Merge branch 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
  dma-debug: make memory range checks more consistent
  dma-debug: warn of unmapping an invalid dma address
  dma-debug: fix dma_debug_add_bus() definition for !CONFIG_DMA_API_DEBUG
  dma-debug/x86: register pci bus for dma-debug leak detection
  dma-debug: add a check dma memory leaks
  dma-debug: add checks for kernel text and rodata
  dma-debug: print stacktrace of mapping path on unmap error
  dma-debug: Documentation update
  dma-debug: x86 architecture bindings
  dma-debug: add function to dump dma mappings
  dma-debug: add checks for sync_single_sg_*
  dma-debug: add checks for sync_single_range_*
  dma-debug: add checks for sync_single_*
  dma-debug: add checking for [alloc|free]_coherent
  dma-debug: add add checking for map/unmap_sg
  dma-debug: add checking for map/unmap_page/single
  dma-debug: add core checking functions
  dma-debug: add debugfs interface
  dma-debug: add kernel command line parameters
  dma-debug: add initialization code
  ...

Fix trivial conflicts due to whitespace changes in arch/x86/kernel/pci-nommu.c

40 files changed, 1899 insertions, 844 deletions

diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 2a3fcc55e98..d9aa43d78bc 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -609,3 +609,109 @@ size is the size (and should be a page-sized multiple).
 The return value will be either a pointer to the processor virtual
 address of the memory, or an error (via PTR_ERR()) if any part of the
 region is occupied.
+
+Part III - Debug drivers use of the DMA-API
+-------------------------------------------
+
+The DMA-API as described above as some constraints. DMA addresses must be
+released with the corresponding function with the same size for example. With
+the advent of hardware IOMMUs it becomes more and more important that drivers
+do not violate those constraints. In the worst case such a violation can
+result in data corruption up to destroyed filesystems.
+
+To debug drivers and find bugs in the usage of the DMA-API checking code can
+be compiled into the kernel which will tell the developer about those
+violations. If your architecture supports it you can select the "Enable
+debugging of DMA-API usage" option in your kernel configuration. Enabling this
+option has a performance impact. Do not enable it in production kernels.
+
+If you boot the resulting kernel will contain code which does some bookkeeping
+about what DMA memory was allocated for which device. If this code detects an
+error it prints a warning message with some details into your kernel log. An
+example warning message may look like this:
+
+------------[ cut here ]------------
+WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
+	check_unmap+0x203/0x490()
+Hardware name:
+forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
+	function [device address=0x00000000640444be] [size=66 bytes] [mapped as
+single] [unmapped as page]
+Modules linked in: nfsd exportfs bridge stp llc r8169
+Pid: 0, comm: swapper Tainted: G        W  2.6.28-dmatest-09289-g8bb99c0 #1
+Call Trace:
+ <IRQ>  [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
+ [<ffffffff80647b70>] _spin_unlock+0x10/0x30
+ [<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
+ [<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
+ [<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
+ [<ffffffff80252f96>] queue_work+0x56/0x60
+ [<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
+ [<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
+ [<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
+ [<ffffffff80235177>] find_busiest_group+0x207/0x8a0
+ [<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
+ [<ffffffff803c7ea3>] check_unmap+0x203/0x490
+ [<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
+ [<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
+ [<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
+ [<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
+ [<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
+ [<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
+ [<ffffffff8020c093>] ret_from_intr+0x0/0xa
+ <EOI> <4>---[ end trace f6435a98e2a38c0e ]---
+
+The driver developer can find the driver and the device including a stacktrace
+of the DMA-API call which caused this warning.
+
+Per default only the first error will result in a warning message. All other
+errors will only silently counted. This limitation exist to prevent the code
+from flooding your kernel log. To support debugging a device driver this can
+be disabled via debugfs. See the debugfs interface documentation below for
+details.
+
+The debugfs directory for the DMA-API debugging code is called dma-api/. In
+this directory the following files can currently be found:
+
+	dma-api/all_errors	This file contains a numeric value. If this
+				value is not equal to zero the debugging code
+				will print a warning for every error it finds
+				into the kernel log. Be carefull with this
+				option. It can easily flood your logs.
+
+	dma-api/disabled	This read-only file contains the character 'Y'
+				if the debugging code is disabled. This can
+				happen when it runs out of memory or if it was
+				disabled at boot time
+
+	dma-api/error_count	This file is read-only and shows the total
+				numbers of errors found.
+
+	dma-api/num_errors	The number in this file shows how many
+				warnings will be printed to the kernel log
+				before it stops. This number is initialized to
+				one at system boot and be set by writing into
+				this file
+
+	dma-api/min_free_entries
+				This read-only file can be read to get the
+				minimum number of free dma_debug_entries the
+				allocator has ever seen. If this value goes
+				down to zero the code will disable itself
+				because it is not longer reliable.
+
+	dma-api/num_free_entries
+				The current number of free dma_debug_entries
+				in the allocator.
+
+If you have this code compiled into your kernel it will be enabled by default.
+If you want to boot without the bookkeeping anyway you can provide
+'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
+Notice that you can not enable it again at runtime. You have to reboot to do
+so.
+
+When the code disables itself at runtime this is most likely because it ran
+out of dma_debug_entries. These entries are preallocated at boot. The number
+of preallocated entries is defined per architecture. If it is too low for you
+boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
+architectural default.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index be3bde51b56..aeedb89a307 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -492,6 +492,16 @@ and is between 256 and 4096 characters. It is defined in the file
 			Range: 0 - 8192
 			Default: 64
 
+	dma_debug=off	If the kernel is compiled with DMA_API_DEBUG support
+			this option disables the debugging code at boot.
+
+	dma_debug_entries=<number>
+			This option allows to tune the number of preallocated
+			entries for DMA-API debugging code. One entry is
+			required per DMA-API allocation. Use this if the
+			DMA-API debugging code disables itself because the
+			architectural default is too low.
+
 	hpet=		[X86-32,HPET] option to control HPET usage
 			Format: { enable (default) | disable | force |
 				verbose }
diff --git a/arch/Kconfig b/arch/Kconfig
index 550dab22daa..830c16a2b80 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -106,3 +106,5 @@ config HAVE_CLK
 	  The <linux/clk.h> calls support software clock gating and
 	  thus are a key power management tool on many systems.
 
+config HAVE_DMA_API_DEBUG
+	bool
diff --git a/arch/ia64/dig/Makefile b/arch/ia64/dig/Makefile
index 5c0283830bd..2f7caddf093 100644
--- a/arch/ia64/dig/Makefile
+++ b/arch/ia64/dig/Makefile
@@ -7,8 +7,8 @@
 
 obj-y := setup.o
 ifeq ($(CONFIG_DMAR), y)
-obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o dig_vtd_iommu.o
+obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o
 else
 obj-$(CONFIG_IA64_GENERIC) += machvec.o
 endif
-obj-$(CONFIG_IA64_DIG_VTD) += dig_vtd_iommu.o
+
diff --git a/arch/ia64/dig/dig_vtd_iommu.c b/arch/ia64/dig/dig_vtd_iommu.c
deleted file mode 100644
index 1c8a079017a..00000000000
--- a/arch/ia64/dig/dig_vtd_iommu.c
+++ /dev/null
@@ -1,59 +0,0 @@
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/intel-iommu.h>
-
-void *
-vtd_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		 gfp_t flags)
-{
-	return intel_alloc_coherent(dev, size, dma_handle, flags);
-}
-EXPORT_SYMBOL_GPL(vtd_alloc_coherent);
-
-void
-vtd_free_coherent(struct device *dev, size_t size, void *vaddr,
-		 dma_addr_t dma_handle)
-{
-	intel_free_coherent(dev, size, vaddr, dma_handle);
-}
-EXPORT_SYMBOL_GPL(vtd_free_coherent);
-
-dma_addr_t
-vtd_map_single_attrs(struct device *dev, void *addr, size_t size,
-		     int dir, struct dma_attrs *attrs)
-{
-	return intel_map_single(dev, (phys_addr_t)addr, size, dir);
-}
-EXPORT_SYMBOL_GPL(vtd_map_single_attrs);
-
-void
-vtd_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
-		       int dir, struct dma_attrs *attrs)
-{
-	intel_unmap_single(dev, iova, size, dir);
-}
-EXPORT_SYMBOL_GPL(vtd_unmap_single_attrs);
-
-int
-vtd_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
-		 int dir, struct dma_attrs *attrs)
-{
-	return intel_map_sg(dev, sglist, nents, dir);
-}
-EXPORT_SYMBOL_GPL(vtd_map_sg_attrs);
-
-void
-vtd_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
-		   int nents, int dir, struct dma_attrs *attrs)
-{
-	intel_unmap_sg(dev, sglist, nents, dir);
-}
-EXPORT_SYMBOL_GPL(vtd_unmap_sg_attrs);
-
-int
-vtd_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(vtd_dma_mapping_error);
diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c
index 2769dbfd03b..e4a80d82e3d 100644
--- a/arch/ia64/hp/common/hwsw_iommu.c
+++ b/arch/ia64/hp/common/hwsw_iommu.c
@@ -13,49 +13,34 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/swiotlb.h>
-
 #include <asm/machvec.h>
 
+extern struct dma_map_ops sba_dma_ops, swiotlb_dma_ops;
+
 /* swiotlb declarations & definitions: */
 extern int swiotlb_late_init_with_default_size (size_t size);
 
-/* hwiommu declarations & definitions: */
-
-extern ia64_mv_dma_alloc_coherent	sba_alloc_coherent;
-extern ia64_mv_dma_free_coherent	sba_free_coherent;
-extern ia64_mv_dma_map_single_attrs	sba_map_single_attrs;
-extern ia64_mv_dma_unmap_single_attrs	sba_unmap_single_attrs;
-extern ia64_mv_dma_map_sg_attrs		sba_map_sg_attrs;
-extern ia64_mv_dma_unmap_sg_attrs	sba_unmap_sg_attrs;
-extern ia64_mv_dma_supported		sba_dma_supported;
-extern ia64_mv_dma_mapping_error	sba_dma_mapping_error;
-
-#define hwiommu_alloc_coherent		sba_alloc_coherent
-#define hwiommu_free_coherent		sba_free_coherent
-#define hwiommu_map_single_attrs	sba_map_single_attrs
-#define hwiommu_unmap_single_attrs	sba_unmap_single_attrs
-#define hwiommu_map_sg_attrs		sba_map_sg_attrs
-#define hwiommu_unmap_sg_attrs		sba_unmap_sg_attrs
-#define hwiommu_dma_supported		sba_dma_supported
-#define hwiommu_dma_mapping_error	sba_dma_mapping_error
-#define hwiommu_sync_single_for_cpu	machvec_dma_sync_single
-#define hwiommu_sync_sg_for_cpu		machvec_dma_sync_sg
-#define hwiommu_sync_single_for_device	machvec_dma_sync_single
-#define hwiommu_sync_sg_for_device	machvec_dma_sync_sg
-
-
 /*
  * Note: we need to make the determination of whether or not to use
  * the sw I/O TLB based purely on the device structure.  Anything else
  * would be unreliable or would be too intrusive.
  */
-static inline int
-use_swiotlb (struct device *dev)
+static inline int use_swiotlb(struct device *dev)
 {
-	return dev && dev->dma_mask && !hwiommu_dma_supported(dev, *dev->dma_mask);
+	return dev && dev->dma_mask &&
+		!sba_dma_ops.dma_supported(dev, *dev->dma_mask);
 }
 
+struct dma_map_ops *hwsw_dma_get_ops(struct device *dev)
+{
+	if (use_swiotlb(dev))
+		return &swiotlb_dma_ops;
+	return &sba_dma_ops;
+}
+EXPORT_SYMBOL(hwsw_dma_get_ops);
+
 void __init
 hwsw_init (void)
 {
@@ -71,125 +56,3 @@ hwsw_init (void)
 #endif
 	}
 }
-
-void *
-hwsw_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
-{
-	if (use_swiotlb(dev))
-		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
-	else
-		return hwiommu_alloc_coherent(dev, size, dma_handle, flags);
-}
-
-void
-hwsw_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle)
-{
-	if (use_swiotlb(dev))
-		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-	else
-		hwiommu_free_coherent(dev, size, vaddr, dma_handle);
-}
-
-dma_addr_t
-hwsw_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
-		       struct dma_attrs *attrs)
-{
-	if (use_swiotlb(dev))
-		return swiotlb_map_single_attrs(dev, addr, size, dir, attrs);
-	else
-		return hwiommu_map_single_attrs(dev, addr, size, dir, attrs);
-}
-EXPORT_SYMBOL(hwsw_map_single_attrs);
-
-void
-hwsw_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
-			 int dir, struct dma_attrs *attrs)
-{
-	if (use_swiotlb(dev))
-		return swiotlb_unmap_single_attrs(dev, iova, size, dir, attrs);
-	else
-		return hwiommu_unmap_single_attrs(dev, iova, size, dir, attrs);
-}
-EXPORT_SYMBOL(hwsw_unmap_single_attrs);
-
-int
-hwsw_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
-		   int dir, struct dma_attrs *attrs)
-{
-	if (use_swiotlb(dev))
-		return swiotlb_map_sg_attrs(dev, sglist, nents, dir, attrs);
-	else
-		return hwiommu_map_sg_attrs(dev, sglist, nents, dir, attrs);
-}
-EXPORT_SYMBOL(hwsw_map_sg_attrs);
-
-void
-hwsw_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
-		     int dir, struct dma_attrs *attrs)
-{
-	if (use_swiotlb(dev))
-		return swiotlb_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
-	else
-		return hwiommu_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
-}
-EXPORT_SYMBOL(hwsw_unmap_sg_attrs);
-
-void
-hwsw_sync_single_for_cpu (struct device *dev, dma_addr_t addr, size_t size, int dir)
-{
-	if (use_swiotlb(dev))
-		swiotlb_sync_single_for_cpu(dev, addr, size, dir);
-	else
-		hwiommu_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-void
-hwsw_sync_sg_for_cpu (struct device *dev, struct scatterlist *sg, int nelems, int dir)
-{
-	if (use_swiotlb(dev))
-		swiotlb_sync_sg_for_cpu(dev, sg, nelems, dir);
-	else
-		hwiommu_sync_sg_for_cpu(dev, sg, nelems, dir);
-}
-
-void
-hwsw_sync_single_for_device (struct device *dev, dma_addr_t addr, size_t size, int dir)
-{
-	if (use_swiotlb(dev))
-		swiotlb_sync_single_for_device(dev, addr, size, dir);
-	else
-		hwiommu_sync_single_for_device(dev, addr, size, dir);
-}
-
-void
-hwsw_sync_sg_for_device (struct device *dev, struct scatterlist *sg, int nelems, int dir)
-{
-	if (use_swiotlb(dev))
-		swiotlb_sync_sg_for_device(dev, sg, nelems, dir);
-	else
-		hwiommu_sync_sg_for_device(dev, sg, nelems, dir);
-}
-
-int
-hwsw_dma_supported (struct device *dev, u64 mask)
-{
-	if (hwiommu_dma_supported(dev, mask))
-		return 1;
-	return swiotlb_dma_supported(dev, mask);
-}
-
-int
-hwsw_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return hwiommu_dma_mapping_error(dev, dma_addr) ||
-		swiotlb_dma_mapping_error(dev, dma_addr);
-}
-
-EXPORT_SYMBOL(hwsw_dma_mapping_error);
-EXPORT_SYMBOL(hwsw_dma_supported);
-EXPORT_SYMBOL(hwsw_alloc_coherent);
-EXPORT_SYMBOL(hwsw_free_coherent);
-EXPORT_SYMBOL(hwsw_sync_single_for_cpu);
-EXPORT_SYMBOL(hwsw_sync_single_for_device);
-EXPORT_SYMBOL(hwsw_sync_sg_for_cpu);
-EXPORT_SYMBOL(hwsw_sync_sg_for_device);
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 6d5e6c5630e..56ceb68eb99 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -36,6 +36,7 @@
 #include <linux/bitops.h>         /* hweight64() */
 #include <linux/crash_dump.h>
 #include <linux/iommu-helper.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/delay.h>		/* ia64_get_itc() */
 #include <asm/io.h>
@@ -908,11 +909,13 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-dma_addr_t
-sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
-		     struct dma_attrs *attrs)
+static dma_addr_t sba_map_page(struct device *dev, struct page *page,
+			       unsigned long poff, size_t size,
+			       enum dma_data_direction dir,
+			       struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
+	void *addr = page_address(page) + poff;
 	dma_addr_t iovp;
 	dma_addr_t offset;
 	u64 *pdir_start;
@@ -990,7 +993,14 @@ sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
 #endif
 	return SBA_IOVA(ioc, iovp, offset);
 }
-EXPORT_SYMBOL(sba_map_single_attrs);
+
+static dma_addr_t sba_map_single_attrs(struct device *dev, void *addr,
+				       size_t size, enum dma_data_direction dir,
+				       struct dma_attrs *attrs)
+{
+	return sba_map_page(dev, virt_to_page(addr),
+			    (unsigned long)addr & ~PAGE_MASK, size, dir, attrs);
+}
 
 #ifdef ENABLE_MARK_CLEAN
 static SBA_INLINE void
@@ -1026,8 +1036,8 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size)
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
-			    int dir, struct dma_attrs *attrs)
+static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
+			   enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 #if DELAYED_RESOURCE_CNT > 0
@@ -1094,7 +1104,12 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif /* DELAYED_RESOURCE_CNT == 0 */
 }
-EXPORT_SYMBOL(sba_unmap_single_attrs);
+
+void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
+			    enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	sba_unmap_page(dev, iova, size, dir, attrs);
+}
 
 /**
  * sba_alloc_coherent - allocate/map shared mem for DMA
@@ -1104,7 +1119,7 @@ EXPORT_SYMBOL(sba_unmap_single_attrs);
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-void *
+static void *
 sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
 {
 	struct ioc *ioc;
@@ -1167,7 +1182,8 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-void sba_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle)
+static void sba_free_coherent (struct device *dev, size_t size, void *vaddr,
+			       dma_addr_t dma_handle)
 {
 	sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL);
 	free_pages((unsigned long) vaddr, get_order(size));
@@ -1422,8 +1438,9 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev,
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
-		     int dir, struct dma_attrs *attrs)
+static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
+			    int nents, enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	int coalesced, filled = 0;
@@ -1502,7 +1519,6 @@ int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
 
 	return filled;
 }
-EXPORT_SYMBOL(sba_map_sg_attrs);
 
 /**
  * sba_unmap_sg_attrs - unmap Scatter/Gather list
@@ -1514,8 +1530,9 @@ EXPORT_SYMBOL(sba_map_sg_attrs);
  *
  * See Documentation/PCI/PCI-DMA-mapping.txt
  */
-void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
-			int nents, int dir, struct dma_attrs *attrs)
+static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
+			       int nents, enum dma_data_direction dir,
+			       struct dma_attrs *attrs)
 {
 #ifdef ASSERT_PDIR_SANITY
 	struct ioc *ioc;
@@ -1551,7 +1568,6 @@ void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
 #endif
 
 }
-EXPORT_SYMBOL(sba_unmap_sg_attrs);
 
 /**************************************************************
 *
@@ -2064,6 +2080,8 @@ static struct acpi_driver acpi_sba_ioc_driver = {
 	},
 };
 
+extern struct dma_map_ops swiotlb_dma_ops;
+
 static int __init
 sba_init(void)
 {
@@ -2077,6 +2095,7 @@ sba_init(void)
 	 * a successful kdump kernel boot is to use the swiotlb.
 	 */
 	if (is_kdump_kernel()) {
+		dma_ops = &swiotlb_dma_ops;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to initialize software I/O TLB:"
 				  " Try machvec=dig boot option");
@@ -2092,6 +2111,7 @@ sba_init(void)
 		 * If we didn't find something sba_iommu can claim, we
 		 * need to setup the swiotlb and switch to the dig machvec.
 		 */
+		dma_ops = &swiotlb_dma_ops;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to find SBA IOMMU or initialize "
 			      "software I/O TLB: Try machvec=dig boot option");
@@ -2138,15 +2158,13 @@ nosbagart(char *str)
 	return 1;
 }
 
-int
-sba_dma_supported (struct device *dev, u64 mask)
+static int sba_dma_supported (struct device *dev, u64 mask)
 {
 	/* make sure it's at least 32bit capable */
 	return ((mask & 0xFFFFFFFFUL) == 0xFFFFFFFFUL);
 }
 
-int
-sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+static int sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return 0;
 }
@@ -2176,7 +2194,22 @@ sba_page_override(char *str)
 
 __setup("sbapagesize=",sba_page_override);
 
-EXPORT_SYMBOL(sba_dma_mapping_error);
-EXPORT_SYMBOL(sba_dma_supported);
-EXPORT_SYMBOL(sba_alloc_coherent);
-EXPORT_SYMBOL(sba_free_coherent);
+struct dma_map_ops sba_dma_ops = {
+	.alloc_coherent		= sba_alloc_coherent,
+	.free_coherent		= sba_free_coherent,
+	.map_page		= sba_map_page,
+	.unmap_page		= sba_unmap_page,
+	.map_sg			= sba_map_sg_attrs,
+	.unmap_sg		= sba_unmap_sg_attrs,
+	.sync_single_for_cpu	= machvec_dma_sync_single,
+	.sync_sg_for_cpu	= machvec_dma_sync_sg,
+	.sync_single_for_device	= machvec_dma_sync_single,
+	.sync_sg_for_device	= machvec_dma_sync_sg,
+	.dma_supported		= sba_dma_supported,
+	.mapping_error		= sba_dma_mapping_error,
+};
+
+void sba_dma_init(void)
+{
+	dma_ops = &sba_dma_ops;
+}
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 1f912d92758..36c0009dbec 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -11,99 +11,128 @@
 
 #define ARCH_HAS_DMA_GET_REQUIRED_MASK
 
-struct dma_mapping_ops {
-	int             (*mapping_error)(struct device *dev,
-					 dma_addr_t dma_addr);
-	void*           (*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp);
-	void            (*free_coherent)(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t      (*map_single)(struct device *hwdev, unsigned long ptr,
-				size_t size, int direction);
-	void            (*unmap_single)(struct device *dev, dma_addr_t addr,
-				size_t size, int direction);
-	void            (*sync_single_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, size_t size,
-				int direction);
-	void            (*sync_single_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, size_t size,
-				int direction);
-	void            (*sync_single_range_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size, int direction);
-	void            (*sync_single_range_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size, int direction);
-	void            (*sync_sg_for_cpu)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				int direction);
-	void            (*sync_sg_for_device)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				int direction);
-	int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
-				int nents, int direction);
-	void            (*unmap_sg)(struct device *hwdev,
-				struct scatterlist *sg, int nents,
-				int direction);
-	int             (*dma_supported_op)(struct device *hwdev, u64 mask);
-	int		is_phys;
-};
-
-extern struct dma_mapping_ops *dma_ops;
+extern struct dma_map_ops *dma_ops;
 extern struct ia64_machine_vector ia64_mv;
 extern void set_iommu_machvec(void);
 
-#define dma_alloc_coherent(dev, size, handle, gfp)	\
-	platform_dma_alloc_coherent(dev, size, handle, (gfp) | GFP_DMA)
+extern void machvec_dma_sync_single(struct device *, dma_addr_t, size_t,
+				    enum dma_data_direction);
+extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int,
+				enum dma_data_direction);
 
-/* coherent mem. is cheap */
-static inline void *
-dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		      gfp_t flag)
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *daddr, gfp_t gfp)
 {
-	return dma_alloc_coherent(dev, size, dma_handle, flag);
+	struct dma_map_ops *ops = platform_dma_get_ops(dev);
+	return ops->alloc_coherent(dev, size, daddr, gfp);
 }
-#define dma_free_coherent	platform_dma_free_coherent
-static inline void
-dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-		     dma_addr_t dma_handle)
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *caddr, dma_addr_t daddr)
+{
+	struct dma_map_ops *ops = platform_dma_get_ops(dev);
+	ops->free_coherent(dev, size, caddr, daddr);