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
  ...

16 files changed, 99 insertions, 1429 deletions

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");
-		BUG();
-	}
-
-	if (device_info->small.pool)
-		dma_pool_destroy(device_info->small.pool);
-	if (device_info->large.pool)
-		dma_pool_destroy(device_info->large.pool);
-
-#ifdef STATS
-	if (device_info->attr_res == 0)
-		device_remove_file(dev, &dev_attr_dmabounce_stats);
-#endif
-
-	kfree(device_info);
-
-	dev_info(dev, "dmabounce: device unregistered\n");
-}
-EXPORT_SYMBOL(dmabounce_unregister_dev);
-
-MODULE_AUTHOR("Christopher Hoover <ch@hpl.hp.com>, Deepak Saxena <dsaxena@plexity.net>");
-MODULE_DESCRIPTION("Special dma_{map/unmap/dma_sync}_* routines for systems with limited DMA windows");
-MODULE_LICENSE("GPL");
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 2343e2b6214d..f5e6990b8856 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -1389,70 +1389,9 @@ void sa1111_driver_unregister(struct sa1111_driver *driver)
 }
 EXPORT_SYMBOL(sa1111_driver_unregister);
 
-#ifdef CONFIG_DMABOUNCE
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-	/*
-	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-	 * User's Guide" mentions that jumpers R51 and R52 control the
-	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-	 * SDRAM bank 1 on Neponset). The default configuration selects
-	 * Assabet, so any address in bank 1 is necessarily invalid.
-	 */
-	return (machine_is_assabet() || machine_is_pfs168()) &&
-		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
-}
-
-static int sa1111_notifier_call(struct notifier_block *n, unsigned long action,
-	void *data)
-{
-	struct sa1111_dev *dev = to_sa1111_device(data);
-
-	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
-		if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL) {
-			int ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
-					sa1111_needs_bounce);
-			if (ret)
-				dev_err(&dev->dev, "failed to register with dmabounce: %d\n", ret);
-		}
-		break;
-
-	case BUS_NOTIFY_DEL_DEVICE:
-		if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL)
-			dmabounce_unregister_dev(&dev->dev);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block sa1111_bus_notifier = {
-	.notifier_call = sa1111_notifier_call,
-};
-#endif
-
 static int __init sa1111_init(void)
 {
 	int ret = bus_register(&sa1111_bus_type);
-#ifdef CONFIG_DMABOUNCE
-	if (ret == 0)
-		bus_register_notifier(&sa1111_bus_type, &sa1111_bus_notifier);
-#endif
 	if (ret == 0)
 		platform_driver_register(&sa1111_device_driver);
 	return ret;
@@ -1461,9 +1400,6 @@ static int __init sa1111_init(void)
 static void __exit sa1111_exit(void)
 {
 	platform_driver_unregister(&sa1111_device_driver);
-#ifdef CONFIG_DMABOUNCE
-	bus_unregister_notifier(&sa1111_bus_type, &sa1111_bus_notifier);
-#endif
 	bus_unregister(&sa1111_bus_type);
 }
 
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index be666f58bf7a..8754c0f5fc90 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -6,9 +6,6 @@
 #define ASMARM_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_DMABOUNCE
-	struct dmabounce_device_info *dmabounce;
-#endif
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
 #endif
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index 77fcb7ee5ec9..4f7bcde03abb 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -1,48 +1 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_ARM_DMA_DIRECT_H
-#define ASM_ARM_DMA_DIRECT_H 1
-
-#include <asm/memory.h>
-
-/*
- * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private
- * functions used internally by the DMA-mapping API to provide DMA
- * addresses. They must not be used by drivers.
- */
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	if (dev && dev->dma_range_map)
-		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
-	return (dma_addr_t)__pfn_to_bus(pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	unsigned long pfn = __bus_to_pfn(addr);
-
-	if (dev && dev->dma_range_map)
-		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
-	return pfn;
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	if (dev)
-		return pfn_to_dma(dev, virt_to_pfn(addr));
-
-	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	unsigned int offset = paddr & ~PAGE_MASK;
-	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
-{
-	unsigned int offset = dev_addr & ~PAGE_MASK;
-	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
-}
-
-#endif /* ASM_ARM_DMA_DIRECT_H */
+#include <mach/dma-direct.h>
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
deleted file mode 100644
index 77082246a5e1..000000000000
--- a/arch/arm/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASMARM_DMA_MAPPING_H
-#define ASMARM_DMA_MAPPING_H
-
-#ifdef __KERNEL__
-
-#include <linux/mm_types.h>
-#include <linux/scatterlist.h>
-
-#include <xen/xen.h>
-#include <asm/xen/hypervisor.h>
-
-extern const struct dma_map_ops arm_dma_ops;
-extern const struct dma_map_ops arm_coherent_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	if (IS_ENABLED(CONFIG_MMU) && !IS_ENABLED(CONFIG_ARM_LPAE))
-		return &arm_dma_ops;
-	return NULL;
-}
-
-/**
- * arm_dma_alloc - allocate consistent memory for DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: required memory size
- * @handle: bus-specific DMA address
- * @attrs: optinal attributes that specific mapping properties
- *
- * Allocate some memory for a device for performing DMA.  This function
- * allocates pages, and will return the CPU-viewed address, and sets @handle
- * to be the device-viewed address.
- */
-extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-			   gfp_t gfp, unsigned long attrs);
-
-/**
- * arm_dma_free - free memory allocated by arm_dma_alloc
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: size of memory originally requested in dma_alloc_coherent
- * @cpu_addr: CPU-view address returned from dma_alloc_coherent
- * @handle: device-view address returned from dma_alloc_coherent
- * @attrs: optinal attributes that specific mapping properties
- *
- * Free (and unmap) a DMA buffer previously allocated by
- * arm_dma_alloc().
- *
- * References to memory and mappings associated with cpu_addr/handle
- * during and after this call executing are illegal.
- */
-extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
-			 dma_addr_t handle, unsigned long attrs);
-
-/**
- * arm_dma_mmap - map a coherent DMA allocation into user space
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @vma: vm_area_struct describing requested user mapping
- * @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent
- * @handle: device-view address returned from dma_alloc_coherent
- * @size: size of memory originally requested in dma_alloc_coherent
- * @attrs: optinal attributes that specific mapping properties
- *
- * Map a coherent DMA buffer previously allocated by dma_alloc_coherent
- * into user space.  The coherent DMA buffer must not be freed by the
- * driver until the user space mapping has been released.
- */
-extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-			void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			unsigned long attrs);
-
-/*
- * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
- * and utilize bounce buffers as needed to work around limited DMA windows.
- *
- * On the SA-1111, a bug limits DMA to only certain regions of RAM.
- * On the IXP425, the PCI inbound window is 64MB (256MB total RAM)
- * On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM)
- *
- * The following are helper functions used by the dmabounce subystem
- *
- */
-
-/**
- * dmabounce_register_dev
- *
- * @dev: valid struct device pointer
- * @small_buf_size: size of buffers to use with small buffer pool
- * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
- * @needs_bounce_fn: called to determine whether buffer needs bouncing
- *
- * This function should be called by low-level platform code to register
- * a device as requireing DMA buffer bouncing. The function will allocate
- * appropriate DMA pools for the device.
- */
-extern int dmabounce_register_dev(struct device *, unsigned long,
-		unsigned long, int (*)(struct device *, dma_addr_t, size_t));
-
-/**
- * dmabounce_unregister_dev
- *
- * @dev: valid struct device pointer
- *
- * This function should be called by low-level platform code when device
- * that was previously registered with dmabounce_register_dev is removed
- * from the system.
- *
- */
-extern void dmabounce_unregister_dev(struct device *);
-
-
-
-/*
- * The scatter list versions of the above methods.
- */
-extern int arm_dma_map_sg(struct device *, struct scatterlist *, int,
-		enum dma_data_direction, unsigned long attrs);
-extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int,
-		enum dma_data_direction, unsigned long attrs);
-extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-
-#endif /* __KERNEL__ */
-#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index f673e13e0f94..a55a9038abc8 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -378,8 +378,6 @@ static inline unsigned long __virt_to_idmap(unsigned long x)
 #ifndef __virt_to_bus
 #define __virt_to_bus	__virt_to_phys
 #define __bus_to_virt	__phys_to_virt
-#define __pfn_to_bus(x)	__pfn_to_phys(x)
-#define __bus_to_pfn(x)	__phys_to_pfn(x)
 #endif
 
 /*
diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig
index bcd4e4ca34f7..acc10b1caa69 100644
--- a/arch/arm/mach-footbridge/Kconfig
+++ b/arch/arm/mach-footbridge/Kconfig
@@ -61,6 +61,7 @@ endmenu
 
 # Footbridge support
 config FOOTBRIDGE
+	select ARCH_HAS_PHYS_TO_DMA
 	bool
 
 # Footbridge in host mode
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index 322495df271d..5020eb96b025 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <linux/dma-direct.h>
 #include <video/vga.h>
 
 #include <asm/page.h>
@@ -335,17 +336,19 @@ unsigned long __bus_to_virt(unsigned long res)
 	return res;
 }
 EXPORT_SYMBOL(__bus_to_virt);
-
-unsigned long __pfn_to_bus(unsigned long pfn)
+#else
+static inline unsigned long fb_bus_sdram_offset(void)
 {
-	return __pfn_to_phys(pfn) + (fb_bus_sdram_offset() - PHYS_OFFSET);
+	return BUS_OFFSET;
 }
-EXPORT_SYMBOL(__pfn_to_bus);
+#endif /* CONFIG_FOOTBRIDGE_ADDIN */
 
-unsigned long __bus_to_pfn(unsigned long bus)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return __phys_to_pfn(bus - (fb_bus_sdram_offset() - PHYS_OFFSET));
+	return paddr + (fb_bus_sdram_offset() - PHYS_OFFSET);
 }
-EXPORT_SYMBOL(__bus_to_pfn);
 
-#endif
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+{
+	return dev_addr - (fb_bus_sdram_offset() - PHYS_OFFSET);
+}
diff --git a/arch/arm/mach-footbridge/include/mach/dma-direct.h b/arch/arm/mach-footbridge/include/mach/dma-direct.h
new file mode 100644
index 000000000000..01f9e8367c00
--- /dev/null
+++ b/arch/arm/mach-footbridge/include/mach/dma-direct.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef MACH_FOOTBRIDGE_DMA_DIRECT_H
+#define MACH_FOOTBRIDGE_DMA_DIRECT_H 1
+
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr);
+
+#endif /* MACH_FOOTBRIDGE_DMA_DIRECT_H */
diff --git a/arch/arm/mach-footbridge/include/mach/memory.h b/arch/arm/mach-footbridge/include/mach/memory.h
index 46fd4a8872b9..3a5d2638c18f 100644
--- a/arch/arm/mach-footbridge/include/mach/memory.h
+++ b/arch/arm/mach-footbridge/include/mach/memory.h
@@ -26,8 +26,6 @@
 #ifndef __ASSEMBLY__
 extern unsigned long __virt_to_bus(unsigned long);
 extern unsigned long __bus_to_virt(unsigned long);
-extern unsigned long __pfn_to_bus(unsigned long);
-extern unsigned long __bus_to_pfn(unsigned long);
 #endif
 #define __virt_to_bus	__virt_to_bus
 #define __bus_to_virt	__bus_to_virt
@@ -42,8 +40,6 @@ extern unsigned long __bus_to_pfn(unsigned long);
 #define BUS_OFFSET		0xe0000000
 #define __virt_to_bus(x)	((x) + (BUS_OFFSET - PAGE_OFFSET))
 #define __bus_to_virt(x)	((x) - (BUS_OFFSET - PAGE_OFFSET))
-#define __pfn_to_bus(x)		(__pfn_to_phys(x) + (BUS_OFFSET - PHYS_OFFSET))
-#define __bus_to_pfn(x)		__phys_to_pfn((x) - (BUS_OFFSET - PHYS_OFFSET))
 
 #else
 
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index db607955a7e4..5d4f977ac7d2 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -98,7 +98,7 @@ static int highbank_platform_notifier(struct notifier_block *nb,
 	if (of_property_read_bool(dev->of_node, "dma-coherent")) {
 		val = readl(sregs_base + reg);
 		writel(val | 0xff01, sregs_base + reg);
-		set_dma_ops(dev, &arm_coherent_dma_ops);
+		dev->dma_coherent = true;
 	}
 
 	return NOTIFY_OK;
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 883dab1b54f3..a6b621ff0b87 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -95,7 +95,7 @@ static int mvebu_hwcc_notifier(struct notifier_block *nb,
 
 	if (event != BUS_NOTIFY_ADD_DEVICE)
 		return NOTIFY_DONE;
-	set_dma_ops(dev, &arm_coherent_dma_ops);
+	dev->dma_coherent = true;
 
 	return NOTIFY_OK;
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1483b6a4319d..089c9c644cce 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -103,139 +103,6 @@ static struct arm_dma_buffer *arm_dma_buffer_find(void *virt)
  * before transfers and delay cache invalidation until transfer completion.
  *
  */
-static void __dma_page_cpu_to_dev(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-static void __dma_page_dev_to_cpu(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-/**
- * arm_dma_map_page - map a portion of a page for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page().
- */
-static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_cpu_to_dev(page, offset, size, dir);
-	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
-}
-
-static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
-}
-
-/**
- * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Unmap a page streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_page() 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.
- */
-static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
-				      handle & ~PAGE_MASK, size, dir);
-}
-
-static void arm_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned int offset = handle & (PAGE_SIZE - 1);
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-	__dma_page_dev_to_cpu(page, offset, size, dir);
-}
-
-static void arm_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned int offset = handle & (PAGE_SIZE - 1);
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-	__dma_page_cpu_to_dev(page, offset, size, dir);
-}
-
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- */
-static int arm_dma_supported(struct device *dev, u64 mask)
-{
-	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
-
-	/*
-	 * Translate the device's DMA mask to a PFN limit.  This
-	 * PFN number includes the page which we can DMA to.
-	 */
-	return dma_to_pfn(dev, mask) >= max_dma_pfn;
-}
-
-const struct dma_map_ops arm_dma_ops = {
-	.alloc			= arm_dma_alloc,
-	.free			= arm_dma_free,
-	.alloc_pages		= dma_direct_alloc_pages,
-	.free_pages		= dma_direct_free_pages,
-	.mmap			= arm_dma_mmap,
-	.get_sgtable		= arm_dma_get_sgtable,
-	.map_page		= arm_dma_map_page,
-	.unmap_page		= arm_dma_unmap_page,
-	.map_sg			= arm_dma_map_sg,
-	.unmap_sg		= arm_dma_unmap_sg,
-	.map_resource		= dma_direct_map_resource,
-	.sync_single_for_cpu	= arm_dma_sync_single_for_cpu,
-	.sync_single_for_device	= arm_dma_sync_single_for_device,
-	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.dma_supported		= arm_dma_supported,
-	.get_required_mask	= dma_direct_get_required_mask,
-};
-EXPORT_SYMBOL(arm_dma_ops);
-
-static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
-	dma_addr_t *handle, gfp_t gfp, unsigned long attrs);
-static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
-				  dma_addr_t handle, unsigned long attrs);
-static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs);
-
-const struct dma_map_ops arm_coherent_dma_ops = {
-	.alloc			= arm_coherent_dma_alloc,
-	.free			= arm_coherent_dma_free,
-	.alloc_pages		= dma_direct_alloc_pages,
-	.free_pages		= dma_direct_free_pages,
-	.mmap			= arm_coherent_dma_mmap,
-	.get_sgtable		= arm_dma_get_sgtable,
-	.map_page		= arm_coherent_dma_map_page,
-	.map_sg			= arm_dma_map_sg,
-	.map_resource		= dma_direct_map_resource,
-	.dma_supported		= arm_dma_supported,
-	.get_required_mask	= dma_direct_get_required_mask,
-};
-EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
@@ -725,7 +592,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	if (page) {
 		unsigned long flags;
 
-		*handle = pfn_to_dma(dev, page_to_pfn(page));
+		*handle = phys_to_dma(dev, page_to_phys(page));
 		buf->virt = args.want_vaddr ? addr : page;
 
 		spin_lock_irqsave(&arm_dma_bufs_lock, flags);
@@ -739,74 +606,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 }
 
 /*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-		    gfp_t gfp, unsigned long attrs)
-{
-	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
-
-	return __dma_alloc(dev, size, handle, gfp, prot, false,
-			   attrs, __builtin_return_address(0));
-}
-
-static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
-	dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true,
-			   attrs, __builtin_return_address(0));
-}
-
-static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	int ret = -ENXIO;
-	unsigned long nr_vma_pages = vma_pages(vma);
-	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long pfn = dma_to_pfn(dev, dma_addr);
-	unsigned long off = vma->vm_pgoff;
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      vma->vm_end - vma->vm_start,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-/*
- * Create userspace mapping for the DMA-coherent memory.
- */
-static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		 unsigned long attrs)
-{
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-/*
  * Free a buffer as defined by the above mapping.
  */
 static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 			   dma_addr_t handle, unsigned long attrs,
 			   bool is_coherent)
 {
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	struct page *page = phys_to_page(dma_to_phys(dev, handle));
 	struct arm_dma_buffer *buf;
 	struct arm_dma_free_args args = {
 		.dev = dev,
@@ -824,40 +630,6 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	kfree(buf);
 }
 
-void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		  dma_addr_t handle, unsigned long attrs)
-{
-	__arm_dma_free(dev, size, cpu_addr, handle, attrs, false);
-}
-
-static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
-				  dma_addr_t handle, unsigned long attrs)
-{
-	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
-}
-
-int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-		 void *cpu_addr, dma_addr_t handle, size_t size,
-		 unsigned long attrs)
-{
-	unsigned long pfn = dma_to_pfn(dev, handle);
-	struct page *page;
-	int ret;
-
-	/* If the PFN is not valid, we do not have a struct page */
-	if (!pfn_valid(pfn))
-		return -ENXIO;
-
-	page = pfn_to_page(pfn);
-
-	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-	if (unlikely(ret))
-		return ret;
-
-	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-	return 0;
-}
-
 static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
@@ -907,8 +679,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 
 /*
  * Make an area consistent for devices.
- * Note: Drivers should NOT use this function directly, as it will break
- * platforms with CONFIG_DMABOUNCE.
+ * Note: Drivers should NOT use this function directly.
  * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
  */
 static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
@@ -961,122 +732,6 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	}
 }
 
-/**
- * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the dma_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}.
- *
- * Device ownership issues as mentioned for dma_map_single are the same
- * here.
- */
-int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i, j, ret;
-
-	for_each_sg(sg, s, nents, i) {
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		s->dma_length = s->length;
-#endif
-		s->dma_address = ops->map_page(dev, sg_page(s), s->offset,
-						s->length, dir, attrs);
-		if (dma_mapping_error(dev, s->dma_address)) {
-			ret = -EIO;
-			goto bad_mapping;
-		}
-	}
-	return nents;
-
- bad_mapping:
-	for_each_sg(sg, s, i, j)
-		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
-	return ret;
-}
-
-/**
- * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
-}
-
-/**
- * arm_dma_sync_sg_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map (returned from dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- */
-void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length,
-					 dir);
-}
-
-/**
- * arm_dma_sync_sg_for_device
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map (returned from dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- */
-void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		ops->sync_single_for_device(dev, sg_dma_address(s), s->length,
-					    dir);
-}
-
-static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
-{
-	/*
-	 * When CONFIG_ARM_LPAE is set, physical address can extend above
-	 * 32-bits, which then can't be addressed by devices that only support
-	 * 32-bit DMA.
-	 * Use the generic dma-direct / swiotlb ops code in that case, as that
-	 * handles bounce buffering for us.
-	 */
-	if (IS_ENABLED(CONFIG_ARM_LPAE))
-		return NULL;
-	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
-}
-
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
 static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
@@ -1423,13 +1078,13 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
 		__free_from_pool(cpu_addr, size);
 }
 
-static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs,
-	    int coherent_flag)
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
 {
 	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	struct page **pages;
 	void *addr = NULL;
+	int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL;
 
 	*handle = DMA_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
@@ -1472,19 +1127,7 @@ err_buffer:
 	return NULL;
 }
 
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL);
-}
-
-static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
-		    dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
-	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT);
-}
-
-static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    unsigned long attrs)
 {
@@ -1498,35 +1141,24 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma
 	if (vma->vm_pgoff >= nr_pages)
 		return -ENXIO;
 
+	if (!dev->dma_coherent)
+		vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
 	err = vm_map_pages(vma, pages, nr_pages);
 	if (err)
 		pr_err("Remapping memory failed: %d\n", err);
 
 	return err;
 }
-static int arm_iommu_mmap_attrs(struct device *dev,
-		struct vm_area_struct *vma, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs)
-{
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
-	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-static int arm_coherent_iommu_mmap_attrs(struct device *dev,
-		struct vm_area_struct *vma, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs)
-{
-	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
 
 /*
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-	dma_addr_t handle, unsigned long attrs, int coherent_flag)
+static void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+	dma_addr_t handle, unsigned long attrs)
 {
+	int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL;
 	struct page **pages;
 	size = PAGE_ALIGN(size);
 
@@ -1548,19 +1180,6 @@ static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_ad
 	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
-static void arm_iommu_free_attrs(struct device *dev, size_t size,
-				 void *cpu_addr, dma_addr_t handle,
-				 unsigned long attrs)
-{
-	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
-}
-
-static void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
-		    void *cpu_addr, dma_addr_t handle, unsigned long attrs)
-{
-	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
-}
-
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 				 void *cpu_addr, dma_addr_t dma_addr,
 				 size_t size, unsigned long attrs)
@@ -1580,8 +1199,7 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
  */
 static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			  size_t size, dma_addr_t *handle,
-			  enum dma_data_direction dir, unsigned long attrs,
-			  bool is_coherent)
+			  enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova, iova_base;
@@ -1601,7 +1219,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
-		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
 		prot = __dma_info_to_prot(dir, attrs);
@@ -1621,9 +1239,20 @@ fail:
 	return ret;
 }
 
-static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		     enum dma_data_direction dir, unsigned long attrs,
-		     bool is_coherent)
+/**
+ * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map
+ * @dir: DMA transfer direction
+ *
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * The scatter gather list elements are merged together (if possible) and
+ * tagged with the appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}.
+ */
+static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *s = sg, *dma = sg, *start = sg;
 	int i, count = 0, ret;
@@ -1638,8 +1267,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
 			ret = __map_sg_chunk(dev, start, size,
-					     &dma->dma_address, dir, attrs,
-					     is_coherent);
+					     &dma->dma_address, dir, attrs);
 			if (ret < 0)
 				goto bad_mapping;
 
@@ -1653,8 +1281,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		}
 		size += s->length;
 	}
-	ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs,
-			     is_coherent);
+	ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs);
 	if (ret < 0)
 		goto bad_mapping;
 
@@ -1672,44 +1299,19 @@ bad_mapping:
 }
 
 /**
- * arm_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of i/o coherent buffers described by scatterlist in streaming
- * mode for DMA. The scatter gather list elements are merged together (if
- * possible) and tagged with the appropriate dma address and length. They are
- * obtained via sg_dma_{address,length}.
- */
-static int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, true);
-}
-
-/**
- * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
  * @dev: valid struct device pointer
  * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  *
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * The scatter gather list elements are merged together (if possible) and
- * tagged with the appropriate dma address and length. They are obtained via
- * sg_dma_{address,length}.
+ * Unmap a set of streaming mode DMA translations.  Again, CPU access
+ * rules concerning calls here are the same as for dma_unmap_single().
  */
-static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_map_sg(dev, sg, nents, dir, attrs, false);
-}
-
-static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir,
-		unsigned long attrs, bool is_coherent)
+static void arm_iommu_unmap_sg(struct device *dev,
+			       struct scatterlist *sg, int nents,
+			       enum dma_data_direction dir,
+			       unsigned long attrs)
 {
 	struct scatterlist *s;
 	int i;
@@ -1718,48 +1320,13 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 		if (sg_dma_len(s))
 			__iommu_remove_mapping(dev, sg_dma_address(s),
 					       sg_dma_len(s));
-		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			__dma_page_dev_to_cpu(sg_page(s), s->offset,
 					      s->length, dir);
 	}
 }
 
 /**
- * arm_coherent_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-static void arm_coherent_iommu_unmap_sg(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, true);
-}
-
-/**
- * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer
- * @sg: list of buffers
- * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
- * @dir: DMA transfer direction (same as was passed to dma_map_sg)
- *
- * Unmap a set of streaming mode DMA translations.  Again, CPU access
- * rules concerning calls here are the same as for dma_unmap_single().
- */
-static void arm_iommu_unmap_sg(struct device *dev,
-			       struct scatterlist *sg, int nents,
-			       enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	__iommu_unmap_sg(dev, sg, nents, dir, attrs, false);
-}
-
-/**
  * arm_iommu_sync_sg_for_cpu
  * @dev: valid struct device pointer
  * @sg: list of buffers
@@ -1773,6 +1340,9 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *s;
 	int i;
 
+	if (dev->dma_coherent)
+		return;
+
 	for_each_sg(sg, s, nents, i)
 		__dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
 
@@ -1792,22 +1362,24 @@ static void arm_iommu_sync_sg_for_device(struct device *dev,
 	struct scatterlist *s;
 	int i;
 
+	if (dev->dma_coherent)
+		return;
+
 	for_each_sg(sg, s, nents, i)
 		__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 }
 
-
 /**
- * arm_coherent_iommu_map_page
+ * arm_iommu_map_page
  * @dev: valid struct device pointer
  * @page: page that buffer resides in
  * @offset: offset into page for start of buffer
  * @size: size of buffer to map
  * @dir: DMA transfer direction
  *
- * Coherent IOMMU aware version of arm_dma_map_page()
+ * IOMMU aware version of arm_dma_map_page()
  */
-static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page,
+static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     unsigned long attrs)
 {
@@ -1815,6 +1387,9 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	dma_addr_t dma_addr;
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
+	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
@@ -1832,50 +1407,6 @@ fail:
 }
 
 /**
- * arm_iommu_map_page
- * @dev: valid struct device pointer
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * IOMMU aware version of arm_dma_map_page()
- */
-static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
-{
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__dma_page_cpu_to_dev(page, offset, size, dir);
-
-	return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs);
-}
-
-/**
- * arm_coherent_iommu_unmap_page
- * @dev: valid struct device pointer
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Coherent IOMMU aware version of arm_dma_unmap_page()
- */
-static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t iova = handle & PAGE_MASK;
-	int offset = handle & ~PAGE_MASK;
-	int len = PAGE_ALIGN(size + offset);
-
-	if (!iova)
-		return;
-
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
-}
-
-/**
  * arm_iommu_unmap_page
  * @dev: valid struct device pointer
  * @handle: DMA address of buffer
@@ -1889,15 +1420,17 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
 
 	if (!iova)
 		return;
 
-	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
+		page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 		__dma_page_dev_to_cpu(page, offset, size, dir);
+	}
 
 	iommu_unmap(mapping->domain, iova, len);
 	__free_iova(mapping, iova, len);
@@ -1965,12 +1498,13 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
 
-	if (!iova)
+	if (dev->dma_coherent || !iova)
 		return;
 
+	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	__dma_page_dev_to_cpu(page, offset, size, dir);
 }
 
@@ -1979,12 +1513,13 @@ static void arm_iommu_sync_single_for_device(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
 
-	if (!iova)
+	if (dev->dma_coherent || !iova)
 		return;
 
+	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
@@ -2006,26 +1541,6 @@ static const struct dma_map_ops iommu_ops = {
 
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
-
-	.dma_supported		= arm_dma_supported,
-};
-
-static const struct dma_map_ops iommu_coherent_ops = {
-	.alloc		= arm_coherent_iommu_alloc_attrs,
-	.free		= arm_coherent_iommu_free_attrs,
-	.mmap		= arm_coherent_iommu_mmap_attrs,
-	.get_sgtable	= arm_iommu_get_sgtable,
-
-	.map_page	= arm_coherent_iommu_map_page,
-	.unmap_page	= arm_coherent_iommu_unmap_page,
-
-	.map_sg		= arm_coherent_iommu_map_sg,
-	.unmap_sg	= arm_coherent_iommu_unmap_sg,
-
-	.map_resource	= arm_iommu_map_resource,
-	.unmap_resource	= arm_iommu_unmap_resource,
-
-	.dma_supported		= arm_dma_supported,
 };
 
 /**
@@ -2201,40 +1716,32 @@ void arm_iommu_detach_device(struct device *dev)
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
-	set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent));
+	set_dma_ops(dev, NULL);
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
-static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
-{
-	return coherent ? &iommu_coherent_ops : &iommu_ops;
-}
-
-static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu)
+static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				    const struct iommu_ops *iommu, bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
-	if (!iommu)
-		return false;
-
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
 				size, dev_name(dev));
-		return false;
+		return;
 	}
 
 	if (__arm_iommu_attach_device(dev, mapping)) {
 		pr_warn("Failed to attached device %s to IOMMU_mapping\n",
 				dev_name(dev));
 		arm_iommu_release_mapping(mapping);
-		return false;
+		return;
 	}
 
-	return true;
+	set_dma_ops(dev, &iommu_ops);
 }
 
 static void arm_teardown_iommu_dma_ops(struct device *dev)
@@ -2250,27 +1757,20 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 
 #else
 
-static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu)
+static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				    const struct iommu_ops *iommu, bool coherent)
 {
-	return false;
 }
 
 static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
-#define arm_get_iommu_dma_map_ops arm_get_dma_map_ops
-
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	const struct dma_map_ops *dma_ops;
-
 	dev->archdata.dma_coherent = coherent;
-#ifdef CONFIG_SWIOTLB
 	dev->dma_coherent = coherent;
-#endif
 
 	/*
 	 * Don't override the dma_ops if they have already been set. Ideally
@@ -2280,12 +1780,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu))
-		dma_ops = arm_get_iommu_dma_map_ops(coherent);
-	else
-		dma_ops = arm_get_dma_map_ops(coherent);
-
-	set_dma_ops(dev, dma_ops);
+	if (iommu)
+		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
@@ -2301,7 +1797,6 @@ void arch_teardown_dma_ops(struct device *dev)
 	set_dma_ops(dev, NULL);
 }
 
-#ifdef CONFIG_SWIOTLB
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
@@ -2329,4 +1824,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 {
 	__arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
 }
-#endif /* CONFIG_SWIOTLB */