[PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[FUJITA Tomonori]

This is the second version of the patchset to convert POWERPC to use
asm-generic/dma-mapping-common.h:

http://marc.info/?l=linux-kernel&m=124840628128189&w=2

There are some minor changes since the first version are:

- removed unused CONFIG_PPC_NEED_DMA_SYNC_OPS [5/7] (Becky pointed
  out).

- added Becky's Acked-by

- added two new patches ([6/7] and [7/7]). [6/7] fixes SWIOTLB's
  dma_mapping_error(). [7/7] addes CONFIG_DMA_API_DEBUG support.


This is on the top of my swiotlb cleanup patchset:

http://marc.info/?l=linuxppc-embedded&m=124718920320951&w=2


The above swiotlb patchset was merged in -tip so I think that merging
this patchset via -tip too is the easiest way to handle this patchset.

The patchset also is available via a git tree:

git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc


=
 arch/powerpc/Kconfig                       |    7 +-
 arch/powerpc/include/asm/device.h          |    7 +-
 arch/powerpc/include/asm/dma-mapping.h     |  318 +++-------------------------
 arch/powerpc/include/asm/pci.h             |    4 +-
 arch/powerpc/include/asm/swiotlb.h         |    8 +-
 arch/powerpc/kernel/dma-iommu.c            |    2 +-
 arch/powerpc/kernel/dma-swiotlb.c          |   53 ++---
 arch/powerpc/kernel/dma.c                  |   13 +-
 arch/powerpc/kernel/ibmebus.c              |    2 +-
 arch/powerpc/kernel/pci-common.c           |    6 +-
 arch/powerpc/kernel/vio.c                  |    2 +-
 arch/powerpc/platforms/85xx/mpc8536_ds.c   |    3 +-
 arch/powerpc/platforms/85xx/mpc85xx_ds.c   |    3 +-
 arch/powerpc/platforms/85xx/mpc85xx_mds.c  |    3 +-
 arch/powerpc/platforms/86xx/mpc86xx_hpcn.c |    3 +-
 arch/powerpc/platforms/cell/iommu.c        |    2 +-
 arch/powerpc/platforms/ps3/system-bus.c    |    4 +-
 include/linux/dma-mapping.h                |    1 +
 18 files changed, 89 insertions(+), 352 deletions(-)

[PATCH -v2 1/7] powerpc: remove addr_needs_map in struct dma_mapping_ops

[FUJITA Tomonori]

This patch adds max_direct_dma_addr to struct dev_archdata to remove
addr_needs_map in struct dma_mapping_ops. It also converts
dma_capable() to use max_direct_dma_addr.

max_direct_dma_addr is initialized in pci_dma_dev_setup_swiotlb(),
called via ppc_md.pci_dma_dev_setup hook.

For further information:
http://marc.info/?t=124719060200001&r=1&w=2

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Becky Bruce <beckyb@kernel.crashing.org>
---
 arch/powerpc/include/asm/device.h          |    3 ++
 arch/powerpc/include/asm/dma-mapping.h     |    8 +++---
 arch/powerpc/include/asm/swiotlb.h         |    5 +--
 arch/powerpc/kernel/dma-swiotlb.c          |   36 +++++++++++----------------
 arch/powerpc/platforms/85xx/mpc8536_ds.c   |    1 +
 arch/powerpc/platforms/85xx/mpc85xx_ds.c   |    1 +
 arch/powerpc/platforms/85xx/mpc85xx_mds.c  |    1 +
 arch/powerpc/platforms/86xx/mpc86xx_hpcn.c |    1 +
 8 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 7d2277c..0086f8d 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -16,6 +16,9 @@ struct dev_archdata {
 	/* DMA operations on that device */
 	struct dma_mapping_ops	*dma_ops;
 	void			*dma_data;
+#ifdef CONFIG_SWIOTLB
+	dma_addr_t		max_direct_dma_addr;
+#endif
 };
 
 static inline void dev_archdata_set_node(struct dev_archdata *ad,
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 0c34371..1765c37 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -87,8 +87,6 @@ struct dma_mapping_ops {
 				dma_addr_t dma_address, size_t size,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs);
-	int		(*addr_needs_map)(struct device *dev, dma_addr_t addr,
-				size_t size);
 #ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
 	void            (*sync_single_range_for_cpu)(struct device *hwdev,
 				dma_addr_t dma_handle, unsigned long offset,
@@ -426,10 +424,12 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
+#ifdef CONFIG_SWIOTLB
+	struct dev_archdata *sd = &dev->archdata;
 
-	if (ops->addr_needs_map && ops->addr_needs_map(dev, addr, size))
+	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
 		return 0;
+#endif
 
 	if (!dev->dma_mask)
 		return 0;
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 30891d6..31e0e43 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -16,12 +16,11 @@
 extern struct dma_mapping_ops swiotlb_dma_ops;
 extern struct dma_mapping_ops swiotlb_pci_dma_ops;
 
-int swiotlb_arch_address_needs_mapping(struct device *, dma_addr_t,
-				       size_t size);
-
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
 extern unsigned int ppc_swiotlb_enable;
 int __init swiotlb_setup_bus_notifier(void);
 
+extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev);
+
 #endif /* __ASM_SWIOTLB_H */
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index e8a57de..c9f6a30 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -25,26 +25,6 @@ int swiotlb __read_mostly;
 unsigned int ppc_swiotlb_enable;
 
 /*
- * Determine if an address is reachable by a pci device, or if we must bounce.
- */
-static int
-swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
-{
-	dma_addr_t max;
-	struct pci_controller *hose;
-	struct pci_dev *pdev = to_pci_dev(hwdev);
-
-	hose = pci_bus_to_host(pdev->bus);
-	max = hose->dma_window_base_cur + hose->dma_window_size;
-
-	/* check that we're within mapped pci window space */
-	if ((addr + size > max) | (addr < hose->dma_window_base_cur))
-		return 1;
-
-	return 0;
-}
-
-/*
  * At the moment, all platforms that use this code only require
  * swiotlb to be used if we're operating on HIGHMEM.  Since
  * we don't ever call anything other than map_sg, unmap_sg,
@@ -73,22 +53,36 @@ struct dma_mapping_ops swiotlb_pci_dma_ops = {
 	.dma_supported = swiotlb_dma_supported,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
-	.addr_needs_map = swiotlb_pci_addr_needs_map,
 	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
 	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = swiotlb_sync_sg_for_device
 };
 
+void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
+{
+	struct pci_controller *hose;
+	struct dev_archdata *sd;
+
+	hose = pci_bus_to_host(pdev->bus);
+	sd = &pdev->dev.archdata;
+	sd->max_direct_dma_addr =
+		hose->dma_window_base_cur + hose->dma_window_size;
+}
+
 static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
 				  unsigned long action, void *data)
 {
 	struct device *dev = data;
+	struct dev_archdata *sd;
 
 	/* We are only intereted in device addition */
 	if (action != BUS_NOTIFY_ADD_DEVICE)
 		return 0;
 
+	sd = &dev->archdata;
+	sd->max_direct_dma_addr = 0;
+
 	/* May need to bounce if the device can't address all of DRAM */
 	if (dma_get_mask(dev) < lmb_end_of_DRAM())
 		set_dma_ops(dev, &swiotlb_dma_ops);
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 055ff41..bf052c0 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -97,6 +97,7 @@ static void __init mpc8536_ds_setup_arch(void)
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 849c0ac..c6f92cc 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -193,6 +193,7 @@ static void __init mpc85xx_ds_setup_arch(void)
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index bfb3283..e1f82f8 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -255,6 +255,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
 }
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 6632702..8032301 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -106,6 +106,7 @@ mpc86xx_hpcn_setup_arch(void)
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
 }
-- 
1.6.0.6

[PATCH -v2 2/7] powerpc: remove swiotlb_pci_dma_ops

[FUJITA Tomonori]

Now swiotlb_pci_dma_ops is identical to swiotlb_dma_ops; we can use
swiotlb_dma_ops with any devices. This removes swiotlb_pci_dma_ops.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Becky Bruce <beckyb@kernel.crashing.org>
---
 arch/powerpc/include/asm/swiotlb.h         |    1 -
 arch/powerpc/kernel/dma-swiotlb.c          |   14 --------------
 arch/powerpc/platforms/85xx/mpc8536_ds.c   |    2 +-
 arch/powerpc/platforms/85xx/mpc85xx_ds.c   |    2 +-
 arch/powerpc/platforms/85xx/mpc85xx_mds.c  |    2 +-
 arch/powerpc/platforms/86xx/mpc86xx_hpcn.c |    2 +-
 6 files changed, 4 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 31e0e43..21ce0a3 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -14,7 +14,6 @@
 #include <linux/swiotlb.h>
 
 extern struct dma_mapping_ops swiotlb_dma_ops;
-extern struct dma_mapping_ops swiotlb_pci_dma_ops;
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index c9f6a30..ca141e1 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -45,20 +45,6 @@ struct dma_mapping_ops swiotlb_dma_ops = {
 	.sync_sg_for_device = swiotlb_sync_sg_for_device
 };
 
-struct dma_mapping_ops swiotlb_pci_dma_ops = {
-	.alloc_coherent = dma_direct_alloc_coherent,
-	.free_coherent = dma_direct_free_coherent,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.dma_supported = swiotlb_dma_supported,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
-	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device
-};
-
 void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index bf052c0..004b7d3 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -96,7 +96,7 @@ static void __init mpc8536_ds_setup_arch(void)
 #ifdef CONFIG_SWIOTLB
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index c6f92cc..544011a 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -192,7 +192,7 @@ static void __init mpc85xx_ds_setup_arch(void)
 #ifdef CONFIG_SWIOTLB
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index e1f82f8..5ea1b68 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -254,7 +254,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 #ifdef CONFIG_SWIOTLB
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 8032301..2aa69a6 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -105,7 +105,7 @@ mpc86xx_hpcn_setup_arch(void)
 #ifdef CONFIG_SWIOTLB
 	if (lmb_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_pci_dma_ops);
+		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
 	}
 #endif
-- 
1.6.0.6

[PATCH -v2 3/7] add set_dma_mask hook to struct dma_map_ops

[FUJITA Tomonori]

POWERPC needs this hook. SPARC could use it too.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Becky Bruce <beckyb@kernel.crashing.org>
---
 include/linux/dma-mapping.h |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index c0f6c3c..91b7618 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -58,6 +58,7 @@ struct dma_map_ops {
 				   enum dma_data_direction dir);
 	int (*mapping_error)(struct device *dev, dma_addr_t dma_addr);
 	int (*dma_supported)(struct device *dev, u64 mask);
+	int (*set_dma_mask)(struct device *dev, u64 mask);
 	int is_phys;
 };
 
-- 
1.6.0.6

[PATCH -v2 4/7] powerpc: use dma_map_ops struct

[FUJITA Tomonori]

This converts uses dma_map_ops struct (in include/linux/dma-mapping.h)
instead of POWERPC homegrown dma_mapping_ops.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Becky Bruce <beckyb@kernel.crashing.org>
---
 arch/powerpc/include/asm/device.h       |    4 +-
 arch/powerpc/include/asm/dma-mapping.h  |   84 ++++++++-----------------------
 arch/powerpc/include/asm/pci.h          |    4 +-
 arch/powerpc/include/asm/swiotlb.h      |    2 +-
 arch/powerpc/kernel/dma-iommu.c         |    2 +-
 arch/powerpc/kernel/dma-swiotlb.c       |    2 +-
 arch/powerpc/kernel/dma.c               |    2 +-
 arch/powerpc/kernel/ibmebus.c           |    2 +-
 arch/powerpc/kernel/pci-common.c        |    6 +-
 arch/powerpc/kernel/vio.c               |    2 +-
 arch/powerpc/platforms/cell/iommu.c     |    2 +-
 arch/powerpc/platforms/ps3/system-bus.c |    4 +-
 12 files changed, 37 insertions(+), 79 deletions(-)

diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 0086f8d..67fcd7f 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_POWERPC_DEVICE_H
 #define _ASM_POWERPC_DEVICE_H
 
-struct dma_mapping_ops;
+struct dma_map_ops;
 struct device_node;
 
 struct dev_archdata {
@@ -14,7 +14,7 @@ struct dev_archdata {
 	struct device_node	*of_node;
 
 	/* DMA operations on that device */
-	struct dma_mapping_ops	*dma_ops;
+	struct dma_map_ops	*dma_ops;
 	void			*dma_data;
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 1765c37..8ca2b51 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -64,56 +64,14 @@ static inline unsigned long device_to_mask(struct device *dev)
 }
 
 /*
- * 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);
-	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
-				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,
-				struct dma_attrs *attrs);
-	int		(*dma_supported)(struct device *dev, u64 mask);
-	int		(*set_dma_mask)(struct device *dev, u64 dma_mask);
-	dma_addr_t 	(*map_page)(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	void		(*unmap_page)(struct device *dev,
-				dma_addr_t dma_address, size_t size,
-				enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
-	void            (*sync_single_range_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size,
-				enum dma_data_direction direction);
-	void            (*sync_single_range_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size,
-				enum dma_data_direction direction);
-	void            (*sync_sg_for_cpu)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				enum dma_data_direction direction);
-	void            (*sync_sg_for_device)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				enum dma_data_direction direction);
-#endif
-};
-
-/*
  * Available generic sets of operations
  */
 #ifdef CONFIG_PPC64
-extern struct dma_mapping_ops dma_iommu_ops;
+extern struct dma_map_ops dma_iommu_ops;
 #endif
-extern struct dma_mapping_ops dma_direct_ops;
+extern struct dma_map_ops dma_direct_ops;
 
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_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
@@ -126,14 +84,14 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 	return dev->archdata.dma_ops;
 }
 
-static inline void set_dma_ops(struct device *dev, struct dma_mapping_ops *ops)
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 {
 	dev->archdata.dma_ops = ops;
 }
 
 static inline int dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	if (unlikely(dma_ops == NULL))
 		return 0;
@@ -147,7 +105,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	if (unlikely(dma_ops == NULL))
 		return -EIO;
@@ -161,7 +119,7 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 
 /*
  * map_/unmap_single actually call through to map/unmap_page now that all the
- * dma_mapping_ops have been converted over. We just have to get the page and
+ * dma_map_ops have been converted over. We just have to get the page and
  * offset to pass through to map_page
  */
 static inline dma_addr_t dma_map_single_attrs(struct device *dev,
@@ -170,7 +128,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 					      enum dma_data_direction direction,
 					      struct dma_attrs *attrs)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -185,7 +143,7 @@ static inline void dma_unmap_single_attrs(struct device *dev,
 					  enum dma_data_direction direction,
 					  struct dma_attrs *attrs)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -198,7 +156,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 					    enum dma_data_direction direction,
 					    struct dma_attrs *attrs)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -211,7 +169,7 @@ static inline void dma_unmap_page_attrs(struct device *dev,
 					enum dma_data_direction direction,
 					struct dma_attrs *attrs)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -222,7 +180,7 @@ 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);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 	return dma_ops->map_sg(dev, sg, nents, direction, attrs);
@@ -234,7 +192,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev,
 				      enum dma_data_direction direction,
 				      struct dma_attrs *attrs)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 	dma_ops->unmap_sg(dev, sg, nhwentries, direction, attrs);
@@ -243,7 +201,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev,
 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);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
@@ -252,7 +210,7 @@ static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 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);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
@@ -304,7 +262,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -317,7 +275,7 @@ static inline void dma_sync_single_for_device(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -330,7 +288,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -342,7 +300,7 @@ static inline void dma_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -354,7 +312,7 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, unsigned long offset, size_t size,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
@@ -367,7 +325,7 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 		dma_addr_t dma_handle, unsigned long offset, size_t size,
 		enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index d9483c5..7ae46d7 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -61,8 +61,8 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 
 #ifdef CONFIG_PCI
-extern void set_pci_dma_ops(struct dma_mapping_ops *dma_ops);
-extern struct dma_mapping_ops *get_pci_dma_ops(void);
+extern void set_pci_dma_ops(struct dma_map_ops *dma_ops);
+extern struct dma_map_ops *get_pci_dma_ops(void);
 #else	/* CONFIG_PCI */
 #define set_pci_dma_ops(d)
 #define get_pci_dma_ops()	NULL
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 21ce0a3..8979d4c 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -13,7 +13,7 @@
 
 #include <linux/swiotlb.h>
 
-extern struct dma_mapping_ops swiotlb_dma_ops;
+extern struct dma_map_ops swiotlb_dma_ops;
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 2983ada..87ddb3f 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -89,7 +89,7 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 1;
 }
 
-struct dma_mapping_ops dma_iommu_ops = {
+struct dma_map_ops dma_iommu_ops = {
 	.alloc_coherent	= dma_iommu_alloc_coherent,
 	.free_coherent	= dma_iommu_free_coherent,
 	.map_sg		= dma_iommu_map_sg,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index ca141e1..d1143a6 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -31,7 +31,7 @@ unsigned int ppc_swiotlb_enable;
  * map_page, and unmap_page on highmem, use normal dma_ops
  * for everything else.
  */
-struct dma_mapping_ops swiotlb_dma_ops = {
+struct dma_map_ops swiotlb_dma_ops = {
 	.alloc_coherent = dma_direct_alloc_coherent,
 	.free_coherent = dma_direct_free_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 20a60d6..3e8bb9a 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -140,7 +140,7 @@ static inline void dma_direct_sync_single_range(struct device *dev,
 }
 #endif
 
-struct dma_mapping_ops dma_direct_ops = {
+struct dma_map_ops dma_direct_ops = {
 	.alloc_coherent	= dma_direct_alloc_coherent,
 	.free_coherent	= dma_direct_free_coherent,
 	.map_sg		= dma_direct_map_sg,
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 6e3f624..a4c8b38 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -127,7 +127,7 @@ static int ibmebus_dma_supported(struct device *dev, u64 mask)
 	return 1;
 }
 
-static struct dma_mapping_ops ibmebus_dma_ops = {
+static struct dma_map_ops ibmebus_dma_ops = {
 	.alloc_coherent = ibmebus_alloc_coherent,
 	.free_coherent  = ibmebus_free_coherent,
 	.map_sg         = ibmebus_map_sg,
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 5a56e97..7585f1f 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -50,14 +50,14 @@ resource_size_t isa_mem_base;
 unsigned int ppc_pci_flags = 0;
 
 
-static struct dma_mapping_ops *pci_dma_ops = &dma_direct_ops;
+static struct dma_map_ops *pci_dma_ops = &dma_direct_ops;
 
-void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
+void set_pci_dma_ops(struct dma_map_ops *dma_ops)
 {
 	pci_dma_ops = dma_ops;
 }
 
-struct dma_mapping_ops *get_pci_dma_ops(void)
+struct dma_map_ops *get_pci_dma_ops(void)
 {
 	return pci_dma_ops;
 }
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 819e59f..bc7b41e 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -601,7 +601,7 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
-struct dma_mapping_ops vio_dma_mapping_ops = {
+struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc_coherent = vio_dma_iommu_alloc_coherent,
 	.free_coherent  = vio_dma_iommu_free_coherent,
 	.map_sg         = vio_dma_iommu_map_sg,
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 5b34fc2..416db17 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -642,7 +642,7 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask)
 
 static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
 
-struct dma_mapping_ops dma_iommu_fixed_ops = {
+struct dma_map_ops dma_iommu_fixed_ops = {
 	.alloc_coherent = dma_fixed_alloc_coherent,
 	.free_coherent  = dma_fixed_free_coherent,
 	.map_sg         = dma_fixed_map_sg,
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 3f763c5..02ddcc2 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -694,7 +694,7 @@ static int ps3_dma_supported(struct device *_dev, u64 mask)
 	return mask >= DMA_BIT_MASK(32);
 }
 
-static struct dma_mapping_ops ps3_sb_dma_ops = {
+static struct dma_map_ops ps3_sb_dma_ops = {
 	.alloc_coherent = ps3_alloc_coherent,
 	.free_coherent = ps3_free_coherent,
 	.map_sg = ps3_sb_map_sg,
@@ -704,7 +704,7 @@ static struct dma_mapping_ops ps3_sb_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 };
 
-static struct dma_mapping_ops ps3_ioc0_dma_ops = {
+static struct dma_map_ops ps3_ioc0_dma_ops = {
 	.alloc_coherent = ps3_alloc_coherent,
 	.free_coherent = ps3_free_coherent,
 	.map_sg = ps3_ioc0_map_sg,
-- 
1.6.0.6

[PATCH -v2 5/7] powerpc: use asm-generic/dma-mapping-common.h

[FUJITA Tomonori]

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Becky Bruce <beckyb@kernel.crashing.org>
---
 arch/powerpc/Kconfig                   |    6 +-
 arch/powerpc/include/asm/dma-mapping.h |  242 +-------------------------------
 2 files changed, 7 insertions(+), 241 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d00131c..fb3f4ff 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -120,7 +120,7 @@ config PPC
 	select HAVE_KRETPROBES
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_LMB
-	select HAVE_DMA_ATTRS if PPC64
+	select HAVE_DMA_ATTRS
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
@@ -307,10 +307,6 @@ config SWIOTLB
 	  platforms where the size of a physical address is larger
 	  than the bus address.  Not all platforms support this.
 
-config PPC_NEED_DMA_SYNC_OPS
-	def_bool y
-	depends on (NOT_COHERENT_CACHE || SWIOTLB)
-
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC)
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 8ca2b51..91217e4 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
@@ -89,6 +90,11 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
+/* this will be removed soon */
+#define flush_write_buffers()
+
+#include <asm-generic/dma-mapping-common.h>
+
 static inline int dma_supported(struct device *dev, u64 mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
@@ -117,87 +123,6 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 
-/*
- * map_/unmap_single actually call through to map/unmap_page now that all the
- * dma_map_ops have been converted over. We just have to get the page and
- * offset to pass through to map_page
- */
-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_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
-				 (unsigned long)cpu_addr % PAGE_SIZE, 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_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	dma_ops->unmap_page(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_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->map_page(dev, 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_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	dma_ops->unmap_page(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_map_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_map_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)
 {
@@ -216,161 +141,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 	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)
-{
-	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)
-{
-	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)
-{
-	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)
-{
-	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)
-{
-	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)
-{
-	dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
-}
-
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_cpu)
-		dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
-					   size, direction);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_device)
-		dma_ops->sync_single_range_for_device(dev, dma_handle,
-					      0, size, direction);
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_sg_for_cpu)
-		dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
-}
-
-static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_sg_for_device)
-		dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_cpu)
-		dma_ops->sync_single_range_for_cpu(dev, dma_handle,
-					   offset, size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_device)
-		dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
-					      size, direction);
-}
-#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-}
-#endif
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 #ifdef CONFIG_PPC64
-- 
1.6.0.6

[PATCH -v2 6/7] powerpc: handle SWIOTLB mapping error properly

[FUJITA Tomonori]

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
 arch/powerpc/include/asm/dma-mapping.h |    5 +++++
 arch/powerpc/kernel/dma-swiotlb.c      |    3 ++-
 2 files changed, 7 insertions(+), 1 deletions(-)

diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 91217e4..4bd41b4 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -143,6 +143,11 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	if (dma_ops->mapping_error)
+		return dma_ops->mapping_error(dev, dma_addr);
+
 #ifdef CONFIG_PPC64
 	return (dma_addr == DMA_ERROR_CODE);
 #else
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index d1143a6..e96cbbd 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -42,7 +42,8 @@ struct dma_map_ops swiotlb_dma_ops = {
 	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
 	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device
+	.sync_sg_for_device = swiotlb_sync_sg_for_device,
+	.mapping_error = swiotlb_dma_mapping_error,
 };
 
 void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
-- 
1.6.0.6

[PATCH -v2 7/7] powerpc: add CONFIG_DMA_API_DEBUG support

[FUJITA Tomonori]

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
 arch/powerpc/Kconfig                   |    1 +
 arch/powerpc/include/asm/dma-mapping.h |   11 ++++++++++-
 arch/powerpc/kernel/dma.c              |   11 +++++++++++
 3 files changed, 22 insertions(+), 1 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fb3f4ff..4459b78 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -121,6 +121,7 @@ config PPC
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_LMB
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_API_DEBUG
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 4bd41b4..cb2ca41 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -127,9 +127,15 @@ static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+	void *cpu_addr;
 
 	BUG_ON(!dma_ops);
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+
+	cpu_addr = dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+
+	return cpu_addr;
 }
 
 static inline void dma_free_coherent(struct device *dev, size_t size,
@@ -138,6 +144,9 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+
 	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
 }
 
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 3e8bb9a..c6d730e 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -7,6 +7,7 @@
 
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-debug.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
 
@@ -156,3 +157,13 @@ struct dma_map_ops dma_direct_ops = {
 #endif
 };
 EXPORT_SYMBOL(dma_direct_ops);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init dma_init(void)
+{
+       dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+
+       return 0;
+}
+fs_initcall(dma_init);
-- 
1.6.0.6

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Wed, 2009-08-05 at 14:08 +0900, FUJITA Tomonori wrote:

> The above swiotlb patchset was merged in -tip so I think that merging
> this patchset via -tip too is the easiest way to handle this patchset.
> 
> The patchset also is available via a git tree:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc

Hi !

While I generally agree here with the patches, I'm not sure it should be
merged via -tip since it mostly touches arch/powerpc files (and I need
to review it a bit more carefully, hopefully you'll have Ack's hitting
your mailbox later today).

Ben.

> =
>  arch/powerpc/Kconfig                       |    7 +-
>  arch/powerpc/include/asm/device.h          |    7 +-
>  arch/powerpc/include/asm/dma-mapping.h     |  318 +++-------------------------
>  arch/powerpc/include/asm/pci.h             |    4 +-
>  arch/powerpc/include/asm/swiotlb.h         |    8 +-
>  arch/powerpc/kernel/dma-iommu.c            |    2 +-
>  arch/powerpc/kernel/dma-swiotlb.c          |   53 ++---
>  arch/powerpc/kernel/dma.c                  |   13 +-
>  arch/powerpc/kernel/ibmebus.c              |    2 +-
>  arch/powerpc/kernel/pci-common.c           |    6 +-
>  arch/powerpc/kernel/vio.c                  |    2 +-
>  arch/powerpc/platforms/85xx/mpc8536_ds.c   |    3 +-
>  arch/powerpc/platforms/85xx/mpc85xx_ds.c   |    3 +-
>  arch/powerpc/platforms/85xx/mpc85xx_mds.c  |    3 +-
>  arch/powerpc/platforms/86xx/mpc86xx_hpcn.c |    3 +-
>  arch/powerpc/platforms/cell/iommu.c        |    2 +-
>  arch/powerpc/platforms/ps3/system-bus.c    |    4 +-
>  include/linux/dma-mapping.h                |    1 +
>  18 files changed, 89 insertions(+), 352 deletions(-)
> 
> 
> 
> 
> 
> 
> 
> 

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-13 at 16:44 +1000, Benjamin Herrenschmidt wrote:
> On Wed, 2009-08-05 at 14:08 +0900, FUJITA Tomonori wrote:
> 
> > The above swiotlb patchset was merged in -tip so I think that merging
> > this patchset via -tip too is the easiest way to handle this patchset.
> > 
> > The patchset also is available via a git tree:
> > 
> > git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc
> 
> Hi !
> 
> While I generally agree here with the patches, I'm not sure it should be
> merged via -tip since it mostly touches arch/powerpc files (and I need
> to review it a bit more carefully, hopefully you'll have Ack's hitting
> your mailbox later today).

Maybe best is that I pull your series too. Note that your patch clashes
with Takashi's addition of dma_mmap_coherent() :

http://patchwork.ozlabs.org/patch/29595/

Can you sort that out with Takashi as I'd like his patch in -next soon
too.

Cheers,
Ben.

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Takashi Iwai]

At Thu, 13 Aug 2009 16:51:53 +1000,
Benjamin Herrenschmidt wrote:
> 
> On Thu, 2009-08-13 at 16:44 +1000, Benjamin Herrenschmidt wrote:
> > On Wed, 2009-08-05 at 14:08 +0900, FUJITA Tomonori wrote:
> > 
> > > The above swiotlb patchset was merged in -tip so I think that merging
> > > this patchset via -tip too is the easiest way to handle this patchset.
> > > 
> > > The patchset also is available via a git tree:
> > > 
> > > git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc
> > 
> > Hi !
> > 
> > While I generally agree here with the patches, I'm not sure it should be
> > merged via -tip since it mostly touches arch/powerpc files (and I need
> > to review it a bit more carefully, hopefully you'll have Ack's hitting
> > your mailbox later today).
> 
> Maybe best is that I pull your series too. Note that your patch clashes
> with Takashi's addition of dma_mmap_coherent() :
> 
> http://patchwork.ozlabs.org/patch/29595/
> 
> Can you sort that out with Takashi as I'd like his patch in -next soon
> too.

I'm willing to rebase my patches to the generic dma_ops, so feel free
to pull it first.

It might need to add mmap_coherent op to all platforms when generic
dma ops is used.  This would be more volume but less hackish than the
previous version, OTOH :)


thanks,

Takashi

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-13 at 09:11 +0200, Takashi Iwai wrote:
> I'm willing to rebase my patches to the generic dma_ops, so feel free
> to pull it first.

I think I'll end up pulling Ingo's iommu branch into powerpc-next to
get Fujita stuff, so if you rebase on top of his stuff, it will come
along just fine.

> It might need to add mmap_coherent op to all platforms when generic
> dma ops is used.  This would be more volume but less hackish than the
> previous version, OTOH :)
> 
Right :-)

Cheers,
Ben.

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Takashi Iwai]

At Thu, 13 Aug 2009 18:07:57 +1000,
Benjamin Herrenschmidt wrote:
> 
> On Thu, 2009-08-13 at 09:11 +0200, Takashi Iwai wrote:
> > I'm willing to rebase my patches to the generic dma_ops, so feel free
> > to pull it first.
> 
> I think I'll end up pulling Ingo's iommu branch into powerpc-next to
> get Fujita stuff, so if you rebase on top of his stuff, it will come
> along just fine.

OK, I'll work on it later.


thanks,

Takashi

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[FUJITA Tomonori]

On Thu, 13 Aug 2009 15:48:42 +1000
Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> On Wed, 2009-08-05 at 14:08 +0900, FUJITA Tomonori wrote:
> 
> > The above swiotlb patchset was merged in -tip so I think that merging
> > this patchset via -tip too is the easiest way to handle this patchset.
> > 
> > The patchset also is available via a git tree:
> > 
> > git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc
> 
> Hi !
> 
> While I generally agree here with the patches, I'm not sure it should be
> merged via -tip since it mostly touches arch/powerpc files (and I need
> to review it a bit more carefully, hopefully you'll have Ack's hitting
> your mailbox later today).

Thanks!

This patchset depends on my swiotlb cleanup patchset:

git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git swiotlb

http://marc.info/?l=linux-ia64&m=124718816520156&w=2


My swiotlb cleanup patchset has been in -tip. It might be easier to
merge both the swiotlb patchset and this patchset in powerpc tree?

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Ingo Molnar]

* FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> wrote:

> On Thu, 13 Aug 2009 15:48:42 +1000
> Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:
> 
> > On Wed, 2009-08-05 at 14:08 +0900, FUJITA Tomonori wrote:
> > 
> > > The above swiotlb patchset was merged in -tip so I think that merging
> > > this patchset via -tip too is the easiest way to handle this patchset.
> > > 
> > > The patchset also is available via a git tree:
> > > 
> > > git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc
> > 
> > Hi !
> > 
> > While I generally agree here with the patches, I'm not sure it should be
> > merged via -tip since it mostly touches arch/powerpc files (and I need
> > to review it a bit more carefully, hopefully you'll have Ack's hitting
> > your mailbox later today).
> 
> Thanks!
> 
> This patchset depends on my swiotlb cleanup patchset:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git swiotlb
> 
> http://marc.info/?l=linux-ia64&m=124718816520156&w=2
> 
> My swiotlb cleanup patchset has been in -tip. It might be easier 
> to merge both the swiotlb patchset and this patchset in powerpc 
> tree?

Ben, what's your preference? I waited for your reaction with these 
bits, i.e. they are not in tip:core/iommu yet.

One variant would be what Fujita suggested: you could pull 
core/iommu as a basis (it's a well-tested, problem-free tree at the 
moment, with no big risky items), and then pull/apply the powerpc 
specific bits from Fujita.

A second variant would be that we could pull these bits into 
core/iommu ... albeit you are right that the PowerPC tree is much 
better at testing PowerPC patches.

A third variant would be to wait with these bits until the swiotlb 
bits in core/iommu hit upstream. This would increase patch latency.

Any of these variants is good to me. What Fujita suggests seems to 
be the best to me: #1 gets us the most testing and the lowest 
latency - at the cost of tree dependency. We wont rebase core/iommu.

[ We've got three good tree properties: "tree independence",
  "good testing", "low patch latency", but we cannot have all
  three at once, we must pick two of them ;-) ]

	Ingo

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

> Ben, what's your preference? I waited for your reaction with these 
> bits, i.e. they are not in tip:core/iommu yet.

Oh I though they were... discard my previous private mail about
missing Ack's then :-)

I'll review them more in depth hopefully tomorrow but they look good.

> One variant would be what Fujita suggested: you could pull 
> core/iommu as a basis (it's a well-tested, problem-free tree at the 
> moment, with no big risky items), and then pull/apply the powerpc 
> specific bits from Fujita.

Or we can have the patches in core/iommu and I pull the whole thing
in powerpc-next. My main concern isn't which tree they go through but
that they are in powerpc-next for better testing.

Cheers,
Ben.

> A second variant would be that we could pull these bits into 
> core/iommu ... albeit you are right that the PowerPC tree is much 
> better at testing PowerPC patches.
> 
> A third variant would be to wait with these bits until the swiotlb 
> bits in core/iommu hit upstream. This would increase patch latency.
> 
> Any of these variants is good to me. What Fujita suggests seems to 
> be the best to me: #1 gets us the most testing and the lowest 
> latency - at the cost of tree dependency. We wont rebase core/iommu.
> 
> [ We've got three good tree properties: "tree independence",
>   "good testing", "low patch latency", but we cannot have all
>   three at once, we must pick two of them ;-) ]
> 
> 	Ingo

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Ingo Molnar]

* Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> 
> > Ben, what's your preference? I waited for your reaction with these 
> > bits, i.e. they are not in tip:core/iommu yet.
> 
> Oh I though they were... discard my previous private mail about 
> missing Ack's then :-)
> 
> I'll review them more in depth hopefully tomorrow but they look 
> good.

Sure - take your time.

> > One variant would be what Fujita suggested: you could pull 
> > core/iommu as a basis (it's a well-tested, problem-free tree at 
> > the moment, with no big risky items), and then pull/apply the 
> > powerpc specific bits from Fujita.
> 
> Or we can have the patches in core/iommu and I pull the whole 
> thing in powerpc-next. [...]

Ok! We could also stage it a bit (one or two weeks) in a separate 
branch and allow a rebase, should you find any bugs during testing?

	Ingo

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-13 at 10:55 +0200, Ingo Molnar wrote:

> > Or we can have the patches in core/iommu and I pull the whole 
> > thing in powerpc-next. [...]
> 
> Ok! We could also stage it a bit (one or two weeks) in a separate 
> branch and allow a rebase, should you find any bugs during testing?

Sounds like a plan.

I'll try to sort that out tomorrow, I can stick them in my -test branch
(which is rebase friendly) for a while too.

Cheers,
Ben.

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Kumar Gala]

On Aug 13, 2009, at 5:38 AM, Benjamin Herrenschmidt wrote:

> On Thu, 2009-08-13 at 10:55 +0200, Ingo Molnar wrote:
>
>>> Or we can have the patches in core/iommu and I pull the whole
>>> thing in powerpc-next. [...]
>>
>> Ok! We could also stage it a bit (one or two weeks) in a separate
>> branch and allow a rebase, should you find any bugs during testing?
>
> Sounds like a plan.
>
> I'll try to sort that out tomorrow, I can stick them in my -test  
> branch
> (which is rebase friendly) for a while too.

Getting them all in your -test branch gives Becky and I an opportunity  
to test them w/all the other PPC changes on the platforms we have that  
enable SWIOTLB today.

- k

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-13 at 10:55 +0200, Ingo Molnar wrote:

> Ok! We could also stage it a bit (one or two weeks) in a separate 
> branch and allow a rebase, should you find any bugs during testing?

Allright so after various delays and sidetracking on my side, the
patches have been in my -test branch for long enough, I'm happy for them
to go in either way now.

I'm going to take them out of powerpc test for now and not put them in
my -next right away until I'm sure I have the right source to pull, at
which point I can just put from tip iommu.

Cheers,
Ben.

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-27 at 13:12 +1000, Benjamin Herrenschmidt wrote:
> On Thu, 2009-08-13 at 10:55 +0200, Ingo Molnar wrote:
> 
> > Ok! We could also stage it a bit (one or two weeks) in a separate 
> > branch and allow a rebase, should you find any bugs during testing?
> 
> Allright so after various delays and sidetracking on my side, the
> patches have been in my -test branch for long enough, I'm happy for them
> to go in either way now.
> 
> I'm going to take them out of powerpc test for now and not put them in
> my -next right away until I'm sure I have the right source to pull, at
> which point I can just put from tip iommu.

IE. I think I was not clear :-)

I mean, I plan to pull tip/iommu into powerpc-next and then apply the
patches, but I want just your final word that this is a
"stable" (non-rebase) branch and from Fujita that the patches are still
good and haven't changed from those currently on patchwork.

Cheers,
Ben.

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Ingo Molnar]

* Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> On Thu, 2009-08-27 at 13:12 +1000, Benjamin Herrenschmidt wrote:
> > On Thu, 2009-08-13 at 10:55 +0200, Ingo Molnar wrote:
> > 
> > > Ok! We could also stage it a bit (one or two weeks) in a 
> > > separate branch and allow a rebase, should you find any bugs 
> > > during testing?
> > 
> > Allright so after various delays and sidetracking on my side, 
> > the patches have been in my -test branch for long enough, I'm 
> > happy for them to go in either way now.
> > 
> > I'm going to take them out of powerpc test for now and not put 
> > them in my -next right away until I'm sure I have the right 
> > source to pull, at which point I can just put from tip iommu.
> 
> IE. I think I was not clear :-)
> 
> I mean, I plan to pull tip/iommu into powerpc-next and then apply 
> the patches, but I want just your final word that this is a 
> "stable" (non-rebase) branch and from Fujita that the patches are 
> still good and haven't changed from those currently on patchwork.

ah, yes, they are stable/fine. I've put it into a separate branch 
for you.

Ben, please pull the latest iommu-for-powerpc git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git iommu-for-powerpc

And i could pull back the new bits from you once you have the new 
patches added and are happy with them. [I suspect you dont want the 
diffstat below in the powerpc tree]

That was the plan, right?

 Thanks,

	Ingo

------------------>
Arnd Bergmann (1):
      dma-ops: Remove flush_write_buffers() in dma-mapping-common.h

Casey Dahlin (1):
      lib/swiotlb.c: Fix strange panic message selection logic when swiotlb fills up

FUJITA Tomonori (22):
      swiotlb: remove unused swiotlb_alloc_boot()
      swiotlb: remove unused swiotlb_alloc()
      swiotlb: remove swiotlb_arch_range_needs_mapping
      swiotlb: remove unnecessary swiotlb_bus_to_virt
      x86: add dma_capable() to replace is_buffer_dma_capable()
      x86: replace is_buffer_dma_capable() with dma_capable
      ia64: add dma_capable() to replace is_buffer_dma_capable()
      powerpc: add dma_capable() to replace is_buffer_dma_capable()
      swiotlb: use dma_capable()
      powerpc: remove unncesary swiotlb_arch_address_needs_mapping
      remove is_buffer_dma_capable()
      x86, IA64, powerpc: add phys_to_dma() and dma_to_phys()
      swiotlb: use phys_to_dma and dma_to_phys
      powerpc: remove unused swiotlb_phys_to_bus() and swiotlb_bus_to_phys()
      x86: remove unused swiotlb_phys_to_bus() and swiotlb_bus_to_phys()
      IA64: Remove NULL flush_write_buffers
      sparc: Use dma_map_ops struct
      sparc: Use asm-generic/dma-mapping-common.h
      sparc: Remove no-op dma_4v_sync_single_for_cpu and dma_4v_sync_sg_for_cpu
      sparc: Replace sbus_map_single and sbus_unmap_single with sbus_map_page and sbus_unmap_page
      sparc: Use asm-generic/pci-dma-compat
      sparc: Add CONFIG_DMA_API_DEBUG support


 arch/ia64/include/asm/dma-mapping.h      |   19 +++-
 arch/powerpc/include/asm/dma-mapping.h   |   23 ++++
 arch/powerpc/kernel/dma-swiotlb.c        |   48 +--------
 arch/sparc/Kconfig                       |    2 +
 arch/sparc/include/asm/dma-mapping.h     |  145 ++++-------------------
 arch/sparc/include/asm/pci.h             |    3 +
 arch/sparc/include/asm/pci_32.h          |  105 ----------------
 arch/sparc/include/asm/pci_64.h          |   88 --------------
 arch/sparc/kernel/Makefile               |    2 +-
 arch/sparc/kernel/dma.c                  |  175 +--------------------------
 arch/sparc/kernel/dma.h                  |   14 --
 arch/sparc/kernel/iommu.c                |   20 ++-
 arch/sparc/kernel/ioport.c               |  190 ++++++++++++++++-------------
 arch/sparc/kernel/pci.c                  |    2 +-
 arch/sparc/kernel/pci_sun4v.c            |   30 ++----
 arch/x86/include/asm/dma-mapping.h       |   18 +++
 arch/x86/kernel/pci-dma.c                |    2 +-
 arch/x86/kernel/pci-gart_64.c            |    5 +-
 arch/x86/kernel/pci-nommu.c              |   29 ++++-
 arch/x86/kernel/pci-swiotlb.c            |   25 ----
 include/asm-generic/dma-mapping-common.h |    6 -
 include/linux/dma-mapping.h              |    5 -
 include/linux/swiotlb.h                  |   11 --
 lib/swiotlb.c                            |  124 +++++++-------------
 24 files changed, 291 insertions(+), 800 deletions(-)
 delete mode 100644 arch/sparc/kernel/dma.h

diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 5a61b5c..8d3c79c 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -44,7 +44,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
 #define get_dma_ops(dev) platform_dma_get_ops(dev)
-#define flush_write_buffers()
 
 #include <asm-generic/dma-mapping-common.h>
 
@@ -69,6 +68,24 @@ dma_set_mask (struct device *dev, u64 mask)
 	return 0;
 }
 
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
+
+	return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return daddr;
+}
+
 extern int dma_get_cache_alignment(void);
 
 static inline void
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index b44aaab..0c34371 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -424,6 +424,29 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 #endif
 }
 
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+	if (ops->addr_needs_map && ops->addr_needs_map(dev, addr, size))
+		return 0;
+
+	if (!dev->dma_mask)
+		return 0;
+
+	return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + get_dma_direct_offset(dev);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return daddr - get_dma_direct_offset(dev);
+}
+
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 #ifdef CONFIG_NOT_COHERENT_CACHE
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 68ccf11..e8a57de 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -24,50 +24,12 @@
 int swiotlb __read_mostly;
 unsigned int ppc_swiotlb_enable;
 
-void *swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t addr)
-{
-	unsigned long pfn = PFN_DOWN(swiotlb_bus_to_phys(hwdev, addr));
-	void *pageaddr = page_address(pfn_to_page(pfn));
-
-	if (pageaddr != NULL)
-		return pageaddr + (addr % PAGE_SIZE);
-	return NULL;
-}
-
-dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
-	return paddr + get_dma_direct_offset(hwdev);
-}
-
-phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-
-{
-	return baddr - get_dma_direct_offset(hwdev);
-}
-
-/*
- * Determine if an address needs bounce buffering via swiotlb.
- * Going forward I expect the swiotlb code to generalize on using
- * a dma_ops->addr_needs_map, and this function will move from here to the
- * generic swiotlb code.
- */
-int
-swiotlb_arch_address_needs_mapping(struct device *hwdev, dma_addr_t addr,
-				   size_t size)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(hwdev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->addr_needs_map(hwdev, addr, size);
-}
-
 /*
  * Determine if an address is reachable by a pci device, or if we must bounce.
  */
 static int
 swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
 {
-	u64 mask = dma_get_mask(hwdev);
 	dma_addr_t max;
 	struct pci_controller *hose;
 	struct pci_dev *pdev = to_pci_dev(hwdev);
@@ -79,16 +41,9 @@ swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
 	if ((addr + size > max) | (addr < hose->dma_window_base_cur))
 		return 1;
 
-	return !is_buffer_dma_capable(mask, addr, size);
-}
-
-static int
-swiotlb_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
-{
-	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+	return 0;
 }
 
-
 /*
  * At the moment, all platforms that use this code only require
  * swiotlb to be used if we're operating on HIGHMEM.  Since
@@ -104,7 +59,6 @@ struct dma_mapping_ops swiotlb_dma_ops = {
 	.dma_supported = swiotlb_dma_supported,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
-	.addr_needs_map = swiotlb_addr_needs_map,
 	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
 	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3f8b6a9..233cff5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,6 +25,8 @@ config SPARC
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select RTC_CLASS
 	select RTC_DRV_M48T59
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_API_DEBUG
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 204e4bf..5a8c308 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -3,6 +3,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/mm.h>
+#include <linux/dma-debug.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 
@@ -13,142 +14,40 @@ extern int dma_set_mask(struct device *dev, u64 dma_mask);
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 #define dma_is_consistent(d, h)	(1)
 
-struct dma_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 *cpu_addr, dma_addr_t dma_handle);
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction direction);
-	void (*unmap_page)(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 nhwentries,
-			 enum dma_data_direction direction);
-	void (*sync_single_for_cpu)(struct device *dev,
-				    dma_addr_t dma_handle, size_t size,
-				    enum dma_data_direction direction);
-	void (*sync_single_for_device)(struct device *dev,
-				       dma_addr_t dma_handle, size_t size,
-				       enum dma_data_direction direction);
-	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
-				int nelems,
-				enum dma_data_direction direction);
-	void (*sync_sg_for_device)(struct device *dev,
-				   struct scatterlist *sg, int nents,
-				   enum dma_data_direction dir);
-};
-extern const struct dma_ops *dma_ops;
+extern struct dma_map_ops *dma_ops, pci32_dma_ops;
+extern struct bus_type pci_bus_type;
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	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)
-{
-	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)
-{
-	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
-				 (unsigned long)cpu_addr & ~PAGE_MASK, size,
-				 direction);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction)
-{
-	dma_ops->unmap_page(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)
-{
-	return dma_ops->map_page(dev, page, offset, size, direction);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-				  size_t size,
-				  enum dma_data_direction direction)
-{
-	dma_ops->unmap_page(dev, dma_address, size, direction);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction direction)
-{
-	return dma_ops->map_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	dma_ops->unmap_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
-					   dma_addr_t dma_handle, size_t size,
-					   enum dma_data_direction direction)
-{
-	dma_ops->sync_single_for_cpu(dev, dma_handle, size, direction);
+#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+	if (dev->bus == &pci_bus_type)
+		return &pci32_dma_ops;
+#endif
+	return dma_ops;
 }
 
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t dma_handle,
-					      size_t size,
-					      enum dma_data_direction direction)
-{
-	if (dma_ops->sync_single_for_device)
-		dma_ops->sync_single_for_device(dev, dma_handle, size,
-						direction);
-}
+#include <asm-generic/dma-mapping-common.h>
 
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-				       struct scatterlist *sg, int nelems,
-				       enum dma_data_direction direction)
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
 {
-	dma_ops->sync_sg_for_cpu(dev, sg, nelems, direction);
-}
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
 
-static inline void dma_sync_sg_for_device(struct device *dev,
-					  struct scatterlist *sg, int nelems,
-					  enum dma_data_direction direction)
-{
-	if (dma_ops->sync_sg_for_device)
-		dma_ops->sync_sg_for_device(dev, sg, nelems, direction);
+	cpu_addr = ops->alloc_coherent(dev, size, dma_handle, flag);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction dir)
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
 {
-	dma_sync_single_for_cpu(dev, dma_handle+offset, size, dir);
-}
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction dir)
-{
-	dma_sync_single_for_device(dev, dma_handle+offset, size, dir);
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free_coherent(dev, size, cpu_addr, dma_handle);
 }
 
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return (dma_addr == DMA_ERROR_CODE);
diff --git a/arch/sparc/include/asm/pci.h b/arch/sparc/include/asm/pci.h
index 6e14fd1..d9c031f 100644
--- a/arch/sparc/include/asm/pci.h
+++ b/arch/sparc/include/asm/pci.h
@@ -5,4 +5,7 @@
 #else
 #include <asm/pci_32.h>
 #endif
+
+#include <asm-generic/pci-dma-compat.h>
+
 #endif
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index b41c4c1..ac0e836 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -31,42 +31,8 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  */
 #define PCI_DMA_BUS_IS_PHYS	(0)
 
-#include <asm/scatterlist.h>
-
 struct pci_dev;
 
-/* Allocate and map kernel buffer using consistent mode DMA for a device.
- * hwdev should be valid struct pci_dev pointer for PCI devices.
- */
-extern void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size, dma_addr_t *dma_handle);
-
-/* Free and unmap a consistent DMA buffer.
- * cpu_addr is what was returned from pci_alloc_consistent,
- * size must be the same as what as passed into pci_alloc_consistent,
- * and likewise dma_addr must be the same as what *dma_addrp was set to.
- *
- * References to the memory and mappings assosciated with cpu_addr/dma_addr
- * past this call are illegal.
- */
-extern void pci_free_consistent(struct pci_dev *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_for_cpu is performed.
- */
-extern dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction);
-
-/* Unmap a single streaming mode DMA translation.  The dma_addr and size
- * must match what was provided for in a previous pci_map_single call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t size, int direction);
-
 /* pci_unmap_{single,page} is not a nop, thus... */
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
 	dma_addr_t ADDR_NAME;
@@ -81,69 +47,6 @@ extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
 	(((PTR)->LEN_NAME) = (VAL))
 
-/*
- * Same as above, only with pages instead of mapped addresses.
- */
-extern dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
-			unsigned long offset, size_t size, int direction);
-extern void pci_unmap_page(struct pci_dev *hwdev,
-			dma_addr_t dma_address, size_t size, int direction);
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scather-gather version of the
- * above pci_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-extern int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction);
-
-/* Unmap a set of streaming mode DMA translations.
- * Again, cpu read rules concerning calls here are the same as for
- * pci_unmap_single() above.
- */
-extern void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nhwents, int direction);
-
-/* Make physical memory consistent for a single
- * streaming mode DMA translation after a transfer.
- *
- * If you perform a pci_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the PCI dma
- * mapping, you must call this function before doing so.  At the
- * next point you give the PCI dma address back to the card, you
- * must first perform a pci_dma_sync_for_device, and then the device
- * again owns the buffer.
- */
-extern void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-extern void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-
-/* Make physical memory consistent for a set of streaming
- * mode DMA translations after a transfer.
- *
- * The same as pci_dma_sync_single_* but for a scatter-gather list,
- * same rules and usage.
- */
-extern void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-extern void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly.  For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-static inline int pci_dma_supported(struct pci_dev *hwdev, u64 mask)
-{
-	return 1;
-}
-
 #ifdef CONFIG_PCI
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 					enum pci_dma_burst_strategy *strat,
@@ -154,14 +57,6 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 }
 #endif
 
-#define PCI_DMA_ERROR_CODE      (~(dma_addr_t)0x0)
-
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
-					dma_addr_t dma_addr)
-{
-        return (dma_addr == PCI_DMA_ERROR_CODE);
-}
-
 struct device_node;
 extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev);
 
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 7a1e356..5cc9f6a 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -35,37 +35,6 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  */
 #define PCI_DMA_BUS_IS_PHYS	(0)
 
-static inline void *pci_alloc_consistent(struct pci_dev *pdev, size_t size,
-					 dma_addr_t *dma_handle)
-{
-	return dma_alloc_coherent(&pdev->dev, size, dma_handle, GFP_ATOMIC);
-}
-
-static inline void pci_free_consistent(struct pci_dev *pdev, size_t size,
-				       void *vaddr, dma_addr_t dma_handle)
-{
-	return dma_free_coherent(&pdev->dev, size, vaddr, dma_handle);
-}
-
-static inline dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr,
-					size_t size, int direction)
-{
-	return dma_map_single(&pdev->dev, ptr, size,
-			      (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
-				    size_t size, int direction)
-{
-	dma_unmap_single(&pdev->dev, dma_addr, size,
-			 (enum dma_data_direction) direction);
-}
-
-#define pci_map_page(dev, page, off, size, dir) \
-	pci_map_single(dev, (page_address(page) + (off)), size, dir)
-#define pci_unmap_page(dev,addr,sz,dir) \
-	pci_unmap_single(dev,addr,sz,dir)
-
 /* pci_unmap_{single,page} is not a nop, thus... */
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
 	dma_addr_t ADDR_NAME;
@@ -80,57 +49,6 @@ static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
 	(((PTR)->LEN_NAME) = (VAL))
 
-static inline int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sg,
-			     int nents, int direction)
-{
-	return dma_map_sg(&pdev->dev, sg, nents,
-			  (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sg,
-				int nents, int direction)
-{
-	dma_unmap_sg(&pdev->dev, sg, nents,
-		     (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_cpu(struct pci_dev *pdev,
-					       dma_addr_t dma_handle,
-					       size_t size, int direction)
-{
-	dma_sync_single_for_cpu(&pdev->dev, dma_handle, size,
-				(enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_device(struct pci_dev *pdev,
-						  dma_addr_t dma_handle,
-						  size_t size, int direction)
-{
-	/* No flushing needed to sync cpu writes to the device.  */
-}
-
-static inline void pci_dma_sync_sg_for_cpu(struct pci_dev *pdev,
-					   struct scatterlist *sg,
-					   int nents, int direction)
-{
-	dma_sync_sg_for_cpu(&pdev->dev, sg, nents,
-			    (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_sg_for_device(struct pci_dev *pdev,
-					      struct scatterlist *sg,
-					      int nelems, int direction)
-{
-	/* No flushing needed to sync cpu writes to the device.  */
-}
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly.  For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
-
 /* PCI IOMMU mapping bypass support. */
 
 /* PCI 64-bit addressing works for all slots on all controller
@@ -140,12 +58,6 @@ extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
 #define PCI64_REQUIRED_MASK	(~(dma64_addr_t)0)
 #define PCI64_ADDR_BASE		0xfffc000000000000UL
 
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
-					dma_addr_t dma_addr)
-{
-	return dma_mapping_error(&pdev->dev, dma_addr);
-}
-
 #ifdef CONFIG_PCI
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 					enum pci_dma_burst_strategy *strat,
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 475ce46..29b88a5 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -61,7 +61,7 @@ obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 obj-$(CONFIG_SPARC32)     += devres.o
 devres-y                  := ../../../kernel/irq/devres.o
 
-obj-$(CONFIG_SPARC32)     += dma.o
+obj-y                     += dma.o
 
 obj-$(CONFIG_SPARC32_PCI) += pcic.o
 
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
index 524c32f..e1ba8ee 100644
--- a/arch/sparc/kernel/dma.c
+++ b/arch/sparc/kernel/dma.c
@@ -1,178 +1,13 @@
-/* dma.c: PCI and SBUS DMA accessors for 32-bit sparc.
- *
- * Copyright (C) 2008 David S. Miller <davem@davemloft.net>
- */
-
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/mm.h>
-
-#ifdef CONFIG_PCI
-#include <linux/pci.h>
-#endif
+#include <linux/dma-debug.h>
 
-#include "dma.h"
+#define PREALLOC_DMA_DEBUG_ENTRIES       (1 << 15)
 
-int dma_supported(struct device *dev, u64 mask)
+static int __init dma_init(void)
 {
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_dma_supported(to_pci_dev(dev), mask);
-#endif
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
-EXPORT_SYMBOL(dma_supported);
-
-int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
-#endif
-	return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
-static void *dma32_alloc_coherent(struct device *dev, size_t size,
-				  dma_addr_t *dma_handle, gfp_t flag)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_alloc_consistent(to_pci_dev(dev), size, dma_handle);
-#endif
-	return sbus_alloc_consistent(dev, size, dma_handle);
-}
-
-static void dma32_free_coherent(struct device *dev, size_t size,
-				void *cpu_addr, dma_addr_t dma_handle)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_free_consistent(to_pci_dev(dev), size,
-				    cpu_addr, dma_handle);
-		return;
-	}
-#endif
-	sbus_free_consistent(dev, size, cpu_addr, dma_handle);
-}
-
-static dma_addr_t dma32_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_map_page(to_pci_dev(dev), page, offset,
-				    size, (int)direction);
-#endif
-	return sbus_map_single(dev, page_address(page) + offset,
-			       size, (int)direction);
-}
-
-static void dma32_unmap_page(struct device *dev, dma_addr_t dma_address,
-			     size_t size, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_unmap_page(to_pci_dev(dev), dma_address,
-			       size, (int)direction);
-		return;
-	}
-#endif
-	sbus_unmap_single(dev, dma_address, size, (int)direction);
-}
-
-static int dma32_map_sg(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_map_sg(to_pci_dev(dev), sg, nents, (int)direction);
-#endif
-	return sbus_map_sg(dev, sg, nents, direction);
-}
-
-void dma32_unmap_sg(struct device *dev, struct scatterlist *sg,
-		    int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_unmap_sg(to_pci_dev(dev), sg, nents, (int)direction);
-		return;
-	}
-#endif
-	sbus_unmap_sg(dev, sg, nents, (int)direction);
-}
-
-static void dma32_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-				      size_t size,
-				      enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_dma_sync_single_for_cpu(to_pci_dev(dev), dma_handle,
-					    size, (int)direction);
-		return;
-	}
-#endif
-	sbus_dma_sync_single_for_cpu(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_single_for_device(struct device *dev,
-					 dma_addr_t dma_handle, size_t size,
-					 enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_dma_sync_single_for_device(to_pci_dev(dev), dma_handle,
-					       size, (int)direction);
-		return;
-	}
-#endif
-	sbus_dma_sync_single_for_device(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				  int nelems, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_dma_sync_sg_for_cpu(to_pci_dev(dev), sg,
-					nelems, (int)direction);
-		return;
-	}
-#endif
-	BUG();
-}
-
-static void dma32_sync_sg_for_device(struct device *dev,
-				     struct scatterlist *sg, int nelems,
-				     enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_dma_sync_sg_for_device(to_pci_dev(dev), sg,
-					   nelems, (int)direction);
-		return;
-	}
-#endif
-	BUG();
-}
-
-static const struct dma_ops dma32_dma_ops = {
-	.alloc_coherent		= dma32_alloc_coherent,
-	.free_coherent		= dma32_free_coherent,
-	.map_page		= dma32_map_page,
-	.unmap_page		= dma32_unmap_page,
-	.map_sg			= dma32_map_sg,
-	.unmap_sg		= dma32_unmap_sg,
-	.sync_single_for_cpu	= dma32_sync_single_for_cpu,
-	.sync_single_for_device	= dma32_sync_single_for_device,
-	.sync_sg_for_cpu	= dma32_sync_sg_for_cpu,
-	.sync_sg_for_device	= dma32_sync_sg_for_device,
-};
-
-const struct dma_ops *dma_ops = &dma32_dma_ops;
-EXPORT_SYMBOL(dma_ops);
+fs_initcall(dma_init);
diff --git a/arch/sparc/kernel/dma.h b/arch/sparc/kernel/dma.h
deleted file mode 100644
index f8d8951..0000000
--- a/arch/sparc/kernel/dma.h
+++ /dev/null
@@ -1,14 +0,0 @@
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp);
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba);
-dma_addr_t sbus_map_single(struct device *dev, void *va,
-			   size_t len, int direction);
-void sbus_unmap_single(struct device *dev, dma_addr_t ba,
-		       size_t n, int direction);
-int sbus_map_sg(struct device *dev, struct scatterlist *sg,
-		int n, int direction);
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg,
-		   int n, int direction);
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
-				  size_t size, int direction);
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba,
-				     size_t size, int direction);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 0aeaefe..7690cc2 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -353,7 +353,8 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
 
 static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
 				  unsigned long offset, size_t sz,
-				  enum dma_data_direction direction)
+				  enum dma_data_direction direction,
+				  struct dma_attrs *attrs)
 {
 	struct iommu *iommu;
 	struct strbuf *strbuf;
@@ -474,7 +475,8 @@ do_flush_sync:
 }
 
 static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
-			      size_t sz, enum dma_data_direction direction)
+			      size_t sz, enum dma_data_direction direction,
+			      struct dma_attrs *attrs)
 {
 	struct iommu *iommu;
 	struct strbuf *strbuf;
@@ -520,7 +522,8 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
 }
 
 static int dma_4u_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)
 {
 	struct scatterlist *s, *outs, *segstart;
 	unsigned long flags, handle, prot, ctx;
@@ -691,7 +694,8 @@ static unsigned long fetch_sg_ctx(struct iommu *iommu, struct scatterlist *sg)
 }
 
 static void dma_4u_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)
 {
 	unsigned long flags, ctx;
 	struct scatterlist *sg;
@@ -822,7 +826,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static const struct dma_ops sun4u_dma_ops = {
+static struct dma_map_ops sun4u_dma_ops = {
 	.alloc_coherent		= dma_4u_alloc_coherent,
 	.free_coherent		= dma_4u_free_coherent,
 	.map_page		= dma_4u_map_page,
@@ -833,9 +837,11 @@ static const struct dma_ops sun4u_dma_ops = {
 	.sync_sg_for_cpu	= dma_4u_sync_sg_for_cpu,
 };
 
-const struct dma_ops *dma_ops = &sun4u_dma_ops;
+struct dma_map_ops *dma_ops = &sun4u_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
+extern int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
+
 int dma_supported(struct device *dev, u64 device_mask)
 {
 	struct iommu *iommu = dev->archdata.iommu;
@@ -849,7 +855,7 @@ int dma_supported(struct device *dev, u64 device_mask)
 
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type)
-		return pci_dma_supported(to_pci_dev(dev), device_mask);
+		return pci64_dma_supported(to_pci_dev(dev), device_mask);
 #endif
 
 	return 0;
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 87ea0d0..edbea23 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -48,8 +48,6 @@
 #include <asm/iommu.h>
 #include <asm/io-unit.h>
 
-#include "dma.h"
-
 #define mmu_inval_dma_area(p, l)	/* Anton pulled it out for 2.4.0-xx */
 
 static struct resource *_sparc_find_resource(struct resource *r,
@@ -246,7 +244,8 @@ EXPORT_SYMBOL(sbus_set_sbus64);
  * Typically devices use them for control blocks.
  * CPU may access them without any explicit flushing.
  */
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp)
+static void *sbus_alloc_coherent(struct device *dev, size_t len,
+				 dma_addr_t *dma_addrp, gfp_t gfp)
 {
 	struct of_device *op = to_of_device(dev);
 	unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
@@ -299,7 +298,8 @@ err_nopages:
 	return NULL;
 }
 
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
+static void sbus_free_coherent(struct device *dev, size_t n, void *p,
+			       dma_addr_t ba)
 {
 	struct resource *res;
 	struct page *pgv;
@@ -317,7 +317,7 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
 
 	n = (n + PAGE_SIZE-1) & PAGE_MASK;
 	if ((res->end-res->start)+1 != n) {
-		printk("sbus_free_consistent: region 0x%lx asked 0x%lx\n",
+		printk("sbus_free_consistent: region 0x%lx asked 0x%zx\n",
 		    (long)((res->end-res->start)+1), n);
 		return;
 	}
@@ -337,8 +337,13 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
  * CPU view of this memory may be inconsistent with
  * a device view and explicit flushing is necessary.
  */
-dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int direction)
+static dma_addr_t sbus_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t len,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
 {
+	void *va = page_address(page) + offset;
+
 	/* XXX why are some lengths signed, others unsigned? */
 	if (len <= 0) {
 		return 0;
@@ -350,12 +355,14 @@ dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int directi
 	return mmu_get_scsi_one(dev, va, len);
 }
 
-void sbus_unmap_single(struct device *dev, dma_addr_t ba, size_t n, int direction)
+static void sbus_unmap_page(struct device *dev, dma_addr_t ba, size_t n,
+			    enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	mmu_release_scsi_one(dev, ba, n);
 }
 
-int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n,
+		       enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	mmu_get_scsi_sgl(dev, sg, n);
 
@@ -366,19 +373,38 @@ int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction
 	return n;
 }
 
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n,
+			  enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	mmu_release_scsi_sgl(dev, sg, n);
 }
 
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+				 int n,	enum dma_data_direction dir)
 {
+	BUG();
 }
 
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+				    int n, enum dma_data_direction dir)
 {
+	BUG();
 }
 
+struct dma_map_ops sbus_dma_ops = {
+	.alloc_coherent		= sbus_alloc_coherent,
+	.free_coherent		= sbus_free_coherent,
+	.map_page		= sbus_map_page,
+	.unmap_page		= sbus_unmap_page,
+	.map_sg			= sbus_map_sg,
+	.unmap_sg		= sbus_unmap_sg,
+	.sync_sg_for_cpu	= sbus_sync_sg_for_cpu,
+	.sync_sg_for_device	= sbus_sync_sg_for_device,
+};
+
+struct dma_map_ops *dma_ops = &sbus_dma_ops;
+EXPORT_SYMBOL(dma_ops);
+
 static int __init sparc_register_ioport(void)
 {
 	register_proc_sparc_ioport();
@@ -395,7 +421,8 @@ arch_initcall(sparc_register_ioport);
 /* Allocate and map kernel buffer using consistent mode DMA for a device.
  * hwdev should be valid struct pci_dev pointer for PCI devices.
  */
-void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
+static void *pci32_alloc_coherent(struct device *dev, size_t len,
+				  dma_addr_t *pba, gfp_t gfp)
 {
 	unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
 	unsigned long va;
@@ -439,7 +466,6 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
 	*pba = virt_to_phys(va); /* equals virt_to_bus (R.I.P.) for us. */
 	return (void *) res->start;
 }
-EXPORT_SYMBOL(pci_alloc_consistent);
 
 /* Free and unmap a consistent DMA buffer.
  * cpu_addr is what was returned from pci_alloc_consistent,
@@ -449,7 +475,8 @@ EXPORT_SYMBOL(pci_alloc_consistent);
  * References to the memory and mappings associated with cpu_addr/dma_addr
  * past this call are illegal.
  */
-void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
+static void pci32_free_coherent(struct device *dev, size_t n, void *p,
+				dma_addr_t ba)
 {
 	struct resource *res;
 	unsigned long pgp;
@@ -481,60 +508,18 @@ void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
 
 	free_pages(pgp, get_order(n));
 }
-EXPORT_SYMBOL(pci_free_consistent);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_* is performed.
- */
-dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size,
-    int direction)
-{
-	BUG_ON(direction == PCI_DMA_NONE);
-	/* IIep is write-through, not flushing. */
-	return virt_to_phys(ptr);
-}
-EXPORT_SYMBOL(pci_map_single);
-
-/* Unmap a single streaming mode DMA translation.  The dma_addr and size
- * must match what was provided for in a previous pci_map_single call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t ba, size_t size,
-    int direction)
-{
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
-		mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
-		    (size + PAGE_SIZE-1) & PAGE_MASK);
-	}
-}
-EXPORT_SYMBOL(pci_unmap_single);
 
 /*
  * Same as pci_map_single, but with pages.
  */
-dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
-			unsigned long offset, size_t size, int direction)
+static dma_addr_t pci32_map_page(struct device *dev, struct page *page,
+				 unsigned long offset, size_t size,
+				 enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
 {
-	BUG_ON(direction == PCI_DMA_NONE);
 	/* IIep is write-through, not flushing. */
 	return page_to_phys(page) + offset;
 }
-EXPORT_SYMBOL(pci_map_page);
-
-void pci_unmap_page(struct pci_dev *hwdev,
-			dma_addr_t dma_address, size_t size, int direction)
-{
-	BUG_ON(direction == PCI_DMA_NONE);
-	/* mmu_inval_dma_area XXX */
-}
-EXPORT_SYMBOL(pci_unmap_page);
 
 /* Map a set of buffers described by scatterlist in streaming
  * mode for DMA.  This is the scather-gather version of the
@@ -551,13 +536,13 @@ EXPORT_SYMBOL(pci_unmap_page);
  * Device ownership issues as mentioned above for pci_map_single are
  * the same here.
  */
-int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
-    int direction)
+static int pci32_map_sg(struct device *device, struct scatterlist *sgl,
+			int nents, enum dma_data_direction dir,
+			struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int n;
 
-	BUG_ON(direction == PCI_DMA_NONE);
 	/* IIep is write-through, not flushing. */
 	for_each_sg(sgl, sg, nents, n) {
 		BUG_ON(page_address(sg_page(sg)) == NULL);
@@ -566,20 +551,19 @@ int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
 	}
 	return nents;
 }
-EXPORT_SYMBOL(pci_map_sg);
 
 /* Unmap a set of streaming mode DMA translations.
  * Again, cpu read rules concerning calls here are the same as for
  * pci_unmap_single() above.
  */
-void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
-    int direction)
+static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl,
+			   int nents, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int n;
 
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE) {
 		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg_page(sg)) == NULL);
 			mmu_inval_dma_area(
@@ -588,7 +572,6 @@ void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
 		}
 	}
 }
-EXPORT_SYMBOL(pci_unmap_sg);
 
 /* Make physical memory consistent for a single
  * streaming mode DMA translation before or after a transfer.
@@ -600,25 +583,23 @@ EXPORT_SYMBOL(pci_unmap_sg);
  * must first perform a pci_dma_sync_for_device, and then the
  * device again owns the buffer.
  */
-void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
+				      size_t size, enum dma_data_direction dir)
 {
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE) {
 		mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
 		    (size + PAGE_SIZE-1) & PAGE_MASK);
 	}
 }
-EXPORT_SYMBOL(pci_dma_sync_single_for_cpu);
 
-void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_device(struct device *dev, dma_addr_t ba,
+					 size_t size, enum dma_data_direction dir)
 {
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE) {
 		mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
 		    (size + PAGE_SIZE-1) & PAGE_MASK);
 	}
 }
-EXPORT_SYMBOL(pci_dma_sync_single_for_device);
 
 /* Make physical memory consistent for a set of streaming
  * mode DMA translations after a transfer.
@@ -626,13 +607,13 @@ EXPORT_SYMBOL(pci_dma_sync_single_for_device);
  * The same as pci_dma_sync_single_* but for a scatter-gather list,
  * same rules and usage.
  */
-void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+				  int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int n;
 
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE) {
 		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg_page(sg)) == NULL);
 			mmu_inval_dma_area(
@@ -641,15 +622,14 @@ void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int
 		}
 	}
 }
-EXPORT_SYMBOL(pci_dma_sync_sg_for_cpu);
 
-void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *sgl,
+				     int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int n;
 
-	BUG_ON(direction == PCI_DMA_NONE);
-	if (direction != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE) {
 		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg_page(sg)) == NULL);
 			mmu_inval_dma_area(
@@ -658,9 +638,49 @@ void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl,
 		}
 	}
 }
-EXPORT_SYMBOL(pci_dma_sync_sg_for_device);
+
+struct dma_map_ops pci32_dma_ops = {
+	.alloc_coherent		= pci32_alloc_coherent,
+	.free_coherent		= pci32_free_coherent,
+	.map_page		= pci32_map_page,
+	.map_sg			= pci32_map_sg,
+	.unmap_sg		= pci32_unmap_sg,
+	.sync_single_for_cpu	= pci32_sync_single_for_cpu,
+	.sync_single_for_device	= pci32_sync_single_for_device,
+	.sync_sg_for_cpu	= pci32_sync_sg_for_cpu,
+	.sync_sg_for_device	= pci32_sync_sg_for_device,
+};
+EXPORT_SYMBOL(pci32_dma_ops);
+
 #endif /* CONFIG_PCI */
 
+/*
+ * Return whether the given PCI device DMA address mask can be
+ * supported properly.  For example, if your device can only drive the
+ * low 24-bits during PCI bus mastering, then you would pass
+ * 0x00ffffff as the mask to this function.
+ */
+int dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PCI
+	if (dev->bus == &pci_bus_type)
+		return 1;
+#endif
+	return 0;
+}
+EXPORT_SYMBOL(dma_supported);
+
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+#ifdef CONFIG_PCI
+	if (dev->bus == &pci_bus_type)
+		return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
+#endif
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
+
 #ifdef CONFIG_PROC_FS
 
 static int
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 57859ad..c686486 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1039,7 +1039,7 @@ static void ali_sound_dma_hack(struct pci_dev *pdev, int set_bit)
 	pci_dev_put(ali_isa_bridge);
 }
 
-int pci_dma_supported(struct pci_dev *pdev, u64 device_mask)
+int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask)
 {
 	u64 dma_addr_mask;
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 2485eaa..23c33ff 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -232,7 +232,8 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 
 static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 				  unsigned long offset, size_t sz,
-				  enum dma_data_direction direction)
+				  enum dma_data_direction direction,
+				  struct dma_attrs *attrs)
 {
 	struct iommu *iommu;
 	unsigned long flags, npages, oaddr;
@@ -296,7 +297,8 @@ iommu_map_fail:
 }
 
 static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
-			      size_t sz, enum dma_data_direction direction)
+			      size_t sz, enum dma_data_direction direction,
+			      struct dma_attrs *attrs)
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
@@ -336,7 +338,8 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 }
 
 static int dma_4v_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)
 {
 	struct scatterlist *s, *outs, *segstart;
 	unsigned long flags, handle, prot;
@@ -478,7 +481,8 @@ iommu_map_failed:
 }
 
 static void dma_4v_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)
 {
 	struct pci_pbm_info *pbm;
 	struct scatterlist *sg;
@@ -521,29 +525,13 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static void dma_4v_sync_single_for_cpu(struct device *dev,
-				       dma_addr_t bus_addr, size_t sz,
-				       enum dma_data_direction direction)
-{
-	/* Nothing to do... */
-}
-
-static void dma_4v_sync_sg_for_cpu(struct device *dev,
-				   struct scatterlist *sglist, int nelems,
-				   enum dma_data_direction direction)
-{
-	/* Nothing to do... */
-}
-
-static const struct dma_ops sun4v_dma_ops = {
+static struct dma_map_ops sun4v_dma_ops = {
 	.alloc_coherent			= dma_4v_alloc_coherent,
 	.free_coherent			= dma_4v_free_coherent,
 	.map_page			= dma_4v_map_page,
 	.unmap_page			= dma_4v_unmap_page,
 	.map_sg				= dma_4v_map_sg,
 	.unmap_sg			= dma_4v_unmap_sg,
-	.sync_single_for_cpu		= dma_4v_sync_single_for_cpu,
-	.sync_sg_for_cpu		= dma_4v_sync_sg_for_cpu,
 };
 
 static void __devinit pci_sun4v_scan_bus(struct pci_pbm_info *pbm,
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 1c3f943..0ee770d 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -55,6 +55,24 @@ extern int dma_set_mask(struct device *dev, u64 mask);
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag);
 
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
+
+	return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return daddr;
+}
+
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	enum dma_data_direction dir)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1a041bc..3c945c0 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -147,7 +147,7 @@ again:
 		return NULL;
 
 	addr = page_to_phys(page);
-	if (!is_buffer_dma_capable(dma_mask, addr, size)) {
+	if (addr + size > dma_mask) {
 		__free_pages(page, get_order(size));
 
 		if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index d2e56b8..98a827e 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -190,14 +190,13 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 static inline int
 need_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return force_iommu ||
-		!is_buffer_dma_capable(*dev->dma_mask, addr, size);
+	return force_iommu || !dma_capable(dev, addr, size);
 }
 
 static inline int
 nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return !is_buffer_dma_capable(*dev->dma_mask, addr, size);
+	return !dma_capable(dev, addr, size);
 }
 
 /* Map a single continuous physical area into the IOMMU.
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 71d412a..a3933d4 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -14,7 +14,7 @@
 static int
 check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
 {
-	if (hwdev && !is_buffer_dma_capable(*hwdev->dma_mask, bus, size)) {
+	if (hwdev && !dma_capable(hwdev, bus, size)) {
 		if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
 			printk(KERN_ERR
 			    "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
@@ -79,12 +79,29 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
+static void nommu_sync_single_for_device(struct device *dev,
+			dma_addr_t addr, size_t size,
+			enum dma_data_direction dir)
+{
+	flush_write_buffers();
+}
+
+
+static void nommu_sync_sg_for_device(struct device *dev,
+			struct scatterlist *sg, int nelems,
+			enum dma_data_direction dir)
+{
+	flush_write_buffers();
+}
+
 struct dma_map_ops nommu_dma_ops = {
-	.alloc_coherent	= dma_generic_alloc_coherent,
-	.free_coherent	= nommu_free_coherent,
-	.map_sg		= nommu_map_sg,
-	.map_page	= nommu_map_page,
-	.is_phys	= 1,
+	.alloc_coherent		= dma_generic_alloc_coherent,
+	.free_coherent		= nommu_free_coherent,
+	.map_sg			= nommu_map_sg,
+	.map_page		= nommu_map_page,
+	.sync_single_for_device = nommu_sync_single_for_device,
+	.sync_sg_for_device	= nommu_sync_sg_for_device,
+	.is_phys		= 1,
 };
 
 void __init no_iommu_init(void)
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 6af96ee..e8a3501 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -13,31 +13,6 @@
 
 int swiotlb __read_mostly;
 
-void * __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
-	return alloc_bootmem_low_pages(size);
-}
-
-void *swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
-	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
-	return baddr;
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
-	return 0;
-}
-
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flags)
 {
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 5406a60..e694263 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -103,7 +103,6 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 	if (ops->sync_single_for_cpu)
 		ops->sync_single_for_cpu(dev, addr, size, dir);
 	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-	flush_write_buffers();
 }
 
 static inline void dma_sync_single_for_device(struct device *dev,
@@ -116,7 +115,6 @@ static inline void dma_sync_single_for_device(struct device *dev,
 	if (ops->sync_single_for_device)
 		ops->sync_single_for_device(dev, addr, size, dir);
 	debug_dma_sync_single_for_device(dev, addr, size, dir);
-	flush_write_buffers();
 }
 
 static inline void dma_sync_single_range_for_cpu(struct device *dev,
@@ -132,7 +130,6 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 		ops->sync_single_range_for_cpu(dev, addr, offset, size, dir);
 		debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
 
-		flush_write_buffers();
 	} else
 		dma_sync_single_for_cpu(dev, addr, size, dir);
 }
@@ -150,7 +147,6 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 		ops->sync_single_range_for_device(dev, addr, offset, size, dir);
 		debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
 
-		flush_write_buffers();
 	} else
 		dma_sync_single_for_device(dev, addr, size, dir);
 }
@@ -165,7 +161,6 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 	if (ops->sync_sg_for_cpu)
 		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
 	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
-	flush_write_buffers();
 }
 
 static inline void
@@ -179,7 +174,6 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 		ops->sync_sg_for_device(dev, sg, nelems, dir);
 	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
 
-	flush_write_buffers();
 }
 
 #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 07dfd46..c0f6c3c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -98,11 +98,6 @@ static inline int is_device_dma_capable(struct device *dev)
 	return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
 }
 
-static inline int is_buffer_dma_capable(u64 mask, dma_addr_t addr, size_t size)
-{
-	return addr + size <= mask;
-}
-
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 #else
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index cb1a663..73b1f1c 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -14,7 +14,6 @@ struct scatterlist;
  */
 #define IO_TLB_SEGSIZE	128
 
-
 /*
  * log of the size of each IO TLB slab.  The number of slabs is command line
  * controllable.
@@ -24,16 +23,6 @@ struct scatterlist;
 extern void
 swiotlb_init(void);
 
-extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
-extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
-
-extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
-				      phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
-				       dma_addr_t address);
-
-extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
-
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			dma_addr_t *dma_handle, gfp_t flags);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bffe6d7..ac25cd2 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -114,46 +114,11 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
-void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
-	return alloc_bootmem_low_pages(size);
-}
-
-void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
-	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
-	return baddr;
-}
-
+/* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 				      volatile void *address)
 {
-	return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
-}
-
-void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
-{
-	return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
-}
-
-int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
-					       dma_addr_t addr, size_t size)
-{
-	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
-	return 0;
+	return phys_to_dma(hwdev, virt_to_phys(address));
 }
 
 static void swiotlb_print_info(unsigned long bytes)
@@ -189,7 +154,7 @@ swiotlb_init_with_default_size(size_t default_size)
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
+	io_tlb_start = alloc_bootmem_low_pages(bytes);
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
 	io_tlb_end = io_tlb_start + bytes;
@@ -245,7 +210,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
+		io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+							order);
 		if (io_tlb_start)
 			break;
 		order--;
@@ -315,20 +281,10 @@ cleanup1:
 	return -ENOMEM;
 }
 
-static inline int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
+static int is_swiotlb_buffer(phys_addr_t paddr)
 {
-	return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
-}
-
-static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
-{
-	return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
-}
-
-static int is_swiotlb_buffer(char *addr)
-{
-	return addr >= io_tlb_start && addr < io_tlb_end;
+	return paddr >= virt_to_phys(io_tlb_start) &&
+		paddr < virt_to_phys(io_tlb_end);
 }
 
 /*
@@ -561,9 +517,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		dma_mask = hwdev->coherent_dma_mask;
 
 	ret = (void *)__get_free_pages(flags, order);
-	if (ret &&
-	    !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
-				   size)) {
+	if (ret && swiotlb_virt_to_bus(hwdev, ret) + size > dma_mask) {
 		/*
 		 * The allocated memory isn't reachable by the device.
 		 */
@@ -585,7 +539,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	dev_addr = swiotlb_virt_to_bus(hwdev, ret);
 
 	/* Confirm address can be DMA'd by device */
-	if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
+	if (dev_addr + size > dma_mask) {
 		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
 		       (unsigned long long)dma_mask,
 		       (unsigned long long)dev_addr);
@@ -601,11 +555,13 @@ EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
 void
 swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-		      dma_addr_t dma_handle)
+		      dma_addr_t dev_addr)
 {
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
 	WARN_ON(irqs_disabled());
-	if (!is_swiotlb_buffer(vaddr))
-		free_pages((unsigned long) vaddr, get_order(size));
+	if (!is_swiotlb_buffer(paddr))
+		free_pages((unsigned long)vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 		do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
@@ -625,12 +581,15 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
 	       "device %s\n", size, dev ? dev_name(dev) : "?");
 
-	if (size > io_tlb_overflow && do_panic) {
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Memory would be corrupted\n");
-		if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Random memory would be DMAed\n");
-	}
+	if (size <= io_tlb_overflow || !do_panic)
+		return;
+
+	if (dir == DMA_BIDIRECTIONAL)
+		panic("DMA: Random memory could be DMA accessed\n");
+	if (dir == DMA_FROM_DEVICE)
+		panic("DMA: Random memory could be DMA written\n");
+	if (dir == DMA_TO_DEVICE)
+		panic("DMA: Random memory could be DMA read\n");
 }
 
 /*
@@ -646,7 +605,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    struct dma_attrs *attrs)
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
+	dma_addr_t dev_addr = phys_to_dma(dev, phys);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
@@ -655,8 +614,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(dev, dev_addr, size) &&
-	    !range_needs_mapping(phys, size))
+	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
 		return dev_addr;
 
 	/*
@@ -673,7 +631,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (address_needs_mapping(dev, dev_addr, size))
+	if (!dma_capable(dev, dev_addr, size))
 		panic("map_single: bounce buffer is not DMA'ble");
 
 	return dev_addr;
@@ -691,19 +649,25 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
 static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 			 size_t size, int dir)
 {
-	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
-	if (is_swiotlb_buffer(dma_addr)) {
-		do_unmap_single(hwdev, dma_addr, size, dir);
+	if (is_swiotlb_buffer(paddr)) {
+		do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
 		return;
 	}
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
 
-	dma_mark_clean(dma_addr, size);
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
@@ -728,19 +692,19 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
-	if (is_swiotlb_buffer(dma_addr)) {
-		sync_single(hwdev, dma_addr, size, dir, target);
+	if (is_swiotlb_buffer(paddr)) {
+		sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
 		return;
 	}
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
 
-	dma_mark_clean(dma_addr, size);
+	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void
@@ -817,10 +781,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 
 	for_each_sg(sgl, sg, nelems, i) {
 		phys_addr_t paddr = sg_phys(sg);
-		dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr);
+		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
 
-		if (range_needs_mapping(paddr, sg->length) ||
-		    address_needs_mapping(hwdev, dev_addr, sg->length)) {
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length)) {
 			void *map = map_single(hwdev, sg_phys(sg),
 					       sg->length, dir);
 			if (!map) {

Re: [PATCH -v2 0/7] powerpc: use asm-generic/dma-mapping-common.h

[Benjamin Herrenschmidt]

On Thu, 2009-08-27 at 09:22 +0200, Ingo Molnar wrote:
> 
> ah, yes, they are stable/fine. I've put it into a separate branch 
> for you.
> 
> Ben, please pull the latest iommu-for-powerpc git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git
> iommu-for-powerpc
> 
> And i could pull back the new bits from you once you have the new 
> patches added and are happy with them. [I suspect you dont want the 
> diffstat below in the powerpc tree]
> 
> That was the plan, right?

Sure, no problem. I'll stick that in powerpc-next tomorrow hopefully.

Cheers,
Ben.