Merge branch 'api-features' into x86/vt-d

7 files changed, 245 insertions, 17 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b319e51c379b..f7cdd2ab7f11 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2608,7 +2608,12 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 
 	/* Everything is mapped - write the right values into s->dma_address */
 	for_each_sg(sglist, s, nelems, i) {
-		s->dma_address += address + s->offset;
+		/*
+		 * Add in the remaining piece of the scatter-gather offset that
+		 * was masked out when we were determining the physical address
+		 * via (sg_phys(s) & PAGE_MASK) earlier.
+		 */
+		s->dma_address += address + (s->offset & ~PAGE_MASK);
 		s->dma_length   = s->length;
 	}
 
@@ -3164,21 +3169,24 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+		int type, prot = 0;
 		size_t length;
-		int prot = 0;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;
 
+		type   = IOMMU_RESV_DIRECT;
 		length = entry->address_end - entry->address_start;
 		if (entry->prot & IOMMU_PROT_IR)
 			prot |= IOMMU_READ;
 		if (entry->prot & IOMMU_PROT_IW)
 			prot |= IOMMU_WRITE;
+		if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE)
+			/* Exclusion range */
+			type = IOMMU_RESV_RESERVED;
 
 		region = iommu_alloc_resv_region(entry->address_start,
-						 length, prot,
-						 IOMMU_RESV_DIRECT);
+						 length, prot, type);
 		if (!region) {
 			dev_err(dev, "Out of memory allocating dm-regions\n");
 			return;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index f773792d77fd..1b1378619fc9 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2013,6 +2013,9 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	if (e == NULL)
 		return -ENOMEM;
 
+	if (m->flags & IVMD_FLAG_EXCL_RANGE)
+		init_exclusion_range(m);
+
 	switch (m->type) {
 	default:
 		kfree(e);
@@ -2059,9 +2062,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
 
 	while (p < end) {
 		m = (struct ivmd_header *)p;
-		if (m->flags & IVMD_FLAG_EXCL_RANGE)
-			init_exclusion_range(m);
-		else if (m->flags & IVMD_FLAG_UNITY_MAP)
+		if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
 			init_unity_map_range(m);
 
 		p += m->length;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index eae0741f72dc..87965e4d9647 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -374,6 +374,8 @@
 #define IOMMU_PROT_IR 0x01
 #define IOMMU_PROT_IW 0x02
 
+#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE	(1 << 2)
+
 /* IOMMU capabilities */
 #define IOMMU_CAP_IOTLB   24
 #define IOMMU_CAP_NPCACHE 26
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 87274b54febd..28cb713d728c 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1538,6 +1538,9 @@ static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
 	u32 pmen;
 	unsigned long flags;
 
+	if (!cap_plmr(iommu->cap) && !cap_phmr(iommu->cap))
+		return;
+
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 	pmen = readl(iommu->reg + DMAR_PMEN_REG);
 	pmen &= ~DMA_PMEN_EPM;
@@ -5332,7 +5335,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
 
 	ctx_lo = context[0].lo;
 
-	sdev->did = domain->iommu_did[iommu->seq_id];
+	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 
 	if (!(ctx_lo & CONTEXT_PASIDE)) {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index f101afc315ab..9a8a8870e267 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -160,6 +160,14 @@
 
 #define ARM_V7S_TCR_PD1			BIT(5)
 
+#ifdef CONFIG_ZONE_DMA32
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
+#else
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA
+#endif
+
 typedef u32 arm_v7s_iopte;
 
 static bool selftest_running;
@@ -197,13 +205,16 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 	void *table = NULL;
 
 	if (lvl == 1)
-		table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size));
+		table = (void *)__get_free_pages(
+			__GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size));
 	else if (lvl == 2)
-		table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA);
+		table = kmem_cache_zalloc(data->l2_tables, gfp);
 	phys = virt_to_phys(table);
-	if (phys != (arm_v7s_iopte)phys)
+	if (phys != (arm_v7s_iopte)phys) {
 		/* Doesn't fit in PTE */
+		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
 		goto out_free;
+	}
 	if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
 		dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -733,7 +744,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
 					    ARM_V7S_TABLE_SIZE(2),
 					    ARM_V7S_TABLE_SIZE(2),
-					    SLAB_CACHE_DMA, NULL);
+					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 33a982e33716..f8fe112e507a 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1105,10 +1105,12 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 
 		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
 		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
-			dev_warn(dev,
-				 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
-				 iommu_def_domain_type);
 			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+			if (dom) {
+				dev_warn(dev,
+					 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+					 iommu_def_domain_type);
+			}
 		}
 
 		group->default_domain = dom;
@@ -2037,3 +2039,203 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
+
+/*
+ * Per device IOMMU features.
+ */
+bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->dev_has_feat)
+		return ops->dev_has_feat(dev, feat);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_has_feature);
+
+int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->dev_enable_feat)
+		return ops->dev_enable_feat(dev, feat);
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
+
+/*
+ * The device drivers should do the necessary cleanups before calling this.
+ * For example, before disabling the aux-domain feature, the device driver
+ * should detach all aux-domains. Otherwise, this will return -EBUSY.
+ */
+int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->dev_disable_feat)
+		return ops->dev_disable_feat(dev, feat);
+
+	return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_disable_feature);
+
+bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->dev_feat_enabled)
+		return ops->dev_feat_enabled(dev, feat);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
+
+/*
+ * Aux-domain specific attach/detach.
+ *
+ * Only works if iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX) returns
+ * true. Also, as long as domains are attached to a device through this
+ * interface, any tries to call iommu_attach_device() should fail
+ * (iommu_detach_device() can't fail, so we fail when trying to re-attach).
+ * This should make us safe against a device being attached to a guest as a
+ * whole while there are still pasid users on it (aux and sva).
+ */
+int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	int ret = -ENODEV;
+
+	if (domain->ops->aux_attach_dev)
+		ret = domain->ops->aux_attach_dev(domain, dev);
+
+	if (!ret)
+		trace_attach_device_to_domain(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_attach_device);
+
+void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	if (domain->ops->aux_detach_dev) {
+		domain->ops->aux_detach_dev(domain, dev);
+		trace_detach_device_from_domain(dev);
+	}
+}
+EXPORT_SYMBOL_GPL(iommu_aux_detach_device);
+
+int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+{
+	int ret = -ENODEV;
+
+	if (domain->ops->aux_get_pasid)
+		ret = domain->ops->aux_get_pasid(domain, dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_get_pasid);
+
+/**
+ * iommu_sva_bind_device() - Bind a process address space to a device
+ * @dev: the device
+ * @mm: the mm to bind, caller must hold a reference to it
+ *
+ * Create a bond between device and address space, allowing the device to access
+ * the mm using the returned PASID. If a bond already exists between @device and
+ * @mm, it is returned and an additional reference is taken. Caller must call
+ * iommu_sva_unbind_device() to release each reference.
+ *
+ * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
+ * initialize the required SVA features.
+ *
+ * On error, returns an ERR_PTR value.
+ */
+struct iommu_sva *
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct iommu_group *group;
+	struct iommu_sva *handle = ERR_PTR(-EINVAL);
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (!ops || !ops->sva_bind)
+		return ERR_PTR(-ENODEV);
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
+	/* Ensure device count and domain don't change while we're binding */
+	mutex_lock(&group->mutex);
+
+	/*
+	 * To keep things simple, SVA currently doesn't support IOMMU groups
+	 * with more than one device. Existing SVA-capable systems are not
+	 * affected by the problems that required IOMMU groups (lack of ACS
+	 * isolation, device ID aliasing and other hardware issues).
+	 */
+	if (iommu_group_device_count(group) != 1)
+		goto out_unlock;
+
+	handle = ops->sva_bind(dev, mm, drvdata);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return handle;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
+
+/**
+ * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
+ * @handle: the handle returned by iommu_sva_bind_device()
+ *
+ * Put reference to a bond between device and address space. The device should
+ * not be issuing any more transaction for this PASID. All outstanding page
+ * requests for this PASID must have been flushed to the IOMMU.
+ *
+ * Returns 0 on success, or an error value
+ */
+void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+	struct iommu_group *group;
+	struct device *dev = handle->dev;
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (!ops || !ops->sva_unbind)
+		return;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	ops->sva_unbind(handle);
+	mutex_unlock(&group->mutex);
+
+	iommu_group_put(group);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
+
+int iommu_sva_set_ops(struct iommu_sva *handle,
+		      const struct iommu_sva_ops *sva_ops)
+{
+	if (handle->ops && handle->ops != sva_ops)
+		return -EEXIST;
+
+	handle->ops = sva_ops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_set_ops);
+
+int iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+	const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
+
+	if (!ops || !ops->sva_get_pasid)
+		return IOMMU_PASID_INVALID;
+
+	return ops->sva_get_pasid(handle);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index f8d3ba247523..2de8122e218f 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -207,8 +207,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		curr_iova = rb_entry(curr, struct iova, node);
 	} while (curr && new_pfn <= curr_iova->pfn_hi);
 
-	if (limit_pfn < size || new_pfn < iovad->start_pfn)
+	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+		iovad->max32_alloc_size = size;
 		goto iova32_full;
+	}
 
 	/* pfn_lo will point to size aligned address if size_aligned is set */
 	new->pfn_lo = new_pfn;
@@ -222,7 +224,6 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	return 0;
 
 iova32_full:
-	iovad->max32_alloc_size = size;
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 	return -ENOMEM;
 }