SPARC64: sg chaining support

This updates the sparc64 iommu/pci dma mappers to sg chaining.

Acked-by: David S. Miller <davem@davemloft.net>

Later updated to newer kernel with unified sparc64 iommu sg handling.

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

3 files changed, 45 insertions, 28 deletions

diff --git a/arch/sparc64/kernel/iommu.c b/arch/sparc64/kernel/iommu.c
index b35a62167e9c..db3ffcf7a120 100644
--- a/arch/sparc64/kernel/iommu.c
+++ b/arch/sparc64/kernel/iommu.c
@@ -10,6 +10,7 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/errno.h>
+#include <linux/scatterlist.h>
 
 #ifdef CONFIG_PCI
 #include <linux/pci.h>
@@ -480,7 +481,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 			   unsigned long iopte_protection)
 {
 	struct scatterlist *dma_sg = sg;
-	struct scatterlist *sg_end = sg + nelems;
+	struct scatterlist *sg_end = sg_last(sg, nelems);
 	int i;
 
 	for (i = 0; i < nused; i++) {
@@ -515,7 +516,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 					len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL)));
 					break;
 				}
-				sg++;
+				sg = sg_next(sg);
 			}
 
 			pteval = iopte_protection | (pteval & IOPTE_PAGE);
@@ -528,24 +529,24 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 			}
 
 			pteval = (pteval & IOPTE_PAGE) + len;
-			sg++;
+			sg = sg_next(sg);
 
 			/* Skip over any tail mappings we've fully mapped,
 			 * adjusting pteval along the way.  Stop when we
 			 * detect a page crossing event.
 			 */
-			while (sg < sg_end &&
+			while (sg != sg_end &&
 			       (pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
 			       (pteval == SG_ENT_PHYS_ADDRESS(sg)) &&
 			       ((pteval ^
 				 (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) {
 				pteval += sg->length;
-				sg++;
+				sg = sg_next(sg);
 			}
 			if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL)
 				pteval = ~0UL;
 		} while (dma_npages != 0);
-		dma_sg++;
+		dma_sg = sg_next(dma_sg);
 	}
 }
 
@@ -606,7 +607,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	sgtmp = sglist;
 	while (used && sgtmp->dma_length) {
 		sgtmp->dma_address += dma_base;
-		sgtmp++;
+		sgtmp = sg_next(sgtmp);
 		used--;
 	}
 	used = nelems - used;
@@ -642,6 +643,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct strbuf *strbuf;
 	iopte_t *base;
 	unsigned long flags, ctx, i, npages;
+	struct scatterlist *sg, *sgprv;
 	u32 bus_addr;
 
 	if (unlikely(direction == DMA_NONE)) {
@@ -654,11 +656,14 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	bus_addr = sglist->dma_address & IO_PAGE_MASK;
 
-	for (i = 1; i < nelems; i++)
-		if (sglist[i].dma_length == 0)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) -
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) -
 		  bus_addr) >> IO_PAGE_SHIFT;
 
 	base = iommu->page_table +
@@ -730,6 +735,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 	struct iommu *iommu;
 	struct strbuf *strbuf;
 	unsigned long flags, ctx, npages, i;
+	struct scatterlist *sg, *sgprv;
 	u32 bus_addr;
 
 	iommu = dev->archdata.iommu;
@@ -753,11 +759,14 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 
 	/* Step 2: Kick data out of streaming buffers. */
 	bus_addr = sglist[0].dma_address & IO_PAGE_MASK;
-	for(i = 1; i < nelems; i++)
-		if (!sglist[i].dma_length)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length)
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length)
 		  - bus_addr) >> IO_PAGE_SHIFT;
 	strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c
index 95de1444ee67..cacacfae5451 100644
--- a/arch/sparc64/kernel/pci_sun4v.c
+++ b/arch/sparc64/kernel/pci_sun4v.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/log2.h>
+#include <linux/scatterlist.h>
 
 #include <asm/iommu.h>
 #include <asm/irq.h>
@@ -373,7 +374,7 @@ static inline long fill_sg(long entry, struct device *dev,
 			   int nused, int nelems, unsigned long prot)
 {
 	struct scatterlist *dma_sg = sg;
-	struct scatterlist *sg_end = sg + nelems;
+	struct scatterlist *sg_end = sg_last(sg, nelems);
 	unsigned long flags;
 	int i;
 
@@ -413,7 +414,7 @@ static inline long fill_sg(long entry, struct device *dev,
 					len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL)));
 					break;
 				}
-				sg++;
+				sg = sg_next(sg);
 			}
 
 			pteval = (pteval & IOPTE_PAGE);
@@ -431,24 +432,25 @@ static inline long fill_sg(long entry, struct device *dev,
 			}
 
 			pteval = (pteval & IOPTE_PAGE) + len;
-			sg++;
+			sg = sg_next(sg);
 
 			/* Skip over any tail mappings we've fully mapped,
 			 * adjusting pteval along the way.  Stop when we
 			 * detect a page crossing event.
 			 */
-			while (sg < sg_end &&
-			       (pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
+			while ((pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
 			       (pteval == SG_ENT_PHYS_ADDRESS(sg)) &&
 			       ((pteval ^
 				 (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) {
 				pteval += sg->length;
-				sg++;
+				if (sg == sg_end)
+					break;
+				sg = sg_next(sg);
 			}
 			if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL)
 				pteval = ~0UL;
 		} while (dma_npages != 0);
-		dma_sg++;
+		dma_sg = sg_next(dma_sg);
 	}
 
 	if (unlikely(iommu_batch_end() < 0L))
@@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	sgtmp = sglist;
 	while (used && sgtmp->dma_length) {
 		sgtmp->dma_address += dma_base;
-		sgtmp++;
+		sgtmp = sg_next(sgtmp);
 		used--;
 	}
 	used = nelems - used;
@@ -545,6 +547,7 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
 	unsigned long flags, i, npages;
+	struct scatterlist *sg, *sgprv;
 	long entry;
 	u32 devhandle, bus_addr;
 
@@ -558,12 +561,15 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	devhandle = pbm->devhandle;
 	
 	bus_addr = sglist->dma_address & IO_PAGE_MASK;
-
-	for (i = 1; i < nelems; i++)
-		if (sglist[i].dma_length == 0)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) -
+
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) -
 		  bus_addr) >> IO_PAGE_SHIFT;
 
 	entry = ((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
diff --git a/include/asm-sparc64/scatterlist.h b/include/asm-sparc64/scatterlist.h
index 048fdb40e81d..703c5bbe6c8c 100644
--- a/include/asm-sparc64/scatterlist.h
+++ b/include/asm-sparc64/scatterlist.h
@@ -20,4 +20,6 @@ struct scatterlist {
 
 #define ISA_DMA_THRESHOLD	(~0UL)
 
+#define ARCH_HAS_SG_CHAIN
+
 #endif /* !(_SPARC64_SCATTERLIST_H) */