of_iommu: add support for "iommu-ranges"

index 78742aeba932de1054fbf394c4fae86e9b1be20c..fbf788ac055b6d1e87482c3de043ef57bb12d9e6 100644
@@ -505,21 +505,34 @@ static int iommu_dma_ranges_sort(void *priv, const struct list_head *a,
 	return res_a->res->start > res_b->res->start;
 }
 
+/*
+ * IOVA PFNs are unsigned long, and ~0UL is the rbtree anchor. On 32-bit
+ * with a 64-bit dma_addr_t, iova_pfn() would truncate the range. Compute
+ * the PFNs in u64 instead, skip a range that starts beyond the PFN space
+ * and clamp its end below the anchor. Such IOVAs cannot be allocated.
+ */
+static void iova_reserve_range(struct iova_domain *iovad, u64 start, u64 end)
+{
+	u64 lo = start >> iova_shift(iovad);
+	u64 hi = end >> iova_shift(iovad);
+
+	if (lo < ULONG_MAX)
+		reserve_iova(iovad, lo, min(hi, ULONG_MAX - 1));
+}
+
 static int iova_reserve_pci_windows(struct pci_dev *dev,
 		struct iova_domain *iovad)
 {
 	struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
 	struct resource_entry *window;
-	unsigned long lo, hi;
 	phys_addr_t start = 0, end;
 
 	resource_list_for_each_entry(window, &bridge->windows) {
 		if (resource_type(window->res) != IORESOURCE_MEM)
 			continue;
 
-		lo = iova_pfn(iovad, window->res->start - window->offset);
-		hi = iova_pfn(iovad, window->res->end - window->offset);
-		reserve_iova(iovad, lo, hi);
+		iova_reserve_range(iovad, window->res->start - window->offset,
+				   window->res->end - window->offset);
 	}
 
 	/* Get reserved DMA windows from host bridge */

@@ -528,9 +541,7 @@ static int iova_reserve_pci_windows(struct pci_dev *dev,
 		end = window->res->start - window->offset;
 resv_iova:
 		if (end > start) {
-			lo = iova_pfn(iovad, start);
-			hi = iova_pfn(iovad, end);
-			reserve_iova(iovad, lo, hi);
+			iova_reserve_range(iovad, start, end);
 		} else if (end < start) {
 			/* DMA ranges should be non-overlapping */
 			dev_err(&dev->dev,

@@ -568,15 +579,12 @@ static int iova_reserve_iommu_regions(struct device *dev,
 
 	iommu_get_resv_regions(dev, &resv_regions);
 	list_for_each_entry(region, &resv_regions, list) {
-		unsigned long lo, hi;
-
 		/* We ARE the software that manages these! */
 		if (region->type == IOMMU_RESV_SW_MSI)
 			continue;
 
-		lo = iova_pfn(iovad, region->start);
-		hi = iova_pfn(iovad, region->start + region->length - 1);
-		reserve_iova(iovad, lo, hi);
+		iova_reserve_range(iovad, region->start,
+				   region->start + region->length - 1);
 
 		if (region->type == IOMMU_RESV_MSI)
 			ret = cookie_init_hw_msi_region(cookie, region->start,

index 960e1dc05ec69b346d1af73241dfa51393b0851a..179e6c28afe6f86c233d9d7e64abb0870095e985 100644
@@ -3327,7 +3327,7 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 
 	list_for_each_entry(entry, &pci_seg->unity_map, list) {
 		int type, prot = 0;
-		size_t length;
+		resource_size_t length;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;

index 5a2e705a2f2e025245d4b42c4a9f765c67d708d4..70e210ca085ff52519376358a3e3b7a01619d7a8 100644
@@ -3535,7 +3535,7 @@ static void intel_iommu_get_resv_regions(struct device *device,
 					  i, i_dev) {
 			struct iommu_resv_region *resv;
 			enum iommu_resv_type type;
-			size_t length;
+			resource_size_t length;
 
 			if (i_dev != device &&
 			    !is_downstream_to_pci_bridge(device, i_dev))

index b486b8bbd1fcdc359d936234bb3f8631306c8786..18f3efb94043ace9f1f4abc7c6ac8974dc25b0c0 100644
@@ -3010,7 +3010,7 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 EXPORT_SYMBOL(iommu_put_resv_regions);
 
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
-						  size_t length, int prot,
+						  resource_size_t length, int prot,
 						  enum iommu_resv_type type,
 						  gfp_t gfp)
 {

index a18bb60f6f3dfdba853b6e16dd2a8616f6a731c7..5c266511db78910d6fd221af5437cecff4931c22 100644
@@ -170,7 +170,7 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np,
 static enum iommu_resv_type __maybe_unused
 iommu_resv_region_get_type(struct device *dev,
 			   struct resource *phys,
-			   phys_addr_t start, size_t length)
+			   phys_addr_t start, resource_size_t length)
 {
 	phys_addr_t end = start + length - 1;
 

@@ -246,7 +246,7 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				struct iommu_resv_region *region;
 				enum iommu_resv_type type;
 				phys_addr_t iova;
-				size_t length;
+				resource_size_t length;
 
 				if (of_dma_is_coherent(dev->of_node))
 					prot |= IOMMU_CACHE;

index 587fc13197f12227e69aedbc721cfd49cebde2ef..a37e713b0678a516a777436d616f0d3df54eae38 100644
@@ -483,7 +483,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
 			       struct virtio_iommu_probe_resv_mem *mem,
 			       size_t len)
 {
-	size_t size;
+	resource_size_t size;
 	u64 start64, end64;
 	phys_addr_t start, end;
 	struct iommu_resv_region *region = NULL, *next;

index 499d37ceae210ac844eef853aeecbfabaaa5e138..f665432638a6d1cc1ebfc0d2356b813c8c584910 100644
@@ -655,7 +655,7 @@ EXPORT_SYMBOL(of_translate_dma_address);
  * Returns a pointer to the cell immediately following the translated DMA region.
  */
 const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *prop,
-				      phys_addr_t *start, size_t *length)
+				      phys_addr_t *start, resource_size_t *length)
 {
 	struct device_node *parent __free(device_node) = __of_get_dma_parent(dev);
 	u64 address, size;

index f7addfbe1aab4f6fb662b8b2fa66bc02d98b5f03..9f508143505ad9e603af1730e811c30bd5edce16 100644
@@ -164,7 +164,7 @@ vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
  */
 
 static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
-				      dma_addr_t start, size_t size)
+				      dma_addr_t start, resource_size_t size)
 {
 	struct rb_node *node = iommu->dma_list.rb_node;
 

index ef5043752a3651419679316c5a20cdf049efeaba..1d8f9381a358ec2309503bfe2866f08a1f236b2b 100644
@@ -306,7 +306,7 @@ enum iommu_resv_type {
 struct iommu_resv_region {
 	struct list_head	list;
 	phys_addr_t		start;
-	size_t			length;
+	resource_size_t		length;
 	int			prot;
 	enum iommu_resv_type	type;
 	void (*free)(struct device *dev, struct iommu_resv_region *region);

@@ -968,7 +968,7 @@ extern void iommu_set_default_passthrough(bool cmd_line);
 extern void iommu_set_default_translated(bool cmd_line);
 extern bool iommu_default_passthrough(void);
 extern struct iommu_resv_region *
-iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
+iommu_alloc_resv_region(phys_addr_t start, resource_size_t length, int prot,
 			enum iommu_resv_type type, gfp_t gfp);
 extern int iommu_get_group_resv_regions(struct iommu_group *group,
 					struct list_head *head);

index 0cff9036539168b0cf2826ee34417738a4836ace..ae6d96c8c110adad966f2c1bad2cbefaf55e5c57 100644
@@ -56,7 +56,7 @@ static inline int of_range_count(const struct of_range_parser *parser)
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
 extern const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *addr,
-					     phys_addr_t *start, size_t *length);
+					     phys_addr_t *start, resource_size_t *length);
 
 #ifdef CONFIG_OF_ADDRESS
 extern u64 of_translate_address(struct device_node *np, const __be32 *addr);

index 5c266511db78910d6fd221af5437cecff4931c22..6675fc900e6c2d55b34c61dc9effaeb48e24f18f 100644
@@ -167,7 +167,7 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np,
 	return err;
 }
 
-static enum iommu_resv_type __maybe_unused
+static enum iommu_resv_type
 iommu_resv_region_get_type(struct device *dev,
 			   struct resource *phys,
 			   phys_addr_t start, resource_size_t length)

@@ -203,7 +203,6 @@ iommu_resv_region_get_type(struct device *dev,
  */
 void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 {
-#if IS_ENABLED(CONFIG_OF_ADDRESS)
 	struct of_phandle_iterator it;
 	int err;
 

@@ -265,6 +264,5 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 			}
 		}
 	}
-#endif
 }
 EXPORT_SYMBOL(of_iommu_get_resv_regions);

index 6675fc900e6c2d55b34c61dc9effaeb48e24f18f..00b02c19f27e195fc36c4bc1d91253255147c9ab 100644
@@ -174,19 +174,12 @@ iommu_resv_region_get_type(struct device *dev,
 {
 	phys_addr_t end = start + length - 1;
 
-	/*
-	 * IOMMU regions without an associated physical region cannot be
-	 * mapped and are simply reservations.
-	 */
-	if (phys->start >= phys->end)
-		return IOMMU_RESV_RESERVED;
-
 	/* may be IOMMU_RESV_DIRECT_RELAXABLE for certain cases */
 	if (start == phys->start && end == phys->end)
 		return IOMMU_RESV_DIRECT;
 
-	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", phys,
-		 &start, &end);
+	dev_err(dev, "non-direct mapping [%pr] -> [%pap-%pap] is not supported\n", phys,
+		&start, &end);
 	return IOMMU_RESV_RESERVED;
 }
 

@@ -211,12 +204,14 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 		struct resource phys;
 		int size;
 
-		memset(&phys, 0, sizeof(phys));
+		maps = of_get_property(it.node, "iommu-addresses", &size);
+		if (!maps)
+			continue;
 
 		/*
-		 * The "reg" property is optional and can be omitted by reserved-memory regions
-		 * that represent reservations in the IOVA space, which are regions that should
-		 * not be mapped.
+		 * "iommu-addresses" must be used in combination with a "reg" that provides
+		 * the physical address and size of this memory region, for an identity 1:1
+		 * IOVA mapping to that physical memory.
 		 */
 		if (of_property_present(it.node, "reg")) {
 			err = of_address_to_resource(it.node, 0, &phys);

@@ -225,11 +220,11 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 					it.node, err);
 				continue;
 			}
-		}
-
-		maps = of_get_property(it.node, "iommu-addresses", &size);
-		if (!maps)
+		} else {
+			dev_err(dev, "%pOF: iommu-addresses requires a reg property\n",
+				it.node);
 			continue;
+		}
 
 		end = maps + size / sizeof(__be32);
 

@@ -257,6 +252,9 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				}
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
+				if (type != IOMMU_RESV_DIRECT)
+					continue;
+
 				region = iommu_alloc_resv_region(iova, length, prot, type,
 								 GFP_KERNEL);
 				if (region)

index 00b02c19f27e195fc36c4bc1d91253255147c9ab..e133d3b346feecac7e2bfaec44e4882060ee89ec 100644
@@ -183,6 +183,111 @@ iommu_resv_region_get_type(struct device *dev,
 	return IOMMU_RESV_RESERVED;
 }
 
+/**
+ * of_iommu_derive_resv_regions - derive reserved regions which
+ *                                are outside of iommu-ranges
+ * @dev: device for which to get reserved regions
+ * @list: reserved region list
+ *
+ * A device can describe its own usable IOVA ranges directly on its node
+ * via "iommu-ranges". Everything not under those ranges is derived
+ * as a reserved region so the IOMMU allocator won't use it. Entries may
+ * appear in any order in the property.
+ */
+static void of_iommu_derive_resv_regions(struct device *dev, struct list_head *list)
+{
+	struct of_iommu_range {
+		struct list_head node;
+		phys_addr_t start;
+		phys_addr_t end;
+	} *pos, *new, *next_range;
+	int size, prot = IOMMU_READ | IOMMU_WRITE;
+	struct iommu_resv_region *region;
+	const __be32 *maps, *end;
+	struct list_head *prev;
+	phys_addr_t next = 0;
+	LIST_HEAD(ranges);
+
+	maps = of_get_property(dev->of_node, "iommu-ranges", &size);
+	if (!maps)
+		return;
+
+	end = maps + size / sizeof(__be32);
+
+	while (maps < end) {
+		phys_addr_t iova, iova_end;
+		resource_size_t length;
+
+		maps = of_translate_dma_region(dev->of_node, maps, &iova, &length);
+		if (!maps) {
+			dev_err(dev, "%pOF: failed to parse iommu-ranges\n",
+				dev->of_node);
+			goto exit;
+		}
+
+		if (!length)
+			continue;
+
+		iova_end = iova + length - 1;
+
+		if (iova_end < iova) {
+			dev_err(dev, "%pOF: iommu-ranges overflows address space\n",
+				dev->of_node);
+			goto exit;
+		}
+
+		prev = &ranges;
+		list_for_each_entry(pos, &ranges, node) {
+			if (pos->start > iova)
+				break;
+			prev = &pos->node;
+		}
+
+		new = kmalloc_obj(*new);
+		if (!new)
+			goto exit;
+
+		new->start = iova;
+		new->end = iova_end;
+		list_add(&new->node, prev);
+	}
+
+	if (list_empty(&ranges))
+		return;
+
+	if (of_dma_is_coherent(dev->of_node))
+		prot |= IOMMU_CACHE;
+
+	list_for_each_entry_safe(pos, next_range, &ranges, node) {
+		if (pos->start > next) {
+			region = iommu_alloc_resv_region(next, pos->start - next, prot,
+							 IOMMU_RESV_RESERVED, GFP_KERNEL);
+			if (region)
+				list_add_tail(&region->list, list);
+		}
+
+		if (pos->end >= PHYS_ADDR_MAX - 1)
+			goto exit;
+
+		if (pos->end >= next)
+			next = pos->end + 1;
+
+		list_del(&pos->node);
+		kfree(pos);
+	}
+
+	region = iommu_alloc_resv_region(next, PHYS_ADDR_MAX - next,
+					 prot, IOMMU_RESV_RESERVED, GFP_KERNEL);
+	if (region)
+		list_add_tail(&region->list, list);
+
+exit:
+	list_for_each_entry_safe(pos, next_range, &ranges, node) {
+		list_del(&pos->node);
+		kfree(pos);
+	}
+}
+
 /**
  * of_iommu_get_resv_regions - reserved region driver helper for device tree
  * @dev: device for which to get reserved regions

@@ -262,5 +367,7 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 			}
 		}
 	}
+
+	of_iommu_derive_resv_regions(dev, list);
 }
 EXPORT_SYMBOL(of_iommu_get_resv_regions);