PPC: sg chaining support

This updates the ppc iommu/pci dma mappers to sg chaining. Includes
further fixes from FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

5 files changed, 34 insertions, 165 deletions

diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c
index 7b0e754383c..9001104b56b 100644
--- a/arch/powerpc/kernel/dma_64.c
+++ b/arch/powerpc/kernel/dma_64.c
@@ -154,12 +154,13 @@ static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
 {
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sg,
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++, sg++) {
+	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = (page_to_phys(sg->page) + sg->offset) |
 			dma_direct_offset;
 		sg->dma_length = sg->length;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 53bf64623bd..2e16ca5778a 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -87,15 +87,16 @@ static void ibmebus_unmap_single(struct device *dev,
 }
 
 static int ibmebus_map_sg(struct device *dev,
-			  struct scatterlist *sg,
+			  struct scatterlist *sgl,
 			  int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++) {
-		sg[i].dma_address = (dma_addr_t)page_address(sg[i].page)
-			+ sg[i].offset;
-		sg[i].dma_length = sg[i].length;
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = (dma_addr_t)page_address(sg->page)
+			+ sg->offset;
+		sg->dma_length = sg->length;
 	}
 
 	return nents;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index e4ec6eee81a..306a6f75b6c 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -277,7 +277,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;
-	int outcount, incount;
+	int outcount, incount, i;
 	unsigned long handle;
 
 	BUG_ON(direction == DMA_NONE);
@@ -297,7 +297,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
-	for (s = outs; nelems; nelems--, s++) {
+	for_each_sg(sglist, s, nelems, i) {
 		unsigned long vaddr, npages, entry, slen;
 
 		slen = s->length;
@@ -341,7 +341,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 			if (novmerge || (dma_addr != dma_next)) {
 				/* Can't merge: create a new segment */
 				segstart = s;
-				outcount++; outs++;
+				outcount++;
+				outs = sg_next(outs);
 				DBG("    can't merge, new segment.\n");
 			} else {
 				outs->dma_length += s->length;
@@ -374,7 +375,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	 * next entry of the sglist if we didn't fill the list completely
 	 */
 	if (outcount < incount) {
-		outs++;
+		outs = sg_next(outs);
 		outs->dma_address = DMA_ERROR_CODE;
 		outs->dma_length = 0;
 	}
@@ -385,7 +386,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	return outcount;
 
  failure:
-	for (s = &sglist[0]; s <= outs; s++) {
+	for_each_sg(sglist, s, nelems, i) {
 		if (s->dma_length != 0) {
 			unsigned long vaddr, npages;
 
@@ -395,6 +396,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
 		}
+		if (s == outs)
+			break;
 	}
 	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 	return 0;
@@ -404,6 +407,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	unsigned long flags;
 
 	BUG_ON(direction == DMA_NONE);
@@ -413,15 +417,16 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
+	sg = sglist;
 	while (nelems--) {
 		unsigned int npages;
-		dma_addr_t dma_handle = sglist->dma_address;
+		dma_addr_t dma_handle = sg->dma_address;
 
-		if (sglist->dma_length == 0)
+		if (sg->dma_length == 0)
 			break;
-		npages = iommu_num_pages(dma_handle,sglist->dma_length);
+		npages = iommu_num_pages(dma_handle, sg->dma_length);
 		__iommu_free(tbl, dma_handle, npages);
-		sglist++;
+		sg = sg_next(sg);
 	}
 
 	/* Flush/invalidate TLBs if necessary. As for iommu_free(), we
diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h
index 60eacde828c..2af321f36ab 100644
--- a/include/asm-powerpc/dma-mapping.h
+++ b/include/asm-powerpc/dma-mapping.h
@@ -6,149 +6,6 @@
  */
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-#include <linux/cache.h>
-/* need struct page definitions */
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <asm/io.h>
-
-#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
-
-#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.
- */
-extern void *__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp);
-extern void __dma_free_coherent(size_t size, void *vaddr);
-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);
-
-#else /* ! CONFIG_NOT_COHERENT_CACHE */
-/*
- * Cache coherent cores.
- */
-
-#define __dma_alloc_coherent(gfp, size, handle)	NULL
-#define __dma_free_coherent(size, addr)		((void)0)
-#define __dma_sync(addr, size, rw)		((void)0)
-#define __dma_sync_page(pg, off, sz, rw)	((void)0)
-
-#endif /* ! CONFIG_NOT_COHERENT_CACHE */
-
-#ifdef CONFIG_PPC64
-/*
- * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
- */
-struct dma_mapping_ops {
-	void *		(*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag);
-	void		(*free_coherent)(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t	(*map_single)(struct device *dev, void *ptr,
-				size_t size, enum dma_data_direction direction);
-	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction);
-	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
-	void		(*unmap_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
-	int		(*dma_supported)(struct device *dev, u64 mask);
-	int		(*set_dma_mask)(struct device *dev, u64 dma_mask);
-};
-
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
-{
-	/* We don't handle the NULL dev case for ISA for now. We could
-	 * do it via an out of line call but it is not needed for now. The
-	 * only ISA DMA device we support is the floppy and we have a hack
-	 * in the floppy driver directly to get a device for us.
-	 */
-	if (unlikely(dev == NULL || dev->archdata.dma_ops == NULL))
-		return NULL;
-	return dev->archdata.dma_ops;
-}
-
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return 0;
-	if (dma_ops->dma_supported == NULL)
-		return 1;
-	return dma_ops->dma_supported(dev, mask);
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return -EIO;
-	if (dma_ops->set_dma_mask != NULL)
-		return dma_ops->set_dma_mask(dev, dma_mask);
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-					size_t size,
-					enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->map_single(dev, cpu_addr, size, direction);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	dma_ops->unmap_single(dev, dma_addr, size, direction);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->map_single(dev, page_address(page) + offset, size,
-			direction);
-}
 
 static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 				  size_t size,
@@ -276,14 +133,15 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 }
 
 static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+dma_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 	   enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sg++) {
+	for_each_sg(sgl, sg, nents, i) {
 		BUG_ON(!sg->page);
 		__dma_sync_page(sg->page, sg->offset, sg->length, direction);
 		sg->dma_address = page_to_bus(sg->page) + sg->offset;
@@ -318,26 +176,28 @@ static inline void dma_sync_single_for_device(struct device *dev,
 }
 
 static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sg, int nents,
+		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sg++)
+	for_each_sg(sgl, sg, nents, i)
 		__dma_sync_page(sg->page, sg->offset, sg->length, direction);
 }
 
 static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nents,
+		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sg++)
+	for_each_sg(sgl, sg, nents, i)
 		__dma_sync_page(sg->page, sg->offset, sg->length, direction);
 }
 
diff --git a/include/asm-powerpc/scatterlist.h b/include/asm-powerpc/scatterlist.h
index 8c992d1491d..b075f619c3b 100644
--- a/include/asm-powerpc/scatterlist.h
+++ b/include/asm-powerpc/scatterlist.h
@@ -41,5 +41,7 @@ struct scatterlist {
 #define ISA_DMA_THRESHOLD	(~0UL)
 #endif
 
+#define ARCH_HAS_SG_CHAIN
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SCATTERLIST_H */