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
  ...

Author: torvalds

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;