powerpc: Merge 32 and 64-bit dma code

We essentially adopt the 64-bit dma code, with some changes to support
32-bit systems, including HIGHMEM.  dma functions on 32-bit are now
invoked via accessor functions which call the correct op for a device based
on archdata dma_ops.  If there is no archdata dma_ops, this defaults
to dma_direct_ops.

In addition, the dma_map/unmap_page functions are added to dma_ops
because we can't just fall back on map/unmap_single when HIGHMEM is
enabled. In the case of dma_direct_*, we stop using map/unmap_single
and just use the page version - this saves a lot of ugly
ifdeffing.  We leave map/unmap_single in the dma_ops definition,
though, because they are needed by the iommu code, which does not
implement map/unmap_page.  Ideally, going forward, we will completely
eliminate map/unmap_single and just have map/unmap_page, if it's
workable for 64-bit.

Signed-off-by: Becky Bruce <becky.bruce@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>

5 files changed, 103 insertions, 71 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 09b3cabf2f91..fdb58253fa5b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -70,10 +70,10 @@ extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
 obj-y				+= time.o prom.o traps.o setup-common.o \
-				   udbg.o misc.o io.o \
+				   udbg.o misc.o io.o dma.o \
 				   misc_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
-obj-$(CONFIG_PPC64)		+= dma.o dma-iommu.o iommu.o
+obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_PPC_MULTIPLATFORM)	+= prom_init.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 124f86743bde..41fdd48bf433 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -16,21 +16,30 @@
  * This implementation supports a per-device offset that can be applied if
  * the address at which memory is visible to devices is not 0. Platform code
  * can set archdata.dma_data to an unsigned long holding the offset. By
- * default the offset is zero.
+ * default the offset is PCI_DRAM_OFFSET.
  */
 
 static unsigned long get_dma_direct_offset(struct device *dev)
 {
-	return (unsigned long)dev->archdata.dma_data;
+	if (dev)
+		return (unsigned long)dev->archdata.dma_data;
+
+	return PCI_DRAM_OFFSET;
 }
 
-static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t flag)
 {
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	return __dma_alloc_coherent(size, dma_handle, flag);
+#else
 	struct page *page;
 	void *ret;
 	int node = dev_to_node(dev);
 
+	/* ignore region specifiers */
+	flag  &= ~(__GFP_HIGHMEM);
+
 	page = alloc_pages_node(node, flag, get_order(size));
 	if (page == NULL)
 		return NULL;
@@ -39,27 +48,17 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 	*dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev);
 
 	return ret;
+#endif
 }
 
-static void dma_direct_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle)
+void dma_direct_free_coherent(struct device *dev, size_t size,
+			      void *vaddr, dma_addr_t dma_handle)
 {
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	__dma_free_coherent(size, vaddr);
+#else
 	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t dma_direct_map_single(struct device *dev, void *ptr,
-					size_t size,
-					enum dma_data_direction direction,
-					struct dma_attrs *attrs)
-{
-	return virt_to_abs(ptr) + get_dma_direct_offset(dev);
-}
-
-static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction,
-				    struct dma_attrs *attrs)
-{
+#endif
 }
 
 static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
@@ -85,20 +84,44 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
 
 static int dma_direct_dma_supported(struct device *dev, u64 mask)
 {
+#ifdef CONFIG_PPC64
 	/* Could be improved to check for memory though it better be
 	 * done via some global so platforms can set the limit in case
 	 * they have limited DMA windows
 	 */
 	return mask >= DMA_32BIT_MASK;
+#else
+	return 1;
+#endif
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+					     struct page *page,
+					     unsigned long offset,
+					     size_t size,
+					     enum dma_data_direction dir,
+					     struct dma_attrs *attrs)
+{
+	BUG_ON(dir == DMA_NONE);
+	__dma_sync_page(page, offset, size, dir);
+	return page_to_phys(page) + offset + get_dma_direct_offset(dev);
+}
+
+static inline void dma_direct_unmap_page(struct device *dev,
+					 dma_addr_t dma_address,
+					 size_t size,
+					 enum dma_data_direction direction,
+					 struct dma_attrs *attrs)
+{
 }
 
 struct dma_mapping_ops dma_direct_ops = {
 	.alloc_coherent	= dma_direct_alloc_coherent,
 	.free_coherent	= dma_direct_free_coherent,
-	.map_single	= dma_direct_map_single,
-	.unmap_single	= dma_direct_unmap_single,
 	.map_sg		= dma_direct_map_sg,
 	.unmap_sg	= dma_direct_unmap_sg,
 	.dma_supported	= dma_direct_dma_supported,
+	.map_page	= dma_direct_map_page,
+	.unmap_page	= dma_direct_unmap_page,
 };
 EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index ea0c61e09b76..52ccfed416ad 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -56,6 +56,34 @@ resource_size_t isa_mem_base;
 /* Default PCI flags is 0 */
 unsigned int ppc_pci_flags;
 
+static struct dma_mapping_ops *pci_dma_ops;
+
+void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
+{
+	pci_dma_ops = dma_ops;
+}
+
+struct dma_mapping_ops *get_pci_dma_ops(void)
+{
+	return pci_dma_ops;
+}
+EXPORT_SYMBOL(get_pci_dma_ops);
+
+int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	return dma_set_mask(&dev->dev, mask);
+}
+
+int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
+{
+	int rc;
+
+	rc = dma_set_mask(&dev->dev, mask);
+	dev->dev.coherent_dma_mask = dev->dma_mask;
+
+	return rc;
+}
+
 struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 {
 	struct pci_controller *phb;
@@ -180,6 +208,26 @@ char __devinit *pcibios_setup(char *str)
 	return str;
 }
 
+void __devinit pcibios_setup_new_device(struct pci_dev *dev)
+{
+	struct dev_archdata *sd = &dev->dev.archdata;
+
+	sd->of_node = pci_device_to_OF_node(dev);
+
+	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
+	    sd->of_node ? sd->of_node->full_name : "<none>");
+
+	sd->dma_ops = pci_dma_ops;
+#ifdef CONFIG_PPC32
+	sd->dma_data = (void *)PCI_DRAM_OFFSET;
+#endif
+	set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+	if (ppc_md.pci_dma_dev_setup)
+		ppc_md.pci_dma_dev_setup(dev);
+}
+EXPORT_SYMBOL(pcibios_setup_new_device);
+
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 88db4ffaf11c..174b77ee18ff 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -424,6 +424,7 @@ void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 	unsigned long io_offset;
 	struct resource *res;
 	int i;
+	struct pci_dev *dev;
 
 	/* Hookup PHB resources */
 	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
@@ -457,6 +458,12 @@ void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 			bus->resource[i+1] = res;
 		}
 	}
+
+	if (ppc_md.pci_dma_bus_setup)
+		ppc_md.pci_dma_bus_setup(bus);
+
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		pcibios_setup_new_device(dev);
 }
 
 /* the next one is stolen from the alpha port... */
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 1f75bf03446f..8247cff1cb3e 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -52,35 +52,6 @@ EXPORT_SYMBOL(pci_io_base);
 
 LIST_HEAD(hose_list);
 
-static struct dma_mapping_ops *pci_dma_ops;
-
-void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
-{
-	pci_dma_ops = dma_ops;
-}
-
-struct dma_mapping_ops *get_pci_dma_ops(void)
-{
-	return pci_dma_ops;
-}
-EXPORT_SYMBOL(get_pci_dma_ops);
-
-
-int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
-{
-	return dma_set_mask(&dev->dev, mask);
-}
-
-int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
-{
-	int rc;
-
-	rc = dma_set_mask(&dev->dev, mask);
-	dev->dev.coherent_dma_mask = dev->dma_mask;
-
-	return rc;
-}
-
 static void fixup_broken_pcnet32(struct pci_dev* dev)
 {
 	if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
@@ -548,23 +519,6 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-void __devinit pcibios_setup_new_device(struct pci_dev *dev)
-{
-	struct dev_archdata *sd = &dev->dev.archdata;
-
-	sd->of_node = pci_device_to_OF_node(dev);
-
-	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
-	    sd->of_node ? sd->of_node->full_name : "<none>");
-
-	sd->dma_ops = pci_dma_ops;
-	set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
-
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
-}
-EXPORT_SYMBOL(pcibios_setup_new_device);
-
 void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
 {
 	struct pci_dev *dev;