Merge tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - rework the non-coherent DMA allocator

 - move private definitions out of <linux/dma-mapping.h>

 - lower CMA_ALIGNMENT (Paul Cercueil)

 - remove the omap1 dma address translation in favor of the common code

 - make dma-direct aware of multiple dma offset ranges (Jim Quinlan)

 - support per-node DMA CMA areas (Barry Song)

 - increase the default seg boundary limit (Nicolin Chen)

 - misc fixes (Robin Murphy, Thomas Tai, Xu Wang)

 - various cleanups

* tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping: (63 commits)
  ARM/ixp4xx: add a missing include of dma-map-ops.h
  dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling
  dma-direct: factor out a dma_direct_alloc_from_pool helper
  dma-direct check for highmem pages in dma_direct_alloc_pages
  dma-mapping: merge <linux/dma-noncoherent.h> into <linux/dma-map-ops.h>
  dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma
  dma-mapping: move dma-debug.h to kernel/dma/
  dma-mapping: remove <asm/dma-contiguous.h>
  dma-mapping: merge <linux/dma-contiguous.h> into <linux/dma-map-ops.h>
  dma-contiguous: remove dma_contiguous_set_default
  dma-contiguous: remove dev_set_cma_area
  dma-contiguous: remove dma_declare_contiguous
  dma-mapping: split <linux/dma-mapping.h>
  cma: decrease CMA_ALIGNMENT lower limit to 2
  firewire-ohci: use dma_alloc_pages
  dma-iommu: implement ->alloc_noncoherent
  dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods
  dma-mapping: add a new dma_alloc_pages API
  dma-mapping: remove dma_cache_sync
  53c700: convert to dma_alloc_noncoherent
  ...

4 files changed, 90 insertions, 73 deletions

diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f..eb9ab4f1e80b 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
+
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
-	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e05434..655dee422563 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,8 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +91,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +107,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +154,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +171,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c00..d9e6a324de0a 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d4..06cc988faf78 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)