Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin
   Murphy, Christoph Hellwig)

 - restructure the PCIe peer to peer mapping support (Logan Gunthorpe)

 - allow the IOMMU code to communicate an optional DMA mapping length
   and use that in scsi and libata (John Garry)

 - split the global swiotlb lock (Tianyu Lan)

 - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang,
   Lukas Bulwahn, Robin Murphy)

* tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits)
  swiotlb: fix passing local variable to debugfs_create_ulong()
  dma-mapping: reformat comment to suppress htmldoc warning
  PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg()
  RDMA/rw: drop pci_p2pdma_[un]map_sg()
  RDMA/core: introduce ib_dma_pci_p2p_dma_supported()
  nvme-pci: convert to using dma_map_sgtable()
  nvme-pci: check DMA ops when indicating support for PCI P2PDMA
  iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg
  iommu: Explicitly skip bus address marked segments in __iommu_map_sg()
  dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support
  dma-direct: support PCI P2PDMA pages in dma-direct map_sg
  dma-mapping: allow EREMOTEIO return code for P2PDMA transfers
  PCI/P2PDMA: Introduce helpers for dma_map_sg implementations
  PCI/P2PDMA: Attempt to set map_type if it has not been set
  lib/scatterlist: add flag for indicating P2PDMA segments in an SGL
  swiotlb: clean up some coding style and minor issues
  dma-mapping: update comment after dmabounce removal
  scsi: sd: Add a comment about limiting max_sectors to shost optimal limit
  ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors
  scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit
  ...

48 files changed, 833 insertions, 1694 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 22d7b5127184..9dc68a12a5bf 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5999,8 +5999,11 @@
 			it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst)
 
 	swiotlb=	[ARM,IA-64,PPC,MIPS,X86]
-			Format: { <int> | force | noforce }
+			Format: { <int> [,<int>] | force | noforce }
 			<int> -- Number of I/O TLB slabs
+			<int> -- Second integer after comma. Number of swiotlb
+				 areas with their own lock. Will be rounded up
+				 to a power of 2.
 			force -- force using of bounce buffers even if they
 			         wouldn't be automatically used by the kernel
 			noforce -- Never use bounce buffers (for debugging)
diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 6d6d0edd2d27..829f20a193ca 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -206,6 +206,20 @@ others should not be larger than the returned value.
 
 ::
 
+	size_t
+	dma_opt_mapping_size(struct device *dev);
+
+Returns the maximum optimal size of a mapping for the device.
+
+Mapping larger buffers may take much longer in certain scenarios. In
+addition, for high-rate short-lived streaming mappings, the upfront time
+spent on the mapping may account for an appreciable part of the total
+request lifetime. As such, if splitting larger requests incurs no
+significant performance penalty, then device drivers are advised to
+limit total DMA streaming mappings length to the returned value.
+
+::
+
 	bool
 	dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 
diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst
index 03ec9cf01181..cbd14124a667 100644
--- a/Documentation/x86/x86_64/boot-options.rst
+++ b/Documentation/x86/x86_64/boot-options.rst
@@ -287,11 +287,13 @@ iommu options only relevant to the AMD GART hardware IOMMU:
 iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU
 implementation:
 
-    swiotlb=<pages>[,force]
-      <pages>
-        Prereserve that many 128K pages for the software IO bounce buffering.
+    swiotlb=<slots>[,force,noforce]
+      <slots>
+        Prereserve that many 2K slots for the software IO bounce buffering.
       force
         Force all IO through the software TLB.
+      noforce
+        Do not initialize the software TLB.
 
 
 Miscellaneous
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 53e6a1da9af5..87badeae3181 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -15,13 +15,12 @@ config ARM
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
-	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB || !MMU
-	select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB || !MMU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_TEARDOWN_DMA_OPS if MMU
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index c8e198631d41..d2fdb1796f48 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -1,11 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config SA1111
 	bool
-	select DMABOUNCE if !ARCH_PXA
-
-config DMABOUNCE
-	bool
-	select ZONE_DMA
+	select ZONE_DMA if ARCH_SA1100
 
 config KRAIT_L2_ACCESSORS
 	bool
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 8cd574be94cf..7bae8cbaafe7 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -6,7 +6,6 @@
 obj-y				+= firmware.o
 
 obj-$(CONFIG_SA1111)		+= sa1111.o
-obj-$(CONFIG_DMABOUNCE)		+= dmabounce.o
 obj-$(CONFIG_KRAIT_L2_ACCESSORS) += krait-l2-accessors.o
 obj-$(CONFIG_SHARP_LOCOMO)	+= locomo.o
 obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
deleted file mode 100644
index 7996c04393d5..000000000000
--- a/arch/arm/common/dmabounce.c
+++ /dev/null
@@ -1,582 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  arch/arm/common/dmabounce.c
- *
- *  Special dma_{map/unmap/dma_sync}_* routines for systems that have
- *  limited DMA windows. These functions utilize bounce buffers to
- *  copy data to/from buffers located outside the DMA region. This
- *  only works for systems in which DMA memory is at the bottom of
- *  RAM, the remainder of memory is at the top and the DMA memory
- *  can be marked as ZONE_DMA. Anything beyond that such as discontiguous
- *  DMA windows will require custom implementations that reserve memory
- *  areas at early bootup.
- *
- *  Original version by Brad Parker (brad@heeltoe.com)
- *  Re-written by Christopher Hoover <ch@murgatroid.com>
- *  Made generic by Deepak Saxena <dsaxena@plexity.net>
- *
- *  Copyright (C) 2002 Hewlett Packard Company.
- *  Copyright (C) 2004 MontaVista Software, Inc.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/page-flags.h>
-#include <linux/device.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-map-ops.h>
-#include <linux/dmapool.h>
-#include <linux/list.h>
-#include <linux/scatterlist.h>
-
-#include <asm/cacheflush.h>
-#include <asm/dma-iommu.h>
-
-#undef STATS
-
-#ifdef STATS
-#define DO_STATS(X) do { X ; } while (0)
-#else
-#define DO_STATS(X) do { } while (0)
-#endif
-
-/* ************************************************** */
-
-struct safe_buffer {
-	struct list_head node;
-
-	/* original request */
-	void		*ptr;
-	size_t		size;
-	int		direction;
-
-	/* safe buffer info */
-	struct dmabounce_pool *pool;
-	void		*safe;
-	dma_addr_t	safe_dma_addr;
-};
-
-struct dmabounce_pool {
-	unsigned long	size;
-	struct dma_pool	*pool;
-#ifdef STATS
-	unsigned long	allocs;
-#endif
-};
-
-struct dmabounce_device_info {
-	struct device *dev;
-	struct list_head safe_buffers;
-#ifdef STATS
-	unsigned long total_allocs;
-	unsigned long map_op_count;
-	unsigned long bounce_count;
-	int attr_res;
-#endif
-	struct dmabounce_pool	small;
-	struct dmabounce_pool	large;
-
-	rwlock_t lock;
-
-	int (*needs_bounce)(struct device *, dma_addr_t, size_t);
-};
-
-#ifdef STATS
-static ssize_t dmabounce_show(struct device *dev, struct device_attribute *attr,
-			      char *buf)
-{
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	return sprintf(buf, "%lu %lu %lu %lu %lu %lu\n",
-		device_info->small.allocs,
-		device_info->large.allocs,
-		device_info->total_allocs - device_info->small.allocs -
-			device_info->large.allocs,
-		device_info->total_allocs,
-		device_info->map_op_count,
-		device_info->bounce_count);
-}
-
-static DEVICE_ATTR(dmabounce_stats, 0400, dmabounce_show, NULL);
-#endif
-
-
-/* allocate a 'safe' buffer and keep track of it */
-static inline struct safe_buffer *
-alloc_safe_buffer(struct dmabounce_device_info *device_info, void *ptr,
-		  size_t size, enum dma_data_direction dir)
-{
-	struct safe_buffer *buf;
-	struct dmabounce_pool *pool;
-	struct device *dev = device_info->dev;
-	unsigned long flags;
-
-	dev_dbg(dev, "%s(ptr=%p, size=%d, dir=%d)\n",
-		__func__, ptr, size, dir);
-
-	if (size <= device_info->small.size) {
-		pool = &device_info->small;
-	} else if (size <= device_info->large.size) {
-		pool = &device_info->large;
-	} else {
-		pool = NULL;
-	}
-
-	buf = kmalloc(sizeof(struct safe_buffer), GFP_ATOMIC);
-	if (buf == NULL) {
-		dev_warn(dev, "%s: kmalloc failed\n", __func__);
-		return NULL;
-	}
-
-	buf->ptr = ptr;
-	buf->size = size;
-	buf->direction = dir;
-	buf->pool = pool;
-
-	if (pool) {
-		buf->safe = dma_pool_alloc(pool->pool, GFP_ATOMIC,
-					   &buf->safe_dma_addr);
-	} else {
-		buf->safe = dma_alloc_coherent(dev, size, &buf->safe_dma_addr,
-					       GFP_ATOMIC);
-	}
-
-	if (buf->safe == NULL) {
-		dev_warn(dev,
-			 "%s: could not alloc dma memory (size=%d)\n",
-			 __func__, size);
-		kfree(buf);
-		return NULL;
-	}
-
-#ifdef STATS
-	if (pool)
-		pool->allocs++;
-	device_info->total_allocs++;
-#endif
-
-	write_lock_irqsave(&device_info->lock, flags);
-	list_add(&buf->node, &device_info->safe_buffers);
-	write_unlock_irqrestore(&device_info->lock, flags);
-
-	return buf;
-}
-
-/* determine if a buffer is from our "safe" pool */
-static inline struct safe_buffer *
-find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_addr)
-{
-	struct safe_buffer *b, *rb = NULL;
-	unsigned long flags;
-
-	read_lock_irqsave(&device_info->lock, flags);
-
-	list_for_each_entry(b, &device_info->safe_buffers, node)
-		if (b->safe_dma_addr <= safe_dma_addr &&
-		    b->safe_dma_addr + b->size > safe_dma_addr) {
-			rb = b;
-			break;
-		}
-
-	read_unlock_irqrestore(&device_info->lock, flags);
-	return rb;
-}
-
-static inline void
-free_safe_buffer(struct dmabounce_device_info *device_info, struct safe_buffer *buf)
-{
-	unsigned long flags;
-
-	dev_dbg(device_info->dev, "%s(buf=%p)\n", __func__, buf);
-
-	write_lock_irqsave(&device_info->lock, flags);
-
-	list_del(&buf->node);
-
-	write_unlock_irqrestore(&device_info->lock, flags);
-
-	if (buf->pool)
-		dma_pool_free(buf->pool->pool, buf->safe, buf->safe_dma_addr);
-	else
-		dma_free_coherent(device_info->dev, buf->size, buf->safe,
-				    buf->safe_dma_addr);
-
-	kfree(buf);
-}
-
-/* ************************************************** */
-
-static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
-		dma_addr_t dma_addr, const char *where)
-{
-	if (!dev || !dev->archdata.dmabounce)
-		return NULL;
-	if (dma_mapping_error(dev, dma_addr)) {
-		dev_err(dev, "Trying to %s invalid mapping\n", where);
-		return NULL;
-	}
-	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
-}
-
-static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	if (!dev || !dev->archdata.dmabounce)
-		return 0;
-
-	if (dev->dma_mask) {
-		unsigned long limit, mask = *dev->dma_mask;
-
-		limit = (mask + 1) & ~mask;
-		if (limit && size > limit) {
-			dev_err(dev, "DMA mapping too big (requested %#x "
-				"mask %#Lx)\n", size, *dev->dma_mask);
-			return -E2BIG;
-		}
-
-		/* Figure out if we need to bounce from the DMA mask. */
-		if ((dma_addr | (dma_addr + size - 1)) & ~mask)
-			return 1;
-	}
-
-	return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
-}
-
-static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-				    enum dma_data_direction dir,
-				    unsigned long attrs)
-{
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	struct safe_buffer *buf;
-
-	if (device_info)
-		DO_STATS ( device_info->map_op_count++ );
-
-	buf = alloc_safe_buffer(device_info, ptr, size, dir);
-	if (buf == NULL) {
-		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
-		       __func__, ptr);
-		return DMA_MAPPING_ERROR;
-	}
-
-	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-		buf->safe, buf->safe_dma_addr);
-
-	if ((dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) &&
-	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
-		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
-			__func__, ptr, buf->safe, size);
-		memcpy(buf->safe, ptr, size);
-	}
-
-	return buf->safe_dma_addr;
-}
-
-static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
-				size_t size, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	BUG_ON(buf->size != size);
-	BUG_ON(buf->direction != dir);
-
-	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-		buf->safe, buf->safe_dma_addr);
-
-	DO_STATS(dev->archdata.dmabounce->bounce_count++);
-
-	if ((dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) &&
-	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
-		void *ptr = buf->ptr;
-
-		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
-			__func__, buf->safe, ptr, size);
-		memcpy(ptr, buf->safe, size);
-
-		/*
-		 * Since we may have written to a page cache page,
-		 * we need to ensure that the data will be coherent
-		 * with user mappings.
-		 */
-		__cpuc_flush_dcache_area(ptr, size);
-	}
-	free_safe_buffer(dev->archdata.dmabounce, buf);
-}
-
-/* ************************************************** */
-
-/*
- * see if a buffer address is in an 'unsafe' range.  if it is
- * allocate a 'safe' buffer and copy the unsafe buffer into it.
- * substitute the safe buffer for the unsafe one.
- * (basically move the buffer from an unsafe area to a safe one)
- */
-static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	dma_addr_t dma_addr;
-	int ret;
-
-	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
-		__func__, page, offset, size, dir);
-
-	dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;
-
-	ret = needs_bounce(dev, dma_addr, size);
-	if (ret < 0)
-		return DMA_MAPPING_ERROR;
-
-	if (ret == 0) {
-		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
-		return dma_addr;
-	}
-
-	if (PageHighMem(page)) {
-		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
-		return DMA_MAPPING_ERROR;
-	}
-
-	return map_single(dev, page_address(page) + offset, size, dir, attrs);
-}
-
-/*
- * see if a mapped address was really a "safe" buffer and if so, copy
- * the data from the safe buffer back to the unsafe buffer and free up
- * the safe buffer.  (basically return things back to the way they
- * should be)
- */
-static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	struct safe_buffer *buf;
-
-	dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
-		__func__, dma_addr, size, dir);
-
-	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
-	if (!buf) {
-		arm_dma_ops.sync_single_for_cpu(dev, dma_addr, size, dir);
-		return;
-	}
-
-	unmap_single(dev, buf, size, dir, attrs);
-}
-
-static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
-		size_t sz, enum dma_data_direction dir)
-{
-	struct safe_buffer *buf;
-	unsigned long off;
-
-	dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n",
-		__func__, addr, sz, dir);
-
-	buf = find_safe_buffer_dev(dev, addr, __func__);
-	if (!buf)
-		return 1;
-
-	off = addr - buf->safe_dma_addr;
-
-	BUG_ON(buf->direction != dir);
-
-	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n",
-		__func__, buf->ptr, virt_to_dma(dev, buf->ptr), off,
-		buf->safe, buf->safe_dma_addr);
-
-	DO_STATS(dev->archdata.dmabounce->bounce_count++);
-
-	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
-		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
-			__func__, buf->safe + off, buf->ptr + off, sz);
-		memcpy(buf->ptr + off, buf->safe + off, sz);
-	}
-	return 0;
-}
-
-static void dmabounce_sync_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (!__dmabounce_sync_for_cpu(dev, handle, size, dir))
-		return;
-
-	arm_dma_ops.sync_single_for_cpu(dev, handle, size, dir);
-}
-
-static int __dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
-		size_t sz, enum dma_data_direction dir)
-{
-	struct safe_buffer *buf;
-	unsigned long off;
-
-	dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n",
-		__func__, addr, sz, dir);
-
-	buf = find_safe_buffer_dev(dev, addr, __func__);
-	if (!buf)
-		return 1;
-
-	off = addr - buf->safe_dma_addr;
-
-	BUG_ON(buf->direction != dir);
-
-	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n",
-		__func__, buf->ptr, virt_to_dma(dev, buf->ptr), off,
-		buf->safe, buf->safe_dma_addr);
-
-	DO_STATS(dev->archdata.dmabounce->bounce_count++);
-
-	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
-		dev_dbg(dev, "%s: copy out unsafe %p to safe %p, size %d\n",
-			__func__,buf->ptr + off, buf->safe + off, sz);
-		memcpy(buf->safe + off, buf->ptr + off, sz);
-	}
-	return 0;
-}
-
-static void dmabounce_sync_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (!__dmabounce_sync_for_device(dev, handle, size, dir))
-		return;
-
-	arm_dma_ops.sync_single_for_device(dev, handle, size, dir);
-}
-
-static int dmabounce_dma_supported(struct device *dev, u64 dma_mask)
-{
-	if (dev->archdata.dmabounce)
-		return 0;
-
-	return arm_dma_ops.dma_supported(dev, dma_mask);
-}
-
-static const struct dma_map_ops dmabounce_ops = {
-	.alloc			= arm_dma_alloc,
-	.free			= arm_dma_free,
-	.mmap			= arm_dma_mmap,
-	.get_sgtable		= arm_dma_get_sgtable,
-	.map_page		= dmabounce_map_page,
-	.unmap_page		= dmabounce_unmap_page,
-	.sync_single_for_cpu	= dmabounce_sync_for_cpu,
-	.sync_single_for_device	= dmabounce_sync_for_device,
-	.map_sg			= arm_dma_map_sg,
-	.unmap_sg		= arm_dma_unmap_sg,
-	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.dma_supported		= dmabounce_dma_supported,
-};
-
-static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
-		const char *name, unsigned long size)
-{
-	pool->size = size;
-	DO_STATS(pool->allocs = 0);
-	pool->pool = dma_pool_create(name, dev, size,
-				     0 /* byte alignment */,
-				     0 /* no page-crossing issues */);
-
-	return pool->pool ? 0 : -ENOMEM;
-}
-
-int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-		unsigned long large_buffer_size,
-		int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
-{
-	struct dmabounce_device_info *device_info;
-	int ret;
-
-	device_info = kmalloc(sizeof(struct dmabounce_device_info), GFP_ATOMIC);
-	if (!device_info) {
-		dev_err(dev,
-			"Could not allocated dmabounce_device_info\n");
-		return -ENOMEM;
-	}
-
-	ret = dmabounce_init_pool(&device_info->small, dev,
-				  "small_dmabounce_pool", small_buffer_size);
-	if (ret) {
-		dev_err(dev,
-			"dmabounce: could not allocate DMA pool for %ld byte objects\n",
-			small_buffer_size);
-		goto err_free;
-	}
-
-	if (large_buffer_size) {
-		ret = dmabounce_init_pool(&device_info->large, dev,
-					  "large_dmabounce_pool",
-					  large_buffer_size);
-		if (ret) {
-			dev_err(dev,
-				"dmabounce: could not allocate DMA pool for %ld byte objects\n",
-				large_buffer_size);
-			goto err_destroy;
-		}
-	}
-
-	device_info->dev = dev;
-	INIT_LIST_HEAD(&device_info->safe_buffers);
-	rwlock_init(&device_info->lock);
-	device_info->needs_bounce = needs_bounce_fn;
-
-#ifdef STATS
-	device_info->total_allocs = 0;
-	device_info->map_op_count = 0;
-	device_info->bounce_count = 0;
-	device_info->attr_res = device_create_file(dev, &dev_attr_dmabounce_stats);
-#endif
-
-	dev->archdata.dmabounce = device_info;
-	set_dma_ops(dev, &dmabounce_ops);
-
-	dev_info(dev, "dmabounce: registered device\n");
-
-	return 0;
-
- err_destroy:
-	dma_pool_destroy(device_info->small.pool);
- err_free:
-	kfree(device_info);
-	return ret;
-}
-EXPORT_SYMBOL(dmabounce_register_dev);
-
-void dmabounce_unregister_dev(struct device *dev)
-{
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-
-	dev->archdata.dmabounce = NULL;
-	set_dma_ops(dev, NULL);
-
-	if (!device_info) {
-		dev_warn(dev,
-			 "Never registered with dmabounce but attempting"
-			 "to unregister!\n");
-		return;
-	}
-
-	if (!list_empty(&device_info->safe_buffers)) {
-		dev_err(dev,
-			"Removing from dmabounce with pending buffers!\n");