Merge drm/drm-next into drm-intel-next

Sync up with v5.18-rc1, in particular to get 5e3094cfd9fb
("drm/i915/xehpsdv: Add has_flat_ccs to device info").

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

42 files changed, 712 insertions, 2015 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 3eb68fa1b8cc..c79a0df090c0 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -144,8 +144,8 @@ config IOMMU_DMA
 	select IRQ_MSI_IOMMU
 	select NEED_SG_DMA_LENGTH
 
-# Shared Virtual Addressing library
-config IOMMU_SVA_LIB
+# Shared Virtual Addressing
+config IOMMU_SVA
 	bool
 	select IOASID
 
@@ -379,7 +379,7 @@ config ARM_SMMU_V3
 config ARM_SMMU_V3_SVA
 	bool "Shared Virtual Addressing support for the ARM SMMUv3"
 	depends on ARM_SMMU_V3
-	select IOMMU_SVA_LIB
+	select IOMMU_SVA
 	select MMU_NOTIFIER
 	help
 	  Support for sharing process address spaces with devices using the
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index bc7f730edbb0..44475a9b3eea 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -27,6 +27,6 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
 obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
 obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
 obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
-obj-$(CONFIG_IOMMU_SVA_LIB) += iommu-sva-lib.o io-pgfault.o
+obj-$(CONFIG_IOMMU_SVA) += iommu-sva-lib.o io-pgfault.o
 obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o
 obj-$(CONFIG_APPLE_DART) += apple-dart.o
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 416815a525d6..1ab31074f5b3 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -14,7 +14,7 @@
 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_reset_cmd_buffer(struct amd_iommu *iommu);
+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);
@@ -116,8 +116,7 @@ void amd_iommu_domain_clr_pt_root(struct protection_domain *domain)
 
 
 extern bool translation_pre_enabled(struct amd_iommu *iommu);
-extern bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
-					 struct device *dev);
+extern bool amd_iommu_is_attach_deferred(struct device *dev);
 extern int __init add_special_device(u8 type, u8 id, u16 *devid,
 				     bool cmd_line);
 
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index ffc89c4fb120..47108ed44fbb 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -110,6 +110,7 @@
 #define PASID_MASK		0x0000ffff
 
 /* MMIO status bits */
+#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK	(1 << 0)
 #define MMIO_STATUS_EVT_INT_MASK	(1 << 1)
 #define MMIO_STATUS_COM_WAIT_INT_MASK	(1 << 2)
 #define MMIO_STATUS_PPR_INT_MASK	(1 << 6)
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index b10fb52ea442..b4a798c7b347 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -658,10 +658,20 @@ static int __init alloc_command_buffer(struct amd_iommu *iommu)
 }
 
 /*
+ * This function restarts event logging in case the IOMMU experienced
+ * an event log buffer overflow.
+ */
+void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
+	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+}
+
+/*
  * This function resets the command buffer if the IOMMU stopped fetching
  * commands from it.
  */
-void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
+static void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
 {
 	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
 
@@ -980,6 +990,7 @@ static bool copy_device_table(void)
 				get_order(dev_table_size));
 	if (old_dev_tbl_cpy == NULL) {
 		pr_err("Failed to allocate memory for copying old device table!\n");
+		memunmap(old_devtb);
 		return false;
 	}
 
@@ -1010,6 +1021,7 @@ static bool copy_device_table(void)
 			if ((int_ctl != DTE_IRQ_REMAP_INTCTL) ||
 			    (int_tab_len != DTE_INTTABLEN)) {
 				pr_err("Wrong old irq remapping flag: %#x\n", devid);
+				memunmap(old_devtb);
 				return false;
 			}
 
@@ -1943,9 +1955,11 @@ static int __init amd_iommu_init_pci(void)
 
 	for_each_iommu(iommu) {
 		ret = iommu_init_pci(iommu);
-		if (ret)
-			break;
-
+		if (ret) {
+			pr_err("IOMMU%d: Failed to initialize IOMMU Hardware (error=%d)!\n",
+			       iommu->index, ret);
+			goto out;
+		}
 		/* Need to setup range after PCI init */
 		iommu_set_cwwb_range(iommu);
 	}
@@ -1961,6 +1975,11 @@ static int __init amd_iommu_init_pci(void)
 	 * active.
 	 */
 	ret = amd_iommu_init_api();
+	if (ret) {
+		pr_err("IOMMU: Failed to initialize IOMMU-API interface (error=%d)!\n",
+		       ret);
+		goto out;
+	}
 
 	init_device_table_dma();
 
@@ -1970,6 +1989,7 @@ static int __init amd_iommu_init_pci(void)
 	if (!ret)
 		print_iommu_info();
 
+out:
 	return ret;
 }
 
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index b1bf4125b0f7..6608d1717574 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -492,18 +492,18 @@ static void v1_free_pgtable(struct io_pgtable *iop)
 
 	dom = container_of(pgtable, struct protection_domain, iop);
 
-	/* Update data structure */
-	amd_iommu_domain_clr_pt_root(dom);
-
-	/* Make changes visible to IOMMUs */
-	amd_iommu_domain_update(dom);
-
 	/* Page-table is not visible to IOMMU anymore, so free it */
 	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
 	       pgtable->mode > PAGE_MODE_6_LEVEL);
 
 	free_sub_pt(pgtable->root, pgtable->mode, &freelist);
 
+	/* Update data structure */
+	amd_iommu_domain_clr_pt_root(dom);
+
+	/* Make changes visible to IOMMUs */
+	amd_iommu_domain_update(dom);
+
 	put_pages_list(&freelist);
 }
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 461f1844ed1f..a1ada7bff44e 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -764,7 +764,8 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
 #endif /* !CONFIG_IRQ_REMAP */
 
 #define AMD_IOMMU_INT_MASK	\
-	(MMIO_STATUS_EVT_INT_MASK | \
+	(MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
+	 MMIO_STATUS_EVT_INT_MASK | \
 	 MMIO_STATUS_PPR_INT_MASK | \
 	 MMIO_STATUS_GALOG_INT_MASK)
 
@@ -774,7 +775,7 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
 	u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
 
 	while (status & AMD_IOMMU_INT_MASK) {
-		/* Enable EVT and PPR and GA interrupts again */
+		/* Enable interrupt sources again */
 		writel(AMD_IOMMU_INT_MASK,
 			iommu->mmio_base + MMIO_STATUS_OFFSET);
 
@@ -795,6 +796,11 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
 		}
 #endif
 
+		if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
+			pr_info_ratelimited("IOMMU event log overflow\n");
+			amd_iommu_restart_event_logging(iommu);
+		}
+
 		/*
 		 * Hardware bug: ERBT1312
 		 * When re-enabling interrupt (by writing 1
@@ -2215,8 +2221,7 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 	list_add_tail(&region->list, head);
 }
 
-bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
-				  struct device *dev)
+bool amd_iommu_is_attach_deferred(struct device *dev)
 {
 	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
 
@@ -2269,13 +2274,6 @@ static int amd_iommu_def_domain_type(struct device *dev)
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
-	.domain_free  = amd_iommu_domain_free,
-	.attach_dev = amd_iommu_attach_device,
-	.detach_dev = amd_iommu_detach_device,
-	.map = amd_iommu_map,
-	.iotlb_sync_map	= amd_iommu_iotlb_sync_map,
-	.unmap = amd_iommu_unmap,
-	.iova_to_phys = amd_iommu_iova_to_phys,
 	.probe_device = amd_iommu_probe_device,
 	.release_device = amd_iommu_release_device,
 	.probe_finalize = amd_iommu_probe_finalize,
@@ -2284,9 +2282,18 @@ const struct iommu_ops amd_iommu_ops = {
 	.put_resv_regions = generic_iommu_put_resv_regions,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
-	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
-	.iotlb_sync = amd_iommu_iotlb_sync,
 	.def_domain_type = amd_iommu_def_domain_type,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= amd_iommu_attach_device,
+		.detach_dev	= amd_iommu_detach_device,
+		.map		= amd_iommu_map,
+		.unmap		= amd_iommu_unmap,
+		.iotlb_sync_map	= amd_iommu_iotlb_sync_map,
+		.iova_to_phys	= amd_iommu_iova_to_phys,
+		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
+		.iotlb_sync	= amd_iommu_iotlb_sync,
+		.free		= amd_iommu_domain_free,
+	}
 };
 
 /*****************************************************************************
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 58da08cc3d01..e56b137ceabd 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -24,7 +24,6 @@
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Joerg Roedel <jroedel@suse.de>");
 
-#define MAX_DEVICES		0x10000
 #define PRI_QUEUE_SIZE		512
 
 struct pri_queue {
@@ -71,7 +70,6 @@ struct fault {
 	struct pasid_state *state;
 	struct mm_struct *mm;
 	u64 address;
-	u16 devid;
 	u32 pasid;
 	u16 tag;
 	u16 finish;
@@ -125,6 +123,15 @@ static void free_device_state(struct device_state *dev_state)
 {
 	struct iommu_group *group;
 
+	/* Get rid of any remaining pasid states */
+	free_pasid_states(dev_state);
+
+	/*
+	 * Wait until the last reference is dropped before freeing
+	 * the device state.
+	 */
+	wait_event(dev_state->wq, !atomic_read(&dev_state->count));
+
 	/*
 	 * First detach device from domain - No more PRI requests will arrive
 	 * from that device after it is unbound from the IOMMUv2 domain.
@@ -537,7 +544,7 @@ static int ppr_notifier(struct notifier_block *nb, unsigned long e, void *data)
 	ret = NOTIFY_DONE;
 
 	/* In kdump kernel pci dev is not initialized yet -> send INVALID */
-	if (amd_iommu_is_attach_deferred(NULL, &pdev->dev)) {
+	if (amd_iommu_is_attach_deferred(&pdev->dev)) {
 		amd_iommu_complete_ppr(pdev, iommu_fault->pasid,
 				       PPR_INVALID, tag);
 		goto out;
@@ -850,15 +857,7 @@ void amd_iommu_free_device(struct pci_dev *pdev)
 
 	spin_unlock_irqrestore(&state_lock, flags);
 
-	/* Get rid of any remaining pasid states */
-	free_pasid_states(dev_state);
-
 	put_device_state(dev_state);
-	/*
-	 * Wait until the last reference is dropped before freeing
-	 * the device state.
-	 */
-	wait_event(dev_state->wq, !atomic_read(&dev_state->count));
 	free_device_state(dev_state);
 }
 EXPORT_SYMBOL(amd_iommu_free_device);
@@ -955,8 +954,8 @@ out:
 
 static void __exit amd_iommu_v2_exit(void)
 {
-	struct device_state *dev_state;
-	int i;
+	struct device_state *dev_state, *next;
+	unsigned long flags;
 
 	if (!amd_iommu_v2_supported())
 		return;
@@ -969,18 +968,18 @@ static void __exit amd_iommu_v2_exit(void)
 	 * The loop below might call flush_workqueue(), so call
 	 * destroy_workqueue() after it
 	 */
-	for (i = 0; i < MAX_DEVICES; ++i) {
-		dev_state = get_device_state(i);
-
-		if (dev_state == NULL)
-			continue;
+	spin_lock_irqsave(&state_lock, flags);
 
+	list_for_each_entry_safe(dev_state, next, &state_list, list) {
 		WARN_ON_ONCE(1);
 
 		put_device_state(dev_state);
-		amd_iommu_free_device(dev_state->pdev);
+		list_del(&dev_state->list);
+		free_device_state(dev_state);
 	}
 
+	spin_unlock_irqrestore(&state_lock, flags);
+
 	destroy_workqueue(iommu_wq);
 }
 
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 565ef5598811..decafb07ad08 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -765,15 +765,6 @@ static void apple_dart_get_resv_regions(struct device *dev,
 
 static const struct iommu_ops apple_dart_iommu_ops = {
 	.domain_alloc = apple_dart_domain_alloc,
-	.domain_free = apple_dart_domain_free,
-	.attach_dev = apple_dart_attach_dev,
-	.detach_dev = apple_dart_detach_dev,
-	.map_pages = apple_dart_map_pages,
-	.unmap_pages = apple_dart_unmap_pages,
-	.flush_iotlb_all = apple_dart_flush_iotlb_all,
-	.iotlb_sync = apple_dart_iotlb_sync,
-	.iotlb_sync_map = apple_dart_iotlb_sync_map,
-	.iova_to_phys = apple_dart_iova_to_phys,
 	.probe_device = apple_dart_probe_device,
 	.release_device = apple_dart_release_device,
 	.device_group = apple_dart_device_group,
@@ -782,6 +773,17 @@ static const struct iommu_ops apple_dart_iommu_ops = {
 	.get_resv_regions = apple_dart_get_resv_regions,
 	.put_resv_regions = generic_iommu_put_resv_regions,
 	.pgsize_bitmap = -1UL, /* Restricted during dart probe */
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= apple_dart_attach_dev,
+		.detach_dev	= apple_dart_detach_dev,
+		.map_pages	= apple_dart_map_pages,
+		.unmap_pages	= apple_dart_unmap_pages,
+		.flush_iotlb_all = apple_dart_flush_iotlb_all,
+		.iotlb_sync	= apple_dart_iotlb_sync,
+		.iotlb_sync_map	= apple_dart_iotlb_sync_map,
+		.iova_to_phys	= apple_dart_iova_to_phys,
+		.free		= apple_dart_domain_free,
+	}
 };
 
 static irqreturn_t apple_dart_irq(int irq, void *dev)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index a737ba5f727e..22ddd05bbdcd 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -340,14 +340,12 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 	bond->smmu_mn = arm_smmu_mmu_notifier_get(smmu_domain, mm);
 	if (IS_ERR(bond->smmu_mn)) {
 		ret = PTR_ERR(bond->smmu_mn);
-		goto err_free_pasid;
+		goto err_free_bond;
 	}
 
 	list_add(&bond->list, &master->bonds);
 	return &bond->sva;
 
-err_free_pasid:
-	iommu_sva_free_pasid(mm);
 err_free_bond:
 	kfree(bond);
 	return ERR_PTR(ret);
@@ -377,7 +375,6 @@ void arm_smmu_sva_unbind(struct iommu_sva *handle)
 	if (refcount_dec_and_test(&bond->refs)) {
 		list_del(&bond->list);
 		arm_smmu_mmu_notifier_put(bond->smmu_mn);
-		iommu_sva_free_pasid(bond->mm);
 		kfree(bond);
 	}
 	mutex_unlock(&sva_lock);
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 6dc6d8b6b368..627a3ed5ee8f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1558,6 +1558,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 				dev_info(smmu->dev, "\t0x%016llx\n",
 					 (unsigned long long)evt[i]);
 
+			cond_resched();
 		}
 
 		/*
@@ -2841,17 +2842,9 @@ static int arm_smmu_dev_disable_feature(struct device *dev,
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
-	.domain_free		= arm_smmu_domain_free,
-	.attach_dev		= arm_smmu_attach_dev,
-	.map_pages		= arm_smmu_map_pages,
-	.unmap_pages		= arm_smmu_unmap_pages,
-	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
-	.iotlb_sync		= arm_smmu_iotlb_sync,
-	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.device_group		= arm_smmu_device_group,
-	.enable_nesting		= arm_smmu_enable_nesting,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,
@@ -2865,6 +2858,16 @@ static struct iommu_ops arm_smmu_ops = {
 	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= arm_smmu_attach_dev,
+		.map_pages		= arm_smmu_map_pages,
+		.unmap_pages		= arm_smmu_unmap_pages,
+		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
+		.iotlb_sync		= arm_smmu_iotlb_sync,
+		.iova_to_phys		= arm_smmu_iova_to_phys,
+		.enable_nesting		= arm_smmu_enable_nesting,
+		.free			= arm_smmu_domain_free,
+	}
 };
 
 /* Probing and initialisation functions */
@@ -2911,32 +2914,20 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 	return 0;
 }
 
-static void arm_smmu_cmdq_free_bitmap(void *data)
-{
-	unsigned long *bitmap = data;
-	bitmap_free(bitmap);
-}
-
 static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
 {
-	int ret = 0;
 	struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
 	unsigned int nents = 1 << cmdq->q.llq.max_n_shift;
-	atomic_long_t *bitmap;
 
 	atomic_set(&cmdq->owner_prod, 0);
 	atomic_set(&cmdq->lock, 0);
 
-	bitmap = (atomic_long_t *)bitmap_zalloc(nents, GFP_KERNEL);
-	if (!bitmap) {
-		dev_err(smmu->dev, "failed to allocate cmdq bitmap\n");
-		ret = -ENOMEM;
-	} else {
-		cmdq->valid_map = bitmap;
-		devm_add_action(smmu->dev, arm_smmu_cmdq_free_bitmap, bitmap);
-	}
+	cmdq->valid_map = (atomic_long_t *)devm_bitmap_zalloc(smmu->dev, nents,
+							      GFP_KERNEL);
+	if (!cmdq->valid_map)
+		return -ENOMEM;
 
-	return ret;
+	return 0;
 }
 
 static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
@@ -2981,10 +2972,10 @@ static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
 {
 	unsigned int i;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
-	size_t size = sizeof(*cfg->l1_desc) * cfg->num_l1_ents;
 	void *strtab = smmu->strtab_cfg.strtab;
 
-	cfg->l1_desc = devm_kzalloc(smmu->dev, size, GFP_KERNEL);
+	cfg->l1_desc = devm_kcalloc(smmu->dev, cfg->num_l1_ents,
+				    sizeof(*cfg->l1_desc), GFP_KERNEL);
 	if (!cfg->l1_desc)
 		return -ENOMEM;
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 4bc75c4ce402..568cce590ccc 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -807,7 +807,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	 * Request context fault interrupt. Do this last to avoid the
 	 * handler seeing a half-initialised domain state.
 	 */
-	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
+	irq = smmu->irqs[cfg->irptndx];
 
 	if (smmu->impl && smmu->impl->context_fault)
 		context_fault = smmu->impl->context_fault;
@@ -858,7 +858,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	arm_smmu_write_context_bank(smmu, cfg->cbndx);
 
 	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
-		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
+		irq = smmu->irqs[cfg->irptndx];
 		devm_free_irq(smmu->dev, irq, domain);
 	}
 
@@ -1583,25 +1583,27 @@ static int arm_smmu_def_domain_type(struct device *dev)
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
-	.domain_free		= arm_smmu_domain_free,
-	.attach_dev		= arm_smmu_attach_dev,
-	.map_pages		= arm_smmu_map_pages,
-	.unmap_pages		= arm_smmu_unmap_pages,
-	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
-	.iotlb_sync		= arm_smmu_iotlb_sync,
-	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.probe_finalize		= arm_smmu_probe_finalize,
 	.device_group		= arm_smmu_device_group,
-	.enable_nesting		= arm_smmu_enable_nesting,
-	.set_pgtable_quirks	= arm_smmu_set_pgtable_quirks,
 	.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,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= arm_smmu_attach_dev,
+		.map_pages		= arm_smmu_map_pages,
+		.unmap_pages		= arm_smmu_unmap_pages,
+		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
+		.iotlb_sync		= arm_smmu_iotlb_sync,
+		.iova_to_phys		= arm_smmu_iova_to_phys,
+		.enable_nesting		= arm_smmu_enable_nesting,
+		.set_pgtable_quirks	= arm_smmu_set_pgtable_quirks,
+		.free			= arm_smmu_domain_free,
+	}
 };
 
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
@@ -1951,8 +1953,8 @@ static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
 	return ret;
 }
 
-static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
-				      struct arm_smmu_device *smmu)
+static int arm_smmu_device_acpi_probe(struct arm_smmu_device *smmu,
+				      u32 *global_irqs, u32 *pmu_irqs)
 {
 	struct device *dev = smmu->dev;
 	struct acpi_iort_node *node =
@@ -1968,7 +1970,8 @@ static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
 		return ret;
 
 	/* Ignore the configuration access interrupt */
-	smmu->num_global_irqs = 1;
+	*global_irqs = 1;
+	*pmu_irqs = 0;
 
 	if (iort_smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK)
 		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
@@ -1976,25 +1979,24 @@ static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
 	return 0;
 }
 #else
-static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
-					     struct arm_smmu_device *smmu)
+static inline int arm_smmu_device_acpi_probe(struct arm_smmu_device *smmu,
+					     u32 *global_irqs, u32 *pmu_irqs)
 {
 	return -ENODEV;
 }
 #endif
 
-static int arm_smmu_device_dt_probe(struct platform_device *pdev,
-				    struct arm_smmu_device *smmu)
+static int arm_smmu_device_dt_probe(struct arm_smmu_device *smmu,
+				    u32 *global_irqs, u32 *pmu_irqs)
 {
 	const struct arm_smmu_match_data *data;
-	struct device *dev = &pdev->dev;
+	struct device *dev = smmu->dev;
 	bool legacy_binding;
 
-	if (of_property_read_u32(dev->of_node, "#global-interrupts",
-				 &smmu->num_global_irqs)) {
-		dev_err(dev, "missing #global-interrupts property\n");
-		return -ENODEV;
-	}
+	if (of_property_read_u32(dev->of_node, "#global-interrupts", global_irqs))
+		return dev_err_probe(dev, -ENODEV,
+				     "missing #global-interrupts property\n");
+	*pmu_irqs = 0;
 
 	data = of_device_get_match_data(dev);
 	smmu->version = data->version;
@@ -2073,6 +2075,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
+	u32 global_irqs, pmu_irqs;
 	irqreturn_t (*global_fault)(int irq, void *dev);
 
 	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
@@ -2083,10 +2086,9 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	smmu->dev = dev;
 
 	if (dev->of_node)
-		err = arm_smmu_device_dt_probe(pdev, smmu);
+		err = arm_smmu_device_dt_probe(smmu, &global_irqs, &pmu_irqs);
 	else
-		err = arm_smmu_device_acpi_probe(pdev, smmu);
-
+		err = arm_smmu_device_acpi_probe(smmu, &global_irqs, &pmu_irqs);
 	if (err)
 		return err;
 
@@ -2105,31 +2107,25 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	if (IS_ERR(smmu))
 		return PTR_ERR(smmu);
 
-	num_irqs = 0;
-	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
-		num_irqs++;
-		if (num_irqs > smmu->num_global_irqs)
-			smmu->num_context_irqs++;
-	}
+	num_irqs = platform_irq_count(pdev);
 
-	if (!smmu->num_context_irqs) {
-		dev_err(dev, "found %d interrupts but expected at least %d\n",
-			num_irqs, smmu->num_global_irqs + 1);
-		return -ENODEV;
-	}
+	smmu->num_context_irqs = num_irqs - global_irqs - pmu_irqs;
+	if (smmu->num_context_irqs <= 0)
+		return dev_err_probe(dev, -ENODEV,
+				"found %d interrupts but expected at least %d\n",
+				num_irqs, global_irqs + pmu_irqs + 1);
 
-	smmu->irqs = devm_kcalloc(dev, num_irqs, sizeof(*smmu->irqs),
-				  GFP_KERNEL);
-	if (!smmu->irqs) {
-		dev_err(dev, "failed to allocate %d irqs\n", num_irqs);
-		return -ENOMEM;
-	}
+	smmu->irqs = devm_kcalloc(dev, smmu->num_context_irqs,
+				  sizeof(*smmu->irqs), GFP_KERNEL);
+	if (!smmu->irqs)
+		return dev_err_probe(dev, -ENOMEM, "failed to allocate %d irqs\n",
+				     smmu->num_context_irqs);
 
-	for (i = 0; i < num_irqs; ++i) {
-		int irq = platform_get_irq(pdev, i);
+	for (i = 0; i < smmu->num_context_irqs; i++) {
+		int irq = platform_get_irq(pdev, global_irqs + pmu_irqs + i);
 
 		if (irq < 0)
-			return -ENODEV;
+			return irq;
 		smmu->irqs[i] = irq;
 	}
 
@@ -2165,17 +2161,18 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	else
 		global_fault = arm_smmu_global_fault;
 
-	for (i = 0; i < smmu->num_global_irqs; ++i) {
-		err = devm_request_irq(smmu->dev, smmu->irqs[i],
-				       global_fault,
-				       IRQF_SHARED,
-				       "arm-smmu global fault",
-				       smmu);
-		if (err) {
-			dev_err(dev, "failed to request global IRQ %d (%u)\n",
-				i, smmu->irqs[i]);
-			return err;
-		}
+	for (i = 0; i < global_irqs; i++) {
+		int irq = platform_get_irq(pdev, i);
+
+		if (irq < 0)
+			return irq;
+
+		err = devm_request_irq(dev, irq, global_fault, IRQF_SHARED,
+				       "arm-smmu global fault", smmu);
+		if (err)
+			return dev_err_probe(dev, err,
+					"failed to request global IRQ %d (%u)\n",
+					i, irq);
 	}
 
 	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 432de2f742c3..2b9b42fb6f30 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -318,11 +318,10 @@ struct arm_smmu_device {
 	unsigned long			pa_size;
 	unsigned long			pgsize_bitmap;
 
-	u32				num_global_irqs;
-	u32				num_context_irqs;
+	int				num_context_irqs;
+	int				num_clks;
 	unsigned int			*irqs;
 	struct clk_bulk_data		*clks;
-	int				num_clks;
 
 	spinlock_t			global_sync_lock;
 
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index b91874cb6cf3..4c077c38fbd6 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -590,19 +590,21 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 static const struct iommu_ops qcom_iommu_ops = {
 	.capable	= qcom_iommu_capable,
 	.domain_alloc	= qcom_iommu_domain_alloc,
-	.domain_free	= qcom_iommu_domain_free,
-	.attach_dev	= qcom_iommu_attach_dev,
-	.detach_dev	= qcom_iommu_detach_dev,
-	.map		= qcom_iommu_map,
-	.unmap		= qcom_iommu_unmap,
-	.flush_iotlb_all = qcom_iommu_flush_iotlb_all,
-	.iotlb_sync	= qcom_iommu_iotlb_sync,
-	.iova_to_phys	= qcom_iommu_iova_to_phys,
 	.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,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= qcom_iommu_attach_dev,
+		.detach_dev	= qcom_iommu_detach_dev,
+		.map		= qcom_iommu_map,
+		.unmap		= qcom_iommu_unmap,
+		.flush_iotlb_all = qcom_iommu_flush_iotlb_all,
+		.iotlb_sync	= qcom_iommu_iotlb_sync,
+		.iova_to_phys	= qcom_iommu_iova_to_phys,
+		.free		= qcom_iommu_domain_free,
+	}
 };
 
 static int qcom_iommu_sec_ptbl_init(struct device *dev)
@@ -827,20 +829,20 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	ret = devm_of_platform_populate(dev);
 	if (ret) {
 		dev_err(dev, "Failed to populate iommu contexts\n");
-		return ret;
+		goto err_pm_disable;
 	}
 
 	ret = iommu_device_sysfs_add(&qcom_iommu->iommu, dev, NULL,
 				     dev_name(dev));
 	if (ret) {
 		dev_err(dev, "Failed to register iommu in sysfs\n");
-		return ret;
+		goto err_pm_disable;
 	}
 
 	ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev);
 	if (ret) {
 		dev_err(dev, "Failed to register iommu\n");
-		return ret;
+		goto err_pm_disable;
 	}
 
 	bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
@@ -852,6 +854,10 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	}
 
 	return 0;
+
+err_pm_disable:
+	pm_runtime_disable(dev);
+	return ret;
 }
 
 static int qcom_iommu_device_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d85d54f2b549..09f6e1c0f9c0 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -525,6 +525,7 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	unsigned long order, base_pfn;
 	struct iova_domain *iovad;
+	int ret;
 
 	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
 		return -EINVAL;
@@ -559,6 +560,9 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	}
 
 	init_iova_domain(iovad, 1UL << order, base_pfn);
+	ret = iova_domain_init_rcaches(iovad);
+	if (ret)
+		return ret;
 
 	/* If the FQ fails we can simply fall back to strict mode */
 	if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain))
@@ -852,7 +856,6 @@ out_unmap:
 	return NULL;
 }
 
-#ifdef CONFIG_DMA_REMAP
 static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
 		size_t size, enum dma_data_direction dir, gfp_t gfp,
 		unsigned long attrs)
@@ -882,7 +885,6 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 	sg_free_table(&sh->sgt);
 	kfree(sh);
 }
-#endif /* CONFIG_DMA_REMAP */
 
 static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
@@ -1276,7 +1278,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 	    dma_free_from_pool(dev, cpu_addr, alloc_size))
 		return;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		/*
 		 * If it the address is remapped, then it's either non-coherent
 		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
@@ -1318,7 +1320,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
+	if (!coherent || PageHighMem(page)) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
 		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
@@ -1350,7 +1352,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	gfp |= __GFP_ZERO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
+	if (gfpflags_allow_blocking(gfp) &&
 	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
 		return iommu_dma_alloc_remap(dev, size, handle, gfp,
 				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
@@ -1391,7 +1393,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	if (off >= nr_pages || vma_pages(vma) > nr_pages - off)
 		return -ENXIO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages)
@@ -1413,7 +1415,7 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	struct page *page;
 	int ret;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages) {
@@ -1445,10 +1447,8 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
 	.free_pages		= dma_common_free_pages,
-#ifdef CONFIG_DMA_REMAP
 	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
 	.free_noncontiguous	= iommu_dma_free_noncontiguous,
-#endif
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 939ffa768986..71f2018e23fe 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1309,17 +1309,19 @@ static int exynos_iommu_of_xlate(struct device *dev,
 
 static const struct iommu_ops exynos_iommu_ops = {
 	.domain_alloc = exynos_iommu_domain_alloc,
-	.domain_free = exynos_iommu_domain_free,
-	.attach_dev = exynos_iommu_attach_device,
-	.detach_dev = exynos_iommu_detach_device,
-	.map = exynos_iommu_map,
-	.unmap = exynos_iommu_unmap,
-	.iova_to_phys = exynos_iommu_iova_to_phys,
 	.device_group = generic_device_group,
 	.probe_device = exynos_iommu_probe_device,
 	.release_device = exynos_iommu_release_device,
 	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
 	.of_xlate = exynos_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= exynos_iommu_attach_device,
+		.detach_dev	= exynos_iommu_detach_device,
+		.map		= exynos_iommu_map,
+		.unmap		= exynos_iommu_unmap,
+		.iova_to_phys	= exynos_iommu_iova_to_phys,
+		.free		= exynos_iommu_domain_free,
+	}
 };
 
 static int __init exynos_iommu_init(void)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index a47f47307109..69a4a62dc3b9 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -453,13 +453,15 @@ 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,
-	.domain_free    = fsl_pamu_domain_free,
-	.attach_dev	= fsl_pamu_attach_device,
-	.detach_dev	= fsl_pamu_detach_device,
-	.iova_to_phys	= fsl_pamu_iova_to_phys,
 	.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,
+		.detach_dev	= fsl_pamu_detach_device,
+		.iova_to_phys	= fsl_pamu_iova_to_phys,
+		.free		= fsl_pamu_domain_free,
+	}
 };
 
 int __init pamu_domain_init(void)
diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index 247d0f2d5fdf..39a06d245f12 100644
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -52,7 +52,7 @@ config INTEL_IOMMU_SVM
 	select PCI_PRI
 	select MMU_NOTIFIER
 	select IOASID
-	select IOMMU_SVA_LIB
+	select IOMMU_SVA
 	help
 	  Shared Virtual Memory (SVM) provides a facility for devices
 	  to access DMA resources through process address space by
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index 62e23ff3c987..ed796eea4581 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -344,15 +344,15 @@ static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
 
 static int show_device_domain_translation(struct device *dev, void *data)
 {
-	struct dmar_domain *domain = find_domain(dev);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *domain = info->domain;
 	struct seq_file *m = data;
 	u64 path[6] = { 0 };
 
 	if (!domain)
 		return 0;
 
-	seq_printf(m, "Device %s with pasid %d @0x%llx\n",
-		   dev_name(dev), domain->default_pasid,
+	seq_printf(m, "Device %s @0x%llx\n", dev_name(dev),
 		   (u64)virt_to_phys(domain->pgd));
 	seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
 
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 915bff76fe96..4de960834a1b 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -66,8 +66,6 @@ static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
-extern const struct iommu_ops intel_iommu_ops;
-
 static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
@@ -789,7 +787,8 @@ static int __init dmar_acpi_dev_scope_init(void)
 				       andd->device_name);
 				continue;
 			}
-			if (acpi_bus_get_device(h, &adev)) {
+			adev = acpi_fetch_acpi_dev(h);
+			if (!adev) {
 				pr_err("Failed to get device for ACPI object %s\n",
 				       andd->device_name);
 				continue;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index be9487516617..2200e3c5d506 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -13,38 +13,18 @@
 #define pr_fmt(fmt)     "DMAR: " fmt
 #define dev_fmt(fmt)    pr_fmt(fmt)
 
-#include <linux/init.h>
-#include <linux/bitmap.h>
-#include <linux/debugfs.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/pci.h>
-#include <linux/dmar.h>
-#include <linux/dma-map-ops.h>
-#include <linux/mempool.h>
-#include <linux/memory.h>
-#include <linux/cpu.h>
-#include <linux/timer.h>
-#include <linux/io.h>
-#include <linux/iova.h>
-#include <linux/iommu.h>
+#include <linux/crash_dump.h>
+#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>
+#include <linux/pci-ats.h>
+#include <linux/spinlock.h>
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
-#include <linux/dmi.h>
-#include <linux/pci-ats.h>
-#include <linux/memblock.h>
-#include <linux/dma-direct.h>
-#include <linux/crash_dump.h>
-#include <linux/numa.h>
-#include <asm/irq_remapping.h>
-#include <asm/cacheflush.h>
-#include <asm/iommu.h>
 
 #include "../irq_remapping.h"
 #include "../iommu-sva-lib.h"
@@ -316,14 +296,9 @@ static LIST_HEAD(dmar_satc_units);
 /* bitmap for indexing intel_iommus */
 static int g_num_of_iommus;
 
-static void domain_exit(struct dmar_domain *domain);
 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);
-static int intel_iommu_attach_device(struct iommu_domain *domain,
-				     struct device *dev);
-static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
-					    dma_addr_t iova);
 
 int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON);
 int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);
@@ -342,21 +317,6 @@ static int iommu_skip_te_disable;
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
-#define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
-struct device_domain_info *get_domain_info(struct device *dev)
-{
-	struct device_domain_info *info;
-
-	if (!dev)
-		return NULL;
-
-	info = dev_iommu_priv_get(dev);
-	if (unlikely(info == DEFER_DEVICE_DOMAIN_INFO))
-		return NULL;
-
-	return info;
-}
-
 DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
@@ -452,39 +412,6 @@ static int __init intel_iommu_setup(char *str)
 }
 __setup("intel_iommu=", intel_iommu_setup);
 
-static struct kmem_cache *iommu_domain_cache;
-static struct kmem_cache *iommu_devinfo_cache;
-
-static struct dmar_domain* get_iommu_domain(struct intel_iommu *iommu, u16 did)
-{
-	struct dmar_domain **domains;
-	int idx = did >> 8;
-
-	domains = iommu->domains[idx];
-	if (!domains)
-		return NULL;
-
-	return domains[did & 0xff];
-}
-
-static void set_iommu_domain(struct intel_iommu *iommu, u16 did,
-			     struct dmar_domain *domain)
-{
-	struct dmar_domain **domains;
-	int idx = did >> 8;
-
-	if (!iommu->domains[idx]) {
-		size_t size = 256 * sizeof(struct dmar_domain *);
-		iommu->domains[idx] = kzalloc(size, GFP_ATOMIC);
-	}
-
-	domains = iommu->domains[idx];
-	if (WARN_ON(!domains))
-		return;
-	else
-		domains[did & 0xff] = domain;
-}
-
 void *alloc_pgtable_page(int node)
 {
 	struct page *page;
@@ -501,26 +428,6 @@ void free_pgtable_page(void *vaddr)
 	free_page((unsigned long)vaddr);
 }
 
-static inline void *alloc_domain_mem(void)
-{
-	return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC);
-}
-
-static void free_domain_mem(void *vaddr)
-{
-	kmem_cache_free(iommu_domain_cache, vaddr);
-}
-
-static inline void * alloc_devinfo_mem(void)
-{
-	return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC);
-}
-
-static inline void free_devinfo_mem(void *vaddr)
-{
-	kmem_cache_free(iommu_devinfo_cache, vaddr);
-}
-
 static inline int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
@@ -794,11 +701,6 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 	return &context[devfn];
 }
 
-static bool attach_deferred(struct device *dev)
-{
-	return dev_iommu_priv_get(dev) == DEFER_DEVICE_DOMAIN_INFO;
-}
-
 /**
  * is_downstream_to_pci_bridge - test if a device belongs to the PCI
  *				 sub-hierarchy of a candidate PCI-PCI bridge
@@ -925,7 +827,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 		}
 
 		if (pdev && drhd->include_all) {
-		got_pdev:
+got_pdev:
 			if (bus && devfn) {
 				*bus = pdev->bus->number;
 				*devfn = pdev->devfn;
@@ -934,7 +836,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 		}
 	}
 	iommu = NULL;
- out:
+out:
 	if (iommu_is_dummy(iommu, dev))
 		iommu = NULL;
 
@@ -1573,18 +1475,6 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 			break;
 		}
 
-	if (!has_iotlb_device) {
-		struct subdev_domain_info *sinfo;
-
-		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
-			info = get_domain_info(sinfo->pdev);
-			if (info && info->ats_enabled) {
-				has_iotlb_device = true;
-				break;
-			}
-		}
-	}
-
 	domain->has_iotlb_device = has_iotlb_device;
 }
 
@@ -1682,7 +1572,6 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 {
 	unsigned long flags;
 	struct device_domain_info *info;
-	struct subdev_domain_info *sinfo;
 
 	if (!domain->has_iotlb_device)
 		return;
@@ -1691,27 +1580,9 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 	list_for_each_entry(info, &domain->devices, link)
 		__iommu_flush_dev_iotlb(info, addr, mask);
 
-	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
-		info = get_domain_info(sinfo->pdev);
-		__iommu_flush_dev_iotlb(info, addr, mask);
-	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-static void domain_flush_piotlb(struct intel_iommu *iommu,
-				struct dmar_domain *domain,
-				u64 addr, unsigned long npages, bool ih)
-{
-	u16 did = domain->iommu_did[iommu->seq_id];
-
-	if (domain->default_pasid)
-		qi_flush_piotlb(iommu, did, domain->default_pasid,
-				addr, npages, ih);
-
-	if (!list_empty(&domain->devices))
-		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, npages, ih);
-}
-
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1727,7 +1598,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 		ih = 1 << 6;
 
 	if (domain_use_first_level(domain)) {
-		domain_flush_piotlb(iommu, domain, addr, pages, ih);
+		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih);
 	} else {
 		/*
 		 * Fallback to domain selective flush if no PSI support or
@@ -1776,14 +1647,13 @@ static void intel_flush_iotlb_all(struct iommu_domain *domain)
 		u16 did = dmar_domain->iommu_did[iommu->seq_id];
 
 		if (domain_use_first_level(dmar_domain))
-			domain_flush_piotlb(iommu, dmar_domain, 0, -1, 0);
+			qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0);
 		else
 			iommu->flush.flush_iotlb(iommu, did, 0, 0,
 						 DMA_TLB_DSI_FLUSH);
 
 		if (!cap_caching_mode(iommu->cap))
-			iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
-					      0, MAX_AGAW_PFN_WIDTH);
+			iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
 	}
 }
 
@@ -1846,7 +1716,6 @@ static void iommu_disable_translation(struct intel_iommu *iommu)
 static int iommu_init_domains(struct intel_iommu *iommu)
 {
 	u32 ndomains;
-	size_t size;
 
 	ndomains = cap_ndoms(iommu->cap);
 	pr_debug("%s: Number of Domains supported <%d>\n",
@@ -1858,24 +1727,6 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	if (!iommu->domain_ids)
 		return -ENOMEM;
 
-	size = (ALIGN(ndomains, 256) >> 8) * sizeof(struct dmar_domain **);
-	iommu->domains = kzalloc(size, GFP_KERNEL);
-
-	if (iommu->domains) {
-		size = 256 * sizeof(struct dmar_domain *);
-		iommu->domains[0] = kzalloc(size, GFP_KERNEL);
-	}
-
-	if (!iommu->domains || !iommu->domains[0]) {
-		pr_err("%s: Allocating domain array failed\n",
-		       iommu->name);
-		bitmap_free(iommu->domain_ids);
-		kfree(iommu->domains);
-		iommu->domain_ids = NULL;
-		iommu->domains    = NULL;
-		return -ENOMEM;
-	}
-
 	/*
 	 * If Caching mode is set, then invalid translations are tagged
 	 * with domain-id 0, hence we need to pre-allocate it. We also
@@ -1902,7 +1753,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 	struct device_domain_info *info, *tmp;
 	unsigned long flags;
 
-	if (!iommu->domains || !iommu->domain_ids)
+	if (!iommu->domain_ids)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
@@ -1923,15 +1774,8 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 
 static void free_dmar_iommu(struct intel_iommu *iommu)
 {
-	if ((iommu->domains) && (iommu->domain_ids)) {
-		int elems = ALIGN(cap_ndoms(iommu->cap), 256) >> 8;
-		int i;
-
-		for (i = 0; i < elems; i++)
-			kfree(iommu->domains[i]);
-		kfree(iommu->domains);
+	if (iommu->domain_ids) {
 		bitmap_free(iommu->domain_ids);
-		iommu->domains = NULL;
 		iommu->domain_ids = NULL;
 	}
 
@@ -1973,17 +1817,15 @@ static struct dmar_domain *alloc_domain(unsigned int type)
 {
 	struct dmar_domain *domain;
 
-	domain = alloc_domain_mem();
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
 		return NULL;
 
-	memset(domain, 0, sizeof(*domain));
 	domain->nid = NUMA_NO_NODE;
 	if (first_level_by_default(type))
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
-	INIT_LIST_HEAD(&domain->subdevices);
 
 	return domain;
 }
@@ -2010,11 +1852,8 @@ static int domain_attach_iommu(struct dmar_domain *domain,
 		}
 
 		set_bit(num, iommu->domain_ids);
-		set_iommu_domain(iommu, num, domain);
-
 		domain->iommu_did[iommu->seq_id] = num;
 		domain->nid			 = iommu->node;
-
 		domain_update_iommu_cap(domain);
 	}
 
@@ -2033,8 +1872,6 @@ static void domain_detach_iommu(struct dmar_domain *domain,
 	if (domain->iommu_refcnt[iommu->seq_id] == 0) {
 		num = domain->iommu_did[iommu->seq_id];
 		clear_bit(num, iommu->domain_ids);
-		set_iommu_domain(iommu, num, NULL);
-
 		domain_update_iommu_cap(domain);
 		domain->iommu_did[iommu->seq_id] = 0;
 	}
@@ -2067,7 +1904,7 @@ static void domain_exit(struct dmar_domain *domain)
 		put_pages_list(&freelist);
 	}
 
-	free_domain_mem(domain);
+	kfree(domain);
 }
 
 /*
@@ -2550,15 +2387,6 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 	__iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH);
 }
 
-static inline void unlink_domain_info(struct device_domain_info *info)
-{
-	assert_spin_locked(&device_domain_lock);
-	list_del(&info->link);
-	list_del(&info->global);
-	if (info->dev)
-		dev_iommu_priv_set(info->dev, NULL);
-}
-
 static void domain_remove_dev_info(struct dmar_domain *domain)
 {
 	struct device_domain_info *info, *tmp;
@@ -2570,24 +2398,6 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-struct dmar_domain *find_domain(struct device *dev)
-{
-	struct device_domain_info *info;
-
-	if (unlikely(!dev || !dev->iommu))
-		return NULL;
-
-	if (unlikely(attach_deferred(dev)))
-		return NULL;
-
-	/* No lock here, assumes no domain exit in normal case */
-	info = get_domain_info(dev);
-	if (likely(info))
-		return info->domain;
-
-	return NULL;
-}
-
 static inline struct device_domain_info *
 dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 {
@@ -2648,97 +2458,24 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 						    struct device *dev,
 						    struct dmar_domain *domain)
 {
-	struct dmar_domain *found = NULL;
-	struct device_domain_info *info;
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	unsigned long flags;
 	int ret;
 
-	info = alloc_devinfo_mem();
-	if (!info)
-		return NULL;
-
-	if (!dev_is_real_dma_subdevice(dev)) {
-		info->bus = bus;
-		info->devfn = devfn;
-		info->segment = iommu->segment;
-	} else {
-		struct pci_dev *pdev = to_pci_dev(dev);
-
-		info->bus = pdev->bus->number;
-		info->devfn = pdev->devfn;
-		info->segment = pci_domain_nr(pdev->bus);
-	}
-
-	info->ats_supported = info->pasid_supported = info->pri_supported = 0;
-	info->ats_enabled = info->pasid_enabled = info->pri_enabled = 0;
-	info->ats_qdep = 0;
-	info->dev = dev;
-	info->domain = domain;
-	info->iommu = iommu;
-	info->pasid_table = NULL;
-	info->auxd_enabled = 0;
-	INIT_LIST_HEAD(&info->subdevices);
-
-	if (dev && dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(info->dev);
-
-		if (ecap_dev_iotlb_support(iommu->ecap) &&
-		    pci_ats_supported(pdev) &&
-		    dmar_find_matched_atsr_unit(pdev))
-			info->ats_supported = 1;
-
-		if (sm_supported(iommu)) {
-			if (pasid_supported(iommu)) {
-				int features = pci_pasid_features(pdev);
-				if (features >= 0)
-					info->pasid_supported = features | 1;
-			}
-
-			if (info->ats_supported && ecap_prs(iommu->ecap) &&
-			    pci_pri_supported(pdev))
-				info->pri_supported = 1;
-		}
-	}
-
 	spin_lock_irqsave(&device_domain_lock, flags);
-	if (dev)
-		found = find_domain(dev);
-
-	if (!found) {
-		struct device_domain_info *info2;
-		info2 = dmar_search_domain_by_dev_info(info->segment, info->bus,
-						       info->devfn);
-		if (info2) {
-			found      = info2->domain;
-			info2->dev = dev;
-		}
-	}
-
-	if (found) {
-		spin_unlock_irqrestore(&device_domain_lock, flags);
-		free_devinfo_mem(info);
-		/* Caller must free the original domain */
-		return found;
-	}
-
+	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);
-		free_devinfo_mem(info);
 		return NULL;
 	}
-
 	list_add(&info->link, &domain->devices);
-	list_add(&info->global, &device_domain_list);
-	if (dev)
-		dev_iommu_priv_set(dev, info);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	/* PASID table is mandatory for a PCI device in scalable mode. */
-	if (dev && dev_is_pci(dev) && sm_supported(iommu)) {
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
@@ -3460,70 +3197,6 @@ error:
 	return ret;
 }
 
-static inline int iommu_domain_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_domain_cache = kmem_cache_create("iommu_domain",
-					 sizeof(struct dmar_domain),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-
-					 NULL);
-	if (!iommu_domain_cache) {
-		pr_err("Couldn't create iommu_domain cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
-static inline int iommu_devinfo_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
-					 sizeof(struct device_domain_info),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!iommu_devinfo_cache) {
-		pr_err("Couldn't create devinfo cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
-static int __init iommu_init_mempool(void)
-{
-	int ret;
-	ret = iova_cache_get();
-	if (ret)
-		return ret;
-
-	ret = iommu_domain_cache_init();
-	if (ret)
-		goto domain_error;
-
-	ret = iommu_devinfo_cache_init();
-	if (!ret)
-		return ret;
-
-	kmem_cache_destroy(iommu_domain_cache);
-domain_error:
-	iova_cache_put();
-
-	return -ENOMEM;
-}
-
-static void __init iommu_exit_mempool(void)
-{
-	kmem_cache_destroy(iommu_devinfo_cache);
-	kmem_cache_destroy(iommu_domain_cache);
-	iova_cache_put();
-}
-
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -3691,7 +3364,7 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
-static int rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+static int __init rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
 {
 	if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
 	    !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
@@ -4020,7 +3693,31 @@ static void intel_iommu_free_dmars(void)
 	}
 }
 
-int dmar_find_matched_atsr_unit(struct pci_dev *dev)
+static struct dmar_satc_unit *dmar_find_matched_satc_unit(struct pci_dev *dev)
+{
+	struct dmar_satc_unit *satcu;
+	struct acpi_dmar_satc *satc;
+	struct device *tmp;
+	int i;
+
+	dev = pci_physfn(dev);
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(satcu, &dmar_satc_units, list) {
+		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
+		if (satc->segment != pci_domain_nr(dev->bus))
+			continue;
+		for_each_dev_scope(satcu->devices, satcu->devices_cnt, i, tmp)
+			if (to_pci_dev(tmp) == dev)
+				goto out;
+	}
+	satcu = NULL;
+out:
+	rcu_read_unlock();
+	return satcu;
+}
+
+static int dmar_ats_supported(struct pci_dev *dev, struct intel_iommu *iommu)
 {
 	int i, ret = 1;
 	struct pci_bus *bus;
@@ -4028,8 +3725,20 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 	struct device *tmp;
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
+	struct dmar_satc_unit *satcu;
 
 	dev = pci_physfn(dev);
+	satcu = dmar_find_matched_satc_unit(dev);
+	if (satcu)
+		/*
+		 * This device supports ATS as it is in SATC table.
+		 * When IOMMU is in legacy mode, enabling ATS is done
+		 * automatically by HW for the device that requires
+		 * ATS, hence OS should not enable this device ATS
+		 * to avoid duplicated TLB invalidation.
+		 */
+		return !(satcu->atc_required && !sm_supported(iommu));
+
 	for (bus = dev->bus; bus; bus = bus->parent) {
 		bridge = bus->self;
 		/* If it's an integrated device, allow ATS */
@@ -4375,12 +4084,6 @@ int __init intel_iommu_init(void)
 	force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
 		    platform_optin_force_iommu();
 
-	if (iommu_init_mempool()) {
-		if (force_on)
-			panic("tboot: Failed to initialize iommu memory\n");
-		return -ENOMEM;
-	}
-
 	down_write(&dmar_global_lock);
 	if (dmar_table_init()) {
 		if (force_on)
@@ -4501,7 +4204,6 @@ int __init intel_iommu_init(void)
 out_free_dmar:
 	intel_iommu_free_dmars();
 	up_write(&dmar_global_lock);
-	iommu_exit_mempool();
 	return ret;
 }
 
@@ -4552,13 +4254,11 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
 		intel_pasid_free_table(info->dev);
 	}
 
-	unlink_domain_info(info);
+	list_del(&info->link);
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	domain_detach_iommu(domain, iommu);
 	spin_unlock_irqrestore(&iommu->lock, flags);
-
-	free_devinfo_mem(info);
 }
 
 static void dmar_remove_one_dev_info(struct device *dev)
@@ -4567,7 +4267,7 @@ static void dmar_remove_one_dev_info(struct device *dev)
 	unsigned long flags;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (info)
 		__dmar_remove_one_dev_info(info);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -4637,183 +4337,6 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 		domain_exit(to_dmar_domain(domain));
 }
 
-/*
- * Check whether a @domain could be attached to the @dev through the
- * aux-domain attach/detach APIs.
- */
-static inline bool
-is_aux_domain(struct device *dev, struct iommu_domain *domain)
-{
-	struct device_domain_info *info = get_domain_info(dev);
-
-	return info && info->auxd_enabled &&
-			domain->type == IOMMU_DOMAIN_UNMANAGED;
-}
-
-static inline struct subdev_domain_info *
-lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
-{
-	struct subdev_domain_info *sinfo;
-
-	if (!list_empty(&domain->subdevices)) {
-		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
-			if (sinfo->pdev == dev)
-				return sinfo;
-		}
-	}
-
-	return NULL;
-}
-
-static int auxiliary_link_device(struct dmar_domain *domain,
-				 struct device *dev)
-{
-	struct device_domain_info *info = get_domain_info(dev);
-	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
-
-	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return -EINVAL;
-
-	if (!sinfo) {
-		sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
-		if (!sinfo)
-			return -ENOMEM;
-		sinfo->domain = domain;
-		sinfo->pdev = dev;
-		list_add(&sinfo->link_phys, &info->subdevices);
-		list_add(&sinfo->link_domain, &domain->subdevices);
-	}
-
-	return ++sinfo->users;
-}
-
-static int auxiliary_unlink_device(struct dmar_domain *domain,
-				   struct device *dev)
-{
-	struct device_domain_info *info = get_domain_info(dev);
-	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
-	int ret;
-
-	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
-		return -EINVAL;
-
-	ret = --sinfo->users;
-	if (!ret) {
-		list_del(&sinfo->link_phys);
-		list_del(&sinfo->link_domain);
-		kfree(sinfo);
-	}
-
-	return ret;
-}
-
-static int aux_domain_add_dev(struct dmar_domain *domain,
-			      struct device *dev)
-{
-	int ret;
-	unsigned long flags;
-	struct intel_iommu *iommu;
-
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return -ENODEV;
-
-	if (domain->default_pasid <= 0) {
-		u32 pasid;
-
-		/* No private data needed for the default pasid */
-		pasid = ioasid_alloc(NULL, PASID_MIN,
-				     pci_max_pasids(to_pci_dev(dev)) - 1,
-				     NULL);
-		if (pasid == INVALID_IOASID) {
-			pr_err("Can't allocate default pasid\n");
-			return -ENODEV;
-		}
-		domain->default_pasid = pasid;
-	}
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	ret = auxiliary_link_device(domain, dev);
-	if (ret <= 0)
-		goto link_failed;
-
-	/*
-	 * Subdevices from the same physical device can be attached to the
-	 * same domain. For such cases, only the first subdevice attachment
-	 * needs to go through the full steps in this function. So if ret >
-	 * 1, just goto out.
-	 */
-	if (ret > 1)
-		goto out;
-
-	/*
-	 * iommu->lock must be held to attach domain to iommu and setup the
-	 * pasid entry for second level translation.
-	 */
-	spin_lock(&iommu->lock);
-	ret = domain_attach_iommu(domain, iommu);
-	if (ret)
-		goto attach_failed;
-
-	/* Setup the PASID entry for mediated devices: */
-	if (domain_use_first_level(domain))
-		ret = domain_setup_first_level(iommu, domain, dev,
-					       domain->default_pasid);
-	else
-		ret = intel_pasid_setup_second_level(iommu, domain, dev,
-						     domain->default_pasid);
-	if (ret)
-		goto table_failed;
-
-	spin_unlock(&iommu->lock);
-out:
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return 0;
-
-table_failed:
-	domain_detach_iommu(domain, iommu);
-attach_failed:
-	spin_unlock(&iommu->lock);
-	auxiliary_unlink_device(domain, dev);
-link_failed:
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
-
-	return ret;
-}
-
-static void aux_domain_remove_dev(struct dmar_domain *domain,
-				  struct device *dev)
-{
-	struct device_domain_info *info;
-	struct intel_iommu *iommu;
-	unsigned long flags;
-
-	if (!is_aux_domain(dev, &domain->domain))
-		return;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info = get_domain_info(dev);
-	iommu = info->iommu;
-
-	if (!auxiliary_unlink_device(domain, dev)) {
-		spin_lock(&iommu->lock);
-		intel_pasid_tear_down_entry(iommu, dev,
-					    domain->default_pasid, false);
-		domain_detach_iommu(domain, iommu);
-		spin_unlock(&iommu->lock);
-	}
-
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
-}
-
 static int prepare_domain_attach_device(struct iommu_domain *domain,
 					struct device *dev)
 {
@@ -4825,13 +4348,6 @@ static int prepare_domain_attach_device(struct iommu_domain *domain,
 	if (!iommu)
 		return -ENODEV;
 
-	if ((dmar_domain->flags & DOMAIN_FLAG_NESTING_MODE) &&
-	    !ecap_nest(iommu->ecap)) {
-		dev_err(dev, "%s: iommu not support nested translation\n",
-			iommu->name);
-		return -EINVAL;
-	}
-
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
 	if (addr_width > cap_mgaw(iommu->cap))
@@ -4873,15 +4389,11 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		return -EPERM;
 	}
 
-	if (is_aux_domain(dev, domain))
-		return -EPERM;
-
 	/* normally dev is not mapped */
 	if (unlikely(domain_context_mapped(dev))) {
-		struct dmar_domain *old_domain;
+		struct device_domain_info *info = dev_iommu_priv_get(dev);
 
-		old_domain = find_domain(dev);
-		if (old_domain)
+		if (info->domain)
 			dmar_remove_one_dev_info(dev);
 	}
 
@@ -4892,212 +4404,12 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 	return domain_add_dev_info(to_dmar_domain(domain), dev);
 }
 
-static int intel_iommu_aux_attach_device(struct iommu_domain *domain,
-					 struct device *dev)
-{
-	int ret;
-
-	if (!is_aux_domain(dev, domain))
-		return -EPERM;
-
-	ret = prepare_domain_attach_device(domain, dev);
-	if (ret)
-		return ret;
-
-	return aux_domain_add_dev(to_dmar_domain(domain), dev);
-}
-
 static void intel_iommu_detach_device(struct iommu_domain *domain,
 				      struct device *dev)
 {
 	dmar_remove_one_dev_info(dev);
 }
 
-static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
-					  struct device *dev)
-{
-	aux_domain_remove_dev(to_dmar_domain(domain), dev);
-}
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-/*
- * 2D array for converting and sanitizing IOMMU generic TLB granularity to
- * VT-d granularity. Invalidation is typically included in the unmap operation
- * as a result of DMA or VFIO unmap. However, for assigned devices guest
- * owns the first level page tables. Invalidations of translation caches in the
- * guest are trapped and passed down to the host.
- *
- * vIOMMU in the guest will only expose first level page tables, therefore
- * we do not support IOTLB granularity for request without PASID (second level).
- *
- * For example, to find the VT-d granularity encoding for IOTLB
- * type and page selective granularity within PASID:
- * X: indexed by iommu cache type
- * Y: indexed by enum iommu_inv_granularity
- * [IOMMU_CACHE_INV_TYPE_IOTLB][IOMMU_INV_GRANU_ADDR]
- */
-
-static const int
-inv_type_granu_table[IOMMU_CACHE_INV_TYPE_NR][IOMMU_INV_GRANU_NR] = {
-	/*
-	 * PASID based IOTLB invalidation: PASID selective (per PASID),
-	 * page selective (address granularity)
-	 */
-	{-EINVAL, QI_GRAN_NONG_PASID, QI_GRAN_PSI_PASID},
-	/* PASID based dev TLBs */
-	{-EINVAL, -EINVAL, QI_DEV_IOTLB_GRAN_PASID_SEL},
-	/* PASID cache */
-	{-EINVAL, -EINVAL, -EINVAL}
-};
-
-static inline int to_vtd_granularity(int type, int granu)
-{
-	return inv_type_granu_table[type][granu];
-}
-
-static inline u64 to_vtd_size(u64 granu_size, u64 nr_granules)
-{
-	u64 nr_pages = (granu_size * nr_granules) >> VTD_PAGE_SHIFT;
-
-	/* VT-d size is encoded as 2^size of 4K pages, 0 for 4k, 9 for 2MB, etc.
-	 * IOMMU cache invalidate API passes granu_size in bytes, and number of
-	 * granu size in contiguous memory.
-	 */
-	return order_base_2(nr_pages);
-}
-
-static int
-intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
-{
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct device_domain_info *info;
-	struct intel_iommu *iommu;
-	unsigned long flags;
-	int cache_type;
-	u8 bus, devfn;
-	u16 did, sid;
-	int ret = 0;
-	u64 size = 0;
-
-	if (!inv_info || !dmar_domain)
-		return -EINVAL;
-
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
-	if (!(dmar_domain->flags & DOMAIN_FLAG_NESTING_MODE))
-		return -EINVAL;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	spin_lock(&iommu->lock);
-	info = get_domain_info(dev);
-	if (!info) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-	did = dmar_domain->iommu_did[iommu->seq_id];
-	sid = PCI_DEVID(bus, devfn);
-
-	/* Size is only valid in address selective invalidation */
-	if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
-		size = to_vtd_size(inv_info->granu.addr_info.granule_size,
-				   inv_info->granu.addr_info.nb_granules);
-
-	for_each_set_bit(cache_type,
-			 (unsigned long *)&inv_info->cache,
-			 IOMMU_CACHE_INV_TYPE_NR) {
-		int granu = 0;
-		u64 pasid = 0;
-		u64 addr = 0;
-
-		granu = to_vtd_granularity(cache_type, inv_info->granularity);
-		if (granu == -EINVAL) {
-			pr_err_ratelimited("Invalid cache type and granu combination %d/%d\n",
-					   cache_type, inv_info->granularity);
-			break;
-		}
-
-		/*
-		 * PASID is stored in different locations based on the
-		 * granularity.
-		 */
-		if (inv_info->granularity == IOMMU_INV_GRANU_PASID &&
-		    (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
-			pasid = inv_info->granu.pasid_info.pasid;
-		else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
-			 (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
-			pasid = inv_info->granu.addr_info.pasid;
-
-		switch (BIT(cache_type)) {
-		case IOMMU_CACHE_INV_TYPE_IOTLB:
-			/* HW will ignore LSB bits based on address mask */
-			if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
-			    size &&
-			    (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
-				pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n",
-						   inv_info->granu.addr_info.addr, size);
-			}
-
-			/*
-			 * If granu is PASID-selective, address is ignored.
-			 * We use npages = -1 to indicate that.
-			 */
-			qi_flush_piotlb(iommu, did, pasid,
-					mm_to_dma_pfn(inv_info->granu.addr_info.addr),
-					(granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size,
-					inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
-
-			if (!info->ats_enabled)
-				break;
-			/*
-			 * Always flush device IOTLB if ATS is enabled. vIOMMU
-			 * in the guest may assume IOTLB flush is inclusive,
-			 * which is more efficient.
-			 */
-			fallthrough;
-		case IOMMU_CACHE_INV_TYPE_DEV_IOTLB:
-			/*
-			 * PASID based device TLB invalidation does not support
-			 * IOMMU_INV_GRANU_PASID granularity but only supports
-			 * IOMMU_INV_GRANU_ADDR.
-			 * The equivalent of that is we set the size to be the
-			 * entire range of 64 bit. User only provides PASID info
-			 * without address info. So we set addr to 0.
-			 */
-			if (inv_info->granularity == IOMMU_INV_GRANU_PASID) {
-				size = 64 - VTD_PAGE_SHIFT;
-				addr = 0;
-			} else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) {
-				addr = inv_info->granu.addr_info.addr;
-			}
-
-			if (info->ats_enabled)
-				qi_flush_dev_iotlb_pasid(iommu, sid,
-						info->pfsid, pasid,
-						info->ats_qdep, addr,
-						size);
-			else
-				pr_warn_ratelimited("Passdown device IOTLB flush w/o ATS!\n");
-			break;
-		default:
-			dev_err_ratelimited(dev, "Unsupported IOMMU invalidation type %d\n",
-					    cache_type);
-			ret = -EINVAL;
-		}
-	}
-out_unlock:
-	spin_unlock(&iommu->lock);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return ret;
-}
-#endif
-
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
 			   size_t size, int iommu_prot, gfp_t gfp)
@@ -5245,28 +4557,73 @@ static bool intel_iommu_capable(enum iommu_cap cap)
 
 static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 {
+	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, NULL, NULL);
+	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return ERR_PTR(-ENODEV);
 
-	if (translation_pre_enabled(iommu))
-		dev_iommu_priv_set(dev, DEFER_DEVICE_DOMAIN_INFO);
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	if (dev_is_real_dma_subdevice(dev)) {
+		info->bus = pdev->bus->number;
+		info->devfn = pdev->devfn;
+		info->segment = pci_domain_nr(pdev->bus);
+	} else {
+		info->bus = bus;
+		info->devfn = devfn;
+		info->segment = iommu->segment;
+	}
+
+	info->dev = dev;
+	info->iommu = iommu;
+	if (dev_is_pci(dev)) {
+		if (ecap_dev_iotlb_support(iommu->ecap) &&
+		    pci_ats_supported(pdev) &&
+		    dmar_ats_supported(pdev, iommu))
+			info->ats_supported = 1;
+
+		if (sm_supported(iommu)) {
+			if (pasid_supported(iommu)) {
+				int features = pci_pasid_features(pdev);
+
+				if (features >= 0)
+					info->pasid_supported = features | 1;
+			}
+
+			if (info->ats_supported && ecap_prs(iommu->ecap) &&
+			    pci_pri_supported(pdev))
+				info->pri_supported = 1;
+		}
+	}
+
+	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;
 }
 
 static void intel_iommu_release_device(struct device *dev)
 {
-	struct intel_iommu *iommu;
-
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return;
+	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);
 }
 
@@ -5335,14 +4692,14 @@ static void intel_iommu_get_resv_regions(struct device *device,
 
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
 {
-	struct device_domain_info *info;
+	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;
 
-	domain = find_domain(dev);
+	domain = info->domain;
 	if (!domain)
 		return -EINVAL;
 
@@ -5350,8 +4707,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
 	spin_lock(&iommu->lock);
 
 	ret = -EINVAL;
-	info = get_domain_info(dev);
-	if (!info || !info->pasid_supported)
+	if (!info->pasid_supported)
 		goto out;
 
 	context = iommu_context_addr(iommu, info->bus, info->devfn, 0);
@@ -5391,49 +4747,9 @@ static struct iommu_group *intel_iommu_device_group(struct device *dev)
 	return generic_device_group(dev);
 }
 
-static int intel_iommu_enable_auxd(struct device *dev)
-{
-	struct device_domain_info *info;
-	struct intel_iommu *iommu;
-	unsigned long flags;
-	int ret;
-
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu || dmar_disabled)
-		return -EINVAL;
-
-	if (!sm_supported(iommu) || !pasid_supported(iommu))
-		return -EINVAL;
-
-	ret = intel_iommu_enable_pasid(iommu, dev);
-	if (ret)
-		return -ENODEV;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info = get_domain_info(dev);
-	info->auxd_enabled = 1;
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return 0;
-}
-
-static int intel_iommu_disable_auxd(struct device *dev)
-{
-	struct device_domain_info *info;
-	unsigned long flags;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	info = get_domain_info(dev);
-	if (!WARN_ON(!info))
-		info->auxd_enabled = 0;
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return 0;
-}
-
 static int intel_iommu_enable_sva(struct device *dev)
 {
-	struct device_domain_info *info = get_domain_info(dev);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu;
 	int ret;
 
@@ -5462,7 +4778,7 @@ static int intel_iommu_enable_sva(struct device *dev)
 
 static int intel_iommu_disable_sva(struct device *dev)
 {
-	struct device_domain_info *info = get_domain_info(dev);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	int ret;
 
@@ -5475,7 +4791,7 @@ static int intel_iommu_disable_sva(struct device *dev)
 
 static int intel_iommu_enable_iopf(struct device *dev)
 {
-	struct device_domain_info *info = get_domain_info(dev);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
 	if (info && info->pri_supported)
 		return 0;
@@ -5487,9 +4803,6 @@ static int
 intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
 {
 	switch (feat) {
-	case IOMMU_DEV_FEAT_AUX:
-		return intel_iommu_enable_auxd(dev);
-
 	case IOMMU_DEV_FEAT_IOPF:
 		return intel_iommu_enable_iopf(dev);
 
@@ -5505,9 +4818,6 @@ static int
 intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
 {
 	switch (feat) {
-	case IOMMU_DEV_FEAT_AUX:
-		return intel_iommu_disable_auxd(dev);
-
 	case IOMMU_DEV_FEAT_IOPF:
 		return 0;
 
@@ -5519,48 +4829,11 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
 	}
 }
 
-static bool
-intel_iommu_dev_feat_enabled(struct device *dev, enum iommu_dev_features feat)
-{
-	struct device_domain_info *info = get_domain_info(dev);
-
-	if (feat == IOMMU_DEV_FEAT_AUX)
-		return scalable_mode_support() && info && info->auxd_enabled;
-
-	return false;
-}
-
-static int
-intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+static bool intel_iommu_is_attach_deferred(struct device *dev)
 {
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
-	return dmar_domain->default_pasid > 0 ?
-			dmar_domain->default_pasid : -EINVAL;
-}
-
-static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
-					   struct device *dev)
-{
-	return attach_deferred(dev);
-}
-
-static int
-intel_iommu_enable_nesting(struct iommu_domain *domain)
-{
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	unsigned long flags;
-	int ret = -ENODEV;
-
-	spin_lock_irqsave(&device_domain_lock, flags);
-	if (list_empty(&dmar_domain->devices)) {
-		dmar_domain->flags |= DOMAIN_FLAG_NESTING_MODE;
-		dmar_domain->flags &= ~DOMAIN_FLAG_USE_FIRST_LEVEL;
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&device_domain_lock, flags);
-
-	return ret;
+	return translation_pre_enabled(info->iommu) && !info->domain;
 }
 
 /*
@@ -5598,40 +4871,34 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
-	.domain_free		= intel_iommu_domain_free,
-	.enable_nesting		= intel_iommu_enable_nesting,
-	.attach_dev		= intel_iommu_attach_device,
-	.detach_dev		= intel_iommu_detach_device,
-	.aux_attach_dev		= intel_iommu_aux_attach_device,
-	.aux_detach_dev		= intel_iommu_aux_detach_device,
-	.aux_get_pasid		= intel_iommu_aux_get_pasid,
-	.map_pages		= intel_iommu_map_pages,
-	.unmap_pages		= intel_iommu_unmap_pages,
-	.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
-	.flush_iotlb_all        = intel_flush_iotlb_all,
-	.iotlb_sync		= intel_iommu_tlb_sync,
-	.iova_to_phys		= intel_iommu_iova_to_phys,
 	.probe_device		= intel_iommu_probe_device,
 	.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_feat_enabled	= intel_iommu_dev_feat_enabled,
 	.dev_enable_feat	= intel_iommu_dev_enable_feat,
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
 	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.def_domain_type	= device_def_domain_type,
 	.pgsize_bitmap		= SZ_4K,
 #ifdef CONFIG_INTEL_IOMMU_SVM
-	.cache_invalidate	= intel_iommu_sva_invalidate,
-	.sva_bind_gpasid	= intel_svm_bind_gpasid,
-	.sva_unbind_gpasid	= intel_svm_unbind_gpasid,
 	.sva_bind		= intel_svm_bind,
 	.sva_unbind		= intel_svm_unbind,
 	.sva_get_pasid		= intel_svm_get_pasid,
 	.page_response		= intel_svm_page_response,
 #endif
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= intel_iommu_attach_device,
+		.detach_dev		= intel_iommu_detach_device,
+		.map_pages		= intel_iommu_map_pages,
+		.unmap_pages		= intel_iommu_unmap_pages,
+		.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
+		.flush_iotlb_all        = intel_flush_iotlb_all,
+		.iotlb_sync		= intel_iommu_tlb_sync,
+		.iova_to_phys		= intel_iommu_iova_to_phys,
+		.free			= intel_iommu_domain_free,
+	}
 };
 
 static void quirk_iommu_igfx(struct pci_dev *dev)
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 07c390aed1fe..f8d215d85695 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -150,7 +150,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	int size;
 
 	might_sleep();
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
 		return -EINVAL;
 
@@ -197,7 +197,7 @@ void intel_pasid_free_table(struct device *dev)
 	struct pasid_entry *table;
 	int i, max_pde;
 
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (!info || !dev_is_pci(dev) || !info->pasid_table)
 		return;
 
@@ -223,7 +223,7 @@ struct pasid_table *intel_pasid_get_table(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (!info)
 		return NULL;
 
@@ -234,7 +234,7 @@ static int intel_pasid_get_dev_max_id(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (!info || !info->pasid_table)
 		return 0;
 
@@ -254,7 +254,7 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
 		return NULL;
 
 	dir = pasid_table->table;
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	dir_index = pasid >> PASID_PDE_SHIFT;
 	index = pasid & PASID_PTE_MASK;
 
@@ -487,7 +487,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	struct device_domain_info *info;
 	u16 sid, qdep, pfsid;
 
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (!info || !info->ats_enabled)
 		return;
 
@@ -762,164 +762,3 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
-
-static int
-intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
-			    struct iommu_gpasid_bind_data_vtd *pasid_data)
-{
-	/*
-	 * Not all guest PASID table entry fields are passed down during bind,
-	 * here we only set up the ones that are dependent on guest settings.
-	 * Execution related bits such as NXE, SMEP are not supported.
-	 * Other fields, such as snoop related, are set based on host needs
-	 * regardless of guest settings.
-	 */
-	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) {
-		if (!ecap_srs(iommu->ecap)) {
-			pr_err_ratelimited("No supervisor request support on %s\n",
-					   iommu->name);
-			return -EINVAL;
-		}
-		pasid_set_sre(pte);
-		/* Enable write protect WP if guest requested */
-		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_WPE)
-			pasid_set_wpe(pte);
-	}
-
-	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) {
-		if (!ecap_eafs(iommu->ecap)) {
-			pr_err_ratelimited("No extended access flag support on %s\n",
-					   iommu->name);
-			return -EINVAL;
-		}
-		pasid_set_eafe(pte);
-	}
-
-	/*
-	 * Memory type is only applicable to devices inside processor coherent
-	 * domain. Will add MTS support once coherent devices are available.
-	 */
-	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) {
-		pr_warn_ratelimited("No memory type support %s\n",
-				    iommu->name);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * intel_pasid_setup_nested() - Set up PASID entry for nested translation.
- * This could be used for guest shared virtual address. In this case, the
- * first level page tables are used for GVA-GPA translation in the guest,
- * second level page tables are used for GPA-HPA translation.
- *
- * @iommu:      IOMMU which the device belong to
- * @dev:        Device to be set up for translation
- * @gpgd:       FLPTPTR: First Level Page translation pointer in GPA
- * @pasid:      PASID to be programmed in the device PASID table
- * @pasid_data: Additional PASID info from the guest bind request
- * @domain:     Domain info for setting up second level page tables
- * @addr_width: Address width of the first level (guest)
- */
-int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
-			     pgd_t *gpgd, u32 pasid,
-			     struct iommu_gpasid_bind_data_vtd *pasid_data,
-			     struct dmar_domain *domain, int addr_width)
-{
-	struct pasid_entry *pte;
-	struct dma_pte *pgd;
-	int ret = 0;
-	u64 pgd_val;
-	int agaw;
-	u16 did;
-
-	if (!ecap_nest(iommu->ecap)) {
-		pr_err_ratelimited("IOMMU: %s: No nested translation support\n",
-				   iommu->name);
-		return -EINVAL;
-	}
-
-	if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) {
-		pr_err_ratelimited("Domain is not in nesting mode, %x\n",
-				   domain->flags);
-		return -EINVAL;
-	}
-
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (WARN_ON(!pte))
-		return -EINVAL;
-
-	/*
-	 * Caller must ensure PASID entry is not in use, i.e. not bind the
-	 * same PASID to the same device twice.
-	 */
-	if (pasid_pte_is_present(pte))
-		return -EBUSY;
-
-	pasid_clear_entry(pte);
-
-	/* Sanity checking performed by caller to make sure address
-	 * width matching in two dimensions:
-	 * 1. CPU vs. IOMMU
-	 * 2. Guest vs. Host.
-	 */
-	switch (addr_width) {
-#ifdef CONFIG_X86
-	case ADDR_WIDTH_5LEVEL:
-		if (!cpu_feature_enabled(X86_FEATURE_LA57) ||
-		    !cap_5lp_support(iommu->cap)) {
-			dev_err_ratelimited(dev,
-					    "5-level paging not supported\n");
-			return -EINVAL;
-		}
-
-		pasid_set_flpm(pte, 1);
-		break;
-#endif
-	case ADDR_WIDTH_4LEVEL:
-		pasid_set_flpm(pte, 0);
-		break;
-	default:
-		dev_err_ratelimited(dev, "Invalid guest address width %d\n",
-				    addr_width);
-		return -EINVAL;
-	}
-
-	/* First level PGD is in GPA, must be supported by the second level */
-	if ((uintptr_t)gpgd > domain->max_addr) {
-		dev_err_ratelimited(dev,
-				    "Guest PGD %lx not supported, max %llx\n",
-				    (uintptr_t)gpgd, domain->max_addr);
-		return -EINVAL;
-	}
-	pasid_set_flptr(pte, (uintptr_t)gpgd);
-
-	ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data);
-	if (ret)
-		return ret;
-
-	/* Setup the second level based on the given domain */
-	pgd = domain->pgd;
-
-	agaw = iommu_skip_agaw(domain, iommu, &pgd);
-	if (agaw < 0) {
-		dev_err_ratelimited(dev, "Invalid domain page table\n");
-		return -EINVAL;
-	}
-	pgd_val = virt_to_phys(pgd);
-	pasid_set_slptr(pte, pgd_val);
-	pasid_set_fault_enable(pte);
-
-	did = domain->iommu_did[iommu->seq_id];
-	pasid_set_domain_id(pte, did);
-
-	pasid_set_address_width(pte, agaw);
-	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-
-	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
-	pasid_set_present(pte);
-	pasid_flush_caches(iommu, pte, pasid, did);
-
-	return ret;
-}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index d5552e2c160d..ab4408c824a5 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -118,10 +118,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
-int intel_pasid_setup_nested(struct intel_iommu *iommu,
-			     struct device *dev, pgd_t *pgd, u32 pasid,
-			     struct iommu_gpasid_bind_data_vtd *pasid_data,
-			     struct dmar_domain *domain, int addr_width);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 5b5d69b04fcc..23a38763c1d1 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -168,11 +168,6 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 	return 0;
 }
 
-static inline bool intel_svm_capable(struct intel_iommu *iommu)
-{
-	return iommu->flags & VTD_FLAG_SVM_CAPABLE;
-}
-
 void intel_svm_check(struct intel_iommu *iommu)
 {
 	if (!pasid_supported(iommu))
@@ -200,7 +195,7 @@ static void __flush_svm_range_dev(struct intel_svm *svm,
 				  unsigned long address,
 				  unsigned long pages, int ih)
 {
-	struct device_domain_info *info = get_domain_info(sdev->dev);
+	struct device_domain_info *info = dev_iommu_priv_get(sdev->dev);
 
 	if (WARN_ON(!pages))
 		return;
@@ -318,193 +313,6 @@ out:
 	return 0;
 }
 
-int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
-			  struct iommu_gpasid_bind_data *data)
-{
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	struct intel_svm_dev *sdev = NULL;
-	struct dmar_domain *dmar_domain;
-	struct device_domain_info *info;
-	struct intel_svm *svm = NULL;
-	unsigned long iflags;
-	int ret = 0;
-
-	if (WARN_ON(!iommu) || !data)
-		return -EINVAL;
-
-	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
-		return -EINVAL;
-
-	/* IOMMU core ensures argsz is more than the start of the union */
-	if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd))
-		return -EINVAL;
-
-	/* Make sure no undefined flags are used in vendor data */
-	if (data->vendor.vtd.flags & ~(IOMMU_SVA_VTD_GPASID_LAST - 1))
-		return -EINVAL;
-
-	if (!dev_is_pci(dev))
-		return -ENOTSUPP;
-
-	/* VT-d supports devices with full 20 bit PASIDs only */
-	if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX)
-		return -EINVAL;
-
-	/*
-	 * We only check host PASID range, we have no knowledge to check
-	 * guest PASID range.
-	 */
-	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
-		return -EINVAL;
-
-	info = get_domain_info(dev);
-	if (!info)
-		return -EINVAL;
-
-	dmar_domain = to_dmar_domain(domain);
-
-	mutex_lock(&pasid_mutex);
-	ret = pasid_to_svm_sdev(dev, data->hpasid, &svm, &sdev);
-	if (ret)
-		goto out;
-
-	if (sdev) {
-		/*
-		 * Do not allow multiple bindings of the same device-PASID since
-		 * there is only one SL page tables per PASID. We may revisit
-		 * once sharing PGD across domains are supported.
-		 */
-		dev_warn_ratelimited(dev, "Already bound with PASID %u\n",
-				     svm->pasid);
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (!svm) {
-		/* We come here when PASID has never been bond to a device. */
-		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
-		if (!svm) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		/* REVISIT: upper layer/VFIO can track host process that bind
-		 * the PASID. ioasid_set = mm might be sufficient for vfio to
-		 * check pasid VMM ownership. We can drop the following line
-		 * once VFIO and IOASID set check is in place.
-		 */
-		svm->mm = get_task_mm(current);
-		svm->pasid = data->hpasid;
-		if (data->flags & IOMMU_SVA_GPASID_VAL) {
-			svm->gpasid = data->gpasid;
-			svm->flags |= SVM_FLAG_GUEST_PASID;
-		}
-		pasid_private_add(data->hpasid, svm);
-		INIT_LIST_HEAD_RCU(&svm->devs);
-		mmput(svm->mm);
-	}
-	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
-	if (!sdev) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	sdev->dev = dev;
-	sdev->sid = PCI_DEVID(info->bus, info->devfn);
-	sdev->iommu = iommu;
-
-	/* Only count users if device has aux domains */
-	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
-		sdev->users = 1;
-
-	/* Set up device context entry for PASID if not enabled already */
-	ret = intel_iommu_enable_pasid(iommu, sdev->dev);
-	if (ret) {
-		dev_err_ratelimited(dev, "Failed to enable PASID capability\n");
-		kfree(sdev);
-		goto out;
-	}
-
-	/*
-	 * PASID table is per device for better security. Therefore, for
-	 * each bind of a new device even with an existing PASID, we need to
-	 * call the nested mode setup function here.
-	 */
-	spin_lock_irqsave(&iommu->lock, iflags);
-	ret = intel_pasid_setup_nested(iommu, dev,
-				       (pgd_t *)(uintptr_t)data->gpgd,
-				       data->hpasid, &data->vendor.vtd, dmar_domain,
-				       data->addr_width);
-	spin_unlock_irqrestore(&iommu->lock, iflags);
-	if (ret) {
-		dev_err_ratelimited(dev, "Failed to set up PASID %llu in nested mode, Err %d\n",
-				    data->hpasid, ret);
-		/*
-		 * PASID entry should be in cleared state if nested mode
-		 * set up failed. So we only need to clear IOASID tracking
-		 * data such that free call will succeed.
-		 */
-		kfree(sdev);
-		goto out;
-	}
-
-	svm->flags |= SVM_FLAG_GUEST_MODE;
-
-	init_rcu_head(&sdev->rcu);
-	list_add_rcu(&sdev->list, &svm->devs);
- out:
-	if (!IS_ERR_OR_NULL(svm) && list_empty(&svm->devs)) {
-		pasid_private_remove(data->hpasid);
-		kfree(svm);
-	}
-
-	mutex_unlock(&pasid_mutex);
-	return ret;
-}
-
-int intel_svm_unbind_gpasid(struct device *dev, u32 pasid)
-{
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	struct intel_svm_dev *sdev;
-	struct intel_svm *svm;
-	int ret;
-
-	if (WARN_ON(!iommu))
-		return -EINVAL;
-
-	mutex_lock(&pasid_mutex);
-	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
-	if (ret)
-		goto out;
-
-	if (sdev) {
-		if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
-			sdev->users--;
-		if (!sdev->users) {
-			list_del_rcu(&sdev->list);
-			intel_pasid_tear_down_entry(iommu, dev,
-						    svm->pasid, false);
-			intel_svm_drain_prq(dev, svm->pasid);
-			kfree_rcu(sdev, rcu);
-
-			if (list_empty(&svm->devs)) {
-				/*
-				 * We do not free the IOASID here in that
-				 * IOMMU driver did not allocate it.
-				 * Unlike native SVM, IOASID for guest use was
-				 * allocated prior to the bind call.
-				 * In any case, if the free call comes before
-				 * the unbind, IOMMU driver will get notified
-				 * and perform cleanup.
-				 */
-				pasid_private_remove(pasid);
-				kfree(svm);
-			}
-		}
-	}
-out:
-	mutex_unlock(&pasid_mutex);
-	return ret;
-}
-
 static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
 				 unsigned int flags)
 {
@@ -514,17 +322,12 @@ static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
 	return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1);
 }
 
-static void intel_svm_free_pasid(struct mm_struct *mm)
-{
-	iommu_sva_free_pasid(mm);
-}
-
 static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 					   struct device *dev,
 					   struct mm_struct *mm,
 					   unsigned int flags)
 {
-	struct device_domain_info *info = get_domain_info(dev);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	unsigned long iflags, sflags;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
@@ -662,8 +465,6 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 				kfree(svm);
 			}
 		}
-		/* Drop a PASID reference and free it if no reference. */
-		intel_svm_free_pasid(mm);
 	}
 out:
 	return ret;
@@ -732,7 +533,7 @@ static void intel_svm_drain_prq(struct device *dev, u32 pasid)
 	u16 sid, did;
 	int qdep;
 
-	info = get_domain_info(dev);
+	info = dev_iommu_priv_get(dev);
 	if (WARN_ON(!info || !dev_is_pci(dev)))
 		return;
 
@@ -1047,8 +848,6 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void
 	}
 
 	sva = intel_svm_bind_mm(iommu, dev, mm, flags);
-	if (IS_ERR_OR_NULL(sva))
-		intel_svm_free_pasid(mm);
 	mutex_unlock(&pasid_mutex);
 
 	return sva;
@@ -1126,28 +925,6 @@ int intel_svm_page_response(struct device *dev,
 	}
 
 	/*
-	 * For responses from userspace, need to make sure that the
-	 * pasid has been bound to its mm.
-	 */
-	if (svm->flags & SVM_FLAG_GUEST_MODE) {
-		struct mm_struct *mm;
-
-		mm = get_task_mm(current);
-		if (!mm) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		if (mm != svm->mm) {
-			ret = -ENODEV;
-			mmput(mm);
-			goto out;
-		}
-
-		mmput(mm);
-	}
-
-	/*
 	 * Per VT-d spec. v3.0 ch7.7, system software must respond
 	 * with page group response if private data is present (PDP)
 	 * or last page in group (LPIG) bit is set. This is an
diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c
index 06fee7416816..a786c034907c 100644
--- a/drivers/iommu/ioasid.c
+++ b/drivers/iommu/ioasid.c
@@ -2,7 +2,7 @@
 /*
  * I/O Address Space ID allocator. There is one global IOASID space, split into
  * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and
- * free IOASIDs with ioasid_alloc and ioasid_put.
+ * free IOASIDs with ioasid_alloc() and ioasid_free().
  */
 #include <linux/ioasid.h>
 #include <linux/module.h>
@@ -15,7 +15,6 @@ struct ioasid_data {
 	struct ioasid_set *set;
 	void *private;
 	struct rcu_head rcu;
-	refcount_t refs;
 };
 
 /*
@@ -315,7 +314,6 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
 
 	data->set = set;
 	data->private = private;
-	refcount_set(&data->refs, 1);
 
 	/*
 	 * Custom allocator needs allocator data to perform platform specific
@@ -348,35 +346,11 @@ exit_free:
 EXPORT_SYMBOL_GPL(ioasid_alloc);
 
 /**
- * ioasid_get - obtain a reference to the IOASID
- * @ioasid: the ID to get
- */
-void ioasid_get(ioasid_t ioasid)
-{
-	struct ioasid_data *ioasid_data;
-
-	spin_lock(&ioasid_allocator_lock);
-	ioasid_data = xa_load(&active_allocator->xa, ioasid);
-	if (ioasid_data)
-		refcount_inc(&ioasid_data->refs);
-	else
-		WARN_ON(1);
-	spin_unlock(&ioasid_allocator_lock);
-}
-EXPORT_SYMBOL_GPL(ioasid_get);
-
-/**
- * ioasid_put - Release a reference to an ioasid
+ * ioasid_free - Free an ioasid
  * @ioasid: the ID to remove
- *
- * Put a reference to the IOASID, free it when the number of references drops to
- * zero.
- *
- * Return: %true if the IOASID was freed, %false otherwise.
  */
-bool ioasid_put(ioasid_t ioasid)
+void ioasid_free(ioasid_t ioasid)
 {
-	bool free = false;
 	struct ioasid_data *ioasid_data;
 
 	spin_lock(&ioasid_allocator_lock);
@@ -386,10 +360,6 @@ bool ioasid_put(ioasid_t ioasid)
 		goto exit_unlock;
 	}
 
-	free = refcount_dec_and_test(&ioasid_data->refs);
-	if (!free)
-		goto exit_unlock;
-
 	active_allocator->ops->free(ioasid, active_allocator->ops->pdata);
 	/* Custom allocator needs additional steps to free the xa element */
 	if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) {
@@ -399,9 +369,8 @@ bool ioasid_put(ioasid_t ioasid)
 
 exit_unlock:
 	spin_unlock(&ioasid_allocator_lock);
-	return free;
 }
-EXPORT_SYMBOL_GPL(ioasid_put);
+EXPORT_SYMBOL_GPL(ioasid_free);
 
 /**
  * ioasid_find - Find IOASID data
diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c
index bd41405d34e9..106506143896 100644
--- a/drivers/iommu/iommu-sva-lib.c
+++ b/drivers/iommu/iommu-sva-lib.c
@@ -18,8 +18,7 @@ static DECLARE_IOASID_SET(iommu_sva_pasid);
  *
  * Try to allocate a PASID for this mm, or take a reference to the existing one
  * provided it fits within the [@min, @max] range. On success the PASID is
- * available in mm->pasid, and must be released with iommu_sva_free_pasid().
- * @min must be greater than 0, because 0 indicates an unused mm->pasid.
+ * available in mm->pasid and will be available for the lifetime of the mm.
  *
  * Returns 0 on success and < 0 on error.
  */
@@ -33,38 +32,24 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max)
 		return -EINVAL;
 
 	mutex_lock(&iommu_sva_lock);
-	if (mm->pasid) {
-		if (mm->pasid >= min && mm->pasid <= max)
-			ioasid_get(mm->pasid);
-		else
+	/* Is a PASID already associated with this mm? */
+	if (pasid_valid(mm->pasid)) {
+		if (mm->pasid < min || mm->pasid >= max)
 			ret = -EOVERFLOW;
-	} else {
-		pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm);
-		if (pasid == INVALID_IOASID)
-			ret = -ENOMEM;
-		else
-			mm->pasid = pasid;
+		goto out;
 	}
+
+	pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm);
+	if (!pasid_valid(pasid))
+		ret = -ENOMEM;
+	else
+		mm_pasid_set(mm, pasid);
+out:
 	mutex_unlock(&iommu_sva_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid);
 
-/**
- * iommu_sva_free_pasid - Release the mm's PASID
- * @mm: the mm
- *
- * Drop one reference to a PASID allocated with iommu_sva_alloc_pasid()
- */
-void iommu_sva_free_pasid(struct mm_struct *mm)
-{
-	mutex_lock(&iommu_sva_lock);
-	if (ioasid_put(mm->pasid))
-		mm->pasid = 0;
-	mutex_unlock(&iommu_sva_lock);
-}
-EXPORT_SYMBOL_GPL(iommu_sva_free_pasid);
-
 /* ioasid_find getter() requires a void * argument */
 static bool __mmget_not_zero(void *mm)
 {
diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h
index 031155010ca8..8909ea1094e3 100644
--- a/drivers/iommu/iommu-sva-lib.h
+++ b/drivers/iommu/iommu-sva-lib.h
@@ -9,7 +9,6 @@
 #include <linux/mm_types.h>
 
 int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
-void iommu_sva_free_pasid(struct mm_struct *mm);
 struct mm_struct *iommu_sva_find(ioasid_t pasid);
 
 /* I/O Page fault */
@@ -17,7 +16,7 @@ struct device;
 struct iommu_fault;
 struct iopf_queue;
 
-#ifdef CONFIG_IOMMU_SVA_LIB
+#ifdef CONFIG_IOMMU_SVA
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
 
 int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev);
@@ -28,7 +27,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name);
 void iopf_queue_free(struct iopf_queue *queue);
 int iopf_queue_discard_partial(struct iopf_queue *queue);
 
-#else /* CONFIG_IOMMU_SVA_LIB */
+#else /* CONFIG_IOMMU_SVA */
 static inline int iommu_queue_iopf(struct iommu_fault *fault, void *cookie)
 {
 	return -ENODEV;
@@ -64,5 +63,5 @@ static inline int iopf_queue_discard_partial(struct iopf_queue *queue)
 {
 	return -ENODEV;
 }
-#endif /* CONFIG_IOMMU_SVA_LIB */
+#endif /* CONFIG_IOMMU_SVA */
 #endif /* _IOMMU_SVA_LIB_H */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 107dcf5938d6..f2c45b85b9fc 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -323,13 +323,14 @@ err_out:
 
 void iommu_release_device(struct device *dev)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
 
 	if (!dev->iommu)
 		return;
 
 	iommu_device_unlink(dev->iommu->iommu_dev, dev);
 
+	ops = dev_iommu_ops(dev);
 	ops->release_device(dev);
 
 	iommu_group_remove_device(dev);
@@ -790,9 +791,6 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 		dma_addr_t start, end, addr;
 		size_t map_size = 0;
 
-		if (domain->ops->apply_resv_region)
-			domain->ops->apply_resv_region(dev, domain, entry);
-
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
 
@@ -833,11 +831,12 @@ out:
 	return ret;
 }
 
-static bool iommu_is_attach_deferred(struct iommu_domain *domain,
-				     struct device *dev)
+static bool iommu_is_attach_deferred(struct device *dev)
 {
-	if (domain->ops->is_attach_deferred)
-		return domain->ops->is_attach_deferred(domain, dev);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (ops->is_attach_deferred)
+		return ops->is_attach_deferred(dev);
 
 	return false;
 }
@@ -894,7 +893,7 @@ rename:
 
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
-	if (group->domain  && !iommu_is_attach_deferred(group->domain, dev))
+	if (group->domain  && !iommu_is_attach_deferred(dev))
 		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
 	if (ret)
@@ -1255,10 +1254,10 @@ int iommu_page_response(struct device *dev,
 	struct iommu_fault_event *evt;
 	struct iommu_fault_page_request *prm;
 	struct dev_iommu *param = dev->iommu;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	bool has_pasid = msg->flags & IOMMU_PAGE_RESP_PASID_VALID;
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
-	if (!domain || !domain->ops->page_response)
+	if (!ops->page_response)
 		return -ENODEV;
 
 	if (!param || !param->fault_param)
@@ -1299,7 +1298,7 @@ int iommu_page_response(struct device *dev,
 			msg->pasid = 0;
 		}
 
-		ret = domain->ops->page_response(dev, evt, msg);
+		ret = ops->page_response(dev, evt, msg);
 		list_del(&evt->list);
 		kfree(evt);
 		break;
@@ -1524,7 +1523,7 @@ EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 
 static int iommu_get_def_domain_type(struct device *dev)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 	if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted)
 		return IOMMU_DOMAIN_DMA;
@@ -1583,7 +1582,7 @@ static int iommu_alloc_default_domain(struct iommu_group *group,
  */
 static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	struct iommu_group *group;
 	int ret;
 
@@ -1591,9 +1590,6 @@ static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	if (group)
 		return group;
 
-	if (!ops)
-		return ERR_PTR(-EINVAL);
-
 	group = ops->device_group(dev);
 	if (WARN_ON_ONCE(group == NULL))
 		return ERR_PTR(-EINVAL);
@@ -1748,7 +1744,7 @@ static int iommu_group_do_dma_attach(struct device *dev, void *data)
 	struct iommu_domain *domain = data;
 	int ret = 0;
 
-	if (!iommu_is_attach_deferred(domain, dev))
+	if (!iommu_is_attach_deferred(dev))
 		ret = __iommu_attach_device(domain, dev);
 
 	return ret;
@@ -1762,10 +1758,10 @@ static int __iommu_group_dma_attach(struct iommu_group *group)
 
 static int iommu_group_do_probe_finalize(struct device *dev, void *data)
 {
-	struct iommu_domain *domain = data;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
-	if (domain->ops->probe_finalize)
-		domain->ops->probe_finalize(dev);
+	if (ops->probe_finalize)
+		ops->probe_finalize(dev);
 
 	return 0;
 }
@@ -1954,10 +1950,11 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 	if (!domain)
 		return NULL;
 
-	domain->ops  = bus->iommu_ops;
 	domain->type = type;
 	/* Assume all sizes by default; the driver may override this later */
-	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
+	domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap;
+	if (!domain->ops)
+		domain->ops = bus->iommu_ops->default_domain_ops;
 
 	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
 		iommu_domain_free(domain);
@@ -1975,7 +1972,7 @@ EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 void iommu_domain_free(struct iommu_domain *domain)
 {
 	iommu_put_dma_cookie(domain);
-	domain->ops->domain_free(domain);
+	domain->ops->free(domain);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
 
@@ -2023,228 +2020,16 @@ EXPORT_SYMBOL_GPL(iommu_attach_device);
 
 int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
 {
-	const struct iommu_ops *ops = domain->ops;
-
-	if (ops->is_attach_deferred && ops->is_attach_deferred(domain, dev))
+	if (iommu_is_attach_deferred(dev))
 		return __iommu_attach_device(domain, dev);
 
 	return 0;
 }
 
-/*
- * Check flags and other user provided data for valid combinations. We also
- * make sure no reserved fields or unused flags are set. This is to ensure
- * not breaking userspace in the future when these fields or flags are used.
- */
-static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
-{
-	u32 mask;
-	int i;
-
-	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
-		return -EINVAL;
-
-	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
-	if (info->cache & ~mask)
-		return -EINVAL;
-
-	if (info->granularity >= IOMMU_INV_GRANU_NR)
-		return -EINVAL;
-
-	switch (info->granularity) {
-	case IOMMU_INV_GRANU_ADDR:
-		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
-			return -EINVAL;
-
-		mask = IOMMU_INV_ADDR_FLAGS_PASID |
-			IOMMU_INV_ADDR_FLAGS_ARCHID |
-			IOMMU_INV_ADDR_FLAGS_LEAF;
-
-		if (info->granu.addr_info.flags & ~mask)
-			return -EINVAL;
-		break;
-	case IOMMU_INV_GRANU_PASID:
-		mask = IOMMU_INV_PASID_FLAGS_PASID |
-			IOMMU_INV_PASID_FLAGS_ARCHID;
-		if (info->granu.pasid_info.flags & ~mask)
-			return -EINVAL;
-
-		break;
-	case IOMMU_INV_GRANU_DOMAIN:
-		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Check reserved padding fields */
-	for (i = 0; i < sizeof(info->padding); i++) {
-		if (info->padding[i])
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-				void __user *uinfo)
-{
-	struct iommu_cache_invalidate_info inv_info = { 0 };
-	u32 minsz;
-	int ret;
-
-	if (unlikely(!domain->ops->cache_invalidate))
-		return -ENODEV;
-
-	/*
-	 * No new spaces can be added before the variable sized union, the
-	 * minimum size is the offset to the union.
-	 */
-	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
-
-	/* Copy minsz from user to get flags and argsz */
-	if (copy_from_user(&inv_info, uinfo, minsz))
-		return -EFAULT;
-
-	/* Fields before the variable size union are mandatory */
-	if (inv_info.argsz < minsz)
-		return -EINVAL;
-
-	/* PASID and address granu require additional info beyond minsz */
-	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
-	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
-		return -EINVAL;
-
-	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
-	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
-		return -EINVAL;
-
-	/*
-	 * User might be using a newer UAPI header which has a larger data
-	 * size, we shall support the existing flags within the current
-	 * size. Copy the remaining user data _after_ minsz but not more
-	 * than the current kernel supported size.
-	 */
-	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
-			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
-		return -EFAULT;
-
-	/* Now the argsz is validated, check the content */
-	ret = iommu_check_cache_invl_data(&inv_info);
-	if (ret)
-		return ret;
-
-	return domain->ops->cache_invalidate(domain, dev, &inv_info);
-}
-EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
-
-static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
-{
-	u64 mask;
-	int i;
-
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
-		return -EINVAL;
-
-	/* Check the range of supported formats */
-	if (data->format >= IOMMU_PASID_FORMAT_LAST)
-		return -EINVAL;
-
-	/* Check all flags */
-	mask = IOMMU_SVA_GPASID_VAL;
-	if (data->flags & ~mask)
-		return -EINVAL;
-
-	/* Check reserved padding fields */
-	for (i = 0; i < sizeof(data->padding); i++) {
-		if (data->padding[i])
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int iommu_sva_prepare_bind_data(void __user *udata,
-				       struct iommu_gpasid_bind_data *data)
-{
-	u32 minsz;
-
-	/*
-	 * No new spaces can be added before the variable sized union, the
-	 * minimum size is the offset to the union.
-	 */
-	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
-
-	/* Copy minsz from user to get flags and argsz */
-	if (copy_from_user(data, udata, minsz))
-		return -EFAULT;
-
-	/* Fields before the variable size union are mandatory */
-	if (data->argsz < minsz)
-		return -EINVAL;
-	/*
-	 * User might be using a newer UAPI header, we shall let IOMMU vendor
-	 * driver decide on what size it needs. Since the guest PASID bind data
-	 * can be vendor specific, larger argsz could be the result of extension
-	 * for one vendor but it should not affect another vendor.
-	 * Copy the remaining user data _after_ minsz
-	 */
-	if (copy_from_user((void *)data + minsz, udata + minsz,
-			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
-		return -EFAULT;
-
-	return iommu_check_bind_data(data);
-}
-
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
-			       void __user *udata)
-{
-	struct iommu_gpasid_bind_data data = { 0 };
-	int ret;
-
-	if (unlikely(!domain->ops->sva_bind_gpasid))
-		return -ENODEV;
-
-	ret = iommu_sva_prepare_bind_data(udata, &data);
-	if (ret)
-		return ret;
-
-	return domain->ops->sva_bind_gpasid(domain, dev, &data);
-}
-EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
-
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid)
-{
-	if (unlikely(!domain->ops->sva_unbind_gpasid))
-		return -ENODEV;
-
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
-}
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
-
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-				 void __user *udata)
-{
-	struct iommu_gpasid_bind_data data = { 0 };
-	int ret;
-
-	if (unlikely(!domain->ops->sva_bind_gpasid))
-		return -ENODEV;
-
-	ret = iommu_sva_prepare_bind_data(udata, &data);
-	if (ret)
-		return ret;
-
-	return iommu_sva_unbind_gpasid(domain, dev, data.hpasid);
-}
-EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
-
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
-	if (iommu_is_attach_deferred(domain, dev))
+	if (iommu_is_attach_deferred(dev))
 		return;
 
 	if (unlikely(domain->ops->detach_dev == NULL))
@@ -2458,7 +2243,7 @@ static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			     phys_addr_t paddr, size_t size, int prot,
 			     gfp_t gfp, size_t *mapped)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	size_t pgsize, count;
 	int ret;
 
@@ -2481,7 +2266,7 @@ static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
 	unsigned int min_pagesz;
 	size_t orig_size = size;
@@ -2541,7 +2326,7 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
 		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	int ret;
 
 	ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
@@ -2570,7 +2355,7 @@ static size_t __iommu_unmap_pages(struct iommu_domain *domain,
 				  unsigned long iova, size_t size,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	size_t pgsize, count;
 
 	pgsize = iommu_pgsize(domain, iova, iova, size, &count);
@@ -2583,7 +2368,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
 			    struct iommu_iotlb_gather *iotlb_gather)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	size_t unmapped_page, unmapped = 0;
 	unsigned long orig_iova = iova;
 	unsigned int min_pagesz;
@@ -2659,7 +2444,7 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		struct scatterlist *sg, unsigned int nents, int prot,
 		gfp_t gfp)
 {
-	const struct iommu_ops *ops = domain->ops;
+	const struct iommu_domain_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
 	unsigned int i = 0;
@@ -2792,17 +2577,17 @@ EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);
 
 void iommu_get_resv_regions(struct device *dev, struct list_head *list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
-	if (ops && ops->get_resv_regions)
+	if (ops->get_resv_regions)
 		ops->get_resv_regions(dev, list);
 }
 
 void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
-	if (ops && ops->put_resv_regions)
+	if (ops->put_resv_regions)
 		ops->put_resv_regions(dev, list);
 }
 
@@ -2959,8 +2744,6 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
 
 /*
  * The device drivers should do the necessary cleanups before calling this.
- * For example, before disabling the aux-domain feature, the device driver
- * should detach all aux-domains. Otherwise, this will return -EBUSY.
  */
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 {
@@ -2988,50 +2771,6 @@ bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
 }
 EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
 
-/*
- * Aux-domain specific attach/detach.
- *
- * Only works if iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX) returns
- * true. Also, as long as domains are attached to a device through this
- * interface, any tries to call iommu_attach_device() should fail
- * (iommu_detach_device() can't fail, so we fail when trying to re-attach).
- * This should make us safe against a device being attached to a guest as a
- * whole while there are still pasid users on it (aux and sva).
- */
-int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev)
-{
-	int ret = -ENODEV;
-
-	if (domain->ops->aux_attach_dev)
-		ret = domain->ops->aux_attach_dev(domain, dev);
-
-	if (!ret)
-		trace_attach_device_to_domain(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_aux_attach_device);
-
-void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev)
-{
-	if (domain->ops->aux_detach_dev) {
-		domain->ops->aux_detach_dev(domain, dev);
-		trace_detach_device_from_domain(dev);
-	}
-}
-EXPORT_SYMBOL_GPL(iommu_aux_detach_device);
-
-int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
-{
-	int ret = -ENODEV;
-
-	if (domain->ops->aux_get_pasid)
-		ret = domain->ops->aux_get_pasid(domain, dev);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_aux_get_pasid);
-
 /**
  * iommu_sva_bind_device() - Bind a process address space to a device
  * @dev: the device
@@ -3053,9 +2792,9 @@ iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
 {
 	struct iommu_group *group;
 	struct iommu_sva *handle = ERR_PTR(-EINVAL);
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
-	if (!ops || !ops->sva_bind)
+	if (!ops->sva_bind)
 		return ERR_PTR(-ENODEV);
 
 	group = iommu_group_get(dev);
@@ -3096,9 +2835,9 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_group *group;
 	struct device *dev = handle->dev;
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
-	if (!ops || !ops->sva_unbind)
+	if (!ops->sva_unbind)
 		return;
 
 	group = iommu_group_get(dev);
@@ -3115,9 +2854,9 @@ EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
 u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
-	const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
+	const struct iommu_ops *ops = dev_iommu_ops(handle->dev);
 
-	if (!ops || !ops->sva_get_pasid)
+	if (!ops->sva_get_pasid)
 		return IOMMU_PASID_INVALID;
 
 	return ops->sva_get_pasid(handle);
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index b28c9435b898..db77aa675145 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -15,13 +15,14 @@
 /* The anchor node sits above the top of the usable address space */
 #define IOVA_ANCHOR	~0UL
 
+#define IOVA_RANGE_CACHE_MAX_SIZE 6	/* log of max cached IOVA range size (in pages) */
+
 static bool iova_rcache_insert(struct iova_domain *iovad,
 			       unsigned long pfn,
 			       unsigned long size);
 static unsigned long iova_rcache_get(struct iova_domain *iovad,
 				     unsigned long size,
 				     unsigned long limit_pfn);
-static void init_iova_rcaches(struct iova_domain *iovad);
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
@@ -64,8 +65,6 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
 	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
 	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
-	cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, &iovad->cpuhp_dead);
-	init_iova_rcaches(iovad);
 }
 EXPORT_SYMBOL_GPL(init_iova_domain);
 
@@ -95,10 +94,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	cached_iova = to_iova(iovad->cached32_node);
 	if (free == cached_iova ||
 	    (free->pfn_hi < iovad->dma_32bit_pfn &&
-	     free->pfn_lo >= cached_iova->pfn_lo)) {
+	     free->pfn_lo >= cached_iova->pfn_lo))
 		iovad->cached32_node = rb_next(&free->node);
+
+	if (free->pfn_lo < iovad->dma_32bit_pfn)
 		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
-	}
 
 	cached_iova = to_iova(iovad->cached_node);
 	if (free->pfn_lo >= cached_iova->pfn_lo)
@@ -488,6 +488,13 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(free_iova_fast);
 
+static void iova_domain_free_rcaches(struct iova_domain *iovad)
+{
+	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					    &iovad->cpuhp_dead);
+	free_iova_rcaches(iovad);
+}
+
 /**
  * put_iova_domain - destroys the iova domain
  * @iovad: - iova domain in question.
@@ -497,9 +504,9 @@ void put_iova_domain(struct iova_domain *iovad)
 {
 	struct iova *iova, *tmp;
 
-	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
-					    &iovad->cpuhp_dead);
-	free_iova_rcaches(iovad);
+	if (iovad->rcaches)
+		iova_domain_free_rcaches(iovad);
+
 	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
 		free_iova_mem(iova);
 }
@@ -608,6 +615,7 @@ EXPORT_SYMBOL_GPL(reserve_iova);
  */
 
 #define IOVA_MAG_SIZE 128
+#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
 
 struct iova_magazine {
 	unsigned long size;
@@ -620,6 +628,13 @@ struct iova_cpu_rcache {
 	struct iova_magazine *prev;
 };
 
+struct iova_rcache {
+	spinlock_t lock;
+	unsigned long depot_size;
+	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+	struct iova_cpu_rcache __percpu *cpu_rcaches;
+};
+
 static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
 {
 	return kzalloc(sizeof(struct iova_magazine), flags);
@@ -693,28 +708,54 @@ static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
 	mag->pfns[mag->size++] = pfn;
 }
 
-static void init_iova_rcaches(struct iova_domain *iovad)
+int iova_domain_init_rcaches(struct iova_domain *iovad)
 {
-	struct iova_cpu_rcache *cpu_rcache;
-	struct iova_rcache *rcache;
 	unsigned int cpu;
-	int i;
+	int i, ret;
+
+	iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
+				 sizeof(struct iova_rcache),
+				 GFP_KERNEL);
+	if (!iovad->rcaches)
+		return -ENOMEM;
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		struct iova_cpu_rcache *cpu_rcache;
+		struct iova_rcache *rcache;
+
 		rcache = &iovad->rcaches[i];
 		spin_lock_init(&rcache->lock);
 		rcache->depot_size = 0;
-		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size());
-		if (WARN_ON(!rcache->cpu_rcaches))
-			continue;
+		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),
+						     cache_line_size());
+		if (!rcache->cpu_rcaches) {
+			ret = -ENOMEM;
+			goto out_err;
+		}
 		for_each_possible_cpu(cpu) {
 			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+
 			spin_lock_init(&cpu_rcache->lock);
 			cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
 			cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
+			if (!cpu_rcache->loaded || !cpu_rcache->prev) {
+				ret = -ENOMEM;
+				goto out_err;
+			}
 		}
 	}
+
+	ret = cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					       &iovad->cpuhp_dead);
+	if (ret)
+		goto out_err;
+	return 0;
+
+out_err:
+	free_iova_rcaches(iovad);
+	return ret;
 }
+EXPORT_SYMBOL_GPL(iova_domain_init_rcaches);
 
 /*
  * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
@@ -831,7 +872,7 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 {
 	unsigned int log_size = order_base_2(size);
 
-	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE || !iovad->rcaches)
 		return 0;
 
 	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
@@ -849,6 +890,8 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
+		if (!rcache->cpu_rcaches)
+			break;
 		for_each_possible_cpu(cpu) {
 			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
 			iova_magazine_free(cpu_rcache->loaded);
@@ -858,6 +901,9 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 		for (j = 0; j < rcache->depot_size; ++j)
 			iova_magazine_free(rcache->depot[j]);
 	}
+
+	kfree(iovad->rcaches);
+	iovad->rcaches = NULL;
 }
 
 /*
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ca752bdc710f..8fdb84b3642b 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -719,6 +719,7 @@ static int ipmmu_init_platform_device(struct device *dev,
 
 static const struct soc_device_attribute soc_needs_opt_in[] = {
 	{ .family = "R-Car Gen3", },
+	{ .family = "R-Car Gen4", },
 	{ .family = "RZ/G2", },
 	{ /* sentinel */ }
 };
@@ -743,7 +744,7 @@ static bool ipmmu_device_is_allowed(struct device *dev)
 	unsigned int i;
 
 	/*
-	 * R-Car Gen3 and RZ/G2 use the allow list to opt-in devices.
+	 * R-Car Gen3/4 and RZ/G2 use the allow list to opt-in devices.
 	 * For Other SoCs, this returns true anyway.
 	 */
 	if (!soc_device_match(soc_needs_opt_in))
@@ -868,14 +869,6 @@ static struct iommu_group *ipmmu_find_group(struct device *dev)
 
 static const struct iommu_ops ipmmu_ops = {
 	.domain_alloc = ipmmu_domain_alloc,
-	.domain_free = ipmmu_domain_free,
-	.attach_dev = ipmmu_attach_device,
-	.detach_dev = ipmmu_detach_device,
-	.map = ipmmu_map,
-	.unmap = ipmmu_unmap,
-	.flush_iotlb_all = ipmmu_flush_iotlb_all,
-	.iotlb_sync = ipmmu_iotlb_sync,
-	.iova_to_phys = ipmmu_iova_to_phys,
 	.probe_device = ipmmu_probe_device,
 	.release_device = ipmmu_release_device,
 	.probe_finalize = ipmmu_probe_finalize,
@@ -883,6 +876,16 @@ static const struct iommu_ops ipmmu_ops = {
 			? generic_device_group : ipmmu_find_group,
 	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
 	.of_xlate = ipmmu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= ipmmu_attach_device,
+		.detach_dev	= ipmmu_detach_device,
+		.map		= ipmmu_map,
+		.unmap		= ipmmu_unmap,
+		.flush_iotlb_all = ipmmu_flush_iotlb_all,
+		.iotlb_sync	= ipmmu_iotlb_sync,
+		.iova_to_phys	= ipmmu_iova_to_phys,
+		.free		= ipmmu_domain_free,
+	}
 };
 
 /* -----------------------------------------------------------------------------
@@ -926,7 +929,7 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
 	.utlb_offset_base = 0,
 };
 
-static const struct ipmmu_features ipmmu_features_r8a779a0 = {
+static const struct ipmmu_features ipmmu_features_rcar_gen4 = {
 	.use_ns_alias_offset = false,
 	.has_cache_leaf_nodes = true,
 	.number_of_contexts = 16,
@@ -982,7 +985,10 @@ static const struct of_device_id ipmmu_of_ids[] = {
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
 		.compatible = "renesas,ipmmu-r8a779a0",
-		.data = &ipmmu_features_r8a779a0,
+		.data = &ipmmu_features_rcar_gen4,
+	}, {
+		.compatible = "renesas,rcar-gen4-ipmmu",
+		.data = &ipmmu_features_rcar_gen4,
 	}, {
 		/* Terminator */
 	},
@@ -1006,7 +1012,9 @@ static int ipmmu_probe(struct platform_device *pdev)
 	bitmap_zero(mmu->ctx, IPMMU_CTX_MAX);
 	mmu->features = of_device_get_match_data(&pdev->dev);
 	memset(mmu->utlb_ctx, IPMMU_CTX_INVALID, mmu->features->num_utlbs);
-	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret)
+		return ret;
 
 	/* Map I/O memory and request IRQ. */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 3a38352b603f..50f57624610f 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -558,11 +558,6 @@ fail:
 	return ret;
 }
 
-static bool msm_iommu_capable(enum iommu_cap cap)
-{
-	return false;
-}
-
 static void print_ctx_regs(void __iomem *base, int ctx)
 {
 	unsigned int fsr = GET_FSR(base, ctx);
@@ -672,27 +667,28 @@ fail:
 }
 
 static struct iommu_ops msm_iommu_ops = {
-	.capable = msm_iommu_capable,
 	.domain_alloc = msm_iommu_domain_alloc,
-	.domain_free = msm_iommu_domain_free,
-	.attach_dev = msm_iommu_attach_dev,
-	.detach_dev = msm_iommu_detach_dev,
-	.map = msm_iommu_map,
-	.unmap = msm_iommu_unmap,
-	/*
-	 * Nothing is needed here, the barrier to guarantee
-	 * completion of the tlb sync operation is implicitly
-	 * taken care when the iommu client does a writel before
-	 * kick starting the other master.
-	 */
-	.iotlb_sync = NULL,
-	.iotlb_sync_map = msm_iommu_sync_map,
-	.iova_to_phys = msm_iommu_iova_to_phys,
 	.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,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= msm_iommu_attach_dev,
+		.detach_dev	= msm_iommu_detach_dev,
+		.map		= msm_iommu_map,
+		.unmap		= msm_iommu_unmap,
+		/*
+		 * Nothing is needed here, the barrier to guarantee
+		 * completion of the tlb sync operation is implicitly
+		 * taken care when the iommu client does a writel before
+		 * kick starting the other master.
+		 */
+		.iotlb_sync	= NULL,
+		.iotlb_sync_map	= msm_iommu_sync_map,
+		.iova_to_phys	= msm_iommu_iova_to_phys,
+		.free		= msm_iommu_domain_free,
+	}
 };
 
 static int msm_iommu_probe(struct platform_device *pdev)
@@ -710,36 +706,32 @@ static int msm_iommu_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&iommu->ctx_list);
 
 	iommu->pclk = devm_clk_get(iommu->dev, "smmu_pclk");
-	if (IS_ERR(iommu->pclk)) {
-		dev_err(iommu->dev, "could not get smmu_pclk\n");
-		return PTR_ERR(iommu->pclk);
-	}
+	if (IS_ERR(iommu->pclk))
+		return dev_err_probe(iommu->dev, PTR_ERR(iommu->pclk),
+				     "could not get smmu_pclk\n");
 
 	ret = clk_prepare(iommu->pclk);
-	if (ret) {
-		dev_err(iommu->dev, "could not prepare smmu_pclk\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(iommu->dev, ret,
+				     "could not prepare smmu_pclk\n");
 
 	iommu->clk = devm_clk_get(iommu->dev, "iommu_clk");
 	if (IS_ERR(iommu->clk)) {
-		dev_err(iommu->dev, "could not get iommu_clk\n");
 		clk_unprepare(iommu->pclk);
-		return PTR_ERR(iommu->clk);
+		return dev_err_probe(iommu->dev, PTR_ERR(iommu->clk),
+				     "could not get iommu_clk\n");
 	}
 
 	ret = clk_prepare(iommu->clk);
 	if (ret) {
-		dev_err(iommu->dev, "could not prepare iommu_clk\n");
 		clk_unprepare(iommu->pclk);
-		return ret;
+		return dev_err_probe(iommu->dev, ret, "could not prepare iommu_clk\n");
 	}
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iommu->base = devm_ioremap_resource(iommu->dev, r);
 	if (IS_ERR(iommu->base)) {
-		dev_err(iommu->dev, "could not get iommu base\n");
-		ret = PTR_ERR(iommu->base);
+		ret = dev_err_probe(iommu->dev, PTR_ERR(iommu->base), "could not get iommu base\n");
 		goto fail;
 	}
 	ioaddr = r->start;
@@ -831,16 +823,4 @@ static struct platform_driver msm_iommu_driver = {
 	.probe		= msm_iommu_probe,
 	.remove		= msm_iommu_remove,
 };
-
-static int __init msm_iommu_driver_init(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&msm_iommu_driver);
-	if (ret != 0)
-		pr_err("Failed to register IOMMU driver\n");
-
-	return ret;
-}
-subsys_initcall(msm_iommu_driver_init);
-
+builtin_platform_driver(msm_iommu_driver);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 25b834104790..6fd75a60abd6 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -210,33 +210,27 @@ static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
 
 static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
 {
-	for_each_m4u(data) {
-		if (pm_runtime_get_if_in_use(data->dev) <= 0)
-			continue;
-
-		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
-			       data->base + data->plat_data->inv_sel_reg);
-		writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
-		wmb(); /* Make sure the tlb flush all done */
+	unsigned long flags;
 
-		pm_runtime_put(data->dev);
-	}
+	spin_lock_irqsave(&data->tlb_lock, flags);
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+		       data->base + data->plat_data->inv_sel_reg);
+	writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
+	wmb(); /* Make sure the tlb flush all done */
+	spin_unlock_irqrestore(&data->tlb_lock, flags);
 }
 
 static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 					   size_t granule,
 					   struct mtk_iommu_data *data)
 {
-	bool has_pm = !!data->dev->pm_domain;
 	unsigned long flags;
 	int ret;
 	u32 tmp;
 
 	for_each_m4u(data) {
-		if (has_pm) {
-			if (pm_runtime_get_if_in_use(data->dev) <= 0)
-				continue;
-		}
+		if (pm_runtime_get_if_in_use(data->dev) <= 0)
+			continue;
 
 		spin_lock_irqsave(&data->tlb_lock, flags);
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
@@ -252,17 +246,18 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
 		/* tlb sync */
 		ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
 						tmp, tmp != 0, 10, 1000);
+
+		/* Clear the CPE status */
+		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
+		spin_unlock_irqrestore(&data->tlb_lock, flags);
+
 		if (ret) {
 			dev_warn(data->dev,
 				 "Partial TLB flush timed out, falling back to full flush\n");
 			mtk_iommu_tlb_flush_all(data);
 		}
-		/* Clear the CPE status */
-		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
-		spin_unlock_irqrestore(&data->tlb_lock, flags);
 
-		if (has_pm)
-			pm_runtime_put(data->dev);
+		pm_runtime_put(data->dev);
 	}
 }
 
@@ -562,22 +557,52 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct mtk_iommu_data *data;
+	struct device_link *link;
+	struct device *larbdev;
+	unsigned int larbid, larbidx, i;
 
 	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
 		return ERR_PTR(-ENODEV); /* Not a iommu client device */
 
 	data = dev_iommu_priv_get(dev);
 
+	/*
+	 * Link the consumer device with the smi-larb device(supplier).
+	 * The device that connects with each a larb is a independent HW.
+	 * All the ports in each a device should be in the same larbs.
+	 */
+	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+	for (i = 1; i < fwspec->num_ids; i++) {
+		larbidx = MTK_M4U_TO_LARB(fwspec->ids[i]);
+		if (larbid != larbidx) {
+			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
+				larbid, larbidx);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+	larbdev = data->larb_imu[larbid].dev;
+	link = device_link_add(dev, larbdev,
+			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
+	if (!link)
+		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
 	return &data->iommu;
 }
 
 static void mtk_iommu_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_data *data;
+	struct device *larbdev;
+	unsigned int larbid;
 
 	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
 		return;
 
+	data = dev_iommu_priv_get(dev);
+	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+	larbdev = data->larb_imu[larbid].dev;
+	device_link_remove(dev, larbdev);
+
 	iommu_fwspec_free(dev);
 }
 
@@ -658,15 +683,6 @@ static void mtk_iommu_get_resv_regions(struct device *dev,
 
 static const struct iommu_ops mtk_iommu_ops = {
 	.domain_alloc	= mtk_iommu_domain_alloc,
-	.domain_free	= mtk_iommu_domain_free,
-	.attach_dev	= mtk_iommu_attach_device,
-	.detach_dev	= mtk_iommu_detach_device,
-	.map		= mtk_iommu_map,
-	.unmap		= mtk_iommu_unmap,
-	.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
-	.iotlb_sync	= mtk_iommu_iotlb_sync,
-	.iotlb_sync_map	= mtk_iommu_sync_map,
-	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.probe_device	= mtk_iommu_probe_device,
 	.release_device	= mtk_iommu_release_device,
 	.device_group	= mtk_iommu_device_group,
@@ -675,6 +691,17 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.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) {
+		.attach_dev	= mtk_iommu_attach_device,
+		.detach_dev	= mtk_iommu_detach_device,
+		.map		= mtk_iommu_map,
+		.unmap		= mtk_iommu_unmap,
+		.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
+		.iotlb_sync	= mtk_iommu_iotlb_sync,
+		.iotlb_sync_map	= mtk_iommu_sync_map,
+		.iova_to_phys	= mtk_iommu_iova_to_phys,
+		.free		= mtk_iommu_domain_free,
+	}
 };
 
 static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
@@ -848,12 +875,16 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		plarbdev = of_find_device_by_node(larbnode);
 		if (!plarbdev) {
 			of_node_put(larbnode);
+			return -ENODEV;
+		}
+		if (!plarbdev->dev.driver) {
+			of_node_put(larbnode);
 			return -EPROBE_DEFER;
 		}
 		data->larb_imu[id].dev = &plarbdev->dev;
 
-		component_match_add_release(dev, &match, release_of,
-					    compare_of, larbnode);
+		component_match_add_release(dev, &match, component_release_of,
+					    component_compare_of, larbnode);
 	}
 
 	/* Get smi-common dev from the last larb. */
@@ -980,6 +1011,13 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
 	writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK, base + REG_MMU_PT_BASE_ADDR);
+
+	/*
+	 * Users may allocate dma buffer before they call pm_runtime_get,
+	 * in which case it will lack the necessary tlb flush.
+	 * Thus, make sure to update the tlb after each PM resume.
+	 */
+	mtk_iommu_tlb_flush_all(data);
 	return 0;
 }
 
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index f81fa8862ed0..b742432220c5 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -84,16 +84,6 @@ struct mtk_iommu_data {
 	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
 };
 
-static inline int compare_of(struct device *dev, void *data)
-{
-	return dev->of_node == data;
-}
-
-static inline void release_of(struct device *dev, void *data)
-{
-	of_node_put(data);
-}
-
 static inline int mtk_iommu_bind(struct device *dev)
 {
 	struct mtk_iommu_data *data = dev_get_drvdata(dev);
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index be22fcf988ce..ecff800656e6 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -423,7 +423,18 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct of_phandle_args iommu_spec;
 	struct mtk_iommu_data *data;
-	int err, idx = 0;
+	int err, idx = 0, larbid, larbidx;
+	struct device_link *link;
+	struct device *larbdev;
+
+	/*
+	 * In the deferred case, free the existed fwspec.
+	 * Always initialize the fwspec internally.
+	 */
+	if (fwspec) {
+		iommu_fwspec_free(dev);
+		fwspec = dev_iommu_fwspec_get(dev);
+	}
 
 	while (!of_parse_phandle_with_args(dev->of_node, "iommus",
 					   "#iommu-cells",
@@ -444,6 +455,23 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 
 	data = dev_iommu_priv_get(dev);
 
+	/* Link the consumer device with the smi-larb device(supplier) */
+	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	for (idx = 1; idx < fwspec->num_ids; idx++) {
+		larbidx = mt2701_m4u_to_larb(fwspec->ids[idx]);
+		if (larbid != larbidx) {
+			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
+				larbid, larbidx);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	larbdev = data->larb_imu[larbid].dev;
+	link = device_link_add(dev, larbdev,
+			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
+	if (!link)
+		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
+
 	return &data->iommu;
 }
 
@@ -464,10 +492,18 @@ static void mtk_iommu_probe_finalize(struct device *dev)
 static void mtk_iommu_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_data *data;
+	struct device *larbdev;
+	unsigned int larbid;
 
 	if (!fwspec || fwspec->ops != &mtk_iommu_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);
 }
 
@@ -514,12 +550,6 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 
 static const struct iommu_ops mtk_iommu_ops = {
 	.domain_alloc	= mtk_iommu_domain_alloc,
-	.domain_free	= mtk_iommu_domain_free,
-	.attach_dev	= mtk_iommu_attach_device,
-	.detach_dev	= mtk_iommu_detach_device,
-	.map		= mtk_iommu_map,
-	.unmap		= mtk_iommu_unmap,
-	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.probe_device	= mtk_iommu_probe_device,
 	.probe_finalize = mtk_iommu_probe_finalize,
 	.release_device	= mtk_iommu_release_device,
@@ -527,6 +557,14 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.device_group	= generic_device_group,
 	.pgsize_bitmap	= ~0UL << MT2701_IOMMU_PAGE_SHIFT,
 	.owner          = THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= mtk_iommu_attach_device,
+		.detach_dev	= mtk_iommu_detach_device,
+		.map		= mtk_iommu_map,
+		.unmap		= mtk_iommu_unmap,
+		.iova_to_phys	= mtk_iommu_iova_to_phys,
+		.free		= mtk_iommu_domain_free,
+	}
 };
 
 static const struct of_device_id mtk_iommu_of_ids[] = {
@@ -595,12 +633,16 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		plarbdev = of_find_device_by_node(larbnode);
 		if (!plarbdev) {
 			of_node_put(larbnode);
+			return -ENODEV;
+		}
+		if (!plarbdev->dev.driver) {
+			of_node_put(larbnode);
 			return -EPROBE_DEFER;
 		}
 		data->larb_imu[i].dev = &plarbdev->dev;
 
-		component_match_add_release(dev, &match, release_of,
-					    compare_of, larbnode);
+		component_match_add_release(dev, &match, component_release_of,
+					    component_compare_of, larbnode);
 	}
 
 	platform_set_drvdata(pdev, data);
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 980e4af3f06b..4aab631ef517 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1734,16 +1734,18 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev)
 
 static const struct iommu_ops omap_iommu_ops = {
 	.domain_alloc	= omap_iommu_domain_alloc,
-	.domain_free	= omap_iommu_domain_free,
-	.attach_dev	= omap_iommu_attach_dev,
-	.detach_dev	= omap_iommu_detach_dev,
-	.map		= omap_iommu_map,
-	.unmap		= omap_iommu_unmap,
-	.iova_to_phys	= omap_iommu_iova_to_phys,
 	.probe_device	= omap_iommu_probe_device,
 	.release_device	= omap_iommu_release_device,
 	.device_group	= omap_iommu_device_group,
 	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= omap_iommu_attach_dev,
+		.detach_dev	= omap_iommu_detach_dev,
+		.map		= omap_iommu_map,
+		.unmap		= omap_iommu_unmap,
+		.iova_to_phys	= omap_iommu_iova_to_phys,
+		.free		= omap_iommu_domain_free,
+	}
 };
 
 static int __init omap_iommu_init(void)
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 7f23ad61c094..ab57c4b8fade 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1187,17 +1187,19 @@ static int rk_iommu_of_xlate(struct device *dev,
 
 static const struct iommu_ops rk_iommu_ops = {
 	.domain_alloc = rk_iommu_domain_alloc,
-	.domain_free = rk_iommu_domain_free,
-	.attach_dev = rk_iommu_attach_device,
-	.detach_dev = rk_iommu_detach_device,
-	.map = rk_iommu_map,
-	.unmap = rk_iommu_unmap,
 	.probe_device = rk_iommu_probe_device,
 	.release_device = rk_iommu_release_device,
-	.iova_to_phys = rk_iommu_iova_to_phys,
 	.device_group = rk_iommu_device_group,
 	.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
 	.of_xlate = rk_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= rk_iommu_attach_device,
+		.detach_dev	= rk_iommu_detach_device,
+		.map		= rk_iommu_map,
+		.unmap		= rk_iommu_unmap,
+		.iova_to_phys	= rk_iommu_iova_to_phys,
+		.free		= rk_iommu_domain_free,
+	}
 };
 
 static int rk_iommu_probe(struct platform_device *pdev)
@@ -1407,9 +1409,4 @@ static struct platform_driver rk_iommu_driver = {
 		   .suppress_bind_attrs = true,
 	},
 };
-
-static int __init rk_iommu_init(void)
-{
-	return platform_driver_register(&rk_iommu_driver);
-}
-subsys_initcall(rk_iommu_init);
+builtin_platform_driver(rk_iommu_driver);
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 50860ebdd087..3833e86c6e7b 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -363,16 +363,18 @@ void zpci_destroy_iommu(struct zpci_dev *zdev)
 static const struct iommu_ops s390_iommu_ops = {
 	.capable = s390_iommu_capable,
 	.domain_alloc = s390_domain_alloc,
-	.domain_free = s390_domain_free,
-	.attach_dev = s390_iommu_attach_device,
-	.detach_dev = s390_iommu_detach_device,
-	.map = s390_iommu_map,
-	.unmap = s390_iommu_unmap,
-	.iova_to_phys = s390_iommu_iova_to_phys,
 	.probe_device = s390_iommu_probe_device,
 	.release_device = s390_iommu_release_device,
 	.device_group = generic_device_group,
 	.pgsize_bitmap = S390_IOMMU_PGSIZES,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= s390_iommu_attach_device,
+		.detach_dev	= s390_iommu_detach_device,
+		.map		= s390_iommu_map,
+		.unmap		= s390_iommu_unmap,
+		.iova_to_phys	= s390_iommu_iova_to_phys,
+		.free		= s390_domain_free,
+	}
 };
 
 static int __init s390_iommu_init(void)
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index 27ac818b0354..bd409bab6286 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -416,20 +416,22 @@ static int sprd_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 
 static const struct iommu_ops sprd_iommu_ops = {
 	.domain_alloc	= sprd_iommu_domain_alloc,
-	.domain_free	= sprd_iommu_domain_free,
-	.attach_dev	= sprd_iommu_attach_device,
-	.detach_dev	= sprd_iommu_detach_device,
-	.map		= sprd_iommu_map,
-	.unmap		= sprd_iommu_unmap,
-	.iotlb_sync_map	= sprd_iommu_sync_map,
-	.iotlb_sync	= sprd_iommu_sync,
-	.iova_to_phys	= sprd_iommu_iova_to_phys,
 	.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,
 	.owner		= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= sprd_iommu_attach_device,
+		.detach_dev	= sprd_iommu_detach_device,
+		.map		= sprd_iommu_map,
+		.unmap		= sprd_iommu_unmap,
+		.iotlb_sync_map	= sprd_iommu_sync_map,
+		.iotlb_sync	= sprd_iommu_sync,
+		.iova_to_phys	= sprd_iommu_iova_to_phys,
+		.free		= sprd_iommu_domain_free,
+	}
 };
 
 static const struct of_device_id sprd_iommu_of_match[] = {
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
index 92997021e188..c54ab477b8fd 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -760,19 +760,21 @@ static int sun50i_iommu_of_xlate(struct device *dev,
 
 static const struct iommu_ops sun50i_iommu_ops = {
 	.pgsize_bitmap	= SZ_4K,
-	.attach_dev	= sun50i_iommu_attach_device,
-	.detach_dev	= sun50i_iommu_detach_device,
 	.device_group	= sun50i_iommu_device_group,
 	.domain_alloc	= sun50i_iommu_domain_alloc,
-	.domain_free	= sun50i_iommu_domain_free,
-	.flush_iotlb_all = sun50i_iommu_flush_iotlb_all,
-	.iotlb_sync	= sun50i_iommu_iotlb_sync,
-	.iova_to_phys	= sun50i_iommu_iova_to_phys,
-	.map		= sun50i_iommu_map,
 	.of_xlate	= sun50i_iommu_of_xlate,
 	.probe_device	= sun50i_iommu_probe_device,
 	.release_device	= sun50i_iommu_release_device,
-	.unmap		= sun50i_iommu_unmap,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= sun50i_iommu_attach_device,
+		.detach_dev	= sun50i_iommu_detach_device,
+		.flush_iotlb_all = sun50i_iommu_flush_iotlb_all,
+		.iotlb_sync	= sun50i_iommu_iotlb_sync,
+		.iova_to_phys	= sun50i_iommu_iova_to_phys,
+		.map		= sun50i_iommu_map,
+		.unmap		= sun50i_iommu_unmap,
+		.free		= sun50i_iommu_domain_free,
+	}
 };
 
 static void sun50i_iommu_report_fault(struct sun50i_iommu *iommu,
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 6a358f92c7e5..a6700a40a6f8 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -238,11 +238,6 @@ static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pte & GART_PAGE_MASK;
 }
 
-static bool gart_iommu_capable(enum iommu_cap cap)
-{
-	return false;
-}
-
 static struct iommu_device *gart_iommu_probe_device(struct device *dev)
 {
 	if (!dev_iommu_fwspec_get(dev))
@@ -276,21 +271,22 @@ static void gart_iommu_sync(struct iommu_domain *domain,
 }
 
 static const struct iommu_ops gart_iommu_ops = {
-	.capable	= gart_iommu_capable,
 	.domain_alloc	= gart_iommu_domain_alloc,
-	.domain_free	= gart_iommu_domain_free,
-	.attach_dev	= gart_iommu_attach_dev,
-	.detach_dev	= gart_iommu_detach_dev,
 	.probe_device	= gart_iommu_probe_device,
 	.release_device	= gart_iommu_release_device,
 	.device_group	= generic_device_group,
-	.map		= gart_iommu_map,
-	.unmap		= gart_iommu_unmap,
-	.iova_to_phys	= gart_iommu_iova_to_phys,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
 	.of_xlate	= gart_iommu_of_xlate,
-	.iotlb_sync_map	= gart_iommu_sync_map,
-	.iotlb_sync	= gart_iommu_sync,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= gart_iommu_attach_dev,
+		.detach_dev	= gart_iommu_detach_dev,
+		.map		= gart_iommu_map,
+		.unmap		= gart_iommu_unmap,
+		.iova_to_phys	= gart_iommu_iova_to_phys,
+		.iotlb_sync_map	= gart_iommu_sync_map,
+		.iotlb_sync	= gart_iommu_sync,
+		.free		= gart_iommu_domain_free,
+	}
 };
 
 int tegra_gart_suspend(struct gart_device *gart)
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index e900e3c46903..1fea68e551f1 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -272,11 +272,6 @@ static void tegra_smmu_free_asid(struct tegra_smmu *smmu, unsigned int id)
 	clear_bit(id, smmu->asids);
 }
 
-static bool tegra_smmu_capable(enum iommu_cap cap)
-{
-	return false;
-}
-
 static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
 {
 	struct tegra_smmu_as *as;
@@ -808,8 +803,10 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
 		return NULL;
 
 	mc = platform_get_drvdata(pdev);
-	if (!mc)
+	if (!mc) {
+		put_device(&pdev->dev);
 		return NULL;
+	}
 
 	return mc->smmu;
 }
@@ -967,19 +964,20 @@ static int tegra_smmu_of_xlate(struct device *dev,
 }
 
 static const struct iommu_ops tegra_smmu_ops = {
-	.capable = tegra_smmu_capable,
 	.domain_alloc = tegra_smmu_domain_alloc,
-	.domain_free = tegra_smmu_domain_free,
-	.attach_dev = tegra_smmu_attach_dev,
-	.detach_dev = tegra_smmu_detach_dev,
 	.probe_device = tegra_smmu_probe_device,
 	.release_device = tegra_smmu_release_device,
 	.device_group = tegra_smmu_device_group,
-	.map = tegra_smmu_map,
-	.unmap = tegra_smmu_unmap,
-	.iova_to_phys = tegra_smmu_iova_to_phys,
 	.of_xlate = tegra_smmu_of_xlate,
 	.pgsize_bitmap = SZ_4K,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= tegra_smmu_attach_dev,
+		.detach_dev	= tegra_smmu_detach_dev,
+		.map		= tegra_smmu_map,
+		.unmap		= tegra_smmu_unmap,
+		.iova_to_phys	= tegra_smmu_iova_to_phys,
+		.free		= tegra_smmu_domain_free,
+	}
 };
 
 static void tegra_smmu_ahb_enable(void)
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index f2aa34f57454..25be4b822aa0 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -1008,12 +1008,6 @@ static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 
 static struct iommu_ops viommu_ops = {
 	.domain_alloc		= viommu_domain_alloc,
-	.domain_free		= viommu_domain_free,
-	.attach_dev		= viommu_attach_dev,
-	.map			= viommu_map,
-	.unmap			= viommu_unmap,
-	.iova_to_phys		= viommu_iova_to_phys,
-	.iotlb_sync		= viommu_iotlb_sync,
 	.probe_device		= viommu_probe_device,
 	.probe_finalize		= viommu_probe_finalize,
 	.release_device		= viommu_release_device,
@@ -1022,6 +1016,14 @@ static struct iommu_ops viommu_ops = {
 	.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,
+		.iova_to_phys		= viommu_iova_to_phys,
+		.iotlb_sync		= viommu_iotlb_sync,
+		.free			= viommu_domain_free,
+	}
 };
 
 static int viommu_init_vqs(struct viommu_dev *viommu)