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");
-		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 */
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 9b999c0e8c37..29e2f55c6faa 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1060,6 +1060,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
+	dev->max_sectors = min(dev->max_sectors, sdev->host->max_sectors);
 	blk_queue_max_hw_sectors(q, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 4d98f931a13d..8367974b7998 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -274,33 +274,6 @@ static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	return 1;
 }
 
-static void rdma_rw_unmap_sg(struct ib_device *dev, struct scatterlist *sg,
-			     u32 sg_cnt, enum dma_data_direction dir)
-{
-	if (is_pci_p2pdma_page(sg_page(sg)))
-		pci_p2pdma_unmap_sg(dev->dma_device, sg, sg_cnt, dir);
-	else
-		ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
-}
-
-static int rdma_rw_map_sgtable(struct ib_device *dev, struct sg_table *sgt,
-			       enum dma_data_direction dir)
-{
-	int nents;
-
-	if (is_pci_p2pdma_page(sg_page(sgt->sgl))) {
-		if (WARN_ON_ONCE(ib_uses_virt_dma(dev)))
-			return 0;
-		nents = pci_p2pdma_map_sg(dev->dma_device, sgt->sgl,
-					  sgt->orig_nents, dir);
-		if (!nents)
-			return -EIO;
-		sgt->nents = nents;
-		return 0;
-	}
-	return ib_dma_map_sgtable_attrs(dev, sgt, dir, 0);
-}
-
 /**
  * rdma_rw_ctx_init - initialize a RDMA READ/WRITE context
  * @ctx:	context to initialize
@@ -327,7 +300,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 	};
 	int ret;
 
-	ret = rdma_rw_map_sgtable(dev, &sgt, dir);
+	ret = ib_dma_map_sgtable_attrs(dev, &sgt, dir, 0);
 	if (ret)
 		return ret;
 	sg_cnt = sgt.nents;
@@ -366,7 +339,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 	return ret;
 
 out_unmap_sg:
-	rdma_rw_unmap_sg(dev, sgt.sgl, sgt.orig_nents, dir);
+	ib_dma_unmap_sgtable_attrs(dev, &sgt, dir, 0);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_rw_ctx_init);
@@ -414,12 +387,12 @@ int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		return -EINVAL;
 	}
 
-	ret = rdma_rw_map_sgtable(dev, &sgt, dir);
+	ret = ib_dma_map_sgtable_attrs(dev, &sgt, dir, 0);
 	if (ret)
 		return ret;
 
 	if (prot_sg_cnt) {
-		ret = rdma_rw_map_sgtable(dev, &prot_sgt, dir);
+		ret = ib_dma_map_sgtable_attrs(dev, &prot_sgt, dir, 0);
 		if (ret)
 			goto out_unmap_sg;
 	}
@@ -486,9 +459,9 @@ out_free_ctx:
 	kfree(ctx->reg);
 out_unmap_prot_sg:
 	if (prot_sgt.nents)
-		rdma_rw_unmap_sg(dev, prot_sgt.sgl, prot_sgt.orig_nents, dir);
+		ib_dma_unmap_sgtable_attrs(dev, &prot_sgt, dir, 0);
 out_unmap_sg:
-	rdma_rw_unmap_sg(dev, sgt.sgl, sgt.orig_nents, dir);
+	ib_dma_unmap_sgtable_attrs(dev, &sgt, dir, 0);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_rw_ctx_signature_init);
@@ -621,7 +594,7 @@ void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		break;
 	}
 
-	rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy);
 
@@ -649,8 +622,8 @@ void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	kfree(ctx->reg);
 
 	if (prot_sg_cnt)
-		rdma_rw_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
-	rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+		ib_dma_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
+	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy_signature);
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 458fb6738223..376c4e3ae0e6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -21,6 +21,7 @@
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/list_sort.h>
+#include <linux/memremap.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -1062,15 +1063,30 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
+		dma_addr_t s_dma_addr = sg_dma_address(s);
 		unsigned int s_iova_off = sg_dma_address(s);
 		unsigned int s_length = sg_dma_len(s);
 		unsigned int s_iova_len = s->length;
 
-		s->offset += s_iova_off;
-		s->length = s_length;
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
+		if (sg_is_dma_bus_address(s)) {
+			if (i > 0)
+				cur = sg_next(cur);
+
+			sg_dma_unmark_bus_address(s);
+			sg_dma_address(cur) = s_dma_addr;
+			sg_dma_len(cur) = s_length;
+			sg_dma_mark_bus_address(cur);
+			count++;
+			cur_len = 0;
+			continue;
+		}
+
+		s->offset += s_iova_off;
+		s->length = s_length;
+
 		/*
 		 * Now fill in the real DMA data. If...
 		 * - there is a valid output segment to append to
@@ -1111,10 +1127,14 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		if (sg_dma_address(s) != DMA_MAPPING_ERROR)
-			s->offset += sg_dma_address(s);
-		if (sg_dma_len(s))
-			s->length = sg_dma_len(s);
+		if (sg_is_dma_bus_address(s)) {
+			sg_dma_unmark_bus_address(s);
+		} else {
+			if (sg_dma_address(s) != DMA_MAPPING_ERROR)
+				s->offset += sg_dma_address(s);
+			if (sg_dma_len(s))
+				s->length = sg_dma_len(s);
+		}
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 	}
@@ -1167,6 +1187,8 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
 	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
@@ -1196,6 +1218,30 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		size_t s_length = s->length;
 		size_t pad_len = (mask - iova_len + 1) & mask;
 
+		if (is_pci_p2pdma_page(sg_page(s))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, s);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				/*
+				 * iommu_map_sg() will skip this segment as
+				 * it is marked as a bus address,
+				 * __finalise_sg() will copy the dma address
+				 * into the output segment.
+				 */
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Mapping through host bridge should be
+				 * mapped with regular IOVAs, thus we
+				 * do nothing here and continue below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_restore_sg;
+			}
+		}
+
 		sg_dma_address(s) = s_iova_off;
 		sg_dma_len(s) = s_length;
 		s->offset -= s_iova_off;
@@ -1224,6 +1270,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
+	if (!iova_len)
+		return __finalise_sg(dev, sg, nents, 0);
+
 	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova) {
 		ret = -ENOMEM;
@@ -1245,7 +1294,7 @@ out_free_iova:
 out_restore_sg:
 	__invalidate_sg(sg, nents);
 out:
-	if (ret != -ENOMEM)
+	if (ret != -ENOMEM && ret != -EREMOTEIO)
 		return -EINVAL;
 	return ret;
 }
@@ -1253,7 +1302,7 @@ out:
 static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start, end;
+	dma_addr_t end = 0, start;
 	struct scatterlist *tmp;
 	int i;
 
@@ -1267,16 +1316,37 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 
 	/*
 	 * The scatterlist segments are mapped into a single
-	 * contiguous IOVA allocation, so this is incredibly easy.
+	 * contiguous IOVA allocation, the start and end points
+	 * just have to be determined.
 	 */
-	start = sg_dma_address(sg);
-	for_each_sg(sg_next(sg), tmp, nents - 1, i) {
+	for_each_sg(sg, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
 		if (sg_dma_len(tmp) == 0)
 			break;
-		sg = tmp;
+
+		start = sg_dma_address(tmp);
+		break;
 	}
-	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(dev, start, end - start);
+
+	nents -= i;
+	for_each_sg(tmp, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
+		if (sg_dma_len(tmp) == 0)
+			break;
+
+		end = sg_dma_address(tmp) + sg_dma_len(tmp);
+	}
+
+	if (end)
+		__iommu_dma_unmap(dev, start, end - start);
 }
 
 static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
@@ -1468,7 +1538,13 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
+	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
@@ -1488,6 +1564,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 };
 
 /*
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f53f8b2d27a5..780fb7071577 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2460,6 +2460,9 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			len = 0;
 		}
 
+		if (sg_is_dma_bus_address(sg))
+			goto next;
+
 		if (len) {
 			len += sg->length;
 		} else {
@@ -2467,6 +2470,7 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			start = s_phys;
 		}
 
+next:
 		if (++i < nents)
 			sg = sg_next(sg);
 	}
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index e44f565c5319..47d1983dfa2a 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
 static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct iova_domain *iovad;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2429b11eb9a8..af367b22871b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4198,7 +4198,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
-	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
+	if (ctrl->ops->supports_pci_p2pdma &&
+	    ctrl->ops->supports_pci_p2pdma(ctrl))
 		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
 
 	ns->ctrl = ctrl;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bdc0ff7ed9ab..1bdf714dcd9e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -504,7 +504,6 @@ struct nvme_ctrl_ops {
 	unsigned int flags;
 #define NVME_F_FABRICS			(1 << 0)
 #define NVME_F_METADATA_SUPPORTED	(1 << 1)
-#define NVME_F_PCI_P2PDMA		(1 << 2)
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
@@ -514,6 +513,7 @@ struct nvme_ctrl_ops {
 	void (*stop_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 	void (*print_device_info)(struct nvme_ctrl *ctrl);
+	bool (*supports_pci_p2pdma)(struct nvme_ctrl *ctrl);
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 71a4f26ba476..de1b4463142d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -230,11 +230,10 @@ struct nvme_iod {
 	bool use_sgl;
 	int aborted;
 	int npages;		/* In the PRP list. 0 means small pool in use */
-	int nents;		/* Used in scatterlist */
 	dma_addr_t first_dma;
 	unsigned int dma_len;	/* length of single DMA segment mapping */
 	dma_addr_t meta_dma;
-	struct scatterlist *sg;
+	struct sg_table sgt;
 };
 
 static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
@@ -524,7 +523,7 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 static void **nvme_pci_iod_list(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	return (void **)(iod->sg + blk_rq_nr_phys_segments(req));
+	return (void **)(iod->sgt.sgl + blk_rq_nr_phys_segments(req));
 }
 
 static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
@@ -576,17 +575,6 @@ static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
 	}
 }
 
-static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
-{
-	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-
-	if (is_pci_p2pdma_page(sg_page(iod->sg)))
-		pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents,
-				    rq_dma_dir(req));
-	else
-		dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req));
-}
-
 static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -597,9 +585,10 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		return;
 	}
 
-	WARN_ON_ONCE(!iod->nents);
+	WARN_ON_ONCE(!iod->sgt.nents);
+
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 
-	nvme_unmap_sg(dev, req);
 	if (iod->npages == 0)
 		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
 			      iod->first_dma);
@@ -607,7 +596,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		nvme_free_sgls(dev, req);
 	else
 		nvme_free_prps(dev, req);
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 }
 
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
@@ -630,7 +619,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct dma_pool *pool;
 	int length = blk_rq_payload_bytes(req);
-	struct scatterlist *sg = iod->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
 	int dma_len = sg_dma_len(sg);
 	u64 dma_addr = sg_dma_address(sg);
 	int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
@@ -702,16 +691,16 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 		dma_len = sg_dma_len(sg);
 	}
 done:
-	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sgt.sgl));
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
 	return BLK_STS_OK;
 free_prps:
 	nvme_free_prps(dev, req);
 	return BLK_STS_RESOURCE;
 bad_sgl:
-	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+	WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
 			"Invalid SGL for payload:%d nents:%d\n",
-			blk_rq_payload_bytes(req), iod->nents);
+			blk_rq_payload_bytes(req), iod->sgt.nents);
 	return BLK_STS_IOERR;
 }
 
@@ -737,12 +726,13 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
 }
 
 static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
-		struct request *req, struct nvme_rw_command *cmd, int entries)
+		struct request *req, struct nvme_rw_command *cmd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct dma_pool *pool;
 	struct nvme_sgl_desc *sg_list;
-	struct scatterlist *sg = iod->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
+	unsigned int entries = iod->sgt.nents;
 	dma_addr_t sgl_dma;
 	int i = 0;
 
@@ -840,7 +830,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret = BLK_STS_RESOURCE;
-	int nr_mapped;
+	int rc;
 
 	if (blk_rq_nr_phys_segments(req) == 1) {
 		struct bio_vec bv = req_bvec(req);
@@ -858,26 +848,25 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	}
 
 	iod->dma_len = 0;
-	iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
-	if (!iod->sg)
+	iod->sgt.sgl = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
+	if (!iod->sgt.sgl)
 		return BLK_STS_RESOURCE;
-	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
-	iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
-	if (!iod->nents)
+	sg_init_table(iod->sgt.sgl, blk_rq_nr_phys_segments(req));
+	iod->sgt.orig_nents = blk_rq_map_sg(req->q, req, iod->sgt.sgl);
+	if (!iod->sgt.orig_nents)
 		goto out_free_sg;
 
-	if (is_pci_p2pdma_page(sg_page(iod->sg)))
-		nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg,
-				iod->nents, rq_dma_dir(req), DMA_ATTR_NO_WARN);
-	else
-		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
-					     rq_dma_dir(req), DMA_ATTR_NO_WARN);
-	if (!nr_mapped)
+	rc = dma_map_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req),
+			     DMA_ATTR_NO_WARN);
+	if (rc) {
+		if (rc == -EREMOTEIO)
+			ret = BLK_STS_TARGET;
 		goto out_free_sg;
+	}
 
 	iod->use_sgl = nvme_pci_use_sgls(dev, req);
 	if (iod->use_sgl)
-		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped);
+		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw);
 	else
 		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
 	if (ret != BLK_STS_OK)
@@ -885,9 +874,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	return BLK_STS_OK;
 
 out_unmap_sg:
-	nvme_unmap_sg(dev, req);
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 out_free_sg:
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 	return ret;
 }
 
@@ -911,7 +900,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 
 	iod->aborted = 0;
 	iod->npages = -1;
-	iod->nents = 0;
+	iod->sgt.nents = 0;
 
 	ret = nvme_setup_cmd(req->q->queuedata, req);
 	if (ret)
@@ -2992,7 +2981,6 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 	return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
 }
 
-
 static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
 {
 	struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
@@ -3007,11 +2995,17 @@ static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
 		subsys->firmware_rev);
 }
 
+static bool nvme_pci_supports_pci_p2pdma(struct nvme_ctrl *ctrl)
+{
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
+
+	return dma_pci_p2pdma_supported(dev->dev);
+}
+
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
-	.flags			= NVME_F_METADATA_SUPPORTED |
-				  NVME_F_PCI_P2PDMA,
+	.flags			= NVME_F_METADATA_SUPPORTED,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
@@ -3019,6 +3013,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.submit_async_event	= nvme_pci_submit_async_event,
 	.get_address		= nvme_pci_get_address,
 	.print_device_info	= nvme_pci_print_device_info,
+	.supports_pci_p2pdma	= nvme_pci_supports_pci_p2pdma,
 };
 
 static int nvme_dev_map(struct nvme_dev *dev)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 09fdcac87d17..4597bca43a6d 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -415,7 +415,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
 	if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
 		goto out_free_rsp;
 
-	if (!ib_uses_virt_dma(ndev->device))
+	if (ib_dma_pci_p2p_dma_supported(ndev->device))
 		r->req.p2p_client = &ndev->device->dev;
 	r->send_sge.length = sizeof(*r->req.cqe);
 	r->send_sge.lkey = ndev->pd->local_dma_lkey;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 133c73207782..5cc7cba1941f 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -164,6 +164,11 @@ config PCI_PASID
 config PCI_P2PDMA
 	bool "PCI peer-to-peer transfer support"
 	depends on ZONE_DEVICE
+	#
+	# The need for the scatterlist DMA bus address flag means PCI P2PDMA
+	# requires 64bit
+	#
+	depends on 64BIT
 	select GENERIC_ALLOCATOR
 	help
 	  Enableѕ drivers to do PCI peer-to-peer transactions to and from
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 462b429ad243..4496a7c5c478 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -10,6 +10,7 @@
 
 #define pr_fmt(fmt) "pci-p2pdma: " fmt
 #include <linux/ctype.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -20,13 +21,6 @@
 #include <linux/seq_buf.h>
 #include <linux/xarray.h>
 
-enum pci_p2pdma_map_type {
-	PCI_P2PDMA_MAP_UNKNOWN = 0,
-	PCI_P2PDMA_MAP_NOT_SUPPORTED,
-	PCI_P2PDMA_MAP_BUS_ADDR,
-	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
 struct pci_p2pdma {
 	struct gen_pool *pool;
 	bool p2pmem_published;
@@ -854,6 +848,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 	struct pci_dev *provider = to_p2p_pgmap(pgmap)->provider;
 	struct pci_dev *client;
 	struct pci_p2pdma *p2pdma;
+	int dist;
 
 	if (!provider->p2pdma)
 		return PCI_P2PDMA_MAP_NOT_SUPPORTED;
@@ -870,74 +865,48 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 		type = xa_to_value(xa_load(&p2pdma->map_types,
 					   map_types_idx(client)));
 	rcu_read_unlock();
-	return type;
-}
 
-static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap,
-		struct device *dev, struct scatterlist *sg, int nents)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i) {
-		s->dma_address = sg_phys(s) + p2p_pgmap->bus_offset;
-		sg_dma_len(s) = s->length;
-	}
+	if (type == PCI_P2PDMA_MAP_UNKNOWN)
+		return calc_map_type_and_dist(provider, client, &dist, true);
 
-	return nents;
+	return type;
 }
 
 /**
- * pci_p2pdma_map_sg_attrs - map a PCI peer-to-peer scatterlist for DMA
- * @dev: device doing the DMA request
- * @sg: scatter list to map
- * @nents: elements in the scatterlist
- * @dir: DMA direction
- * @attrs: DMA attributes passed to dma_map_sg() (if called)
+ * pci_p2pdma_map_segment - map an sg segment determining the mapping type
+ * @state: State structure that should be declared outside of the for_each_sg()
+ *	loop and initialized to zero.
+ * @dev: DMA device that's doing the mapping operation
+ * @sg: scatterlist segment to map
  *
- * Scatterlists mapped with this function should be unmapped using
- * pci_p2pdma_unmap_sg_attrs().
+ * This is a helper to be used by non-IOMMU dma_map_sg() implementations where
+ * the sg segment is the same for the page_link and the dma_address.
  *
- * Returns the number of SG entries mapped or 0 on error.
+ * Attempt to map a single segment in an SGL with the PCI bus address.
+ * The segment must point to a PCI P2PDMA page and thus must be
+ * wrapped in a is_pci_p2pdma_page(sg_page(sg)) check.
+ *
+ * Returns the type of mapping used and maps the page if the type is
+ * PCI_P2PDMA_MAP_BUS_ADDR.
  */
-int pci_p2pdma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+enum pci_p2pdma_map_type
+pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
+		       struct scatterlist *sg)
 {
-	struct pci_p2pdma_pagemap *p2p_pgmap =
-		to_p2p_pgmap(sg_page(sg)->pgmap);
-
-	switch (pci_p2pdma_map_type(sg_page(sg)->pgmap, dev)) {
-	case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-		return dma_map_sg_attrs(dev, sg, nents, dir, attrs);
-	case PCI_P2PDMA_MAP_BUS_ADDR:
-		return __pci_p2pdma_map_sg(p2p_pgmap, dev, sg, nents);
-	default:
-		WARN_ON_ONCE(1);
-		return 0;
+	if (state->pgmap != sg_page(sg)->pgmap) {
+		state->pgmap = sg_page(sg)->pgmap;
+		state->map = pci_p2pdma_map_type(state->pgmap, dev);
+		state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 	}
-}
-EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg_attrs);
 
-/**
- * pci_p2pdma_unmap_sg_attrs - unmap a PCI peer-to-peer scatterlist that was
- *	mapped with pci_p2pdma_map_sg()
- * @dev: device doing the DMA request
- * @sg: scatter list to map
- * @nents: number of elements returned by pci_p2pdma_map_sg()
- * @dir: DMA direction
- * @attrs: DMA attributes passed to dma_unmap_sg() (if called)
- */
-void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	enum pci_p2pdma_map_type map_type;
-
-	map_type = pci_p2pdma_map_type(sg_page(sg)->pgmap, dev);
+	if (state->map == PCI_P2PDMA_MAP_BUS_ADDR) {
+		sg->dma_address = sg_phys(sg) + state->bus_off;
+		sg_dma_len(sg) = sg->length;
+		sg_dma_mark_bus_address(sg);
+	}
 
-	if (map_type == PCI_P2PDMA_MAP_THRU_HOST_BRIDGE)
-		dma_unmap_sg_attrs(dev, sg, nents, dir, attrs);
+	return state->map;
 }
-EXPORT_SYMBOL_GPL(pci_p2pdma_unmap_sg_attrs);
 
 /**
  * pci_p2pdma_enable_store - parse a configfs/sysfs attribute store
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index bbcb901f6926..26bf3b153595 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -236,6 +236,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	shost->dma_dev = dma_dev;
 
+	if (dma_dev->dma_mask) {
+		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_max_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	error = scsi_mq_setup_tags(shost);
 	if (error)
 		goto fail;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b59a71aedcd7..4dbd29ab1dcc 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1876,10 +1876,6 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
 	}
 
-	if (dev->dma_mask) {
-		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
-				dma_max_mapping_size(dev) >> SECTOR_SHIFT);
-	}
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 12bff64dade6..2f88c61216ee 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -225,6 +225,7 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
 {
 	struct Scsi_Host *shost = dev_to_shost(dev);
 	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
+	struct device *dma_dev = shost->dma_dev;
 
 	INIT_LIST_HEAD(&sas_host->rphy_list);
 	mutex_init(&sas_host->lock);
@@ -236,6 +237,11 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
 		dev_printk(KERN_ERR, dev, "fail to a bsg device %d\n",
 			   shost->host_no);
 
+	if (dma_dev->dma_mask) {
+		shost->opt_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 6f7a39b96750..8f79fa6318fe 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3297,6 +3297,13 @@ static int sd_revalidate_disk(struct gendisk *disk)
 				      (sector_t)BLK_DEF_MAX_SECTORS);
 	}
 
+	/*
+	 * Limit default to SCSI host optimal sector limit if set. There may be
+	 * an impact on performance for when the size of a request exceeds this
+	 * host limit.
+	 */
+	rw_max = min_not_zero(rw_max, sdp->host->opt_sectors);
+
 	/* Do not exceed controller limit */
 	rw_max = min(rw_max, queue_max_hw_sectors(q));
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index a6a87c5d1b05..94b305bbd621 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1251,7 +1251,8 @@ void usb_hcd_unlink_urb_from_ep(struct usb_hcd *hcd, struct urb *urb)
 EXPORT_SYMBOL_GPL(usb_hcd_unlink_urb_from_ep);
 
 /*
- * Some usb host controllers can only perform dma using a small SRAM area.
+ * Some usb host controllers can only perform dma using a small SRAM area,
+ * or have restrictions on addressable DRAM.
  * The usb core itself is however optimized for host controllers that can dma
  * using regular system memory - like pci devices doing bus mastering.
  *
@@ -3127,8 +3128,18 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr,
 	if (IS_ERR(hcd->localmem_pool))
 		return PTR_ERR(hcd->localmem_pool);
 
-	local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
-				  size, MEMREMAP_WC);
+	/*
+	 * if a physical SRAM address was passed, map it, otherwise
+	 * allocate system memory as a buffer.
+	 */
+	if (phys_addr)
+		local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
+					  size, MEMREMAP_WC);
+	else
+		local_mem = dmam_alloc_attrs(hcd->self.sysdev, size, &dma,
+					     GFP_KERNEL,
+					     DMA_ATTR_WRITE_COMBINE);
+
 	if (IS_ERR(local_mem))
 		return PTR_ERR(local_mem);
 
diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c
index feca826d3f6a..75c2b28b3379 100644
--- a/drivers/usb/host/ohci-sa1111.c
+++ b/drivers/usb/host/ohci-sa1111.c
@@ -203,6 +203,31 @@ static int ohci_hcd_sa1111_probe(struct sa1111_dev *dev)
 		goto err1;
 	}
 
+	/*
+	 * 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.
+	 *
+	 * 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.
+	 *
+	 * As a workaround, use a bounce buffer in addressable memory
+	 * as local_mem, relying on ZONE_DMA to provide an area that
+	 * fits within the above constraints.
+	 *
+	 * SZ_64K is an estimate for what size this might need.
+	 */
+	ret = usb_hcd_setup_local_mem(hcd, 0, 0, SZ_64K);
+	if (ret)
+		goto err1;
+
 	if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) {
 		dev_dbg(&dev->dev, "request_mem_region failed\n");
 		ret = -EBUSY;
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 0d5b06b3a4a6..010df04358aa 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,7 +11,17 @@
 
 struct cma;
 
+/*
+ * Values for struct dma_map_ops.flags:
+ *
+ * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can
+ * handle PCI P2PDMA pages in the map_sg/unmap_sg operation.
+ */
+#define DMA_F_PCI_P2PDMA_SUPPORTED     (1 << 0)
+
 struct dma_map_ops {
+	unsigned int flags;
+
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
 			unsigned long attrs);
@@ -69,6 +79,7 @@ struct dma_map_ops {
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
+	size_t (*opt_mapping_size)(void);
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
@@ -379,4 +390,57 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 
 extern const struct dma_map_ops dma_dummy_ops;
 
+enum pci_p2pdma_map_type {
+	/*
+	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally for indicating the mapping
+	 * type hasn't been calculated yet. Functions that return this enum
+	 * never return this value.
+	 */
+	PCI_P2PDMA_MAP_UNKNOWN = 0,
+
+	/*
+	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
+	 * traverse the host bridge and the host bridge is not in the
+	 * allowlist. DMA Mapping routines should return an error when
+	 * this is returned.
+	 */
+	PCI_P2PDMA_MAP_NOT_SUPPORTED,
+
+	/*
+	 * PCI_P2PDMA_BUS_ADDR: Indicates that two devices can talk to
+	 * each other directly through a PCI switch and the transaction will
+	 * not traverse the host bridge. Such a mapping should program
+	 * the DMA engine with PCI bus addresses.
+	 */
+	PCI_P2PDMA_MAP_BUS_ADDR,
+
+	/*
+	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
+	 * to each other, but the transaction traverses a host bridge on the
+	 * allowlist. In this case, a normal mapping either with CPU physical
+	 * addresses (in the case of dma-direct) or IOVA addresses (in the
+	 * case of IOMMUs) should be used to program the DMA engine.
+	 */
+	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
+};
+
+struct pci_p2pdma_map_state {
+	struct dev_pagemap *pgmap;
+	int map;
+	u64 bus_off;
+};
+
+#ifdef CONFIG_PCI_P2PDMA
+enum pci_p2pdma_map_type
+pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
+		       struct scatterlist *sg);
+#else /* CONFIG_PCI_P2PDMA */
+static inline enum pci_p2pdma_map_type
+pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
+		       struct scatterlist *sg)
+{
+	return PCI_P2PDMA_MAP_NOT_SUPPORTED;
+}
+#endif /* CONFIG_PCI_P2PDMA */
+
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index dca2b1355bb1..25a30906289d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -140,10 +140,12 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 bool dma_can_mmap(struct device *dev);
 int dma_supported(struct device *dev, u64 mask);
+bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+size_t dma_opt_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
@@ -250,6 +252,10 @@ static inline int dma_supported(struct device *dev, u64 mask)
 {
 	return 0;
 }
+static inline bool dma_pci_p2pdma_supported(struct device *dev)
+{
+	return false;
+}
 static inline int dma_set_mask(struct device *dev, u64 mask)
 {
 	return -EIO;
@@ -266,6 +272,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline size_t dma_opt_mapping_size(struct device *dev)
+{
+	return 0;
+}
 static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 320a70e40233..c6ba6d95d79c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
+unsigned long iova_rcache_range(void);
+
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 8318a97c9c61..2c07aa6b7665 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -30,10 +30,6 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
 					 unsigned int *nents, u32 length);
 void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl);
 void pci_p2pmem_publish(struct pci_dev *pdev, bool publish);
-int pci_p2pdma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
 int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev,
 			    bool *use_p2pdma);
 ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev,
@@ -83,17 +79,6 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev,
 static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
 {
 }
-static inline int pci_p2pdma_map_sg_attrs(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	return 0;
-}
-static inline void pci_p2pdma_unmap_sg_attrs(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
 static inline int pci_p2pdma_enable_store(const char *page,
 		struct pci_dev **p2p_dev, bool *use_p2pdma)
 {
@@ -119,16 +104,4 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client)
 	return pci_p2pmem_find_many(&client, 1);
 }
 
-static inline int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg,
-				    int nents, enum dma_data_direction dir)
-{
-	return pci_p2pdma_map_sg_attrs(dev, sg, nents, dir, 0);
-}
-
-static inline void pci_p2pdma_unmap_sg(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir)
-{
-	pci_p2pdma_unmap_sg_attrs(dev, sg, nents, dir, 0);
-}
-
 #endif /* _LINUX_PCI_P2P_H */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 7ff9d6386c12..375a5e90d86a 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -16,6 +16,9 @@ struct scatterlist {
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 	unsigned int	dma_length;
 #endif
+#ifdef CONFIG_PCI_P2PDMA
+	unsigned int    dma_flags;
+#endif
 };
 
 /*
@@ -245,6 +248,72 @@ static inline void sg_unmark_end(struct scatterlist *sg)
 	sg->page_link &= ~SG_END;
 }
 
+/*
+ * CONFGI_PCI_P2PDMA depends on CONFIG_64BIT which means there is 4 bytes
+ * in struct scatterlist (assuming also CONFIG_NEED_SG_DMA_LENGTH is set).
+ * Use this padding for DMA flags bits to indicate when a specific
+ * dma address is a bus address.
+ */
+#ifdef CONFIG_PCI_P2PDMA
+
+#define SG_DMA_BUS_ADDRESS (1 << 0)
+
+/**
+ * sg_dma_is_bus address - Return whether a given segment was marked
+ *			   as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Returns true if sg_dma_mark_bus_address() has been called on
+ *   this segment.
+ **/
+static inline bool sg_is_dma_bus_address(struct scatterlist *sg)
+{
+	return sg->dma_flags & SG_DMA_BUS_ADDRESS;
+}
+
+/**
+ * sg_dma_mark_bus address - Mark the scatterlist entry as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Marks the passed in sg entry to indicate that the dma_address is
+ *   a bus address and doesn't need to be unmapped. This should only be
+ *   used by dma_map_sg() implementations to mark bus addresses
+ *   so they can be properly cleaned up in dma_unmap_sg().
+ **/
+static inline void sg_dma_mark_bus_address(struct scatterlist *sg)
+{
+	sg->dma_flags |= SG_DMA_BUS_ADDRESS;
+}
+
+/**
+ * sg_unmark_bus_address - Unmark the scatterlist entry as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Clears the bus address mark.
+ **/
+static inline void sg_dma_unmark_bus_address(struct scatterlist *sg)
+{
+	sg->dma_flags &= ~SG_DMA_BUS_ADDRESS;
+}
+
+#else
+
+static inline bool sg_is_dma_bus_address(struct scatterlist *sg)
+{
+	return false;
+}
+static inline void sg_dma_mark_bus_address(struct scatterlist *sg)
+{
+}
+static inline void sg_dma_unmark_bus_address(struct scatterlist *sg)
+{
+}
+
+#endif
+
 /**
  * sg_phys - Return physical address of an sg entry
  * @sg:	     SG entry
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 7ed35dd3de6e..35bc4e281c21 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -60,7 +60,6 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #ifdef CONFIG_SWIOTLB
-extern enum swiotlb_force swiotlb_force;
 
 /**
  * struct io_tlb_mem - IO TLB Memory Pool Descriptor
@@ -80,15 +79,14 @@ extern enum swiotlb_force swiotlb_force;
  * @used:	The number of used IO TLB block.
  * @list:	The free list describing the number of free entries available
  *		from each index.
- * @index:	The index to start searching in the next round.
  * @orig_addr:	The original address corresponding to a mapped entry.
  * @alloc_size:	Size of the allocated buffer.
- * @lock:	The lock to protect the above data structures in the map and
- *		unmap calls.
  * @debugfs:	The dentry to debugfs.
  * @late_alloc:	%true if allocated using the page allocator
  * @force_bounce: %true if swiotlb bouncing is forced
  * @for_alloc:  %true if the pool is used for memory allocation
+ * @nareas:  The area number in the pool.
+ * @area_nslabs: The slot number in the area.
  */
 struct io_tlb_mem {
 	phys_addr_t start;
@@ -96,17 +94,14 @@ struct io_tlb_mem {
 	void *vaddr;
 	unsigned long nslabs;
 	unsigned long used;
-	unsigned int index;
-	spinlock_t lock;
 	struct dentry *debugfs;
 	bool late_alloc;
 	bool force_bounce;
 	bool for_alloc;
-	struct io_tlb_slot {
-		phys_addr_t orig_addr;
-		size_t alloc_size;
-		unsigned int list;
-	} *slots;
+	unsigned int nareas;
+	unsigned int area_nslabs;
+	struct io_tlb_area *areas;
+	struct io_tlb_slot *slots;
 };
 extern struct io_tlb_mem io_tlb_default_mem;
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 7c2f76f34f6f..975d6e9efbcb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4013,6 +4013,17 @@ static inline bool ib_uses_virt_dma(struct ib_device *dev)
 	return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device;
 }
 
+/*
+ * Check if a IB device's underlying DMA mapping supports P2PDMA transfers.
+ */
+static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev)
+{
+	if (ib_uses_virt_dma(dev))
+		return false;
+
+	return dma_pci_p2pdma_supported(dev->dma_device);
+}
+
 /**
  * ib_dma_mapping_error - check a DMA addr for error
  * @dev: The device for which the dma_addr was created
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 65082ecdd557..b6e41ee3d566 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -607,6 +607,7 @@ struct Scsi_Host {
 	short unsigned int sg_tablesize;
 	short unsigned int sg_prot_tablesize;
 	unsigned int max_sectors;
+	unsigned int opt_sectors;
 	unsigned int max_segment_size;
 	unsigned long dma_boundary;
 	unsigned long virt_boundary_mask;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8d0b68a17042..63859a101ed8 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -453,29 +453,60 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu_all();
 }
 
+/*
+ * Unmaps segments, except for ones marked as pci_p2pdma which do not
+ * require any further action as they contain a bus address.
+ */
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(sgl, sg, nents, i)
-		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
+	for_each_sg(sgl,  sg, nents, i) {
+		if (sg_is_dma_bus_address(sg))
+			sg_dma_unmark_bus_address(sg);
+		else
+			dma_direct_unmap_page(dev, sg->dma_address,
+					      sg_dma_len(sg), dir, attrs);
+	}
 }
 #endif
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	int i;
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
+	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
+		if (is_pci_p2pdma_page(sg_page(sg))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Any P2P mapping that traverses the PCI
+				 * host bridge must be mapped with CPU physical
+				 * address and not PCI bus addresses. This is
+				 * done with dma_direct_map_page() below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_unmap;
+			}
+		}
+
 		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR)
+		if (sg->dma_address == DMA_MAPPING_ERROR) {
+			ret = -EIO;
 			goto out_unmap;
+		}
 		sg_dma_len(sg) = sg->length;
 	}
 
@@ -483,7 +514,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 
 out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return -EIO;
+	return ret;
 }
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index a78c0ba70645..e38ffc5e6bdd 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -8,6 +8,7 @@
 #define _KERNEL_DMA_DIRECT_H
 
 #include <linux/dma-direct.h>
+#include <linux/memremap.h>
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
@@ -87,10 +88,15 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (is_swiotlb_force_bounce(dev))
+	if (is_swiotlb_force_bounce(dev)) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		return swiotlb_map(dev, phys, size, dir, attrs);
+	}
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))
 			return swiotlb_map(dev, phys, size, dir, attrs);
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index db7244291b74..49cbf3e33de7 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -197,7 +197,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 	if (ents > 0)
 		debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
 	else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
-			      ents != -EIO))
+			      ents != -EIO && ents != -EREMOTEIO))
 		return -EIO;
 
 	return ents;
@@ -249,12 +249,15 @@ EXPORT_SYMBOL(dma_map_sg_attrs);
  * Returns 0 on success or a negative error code on error. The following
  * error codes are supported with the given meaning:
  *
- *   -EINVAL	An invalid argument, unaligned access or other error
- *		in usage. Will not succeed if retried.
- *   -ENOMEM	Insufficient resources (like memory or IOVA space) to
- *		complete the mapping. Should succeed if retried later.
- *   -EIO	Legacy error code with an unknown meaning. eg. this is
- *		returned if a lower level call returned DMA_MAPPING_ERROR.
+ *   -EINVAL		An invalid argument, unaligned access or other error
+ *			in usage. Will not succeed if retried.
+ *   -ENOMEM		Insufficient resources (like memory or IOVA space) to
+ *			complete the mapping. Should succeed if retried later.
+ *   -EIO		Legacy error code with an unknown meaning. eg. this is
+ *			returned if a lower level call returned
+ *			DMA_MAPPING_ERROR.
+ *   -EREMOTEIO		The DMA device cannot access P2PDMA memory specified
+ *			in the sg_table. This will not succeed if retried.
  */
 int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
 		    enum dma_data_direction dir, unsigned long attrs)
@@ -720,6 +723,24 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
+bool dma_pci_p2pdma_supported(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	/* if ops is not set, dma direct will be used which supports P2PDMA */
+	if (!ops)
+		return true;
+
+	/*
+	 * Note: dma_ops_bypass is not checked here because P2PDMA should
+	 * not be used with dma mapping ops that do not have support even
+	 * if the specific device is bypassing them.
+	 */
+
+	return ops->flags & DMA_F_PCI_P2PDMA_SUPPORTED;
+}
+EXPORT_SYMBOL_GPL(dma_pci_p2pdma_supported);
+
 #ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
 void arch_dma_set_mask(struct device *dev, u64 mask);
 #else
@@ -773,6 +794,18 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+size_t dma_opt_mapping_size(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	size_t size = SIZE_MAX;
+
+	if (ops && ops->opt_mapping_size)
+		size = ops->opt_mapping_size();
+
+	return min(dma_max_mapping_size(dev), size);
+}
+EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
+
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index cb50f8d38360..c5a9190b218f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -62,6 +62,12 @@
 
 #define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 
+struct io_tlb_slot {
+	phys_addr_t orig_addr;
+	size_t alloc_size;
+	unsigned int list;
+};
+
 static bool swiotlb_force_bounce;
 static bool swiotlb_force_disable;
 
@@ -70,6 +76,62 @@ struct io_tlb_mem io_tlb_default_mem;
 phys_addr_t swiotlb_unencrypted_base;
 
 static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
+static unsigned long default_nareas;
+
+/**
+ * struct io_tlb_area - IO TLB memory area descriptor
+ *
+ * This is a single area with a single lock.
+ *
+ * @used:	The number of used IO TLB block.
+ * @index:	The slot index to start searching in this area for next round.
+ * @lock:	The lock to protect the above data structures in the map and
+ *		unmap calls.
+ */
+struct io_tlb_area {
+	unsigned long used;
+	unsigned int index;
+	spinlock_t lock;
+};
+
+/*
+ * Round up number of slabs to the next power of 2. The last area is going
+ * be smaller than the rest if default_nslabs is not power of two.
+ * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE,
+ * otherwise a segment may span two or more areas. It conflicts with free
+ * contiguous slots tracking: free slots are treated contiguous no matter
+ * whether they cross an area boundary.
+ *
+ * Return true if default_nslabs is rounded up.
+ */
+static bool round_up_default_nslabs(void)
+{
+	if (!default_nareas)
+		return false;
+
+	if (default_nslabs < IO_TLB_SEGSIZE * default_nareas)
+		default_nslabs = IO_TLB_SEGSIZE * default_nareas;
+	else if (is_power_of_2(default_nslabs))
+		return false;
+	default_nslabs = roundup_pow_of_two(default_nslabs);
+	return true;
+}
+
+static void swiotlb_adjust_nareas(unsigned int nareas)
+{
+	/* use a single area when non is specified */
+	if (!nareas)
+		nareas = 1;
+	else if (!is_power_of_2(nareas))
+		nareas = roundup_pow_of_two(nareas);
+
+	default_nareas = nareas;
+
+	pr_info("area num %d.\n", nareas);
+	if (round_up_default_nslabs())
+		pr_info("SWIOTLB bounce buffer size roundup to %luMB",
+			(default_nslabs << IO_TLB_SHIFT) >> 20);
+}
 
 static int __init
 setup_io_tlb_npages(char *str)
@@ -81,6 +143,10 @@ setup_io_tlb_npages(char *str)
 	}
 	if (*str == ',')
 		++str;
+	if (isdigit(*str))
+		swiotlb_adjust_nareas(simple_strtoul(str, &str, 0));
+	if (*str == ',')
+		++str;
 	if (!strcmp(str, "force"))
 		swiotlb_force_bounce = true;
 	else if (!strcmp(str, "noforce"))
@@ -112,8 +178,11 @@ void __init swiotlb_adjust_size(unsigned long size)
 	 */
 	if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT)
 		return;
+
 	size = ALIGN(size, IO_TLB_SIZE);
 	default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	if (round_up_default_nslabs())
+		size = default_nslabs << IO_TLB_SHIFT;
 	pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
 }
 
@@ -192,7 +261,8 @@ void __init swiotlb_update_mem_attributes(void)
 }
 
 static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
-		unsigned long nslabs, unsigned int flags, bool late_alloc)
+		unsigned long nslabs, unsigned int flags,
+		bool late_alloc, unsigned int nareas)
 {
 	void *vaddr = phys_to_virt(start);
 	unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
@@ -200,12 +270,18 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	mem->nslabs = nslabs;
 	mem->start = start;
 	mem->end = mem->start + bytes;
-	mem->index = 0;
 	mem->late_alloc = late_alloc;
+	mem->nareas = nareas;
+	mem->area_nslabs = nslabs / mem->nareas;
 
 	mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
 
-	spin_lock_init(&mem->lock);
+	for (i = 0; i < mem->nareas; i++) {
+		spin_lock_init(&mem->areas[i].lock);
+		mem->areas[i].index = 0;
+		mem->areas[i].used = 0;
+	}
+
 	for (i = 0; i < mem->nslabs; i++) {
 		mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
@@ -232,7 +308,7 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		int (*remap)(void *tlb, unsigned long nslabs))
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	unsigned long nslabs = default_nslabs;
+	unsigned long nslabs;
 	size_t alloc_size;
 	size_t bytes;
 	void *tlb;
@@ -243,6 +319,17 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		return;
 
 	/*
+	 * default_nslabs maybe changed when adjust area number.
+	 * So allocate bounce buffer after adjusting area number.
+	 */
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
+	nslabs = default_nslabs;
+	if (nslabs < IO_TLB_MIN_SLABS)
+		panic("%s: nslabs = %lu too small\n", __func__, nslabs);
+
+	/*
 	 * By default allocate the bounce buffer memory from low memory, but
 	 * allow to pick a location everywhere for hypervisors with guest
 	 * memory encryption.
@@ -254,7 +341,8 @@ retry:
 	else
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb) {
-		pr_warn("%s: failed to allocate tlb structure\n", __func__);
+		pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
+			__func__, bytes);
 		return;
 	}
 
@@ -274,7 +362,13 @@ retry:
 		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
 		      __func__, alloc_size, PAGE_SIZE);
 
-	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false);
+	mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
+		default_nareas), SMP_CACHE_BYTES);
+	if (!mem->areas)
+		panic("%s: Failed to allocate mem->areas.\n", __func__);
+
+	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
+				default_nareas);
 
 	if (flags & SWIOTLB_VERBOSE)
 		swiotlb_print_info();
@@ -282,7 +376,7 @@ retry:
 
 void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 {
-	return swiotlb_init_remap(addressing_limit, flags, NULL);
+	swiotlb_init_remap(addressing_limit, flags, NULL);
 }
 
 /*
@@ -296,7 +390,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned char *vstart = NULL;
-	unsigned int order;
+	unsigned int order, area_order;
 	bool retried = false;
 	int rc = 0;
 
@@ -337,19 +431,34 @@ retry:
 			(PAGE_SIZE << order) >> 20);
 	}
 
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
+	area_order = get_order(array_size(sizeof(*mem->areas),
+		default_nareas));
+	mem->areas = (struct io_tlb_area *)
+		__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
+	if (!mem->areas)
+		goto error_area;
+
 	mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 		get_order(array_size(sizeof(*mem->slots), nslabs)));
-	if (!mem->slots) {
-		free_pages((unsigned long)vstart, order);
-		return -ENOMEM;
-	}
+	if (!mem->slots)
+		goto error_slots;
 
 	set_memory_decrypted((unsigned long)vstart,
 			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
-	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true);
+	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
+				default_nareas);
 
 	swiotlb_print_info();
 	return 0;
+
+error_slots:
+	free_pages((unsigned long)mem->areas, area_order);
+error_area:
+	free_pages((unsigned long)vstart, order);
+	return -ENOMEM;
 }
 
 void __init swiotlb_exit(void)
@@ -357,6 +466,7 @@ void __init swiotlb_exit(void)
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long tbl_vaddr;
 	size_t tbl_size, slots_size;
+	unsigned int area_order;
 
 	if (swiotlb_force_bounce)
 		return;
@@ -371,9 +481,14 @@ void __init swiotlb_exit(void)
 
 	set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
 	if (mem->late_alloc) {
+		area_order = get_order(array_size(sizeof(*mem->areas),
+			mem->nareas));
+		free_pages((unsigned long)mem->areas, area_order);
 		free_pages(tbl_vaddr, get_order(tbl_size));
 		free_pages((unsigned long)mem->slots, get_order(slots_size));
 	} else {
+		memblock_free_late(__pa(mem->areas),
+			array_size(sizeof(*mem->areas), mem->nareas));
 		memblock_free_late(mem->start, tbl_size);
 		memblock_free_late(__pa(mem->slots), slots_size);
 	}
@@ -476,9 +591,9 @@ static inline unsigned long get_max_slots(unsigned long boundary_mask)
 	return nr_slots(boundary_mask + 1);
 }
 
-static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
+static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index)
 {
-	if (index >= mem->nslabs)
+	if (index >= mem->area_nslabs)
 		return 0;
 	return index;
 }
@@ -487,10 +602,12 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
  * Find a suitable number of IO TLB entries size that will fit this request and
  * allocate a buffer from that IO TLB pool.
  */
-static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
-			      size_t alloc_size, unsigned int alloc_align_mask)
+static int swiotlb_do_find_slots(struct device *dev, int area_index,
+		phys_addr_t orig_addr, size_t alloc_size,
+		unsigned int alloc_align_mask)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+	struct io_tlb_area *area = mem->areas + area_index;
 	unsigned long boundary_mask = dma_get_seg_boundary(dev);
 	dma_addr_t tbl_dma_addr =
 		phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
@@ -501,8 +618,11 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	unsigned int index, wrap, count = 0, i;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
 	unsigned long flags;
+	unsigned int slot_base;
+	unsigned int slot_index;
 
 	BUG_ON(!nslots);
+	BUG_ON(area_index >= mem->nareas);
 
 	/*
 	 * For mappings with an alignment requirement don't bother looping to
@@ -514,16 +634,20 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
 	stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1);
 
-	spin_lock_irqsave(&mem->lock, flags);
-	if (unlikely(nslots > mem->nslabs - mem->used))
+	spin_lock_irqsave(&area->lock, flags);
+	if (unlikely(nslots > mem->area_nslabs - area->used))
 		goto not_found;
 
-	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
+	slot_base = area_index * mem->area_nslabs;
+	index = wrap = wrap_area_index(mem, ALIGN(area->index, stride));
+
 	do {
+		slot_index = slot_base + index;
+
 		if (orig_addr &&
-		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
-			    (orig_addr & iotlb_align_mask)) {
-			index = wrap_index(mem, index + 1);
+		    (slot_addr(tbl_dma_addr, slot_index) &
+		     iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
+			index = wrap_area_index(mem, index + 1);
 			continue;
 		}
 
@@ -532,26 +656,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 		 * contiguous buffers, we allocate the buffers from that slot
 		 * and mark the entries as '0' indicating unavailable.
 		 */
-		if (!iommu_is_span_boundary(index, nslots,
+		if (!iommu_is_span_boundary(slot_index, nslots,
 					    nr_slots(tbl_dma_addr),
 					    max_slots)) {
-			if (mem->slots[index].list >= nslots)
+			if (mem->slots[slot_index].list >= nslots)
 				goto found;
 		}
-		index = wrap_index(mem, index + stride);
+		index = wrap_area_index(mem, index + stride);
 	} while (index != wrap);
 
 not_found:
-	spin_unlock_irqrestore(&mem->lock, flags);
+	spin_unlock_irqrestore(&area->lock, flags);
 	return -1;
 
 found:
-	for (i = index; i < index + nslots; i++) {
+	for (i = slot_index; i < slot_index + nslots; i++) {
 		mem->slots[i].list = 0;
-		mem->slots[i].alloc_size =
-			alloc_size - (offset + ((i - index) << IO_TLB_SHIFT));
+		mem->slots[i].alloc_size = alloc_size - (offset +
+				((i - slot_index) << IO_TLB_SHIFT));
 	}
-	for (i = index - 1;
+	for (i = slot_index - 1;
 	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
 	     mem->slots[i].list; i--)
 		mem->slots[i].list = ++count;
@@ -559,14 +683,42 @@ found:
 	/*
 	 * Update the indices to avoid searching in the next round.
 	 */
-	if (index + nslots < mem->nslabs)
-		mem->index = index + nslots;
+	if (index + nslots < mem->area_nslabs)
+		area->index = index + nslots;
 	else
-		mem->index = 0;
-	mem->used += nslots;
+		area->index = 0;
+	area->used += nslots;
+	spin_unlock_irqrestore(&area->lock, flags);
+	return slot_index;
+}
 
-	spin_unlock_irqrestore(&mem->lock, flags);
-	return index;
+static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
+		size_t alloc_size, unsigned int alloc_align_mask)
+{
+	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+	int start = raw_smp_processor_id() & (mem->nareas - 1);
+	int i = start, index;
+
+	do {
+		index = swiotlb_do_find_slots(dev, i, orig_addr, alloc_size,
+					      alloc_align_mask);
+		if (index >= 0)
+			return index;
+		if (++i >= mem->nareas)
+			i = 0;
+	} while (i != start);
+
+	return -1;
+}
+
+static unsigned long mem_used(struct io_tlb_mem *mem)
+{
+	int i;
+	unsigned long used = 0;
+
+	for (i = 0; i < mem->nareas; i++)
+		used += mem->areas[i].used;
+	return used;
 }
 
 phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
@@ -580,7 +732,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	int index;
 	phys_addr_t tlb_addr;
 
-	if (!mem)
+	if (!mem || !mem->nslabs)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
 	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
@@ -598,7 +750,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		if (!(attrs & DMA_ATTR_NO_WARN))
 			dev_warn_ratelimited(dev,
 	"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-				 alloc_size, mem->nslabs, mem->used);
+				 alloc_size, mem->nslabs, mem_used(mem));
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
@@ -628,6 +780,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
 	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
 	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	int aindex = index / mem->area_nslabs;
+	struct io_tlb_area *area = &mem->areas[aindex];
 	int count, i;
 
 	/*
@@ -636,7 +790,9 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 	 * While returning the entries to the free list, we merge the entries
 	 * with slots below and above the pool being returned.
 	 */
-	spin_lock_irqsave(&mem->lock, flags);
+	BUG_ON(aindex >= mem->nareas);
+
+	spin_lock_irqsave(&area->lock, flags);
 	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
 		count = mem->slots[index + nslots].list;
 	else
@@ -660,8 +816,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list;
 	     i--)
 		mem->slots[i].list = ++count;
-	mem->used -= nslots;
-	spin_unlock_irqrestore(&mem->lock, flags);
+	area->used -= nslots;
+	spin_unlock_irqrestore(&area->lock, flags);
 }
 
 /*
@@ -756,6 +912,13 @@ bool is_swiotlb_active(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(is_swiotlb_active);
 
+static int io_tlb_used_get(void *data, u64 *val)
+{
+	*val = mem_used(&io_tlb_default_mem);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n");
+
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
@@ -764,7 +927,8 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 		return;
 
 	debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
-	debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used);
+	debugfs_create_file("io_tlb_used", 0400, mem->debugfs, NULL,
+			&fops_io_tlb_used);
 }
 
 static int __init __maybe_unused swiotlb_create_default_debugfs(void)
@@ -815,6 +979,9 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 	struct io_tlb_mem *mem = rmem->priv;
 	unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;
 
+	/* Set Per-device io tlb area to one */
+	unsigned int nareas = 1;
+
 	/*
 	 * Since multiple devices can share the same pool, the private data,
 	 * io_tlb_mem struct, will be initialized by the first device attached
@@ -831,10 +998,18 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 			return -ENOMEM;
 		}
 
+		mem->areas = kcalloc(nareas, sizeof(*mem->areas),
+				GFP_KERNEL);
+		if (!mem->areas) {
+			kfree(mem->slots);
+			kfree(mem);
+			return -ENOMEM;
+		}
+
 		set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
 				     rmem->size >> PAGE_SHIFT);
 		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
-				false);
+					false, nareas);
 		mem->for_alloc = true;
 
 		rmem->priv = mem;