powerpc/dma: use the dma_direct mapping routines

Switch the streaming DMA mapping and ownership transfer methods to the
functionally identical dma_direct_ versions.  Factor the cache
maintainance helpers into the form expected by the common code for that.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

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

@@ -25,36 +25,6 @@ extern void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
 extern void __dma_nommu_free_coherent(struct device *dev, size_t size,
 				       void *vaddr, dma_addr_t dma_handle,
 				       unsigned long attrs);
-int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs);
-dma_addr_t dma_nommu_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs);
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-/*
- * DMA-consistent mapping functions for PowerPCs that don't support
- * cache snooping.  These allocate/free a region of uncached mapped
- * memory space for use with DMA devices.  Alternatively, you could
- * allocate the space "normally" and use the cache management functions
- * to ensure it is consistent.
- */
-struct device;
-extern void __dma_sync(void *vaddr, size_t size, int direction);
-extern void __dma_sync_page(struct page *page, unsigned long offset,
-				 size_t size, int direction);
-extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr);
-
-#else /* ! CONFIG_NOT_COHERENT_CACHE */
-/*
- * Cache coherent cores.
- */
-
-#define __dma_sync(addr, size, rw)		((void)0)
-#define __dma_sync_page(pg, off, sz, rw)	((void)0)
-
-#endif /* ! CONFIG_NOT_COHERENT_CACHE */
 
 static inline unsigned long device_to_mask(struct device *dev)
 {

arch/powerpc/kernel/dma-iommu.c

@@ -68,7 +68,7 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
 				     unsigned long attrs)
 {
 	if (dma_iommu_map_bypass(dev, attrs))
-		return dma_nommu_map_page(dev, page, offset, size, direction,
+		return dma_direct_map_page(dev, page, offset, size, direction,
 				attrs);
 	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
 			      size, device_to_mask(dev), direction, attrs);
@@ -90,7 +90,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    unsigned long attrs)
 {
 	if (dma_iommu_map_bypass(dev, attrs))
-		return dma_nommu_map_sg(dev, sglist, nelems, direction, attrs);
+		return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
 	return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
 				device_to_mask(dev), direction, attrs);
 }

arch/powerpc/kernel/dma.c

@@ -27,77 +27,6 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
-int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = phys_to_dma(dev, sg_phys(sg));
-		sg->dma_length = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
-				int nents, enum dma_data_direction direction,
-				unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-}
-
-dma_addr_t dma_nommu_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_page(page, offset, size, dir);
-
-	return phys_to_dma(dev, page_to_phys(page)) + offset;
-}
-
-static inline void dma_nommu_unmap_page(struct device *dev,
-					 dma_addr_t dma_address,
-					 size_t size,
-					 enum dma_data_direction direction,
-					 unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(bus_to_virt(dma_address), size, direction);
-}
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-static inline void dma_nommu_sync_sg(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-}
-
-static inline void dma_nommu_sync_single(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  enum dma_data_direction direction)
-{
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
-}
-#endif
-
 const struct dma_map_ops dma_nommu_ops = {
 #ifdef CONFIG_NOT_COHERENT_CACHE
 	.alloc				= __dma_nommu_alloc_coherent,
@@ -106,17 +35,17 @@ const struct dma_map_ops dma_nommu_ops = {
 	.alloc				= dma_direct_alloc,
 	.free				= dma_direct_free,
 #endif
-	.map_sg				= dma_nommu_map_sg,
+	.map_sg				= dma_direct_map_sg,
-	.unmap_sg			= dma_nommu_unmap_sg,
 	.dma_supported			= dma_direct_supported,
-	.map_page			= dma_nommu_map_page,
+	.map_page			= dma_direct_map_page,
-	.unmap_page			= dma_nommu_unmap_page,
 	.get_required_mask		= dma_direct_get_required_mask,
 #ifdef CONFIG_NOT_COHERENT_CACHE
-	.sync_single_for_cpu 		= dma_nommu_sync_single,
+	.unmap_sg			= dma_direct_unmap_sg,
-	.sync_single_for_device 	= dma_nommu_sync_single,
+	.unmap_page			= dma_direct_unmap_page,
-	.sync_sg_for_cpu 		= dma_nommu_sync_sg,
+	.sync_single_for_cpu 		= dma_direct_sync_single_for_cpu,
-	.sync_sg_for_device 		= dma_nommu_sync_sg,
+	.sync_single_for_device 	= dma_direct_sync_single_for_device,
+	.sync_sg_for_cpu 		= dma_direct_sync_sg_for_cpu,
+	.sync_sg_for_device 		= dma_direct_sync_sg_for_device,
 #endif
 };
 EXPORT_SYMBOL(dma_nommu_ops);

arch/powerpc/mm/dma-noncoherent.c

@@ -314,7 +314,7 @@ void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
 /*
  * make an area consistent.
  */
-void __dma_sync(void *vaddr, size_t size, int direction)
+static void __dma_sync(void *vaddr, size_t size, int direction)
 {
 	unsigned long start = (unsigned long)vaddr;
 	unsigned long end   = start + size;
@@ -340,7 +340,6 @@ void __dma_sync(void *vaddr, size_t size, int direction)
 		break;
 	}
 }
-EXPORT_SYMBOL(__dma_sync);
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -387,21 +386,33 @@ static inline void __dma_sync_page_highmem(struct page *page,
  * __dma_sync_page makes memory consistent. identical to __dma_sync, but
  * takes a struct page instead of a virtual address
  */
-void __dma_sync_page(struct page *page, unsigned long offset,
+static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
-	size_t size, int direction)
 {
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned offset = paddr & ~PAGE_MASK;
+
 #ifdef CONFIG_HIGHMEM
-	__dma_sync_page_highmem(page, offset, size, direction);
+	__dma_sync_page_highmem(page, offset, size, dir);
 #else
 	unsigned long start = (unsigned long)page_address(page) + offset;
-	__dma_sync((void *)start, size, direction);
+	__dma_sync((void *)start, size, dir);
 #endif
 }
-EXPORT_SYMBOL(__dma_sync_page);
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_sync_page(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_sync_page(paddr, size, dir);
+}
 
 /*
- * Return the PFN for a given cpu virtual address returned by
+ * Return the PFN for a given cpu virtual address returned by arch_dma_alloc.
- * __dma_nommu_alloc_coherent.
  */
 long arch_dma_coherent_to_pfn(struct device *dev, void *vaddr,
 		dma_addr_t dma_addr)

arch/powerpc/platforms/Kconfig.cputype

@@ -403,6 +403,8 @@ config NOT_COHERENT_CACHE
 	depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
 		GAMECUBE_COMMON || AMIGAONE
 	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	default n if PPC_47x
 	default y