Merge branches 'iommu/fixes', 'arm/omap', 'arm/exynos', 'x86/amd', 'x…

…86/vt-d' and 'core' into next

drivers/gpu/drm/tegra/drm.c

@@ -155,8 +155,7 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 
 		order = __ffs(tegra->domain->pgsize_bitmap);
 		init_iova_domain(&tegra->carveout.domain, 1UL << order,
-				 carveout_start >> order,
-				 carveout_end >> order);
+				 carveout_start >> order);
 
 		tegra->carveout.shift = iova_shift(&tegra->carveout.domain);
 		tegra->carveout.limit = carveout_end >> tegra->carveout.shift;

drivers/gpu/host1x/dev.c

@@ -198,8 +198,7 @@ static int host1x_probe(struct platform_device *pdev)
 
 		order = __ffs(host->domain->pgsize_bitmap);
 		init_iova_domain(&host->iova, 1UL << order,
-				 geometry->aperture_start >> order,
-				 geometry->aperture_end >> order);
+				 geometry->aperture_start >> order);
 		host->iova_end = geometry->aperture_end;
 	}
 

drivers/iommu/amd_iommu.c

@@ -63,7 +63,6 @@
 /* IO virtual address start page frame number */
 #define IOVA_START_PFN		(1)
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 
 /* Reserved IOVA ranges */
 #define MSI_RANGE_START		(0xfee00000)
@@ -1547,10 +1546,11 @@ static unsigned long dma_ops_alloc_iova(struct device *dev,
 
 	if (dma_mask > DMA_BIT_MASK(32))
 		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-				      IOVA_PFN(DMA_BIT_MASK(32)));
+				      IOVA_PFN(DMA_BIT_MASK(32)), false);
 
 	if (!pfn)
-		pfn = alloc_iova_fast(&dma_dom->iovad, pages, IOVA_PFN(dma_mask));
+		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
+				      IOVA_PFN(dma_mask), true);
 
 	return (pfn << PAGE_SHIFT);
 }
@@ -1788,8 +1788,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
 
-	init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&dma_dom->iovad, PAGE_SIZE, IOVA_START_PFN);
 
 	if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
 		goto free_dma_dom;
@@ -2696,8 +2695,7 @@ static int init_reserved_iova_ranges(void)
 	struct pci_dev *pdev = NULL;
 	struct iova *val;
 
-	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE, IOVA_START_PFN);
 
 	lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
 			  &reserved_rbtree_key);
@@ -3663,11 +3661,11 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count, bool align)
 {
 	struct irq_remap_table *table;
+	int index, c, alignment = 1;
 	unsigned long flags;
-	int index, c;
 	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
 	if (!iommu)
@@ -3677,16 +3675,22 @@ static int alloc_irq_index(u16 devid, int count)
 	if (!table)
 		return -ENODEV;
 
+	if (align)
+		alignment = roundup_pow_of_two(count);
+
 	spin_lock_irqsave(&table->lock, flags);
 
 	/* Scan table for free entries */
-	for (c = 0, index = table->min_index;
+	for (index = ALIGN(table->min_index, alignment), c = 0;
 	     index < MAX_IRQS_PER_TABLE;
-	     ++index) {
-		if (!iommu->irte_ops->is_allocated(table, index))
+	     index++) {
+		if (!iommu->irte_ops->is_allocated(table, index)) {
 			c += 1;
-		else
-			c = 0;
+		} else {
+			c     = 0;
+			index = ALIGN(index, alignment);
+			continue;
+		}
 
 		if (c == count)	{
 			for (; c != 0; --c)
@@ -4099,7 +4103,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		else
 			ret = -ENOMEM;
 	} else {
-		index = alloc_irq_index(devid, nr_irqs);
+		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
+
+		index = alloc_irq_index(devid, nr_irqs, align);
 	}
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");

drivers/iommu/arm-smmu-v3.c

@@ -1743,6 +1743,14 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+
+	if (smmu)
+		__arm_smmu_tlb_sync(smmu);
+}
+
 static phys_addr_t
 arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
@@ -1963,6 +1971,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,

drivers/iommu/arm-smmu.c

@@ -250,6 +250,7 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
+	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
@@ -735,7 +736,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	const struct iommu_gather_ops *tlb_ops;
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)
@@ -813,7 +813,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			ias = min(ias, 32UL);
 			oas = min(oas, 32UL);
 		}
-		tlb_ops = &arm_smmu_s1_tlb_ops;
+		smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
 		break;
 	case ARM_SMMU_DOMAIN_NESTED:
 		/*
@@ -833,9 +833,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			oas = min(oas, 40UL);
 		}
 		if (smmu->version == ARM_SMMU_V2)
-			tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
 		else
-			tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
 		break;
 	default:
 		ret = -EINVAL;
@@ -863,7 +863,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
-		.tlb		= tlb_ops,
+		.tlb		= smmu_domain->tlb_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1259,6 +1259,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+}
+
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 					      dma_addr_t iova)
 {
@@ -1562,6 +1570,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,

drivers/iommu/dma-iommu.c

@@ -292,18 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		/* ...then finally give it a kicking to make sure it fits */
 		base_pfn = max_t(unsigned long, base_pfn,
 				domain->geometry.aperture_start >> order);
-		end_pfn = min_t(unsigned long, end_pfn,
-				domain->geometry.aperture_end >> order);
 	}
-	/*
-	 * PCI devices may have larger DMA masks, but still prefer allocating
-	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
-	 * apply to the typical platform device, so for those we may as well
-	 * leave the cache limit at the top of their range to save an rb_last()
-	 * traversal on every allocation.
-	 */
-	if (dev && dev_is_pci(dev))
-		end_pfn &= DMA_BIT_MASK(32) >> order;
 
 	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
@@ -312,16 +301,11 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		/*
-		 * If we have devices with different DMA masks, move the free
-		 * area cache limit down for the benefit of the smaller one.
-		 */
-		iovad->dma_32bit_pfn = min(end_pfn + 1, iovad->dma_32bit_pfn);
 
 		return 0;
 	}
 
-	init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
+	init_iova_domain(iovad, 1UL << order, base_pfn);
 	if (!dev)
 		return 0;
 
@@ -386,10 +370,12 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 
 	/* Try to get PCI devices a SAC address */
 	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
-		iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
+		iova = alloc_iova_fast(iovad, iova_len,
+				       DMA_BIT_MASK(32) >> shift, false);
 
 	if (!iova)
-		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
+		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
+				       true);
 
 	return (dma_addr_t)iova << shift;
 }

drivers/iommu/dmar.c

@@ -801,13 +801,16 @@ int __init dmar_dev_scope_init(void)
 				dmar_free_pci_notify_info(info);
 			}
 		}
-
-		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 	}
 
 	return dmar_dev_scope_status;
 }
 
+void dmar_register_bus_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+}
+
 
 int __init dmar_table_init(void)
 {

drivers/iommu/exynos-iommu.c

@@ -263,6 +263,7 @@ struct exynos_iommu_domain {
 struct sysmmu_drvdata {
 	struct device *sysmmu;		/* SYSMMU controller device */
 	struct device *master;		/* master device (owner) */
+	struct device_link *link;	/* runtime PM link to master */
 	void __iomem *sfrbase;		/* our registers */
 	struct clk *clk;		/* SYSMMU's clock */
 	struct clk *aclk;		/* SYSMMU's aclk clock */
@@ -1250,6 +1251,8 @@ static struct iommu_group *get_device_iommu_group(struct device *dev)
 
 static int exynos_iommu_add_device(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 	struct iommu_group *group;
 
 	if (!has_sysmmu(dev))
@@ -1260,6 +1263,15 @@ static int exynos_iommu_add_device(struct device *dev)
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		/*
+		 * SYSMMU will be runtime activated via device link
+		 * (dependency) to its master device, so there are no
+		 * direct calls to pm_runtime_get/put in this driver.
+		 */
+		data->link = device_link_add(dev, data->sysmmu,
+					     DL_FLAG_PM_RUNTIME);
+	}
 	iommu_group_put(group);
 
 	return 0;
@@ -1268,6 +1280,7 @@ static int exynos_iommu_add_device(struct device *dev)
 static void exynos_iommu_remove_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 
 	if (!has_sysmmu(dev))
 		return;
@@ -1283,6 +1296,9 @@ static void exynos_iommu_remove_device(struct device *dev)
 		}
 	}
 	iommu_group_remove_device(dev);
+
+	list_for_each_entry(data, &owner->controllers, owner_node)
+		device_link_del(data->link);
 }
 
 static int exynos_iommu_of_xlate(struct device *dev,
@@ -1316,13 +1332,6 @@ static int exynos_iommu_of_xlate(struct device *dev,
 	list_add_tail(&data->owner_node, &owner->controllers);
 	data->master = dev;
 
-	/*
-	 * SYSMMU will be runtime activated via device link (dependency) to its
-	 * master device, so there are no direct calls to pm_runtime_get/put
-	 * in this driver.
-	 */
-	device_link_add(dev, data->sysmmu, DL_FLAG_PM_RUNTIME);
-
 	return 0;
 }