Merge tag 'iommu-updates-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - IOMMU Core changes:
      - Removal of aux domain related code as it is basically dead and
        will be replaced by iommu-fd framework
      - Split of iommu_ops to carry domain-specific call-backs separatly
      - Cleanup to remove useless ops->capable implementations
      - Improve 32-bit free space estimate in iova allocator

 - Intel VT-d updates:
      - Various cleanups of the driver
      - Support for ATS of SoC-integrated devices listed in ACPI/SATC
        table

 - ARM SMMU updates:
      - Fix SMMUv3 soft lockup during continuous stream of events
      - Fix error path for Qualcomm SMMU probe()
      - Rework SMMU IRQ setup to prepare the ground for PMU support
      - Minor cleanups and refactoring

 - AMD IOMMU driver:
      - Some minor cleanups and error-handling fixes

 - Rockchip IOMMU driver:
      - Use standard driver registration

 - MSM IOMMU driver:
      - Minor cleanup and change to standard driver registration

 - Mediatek IOMMU driver:
      - Fixes for IOTLB flushing logic

* tag 'iommu-updates-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (47 commits)
  iommu/amd: Improve amd_iommu_v2_exit()
  iommu/amd: Remove unused struct fault.devid
  iommu/amd: Clean up function declarations
  iommu/amd: Call memunmap in error path
  iommu/arm-smmu: Account for PMU interrupts
  iommu/vt-d: Enable ATS for the devices in SATC table
  iommu/vt-d: Remove unused function intel_svm_capable()
  iommu/vt-d: Add missing "__init" for rmrr_sanity_check()
  iommu/vt-d: Move intel_iommu_ops to header file
  iommu/vt-d: Fix indentation of goto labels
  iommu/vt-d: Remove unnecessary prototypes
  iommu/vt-d: Remove unnecessary includes
  iommu/vt-d: Remove DEFER_DEVICE_DOMAIN_INFO
  iommu/vt-d: Remove domain and devinfo mempool
  iommu/vt-d: Remove iova_cache_get/put()
  iommu/vt-d: Remove finding domain in dmar_insert_one_dev_info()
  iommu/vt-d: Remove intel_iommu::domains
  iommu/mediatek: Always tlb_flush_all when each PM resume
  iommu/mediatek: Add tlb_lock in tlb_flush_all
  iommu/mediatek: Remove the power status checking in tlb flush all
  ...

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

@@ -44,6 +44,10 @@ properties:
               - renesas,ipmmu-r8a77990 # R-Car E3
               - renesas,ipmmu-r8a77995 # R-Car D3
               - renesas,ipmmu-r8a779a0 # R-Car V3U
+      - items:
+          - enum:
+              - renesas,ipmmu-r8a779f0 # R-Car S4-8
+          - const: renesas,rcar-gen4-ipmmu-vmsa  # R-Car Gen4
 
   reg:
     maxItems: 1

drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c

@@ -133,7 +133,7 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 		 * or equal to the system's PAGE_SIZE, with a preference if
 		 * both are equal.
 		 */
-		pgsize_bitmap = tdev->iommu.domain->ops->pgsize_bitmap;
+		pgsize_bitmap = tdev->iommu.domain->pgsize_bitmap;
 		if (pgsize_bitmap & PAGE_SIZE) {
 			tdev->iommu.pgshift = PAGE_SHIFT;
 		} else {

drivers/iommu/amd/amd_iommu.h

@@ -15,7 +15,6 @@ 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_restart_event_logging(struct amd_iommu *iommu);
-extern void amd_iommu_reset_cmd_buffer(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);
@@ -117,8 +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);
 

drivers/iommu/amd/init.c

@@ -671,7 +671,7 @@ void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
  * 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);
 
@@ -990,6 +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;
 	}
 
@@ -1020,6 +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;
 			}
 
@@ -1953,9 +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);
 	}
@@ -1971,6 +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();
 
@@ -1980,6 +1989,7 @@ static int __init amd_iommu_init_pci(void)
 	if (!ret)
 		print_iommu_info();
 
+out:
 	return ret;
 }
 

drivers/iommu/amd/iommu.c

@@ -2221,8 +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);
 
@@ -2275,13 +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,
@@ -2290,9 +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,
+	}
 };
 
 /*****************************************************************************

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 @@ static int __init amd_iommu_v2_init(void)
 
 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);
 }
 

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)

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;
 

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,

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;
 

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)

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))

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)

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)

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");
 

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;

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;
-}

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);

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 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 	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)
 {
@@ -519,7 +327,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 					   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;
@@ -725,7 +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;
 
@@ -1116,28 +924,6 @@ int intel_svm_page_response(struct device *dev,
 		goto out;
 	}
 
-	/*
-	 * 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)

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;
 }
 
 /*

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);

drivers/iommu/msm_iommu.c

@@ -558,11 +558,6 @@ static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
 	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 @@ irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
 }
 
 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);

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);
 	}
 }
 
@@ -688,15 +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,
@@ -705,6 +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)
@@ -1014,6 +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;
 }
 

drivers/iommu/mtk_iommu_v1.c

@@ -550,12 +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,
@@ -563,6 +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[] = {

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)

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);

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)

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[] = {

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,

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)

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;
@@ -969,19 +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)

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)

drivers/perf/arm_smmuv3_pmu.c

@@ -654,6 +654,7 @@ static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
 {
 	struct smmu_pmu *smmu_pmu = data;
+	DECLARE_BITMAP(ovs, BITS_PER_TYPE(u64));
 	u64 ovsr;
 	unsigned int idx;
 
@@ -663,7 +664,8 @@ static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
 
 	writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
 
-	for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+	bitmap_from_u64(ovs, ovsr);
+	for_each_set_bit(idx, ovs, smmu_pmu->num_counters) {
 		struct perf_event *event = smmu_pmu->events[idx];
 		struct hw_perf_event *hwc;
 

drivers/vdpa/vdpa_user/iova_domain.c

@@ -480,6 +480,7 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size)
 	struct file *file;
 	struct vduse_bounce_map *map;
 	unsigned long pfn, bounce_pfns;
+	int ret;
 
 	bounce_pfns = PAGE_ALIGN(bounce_size) >> PAGE_SHIFT;
 	if (iova_limit <= bounce_size)
@@ -513,10 +514,20 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size)
 	spin_lock_init(&domain->iotlb_lock);
 	init_iova_domain(&domain->stream_iovad,
 			PAGE_SIZE, IOVA_START_PFN);
+	ret = iova_domain_init_rcaches(&domain->stream_iovad);
+	if (ret)
+		goto err_iovad_stream;
 	init_iova_domain(&domain->consistent_iovad,
 			PAGE_SIZE, bounce_pfns);
+	ret = iova_domain_init_rcaches(&domain->consistent_iovad);
+	if (ret)
+		goto err_iovad_consistent;
 
 	return domain;
+err_iovad_consistent:
+	put_iova_domain(&domain->stream_iovad);
+err_iovad_stream:
+	fput(file);
 err_file:
 	vfree(domain->bounce_maps);
 err_map:

include/linux/intel-iommu.h

@@ -525,12 +525,6 @@ struct context_entry {
  */
 #define DOMAIN_FLAG_USE_FIRST_LEVEL		BIT(1)
 
-/*
- * Domain represents a virtual machine which demands iommu nested
- * translation mode support.
- */
-#define DOMAIN_FLAG_NESTING_MODE		BIT(2)
-
 struct dmar_domain {
 	int	nid;			/* node id */
 
@@ -548,7 +542,6 @@ struct dmar_domain {
 	u8 iommu_snooping: 1;		/* indicate snooping control feature */
 
 	struct list_head devices;	/* all devices' list */
-	struct list_head subdevices;	/* all subdevices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -563,11 +556,6 @@ struct dmar_domain {
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	u64		max_addr;	/* maximum mapped address */
 
-	u32		default_pasid;	/*
-					 * The default pasid used for non-SVM
-					 * traffic on mediated devices.
-					 */
-
 	struct iommu_domain domain;	/* generic domain data structure for
 					   iommu core */
 };
@@ -590,7 +578,6 @@ struct intel_iommu {
 
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
-	struct dmar_domain ***domains; /* ptr to domains */
 	spinlock_t	lock; /* protect context, domain ids */
 	struct root_entry *root_entry; /* virtual address */
 
@@ -620,21 +607,11 @@ struct intel_iommu {
 	void *perf_statistic;
 };
 
-/* Per subdevice private data */
-struct subdev_domain_info {
-	struct list_head link_phys;	/* link to phys device siblings */
-	struct list_head link_domain;	/* link to domain siblings */
-	struct device *pdev;		/* physical device derived from */
-	struct dmar_domain *domain;	/* aux-domain */
-	int users;			/* user count */
-};
-
 /* PCI domain-device relationship */
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
 	struct list_head table;	/* link to pasid table */
-	struct list_head subdevices; /* subdevices sibling */
 	u32 segment;		/* PCI segment number */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
@@ -645,7 +622,6 @@ struct device_domain_info {
 	u8 pri_enabled:1;
 	u8 ats_supported:1;
 	u8 ats_enabled:1;
-	u8 auxd_enabled:1;	/* Multiple domains per device */
 	u8 ats_qdep;
 	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
@@ -717,7 +693,6 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte)
 }
 
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
-extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
 
 extern int dmar_enable_qi(struct intel_iommu *iommu);
 extern void dmar_disable_qi(struct intel_iommu *iommu);
@@ -757,17 +732,12 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
-struct dmar_domain *find_domain(struct device *dev);
-struct device_domain_info *get_domain_info(struct device *dev);
 struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
-			  struct iommu_gpasid_bind_data *data);
-int intel_svm_unbind_gpasid(struct device *dev, u32 pasid);
 struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
 				 void *drvdata);
 void intel_svm_unbind(struct iommu_sva *handle);
@@ -795,7 +765,6 @@ struct intel_svm {
 
 	unsigned int flags;
 	u32 pasid;
-	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
 };
 #else
@@ -813,6 +782,8 @@ bool context_present(struct context_entry *context);
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 					 u8 devfn, int alloc);
 
+extern const struct iommu_ops intel_iommu_ops;
+
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);

include/linux/intel-svm.h

@@ -25,17 +25,5 @@
  * do such IOTLB flushes automatically.
  */
 #define SVM_FLAG_SUPERVISOR_MODE	BIT(0)
-/*
- * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest
- * processes. Compared to the host bind, the primary differences are:
- * 1. mm life cycle management
- * 2. fault reporting
- */
-#define SVM_FLAG_GUEST_MODE		BIT(1)
-/*
- * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space,
- * which requires guest and host PASID translation at both directions.
- */
-#define SVM_FLAG_GUEST_PASID		BIT(2)
 
 #endif /* __INTEL_SVM_H__ */

include/linux/iova.h

@@ -21,18 +21,8 @@ struct iova {
 	unsigned long	pfn_lo; /* Lowest allocated pfn */
 };
 
-struct iova_magazine;
-struct iova_cpu_rcache;
 
-#define IOVA_RANGE_CACHE_MAX_SIZE 6	/* log of max cached IOVA range size (in pages) */
-#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
-
-struct iova_rcache {
-	spinlock_t lock;
-	unsigned long depot_size;
-	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
-	struct iova_cpu_rcache __percpu *cpu_rcaches;
-};
+struct iova_rcache;
 
 /* holds all the iova translations for a domain */
 struct iova_domain {
@@ -46,7 +36,7 @@ struct iova_domain {
 	unsigned long	max32_alloc_size; /* Size of last failed allocation */
 	struct iova	anchor;		/* rbtree lookup anchor */
 
-	struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE];	/* IOVA range caches */
+	struct iova_rcache	*rcaches;
 	struct hlist_node	cpuhp_dead;
 };
 
@@ -102,6 +92,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	unsigned long start_pfn);
+int iova_domain_init_rcaches(struct iova_domain *iovad);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
 #else

include/uapi/linux/iommu.h

@@ -158,185 +158,4 @@ struct iommu_page_response {
 	__u32	code;
 };
 
-/* defines the granularity of the invalidation */
-enum iommu_inv_granularity {
-	IOMMU_INV_GRANU_DOMAIN,	/* domain-selective invalidation */
-	IOMMU_INV_GRANU_PASID,	/* PASID-selective invalidation */
-	IOMMU_INV_GRANU_ADDR,	/* page-selective invalidation */
-	IOMMU_INV_GRANU_NR,	/* number of invalidation granularities */
-};
-
-/**
- * struct iommu_inv_addr_info - Address Selective Invalidation Structure
- *
- * @flags: indicates the granularity of the address-selective invalidation
- * - If the PASID bit is set, the @pasid field is populated and the invalidation
- *   relates to cache entries tagged with this PASID and matching the address
- *   range.
- * - If ARCHID bit is set, @archid is populated and the invalidation relates
- *   to cache entries tagged with this architecture specific ID and matching
- *   the address range.
- * - Both PASID and ARCHID can be set as they may tag different caches.
- * - If neither PASID or ARCHID is set, global addr invalidation applies.
- * - The LEAF flag indicates whether only the leaf PTE caching needs to be
- *   invalidated and other paging structure caches can be preserved.
- * @pasid: process address space ID
- * @archid: architecture-specific ID
- * @addr: first stage/level input address
- * @granule_size: page/block size of the mapping in bytes
- * @nb_granules: number of contiguous granules to be invalidated
- */
-struct iommu_inv_addr_info {
-#define IOMMU_INV_ADDR_FLAGS_PASID	(1 << 0)
-#define IOMMU_INV_ADDR_FLAGS_ARCHID	(1 << 1)
-#define IOMMU_INV_ADDR_FLAGS_LEAF	(1 << 2)
-	__u32	flags;
-	__u32	archid;
-	__u64	pasid;
-	__u64	addr;
-	__u64	granule_size;
-	__u64	nb_granules;
-};
-
-/**
- * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure
- *
- * @flags: indicates the granularity of the PASID-selective invalidation
- * - If the PASID bit is set, the @pasid field is populated and the invalidation
- *   relates to cache entries tagged with this PASID and matching the address
- *   range.
- * - If the ARCHID bit is set, the @archid is populated and the invalidation
- *   relates to cache entries tagged with this architecture specific ID and
- *   matching the address range.
- * - Both PASID and ARCHID can be set as they may tag different caches.
- * - At least one of PASID or ARCHID must be set.
- * @pasid: process address space ID
- * @archid: architecture-specific ID
- */
-struct iommu_inv_pasid_info {
-#define IOMMU_INV_PASID_FLAGS_PASID	(1 << 0)
-#define IOMMU_INV_PASID_FLAGS_ARCHID	(1 << 1)
-	__u32	flags;
-	__u32	archid;
-	__u64	pasid;
-};
-
-/**
- * struct iommu_cache_invalidate_info - First level/stage invalidation
- *     information
- * @argsz: User filled size of this data
- * @version: API version of this structure
- * @cache: bitfield that allows to select which caches to invalidate
- * @granularity: defines the lowest granularity used for the invalidation:
- *     domain > PASID > addr
- * @padding: reserved for future use (should be zero)
- * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID
- * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR
- *
- * Not all the combinations of cache/granularity are valid:
- *
- * +--------------+---------------+---------------+---------------+
- * | type /       |   DEV_IOTLB   |     IOTLB     |      PASID    |
- * | granularity  |               |               |      cache    |
- * +==============+===============+===============+===============+
- * | DOMAIN       |       N/A     |       Y       |       Y       |
- * +--------------+---------------+---------------+---------------+
- * | PASID        |       Y       |       Y       |       Y       |
- * +--------------+---------------+---------------+---------------+
- * | ADDR         |       Y       |       Y       |       N/A     |
- * +--------------+---------------+---------------+---------------+
- *
- * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than
- * @version and @cache.
- *
- * If multiple cache types are invalidated simultaneously, they all
- * must support the used granularity.
- */
-struct iommu_cache_invalidate_info {
-	__u32	argsz;
-#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
-	__u32	version;
-/* IOMMU paging structure cache */
-#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
-#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
-#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
-#define IOMMU_CACHE_INV_TYPE_NR		(3)
-	__u8	cache;
-	__u8	granularity;
-	__u8	padding[6];
-	union {
-		struct iommu_inv_pasid_info pasid_info;
-		struct iommu_inv_addr_info addr_info;
-	} granu;
-};
-
-/**
- * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest
- * SVA binding.
- *
- * @flags:	VT-d PASID table entry attributes
- * @pat:	Page attribute table data to compute effective memory type
- * @emt:	Extended memory type
- *
- * Only guest vIOMMU selectable and effective options are passed down to
- * the host IOMMU.
- */
-struct iommu_gpasid_bind_data_vtd {
-#define IOMMU_SVA_VTD_GPASID_SRE	(1 << 0) /* supervisor request */
-#define IOMMU_SVA_VTD_GPASID_EAFE	(1 << 1) /* extended access enable */
-#define IOMMU_SVA_VTD_GPASID_PCD	(1 << 2) /* page-level cache disable */
-#define IOMMU_SVA_VTD_GPASID_PWT	(1 << 3) /* page-level write through */
-#define IOMMU_SVA_VTD_GPASID_EMTE	(1 << 4) /* extended mem type enable */
-#define IOMMU_SVA_VTD_GPASID_CD		(1 << 5) /* PASID-level cache disable */
-#define IOMMU_SVA_VTD_GPASID_WPE	(1 << 6) /* Write protect enable */
-#define IOMMU_SVA_VTD_GPASID_LAST	(1 << 7)
-	__u64 flags;
-	__u32 pat;
-	__u32 emt;
-};
-
-#define IOMMU_SVA_VTD_GPASID_MTS_MASK	(IOMMU_SVA_VTD_GPASID_CD | \
-					 IOMMU_SVA_VTD_GPASID_EMTE | \
-					 IOMMU_SVA_VTD_GPASID_PCD |  \
-					 IOMMU_SVA_VTD_GPASID_PWT)
-
-/**
- * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
- * @argsz:	User filled size of this data
- * @version:	Version of this data structure
- * @format:	PASID table entry format
- * @flags:	Additional information on guest bind request
- * @gpgd:	Guest page directory base of the guest mm to bind
- * @hpasid:	Process address space ID used for the guest mm in host IOMMU
- * @gpasid:	Process address space ID used for the guest mm in guest IOMMU
- * @addr_width:	Guest virtual address width
- * @padding:	Reserved for future use (should be zero)
- * @vtd:	Intel VT-d specific data
- *
- * Guest to host PASID mapping can be an identity or non-identity, where guest
- * has its own PASID space. For non-identify mapping, guest to host PASID lookup
- * is needed when VM programs guest PASID into an assigned device. VMM may
- * trap such PASID programming then request host IOMMU driver to convert guest
- * PASID to host PASID based on this bind data.
- */
-struct iommu_gpasid_bind_data {
-	__u32 argsz;
-#define IOMMU_GPASID_BIND_VERSION_1	1
-	__u32 version;
-#define IOMMU_PASID_FORMAT_INTEL_VTD	1
-#define IOMMU_PASID_FORMAT_LAST		2
-	__u32 format;
-	__u32 addr_width;
-#define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
-	__u64 flags;
-	__u64 gpgd;
-	__u64 hpasid;
-	__u64 gpasid;
-	__u8  padding[8];
-	/* Vendor specific data */
-	union {
-		struct iommu_gpasid_bind_data_vtd vtd;
-	} vendor;
-};
-
 #endif /* _UAPI_IOMMU_H */