[2/4] dma: redefine dma_flags_set_dmabarrier() for sn-ia64

[akepner@sgi.com]

define dma_flags_set_dmabarrier() for sn-ia64 - it "borrows"
bits from the direction argument (renamed "flags") to the
dma_map_* routines to pass an additional "dmabarrier" attribute.
Also define routines to retrieve the original direction and
attribute from "flags".

Signed-off-by: Arthur Kepner <akepner@sgi.com>

---
 arch/ia64/sn/pci/pci_dma.c |   35 ++++++++++++++++++++++++++---------
 include/asm-ia64/sn/io.h   |   24 ++++++++++++++++++++++++
 2 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index d79ddac..6c0a498 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -153,7 +153,7 @@ EXPORT_SYMBOL(sn_dma_free_coherent);
  * @dev: device to map for
  * @cpu_addr: kernel virtual address of the region to map
  * @size: size of the region
- * @direction: DMA direction
+ * @flags: DMA direction, and arch-specific attributes
  *
  * Map the region pointed to by @cpu_addr for DMA and return the
  * DMA address.
@@ -167,17 +167,23 @@ EXPORT_SYMBOL(sn_dma_free_coherent);
  *       figure out how to save dmamap handle so can use two step.
  */
 dma_addr_t sn_dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-			     int direction)
+			     int flags)
 {
 	dma_addr_t dma_addr;
 	unsigned long phys_addr;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
+	int dmabarrier = dma_flags_get_dmabarrier(flags);
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
 	phys_addr = __pa(cpu_addr);
-	dma_addr = provider->dma_map(pdev, phys_addr, size, SN_DMA_ADDR_PHYS);
+	if (dmabarrier)
+		dma_addr = provider->dma_map_consistent(pdev, phys_addr, size, 
+							SN_DMA_ADDR_PHYS);
+	else
+		dma_addr = provider->dma_map(pdev, phys_addr, size, 
+					     SN_DMA_ADDR_PHYS);
 	if (!dma_addr) {
 		printk(KERN_ERR "%s: out of ATEs\n", __FUNCTION__);
 		return 0;
@@ -240,18 +246,20 @@ EXPORT_SYMBOL(sn_dma_unmap_sg);
  * @dev: device to map for
  * @sg: scatterlist to map
  * @nhwentries: number of entries
- * @direction: direction of the DMA transaction
+ * @flags: direction of the DMA transaction, and arch-specific attributes
  *
  * Maps each entry of @sg for DMA.
  */
 int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-		  int direction)
+		  int flags)
 {
 	unsigned long phys_addr;
 	struct scatterlist *saved_sg = sg;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 	int i;
+	int dmabarrier = dma_flags_get_dmabarrier(flags);
+	int direction = dma_flags_get_direction(flags);
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
@@ -259,12 +267,21 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 	 * Setup a DMA address for each entry in the scatterlist.
 	 */
 	for (i = 0; i < nhwentries; i++, sg++) {
+		dma_addr_t dma_addr;
 		phys_addr = SG_ENT_PHYS_ADDRESS(sg);
-		sg->dma_address = provider->dma_map(pdev,
-						    phys_addr, sg->length,
-						    SN_DMA_ADDR_PHYS);
 
-		if (!sg->dma_address) {
+		if (dmabarrier) {
+			dma_addr = provider->dma_map_consistent(pdev,
+								phys_addr,
+								sg->length,
+								SN_DMA_ADDR_PHYS);
+		} else {
+			dma_addr = provider->dma_map(pdev,
+						     phys_addr, sg->length,
+						     SN_DMA_ADDR_PHYS);
+		}
+
+		if (!(sg->dma_address = dma_addr)) {
 			printk(KERN_ERR "%s: out of ATEs\n", __FUNCTION__);
 
 			/*
diff --git a/include/asm-ia64/sn/io.h b/include/asm-ia64/sn/io.h
index 41c73a7..301bc47 100644
--- a/include/asm-ia64/sn/io.h
+++ b/include/asm-ia64/sn/io.h
@@ -271,4 +271,28 @@ sn_pci_set_vchan(struct pci_dev *pci_dev, unsigned long *addr, int vchan)
 	return 0;
 }
 
+#define ARCH_CAN_REORDER_DMA
+/* here we steal some upper bits from the "direction" argument to the 
+ * dma_map_* routines */
+#define DMA_ATTR_SHIFT	8
+/* bottom 8 bits for direction, remaining bits for additional "attributes" */
+#define DMA_BARRIER_ATTR	0x1
+/* Setting DMA_BARRIER_ATTR on a DMA-mapped memory region causes all in-
+ * flight DMA to be flushed when the memory region is written to. So 
+ * DMA_BARRIER_ATTR is a mechanism to enforce ordering of DMA. */
+#define DMA_DIR_MASK   ((1 << DMA_ATTR_SHIFT) - 1)
+#define DMA_ATTR_MASK  ~DMA_DIR_MASK
+
+static inline int dma_flags_set_dmabarrier(int dir) {
+	return (dir | (DMA_BARRIER_ATTR<< DMA_ATTR_SHIFT));
+}
+
+static inline int dma_flags_get_direction(int dir) {
+	return (dir & DMA_DIR_MASK);
+}
+
+static inline int dma_flags_get_dmabarrier(int dir) {
+	return (((dir & DMA_ATTR_MASK) >> DMA_ATTR_SHIFT) & DMA_BARRIER_ATTR);
+}
+
 #endif	/* _ASM_SN_IO_H */