_init(void)
 {
 	struct acpi_table_header *ivrs_base;
-	int i, remap_cache_sz, ret;
+	int remap_cache_sz, ret;
 	acpi_status status;
 
 	if (!amd_iommu_detected)
@@ -2737,42 +2998,8 @@
 	amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
 	DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
 
-	/*
-	 * First parse ACPI tables to find the largest Bus/Dev/Func
-	 * we need to handle. Upon this information the shared data
-	 * structures for the IOMMUs in the system will be allocated
-	 */
-	ret = find_last_devid_acpi(ivrs_base);
-	if (ret)
-		goto out;
-
-	dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
-	alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
-	rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);
-
 	/* Device table - directly used by all IOMMUs */
 	ret = -ENOMEM;
-	amd_iommu_dev_table = (void *)__get_free_pages(
-				      GFP_KERNEL | __GFP_ZERO | GFP_DMA32,
-				      get_order(dev_table_size));
-	if (amd_iommu_dev_table == NULL)
-		goto out;
-
-	/*
-	 * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the
-	 * IOMMU see for that device
-	 */
-	amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL,
-			get_order(alias_table_size));
-	if (amd_iommu_alias_table == NULL)
-		goto out;
-
-	/* IOMMU rlookup table - find the IOMMU for a specific device */
-	amd_iommu_rlookup_table = (void *)__get_free_pages(
-			GFP_KERNEL | __GFP_ZERO,
-			get_order(rlookup_table_size));
-	if (amd_iommu_rlookup_table == NULL)
-		goto out;
 
 	amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(
 					    GFP_KERNEL | __GFP_ZERO,
@@ -2781,12 +3008,6 @@
 		goto out;
 
 	/*
-	 * let all alias entries point to itself
-	 */
-	for (i = 0; i <= amd_iommu_last_bdf; ++i)
-		amd_iommu_alias_table[i] = i;
-
-	/*
 	 * never allocate domain 0 because its used as the non-allocated and
 	 * error value placeholder
 	 */
@@ -2808,6 +3029,7 @@
 		amd_iommu_irq_remap = check_ioapic_information();
 
 	if (amd_iommu_irq_remap) {
+		struct amd_iommu_pci_seg *pci_seg;
 		/*
 		 * Interrupt remapping enabled, create kmem_cache for the
 		 * remapping tables.
@@ -2824,13 +3046,10 @@
 		if (!amd_iommu_irq_cache)
 			goto out;
 
-		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;
+		for_each_pci_segment(pci_seg) {
+			if (alloc_irq_lookup_table(pci_seg))
+				goto out;
+		}
 	}
 
 	ret = init_memory_definitions(ivrs_base);
@@ -2937,6 +3156,7 @@
 		register_syscore_ops(&amd_iommu_syscore_ops);
 		ret = amd_iommu_init_pci();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
+		enable_iommus_vapic();
 		enable_iommus_v2();
 		break;
 	case IOMMU_PCI_INIT:
@@ -2967,8 +3187,11 @@
 			free_iommu_resources();
 		} else {
 			struct amd_iommu *iommu;
+			struct amd_iommu_pci_seg *pci_seg;
 
-			uninit_device_table_dma();
+			for_each_pci_segment(pci_seg)
+				uninit_device_table_dma(pci_seg);
+
 			for_each_iommu(iommu)
 				iommu_flush_all_caches(iommu);
 		}
@@ -3161,15 +3384,17 @@
 
 static int __init parse_ivrs_ioapic(char *str)
 {
-	unsigned int bus, dev, fn;
+	u32 seg = 0, bus, dev, fn;
 	int ret, id, i;
-	u16 devid;
+	u32 devid;
 
 	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
-
 	if (ret != 4) {
-		pr_err("Invalid command line: ivrs_ioapic%s\n", str);
-		return 1;
+		ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn);
+		if (ret != 5) {
+			pr_err("Invalid command line: ivrs_ioapic%s\n", str);
+			return 1;
+		}
 	}
 
 	if (early_ioapic_map_size == EARLY_MAP_SIZE) {
@@ -3178,7 +3403,7 @@
 		return 1;
 	}
 
-	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
 
 	cmdline_maps			= true;
 	i				= early_ioapic_map_size++;
@@ -3191,15 +3416,17 @@
 
 static int __init parse_ivrs_hpet(char *str)
 {
-	unsigned int bus, dev, fn;
+	u32 seg = 0, bus, dev, fn;
 	int ret, id, i;
-	u16 devid;
+	u32 devid;
 
 	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
-
 	if (ret != 4) {
-		pr_err("Invalid command line: ivrs_hpet%s\n", str);
-		return 1;
+		ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn);
+		if (ret != 5) {
+			pr_err("Invalid command line: ivrs_hpet%s\n", str);
+			return 1;
+		}
 	}
 
 	if (early_hpet_map_size == EARLY_MAP_SIZE) {
@@ -3208,7 +3435,7 @@
 		return 1;
 	}
 
-	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
 
 	cmdline_maps			= true;
 	i				= early_hpet_map_size++;
@@ -3221,15 +3448,18 @@
 
 static int __init parse_ivrs_acpihid(char *str)
 {
-	u32 bus, dev, fn;
+	u32 seg = 0, bus, dev, fn;
 	char *hid, *uid, *p;
 	char acpiid[ACPIHID_UID_LEN + ACPIHID_HID_LEN] = {0};
 	int ret, i;
 
 	ret = sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid);
 	if (ret != 4) {
-		pr_err("Invalid command line: ivrs_acpihid(%s)\n", str);
-		return 1;
+		ret = sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid);
+		if (ret != 5) {
+			pr_err("Invalid command line: ivrs_acpihid(%s)\n", str);
+			return 1;
+		}
 	}
 
 	p = acpiid;
@@ -3244,8 +3474,7 @@
 	i = early_acpihid_map_size++;
 	memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
 	memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
-	early_acpihid_map[i].devid =
-		((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+	early_acpihid_map[i].devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
 	early_acpihid_map[i].cmd_line	= true;
 
 	return 1;
@@ -3260,7 +3489,12 @@
 
 bool amd_iommu_v2_supported(void)
 {
-	return amd_iommu_v2_present;
+	/*
+	 * Since DTE[Mode]=0 is prohibited on SNP-enabled system
+	 * (i.e. EFR[SNPSup]=1), IOMMUv2 page table cannot be used without
+	 * setting up IOMMUv1 page table.
+	 */
+	return amd_iommu_v2_present && !amd_iommu_snp_en;
 }
 EXPORT_SYMBOL(amd_iommu_v2_supported);
 
@@ -3363,3 +3597,41 @@
 
 	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
 }
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+int amd_iommu_snp_enable(void)
+{
+	/*
+	 * The SNP support requires that IOMMU must be enabled, and is
+	 * not configured in the passthrough mode.
+	 */
+	if (no_iommu || iommu_default_passthrough()) {
+		pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported");
+		return -EINVAL;
+	}
+
+	/*
+	 * Prevent enabling SNP after IOMMU_ENABLED state because this process
+	 * affect how IOMMU driver sets up data structures and configures
+	 * IOMMU hardware.
+	 */
+	if (init_state > IOMMU_ENABLED) {
+		pr_err("SNP: Too late to enable SNP for IOMMU.\n");
+		return -EINVAL;
+	}
+
+	amd_iommu_snp_en = check_feature_on_all_iommus(FEATURE_SNP);
+	if (!amd_iommu_snp_en)
+		return -EINVAL;
+
+	pr_info("SNP enabled\n");
+
+	/* Enforce IOMMU v1 pagetable when SNP is enabled. */
+	if (amd_iommu_pgtable != AMD_IOMMU_V1) {
+		pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n");
+		amd_iommu_pgtable = AMD_IOMMU_V1;
+	}
+
+	return 0;
+}
+#endif
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 6608d17..7d4b61e 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -258,7 +258,7 @@
 			__npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
 
 			/* pte could have been changed somewhere. */
-			if (cmpxchg64(pte, __pte, __npte) != __pte)
+			if (!try_cmpxchg64(pte, &__pte, __npte))
 				free_page((unsigned long)page);
 			else if (IOMMU_PTE_PRESENT(__pte))
 				*updated = true;
@@ -341,10 +341,8 @@
 	u64 *pt;
 	int mode;
 
-	while (cmpxchg64(pte, pteval, 0) != pteval) {
+	while (!try_cmpxchg64(pte, &pteval, 0))
 		pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");
-		pteval = *pte;
-	}
 
 	if (!IOMMU_PTE_PRESENT(pteval))
 		return;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 840831d..65b8e4f 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -62,9 +62,6 @@
 
 static DEFINE_SPINLOCK(pd_bitmap_lock);
 
-/* List of all available dev_data structures */
-static LLIST_HEAD(dev_data_list);
-
 LIST_HEAD(ioapic_map);
 LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
@@ -95,13 +92,6 @@
  *
  ****************************************************************************/
 
-static inline u16 get_pci_device_id(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	return pci_dev_id(pdev);
-}
-
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
@@ -122,16 +112,74 @@
 	return -EINVAL;
 }
 
-static inline int get_device_id(struct device *dev)
+static inline int get_device_sbdf_id(struct device *dev)
 {
-	int devid;
+	int sbdf;
 
 	if (dev_is_pci(dev))
-		devid = get_pci_device_id(dev);
+		sbdf = get_pci_sbdf_id(to_pci_dev(dev));
 	else
-		devid = get_acpihid_device_id(dev, NULL);
+		sbdf = get_acpihid_device_id(dev, NULL);
 
-	return devid;
+	return sbdf;
+}
+
+struct dev_table_entry *get_dev_table(struct amd_iommu *iommu)
+{
+	struct dev_table_entry *dev_table;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	BUG_ON(pci_seg == NULL);
+	dev_table = pci_seg->dev_table;
+	BUG_ON(dev_table == NULL);
+
+	return dev_table;
+}
+
+static inline u16 get_device_segment(struct device *dev)
+{
+	u16 seg;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		seg = pci_domain_nr(pdev->bus);
+	} else {
+		u32 devid = get_acpihid_device_id(dev, NULL);
+
+		seg = PCI_SBDF_TO_SEGID(devid);
+	}
+
+	return seg;
+}
+
+/* Writes the specific IOMMU for a device into the PCI segment rlookup table */
+void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid)
+{
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	pci_seg->rlookup_table[devid] = iommu;
+}
+
+static struct amd_iommu *__rlookup_amd_iommu(u16 seg, u16 devid)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id == seg)
+			return pci_seg->rlookup_table[devid];
+	}
+	return NULL;
+}
+
+static struct amd_iommu *rlookup_amd_iommu(struct device *dev)
+{
+	u16 seg = get_device_segment(dev);
+	int devid = get_device_sbdf_id(dev);
+
+	if (devid < 0)
+		return NULL;
+	return __rlookup_amd_iommu(seg, PCI_SBDF_TO_DEVID(devid));
 }
 
 static struct protection_domain *to_pdomain(struct iommu_domain *dom)
@@ -139,9 +187,10 @@
 	return container_of(dom, struct protection_domain, domain);
 }
 
-static struct iommu_dev_data *alloc_dev_data(u16 devid)
+static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_dev_data *dev_data;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 
 	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
 	if (!dev_data)
@@ -151,19 +200,20 @@
 	dev_data->devid = devid;
 	ratelimit_default_init(&dev_data->rs);
 
-	llist_add(&dev_data->dev_data_list, &dev_data_list);
+	llist_add(&dev_data->dev_data_list, &pci_seg->dev_data_list);
 	return dev_data;
 }
 
-static struct iommu_dev_data *search_dev_data(u16 devid)
+static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_dev_data *dev_data;
 	struct llist_node *node;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 
-	if (llist_empty(&dev_data_list))
+	if (llist_empty(&pci_seg->dev_data_list))
 		return NULL;
 
-	node = dev_data_list.first;
+	node = pci_seg->dev_data_list.first;
 	llist_for_each_entry(dev_data, node, dev_data_list) {
 		if (dev_data->devid == devid)
 			return dev_data;
@@ -174,67 +224,74 @@
 
 static int clone_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
+	struct amd_iommu *iommu;
+	struct dev_table_entry *dev_table;
 	u16 devid = pci_dev_id(pdev);
 
 	if (devid == alias)
 		return 0;
 
-	amd_iommu_rlookup_table[alias] =
-		amd_iommu_rlookup_table[devid];
-	memcpy(amd_iommu_dev_table[alias].data,
-	       amd_iommu_dev_table[devid].data,
-	       sizeof(amd_iommu_dev_table[alias].data));
+	iommu = rlookup_amd_iommu(&pdev->dev);
+	if (!iommu)
+		return 0;
+
+	amd_iommu_set_rlookup_table(iommu, alias);
+	dev_table = get_dev_table(iommu);
+	memcpy(dev_table[alias].data,
+	       dev_table[devid].data,
+	       sizeof(dev_table[alias].data));
 
 	return 0;
 }
 
-static void clone_aliases(struct pci_dev *pdev)
+static void clone_aliases(struct amd_iommu *iommu, struct device *dev)
 {
-	if (!pdev)
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(dev))
 		return;
+	pdev = to_pci_dev(dev);
 
 	/*
 	 * The IVRS alias stored in the alias table may not be
 	 * part of the PCI DMA aliases if it's bus differs
 	 * from the original device.
 	 */
-	clone_alias(pdev, amd_iommu_alias_table[pci_dev_id(pdev)], NULL);
+	clone_alias(pdev, iommu->pci_seg->alias_table[pci_dev_id(pdev)], NULL);
 
 	pci_for_each_dma_alias(pdev, clone_alias, NULL);
 }
 
-static struct pci_dev *setup_aliases(struct device *dev)
+static void setup_aliases(struct amd_iommu *iommu, struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 	u16 ivrs_alias;
 
 	/* For ACPI HID devices, there are no aliases */
 	if (!dev_is_pci(dev))
-		return NULL;
+		return;
 
 	/*
 	 * Add the IVRS alias to the pci aliases if it is on the same
 	 * bus. The IVRS table may know about a quirk that we don't.
 	 */
-	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
+	ivrs_alias = pci_seg->alias_table[pci_dev_id(pdev)];
 	if (ivrs_alias != pci_dev_id(pdev) &&
 	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
 		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
 
-	clone_aliases(pdev);
-
-	return pdev;
+	clone_aliases(iommu, dev);
 }
 
-static struct iommu_dev_data *find_dev_data(u16 devid)
+static struct iommu_dev_data *find_dev_data(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_dev_data *dev_data;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
-	dev_data = search_dev_data(devid);
+	dev_data = search_dev_data(iommu, devid);
 
 	if (dev_data == NULL) {
-		dev_data = alloc_dev_data(devid);
+		dev_data = alloc_dev_data(iommu, devid);
 		if (!dev_data)
 			return NULL;
 
@@ -296,42 +353,49 @@
  */
 static bool check_device(struct device *dev)
 {
-	int devid;
+	struct amd_iommu_pci_seg *pci_seg;
+	struct amd_iommu *iommu;
+	int devid, sbdf;
 
 	if (!dev)
 		return false;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return false;
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
 		return false;
 
 	/* Out of our scope? */
-	if (devid > amd_iommu_last_bdf)
-		return false;
-
-	if (amd_iommu_rlookup_table[devid] == NULL)
+	pci_seg = iommu->pci_seg;
+	if (devid > pci_seg->last_bdf)
 		return false;
 
 	return true;
 }
 
-static int iommu_init_device(struct device *dev)
+static int iommu_init_device(struct amd_iommu *iommu, struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
-	int devid;
+	int devid, sbdf;
 
 	if (dev_iommu_priv_get(dev))
 		return 0;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
-		return devid;
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return sbdf;
 
-	dev_data = find_dev_data(devid);
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	dev_data = find_dev_data(iommu, devid);
 	if (!dev_data)
 		return -ENOMEM;
 
-	dev_data->pdev = setup_aliases(dev);
+	dev_data->dev = dev;
+	setup_aliases(iommu, dev);
 
 	/*
 	 * By default we use passthrough mode for IOMMUv2 capable device.
@@ -341,9 +405,6 @@
 	 */
 	if ((iommu_default_passthrough() || !amd_iommu_force_isolation) &&
 	    dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
-		struct amd_iommu *iommu;
-
-		iommu = amd_iommu_rlookup_table[dev_data->devid];
 		dev_data->iommu_v2 = iommu->is_iommu_v2;
 	}
 
@@ -352,18 +413,21 @@
 	return 0;
 }
 
-static void iommu_ignore_device(struct device *dev)
+static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev)
 {
-	int devid;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+	int devid, sbdf;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
 		return;
 
-	amd_iommu_rlookup_table[devid] = NULL;
-	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	pci_seg->rlookup_table[devid] = NULL;
+	memset(&dev_table[devid], 0, sizeof(struct dev_table_entry));
 
-	setup_aliases(dev);
+	setup_aliases(iommu, dev);
 }
 
 static void amd_iommu_uninit_device(struct device *dev)
@@ -391,13 +455,13 @@
  *
  ****************************************************************************/
 
-static void dump_dte_entry(u16 devid)
+static void dump_dte_entry(struct amd_iommu *iommu, u16 devid)
 {
 	int i;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
 
 	for (i = 0; i < 4; ++i)
-		pr_err("DTE[%d]: %016llx\n", i,
-			amd_iommu_dev_table[devid].data[i]);
+		pr_err("DTE[%d]: %016llx\n", i, dev_table[devid].data[i]);
 }
 
 static void dump_command(unsigned long phys_addr)
@@ -409,7 +473,7 @@
 		pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
 }
 
-static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
+static void amd_iommu_report_rmp_hw_error(struct amd_iommu *iommu, volatile u32 *event)
 {
 	struct iommu_dev_data *dev_data = NULL;
 	int devid, vmg_tag, flags;
@@ -421,7 +485,7 @@
 	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	spa     = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8);
 
-	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
 					   devid & 0xff);
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
@@ -432,8 +496,8 @@
 				vmg_tag, spa, flags);
 		}
 	} else {
-		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			vmg_tag, spa, flags);
 	}
 
@@ -441,7 +505,7 @@
 		pci_dev_put(pdev);
 }
 
-static void amd_iommu_report_rmp_fault(volatile u32 *event)
+static void amd_iommu_report_rmp_fault(struct amd_iommu *iommu, volatile u32 *event)
 {
 	struct iommu_dev_data *dev_data = NULL;
 	int devid, flags_rmp, vmg_tag, flags;
@@ -454,7 +518,7 @@
 	flags     = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	gpa       = ((u64)event[3] << 32) | event[2];
 
-	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
 					   devid & 0xff);
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
@@ -465,8 +529,8 @@
 				vmg_tag, gpa, flags_rmp, flags);
 		}
 	} else {
-		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			vmg_tag, gpa, flags_rmp, flags);
 	}
 
@@ -480,13 +544,14 @@
 #define IS_WRITE_REQUEST(flags)			\
 	((flags) & EVENT_FLAG_RW)
 
-static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
+static void amd_iommu_report_page_fault(struct amd_iommu *iommu,
+					u16 devid, u16 domain_id,
 					u64 address, int flags)
 {
 	struct iommu_dev_data *dev_data = NULL;
 	struct pci_dev *pdev;
 
-	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
 					   devid & 0xff);
 	if (pdev)
 		dev_data = dev_iommu_priv_get(&pdev->dev);
@@ -511,8 +576,8 @@
 				domain_id, address, flags);
 		}
 	} else {
-		pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%04x:%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			domain_id, address, flags);
 	}
 
@@ -549,26 +614,26 @@
 	}
 
 	if (type == EVENT_TYPE_IO_FAULT) {
-		amd_iommu_report_page_fault(devid, pasid, address, flags);
+		amd_iommu_report_page_fault(iommu, devid, pasid, address, flags);
 		return;
 	}
 
 	switch (type) {
 	case EVENT_TYPE_ILL_DEV:
-		dev_err(dev, "Event logged [ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		dev_err(dev, "Event logged [ILLEGAL_DEV_TABLE_ENTRY device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
-		dump_dte_entry(devid);
+		dump_dte_entry(iommu, devid);
 		break;
 	case EVENT_TYPE_DEV_TAB_ERR:
-		dev_err(dev, "Event logged [DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
+		dev_err(dev, "Event logged [DEV_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x "
 			"address=0x%llx flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
 	case EVENT_TYPE_ILL_CMD:
@@ -580,26 +645,26 @@
 			address, flags);
 		break;
 	case EVENT_TYPE_IOTLB_INV_TO:
-		dev_err(dev, "Event logged [IOTLB_INV_TIMEOUT device=%02x:%02x.%x address=0x%llx]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		dev_err(dev, "Event logged [IOTLB_INV_TIMEOUT device=%04x:%02x:%02x.%x address=0x%llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			address);
 		break;
 	case EVENT_TYPE_INV_DEV_REQ:
-		dev_err(dev, "Event logged [INVALID_DEVICE_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		dev_err(dev, "Event logged [INVALID_DEVICE_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
 	case EVENT_TYPE_RMP_FAULT:
-		amd_iommu_report_rmp_fault(event);
+		amd_iommu_report_rmp_fault(iommu, event);
 		break;
 	case EVENT_TYPE_RMP_HW_ERR:
-		amd_iommu_report_rmp_hw_error(event);
+		amd_iommu_report_rmp_hw_error(iommu, event);
 		break;
 	case EVENT_TYPE_INV_PPR_REQ:
 		pasid = PPR_PASID(*((u64 *)__evt));
 		tag = event[1] & 0x03FF;
-		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n",
-			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags, tag);
 		break;
 	default:
@@ -636,7 +701,7 @@
 
 	fault.address   = raw[1];
 	fault.pasid     = PPR_PASID(raw[0]);
-	fault.device_id = PPR_DEVID(raw[0]);
+	fault.sbdf      = PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->id, PPR_DEVID(raw[0]));
 	fault.tag       = PPR_TAG(raw[0]);
 	fault.flags     = PPR_FLAGS(raw[0]);
 
@@ -1125,8 +1190,9 @@
 static void amd_iommu_flush_dte_all(struct amd_iommu *iommu)
 {
 	u32 devid;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
 
-	for (devid = 0; devid <= 0xffff; ++devid)
+	for (devid = 0; devid <= last_bdf; ++devid)
 		iommu_flush_dte(iommu, devid);
 
 	iommu_completion_wait(iommu);
@@ -1139,8 +1205,9 @@
 static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 {
 	u32 dom_id;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
 
-	for (dom_id = 0; dom_id <= 0xffff; ++dom_id) {
+	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 				      dom_id, 1);
@@ -1183,8 +1250,9 @@
 static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 {
 	u32 devid;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
 
-	for (devid = 0; devid <= MAX_DEV_TABLE_ENTRIES; devid++)
+	for (devid = 0; devid <= last_bdf; devid++)
 		iommu_flush_irt(iommu, devid);
 
 	iommu_completion_wait(iommu);
@@ -1212,7 +1280,9 @@
 	int qdep;
 
 	qdep     = dev_data->ats.qdep;
-	iommu    = amd_iommu_rlookup_table[dev_data->devid];
+	iommu    = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return -EINVAL;
 
 	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
 
@@ -1232,20 +1302,28 @@
 static int device_flush_dte(struct iommu_dev_data *dev_data)
 {
 	struct amd_iommu *iommu;
+	struct pci_dev *pdev = NULL;
+	struct amd_iommu_pci_seg *pci_seg;
 	u16 alias;
 	int ret;
 
-	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return -EINVAL;
 
-	if (dev_data->pdev)
-		ret = pci_for_each_dma_alias(dev_data->pdev,
+	if (dev_is_pci(dev_data->dev))
+		pdev = to_pci_dev(dev_data->dev);
+
+	if (pdev)
+		ret = pci_for_each_dma_alias(pdev,
 					     device_flush_dte_alias, iommu);
 	else
 		ret = iommu_flush_dte(iommu, dev_data->devid);
 	if (ret)
 		return ret;
 
-	alias = amd_iommu_alias_table[dev_data->devid];
+	pci_seg = iommu->pci_seg;
+	alias = pci_seg->alias_table[dev_data->devid];
 	if (alias != dev_data->devid) {
 		ret = iommu_flush_dte(iommu, alias);
 		if (ret)
@@ -1461,28 +1539,35 @@
 	free_page((unsigned long)domain->gcr3_tbl);
 }
 
-static void set_dte_entry(u16 devid, struct protection_domain *domain,
-			  bool ats, bool ppr)
+static void set_dte_entry(struct amd_iommu *iommu, u16 devid,
+			  struct protection_domain *domain, bool ats, bool ppr)
 {
 	u64 pte_root = 0;
 	u64 flags = 0;
 	u32 old_domid;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
 
 	if (domain->iop.mode != PAGE_MODE_NONE)
 		pte_root = iommu_virt_to_phys(domain->iop.root);
 
 	pte_root |= (domain->iop.mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
-	pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV;
 
-	flags = amd_iommu_dev_table[devid].data[1];
+	pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V;
+
+	/*
+	 * When SNP is enabled, Only set TV bit when IOMMU
+	 * page translation is in use.
+	 */
+	if (!amd_iommu_snp_en || (domain->id != 0))
+		pte_root |= DTE_FLAG_TV;
+
+	flags = dev_table[devid].data[1];
 
 	if (ats)
 		flags |= DTE_FLAG_IOTLB;
 
 	if (ppr) {
-		struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
-
 		if (iommu_feature(iommu, FEATURE_EPHSUP))
 			pte_root |= 1ULL << DEV_ENTRY_PPR;
 	}
@@ -1516,9 +1601,9 @@
 	flags &= ~DEV_DOMID_MASK;
 	flags |= domain->id;
 
-	old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK;
-	amd_iommu_dev_table[devid].data[1]  = flags;
-	amd_iommu_dev_table[devid].data[0]  = pte_root;
+	old_domid = dev_table[devid].data[1] & DEV_DOMID_MASK;
+	dev_table[devid].data[1]  = flags;
+	dev_table[devid].data[0]  = pte_root;
 
 	/*
 	 * A kdump kernel might be replacing a domain ID that was copied from
@@ -1526,19 +1611,23 @@
 	 * entries for the old domain ID that is being overwritten
 	 */
 	if (old_domid) {
-		struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
-
 		amd_iommu_flush_tlb_domid(iommu, old_domid);
 	}
 }
 
-static void clear_dte_entry(u16 devid)
+static void clear_dte_entry(struct amd_iommu *iommu, u16 devid)
 {
-	/* remove entry from the device table seen by the hardware */
-	amd_iommu_dev_table[devid].data[0]  = DTE_FLAG_V | DTE_FLAG_TV;
-	amd_iommu_dev_table[devid].data[1] &= DTE_FLAG_MASK;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
 
-	amd_iommu_apply_erratum_63(devid);
+	/* remove entry from the device table seen by the hardware */
+	dev_table[devid].data[0]  = DTE_FLAG_V;
+
+	if (!amd_iommu_snp_en)
+		dev_table[devid].data[0] |= DTE_FLAG_TV;
+
+	dev_table[devid].data[1] &= DTE_FLAG_MASK;
+
+	amd_iommu_apply_erratum_63(iommu, devid);
 }
 
 static void do_attach(struct iommu_dev_data *dev_data,
@@ -1547,7 +1636,9 @@
 	struct amd_iommu *iommu;
 	bool ats;
 
-	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return;
 	ats   = dev_data->ats.enabled;
 
 	/* Update data structures */
@@ -1559,9 +1650,9 @@
 	domain->dev_cnt                 += 1;
 
 	/* Update device table */
-	set_dte_entry(dev_data->devid, domain,
+	set_dte_entry(iommu, dev_data->devid, domain,
 		      ats, dev_data->iommu_v2);
-	clone_aliases(dev_data->pdev);
+	clone_aliases(iommu, dev_data->dev);
 
 	device_flush_dte(dev_data);
 }
@@ -1571,13 +1662,15 @@
 	struct protection_domain *domain = dev_data->domain;
 	struct amd_iommu *iommu;
 
-	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return;
 
 	/* Update data structures */
 	dev_data->domain = NULL;
 	list_del(&dev_data->list);
-	clear_dte_entry(dev_data->devid);
-	clone_aliases(dev_data->pdev);
+	clear_dte_entry(iommu, dev_data->devid);
+	clone_aliases(iommu, dev_data->dev);
 
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
@@ -1749,23 +1842,24 @@
 {
 	struct iommu_device *iommu_dev;
 	struct amd_iommu *iommu;
-	int ret, devid;
+	int ret;
 
 	if (!check_device(dev))
 		return ERR_PTR(-ENODEV);
 
-	devid = get_device_id(dev);
-	iommu = amd_iommu_rlookup_table[devid];
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return ERR_PTR(-ENODEV);
 
 	if (dev_iommu_priv_get(dev))
 		return &iommu->iommu;
 
-	ret = iommu_init_device(dev);
+	ret = iommu_init_device(iommu, dev);
 	if (ret) {
 		if (ret != -ENOTSUPP)
 			dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
 		iommu_dev = ERR_PTR(ret);
-		iommu_ignore_device(dev);
+		iommu_ignore_device(iommu, dev);
 	} else {
 		amd_iommu_set_pci_msi_domain(dev, iommu);
 		iommu_dev = &iommu->iommu;
@@ -1785,13 +1879,14 @@
 
 static void amd_iommu_release_device(struct device *dev)
 {
-	int devid = get_device_id(dev);
 	struct amd_iommu *iommu;
 
 	if (!check_device(dev))
 		return;
 
-	iommu = amd_iommu_rlookup_table[devid];
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return;
 
 	amd_iommu_uninit_device(dev);
 	iommu_completion_wait(iommu);
@@ -1816,9 +1911,13 @@
 	struct iommu_dev_data *dev_data;
 
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
-		set_dte_entry(dev_data->devid, domain,
+		struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev);
+
+		if (!iommu)
+			continue;
+		set_dte_entry(iommu, dev_data->devid, domain,
 			      dev_data->ats.enabled, dev_data->iommu_v2);
-		clone_aliases(dev_data->pdev);
+		clone_aliases(iommu, dev_data->dev);
 	}
 }
 
@@ -1969,6 +2068,13 @@
 {
 	struct protection_domain *domain;
 
+	/*
+	 * Since DTE[Mode]=0 is prohibited on SNP-enabled system,
+	 * default to use IOMMU_DOMAIN_DMA[_FQ].
+	 */
+	if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY))
+		return NULL;
+
 	domain = protection_domain_alloc(type);
 	if (!domain)
 		return NULL;
@@ -2004,7 +2110,6 @@
 				    struct device *dev)
 {
 	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
-	int devid = get_device_id(dev);
 	struct amd_iommu *iommu;
 
 	if (!check_device(dev))
@@ -2013,7 +2118,7 @@
 	if (dev_data->domain != NULL)
 		detach_device(dev);
 
-	iommu = amd_iommu_rlookup_table[devid];
+	iommu = rlookup_amd_iommu(dev);
 	if (!iommu)
 		return;
 
@@ -2040,7 +2145,7 @@
 	dev_data = dev_iommu_priv_get(dev);
 	dev_data->defer_attach = false;
 
-	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	iommu = rlookup_amd_iommu(dev);
 	if (!iommu)
 		return -EINVAL;
 
@@ -2169,13 +2274,21 @@
 {
 	struct iommu_resv_region *region;
 	struct unity_map_entry *entry;
-	int devid;
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+	int devid, sbdf;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
 		return;
 
-	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return;
+	pci_seg = iommu->pci_seg;
+
+	list_for_each_entry(entry, &pci_seg->unity_map, list) {
 		int type, prot = 0;
 		size_t length;
 
@@ -2280,7 +2393,6 @@
 	.probe_finalize = amd_iommu_probe_finalize,
 	.device_group = amd_iommu_device_group,
 	.get_resv_regions = amd_iommu_get_resv_regions,
-	.put_resv_regions = generic_iommu_put_resv_regions,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.def_domain_type = amd_iommu_def_domain_type,
@@ -2419,8 +2531,9 @@
 			continue;
 
 		qdep  = dev_data->ats.qdep;
-		iommu = amd_iommu_rlookup_table[dev_data->devid];
-
+		iommu = rlookup_amd_iommu(dev_data->dev);
+		if (!iommu)
+			continue;
 		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
 				      qdep, address, size);
 
@@ -2582,7 +2695,9 @@
 	struct iommu_cmd cmd;
 
 	dev_data = dev_iommu_priv_get(&pdev->dev);
-	iommu    = amd_iommu_rlookup_table[dev_data->devid];
+	iommu    = rlookup_amd_iommu(&pdev->dev);
+	if (!iommu)
+		return -ENODEV;
 
 	build_complete_ppr(&cmd, dev_data->devid, pasid, status,
 			   tag, dev_data->pri_tlp);
@@ -2644,30 +2759,35 @@
 static struct irq_chip amd_ir_chip;
 static DEFINE_SPINLOCK(iommu_table_lock);
 
-static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
+static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid,
+			      struct irq_remap_table *table)
 {
 	u64 dte;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
 
-	dte	= amd_iommu_dev_table[devid].data[2];
+	dte	= dev_table[devid].data[2];
 	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
 	dte	|= iommu_virt_to_phys(table->table);
 	dte	|= DTE_IRQ_REMAP_INTCTL;
 	dte	|= DTE_INTTABLEN;
 	dte	|= DTE_IRQ_REMAP_ENABLE;
 
-	amd_iommu_dev_table[devid].data[2] = dte;
+	dev_table[devid].data[2] = dte;
 }
 
-static struct irq_remap_table *get_irq_table(u16 devid)
+static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid)
 {
 	struct irq_remap_table *table;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
 
-	if (WARN_ONCE(!amd_iommu_rlookup_table[devid],
-		      "%s: no iommu for devid %x\n", __func__, devid))
+	if (WARN_ONCE(!pci_seg->rlookup_table[devid],
+		      "%s: no iommu for devid %x:%x\n",
+		      __func__, pci_seg->id, devid))
 		return NULL;
 
-	table = irq_lookup_table[devid];
-	if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid))
+	table = pci_seg->irq_lookup_table[devid];
+	if (WARN_ONCE(!table, "%s: no table for devid %x:%x\n",
+		      __func__, pci_seg->id, devid))
 		return NULL;
 
 	return table;
@@ -2700,8 +2820,10 @@
 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);
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	pci_seg->irq_lookup_table[devid] = table;
+	set_dte_irq_entry(iommu, devid, table);
 	iommu_flush_dte(iommu, devid);
 }
 
@@ -2709,35 +2831,38 @@
 				       void *data)
 {
 	struct irq_remap_table *table = data;
+	struct amd_iommu_pci_seg *pci_seg;
+	struct amd_iommu *iommu = rlookup_amd_iommu(&pdev->dev);
 
-	irq_lookup_table[alias] = table;
-	set_dte_irq_entry(alias, table);
+	if (!iommu)
+		return -EINVAL;
 
-	iommu_flush_dte(amd_iommu_rlookup_table[alias], alias);
+	pci_seg = iommu->pci_seg;
+	pci_seg->irq_lookup_table[alias] = table;
+	set_dte_irq_entry(iommu, alias, table);
+	iommu_flush_dte(pci_seg->rlookup_table[alias], alias);
 
 	return 0;
 }
 
-static struct irq_remap_table *alloc_irq_table(u16 devid, struct pci_dev *pdev)
+static struct irq_remap_table *alloc_irq_table(struct amd_iommu *iommu,
+					       u16 devid, struct pci_dev *pdev)
 {
 	struct irq_remap_table *table = NULL;
 	struct irq_remap_table *new_table = NULL;
-	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
 	unsigned long flags;
 	u16 alias;
 
 	spin_lock_irqsave(&iommu_table_lock, flags);
 
-	iommu = amd_iommu_rlookup_table[devid];
-	if (!iommu)
-		goto out_unlock;
-
-	table = irq_lookup_table[devid];
+	pci_seg = iommu->pci_seg;
+	table = pci_seg->irq_lookup_table[devid];
 	if (table)
 		goto out_unlock;
 
-	alias = amd_iommu_alias_table[devid];
-	table = irq_lookup_table[alias];
+	alias = pci_seg->alias_table[devid];
+	table = pci_seg->irq_lookup_table[alias];
 	if (table) {
 		set_remap_table_entry(iommu, devid, table);
 		goto out_wait;
@@ -2751,11 +2876,11 @@
 
 	spin_lock_irqsave(&iommu_table_lock, flags);
 
-	table = irq_lookup_table[devid];
+	table = pci_seg->irq_lookup_table[devid];
 	if (table)
 		goto out_unlock;
 
-	table = irq_lookup_table[alias];
+	table = pci_seg->irq_lookup_table[alias];
 	if (table) {
 		set_remap_table_entry(iommu, devid, table);
 		goto out_wait;
@@ -2786,18 +2911,14 @@
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count, bool align,
-			   struct pci_dev *pdev)
+static int alloc_irq_index(struct amd_iommu *iommu, u16 devid, int count,
+			   bool align, struct pci_dev *pdev)
 {
 	struct irq_remap_table *table;
 	int index, c, alignment = 1;
 	unsigned long flags;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
-	if (!iommu)
-		return -ENODEV;
-
-	table = alloc_irq_table(devid, pdev);
+	table = alloc_irq_table(iommu, devid, pdev);
 	if (!table)
 		return -ENODEV;
 
@@ -2836,20 +2957,15 @@
 	return index;
 }
 
-static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
-			  struct amd_ir_data *data)
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte, struct amd_ir_data *data)
 {
 	bool ret;
 	struct irq_remap_table *table;
-	struct amd_iommu *iommu;
 	unsigned long flags;
 	struct irte_ga *entry;
 
-	iommu = amd_iommu_rlookup_table[devid];
-	if (iommu == NULL)
-		return -EINVAL;
-
-	table = get_irq_table(devid);
+	table = get_irq_table(iommu, devid);
 	if (!table)
 		return -ENOMEM;
 
@@ -2880,17 +2996,13 @@
 	return 0;
 }
 
-static int modify_irte(u16 devid, int index, union irte *irte)
+static int modify_irte(struct amd_iommu *iommu,
+		       u16 devid, int index, union irte *irte)
 {
 	struct irq_remap_table *table;
-	struct amd_iommu *iommu;
 	unsigned long flags;
 
-	iommu = amd_iommu_rlookup_table[devid];
-	if (iommu == NULL)
-		return -EINVAL;
-
-	table = get_irq_table(devid);
+	table = get_irq_table(iommu, devid);
 	if (!table)
 		return -ENOMEM;
 
@@ -2904,17 +3016,12 @@
 	return 0;
 }
 
-static void free_irte(u16 devid, int index)
+static void free_irte(struct amd_iommu *iommu, u16 devid, int index)
 {
 	struct irq_remap_table *table;
-	struct amd_iommu *iommu;
 	unsigned long flags;
 
-	iommu = amd_iommu_rlookup_table[devid];
-	if (iommu == NULL)
-		return;
-
-	table = get_irq_table(devid);
+	table = get_irq_table(iommu, devid);
 	if (!table)
 		return;
 
@@ -2956,49 +3063,49 @@
 	irte->lo.fields_remap.valid       = 1;
 }
 
-static void irte_activate(void *entry, u16 devid, u16 index)
+static void irte_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
 {
 	union irte *irte = (union irte *) entry;
 
 	irte->fields.valid = 1;
-	modify_irte(devid, index, irte);
+	modify_irte(iommu, devid, index, irte);
 }
 
-static void irte_ga_activate(void *entry, u16 devid, u16 index)
+static void irte_ga_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
 {
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 1;
-	modify_irte_ga(devid, index, irte, NULL);
+	modify_irte_ga(iommu, devid, index, irte, NULL);
 }
 
-static void irte_deactivate(void *entry, u16 devid, u16 index)
+static void irte_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
 {
 	union irte *irte = (union irte *) entry;
 
 	irte->fields.valid = 0;
-	modify_irte(devid, index, irte);
+	modify_irte(iommu, devid, index, irte);
 }
 
-static void irte_ga_deactivate(void *entry, u16 devid, u16 index)
+static void irte_ga_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
 {
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 0;
-	modify_irte_ga(devid, index, irte, NULL);
+	modify_irte_ga(iommu, devid, index, irte, NULL);
 }
 
-static void irte_set_affinity(void *entry, u16 devid, u16 index,
+static void irte_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index,
 			      u8 vector, u32 dest_apicid)
 {
 	union irte *irte = (union irte *) entry;
 
 	irte->fields.vector = vector;
 	irte->fields.destination = dest_apicid;
-	modify_irte(devid, index, irte);
+	modify_irte(iommu, devid, index, irte);
 }
 
-static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
+static void irte_ga_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index,
 				 u8 vector, u32 dest_apicid)
 {
 	struct irte_ga *irte = (struct irte_ga *) entry;
@@ -3009,7 +3116,7 @@
 					APICID_TO_IRTE_DEST_LO(dest_apicid);
 		irte->hi.fields.destination =
 					APICID_TO_IRTE_DEST_HI(dest_apicid);
-		modify_irte_ga(devid, index, irte, NULL);
+		modify_irte_ga(iommu, devid, index, irte, NULL);
 	}
 }
 
@@ -3068,7 +3175,7 @@
 		return get_hpet_devid(info->devid);
 	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
 	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
-		return get_device_id(msi_desc_to_dev(info->desc));
+		return get_device_sbdf_id(msi_desc_to_dev(info->desc));
 	default:
 		WARN_ON_ONCE(1);
 		return -1;
@@ -3097,7 +3204,7 @@
 				       int devid, int index, int sub_handle)
 {
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+	struct amd_iommu *iommu = data->iommu;
 
 	if (!iommu)
 		return;
@@ -3148,8 +3255,9 @@
 	struct irq_alloc_info *info = arg;
 	struct irq_data *irq_data;
 	struct amd_ir_data *data = NULL;
+	struct amd_iommu *iommu;
 	struct irq_cfg *cfg;
-	int i, ret, devid;
+	int i, ret, devid, seg, sbdf;
 	int index;
 
 	if (!info)
@@ -3165,8 +3273,14 @@
 	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
 		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
 
-	devid = get_devid(info);
-	if (devid < 0)
+	sbdf = get_devid(info);
+	if (sbdf < 0)
+		return -EINVAL;
+
+	seg = PCI_SBDF_TO_SEGID(sbdf);
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	iommu = __rlookup_amd_iommu(seg, devid);
+	if (!iommu)
 		return -EINVAL;
 
 	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
@@ -3175,9 +3289,8 @@
 
 	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
 		struct irq_remap_table *table;
-		struct amd_iommu *iommu;
 
-		table = alloc_irq_table(devid, NULL);
+		table = alloc_irq_table(iommu, devid, NULL);
 		if (table) {
 			if (!table->min_index) {
 				/*
@@ -3185,7 +3298,6 @@
 				 * interrupts.
 				 */
 				table->min_index = 32;
-				iommu = amd_iommu_rlookup_table[devid];
 				for (i = 0; i < 32; ++i)
 					iommu->irte_ops->set_allocated(table, i);
 			}
@@ -3198,10 +3310,10 @@
 		   info->type == X86_IRQ_ALLOC_TYPE_PCI_MSIX) {
 		bool align = (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI);
 
-		index = alloc_irq_index(devid, nr_irqs, align,
+		index = alloc_irq_index(iommu, devid, nr_irqs, align,
 					msi_desc_to_pci_dev(info->desc));
 	} else {
-		index = alloc_irq_index(devid, nr_irqs, false, NULL);
+		index = alloc_irq_index(iommu, devid, nr_irqs, false, NULL);
 	}
 
 	if (index < 0) {
@@ -3233,6 +3345,7 @@
 			goto out_free_data;
 		}
 
+		data->iommu = iommu;
 		irq_data->hwirq = (devid << 16) + i;
 		irq_data->chip_data = data;
 		irq_data->chip = &amd_ir_chip;
@@ -3249,7 +3362,7 @@
 			kfree(irq_data->chip_data);
 	}
 	for (i = 0; i < nr_irqs; i++)
-		free_irte(devid, index + i);
+		free_irte(iommu, devid, index + i);
 out_free_parent:
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 	return ret;
@@ -3268,7 +3381,7 @@
 		if (irq_data && irq_data->chip_data) {
 			data = irq_data->chip_data;
 			irte_info = &data->irq_2_irte;
-			free_irte(irte_info->devid, irte_info->index);
+			free_irte(data->iommu, irte_info->devid, irte_info->index);
 			kfree(data->entry);
 			kfree(data);
 		}
@@ -3286,13 +3399,13 @@
 {
 	struct amd_ir_data *data = irq_data->chip_data;
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
+	struct amd_iommu *iommu = data->iommu;
 	struct irq_cfg *cfg = irqd_cfg(irq_data);
 
 	if (!iommu)
 		return 0;
 
-	iommu->irte_ops->activate(data->entry, irte_info->devid,
+	iommu->irte_ops->activate(iommu, data->entry, irte_info->devid,
 				  irte_info->index);
 	amd_ir_update_irte(irq_data, iommu, data, irte_info, cfg);
 	return 0;
@@ -3303,10 +3416,10 @@
 {
 	struct amd_ir_data *data = irq_data->chip_data;
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
+	struct amd_iommu *iommu = data->iommu;
 
 	if (iommu)
-		iommu->irte_ops->deactivate(data->entry, irte_info->devid,
+		iommu->irte_ops->deactivate(iommu, data->entry, irte_info->devid,
 					    irte_info->index);
 }
 
@@ -3326,8 +3439,8 @@
 
 	if (devid < 0)
 		return 0;
+	iommu = __rlookup_amd_iommu((devid >> 16), (devid & 0xffff));
 
-	iommu = amd_iommu_rlookup_table[devid];
 	return iommu && iommu->ir_domain == d;
 }
 
@@ -3361,7 +3474,7 @@
 	entry->hi.fields.vector            = ir_data->ga_vector;
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
-	return modify_irte_ga(ir_data->irq_2_irte.devid,
+	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
@@ -3391,7 +3504,7 @@
 	entry->hi.fields.destination =
 				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
 
-	return modify_irte_ga(ir_data->irq_2_irte.devid,
+	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
@@ -3399,12 +3512,16 @@
 static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 {
 	int ret;
-	struct amd_iommu *iommu;
 	struct amd_iommu_pi_data *pi_data = vcpu_info;
 	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
 	struct amd_ir_data *ir_data = data->chip_data;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
-	struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid);
+	struct iommu_dev_data *dev_data;
+
+	if (ir_data->iommu == NULL)
+		return -EINVAL;
+
+	dev_data = search_dev_data(ir_data->iommu, irte_info->devid);
 
 	/* Note:
 	 * This device has never been set up for guest mode.
@@ -3426,10 +3543,6 @@
 		pi_data->is_guest_mode = false;
 	}
 
-	iommu = amd_iommu_rlookup_table[irte_info->devid];
-	if (iommu == NULL)
-		return -EINVAL;
-
 	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {
 		ir_data->ga_root_ptr = (pi_data->base >> 12);
@@ -3463,7 +3576,7 @@
 	 * Atomically updates the IRTE with the new destination, vector
 	 * and flushes the interrupt entry cache.
 	 */
-	iommu->irte_ops->set_affinity(ir_data->entry, irte_info->devid,
+	iommu->irte_ops->set_affinity(iommu, ir_data->entry, irte_info->devid,
 				      irte_info->index, cfg->vector,
 				      cfg->dest_apicid);
 }
@@ -3475,7 +3588,7 @@
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct irq_cfg *cfg = irqd_cfg(data);
 	struct irq_data *parent = data->parent_data;
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
+	struct amd_iommu *iommu = ir_data->iommu;
 	int ret;
 
 	if (!iommu)
@@ -3545,11 +3658,11 @@
 	    !ref || !entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
-	iommu = amd_iommu_rlookup_table[devid];
+	iommu = ir_data->iommu;
 	if (!iommu)
 		return -ENODEV;
 
-	table = get_irq_table(devid);
+	table = get_irq_table(iommu, devid);
 	if (!table)
 		return -ENODEV;
 
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index afb3efd..696d555 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -51,7 +51,7 @@
 
 struct device_state {
 	struct list_head list;
-	u16 devid;
+	u32 sbdf;
 	atomic_t count;
 	struct pci_dev *pdev;
 	struct pasid_state **states;
@@ -83,35 +83,25 @@
 
 static void free_pasid_states(struct device_state *dev_state);
 
-static u16 device_id(struct pci_dev *pdev)
-{
-	u16 devid;
-
-	devid = pdev->bus->number;
-	devid = (devid << 8) | pdev->devfn;
-
-	return devid;
-}
-
-static struct device_state *__get_device_state(u16 devid)
+static struct device_state *__get_device_state(u32 sbdf)
 {
 	struct device_state *dev_state;
 
 	list_for_each_entry(dev_state, &state_list, list) {
-		if (dev_state->devid == devid)
+		if (dev_state->sbdf == sbdf)
 			return dev_state;
 	}
 
 	return NULL;
 }
 
-static struct device_state *get_device_state(u16 devid)
+static struct device_state *get_device_state(u32 sbdf)
 {
 	struct device_state *dev_state;
 	unsigned long flags;
 
 	spin_lock_irqsave(&state_lock, flags);
-	dev_state = __get_device_state(devid);
+	dev_state = __get_device_state(sbdf);
 	if (dev_state != NULL)
 		atomic_inc(&dev_state->count);
 	spin_unlock_irqrestore(&state_lock, flags);
@@ -528,15 +518,16 @@
 	unsigned long flags;
 	struct fault *fault;
 	bool finish;
-	u16 tag, devid;
+	u16 tag, devid, seg_id;
 	int ret;
 
 	iommu_fault = data;
 	tag         = iommu_fault->tag & 0x1ff;
 	finish      = (iommu_fault->tag >> 9) & 1;
 
-	devid = iommu_fault->device_id;
-	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+	seg_id = PCI_SBDF_TO_SEGID(iommu_fault->sbdf);
+	devid = PCI_SBDF_TO_DEVID(iommu_fault->sbdf);
+	pdev = pci_get_domain_bus_and_slot(seg_id, PCI_BUS_NUM(devid),
 					   devid & 0xff);
 	if (!pdev)
 		return -ENODEV;
@@ -550,7 +541,7 @@
 		goto out;
 	}
 
-	dev_state = get_device_state(iommu_fault->device_id);
+	dev_state = get_device_state(iommu_fault->sbdf);
 	if (dev_state == NULL)
 		goto out;
 
@@ -609,7 +600,7 @@
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
 	struct mm_struct *mm;
-	u16 devid;
+	u32 sbdf;
 	int ret;
 
 	might_sleep();
@@ -617,8 +608,8 @@
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;
 
-	devid     = device_id(pdev);
-	dev_state = get_device_state(devid);
+	sbdf      = get_pci_sbdf_id(pdev);
+	dev_state = get_device_state(sbdf);
 
 	if (dev_state == NULL)
 		return -EINVAL;
@@ -692,15 +683,15 @@
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
-	u16 devid;
+	u32 sbdf;
 
 	might_sleep();
 
 	if (!amd_iommu_v2_supported())
 		return;
 
-	devid = device_id(pdev);
-	dev_state = get_device_state(devid);
+	sbdf = get_pci_sbdf_id(pdev);
+	dev_state = get_device_state(sbdf);
 	if (dev_state == NULL)
 		return;
 
@@ -742,7 +733,7 @@
 	struct iommu_group *group;
 	unsigned long flags;
 	int ret, tmp;
-	u16 devid;
+	u32 sbdf;
 
 	might_sleep();
 
@@ -759,7 +750,7 @@
 	if (pasids <= 0 || pasids > (PASID_MASK + 1))
 		return -EINVAL;
 
-	devid = device_id(pdev);
+	sbdf = get_pci_sbdf_id(pdev);
 
 	dev_state = kzalloc(sizeof(*dev_state), GFP_KERNEL);
 	if (dev_state == NULL)
@@ -768,7 +759,7 @@
 	spin_lock_init(&dev_state->lock);
 	init_waitqueue_head(&dev_state->wq);
 	dev_state->pdev  = pdev;
-	dev_state->devid = devid;
+	dev_state->sbdf = sbdf;
 
 	tmp = pasids;
 	for (dev_state->pasid_levels = 0; (tmp - 1) & ~0x1ff; tmp >>= 9)
@@ -806,7 +797,7 @@
 
 	spin_lock_irqsave(&state_lock, flags);
 
-	if (__get_device_state(devid) != NULL) {
+	if (__get_device_state(sbdf) != NULL) {
 		spin_unlock_irqrestore(&state_lock, flags);
 		ret = -EBUSY;
 		goto out_free_domain;
@@ -838,16 +829,16 @@
 {
 	struct device_state *dev_state;
 	unsigned long flags;
-	u16 devid;
+	u32 sbdf;
 
 	if (!amd_iommu_v2_supported())
 		return;
 
-	devid = device_id(pdev);
+	sbdf = get_pci_sbdf_id(pdev);
 
 	spin_lock_irqsave(&state_lock, flags);
 
-	dev_state = __get_device_state(devid);
+	dev_state = __get_device_state(sbdf);
 	if (dev_state == NULL) {
 		spin_unlock_irqrestore(&state_lock, flags);
 		return;
@@ -867,18 +858,18 @@
 {
 	struct device_state *dev_state;
 	unsigned long flags;
-	u16 devid;
+	u32 sbdf;
 	int ret;
 
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;
 
-	devid = device_id(pdev);
+	sbdf = get_pci_sbdf_id(pdev);
 
 	spin_lock_irqsave(&state_lock, flags);
 
 	ret = -EINVAL;
-	dev_state = __get_device_state(devid);
+	dev_state = __get_device_state(sbdf);
 	if (dev_state == NULL)
 		goto out_unlock;
 
@@ -898,18 +889,18 @@
 {
 	struct device_state *dev_state;
 	unsigned long flags;
-	u16 devid;
+	u32 sbdf;
 	int ret;
 
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;
 
-	devid = device_id(pdev);
+	sbdf = get_pci_sbdf_id(pdev);
 
 	spin_lock_irqsave(&state_lock, flags);
 
 	ret = -EINVAL;
-	dev_state = __get_device_state(devid);
+	dev_state = __get_device_state(sbdf);
 	if (dev_state == NULL)
 		goto out_unlock;
 
diff --git a/drivers/iommu/amd/quirks.c b/drivers/iommu/amd/quirks.c
index 5120ce4..79dbb8f 100644
--- a/drivers/iommu/amd/quirks.c
+++ b/drivers/iommu/amd/quirks.c
@@ -15,7 +15,7 @@
 
 struct ivrs_quirk_entry {
 	u8 id;
-	u16 devid;
+	u32 devid;
 };
 
 enum {
@@ -49,7 +49,7 @@
 	const struct ivrs_quirk_entry *i;
 
 	for (i = d->driver_data; i->id != 0 && i->devid != 0; i++)
-		add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u16 *)&i->devid, 0);
+		add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u32 *)&i->devid, 0);
 
 	return 0;
 }
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 8af0242..1b17257 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -564,9 +564,6 @@
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	if (!cfg)
-		return;
-
 	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
@@ -771,7 +768,6 @@
 	.of_xlate = apple_dart_of_xlate,
 	.def_domain_type = apple_dart_def_domain_type,
 	.get_resv_regions = apple_dart_get_resv_regions,
-	.put_resv_regions = generic_iommu_put_resv_regions,
 	.pgsize_bitmap = -1UL, /* Restricted during dart probe */
 	.owner = THIS_MODULE,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 88817a3..d32b023 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1380,12 +1380,21 @@
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent)
+static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
 {
 	unsigned int i;
+	u64 val = STRTAB_STE_0_V;
+
+	if (disable_bypass && !force)
+		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT);
+	else
+		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		arm_smmu_write_strtab_ent(NULL, -1, strtab);
+		strtab[0] = cpu_to_le64(val);
+		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+						   STRTAB_STE_1_SHCFG_INCOMING));
+		strtab[2] = 0;
 		strtab += STRTAB_STE_DWORDS;
 	}
 }
@@ -1413,7 +1422,7 @@
 		return -ENOMEM;
 	}
 
-	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
+	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT, false);
 	arm_smmu_write_strtab_l1_desc(strtab, desc);
 	return 0;
 }
@@ -2537,6 +2546,19 @@
 	return sid < limit;
 }
 
+static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+	/* Check the SIDs are in range of the SMMU and our stream table */
+	if (!arm_smmu_sid_in_range(smmu, sid))
+		return -ERANGE;
+
+	/* Ensure l2 strtab is initialised */
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		return arm_smmu_init_l2_strtab(smmu, sid);
+
+	return 0;
+}
+
 static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 				  struct arm_smmu_master *master)
 {
@@ -2560,20 +2582,9 @@
 		new_stream->id = sid;
 		new_stream->master = master;
 
-		/*
-		 * Check the SIDs are in range of the SMMU and our stream table
-		 */
-		if (!arm_smmu_sid_in_range(smmu, sid)) {
-			ret = -ERANGE;
+		ret = arm_smmu_init_sid_strtab(smmu, sid);
+		if (ret)
 			break;
-		}
-
-		/* Ensure l2 strtab is initialised */
-		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-			ret = arm_smmu_init_l2_strtab(smmu, sid);
-			if (ret)
-				break;
-		}
 
 		/* Insert into SID tree */
 		new_node = &(smmu->streams.rb_node);
@@ -2691,20 +2702,14 @@
 
 static void arm_smmu_release_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct arm_smmu_master *master;
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return;
-
-	master = dev_iommu_priv_get(dev);
 	if (WARN_ON(arm_smmu_master_sva_enabled(master)))
 		iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
 	arm_smmu_detach_dev(master);
 	arm_smmu_disable_pasid(master);
 	arm_smmu_remove_master(master);
 	kfree(master);
-	iommu_fwspec_free(dev);
 }
 
 static struct iommu_group *arm_smmu_device_group(struct device *dev)
@@ -2760,58 +2765,27 @@
 	iommu_dma_get_resv_regions(dev, head);
 }
 
-static bool arm_smmu_dev_has_feature(struct device *dev,
-				     enum iommu_dev_features feat)
-{
-	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
-
-	if (!master)
-		return false;
-
-	switch (feat) {
-	case IOMMU_DEV_FEAT_IOPF:
-		return arm_smmu_master_iopf_supported(master);
-	case IOMMU_DEV_FEAT_SVA:
-		return arm_smmu_master_sva_supported(master);
-	default:
-		return false;
-	}
-}
-
-static bool arm_smmu_dev_feature_enabled(struct device *dev,
-					 enum iommu_dev_features feat)
-{
-	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
-
-	if (!master)
-		return false;
-
-	switch (feat) {
-	case IOMMU_DEV_FEAT_IOPF:
-		return master->iopf_enabled;
-	case IOMMU_DEV_FEAT_SVA:
-		return arm_smmu_master_sva_enabled(master);
-	default:
-		return false;
-	}
-}
-
 static int arm_smmu_dev_enable_feature(struct device *dev,
 				       enum iommu_dev_features feat)
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 
-	if (!arm_smmu_dev_has_feature(dev, feat))
+	if (!master)
 		return -ENODEV;
 
-	if (arm_smmu_dev_feature_enabled(dev, feat))
-		return -EBUSY;
-
 	switch (feat) {
 	case IOMMU_DEV_FEAT_IOPF:
+		if (!arm_smmu_master_iopf_supported(master))
+			return -EINVAL;
+		if (master->iopf_enabled)
+			return -EBUSY;
 		master->iopf_enabled = true;
 		return 0;
 	case IOMMU_DEV_FEAT_SVA:
+		if (!arm_smmu_master_sva_supported(master))
+			return -EINVAL;
+		if (arm_smmu_master_sva_enabled(master))
+			return -EBUSY;
 		return arm_smmu_master_enable_sva(master);
 	default:
 		return -EINVAL;
@@ -2823,16 +2797,20 @@
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 
-	if (!arm_smmu_dev_feature_enabled(dev, feat))
+	if (!master)
 		return -EINVAL;
 
 	switch (feat) {
 	case IOMMU_DEV_FEAT_IOPF:
+		if (!master->iopf_enabled)
+			return -EINVAL;
 		if (master->sva_enabled)
 			return -EBUSY;
 		master->iopf_enabled = false;
 		return 0;
 	case IOMMU_DEV_FEAT_SVA:
+		if (!arm_smmu_master_sva_enabled(master))
+			return -EINVAL;
 		return arm_smmu_master_disable_sva(master);
 	default:
 		return -EINVAL;
@@ -2847,9 +2825,6 @@
 	.device_group		= arm_smmu_device_group,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
-	.put_resv_regions	= generic_iommu_put_resv_regions,
-	.dev_has_feat		= arm_smmu_dev_has_feature,
-	.dev_feat_enabled	= arm_smmu_dev_feature_enabled,
 	.dev_enable_feat	= arm_smmu_dev_enable_feature,
 	.dev_disable_feat	= arm_smmu_dev_disable_feature,
 	.sva_bind		= arm_smmu_sva_bind,
@@ -3049,7 +3024,7 @@
 	reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits);
 	cfg->strtab_base_cfg = reg;
 
-	arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents);
+	arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents, false);
 	return 0;
 }
 
@@ -3743,6 +3718,36 @@
 	return devm_ioremap_resource(dev, &res);
 }
 
+static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
+{
+	struct list_head rmr_list;
+	struct iommu_resv_region *e;
+
+	INIT_LIST_HEAD(&rmr_list);
+	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+
+	list_for_each_entry(e, &rmr_list, list) {
+		__le64 *step;
+		struct iommu_iort_rmr_data *rmr;
+		int ret, i;
+
+		rmr = container_of(e, struct iommu_iort_rmr_data, rr);
+		for (i = 0; i < rmr->num_sids; i++) {
+			ret = arm_smmu_init_sid_strtab(smmu, rmr->sids[i]);
+			if (ret) {
+				dev_err(smmu->dev, "RMR SID(0x%x) bypass failed\n",
+					rmr->sids[i]);
+				continue;
+			}
+
+			step = arm_smmu_get_step_for_sid(smmu, rmr->sids[i]);
+			arm_smmu_init_bypass_stes(step, 1, true);
+		}
+	}
+
+	iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+}
+
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	int irq, ret;
@@ -3826,6 +3831,9 @@
 	/* Record our private device structure */
 	platform_set_drvdata(pdev, smmu);
 
+	/* Check for RMRs and install bypass STEs if any */
+	arm_smmu_rmr_install_bypass_ste(smmu);
+
 	/* Reset the device */
 	ret = arm_smmu_device_reset(smmu, bypass);
 	if (ret)
diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile
index b0cc01a..2a5a95e 100644
--- a/drivers/iommu/arm/arm-smmu/Makefile
+++ b/drivers/iommu/arm/arm-smmu/Makefile
@@ -3,3 +3,4 @@
 obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
 arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o
 arm_smmu-$(CONFIG_ARM_SMMU_QCOM) += arm-smmu-qcom.o
+arm_smmu-$(CONFIG_ARM_SMMU_QCOM_DEBUG) += arm-smmu-qcom-debug.o
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
new file mode 100644
index 0000000..6eed8e6
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/of_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/ratelimit.h>
+
+#include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
+
+enum qcom_smmu_impl_reg_offset {
+	QCOM_SMMU_TBU_PWR_STATUS,
+	QCOM_SMMU_STATS_SYNC_INV_TBU_ACK,
+	QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR,
+};
+
+struct qcom_smmu_config {
+	const u32 *reg_offset;
+};
+
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu)
+{
+	int ret;
+	u32 tbu_pwr_status, sync_inv_ack, sync_inv_progress;
+	struct qcom_smmu *qsmmu = container_of(smmu, struct qcom_smmu, smmu);
+	const struct qcom_smmu_config *cfg;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	if (__ratelimit(&rs)) {
+		dev_err(smmu->dev, "TLB sync timed out -- SMMU may be deadlocked\n");
+
+		cfg = qsmmu->cfg;
+		if (!cfg)
+			return;
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_TBU_PWR_STATUS],
+					&tbu_pwr_status);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU power status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK],
+					&sync_inv_ack);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU sync/inv ack status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR],
+					&sync_inv_progress);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TCU syn/inv progress: %d\n", ret);
+
+		dev_err(smmu->dev,
+			"TBU: power_status %#x sync_inv_ack %#x sync_inv_progress %#x\n",
+			tbu_pwr_status, sync_inv_ack, sync_inv_progress);
+	}
+}
+
+/* Implementation Defined Register Space 0 register offsets */
+static const u32 qcom_smmu_impl0_reg_offset[] = {
+	[QCOM_SMMU_TBU_PWR_STATUS]		= 0x2204,
+	[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK]	= 0x25dc,
+	[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR]	= 0x2670,
+};
+
+static const struct qcom_smmu_config qcm2290_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7180_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7280_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8180x_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8280xp_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6125_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8150_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8250_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8450_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct of_device_id __maybe_unused qcom_smmu_impl_debug_match[] = {
+	{ .compatible = "qcom,msm8998-smmu-v2" },
+	{ .compatible = "qcom,qcm2290-smmu-500", .data = &qcm2290_smmu_cfg },
+	{ .compatible = "qcom,sc7180-smmu-500", .data = &sc7180_smmu_cfg },
+	{ .compatible = "qcom,sc7280-smmu-500", .data = &sc7280_smmu_cfg},
+	{ .compatible = "qcom,sc8180x-smmu-500", .data = &sc8180x_smmu_cfg },
+	{ .compatible = "qcom,sc8280xp-smmu-500", .data = &sc8280xp_smmu_cfg },
+	{ .compatible = "qcom,sdm630-smmu-v2" },
+	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm6125-smmu-500", .data = &sm6125_smmu_cfg},
+	{ .compatible = "qcom,sm6350-smmu-500", .data = &sm6350_smmu_cfg},
+	{ .compatible = "qcom,sm8150-smmu-500", .data = &sm8150_smmu_cfg },
+	{ .compatible = "qcom,sm8250-smmu-500", .data = &sm8250_smmu_cfg },
+	{ .compatible = "qcom,sm8350-smmu-500", .data = &sm8350_smmu_cfg },
+	{ .compatible = "qcom,sm8450-smmu-500", .data = &sm8450_smmu_cfg },
+	{ }
+};
+
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	const struct of_device_id *match;
+	const struct device_node *np = smmu->dev->of_node;
+
+	match = of_match_node(qcom_smmu_impl_debug_match, np);
+	if (!match)
+		return NULL;
+
+	return match->data;
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 7820711..b2708de 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -5,23 +5,40 @@
 
 #include <linux/acpi.h>
 #include <linux/adreno-smmu-priv.h>
+#include <linux/delay.h>
 #include <linux/of_device.h>
 #include <linux/qcom_scm.h>
 
 #include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
 
-struct qcom_smmu {
-	struct arm_smmu_device smmu;
-	bool bypass_quirk;
-	u8 bypass_cbndx;
-	u32 stall_enabled;
-};
+#define QCOM_DUMMY_VAL	-1
 
 static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
 {
 	return container_of(smmu, struct qcom_smmu, smmu);
 }
 
+static void qcom_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+				int sync, int status)
+{
+	unsigned int spin_cnt, delay;
+	u32 reg;
+
+	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = arm_smmu_readl(smmu, page, status);
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+
+	qcom_smmu_tlb_sync_debug(smmu);
+}
+
 static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx,
 		u32 reg)
 {
@@ -233,6 +250,7 @@
 	{ .compatible = "qcom,sc7280-mdss" },
 	{ .compatible = "qcom,sc7280-mss-pil" },
 	{ .compatible = "qcom,sc8180x-mdss" },
+	{ .compatible = "qcom,sm8250-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
 	{ }
@@ -374,6 +392,7 @@
 	.def_domain_type = qcom_smmu_def_domain_type,
 	.reset = qcom_smmu500_reset,
 	.write_s2cr = qcom_smmu_write_s2cr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
@@ -382,6 +401,7 @@
 	.reset = qcom_smmu500_reset,
 	.alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
 	.write_sctlr = qcom_adreno_smmu_write_sctlr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
@@ -398,6 +418,7 @@
 		return ERR_PTR(-ENOMEM);
 
 	qsmmu->smmu.impl = impl;
+	qsmmu->cfg = qcom_smmu_impl_data(smmu);
 
 	return &qsmmu->smmu;
 }
@@ -413,6 +434,7 @@
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
 	{ .compatible = "qcom,sm6350-smmu-500" },
+	{ .compatible = "qcom,sm6375-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
new file mode 100644
index 0000000..99ec8f8
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _ARM_SMMU_QCOM_H
+#define _ARM_SMMU_QCOM_H
+
+struct qcom_smmu {
+	struct arm_smmu_device smmu;
+	const struct qcom_smmu_config *cfg;
+	bool bypass_quirk;
+	u8 bypass_cbndx;
+	u32 stall_enabled;
+};
+
+#ifdef CONFIG_ARM_SMMU_QCOM_DEBUG
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu);
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu);
+#else
+static inline void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) { }
+static inline const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _ARM_SMMU_QCOM_H */
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 2ed3594..dfa82df 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1432,27 +1432,19 @@
 static void arm_smmu_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct arm_smmu_master_cfg *cfg;
-	struct arm_smmu_device *smmu;
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
 	int ret;
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return;
-
-	cfg  = dev_iommu_priv_get(dev);
-	smmu = cfg->smmu;
-
-	ret = arm_smmu_rpm_get(smmu);
+	ret = arm_smmu_rpm_get(cfg->smmu);
 	if (ret < 0)
 		return;
 
 	arm_smmu_master_free_smes(cfg, fwspec);
 
-	arm_smmu_rpm_put(smmu);
+	arm_smmu_rpm_put(cfg->smmu);
 
 	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
-	iommu_fwspec_free(dev);
 }
 
 static void arm_smmu_probe_finalize(struct device *dev)
@@ -1592,7 +1584,6 @@
 	.device_group		= arm_smmu_device_group,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
-	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.def_domain_type	= arm_smmu_def_domain_type,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
@@ -2071,10 +2062,57 @@
 	return err;
 }
 
+static void arm_smmu_rmr_install_bypass_smr(struct arm_smmu_device *smmu)
+{
+	struct list_head rmr_list;
+	struct iommu_resv_region *e;
+	int idx, cnt = 0;
+	u32 reg;
+
+	INIT_LIST_HEAD(&rmr_list);
+	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+
+	/*
+	 * Rather than trying to look at existing mappings that
+	 * are setup by the firmware and then invalidate the ones
+	 * that do no have matching RMR entries, just disable the
+	 * SMMU until it gets enabled again in the reset routine.
+	 */
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
+	reg |= ARM_SMMU_sCR0_CLIENTPD;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, reg);
+
+	list_for_each_entry(e, &rmr_list, list) {
+		struct iommu_iort_rmr_data *rmr;
+		int i;
+
+		rmr = container_of(e, struct iommu_iort_rmr_data, rr);
+		for (i = 0; i < rmr->num_sids; i++) {
+			idx = arm_smmu_find_sme(smmu, rmr->sids[i], ~0);
+			if (idx < 0)
+				continue;
+
+			if (smmu->s2crs[idx].count == 0) {
+				smmu->smrs[idx].id = rmr->sids[i];
+				smmu->smrs[idx].mask = 0;
+				smmu->smrs[idx].valid = true;
+			}
+			smmu->s2crs[idx].count++;
+			smmu->s2crs[idx].type = S2CR_TYPE_BYPASS;
+			smmu->s2crs[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
+
+			cnt++;
+		}
+	}
+
+	dev_notice(smmu->dev, "\tpreserved %d boot mapping%s\n", cnt,
+		   cnt == 1 ? "" : "s");
+	iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+}
+
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	struct resource *res;
-	resource_size_t ioaddr;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
@@ -2098,7 +2136,8 @@
 	smmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
-	ioaddr = res->start;
+	smmu->ioaddr = res->start;
+
 	/*
 	 * The resource size should effectively match the value of SMMU_TOP;
 	 * stash that temporarily until we know PAGESIZE to validate it with.
@@ -2178,7 +2217,7 @@
 	}
 
 	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
-				     "smmu.%pa", &ioaddr);
+				     "smmu.%pa", &smmu->ioaddr);
 	if (err) {
 		dev_err(dev, "Failed to register iommu in sysfs\n");
 		return err;
@@ -2191,6 +2230,10 @@
 	}
 
 	platform_set_drvdata(pdev, smmu);
+
+	/* Check for RMRs and install bypass SMRs if any */
+	arm_smmu_rmr_install_bypass_smr(smmu);
+
 	arm_smmu_device_reset(smmu);
 	arm_smmu_test_smr_masks(smmu);
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 2b9b42f..703fd58 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -278,6 +278,7 @@
 	struct device			*dev;
 
 	void __iomem			*base;
+	phys_addr_t			ioaddr;
 	unsigned int			numpage;
 	unsigned int			pgshift;
 
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 4c077c3..1723511 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -532,16 +532,6 @@
 	return &qcom_iommu->iommu;
 }
 
-static void qcom_iommu_release_device(struct device *dev)
-{
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
-
-	if (!qcom_iommu)
-		return;
-
-	iommu_fwspec_free(dev);
-}
-
 static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 {
 	struct qcom_iommu_dev *qcom_iommu;
@@ -591,7 +581,6 @@
 	.capable	= qcom_iommu_capable,
 	.domain_alloc	= qcom_iommu_domain_alloc,
 	.probe_device	= qcom_iommu_probe_device,
-	.release_device	= qcom_iommu_release_device,
 	.device_group	= generic_device_group,
 	.of_xlate	= qcom_iommu_of_xlate,
 	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
@@ -750,9 +739,12 @@
 {
 	struct device_node *child;
 
-	for_each_child_of_node(qcom_iommu->dev->of_node, child)
-		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec"))
+	for_each_child_of_node(qcom_iommu->dev->of_node, child) {
+		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec")) {
+			of_node_put(child);
 			return true;
+		}
+	}
 
 	return false;
 }
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f9025157..458fb67 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -64,10 +64,11 @@
 
 	/* Domain for flush queue callback; NULL if flush queue not in use */
 	struct iommu_domain		*fq_domain;
+	struct mutex			mutex;
 };
 
 static DEFINE_STATIC_KEY_FALSE(iommu_deferred_attach_enabled);
-bool iommu_dma_forcedac __read_mostly;
+bool iommu_dma_forcedac __read_mostly = !IS_ENABLED(CONFIG_IOMMU_DMA_PCI_SAC);
 
 static int __init iommu_dma_forcedac_setup(char *str)
 {
@@ -310,6 +311,7 @@
 	if (!domain->iova_cookie)
 		return -ENOMEM;
 
+	mutex_init(&domain->iova_cookie->mutex);
 	return 0;
 }
 
@@ -385,7 +387,7 @@
 {
 
 	if (!is_of_node(dev_iommu_fwspec_get(dev)->iommu_fwnode))
-		iort_iommu_msi_get_resv_regions(dev, list);
+		iort_iommu_get_resv_regions(dev, list);
 
 }
 EXPORT_SYMBOL(iommu_dma_get_resv_regions);
@@ -560,26 +562,33 @@
 	}
 
 	/* start_pfn is always nonzero for an already-initialised domain */
+	mutex_lock(&cookie->mutex);
 	if (iovad->start_pfn) {
 		if (1UL << order != iovad->granule ||
 		    base_pfn != iovad->start_pfn) {
 			pr_warn("Incompatible range for DMA domain\n");
-			return -EFAULT;
+			ret = -EFAULT;
+			goto done_unlock;
 		}
 
-		return 0;
+		ret = 0;
+		goto done_unlock;
 	}
 
 	init_iova_domain(iovad, 1UL << order, base_pfn);
 	ret = iova_domain_init_rcaches(iovad);
 	if (ret)
-		return ret;
+		goto done_unlock;
 
 	/* If the FQ fails we can simply fall back to strict mode */
 	if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain))
 		domain->type = IOMMU_DOMAIN_DMA;
 
-	return iova_reserve_iommu_regions(dev, domain);
+	ret = iova_reserve_iommu_regions(dev, domain);
+
+done_unlock:
+	mutex_unlock(&cookie->mutex);
+	return ret;
 }
 
 /**
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 71f2018..8e18984 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -135,6 +135,11 @@
 #define CFG_SYSSEL	(1 << 22) /* System MMU 3.2 only */
 #define CFG_FLPDCACHE	(1 << 20) /* System MMU 3.2+ only */
 
+#define CTRL_VM_ENABLE			BIT(0)
+#define CTRL_VM_FAULT_MODE_STALL	BIT(3)
+#define CAPA0_CAPA1_EXIST		BIT(11)
+#define CAPA1_VCR_ENABLED		BIT(14)
+
 /* common registers */
 #define REG_MMU_CTRL		0x000
 #define REG_MMU_CFG		0x004
@@ -148,29 +153,20 @@
 #define MAKE_MMU_VER(maj, min)	((((maj) & 0xF) << 7) | ((min) & 0x7F))
 
 /* v1.x - v3.x registers */
-#define REG_MMU_FLUSH		0x00C
-#define REG_MMU_FLUSH_ENTRY	0x010
-#define REG_PT_BASE_ADDR	0x014
-#define REG_INT_STATUS		0x018
-#define REG_INT_CLEAR		0x01C
-
 #define REG_PAGE_FAULT_ADDR	0x024
 #define REG_AW_FAULT_ADDR	0x028
 #define REG_AR_FAULT_ADDR	0x02C
 #define REG_DEFAULT_SLAVE_ADDR	0x030
 
 /* v5.x registers */
-#define REG_V5_PT_BASE_PFN	0x00C
-#define REG_V5_MMU_FLUSH_ALL	0x010
-#define REG_V5_MMU_FLUSH_ENTRY	0x014
-#define REG_V5_MMU_FLUSH_RANGE	0x018
-#define REG_V5_MMU_FLUSH_START	0x020
-#define REG_V5_MMU_FLUSH_END	0x024
-#define REG_V5_INT_STATUS	0x060
-#define REG_V5_INT_CLEAR	0x064
 #define REG_V5_FAULT_AR_VA	0x070
 #define REG_V5_FAULT_AW_VA	0x080
 
+/* v7.x registers */
+#define REG_V7_CAPA0		0x870
+#define REG_V7_CAPA1		0x874
+#define REG_V7_CTRL_VM		0x8000
+
 #define has_sysmmu(dev)		(dev_iommu_priv_get(dev) != NULL)
 
 static struct device *dma_dev;
@@ -251,6 +247,21 @@
 };
 
 /*
+ * SysMMU version specific data. Contains offsets for the registers which can
+ * be found in different SysMMU variants, but have different offset values.
+ */
+struct sysmmu_variant {
+	u32 pt_base;		/* page table base address (physical) */
+	u32 flush_all;		/* invalidate all TLB entries */
+	u32 flush_entry;	/* invalidate specific TLB entry */
+	u32 flush_range;	/* invalidate TLB entries in specified range */
+	u32 flush_start;	/* start address of range invalidation */
+	u32 flush_end;		/* end address of range invalidation */
+	u32 int_status;		/* interrupt status information */
+	u32 int_clear;		/* clear the interrupt */
+};
+
+/*
  * This structure hold all data of a single SYSMMU controller, this includes
  * hw resources like registers and clocks, pointers and list nodes to connect
  * it to all other structures, internal state and parameters read from device
@@ -274,6 +285,45 @@
 	unsigned int version;		/* our version */
 
 	struct iommu_device iommu;	/* IOMMU core handle */
+	const struct sysmmu_variant *variant; /* version specific data */
+
+	/* v7 fields */
+	bool has_vcr;			/* virtual machine control register */
+};
+
+#define SYSMMU_REG(data, reg) ((data)->sfrbase + (data)->variant->reg)
+
+/* SysMMU v1..v3 */
+static const struct sysmmu_variant sysmmu_v1_variant = {
+	.flush_all	= 0x0c,
+	.flush_entry	= 0x10,
+	.pt_base	= 0x14,
+	.int_status	= 0x18,
+	.int_clear	= 0x1c,
+};
+
+/* SysMMU v5 and v7 (non-VM capable) */
+static const struct sysmmu_variant sysmmu_v5_variant = {
+	.pt_base	= 0x0c,
+	.flush_all	= 0x10,
+	.flush_entry	= 0x14,
+	.flush_range	= 0x18,
+	.flush_start	= 0x20,
+	.flush_end	= 0x24,
+	.int_status	= 0x60,
+	.int_clear	= 0x64,
+};
+
+/* SysMMU v7: VM capable register set */
+static const struct sysmmu_variant sysmmu_v7_vm_variant = {
+	.pt_base	= 0x800c,
+	.flush_all	= 0x8010,
+	.flush_entry	= 0x8014,
+	.flush_range	= 0x8018,
+	.flush_start	= 0x8020,
+	.flush_end	= 0x8024,
+	.int_status	= 0x60,
+	.int_clear	= 0x64,
 };
 
 static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
@@ -304,10 +354,7 @@
 
 static void __sysmmu_tlb_invalidate(struct sysmmu_drvdata *data)
 {
-	if (MMU_MAJ_VER(data->version) < 5)
-		writel(0x1, data->sfrbase + REG_MMU_FLUSH);
-	else
-		writel(0x1, data->sfrbase + REG_V5_MMU_FLUSH_ALL);
+	writel(0x1, SYSMMU_REG(data, flush_all));
 }
 
 static void __sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
@@ -315,34 +362,30 @@
 {
 	unsigned int i;
 
-	if (MMU_MAJ_VER(data->version) < 5) {
+	if (MMU_MAJ_VER(data->version) < 5 || num_inv == 1) {
 		for (i = 0; i < num_inv; i++) {
 			writel((iova & SPAGE_MASK) | 1,
-				     data->sfrbase + REG_MMU_FLUSH_ENTRY);
+			       SYSMMU_REG(data, flush_entry));
 			iova += SPAGE_SIZE;
 		}
 	} else {
-		if (num_inv == 1) {
-			writel((iova & SPAGE_MASK) | 1,
-				     data->sfrbase + REG_V5_MMU_FLUSH_ENTRY);
-		} else {
-			writel((iova & SPAGE_MASK),
-				     data->sfrbase + REG_V5_MMU_FLUSH_START);
-			writel((iova & SPAGE_MASK) + (num_inv - 1) * SPAGE_SIZE,
-				     data->sfrbase + REG_V5_MMU_FLUSH_END);
-			writel(1, data->sfrbase + REG_V5_MMU_FLUSH_RANGE);
-		}
+		writel(iova & SPAGE_MASK, SYSMMU_REG(data, flush_start));
+		writel((iova & SPAGE_MASK) + (num_inv - 1) * SPAGE_SIZE,
+		       SYSMMU_REG(data, flush_end));
+		writel(0x1, SYSMMU_REG(data, flush_range));
 	}
 }
 
 static void __sysmmu_set_ptbase(struct sysmmu_drvdata *data, phys_addr_t pgd)
 {
-	if (MMU_MAJ_VER(data->version) < 5)
-		writel(pgd, data->sfrbase + REG_PT_BASE_ADDR);
-	else
-		writel(pgd >> PAGE_SHIFT,
-			     data->sfrbase + REG_V5_PT_BASE_PFN);
+	u32 pt_base;
 
+	if (MMU_MAJ_VER(data->version) < 5)
+		pt_base = pgd;
+	else
+		pt_base = pgd >> SPAGE_ORDER;
+
+	writel(pt_base, SYSMMU_REG(data, pt_base));
 	__sysmmu_tlb_invalidate(data);
 }
 
@@ -362,6 +405,20 @@
 	clk_disable_unprepare(data->clk_master);
 }
 
+static bool __sysmmu_has_capa1(struct sysmmu_drvdata *data)
+{
+	u32 capa0 = readl(data->sfrbase + REG_V7_CAPA0);
+
+	return capa0 & CAPA0_CAPA1_EXIST;
+}
+
+static void __sysmmu_get_vcr(struct sysmmu_drvdata *data)
+{
+	u32 capa1 = readl(data->sfrbase + REG_V7_CAPA1);
+
+	data->has_vcr = capa1 & CAPA1_VCR_ENABLED;
+}
+
 static void __sysmmu_get_version(struct sysmmu_drvdata *data)
 {
 	u32 ver;
@@ -379,6 +436,19 @@
 	dev_dbg(data->sysmmu, "hardware version: %d.%d\n",
 		MMU_MAJ_VER(data->version), MMU_MIN_VER(data->version));
 
+	if (MMU_MAJ_VER(data->version) < 5) {
+		data->variant = &sysmmu_v1_variant;
+	} else if (MMU_MAJ_VER(data->version) < 7) {
+		data->variant = &sysmmu_v5_variant;
+	} else {
+		if (__sysmmu_has_capa1(data))
+			__sysmmu_get_vcr(data);
+		if (data->has_vcr)
+			data->variant = &sysmmu_v7_vm_variant;
+		else
+			data->variant = &sysmmu_v5_variant;
+	}
+
 	__sysmmu_disable_clocks(data);
 }
 
@@ -406,19 +476,14 @@
 	const struct sysmmu_fault_info *finfo;
 	unsigned int i, n, itype;
 	sysmmu_iova_t fault_addr;
-	unsigned short reg_status, reg_clear;
 	int ret = -ENOSYS;
 
 	WARN_ON(!data->active);
 
 	if (MMU_MAJ_VER(data->version) < 5) {
-		reg_status = REG_INT_STATUS;
-		reg_clear = REG_INT_CLEAR;
 		finfo = sysmmu_faults;
 		n = ARRAY_SIZE(sysmmu_faults);
 	} else {
-		reg_status = REG_V5_INT_STATUS;
-		reg_clear = REG_V5_INT_CLEAR;
 		finfo = sysmmu_v5_faults;
 		n = ARRAY_SIZE(sysmmu_v5_faults);
 	}
@@ -427,7 +492,7 @@
 
 	clk_enable(data->clk_master);
 
-	itype = __ffs(readl(data->sfrbase + reg_status));
+	itype = __ffs(readl(SYSMMU_REG(data, int_status)));
 	for (i = 0; i < n; i++, finfo++)
 		if (finfo->bit == itype)
 			break;
@@ -444,7 +509,7 @@
 	/* fault is not recovered by fault handler */
 	BUG_ON(ret != 0);
 
-	writel(1 << itype, data->sfrbase + reg_clear);
+	writel(1 << itype, SYSMMU_REG(data, int_clear));
 
 	sysmmu_unblock(data);
 
@@ -486,6 +551,18 @@
 	writel(cfg, data->sfrbase + REG_MMU_CFG);
 }
 
+static void __sysmmu_enable_vid(struct sysmmu_drvdata *data)
+{
+	u32 ctrl;
+
+	if (MMU_MAJ_VER(data->version) < 7 || !data->has_vcr)
+		return;
+
+	ctrl = readl(data->sfrbase + REG_V7_CTRL_VM);
+	ctrl |= CTRL_VM_ENABLE | CTRL_VM_FAULT_MODE_STALL;
+	writel(ctrl, data->sfrbase + REG_V7_CTRL_VM);
+}
+
 static void __sysmmu_enable(struct sysmmu_drvdata *data)
 {
 	unsigned long flags;
@@ -496,6 +573,7 @@
 	writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
 	__sysmmu_init_config(data);
 	__sysmmu_set_ptbase(data, data->pgtable);
+	__sysmmu_enable_vid(data);
 	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
 	data->active = true;
 	spin_unlock_irqrestore(&data->lock, flags);
@@ -551,7 +629,7 @@
 		 * 64KB page can be one of 16 consecutive sets.
 		 */
 		if (MMU_MAJ_VER(data->version) == 2)
-			num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);
+			num_inv = min_t(unsigned int, size / SPAGE_SIZE, 64);
 
 		if (sysmmu_block(data)) {
 			__sysmmu_tlb_invalidate_entry(data, iova, num_inv);
@@ -623,6 +701,8 @@
 	data->sysmmu = dev;
 	spin_lock_init(&data->lock);
 
+	__sysmmu_get_version(data);
+
 	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
 				     dev_name(data->sysmmu));
 	if (ret)
@@ -630,11 +710,10 @@
 
 	ret = iommu_device_register(&data->iommu, &exynos_iommu_ops, dev);
 	if (ret)
-		return ret;
+		goto err_iommu_register;
 
 	platform_set_drvdata(pdev, data);
 
-	__sysmmu_get_version(data);
 	if (PG_ENT_SHIFT < 0) {
 		if (MMU_MAJ_VER(data->version) < 5) {
 			PG_ENT_SHIFT = SYSMMU_PG_ENT_SHIFT;
@@ -647,6 +726,14 @@
 		}
 	}
 
+	if (MMU_MAJ_VER(data->version) >= 5) {
+		ret = dma_set_mask(dev, DMA_BIT_MASK(36));
+		if (ret) {
+			dev_err(dev, "Unable to set DMA mask: %d\n", ret);
+			goto err_dma_set_mask;
+		}
+	}
+
 	/*
 	 * use the first registered sysmmu device for performing
 	 * dma mapping operations on iommu page tables (cpu cache flush)
@@ -657,6 +744,12 @@
 	pm_runtime_enable(dev);
 
 	return 0;
+
+err_dma_set_mask:
+	iommu_device_unregister(&data->iommu);
+err_iommu_register:
+	iommu_device_sysfs_remove(&data->iommu);
+	return ret;
 }
 
 static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
@@ -1251,9 +1344,6 @@
 	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
 	struct sysmmu_drvdata *data;
 
-	if (!has_sysmmu(dev))
-		return;
-
 	if (owner->domain) {
 		struct iommu_group *group = iommu_group_get(dev);
 
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 94b4589d..011f9ab 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -447,15 +447,10 @@
 	return &pamu_iommu;
 }
 
-static void fsl_pamu_release_device(struct device *dev)
-{
-}
-
 static const struct iommu_ops fsl_pamu_ops = {
 	.capable	= fsl_pamu_capable,
 	.domain_alloc	= fsl_pamu_domain_alloc,
 	.probe_device	= fsl_pamu_probe_device,
-	.release_device	= fsl_pamu_release_device,
 	.device_group   = fsl_pamu_device_group,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev	= fsl_pamu_attach_device,
diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c
index 71596fc..3ee6839 100644
--- a/drivers/iommu/intel/cap_audit.c
+++ b/drivers/iommu/intel/cap_audit.c
@@ -10,7 +10,7 @@
 
 #define pr_fmt(fmt)	"DMAR: " fmt
 
-#include <linux/intel-iommu.h>
+#include "iommu.h"
 #include "cap_audit.h"
 
 static u64 intel_iommu_cap_sanity;
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index ed796ee..1f92528 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -10,11 +10,11 @@
 
 #include <linux/debugfs.h>
 #include <linux/dmar.h>
-#include <linux/intel-iommu.h>
 #include <linux/pci.h>
 
 #include <asm/irq_remapping.h>
 
+#include "iommu.h"
 #include "pasid.h"
 #include "perf.h"
 
@@ -263,10 +263,9 @@
 
 static void root_tbl_walk(struct seq_file *m, struct intel_iommu *iommu)
 {
-	unsigned long flags;
 	u16 bus;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	spin_lock(&iommu->lock);
 	seq_printf(m, "IOMMU %s: Root Table Address: 0x%llx\n", iommu->name,
 		   (u64)virt_to_phys(iommu->root_entry));
 	seq_puts(m, "B.D.F\tRoot_entry\t\t\t\tContext_entry\t\t\t\tPASID\tPASID_table_entry\n");
@@ -278,8 +277,7 @@
 	 */
 	for (bus = 0; bus < 256; bus++)
 		ctx_tbl_walk(m, iommu, bus);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	spin_unlock(&iommu->lock);
 }
 
 static int dmar_translation_struct_show(struct seq_file *m, void *unused)
@@ -342,13 +340,13 @@
 	}
 }
 
-static int show_device_domain_translation(struct device *dev, void *data)
+static int __show_device_domain_translation(struct device *dev, void *data)
 {
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct dmar_domain *domain = info->domain;
+	struct dmar_domain *domain;
 	struct seq_file *m = data;
 	u64 path[6] = { 0 };
 
+	domain = to_dmar_domain(iommu_get_domain_for_dev(dev));
 	if (!domain)
 		return 0;
 
@@ -359,20 +357,39 @@
 	pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
 	seq_putc(m, '\n');
 
+	/* Don't iterate */
+	return 1;
+}
+
+static int show_device_domain_translation(struct device *dev, void *data)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (group) {
+		/*
+		 * The group->mutex is held across the callback, which will
+		 * block calls to iommu_attach/detach_group/device. Hence,
+		 * the domain of the device will not change during traversal.
+		 *
+		 * All devices in an iommu group share a single domain, hence
+		 * we only dump the domain of the first device. Even though,
+		 * this code still possibly races with the iommu_unmap()
+		 * interface. This could be solved by RCU-freeing the page
+		 * table pages in the iommu_unmap() path.
+		 */
+		iommu_group_for_each_dev(group, data,
+					 __show_device_domain_translation);
+		iommu_group_put(group);
+	}
+
 	return 0;
 }
 
 static int domain_translation_struct_show(struct seq_file *m, void *unused)
 {
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	ret = bus_for_each_dev(&pci_bus_type, NULL, m,
-			       show_device_domain_translation);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return ret;
+	return bus_for_each_dev(&pci_bus_type, NULL, m,
+				show_device_domain_translation);
 }
 DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
 
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 9699ca1..6327b34 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -19,7 +19,6 @@
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/iova.h>
-#include <linux/intel-iommu.h>
 #include <linux/timer.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
@@ -30,10 +29,11 @@
 #include <linux/numa.h>
 #include <linux/limits.h>
 #include <asm/irq_remapping.h>
-#include <trace/events/intel_iommu.h>
 
+#include "iommu.h"
 #include "../irq_remapping.h"
 #include "perf.h"
+#include "trace.h"
 
 typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
 struct dmar_res_callback {
@@ -60,7 +60,7 @@
 
 struct acpi_table_header * __initdata dmar_tbl;
 static int dmar_dev_scope_status = 1;
-static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
+static DEFINE_IDA(dmar_seq_ids);
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
@@ -1023,28 +1023,6 @@
 	return err;
 }
 
-static int dmar_alloc_seq_id(struct intel_iommu *iommu)
-{
-	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
-					    DMAR_UNITS_SUPPORTED);
-	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
-		iommu->seq_id = -1;
-	} else {
-		set_bit(iommu->seq_id, dmar_seq_ids);
-		sprintf(iommu->name, "dmar%d", iommu->seq_id);
-	}
-
-	return iommu->seq_id;
-}
-
-static void dmar_free_seq_id(struct intel_iommu *iommu)
-{
-	if (iommu->seq_id >= 0) {
-		clear_bit(iommu->seq_id, dmar_seq_ids);
-		iommu->seq_id = -1;
-	}
-}
-
 static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
@@ -1062,11 +1040,14 @@
 	if (!iommu)
 		return -ENOMEM;
 
-	if (dmar_alloc_seq_id(iommu) < 0) {
+	iommu->seq_id = ida_alloc_range(&dmar_seq_ids, 0,
+					DMAR_UNITS_SUPPORTED - 1, GFP_KERNEL);
+	if (iommu->seq_id < 0) {
 		pr_err("Failed to allocate seq_id\n");
-		err = -ENOSPC;
+		err = iommu->seq_id;
 		goto error;
 	}
+	sprintf(iommu->name, "dmar%d", iommu->seq_id);
 
 	err = map_iommu(iommu, drhd->reg_base_addr);
 	if (err) {
@@ -1150,7 +1131,7 @@
 err_unmap:
 	unmap_iommu(iommu);
 error_free_seq_id:
-	dmar_free_seq_id(iommu);
+	ida_free(&dmar_seq_ids, iommu->seq_id);
 error:
 	kfree(iommu);
 	return err;
@@ -1183,7 +1164,7 @@
 	if (iommu->reg)
 		unmap_iommu(iommu);
 
-	dmar_free_seq_id(iommu);
+	ida_free(&dmar_seq_ids, iommu->seq_id);
 	kfree(iommu);
 }
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 5c0dce7..7cca030 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -17,7 +17,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/dmi.h>
-#include <linux/intel-iommu.h>
 #include <linux/intel-svm.h>
 #include <linux/memory.h>
 #include <linux/pci.h>
@@ -26,6 +25,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 
+#include "iommu.h"
 #include "../irq_remapping.h"
 #include "../iommu-sva-lib.h"
 #include "pasid.h"
@@ -126,13 +126,8 @@
 	return page_to_dma_pfn(virt_to_page(p));
 }
 
-/* global iommu list, set NULL for ignored DMAR units */
-static struct intel_iommu **g_iommus;
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
-static inline struct device_domain_info *
-dmar_search_domain_by_dev_info(int segment, int bus, int devfn);
 
 /*
  * set to 1 to panic kernel if can't successfully enable VT-d
@@ -256,10 +251,6 @@
 static struct dmar_domain *si_domain;
 static int hw_pass_through = 1;
 
-#define for_each_domain_iommu(idx, domain)			\
-	for (idx = 0; idx < g_num_of_iommus; idx++)		\
-		if (domain->iommu_refcnt[idx])
-
 struct dmar_rmrr_unit {
 	struct list_head list;		/* list of rmrr units	*/
 	struct acpi_dmar_header *hdr;	/* ACPI header		*/
@@ -293,12 +284,7 @@
 #define for_each_rmrr_units(rmrr) \
 	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
 
-/* bitmap for indexing intel_iommus */
-static int g_num_of_iommus;
-
-static void domain_remove_dev_info(struct dmar_domain *domain);
 static void dmar_remove_one_dev_info(struct device *dev);
-static void __dmar_remove_one_dev_info(struct device_domain_info *info);
 
 int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON);
 int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);
@@ -314,12 +300,6 @@
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
-int intel_iommu_gfx_mapped;
-EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
-
-DEFINE_SPINLOCK(device_domain_lock);
-static LIST_HEAD(device_domain_list);
-
 const struct iommu_ops intel_iommu_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
@@ -455,24 +435,6 @@
 	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 }
 
-/* This functionin only returns single iommu in a domain */
-struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
-{
-	int iommu_id;
-
-	/* si_domain and vm domain should not get here. */
-	if (WARN_ON(!iommu_is_dma_domain(&domain->domain)))
-		return NULL;
-
-	for_each_domain_iommu(iommu_id, domain)
-		break;
-
-	if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
-		return NULL;
-
-	return g_iommus[iommu_id];
-}
-
 static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 {
 	return sm_supported(iommu) ?
@@ -481,16 +443,16 @@
 
 static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
+	struct iommu_domain_info *info;
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
 	bool found = false;
-	int i;
+	unsigned long i;
 
 	domain->iommu_coherency = true;
-
-	for_each_domain_iommu(i, domain) {
+	xa_for_each(&domain->iommu_array, i, info) {
 		found = true;
-		if (!iommu_paging_structure_coherency(g_iommus[i])) {
+		if (!iommu_paging_structure_coherency(info->iommu)) {
 			domain->iommu_coherency = false;
 			break;
 		}
@@ -544,15 +506,8 @@
 	struct device_domain_info *info;
 	int nid = NUMA_NO_NODE;
 
-	assert_spin_locked(&device_domain_lock);
-
-	if (list_empty(&domain->devices))
-		return NUMA_NO_NODE;
-
+	spin_lock(&domain->lock);
 	list_for_each_entry(info, &domain->devices, link) {
-		if (!info->dev)
-			continue;
-
 		/*
 		 * There could possibly be multiple device numa nodes as devices
 		 * within the same domain may sit behind different IOMMUs. There
@@ -563,6 +518,7 @@
 		if (nid != NUMA_NO_NODE)
 			break;
 	}
+	spin_unlock(&domain->lock);
 
 	return nid;
 }
@@ -804,26 +760,23 @@
 {
 	struct context_entry *context;
 	int ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	spin_lock(&iommu->lock);
 	context = iommu_context_addr(iommu, bus, devfn, 0);
 	if (context)
 		ret = context_present(context);
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	spin_unlock(&iommu->lock);
 	return ret;
 }
 
 static void free_context_table(struct intel_iommu *iommu)
 {
-	int i;
-	unsigned long flags;
 	struct context_entry *context;
+	int i;
 
-	spin_lock_irqsave(&iommu->lock, flags);
-	if (!iommu->root_entry) {
-		goto out;
-	}
+	if (!iommu->root_entry)
+		return;
+
 	for (i = 0; i < ROOT_ENTRY_NR; i++) {
 		context = iommu_context_addr(iommu, i, 0, 0);
 		if (context)
@@ -835,12 +788,10 @@
 		context = iommu_context_addr(iommu, i, 0x80, 0);
 		if (context)
 			free_pgtable_page(context);
-
 	}
+
 	free_pgtable_page(iommu->root_entry);
 	iommu->root_entry = NULL;
-out:
-	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 #ifdef CONFIG_DMAR_DEBUG
@@ -849,9 +800,14 @@
 	struct device_domain_info *info;
 	struct dma_pte *parent, *pte;
 	struct dmar_domain *domain;
+	struct pci_dev *pdev;
 	int offset, level;
 
-	info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
+	pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn);
+	if (!pdev)
+		return;
+
+	info = dev_iommu_priv_get(&pdev->dev);
 	if (!info || !info->domain) {
 		pr_info("device [%02x:%02x.%d] not probed\n",
 			bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
@@ -1234,7 +1190,6 @@
 static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 {
 	struct root_entry *root;
-	unsigned long flags;
 
 	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
 	if (!root) {
@@ -1244,10 +1199,7 @@
 	}
 
 	__iommu_flush_cache(iommu, root, ROOT_SIZE);
-
-	spin_lock_irqsave(&iommu->lock, flags);
 	iommu->root_entry = root;
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return 0;
 }
@@ -1389,23 +1341,23 @@
 }
 
 static struct device_domain_info *
-iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
-			 u8 bus, u8 devfn)
+iommu_support_dev_iotlb(struct dmar_domain *domain, struct intel_iommu *iommu,
+			u8 bus, u8 devfn)
 {
 	struct device_domain_info *info;
 
-	assert_spin_locked(&device_domain_lock);
-
 	if (!iommu->qi)
 		return NULL;
 
-	list_for_each_entry(info, &domain->devices, link)
+	spin_lock(&domain->lock);
+	list_for_each_entry(info, &domain->devices, link) {
 		if (info->iommu == iommu && info->bus == bus &&
 		    info->devfn == devfn) {
-			if (info->ats_supported && info->dev)
-				return info;
-			break;
+			spin_unlock(&domain->lock);
+			return info->ats_supported ? info : NULL;
 		}
+	}
+	spin_unlock(&domain->lock);
 
 	return NULL;
 }
@@ -1415,23 +1367,21 @@
 	struct device_domain_info *info;
 	bool has_iotlb_device = false;
 
-	assert_spin_locked(&device_domain_lock);
-
-	list_for_each_entry(info, &domain->devices, link)
+	spin_lock(&domain->lock);
+	list_for_each_entry(info, &domain->devices, link) {
 		if (info->ats_enabled) {
 			has_iotlb_device = true;
 			break;
 		}
-
+	}
 	domain->has_iotlb_device = has_iotlb_device;
+	spin_unlock(&domain->lock);
 }
 
 static void iommu_enable_dev_iotlb(struct device_domain_info *info)
 {
 	struct pci_dev *pdev;
 
-	assert_spin_locked(&device_domain_lock);
-
 	if (!info || !dev_is_pci(info->dev))
 		return;
 
@@ -1477,8 +1427,6 @@
 {
 	struct pci_dev *pdev;
 
-	assert_spin_locked(&device_domain_lock);
-
 	if (!dev_is_pci(info->dev))
 		return;
 
@@ -1518,17 +1466,15 @@
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
-	unsigned long flags;
 	struct device_domain_info *info;
 
 	if (!domain->has_iotlb_device)
 		return;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
+	spin_lock(&domain->lock);
 	list_for_each_entry(info, &domain->devices, link)
 		__iommu_flush_dev_iotlb(info, addr, mask);
-
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	spin_unlock(&domain->lock);
 }
 
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
@@ -1539,7 +1485,7 @@
 	unsigned int aligned_pages = __roundup_pow_of_two(pages);
 	unsigned int mask = ilog2(aligned_pages);
 	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
-	u16 did = domain->iommu_did[iommu->seq_id];
+	u16 did = domain_id_iommu(domain, iommu);
 
 	BUG_ON(pages == 0);
 
@@ -1609,11 +1555,12 @@
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	int idx;
+	struct iommu_domain_info *info;
+	unsigned long idx;
 
-	for_each_domain_iommu(idx, dmar_domain) {
-		struct intel_iommu *iommu = g_iommus[idx];
-		u16 did = dmar_domain->iommu_did[iommu->seq_id];
+	xa_for_each(&dmar_domain->iommu_array, idx, info) {
+		struct intel_iommu *iommu = info->iommu;
+		u16 did = domain_id_iommu(dmar_domain, iommu);
 
 		if (domain_use_first_level(dmar_domain))
 			qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0);
@@ -1719,23 +1666,16 @@
 
 static void disable_dmar_iommu(struct intel_iommu *iommu)
 {
-	struct device_domain_info *info, *tmp;
-	unsigned long flags;
-
 	if (!iommu->domain_ids)
 		return;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
-	list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
-		if (info->iommu != iommu)
-			continue;
-
-		if (!info->dev || !info->domain)
-			continue;
-
-		__dmar_remove_one_dev_info(info);
-	}
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	/*
+	 * All iommu domains must have been detached from the devices,
+	 * hence there should be no domain IDs in use.
+	 */
+	if (WARN_ON(bitmap_weight(iommu->domain_ids, cap_ndoms(iommu->cap))
+		    > NUM_RESERVED_DID))
+		return;
 
 	if (iommu->gcmd & DMA_GCMD_TE)
 		iommu_disable_translation(iommu);
@@ -1748,8 +1688,6 @@
 		iommu->domain_ids = NULL;
 	}
 
-	g_iommus[iommu->seq_id] = NULL;
-
 	/* free context mapping */
 	free_context_table(iommu);
 
@@ -1795,55 +1733,77 @@
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	spin_lock_init(&domain->lock);
+	xa_init(&domain->iommu_array);
 
 	return domain;
 }
 
-/* Must be called with iommu->lock */
 static int domain_attach_iommu(struct dmar_domain *domain,
 			       struct intel_iommu *iommu)
 {
+	struct iommu_domain_info *info, *curr;
 	unsigned long ndomains;
-	int num;
+	int num, ret = -ENOSPC;
 
-	assert_spin_locked(&device_domain_lock);
-	assert_spin_locked(&iommu->lock);
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
 
-	domain->iommu_refcnt[iommu->seq_id] += 1;
-	if (domain->iommu_refcnt[iommu->seq_id] == 1) {
-		ndomains = cap_ndoms(iommu->cap);
-		num      = find_first_zero_bit(iommu->domain_ids, ndomains);
-
-		if (num >= ndomains) {
-			pr_err("%s: No free domain ids\n", iommu->name);
-			domain->iommu_refcnt[iommu->seq_id] -= 1;
-			return -ENOSPC;
-		}
-
-		set_bit(num, iommu->domain_ids);
-		domain->iommu_did[iommu->seq_id] = num;
-		domain->nid			 = iommu->node;
-		domain_update_iommu_cap(domain);
+	spin_lock(&iommu->lock);
+	curr = xa_load(&domain->iommu_array, iommu->seq_id);
+	if (curr) {
+		curr->refcnt++;
+		spin_unlock(&iommu->lock);
+		kfree(info);
+		return 0;
 	}
 
+	ndomains = cap_ndoms(iommu->cap);
+	num = find_first_zero_bit(iommu->domain_ids, ndomains);
+	if (num >= ndomains) {
+		pr_err("%s: No free domain ids\n", iommu->name);
+		goto err_unlock;
+	}
+
+	set_bit(num, iommu->domain_ids);
+	info->refcnt	= 1;
+	info->did	= num;
+	info->iommu	= iommu;
+	curr = xa_cmpxchg(&domain->iommu_array, iommu->seq_id,
+			  NULL, info, GFP_ATOMIC);
+	if (curr) {
+		ret = xa_err(curr) ? : -EBUSY;
+		goto err_clear;
+	}
+	domain_update_iommu_cap(domain);
+
+	spin_unlock(&iommu->lock);
 	return 0;
+
+err_clear:
+	clear_bit(info->did, iommu->domain_ids);
+err_unlock:
+	spin_unlock(&iommu->lock);
+	kfree(info);
+	return ret;
 }
 
 static void domain_detach_iommu(struct dmar_domain *domain,
 				struct intel_iommu *iommu)
 {
-	int num;
+	struct iommu_domain_info *info;
 
-	assert_spin_locked(&device_domain_lock);
-	assert_spin_locked(&iommu->lock);
-
-	domain->iommu_refcnt[iommu->seq_id] -= 1;
-	if (domain->iommu_refcnt[iommu->seq_id] == 0) {
-		num = domain->iommu_did[iommu->seq_id];
-		clear_bit(num, iommu->domain_ids);
+	spin_lock(&iommu->lock);
+	info = xa_load(&domain->iommu_array, iommu->seq_id);
+	if (--info->refcnt == 0) {
+		clear_bit(info->did, iommu->domain_ids);
+		xa_erase(&domain->iommu_array, iommu->seq_id);
+		domain->nid = NUMA_NO_NODE;
 		domain_update_iommu_cap(domain);
-		domain->iommu_did[iommu->seq_id] = 0;
+		kfree(info);
 	}
+	spin_unlock(&iommu->lock);
 }
 
 static inline int guestwidth_to_adjustwidth(int gaw)
@@ -1862,10 +1822,6 @@
 
 static void domain_exit(struct dmar_domain *domain)
 {
-
-	/* Remove associated devices and clear attached or cached domains */
-	domain_remove_dev_info(domain);
-
 	if (domain->pgd) {
 		LIST_HEAD(freelist);
 
@@ -1873,6 +1829,9 @@
 		put_pages_list(&freelist);
 	}
 
+	if (WARN_ON(!list_empty(&domain->devices)))
+		return;
+
 	kfree(domain);
 }
 
@@ -1930,11 +1889,11 @@
 				      struct pasid_table *table,
 				      u8 bus, u8 devfn)
 {
-	u16 did = domain->iommu_did[iommu->seq_id];
+	struct device_domain_info *info =
+			iommu_support_dev_iotlb(domain, iommu, bus, devfn);
+	u16 did = domain_id_iommu(domain, iommu);
 	int translation = CONTEXT_TT_MULTI_LEVEL;
-	struct device_domain_info *info = NULL;
 	struct context_entry *context;
-	unsigned long flags;
 	int ret;
 
 	WARN_ON(did == 0);
@@ -1947,9 +1906,7 @@
 
 	BUG_ON(!domain->pgd);
 
-	spin_lock_irqsave(&device_domain_lock, flags);
 	spin_lock(&iommu->lock);
-
 	ret = -ENOMEM;
 	context = iommu_context_addr(iommu, bus, devfn, 1);
 	if (!context)
@@ -2000,7 +1957,6 @@
 		 * Setup the Device-TLB enable bit and Page request
 		 * Enable bit:
 		 */
-		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
 		if (info && info->ats_supported)
 			context_set_sm_dte(context);
 		if (info && info->pri_supported)
@@ -2023,7 +1979,6 @@
 					goto out_unlock;
 			}
 
-			info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
 			if (info && info->ats_supported)
 				translation = CONTEXT_TT_DEV_IOTLB;
 			else
@@ -2069,7 +2024,6 @@
 
 out_unlock:
 	spin_unlock(&iommu->lock);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return ret;
 }
@@ -2186,8 +2140,9 @@
 				 unsigned long end_pfn, int level)
 {
 	unsigned long lvl_pages = lvl_to_nr_pages(level);
+	struct iommu_domain_info *info;
 	struct dma_pte *pte = NULL;
-	int i;
+	unsigned long i;
 
 	while (start_pfn <= end_pfn) {
 		if (!pte)
@@ -2198,8 +2153,8 @@
 					       start_pfn + lvl_pages - 1,
 					       level + 1);
 
-			for_each_domain_iommu(i, domain)
-				iommu_flush_iotlb_psi(g_iommus[i], domain,
+			xa_for_each(&domain->iommu_array, i, info)
+				iommu_flush_iotlb_psi(info->iommu, domain,
 						      start_pfn, lvl_pages,
 						      0, 0);
 		}
@@ -2313,16 +2268,15 @@
 {
 	struct intel_iommu *iommu = info->iommu;
 	struct context_entry *context;
-	unsigned long flags;
 	u16 did_old;
 
 	if (!iommu)
 		return;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	spin_lock(&iommu->lock);
 	context = iommu_context_addr(iommu, bus, devfn, 0);
 	if (!context) {
-		spin_unlock_irqrestore(&iommu->lock, flags);
+		spin_unlock(&iommu->lock);
 		return;
 	}
 
@@ -2330,14 +2284,14 @@
 		if (hw_pass_through && domain_type_is_si(info->domain))
 			did_old = FLPT_DEFAULT_DID;
 		else
-			did_old = info->domain->iommu_did[iommu->seq_id];
+			did_old = domain_id_iommu(info->domain, iommu);
 	} else {
 		did_old = context_domain_id(context);
 	}
 
 	context_clear_entry(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	spin_unlock(&iommu->lock);
 	iommu->flush.flush_context(iommu,
 				   did_old,
 				   (((u16)bus) << 8) | devfn,
@@ -2356,30 +2310,6 @@
 	__iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH);
 }
 
-static void domain_remove_dev_info(struct dmar_domain *domain)
-{
-	struct device_domain_info *info, *tmp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	list_for_each_entry_safe(info, tmp, &domain->devices, link)
-		__dmar_remove_one_dev_info(info);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-}
-
-static inline struct device_domain_info *
-dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
-{
-	struct device_domain_info *info;
-
-	list_for_each_entry(info, &device_domain_list, global)
-		if (info->segment == segment && info->bus == bus &&
-		    info->devfn == devfn)
-			return info;
-
-	return NULL;
-}
-
 static int domain_setup_first_level(struct intel_iommu *iommu,
 				    struct dmar_domain *domain,
 				    struct device *dev,
@@ -2412,7 +2342,7 @@
 		flags |= PASID_FLAG_PAGE_SNOOP;
 
 	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
-					     domain->iommu_did[iommu->seq_id],
+					     domain_id_iommu(domain, iommu),
 					     flags);
 }
 
@@ -2499,7 +2429,6 @@
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu;
-	unsigned long flags;
 	u8 bus, devfn;
 	int ret;
 
@@ -2507,17 +2436,13 @@
 	if (!iommu)
 		return -ENODEV;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info->domain = domain;
-	spin_lock(&iommu->lock);
 	ret = domain_attach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
-	if (ret) {
-		spin_unlock_irqrestore(&device_domain_lock, flags);
+	if (ret)
 		return ret;
-	}
+	info->domain = domain;
+	spin_lock(&domain->lock);
 	list_add(&info->link, &domain->devices);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	spin_unlock(&domain->lock);
 
 	/* PASID table is mandatory for a PCI device in scalable mode. */
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
@@ -2529,7 +2454,6 @@
 		}
 
 		/* Setup the PASID entry for requests without PASID: */
-		spin_lock_irqsave(&iommu->lock, flags);
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
 					dev, PASID_RID2PASID);
@@ -2539,7 +2463,6 @@
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
 					dev, PASID_RID2PASID);
-		spin_unlock_irqrestore(&iommu->lock, flags);
 		if (ret) {
 			dev_err(dev, "Setup RID2PASID failed\n");
 			dmar_remove_one_dev_info(dev);
@@ -2807,7 +2730,6 @@
 	struct root_entry *old_rt;
 	phys_addr_t old_rt_phys;
 	int ctxt_table_entries;
-	unsigned long flags;
 	u64 rtaddr_reg;
 	int bus, ret;
 	bool new_ext, ext;
@@ -2850,7 +2772,7 @@
 		}
 	}
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	spin_lock(&iommu->lock);
 
 	/* Context tables are copied, now write them to the root_entry table */
 	for (bus = 0; bus < 256; bus++) {
@@ -2869,7 +2791,7 @@
 		iommu->root_entry[bus].hi = val;
 	}
 
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	spin_unlock(&iommu->lock);
 
 	kfree(ctxt_tbls);
 
@@ -2968,36 +2890,6 @@
 	struct intel_iommu *iommu;
 	int ret;
 
-	/*
-	 * for each drhd
-	 *    allocate root
-	 *    initialize and program root entry to not present
-	 * endfor
-	 */
-	for_each_drhd_unit(drhd) {
-		/*
-		 * lock not needed as this is only incremented in the single
-		 * threaded kernel __init code path all other access are read
-		 * only
-		 */
-		if (g_num_of_iommus < DMAR_UNITS_SUPPORTED) {
-			g_num_of_iommus++;
-			continue;
-		}
-		pr_err_once("Exceeded %d IOMMUs\n", DMAR_UNITS_SUPPORTED);
-	}
-
-	/* Preallocate enough resources for IOMMU hot-addition */
-	if (g_num_of_iommus < DMAR_UNITS_SUPPORTED)
-		g_num_of_iommus = DMAR_UNITS_SUPPORTED;
-
-	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
-			GFP_KERNEL);
-	if (!g_iommus) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
 	ret = intel_cap_audit(CAP_AUDIT_STATIC_DMAR, NULL);
 	if (ret)
 		goto free_iommu;
@@ -3020,8 +2912,6 @@
 						   intel_pasid_max_id);
 		}
 
-		g_iommus[iommu->seq_id] = iommu;
-
 		intel_iommu_init_qi(iommu);
 
 		ret = iommu_init_domains(iommu);
@@ -3147,9 +3037,6 @@
 		free_dmar_iommu(iommu);
 	}
 
-	kfree(g_iommus);
-
-error:
 	return ret;
 }
 
@@ -3530,9 +3417,6 @@
 	int sp, ret;
 	struct intel_iommu *iommu = dmaru->iommu;
 
-	if (g_iommus[iommu->seq_id])
-		return 0;
-
 	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu);
 	if (ret)
 		goto out;
@@ -3556,7 +3440,6 @@
 	if (iommu->gcmd & DMA_GCMD_TE)
 		iommu_disable_translation(iommu);
 
-	g_iommus[iommu->seq_id] = iommu;
 	ret = iommu_init_domains(iommu);
 	if (ret == 0)
 		ret = iommu_alloc_root_entry(iommu);
@@ -4022,6 +3905,20 @@
 	return 0;
 }
 
+static __init int tboot_force_iommu(void)
+{
+	if (!tboot_enabled())
+		return 0;
+
+	if (no_iommu || dmar_disabled)
+		pr_warn("Forcing Intel-IOMMU to enabled\n");
+
+	dmar_disabled = 0;
+	no_iommu = 0;
+
+	return 1;
+}
+
 int __init intel_iommu_init(void)
 {
 	int ret = -ENODEV;
@@ -4093,9 +3990,6 @@
 	if (list_empty(&dmar_satc_units))
 		pr_info("No SATC found\n");
 
-	if (dmar_map_gfx)
-		intel_iommu_gfx_mapped = 1;
-
 	init_no_remapping_devices();
 
 	ret = init_dmars();
@@ -4181,21 +4075,13 @@
 			       &domain_context_clear_one_cb, info);
 }
 
-static void __dmar_remove_one_dev_info(struct device_domain_info *info)
+static void dmar_remove_one_dev_info(struct device *dev)
 {
-	struct dmar_domain *domain;
-	struct intel_iommu *iommu;
-	unsigned long flags;
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *domain = info->domain;
+	struct intel_iommu *iommu = info->iommu;
 
-	assert_spin_locked(&device_domain_lock);
-
-	if (WARN_ON(!info))
-		return;
-
-	iommu = info->iommu;
-	domain = info->domain;
-
-	if (info->dev && !dev_is_real_dma_subdevice(info->dev)) {
+	if (!dev_is_real_dma_subdevice(info->dev)) {
 		if (dev_is_pci(info->dev) && sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, info->dev,
 					PASID_RID2PASID, false);
@@ -4205,23 +4091,12 @@
 		intel_pasid_free_table(info->dev);
 	}
 
+	spin_lock(&domain->lock);
 	list_del(&info->link);
+	spin_unlock(&domain->lock);
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	domain_detach_iommu(domain, iommu);
-	spin_unlock_irqrestore(&iommu->lock, flags);
-}
-
-static void dmar_remove_one_dev_info(struct device *dev)
-{
-	struct device_domain_info *info;
-	unsigned long flags;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info = dev_iommu_priv_get(dev);
-	if (info)
-		__dmar_remove_one_dev_info(info);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	info->domain = NULL;
 }
 
 static int md_domain_init(struct dmar_domain *domain, int guest_width)
@@ -4466,15 +4341,16 @@
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	unsigned long iova_pfn = IOVA_PFN(gather->start);
 	size_t size = gather->end - gather->start;
+	struct iommu_domain_info *info;
 	unsigned long start_pfn;
 	unsigned long nrpages;
-	int iommu_id;
+	unsigned long i;
 
 	nrpages = aligned_nrpages(gather->start, size);
 	start_pfn = mm_to_dma_pfn(iova_pfn);
 
-	for_each_domain_iommu(iommu_id, dmar_domain)
-		iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
+	xa_for_each(&dmar_domain->iommu_array, i, info)
+		iommu_flush_iotlb_psi(info->iommu, dmar_domain,
 				      start_pfn, nrpages,
 				      list_empty(&gather->freelist), 0);
 
@@ -4503,7 +4379,7 @@
 	struct device_domain_info *info;
 	bool support = true;
 
-	assert_spin_locked(&device_domain_lock);
+	assert_spin_locked(&domain->lock);
 	list_for_each_entry(info, &domain->devices, link) {
 		if (!ecap_sc_support(info->iommu->ecap)) {
 			support = false;
@@ -4518,8 +4394,7 @@
 {
 	struct device_domain_info *info;
 
-	assert_spin_locked(&device_domain_lock);
-
+	assert_spin_locked(&domain->lock);
 	/*
 	 * Second level page table supports per-PTE snoop control. The
 	 * iommu_map() interface will handle this by setting SNP bit.
@@ -4537,20 +4412,19 @@
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	unsigned long flags;
 
 	if (dmar_domain->force_snooping)
 		return true;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
+	spin_lock(&dmar_domain->lock);
 	if (!domain_support_force_snooping(dmar_domain)) {
-		spin_unlock_irqrestore(&device_domain_lock, flags);
+		spin_unlock(&dmar_domain->lock);
 		return false;
 	}
 
 	domain_set_force_snooping(dmar_domain);
 	dmar_domain->force_snooping = true;
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	spin_unlock(&dmar_domain->lock);
 
 	return true;
 }
@@ -4572,7 +4446,6 @@
 	struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL;
 	struct device_domain_info *info;
 	struct intel_iommu *iommu;
-	unsigned long flags;
 	u8 bus, devfn;
 
 	iommu = device_to_iommu(dev, &bus, &devfn);
@@ -4615,10 +4488,7 @@
 		}
 	}
 
-	spin_lock_irqsave(&device_domain_lock, flags);
-	list_add(&info->global, &device_domain_list);
 	dev_iommu_priv_set(dev, info);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return &iommu->iommu;
 }
@@ -4626,15 +4496,9 @@
 static void intel_iommu_release_device(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	unsigned long flags;
 
 	dmar_remove_one_dev_info(dev);
-
-	spin_lock_irqsave(&device_domain_lock, flags);
 	dev_iommu_priv_set(dev, NULL);
-	list_del(&info->global);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
@@ -4707,7 +4571,6 @@
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct context_entry *context;
 	struct dmar_domain *domain;
-	unsigned long flags;
 	u64 ctx_lo;
 	int ret;
 
@@ -4715,9 +4578,7 @@
 	if (!domain)
 		return -EINVAL;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
 	spin_lock(&iommu->lock);
-
 	ret = -EINVAL;
 	if (!info->pasid_supported)
 		goto out;
@@ -4733,7 +4594,7 @@
 		context[0].lo = ctx_lo;
 		wmb();
 		iommu->flush.flush_context(iommu,
-					   domain->iommu_did[iommu->seq_id],
+					   domain_id_iommu(domain, iommu),
 					   PCI_DEVID(info->bus, info->devfn),
 					   DMA_CCMD_MASK_NOBIT,
 					   DMA_CCMD_DEVICE_INVL);
@@ -4747,7 +4608,6 @@
 
  out:
 	spin_unlock(&iommu->lock);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return ret;
 }
@@ -4871,13 +4731,11 @@
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	unsigned long pages = aligned_nrpages(iova, size);
 	unsigned long pfn = iova >> VTD_PAGE_SHIFT;
-	struct intel_iommu *iommu;
-	int iommu_id;
+	struct iommu_domain_info *info;
+	unsigned long i;
 
-	for_each_domain_iommu(iommu_id, dmar_domain) {
-		iommu = g_iommus[iommu_id];
-		__mapping_notify_one(iommu, dmar_domain, pfn, pages);
-	}
+	xa_for_each(&dmar_domain->iommu_array, i, info)
+		__mapping_notify_one(info->iommu, dmar_domain, pfn, pages);
 }
 
 const struct iommu_ops intel_iommu_ops = {
@@ -4887,7 +4745,6 @@
 	.probe_finalize		= intel_iommu_probe_finalize,
 	.release_device		= intel_iommu_release_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
-	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.device_group		= intel_iommu_device_group,
 	.dev_enable_feat	= intel_iommu_dev_enable_feat,
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
diff --git a/include/linux/intel-iommu.h b/drivers/iommu/intel/iommu.h
similarity index 97%
rename from include/linux/intel-iommu.h
rename to drivers/iommu/intel/iommu.h
index 5fcf89f..fae45bb 100644
--- a/include/linux/intel-iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -21,6 +21,7 @@
 #include <linux/dmar.h>
 #include <linux/ioasid.h>
 #include <linux/bitfield.h>
+#include <linux/xarray.h>
 
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
@@ -480,7 +481,6 @@
 #define VTD_FLAG_SVM_CAPABLE		(1 << 2)
 
 extern int intel_iommu_sm;
-extern spinlock_t device_domain_lock;
 
 #define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
 #define pasid_supported(iommu)	(sm_supported(iommu) &&			\
@@ -525,25 +525,25 @@
  */
 #define DOMAIN_FLAG_USE_FIRST_LEVEL		BIT(1)
 
-struct dmar_domain {
-	int	nid;			/* node id */
-
-	unsigned int iommu_refcnt[DMAR_UNITS_SUPPORTED];
-					/* Refcount of devices per iommu */
-
-
-	u16		iommu_did[DMAR_UNITS_SUPPORTED];
-					/* Domain ids per IOMMU. Use u16 since
+struct iommu_domain_info {
+	struct intel_iommu *iommu;
+	unsigned int refcnt;		/* Refcount of devices per iommu */
+	u16 did;			/* Domain ids per IOMMU. Use u16 since
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
+};
+
+struct dmar_domain {
+	int	nid;			/* node id */
+	struct xarray iommu_array;	/* Attached IOMMU array */
 
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
 	u8 set_pte_snp:1;
 
+	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
-	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
 	int		gaw;		/* max guest address width */
@@ -611,7 +611,6 @@
 /* PCI domain-device relationship */
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
-	struct list_head global; /* link to global list */
 	u32 segment;		/* PCI segment number */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
@@ -642,6 +641,16 @@
 	return container_of(dom, struct dmar_domain, domain);
 }
 
+/* Retrieve the domain ID which has allocated to the domain */
+static inline u16
+domain_id_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
+{
+	struct iommu_domain_info *info =
+			xa_load(&domain->iommu_array, iommu->seq_id);
+
+	return info->did;
+}
+
 /*
  * 0: readable
  * 1: writable
@@ -727,7 +736,6 @@
 
 void *alloc_pgtable_page(int node);
 void free_pgtable_page(void *vaddr);
-struct intel_iommu *domain_get_iommu(struct dmar_domain *domain);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
 struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
@@ -787,7 +795,6 @@
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
-extern int intel_iommu_gfx_mapped;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index a673195..2e9683e 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -10,7 +10,6 @@
 #include <linux/hpet.h>
 #include <linux/pci.h>
 #include <linux/irq.h>
-#include <linux/intel-iommu.h>
 #include <linux/acpi.h>
 #include <linux/irqdomain.h>
 #include <linux/crash_dump.h>
@@ -21,6 +20,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/pci-direct.h>
 
+#include "iommu.h"
 #include "../irq_remapping.h"
 #include "cap_audit.h"
 
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 17cad7c..c5e7e8b 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -12,13 +12,13 @@
 #include <linux/bitops.h>
 #include <linux/cpufeature.h>
 #include <linux/dmar.h>
-#include <linux/intel-iommu.h>
 #include <linux/iommu.h>
 #include <linux/memory.h>
 #include <linux/pci.h>
 #include <linux/pci-ats.h>
 #include <linux/spinlock.h>
 
+#include "iommu.h"
 #include "pasid.h"
 
 /*
@@ -450,17 +450,17 @@
 	struct pasid_entry *pte;
 	u16 did, pgtt;
 
+	spin_lock(&iommu->lock);
 	pte = intel_pasid_get_entry(dev, pasid);
-	if (WARN_ON(!pte))
+	if (WARN_ON(!pte) || !pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
 		return;
-
-	if (!pasid_pte_is_present(pte))
-		return;
+	}
 
 	did = pasid_get_domain_id(pte);
 	pgtt = pasid_pte_get_pgtt(pte);
-
 	intel_pasid_clear_entry(dev, pasid, fault_ignore);
+	spin_unlock(&iommu->lock);
 
 	if (!ecap_coherent(iommu->ecap))
 		clflush_cache_range(pte, sizeof(*pte));
@@ -496,22 +496,6 @@
 	}
 }
 
-static inline int pasid_enable_wpe(struct pasid_entry *pte)
-{
-#ifdef CONFIG_X86
-	unsigned long cr0 = read_cr0();
-
-	/* CR0.WP is normally set but just to be sure */
-	if (unlikely(!(cr0 & X86_CR0_WP))) {
-		pr_err_ratelimited("No CPU write protect!\n");
-		return -EINVAL;
-	}
-#endif
-	pasid_set_wpe(pte);
-
-	return 0;
-};
-
 /*
  * Set up the scalable mode pasid table entry for first only
  * translation type.
@@ -528,39 +512,52 @@
 		return -EINVAL;
 	}
 
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (WARN_ON(!pte))
-		return -EINVAL;
+	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
+#ifdef CONFIG_X86
+		unsigned long cr0 = read_cr0();
 
-	/* Caller must ensure PASID entry is not in use. */
-	if (pasid_pte_is_present(pte))
+		/* CR0.WP is normally set but just to be sure */
+		if (unlikely(!(cr0 & X86_CR0_WP))) {
+			pr_err("No CPU write protect!\n");
+			return -EINVAL;
+		}
+#endif
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err("No supervisor request support on %s\n",
+			       iommu->name);
+			return -EINVAL;
+		}
+	}
+
+	if ((flags & PASID_FLAG_FL5LP) && !cap_5lp_support(iommu->cap)) {
+		pr_err("No 5-level paging support for first-level on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
 		return -EBUSY;
+	}
 
 	pasid_clear_entry(pte);
 
 	/* Setup the first level page table pointer: */
 	pasid_set_flptr(pte, (u64)__pa(pgd));
 	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
-		if (!ecap_srs(iommu->ecap)) {
-			pr_err("No supervisor request support on %s\n",
-			       iommu->name);
-			return -EINVAL;
-		}
 		pasid_set_sre(pte);
-		if (pasid_enable_wpe(pte))
-			return -EINVAL;
-
+		pasid_set_wpe(pte);
 	}
 
-	if (flags & PASID_FLAG_FL5LP) {
-		if (cap_5lp_support(iommu->cap)) {
-			pasid_set_flpm(pte, 1);
-		} else {
-			pr_err("No 5-level paging support for first-level\n");
-			pasid_clear_entry(pte);
-			return -EINVAL;
-		}
-	}
+	if (flags & PASID_FLAG_FL5LP)
+		pasid_set_flpm(pte, 1);
 
 	if (flags & PASID_FLAG_PAGE_SNOOP)
 		pasid_set_pgsnp(pte);
@@ -572,6 +569,8 @@
 	/* Setup Present and PASID Granular Transfer Type: */
 	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
 	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
 	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
@@ -627,17 +626,19 @@
 	}
 
 	pgd_val = virt_to_phys(pgd);
-	did = domain->iommu_did[iommu->seq_id];
+	did = domain_id_iommu(domain, iommu);
 
+	spin_lock(&iommu->lock);
 	pte = intel_pasid_get_entry(dev, pasid);
 	if (!pte) {
-		dev_err(dev, "Failed to get pasid entry of PASID %d\n", pasid);
+		spin_unlock(&iommu->lock);
 		return -ENODEV;
 	}
 
-	/* Caller must ensure PASID entry is not in use. */
-	if (pasid_pte_is_present(pte))
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
 		return -EBUSY;
+	}
 
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
@@ -654,6 +655,8 @@
 	if (pasid != PASID_RID2PASID)
 		pasid_set_sre(pte);
 	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
 	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
@@ -669,15 +672,17 @@
 	u16 did = FLPT_DEFAULT_DID;
 	struct pasid_entry *pte;
 
+	spin_lock(&iommu->lock);
 	pte = intel_pasid_get_entry(dev, pasid);
 	if (!pte) {
-		dev_err(dev, "Failed to get pasid entry of PASID %d\n", pasid);
+		spin_unlock(&iommu->lock);
 		return -ENODEV;
 	}
 
-	/* Caller must ensure PASID entry is not in use. */
-	if (pasid_pte_is_present(pte))
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
 		return -EBUSY;
+	}
 
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
@@ -692,6 +697,8 @@
 	 */
 	pasid_set_sre(pte);
 	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
 	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index bf5b937..20c54e5 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -39,6 +39,7 @@
  * only and pass-through transfer modes.
  */
 #define FLPT_DEFAULT_DID		1
+#define NUM_RESERVED_DID		2
 
 /*
  * The SUPERVISOR_MODE flag indicates a first level translation which
diff --git a/drivers/iommu/intel/perf.c b/drivers/iommu/intel/perf.c
index 0e8e032..94ee70a 100644
--- a/drivers/iommu/intel/perf.c
+++ b/drivers/iommu/intel/perf.c
@@ -9,8 +9,8 @@
  */
 
 #include <linux/spinlock.h>
-#include <linux/intel-iommu.h>
 
+#include "iommu.h"
 #include "perf.h"
 
 static DEFINE_SPINLOCK(latency_lock);
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 7ee37d9..8bcfb93 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -5,7 +5,6 @@
  * Authors: David Woodhouse <dwmw2@infradead.org>
  */
 
-#include <linux/intel-iommu.h>
 #include <linux/mmu_notifier.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -21,11 +20,12 @@
 #include <linux/ioasid.h>
 #include <asm/page.h>
 #include <asm/fpu/api.h>
-#include <trace/events/intel_iommu.h>
 
+#include "iommu.h"
 #include "pasid.h"
 #include "perf.h"
 #include "../iommu-sva-lib.h"
+#include "trace.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 static void intel_svm_drain_prq(struct device *dev, u32 pasid);
@@ -328,9 +328,9 @@
 					   unsigned int flags)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	unsigned long iflags, sflags;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
+	unsigned long sflags;
 	int ret = 0;
 
 	svm = pasid_private_find(mm->pasid);
@@ -394,11 +394,8 @@
 	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
 			PASID_FLAG_SUPERVISOR_MODE : 0;
 	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	spin_lock_irqsave(&iommu->lock, iflags);
 	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
 					    FLPT_DEFAULT_DID, sflags);
-	spin_unlock_irqrestore(&iommu->lock, iflags);
-
 	if (ret)
 		goto free_sdev;
 
@@ -544,7 +541,7 @@
 	domain = info->domain;
 	pdev = to_pci_dev(dev);
 	sid = PCI_DEVID(info->bus, info->devfn);
-	did = domain->iommu_did[iommu->seq_id];
+	did = domain_id_iommu(domain, iommu);
 	qdep = pci_ats_queue_depth(pdev);
 
 	/*
diff --git a/drivers/iommu/intel/trace.c b/drivers/iommu/intel/trace.c
index bfb6a6e..117e626 100644
--- a/drivers/iommu/intel/trace.c
+++ b/drivers/iommu/intel/trace.c
@@ -11,4 +11,4 @@
 #include <linux/types.h>
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/intel_iommu.h>
+#include "trace.h"
diff --git a/include/trace/events/intel_iommu.h b/drivers/iommu/intel/trace.h
similarity index 92%
rename from include/trace/events/intel_iommu.h
rename to drivers/iommu/intel/trace.h
index e5c1ca6..93d96f9 100644
--- a/include/trace/events/intel_iommu.h
+++ b/drivers/iommu/intel/trace.h
@@ -13,7 +13,8 @@
 #define _TRACE_INTEL_IOMMU_H
 
 #include <linux/tracepoint.h>
-#include <linux/intel-iommu.h>
+
+#include "iommu.h"
 
 #define MSG_MAX		256
 
@@ -91,4 +92,8 @@
 #endif /* _TRACE_INTEL_IOMMU_H */
 
 /* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ../../drivers/iommu/intel/
+#define TRACE_INCLUDE_FILE trace
 #include <trace/define_trace.h>
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index be066c1..ba3115f 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -182,14 +182,8 @@
 		(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT);
 }
 
-static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
-				    struct io_pgtable_cfg *cfg)
+static arm_v7s_iopte to_mtk_iopte(phys_addr_t paddr, arm_v7s_iopte pte)
 {
-	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
-
-	if (!arm_v7s_is_mtk_enabled(cfg))
-		return pte;
-
 	if (paddr & BIT_ULL(32))
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
 	if (paddr & BIT_ULL(33))
@@ -199,6 +193,17 @@
 	return pte;
 }
 
+static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
+				    struct io_pgtable_cfg *cfg)
+{
+	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
+
+	if (arm_v7s_is_mtk_enabled(cfg))
+		return to_mtk_iopte(paddr, pte);
+
+	return pte;
+}
+
 static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 				  struct io_pgtable_cfg *cfg)
 {
@@ -240,10 +245,17 @@
 	dma_addr_t dma;
 	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 	void *table = NULL;
+	gfp_t gfp_l1;
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	gfp_l1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		 GFP_KERNEL : ARM_V7S_TABLE_GFP_DMA;
 
 	if (lvl == 1)
-		table = (void *)__get_free_pages(
-			__GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size));
+		table = (void *)__get_free_pages(gfp_l1 | __GFP_ZERO, get_order(size));
 	else if (lvl == 2)
 		table = kmem_cache_zalloc(data->l2_tables, gfp);
 
@@ -251,7 +263,8 @@
 		return NULL;
 
 	phys = virt_to_phys(table);
-	if (phys != (arm_v7s_iopte)phys) {
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+	    phys >= (1ULL << cfg->oas) : phys != (arm_v7s_iopte)phys) {
 		/* Doesn't fit in PTE */
 		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
 		goto out_free;
@@ -457,9 +470,14 @@
 					   arm_v7s_iopte curr,
 					   struct io_pgtable_cfg *cfg)
 {
+	phys_addr_t phys = virt_to_phys(table);
 	arm_v7s_iopte old, new;
 
-	new = virt_to_phys(table) | ARM_V7S_PTE_TYPE_TABLE;
+	new = phys | ARM_V7S_PTE_TYPE_TABLE;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)
+		new = to_mtk_iopte(phys, new);
+
 	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
 		new |= ARM_V7S_ATTR_NS_TABLE;
 
@@ -779,6 +797,8 @@
 						void *cookie)
 {
 	struct arm_v7s_io_pgtable *data;
+	slab_flags_t slab_flag;
+	phys_addr_t paddr;
 
 	if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
 		return NULL;
@@ -788,7 +808,8 @@
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
-			    IO_PGTABLE_QUIRK_ARM_MTK_EXT))
+			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
+			    IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT))
 		return NULL;
 
 	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
@@ -796,15 +817,27 @@
 	    !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
 			return NULL;
 
+	if ((cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) &&
+	    !arm_v7s_is_mtk_enabled(cfg))
+		return NULL;
+
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;
 
 	spin_lock_init(&data->split_lock);
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	slab_flag = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		    0 : ARM_V7S_TABLE_SLAB_FLAGS;
+
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
 					    ARM_V7S_TABLE_SIZE(2, cfg),
 					    ARM_V7S_TABLE_SIZE(2, cfg),
-					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
+					    slab_flag, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;
 
@@ -850,12 +883,16 @@
 	wmb();
 
 	/* TTBR */
-	cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) | ARM_V7S_TTBR_S |
-				(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
-				 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
-				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
-				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
+	paddr = virt_to_phys(data->pgd);
+	if (arm_v7s_is_mtk_enabled(cfg))
+		cfg->arm_v7s_cfg.ttbr = paddr | upper_32_bits(paddr);
+	else
+		cfg->arm_v7s_cfg.ttbr = paddr | ARM_V7S_TTBR_S |
+					(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
+					 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+					(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 847ad47..f53f8b2 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -259,7 +259,8 @@
 	return 0;
 
 out_release:
-	ops->release_device(dev);
+	if (ops->release_device)
+		ops->release_device(dev);
 
 out_module_put:
 	module_put(ops->owner);
@@ -272,7 +273,7 @@
 
 int iommu_probe_device(struct device *dev)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
 	struct iommu_group *group;
 	int ret;
 
@@ -313,6 +314,7 @@
 	mutex_unlock(&group->mutex);
 	iommu_group_put(group);
 
+	ops = dev_iommu_ops(dev);
 	if (ops->probe_finalize)
 		ops->probe_finalize(dev);
 
@@ -336,7 +338,8 @@
 	iommu_device_unlink(dev->iommu->iommu_dev, dev);
 
 	ops = dev_iommu_ops(dev);
-	ops->release_device(dev);
+	if (ops->release_device)
+		ops->release_device(dev);
 
 	iommu_group_remove_device(dev);
 	module_put(ops->owner);
@@ -600,7 +603,7 @@
 	if (group->iommu_data_release)
 		group->iommu_data_release(group->iommu_data);
 
-	ida_simple_remove(&iommu_group_ida, group->id);
+	ida_free(&iommu_group_ida, group->id);
 
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
@@ -641,7 +644,7 @@
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
 
-	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&iommu_group_ida, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(group);
 		return ERR_PTR(ret);
@@ -651,7 +654,7 @@
 	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
 				   NULL, "%d", group->id);
 	if (ret) {
-		ida_simple_remove(&iommu_group_ida, group->id);
+		ida_free(&iommu_group_ida, group->id);
 		kobject_put(&group->kobj);
 		return ERR_PTR(ret);
 	}
@@ -2576,32 +2579,25 @@
 		ops->get_resv_regions(dev, list);
 }
 
-void iommu_put_resv_regions(struct device *dev, struct list_head *list)
-{
-	const struct iommu_ops *ops = dev_iommu_ops(dev);
-
-	if (ops->put_resv_regions)
-		ops->put_resv_regions(dev, list);
-}
-
 /**
- * generic_iommu_put_resv_regions - Reserved region driver helper
+ * iommu_put_resv_regions - release resered regions
  * @dev: device for which to free reserved regions
  * @list: reserved region list for device
  *
- * IOMMU drivers can use this to implement their .put_resv_regions() callback
- * for simple reservations. Memory allocated for each reserved region will be
- * freed. If an IOMMU driver allocates additional resources per region, it is
- * going to have to implement a custom callback.
+ * This releases a reserved region list acquired by iommu_get_resv_regions().
  */
-void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list)
+void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 {
 	struct iommu_resv_region *entry, *next;
 
-	list_for_each_entry_safe(entry, next, list, list)
-		kfree(entry);
+	list_for_each_entry_safe(entry, next, list, list) {
+		if (entry->free)
+			entry->free(dev, entry);
+		else
+			kfree(entry);
+	}
 }
-EXPORT_SYMBOL(generic_iommu_put_resv_regions);
+EXPORT_SYMBOL(iommu_put_resv_regions);
 
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 						  size_t length, int prot,
@@ -2751,19 +2747,6 @@
 }
 EXPORT_SYMBOL_GPL(iommu_dev_disable_feature);
 
-bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
-{
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
-
-		if (ops->dev_feat_enabled)
-			return ops->dev_feat_enabled(dev, feat);
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
-
 /**
  * iommu_sva_bind_device() - Bind a process address space to a device
  * @dev: the device
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index db77aa6..e44f565 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -614,7 +614,12 @@
  * dynamic size tuning described in the paper.
  */
 
-#define IOVA_MAG_SIZE 128
+/*
+ * As kmalloc's buffer size is fixed to power of 2, 127 is chosen to
+ * assure size of 'iova_magazine' to be 1024 bytes, so that no memory
+ * will be wasted.
+ */
+#define IOVA_MAG_SIZE 127
 #define MAX_GLOBAL_MAGS 32	/* magazines per bin */
 
 struct iova_magazine {
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index f09aedf..6a24aa8 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -394,10 +394,6 @@
 	return &iommu->iommu;
 }
 
-static void msm_iommu_release_device(struct device *dev)
-{
-}
-
 static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	int ret = 0;
@@ -603,7 +599,7 @@
 
 	for (sid = 0; sid < master->num_mids; sid++)
 		if (master->mids[sid] == spec->args[0]) {
-			dev_warn(dev, "Stream ID 0x%hx repeated; ignoring\n",
+			dev_warn(dev, "Stream ID 0x%x repeated; ignoring\n",
 				 sid);
 			return 0;
 		}
@@ -677,7 +673,6 @@
 static struct iommu_ops msm_iommu_ops = {
 	.domain_alloc = msm_iommu_domain_alloc,
 	.probe_device = msm_iommu_probe_device,
-	.release_device = msm_iommu_release_device,
 	.device_group = generic_device_group,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 	.of_xlate = qcom_iommu_of_xlate,
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index bb9dd92..7e363b1 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -34,7 +34,6 @@
 #include <dt-bindings/memory/mtk-memory-port.h>
 
 #define REG_MMU_PT_BASE_ADDR			0x000
-#define MMU_PT_ADDR_MASK			GENMASK(31, 7)
 
 #define REG_MMU_INVALIDATE			0x020
 #define F_ALL_INVLD				0x2
@@ -138,6 +137,7 @@
 /* PM and clock always on. e.g. infra iommu */
 #define PM_CLK_AO			BIT(15)
 #define IFA_IOMMU_PCIE_SUPPORT		BIT(16)
+#define PGTABLE_PA_35_EN		BIT(17)
 
 #define MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, mask)	\
 				((((pdata)->flags) & (mask)) == (_x))
@@ -596,6 +596,9 @@
 		.iommu_dev = data->dev,
 	};
 
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, PGTABLE_PA_35_EN))
+		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT;
+
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
 		dom->cfg.oas = data->enable_4GB ? 33 : 32;
 	else
@@ -684,8 +687,7 @@
 			goto err_unlock;
 		}
 		bank->m4u_dom = dom;
-		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
-		       bank->base + REG_MMU_PT_BASE_ADDR);
+		writel(dom->cfg.arm_v7s_cfg.ttbr, bank->base + REG_MMU_PT_BASE_ADDR);
 
 		pm_runtime_put(m4udev);
 	}
@@ -819,17 +821,12 @@
 	struct device *larbdev;
 	unsigned int larbid;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
-		return;
-
 	data = dev_iommu_priv_get(dev);
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
 		larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
 		larbdev = data->larb_imu[larbid].dev;
 		device_link_remove(dev, larbdev);
 	}
-
-	iommu_fwspec_free(dev);
 }
 
 static int mtk_iommu_get_group_id(struct device *dev, const struct mtk_iommu_plat_data *plat_data)
@@ -933,7 +930,6 @@
 	.device_group	= mtk_iommu_device_group,
 	.of_xlate	= mtk_iommu_of_xlate,
 	.get_resv_regions = mtk_iommu_get_resv_regions,
-	.put_resv_regions = generic_iommu_put_resv_regions,
 	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
 	.owner		= THIS_MODULE,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
@@ -1140,22 +1136,32 @@
 	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
 
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
-		switch (data->plat_data->m4u_plat) {
-		case M4U_MT2712:
-			p = "mediatek,mt2712-infracfg";
-			break;
-		case M4U_MT8173:
-			p = "mediatek,mt8173-infracfg";
-			break;
-		default:
-			p = NULL;
+		infracfg = syscon_regmap_lookup_by_phandle(dev->of_node, "mediatek,infracfg");
+		if (IS_ERR(infracfg)) {
+			/*
+			 * Legacy devicetrees will not specify a phandle to
+			 * mediatek,infracfg: in that case, we use the older
+			 * way to retrieve a syscon to infra.
+			 *
+			 * This is for retrocompatibility purposes only, hence
+			 * no more compatibles shall be added to this.
+			 */
+			switch (data->plat_data->m4u_plat) {
+			case M4U_MT2712:
+				p = "mediatek,mt2712-infracfg";
+				break;
+			case M4U_MT8173:
+				p = "mediatek,mt8173-infracfg";
+				break;
+			default:
+				p = NULL;
+			}
+
+			infracfg = syscon_regmap_lookup_by_compatible(p);
+			if (IS_ERR(infracfg))
+				return PTR_ERR(infracfg);
 		}
 
-		infracfg = syscon_regmap_lookup_by_compatible(p);
-
-		if (IS_ERR(infracfg))
-			return PTR_ERR(infracfg);
-
 		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
 		if (ret)
 			return ret;
@@ -1204,18 +1210,16 @@
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
 		ret = mtk_iommu_mm_dts_parse(dev, &match, data);
 		if (ret) {
-			dev_err(dev, "mm dts parse fail(%d).", ret);
+			dev_err_probe(dev, ret, "mm dts parse fail\n");
 			goto out_runtime_disable;
 		}
-	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
-		   data->plat_data->pericfg_comp_str) {
-		infracfg = syscon_regmap_lookup_by_compatible(data->plat_data->pericfg_comp_str);
-		if (IS_ERR(infracfg)) {
-			ret = PTR_ERR(infracfg);
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+		p = data->plat_data->pericfg_comp_str;
+		data->pericfg = syscon_regmap_lookup_by_compatible(p);
+		if (IS_ERR(data->pericfg)) {
+			ret = PTR_ERR(data->pericfg);
 			goto out_runtime_disable;
 		}
-
-		data->pericfg = infracfg;
 	}
 
 	platform_set_drvdata(pdev, data);
@@ -1366,8 +1370,7 @@
 		writel_relaxed(reg->int_control[i], base + REG_MMU_INT_CONTROL0);
 		writel_relaxed(reg->int_main_control[i], base + REG_MMU_INT_MAIN_CONTROL);
 		writel_relaxed(reg->ivrp_paddr[i], base + REG_MMU_IVRP_PADDR);
-		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
-		       base + REG_MMU_PT_BASE_ADDR);
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr, base + REG_MMU_PT_BASE_ADDR);
 	} while (++i < data->plat_data->banks_num);
 
 	/*
@@ -1401,7 +1404,7 @@
 static const struct mtk_iommu_plat_data mt6779_data = {
 	.m4u_plat      = M4U_MT6779,
 	.flags         = HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | WR_THROT_EN |
-			 MTK_IOMMU_TYPE_MM,
+			 MTK_IOMMU_TYPE_MM | PGTABLE_PA_35_EN,
 	.inv_sel_reg   = REG_MMU_INV_SEL_GEN2,
 	.banks_num    = 1,
 	.banks_enable = {true},
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index e1cb51b..128c7a3 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -532,15 +532,10 @@
 	struct device *larbdev;
 	unsigned int larbid;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
-		return;
-
 	data = dev_iommu_priv_get(dev);
 	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
 	larbdev = data->larb_imu[larbid].dev;
 	device_link_remove(dev, larbdev);
-
-	iommu_fwspec_free(dev);
 }
 
 static int mtk_iommu_v1_hw_init(const struct mtk_iommu_v1_data *data)
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index bd409bab..511959c 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -383,16 +383,6 @@
 	return &sdev->iommu;
 }
 
-static void sprd_iommu_release_device(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
-		return;
-
-	iommu_fwspec_free(dev);
-}
-
 static struct iommu_group *sprd_iommu_device_group(struct device *dev)
 {
 	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
@@ -417,7 +407,6 @@
 static const struct iommu_ops sprd_iommu_ops = {
 	.domain_alloc	= sprd_iommu_domain_alloc,
 	.probe_device	= sprd_iommu_probe_device,
-	.release_device	= sprd_iommu_release_device,
 	.device_group	= sprd_iommu_device_group,
 	.of_xlate	= sprd_iommu_of_xlate,
 	.pgsize_bitmap	= ~0UL << SPRD_IOMMU_PAGE_SHIFT,
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
index c54ab47..a84c635 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -738,8 +738,6 @@
 	return &iommu->iommu;
 }
 
-static void sun50i_iommu_release_device(struct device *dev) {}
-
 static struct iommu_group *sun50i_iommu_device_group(struct device *dev)
 {
 	struct sun50i_iommu *iommu = sun50i_iommu_from_dev(dev);
@@ -764,7 +762,6 @@
 	.domain_alloc	= sun50i_iommu_domain_alloc,
 	.of_xlate	= sun50i_iommu_of_xlate,
 	.probe_device	= sun50i_iommu_probe_device,
-	.release_device	= sun50i_iommu_release_device,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev	= sun50i_iommu_attach_device,
 		.detach_dev	= sun50i_iommu_detach_device,
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index a6700a4..e5ca3cf 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -246,10 +246,6 @@
 	return &gart_handle->iommu;
 }
 
-static void gart_iommu_release_device(struct device *dev)
-{
-}
-
 static int gart_iommu_of_xlate(struct device *dev,
 			       struct of_phandle_args *args)
 {
@@ -273,7 +269,6 @@
 static const struct iommu_ops gart_iommu_ops = {
 	.domain_alloc	= gart_iommu_domain_alloc,
 	.probe_device	= gart_iommu_probe_device,
-	.release_device	= gart_iommu_release_device,
 	.device_group	= generic_device_group,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
 	.of_xlate	= gart_iommu_of_xlate,
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 1fea68e..2a8de97 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -864,8 +864,6 @@
 	return &smmu->iommu;
 }
 
-static void tegra_smmu_release_device(struct device *dev) {}
-
 static const struct tegra_smmu_group_soc *
 tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup)
 {
@@ -966,7 +964,6 @@
 static const struct iommu_ops tegra_smmu_ops = {
 	.domain_alloc = tegra_smmu_domain_alloc,
 	.probe_device = tegra_smmu_probe_device,
-	.release_device = tegra_smmu_release_device,
 	.device_group = tegra_smmu_device_group,
 	.of_xlate = tegra_smmu_of_xlate,
 	.pgsize_bitmap = SZ_4K,
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 25be4b8..08eeafc 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -788,11 +788,13 @@
 	return 0;
 }
 
-static int viommu_map(struct iommu_domain *domain, unsigned long iova,
-		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			    int prot, gfp_t gfp, size_t *mapped)
 {
 	int ret;
 	u32 flags;
+	size_t size = pgsize * pgcount;
 	u64 end = iova + size - 1;
 	struct virtio_iommu_req_map map;
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
@@ -823,17 +825,21 @@
 	ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
 	if (ret)
 		viommu_del_mappings(vdomain, iova, end);
+	else if (mapped)
+		*mapped = size;
 
 	return ret;
 }
 
-static size_t viommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			   size_t size, struct iommu_iotlb_gather *gather)
+static size_t viommu_unmap_pages(struct iommu_domain *domain, unsigned long iova,
+				 size_t pgsize, size_t pgcount,
+				 struct iommu_iotlb_gather *gather)
 {
 	int ret = 0;
 	size_t unmapped;
 	struct virtio_iommu_req_unmap unmap;
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
+	size_t size = pgsize * pgcount;
 
 	unmapped = viommu_del_mappings(vdomain, iova, iova + size - 1);
 	if (unmapped < size)
@@ -964,7 +970,7 @@
 	return &viommu->iommu;
 
 err_free_dev:
-	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
+	iommu_put_resv_regions(dev, &vdev->resv_regions);
 	kfree(vdev);
 
 	return ERR_PTR(ret);
@@ -981,15 +987,9 @@
 
 static void viommu_release_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct viommu_endpoint *vdev;
+	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
 
-	if (!fwspec || fwspec->ops != &viommu_ops)
-		return;
-
-	vdev = dev_iommu_priv_get(dev);
-
-	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
+	iommu_put_resv_regions(dev, &vdev->resv_regions);
 	kfree(vdev);
 }
 
@@ -1013,13 +1013,12 @@
 	.release_device		= viommu_release_device,
 	.device_group		= viommu_device_group,
 	.get_resv_regions	= viommu_get_resv_regions,
-	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.of_xlate		= viommu_of_xlate,
 	.owner			= THIS_MODULE,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= viommu_attach_dev,
-		.map			= viommu_map,
-		.unmap			= viommu_unmap,
+		.map_pages		= viommu_map_pages,
+		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
 		.iotlb_sync		= viommu_iotlb_sync,
 		.free			= viommu_domain_free,
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index f1f0842..b43be09 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -33,10 +33,14 @@
 					  enum irq_domain_bus_token bus_token);
 void acpi_configure_pmsi_domain(struct device *dev);
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
+void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode,
+		       struct list_head *head);
+void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode,
+		       struct list_head *head);
 /* IOMMU interface */
 int iort_dma_get_ranges(struct device *dev, u64 *size);
 int iort_iommu_configure_id(struct device *dev, const u32 *id_in);
-int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
+void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head);
 phys_addr_t acpi_iort_dma_get_max_cpu_address(void);
 #else
 static inline void acpi_iort_init(void) { }
@@ -46,14 +50,18 @@
 	struct device *dev, u32 id, enum irq_domain_bus_token bus_token)
 { return NULL; }
 static inline void acpi_configure_pmsi_domain(struct device *dev) { }
+static inline
+void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { }
+static inline
+void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { }
 /* IOMMU interface */
 static inline int iort_dma_get_ranges(struct device *dev, u64 *size)
 { return -ENODEV; }
 static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in)
 { return -ENODEV; }
 static inline
-int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
-{ return 0; }
+void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head)
+{ }
 
 static inline phys_addr_t acpi_iort_dma_get_max_cpu_address(void)
 { return PHYS_ADDR_MAX; }
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 58e6c38..953e6f1 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -206,4 +206,8 @@
 		u64 *value);
 struct amd_iommu *get_amd_iommu(unsigned int idx);
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+int amd_iommu_snp_enable(void);
+#endif
+
 #endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index cbd714a..d81a519 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -18,11 +18,7 @@
 
 struct acpi_dmar_header;
 
-#ifdef	CONFIG_X86
-# define	DMAR_UNITS_SUPPORTED	MAX_IO_APICS
-#else
-# define	DMAR_UNITS_SUPPORTED	64
-#endif
+#define DMAR_UNITS_SUPPORTED	1024
 
 /* DMAR Flags */
 #define DMAR_INTR_REMAP		0x1
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 86af6f0..ca98aea 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -74,17 +74,22 @@
 	 *	to support up to 35 bits PA where the bit32, bit33 and bit34 are
 	 *	encoded in the bit9, bit4 and bit5 of the PTE respectively.
 	 *
+	 * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek IOMMUs
+	 *	extend the translation table base support up to 35 bits PA, the
+	 *	encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT.
+	 *
 	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
 	 *	for use in the upper half of a split address space.
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
 	 *	attributes set in the TCR for a non-coherent page-table walker.
 	 */
-	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
-	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
-	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
-	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
-	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA	BIT(6)
+	#define IO_PGTABLE_QUIRK_ARM_NS			BIT(0)
+	#define IO_PGTABLE_QUIRK_NO_PERMS		BIT(1)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT		BIT(3)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT	BIT(4)
+	#define IO_PGTABLE_QUIRK_ARM_TTBR1		BIT(5)
+	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA		BIT(6)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 5e1afe1..ea30f00 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -135,6 +135,7 @@
  * @length: Length of the region in bytes
  * @prot: IOMMU Protection flags (READ/WRITE/...)
  * @type: Type of the reserved region
+ * @free: Callback to free associated memory allocations
  */
 struct iommu_resv_region {
 	struct list_head	list;
@@ -142,6 +143,15 @@
 	size_t			length;
 	int			prot;
 	enum iommu_resv_type	type;
+	void (*free)(struct device *dev, struct iommu_resv_region *region);
+};
+
+struct iommu_iort_rmr_data {
+	struct iommu_resv_region rr;
+
+	/* Stream IDs associated with IORT RMR entry */
+	const u32 *sids;
+	u32 num_sids;
 };
 
 /**
@@ -154,8 +164,7 @@
  *			 supported, this feature must be enabled before and
  *			 disabled after %IOMMU_DEV_FEAT_SVA.
  *
- * Device drivers query whether a feature is supported using
- * iommu_dev_has_feature(), and enable it using iommu_dev_enable_feature().
+ * Device drivers enable a feature using iommu_dev_enable_feature().
  */
 enum iommu_dev_features {
 	IOMMU_DEV_FEAT_SVA,
@@ -200,13 +209,11 @@
  *                  group and attached to the groups domain
  * @device_group: find iommu group for a particular device
  * @get_resv_regions: Request list of reserved regions for a device
- * @put_resv_regions: Free list of reserved regions for a device
  * @of_xlate: add OF master IDs to iommu grouping
  * @is_attach_deferred: Check if domain attach should be deferred from iommu
  *                      driver init to device driver init (default no)
  * @dev_has/enable/disable_feat: per device entries to check/enable/disable
  *                               iommu specific features.
- * @dev_feat_enabled: check enabled feature
  * @sva_bind: Bind process address space to device
  * @sva_unbind: Unbind process address space from device
  * @sva_get_pasid: Get PASID associated to a SVA handle
@@ -232,14 +239,11 @@
 
 	/* Request/Free a list of reserved regions for a device */
 	void (*get_resv_regions)(struct device *dev, struct list_head *list);
-	void (*put_resv_regions)(struct device *dev, struct list_head *list);
 
 	int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
 	bool (*is_attach_deferred)(struct device *dev);
 
 	/* Per device IOMMU features */
-	bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f);
-	bool (*dev_feat_enabled)(struct device *dev, enum iommu_dev_features f);
 	int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
 
@@ -448,8 +452,6 @@
 
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
-extern void generic_iommu_put_resv_regions(struct device *dev,
-					   struct list_head *list);
 extern void iommu_set_default_passthrough(bool cmd_line);
 extern void iommu_set_default_translated(bool cmd_line);
 extern bool iommu_default_passthrough(void);
@@ -662,7 +664,6 @@
 
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
-bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
 
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm,
@@ -989,12 +990,6 @@
 	return NULL;
 }
 
-static inline bool
-iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
-{
-	return false;
-}
-
 static inline int
 iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
 {
diff --git a/include/linux/tboot.h b/include/linux/tboot.h
index 5146d25..d227916 100644
--- a/include/linux/tboot.h
+++ b/include/linux/tboot.h
@@ -126,7 +126,6 @@
 extern void tboot_shutdown(u32 shutdown_type);
 extern struct acpi_table_header *tboot_get_dmar_table(
 				      struct acpi_table_header *dmar_tbl);
-extern int tboot_force_iommu(void);
 
 #else
 
@@ -136,7 +135,6 @@
 #define tboot_sleep(sleep_state, pm1a_control, pm1b_control)	\
 					do { } while (0)
 #define tboot_get_dmar_table(dmar_tbl)	(dmar_tbl)
-#define tboot_force_iommu()		0
 
 #endif /* !CONFIG_INTEL_TXT */