DT support for 'dma-ranges'and 'dma-coherent' properties with ARM updates

- The 'dma-ranges' helps to take care of few DMAable system memory
         restrictions by use of dma_pfn_offset which is maintained per
         device. Arch code then uses it for dma address translations for such
         cases. We update the dma_pfn_offset accordingly during DT the device
         creation process.
 - The 'dma-coherent' property is used to setup arch's coherent dma_ops.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABAgAGBQJTajacAAoJEHJsHOdBp5c/780QAJN50zmxyZ7sqA9xGum8MSJl
 Vjpp1mw3eu7dZ1HoWcpn35l0tOEVpU/wo4ymtt6YYUhD3Po2LZCl3e43h91B/9/B
 Ih++WZaN+UmpUpp9YJyeS9pkl0wwEqSmJyTBXZrhFhl4o3KNQlHWPGOMJ5CBPaA0
 Z03TT1MeOMiCo10xz6JCA/DjPnQz9m5ClxNXLwdP1KOiTDDsv4gtkTZ0UenttIoU
 DTerJ+GIt1Gzb+P92aGvuc9wgLKacYmH599m6fQcmd9cIG2oMN2Xdxzfqo56v7Sb
 TGwFcKWYlhPDbDPmcPlidS6j4O+r8cMRwgHLO3r6LHJezCGQOYU8GzN7m6DKt4ww
 lCIR/k9u4YY/ZiLFeQ+G0Au8T1J6DHdbCI5sciFI53XYT4HMsV1aNpogOim7adC8
 4bPRmGCIN03aW+2ynLkFkdnXSBnaAyjt6qlr5zP8owsKDkV7+0WadQqyD2ovQ0FE
 sBt1HtOUGUsiR/97J4JFBGFxb84zMa6hXhFVUeFbyScCJNm2gkKeRQfiiB4mZi9L
 NAX/KVGyS6dktJaoLUiKi/p7aqOat3ezD1PrCziq4ceyWbDLag8Bq9H7rtb7vvqC
 ulHDUPfRy3Z9kmV8+QAznqPJVY1IHXJ18A+YFXF5ktr+5CJ51C8HjVZP3GZKncPC
 LpA1rRUEwEqsAwnjzcXW
 =Q7n3
 -----END PGP SIGNATURE-----

Merge tag 'dt-dma-properties-for-arm' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone into devel-stable

DT support for 'dma-ranges'and 'dma-coherent' properties with ARM updates

- The 'dma-ranges' helps to take care of few DMAable system memory
        restrictions by use of dma_pfn_offset which is maintained per
        device. Arch code then uses it for dma address translations for such
        cases. We update the dma_pfn_offset accordingly during DT the device
        creation process.
- The 'dma-coherent' property is used to setup arch's coherent dma_ops.

arch/arm/include/asm/dma-mapping.h

@@ -58,21 +58,37 @@ static inline int dma_set_mask(struct device *dev, u64 mask)
 #ifndef __arch_pfn_to_dma
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
+	if (dev)
+		pfn -= dev->dma_pfn_offset;
 	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
 static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-	return __bus_to_pfn(addr);
+	unsigned long pfn = __bus_to_pfn(addr);
+
+	if (dev)
+		pfn += dev->dma_pfn_offset;
+
+	return pfn;
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
 {
+	if (dev) {
+		unsigned long pfn = dma_to_pfn(dev, addr);
+
+		return phys_to_virt(__pfn_to_phys(pfn));
+	}
+
 	return (void *)__bus_to_virt((unsigned long)addr);
 }
 
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 {
+	if (dev)
+		return pfn_to_dma(dev, virt_to_pfn(addr));
+
 	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
 }
 
@@ -105,6 +121,13 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 }
 #define dma_max_pfn(dev) dma_max_pfn(dev)
 
+static inline int set_arch_dma_coherent_ops(struct device *dev)
+{
+	set_dma_ops(dev, &arm_coherent_dma_ops);
+	return 0;
+}
+#define set_arch_dma_coherent_ops(dev)	set_arch_dma_coherent_ops(dev)
+
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;

arch/arm/mm/dma-mapping.c

@@ -885,7 +885,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
 	size_t size, enum dma_data_direction dir)
 {
-	unsigned long paddr;
+	phys_addr_t paddr;
 
 	dma_cache_maint_page(page, off, size, dir, dmac_map_area);
 
@@ -901,7 +901,7 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
 static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	size_t size, enum dma_data_direction dir)
 {
-	unsigned long paddr = page_to_phys(page) + off;
+	phys_addr_t paddr = page_to_phys(page) + off;
 
 	/* FIXME: non-speculating: not required */
 	/* don't bother invalidating if DMA to device */

drivers/of/address.c

@@ -721,3 +721,113 @@ void __iomem *of_iomap(struct device_node *np, int index)
 	return ioremap(res.start, resource_size(&res));
 }
 EXPORT_SYMBOL(of_iomap);
+
+/**
+ * of_dma_get_range - Get DMA range info
+ * @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
+ *
+ * Look in bottom up direction for the first "dma-ranges" property
+ * and parse it.
+ *  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.
+ */
+int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+{
+	struct device_node *node = of_node_get(np);
+	const __be32 *ranges = NULL;
+	int len, naddr, nsize, pna;
+	int ret = 0;
+	u64 dmaaddr;
+
+	if (!node)
+		return -EINVAL;
+
+	while (1) {
+		naddr = of_n_addr_cells(node);
+		nsize = of_n_size_cells(node);
+		node = of_get_next_parent(node);
+		if (!node)
+			break;
+
+		ranges = of_get_property(node, "dma-ranges", &len);
+
+		/* Ignore empty ranges, they imply no translation required */
+		if (ranges && len > 0)
+			break;
+
+		/*
+		 * At least empty ranges has to be defined for parent node if
+		 * DMA is supported
+		 */
+		if (!ranges)
+			break;
+	}
+
+	if (!ranges) {
+		pr_debug("%s: no dma-ranges found for node(%s)\n",
+			 __func__, np->full_name);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	len /= sizeof(u32);
+
+	pna = of_n_addr_cells(node);
+
+	/* dma-ranges format:
+	 * DMA addr	: naddr cells
+	 * CPU addr	: pna cells
+	 * size		: nsize cells
+	 */
+	dmaaddr = of_read_number(ranges, naddr);
+	*paddr = of_translate_dma_address(np, ranges);
+	if (*paddr == OF_BAD_ADDR) {
+		pr_err("%s: translation of DMA address(%pad) to CPU address failed node(%s)\n",
+		       __func__, dma_addr, np->full_name);
+		ret = -EINVAL;
+		goto out;
+	}
+	*dma_addr = dmaaddr;
+
+	*size = of_read_number(ranges + naddr + pna, nsize);
+
+	pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
+		 *dma_addr, *paddr, *size);
+
+out:
+	of_node_put(node);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_dma_get_range);
+
+/**
+ * of_dma_is_coherent - Check if device is coherent
+ * @np:	device node
+ *
+ * It returns true if "dma-coherent" property was found
+ * for this device in DT.
+ */
+bool of_dma_is_coherent(struct device_node *np)
+{
+	struct device_node *node = of_node_get(np);
+
+	while (node) {
+		if (of_property_read_bool(node, "dma-coherent")) {
+			of_node_put(node);
+			return true;
+		}
+		node = of_get_next_parent(node);
+	}
+	of_node_put(node);
+	return false;
+}
+EXPORT_SYMBOL_GPL(of_dma_is_coherent);

drivers/of/platform.c

@@ -188,6 +188,64 @@ struct platform_device *of_device_alloc(struct device_node *np,
 }
 EXPORT_SYMBOL(of_device_alloc);
 
+/**
+ * of_dma_configure - Setup DMA configuration
+ * @dev:	Device to apply DMA configuration
+ *
+ * Try to get devices's DMA configuration from DT and update it
+ * accordingly.
+ *
+ * In case if platform code need to use own special DMA configuration,it
+ * can use Platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE event
+ * to fix up DMA configuration.
+ */
+static void of_dma_configure(struct platform_device *pdev)
+{
+	u64 dma_addr, paddr, size;
+	int ret;
+	struct device *dev = &pdev->dev;
+
+#if defined(CONFIG_MICROBLAZE)
+	pdev->archdata.dma_mask = 0xffffffffUL;
+#endif
+
+	/*
+	 * Set default dma-mask to 32 bit. Drivers are expected to setup
+	 * the correct supported dma_mask.
+	 */
+	dev->coherent_dma_mask = DMA_BIT_MASK(32);
+
+	/*
+	 * Set it to coherent_dma_mask by default if the architecture
+	 * code has not set it.
+	 */
+	if (!dev->dma_mask)
+		dev->dma_mask = &dev->coherent_dma_mask;
+
+	/*
+	 * if dma-coherent property exist, call arch hook to setup
+	 * dma coherent operations.
+	 */
+	if (of_dma_is_coherent(dev->of_node)) {
+		set_arch_dma_coherent_ops(dev);
+		dev_dbg(dev, "device is dma coherent\n");
+	}
+
+	/*
+	 * if dma-ranges property doesn't exist - just return else
+	 * setup the dma offset
+	 */
+	ret = of_dma_get_range(dev->of_node, &dma_addr, &paddr, &size);
+	if (ret < 0) {
+		dev_dbg(dev, "no dma range information to setup\n");
+		return;
+	}
+
+	/* DMA ranges found. Calculate and set dma_pfn_offset */
+	dev->dma_pfn_offset = PFN_DOWN(paddr - dma_addr);
+	dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", dev->dma_pfn_offset);
+}
+
 /**
  * of_platform_device_create_pdata - Alloc, initialize and register an of_device
  * @np: pointer to node to create device for
@@ -213,12 +271,7 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		return NULL;
 
-#if defined(CONFIG_MICROBLAZE)
+	of_dma_configure(dev);
-	dev->archdata.dma_mask = 0xffffffffUL;
-#endif
-	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
-	if (!dev->dev.dma_mask)
-		dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 

include/linux/device.h

@@ -685,6 +685,7 @@ struct acpi_dev_node {
  * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
  * 		hardware supports 64-bit addresses for consistent allocations
  * 		such descriptors.
+ * @dma_pfn_offset: offset of DMA memory range relatively of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -750,6 +751,7 @@ struct device {
 					     not all hardware supports
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
+	unsigned long	dma_pfn_offset;
 
 	struct device_dma_parameters *dma_parms;
 

include/linux/dma-mapping.h

@@ -123,6 +123,13 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 
 extern u64 dma_get_required_mask(struct device *dev);
 
+#ifndef set_arch_dma_coherent_ops
+static inline int set_arch_dma_coherent_ops(struct device *dev)
+{
+	return 0;
+}
+#endif
+
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	return dev->dma_parms ? dev->dma_parms->max_segment_size : 65536;

include/linux/of_address.h

@@ -63,6 +63,9 @@ extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 extern struct of_pci_range *of_pci_range_parser_one(
 					struct of_pci_range_parser *parser,
 					struct of_pci_range *range);
+extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
+				u64 *paddr, u64 *size);
+extern bool of_dma_is_coherent(struct device_node *np);
 #else /* CONFIG_OF_ADDRESS */
 static inline struct device_node *of_find_matching_node_by_address(
 					struct device_node *from,
@@ -90,6 +93,17 @@ static inline struct of_pci_range *of_pci_range_parser_one(
 {
 	return NULL;
 }
+
+static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
+				u64 *paddr, u64 *size)
+{
+	return -ENODEV;
+}
+
+static inline bool of_dma_is_coherent(struct device_node *np)
+{
+	return false;
+}
 #endif /* CONFIG_OF_ADDRESS */
 
 #ifdef CONFIG_OF