[patch 0/6] Implement dma_*map*_attrs() and DMA_ATTR_STRONG_ORDERING, use on Cell

@@ -68,7 +68,7 @@ static void dma_iommu_unmap_single(struc
 static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction)
 {
-	return iommu_map_sg(dev, sglist, nelems,
+	return iommu_map_sg(dev, dev->archdata.dma_data, sglist, nelems,
 			    device_to_mask(dev), direction);
 }
 

@@ -267,11 +267,10 @@ static void iommu_free(struct iommu_tabl
 	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 }
 
-int iommu_map_sg(struct device *dev, struct scatterlist *sglist,
-		 int nelems, unsigned long mask,
-		 enum dma_data_direction direction)
+int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
+		 struct scatterlist *sglist, int nelems,
+		 unsigned long mask, enum dma_data_direction direction)
 {
-	struct iommu_table *tbl = dev->archdata.dma_data;
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;

@@ -79,9 +79,9 @@ extern void iommu_free_table(struct iomm
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
 
-extern int iommu_map_sg(struct device *dev, struct scatterlist *sglist,
-			int nelems, unsigned long mask,
-			enum dma_data_direction direction);
+extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
+			struct scatterlist *sglist, int nelems,
+			unsigned long mask, enum dma_data_direction direction);
 extern void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 			   int nelems, enum dma_data_direction direction);
 

@@ -110,6 +110,7 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_LMB
+	select HAVE_DMA_ATTRS
 
 config EARLY_PRINTK
 	bool

@@ -50,32 +50,38 @@ static void dma_iommu_free_coherent(stru
  */
 static dma_addr_t dma_iommu_map_single(struct device *dev, void *vaddr,
 				       size_t size,
-				       enum dma_data_direction direction)
+				       enum dma_data_direction direction,
+				       struct dma_attrs *attrs)
 {
 	return iommu_map_single(dev, dev->archdata.dma_data, vaddr, size,
-			        device_to_mask(dev), direction);
+				device_to_mask(dev), direction, attrs);
 }
 
 
 static void dma_iommu_unmap_single(struct device *dev, dma_addr_t dma_handle,
 				   size_t size,
-				   enum dma_data_direction direction)
+				   enum dma_data_direction direction,
+				   struct dma_attrs *attrs)
 {
-	iommu_unmap_single(dev->archdata.dma_data, dma_handle, size, direction);
+	iommu_unmap_single(dev->archdata.dma_data, dma_handle, size, direction,
+			   attrs);
 }
 
 
 static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
-			    int nelems, enum dma_data_direction direction)
+			    int nelems, enum dma_data_direction direction,
+			    struct dma_attrs *attrs)
 {
 	return iommu_map_sg(dev, dev->archdata.dma_data, sglist, nelems,
-			    device_to_mask(dev), direction);
+			    device_to_mask(dev), direction, attrs);
 }
 
 static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
+		int nelems, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
-	iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction);
+	iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction,
+		       attrs);
 }
 
 /* We support DMA to/from any memory page via the iommu */

@@ -148,19 +154,22 @@ static void dma_direct_free_coherent(str
 
 static dma_addr_t dma_direct_map_single(struct device *dev, void *ptr,
 					size_t size,
-					enum dma_data_direction direction)
+					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)
+				    enum dma_data_direction direction,
+				    struct dma_attrs *attrs)
 {
 }
 
 static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
-			     int nents, enum dma_data_direction direction)
+			     int nents, enum dma_data_direction direction,
+			     struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;

@@ -174,7 +183,8 @@ static int dma_direct_map_sg(struct devi
 }
 
 static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction)
+				int nents, enum dma_data_direction direction,
+				struct dma_attrs *attrs)
 {
 }
 

@@ -82,7 +82,8 @@ static void ibmebus_free_coherent(struct
 static dma_addr_t ibmebus_map_single(struct device *dev,
 				     void *ptr,
 				     size_t size,
-				     enum dma_data_direction direction)
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
 {
 	return (dma_addr_t)(ptr);
 }

@@ -90,14 +91,16 @@ static dma_addr_t ibmebus_map_single(str
 static void ibmebus_unmap_single(struct device *dev,
 				 dma_addr_t dma_addr,
 				 size_t size,
-				 enum dma_data_direction direction)
+				 enum dma_data_direction direction,
+				 struct dma_attrs *attrs)
 {
 	return;
 }
 
 static int ibmebus_map_sg(struct device *dev,
 			  struct scatterlist *sgl,
-			  int nents, enum dma_data_direction direction)
+			  int nents, enum dma_data_direction direction,
+			  struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;

@@ -112,7 +115,8 @@ static int ibmebus_map_sg(struct device 
 
 static void ibmebus_unmap_sg(struct device *dev,
 			     struct scatterlist *sg,
-			     int nents, enum dma_data_direction direction)
+			     int nents, enum dma_data_direction direction,
+			     struct dma_attrs *attrs)
 {
 	return;
 }

@@ -269,7 +269,8 @@ static void iommu_free(struct iommu_tabl
 
 int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		 struct scatterlist *sglist, int nelems,
-		 unsigned long mask, enum dma_data_direction direction)
+		 unsigned long mask, enum dma_data_direction direction,
+		 struct dma_attrs *attrs)
 {
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;

@@ -411,7 +412,8 @@ int iommu_map_sg(struct device *dev, str
 
 
 void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
+		int nelems, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	unsigned long flags;

@@ -553,7 +555,7 @@ void iommu_free_table(struct iommu_table
  */
 dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl,
 			    void *vaddr, size_t size, unsigned long mask,
-			    enum dma_data_direction direction)
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	dma_addr_t dma_handle = DMA_ERROR_CODE;
 	unsigned long uaddr;

@@ -586,7 +588,8 @@ dma_addr_t iommu_map_single(struct devic
 }
 
 void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction)
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	unsigned int npages;
 

@@ -214,13 +214,13 @@ dma_addr_t iseries_hv_map(void *vaddr, s
 			enum dma_data_direction direction)
 {
 	return iommu_map_single(NULL, &vio_iommu_table, vaddr, size,
-				DMA_32BIT_MASK, direction);
+				DMA_32BIT_MASK, direction, NULL);
 }
 
 void iseries_hv_unmap(dma_addr_t dma_handle, size_t size,
 			enum dma_data_direction direction)
 {
-	iommu_unmap_single(&vio_iommu_table, dma_handle, size, direction);
+	iommu_unmap_single(&vio_iommu_table, dma_handle, size, direction, NULL);
 }
 
 void __init iommu_vio_init(void)

@@ -550,7 +550,7 @@ static void ps3_free_coherent(struct dev
  */
 
 static dma_addr_t ps3_sb_map_single(struct device *_dev, void *ptr, size_t size,
-	enum dma_data_direction direction)
+	enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int result;

@@ -570,7 +570,8 @@ static dma_addr_t ps3_sb_map_single(stru
 
 static dma_addr_t ps3_ioc0_map_single(struct device *_dev, void *ptr,
 				      size_t size,
-				      enum dma_data_direction direction)
+				      enum dma_data_direction direction,
+				      struct dma_attrs *attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int result;

@@ -603,7 +604,7 @@ static dma_addr_t ps3_ioc0_map_single(st
 }
 
 static void ps3_unmap_single(struct device *_dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
+	size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int result;

@@ -617,7 +618,7 @@ static void ps3_unmap_single(struct devi
 }
 
 static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sgl,
-	int nents, enum dma_data_direction direction)
+	int nents, enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 #if defined(CONFIG_PS3_DYNAMIC_DMA)
 	BUG_ON("do");

@@ -646,14 +647,15 @@ static int ps3_sb_map_sg(struct device *
 
 static int ps3_ioc0_map_sg(struct device *_dev, struct scatterlist *sg,
 			   int nents,
-			   enum dma_data_direction direction)
+			   enum dma_data_direction direction,
+			   struct dma_attrs *attrs)
 {
 	BUG();
 	return 0;
 }
 
 static void ps3_sb_unmap_sg(struct device *_dev, struct scatterlist *sg,
-	int nents, enum dma_data_direction direction)
+	int nents, enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 #if defined(CONFIG_PS3_DYNAMIC_DMA)
 	BUG_ON("do");

@@ -661,7 +663,8 @@ static void ps3_sb_unmap_sg(struct devic
 }
 
 static void ps3_ioc0_unmap_sg(struct device *_dev, struct scatterlist *sg,
-			    int nents, enum dma_data_direction direction)
+			    int nents, enum dma_data_direction direction,
+			    struct dma_attrs *attrs)
 {
 	BUG();
 }

@@ -13,6 +13,7 @@
 /* need struct page definitions */
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-attrs.h>
 #include <asm/io.h>
 
 #define DMA_ERROR_CODE		(~(dma_addr_t)0x0)

@@ -53,13 +54,17 @@ struct dma_mapping_ops {
 	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);
+				size_t size, enum dma_data_direction direction,
+				struct dma_attrs *attrs);
 	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction);
+				size_t size, enum dma_data_direction direction,
+				struct dma_attrs *attrs);
 	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
+				int nents, enum dma_data_direction direction,
+				struct dma_attrs *attrs);
 	void		(*unmap_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
+				int nents, enum dma_data_direction direction,
+				struct dma_attrs *attrs);
 	int		(*dma_supported)(struct device *dev, u64 mask);
 	int		(*set_dma_mask)(struct device *dev, u64 dma_mask);
 };

@@ -109,6 +114,77 @@ static inline int dma_set_mask(struct de
 	return 0;
 }
 
+static inline dma_addr_t dma_map_single_attrs(struct device *dev,
+					      void *cpu_addr,
+					      size_t size,
+					      enum dma_data_direction direction,
+					      struct dma_attrs *attrs)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->map_single(dev, cpu_addr, size, direction, attrs);
+}
+
+static inline void dma_unmap_single_attrs(struct device *dev,
+					  dma_addr_t dma_addr,
+					  size_t size,
+					  enum dma_data_direction direction,
+					  struct dma_attrs *attrs)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_single(dev, dma_addr, size, direction, attrs);
+}
+
+static inline dma_addr_t dma_map_page_attrs(struct device *dev,
+					    struct page *page,
+					    unsigned long offset, size_t size,
+					    enum dma_data_direction direction,
+					    struct dma_attrs *attrs)
+{
+	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, attrs);
+}
+
+static inline void dma_unmap_page_attrs(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_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_single(dev, dma_address, size, direction, attrs);
+}
+
+static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+				   int nents, enum dma_data_direction direction,
+				   struct dma_attrs *attrs)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->map_sg(dev, sg, nents, direction, attrs);
+}
+
+static inline void dma_unmap_sg_attrs(struct device *dev,
+				      struct scatterlist *sg,
+				      int nhwentries,
+				      enum dma_data_direction direction,
+				      struct dma_attrs *attrs)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_sg(dev, sg, nhwentries, direction, attrs);
+}
+
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
 {

@@ -131,63 +207,43 @@ static inline dma_addr_t dma_map_single(
 					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);
+	return dma_map_single_attrs(dev, cpu_addr, size, direction, NULL);
 }
 
 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);
+	dma_unmap_single_attrs(dev, dma_addr, size, direction, NULL);
 }
 
 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);
+	return dma_map_page_attrs(dev, page, offset, size, direction, NULL);
 }
 
 static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 				  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_address, size, direction);
+	dma_unmap_page_attrs(dev, dma_address, size, direction, NULL);
 }
 
 static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
 			     int nents, enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->map_sg(dev, sg, nents, direction);
+	return dma_map_sg_attrs(dev, sg, nents, direction, NULL);
 }
 
 static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 				int nhwentries,
 				enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	dma_ops->unmap_sg(dev, sg, nhwentries, direction);
+	dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
 }
 
-
 /*
  * Available generic sets of operations
  */

@@ -81,9 +81,11 @@ extern struct iommu_table *iommu_init_ta
 
 extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			struct scatterlist *sglist, int nelems,
-			unsigned long mask, enum dma_data_direction direction);
+			unsigned long mask, enum dma_data_direction direction,
+			struct dma_attrs *attrs);
 extern void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
-			   int nelems, enum dma_data_direction direction);
+			   int nelems, enum dma_data_direction direction,
+			   struct dma_attrs *attrs);
 
 extern void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 				  size_t size, dma_addr_t *dma_handle,

@@ -92,9 +94,11 @@ extern void iommu_free_coherent(struct i
 				void *vaddr, dma_addr_t dma_handle);
 extern dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl,
 				   void *vaddr, size_t size, unsigned long mask,
-				   enum dma_data_direction direction);
+				   enum dma_data_direction direction,
+				   struct dma_attrs *attrs);
 extern void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
-			       size_t size, enum dma_data_direction direction);
+			       size_t size, enum dma_data_direction direction,
+			       struct dma_attrs *attrs);
 
 extern void iommu_init_early_pSeries(void);
 extern void iommu_init_early_iSeries(void);

@@ -541,7 +541,7 @@ static unsigned long cell_dma_direct_off
 static unsigned long dma_iommu_fixed_base;
 struct dma_mapping_ops dma_iommu_fixed_ops;
 
-static void cell_dma_dev_setup_iommu(struct device *dev)
+static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {
 	struct iommu_window *window;
 	struct cbe_iommu *iommu;

@@ -556,11 +556,11 @@ static void cell_dma_dev_setup_iommu(str
 		printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n",
 		       archdata->of_node ? archdata->of_node->full_name : "?",
 		       archdata->numa_node);
-		return;
+		return NULL;
 	}
 	window = list_entry(iommu->windows.next, struct iommu_window, list);
 
-	archdata->dma_data = &window->table;
+	return &window->table;
 }
 
 static void cell_dma_dev_setup_fixed(struct device *dev);

@@ -573,7 +573,7 @@ static void cell_dma_dev_setup(struct de
 	if (get_dma_ops(dev) == &dma_iommu_fixed_ops)
 		cell_dma_dev_setup_fixed(dev);
 	else if (get_pci_dma_ops() == &dma_iommu_ops)
-		cell_dma_dev_setup_iommu(dev);
+		archdata->dma_data = cell_get_iommu_table(dev);
 	else if (get_pci_dma_ops() == &dma_direct_ops)
 		archdata->dma_data = (void *)cell_dma_direct_offset;
 	else

@@ -15,15 +15,6 @@
  * Generic iommu implementation
  */
 
-static inline unsigned long device_to_mask(struct device *dev)
-{
-	if (dev->dma_mask && *dev->dma_mask)
-		return *dev->dma_mask;
-	/* Assume devices without mask can take 32 bit addresses */
-	return 0xfffffffful;
-}
-
-
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.

@@ -45,6 +45,15 @@ extern void __dma_sync_page(struct page 
 #endif /* ! CONFIG_NOT_COHERENT_CACHE */
 
 #ifdef CONFIG_PPC64
+
+static inline unsigned long device_to_mask(struct device *dev)
+{
+	if (dev->dma_mask && *dev->dma_mask)
+		return *dev->dma_mask;
+	/* Assume devices without mask can take 32 bit addresses */
+	return 0xfffffffful;
+}
+
 /*
  * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
  */

@@ -194,11 +194,13 @@ static void tce_build_cell(struct iommu_
 	const unsigned long prot = 0xc48;
 	base_pte =
 		((prot << (52 + 4 * direction)) & (IOPTE_PP_W | IOPTE_PP_R))
-		| IOPTE_M | IOPTE_SO_RW | (window->ioid & IOPTE_IOID_Mask);
+		| IOPTE_M | (window->ioid & IOPTE_IOID_Mask);
 #else
-	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW |
+	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M |
 		(window->ioid & IOPTE_IOID_Mask);
 #endif
+	if (unlikely(dma_get_attr(DMA_ATTR_STRONG_ORDERING, attrs)))
+		base_pte |= IOPTE_SO_RW;
 
 	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 

@@ -539,7 +541,6 @@ static struct cbe_iommu *cell_iommu_for_
 static unsigned long cell_dma_direct_offset;
 
 static unsigned long dma_iommu_fixed_base;
-struct dma_mapping_ops dma_iommu_fixed_ops;
 
 static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {

@@ -563,6 +564,85 @@ static struct iommu_table *cell_get_iomm
 	return &window->table;
 }
 
+static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
+				      dma_addr_t *dma_handle, gfp_t flag)
+{
+	return dma_direct_ops.alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static void dma_fixed_free_coherent(struct device *dev, size_t size,
+				    void *vaddr, dma_addr_t dma_handle)
+{
+	dma_direct_ops.free_coherent(dev, size, vaddr, dma_handle);
+}
+
+static dma_addr_t dma_fixed_map_single(struct device *dev, void *ptr,
+				       size_t size,
+				       enum dma_data_direction direction,
+				       struct dma_attrs *attrs)
+{
+	if (dma_get_attr(DMA_ATTR_STRONG_ORDERING, attrs))
+		return iommu_map_single(dev, cell_get_iommu_table(dev), ptr,
+					size, device_to_mask(dev), direction,
+					attrs);
+	else
+		return dma_direct_ops.map_single(dev, ptr, size, direction,
+						 attrs);
+}
+
+static void dma_fixed_unmap_single(struct device *dev, dma_addr_t dma_addr,
+				   size_t size,
+				   enum dma_data_direction direction,
+				   struct dma_attrs *attrs)
+{
+	if (dma_get_attr(DMA_ATTR_STRONG_ORDERING, attrs))
+		iommu_unmap_single(cell_get_iommu_table(dev), dma_addr, size,
+				   direction, attrs);
+	else
+		dma_direct_ops.unmap_single(dev, dma_addr, size, direction,
+					    attrs);
+}
+
+static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
+			   int nents, enum dma_data_direction direction,
+			   struct dma_attrs *attrs)
+{
+	if (dma_get_attr(DMA_ATTR_STRONG_ORDERING, attrs))
+		return iommu_map_sg(dev, cell_get_iommu_table(dev), sg, nents,
+				    device_to_mask(dev), direction, attrs);
+	else
+		return dma_direct_ops.map_sg(dev, sg, nents, direction, attrs);
+}
+
+static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
+			       int nents, enum dma_data_direction direction,
+			       struct dma_attrs *attrs)
+{
+	if (dma_get_attr(DMA_ATTR_STRONG_ORDERING, attrs))
+		iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents, direction,
+			       attrs);
+	else
+		dma_direct_ops.unmap_sg(dev, sg, nents, direction, attrs);
+}
+
+static int dma_fixed_dma_supported(struct device *dev, u64 mask)
+{
+	return mask == DMA_64BIT_MASK;
+}
+
+static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
+
+struct dma_mapping_ops dma_iommu_fixed_ops = {
+	.alloc_coherent = dma_fixed_alloc_coherent,
+	.free_coherent  = dma_fixed_free_coherent,
+	.map_single     = dma_fixed_map_single,
+	.unmap_single   = dma_fixed_unmap_single,
+	.map_sg         = dma_fixed_map_sg,
+	.unmap_sg       = dma_fixed_unmap_sg,
+	.dma_supported  = dma_fixed_dma_supported,
+	.set_dma_mask   = dma_set_mask_and_switch,
+};
+
 static void cell_dma_dev_setup_fixed(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)

@@ -919,9 +999,11 @@ static void cell_iommu_setup_fixed_ptab(
 
 	pr_debug("iommu: mapping 0x%lx pages from 0x%lx\n", fsize, fbase);
 
-	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW
+	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M
 		    | (cell_iommu_get_ioid(np) & IOPTE_IOID_Mask);
 
+	pr_info("IOMMU: Using weak ordering for fixed mapping\n");
+
 	for (uaddr = 0; uaddr < fsize; uaddr += (1 << 24)) {
 		/* Don't touch the dynamic region */
 		ioaddr = uaddr + fbase;

@@ -1037,9 +1119,6 @@ static int __init cell_iommu_fixed_mappi
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_fixed_ops = dma_direct_ops;
-	dma_iommu_fixed_ops.set_dma_mask = dma_set_mask_and_switch;
-
 	dma_iommu_ops.set_dma_mask = dma_set_mask_and_switch;
 	set_pci_dma_ops(&dma_iommu_ops);
 

@@ -22,3 +22,15 @@ ready and available in memory.  The DMA 
 could race with data DMA.  Mapping the memory used for completion
 indications with DMA_ATTR_WRITE_BARRIER would prevent the race.
 
+
+DMA_ATTR_STRONG_ORDERING
+----------------------
+
+DMA_ATTR_STRONG_ORDERING specifies that previous reads and writes are
+performed in the order in which they're received by the IOMMU; thus
+reads and writes may not pass each other.
+
+Platforms that are strongly ordered by default will ignore this new
+attribute but platforms that are weakly ordered by default should not
+ignore this new attribute. Instead, they should return an error if a
+strongly ordered mapping cannot be used when one is requested.

@@ -12,6 +12,7 @@
  */
 enum dma_attr {
 	DMA_ATTR_WRITE_BARRIER,
+	DMA_ATTR_STRONG_ORDERING,
 	DMA_ATTR_MAX,
 };
 

@@ -186,7 +186,8 @@ static unsigned long iommu_range_alloc(s
 static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 			      void *page, unsigned int npages,
 			      enum dma_data_direction direction,
-			      unsigned long mask, unsigned int align_order)
+			      unsigned long mask, unsigned int align_order,
+			      struct dma_attrs *attrs)
 {
 	unsigned long entry, flags;
 	dma_addr_t ret = DMA_ERROR_CODE;

@@ -205,7 +206,7 @@ static dma_addr_t iommu_alloc(struct dev
 
 	/* Put the TCEs in the HW table */
 	ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
-			 direction);
+			 direction, attrs);
 
 
 	/* Flush/invalidate TLB caches if necessary */

@@ -336,7 +337,8 @@ int iommu_map_sg(struct device *dev, str
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
-		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK, direction);
+		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK,
+				 direction, attrs);
 
 		/* If we are in an open segment, try merging */
 		if (segstart != s) {

@@ -573,7 +575,8 @@ dma_addr_t iommu_map_single(struct devic
 			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
 
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
-					 mask >> IOMMU_PAGE_SHIFT, align);
+					 mask >> IOMMU_PAGE_SHIFT, align,
+					 attrs);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
 				printk(KERN_INFO "iommu_alloc failed, "

@@ -642,7 +645,7 @@ void *iommu_alloc_coherent(struct device
 	nio_pages = size >> IOMMU_PAGE_SHIFT;
 	io_order = get_iommu_order(size);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
-			      mask >> IOMMU_PAGE_SHIFT, io_order);
+			      mask >> IOMMU_PAGE_SHIFT, io_order, NULL);
 	if (mapping == DMA_ERROR_CODE) {
 		free_pages((unsigned long)ret, order);
 		return NULL;

@@ -173,7 +173,8 @@ static void invalidate_tce_cache(struct 
 }
 
 static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
-		unsigned long uaddr, enum dma_data_direction direction)
+		unsigned long uaddr, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 	unsigned long *io_pte, base_pte;

@@ -519,7 +520,7 @@ cell_iommu_setup_window(struct cbe_iommu
 
 	__set_bit(0, window->table.it_map);
 	tce_build_cell(&window->table, window->table.it_offset, 1,
-		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE);
+		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE, NULL);
 	window->table.it_hint = window->table.it_blocksize;
 
 	return window;

@@ -42,7 +42,8 @@
 #include <asm/iseries/iommu.h>
 
 static void tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
-		unsigned long uaddr, enum dma_data_direction direction)
+		unsigned long uaddr, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	u64 rc;
 	u64 tce, rpn;

@@ -85,7 +85,8 @@ static int iommu_table_iobmap_inited;
 
 static void iobmap_build(struct iommu_table *tbl, long index,
 			 long npages, unsigned long uaddr,
-			 enum dma_data_direction direction)
+			 enum dma_data_direction direction,
+			 struct dma_attrs *attrs)
 {
 	u32 *ip;
 	u32 rpn;

@@ -50,7 +50,8 @@
 
 static void tce_build_pSeries(struct iommu_table *tbl, long index,
 			      long npages, unsigned long uaddr,
-			      enum dma_data_direction direction)
+			      enum dma_data_direction direction,
+			      struct dma_attrs *attrs)
 {
 	u64 proto_tce;
 	u64 *tcep;

@@ -95,7 +96,8 @@ static unsigned long tce_get_pseries(str
 
 static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				long npages, unsigned long uaddr,
-				enum dma_data_direction direction)
+				enum dma_data_direction direction,
+				struct dma_attrs *attrs)
 {
 	u64 rc;
 	u64 proto_tce, tce;

@@ -127,7 +129,8 @@ static DEFINE_PER_CPU(u64 *, tce_page) =
 
 static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
-				     enum dma_data_direction direction)
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
 {
 	u64 rc;
 	u64 proto_tce;

@@ -137,7 +140,7 @@ static void tce_buildmulti_pSeriesLP(str
 
 	if (npages == 1)
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-					   direction);
+					   direction, attrs);
 
 	tcep = __get_cpu_var(tce_page);
 

@@ -149,7 +152,7 @@ static void tce_buildmulti_pSeriesLP(str
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep)
 			return tce_build_pSeriesLP(tbl, tcenum, npages,
-						   uaddr, direction);
+						   uaddr, direction, attrs);
 		__get_cpu_var(tce_page) = tcep;
 	}
 

@@ -149,7 +149,8 @@ static void dart_flush(struct iommu_tabl
 
 static void dart_build(struct iommu_table *tbl, long index,
 		       long npages, unsigned long uaddr,
-		       enum dma_data_direction direction)
+		       enum dma_data_direction direction,
+		       struct dma_attrs *attrs)
 {
 	unsigned int *dp;
 	unsigned int rpn;

@@ -80,7 +80,8 @@ struct machdep_calls {
 				     long index,
 				     long npages,
 				     unsigned long uaddr,
-				     enum dma_data_direction direction);
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs);
 	void		(*tce_free)(struct iommu_table *tbl,
 				    long index,
 				    long npages);