1 files changed, 266 insertions, 80 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0c674d80c37f..3e3528436e0b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -22,16 +22,15 @@
 #include <linux/bitops.h>
 #include <linux/property.h>
 #include <linux/fsl/mc.h>
+#include <linux/module.h>
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
-#else
-static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
-#endif
+
+static unsigned int iommu_def_domain_type __read_mostly;
 static bool iommu_dma_strict __read_mostly = true;
+static u32 iommu_cmd_line __read_mostly;
 
 struct iommu_group {
 	struct kobject kobj;
@@ -68,6 +67,18 @@ static const char * const iommu_group_resv_type_string[] = {
 	[IOMMU_RESV_SW_MSI]			= "msi",
 };
 
+#define IOMMU_CMD_LINE_DMA_API		BIT(0)
+
+static void iommu_set_cmd_line_dma_api(void)
+{
+	iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
+}
+
+static bool iommu_cmd_line_dma_api(void)
+{
+	return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API);
+}
+
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
 	__ATTR(_name, _mode, _show, _store)
@@ -80,14 +91,58 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
+/*
+ * Use a function instead of an array here because the domain-type is a
+ * bit-field, so an array would waste memory.
+ */
+static const char *iommu_domain_type_str(unsigned int t)
+{
+	switch (t) {
+	case IOMMU_DOMAIN_BLOCKED:
+		return "Blocked";
+	case IOMMU_DOMAIN_IDENTITY:
+		return "Passthrough";
+	case IOMMU_DOMAIN_UNMANAGED:
+		return "Unmanaged";
+	case IOMMU_DOMAIN_DMA:
+		return "Translated";
+	default:
+		return "Unknown";
+	}
+}
+
+static int __init iommu_subsys_init(void)
+{
+	bool cmd_line = iommu_cmd_line_dma_api();
+
+	if (!cmd_line) {
+		if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH))
+			iommu_set_default_passthrough(false);
+		else
+			iommu_set_default_translated(false);
+
+		if (iommu_default_passthrough() && mem_encrypt_active()) {
+			pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n");
+			iommu_set_default_translated(false);
+		}
+	}
+
+	pr_info("Default domain type: %s %s\n",
+		iommu_domain_type_str(iommu_def_domain_type),
+		cmd_line ? "(set via kernel command line)" : "");
+
+	return 0;
+}
+subsys_initcall(iommu_subsys_init);
+
 int iommu_device_register(struct iommu_device *iommu)
 {
 	spin_lock(&iommu_device_lock);
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
-
 	return 0;
 }
+EXPORT_SYMBOL_GPL(iommu_device_register);
 
 void iommu_device_unregister(struct iommu_device *iommu)
 {
@@ -95,6 +150,7 @@ void iommu_device_unregister(struct iommu_device *iommu)
 	list_del(&iommu->list);
 	spin_unlock(&iommu_device_lock);
 }
+EXPORT_SYMBOL_GPL(iommu_device_unregister);
 
 static struct iommu_param *iommu_get_dev_param(struct device *dev)
 {
@@ -130,10 +186,21 @@ int iommu_probe_device(struct device *dev)
 	if (!iommu_get_dev_param(dev))
 		return -ENOMEM;
 
+	if (!try_module_get(ops->owner)) {
+		ret = -EINVAL;
+		goto err_free_dev_param;
+	}
+
 	ret = ops->add_device(dev);
 	if (ret)
-		iommu_free_dev_param(dev);
+		goto err_module_put;
+
+	return 0;
 
+err_module_put:
+	module_put(ops->owner);
+err_free_dev_param:
+	iommu_free_dev_param(dev);
 	return ret;
 }
 
@@ -144,7 +211,10 @@ void iommu_release_device(struct device *dev)
 	if (dev->iommu_group)
 		ops->remove_device(dev);
 
-	iommu_free_dev_param(dev);
+	if (dev->iommu_param) {
+		module_put(ops->owner);
+		iommu_free_dev_param(dev);
+	}
 }
 
 static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
@@ -165,7 +235,11 @@ static int __init iommu_set_def_domain_type(char *str)
 	if (ret)
 		return ret;
 
-	iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
+	if (pt)
+		iommu_set_default_passthrough(true);
+	else
+		iommu_set_default_translated(true);
+
 	return 0;
 }
 early_param("iommu.passthrough", iommu_set_def_domain_type);
@@ -229,60 +303,58 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
  * @new: new region to insert
  * @regions: list of regions
  *
- * The new element is sorted by address with respect to the other
- * regions of the same type. In case it overlaps with another
- * region of the same type, regions are merged. In case it
- * overlaps with another region of different type, regions are
- * not merged.
+ * Elements are sorted by start address and overlapping segments
+ * of the same type are merged.
  */
-static int iommu_insert_resv_region(struct iommu_resv_region *new,
-				    struct list_head *regions)
+int iommu_insert_resv_region(struct iommu_resv_region *new,
+			     struct list_head *regions)
 {
-	struct iommu_resv_region *region;
-	phys_addr_t start = new->start;
-	phys_addr_t end = new->start + new->length - 1;
-	struct list_head *pos = regions->next;
-
-	while (pos != regions) {
-		struct iommu_resv_region *entry =
-			list_entry(pos, struct iommu_resv_region, list);
-		phys_addr_t a = entry->start;
-		phys_addr_t b = entry->start + entry->length - 1;
-		int type = entry->type;
-
-		if (end < a) {
-			goto insert;
-		} else if (start > b) {
-			pos = pos->next;
-		} else if ((start >= a) && (end <= b)) {
-			if (new->type == type)
-				return 0;
-			else
-				pos = pos->next;
+	struct iommu_resv_region *iter, *tmp, *nr, *top;
+	LIST_HEAD(stack);
+
+	nr = iommu_alloc_resv_region(new->start, new->length,
+				     new->prot, new->type);
+	if (!nr)
+		return -ENOMEM;
+
+	/* First add the new element based on start address sorting */
+	list_for_each_entry(iter, regions, list) {
+		if (nr->start < iter->start ||
+		    (nr->start == iter->start && nr->type <= iter->type))
+			break;
+	}
+	list_add_tail(&nr->list, &iter->list);
+
+	/* Merge overlapping segments of type nr->type in @regions, if any */
+	list_for_each_entry_safe(iter, tmp, regions, list) {
+		phys_addr_t top_end, iter_end = iter->start + iter->length - 1;
+
+		/* no merge needed on elements of different types than @new */
+		if (iter->type != new->type) {
+			list_move_tail(&iter->list, &stack);
+			continue;
+		}
+
+		/* look for the last stack element of same type as @iter */
+		list_for_each_entry_reverse(top, &stack, list)
+			if (top->type == iter->type)
+				goto check_overlap;
+
+		list_move_tail(&iter->list, &stack);
+		continue;
+
+check_overlap:
+		top_end = top->start + top->length - 1;
+
+		if (iter->start > top_end + 1) {
+			list_move_tail(&iter->list, &stack);
 		} else {
-			if (new->type == type) {
-				phys_addr_t new_start = min(a, start);
-				phys_addr_t new_end = max(b, end);
-				int ret;
-
-				list_del(&entry->list);
-				entry->start = new_start;
-				entry->length = new_end - new_start + 1;
-				ret = iommu_insert_resv_region(entry, regions);
-				kfree(entry);
-				return ret;
-			} else {
-				pos = pos->next;
-			}
+			top->length = max(top_end, iter_end) - top->start + 1;
+			list_del(&iter->list);
+			kfree(iter);
 		}
 	}
-insert:
-	region = iommu_alloc_resv_region(new->start, new->length,
-					 new->prot, new->type);
-	if (!region)
-		return -ENOMEM;
-
-	list_add_tail(&region->list, pos);
+	list_splice(&stack, regions);
 	return 0;
 }
 
@@ -696,6 +768,7 @@ err_put_group:
 	mutex_unlock(&group->mutex);
 	dev->iommu_group = NULL;
 	kobject_put(group->devices_kobj);
+	sysfs_remove_link(group->devices_kobj, device->name);
 err_free_name:
 	kfree(device->name);
 err_remove_link:
@@ -831,6 +904,7 @@ struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
 	kobject_get(group->devices_kobj);
 	return group;
 }
+EXPORT_SYMBOL_GPL(iommu_group_ref_get);
 
 /**
  * iommu_group_put - Decrement group reference
@@ -1204,6 +1278,7 @@ struct iommu_group *generic_device_group(struct device *dev)
 {
 	return iommu_group_alloc();
 }
+EXPORT_SYMBOL_GPL(generic_device_group);
 
 /*
  * Use standard PCI bus topology, isolation features, and DMA alias quirks
@@ -1271,6 +1346,7 @@ struct iommu_group *pci_device_group(struct device *dev)
 	/* No shared group found, allocate new */
 	return iommu_group_alloc();
 }
+EXPORT_SYMBOL_GPL(pci_device_group);
 
 /* Get the IOMMU group for device on fsl-mc bus */
 struct iommu_group *fsl_mc_device_group(struct device *dev)
@@ -1283,6 +1359,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev)
 		group = iommu_group_alloc();
 	return group;
 }
+EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 
 /**
  * iommu_group_get_for_dev - Find or create the IOMMU group for a device
@@ -1351,6 +1428,7 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 
 	return group;
 }
+EXPORT_SYMBOL(iommu_group_get_for_dev);
 
 struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
 {
@@ -1481,6 +1559,11 @@ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
 {
 	int err;
 
+	if (ops == NULL) {
+		bus->iommu_ops = NULL;
+		return 0;
+	}
+
 	if (bus->iommu_ops != NULL)
 		return -EBUSY;
 
@@ -1610,6 +1693,36 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+			   struct iommu_cache_invalidate_info *inv_info)
+{
+	if (unlikely(!domain->ops->cache_invalidate))
+		return -ENODEV;
+
+	return domain->ops->cache_invalidate(domain, dev, inv_info);
+}
+EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+
+int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+			   struct device *dev, struct iommu_gpasid_bind_data *data)
+{
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, data);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid)
+{
+	if (unlikely(!domain->ops->sva_unbind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_unbind_gpasid(dev, pasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
@@ -1799,8 +1912,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 	return pgsize;
 }
 
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
+int __iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
@@ -1837,8 +1950,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
 
-		ret = ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
 			break;
 
@@ -1858,11 +1971,25 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	return ret;
 }
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	might_sleep();
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map);
 
+int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_atomic);
+
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
-			    bool sync)
+			    struct iommu_iotlb_gather *iotlb_gather)
 {
 	const struct iommu_ops *ops = domain->ops;
 	size_t unmapped_page, unmapped = 0;
@@ -1899,13 +2026,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	while (unmapped < size) {
 		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
 
-		unmapped_page = ops->unmap(domain, iova, pgsize);
+		unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather);
 		if (!unmapped_page)
 			break;
 
-		if (sync && ops->iotlb_range_add)
-			ops->iotlb_range_add(domain, iova, pgsize);
-
 		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
 			 iova, unmapped_page);
 
@@ -1913,9 +2037,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 		unmapped += unmapped_page;
 	}
 
-	if (sync && ops->iotlb_sync)
-		ops->iotlb_sync(domain);
-
 	trace_unmap(orig_iova, size, unmapped);
 	return unmapped;
 }
@@ -1923,19 +2044,28 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 size_t iommu_unmap(struct iommu_domain *domain,
 		   unsigned long iova, size_t size)
 {
-	return __iommu_unmap(domain, iova, size, true);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t ret;
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
+	iommu_tlb_sync(domain, &iotlb_gather);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
 
 size_t iommu_unmap_fast(struct iommu_domain *domain,
-			unsigned long iova, size_t size)
+			unsigned long iova, size_t size,
+			struct iommu_iotlb_gather *iotlb_gather)
 {
-	return __iommu_unmap(domain, iova, size, false);
+	return __iommu_unmap(domain, iova, size, iotlb_gather);
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
+size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot,
+		    gfp_t gfp)
 {
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
@@ -1946,7 +2076,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		phys_addr_t s_phys = sg_phys(sg);
 
 		if (len && s_phys != start + len) {
-			ret = iommu_map(domain, iova + mapped, start, len, prot);
+			ret = __iommu_map(domain, iova + mapped, start,
+					len, prot, gfp);
+
 			if (ret)
 				goto out_err;
 
@@ -1974,8 +2106,22 @@ out_err:
 	return 0;
 
 }
+
+size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	might_sleep();
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
+size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_sg_atomic);
+
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 			       phys_addr_t paddr, u64 size, int prot)
 {
@@ -2111,6 +2257,25 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 		ops->put_resv_regions(dev, list);
 }
 
+/**
+ * generic_iommu_put_resv_regions - Reserved region driver helper
+ * @dev: device for which to free reserved regions
+ * @list: reserved region list for device
+ *
+ * IOMMU drivers can use this to implement their .put_resv_regions() callback
+ * for simple reservations. Memory allocated for each reserved region will be
+ * freed. If an IOMMU driver allocates additional resources per region, it is
+ * going to have to implement a custom callback.
+ */
+void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, list, list)
+		kfree(entry);
+}
+EXPORT_SYMBOL(generic_iommu_put_resv_regions);
+
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 						  size_t length, int prot,
 						  enum iommu_resv_type type)
@@ -2128,6 +2293,7 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 	region->type = type;
 	return region;
 }
+EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);
 
 static int
 request_default_domain_for_dev(struct device *dev, unsigned long type)
@@ -2143,7 +2309,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
 
 	mutex_lock(&group->mutex);
 
-	/* Check if the default domain is already direct mapped */
 	ret = 0;
 	if (group->default_domain && group->default_domain->type == type)
 		goto out;
@@ -2153,7 +2318,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
 	if (iommu_group_device_count(group) != 1)
 		goto out;
 
-	/* Allocate a direct mapped domain */
 	ret = -ENOMEM;
 	domain = __iommu_domain_alloc(dev->bus, type);
 	if (!domain)
@@ -2166,13 +2330,13 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
 		goto out;
 	}
 
-	iommu_group_create_direct_mappings(group, dev);
-
-	/* Make the direct mapped domain the default for this group */
+	/* Make the domain the default for this group */
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
 	group->default_domain = domain;
 
+	iommu_group_create_direct_mappings(group, dev);
+
 	dev_info(dev, "Using iommu %s mapping\n",
 		 type == IOMMU_DOMAIN_DMA ? "dma" : "direct");
 
@@ -2196,6 +2360,28 @@ int iommu_request_dma_domain_for_dev(struct device *dev)
 	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA);
 }
 
+void iommu_set_default_passthrough(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_set_cmd_line_dma_api();
+
+	iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
+}
+
+void iommu_set_default_translated(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_set_cmd_line_dma_api();
+
+	iommu_def_domain_type = IOMMU_DOMAIN_DMA;
+}
+
+bool iommu_default_passthrough(void)
+{
+	return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY;
+}
+EXPORT_SYMBOL_GPL(iommu_default_passthrough);
+
 const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
 	const struct iommu_ops *ops = NULL;